#define FMODE_READ 1
#define FMODE_WRITE 2
+/* Internal kernel extensions */
+#define FMODE_LSEEK 4
+#define FMODE_PREAD 8
+#define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */
+
#define RW_MASK 1
#define RWA_MASK 2
#define READ 0
#define SPECIAL 4 /* For non-blockdevice requests in request queue */
#define READ_SYNC (READ | (1 << BIO_RW_SYNC))
#define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC))
+#define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
#define SEL_IN 1
#define SEL_OUT 2
#define MS_VERBOSE 32768
#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */
#define MS_ONE_SECOND (1<<17) /* fs has 1 sec a/m/ctime resolution */
-#define MS_TAGXID (1<<24) /* tag inodes with context information */
+#define MS_TAGXID (1<<24) /* tag inodes with context information */
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
#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 */
-#define S_NOQUOTA 64 /* Inode is not counted to quota */
-#define S_DIRSYNC 128 /* Directory modifications are synchronous */
-#define S_NOCMTIME 256 /* Do not update file c/mtime */
-#define S_BARRIER 512 /* Barrier for chroot() */
-#define S_IUNLINK 1024 /* Immutable unlink */
+#define S_APPEND 4 /* Append-only file */
+#define S_IMMUTABLE 8 /* Immutable file */
+#define S_DEAD 16 /* removed, but still open directory */
+#define S_NOQUOTA 32 /* Inode is not counted to quota */
+#define S_DIRSYNC 64 /* Directory modifications are synchronous */
+#define S_NOCMTIME 128 /* Do not update file c/mtime */
+#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */
+#define S_BARRIER 1024 /* Barrier for chroot() */
+#define S_IUNLINK 2048 /* Immutable unlink */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK)
-#define IS_QUOTAINIT(inode) ((inode)->i_flags & S_QUOTA)
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE)
#define IS_BARRIER(inode) (S_ISDIR((inode)->i_mode) && ((inode)->i_flags & S_BARRIER))
#define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
+#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
/* 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. */
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/audit.h>
+#include <linux/init.h>
#include <asm/semaphore.h>
#include <asm/byteorder.h>
/* Used to be a macro which just called the function, now just a function */
extern void update_atime (struct inode *);
-extern void inode_init(unsigned long);
-extern void mnt_init(unsigned long);
-extern void files_init(unsigned long);
+extern void __init inode_init(unsigned long);
+extern void __init inode_init_early(void);
+extern void __init mnt_init(unsigned long);
+extern void __init files_init(unsigned long);
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
#define ATTR_ATTR_FLAG 1024
#define ATTR_KILL_SUID 2048
#define ATTR_KILL_SGID 4096
-#define ATTR_XID 8192
+#define ATTR_XID 8192
/*
* This is the Inode Attributes structure, used for notify_change(). It
struct inode *host; /* owner: inode, block_device */
struct radix_tree_root page_tree; /* radix tree of all pages */
spinlock_t tree_lock; /* and spinlock protecting it */
- unsigned long nrpages; /* number of total pages */
- pgoff_t writeback_index;/* writeback starts here */
- struct address_space_operations *a_ops; /* methods */
- struct prio_tree_root i_mmap; /* tree of private mappings */
unsigned int i_mmap_writable;/* count VM_SHARED mappings */
+ struct prio_tree_root i_mmap; /* tree of private and shared mappings */
struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
spinlock_t i_mmap_lock; /* protect tree, count, list */
atomic_t truncate_count; /* Cover race condition with truncate */
+ unsigned long nrpages; /* number of total pages */
+ pgoff_t writeback_index;/* writeback starts here */
+ struct address_space_operations *a_ops; /* methods */
unsigned long flags; /* error bits/gfp mask */
struct backing_dev_info *backing_dev_info; /* device readahead, etc */
spinlock_t private_lock; /* for use by the address_space */
struct block_device * bd_contains;
unsigned bd_block_size;
struct hd_struct * bd_part;
+ /* number of times partitions within this device have been opened. */
unsigned bd_part_count;
int bd_invalidated;
struct gendisk * bd_disk;
unsigned long i_version;
unsigned long i_blocks;
unsigned short i_bytes;
+ unsigned char i_sock;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
struct semaphore i_sem;
struct rw_semaphore i_alloc_sem;
struct cdev *i_cdev;
int i_cindex;
+ __u32 i_generation;
+
unsigned long i_dnotify_mask; /* Directory notify events */
struct dnotify_struct *i_dnotify; /* for directory notifications */
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned int i_flags;
- unsigned char i_sock;
atomic_t i_writecount;
void *i_security;
- __u32 i_generation;
union {
void *generic_ip;
} u;
unsigned long prev_page; /* Cache last read() position */
unsigned long ahead_start; /* Ahead window */
unsigned long ahead_size;
- unsigned long serial_cnt; /* measure of sequentiality */
- unsigned long average; /* another measure of sequentiality */
+ unsigned long currnt_wnd_hit; /* locality in the current window */
+ unsigned long average; /* size of next current window */
unsigned long ra_pages; /* Maximum readahead window */
unsigned long mmap_hit; /* Cache hit stat for mmap accesses */
unsigned long mmap_miss; /* Cache miss stat for mmap accesses */
unsigned int f_uid, f_gid;
struct file_ra_state f_ra;
+ xid_t f_xid;
+
unsigned long f_version;
void *f_security;
#define get_file(x) atomic_inc(&(x)->f_count)
#define file_count(x) atomic_read(&(x)->f_count)
-/* Initialize and open a private file and allocate its security structure. */
-extern int open_private_file(struct file *, struct dentry *, int);
-/* Release a private file and free its security structure. */
-extern void close_private_file(struct file *file);
-
#define MAX_NON_LFS ((1UL<<31) - 1)
/* Page cache limit. The filesystems should put that into their s_maxbytes
*/
typedef struct files_struct *fl_owner_t;
+struct file_lock_operations {
+ void (*fl_insert)(struct file_lock *); /* lock insertion callback */
+ void (*fl_remove)(struct file_lock *); /* lock removal callback */
+ void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
+ void (*fl_release_private)(struct file_lock *);
+};
+
+struct lock_manager_operations {
+ int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
+ void (*fl_notify)(struct file_lock *); /* unblock callback */
+};
+
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>
loff_t fl_start;
loff_t fl_end;
- void (*fl_notify)(struct file_lock *); /* unblock callback */
- void (*fl_insert)(struct file_lock *); /* lock insertion callback */
- void (*fl_remove)(struct file_lock *); /* lock removal callback */
-
struct fasync_struct * fl_fasync; /* for lease break notifications */
unsigned long fl_break_time; /* for nonblocking lease breaks */
+ struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
+ struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
union {
struct nfs_lock_info nfs_fl;
} fl_u;
#include <linux/fcntl.h>
-extern long generic_file_fcntl(int fd, unsigned int cmd,
- unsigned long arg, struct file *filp);
-
extern int fcntl_getlk(struct file *, struct flock __user *);
extern int fcntl_setlk(struct file *, unsigned int, struct flock __user *);
extern void locks_remove_flock(struct file *);
extern struct file_lock *posix_test_lock(struct file *, struct file_lock *);
extern int posix_lock_file(struct file *, struct file_lock *);
+extern int posix_lock_file_wait(struct file *, struct file_lock *);
extern void posix_block_lock(struct file_lock *, struct file_lock *);
extern void posix_unblock_lock(struct file *, struct file_lock *);
extern int posix_locks_deadlock(struct file_lock *, struct file_lock *);
+extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */
#define MNT_DETACH 0x00000002 /* Just detach from the tree */
+#define MNT_EXPIRE 0x00000004 /* Mark for expiry */
extern struct list_head super_blocks;
extern spinlock_t sb_lock;
extern int vfs_unlink(struct inode *, struct dentry *);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+/*
+ * VFS dentry helper functions.
+ */
+extern void dentry_unhash(struct dentry *dentry);
+
/*
* File types
*
#define DT_SOCK 12
#define DT_WHT 14
+#define OSYNC_METADATA (1<<0)
+#define OSYNC_DATA (1<<1)
+#define OSYNC_INODE (1<<2)
+int generic_osync_inode(struct inode *, struct address_space *, int);
+
/*
* This is the "filldir" function type, used by readdir() to let
* the kernel specify what kind of dirent layout it wants to have.
typedef struct {
size_t written;
size_t count;
- char __user * buf;
+ union {
+ char __user * buf;
+ void *data;
+ } arg;
int error;
} read_descriptor_t;
int (*lock) (struct file *, int, struct file_lock *);
ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *);
ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *);
- ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void __user *);
+ ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *);
ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
- long (*fcntl)(int fd, unsigned int cmd,
- unsigned long arg, struct file *filp);
+ int (*check_flags)(int);
+ int (*dir_notify)(struct file *filp, unsigned long arg);
+ int (*flock) (struct file *, int, struct file_lock *);
};
struct inode_operations {
struct inode *, struct dentry *);
int (*readlink) (struct dentry *, char __user *,int);
int (*follow_link) (struct dentry *, struct nameidata *);
+ void (*put_link) (struct dentry *, struct nameidata *);
void (*truncate) (struct inode *);
int (*permission) (struct inode *, int, struct nameidata *);
int (*setattr) (struct dentry *, struct iattr *);
void (*read_inode) (struct inode *);
void (*dirty_inode) (struct inode *);
- void (*write_inode) (struct inode *, int);
+ int (*write_inode) (struct inode *, int);
void (*put_inode) (struct inode *);
void (*drop_inode) (struct inode *);
void (*delete_inode) (struct inode *);
static inline void file_accessed(struct file *file)
{
- touch_atime(file->f_vfsmnt, file->f_dentry);
+ if (!(file->f_flags & O_NOATIME))
+ touch_atime(file->f_vfsmnt, file->f_dentry);
}
int sync_inode(struct inode *inode, struct writeback_control *wbc);
struct super_block *get_sb_pseudo(struct file_system_type *, char *,
struct super_operations *ops, unsigned long);
int __put_super(struct super_block *sb);
+int __put_super_and_need_restart(struct super_block *sb);
void unnamed_dev_init(void);
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
extern char * getname(const char __user *);
/* fs/dcache.c */
-extern void vfs_caches_init(unsigned long);
+extern void __init vfs_caches_init_early(void);
+extern void __init vfs_caches_init(unsigned long);
#define __getname() kmem_cache_alloc(names_cachep, SLAB_KERNEL)
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
+extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
+
extern void inode_init_once(struct inode *);
extern void iput(struct inode *);
extern struct inode * igrab(struct inode *);
extern void destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
extern int remove_suid(struct dentry *);
+extern void remove_dquot_ref(struct super_block *, int, struct list_head *);
+extern struct semaphore iprune_sem;
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
extern void remove_inode_hash(struct inode *);
extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *);
extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t);
extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
- unsigned long, loff_t *);
+ unsigned long, loff_t *);
+extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
+ unsigned long *, loff_t, loff_t *, size_t, size_t);
+extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
+ unsigned long, loff_t, loff_t *, size_t, ssize_t);
extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos);
-extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void __user *);
+extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *);
extern void do_generic_mapping_read(struct address_space *mapping,
struct file_ra_state *, struct file *,
loff_t *, read_descriptor_t *, read_actor_t);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
extern int generic_file_open(struct inode * inode, struct file * filp);
+extern int nonseekable_open(struct inode * inode, struct file * filp);
static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
read_descriptor_t * desc,
ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, get_blocks_t get_blocks, dio_iodone_t end_io,
- int needs_special_locking);
+ int lock_type);
+
+enum {
+ DIO_LOCKING = 1, /* need locking between buffered and direct access */
+ DIO_NO_LOCKING, /* bdev; no locking at all between buffered/direct */
+ DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */
+};
-/*
- * For filesystems which need locking between buffered and direct access
- */
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
struct inode *inode, struct block_device *bdev, const struct iovec *iov,
loff_t offset, unsigned long nr_segs, get_blocks_t get_blocks,
dio_iodone_t end_io)
{
return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_blocks, end_io, 1);
+ nr_segs, get_blocks, end_io, DIO_LOCKING);
}
static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
dio_iodone_t end_io)
{
return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_blocks, end_io, 0);
+ nr_segs, get_blocks, end_io, DIO_NO_LOCKING);
+}
+
+static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
+ struct inode *inode, struct block_device *bdev, const struct iovec *iov,
+ loff_t offset, unsigned long nr_segs, get_blocks_t get_blocks,
+ dio_iodone_t end_io)
+{
+ return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
+ nr_segs, get_blocks, end_io, DIO_OWN_LOCKING);
}
extern struct file_operations generic_ro_fops;
extern int vfs_follow_link(struct nameidata *, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
extern int page_follow_link(struct dentry *, struct nameidata *);
+extern int page_follow_link_light(struct dentry *, struct nameidata *);
+extern void page_put_link(struct dentry *, struct nameidata *);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern struct inode_operations page_symlink_inode_operations;
+extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
void inode_add_bytes(struct inode *inode, loff_t bytes);
extern int simple_pin_fs(char *name, struct vfsmount **mount, int *count);
extern void simple_release_fs(struct vfsmount **mount, int *count);
+extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t);
+
extern int inode_change_ok(struct inode *, struct iattr *);
-extern int inode_setattr(struct inode *, struct iattr *);
+extern int __must_check inode_setattr(struct inode *, struct iattr *);
extern void inode_update_time(struct inode *inode, int ctime_too);
/* kernel/fork.c */
extern int unshare_files(void);
+/* Transaction based IO helpers */
+
+/*
+ * An argresp is stored in an allocated page and holds the
+ * size of the argument or response, along with its content
+ */
+struct simple_transaction_argresp {
+ ssize_t size;
+ char data[0];
+};
+
+#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
+
+char *simple_transaction_get(struct file *file, const char __user *buf,
+ size_t size);
+ssize_t simple_transaction_read(struct file *file, char __user *buf,
+ size_t size, loff_t *pos);
+int simple_transaction_release(struct inode *inode, struct file *file);
+
+static inline void simple_transaction_set(struct file *file, size_t n)
+{
+ struct simple_transaction_argresp *ar = file->private_data;
+
+ BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);
+
+ /*
+ * The barrier ensures that ar->size will really remain zero until
+ * ar->data is ready for reading.
+ */
+ smp_mb();
+ ar->size = n;
+}
+
#ifdef CONFIG_SECURITY
static inline char *alloc_secdata(void)
{
git://git.onelab.eu / linux-2.6.git / blobdiff