diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-11 01:58:42 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-11 01:58:42 +0200 |
commit | 9967468c0a109644e4a1f5b39b39bf86fe7507a7 (patch) | |
tree | 72b7764c6dd6d74ede25688545a2e0c29dde3a2b /include | |
parent | Merge tag 'devprop-4.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git... (diff) | |
parent | kernel/exit.c: avoid undefined behaviour when calling wait4() (diff) | |
download | linux-9967468c0a109644e4a1f5b39b39bf86fe7507a7.tar.xz linux-9967468c0a109644e4a1f5b39b39bf86fe7507a7.zip |
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
- most of the rest of MM
- KASAN updates
- lib/ updates
- checkpatch updates
- some binfmt_elf changes
- various misc bits
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (115 commits)
kernel/exit.c: avoid undefined behaviour when calling wait4()
kernel/signal.c: avoid undefined behaviour in kill_something_info
binfmt_elf: safely increment argv pointers
s390: reduce ELF_ET_DYN_BASE
powerpc: move ELF_ET_DYN_BASE to 4GB / 4MB
arm64: move ELF_ET_DYN_BASE to 4GB / 4MB
arm: move ELF_ET_DYN_BASE to 4MB
binfmt_elf: use ELF_ET_DYN_BASE only for PIE
fs, epoll: short circuit fetching events if thread has been killed
checkpatch: improve multi-line alignment test
checkpatch: improve macro reuse test
checkpatch: change format of --color argument to --color[=WHEN]
checkpatch: silence perl 5.26.0 unescaped left brace warnings
checkpatch: improve tests for multiple line function definitions
checkpatch: remove false warning for commit reference
checkpatch: fix stepping through statements with $stat and ctx_statement_block
checkpatch: [HLP]LIST_HEAD is also declaration
checkpatch: warn when a MAINTAINERS entry isn't [A-Z]:\t
checkpatch: improve the unnecessary OOM message test
lib/bsearch.c: micro-optimize pivot position calculation
...
Diffstat (limited to 'include')
-rw-r--r-- | include/asm-generic/bug.h | 1 | ||||
-rw-r--r-- | include/linux/backing-dev.h | 15 | ||||
-rw-r--r-- | include/linux/bitmap.h | 33 | ||||
-rw-r--r-- | include/linux/bug.h | 72 | ||||
-rw-r--r-- | include/linux/build_bug.h | 84 | ||||
-rw-r--r-- | include/linux/dax.h | 5 | ||||
-rw-r--r-- | include/linux/extable.h | 5 | ||||
-rw-r--r-- | include/linux/fs.h | 6 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 45 | ||||
-rw-r--r-- | include/linux/hugetlb.h | 39 | ||||
-rw-r--r-- | include/linux/initrd.h | 3 | ||||
-rw-r--r-- | include/linux/khugepaged.h | 3 | ||||
-rw-r--r-- | include/linux/list_lru.h | 1 | ||||
-rw-r--r-- | include/linux/migrate.h | 16 | ||||
-rw-r--r-- | include/linux/mmzone.h | 8 | ||||
-rw-r--r-- | include/linux/page_ref.h | 1 | ||||
-rw-r--r-- | include/linux/sched/coredump.h | 5 | ||||
-rw-r--r-- | include/linux/swap.h | 6 | ||||
-rw-r--r-- | include/linux/swapops.h | 9 | ||||
-rw-r--r-- | include/trace/events/mmflags.h | 2 | ||||
-rw-r--r-- | include/trace/events/oom.h | 80 |
21 files changed, 302 insertions, 137 deletions
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index d6f4aed479a1..87191357d303 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -97,6 +97,7 @@ extern void warn_slowpath_null(const char *file, const int line); /* used internally by panic.c */ struct warn_args; +struct pt_regs; void __warn(const char *file, int line, void *caller, unsigned taint, struct pt_regs *regs, struct warn_args *args); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ace73f96eb1e..334165c911f0 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -104,22 +104,9 @@ static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __wb_stat_sum(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - return percpu_counter_sum_positive(&wb->stat[item]); -} - static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { - s64 sum; - unsigned long flags; - - local_irq_save(flags); - sum = __wb_stat_sum(wb, item); - local_irq_restore(flags); - - return sum; + return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3b77588a9360..5797ca6fdfe2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1, extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); - -extern void bitmap_set(unsigned long *map, unsigned int start, int len); -extern void bitmap_clear(unsigned long *map, unsigned int start, int len); +extern void __bitmap_set(unsigned long *map, unsigned int start, int len); +extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, @@ -267,10 +266,8 @@ static inline int bitmap_equal(const unsigned long *src1, { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); -#ifdef CONFIG_S390 - if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) return !memcmp(src1, src2, nbits / 8); -#endif return __bitmap_equal(src1, src2, nbits); } @@ -315,6 +312,30 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int return __bitmap_weight(src, nbits); } +static __always_inline void bitmap_set(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __set_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0xff, nbits / 8); + else + __bitmap_set(map, start, nbits); +} + +static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __clear_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0, nbits / 8); + else + __bitmap_clear(map, start, nbits); +} + static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, int nbits) { diff --git a/include/linux/bug.h b/include/linux/bug.h index 687b557fc5eb..5d5554c874fd 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -3,6 +3,7 @@ #include <asm/bug.h> #include <linux/compiler.h> +#include <linux/build_bug.h> enum bug_trap_type { BUG_TRAP_TYPE_NONE = 0, @@ -13,80 +14,9 @@ enum bug_trap_type { struct pt_regs; #ifdef __CHECKER__ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_ZERO(e) (0) -#define BUILD_BUG_ON_NULL(e) ((void*)0) -#define BUILD_BUG_ON_INVALID(e) (0) -#define BUILD_BUG_ON_MSG(cond, msg) (0) -#define BUILD_BUG_ON(condition) (0) -#define BUILD_BUG() (0) #define MAYBE_BUILD_BUG_ON(cond) (0) #else /* __CHECKER__ */ -/* Force a compilation error if a constant expression is not a power of 2 */ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON(((n) & ((n) - 1)) != 0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) - -/* Force a compilation error if condition is true, but also produce a - result (of value 0 and type size_t), so the expression can be used - e.g. in a structure initializer (or where-ever else comma expressions - aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) -#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) - -/* - * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the - * expression but avoids the generation of any code, even if that expression - * has side-effects. - */ -#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) - -/** - * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied - * error message. - * @condition: the condition which the compiler should know is false. - * - * See BUILD_BUG_ON for description. - */ -#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) - -/** - * BUILD_BUG_ON - break compile if a condition is true. - * @condition: the condition which the compiler should know is false. - * - * If you have some code which relies on certain constants being equal, or - * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to - * detect if someone changes it. - * - * The implementation uses gcc's reluctance to create a negative array, but gcc - * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to - * inline functions). Luckily, in 4.3 they added the "error" function - * attribute just for this type of case. Thus, we use a negative sized array - * (should always create an error on gcc versions older than 4.4) and then call - * an undefined function with the error attribute (should always create an - * error on gcc 4.3 and later). If for some reason, neither creates a - * compile-time error, we'll still have a link-time error, which is harder to - * track down. - */ -#ifndef __OPTIMIZE__ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#else -#define BUILD_BUG_ON(condition) \ - BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) -#endif - -/** - * BUILD_BUG - break compile if used. - * - * If you have some code that you expect the compiler to eliminate at - * build time, you should use BUILD_BUG to detect if it is - * unexpectedly used. - */ -#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") - #define MAYBE_BUILD_BUG_ON(cond) \ do { \ if (__builtin_constant_p((cond))) \ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h new file mode 100644 index 000000000000..b7d22d60008a --- /dev/null +++ b/include/linux/build_bug.h @@ -0,0 +1,84 @@ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#include <linux/compiler.h> + +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void *)0) +#define BUILD_BUG_ON_INVALID(e) (0) +#define BUILD_BUG_ON_MSG(cond, msg) (0) +#define BUILD_BUG_ON(condition) (0) +#define BUILD_BUG() (0) +#else /* __CHECKER__ */ + +/* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + +/* + * Force a compilation error if condition is true, but also produce a + * result (of value 0 and type size_t), so the expression can be used + * e.g. in a structure initializer (or where-ever else comma expressions + * aren't permitted). + */ +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); })) + +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + +/** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** + * BUILD_BUG_ON - break compile if a condition is true. + * @condition: the condition which the compiler should know is false. + * + * If you have some code which relies on certain constants being equal, or + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * detect if someone changes it. + * + * The implementation uses gcc's reluctance to create a negative array, but gcc + * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to + * inline functions). Luckily, in 4.3 they added the "error" function + * attribute just for this type of case. Thus, we use a negative sized array + * (should always create an error on gcc versions older than 4.4) and then call + * an undefined function with the error attribute (should always create an + * error on gcc 4.3 and later). If for some reason, neither creates a + * compile-time error, we'll still have a link-time error, which is harder to + * track down. + */ +#ifndef __OPTIMIZE__ +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +#else +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) +#endif + +/** + * BUILD_BUG - break compile if used. + * + * If you have some code that you expect the compiler to eliminate at + * build time, you should use BUILD_BUG to detect if it is + * unexpectedly used. + */ +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") + +#endif /* __CHECKER__ */ + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/dax.h b/include/linux/dax.h index 8f39db7439c3..794811875732 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -154,11 +154,6 @@ static inline unsigned int dax_radix_order(void *entry) #endif int dax_pfn_mkwrite(struct vm_fault *vmf); -static inline bool vma_is_dax(struct vm_area_struct *vma) -{ - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); -} - static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/extable.h b/include/linux/extable.h index 7effea4b257d..28addad0dda7 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -2,13 +2,14 @@ #define _LINUX_EXTABLE_H #include <linux/stddef.h> /* for NULL */ +#include <linux/types.h> struct module; struct exception_table_entry; const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, +search_extable(const struct exception_table_entry *base, + const size_t num, unsigned long value); void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0cfa47125d52..78e1dbbe4cfd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -18,6 +18,7 @@ #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> @@ -3127,6 +3128,11 @@ static inline bool io_is_direct(struct file *filp) return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} + static inline int iocb_flags(struct file *file) { int res = 0; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index d3b3e8fcc717..ee696347f928 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -1,6 +1,10 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H +#include <linux/sched/coredump.h> + +#include <linux/fs.h> /* only for vma_is_dax() */ + extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, @@ -85,14 +89,32 @@ extern struct kobj_attribute shmem_enabled_attr; extern bool is_vma_temporary_stack(struct vm_area_struct *vma); -#define transparent_hugepage_enabled(__vma) \ - ((transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG) || \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \ - ((__vma)->vm_flags & VM_HUGEPAGE))) && \ - !((__vma)->vm_flags & VM_NOHUGEPAGE) && \ - !is_vma_temporary_stack(__vma)) +extern unsigned long transparent_hugepage_flags; + +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_NOHUGEPAGE) + return false; + + if (is_vma_temporary_stack(vma)) + return false; + + if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) + return true; + + if (vma_is_dax(vma)) + return true; + + if (transparent_hugepage_flags & + (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) + return !!(vma->vm_flags & VM_HUGEPAGE); + + return false; +} + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) @@ -104,8 +126,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #define transparent_hugepage_debug_cow() 0 #endif /* CONFIG_DEBUG_VM */ -extern unsigned long transparent_hugepage_flags; - extern unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); @@ -224,7 +244,10 @@ void mm_put_huge_zero_page(struct mm_struct *mm); #define hpage_nr_pages(x) 1 -#define transparent_hugepage_enabled(__vma) 0 +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + return false; +} static inline void prep_transhuge_page(struct page *page) {} diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 46bfb702e7d6..8d9fe131a240 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -116,7 +116,6 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); @@ -192,10 +191,6 @@ static inline void hugetlb_show_meminfo(void) #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) #define huge_pte_offset(mm, address, sz) 0 -static inline int dequeue_hwpoisoned_huge_page(struct page *page) -{ - return 0; -} static inline bool isolate_huge_page(struct page *page, struct list_head *list) { @@ -354,6 +349,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); +struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); @@ -472,6 +469,7 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } +extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); static inline bool hugepage_migration_supported(struct hstate *h) @@ -528,6 +526,7 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr struct hstate {}; #define alloc_huge_page(v, a, r) NULL #define alloc_huge_page_node(h, nid) NULL +#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL #define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL @@ -550,15 +549,37 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } -#define hstate_index_to_shift(index) 0 -#define hstate_index(h) 0 + +static inline unsigned hstate_index_to_shift(unsigned index) +{ + return 0; +} + +static inline int hstate_index(struct hstate *h) +{ + return 0; +} static inline pgoff_t basepage_index(struct page *page) { return page->index; } -#define dissolve_free_huge_pages(s, e) 0 -#define hugepage_migration_supported(h) false + +static inline int dissolve_free_huge_page(struct page *page) +{ + return 0; +} + +static inline int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn) +{ + return 0; +} + +static inline bool hugepage_migration_supported(struct hstate *h) +{ + return false; +} static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 55289d261b4f..bc67b767f9ce 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -10,6 +10,9 @@ extern int rd_prompt; /* starting block # of image */ extern int rd_image_start; +/* size of a single RAM disk */ +extern unsigned long rd_size; + /* 1 if it is not an error if initrd_start < memory_start */ extern int initrd_below_start_ok; diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 5d9a400af509..f0d7335336cd 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -48,7 +48,8 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE)) + !(vm_flags & VM_NOHUGEPAGE) && + !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) if (__khugepaged_enter(vma->vm_mm)) return -ENOMEM; return 0; diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index cb0ba9f2a9a2..fa7fd03cb5f9 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -44,6 +44,7 @@ struct list_lru_node { /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg *memcg_lrus; #endif + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 48e24844b3c5..4634da521238 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -4,6 +4,7 @@ #include <linux/mm.h> #include <linux/mempolicy.h> #include <linux/migrate_mode.h> +#include <linux/hugetlb.h> typedef struct page *new_page_t(struct page *page, unsigned long private, int **reason); @@ -30,6 +31,21 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern char *migrate_reason_names[MR_TYPES]; +static inline struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + + if (PageHuge(page)) + return alloc_huge_page_nodemask(page_hstate(compound_head(page)), + preferred_nid, nodemask); + + if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask); +} + #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7e8f100cb56d..fc14b8b3f6ce 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -603,12 +603,9 @@ extern struct page *mem_map; #endif /* - * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM - * (mostly NUMA machines?) to denote a higher-level memory zone than the - * zone denotes. - * * On NUMA machines, each NUMA node would have a pg_data_t to describe - * it's memory layout. + * it's memory layout. On UMA machines there is a single pglist_data which + * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. @@ -1058,6 +1055,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) static inline unsigned long early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #endif diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 610e13271918..1fd71733aa68 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -174,6 +174,7 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); + smp_mb(); atomic_set(&page->_refcount, count); if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) __page_ref_unfreeze(page, count); diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 69eedcef8f03..98ae0d05aa32 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -68,7 +68,10 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK) #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 5ab1c98c7d27..d83d28e53e62 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -277,6 +277,7 @@ extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); +extern void lru_add_drain_all_cpuslocked(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); extern void mark_page_lazyfree(struct page *page); @@ -331,7 +332,7 @@ extern void kswapd_stop(int nid); #include <linux/blk_types.h> /* for bio_end_io_t */ /* linux/mm/page_io.c */ -extern int swap_readpage(struct page *); +extern int swap_readpage(struct page *page, bool do_poll); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, @@ -362,7 +363,8 @@ extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr); + struct vm_area_struct *vma, unsigned long addr, + bool do_poll); extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated); diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5c3a5f3e7eec..c5ff7b217ee6 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -196,15 +196,6 @@ static inline void num_poisoned_pages_dec(void) atomic_long_dec(&num_poisoned_pages); } -static inline void num_poisoned_pages_add(long num) -{ - atomic_long_add(num, &num_poisoned_pages); -} - -static inline void num_poisoned_pages_sub(long num) -{ - atomic_long_sub(num, &num_poisoned_pages); -} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 304ff94363b2..10e3663a75a6 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -257,7 +257,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \ COMPACTION_STATUS COMPACTION_PRIORITY -COMPACTION_FEEDBACK +/* COMPACTION_FEEDBACK are defines not enums. Not needed here. */ ZONE_TYPE LRU_NAMES diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h index 38baeb27221a..c3c19d47ae5e 100644 --- a/include/trace/events/oom.h +++ b/include/trace/events/oom.h @@ -70,6 +70,86 @@ TRACE_EVENT(reclaim_retry_zone, __entry->wmark_check) ); +TRACE_EVENT(mark_victim, + TP_PROTO(int pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __field(int, pid) + ), + + TP_fast_assign( + __entry->pid = pid; + ), + + TP_printk("pid=%d", __entry->pid) +); + +TRACE_EVENT(wake_reaper, + TP_PROTO(int pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __field(int, pid) + ), + + TP_fast_assign( + __entry->pid = pid; + ), + + TP_printk("pid=%d", __entry->pid) +); + +TRACE_EVENT(start_task_reaping, + TP_PROTO(int pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __field(int, pid) + ), + + TP_fast_assign( + __entry->pid = pid; + ), + + TP_printk("pid=%d", __entry->pid) +); + +TRACE_EVENT(finish_task_reaping, + TP_PROTO(int pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __field(int, pid) + ), + + TP_fast_assign( + __entry->pid = pid; + ), + + TP_printk("pid=%d", __entry->pid) +); + +TRACE_EVENT(skip_task_reaping, + TP_PROTO(int pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __field(int, pid) + ), + + TP_fast_assign( + __entry->pid = pid; + ), + + TP_printk("pid=%d", __entry->pid) +); + #ifdef CONFIG_COMPACTION TRACE_EVENT(compact_retry, |