mm.h

linux得一些常用命令,以及linux环境下的c编程

#ifndef _LINUX_MM_H
#define _LINUX_MM_H

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

#ifdef __KERNEL__

#include <linux/config.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/swap.h>
#include <linux/rbtree.h>

extern unsigned long max_mapnr;
extern unsigned long num_physpages;
extern unsigned long num_mappedpages;
extern void * high_memory;
extern int page_cluster;
/* The inactive_clean lists are per zone. */
extern struct list_head active_list;
extern struct list_head inactive_list;

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/atomic.h>
#include <asm/mmu.h>

/*
 * 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. */

	rb_node_t vm_rb;

	/*
	 * 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.
	 */
	struct vm_area_struct *vm_next_share;
	struct vm_area_struct **vm_pprev_share;

	/* 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). */
	unsigned long vm_raend;		/* XXX: put full readahead info here. */
	void * vm_private_data;		/* was vm_pte (shared mem) */
};

/*
 * 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_XIP		0x00200000

#define VM_STACK_FLAGS	(0x00000177 | VM_ACCOUNT)

#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)

/* read ahead limits */
extern int vm_min_readahead;
extern int vm_max_readahead;

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

#define ZPR_MAX_BYTES 256*PAGE_SIZE
#define ZPR_NORMAL 0 /* perform zap_page_range request in one walk */
#define ZPR_PARTITION 1 /* partition into a series of smaller operations */

/*
 * 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 unused);
};

/*
 * 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.
 */
typedef struct page {
	struct list_head list;		/* ->mapping has some page lists. */
	struct address_space *mapping;	/* The inode (or ...) we belong to. */
	unsigned long index;		/* Our offset within mapping. */
	struct page *next_hash;		/* Next page sharing our hash bucket in
					   the pagecache hash table. */
	atomic_t count;			/* Usage count, see below. */
	unsigned long flags;		/* atomic flags, some possibly
					   updated asynchronously */
	struct list_head lru;		/* Pageout list, eg. active_list;
					   protected by pagemap_lru_lock !! */
	struct page **pprev_hash;	/* Complement to *next_hash. */
	struct buffer_head * buffers;	/* Buffer maps us to a disk block. */

	/*
	 * 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(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
	void *virtual;			/* Kernel virtual address (NULL if
					   not kmapped, ie. highmem) */
#endif /* CONFIG_HIGMEM || WANT_PAGE_VIRTUAL */
} mem_map_t;

/*
 * Methods to modify the page usage count.
 *
 * What counts for a page usage:
 * - cache mapping   (page->mapping)
 * - disk mapping    (page->buffers)
 * - 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.
 */
#define get_page(p)		atomic_inc(&(p)->count)
#define put_page(p)		__free_page(p)
#define put_page_testzero(p) 	atomic_dec_and_test(&(p)->count)
#define page_count(p)		atomic_read(&(p)->count)
#define set_page_count(p,v) 	atomic_set(&(p)->count, v)

/*
 * Various page->flags bits:
 *
 * PG_reserved is set for special pages, which can never be swapped
 * out. Some of them might not even exist (eg empty_bad_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 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 may have buffers allocated to it. In this case,
 * page->buffers is a circular list of these buffer heads. Else,
 * page->buffers == NULL.
 *
 * For pages belonging to inodes, the page->count is the number of
 * attaches, plus 1 if buffers are allocated to the page, 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 hash table mapping (mapping,index) to the page
 * in memory if present. The lists for this hash table use the fields
 * page->next_hash and page->pprev_hash.
 *
 * 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.
 * During disk I/O, PG_locked is used. This bit is set before I/O
 * and reset when I/O completes. page_waitqueue(page) is a wait queue of all
 * tasks waiting for the I/O on this page to complete.
 * PG_uptodate tells whether the page's contents is valid.
 * When a read completes, the page becomes uptodate, unless a disk I/O
 * error happened.
 *
 * For choosing which pages to swap out, inode pages carry a
 * PG_referenced bit, which is set any time the system accesses
 * that page through the (mapping,index) hash table. This referenced
 * bit, together with the referenced bit in the page tables, is used
 * to manipulate page->age and move the page across the active,
 * inactive_dirty and inactive_clean lists.
 *
 * Note that the referenced bit, the page->lru list_head and the
 * active, inactive_dirty and inactive_clean lists are protected by
 * the pagemap_lru_lock, and *NOT* by the usual PG_locked bit!
 *
 * PG_skip is used on sparc/sparc64 architectures to "skip" certain
 * parts of the address space.
 *
 * PG_error is set to indicate that an I/O error occurred on this page.
 *
 * PG_arch_1 is an architecture specific page state bit.  The generic
 * code guarantees that this bit is cleared for a page when it first
 * is entered into the page cache.
 *
 * PG_highmem pages are not permanently mapped into the kernel virtual
 * address space, they need to be kmapped separately for doing IO on
 * the pages. The struct page (these bits with information) are always
 * mapped into kernel address space...
 */
#define PG_locked		 0	/* Page is locked. Don't touch. */
#define PG_error		 1
#define PG_referenced		 2
#define PG_uptodate		 3
#define PG_dirty		 4
#define PG_unused		 5
#define PG_lru			 6
#define PG_active		 7
#define PG_slab			 8
#define PG_skip			10
#define PG_highmem		11
#define PG_checked		12	/* kill me in 2.5.<early>. */
#define PG_arch_1		13
#define PG_reserved		14
#define PG_launder		15	/* written out by VM pressure.. */

/* Make it prettier to test the above... */
#define UnlockPage(page)	unlock_page(page)
#define Page_Uptodate(page)	test_bit(PG_uptodate, &(page)->flags)
#define SetPageUptodate(page)	set_bit(PG_uptodate, &(page)->flags)
#define ClearPageUptodate(page)	clear_bit(PG_uptodate, &(page)->flags)
#define PageDirty(page)		test_bit(PG_dirty, &(page)->flags)
#define SetPageDirty(page)	set_bit(PG_dirty, &(page)->flags)
#define ClearPageDirty(page)	clear_bit(PG_dirty, &(page)->flags)
#define PageLocked(page)	test_bit(PG_locked, &(page)->flags)
#define LockPage(page)		set_bit(PG_locked, &(page)->flags)
#define TryLockPage(page)	test_and_set_bit(PG_locked, &(page)->flags)
#define PageChecked(page)	test_bit(PG_checked, &(page)->flags)
#define SetPageChecked(page)	set_bit(PG_checked, &(page)->flags)
#define PageLaunder(page)	test_bit(PG_launder, &(page)->flags)
#define SetPageLaunder(page)	set_bit(PG_launder, &(page)->flags)
#define ClearPageLaunder(page)	clear_bit(PG_launder, &(page)->flags)
#define DelallocPage(page)	((page)->buffers && test_bit(BH_Delay, &(page)->buffers->b_state))

/*
 * The zone field is never updated after free_area_init_core()
 * sets it, so none of the operations on it need to be atomic.
 */
#define NODE_SHIFT 4
#define ZONE_SHIFT (BITS_PER_LONG - 8)