1 files changed, 62 insertions, 74 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5c7e0ff370ba..894918440bc8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -60,24 +60,24 @@ 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 +85,10 @@ 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)
 
 /*
  * The below are the various read and write types that we support. Some of
@@ -129,7 +132,7 @@ 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.
+ * WRITE_ODIRECT_PLUG   Special case write for O_DIRECT only.
  * SWRITE_SYNC
  * SWRITE_SYNC_PLUG     Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
  *                      See SWRITE.
@@ -151,7 +154,8 @@ struct inodes_stat_t {
 #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 WRITE_ODIRECT_PLUG      (WRITE | (1 << BIO_RW_SYNCIO))
+#define WRITE_META      (WRITE | (1 << BIO_RW_META))
 #define SWRITE_SYNC_PLUG        \
                         (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
 #define SWRITE_SYNC     (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
@@ -304,6 +308,7 @@ struct inodes_stat_t {
 #define BLKIOOPT _IO(0x12,121)
 #define BLKALIGNOFF _IO(0x12,122)
 #define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
 
 #define BMAP_IOCTL 1            /* obsolete - kept for compatibility */
 #define FIBMAP     _IO(0x00,1)  /* bmap access */
@@ -728,6 +733,7 @@ struct inode {
         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
@@ -737,7 +743,6 @@ 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 */
@@ -1096,10 +1101,6 @@ 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,
@@ -1310,6 +1311,8 @@ 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;
@@ -1319,9 +1322,9 @@ extern spinlock_t sb_lock;
 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 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;
@@ -1362,16 +1365,16 @@ 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"
@@ -1560,7 +1563,7 @@ struct super_operations {
         void (*destroy_inode)(struct inode *);
 
         void (*dirty_inode) (struct inode *);
-        int (*write_inode) (struct inode *, int);
+        int (*write_inode) (struct inode *, struct writeback_control *wbc);
         void (*drop_inode) (struct inode *);
         void (*delete_inode) (struct inode *);
         void (*put_super) (struct super_block *);
@@ -1592,7 +1595,7 @@ 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.
@@ -1601,8 +1604,14 @@ 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.
@@ -1616,35 +1625,23 @@ struct super_operations {
  *                      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_NEW                 3
+#define I_NEW                   (1 << __I_NEW)
 #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_SYNC                7
 #define I_SYNC                  (1 << __I_SYNC)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
@@ -1805,7 +1802,8 @@ 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 iterate_mounts(int (*)(struct vfsmount *, void *), void *,
+                          struct vfsmount *);
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
 
 extern int current_umask(void);
@@ -2069,12 +2067,6 @@ 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) ||
@@ -2093,8 +2085,6 @@ extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 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,
@@ -2145,6 +2135,7 @@ 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>
@@ -2193,7 +2184,6 @@ static inline void insert_inode_hash(struct inode *inode) {
         __insert_inode_hash(inode, inode->i_ino);
 }
 
-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
@@ -2225,6 +2215,7 @@ extern int generic_segment_checks(const struct iovec *iov,
 /* 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, struct dentry *dentry, int datasync);
 
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
@@ -2268,9 +2259,11 @@ ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         int lock_type);
 
 enum {
-        DIO_LOCKING = 1, /* need locking between buffered and direct access */
-        DIO_NO_LOCKING,  /* bdev; no locking at all between buffered/direct */
-        DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */
+        /* 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,
@@ -2279,7 +2272,8 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
         dio_iodone_t end_io)
 {
         return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
-                                nr_segs, get_block, end_io, DIO_LOCKING);
+                                    nr_segs, get_block, end_io,
+                                    DIO_LOCKING | DIO_SKIP_HOLES);
 }
 
 static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
@@ -2288,16 +2282,7 @@ static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
         dio_iodone_t end_io)
 {
         return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
-                                nr_segs, get_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_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, 0);
 }
 #endif
 
@@ -2317,6 +2302,7 @@ 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);
@@ -2332,8 +2318,9 @@ extern int vfs_fstatat(int , 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);
@@ -2359,8 +2346,6 @@ extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct
 extern int simple_sync_file(struct file *, struct dentry *, 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);
@@ -2482,5 +2467,8 @@ int proc_nr_files(struct ctl_table *table, int write,
 
 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))
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */