1 files changed, 73 insertions, 53 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 177b4ddea418..dbd860af0804 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -102,6 +102,9 @@ struct inodes_stat_t {
 /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
 #define FMODE_UNSIGNED_OFFSET   ((__force fmode_t)0x2000)
 
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH              ((__force fmode_t)0x4000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY          ((__force fmode_t)0x1000000)
 
@@ -135,16 +138,10 @@ struct inodes_stat_t {
  *                      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.
- * WRITE_SYNC_PLUG      Synchronous write. Identical to WRITE, but passes down
+ * WRITE_SYNC           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_PLUG   Special case write for O_DIRECT only.
+ *                      shortly. The write equivalent of READ_SYNC.
+ * WRITE_ODIRECT        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.
@@ -160,18 +157,14 @@ struct inodes_stat_t {
 #define WRITE                   RW_MASK
 #define READA                   RWA_MASK
 
-#define READ_SYNC               (READ | REQ_SYNC | REQ_UNPLUG)
+#define READ_SYNC               (READ | REQ_SYNC)
 #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_SYNC              (WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT           (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 WRITE_FLUSH             (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
+#define WRITE_FUA               (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA         (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define SEL_IN          1
 #define SEL_OUT         2
@@ -364,6 +357,8 @@ struct inodes_stat_t {
 #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_NOCOW_FL                     0x00800000 /* Do not cow file */
+#define FS_COW_FL                       0x02000000 /* Cow file */
 #define FS_RESERVED_FL                  0x80000000 /* reserved for ext2 lib */
 
 #define FS_FL_USER_VISIBLE              0x0003DFFF /* User visible flags */
@@ -470,7 +465,7 @@ struct iattr {
         struct timespec ia_ctime;
 
         /*
-         * Not an attribute, but an auxilary info for filesystems wanting to
+         * Not an attribute, but an auxiliary info for filesystems wanting to
          * implement an ftruncate() like method.  NOTE: filesystem should
          * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
          */
@@ -583,7 +578,6 @@ typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
 struct address_space_operations {
         int (*writepage)(struct page *page, struct writeback_control *wbc);
         int (*readpage)(struct file *, struct page *);
-        void (*sync_page)(struct page *);
 
         /* Write back some dirty pages from this mapping. */
         int (*writepages)(struct address_space *, struct writeback_control *);
@@ -619,6 +613,8 @@ struct address_space_operations {
         int (*error_remove_page)(struct address_space *, struct page *);
 };
 
+extern const struct address_space_operations empty_aops;
+
 /*
  * pagecache_write_begin/pagecache_write_end must be used by general code
  * to write into the pagecache.
@@ -649,18 +645,19 @@ struct address_space {
         spinlock_t              private_lock;   /* for use by the address_space */
         struct list_head        private_list;   /* ditto */
         struct address_space    *assoc_mapping; /* ditto */
+        struct mutex            unmap_mutex;    /* to protect unmapping */
 } __attribute__((aligned(sizeof(long))));
         /*
          * On most architectures that alignment is already the case; but
-         * must be enforced here for CRIS, to let the least signficant bit
+         * must be enforced here for CRIS, to let the least significant bit
          * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
          */
 
 struct block_device {
         dev_t                   bd_dev;  /* not a kdev_t - it's a search key */
+        int                     bd_openers;
         struct inode *          bd_inode;       /* will die */
         struct super_block *    bd_super;
-        int                     bd_openers;
         struct mutex            bd_mutex;       /* open/close mutex */
         struct list_head        bd_inodes;
         void *                  bd_claiming;
@@ -797,8 +794,7 @@ struct inode {
 #endif
 
 #ifdef CONFIG_IMA
-        /* protected by i_lock */
-        unsigned int            i_readcount; /* struct files open RO */
+        atomic_t                i_readcount; /* struct files open RO */
 #endif
         atomic_t                i_writecount;
 #ifdef CONFIG_SECURITY
@@ -977,6 +973,13 @@ struct file {
 #endif
 };
 
+struct file_handle {
+        __u32 handle_bytes;
+        int handle_type;
+        /* file identifier */
+        unsigned char f_handle[0];
+};
+
 #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)
@@ -1400,6 +1403,7 @@ struct super_block {
         wait_queue_head_t       s_wait_unfrozen;
 
         char s_id[32];                          /* Informational name */
+        u8 s_uuid[16];                          /* UUID */
 
         void                    *s_fs_info;     /* Filesystem private info */
         fmode_t                 s_mode;
@@ -1446,8 +1450,13 @@ enum {
 #define put_fs_excl() atomic_dec(&current->fs_excl)
 #define has_fs_excl() atomic_read(&current->fs_excl)
 
-#define is_owner_or_cap(inode)  \
-        ((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
+/*
+ * until VFS tracks user namespaces for inodes, just make all files
+ * belong to init_user_ns
+ */
+extern struct user_namespace init_user_ns;
+#define inode_userns(inode) (&init_user_ns)
+extern bool inode_owner_or_capable(const struct inode *inode);
 
 /* not quite ready to be deprecated, but... */
 extern void lock_super(struct super_block *);
@@ -1483,8 +1492,8 @@ struct fiemap_extent_info {
         unsigned int fi_flags;          /* Flags as passed from user */
         unsigned int fi_extents_mapped; /* Number of mapped extents */
         unsigned int fi_extents_max;    /* Size of fiemap_extent array */
-        struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent
-                                                 * array */
+        struct fiemap_extent __user *fi_extents_start; /* Start of
+                                                        fiemap_extent array */
 };
 int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
                             u64 phys, u64 len, u32 flags);
@@ -1552,6 +1561,8 @@ struct file_operations {
         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);
         int (*setlease)(struct file *, long, struct file_lock **);
+        long (*fallocate)(struct file *file, int mode, loff_t offset,
+                          loff_t len);
 };
 
 #define IPERM_FLAG_RCU  0x0001
@@ -1582,8 +1593,6 @@ struct inode_operations {
         ssize_t (*listxattr) (struct dentry *, char *, size_t);
         int (*removexattr) (struct dentry *, const char *);
         void (*truncate_range)(struct inode *, loff_t, loff_t);
-        long (*fallocate)(struct inode *inode, int mode, loff_t offset,
-                          loff_t len);
         int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
                       u64 len);
 } ____cacheline_aligned;
@@ -1620,6 +1629,8 @@ struct super_operations {
         void (*umount_begin) (struct super_block *);
 
         int (*show_options)(struct seq_file *, struct vfsmount *);
+        int (*show_devname)(struct seq_file *, struct vfsmount *);
+        int (*show_path)(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);
@@ -1629,7 +1640,7 @@ struct super_operations {
 };
 
 /*
- * Inode state bits.  Protected by inode_lock.
+ * Inode state bits.  Protected by inode->i_lock
  *
  * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
  * I_DIRTY_DATASYNC and I_DIRTY_PAGES.
@@ -1783,8 +1794,6 @@ 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 *);
@@ -1807,24 +1816,12 @@ extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
 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),
-        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);
@@ -1840,7 +1837,6 @@ extern struct dentry *mount_pseudo(struct file_system_type *, char *,
         const struct super_operations *ops,
         const struct dentry_operations *dops,
         unsigned long);
-extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 
 static inline void sb_mark_dirty(struct super_block *sb)
 {
@@ -1873,6 +1869,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
                           struct vfsmount *);
 extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, 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);
@@ -1989,6 +1987,8 @@ extern int do_fallocate(struct file *file, int mode, loff_t offset,
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
                         int mode);
 extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+                                   const char *, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
                                  const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
@@ -2139,7 +2139,7 @@ extern void check_disk_size_change(struct gendisk *disk,
                                    struct block_device *bdev);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *);
+extern int __invalidate_device(struct block_device *, bool);
 extern int invalidate_partition(struct gendisk *, int);
 #endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
@@ -2199,15 +2199,31 @@ static inline void allow_write_access(struct file *file)
         if (file)
                 atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 }
+#ifdef CONFIG_IMA
+static inline void i_readcount_dec(struct inode *inode)
+{
+        BUG_ON(!atomic_read(&inode->i_readcount));
+        atomic_dec(&inode->i_readcount);
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+        atomic_inc(&inode->i_readcount);
+}
+#else
+static inline void i_readcount_dec(struct inode *inode)
+{
+        return;
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+        return;
+}
+#endif
 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);
 extern void free_write_pipe(struct file *);
 
-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 *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
  
@@ -2225,6 +2241,7 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 
 extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
+extern void address_space_init_once(struct address_space *mapping);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
@@ -2555,9 +2572,12 @@ 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 __FMODE_EXEC            ((__force int) FMODE_EXEC)
+#define __FMODE_NONOTIFY        ((__force int) FMODE_NONOTIFY)
+
 #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)))
+                                            (flag & __FMODE_NONOTIFY)))
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */