#include <linux/sched.h>
#include <linux/errno.h>
+#include <linux/capability.h>
#ifdef __KERNEL__
-#include <linux/config.h>
#include <linux/gfp.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
#include <linux/fs.h>
+#include <linux/mutex.h>
+#include <linux/debug_locks.h>
+#include <linux/backing-dev.h>
+#include <linux/mm_types.h>
struct mempolicy;
struct anon_vma;
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/atomic.h>
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
#define VM_EXEC 0x00000004
#define VM_SHARED 0x00000008
+/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
#define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */
#define VM_MAYWRITE 0x00000020
#define VM_MAYEXEC 0x00000040
#define VM_GROWSDOWN 0x00000100 /* general info on the segment */
#define VM_GROWSUP 0x00000200
-#define VM_SHM 0x00000400 /* shared memory area, don't swap out */
+#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */
#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */
#define VM_EXECUTABLE 0x00001000
#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
-#define VM_RESERVED 0x00080000 /* Don't unmap it from swap_out */
+#define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#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) */
+#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
void (*open)(struct vm_area_struct * area);
void (*close)(struct vm_area_struct * area);
struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
+ unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address);
int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
+
+ /* 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);
#ifdef CONFIG_NUMA
int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
unsigned long addr);
+ int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
+ const nodemask_t *to, unsigned long flags);
#endif
};
struct mmu_gather;
struct inode;
-#ifdef ARCH_HAS_ATOMIC_UNSIGNED
-typedef unsigned page_flags_t;
-#else
-typedef unsigned long page_flags_t;
-#endif
-
-/*
- * Each physical page in the system has a struct page associated with
- * it to keep track of whatever it is we are using the page for at the
- * moment. Note that we have no way to track which tasks are using
- * a page.
- */
-struct page {
- page_flags_t flags; /* Atomic flags, some possibly
- * updated asynchronously */
- atomic_t _count; /* Usage count, see below. */
- atomic_t _mapcount; /* Count of ptes mapped in mms,
- * to show when page is mapped
- * & limit reverse map searches.
- */
- unsigned long private; /* Mapping-private opaque data:
- * usually used for buffer_heads
- * if PagePrivate set; used for
- * swp_entry_t if PageSwapCache
- * When page is free, this indicates
- * order in the buddy system.
- */
- struct address_space *mapping; /* If low bit clear, points to
- * inode address_space, or NULL.
- * If page mapped as anonymous
- * memory, low bit is set, and
- * it points to anon_vma object:
- * see PAGE_MAPPING_ANON below.
- */
- pgoff_t index; /* Our offset within mapping. */
- struct list_head lru; /* Pageout list, eg. active_list
- * protected by zone->lru_lock !
- */
- /*
- * On machines where all RAM is mapped into kernel address space,
- * we can simply calculate the virtual address. On machines with
- * highmem some memory is mapped into kernel virtual memory
- * dynamically, so we need a place to store that address.
- * Note that this field could be 16 bits on x86 ... ;)
- *
- * Architectures with slow multiplication can define
- * WANT_PAGE_VIRTUAL in asm/page.h
- */
-#if defined(WANT_PAGE_VIRTUAL)
- void *virtual; /* Kernel virtual address (NULL if
- not kmapped, ie. highmem) */
-#endif /* WANT_PAGE_VIRTUAL */
-};
+#define page_private(page) ((page)->private)
+#define set_page_private(page, v) ((page)->private = (v))
/*
* FIXME: take this include out, include page-flags.h in
*/
#include <linux/page-flags.h>
+#ifdef CONFIG_DEBUG_VM
+#define VM_BUG_ON(cond) BUG_ON(cond)
+#else
+#define VM_BUG_ON(condition) do { } while(0)
+#endif
+
/*
* Methods to modify the page usage count.
*
*
* Also, many kernel routines increase the page count before a critical
* routine so they can be sure the page doesn't go away from under them.
- *
- * Since 2.6.6 (approx), a free page has ->_count = -1. This is so that we
- * can use atomic_add_negative(-1, page->_count) to detect when the page
- * becomes free and so that we can also use atomic_inc_and_test to atomically
- * detect when we just tried to grab a ref on a page which some other CPU has
- * already deemed to be freeable.
- *
- * NO code should make assumptions about this internal detail! Use the provided
- * macros which retain the old rules: page_count(page) == 0 is a free page.
