mm.h

讲述linux的初始化过程

 * 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->inode is the pointer to the inode, and page->offset is the
 * file offset of the page (not necessarily a multiple of PAGE_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.
 *
 * All pages belonging to an inode make up a doubly linked list
 * inode->i_pages, using the fields page->next and page->prev. (These
 * fields are also used for freelist management when page->count==0.)
 * There is also a hash table mapping (inode,offset) 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->wait 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 (inode,offset) hash table.
 *
 * 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 guarentees that this bit is cleared for a page when it first
 * is entered into the page cache.
 */

extern mem_map_t * mem_map;

/*
 * There is only one page-allocator function, and two main namespaces to
 * it. The alloc_page*() variants return 'struct page *' and as such
 * can allocate highmem pages, the *get*page*() variants return
 * virtual kernel addresses to the allocated page(s).
 */
extern struct page * FASTCALL(__alloc_pages(zonelist_t *zonelist, unsigned long order));
extern struct page * alloc_pages_node(int nid, int gfp_mask, unsigned long order);

#ifndef CONFIG_DISCONTIGMEM
static inline struct page * alloc_pages(int gfp_mask, unsigned long order)
{
	/*
	 * Gets optimized away by the compiler.
	 */
	if (order >= MAX_ORDER)
		return NULL;
	return __alloc_pages(contig_page_data.node_zonelists+(gfp_mask), order);
}
#else /* !CONFIG_DISCONTIGMEM */
extern struct page * alloc_pages(int gfp_mask, unsigned long order);
#endif /* !CONFIG_DISCONTIGMEM */

#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)

extern unsigned long FASTCALL(__get_free_pages(int gfp_mask, unsigned long order));
extern unsigned long FASTCALL(get_zeroed_page(int gfp_mask));

#define __get_free_page(gfp_mask) \
		__get_free_pages((gfp_mask),0)

#define __get_dma_pages(gfp_mask, order) \
		__get_free_pages((gfp_mask) | GFP_DMA,(order))

/*
 * The old interface name will be removed in 2.5:
 */
#define get_free_page get_zeroed_page

/*
 * There is only one 'core' page-freeing function.
 */
extern void FASTCALL(__free_pages(struct page *page, unsigned long order));
extern void FASTCALL(free_pages(unsigned long addr, unsigned long order));

#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr),0)

extern void show_free_areas(void);
extern void show_free_areas_node(pg_data_t *pgdat);

extern void clear_page_tables(struct mm_struct *, unsigned long, int);

struct page * shmem_nopage(struct vm_area_struct * vma, unsigned long address, int no_share);
struct file *shmem_file_setup(char * name, loff_t size);
extern int shmem_zero_setup(struct vm_area_struct *);

extern void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size);
extern int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma);
extern int remap_page_range(unsigned long from, unsigned long to, unsigned long size, pgprot_t prot);
extern int zeromap_page_range(unsigned long from, unsigned long size, pgprot_t prot);

extern void vmtruncate(struct inode * inode, loff_t offset);
extern int handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
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);
extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char *dst, int len);
extern int ptrace_writedata(struct task_struct *tsk, char * src, unsigned long dst, int len);

extern int pgt_cache_water[2];
extern int check_pgt_cache(void);

extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, pg_data_t *pgdat, struct page *pmap,
	unsigned long * zones_size, unsigned long zone_start_paddr, 
	unsigned long *zholes_size);
extern void mem_init(void);
extern void show_mem(void);
extern void si_meminfo(struct sysinfo * val);
extern void swapin_readahead(swp_entry_t);

/* mmap.c */
extern void lock_vma_mappings(struct vm_area_struct *);
extern void unlock_vma_mappings(struct vm_area_struct *);
extern void insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
extern void __insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
extern void build_mmap_avl(struct mm_struct *);
extern void exit_mmap(struct mm_struct *);
extern unsigned long get_unmapped_area(unsigned long, unsigned long);

extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long pgoff);

static inline unsigned long do_mmap(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long offset)
{
	unsigned long ret = -EINVAL;
	if ((offset + PAGE_ALIGN(len)) < offset)
		goto out;
	if (!(offset & ~PAGE_MASK))
		ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
out:
	return ret;
}

extern int do_munmap(struct mm_struct *, unsigned long, size_t);

extern unsigned long do_brk(unsigned long, unsigned long);

struct zone_t;
/* filemap.c */
extern void remove_inode_page(struct page *);
extern unsigned long page_unuse(struct page *);
extern void truncate_inode_pages(struct address_space *, loff_t);

/* generic vm_area_ops exported for stackable file systems */
extern int filemap_sync(struct vm_area_struct *, unsigned long,	size_t, unsigned int);
extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int);

/*
 * GFP bitmasks..
 */
#define __GFP_WAIT	0x01
#define __GFP_HIGH	0x02
#define __GFP_IO	0x04
#define __GFP_DMA	0x08
#ifdef CONFIG_HIGHMEM
#define __GFP_HIGHMEM	0x10
#else
#define __GFP_HIGHMEM	0x0 /* noop */
#endif


#define GFP_BUFFER	(__GFP_HIGH | __GFP_WAIT)
#define GFP_ATOMIC	(__GFP_HIGH)
#define GFP_USER	(             __GFP_WAIT | __GFP_IO)
#define GFP_HIGHUSER	(             __GFP_WAIT | __GFP_IO | __GFP_HIGHMEM)
#define GFP_KERNEL	(__GFP_HIGH | __GFP_WAIT | __GFP_IO)
#define GFP_NFS		(__GFP_HIGH | __GFP_WAIT | __GFP_IO)
#define GFP_KSWAPD	(                          __GFP_IO)

/* Flag - indicates that the buffer will be suitable for DMA.  Ignored on some
   platforms, used as appropriate on others */

#define GFP_DMA		__GFP_DMA

/* Flag - indicates that the buffer can be taken from high memory which is not
   permanently mapped by the kernel */

#define GFP_HIGHMEM	__GFP_HIGHMEM

/* vma is the first one with  address < vma->vm_end,
 * and even  address < vma->vm_start. Have to extend vma. */
static inline int expand_stack(struct vm_area_struct * vma, unsigned long address)
{
	unsigned long grow;

	address &= PAGE_MASK;
	grow = (vma->vm_start - address) >> PAGE_SHIFT;
	if (vma->vm_end - address > current->rlim[RLIMIT_STACK].rlim_cur ||
	    ((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) > current->rlim[RLIMIT_AS].rlim_cur)
		return -ENOMEM;
	vma->vm_start = address;
	vma->vm_pgoff -= grow;
	vma->vm_mm->total_vm += grow;
	if (vma->vm_flags & VM_LOCKED)
		vma->vm_mm->locked_vm += grow;
	return 0;
}

/* 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);

/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
   NULL if none.  Assume start_addr < end_addr. */
static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr)
{
	struct vm_area_struct * vma = find_vma(mm,start_addr);

	if (vma && end_addr <= vma->vm_start)
		vma = NULL;
	return vma;
}

extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);

#define buffer_under_min()	(atomic_read(&buffermem_pages) * 100 < \
				buffer_mem.min_percent * num_physpages)
#define pgcache_under_min()	(atomic_read(&page_cache_size) * 100 < \
				page_cache.min_percent * num_physpages)

#endif /* __KERNEL__ */

#endif