path: root/include/linux/mm.h

#ifndef _LINUX_MM_H
#define _LINUX_MM_H

#include <linux/errno.h>

#ifdef __KERNEL__

#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;
struct user_struct;

#ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
#endif

extern unsigned long num_physpages;
extern void * high_memory;
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>

#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))

/*
 * Linux kernel virtual memory manager primitives.
 * The idea being to have a "virtual" mm in the same way
 * we have a virtual fs - giving a cleaner interface to the
 * mm details, and allowing different kinds of memory mappings
 * (from shared memory to executable loading to arbitrary
 * mmap() functions).
 */

/*
 * This struct defines a memory VMM memory area. There is one of these
 * 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).
 */
struct vm_area_struct {
	struct mm_struct * vm_mm;	/* The address space we belong to. */
	unsigned long vm_start;		/* Our start address within vm_mm. */
	unsigned long vm_end;		/* The first byte after our end address
					   within vm_mm. */

	/* linked list of VM areas per task, sorted by address */
	struct vm_area_struct *vm_next;

	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
	unsigned long vm_flags;		/* Flags, listed below. */

	struct rb_node vm_rb;

	/*
	 * For areas with an address space and backing store,
	 * 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 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;

	/* Information about our backing store: */
	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
					   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
};

extern struct kmem_cache *vm_area_cachep;

/*
 * 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_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#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_MAYSHARE	0x00000080

#define VM_GROWSDOWN	0x00000100	/* general info on the segment */
#define VM_GROWSUP	0x00000200
#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_LOCKED	0x00002000
#define VM_IO           0x00004000	/* Memory mapped I/O or similar */

					/* Used by sys_madvise() */
#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */

#define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
#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_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 */
#define VM_ALWAYSDUMP	0x04000000	/* Always include in core dumps */

#define VM_CAN_INVALIDATE 0x08000000	/* The mapping may be invalidated,
					 * eg. truncate or invalidate_inode_*.
					 * In this case, do_no_page must
					 * return with the page locked.
					 */

#ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif

#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK_FLAGS	(VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#else
#define VM_STACK_FLAGS	(VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#endif

#define VM_READHINTMASK			(VM_SEQ_READ | VM_RAND_READ)
#define VM_ClearReadHint(v)		(v)->vm_flags &= ~VM_READHINTMASK
#define VM_NormalReadHint(v)		(!((v)->vm_flags & VM_READHINTMASK))
#define VM_SequentialReadHint(v)	((v)->vm_flags & VM_SEQ_READ)
#define VM_RandomReadHint(v)		((v)->vm_flags & VM_RAND_READ)

/*
 * mapping from the currently active vm_flags protection bits (the
 * low four bits) to a page protection mask..
 */
extern pgprot_t protection_map[16];


/*
 * These are the virtual MM functions - opening of an area, closing and
 * unmapping it (needed to keep files on disk up-to-date etc), pointer
 * to the functions called when a no-page or a wp-page exception occurs. 
 */
struct vm_operations_struct {
	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;

#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)
 */
#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.
 *
 * What counts for a page usage:
 * - cache mapping   (page->mapping)
 * - private data    (page->private)
 * - page mapped in a task's page tables, each mapping
 *   is counted separately
 *
 * 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.
 */

/*
 * Drop a ref, return true if the refcount fell to zero (the page has no users)
 */
static inline int put_page_testzero(struct page *page)
{
	VM_BUG_ON(atomic_read(&page->_count) == 0);
	return atomic_dec_and_test(&page->_count);
}

/*
 * 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)
{
	VM_BUG_ON(PageCompound(page));
	return atomic_inc_not_zero(&page->_count);
}

static inline struct page *compound_head(struct page *page)
{
	if (unlikely(PageTail(page)))
		return page->first_page;
	return page;
}

static inline int page_count(struct page *page)
{
	return atomic_read(&compound_head(page)->_count);
}

static inline void get_page(struct page *page)
{
	page = compound_head(page);
	VM_BUG_ON(atomic_read(&page->_count) == 0);
	atomic_inc(&page->_count);
}

static inline struct page *virt_to_head_page(const void *x)
{
	struct page *page = virt_to_page(x);
	return compound_head(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)
{
	atomic_set(&page->_count, 1);
}

void put_page(struct page *page);
void put_pages_list(struct list_head *pages);

void split_page(struct page *page, unsigned int order);

/*
 * Compound pages have a destructor function.  Provide a
 * prototype for that function and accessor functions.
 * These are _only_ valid on the head of a PG_compound page.
 */
typedef void compound_page_dtor(struct page *);

static inline void set_compound_page_dtor(struct page *page,
						compound_page_dtor *dtor)
{
	page[1].lru.next = (void *)dtor;
}

static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
{
	return (compound_page_dtor *)page[1].lru.next;
}

static inline int compound_order(struct page *page)
{
	if (!PageHead(page))
		return 0;
	return (unsigned long)page[1].lru.prev;
}

static inline void set_compound_order(struct page *page, unsigned long order)
{
	page[1].lru.prev = (void *)order;
}

/*
 * Multiple processes may "see" the same page. E.g. for untouched
 * mappings of /dev/null, all processes see the same page full of
 * 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(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() > 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 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 "pagecache pages") are completely
 * managed by the Linux memory manager: I/O, buffers, swapping etc.
 * The following discussion applies only to them.
 *
 * 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 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.
 *
 * 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.
 *
 * 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.
 *
 * 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 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 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.
 */

/*
 * The zone field is never updated after free_area_init_core()
 * sets it, so none of the operations on it need to be atomic.
 */


/*
 * page->flags layout:
 *
 * There are three possibilities for how page->flags get
 * laid out.  The first is for the normal case, without
 * sparsemem.  The second is for sparsemem when there is
 * plenty of space for node and section.  The last is when
 * we have run out of space and have to fall back to an
 * alternate (slower) way of determining the node.
 *
 *        No sparsemem: |       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.
 */
#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
#define NODE_NOT_IN_PAGE_FLAGS
#endif

#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 ID a zone for the buddy allcator */
#ifdef NODE_NOT_IN_PAGEFLAGS
#define ZONEID_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT)
#define ZONEID_PGOFF		((SECTIONS_PGOFF < ZONES_PGOFF)? \
						SECTIONS_PGOFF : ZONES_PGOFF)
#else
#define ZONEID_SHIFT		(NODES_SHIFT + ZONES_SHIFT)
#define ZONEID_PGOFF		((NODES_PGOFF < ZONES_PGOFF)? \
						NODES_PGOFF : ZONES_PGOFF)
#endif

#define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))

#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 ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)

static inline enum zone_type page_zonenum(struct page *page)
{
	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}

/*
 * The identification function is only used by the buddy allocator for
 * determining if two pages could be buddies. We are not really
 * identifying a zone since we could be using a the section number
 * id if we have not node id available in page flags.
 * We guarantee only that it will return the same value for two
 * combinable pages in a zone.
 */
static inline int page_zone_id(struct page *page)
{
	return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
}

static inline int zone_to_nid(struct zone *zone)
{
#ifdef CONFIG_NUMA
	return zone->node;
#else
	return 0;
#endif
}

#ifdef NODE_NOT_IN_PAGE_FLAGS
extern int page_to_nid(struct page *page);
#else
static inline int page_to_nid(struct page *page)
{
	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
}
#endif

static inline struct zone *page_zone(struct page *page)
{
	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(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, 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 |= (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, enum zone_type 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>

static __always_inline void *lowmem_page_address(struct page *page)
{
	return __va(page_to_pfn(page) << PAGE_SHIFT);
}