*/
/*
- * Drop a ref, return true if the logical refcount fell to zero (the page has
- * no users)
+ * Drop a ref, return true if the refcount fell to zero (the page has no users)
*/
-#define put_page_testzero(p) \
- ({ \
- BUG_ON(page_count(p) == 0); \
- atomic_add_negative(-1, &(p)->_count); \
- })
+static inline int put_page_testzero(struct page *page)
+{
+ VM_BUG_ON(atomic_read(&page->_count) == 0);
+ return atomic_dec_and_test(&page->_count);
+}
/*
- * Grab a ref, return true if the page previously had a logical refcount of
- * zero. ie: returns true if we just grabbed an already-deemed-to-be-free page
+ * Try to grab a ref unless the page has a refcount of zero, return false if
+ * that is the case.
*/
-#define get_page_testone(p) atomic_inc_and_test(&(p)->_count)
-
-#define set_page_count(p,v) atomic_set(&(p)->_count, v - 1)
-#define __put_page(p) atomic_dec(&(p)->_count)
-
-extern void FASTCALL(__page_cache_release(struct page *));
-
-#ifdef CONFIG_HUGETLB_PAGE
-
-static inline int page_count(struct page *p)
+static inline int get_page_unless_zero(struct page *page)
{
- if (PageCompound(p))
- p = (struct page *)p->private;
- return atomic_read(&(p)->_count) + 1;
+ VM_BUG_ON(PageCompound(page));
+ return atomic_inc_not_zero(&page->_count);
}
-static inline void get_page(struct page *page)
+static inline int page_count(struct page *page)
{
if (unlikely(PageCompound(page)))
- page = (struct page *)page->private;
- atomic_inc(&page->_count);
+ page = (struct page *)page_private(page);
+ return atomic_read(&page->_count);
}
-void put_page(struct page *page);
-
-#else /* CONFIG_HUGETLB_PAGE */
-
-#define page_count(p) (atomic_read(&(p)->_count) + 1)
-
static inline void get_page(struct page *page)
{
+ if (unlikely(PageCompound(page)))
+ page = (struct page *)page_private(page);
+ VM_BUG_ON(atomic_read(&page->_count) == 0);
atomic_inc(&page->_count);
}
-static inline void put_page(struct page *page)
+/*
+ * Setup the page count before being freed into the page allocator for
+ * the first time (boot or memory hotplug)
+ */
+static inline void init_page_count(struct page *page)
{
- if (!PageReserved(page) && put_page_testzero(page))
- __page_cache_release(page);
+ atomic_set(&page->_count, 1);
}
-#endif /* CONFIG_HUGETLB_PAGE */
+void put_page(struct page *page);
+void put_pages_list(struct list_head *pages);
+
+void split_page(struct page *page, unsigned int order);
/*
* Multiple processes may "see" the same page. E.g. for untouched
* only one copy in memory, at most, normally.
*
* For the non-reserved pages, page_count(page) denotes a reference count.
- * page_count() == 0 means the page is free.
- * page_count() == 1 means the page is used for exactly one purpose
- * (e.g. a private data page of one process).
+ * page_count() == 0 means the page is free. page->lru is then used for
+ * freelist management in the buddy allocator.
+ * page_count() > 0 means the page has been allocated.
+ *
+ * Pages are allocated by the slab allocator in order to provide memory
+ * to kmalloc and kmem_cache_alloc. In this case, the management of the
+ * page, and the fields in 'struct page' are the responsibility of mm/slab.c
+ * unless a particular usage is carefully commented. (the responsibility of
+ * freeing the kmalloc memory is the caller's, of course).
*
- * A page may be used for kmalloc() or anyone else who does a
- * __get_free_page(). In this case the page_count() is at least 1, and
- * all other fields are unused but should be 0 or NULL. The
- * management of this page is the responsibility of the one who uses
- * it.
+ * A page may be used by anyone else who does a __get_free_page().
+ * In this case, page_count still tracks the references, and should only
+ * be used through the normal accessor functions. The top bits of page->flags
+ * and page->virtual store page management information, but all other fields
+ * are unused and could be used privately, carefully. The management of this
+ * page is the responsibility of the one who allocated it, and those who have
+ * subsequently been given references to it.
*
- * The other pages (we may call them "process pages") are completely
+ * The other pages (we may call them "pagecache pages") are completely
* managed by the Linux memory manager: I/O, buffers, swapping etc.
* The following discussion applies only to them.
*
- * A page may belong to an inode's memory mapping. In this case,
- * page->mapping is the pointer to the inode, and page->index is the
- * file offset of the page, in units of PAGE_CACHE_SIZE.
+ * A pagecache page contains an opaque `private' member, which belongs to the
+ * page's address_space. Usually, this is the address of a circular list of
+ * the page's disk buffers. PG_private must be set to tell the VM to call
+ * into the filesystem to release these pages.
*
- * A page contains an opaque `private' member, which belongs to the
- * page's address_space. Usually, this is the address of a circular
- * list of the page's disk buffers.
+ * A page may belong to an inode's memory mapping. In this case, page->mapping
+ * is the pointer to the inode, and page->index is the file offset of the page,
+ * in units of PAGE_CACHE_SIZE.
*
- * For pages belonging to inodes, the page_count() is the number of
- * attaches, plus 1 if `private' contains something, plus one for
- * the page cache itself.
+ * If pagecache pages are not associated with an inode, they are said to be
+ * anonymous pages. These may become associated with the swapcache, and in that
+ * case PG_swapcache is set, and page->private is an offset into the swapcache.
*
- * All pages belonging to an inode are in these doubly linked lists:
- * mapping->clean_pages, mapping->dirty_pages and mapping->locked_pages;
- * using the page->list list_head. These fields are also used for
- * freelist managemet (when page_count()==0).
+ * In either case (swapcache or inode backed), the pagecache itself holds one
+ * reference to the page. Setting PG_private should also increment the
+ * refcount. The each user mapping also has a reference to the page.
*
- * There is also a per-mapping radix tree mapping index to the page
- * in memory if present. The tree is rooted at mapping->root.
+ * The pagecache pages are stored in a per-mapping radix tree, which is
+ * rooted at mapping->page_tree, and indexed by offset.
+ * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space
+ * lists, we instead now tag pages as dirty/writeback in the radix tree.
*
- * All process pages can do I/O:
+ * All pagecache pages may be subject to I/O:
* - inode pages may need to be read from disk,
* - inode pages which have been modified and are MAP_SHARED may need
- * to be written to disk,
- * - private pages which have been modified may need to be swapped out
- * to swap space and (later) to be read back into memory.
+ * to be written back to the inode on disk,
+ * - anonymous pages (including MAP_PRIVATE file mappings) which have been
+ * modified may need to be swapped out to swap space and (later) to be read
+ * back into memory.
*/
/*
#endif
/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
-#define SECTIONS_PGOFF ((sizeof(page_flags_t)*8) - SECTIONS_WIDTH)
+#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
#define ZONETABLE_MASK ((1UL << ZONETABLE_SHIFT) - 1)
-static inline unsigned long page_zonenum(struct page *page)
+static inline enum zone_type page_zonenum(struct page *page)
{
return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
struct zone;
extern struct zone *zone_table[];
+static inline int page_zone_id(struct page *page)
+{
+ return (page->flags >> ZONETABLE_PGSHIFT) & ZONETABLE_MASK;
+}
static inline struct zone *page_zone(struct page *page)
{
- return zone_table[(page->flags >> ZONETABLE_PGSHIFT) &
- ZONETABLE_MASK];
+ return zone_table[page_zone_id(page)];
+}
+
+static inline unsigned long zone_to_nid(struct zone *zone)
+{
+#ifdef CONFIG_NUMA
+ return zone->node;
+#else
+ return 0;
+#endif
}
static inline unsigned long page_to_nid(struct page *page)
if (FLAGS_HAS_NODE)
return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
else
- return page_zone(page)->zone_pgdat->node_id;
+ return zone_to_nid(page_zone(page));
}
static inline unsigned long page_to_section(struct page *page)
{
return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
-static inline void set_page_zone(struct page *page, unsigned long zone)
+static inline void set_page_zone(struct page *page, enum zone_type zone)
{
page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
}
+
static inline void set_page_node(struct page *page, unsigned long node)
{
page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}
-static inline void set_page_links(struct page *page, unsigned long zone,
+static inline void set_page_links(struct page *page, enum zone_type zone,
unsigned long node, unsigned long pfn)
{
set_page_zone(page, zone);
set_page_section(page, pfn_to_section_nr(pfn));
}
-#ifndef CONFIG_DISCONTIGMEM
-/* The array of struct pages - for discontigmem use pgdat->lmem_map */
-extern struct page *mem_map;
-#endif
+/*
+ * Some inline functions in vmstat.h depend on page_zone()
+ */
+#include <linux/vmstat.h>
-static inline void *lowmem_page_address(struct page *page)
+static __always_inline void *lowmem_page_address(struct page *page)
{
return __va(page_to_pfn(page) << PAGE_SHIFT);
}
static inline pgoff_t page_index(struct page *page)
{
if (unlikely(PageSwapCache(page)))
- return page->private;
+ return page_private(page);
return page->index;
}
*/
#define NOPAGE_SIGBUS (NULL)
#define NOPAGE_OOM ((struct page *) (-1))
+#define NOPAGE_REFAULT ((struct page *) (-2)) /* Return to userspace, rerun */
+
+/*
+ * Error return values for the *_nopfn functions
+ */
+#define NOPFN_SIGBUS ((unsigned long) -1)
+#define NOPFN_OOM ((unsigned long) -2)
/*
* Different kinds of faults, as returned by handle_mm_fault().
int shmem_lock(struct file *file, int lock, struct user_struct *user);
#else
#define shmem_nopage filemap_nopage
-#define shmem_lock(a, b, c) ({0;}) /* always in memory, no need to lock */
-#define shmem_set_policy(a, b) (0)
-#define shmem_get_policy(a, b) (NULL)
+
+static inline int shmem_lock(struct file *file, int lock,
+ struct user_struct *user)
+{
+ return 0;
+}
+
+static inline int shmem_set_policy(struct vm_area_struct *vma,
+ struct mempolicy *new)
+{
+ return 0;
+}
+
+static inline struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ return NULL;
+}
#endif
struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags);
+extern int shmem_mmap(struct file *file, struct vm_area_struct *vma);
int shmem_zero_setup(struct vm_area_struct *);
+#ifndef CONFIG_MMU
+extern unsigned long shmem_get_unmapped_area(struct file *file,
+ unsigned long addr,
+ unsigned long len,
+ unsigned long pgoff,
+ unsigned long flags);
+#endif
+
static inline int can_do_mlock(void)
{
if (capable(CAP_IPC_LOCK))
unsigned long truncate_count; /* Compare vm_truncate_count */
};
+struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t);
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, struct mm_struct *mm,
+unsigned long unmap_vmas(struct mmu_gather **tlb,
struct vm_area_struct *start_vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *);
}
extern int vmtruncate(struct inode * inode, loff_t offset);
-extern pud_t *FASTCALL(__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address));
-extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address));
-extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
-extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
+extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
-extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
-static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access)
+#ifdef CONFIG_MMU
+extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,
+ unsigned long address, int write_access);
+
+static inline int handle_mm_fault(struct mm_struct *mm,
+ struct vm_area_struct *vma, unsigned long address,
+ int write_access)
{
- return __handle_mm_fault(mm, vma, address, write_access) & (~VM_FAULT_WRITE);
+ return __handle_mm_fault(mm, vma, address, write_access) &
+ (~VM_FAULT_WRITE);
}
+#else
+static inline int handle_mm_fault(struct mm_struct *mm,
+ struct vm_area_struct *vma, unsigned long address,
+ int write_access)
+{
+ /* should never happen if there's no MMU */
+ BUG();
+ return VM_FAULT_SIGBUS;
+}
+#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);
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);
-int __set_page_dirty_buffers(struct page *page);
int __set_page_dirty_nobuffers(struct page *page);
int redirty_page_for_writepage(struct writeback_control *wbc,
struct page *page);
* The callback will be passed nr_to_scan == 0 when the VM is querying the
* cache size, so a fastpath for that case is appropriate.
*/
-typedef int (*shrinker_t)(int nr_to_scan, unsigned int gfp_mask);
+typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask);
/*
* Add an aging callback. The int is the number of 'seeks' it takes
extern void remove_shrinker(struct shrinker *shrinker);
/*
- * On a two-level or three-level page table, this ends up being trivial. Thus
- * the inlining and the symmetry break with pte_alloc_map() that does all
- * of this out-of-line.
+ * Some shared mappigns will want the pages marked read-only
+ * to track write events. If so, we'll downgrade vm_page_prot
+ * to the private version (using protection_map[] without the
+ * VM_SHARED bit).
*/
+static inline int vma_wants_writenotify(struct vm_area_struct *vma)
+{
+ unsigned int vm_flags = vma->vm_flags;
+
+ /* If it was private or non-writable, the write bit is already clear */
+ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
+ return 0;
+
+ /* The backer wishes to know when pages are first written to? */
+ if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+ return 1;
+
+ /* The open routine did something to the protections already? */
+ if (pgprot_val(vma->vm_page_prot) !=
+ pgprot_val(protection_map[vm_flags &
+ (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]))
+ return 0;
+
+ /* Specialty mapping? */
+ if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE))
+ return 0;
+
+ /* Can the mapping track the dirty pages? */
+ return vma->vm_file && vma->vm_file->f_mapping &&
+ mapping_cap_account_dirty(vma->vm_file->f_mapping);
+}
+
+extern pte_t *FASTCALL(get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl));
+
+int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
+int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
+
/*
* The following ifdef needed to get the 4level-fixup.h header to work.
* Remove it when 4level-fixup.h has been removed.
*/
-#ifdef CONFIG_MMU
-#ifndef __ARCH_HAS_4LEVEL_HACK
+#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
- if (pgd_none(*pgd))
- return __pud_alloc(mm, pgd, address);
- return pud_offset(pgd, address);
+ return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
+ NULL: pud_offset(pgd, address);
}
static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
- if (pud_none(*pud))
- return __pmd_alloc(mm, pud, address);
- return pmd_offset(pud, address);
+ return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
+ NULL: pmd_offset(pud, address);
}
-#endif
-#endif /* CONFIG_MMU */
+#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
+
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+/*
+ * 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
+ * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
+ * When freeing, reset page->mapping so free_pages_check won't complain.
+ */
+#define __pte_lockptr(page) &((page)->ptl)
+#define pte_lock_init(_page) do { \
+ spin_lock_init(__pte_lockptr(_page)); \
+} while (0)
+#define pte_lock_deinit(page) ((page)->mapping = NULL)
+#define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
+#else
+/*
+ * 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 */
+
+#define pte_offset_map_lock(mm, pmd, address, ptlp) \
+({ \
+ spinlock_t *__ptl = pte_lockptr(mm, pmd); \
+ pte_t *__pte = pte_offset_map(pmd, address); \
+ *(ptlp) = __ptl; \
+ spin_lock(__ptl); \
+ __pte; \
+})
+
+#define pte_unmap_unlock(pte, ptl) do { \
+ spin_unlock(ptl); \
+ pte_unmap(pte); \
+} while (0)
+
+#define pte_alloc_map(mm, pmd, address) \
+ ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+ NULL: pte_offset_map(pmd, address))
+
+#define pte_alloc_map_lock(mm, pmd, address, ptlp) \
+ ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+ NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
+
+#define pte_alloc_kernel(pmd, address) \
+ ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
+ 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);
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+/*
+ * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
+ * zones, allocate the backing mem_map and account for memory holes in a more
+ * architecture independent manner. This is a substitute for creating the
+ * zone_sizes[] and zholes_size[] arrays and passing them to
+ * free_area_init_node()
+ *
+ * An architecture is expected to register range of page frames backed by
+ * physical memory with add_active_range() before calling
+ * free_area_init_nodes() passing in the PFN each zone ends at. At a basic
+ * usage, an architecture is expected to do something like
+ *
+ * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
+ * max_highmem_pfn};
+ * for_each_valid_physical_page_range()
+ * add_active_range(node_id, start_pfn, end_pfn)
+ * free_area_init_nodes(max_zone_pfns);
+ *
+ * If the architecture guarantees that there are no holes in the ranges
+ * registered with add_active_range(), free_bootmem_active_regions()
+ * will call free_bootmem_node() for each registered physical page range.
+ * Similarly sparse_memory_present_with_active_regions() calls
+ * memory_present() for each range when SPARSEMEM is enabled.
+ *
+ * See mm/page_alloc.c for more information on each function exposed by
+ * CONFIG_ARCH_POPULATES_NODE_MAP
+ */
+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 push_node_boundaries(unsigned int nid, unsigned long start_pfn,
+ unsigned long end_pfn);
+extern void remove_all_active_ranges(void);
+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,
+ 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);
+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);
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+extern void set_dma_reserve(unsigned long new_dma_reserve);
extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
+extern void setup_per_zone_pages_min(void);
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 void zonetable_add(struct zone *zone, int nid, enum zone_type zid,
+ unsigned long pfn, unsigned long size);
#ifdef CONFIG_NUMA
extern void setup_per_cpu_pageset(void);
extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
struct rb_node **, struct rb_node *);
+extern void unlink_file_vma(struct vm_area_struct *);
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 *);
/* filemap.c */
extern unsigned long page_unuse(struct page *);
extern void truncate_inode_pages(struct address_space *, loff_t);
+extern void truncate_inode_pages_range(struct address_space *,
+ loff_t lstart, loff_t lend);
/* generic vm_area_ops exported for stackable file systems */
extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
* turning readahead off */
int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
- unsigned long offset, unsigned long nr_to_read);
+ pgoff_t offset, unsigned long nr_to_read);
int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
- unsigned long offset, unsigned long nr_to_read);
-unsigned long page_cache_readahead(struct address_space *mapping,
+ pgoff_t offset, unsigned long nr_to_read);
+unsigned long page_cache_readahead(struct address_space *mapping,
struct file_ra_state *ra,
struct file *filp,
- unsigned long offset,
+ pgoff_t offset,
unsigned long size);
void handle_ra_miss(struct address_space *mapping,
struct file_ra_state *ra, pgoff_t offset);
unsigned long max_sane_readahead(unsigned long nr);
/* Do stack extension */
-extern int expand_stack(struct vm_area_struct * vma, unsigned long address);
+extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
+#ifdef CONFIG_IA64
+extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
+#endif
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
}
-extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);
-
-extern struct page * vmalloc_to_page(void *addr);
-extern unsigned long vmalloc_to_pfn(void *addr);
-extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
- int write);
-extern int check_user_page_readable(struct mm_struct *mm, unsigned long address);
-int remap_pfn_range(struct vm_area_struct *, unsigned long,
- unsigned long, unsigned long, pgprot_t);
+pgprot_t vm_get_page_prot(unsigned long vm_flags);
+struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
+struct page *vmalloc_to_page(void *addr);
+unsigned long vmalloc_to_pfn(void *addr);
+int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t);
+int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
+
+struct page *follow_page(struct vm_area_struct *, unsigned long address,
+ unsigned int foll_flags);
+#define FOLL_WRITE 0x01 /* check pte is writable */
+#define FOLL_TOUCH 0x02 /* mark page accessed */
+#define FOLL_GET 0x04 /* do get_page on page */
+#define FOLL_ANON 0x08 /* give ZERO_PAGE if no pgtable */
#ifdef CONFIG_PROC_FS
-void __vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
+void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
#else
-static inline void __vm_stat_account(struct mm_struct *mm,
+static inline void vm_stat_account(struct mm_struct *mm,
unsigned long flags, struct file *file, long pages)
{
}
#endif /* CONFIG_PROC_FS */
-static inline void vm_stat_account(struct vm_area_struct *vma)
-{
- __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
- vma_pages(vma));
-}
-
-static inline void vm_stat_unaccount(struct vm_area_struct *vma)
-{
- __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
- -vma_pages(vma));
-}
-
-/* update per process rss and vm hiwater data */
-extern void update_mem_hiwater(struct task_struct *tsk);
-
#ifndef CONFIG_DEBUG_PAGEALLOC
static inline void
-kernel_map_pages(struct page *page, int numpages, int enable)
-{
-}
+kernel_map_pages(struct page *page, int numpages, int enable) {}
#endif
extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);})
#endif /* __HAVE_ARCH_GATE_AREA */
-/* /proc/<pid>/oom_adj set to -17 protects from the oom-killer */
-#define OOM_DISABLE -17
+int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *,
+ void __user *, size_t *, loff_t *);
+unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
+ unsigned long lru_pages);
+void drop_pagecache(void);
+void drop_slab(void);
+
+#ifndef CONFIG_MMU
+#define randomize_va_space 0
+#else
+extern int randomize_va_space;
+#endif
+
+__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma);
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */