diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-02-24 02:50:35 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-02-24 02:50:35 +0100 |
commit | 5ce1a70e2f00f0bce0cab57f798ca354b9496169 (patch) | |
tree | 6e80200536b7a3576fd71ff2c7135ffe87dc858e /include | |
parent | Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/pow... (diff) | |
parent | ksm: allocate roots when needed (diff) | |
download | linux-5ce1a70e2f00f0bce0cab57f798ca354b9496169.tar.xz linux-5ce1a70e2f00f0bce0cab57f798ca354b9496169.zip |
Merge branch 'akpm' (more incoming from Andrew)
Merge second patch-bomb from Andrew Morton:
- A little DM fix
- the MM queue
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (154 commits)
ksm: allocate roots when needed
mm: cleanup "swapcache" in do_swap_page
mm,ksm: swapoff might need to copy
mm,ksm: FOLL_MIGRATION do migration_entry_wait
ksm: shrink 32-bit rmap_item back to 32 bytes
ksm: treat unstable nid like in stable tree
ksm: add some comments
tmpfs: fix mempolicy object leaks
tmpfs: fix use-after-free of mempolicy object
mm/fadvise.c: drain all pagevecs if POSIX_FADV_DONTNEED fails to discard all pages
mm: export mmu notifier invalidates
mm: accelerate mm_populate() treatment of THP pages
mm: use long type for page counts in mm_populate() and get_user_pages()
mm: accurately document nr_free_*_pages functions with code comments
HWPOISON: change order of error_states[]'s elements
HWPOISON: fix misjudgement of page_action() for errors on mlocked pages
memcg: stop warning on memcg_propagate_kmem
net: change type of virtio_chan->p9_max_pages
vmscan: change type of vm_total_pages to unsigned long
fs/nfsd: change type of max_delegations, nfsd_drc_max_mem and nfsd_drc_mem_used
...
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/acpi.h | 8 | ||||
-rw-r--r-- | include/linux/bootmem.h | 1 | ||||
-rw-r--r-- | include/linux/compaction.h | 5 | ||||
-rw-r--r-- | include/linux/firmware-map.h | 6 | ||||
-rw-r--r-- | include/linux/highmem.h | 6 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 2 | ||||
-rw-r--r-- | include/linux/hugetlb.h | 6 | ||||
-rw-r--r-- | include/linux/ksm.h | 18 | ||||
-rw-r--r-- | include/linux/memblock.h | 2 | ||||
-rw-r--r-- | include/linux/memcontrol.h | 7 | ||||
-rw-r--r-- | include/linux/memory_hotplug.h | 20 | ||||
-rw-r--r-- | include/linux/migrate.h | 14 | ||||
-rw-r--r-- | include/linux/mm.h | 178 | ||||
-rw-r--r-- | include/linux/mm_types.h | 9 | ||||
-rw-r--r-- | include/linux/mman.h | 4 | ||||
-rw-r--r-- | include/linux/mmzone.h | 58 | ||||
-rw-r--r-- | include/linux/page-flags-layout.h | 88 | ||||
-rw-r--r-- | include/linux/page-isolation.h | 19 | ||||
-rw-r--r-- | include/linux/pm.h | 1 | ||||
-rw-r--r-- | include/linux/pm_runtime.h | 3 | ||||
-rw-r--r-- | include/linux/rmap.h | 2 | ||||
-rw-r--r-- | include/linux/sched.h | 22 | ||||
-rw-r--r-- | include/linux/swap.h | 49 | ||||
-rw-r--r-- | include/linux/vm_event_item.h | 1 | ||||
-rw-r--r-- | include/linux/vmstat.h | 2 |
25 files changed, 356 insertions, 175 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index bcbdd7484e58..f46cfd73a553 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -485,6 +485,14 @@ static inline bool acpi_driver_match_device(struct device *dev, #endif /* !CONFIG_ACPI */ +#ifdef CONFIG_ACPI_NUMA +void __init early_parse_srat(void); +#else +static inline void early_parse_srat(void) +{ +} +#endif + #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3cd16ba82f15..cdc3bab01832 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -53,6 +53,7 @@ extern void free_bootmem_node(pg_data_t *pgdat, unsigned long size); extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); +extern void __free_pages_bootmem(struct page *page, unsigned int order); /* * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, diff --git a/include/linux/compaction.h b/include/linux/compaction.h index cc7bddeaf553..091d72e70d8a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -23,7 +23,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, bool sync, bool *contended); -extern int compact_pgdat(pg_data_t *pgdat, int order); +extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -80,9 +80,8 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } -static inline int compact_pgdat(pg_data_t *pgdat, int order) +static inline void compact_pgdat(pg_data_t *pgdat, int order) { - return COMPACT_CONTINUE; } static inline void reset_isolation_suitable(pg_data_t *pgdat) diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index 43fe52fcef0f..71d4fa721db9 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -25,6 +25,7 @@ int firmware_map_add_early(u64 start, u64 end, const char *type); int firmware_map_add_hotplug(u64 start, u64 end, const char *type); +int firmware_map_remove(u64 start, u64 end, const char *type); #else /* CONFIG_FIRMWARE_MEMMAP */ @@ -38,6 +39,11 @@ static inline int firmware_map_add_hotplug(u64 start, u64 end, const char *type) return 0; } +static inline int firmware_map_remove(u64 start, u64 end, const char *type) +{ + return 0; +} + #endif /* CONFIG_FIRMWARE_MEMMAP */ #endif /* _LINUX_FIRMWARE_MAP_H */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index ef788b5b4a35..7fb31da45d03 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -219,12 +219,6 @@ static inline void zero_user(struct page *page, zero_user_segments(page, start, start + size, 0, 0); } -static inline void __deprecated memclear_highpage_flush(struct page *page, - unsigned int offset, unsigned int size) -{ - zero_user(page, offset, size); -} - #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 1d76f8ca90f0..ee1c244a62a1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -113,7 +113,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma, do { \ pmd_t *____pmd = (__pmd); \ anon_vma_lock_write(__anon_vma); \ - anon_vma_unlock(__anon_vma); \ + anon_vma_unlock_write(__anon_vma); \ BUG_ON(pmd_trans_splitting(*____pmd) || \ pmd_trans_huge(*____pmd)); \ } while (0) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c80d3f57a5b..eedc334fb6f5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,9 +43,9 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, #endif int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); -int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, - struct page **, struct vm_area_struct **, - unsigned long *, int *, int, unsigned int flags); +long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, + struct page **, struct vm_area_struct **, + unsigned long *, unsigned long *, long, unsigned int); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *); void __unmap_hugepage_range_final(struct mmu_gather *tlb, diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 3319a6967626..45c9b6a17bcb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -16,9 +16,6 @@ struct stable_node; struct mem_cgroup; -struct page *ksm_does_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); - #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -73,15 +70,8 @@ static inline void set_page_stable_node(struct page *page, * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ -static inline int ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - struct anon_vma *anon_vma = page_anon_vma(page); - - return anon_vma && - (anon_vma->root != vma->anon_vma->root || - page->index != linear_page_index(vma, address)); -} +struct page *ksm_might_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address); int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags); @@ -113,10 +103,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } -static inline int ksm_might_need_to_copy(struct page *page, +static inline struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - return 0; + return page; } static inline int page_referenced_ksm(struct page *page, diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f388203db7e8..3e5ecb2d790e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,6 +42,7 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; +extern struct movablemem_map movablemem_map; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) @@ -60,6 +61,7 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 28bd5fa2ff2e..d6183f06d8c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -116,7 +116,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); * For memory reclaim. */ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); -int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); @@ -321,12 +320,6 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return 1; } -static inline int -mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) -{ - return 1; -} - static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4a45c4e50025..b6a3be7d47bf 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -96,6 +96,7 @@ extern void __online_page_free(struct page *page); #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); +extern int arch_remove_memory(u64 start, u64 size); #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages in a zone */ @@ -173,17 +174,16 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ -#ifdef CONFIG_SPARSEMEM_VMEMMAP +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +extern void register_page_bootmem_info_node(struct pglist_data *pgdat); +#else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } -static inline void put_page_bootmem(struct page *page) -{ -} -#else -extern void register_page_bootmem_info_node(struct pglist_data *pgdat); -extern void put_page_bootmem(struct page *page); #endif +extern void put_page_bootmem(struct page *page); +extern void get_page_bootmem(unsigned long ingo, struct page *page, + unsigned long type); /* * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug @@ -233,6 +233,7 @@ static inline void unlock_memory_hotplug(void) {} #ifdef CONFIG_MEMORY_HOTREMOVE extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); +extern void try_offline_node(int nid); #else static inline int is_mem_section_removable(unsigned long pfn, @@ -240,6 +241,8 @@ static inline int is_mem_section_removable(unsigned long pfn, { return 0; } + +static inline void try_offline_node(int nid) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern int mem_online_node(int nid); @@ -247,7 +250,8 @@ extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int offline_memory_block(struct memory_block *mem); -extern int remove_memory(u64 start, u64 size); +extern bool is_memblock_offlined(struct memory_block *mem); +extern int remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 1e9f627967a3..a405d3dc0f61 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,11 +40,9 @@ extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode, int reason); + unsigned long private, enum migrate_mode mode, int reason); extern int migrate_huge_page(struct page *, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode); + unsigned long private, enum migrate_mode mode); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -62,11 +60,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode, int reason) { return -ENOSYS; } + unsigned long private, enum migrate_mode mode, int reason) + { return -ENOSYS; } static inline int migrate_huge_page(struct page *page, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode) { return -ENOSYS; } + unsigned long private, enum migrate_mode mode) + { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d9dcc35d6a1..e7c3f9a0111a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -87,6 +87,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ +#define VM_POPULATE 0x00001000 #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ @@ -366,7 +367,7 @@ static inline struct page *compound_head(struct page *page) * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ -static inline void reset_page_mapcount(struct page *page) +static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } @@ -580,50 +581,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) * sets it, so none of the operations on it need to be atomic. */ - -/* - * page->flags layout: - * - * There are three possibilities for how page->flags get - * laid out. The first is for the normal case, without - * sparsemem. The second is for sparsemem when there is - * plenty of space for node and section. The last is when - * we have run out of space and have to fall back to an - * alternate (slower) way of determining the node. - * - * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | - * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | - * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | - */ -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) -#define SECTIONS_WIDTH SECTIONS_SHIFT -#else -#define SECTIONS_WIDTH 0 -#endif - -#define ZONES_WIDTH ZONES_SHIFT - -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS -#define NODES_WIDTH NODES_SHIFT -#else -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#error "Vmemmap: No space for nodes field in page flags" -#endif -#define NODES_WIDTH 0 -#endif - -/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */ +/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) - -/* - * We are going to use the flags for the page to node mapping if its in - * there. This includes the case where there is no node, so it is implicit. - */ -#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) -#define NODE_NOT_IN_PAGE_FLAGS -#endif +#define LAST_NID_PGOFF (ZONES_PGOFF - LAST_NID_WIDTH) /* * Define the bit shifts to access each section. For non-existent @@ -633,6 +595,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) +#define LAST_NID_PGSHIFT (LAST_NID_PGOFF * (LAST_NID_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS @@ -654,6 +617,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) +#define LAST_NID_MASK ((1UL << LAST_NID_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) @@ -661,6 +625,10 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#define SECTION_IN_PAGE_FLAGS +#endif + /* * The identification function is only used by the buddy allocator for * determining if two pages could be buddies. We are not really @@ -693,31 +661,48 @@ static inline int page_to_nid(const struct page *page) #endif #ifdef CONFIG_NUMA_BALANCING -static inline int page_xchg_last_nid(struct page *page, int nid) +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS +static inline int page_nid_xchg_last(struct page *page, int nid) { return xchg(&page->_last_nid, nid); } -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return page->_last_nid; } -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { page->_last_nid = -1; } #else -static inline int page_xchg_last_nid(struct page *page, int nid) +static inline int page_nid_last(struct page *page) +{ + return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK; +} + +extern int page_nid_xchg_last(struct page *page, int nid); + +static inline void page_nid_reset_last(struct page *page) +{ + int nid = (1 << LAST_NID_SHIFT) - 1; + + page->flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); + page->flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; +} +#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */ +#else +static inline int page_nid_xchg_last(struct page *page, int nid) { return page_to_nid(page); } -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return page_to_nid(page); } -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { } #endif @@ -727,7 +712,7 @@ static inline struct zone *page_zone(const struct page *page) return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); @@ -757,7 +742,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, { set_page_zone(page, zone); set_page_node(page, node); -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } @@ -817,18 +802,7 @@ void page_address_init(void); #define PAGE_MAPPING_KSM 2 #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) -extern struct address_space swapper_space; -static inline struct address_space *page_mapping(struct page *page) -{ - struct address_space *mapping = page->mapping; - - VM_BUG_ON(PageSlab(page)); - if (unlikely(PageSwapCache(page))) - mapping = &swapper_space; - else if ((unsigned long)mapping & PAGE_MAPPING_ANON) - mapping = NULL; - return mapping; -} +extern struct address_space *page_mapping(struct page *page); /* Neutral page->mapping pointer to address_space or anon_vma or other */ static inline void *page_rmapping(struct page *page) @@ -1035,18 +1009,18 @@ static inline int fixup_user_fault(struct task_struct *tsk, } #endif -extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write); -int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, unsigned int foll_flags, - struct page **pages, struct vm_area_struct **vmas, - int *nonblocking); -int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int nr_pages, int write, int force, - struct page **pages, struct vm_area_struct **vmas); +long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int foll_flags, struct page **pages, + struct vm_area_struct **vmas, int *nonblocking); +long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); struct kvec; @@ -1359,6 +1333,24 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); +#define MOVABLEMEM_MAP_MAX MAX_NUMNODES +struct movablemem_entry { + unsigned long start_pfn; /* start pfn of memory segment */ + unsigned long end_pfn; /* end pfn of memory segment (exclusive) */ +}; + +struct movablemem_map { + bool acpi; /* true if using SRAT info */ + int nr_map; + struct movablemem_entry map[MOVABLEMEM_MAP_MAX]; + nodemask_t numa_nodes_hotplug; /* on which nodes we specify memory */ + nodemask_t numa_nodes_kernel; /* on which nodes kernel resides in */ +}; + +extern void __init insert_movablemem_map(unsigned long start_pfn, + unsigned long end_pfn); +extern int __init movablemem_map_overlap(unsigned long start_pfn, + unsigned long end_pfn); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ @@ -1395,6 +1387,9 @@ extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); +/* page_alloc.c */ +extern int min_free_kbytes; + /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); @@ -1472,13 +1467,24 @@ extern int install_special_mapping(struct mm_struct *mm, extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff); -extern unsigned long do_mmap_pgoff(struct file *, unsigned long, - unsigned long, unsigned long, - unsigned long, unsigned long); + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); +extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, unsigned long flags, + unsigned long pgoff, unsigned long *populate); extern int do_munmap(struct mm_struct *, unsigned long, size_t); +#ifdef CONFIG_MMU +extern int __mm_populate(unsigned long addr, unsigned long len, + int ignore_errors); +static inline void mm_populate(unsigned long addr, unsigned long len) +{ + /* Ignore errors */ + (void) __mm_populate(addr, len, 1); +} +#else +static inline void mm_populate(unsigned long addr, unsigned long len) {} +#endif + /* These take the mm semaphore themselves */ extern unsigned long vm_brk(unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); @@ -1623,8 +1629,17 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -struct page *follow_page(struct vm_area_struct *, unsigned long address, - unsigned int foll_flags); +struct page *follow_page_mask(struct vm_area_struct *vma, + unsigned long address, unsigned int foll_flags, + unsigned int *page_mask); + +static inline struct page *follow_page(struct vm_area_struct *vma, + unsigned long address, unsigned int foll_flags) +{ + unsigned int unused_page_mask; + return follow_page_mask(vma, address, foll_flags, &unused_page_mask); +} + #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ #define FOLL_GET 0x04 /* do get_page on page */ @@ -1636,6 +1651,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ +#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); @@ -1707,7 +1723,11 @@ int vmemmap_populate_basepages(struct page *start_page, unsigned long pages, int node); int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); - +#ifdef CONFIG_MEMORY_HOTPLUG +void vmemmap_free(struct page *memmap, unsigned long nr_pages); +#endif +void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, + unsigned long size); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, @@ -1720,7 +1740,7 @@ extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); -extern atomic_long_t mce_bad_pages; +extern atomic_long_t num_poisoned_pages; extern int soft_offline_page(struct page *page, int flags); extern void dump_page(struct page *page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8f5162a3571..ace9a5f01c64 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include <linux/cpumask.h> #include <linux/page-debug-flags.h> #include <linux/uprobes.h> +#include <linux/page-flags-layout.h> #include <asm/page.h> #include <asm/mmu.h> @@ -173,7 +174,7 @@ struct page { void *shadow; #endif -#ifdef CONFIG_NUMA_BALANCING +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS int _last_nid; #endif } @@ -414,9 +415,9 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time when the PTEs will me marked - * pte_numa to gather statistics and migrate pages to new nodes - * if necessary + * numa_next_scan is the next time that the PTEs will be marked + * pte_numa. NUMA hinting faults will gather statistics and migrate + * pages to new nodes if necessary. */ unsigned long numa_next_scan; diff --git a/include/linux/mman.h b/include/linux/mman.h index 9aa863da287f..61c7a87e5d2b 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -79,6 +79,8 @@ calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | - _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ); + ((flags & MAP_LOCKED) ? (VM_LOCKED | VM_POPULATE) : 0) | + (((flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE) ? + VM_POPULATE : 0); } #endif /* _LINUX_MMAN_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 73b64a38b984..ede274957e05 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -15,7 +15,7 @@ #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> -#include <generated/bounds.h> +#include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <asm/page.h> @@ -57,7 +57,9 @@ enum { */ MIGRATE_CMA, #endif +#ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ +#endif MIGRATE_TYPES }; @@ -308,24 +310,6 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H -/* - * When a memory allocation must conform to specific limitations (such - * as being suitable for DMA) the caller will pass in hints to the - * allocator in the gfp_mask, in the zone modifier bits. These bits - * are used to select a priority ordered list of memory zones which - * match the requested limits. See gfp_zone() in include/linux/gfp.h - */ - -#if MAX_NR_ZONES < 2 -#define ZONES_SHIFT 0 -#elif MAX_NR_ZONES <= 2 -#define ZONES_SHIFT 1 -#elif MAX_NR_ZONES <= 4 -#define ZONES_SHIFT 2 -#else -#error ZONES_SHIFT -- too many zones configured adjust calculation -#endif - struct zone { /* Fields commonly accessed by the page allocator */ @@ -543,6 +527,26 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } +static inline unsigned zone_end_pfn(const struct zone *zone) +{ + return zone->zone_start_pfn + zone->spanned_pages; +} + +static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) +{ + return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); +} + +static inline bool zone_is_initialized(struct zone *zone) +{ + return !!zone->wait_table; +} + +static inline bool zone_is_empty(struct zone *zone) +{ + return zone->spanned_pages == 0; +} + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the @@ -752,11 +756,17 @@ typedef struct pglist_data { #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) +#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) -#define node_end_pfn(nid) ({\ - pg_data_t *__pgdat = NODE_DATA(nid);\ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages;\ -}) +static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) +{ + return pgdat->node_start_pfn + pgdat->node_spanned_pages; +} + +static inline bool pgdat_is_empty(pg_data_t *pgdat) +{ + return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; +} #include <linux/memory_hotplug.h> @@ -1053,8 +1063,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ -#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) - #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h new file mode 100644 index 000000000000..93506a114034 --- /dev/null +++ b/include/linux/page-flags-layout.h @@ -0,0 +1,88 @@ +#ifndef PAGE_FLAGS_LAYOUT_H +#define PAGE_FLAGS_LAYOUT_H + +#include <linux/numa.h> +#include <generated/bounds.h> + +/* + * When a memory allocation must conform to specific limitations (such + * as being suitable for DMA) the caller will pass in hints to the + * allocator in the gfp_mask, in the zone modifier bits. These bits + * are used to select a priority ordered list of memory zones which + * match the requested limits. See gfp_zone() in include/linux/gfp.h + */ +#if MAX_NR_ZONES < 2 +#define ZONES_SHIFT 0 +#elif MAX_NR_ZONES <= 2 +#define ZONES_SHIFT 1 +#elif MAX_NR_ZONES <= 4 +#define ZONES_SHIFT 2 +#else +#error ZONES_SHIFT -- too many zones configured adjust calculation +#endif + +#ifdef CONFIG_SPARSEMEM +#include <asm/sparsemem.h> + +/* SECTION_SHIFT #bits space required to store a section # */ +#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) + +#endif /* CONFIG_SPARSEMEM */ + +/* + * page->flags layout: + * + * There are five possibilities for how page->flags get laid out. The first + * pair is for the normal case without sparsemem. The second pair is for + * sparsemem when there is plenty of space for node and section information. + * The last is when there is insufficient space in page->flags and a separate + * lookup is necessary. + * + * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | + * " plus space for last_nid: | NODE | ZONE | LAST_NID ... | FLAGS | + * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * " plus space for last_nid: | SECTION | NODE | ZONE | LAST_NID ... | FLAGS | + * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | + */ +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#define SECTIONS_WIDTH SECTIONS_SHIFT +#else +#define SECTIONS_WIDTH 0 +#endif + +#define ZONES_WIDTH ZONES_SHIFT + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#define NODES_WIDTH NODES_SHIFT +#else +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#error "Vmemmap: No space for nodes field in page flags" +#endif +#define NODES_WIDTH 0 +#endif + +#ifdef CONFIG_NUMA_BALANCING +#define LAST_NID_SHIFT NODES_SHIFT +#else +#define LAST_NID_SHIFT 0 +#endif + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#define LAST_NID_WIDTH LAST_NID_SHIFT +#else +#define LAST_NID_WIDTH 0 +#endif + +/* + * We are going to use the flags for the page to node mapping if its in + * there. This includes the case where there is no node, so it is implicit. + */ +#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) +#define NODE_NOT_IN_PAGE_FLAGS +#endif + +#if defined(CONFIG_NUMA_BALANCING) && LAST_NID_WIDTH == 0 +#define LAST_NID_NOT_IN_PAGE_FLAGS +#endif + +#endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index a92061e08d48..3fff8e774067 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -1,6 +1,25 @@ #ifndef __LINUX_PAGEISOLATION_H #define __LINUX_PAGEISOLATION_H +#ifdef CONFIG_MEMORY_ISOLATION +static inline bool is_migrate_isolate_page(struct page *page) +{ + return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; +} +static inline bool is_migrate_isolate(int migratetype) +{ + return migratetype == MIGRATE_ISOLATE; +} +#else +static inline bool is_migrate_isolate_page(struct page *page) +{ + return false; +} +static inline bool is_migrate_isolate(int migratetype) +{ + return false; +} +#endif bool has_unmovable_pages(struct zone *zone, struct page *page, int count, bool skip_hwpoisoned_pages); diff --git a/include/linux/pm.h b/include/linux/pm.h index 97bcf23e045a..e5d7230332a4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -537,6 +537,7 @@ struct dev_pm_info { unsigned int irq_safe:1; unsigned int use_autosuspend:1; unsigned int timer_autosuspends:1; + unsigned int memalloc_noio:1; enum rpm_request request; enum rpm_status runtime_status; int runtime_error; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index c785c215abfc..7d7e09efff9b 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -47,6 +47,7 @@ extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); +extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); static inline bool pm_children_suspended(struct device *dev) { @@ -156,6 +157,8 @@ static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline unsigned long pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } +static inline void pm_runtime_set_memalloc_noio(struct device *dev, + bool enable){} #endif /* !CONFIG_PM_RUNTIME */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c20635c527a9..6dacb93a6d94 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -123,7 +123,7 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma) down_write(&anon_vma->root->rwsem); } -static inline void anon_vma_unlock(struct anon_vma *anon_vma) +static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } diff --git a/include/linux/sched.h b/include/linux/sched.h index e4112aad2964..c2182b53dace 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -51,6 +51,7 @@ struct sched_param { #include <linux/cred.h> #include <linux/llist.h> #include <linux/uidgid.h> +#include <linux/gfp.h> #include <asm/processor.h> @@ -1791,6 +1792,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ +#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ @@ -1828,6 +1830,26 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +static inline gfp_t memalloc_noio_flags(gfp_t flags) +{ + if (unlikely(current->flags & PF_MEMALLOC_NOIO)) + flags &= ~__GFP_IO; + return flags; +} + +static inline unsigned int memalloc_noio_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOIO; + current->flags |= PF_MEMALLOC_NOIO; + return flags; +} + +static inline void memalloc_noio_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; +} + /* * task->jobctl flags */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 68df9c17fbbb..2818a123f3ea 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -8,7 +8,7 @@ #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> - +#include <linux/fs.h> #include <linux/atomic.h> #include <asm/page.h> @@ -156,7 +156,7 @@ enum { SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; -#define SWAP_CLUSTER_MAX 32 +#define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* @@ -202,6 +202,18 @@ struct swap_info_struct { unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ #endif + spinlock_t lock; /* + * protect map scan related fields like + * swap_map, lowest_bit, highest_bit, + * inuse_pages, cluster_next, + * cluster_nr, lowest_alloc and + * highest_alloc. other fields are only + * changed at swapon/swapoff, so are + * protected by swap_lock. changing + * flags need hold this lock and + * swap_lock. If both locks need hold, + * hold swap_lock first. + */ }; struct swap_list_t { @@ -209,15 +221,12 @@ struct swap_list_t { int next; /* swapfile to be used next */ }; -/* Swap 50% full? Release swapcache more aggressively.. */ -#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; extern unsigned long dirty_balance_reserve; -extern unsigned int nr_free_buffer_pages(void); -extern unsigned int nr_free_pagecache_pages(void); +extern unsigned long nr_free_buffer_pages(void); +extern unsigned long nr_free_pagecache_pages(void); /* Definition of global_page_state not available yet */ #define nr_free_pages() global_page_state(NR_FREE_PAGES) @@ -266,7 +275,7 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); -extern long vm_total_pages; +extern unsigned long vm_total_pages; #ifdef CONFIG_NUMA extern int zone_reclaim_mode; @@ -330,8 +339,9 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); /* linux/mm/swap_state.c */ -extern struct address_space swapper_space; -#define total_swapcache_pages swapper_space.nrpages +extern struct address_space swapper_spaces[]; +#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)]) +extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); @@ -346,8 +356,20 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); /* linux/mm/swapfile.c */ -extern long nr_swap_pages; +extern atomic_long_t nr_swap_pages; extern long total_swap_pages; + +/* Swap 50% full? Release swapcache more aggressively.. */ +static inline bool vm_swap_full(void) +{ + return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; +} + +static inline long get_nr_swap_pages(void) +{ + return atomic_long_read(&nr_swap_pages); +} + extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); @@ -380,9 +402,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #else /* CONFIG_SWAP */ -#define nr_swap_pages 0L +#define get_nr_swap_pages() 0L #define total_swap_pages 0L -#define total_swapcache_pages 0UL +#define total_swapcache_pages() 0UL +#define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index fce0a2799d43..bd6cf61142be 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -36,7 +36,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, - KSWAPD_SKIP_CONGESTION_WAIT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index a13291f7da88..5fd71a7d0dfd 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -85,7 +85,7 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) -#define count_vm_numa_events(x, y) do {} while (0) +#define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #define __count_zone_vm_events(item, zone, delta) \ |