X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=include%2Flinux%2Ffs.h;h=f78edbf27f13e9417a06432311f77a317ec959a4;hb=43bc926fffd92024b46cafaf7350d669ba9ca884;hp=51ab1eb81078cb154d914ce3e02de252da9dd89a;hpb=cee37fe97739d85991964371c1f3a745c00dd236;p=linux-2.6.git diff --git a/include/linux/fs.h b/include/linux/fs.h index 51ab1eb81..f78edbf27 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -35,6 +35,7 @@ struct files_stat_struct { int max_files; /* tunable */ }; extern struct files_stat_struct files_stat; +extern int get_max_files(void); struct inodes_stat_t { int nr_inodes; @@ -64,11 +65,17 @@ extern int dir_notify_enable; #define FMODE_PREAD 8 #define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */ +/* File is being opened for execution. Primary users of this flag are + distributed filesystems that can use it to achieve correct ETXTBUSY + behavior for cross-node execution/opening_for_writing of files */ +#define FMODE_EXEC 16 + #define RW_MASK 1 #define RWA_MASK 2 #define READ 0 #define WRITE 1 #define READA 2 /* read-ahead - don't block if no resources */ +#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ #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)) @@ -101,8 +108,14 @@ extern int dir_notify_enable; #define MS_BIND 4096 #define MS_MOVE 8192 #define MS_REC 16384 -#define MS_VERBOSE 32768 +#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. + MS_VERBOSE is deprecated. */ +#define MS_SILENT 32768 #define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#define MS_PRIVATE (1<<18) /* change to private */ +#define MS_SLAVE (1<<19) /* change to slave */ +#define MS_SHARED (1<<20) /* change to shared */ #define MS_TAGXID (1<<24) /* tag inodes with context information */ #define MS_XID (1<<25) /* use specific xid for this mount */ #define MS_ACTIVE (1<<30) @@ -111,8 +124,7 @@ extern int dir_notify_enable; /* * Superblock flags that can be altered by MS_REMOUNT */ -#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_NOATIME|\ - MS_NODIRATIME) +#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK) /* * Old magic mount flag and mask @@ -150,20 +162,19 @@ extern int dir_notify_enable; */ #define __IS_FLG(inode,flg) ((inode)->i_sb->s_flags & (flg)) -#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY) +#define IS_RDONLY(inode) __IS_FLG(inode, MS_RDONLY) #define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) +#define IS_TAGXID(inode) __IS_FLG(inode, MS_TAGXID) #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_IUNLINK(inode) ((inode)->i_flags & S_IUNLINK) #define IS_IXORUNLINK(inode) ((IS_IUNLINK(inode) ? S_IMMUTABLE : 0) ^ IS_IMMUTABLE(inode)) -#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_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL) #define IS_BARRIER(inode) (S_ISDIR((inode)->i_mode) && ((inode)->i_flags & S_BARRIER)) @@ -201,11 +212,19 @@ extern int dir_notify_enable; #define BLKBSZGET _IOR(0x12,112,size_t) #define BLKBSZSET _IOW(0x12,113,size_t) #define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */ +#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup) +#define BLKTRACESTART _IO(0x12,116) +#define BLKTRACESTOP _IO(0x12,117) +#define BLKTRACETEARDOWN _IO(0x12,118) #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 */ +#define SYNC_FILE_RANGE_WAIT_BEFORE 1 +#define SYNC_FILE_RANGE_WRITE 2 +#define SYNC_FILE_RANGE_WAIT_AFTER 4 + #ifdef __KERNEL__ #include @@ -220,22 +239,23 @@ extern int dir_notify_enable; #include #include #include +#include +#include #include #include #include +struct hd_geometry; struct iovec; struct nameidata; +struct kiocb; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; -/* Used to be a macro which just called the function, now just a function */ -extern void update_atime (struct inode *); - extern void __init inode_init(unsigned long); extern void __init inode_init_early(void); extern void __init mnt_init(unsigned long); @@ -244,10 +264,7 @@ extern void __init files_init(unsigned long); struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -typedef int (get_blocks_t)(struct inode *inode, sector_t iblock, - unsigned long max_blocks, - struct buffer_head *bh_result, int create); -typedef void (dio_iodone_t)(struct inode *inode, loff_t offset, +typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); /* @@ -267,7 +284,8 @@ typedef void (dio_iodone_t)(struct inode *inode, loff_t offset, #define ATTR_ATTR_FLAG 1024 #define ATTR_KILL_SUID 2048 #define ATTR_KILL_SGID 4096 -#define ATTR_XID 8192 +#define ATTR_FILE 8192 +#define ATTR_XID 16384 /* * This is the Inode Attributes structure, used for notify_change(). It @@ -288,17 +306,14 @@ struct iattr { struct timespec ia_atime; struct timespec ia_mtime; struct timespec 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 */ + /* + * Not an attribute, but an auxilary info for filesystems wanting to + * implement an