diff options
Diffstat (limited to 'include')
-rw-r--r-- | include/asm-generic/pgtable.h | 3 | ||||
-rw-r--r-- | include/asm-generic/vmlinux.lds.h | 6 | ||||
-rw-r--r-- | include/linux/bitops.h | 36 | ||||
-rw-r--r-- | include/linux/bootmem.h | 9 | ||||
-rw-r--r-- | include/linux/compaction.h | 40 | ||||
-rw-r--r-- | include/linux/console.h | 6 | ||||
-rw-r--r-- | include/linux/cpu.h | 5 | ||||
-rw-r--r-- | include/linux/cred.h | 11 | ||||
-rw-r--r-- | include/linux/fsnotify_backend.h | 3 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 15 | ||||
-rw-r--r-- | include/linux/hugetlb.h | 8 | ||||
-rw-r--r-- | include/linux/jiffies.h | 4 | ||||
-rw-r--r-- | include/linux/kernel.h | 48 | ||||
-rw-r--r-- | include/linux/memblock.h | 1 | ||||
-rw-r--r-- | include/linux/memcontrol.h | 21 | ||||
-rw-r--r-- | include/linux/mm.h | 44 | ||||
-rw-r--r-- | include/linux/mm_types.h | 2 | ||||
-rw-r--r-- | include/linux/nmi.h | 31 | ||||
-rw-r--r-- | include/linux/oom.h | 46 | ||||
-rw-r--r-- | include/linux/page_ext.h | 8 | ||||
-rw-r--r-- | include/linux/page_owner.h | 2 | ||||
-rw-r--r-- | include/linux/pagemap.h | 14 | ||||
-rw-r--r-- | include/linux/sched.h | 22 | ||||
-rw-r--r-- | include/linux/seq_file.h | 4 | ||||
-rw-r--r-- | include/linux/swap.h | 11 | ||||
-rw-r--r-- | include/linux/writeback.h | 1 | ||||
-rw-r--r-- | include/trace/events/compaction.h | 2 |
27 files changed, 250 insertions, 153 deletions
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index d4458b6dbfb4..c4f8fd2fd384 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -800,6 +800,9 @@ static inline int pmd_clear_huge(pmd_t *pmd) #endif #endif +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); #endif /* !__ASSEMBLY__ */ #ifndef io_remap_pfn_range diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 24563970ff7b..3e42bcdd014b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -454,6 +454,12 @@ *(.spinlock.text) \ VMLINUX_SYMBOL(__lock_text_end) = .; +#define CPUIDLE_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__cpuidle_text_start) = .; \ + *(.cpuidle.text) \ + VMLINUX_SYMBOL(__cpuidle_text_end) = .; + #define KPROBES_TEXT \ ALIGN_FUNCTION(); \ VMLINUX_SYMBOL(__kprobes_text_start) = .; \ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 299e76b59fe9..a83c822c35c2 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -65,16 +65,6 @@ static inline int get_bitmask_order(unsigned int count) return order; /* We could be slightly more clever with -1 here... */ } -static inline int get_count_order(unsigned int count) -{ - int order; - - order = fls(count) - 1; - if (count & (count - 1)) - order++; - return order; -} - static __always_inline unsigned long hweight_long(unsigned long w) { return sizeof(w) == 4 ? hweight32(w) : hweight64(w); @@ -191,6 +181,32 @@ static inline unsigned fls_long(unsigned long l) return fls64(l); } +static inline int get_count_order(unsigned int count) +{ + int order; + + order = fls(count) - 1; + if (count & (count - 1)) + order++; + return order; +} + +/** + * get_count_order_long - get order after rounding @l up to power of 2 + * @l: parameter + * + * it is same as get_count_order() but with long type parameter + */ +static inline int get_count_order_long(unsigned long l) +{ + if (l == 0UL) + return -1; + else if (l & (l - 1UL)) + return (int)fls_long(l); + else + return (int)fls_long(l) - 1; +} + /** * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index f9be32691718..962164d36506 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -7,6 +7,7 @@ #include <linux/mmzone.h> #include <linux/mm_types.h> #include <asm/dma.h> +#include <asm/processor.h> /* * simple boot-time physical memory area allocator. @@ -119,6 +120,10 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) #endif +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_align(x, align) \ @@ -180,10 +185,6 @@ static inline void * __init memblock_virt_alloc_nopanic( NUMA_NO_NODE); } -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - static inline void * __init memblock_virt_alloc_low( phys_addr_t size, phys_addr_t align) { diff --git a/include/linux/compaction.h b/include/linux/compaction.h index d4e106b5dc27..0d8415820fc3 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -6,8 +6,10 @@ * Lower value means higher priority, analogically to reclaim priority. */ enum compact_priority { + COMPACT_PRIO_SYNC_FULL, + MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL, COMPACT_PRIO_SYNC_LIGHT, - MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, + MIN_COMPACT_COSTLY_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, COMPACT_PRIO_ASYNC, INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC @@ -49,14 +51,37 @@ enum compact_result { COMPACT_CONTENDED, /* - * direct compaction partially compacted a zone and there might be - * suitable pages + * direct compaction terminated after concluding that the allocation + * should now succeed */ - COMPACT_PARTIAL, + COMPACT_SUCCESS, }; struct alloc_context; /* in mm/internal.h */ +/* + * Number of free order-0 pages that should be available above given watermark + * to make sure compaction has reasonable chance of not running out of free + * pages that it needs to isolate as migration target during its work. + */ +static inline unsigned long compact_gap(unsigned int order) +{ + /* + * Although all the isolations for migration are temporary, compaction + * free scanner may have up to 1 << order pages on its list and then + * try to split an (order - 1) free page. At that point, a gap of + * 1 << order might not be enough, so it's safer to require twice that + * amount. Note that the number of pages on the list is also + * effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum + * that the migrate scanner can have isolated on migrate list, and free + * scanner is only invoked when the number of isolated free pages is + * lower than that. But it's not worth to complicate the formula here + * as a bigger gap for higher orders than strictly necessary can also + * improve chances of compaction success. + */ + return 2UL << order; +} + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -70,7 +95,6 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio); -extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, int classzone_idx); @@ -89,7 +113,7 @@ static inline bool compaction_made_progress(enum compact_result result) * that the compaction successfully isolated and migrated some * pageblocks. */ - if (result == COMPACT_PARTIAL) + if (result == COMPACT_SUCCESS) return true; return false; @@ -154,10 +178,6 @@ extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); #else -static inline void compact_pgdat(pg_data_t *pgdat, int order) -{ -} - static inline void reset_isolation_suitable(pg_data_t *pgdat) { } diff --git a/include/linux/console.h b/include/linux/console.h index d530c4627e54..3672809234a7 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -173,6 +173,12 @@ static inline void console_sysfs_notify(void) #endif extern bool console_suspend_enabled; +#ifdef CONFIG_OF +extern void console_set_by_of(void); +#else +static inline void console_set_by_of(void) {} +#endif + /* Suspend and resume console messages over PM events */ extern void suspend_console(void); extern void resume_console(void); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7572d9e9dced..b886dc17f2f3 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -231,6 +231,11 @@ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); +/* Attach to any functions which should be considered cpuidle. */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + +bool cpu_in_idle(unsigned long pc); + void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); diff --git a/include/linux/cred.h b/include/linux/cred.h index 257db64562e5..f0e70a1bb3ac 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -26,15 +26,10 @@ struct inode; /* * COW Supplementary groups list */ -#define NGROUPS_SMALL 32 -#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(kgid_t))) - struct group_info { atomic_t usage; int ngroups; - int nblocks; - kgid_t small_block[NGROUPS_SMALL]; - kgid_t *blocks[0]; + kgid_t gid[0]; }; /** @@ -88,10 +83,6 @@ extern void set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); extern bool may_setgroups(void); -/* access the groups "array" with this macro */ -#define GROUP_AT(gi, i) \ - ((gi)->blocks[(i) / NGROUPS_PER_BLOCK][(i) % NGROUPS_PER_BLOCK]) - /* * The security context of a task * diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7268ed076be8..79467b239fcf 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -135,7 +135,7 @@ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* needed to send notification to userspace */ - struct mutex notification_mutex; /* protect the notification_list */ + spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ @@ -177,7 +177,6 @@ struct fsnotify_group { struct fanotify_group_private_data { #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* allows a group to block waiting for a userspace response */ - spinlock_t access_lock; struct list_head access_list; wait_queue_head_t access_waitq; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 6f14de45b5ce..9b9f65d99873 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -87,6 +87,10 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); 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); + extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); @@ -152,8 +156,8 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return is_huge_zero_page(pmd_page(pmd)); } -struct page *get_huge_zero_page(void); -void put_huge_zero_page(void); +struct page *mm_get_huge_zero_page(struct mm_struct *mm); +void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) @@ -169,6 +173,9 @@ void put_huge_zero_page(void); static inline void prep_transhuge_page(struct page *page) {} #define transparent_hugepage_flags 0UL + +#define thp_get_unmapped_area NULL + static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { @@ -213,9 +220,9 @@ static inline bool is_huge_zero_page(struct page *page) return false; } -static inline void put_huge_zero_page(void) +static inline void mm_put_huge_zero_page(struct mm_struct *mm) { - BUILD_BUG(); + return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c26d4638f665..48c76d612d40 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -90,7 +90,7 @@ 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); -void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve); +void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, struct vm_area_struct *vma, @@ -450,8 +450,8 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } -extern void dissolve_free_huge_pages(unsigned long start_pfn, - unsigned long end_pfn); +extern int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn); static inline bool hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION @@ -518,7 +518,7 @@ static inline pgoff_t basepage_index(struct page *page) { return page->index; } -#define dissolve_free_huge_pages(s, e) do {} while (0) +#define dissolve_free_huge_pages(s, e) 0 #define hugepage_migration_supported(h) false static inline spinlock_t *huge_pte_lockptr(struct hstate *h, diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 5fdc55312334..589d14e970ad 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -150,15 +150,19 @@ static inline u64 get_jiffies_64(void) /* time_is_before_jiffies(a) return true if a is before jiffies */ #define time_is_before_jiffies(a) time_after(jiffies, a) +#define time_is_before_jiffies64(a) time_after64(get_jiffies_64(), a) /* time_is_after_jiffies(a) return true if a is after jiffies */ #define time_is_after_jiffies(a) time_before(jiffies, a) +#define time_is_after_jiffies64(a) time_before64(get_jiffies_64(), a) /* time_is_before_eq_jiffies(a) return true if a is before or equal to jiffies*/ #define time_is_before_eq_jiffies(a) time_after_eq(jiffies, a) +#define time_is_before_eq_jiffies64(a) time_after_eq64(get_jiffies_64(), a) /* time_is_after_eq_jiffies(a) return true if a is after or equal to jiffies*/ #define time_is_after_eq_jiffies(a) time_before_eq(jiffies, a) +#define time_is_after_eq_jiffies64(a) time_before_eq64(get_jiffies_64(), a) /* * Have the 32 bit jiffies value wrap 5 minutes after boot diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 74fd6f05bc5b..bc6ed52a39b9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -733,17 +733,25 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * strict type-checking.. See the * "unnecessary" pointer comparison. */ -#define min(x, y) ({ \ - typeof(x) _min1 = (x); \ - typeof(y) _min2 = (y); \ - (void) (&_min1 == &_min2); \ - _min1 < _min2 ? _min1 : _min2; }) - -#define max(x, y) ({ \ - typeof(x) _max1 = (x); \ - typeof(y) _max2 = (y); \ - (void) (&_max1 == &_max2); \ - _max1 > _max2 ? _max1 : _max2; }) +#define __min(t1, t2, min1, min2, x, y) ({ \ + t1 min1 = (x); \ + t2 min2 = (y); \ + (void) (&min1 == &min2); \ + min1 < min2 ? min1 : min2; }) +#define min(x, y) \ + __min(typeof(x), typeof(y), \ + __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ + x, y) + +#define __max(t1, t2, max1, max2, x, y) ({ \ + t1 max1 = (x); \ + t2 max2 = (y); \ + (void) (&max1 == &max2); \ + max1 > max2 ? max1 : max2; }) +#define max(x, y) \ + __max(typeof(x), typeof(y), \ + __UNIQUE_ID(max1_), __UNIQUE_ID(max2_), \ + x, y) #define min3(x, y, z) min((typeof(x))min(x, y), z) #define max3(x, y, z) max((typeof(x))max(x, y), z) @@ -775,15 +783,15 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * * Or not use min/max/clamp at all, of course. */ -#define min_t(type, x, y) ({ \ - type __min1 = (x); \ - type __min2 = (y); \ - __min1 < __min2 ? __min1: __min2; }) - -#define max_t(type, x, y) ({ \ - type __max1 = (x); \ - type __max2 = (y); \ - __max1 > __max2 ? __max1: __max2; }) +#define min_t(type, x, y) \ + __min(type, type, \ + __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ + x, y) + +#define max_t(type, x, y) \ + __max(type, type, \ + __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ + x, y) /** * clamp_t - return a value clamped to a given range using a given type diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2925da23505d..5b759c9acf97 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -328,6 +328,7 @@ phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t memblock_phys_mem_size(void); +phys_addr_t memblock_reserved_size(void); phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5d8ca6e02e39..61d20c17f3b7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -366,6 +366,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +int mem_cgroup_scan_tasks(struct mem_cgroup *, + int (*)(struct task_struct *, void *), void *); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { @@ -446,6 +448,8 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) void mem_cgroup_handle_over_high(void); +unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg); + void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); @@ -639,6 +643,12 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root, { } +static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, + int (*fn)(struct task_struct *, void *), void *arg) +{ + return 0; +} + static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; @@ -669,6 +679,11 @@ mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, return 0; } +static inline unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) +{ + return 0; +} + static inline void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { @@ -758,13 +773,13 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -void sock_update_memcg(struct sock *sk); -void sock_release_memcg(struct sock *sk); bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) +void mem_cgroup_sk_alloc(struct sock *sk); +void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) @@ -777,6 +792,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) } #else #define mem_cgroup_sockets_enabled 0 +static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; +static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index 5f14534f0c90..e9caec6a51e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -126,7 +126,7 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ -#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)addr, PAGE_SIZE) +#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) /* * Linux kernel virtual memory manager primitives. @@ -1048,28 +1048,16 @@ struct address_space *page_file_mapping(struct page *page) return page->mapping; } -/* - * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use ->private - */ -static inline pgoff_t page_index(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return page_private(page); - return page->index; -} - extern pgoff_t __page_file_index(struct page *page); /* - * Return the file index of the page. Regular pagecache pages use ->index - * whereas swapcache pages use swp_offset(->private) + * Return the pagecache index of the passed page. Regular pagecache pages + * use ->index whereas swapcache pages use swp_offset(->private) */ -static inline pgoff_t page_file_index(struct page *page) +static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); - return page->index; } @@ -1197,10 +1185,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether - * we walk over the current vma or not. A positive returned + * we walk over the current vma or not. Returning 0 * value means "do page table walk over the current vma," * and a negative one means "abort current page table walk - * right now." 0 means "skip the current vma." + * right now." 1 means "skip the current vma." * @mm: mm_struct representing the target process of page table walk * @vma: vma currently walked (NULL if walking outside vmas) * @private: private data for callbacks' usage @@ -1529,7 +1517,7 @@ static inline int pte_devmap(pte_t pte) } #endif -int vma_wants_writenotify(struct vm_area_struct *vma); +int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); @@ -1924,10 +1912,12 @@ extern void show_mem(unsigned int flags); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES +extern unsigned long arch_reserved_kernel_pages(void); +#endif -extern __printf(3, 4) -void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, - const char *fmt, ...); +extern __printf(2, 3) +void warn_alloc(gfp_t gfp_mask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); @@ -1977,8 +1967,14 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern int vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert); +extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, + struct vm_area_struct *expand); +static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) +{ + return __vma_adjust(vma, start, end, pgoff, insert, NULL); +} extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 903200f4ec41..4a8acedf4b7d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -515,9 +515,7 @@ struct mm_struct { #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif -#ifdef CONFIG_MMU struct work_struct async_put_work; -#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4630eeae18e0..a78c35cff1ae 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -35,21 +35,34 @@ static inline void hardlockup_detector_disable(void) {} * base function. Return whether such support was available, * to allow calling code to fall back to some other mechanism: */ -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static inline bool trigger_all_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(true); - + arch_trigger_cpumask_backtrace(cpu_online_mask, false); return true; } + static inline bool trigger_allbutself_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(false); + arch_trigger_cpumask_backtrace(cpu_online_mask, true); + return true; +} + +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + arch_trigger_cpumask_backtrace(mask, false); + return true; +} + +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + arch_trigger_cpumask_backtrace(cpumask_of(cpu), false); return true; } /* generic implementation */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)); bool nmi_cpu_backtrace(struct pt_regs *regs); @@ -62,6 +75,14 @@ static inline bool trigger_allbutself_cpu_backtrace(void) { return false; } +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + return false; +} +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + return false; +} #endif #ifdef CONFIG_LOCKUP_DETECTOR diff --git a/include/linux/oom.h b/include/linux/oom.h index 5bc0457ee3a8..b4e36e92bc87 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -34,23 +34,11 @@ struct oom_control { * for display purposes. */ const int order; -}; - -/* - * Types of limitations to the nodes from which allocations may occur - */ -enum oom_constraint { - CONSTRAINT_NONE, - CONSTRAINT_CPUSET, - CONSTRAINT_MEMORY_POLICY, - CONSTRAINT_MEMCG, -}; -enum oom_scan_t { - OOM_SCAN_OK, /* scan thread and find its badness */ - OOM_SCAN_CONTINUE, /* do not consider thread for oom kill */ - OOM_SCAN_ABORT, /* abort the iteration and return */ - OOM_SCAN_SELECT, /* always select this thread first */ + /* Used by oom implementation, do not set */ + unsigned long totalpages; + struct task_struct *chosen; + unsigned long chosen_points; }; extern struct mutex oom_lock; @@ -70,45 +58,27 @@ static inline bool oom_task_origin(const struct task_struct *p) return p->signal->oom_flag_origin; } -extern void mark_oom_victim(struct task_struct *tsk); - -#ifdef CONFIG_MMU -extern void wake_oom_reaper(struct task_struct *tsk); -#else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline bool tsk_is_oom_victim(struct task_struct * tsk) { + return tsk->signal->oom_mm; } -#endif extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); -extern void oom_kill_process(struct oom_control *oc, struct task_struct *p, - unsigned int points, unsigned long totalpages, - const char *message); - -extern void check_panic_on_oom(struct oom_control *oc, - enum oom_constraint constraint); - -extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, - struct task_struct *task); - extern bool out_of_memory(struct oom_control *oc); -extern void exit_oom_victim(struct task_struct *tsk); +extern void exit_oom_victim(void); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); -extern bool oom_killer_disabled; -extern bool oom_killer_disable(void); +extern bool oom_killer_disable(signed long timeout); extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -bool task_will_free_mem(struct task_struct *task); - /* sysctls */ extern int sysctl_oom_dump_tasks; extern int sysctl_oom_kill_allocating_task; diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 03f2a3e7d76d..9298c393ddaa 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -7,6 +7,8 @@ struct pglist_data; struct page_ext_operations { + size_t offset; + size_t size; bool (*need)(void); void (*init)(void); }; @@ -42,12 +44,6 @@ enum page_ext_flags { */ struct page_ext { unsigned long flags; -#ifdef CONFIG_PAGE_OWNER - unsigned int order; - gfp_t gfp_mask; - int last_migrate_reason; - depot_stack_handle_t handle; -#endif }; extern void pgdat_page_ext_init(struct pglist_data *pgdat); diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 30583ab0ffb1..2be728d156b5 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -14,6 +14,8 @@ extern void __split_page_owner(struct page *page, unsigned int order); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(struct page *page); +extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone); static inline void reset_page_owner(struct page *page, unsigned int order) { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 01e84436cddf..794dbcb91084 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -25,6 +25,8 @@ enum mapping_flags { AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = __GFP_BITS_SHIFT + 4, /* final truncate in progress */ + /* writeback related tags are not used */ + AS_NO_WRITEBACK_TAGS = __GFP_BITS_SHIFT + 5, }; static inline void mapping_set_error(struct address_space *mapping, int error) @@ -64,6 +66,16 @@ static inline int mapping_exiting(struct address_space *mapping) return test_bit(AS_EXITING, &mapping->flags); } +static inline void mapping_set_no_writeback_tags(struct address_space *mapping) +{ + set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); +} + +static inline int mapping_use_writeback_tags(struct address_space *mapping) +{ + return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; @@ -396,7 +408,7 @@ static inline loff_t page_offset(struct page *page) static inline loff_t page_file_offset(struct page *page) { - return ((loff_t)page_file_index(page)) << PAGE_SHIFT; + return ((loff_t)page_index(page)) << PAGE_SHIFT; } extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, diff --git a/include/linux/sched.h b/include/linux/sched.h index 7543a476178b..348f51b0ec92 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -524,8 +524,9 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_REAPED 21 /* mm has been already reaped */ -#define MMF_OOM_NOT_REAPABLE 22 /* mm couldn't be reaped */ +#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_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) @@ -673,7 +674,6 @@ struct signal_struct { atomic_t sigcnt; atomic_t live; int nr_threads; - atomic_t oom_victims; /* # of TIF_MEDIE threads in this thread group */ struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ @@ -806,6 +806,8 @@ struct signal_struct { short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ + struct mm_struct *oom_mm; /* recorded mm when the thread group got + * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations @@ -2876,6 +2878,20 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +static inline void mmdrop_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmdrop(mm); +} + +static inline void mmdrop_async(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) { + INIT_WORK(&mm->async_put_work, mmdrop_async_fn); + schedule_work(&mm->async_put_work); + } +} + static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index f3d45dd42695..e305b66a9fb9 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -117,9 +117,9 @@ __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); void seq_puts(struct seq_file *m, const char *s); -void seq_put_decimal_ull(struct seq_file *m, char delimiter, +void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num); -void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num); +void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num); void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, diff --git a/include/linux/swap.h b/include/linux/swap.h index e1d761463243..a56523cefb9b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -191,6 +191,11 @@ struct percpu_cluster { unsigned int next; /* Likely next allocation offset */ }; +struct swap_cluster_list { + struct swap_cluster_info head; + struct swap_cluster_info tail; +}; + /* * The in-memory structure used to track swap areas. */ @@ -203,8 +208,7 @@ struct swap_info_struct { unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ - struct swap_cluster_info free_cluster_head; /* free cluster list head */ - struct swap_cluster_info free_cluster_tail; /* free cluster list tail */ + struct swap_cluster_list free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ @@ -235,8 +239,7 @@ struct swap_info_struct { * first. */ struct work_struct discard_work; /* discard worker */ - struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */ - struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ + struct swap_cluster_list discard_clusters; /* discard clusters list */ }; /* linux/mm/workingset.c */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fc1e16c25a29..797100e10010 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -319,7 +319,6 @@ void laptop_mode_timer_fn(unsigned long data); #else static inline void laptop_sync_completion(void) { } #endif -void throttle_vm_writeout(gfp_t gfp_mask); bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c2ba402ab256..cbdb90b6b308 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -13,7 +13,7 @@ EM( COMPACT_SKIPPED, "skipped") \ EM( COMPACT_DEFERRED, "deferred") \ EM( COMPACT_CONTINUE, "continue") \ - EM( COMPACT_PARTIAL, "partial") \ + EM( COMPACT_SUCCESS, "success") \ EM( COMPACT_PARTIAL_SKIPPED, "partial_skipped") \ EM( COMPACT_COMPLETE, "complete") \ EM( COMPACT_NO_SUITABLE_PAGE, "no_suitable_page") \ |