X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=include%2Flinux%2Ffs.h;h=72feb9716043048dfac27ee3656750d7916ec62d;hb=refs%2Fheads%2Fvserver;hp=e9041f95f071e0f5c3b8f418d3d45f9284828093;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/include/linux/fs.h b/include/linux/fs.h index e9041f95f..72feb9716 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -6,7 +6,6 @@ * structures etc. */ -#include #include #include @@ -28,6 +27,10 @@ #define BLOCK_SIZE_BITS 10 #define BLOCK_SIZE (1<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_TAGGED(inode) __IS_FLG(inode, MS_TAGGED) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) @@ -176,6 +188,14 @@ extern int dir_notify_enable; #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) +#ifdef CONFIG_VSERVER_COWBL +# define IS_COW(inode) (IS_IUNLINK(inode) && IS_IMMUTABLE(inode)) +# define IS_COW_LINK(inode) (S_ISREG((inode)->i_mode) && ((inode)->i_nlink > 1)) +#else +# define IS_COW(inode) (0) +# define IS_COW_LINK(inode) (0) +#endif + /* 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. */ @@ -205,11 +225,66 @@ 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 FS_IOC_GETFLAGS _IOR('f', 1, long) +#define FS_IOC_SETFLAGS _IOW('f', 2, long) +#define FS_IOC_GETVERSION _IOR('v', 1, long) +#define FS_IOC_SETVERSION _IOW('v', 2, long) +#define FS_IOC32_GETFLAGS _IOR('f', 1, int) +#define FS_IOC32_SETFLAGS _IOW('f', 2, int) +#define FS_IOC32_GETVERSION _IOR('v', 1, int) +#define FS_IOC32_SETVERSION _IOW('v', 2, int) + +/* + * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) + */ +#define FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define FS_UNRM_FL 0x00000002 /* Undelete */ +#define FS_COMPR_FL 0x00000004 /* Compress file */ +#define FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define FS_DIRTY_FL 0x00000100 +#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define FS_NOCOMP_FL 0x00000400 /* Don't compress */ +#define FS_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define FS_BTREE_FL 0x00001000 /* btree format dir */ +#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ +#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define FS_EXTENT_FL 0x00080000 /* Extents */ +#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ +#define FS_BARRIER_FL 0x04000000 /* Barrier for chroot() */ +#define FS_IUNLINK_FL 0x08000000 /* Immutable unlink */ +#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ + +#ifdef CONFIG_VSERVER_LEGACY +#define FS_FL_USER_VISIBLE 0x0803DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x080380FF /* User modifiable flags */ +#else +#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ +#endif + +#define SYNC_FILE_RANGE_WAIT_BEFORE 1 +#define SYNC_FILE_RANGE_WRITE 2 +#define SYNC_FILE_RANGE_WAIT_AFTER 4 + #ifdef __KERNEL__ #include @@ -217,6 +292,7 @@ extern int dir_notify_enable; #include #include #include +#include #include #include #include @@ -224,7 +300,7 @@ extern int dir_notify_enable; #include #include #include -#include +#include #include #include @@ -249,9 +325,6 @@ 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 kiocb *iocb, loff_t offset, ssize_t bytes, void *private); @@ -273,7 +346,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_KILL_SUID 2048 #define ATTR_KILL_SGID 4096 #define ATTR_FILE 8192 -#define ATTR_XID 16384 +#define ATTR_TAG 16384 /* * This is the Inode Attributes structure, used for notify_change(). It @@ -289,7 +362,7 @@ struct iattr { umode_t ia_mode; uid_t ia_uid; gid_t ia_gid; - xid_t ia_xid; + tag_t ia_tag; loff_t ia_size; struct timespec ia_atime; struct timespec ia_mtime; @@ -352,12 +425,12 @@ struct writeback_control; 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, @@ -371,14 +444,16 @@ 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); + 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 *); + int (*migratepage) (struct address_space *, + struct page *, struct page *); + int (*launder_page) (struct page *); }; struct backing_dev_info; @@ -393,7 +468,7 @@ struct address_space { unsigned int 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 */ + const 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 */ @@ -410,11 +485,14 @@ 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 semaphore bd_mount_sem; 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; @@ -480,26 +558,28 @@ struct inode { struct list_head i_dentry; unsigned long i_ino; atomic_t i_count; - umode_t i_mode; unsigned int i_nlink; uid_t i_uid; gid_t i_gid; - xid_t i_xid; + tag_t i_tag; dev_t i_rdev; + unsigned long i_version; loff_t i_size; +#ifdef __NEED_I_SIZE_ORDERED + seqcount_t i_size_seqcount; +#endif struct timespec i_atime; struct timespec i_mtime; struct timespec i_ctime; unsigned int i_blkbits; - unsigned long i_blksize; - unsigned long i_version; - unsigned long i_blocks; + blkcnt_t i_blocks; unsigned short i_bytes; + umode_t i_mode; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ 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; @@ -507,11 +587,12 @@ struct inode { #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif - /* These three should probably be a union */ struct list_head i_devices; - struct pipe_inode_info *i_pipe; - struct block_device *i_bdev; - struct cdev *i_cdev; + union { + struct pipe_inode_info *i_pipe; + struct block_device *i_bdev; + struct cdev *i_cdev; + }; int i_cindex; __u32 i_generation; @@ -523,7 +604,7 @@ struct inode { #ifdef CONFIG_INOTIFY struct list_head inotify_watches; /* watches on this inode */ - struct semaphore inotify_sem; /* protects the watches list */ + struct mutex inotify_mutex; /* protects the watches list */ #endif unsigned long i_state; @@ -532,15 +613,35 @@ struct inode { unsigned int i_flags; atomic_t i_writecount; +#ifdef CONFIG_SECURITY void *i_security; - union { - void *generic_ip; - } u; -#ifdef __NEED_I_SIZE_ORDERED - seqcount_t i_size_seqcount; #endif + void *i_private; /* fs or device private pointer */ }; +/* + * inode->i_mutex nesting subclasses for the lock validator: + * + * 0: the object of the current VFS operation + * 1: parent + * 2: child/target + * 3: quota file + * + * The locking order between these classes is + * parent -> child -> normal -> xattr -> quota + */ +enum inode_i_mutex_lock_class +{ + I_MUTEX_NORMAL, + I_MUTEX_PARENT, + I_MUTEX_CHILD, + I_MUTEX_XATTR, + I_MUTEX_QUOTA +}; + +extern void inode_double_lock(struct inode *inode1, struct inode *inode2); +extern void inode_double_unlock(struct inode *inode1, struct inode *inode2); + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic @@ -551,7 +652,7 @@ struct inode { * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ -static inline loff_t i_size_read(struct inode *inode) +static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; @@ -574,7 +675,11 @@ static inline loff_t i_size_read(struct inode *inode) #endif } - +/* + * NOTE: unlike i_size_read(), i_size_write() does need locking around it + * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount + * can be lost, resulting in subsequent i_size_read() calls spinning forever. + */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) @@ -590,12 +695,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) #endif } -static inline unsigned iminor(struct inode *inode) +static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } -static inline unsigned imajor(struct inode *inode) +static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } @@ -604,9 +709,9 @@ extern struct block_device *I_BDEV(struct inode *inode); struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ - int pid; /* pid or -pgrp where SIGIO should be sent */ + struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ + enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ uid_t uid, euid; /* uid/euid of process setting the owner */ - void *security; int signum; /* posix.1b rt signal to be delivered on IO */ }; @@ -624,6 +729,7 @@ struct file_ra_state { 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 offset; /* Offset where last read() ended in a page */ }; #define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */ #define RA_FLAG_INCACHE 0x02 /* file is already in cache */ @@ -637,21 +743,23 @@ struct file { 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; + struct path f_path; +#define f_dentry f_path.dentry +#define f_vfsmnt f_path.mnt + const struct file_operations *f_op; atomic_t f_count; unsigned int f_flags; mode_t f_mode; 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; + struct file_ra_state f_ra; unsigned long f_version; +#ifdef CONFIG_SECURITY void *f_security; - +#endif /* needed for tty driver, and maybe others */ void *private_data; @@ -682,8 +790,9 @@ 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_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ +#define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ /* @@ -747,8 +856,6 @@ 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 *); @@ -765,17 +872,20 @@ 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 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); extern void lease_get_mtime(struct inode *, struct timespec *time); @@ -783,7 +893,6 @@ extern int setlease(struct file *, long, struct file_lock **); extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); -extern void steal_locks(fl_owner_t from); struct fasync_struct { int magic; @@ -801,8 +910,10 @@ extern void kill_fasync(struct fasync_struct **, int, int); /* only for net: no internal synchronization */ extern void __kill_fasync(struct fasync_struct *, int, int); +extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); +extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* @@ -839,7 +950,9 @@ struct super_block { int s_syncing; int s_need_sync_fs; atomic_t s_active; +#ifdef CONFIG_SECURITY void *s_security; +#endif struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ @@ -863,9 +976,9 @@ 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; }; @@ -884,36 +997,13 @@ 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); -} +#define get_fs_excl() atomic_inc(¤t->fs_excl) +#define put_fs_excl() atomic_dec(¤t->fs_excl) +#define has_fs_excl() atomic_read(¤t->fs_excl) - -/* - * Superblock locking. - */ -static inline void lock_super(struct super_block * sb) -{ - get_fs_excl(); - mutex_lock(&sb->s_lock); -} - -static inline void unlock_super(struct super_block * sb) -{ - put_fs_excl(); - mutex_unlock(&sb->s_lock); -} +/* not quite ready to be deprecated, but... */ +extern void lock_super(struct super_block *); +extern void unlock_super(struct super_block *); /* * VFS helper functions.. @@ -965,7 +1055,7 @@ int generic_osync_inode(struct inode *, struct address_space *, int); * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ -typedef int (*filldir_t)(void *, const char *, int, loff_t, ino_t, unsigned); +typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); struct block_device_operations { int (*open) (struct inode *, struct file *); @@ -1016,9 +1106,9 @@ struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); @@ -1026,20 +1116,20 @@ struct file_operations { long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); - int (*flush) (struct file *); + int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, struct dentry *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); 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 *); 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); 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 { @@ -1070,12 +1160,18 @@ struct inode_operations { struct seq_file; +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *); +ssize_t vfs_sendfile(struct file *, struct file *, loff_t *, size_t, loff_t); /* * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called @@ -1097,15 +1193,17 @@ struct super_operations { int (*sync_fs)(struct super_block *sb, int wait); void (*write_super_lockfs) (struct super_block *); void (*unlockfs) (struct super_block *); - int (*statfs) (struct super_block *, struct kstatfs *); + int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); - void (*umount_begin) (struct super_block *); + void (*umount_begin) (struct vfsmount *, int); int (*show_options)(struct seq_file *, struct vfsmount *); - + int (*show_stats)(struct seq_file *, struct vfsmount *); +#ifdef CONFIG_QUOTA 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); +#endif }; /* Inode state bits. Protected by inode_lock. */ @@ -1132,11 +1230,38 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline void inc_nlink(struct inode *inode) +{ + inode->i_nlink++; +} + +static inline void inode_inc_link_count(struct inode *inode) +{ + inc_nlink(inode); + mark_inode_dirty(inode); +} + +static inline void drop_nlink(struct inode *inode) +{ + inode->i_nlink--; +} + +static inline void clear_nlink(struct inode *inode) +{ + inode->i_nlink = 0; +} + +static inline void inode_dec_link_count(struct inode *inode) +{ + drop_nlink(inode); + 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)) - touch_atime(file->f_vfsmnt, file->f_dentry); + touch_atime(file->f_path.mnt, file->f_path.dentry); } int sync_inode(struct inode *inode, struct writeback_control *wbc); @@ -1257,23 +1382,28 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, struct file_system_type { const char *name; int fs_flags; - struct super_block *(*get_sb) (struct file_system_type *, int, - const char *, void *); + int (*get_sb) (struct file_system_type *, int, + const char *, void *, struct vfsmount *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct list_head fs_supers; + struct lock_class_key s_lock_key; + struct lock_class_key s_umount_key; }; -struct super_block *get_sb_bdev(struct file_system_type *fs_type, +extern int get_sb_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)); -struct super_block *get_sb_single(struct file_system_type *fs_type, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); +extern int get_sb_single(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); -struct super_block *get_sb_nodev(struct file_system_type *fs_type, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); +extern int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); @@ -1284,8 +1414,10 @@ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), void *data); -struct super_block *get_sb_pseudo(struct file_system_type *, char *, - struct super_operations *ops, unsigned long); +extern int get_sb_pseudo(struct file_system_type *, char *, + struct super_operations *ops, unsigned long, + struct vfsmount *mnt); +extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); int __put_super(struct super_block *sb); int __put_super_and_need_restart(struct super_block *sb); void unnamed_dev_init(void); @@ -1308,7 +1440,7 @@ 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 *); +extern int vfs_statfs(struct dentry *, struct kstatfs *); /* /sys/fs */ extern struct subsystem fs_subsys; @@ -1371,7 +1503,9 @@ extern char * getname(const char __user *); 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) +extern struct kmem_cache *names_cachep; + +#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) #ifndef CONFIG_AUDITSYSCALL #define putname(name) __putname(name) @@ -1379,6 +1513,7 @@ extern void __init vfs_caches_init(unsigned long); extern void putname(const char *name); #endif +#ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern int unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); @@ -1386,39 +1521,59 @@ 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 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 address_space_operations def_blk_aops; +#else +static inline void bd_forget(struct inode *inode) {} +#endif +extern const struct file_operations def_blk_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; +#ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); +extern int blkdev_driver_ioctl(struct inode *inode, struct file *file, + struct gendisk *disk, unsigned cmd, + unsigned long arg); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); 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 +#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 */ + +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_HASH_SIZE 255 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); +#else +#define BLKDEV_MAJOR_HASH_SIZE 0 +#endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -1426,12 +1581,13 @@ 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 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 *); +#ifdef CONFIG_BLOCK /* * return READ, READA, or WRITE */ @@ -1443,9 +1599,10 @@ extern int fs_may_remount_ro(struct super_block *); #define bio_data_dir(bio) ((bio)->bi_rw & 1) extern int check_disk_change(struct block_device *); -extern int invalidate_inodes(struct super_block *); extern int __invalidate_device(struct block_device *); extern int invalidate_partition(struct gendisk *, int); +#endif +extern int invalidate_inodes(struct super_block *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); unsigned long invalidate_inode_pages(struct address_space *mapping); @@ -1465,13 +1622,22 @@ 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 __fsync_super(struct super_block *sb); extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, void *data, int force); +#ifdef CONFIG_BLOCK extern sector_t bmap(struct inode *, sector_t); +#endif extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); extern int generic_permission(struct inode *, int, @@ -1486,9 +1652,12 @@ static inline void put_write_access(struct inode * inode) static inline void allow_write_access(struct file *file) { if (file) - atomic_inc(&file->f_dentry->d_inode->i_writecount); + atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern struct file *create_read_pipe(struct file *f); +extern struct file *create_write_pipe(void); +extern void free_write_pipe(struct file *); extern int open_namei(int dfd, const char *, int, int, struct nameidata *); extern int may_open(struct nameidata *, int, int); @@ -1542,9 +1711,10 @@ extern void __iget(struct inode * inode); extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); +extern int __remove_suid(struct dentry *, int); +extern int should_remove_suid(struct dentry *); 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 *); @@ -1555,9 +1725,11 @@ static inline void insert_inode_hash(struct inode *inode) { extern struct file * get_empty_filp(void); extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); +#ifdef CONFIG_BLOCK struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); +#endif extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); @@ -1566,32 +1738,39 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t); -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_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, 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 int generic_file_buffered_write_one_kernel_page(struct address_space *, + pgoff_t, struct page *); 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 *); +extern ssize_t generic_file_sendpage(struct file *, struct page *, int, size_t, loff_t *, int); extern void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *, struct file *, loff_t *, read_descriptor_t *, read_actor_t); + +/* 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_file_splice_write_nolock(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_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, - unsigned long nr_segs, loff_t *ppos); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); 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); @@ -1627,9 +1806,10 @@ static inline void do_generic_file_read(struct file * filp, loff_t *ppos, actor); } +#ifdef CONFIG_BLOCK 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 { @@ -1640,32 +1820,33 @@ 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); } +#endif -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)) @@ -1707,7 +1888,7 @@ extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, void *, filldir_t); extern int dcache_readdir_filter(struct file *, void *, filldir_t, int (*)(struct dentry *)); extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int simple_statfs(struct super_block *, struct kstatfs *); +extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); @@ -1722,18 +1903,19 @@ 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); +extern int simple_pin_fs(struct file_system_type *, 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); #ifdef CONFIG_MIGRATION -extern int buffer_migrate_page(struct page *, struct page *); +extern int buffer_migrate_page(struct address_space *, + struct page *, struct page *); #else #define buffer_migrate_page NULL #endif