1 files changed, 156 insertions, 11 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 24c395694f4d..462acaf36f3a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -12,6 +12,7 @@
 #include <linux/prio_tree.h>
 #include <linux/debug_locks.h>
 #include <linux/mm_types.h>
+#include <linux/range.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -265,6 +266,8 @@ static inline int get_page_unless_zero(struct page *page)
         return atomic_inc_not_zero(&page->_count);
 }
 
+extern int page_is_ram(unsigned long pfn);
+
 /* Support for virtually mapped pages */
 struct page *vmalloc_to_page(const void *addr);
 unsigned long vmalloc_to_pfn(const void *addr);
@@ -620,13 +623,22 @@ void page_address_init(void);
 /*
  * On an anonymous page mapped into a user virtual memory area,
  * page->mapping points to its anon_vma, not to a struct address_space;
- * with the PAGE_MAPPING_ANON bit set to distinguish it.
+ * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
+ *
+ * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
+ * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
+ * and then page->mapping points, not to an anon_vma, but to a private
+ * structure which KSM associates with that merged page.  See ksm.h.
+ *
+ * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
  *
  * Please note that, confusingly, "page_mapping" refers to the inode
  * address_space which maps the page from disk; whereas "page_mapped"
  * refers to user virtual address space into which the page is mapped.
  */
 #define PAGE_MAPPING_ANON       1
+#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)
@@ -634,16 +646,19 @@ static inline struct address_space *page_mapping(struct page *page)
         struct address_space *mapping = page->mapping;
 
         VM_BUG_ON(PageSlab(page));
-#ifdef CONFIG_SWAP
         if (unlikely(PageSwapCache(page)))
                 mapping = &swapper_space;
-        else
-#endif
-        if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+        else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
                 mapping = NULL;
         return mapping;
 }
 
+/* Neutral page->mapping pointer to address_space or anon_vma or other */
+static inline void *page_rmapping(struct page *page)
+{
+        return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
+}
+
 static inline int PageAnon(struct page *page)
 {
         return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
@@ -758,6 +773,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlb,
  * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
  * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
  * @pte_hole: if set, called for each hole at all levels
+ * @hugetlb_entry: if set, called for each hugetlb entry
  *
  * (see walk_page_range for more details)
  */
@@ -767,6 +783,8 @@ struct mm_walk {
         int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
         int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
         int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
+        int (*hugetlb_entry)(pte_t *, unsigned long,
+                             unsigned long, unsigned long, struct mm_walk *);
         struct mm_struct *mm;
         void *private;
 };
@@ -852,6 +870,114 @@ extern int mprotect_fixup(struct vm_area_struct *vma,
  */
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
                           struct page **pages);
+/*
+ * per-process(per-mm_struct) statistics.
+ */
+#if defined(SPLIT_RSS_COUNTING)
+/*
+ * The mm counters are not protected by its page_table_lock,
+ * so must be incremented atomically.
+ */
+static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
+{
+        atomic_long_set(&mm->rss_stat.count[member], value);
+}
+
+unsigned long get_mm_counter(struct mm_struct *mm, int member);
+
+static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
+{
+        atomic_long_add(value, &mm->rss_stat.count[member]);
+}
+
+static inline void inc_mm_counter(struct mm_struct *mm, int member)
+{
+        atomic_long_inc(&mm->rss_stat.count[member]);
+}
+
+static inline void dec_mm_counter(struct mm_struct *mm, int member)
+{
+        atomic_long_dec(&mm->rss_stat.count[member]);
+}
+
+#else  /* !USE_SPLIT_PTLOCKS */
+/*
+ * The mm counters are protected by its page_table_lock,
+ * so can be incremented directly.
+ */
+static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
+{
+        mm->rss_stat.count[member] = value;
+}
+
+static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
+{
+        return mm->rss_stat.count[member];
+}
+
+static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
+{
+        mm->rss_stat.count[member] += value;
+}
+
+static inline void inc_mm_counter(struct mm_struct *mm, int member)
+{
+        mm->rss_stat.count[member]++;
+}
+
+static inline void dec_mm_counter(struct mm_struct *mm, int member)
+{
+        mm->rss_stat.count[member]--;
+}
+
+#endif /* !USE_SPLIT_PTLOCKS */
+
+static inline unsigned long get_mm_rss(struct mm_struct *mm)
+{
+        return get_mm_counter(mm, MM_FILEPAGES) +
+                get_mm_counter(mm, MM_ANONPAGES);
+}
+
+static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
+{
+        return max(mm->hiwater_rss, get_mm_rss(mm));
+}
+
+static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
+{
+        return max(mm->hiwater_vm, mm->total_vm);
+}
+
+static inline void update_hiwater_rss(struct mm_struct *mm)
+{
+        unsigned long _rss = get_mm_rss(mm);
+
+        if ((mm)->hiwater_rss < _rss)
+                (mm)->hiwater_rss = _rss;
+}
+
+static inline void update_hiwater_vm(struct mm_struct *mm)
+{
+        if (mm->hiwater_vm < mm->total_vm)
+                mm->hiwater_vm = mm->total_vm;
+}
+
+static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
+                                         struct mm_struct *mm)
+{
+        unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
+
+        if (*maxrss < hiwater_rss)
+                *maxrss = hiwater_rss;
+}
+
+#if defined(SPLIT_RSS_COUNTING)
+void sync_mm_rss(struct task_struct *task, struct mm_struct *mm);
+#else
+static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
+{
+}
+#endif
 
 /*
  * A callback you can register to apply pressure to ageable caches.
@@ -1022,6 +1148,9 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn,
 extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
                                         unsigned long end_pfn);
 extern void remove_all_active_ranges(void);
+void sort_node_map(void);
+unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
+                                                unsigned long end_pfn);
 extern unsigned long absent_pages_in_range(unsigned long start_pfn,
                                                 unsigned long end_pfn);
 extern void get_pfn_range_for_nid(unsigned int nid,
@@ -1029,6 +1158,10 @@ extern void get_pfn_range_for_nid(unsigned int nid,
 extern unsigned long find_min_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
                                                 unsigned long max_low_pfn);
+int add_from_early_node_map(struct range *range, int az,
+                                   int nr_range, int nid);
+void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
+                                 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
@@ -1061,16 +1194,13 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern int after_bootmem;
 
-#ifdef CONFIG_NUMA
 extern void setup_per_cpu_pageset(void);
-#else
-static inline void setup_per_cpu_pageset(void) {}
-#endif
 
 extern void zone_pcp_update(struct zone *zone);
 
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
+extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
 
 /* prio_tree.c */
 void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
@@ -1092,7 +1222,7 @@ static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
 
 /* mmap.c */
 extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
-extern void vma_adjust(struct vm_area_struct *vma, unsigned long start,
+extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
         unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert);
 extern struct vm_area_struct *vma_merge(struct mm_struct *,
         struct vm_area_struct *prev, unsigned long addr, unsigned long end,
@@ -1300,12 +1430,19 @@ extern int randomize_va_space;
 const char * arch_vma_name(struct vm_area_struct *vma);
 void print_vma_addr(char *prefix, unsigned long rip);
 
+void sparse_mem_maps_populate_node(struct page **map_map,
+                                   unsigned long pnum_begin,
+                                   unsigned long pnum_end,
+                                   unsigned long map_count,
+                                   int nodeid);
+
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
+void *vmemmap_alloc_block_buf(unsigned long size, int node);
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(struct page *start_page,
                                                 unsigned long pages, int node);
@@ -1316,11 +1453,19 @@ extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
                                  size_t size);
 extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 
+enum mf_flags {
+        MF_COUNT_INCREASED = 1 << 0,
+};
 extern void memory_failure(unsigned long pfn, int trapno);
-extern int __memory_failure(unsigned long pfn, int trapno, int ref);
+extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+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 int soft_offline_page(struct page *page, int flags);
+
+extern void dump_page(struct page *page);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */