diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 589 |
1 files changed, 346 insertions, 243 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ff5e4e01952..f84d9928bdb1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -8,6 +8,8 @@ #include <linux/limits.h> #include <linux/ioctl.h> +#include <linux/blk_types.h> +#include <linux/types.h> /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -31,11 +33,17 @@ #define SEEK_END 2 /* seek relative to end of file */ #define SEEK_MAX SEEK_END +struct fstrim_range { + __u64 start; + __u64 len; + __u64 minlen; +}; + /* And dynamically-tunable limits and defaults: */ struct files_stat_struct { - int nr_files; /* read only */ - int nr_free_files; /* read only */ - int max_files; /* tunable */ + unsigned long nr_files; /* read only */ + unsigned long nr_free_files; /* read only */ + unsigned long max_files; /* tunable */ }; struct inodes_stat_t { @@ -53,6 +61,7 @@ struct inodes_stat_t { #define MAY_APPEND 8 #define MAY_ACCESS 16 #define MAY_OPEN 32 +#define MAY_CHDIR 64 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond @@ -60,24 +69,24 @@ struct inodes_stat_t { */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)1) +#define FMODE_READ ((__force fmode_t)0x1) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)2) +#define FMODE_WRITE ((__force fmode_t)0x2) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)4) +#define FMODE_LSEEK ((__force fmode_t)0x4) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)8) +#define FMODE_PREAD ((__force fmode_t)0x8) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)16) +#define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)32) +#define FMODE_EXEC ((__force fmode_t)0x20) /* File is opened with O_NDELAY (only set for block devices) */ -#define FMODE_NDELAY ((__force fmode_t)64) +#define FMODE_NDELAY ((__force fmode_t)0x40) /* File is opened with O_EXCL (only set for block devices) */ -#define FMODE_EXCL ((__force fmode_t)128) +#define FMODE_EXCL ((__force fmode_t)0x80) /* File is opened using open(.., 3, ..) and is writeable only for ioctls (specialy hack for floppy.c) */ -#define FMODE_WRITE_IOCTL ((__force fmode_t)256) +#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* * Don't update ctime and mtime. @@ -85,7 +94,16 @@ struct inodes_stat_t { * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)2048) +#define FMODE_NOCMTIME ((__force fmode_t)0x800) + +/* Expect random access pattern */ +#define FMODE_RANDOM ((__force fmode_t)0x1000) + +/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ +#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) + +/* File was opened by fanotify and shouldn't generate fanotify events */ +#define FMODE_NONOTIFY ((__force fmode_t)0x1000000) /* * The below are the various read and write types that we support. Some of @@ -114,12 +132,9 @@ struct inodes_stat_t { * immediately wait on this read without caring about * unplugging. * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this + * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. - * SWRITE Like WRITE, but a special case for ll_rw_block() that - * tells it to lock the buffer first. Normally a buffer - * must be locked before doing IO. * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down * the hint that someone will be waiting on this IO * shortly. The device must still be unplugged explicitly, @@ -129,40 +144,34 @@ struct inodes_stat_t { * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device * immediately after submission. The write equivalent * of READ_SYNC. - * WRITE_ODIRECT Special case write for O_DIRECT only. - * SWRITE_SYNC - * SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer. - * See SWRITE. - * WRITE_BARRIER Like WRITE, but tells the block layer that all - * previously submitted writes must be safely on storage - * before this one is started. Also guarantees that when - * this write is complete, it itself is also safely on - * storage. Prevents reordering of writes on both sides - * of this IO. + * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only. + * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush. + * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on + * non-volatile media on completion. + * WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded + * by a cache flush and data is guaranteed to be on + * non-volatile media on completion. * */ -#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 READ_SYNC (READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) -#define READ_META (READ | (1 << BIO_RW_META)) -#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_ODIRECT (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) -#define SWRITE_SYNC_PLUG \ - (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_BARRIER (WRITE | (1 << BIO_RW_BARRIER)) - -/* - * These aren't really reads or writes, they pass down information about - * parts of device that are now unused by the file system. - */ -#define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD) -#define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER)) +#define RW_MASK REQ_WRITE +#define RWA_MASK REQ_RAHEAD + +#define READ 0 +#define WRITE RW_MASK +#define READA RWA_MASK + +#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) +#define READ_META (READ | REQ_META) +#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE) +#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) +#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC) +#define WRITE_META (WRITE | REQ_META) +#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_FLUSH) +#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_FUA) +#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_FLUSH | REQ_FUA) #define SEL_IN 1 #define SEL_OUT 2 @@ -205,6 +214,7 @@ struct inodes_stat_t { #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_BORN (1<<29) #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) @@ -231,6 +241,7 @@ struct inodes_stat_t { #define S_NOCMTIME 128 /* Do not update file c/mtime */ #define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE 512 /* Inode is fs-internal */ +#define S_IMA 1024 /* Inode has an associated IMA struct */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -265,6 +276,7 @@ struct inodes_stat_t { #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) +#define IS_IMA(inode) ((inode)->i_flags & S_IMA) /* 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. */ @@ -300,12 +312,19 @@ struct inodes_stat_t { #define BLKTRACESTOP _IO(0x12,117) #define BLKTRACETEARDOWN _IO(0x12,118) #define BLKDISCARD _IO(0x12,119) +#define BLKIOMIN _IO(0x12,120) +#define BLKIOOPT _IO(0x12,121) +#define BLKALIGNOFF _IO(0x12,122) +#define BLKPBSZGET _IO(0x12,123) +#define BLKDISCARDZEROES _IO(0x12,124) +#define BLKSECDISCARD _IO(0x12,125) #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 FIFREEZE _IOWR('X', 119, int) /* Freeze */ #define FITHAW _IOWR('X', 120, int) /* Thaw */ +#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */ #define FS_IOC_GETFLAGS _IOR('f', 1, long) #define FS_IOC_SETFLAGS _IOW('f', 2, long) @@ -363,7 +382,6 @@ struct inodes_stat_t { #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> -#include <linux/kobject.h> #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/prio_tree.h> @@ -373,6 +391,7 @@ struct inodes_stat_t { #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fiemap.h> +#include <linux/rculist_bl.h> #include <asm/atomic.h> #include <asm/byteorder.h> @@ -382,6 +401,7 @@ struct hd_geometry; struct iovec; struct nameidata; struct kiocb; +struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; @@ -394,19 +414,17 @@ extern void __init inode_init_early(void); extern void __init files_init(unsigned long); extern struct files_stat_struct files_stat; -extern int get_max_files(void); +extern unsigned long get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; -#ifdef CONFIG_DNOTIFY -extern int dir_notify_enable; -#endif struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, - ssize_t bytes, void *private); + ssize_t bytes, void *private, int ret, + bool is_async); /* * Attribute flags. These should be or-ed together to figure out what @@ -585,6 +603,7 @@ struct address_space_operations { sector_t (*bmap)(struct address_space *, sector_t); void (*invalidatepage) (struct page *, unsigned long); int (*releasepage) (struct page *, gfp_t); + void (*freepage)(struct page *); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); int (*get_xip_mem)(struct address_space *, pgoff_t, int, @@ -595,6 +614,7 @@ struct address_space_operations { int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); + int (*error_remove_page)(struct address_space *, struct page *); }; /* @@ -640,8 +660,8 @@ struct block_device { struct super_block * bd_super; int bd_openers; struct mutex bd_mutex; /* open/close mutex */ - struct semaphore bd_mount_sem; struct list_head bd_inodes; + void * bd_claiming; void * bd_holder; int bd_holders; #ifdef CONFIG_SYSFS @@ -655,7 +675,6 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct list_head bd_list; - struct backing_dev_info *bd_inode_backing_dev_info; /* * Private data. You must have bd_claim'ed the block_device * to use this. NOTE: bd_claim allows an owner to claim @@ -676,6 +695,7 @@ struct block_device { */ #define PAGECACHE_TAG_DIRTY 0 #define PAGECACHE_TAG_WRITEBACK 1 +#define PAGECACHE_TAG_TOWRITE 2 int mapping_tagged(struct address_space *mapping, int tag); @@ -710,17 +730,37 @@ static inline int mapping_writably_mapped(struct address_space *mapping) #define i_size_ordered_init(inode) do { } while (0) #endif +struct posix_acl; +#define ACL_NOT_CACHED ((void *)(-1)) + struct inode { + /* RCU path lookup touches following: */ + umode_t i_mode; + uid_t i_uid; + gid_t i_gid; + const struct inode_operations *i_op; + struct super_block *i_sb; + + spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ + unsigned int i_flags; + struct mutex i_mutex; + + unsigned long i_state; + unsigned long dirtied_when; /* jiffies of first dirtying */ + struct hlist_node i_hash; - struct list_head i_list; + struct list_head i_wb_list; /* backing dev IO list */ + struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; - struct list_head i_dentry; + union { + struct list_head i_dentry; + struct rcu_head i_rcu; + }; unsigned long i_ino; atomic_t i_count; unsigned int i_nlink; - uid_t i_uid; - gid_t i_gid; dev_t i_rdev; + unsigned int i_blkbits; u64 i_version; loff_t i_size; #ifdef __NEED_I_SIZE_ORDERED @@ -730,15 +770,9 @@ struct inode { struct timespec i_mtime; struct timespec i_ctime; blkcnt_t i_blocks; - unsigned int i_blkbits; 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; - const struct inode_operations *i_op; 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; struct address_space i_data; @@ -756,26 +790,29 @@ struct inode { #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ - struct hlist_head i_fsnotify_mark_entries; /* fsnotify mark entries */ + struct hlist_head i_fsnotify_marks; #endif -#ifdef CONFIG_INOTIFY - struct list_head inotify_watches; /* watches on this inode */ - struct mutex inotify_mutex; /* protects the watches list */ +#ifdef CONFIG_IMA + /* protected by i_lock */ + unsigned int i_readcount; /* struct files open RO */ #endif - - unsigned long i_state; - unsigned long dirtied_when; /* jiffies of first dirtying */ - - unsigned int i_flags; - atomic_t i_writecount; #ifdef CONFIG_SECURITY void *i_security; #endif +#ifdef CONFIG_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif void *i_private; /* fs or device private pointer */ }; +static inline int inode_unhashed(struct inode *inode) +{ + return hlist_unhashed(&inode->i_hash); +} + /* * inode->i_mutex nesting subclasses for the lock validator: * @@ -909,6 +946,9 @@ struct file { #define f_vfsmnt f_path.mnt const struct file_operations *f_op; spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */ +#ifdef CONFIG_SMP + int f_sb_list_cpu; +#endif atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -933,11 +973,9 @@ struct file { unsigned long f_mnt_write_state; #endif }; -extern spinlock_t files_lock; -#define file_list_lock() spin_lock(&files_lock); -#define file_list_unlock() spin_unlock(&files_lock); #define get_file(x) atomic_long_inc(&(x)->f_count) +#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) #ifdef CONFIG_DEBUG_WRITECOUNT @@ -1025,7 +1063,6 @@ struct lock_manager_operations { int (*fl_compare_owner)(struct file_lock *, struct file_lock *); void (*fl_notify)(struct file_lock *); /* unblock callback */ int (*fl_grant)(struct file_lock *, struct file_lock *, int); - void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); void (*fl_break)(struct file_lock *); int (*fl_mylease)(struct file_lock *, struct file_lock *); @@ -1060,8 +1097,8 @@ struct file_lock { 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 */ + const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ + const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; @@ -1083,10 +1120,6 @@ struct file_lock { extern void send_sigio(struct fown_struct *fown, int fd, int band); -/* fs/sync.c */ -extern int do_sync_mapping_range(struct address_space *mapping, loff_t offset, - loff_t endbyte, unsigned int flags); - #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, struct flock __user *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, @@ -1102,7 +1135,9 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ +void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); +extern struct file_lock * locks_alloc_lock(void); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void __locks_copy_lock(struct file_lock *, const struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); @@ -1123,6 +1158,8 @@ extern int vfs_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 lock_flocks(void); +extern void unlock_flocks(void); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, struct flock __user *user) { @@ -1265,24 +1302,37 @@ static inline int lock_may_write(struct inode *inode, loff_t start, return 1; } +static inline void lock_flocks(void) +{ +} + +static inline void unlock_flocks(void) +{ +} + #endif /* !CONFIG_FILE_LOCKING */ struct fasync_struct { - int magic; - int fa_fd; - struct fasync_struct *fa_next; /* singly linked list */ - struct file *fa_file; + spinlock_t fa_lock; + int magic; + int fa_fd; + struct fasync_struct *fa_next; /* singly linked list */ + struct file *fa_file; + struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); +extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); +extern int fasync_remove_entry(struct file *, struct fasync_struct **); +extern struct fasync_struct *fasync_alloc(void); +extern void fasync_free(struct fasync_struct *); + /* can be called from interrupts */ 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); @@ -1297,23 +1347,23 @@ extern int send_sigurg(struct fown_struct *fown); #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ +#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ +#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ extern struct list_head super_blocks; extern spinlock_t sb_lock; -#define sb_entry(list) list_entry((list), struct super_block, s_list) -#define S_BIAS (1<<30) 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 char s_blocksize_bits; unsigned char s_dirt; - unsigned long long s_maxbytes; /* Max file size */ + unsigned char s_blocksize_bits; + unsigned long s_blocksize; + loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; - struct dquot_operations *dq_op; - struct quotactl_ops *s_qcop; + const struct dquot_operations *dq_op; + const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_magic; @@ -1321,24 +1371,25 @@ struct super_block { struct rw_semaphore s_umount; struct mutex s_lock; int s_count; - int s_need_sync; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif - struct xattr_handler **s_xattr; + const struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ - struct list_head s_dirty; /* dirty inodes */ - struct list_head s_io; /* parked for writeback */ - struct list_head s_more_io; /* parked for more writeback */ - struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ + struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ +#ifdef CONFIG_SMP + struct list_head __percpu *s_files; +#else struct list_head s_files; - /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */ +#endif + /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ struct list_head s_dentry_lru; /* unused dentry lru */ int s_nr_dentry_unused; /* # of dentry on lru */ struct block_device *s_bdev; + struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct list_head s_instances; struct quota_info s_dquot; /* Diskquota specific options */ @@ -1351,16 +1402,16 @@ struct super_block { void *s_fs_info; /* Filesystem private info */ fmode_t s_mode; + /* Granularity of c/m/atime in ns. + Cannot be worse than a second */ + u32 s_time_gran; + /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ - /* Granularity of c/m/atime in ns. - Cannot be worse than a second */ - u32 s_time_gran; - /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" @@ -1371,7 +1422,7 @@ struct super_block { * Saved mount options for lazy filesystems using * generic_show_options() */ - char *s_options; + char __rcu *s_options; }; extern struct timespec current_fs_time(struct super_block *sb); @@ -1420,7 +1471,8 @@ extern void dentry_unhash(struct dentry *dentry); * VFS file helper functions. */ extern int file_permission(struct file *, int); - +extern void inode_init_owner(struct inode *inode, const struct inode *dir, + mode_t mode); /* * VFS FS_IOC_FIEMAP helper definitions. */ @@ -1451,11 +1503,6 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); #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. @@ -1473,8 +1520,8 @@ struct block_device_operations; /* * NOTE: - * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl - * can be called without the big kernel lock held in all filesystems. + * all file operations except setlease can be called without + * the big kernel lock held in all filesystems. */ struct file_operations { struct module *owner; @@ -1485,14 +1532,13 @@ struct file_operations { 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); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); 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 *, fl_owner_t id); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, struct dentry *, int datasync); + int (*fsync) (struct file *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -1505,9 +1551,18 @@ struct file_operations { int (*setlease)(struct file *, long, struct file_lock **); }; +#define IPERM_FLAG_RCU 0x0001 + struct inode_operations { - int (*create) (struct inode *,struct dentry *,int, struct nameidata *); struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); + void * (*follow_link) (struct dentry *, struct nameidata *); + int (*permission) (struct inode *, int, unsigned int); + int (*check_acl)(struct inode *, int, unsigned int); + + int (*readlink) (struct dentry *, char __user *,int); + void (*put_link) (struct dentry *, struct nameidata *, void *); + + int (*create) (struct inode *,struct dentry *,int, struct nameidata *); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); @@ -1516,11 +1571,7 @@ struct inode_operations { int (*mknod) (struct inode *,struct dentry *,int,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); - int (*readlink) (struct dentry *, char __user *,int); - void * (*follow_link) (struct dentry *, struct nameidata *); - void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -1532,7 +1583,7 @@ struct inode_operations { loff_t len); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); -}; +} ____cacheline_aligned; struct seq_file; @@ -1553,9 +1604,9 @@ struct super_operations { void (*destroy_inode)(struct inode *); void (*dirty_inode) (struct inode *); - int (*write_inode) (struct inode *, int); - void (*drop_inode) (struct inode *); - void (*delete_inode) (struct inode *); + int (*write_inode) (struct inode *, struct writeback_control *wbc); + int (*drop_inode) (struct inode *); + void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); @@ -1563,7 +1614,6 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); 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 *); int (*show_options)(struct seq_file *, struct vfsmount *); @@ -1585,7 +1635,7 @@ struct super_operations { * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * - * Two bits are used for locking and completion notification, I_LOCK and I_SYNC. + * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync(). i_atime is the usual cause. @@ -1594,51 +1644,46 @@ struct super_operations { * don't have to write inode on fdatasync() when only * mtime has changed in it. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_NEW get_new_inode() sets i_state to I_LOCK|I_NEW. Both - * are cleared by unlock_new_inode(), called from iget(). + * I_NEW Serves as both a mutex and completion notification. + * New inodes set I_NEW. If two processes both create + * the same inode, one of them will release its inode and + * wait for I_NEW to be released before returning. + * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can + * also cause waiting on I_NEW, without I_NEW actually + * being set. find_inode() uses this to prevent returning + * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. - * I_CLEAR Set by clear_inode(). In this state the inode is clean - * and can be destroyed. + * I_CLEAR Added by end_writeback(). In this state the inode is clean + * and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, - * if appropriate. I_LOCK is used for waiting. + * if appropriate. I_NEW is used for waiting. * - * I_LOCK Serves as both a mutex and completion notification. - * New inodes set I_LOCK. If two processes both create - * the same inode, one of them will release its inode and - * wait for I_LOCK to be released before returning. - * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can - * also cause waiting on I_LOCK, without I_LOCK actually - * being set. find_inode() uses this to prevent returning - * nearly-dead inodes. - * I_SYNC Similar to I_LOCK, but limited in scope to writeback - * of inode dirty data. Having a separate lock for this - * purpose reduces latency and prevents some filesystem- - * specific deadlocks. + * I_SYNC Synchonized write of dirty inode data. The bits is + * set during data writeback, and cleared with a wakeup + * on the bit address once it is done. * * Q: What is the difference between I_WILL_FREE and I_FREEING? - * Q: igrab() only checks on (I_FREEING|I_WILL_FREE). Should it also check on - * I_CLEAR? If not, why? */ -#define I_DIRTY_SYNC 1 -#define I_DIRTY_DATASYNC 2 -#define I_DIRTY_PAGES 4 -#define I_NEW 8 -#define I_WILL_FREE 16 -#define I_FREEING 32 -#define I_CLEAR 64 -#define __I_LOCK 7 -#define I_LOCK (1 << __I_LOCK) -#define __I_SYNC 8 +#define I_DIRTY_SYNC (1 << 0) +#define I_DIRTY_DATASYNC (1 << 1) +#define I_DIRTY_PAGES (1 << 2) +#define __I_NEW 3 +#define I_NEW (1 << __I_NEW) +#define I_WILL_FREE (1 << 4) +#define I_FREEING (1 << 5) +#define I_CLEAR (1 << 6) +#define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) +#define I_REFERENCED (1 << 8) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) @@ -1730,12 +1775,15 @@ static inline void file_accessed(struct file *file) } int sync_inode(struct inode *inode, struct writeback_control *wbc); +int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; int (*get_sb) (struct file_system_type *, int, const char *, void *, struct vfsmount *); + struct dentry *(*mount) (struct file_system_type *, int, + const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; @@ -1743,6 +1791,7 @@ struct file_system_type { struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; + struct lock_class_key s_vfs_rename_key; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; @@ -1750,17 +1799,25 @@ struct file_system_type { struct lock_class_key i_alloc_sem_key; }; -extern int get_sb_ns(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int), - struct vfsmount *mnt); +extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags, + void *data, int (*fill_super)(struct super_block *, void *, int)); +extern struct dentry *mount_bdev(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, + int (*fill_super)(struct super_block *, void *, int)); 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 vfsmount *mnt); +extern struct dentry *mount_single(struct file_system_type *fs_type, + int flags, void *data, + int (*fill_super)(struct super_block *, void *, int)); extern int get_sb_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int), struct vfsmount *mnt); +extern struct dentry *mount_nodev(struct file_system_type *fs_type, + int flags, void *data, + int (*fill_super)(struct super_block *, void *, int)); extern int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int), @@ -1776,11 +1833,22 @@ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), void *data); -extern int get_sb_pseudo(struct file_system_type *, char *, - const struct super_operations *ops, unsigned long, - struct vfsmount *mnt); +extern struct dentry *mount_pseudo(struct file_system_type *, char *, + const struct super_operations *ops, unsigned long); extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); -int __put_super_and_need_restart(struct super_block *sb); + +static inline void sb_mark_dirty(struct super_block *sb) +{ + sb->s_dirt = 1; +} +static inline void sb_mark_clean(struct super_block *sb) +{ + sb->s_dirt = 0; +} +static inline int sb_is_dirty(struct super_block *sb) +{ + return sb->s_dirt; +} /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ @@ -1797,14 +1865,19 @@ extern int may_umount(struct vfsmount *); extern long do_mount(char *, char *, char *, unsigned long, void *); extern struct vfsmount *collect_mounts(struct path *); extern void drop_collected_mounts(struct vfsmount *); - -extern int vfs_statfs(struct dentry *, struct kstatfs *); +extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, + struct vfsmount *); +extern int vfs_statfs(struct path *, struct kstatfs *); +extern int statfs_by_dentry(struct dentry *, struct kstatfs *); +extern int freeze_super(struct super_block *super); +extern int thaw_super(struct super_block *super); extern int current_umask(void); /* /sys/fs */ extern struct kobject *fs_kobj; +#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) extern int rw_verify_area(int, struct file *, loff_t *, size_t); #define FLOCK_VERIFY_READ 1 @@ -1906,6 +1979,8 @@ static inline int break_lease(struct inode *inode, unsigned int mode) extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); +extern int do_fallocate(struct file *file, int mode, loff_t offset, + loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, int mode); extern struct file *filp_open(const char *, int, int); @@ -1914,6 +1989,10 @@ extern struct file * dentry_open(struct dentry *, struct vfsmount *, int, extern int filp_close(struct file *, fl_owner_t id); extern char * getname(const char __user *); +/* fs/ioctl.c */ + +extern int ioctl_preallocate(struct file *filp, void __user *argp); + /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(unsigned long); @@ -1933,6 +2012,7 @@ extern void putname(const char *name); extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); +extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); @@ -1984,12 +2064,25 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *); #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 *, - const struct file_operations *); -extern void unregister_chrdev(unsigned int, const char *); +extern int __register_chrdev(unsigned int major, unsigned int baseminor, + unsigned int count, const char *name, + const struct file_operations *fops); +extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, + unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); +static inline int register_chrdev(unsigned int major, const char *name, + const struct file_operations *fops) +{ + return __register_chrdev(major, 0, 256, name, fops); +} + +static inline void unregister_chrdev(unsigned int major, const char *name) +{ + __unregister_chrdev(major, 0, 256, name); +} + /* fs/block_dev.c */ #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ @@ -2037,16 +2130,9 @@ extern int check_disk_change(struct block_device *); 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); -static inline unsigned long __deprecated -invalidate_inode_pages(struct address_space *mapping) -{ - return invalidate_mapping_pages(mapping, 0, ~0UL); -} - static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || @@ -2056,23 +2142,24 @@ static inline void invalidate_remote_inode(struct inode *inode) extern int invalidate_inode_pages2(struct address_space *mapping); extern int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); -extern void generic_sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc); extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait(struct address_space *); +extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, + loff_t lend); 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 int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); -extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync); +extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, + int datasync); +extern int vfs_fsync(struct file *file, int datasync); +extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); extern void sync_supers(void); extern void emergency_sync(void); extern void emergency_remount(void); @@ -2081,8 +2168,8 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int, - int (*check_acl)(struct inode *, int)); +extern int generic_permission(struct inode *, int, unsigned int, + int (*check_acl)(struct inode *, int, unsigned int)); static inline bool execute_ok(struct inode *inode) { @@ -2109,11 +2196,12 @@ extern struct file *do_filp_open(int dfd, const char *pathname, int open_flag, int mode, int acc_mode); extern int may_open(struct path *, int, int); -extern int kernel_read(struct file *, unsigned long, char *, unsigned long); +extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern int is_subdir(struct dentry *, struct dentry *); +extern int path_is_under(struct path *, struct path *); extern ino_t find_inode_number(struct dentry *, struct qstr *); #include <linux/err.h> @@ -2123,15 +2211,15 @@ 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 struct inode * inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); -extern void inode_add_to_lists(struct super_block *, struct inode *); +extern void ihold(struct inode * inode); extern void iput(struct inode *); 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 int generic_delete_inode(struct inode *inode); +extern int generic_drop_inode(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), @@ -2145,42 +2233,41 @@ extern struct inode * iget_locked(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); extern void unlock_new_inode(struct inode *); +extern unsigned int get_next_ino(void); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); -extern void clear_inode(struct inode *); -extern void destroy_inode(struct inode *); +extern void end_writeback(struct inode *); +extern void __destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); +extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); extern void remove_inode_hash(struct inode *); -static inline void insert_inode_hash(struct inode *inode) { +static inline void insert_inode_hash(struct inode *inode) +{ __insert_inode_hash(inode, inode->i_ino); } +extern void inode_sb_list_add(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); -extern int sb_has_dirty_inodes(struct super_block *); 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); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); 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(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); 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 *, @@ -2190,6 +2277,11 @@ extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t l extern int generic_segment_checks(const struct iovec *iov, unsigned long *nr_segs, size_t *count, int access_flags); +/* fs/block_dev.c */ +extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +extern int blkdev_fsync(struct file *filp, int datasync); + /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); @@ -2204,6 +2296,7 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); +extern loff_t noop_llseek(struct file *file, loff_t offset, int origin); 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 generic_file_llseek_unlocked(struct file *file, loff_t offset, @@ -2226,42 +2319,32 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from) #endif #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_block_t get_block, dio_iodone_t end_io, - int lock_type); +typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, + loff_t file_offset); 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 */ + /* need locking between buffered and direct access */ + DIO_LOCKING = 0x01, + + /* filesystem does not support filling holes */ + DIO_SKIP_HOLES = 0x02, }; -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_block_t get_block, - dio_iodone_t end_io) -{ - return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, DIO_LOCKING); -} +void dio_end_io(struct bio *bio, int error); -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_block_t get_block, - dio_iodone_t end_io) -{ - return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, DIO_NO_LOCKING); -} +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_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags); -static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb, +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_block_t get_block, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, DIO_OWN_LOCKING); + nr_segs, get_block, end_io, NULL, + DIO_LOCKING | DIO_SKIP_HOLES); } #endif @@ -2281,6 +2364,7 @@ extern const 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); void inode_add_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); @@ -2288,16 +2372,17 @@ void inode_set_bytes(struct inode *inode, loff_t bytes); 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(const char __user *, struct kstat *); +extern int vfs_lstat(const char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); -extern int vfs_fstatat(int , char __user *, struct kstat *, int); +extern int vfs_fstatat(int , const char __user *, struct kstat *, int); extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg); extern int __generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block); + struct fiemap_extent_info *fieinfo, + loff_t start, loff_t len, + get_block_t *get_block); extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); @@ -2306,24 +2391,25 @@ extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); +extern struct super_block *get_active_super(struct block_device *bdev); extern struct super_block *user_get_super(dev_t); extern void drop_super(struct super_block *sb); +extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, void *, filldir_t); +extern int simple_setattr(struct dentry *, struct iattr *); extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); 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 *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int simple_sync_file(struct file *, struct dentry *, int); +extern int noop_fsync(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); -extern int simple_prepare_write(struct file *file, struct page *page, - unsigned offset, unsigned to); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); @@ -2337,14 +2423,18 @@ extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; 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_fill_super(struct super_block *, unsigned long, struct tree_descr *); 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 *to, size_t count, loff_t *ppos, const void *from, size_t available); +extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, + const void __user *from, size_t count); -extern int simple_fsync(struct file *, struct dentry *, int); +extern int generic_file_fsync(struct file *, int); + +extern int generic_check_addressable(unsigned, u64); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, @@ -2353,8 +2443,9 @@ extern int buffer_migrate_page(struct address_space *, #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 int inode_change_ok(const struct inode *, struct iattr *); +extern int inode_newsize_ok(const struct inode *, loff_t offset); +extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern void file_update_time(struct file *file); @@ -2366,6 +2457,10 @@ static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; + /* + * Don't strictly need d_lock here? If the parent ino could change + * then surely we'd have a deeper race in the caller? + */ spin_lock(&dentry->d_lock); res = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); @@ -2415,12 +2510,13 @@ 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 = { \ +static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = simple_attr_write, \ + .llseek = generic_file_llseek, \ }; static inline void __attribute__((format(printf, 1, 2))) @@ -2439,10 +2535,17 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, struct file *filp, +int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); - +int proc_nr_dentry(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +int proc_nr_inodes(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); +#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) +#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ + (flag & FMODE_NONOTIFY))) + #endif /* __KERNEL__ */ #endif /* _LINUX_FS_H */ |