1 files changed, 273 insertions, 80 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 92734c0012e6..5bed436f4353 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -87,6 +87,60 @@ struct inodes_stat_t {
  */
 #define FMODE_NOCMTIME          ((__force fmode_t)2048)
 
+/*
+ * The below are the various read and write types that we support. Some of
+ * them include behavioral modifiers that send information down to the
+ * block layer and IO scheduler. Terminology:
+ *
+ *      The block layer uses device plugging to defer IO a little bit, in
+ *      the hope that we will see more IO very shortly. This increases
+ *      coalescing of adjacent IO and thus reduces the number of IOs we
+ *      have to send to the device. It also allows for better queuing,
+ *      if the IO isn't mergeable. If the caller is going to be waiting
+ *      for the IO, then he must ensure that the device is unplugged so
+ *      that the IO is dispatched to the driver.
+ *
+ *      All IO is handled async in Linux. This is fine for background
+ *      writes, but for reads or writes that someone waits for completion
+ *      on, we want to notify the block layer and IO scheduler so that they
+ *      know about it. That allows them to make better scheduling
+ *      decisions. So when the below references 'sync' and 'async', it
+ *      is referencing this priority hint.
+ *
+ * With that in mind, the available types are:
+ *
+ * READ                 A normal read operation. Device will be plugged.
+ * READ_SYNC            A synchronous read. Device is not plugged, caller can
+ *                      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
+ *                      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,
+ *                      WRITE_SYNC_PLUG does not do this as we could be
+ *                      submitting more writes before we actually wait on any
+ *                      of them.
+ * 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.
+ *
+ */
 #define RW_MASK         1
 #define RWA_MASK        2
 #define READ 0
@@ -95,9 +149,18 @@ struct inodes_stat_t {
 #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      (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
-#define SWRITE_SYNC     (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
+#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))
 
@@ -141,6 +204,7 @@ struct inodes_stat_t {
 #define MS_RELATIME     (1<<21) /* Update atime relative to mtime/ctime. */
 #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_ACTIVE       (1<<30)
 #define MS_NOUSER       (1<<31)
 
@@ -733,9 +797,6 @@ enum inode_i_mutex_lock_class
         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
@@ -848,6 +909,7 @@ struct file {
 #define f_dentry        f_path.dentry
 #define f_vfsmnt        f_path.mnt
         const struct file_operations    *f_op;
+        spinlock_t              f_lock;  /* f_ep_links, f_flags, no IRQ */
         atomic_long_t           f_count;
         unsigned int            f_flags;
         fmode_t                 f_mode;
@@ -866,7 +928,6 @@ struct file {
 #ifdef CONFIG_EPOLL
         /* Used by fs/eventpoll.c to link all the hooks to this file */
         struct list_head        f_ep_links;
-        spinlock_t              f_ep_lock;
 #endif /* #ifdef CONFIG_EPOLL */
         struct address_space    *f_mapping;
 #ifdef CONFIG_DEBUG_WRITECOUNT
@@ -1063,34 +1124,147 @@ 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);
 #else /* !CONFIG_FILE_LOCKING */
-#define fcntl_getlk(a, b) ({ -EINVAL; })
-#define fcntl_setlk(a, b, c, d) ({ -EACCES; })
+static inline int fcntl_getlk(struct file *file, struct flock __user *user)
+{
+        return -EINVAL;
+}
+
+static inline int fcntl_setlk(unsigned int fd, struct file *file,
+                              unsigned int cmd, struct flock __user *user)
+{
+        return -EACCES;
+}
+
 #if BITS_PER_LONG == 32
-#define fcntl_getlk64(a, b) ({ -EINVAL; })
-#define fcntl_setlk64(a, b, c, d) ({ -EACCES; })
+static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user)
+{
+        return -EINVAL;
+}
+
+static inline int fcntl_setlk64(unsigned int fd, struct file *file,
+                                unsigned int cmd, struct flock64 __user *user)
+{
+        return -EACCES;
+}
 #endif
-#define fcntl_setlease(a, b, c) ({ 0; })
-#define fcntl_getlease(a) ({ 0; })
-#define locks_init_lock(a) ({ })
-#define __locks_copy_lock(a, b) ({ })
-#define locks_copy_lock(a, b) ({ })
-#define locks_remove_posix(a, b) ({ })
-#define locks_remove_flock(a) ({ })
-#define posix_test_lock(a, b) ({ 0; })
-#define posix_lock_file(a, b, c) ({ -ENOLCK; })
-#define posix_lock_file_wait(a, b) ({ -ENOLCK; })
-#define posix_unblock_lock(a, b) (-ENOENT)
-#define vfs_test_lock(a, b) ({ 0; })
-#define vfs_lock_file(a, b, c, d) (-ENOLCK)
-#define vfs_cancel_lock(a, b) ({ 0; })
-#define flock_lock_file_wait(a, b) ({ -ENOLCK; })
-#define __break_lease(a, b) ({ 0; })
-#define lease_get_mtime(a, b) ({ })
-#define generic_setlease(a, b, c) ({ -EINVAL; })
-#define vfs_setlease(a, b, c) ({ -EINVAL; })
-#define lease_modify(a, b) ({ -EINVAL; })
-#define lock_may_read(a, b, c) ({ 1; })
-#define lock_may_write(a, b, c) ({ 1; })
+static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
+{
+        return 0;
+}
+
+static inline int fcntl_getlease(struct file *filp)
+{
+        return 0;
+}
+
+static inline void locks_init_lock(struct file_lock *fl)
+{
+        return;
+}
+
+static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+{
+        return;
+}
+
+static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+{
+        return;
+}
+
+static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
+{
+        return;
+}
+
+static inline void locks_remove_flock(struct file *filp)
+{
+        return;
+}
+
+static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
+{
+        return;
+}
+
+static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
+                                  struct file_lock *conflock)
+{
+        return -ENOLCK;
+}
+
+static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
+{
+        return -ENOLCK;
+}
+
+static inline int posix_unblock_lock(struct file *filp,
+                                     struct file_lock *waiter)
+{
+        return -ENOENT;
+}
+
+static inline int vfs_test_lock(struct file *filp, struct file_lock *fl)
+{
+        return 0;
+}
+
+static inline int vfs_lock_file(struct file *filp, unsigned int cmd,
+                                struct file_lock *fl, struct file_lock *conf)
+{
+        return -ENOLCK;
+}
+
+static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
+{
+        return 0;
+}
+
+static inline int flock_lock_file_wait(struct file *filp,
+                                       struct file_lock *request)
+{
+        return -ENOLCK;
+}
+
+static inline int __break_lease(struct inode *inode, unsigned int mode)
+{
+        return 0;
+}
+
+static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
+{
+        return;
+}
+
+static inline int generic_setlease(struct file *filp, long arg,
+                                    struct file_lock **flp)
+{
+        return -EINVAL;
+}
+
+static inline int vfs_setlease(struct file *filp, long arg,
+                               struct file_lock **lease)
+{
+        return -EINVAL;
+}
+
+static inline int lease_modify(struct file_lock **before, int arg)
+{
+        return -EINVAL;
+}
+
+static inline int lock_may_read(struct inode *inode, loff_t start,
+                                unsigned long len)
+{
+        return 1;
+}
+
+static inline int lock_may_write(struct inode *inode, loff_t start,
+                                 unsigned long len)
+{
+        return 1;
+}
+
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1581,6 +1755,9 @@ 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 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),
@@ -1606,7 +1783,7 @@ struct super_block *sget(struct file_system_type *type,
 extern int get_sb_pseudo(struct file_system_type *, char *,
         const struct super_operations *ops, unsigned long,
         struct vfsmount *mnt);
-extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
+extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 int __put_super_and_need_restart(struct super_block *sb);
 
 /* Alas, no aliases. Too much hassle with bringing module.h everywhere */
@@ -1627,6 +1804,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
 
+extern int current_umask(void);
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -1687,13 +1866,44 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
         return 0;
 }
 #else /* !CONFIG_FILE_LOCKING */
-#define locks_mandatory_locked(a) ({ 0; })
-#define locks_mandatory_area(a, b, c, d, e) ({ 0; })
-#define __mandatory_lock(a) ({ 0; })
-#define mandatory_lock(a) ({ 0; })
-#define locks_verify_locked(a) ({ 0; })
-#define locks_verify_truncate(a, b, c) ({ 0; })
-#define break_lease(a, b) ({ 0; })
+static inline int locks_mandatory_locked(struct inode *inode)
+{
+        return 0;
+}
+
+static inline int locks_mandatory_area(int rw, struct inode *inode,
+                                       struct file *filp, loff_t offset,
+                                       size_t count)
+{
+        return 0;
+}
+
+static inline int __mandatory_lock(struct inode *inode)
+{
+        return 0;
+}
+
+static inline int mandatory_lock(struct inode *inode)
+{
+        return 0;
+}
+
+static inline int locks_verify_locked(struct inode *inode)
+{
+        return 0;
+}
+
+static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
+                                        size_t size)
+{
+        return 0;
+}
+
+static inline int break_lease(struct inode *inode, unsigned int mode)
+{
+        return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */
@@ -1730,8 +1940,28 @@ 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, fmode_t);
+extern void invalidate_bdev(struct block_device *);
+extern int sync_blockdev(struct block_device *bdev);
+extern struct super_block *freeze_bdev(struct block_device *);
+extern void emergency_thaw_all(void);
+extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
+extern int fsync_bdev(struct block_device *);
+extern int fsync_super(struct super_block *);
+extern int fsync_no_super(struct block_device *);
 #else
 static inline void bd_forget(struct inode *inode) {}
+static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline void invalidate_bdev(struct block_device *bdev) {}
+
+static inline struct super_block *freeze_bdev(struct block_device *sb)
+{
+        return NULL;
+}
+
+static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+{
+        return 0;
+}
 #endif
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
@@ -1881,7 +2111,6 @@ static inline void allow_write_access(struct file *file)
         if (file)
                 atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 }
-extern int do_pipe(int *);
 extern int do_pipe_flags(int *, int);
 extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
@@ -1977,8 +2206,6 @@ 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,
@@ -2072,9 +2299,8 @@ extern int vfs_readdir(struct file *, filldir_t, void *);
 
 extern int vfs_stat(char __user *, struct kstat *);
 extern int vfs_lstat(char __user *, struct kstat *);
-extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
-extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
 extern int vfs_fstat(unsigned int, struct kstat *);
+extern int vfs_fstatat(int , char __user *, struct kstat *, int);
 
 extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
                     unsigned long arg);
@@ -2171,19 +2397,7 @@ ssize_t simple_transaction_read(struct file *file, char __user *buf,
                                 size_t size, loff_t *pos);
 int simple_transaction_release(struct inode *inode, struct file *file);
 
-static inline void simple_transaction_set(struct file *file, size_t n)
-{
-        struct simple_transaction_argresp *ar = file->private_data;
-
-        BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);
-
-        /*
-         * The barrier ensures that ar->size will really remain zero until
-         * ar->data is ready for reading.
-         */
-        smp_mb();
-        ar->size = n;
-}
+void simple_transaction_set(struct file *file, size_t n);
 
 /*
  * simple attribute files
@@ -2230,32 +2444,11 @@ ssize_t simple_attr_read(struct file *file, char __user *buf,
 ssize_t simple_attr_write(struct file *file, const char __user *buf,
                           size_t len, loff_t *ppos);
 
-
-#ifdef CONFIG_SECURITY
-static inline char *alloc_secdata(void)
-{
-        return (char *)get_zeroed_page(GFP_KERNEL);
-}
-
-static inline void free_secdata(void *secdata)
-{
-        free_page((unsigned long)secdata);
-}
-#else
-static inline char *alloc_secdata(void)
-{
-        return (char *)1;
-}
-
-static inline void free_secdata(void *secdata)
-{ }
-#endif  /* CONFIG_SECURITY */
-
 struct ctl_table;
 int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
                   void __user *buffer, size_t *lenp, loff_t *ppos);
 
-int get_filesystem_list(char * buf);
+int __init get_filesystem_list(char *buf);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */