1 files changed, 43 insertions, 23 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3414a8813e97..c61ba10768ea 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -42,6 +42,9 @@ extern unsigned long mmap_min_addr;
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+
 /*
  * Linux kernel virtual memory manager primitives.
  * The idea being to have a "virtual" mm in the same way
@@ -71,7 +74,7 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 
 /*
- * vm_flags..
+ * vm_flags in vm_area_struct, see mm_types.h.
  */
 #define VM_READ         0x00000001      /* currently active flags */
 #define VM_WRITE        0x00000002
@@ -101,6 +104,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_DONTEXPAND   0x00040000      /* Cannot expand with mremap() */
 #define VM_RESERVED     0x00080000      /* Count as reserved_vm like IO */
 #define VM_ACCOUNT      0x00100000      /* Is a VM accounted object */
+#define VM_NORESERVE    0x00200000      /* should the VM suppress accounting */
 #define VM_HUGETLB      0x00400000      /* Huge TLB Page VM */
 #define VM_NONLINEAR    0x00800000      /* Is non-linear (remap_file_pages) */
 #define VM_MAPPED_COPY  0x01000000      /* T if mapped copy of data (nommu mmap) */
@@ -109,6 +113,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_CAN_NONLINEAR 0x08000000     /* Has ->fault & does nonlinear pages */
 #define VM_MIXEDMAP     0x10000000      /* Can contain "struct page" and pure PFN pages */
+#define VM_SAO          0x20000000      /* Strong Access Ordering (powerpc) */
 
 #ifndef VM_STACK_DEFAULT_FLAGS          /* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -166,12 +171,16 @@ struct vm_operations_struct {
         void (*open)(struct vm_area_struct * area);
         void (*close)(struct vm_area_struct * area);
         int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-        unsigned long (*nopfn)(struct vm_area_struct *area,
-                        unsigned long address);
 
         /* notification that a previously read-only page is about to become
          * writable, if an error is returned it will cause a SIGBUS */
         int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page);
+
+        /* called by access_process_vm when get_user_pages() fails, typically
+         * for use by special VMAs that can switch between memory and hardware
+         */
+        int (*access)(struct vm_area_struct *vma, unsigned long addr,
+                      void *buf, int len, int write);
 #ifdef CONFIG_NUMA
         /*
          * set_policy() op must add a reference to any non-NULL @new mempolicy
@@ -669,13 +678,6 @@ static inline int page_mapped(struct page *page)
 }
 
 /*
- * Error return values for the *_nopfn functions
- */
-#define NOPFN_SIGBUS    ((unsigned long) -1)
-#define NOPFN_OOM       ((unsigned long) -2)
-#define NOPFN_REFAULT   ((unsigned long) -3)
-
-/*
  * Different kinds of faults, as returned by handle_mm_fault().
  * Used to decide whether a process gets delivered SIGBUS or
  * just gets major/minor fault counters bumped up.
@@ -737,6 +739,8 @@ struct zap_details {
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                 pte_t pte);
 
+int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
+                unsigned long size);
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
                 unsigned long size, struct zap_details *);
 unsigned long unmap_vmas(struct mmu_gather **tlb,
@@ -766,14 +770,14 @@ struct mm_walk {
 
 int walk_page_range(unsigned long addr, unsigned long end,
                 struct mm_walk *walk);
-void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
+void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
                 unsigned long end, unsigned long floor, unsigned long ceiling);
-void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,
-                unsigned long floor, unsigned long ceiling);
 int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
                         struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
                 loff_t const holebegin, loff_t const holelen, int even_cows);
+int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
+                        void *buf, int len, int write);
 
 static inline void unmap_shared_mapping_range(struct address_space *mapping,
                 loff_t const holebegin, loff_t const holelen)
@@ -803,7 +807,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
                 int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
-void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
 extern void do_invalidatepage(struct page *page, unsigned long offset);
@@ -827,6 +830,19 @@ extern int mprotect_fixup(struct vm_area_struct *vma,
                           unsigned long end, unsigned long newflags);
 
 /*
+ * get_user_pages_fast provides equivalent functionality to get_user_pages,
+ * operating on current and current->mm (force=0 and doesn't return any vmas).
+ *
+ * get_user_pages_fast may take mmap_sem and page tables, so no assumptions
+ * can be made about locking. get_user_pages_fast is to be implemented in a
+ * way that is advantageous (vs get_user_pages()) when the user memory area is
+ * already faulted in and present in ptes. However if the pages have to be
+ * faulted in, it may turn out to be slightly slower).
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+                        struct page **pages);
+
+/*
  * A callback you can register to apply pressure to ageable caches.
  *
  * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should
@@ -898,7 +914,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 }
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
-#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+#if USE_SPLIT_PTLOCKS
 /*
  * We tuck a spinlock to guard each pagetable page into its struct page,
  * at page->private, with BUILD_BUG_ON to make sure that this will not
@@ -911,14 +927,14 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 } while (0)
 #define pte_lock_deinit(page)   ((page)->mapping = NULL)
 #define pte_lockptr(mm, pmd)    ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
-#else
+#else   /* !USE_SPLIT_PTLOCKS */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
 #define pte_lock_init(page)     do {} while (0)
 #define pte_lock_deinit(page)   do {} while (0)
 #define pte_lockptr(mm, pmd)    ({(void)(pmd); &(mm)->page_table_lock;})
-#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#endif /* USE_SPLIT_PTLOCKS */
 
 static inline void pgtable_page_ctor(struct page *page)
 {
@@ -959,9 +975,8 @@ static inline void pgtable_page_dtor(struct page *page)
                 NULL: pte_offset_kernel(pmd, address))
 
 extern void free_area_init(unsigned long * zones_size);
-extern void free_area_init_node(int nid, pg_data_t *pgdat,
-        unsigned long * zones_size, unsigned long zone_start_pfn, 
-        unsigned long *zholes_size);
+extern void free_area_init_node(int nid, unsigned long * zones_size,
+                unsigned long zone_start_pfn, unsigned long *zholes_size);
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
 /*
  * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
@@ -993,8 +1008,8 @@ extern void free_area_init_node(int nid, pg_data_t *pgdat,
 extern void free_area_init_nodes(unsigned long *max_zone_pfn);
 extern void add_active_range(unsigned int nid, unsigned long start_pfn,
                                         unsigned long end_pfn);
-extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
-                                                unsigned long new_end_pfn);
+extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
+                                        unsigned long end_pfn);
 extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
                                         unsigned long end_pfn);
 extern void remove_all_active_ranges(void);
@@ -1003,9 +1018,10 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 extern void get_pfn_range_for_nid(unsigned int nid,
                         unsigned long *start_pfn, unsigned long *end_pfn);
 extern unsigned long find_min_pfn_with_active_regions(void);
-extern unsigned long find_max_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
                                                 unsigned long max_low_pfn);
+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);
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 extern int early_pfn_to_nid(unsigned long pfn);
@@ -1019,6 +1035,7 @@ extern void mem_init(void);
 extern void show_mem(void);
 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);
@@ -1063,6 +1080,9 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
         unsigned long addr, unsigned long len, pgoff_t pgoff);
 extern void exit_mmap(struct mm_struct *);
 
+extern int mm_take_all_locks(struct mm_struct *mm);
+extern void mm_drop_all_locks(struct mm_struct *mm);
+
 #ifdef CONFIG_PROC_FS
 /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */
 extern void added_exe_file_vma(struct mm_struct *mm);