mm.h

来自「Linux Kernel 2.6.9 for OMAP1710」· C头文件 代码 · 共 799 行 · 第 1/2 页

#ifndef _LINUX_MM_H
#define _LINUX_MM_H

#include <linux/sched.h>
#include <linux/errno.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>

struct mempolicy;
struct anon_vma;

#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 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

/*
 * 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 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) */

#ifdef CONFIG_NUMA
	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
#endif
};

/*
 * vm_flags..
 */
#define VM_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008

#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_SHM		0x00000400	/* shared memory area, don't swap out */
#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	/* Don't unmap it from swap_out */
#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) */

#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);
	int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
#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);
#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
					 */
	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 */
};

/*
 * FIXME: take this include out, include page-flags.h in
 * files which need it (119 of them)
 */
#include <linux/page-flags.h>

/*
 * 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.
 *
 * 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)
 */
#define put_page_testzero(p)				\
	({						\
		BUG_ON(page_count(p) == 0);		\
		atomic_add_negative(-1, &(p)->_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
 */
#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)
{
	if (PageCompound(p))
		p = (struct page *)p->private;
	return atomic_read(&(p)->_count) + 1;
}

static inline void get_page(struct page *page)
{
	if (unlikely(PageCompound(page)))
		page = (struct page *)page->private;
	atomic_inc(&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)
{
	atomic_inc(&page->_count);
}

static inline void put_page(struct page *page)
{
	if (!PageReserved(page) && put_page_testzero(page))
		__page_cache_release(page);
}

#endif		/* CONFIG_HUGETLB_PAGE */

/*
 * 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_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
 * 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.
 *
 * The other pages (we may call them "process 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 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.
 *
 * 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).
 *
 * There is also a per-mapping radix tree mapping index to the page
 * in memory if present. The tree is rooted at mapping->root.  
 *
 * All process pages can do 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.
 */

/*
 * 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)

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));
}

struct zone;
extern struct zone *zone_table[];

static inline struct zone *page_zone(struct page *page)
{
	return zone_table[page->flags >> NODEZONE_SHIFT];
}

static inline void set_page_zone(struct page *page, unsigned long nodezone_num)
{