fs.h

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

#ifndef _LINUX_FS_H
#define _LINUX_FS_H

/*
 * This file has definitions for some important file table
 * structures etc.
 */

#include <linux/config.h>
#include <linux/linkage.h>
#include <linux/limits.h>
#include <linux/wait.h>
#include <linux/types.h>
#include <linux/vfs.h>
#include <linux/net.h>
#include <linux/kdev_t.h>
#include <linux/ioctl.h>
#include <linux/list.h>
#include <linux/dcache.h>
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/stddef.h>
#include <linux/string.h>

#include <asm/atomic.h>
#include <asm/bitops.h>

struct poll_table_struct;


/*
 * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
 * the file limit at runtime and only root can increase the per-process
 * nr_file rlimit, so it's safe to set up a ridiculously high absolute
 * upper limit on files-per-process.
 *
 * Some programs (notably those using select()) may have to be 
 * recompiled to take full advantage of the new limits..  
 */

/* Fixed constants first: */
#undef NR_OPEN
#define NR_OPEN (1024*1024)	/* Absolute upper limit on fd num */
#define INR_OPEN 1024		/* Initial setting for nfile rlimits */

#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)

/* And dynamically-tunable limits and defaults: */
struct files_stat_struct {
	int nr_files;		/* read only */
	int nr_free_files;	/* read only */
	int max_files;		/* tunable */
};
extern struct files_stat_struct files_stat;
extern int max_super_blocks, nr_super_blocks;
extern int leases_enable, dir_notify_enable, lease_break_time;

#define NR_FILE  8192	/* this can well be larger on a larger system */
#define NR_RESERVED_FILES 10 /* reserved for root */
#define NR_SUPER 256

#define MAY_EXEC 1
#define MAY_WRITE 2
#define MAY_READ 4

#define FMODE_READ 1
#define FMODE_WRITE 2

#define READ 0
#define WRITE 1
#define READA 2		/* read-ahead  - don't block if no resources */
#define SPECIAL 4	/* For non-blockdevice requests in request queue */

#define SEL_IN		1
#define SEL_OUT		2
#define SEL_EX		4

/* public flags for file_system_type */
#define FS_REQUIRES_DEV 1 
#define FS_NO_DCACHE	2 /* Only dcache the necessary things. */
#define FS_NO_PRELIM	4 /* prevent preloading of dentries, even if
			   * FS_NO_DCACHE is not set.
			   */
#define FS_SINGLE	8 /*
			   * Filesystem that can have only one superblock;
			   * kernel-wide vfsmnt is placed in ->kern_mnt by
			   * kern_mount() which must be called _after_
			   * register_filesystem().
			   */
#define FS_NOMOUNT	16 /* Never mount from userland */
#define FS_LITTER	32 /* Keeps the tree in dcache */
#define FS_ODD_RENAME	32768	/* Temporary stuff; will go away as soon
				  * as nfs_rename() will be cleaned up
				  */
/*
 * These are the fs-independent mount-flags: up to 32 flags are supported
 */
#define MS_RDONLY	 1	/* Mount read-only */
#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
#define MS_NODEV	 4	/* Disallow access to device special files */
#define MS_NOEXEC	 8	/* Disallow program execution */
#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
#define MS_NOATIME	1024	/* Do not update access times. */
#define MS_NODIRATIME	2048	/* Do not update directory access times */
#define MS_BIND		4096

/*
 * Flags that can be altered by MS_REMOUNT
 */
#define MS_RMT_MASK	(MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|\
			MS_SYNCHRONOUS|MS_MANDLOCK|MS_NOATIME|MS_NODIRATIME)

/*
 * Magic mount flag number. Has to be or-ed to the flag values.
 */
#define MS_MGC_VAL 0xC0ED0000	/* magic flag number to indicate "new" flags */
#define MS_MGC_MSK 0xffff0000	/* magic flag number mask */

/* Inode flags - they have nothing to superblock flags now */

#define S_SYNC		1	/* Writes are synced at once */
#define S_NOATIME	2	/* Do not update access times */
#define S_QUOTA		4	/* Quota initialized for file */
#define S_APPEND	8	/* Append-only file */
#define S_IMMUTABLE	16	/* Immutable file */
#define S_DEAD		32	/* removed, but still open directory */

/*
 * Note that nosuid etc flags are inode-specific: setting some file-system
 * flags just means all the inodes inherit those flags by default. It might be
 * possible to override it selectively if you really wanted to with some
 * ioctl() that is not currently implemented.
 *
 * Exception: MS_RDONLY is always applied to the entire file system.
 *
 * Unfortunately, it is possible to change a filesystems flags with it mounted
 * with files in use.  This means that all of the inodes will not have their
 * i_flags updated.  Hence, i_flags no longer inherit the superblock mount
 * flags, so these have to be checked separately. -- [e-mail]
 */
#define __IS_FLG(inode,flg) ((inode)->i_sb->s_flags & (flg))

#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
#define IS_NOSUID(inode)	__IS_FLG(inode, MS_NOSUID)
#define IS_NODEV(inode)		__IS_FLG(inode, MS_NODEV)
#define IS_NOEXEC(inode)	__IS_FLG(inode, MS_NOEXEC)
#define IS_SYNC(inode)		(__IS_FLG(inode, MS_SYNCHRONOUS) || ((inode)->i_flags & S_SYNC))
#define IS_MANDLOCK(inode)	__IS_FLG(inode, MS_MANDLOCK)

#define IS_QUOTAINIT(inode)	((inode)->i_flags & S_QUOTA)
#define IS_APPEND(inode)	((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode)	((inode)->i_flags & S_IMMUTABLE)
#define IS_NOATIME(inode)	(__IS_FLG(inode, MS_NOATIME) || ((inode)->i_flags & S_NOATIME))
#define IS_NODIRATIME(inode)	__IS_FLG(inode, MS_NODIRATIME)

#define IS_DEADDIR(inode)	((inode)->i_flags & S_DEAD)

/* the read-only stuff doesn't really belong here, but any other place is
   probably as bad and I don't want to create yet another include file. */

#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
#define BLKGETSIZE _IO(0x12,96)	/* return device size */
#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
#define BLKRASET   _IO(0x12,98)	/* Set read ahead for block device */
#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
#if 0
#define BLKPG      _IO(0x12,105)/* See blkpg.h */
#define BLKELVGET  _IOR(0x12,106,sizeof(blkelv_ioctl_arg_t))/* elevator get */
#define BLKELVSET  _IOW(0x12,107,sizeof(blkelv_ioctl_arg_t))/* elevator set */
/* This was here just to show that the number is taken -
   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
#endif


#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
#define FIBMAP	   _IO(0x00,1)	/* bmap access */
#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */

#ifdef __KERNEL__

#include <asm/semaphore.h>
#include <asm/byteorder.h>

extern void update_atime (struct inode *);
#define UPDATE_ATIME(inode) update_atime (inode)

extern void buffer_init(unsigned long);
extern void inode_init(unsigned long);

/* bh state bits */
#define BH_Uptodate	0	/* 1 if the buffer contains valid data */
#define BH_Dirty	1	/* 1 if the buffer is dirty */
#define BH_Lock		2	/* 1 if the buffer is locked */
#define BH_Req		3	/* 0 if the buffer has been invalidated */
#define BH_Mapped	4	/* 1 if the buffer has a disk mapping */
#define BH_New		5	/* 1 if the buffer is new and not yet written out */
#define BH_Protected	6	/* 1 if the buffer is protected */

/*
 * Try to keep the most commonly used fields in single cache lines (16
 * bytes) to improve performance.  This ordering should be
 * particularly beneficial on 32-bit processors.
 * 
 * We use the first 16 bytes for the data which is used in searches
 * over the block hash lists (ie. getblk() and friends).
 * 
 * The second 16 bytes we use for lru buffer scans, as used by
 * sync_buffers() and refill_freelist().  -- sct
 */
struct buffer_head {
	/* First cache line: */
	struct buffer_head *b_next;	/* Hash queue list */
	unsigned long b_blocknr;	/* block number */
	unsigned short b_size;		/* block size */
	unsigned short b_list;		/* List that this buffer appears */
	kdev_t b_dev;			/* device (B_FREE = free) */

	atomic_t b_count;		/* users using this block */
	kdev_t b_rdev;			/* Real device */
	unsigned long b_state;		/* buffer state bitmap (see above) */
	unsigned long b_flushtime;	/* Time when (dirty) buffer should be written */

	struct buffer_head *b_next_free;/* lru/free list linkage */
	struct buffer_head *b_prev_free;/* doubly linked list of buffers */
	struct buffer_head *b_this_page;/* circular list of buffers in one page */
	struct buffer_head *b_reqnext;	/* request queue */

	struct buffer_head **b_pprev;	/* doubly linked list of hash-queue */
	char * b_data;			/* pointer to data block (512 byte) */
	struct page *b_page;		/* the page this bh is mapped to */
	void (*b_end_io)(struct buffer_head *bh, int uptodate); /* I/O completion */
 	void *b_private;		/* reserved for b_end_io */

	unsigned long b_rsector;	/* Real buffer location on disk */
	wait_queue_head_t b_wait;

	struct inode *	     b_inode;
	struct list_head     b_inode_buffers;	/* doubly linked list of inode dirty buffers */
};

typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate);
void init_buffer(struct buffer_head *, bh_end_io_t *, void *);

#define __buffer_state(bh, state)	(((bh)->b_state & (1UL << BH_##state)) != 0)

#define buffer_uptodate(bh)	__buffer_state(bh,Uptodate)
#define buffer_dirty(bh)	__buffer_state(bh,Dirty)
#define buffer_locked(bh)	__buffer_state(bh,Lock)
#define buffer_req(bh)		__buffer_state(bh,Req)
#define buffer_mapped(bh)	__buffer_state(bh,Mapped)
#define buffer_new(bh)		__buffer_state(bh,New)
#define buffer_protected(bh)	__buffer_state(bh,Protected)

#define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)

extern void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset);

#define touch_buffer(bh)	SetPageReferenced(bh->b_page)


#include <linux/pipe_fs_i.h>
#include <linux/minix_fs_i.h>
#include <linux/ext2_fs_i.h>
#include <linux/hpfs_fs_i.h>
#include <linux/ntfs_fs_i.h>
#include <linux/msdos_fs_i.h>
#include <linux/umsdos_fs_i.h>
#include <linux/iso_fs_i.h>
#include <linux/nfs_fs_i.h>
#include <linux/sysv_fs_i.h>
#include <linux/affs_fs_i.h>
#include <linux/ufs_fs_i.h>
#include <linux/efs_fs_i.h>
#include <linux/coda_fs_i.h>
#include <linux/romfs_fs_i.h>
#include <linux/shmem_fs.h>
#include <linux/smb_fs_i.h>
#include <linux/hfs_fs_i.h>
#include <linux/adfs_fs_i.h>
#include <linux/qnx4_fs_i.h>
#include <linux/bfs_fs_i.h>
#include <linux/udf_fs_i.h>
#include <linux/ncp_fs_i.h>
#include <linux/proc_fs_i.h>
#include <linux/usbdev_fs_i.h>

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
#define ATTR_MODE	1
#define ATTR_UID	2
#define ATTR_GID	4
#define ATTR_SIZE	8
#define ATTR_ATIME	16
#define ATTR_MTIME	32
#define ATTR_CTIME	64
#define ATTR_ATIME_SET	128
#define ATTR_MTIME_SET	256
#define ATTR_FORCE	512	/* Not a change, but a change it */
#define ATTR_ATTR_FLAG	1024

/*
 * This is the Inode Attributes structure, used for notify_change().  It
 * uses the above definitions as flags, to know which values have changed.
 * Also, in this manner, a Filesystem can look at only the values it cares
 * about.  Basically, these are the attributes that the VFS layer can
 * request to change from the FS layer.
 *
 * Derek Atkins <[e-mail]> 94-10-20
 */
struct iattr {
	unsigned int	ia_valid;
	umode_t		ia_mode;
	uid_t		ia_uid;
	gid_t		ia_gid;
	loff_t		ia_size;
	time_t		ia_atime;
	time_t		ia_mtime;
	time_t		ia_ctime;
	unsigned int	ia_attr_flags;
};

/*
 * This is the inode attributes flag definitions
 */
#define ATTR_FLAG_SYNCRONOUS	1 	/* Syncronous write */
#define ATTR_FLAG_NOATIME	2 	/* Don't update atime */
#define ATTR_FLAG_APPEND	4 	/* Append-only file */
#define ATTR_FLAG_IMMUTABLE	8 	/* Immutable file */
#define ATTR_FLAG_NODIRATIME	16 	/* Don't update atime for directory */

/*
 * Includes for diskquotas and mount structures.
 */
#include <linux/quota.h>
#include <linux/mount.h>

/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;

struct address_space_operations {
	int (*writepage)(struct page *);
	int (*readpage)(struct file *, struct page *);