#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>
+
+struct mempolicy;
+struct anon_vma;
#ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
extern unsigned long num_physpages;
extern void * high_memory;
+extern unsigned long vmalloc_earlyreserve;
extern int page_cluster;
+#ifdef CONFIG_SYSCTL
+extern int sysctl_legacy_va_layout;
+#else
+#define sysctl_legacy_va_layout 0
+#endif
+
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/atomic.h>
-#ifndef MM_VM_SIZE
-#define MM_VM_SIZE(mm) TASK_SIZE
-#endif
+#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
/*
* Linux kernel virtual memory manager primitives.
* per VM-area/task. A VM area is any part of the process virtual memory
* space that has a special rule for the page-fault handlers (ie a shared
* library, the executable area etc).
- *
- * This structure is exactly 64 bytes on ia32. Please think very, very hard
- * before adding anything to it.
*/
struct vm_area_struct {
struct mm_struct * vm_mm; /* The address space we belong to. */
/*
* For areas with an address space and backing store,
- * one of the address_space->i_mmap{,shared} lists,
- * for shm areas, the list of attaches, otherwise unused.
+ * linkage into the address_space->i_mmap prio tree, or
+ * linkage to the list of like vmas hanging off its node, or
+ * linkage of vma in the address_space->i_mmap_nonlinear list.
+ */
+ union {
+ struct {
+ struct list_head list;
+ void *parent; /* aligns with prio_tree_node parent */
+ struct vm_area_struct *head;
+ } vm_set;
+
+ struct raw_prio_tree_node prio_tree_node;
+ } shared;
+
+ /*
+ * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
+ * list, after a COW of one of the file pages. A MAP_SHARED vma
+ * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
+ * or brk vma (with NULL file) can only be in an anon_vma list.
*/
- struct list_head shared;
+ struct list_head anon_vma_node; /* Serialized by anon_vma->lock */
+ struct anon_vma *anon_vma; /* Serialized by page_table_lock */
/* Function pointers to deal with this struct. */
struct vm_operations_struct * vm_ops;
units, *not* PAGE_CACHE_SIZE */
struct file * vm_file; /* File we map to (can be NULL). */
void * vm_private_data; /* was vm_pte (shared mem) */
+ unsigned long vm_truncate_count;/* truncate_count or restart_addr */
+
+#ifndef CONFIG_MMU
+ atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */
+#endif
+#ifdef CONFIG_NUMA
+ struct mempolicy *vm_policy; /* NUMA policy for the VMA */
+#endif
};
+/*
+ * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is
+ * disabled, then there's a single shared list of VMAs maintained by the
+ * system, and mm's subscribe to these individually
+ */
+struct vm_list_struct {
+ struct vm_list_struct *next;
+ struct vm_area_struct *vma;
+};
+
+#ifndef CONFIG_MMU
+extern struct rb_root nommu_vma_tree;
+extern struct rw_semaphore nommu_vma_sem;
+
+extern unsigned int kobjsize(const void *objp);
+#endif
+
/*
* vm_flags..
*/
#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) */
-
-/* It makes sense to apply VM_ACCOUNT to this vma. */
-#define VM_MAYACCT(vma) (!!((vma)->vm_flags & VM_HUGETLB))
+#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 */
+#ifdef CONFIG_XEN
+#define VM_FOREIGN 0x04000000 /* Has pages belonging to another VM */
+#endif
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
void (*close)(struct vm_area_struct * area);
struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
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
};
-/* forward declaration; pte_chain is meant to be internal to rmap.c */
-struct pte_chain;
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.
- *
- * Try to keep the most commonly accessed fields in single cache lines
- * here (16 bytes or greater). This ordering should be particularly
- * beneficial on 32-bit processors.
- *
- * The first line is data used in page cache lookup, the second line
- * is used for linear searches (eg. clock algorithm scans).
- *
- * TODO: make this structure smaller, it could be as small as 32 bytes.
*/
struct page {
- page_flags_t flags; /* atomic flags, some possibly
- updated asynchronously */
- atomic_t count; /* Usage count, see below. */
- struct address_space *mapping; /* The inode (or ...) we belong to. */
- pgoff_t index; /* Our offset within mapping. */
- struct list_head lru; /* Pageout list, eg. active_list;
- protected by zone->lru_lock !! */
+ unsigned long 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.
+ */
union {
- struct pte_chain *chain;/* Reverse pte mapping pointer.
- * protected by PG_chainlock */
- pte_addr_t direct;
- } pte;
- unsigned long private; /* Mapping-private opaque data:
- * usually used for buffer_heads
- * if PagePrivate set; used for
- * swp_entry_t if PageSwapCache
+ struct {
+ unsigned long private; /* Mapping-private opaque data:
+ * usually used for buffer_heads
+ * if PagePrivate set; used for
+ * swp_entry_t if PageSwapCache;
+ * indicates order in the buddy
+ * system if PG_buddy is set.
+ */
+ 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.
+ */
+ };
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+ spinlock_t ptl;
+#endif
+ };
+ 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,
#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
* files which need it (119 of them)
* 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.
*/
-#define put_page_testzero(p) \
- ({ \
- BUG_ON(page_count(p) == 0); \
- atomic_dec_and_test(&(p)->count); \
- })
-#define set_page_count(p,v) atomic_set(&(p)->count, v)
-#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)
+/*
+ * Drop a ref, return true if the logical refcount fell to zero (the page has
+ * no users)
+ */
+static inline int put_page_testzero(struct page *page)
{
- if (PageCompound(p))
- p = (struct page *)p->private;
- return atomic_read(&(p)->count);
+ BUG_ON(atomic_read(&page->_count) == 0);
+ return atomic_dec_and_test(&page->_count);
}
-static inline void get_page(struct page *page)
+/*
+ * Try to grab a ref unless the page has a refcount of zero, return false if
+ * that is the case.
+ */
+static inline int get_page_unless_zero(struct page *page)
{
- if (unlikely(PageCompound(page)))
- page = (struct page *)page->private;
- atomic_inc(&page->count);
+ return atomic_inc_not_zero(&page->_count);
}
-void put_page(struct page *page);
-
-#else /* CONFIG_HUGETLB_PAGE */
+extern void FASTCALL(__page_cache_release(struct page *));
-#define page_count(p) atomic_read(&(p)->count)
+static inline int page_count(struct page *page)
+{
+ if (unlikely(PageCompound(page)))
+ page = (struct page *)page_private(page);
+ return atomic_read(&page->_count);
+}
static inline void get_page(struct page *page)
{
- atomic_inc(&page->count);
+ if (unlikely(PageCompound(page)))
+ page = (struct page *)page_private(page);
+ 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
* zeroes, and text pages of executables and shared libraries have
* only one copy in memory, at most, normally.
*
- * For the non-reserved pages, page->count denotes a reference count.
- * page->count == 0 means the page is free.
- * page->count == 1 means the page is used for exactly one purpose
+ * For the non-reserved pages, page_count(page) denotes a reference count.
+ * page_count() == 0 means the page is free. page->lru is then used for
+ * freelist management in the buddy allocator.
+ * page_count() == 1 means the page is used for exactly one purpose
* (e.g. a private data page of one process).
*
* 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
+ * __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.
* page's address_space. Usually, this is the address of a circular
* list of the page's disk buffers.
*
- * For pages belonging to inodes, the page->count is the number of
+ * 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.
*
- * 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).
+ * Instead of keeping dirty/clean pages in per address-space lists, we instead
+ * now tag pages as dirty/under writeback in the radix tree.
*
* 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 zone field is never updated after free_area_init_core()
* sets it, so none of the operations on it need to be atomic.
- * We'll have up to (MAX_NUMNODES * MAX_NR_ZONES) zones total,
- * so we use (MAX_NODES_SHIFT + MAX_ZONES_SHIFT) here to get enough bits.
*/
-#define NODEZONE_SHIFT (sizeof(page_flags_t)*8 - MAX_NODES_SHIFT - MAX_ZONES_SHIFT)
-#define NODEZONE(node, zone) ((node << ZONES_SHIFT) | zone)
+
+
+/*
+ * 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: | NODE | ZONE | ... | FLAGS |
+ * with space for node: | SECTION | NODE | ZONE | ... | FLAGS |
+ * no space for node: | SECTION | ZONE | ... | FLAGS |
+ */
+#ifdef CONFIG_SPARSEMEM
+#define SECTIONS_WIDTH SECTIONS_SHIFT
+#else
+#define SECTIONS_WIDTH 0
+#endif
+
+#define ZONES_WIDTH ZONES_SHIFT
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= FLAGS_RESERVED
+#define NODES_WIDTH NODES_SHIFT
+#else
+#define NODES_WIDTH 0
+#endif
+
+/* Page flags: | [SECTION] | [NODE] | ZONE | ... | 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.
+ */
+#define FLAGS_HAS_NODE (NODES_WIDTH > 0 || NODES_SHIFT == 0)
+
+#ifndef PFN_SECTION_SHIFT
+#define PFN_SECTION_SHIFT 0
+#endif
+
+/*
+ * Define the bit shifts to access each section. For non-existant
+ * sections we define the shift as 0; that plus a 0 mask ensures
+ * the compiler will optimise away reference to them.
+ */
+#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
+#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0))
+#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0))
+
+/* NODE:ZONE or SECTION:ZONE is used to lookup the zone from a page. */
+#if FLAGS_HAS_NODE
+#define ZONETABLE_SHIFT (NODES_SHIFT + ZONES_SHIFT)
+#else
+#define ZONETABLE_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT)
+#endif
+#define ZONETABLE_PGSHIFT ZONES_PGSHIFT
+
+#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
+#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
+#endif
+
+#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
+#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
+#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
+#define ZONETABLE_MASK ((1UL << ZONETABLE_SHIFT) - 1)
static inline unsigned long page_zonenum(struct page *page)
{
- return (page->flags >> NODEZONE_SHIFT) & (~(~0UL << ZONES_SHIFT));
-}
-static inline unsigned long page_to_nid(struct page *page)
-{
- return (page->flags >> (NODEZONE_SHIFT + ZONES_SHIFT));
+ 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 >> NODEZONE_SHIFT];
+ return zone_table[page_zone_id(page)];
+}
+
+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;
+}
+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 nodezone_num)
+static inline void set_page_zone(struct page *page, unsigned long 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 &= ~(~0UL << NODEZONE_SHIFT);
- page->flags |= nodezone_num << NODEZONE_SHIFT;
+ page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
+ page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
+}
+static inline void set_page_section(struct page *page, unsigned long section)
+{
+ page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
+ page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}
+static inline void set_page_links(struct page *page, unsigned long zone,
+ unsigned long node, unsigned long pfn)
+{
+ set_page_zone(page, zone);
+ set_page_node(page, node);
+ set_page_section(page, pfn_to_section_nr(pfn));
+}
+
+/*
+ * Some inline functions in vmstat.h depend on page_zone()
+ */
+#include <linux/vmstat.h>
+
#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
extern struct page *mem_map;
#endif
-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);
}
/*
* On an anonymous page mapped into a user virtual memory area,
- * page->mapping points to its anon_vma, not to a struct address_space.
+ * page->mapping points to its anon_vma, not to a struct address_space;
+ * with the PAGE_MAPPING_ANON bit set to distinguish it.
*
* 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
+
+extern struct address_space swapper_space;
static inline struct address_space *page_mapping(struct page *page)
{
- return PageAnon(page)? NULL: page->mapping;
+ struct address_space *mapping = page->mapping;
+
+ if (unlikely(PageSwapCache(page)))
+ mapping = &swapper_space;
+ else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+ mapping = NULL;
+ return mapping;
+}
+
+static inline int PageAnon(struct page *page)
+{
+ return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
+}
+
+/*
+ * Return the pagecache index of the passed page. Regular pagecache pages
+ * use ->index whereas swapcache pages use ->private
+ */
+static inline pgoff_t page_index(struct page *page)
+{
+ if (unlikely(PageSwapCache(page)))
+ return page_private(page);
+ return page->index;
}
/*
- * Return true if this page is mapped into pagetables. Subtle: test pte.direct
- * rather than pte.chain. Because sometimes pte.direct is 64-bit, and .chain
- * is only 32-bit.
+ * The atomic page->_mapcount, like _count, starts from -1:
+ * so that transitions 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)
+{
+ atomic_set(&(page)->_mapcount, -1);
+}
+
+static inline int page_mapcount(struct page *page)
+{
+ return atomic_read(&(page)->_mapcount) + 1;
+}
+
+/*
+ * Return true if this page is mapped into pagetables.
*/
static inline int page_mapped(struct page *page)
{
- return page->pte.direct != 0;
+ return atomic_read(&(page)->_mapcount) >= 0;
}
/*
* Used to decide whether a process gets delivered SIGBUS or
* just gets major/minor fault counters bumped up.
*/
-#define VM_FAULT_OOM (-1)
-#define VM_FAULT_SIGBUS 0
-#define VM_FAULT_MINOR 1
-#define VM_FAULT_MAJOR 2
+#define VM_FAULT_OOM 0x00
+#define VM_FAULT_SIGBUS 0x01
+#define VM_FAULT_MINOR 0x02
+#define VM_FAULT_MAJOR 0x03
+
+/*
+ * Special case for get_user_pages.
+ * Must be in a distinct bit from the above VM_FAULT_ flags.
+ */
+#define VM_FAULT_WRITE 0x10
#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
extern void show_free_areas(void);
-struct page *shmem_nopage(struct vm_area_struct * vma,
+#ifdef CONFIG_SHMEM
+struct page *shmem_nopage(struct vm_area_struct *vma,
unsigned long address, int *type);
-struct file *shmem_file_setup(char * name, loff_t size, unsigned long flags);
-void shmem_lock(struct file * file, int lock);
+int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new);
+struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
+ unsigned long addr);
+int shmem_lock(struct file *file, int lock, struct user_struct *user);
+#else
+#define shmem_nopage filemap_nopage
+
+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))
+ return 1;
+ if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
+ return 1;
+ return 0;
+}
+extern int user_shm_lock(size_t, struct user_struct *);
+extern void user_shm_unlock(size_t, struct user_struct *);
+
/*
* Parameter block passed down to zap_pte_range in exceptional cases.
*/
struct address_space *check_mapping; /* Check page->mapping if set */
pgoff_t first_index; /* Lowest page->index to unmap */
pgoff_t last_index; /* Highest page->index to unmap */
+ spinlock_t *i_mmap_lock; /* For unmap_mapping_range: */
+ unsigned long truncate_count; /* Compare vm_truncate_count */
};
-void zap_page_range(struct vm_area_struct *vma, unsigned long address,
+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 *);
-int unmap_vmas(struct mmu_gather **tlbp, 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 *);
-void clear_page_tables(struct mmu_gather *tlb, unsigned long first, int nr);
+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);
int zeromap_page_range(struct vm_area_struct *vma, unsigned long from,
}
extern int vmtruncate(struct inode * inode, loff_t offset);
-extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, 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);
+
+#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);
+}
+#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);
-void put_dirty_page(struct task_struct *tsk, struct page *page,
- unsigned long address, pgprot_t prot);
+void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);
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);
int __set_page_dirty_buffers(struct page *page);
int __set_page_dirty_nobuffers(struct page *page);
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);
+extern unsigned long do_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr);
+
/*
* Prototype to add a shrinker callback for ageable caches.
*
* These functions are passed a count `nr_to_scan' and a gfpmask. They should
* scan `nr_to_scan' objects, attempting to free them.
*
- * The callback must the number of objects which remain in the cache.
+ * The callback must return the number of objects which remain in the cache.
*
- * The callback will be passes nr_to_scan == 0 when the VM is querying the
+ * 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 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.
*/
-static inline pmd_t *pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+#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 __pmd_alloc(mm, pgd, address);
- return pmd_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)
+{
+ return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
+ NULL: pmd_offset(pud, address);
+}
+#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, struct page *pmap,
+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 memmap_init_zone(struct page *, unsigned long, int,
- unsigned long, unsigned long);
+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);
+#ifdef CONFIG_NUMA
+extern void setup_per_cpu_pageset(void);
+#else
+static inline void setup_per_cpu_pageset(void) {}
+#endif
+
+/* prio_tree.c */
+void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
+void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
+void vma_prio_tree_remove(struct vm_area_struct *, struct prio_tree_root *);
+struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma,
+ struct prio_tree_iter *iter);
+
+#define vma_prio_tree_foreach(vma, iter, root, begin, end) \
+ for (prio_tree_iter_init(iter, root, begin, end), vma = NULL; \
+ (vma = vma_prio_tree_next(vma, iter)); )
+
+static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
+ struct list_head *list)
+{
+ vma->shared.vm_set.parent = NULL;
+ list_add_tail(&vma->shared.vm_set.list, list);
+}
+
/* mmap.c */
-extern void insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
+extern int __vm_enough_memory(long pages, int cap_sys_admin);
+extern void 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,
+ unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
+ struct mempolicy *);
+extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
+extern int split_vma(struct mm_struct *,
+ struct vm_area_struct *, unsigned long addr, int new_below);
+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, unsigned long pgoff);
+ unsigned long addr, unsigned long len, pgoff_t pgoff);
extern void exit_mmap(struct mm_struct *);
+extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
-extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+extern unsigned long get_unmapped_area_prot(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, int);
+
+
+static inline unsigned long get_unmapped_area(struct file * file, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ return get_unmapped_area_prot(file, addr, len, pgoff, flags, 0);
+}
+
+extern int install_special_mapping(struct mm_struct *mm,
+ unsigned long addr, unsigned long len,
+ unsigned long vm_flags, pgprot_t pgprot,
+ struct page **pages);
extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
extern unsigned long do_brk(unsigned long, unsigned long);
-static inline void
-__vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev)
-{
- prev->vm_next = vma->vm_next;
- rb_erase(&vma->vm_rb, &mm->mm_rb);
- if (mm->mmap_cache == vma)
- mm->mmap_cache = prev;
-}
-
-static inline int
-can_vma_merge(struct vm_area_struct *vma, unsigned long vm_flags)
-{
-#ifdef CONFIG_MMU
- if (!vma->vm_file && vma->vm_flags == vm_flags)
- return 1;
-#endif
- return 0;
-}
-
/* 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 */
-struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
+extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
+extern int filemap_populate(struct vm_area_struct *, unsigned long,
+ unsigned long, pgprot_t, unsigned long, int);
/* mm/page-writeback.c */
int write_one_page(struct page *page, int wait);
/* readahead.c */
#define VM_MAX_READAHEAD 128 /* kbytes */
#define VM_MIN_READAHEAD 16 /* kbytes (includes current page) */
+#define VM_MAX_CACHE_HIT 256 /* max pages in a row in cache before
+ * 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);
-void 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);
-void handle_ra_miss(struct address_space *mapping,
+ 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);
extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
struct vm_area_struct **pprev);
-extern int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
- unsigned long addr, int new_below);
/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
NULL if none. Assume start_addr < end_addr. */
return vma;
}
-extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);
+static inline unsigned long vma_pages(struct vm_area_struct *vma)
+{
+ return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+}
-extern unsigned int nr_used_zone_pages(void);
+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_XEN
+typedef int (*pte_fn_t)(pte_t *pte, struct page *pmd_page, unsigned long addr,
+ void *data);
+extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
+ unsigned long size, pte_fn_t fn, void *data);
+#endif
-extern struct page * vmalloc_to_page(void *addr);
-extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
- int write);
-extern int remap_page_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long to, unsigned long size, pgprot_t prot);
+#ifdef CONFIG_PROC_FS
+void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
+#else
+static inline void vm_stat_account(struct mm_struct *mm,
+ unsigned long flags, struct file *file, long pages)
+{
+}
+#endif /* CONFIG_PROC_FS */
#ifndef CONFIG_DEBUG_PAGEALLOC
static inline void
kernel_map_pages(struct page *page, int numpages, int enable)
{
+ if (!PageHighMem(page) && !enable)
+ debug_check_no_locks_freed(page_address(page),
+ numpages * PAGE_SIZE);
}
#endif
-#ifndef CONFIG_ARCH_GATE_AREA
extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
+#ifdef __HAVE_ARCH_GATE_AREA
+int in_gate_area_no_task(unsigned long addr);
int in_gate_area(struct task_struct *task, unsigned long addr);
+#else
+int in_gate_area_no_task(unsigned long addr);
+#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
+const char *arch_vma_name(struct vm_area_struct *vma);
+
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
git://git.onelab.eu / linux-2.6.git / blobdiff