ftruncate() like method. NOTE: filesystem should + * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). + */ + struct file *ia_file; +}; #define ATTR_FLAG_BARRIER 512 /* Barrier for chroot() */ #define ATTR_FLAG_IUNLINK 1024 /* Immutable unlink */ @@ -308,23 +323,53 @@ struct iattr { */ #include +/** + * enum positive_aop_returns - aop return codes with specific semantics + * + * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has + * completed, that the page is still locked, and + * should be considered active. The VM uses this hint + * to return the page to the active list -- it won't + * be a candidate for writeback again in the near + * future. Other callers must be careful to unlock + * the page if they get this return. Returned by + * writepage(); + * + * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has + * unlocked it and the page might have been truncated. + * The caller should back up to acquiring a new page and + * trying again. The aop will be taking reasonable + * precautions not to livelock. If the caller held a page + * reference, it should drop it before retrying. Returned + * by readpage(), prepare_write(), and commit_write(). + * + * address_space_operation functions return these large constants to indicate + * special semantics to the caller. These are much larger than the bytes in a + * page to allow for functions that return the number of bytes operated on in a + * given page. + */ + +enum positive_aop_returns { + AOP_WRITEPAGE_ACTIVATE = 0x80000, + AOP_TRUNCATED_PAGE = 0x80001, +}; + /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; -struct kiocb; struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); - int (*sync_page)(struct page *); + void (*sync_page)(struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty */ + /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); int (*readpages)(struct file *filp, struct address_space *mapping, @@ -338,10 +383,14 @@ struct address_space_operations { int (*commit_write)(struct file *, struct page *, unsigned, unsigned); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - int (*invalidatepage) (struct page *, unsigned long); - int (*releasepage) (struct page *, int); + void (*invalidatepage) (struct page *, unsigned long); + int (*releasepage) (struct page *, gfp_t); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); + struct page* (*get_xip_page)(struct address_space *, sector_t, + int); + /* migrate the contents of a page to the specified target */ + int (*migratepage) (struct page *, struct page *); }; struct backing_dev_info; @@ -373,11 +422,14 @@ struct block_device { dev_t bd_dev; /* not a kdev_t - it's a search key */ struct inode * bd_inode; /* will die */ int bd_openers; - struct semaphore bd_sem; /* open/close mutex */ - struct semaphore bd_mount_sem; /* mount mutex */ + struct mutex bd_mutex; /* open/close mutex */ + struct mutex bd_mount_mutex; /* mount mutex */ struct list_head bd_inodes; void * bd_holder; int bd_holders; +#ifdef CONFIG_SYSFS + struct list_head bd_holder_list; +#endif struct block_device * bd_contains; unsigned bd_block_size; struct hd_struct * bd_part; @@ -456,13 +508,13 @@ struct inode { unsigned int i_blkbits; unsigned long i_blksize; unsigned long i_version; - unsigned long i_blocks; + blkcnt_t i_blocks; unsigned short i_bytes; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ - struct semaphore i_sem; + struct mutex i_mutex; struct rw_semaphore i_alloc_sem; struct inode_operations *i_op; - struct file_operations *i_fop; /* former ->i_op->default_file_ops */ + const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct super_block *i_sb; struct file_lock *i_flock; struct address_space *i_mapping; @@ -484,6 +536,11 @@ struct inode { struct dnotify_struct *i_dnotify; /* for directory notifications */ #endif +#ifdef CONFIG_INOTIFY + struct list_head inotify_watches; /* watches on this inode */ + struct mutex inotify_mutex; /* protects the watches list */ +#endif + unsigned long i_state; unsigned long dirtied_when; /* jiffies of first dirtying */ @@ -587,21 +644,26 @@ struct file_ra_state { #define RA_FLAG_INCACHE 0x02 /* file is already in cache */ struct file { - struct list_head f_list; + /* + * fu_list becomes invalid after file_free is called and queued via + * fu_rcuhead for RCU freeing + */ + union { + struct list_head fu_list; + struct rcu_head fu_rcuhead; + } f_u; struct dentry *f_dentry; struct vfsmount *f_vfsmnt; - struct file_operations *f_op; + const struct file_operations *f_op; atomic_t f_count; unsigned int f_flags; mode_t f_mode; - int f_error; loff_t f_pos; struct fown_struct f_owner; unsigned int f_uid, f_gid; struct file_ra_state f_ra; xid_t f_xid; - size_t f_maxcount; unsigned long f_version; void *f_security; @@ -635,7 +697,6 @@ extern spinlock_t files_lock; #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_ACCESS 8 /* not trying to lock, just looking */ -#define FL_LOCKD 16 /* lock held by rpc.lockd */ #define FL_LEASE 32 /* lease held on this file */ #define FL_SLEEP 128 /* A blocking lock */ @@ -689,6 +750,7 @@ struct file_lock { struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; + struct nfs4_lock_info nfs4_fl; } fl_u; }; @@ -699,32 +761,36 @@ struct file_lock { #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif -extern struct list_head file_lock_list; - #include extern int fcntl_getlk(struct file *, struct flock __user *); -extern int fcntl_setlk(struct file *, unsigned int, struct flock __user *); +extern int fcntl_setlk(unsigned int, struct file *, unsigned int, + struct flock __user *); #if BITS_PER_LONG == 32 extern int fcntl_getlk64(struct file *, struct flock64 __user *); -extern int fcntl_setlk64(struct file *, unsigned int, struct flock64 __user *); +extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, + struct flock64 __user *); #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); +/* fs/sync.c */ +extern int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte, + unsigned int flags); + /* fs/locks.c */ extern void locks_init_lock(struct file_lock *); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_flock(struct file *); -extern struct file_lock *posix_test_lock(struct file *, struct file_lock *); +extern int posix_test_lock(struct file *, struct file_lock *, struct file_lock *); +extern int posix_lock_file_conf(struct file *, struct file_lock *, 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_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); @@ -772,7 +838,6 @@ struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned long s_blocksize; - unsigned long s_old_blocksize; unsigned char s_blocksize_bits; unsigned char s_dirt; unsigned long long s_maxbytes; /* Max file size */ @@ -785,7 +850,7 @@ struct super_block { unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; - struct semaphore s_lock; + struct mutex s_lock; int s_count; int s_syncing; int s_need_sync_fs; @@ -814,9 +879,9 @@ struct super_block { * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ - struct semaphore s_vfs_rename_sem; /* Kludge */ + struct mutex s_vfs_rename_mutex; /* Kludge */ - /* Granuality of c/m/atime in ns. + /* Granularity of c/m/atime in ns. Cannot be worse than a second */ u32 s_time_gran; }; @@ -835,29 +900,48 @@ enum { #define vfs_check_frozen(sb, level) \ wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) +static inline void get_fs_excl(void) +{ + atomic_inc(¤t->fs_excl); +} + +static inline void put_fs_excl(void) +{ + atomic_dec(¤t->fs_excl); +} + +static inline int has_fs_excl(void) +{ + return atomic_read(¤t->fs_excl); +} + + /* * Superblock locking. */ static inline void lock_super(struct super_block * sb) { - down(&sb->s_lock); + get_fs_excl(); + mutex_lock(&sb->s_lock); } static inline void unlock_super(struct super_block * sb) { - up(&sb->s_lock); + put_fs_excl(); + mutex_unlock(&sb->s_lock); } /* * VFS helper functions.. */ +extern int vfs_permission(struct nameidata *, int); extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *); -extern int vfs_mkdir(struct inode *, struct dentry *, int); -extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *, int); -extern int vfs_link(struct dentry *, struct inode *, struct dentry *); -extern int vfs_rmdir(struct inode *, struct dentry *); -extern int vfs_unlink(struct inode *, struct dentry *); +extern int vfs_mkdir(struct inode *, struct dentry *, int, struct nameidata *); +extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t, struct nameidata *); +extern int vfs_symlink(struct inode *, struct dentry *, const char *, int, struct nameidata *); +extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct nameidata *); +extern int vfs_rmdir(struct inode *, struct dentry *, struct nameidata *); +extern int vfs_unlink(struct inode *, struct dentry *, struct nameidata *); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); /* @@ -865,6 +949,11 @@ extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct de */ extern void dentry_unhash(struct dentry *dentry); +/* + * VFS file helper functions. + */ +extern int file_permission(struct file *, int); + /* * File types * @@ -898,9 +987,12 @@ struct block_device_operations { int (*open) (struct inode *, struct file *); int (*release) (struct inode *, struct file *); int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long); + long (*unlocked_ioctl) (struct file *, unsigned, unsigned long); long (*compat_ioctl) (struct file *, unsigned, unsigned long); + int (*direct_access) (struct block_device *, sector_t, unsigned long *); int (*media_changed) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); + int (*getgeo)(struct block_device *, struct hd_geometry *); struct module *owner; }; @@ -964,6 +1056,8 @@ struct file_operations { int (*check_flags)(int); int (*dir_notify)(struct file *filp, unsigned long arg); int (*flock) (struct file *, int, struct file_lock *); + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); + ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); }; struct inode_operations { @@ -978,8 +1072,8 @@ struct inode_operations { int (*rename) (struct inode *, struct dentry *, 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 * (*follow_link) (struct dentry *, struct nameidata *); + void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); int (*permission) (struct inode *, int, struct nameidata *); int (*setattr) (struct dentry *, struct iattr *); @@ -988,6 +1082,8 @@ struct inode_operations { ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); + void (*truncate_range)(struct inode *, loff_t, loff_t); + int (*sync_flags) (struct inode *); }; struct seq_file; @@ -1025,6 +1121,7 @@ struct super_operations { void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct vfsmount *); + int (*show_stats)(struct seq_file *, struct vfsmount *); ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); @@ -1039,6 +1136,7 @@ struct super_operations { #define I_FREEING 16 #define I_CLEAR 32 #define I_NEW 64 +#define I_WILL_FREE 128 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) @@ -1053,12 +1151,19 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } -static inline void touch_atime(struct vfsmount *mnt, struct dentry *dentry) +static inline void inode_inc_link_count(struct inode *inode) { - /* per-mountpoint checks will go here */ - update_atime(dentry->d_inode); + inode->i_nlink++; + mark_inode_dirty(inode); } +static inline void inode_dec_link_count(struct inode *inode) +{ + inode->i_nlink--; + mark_inode_dirty(inode); +} + +extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) @@ -1074,6 +1179,8 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc); * @get_name: find the name for a given inode in a given directory * @get_parent: find the parent of a given directory * @get_dentry: find a dentry for the inode given a file handle sub-fragment + * @find_exported_dentry: + * set by the exporting module to a standard helper function. * * Description: * The export_operations structure provides a means for nfsd to communicate @@ -1125,7 +1232,7 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc); * directory. The name should be stored in the @name (with the * understanding that it is already pointing to a a %NAME_MAX+1 sized * buffer. get_name() should return %0 on success, a negative error code - * or error. @get_name will be called without @parent->i_sem held. + * or error. @get_name will be called without @parent->i_mutex held. * * get_parent: * @get_parent should find the parent directory for the given @child which @@ -1147,7 +1254,7 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc); * nfsd_find_fh_dentry() in either the @obj or @parent parameters. * * Locking rules: - * get_parent is called with child->d_inode->i_sem down + * get_parent is called with child->d_inode->i_mutex down * get_name is not (which is possibly inconsistent) */ @@ -1225,10 +1332,18 @@ extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount(struct file_system_type *); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); +extern void umount_tree(struct vfsmount *, int, struct list_head *); +extern void release_mounts(struct list_head *); extern long do_mount(char *, char *, char *, unsigned long, void *); +extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int); +extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *, + struct vfsmount *); extern int vfs_statfs(struct super_block *, struct kstatfs *); +/* /sys/fs */ +extern struct subsystem fs_subsys; + #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 @@ -1274,7 +1389,10 @@ static inline int break_lease(struct inode *inode, unsigned int mode) /* fs/open.c */ -extern int do_truncate(struct dentry *, loff_t start); +extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, + struct file *filp); +extern long do_sys_open(int fdf, const char __user *filename, int flags, + int mode); extern struct file *filp_open(const char *, int, int); extern struct file * dentry_open(struct dentry *, struct vfsmount *, int); extern int filp_close(struct file *, fl_owner_t id); @@ -1299,11 +1417,11 @@ extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); -extern struct file_operations def_blk_fops; +extern const struct file_operations def_blk_fops; extern struct address_space_operations def_blk_aops; -extern struct file_operations def_chr_fops; -extern struct file_operations bad_sock_fops; -extern struct file_operations def_fifo_fops; +extern const struct file_operations def_chr_fops; +extern const struct file_operations bad_sock_fops; +extern const struct file_operations def_fifo_fops; extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); @@ -1311,23 +1429,34 @@ extern int blkdev_get(struct block_device *, mode_t, unsigned); extern int blkdev_put(struct block_device *); extern int bd_claim(struct block_device *, void *); extern void bd_release(struct block_device *); +#ifdef CONFIG_SYSFS +extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *); +extern void bd_release_from_disk(struct block_device *, struct gendisk *); +#else +#define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) +#define bd_release_from_disk(bdev, disk) bd_release(bdev) +#endif /* fs/char_dev.c */ +#define CHRDEV_MAJOR_HASH_SIZE 255 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int register_chrdev(unsigned int, const char *, - struct file_operations *); + const struct file_operations *); extern int unregister_chrdev(unsigned int, const char *); extern void unregister_chrdev_region(dev_t, unsigned); extern int chrdev_open(struct inode *, struct file *); +extern void chrdev_show(struct seq_file *,off_t); /* fs/block_dev.c */ +#define BLKDEV_MAJOR_HASH_SIZE 255 #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern struct block_device *open_bdev_excl(const char *, int, void *); extern void close_bdev_excl(struct block_device *); +extern void blkdev_show(struct seq_file *,off_t); extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -1335,12 +1464,9 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern int is_bad_inode(struct inode *); -extern struct file_operations read_fifo_fops; -extern struct file_operations write_fifo_fops; -extern struct file_operations rdwr_fifo_fops; -extern struct file_operations read_pipe_fops; -extern struct file_operations write_pipe_fops; -extern struct file_operations rdwr_pipe_fops; +extern const struct file_operations read_fifo_fops; +extern const struct file_operations write_fifo_fops; +extern const struct file_operations rdwr_fifo_fops; extern int fs_may_remount_ro(struct super_block *); @@ -1377,6 +1503,12 @@ extern int filemap_fdatawait(struct address_space *); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); +extern int wait_on_page_writeback_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +extern int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); + +extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); extern void sync_filesystems(int wait); extern void emergency_sync(void); @@ -1384,7 +1516,6 @@ extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, void *data, int force); extern sector_t bmap(struct inode *, sector_t); -extern int setattr_mask(unsigned int); extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); extern int generic_permission(struct inode *, int, @@ -1403,7 +1534,7 @@ static inline void allow_write_access(struct file *file) } extern int do_pipe(int *); -extern int open_namei(const char *, int, int, struct nameidata *); +extern int open_namei(int dfd, const char *, int, int, struct nameidata *); extern int may_open(struct nameidata *, int, int); extern int kernel_read(struct file *, unsigned long, char *, unsigned long); @@ -1426,7 +1557,11 @@ extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern void generic_delete_inode(struct inode *inode); +extern void generic_drop_inode(struct inode *inode); +extern struct inode *ilookup5_nowait(struct super_block *sb, + unsigned long hashval, int (*test)(struct inode *, void *), + void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); @@ -1453,7 +1588,6 @@ 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 *); @@ -1494,11 +1628,20 @@ ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov, 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); + loff_t *, read_descriptor_t *, read_actor_t, int); + +/* fs/splice.c */ +extern ssize_t generic_file_splice_read(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); +extern ssize_t generic_file_splice_write(struct pipe_inode_info *, + struct file *, loff_t *, size_t, unsigned int); +extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, + struct file *out, loff_t *, size_t len, unsigned int flags); +extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + size_t len, unsigned int flags); + extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs); extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, unsigned long nr_segs, loff_t *ppos); ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, @@ -1509,21 +1652,39 @@ 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); +#ifdef CONFIG_FS_XIP +extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len, + loff_t *ppos); +extern ssize_t xip_file_sendfile(struct file *in_file, loff_t *ppos, + size_t count, read_actor_t actor, + void *target); +extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma); +extern ssize_t xip_file_write(struct file *filp, const char __user *buf, + size_t len, loff_t *ppos); +extern int xip_truncate_page(struct address_space *mapping, loff_t from); +#else +static inline int xip_truncate_page(struct address_space *mapping, loff_t from) +{ + return 0; +} +#endif + static inline void do_generic_file_read(struct file * filp, loff_t *ppos, read_descriptor_t * desc, - read_actor_t actor) + read_actor_t actor, int nonblock) { do_generic_mapping_read(filp->f_mapping, &filp->f_ra, filp, ppos, desc, - actor); + actor, + nonblock); } 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, + unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, int lock_type); enum { @@ -1534,40 +1695,42 @@ enum { 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, + loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_blocks, end_io, DIO_LOCKING); + nr_segs, get_block, end_io, DIO_LOCKING); } static inline ssize_t blockdev_direct_IO_no_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, + loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_blocks, end_io, DIO_NO_LOCKING); + nr_segs, get_block, 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, + loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_blocks, end_io, DIO_OWN_LOCKING); + nr_segs, get_block, end_io, DIO_OWN_LOCKING); } -extern struct file_operations generic_ro_fops; +extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int vfs_readlink(struct dentry *, char __user *, int, const char *); extern int vfs_follow_link(struct nameidata *, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern int page_follow_link_light(struct dentry *, struct nameidata *); -extern void page_put_link(struct dentry *, struct nameidata *); +extern void *page_follow_link_light(struct dentry *, struct nameidata *); +extern void page_put_link(struct dentry *, struct nameidata *, void *); +extern int __page_symlink(struct inode *inode, const char *symname, int len, + gfp_t gfp_mask); 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); @@ -1582,6 +1745,8 @@ extern int vfs_readdir(struct file *, filldir_t, void *); extern int vfs_stat(char __user *, struct kstat *); extern int vfs_lstat(char __user *, struct kstat *); +extern int vfs_stat_fd(int dfd, char __user *, struct kstat *); +extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long); @@ -1612,9 +1777,9 @@ extern int simple_commit_write(struct file *file, struct page *page, extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); -extern struct file_operations simple_dir_operations; +extern const struct file_operations simple_dir_operations; extern struct inode_operations simple_dir_inode_operations; -struct tree_descr { char *name; struct file_operations *ops; int mode; }; +struct tree_descr { char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, int, struct tree_descr *); extern int simple_pin_fs(char *name, struct vfsmount **mount, int *count); @@ -1622,10 +1787,16 @@ 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); +#ifdef CONFIG_MIGRATION +extern int buffer_migrate_page(struct page *, struct page *); +#else +#define buffer_migrate_page NULL +#endif + extern int inode_change_ok(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); +extern void file_update_time(struct file *file); static inline ino_t parent_ino(struct dentry *dentry) { @@ -1673,6 +1844,52 @@ static inline void simple_transaction_set(struct file *file, size_t n) ar->size = n; } +/* + * simple attribute files + * + * These attributes behave similar to those in sysfs: + * + * Writing to an attribute immediately sets a value, an open file can be + * written to multiple times. + * + * Reading from an attribute creates a buffer from the value that might get + * read with multiple read calls. When the attribute has been read + * completely, no further read calls are possible until the file is opened + * again. + * + * All attributes contain a text representation of a numeric value + * that are accessed with the get() and set() functions. + */ +#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ +static int __fops ## _open(struct inode *inode, struct file *file) \ +{ \ + __simple_attr_check_format(__fmt, 0ull); \ + return simple_attr_open(inode, file, __get, __set, __fmt); \ +} \ +static struct file_operations __fops = { \ + .owner = THIS_MODULE, \ + .open = __fops ## _open, \ + .release = simple_attr_close, \ + .read = simple_attr_read, \ + .write = simple_attr_write, \ +}; + +static inline void __attribute__((format(printf, 1, 2))) +__simple_attr_check_format(const char *fmt, ...) +{ + /* don't do anything, just let the compiler check the arguments; */ +} + +int simple_attr_open(struct inode *inode, struct file *file, + u64 (*get)(void *), void (*set)(void *, u64), + const char *fmt); +int simple_attr_close(struct inode *inode, struct file *file); +ssize_t simple_attr_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos); +ssize_t simple_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos); + + #ifdef CONFIG_SECURITY static inline char *alloc_secdata(void) {