Merge branch 'd_real' into overlayfs-next

10 files changed, 80 insertions, 78 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 75eea7ce3d7c..d4def7b78a62 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -20,6 +20,8 @@ prototypes:
         char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
         struct vfsmount *(*d_automount)(struct path *path);
         int (*d_manage)(struct dentry *, bool);
+        struct dentry *(*d_real)(struct dentry *, const struct inode *,
+                                 unsigned int);
 
 locking rules:
                 rename_lock     ->d_lock        may block       rcu-walk
@@ -34,6 +36,7 @@ d_iput:		no		no		yes		no
 d_dname:        no              no              no              no
 d_automount:    no              no              yes             no
 d_manage:       no              no              yes (ref-walk)  maybe
+d_real          no              no              yes             no
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
@@ -66,7 +69,6 @@ prototypes:
                                 struct file *, unsigned open_flag,
                                 umode_t create_mode, int *opened);
         int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-        int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 
 locking rules:
         all may block
@@ -95,7 +97,6 @@ fiemap:		no
 update_time:    no
 atomic_open:    yes
 tmpfile:        no
-dentry_open:    no
 
         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index c61a223ef3ff..01c4f1741c20 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -364,7 +364,6 @@ struct inode_operations {
         int (*atomic_open)(struct inode *, struct dentry *, struct file *,
                         unsigned open_flag, umode_t create_mode, int *opened);
         int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-        int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -696,13 +695,6 @@ struct address_space_operations {
         but instead uses bmap to find out where the blocks in the file
         are and uses those addresses directly.
 
-  dentry_open: *WARNING: probably going away soon, do not use!* This is an
-        alternative to f_op->open(), the difference is that this method may open
-        a file not necessarily originating from the same filesystem as the one
-        i_op->open() was called on.  It may be useful for stacking filesystems
-        which want to allow native I/O directly on underlying files.
-
-
   invalidatepage: If a page has PagePrivate set, then invalidatepage
         will be called when part or all of the page is to be removed
         from the address space.  This generally corresponds to either a
@@ -938,6 +930,8 @@ struct dentry_operations {
         char *(*d_dname)(struct dentry *, char *, int);
         struct vfsmount *(*d_automount)(struct path *);
         int (*d_manage)(struct dentry *, bool);
+        struct dentry *(*d_real)(struct dentry *, const struct inode *,
+                                 unsigned int);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -1022,6 +1016,14 @@ struct dentry_operations {
         at the end of the buffer, and returns a pointer to the first char.
         dynamic_dname() helper function is provided to take care of this.
 
+        Example :
+
+        static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
+        {
+                return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
+                                dentry->d_inode->i_ino);
+        }
+
   d_automount: called when an automount dentry is to be traversed (optional).
         This should create a new VFS mount record and return the record to the
         caller.  The caller is supplied with a path parameter giving the
@@ -1060,13 +1062,23 @@ struct dentry_operations {
         This function is only used if DCACHE_MANAGE_TRANSIT is set on the
         dentry being transited from.
 
-Example :
+  d_real: overlay/union type filesystems implement this method to return one of
+        the underlying dentries hidden by the overlay.  It is used in three
+        different modes:
 
-static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
-{
-        return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
-                                dentry->d_inode->i_ino);
-}
+        Called from open it may need to copy-up the file depending on the
+        supplied open flags.  This mode is selected with a non-zero flags
+        argument.  In this mode the d_real method can return an error.
+
+        Called from file_dentry() it returns the real dentry matching the inode
+        argument.  The real dentry may be from a lower layer already copied up,
+        but still referenced from the file.  This mode is selected with a
+        non-NULL inode argument.  This will always succeed.
+
+        With NULL inode and zero flags the topmost real underlying dentry is
+        returned.  This will always succeed.
+
+        This method is never called with both non-NULL inode and non-zero flags.
 
 Each dentry has a pointer to its parent dentry, as well as a hash list
 of child dentries. Child dentries are basically like files in a
diff --git a/fs/dcache.c b/fs/dcache.c
index d6847d7b123d..5405b89fe8ec 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1729,7 +1729,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
                                 DCACHE_OP_REVALIDATE    |
                                 DCACHE_OP_WEAK_REVALIDATE       |
                                 DCACHE_OP_DELETE        |
-                                DCACHE_OP_SELECT_INODE  |
                                 DCACHE_OP_REAL));
         dentry->d_op = op;
         if (!op)
@@ -1746,8 +1745,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
                 dentry->d_flags |= DCACHE_OP_DELETE;
         if (op->d_prune)
                 dentry->d_flags |= DCACHE_OP_PRUNE;
-        if (op->d_select_inode)
-                dentry->d_flags |= DCACHE_OP_SELECT_INODE;
         if (op->d_real)
                 dentry->d_flags |= DCACHE_OP_REAL;
 
diff --git a/fs/namei.c b/fs/namei.c
index 70580ab1445c..bb7a2e0b959c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4328,7 +4328,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
          * Check source == target.
          * On overlayfs need to look at underlying inodes.
          */
-        if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0))
+        if (d_real_inode(old_dentry) == d_real_inode(new_dentry))
                 return 0;
 
         error = may_delete(old_dir, old_dentry, is_dir);
diff --git a/fs/open.c b/fs/open.c
index 93ae3cdee4ab..bf66cf1a9f5c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -840,13 +840,13 @@ EXPORT_SYMBOL(file_path);
 int vfs_open(const struct path *path, struct file *file,
              const struct cred *cred)
 {
-        struct inode *inode = vfs_select_inode(path->dentry, file->f_flags);
+        struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags);
 
-        if (IS_ERR(inode))
-                return PTR_ERR(inode);
+        if (IS_ERR(dentry))
+                return PTR_ERR(dentry);
 
         file->f_path = *path;
-        return do_dentry_open(file, inode, NULL, cred);
+        return do_dentry_open(file, d_backing_inode(dentry), NULL, cred);
 }
 
 struct file *dentry_open(const struct path *path, int flags,
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index d1cdc60dd68f..d554e86abbe3 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -351,36 +351,25 @@ static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
         return true;
 }
 
-struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags)
+int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
 {
-        int err;
+        int err = 0;
         struct path realpath;
         enum ovl_path_type type;
 
-        if (d_is_dir(dentry))
-                return d_backing_inode(dentry);
-
         type = ovl_path_real(dentry, &realpath);
         if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
                 err = ovl_want_write(dentry);
-                if (err)
-                        return ERR_PTR(err);
-
-                if (file_flags & O_TRUNC)
-                        err = ovl_copy_up_truncate(dentry);
-                else
-                        err = ovl_copy_up(dentry);
-                ovl_drop_write(dentry);
-                if (err)
-                        return ERR_PTR(err);
-
-                ovl_path_upper(dentry, &realpath);
+                if (!err) {
+                        if (file_flags & O_TRUNC)
+                                err = ovl_copy_up_truncate(dentry);
+                        else
+                                err = ovl_copy_up(dentry);
+                        ovl_drop_write(dentry);
+                }
         }
 
-        if (realpath.dentry->d_flags & DCACHE_OP_SELECT_INODE)
-                return realpath.dentry->d_op->d_select_inode(realpath.dentry, file_flags);
-
-        return d_backing_inode(realpath.dentry);
+        return err;
 }
 
 static const struct inode_operations ovl_file_inode_operations = {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index cfbca53590d0..0d3f2ad45708 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -179,7 +179,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
                      const char *name, void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 int ovl_removexattr(struct dentry *dentry, const char *name);
-struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
+int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
                             struct ovl_entry *oe);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 9a7693d5f8ff..5e254b3a8c56 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -304,7 +304,9 @@ static void ovl_dentry_release(struct dentry *dentry)
         }
 }
 
-static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode)
+static struct dentry *ovl_d_real(struct dentry *dentry,
+                                 const struct inode *inode,
+                                 unsigned int open_flags)
 {
         struct dentry *real;
 
@@ -314,6 +316,16 @@ static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode)
                 goto bug;
         }
 
+        if (d_is_negative(dentry))
+                return dentry;
+
+        if (open_flags) {
+                int err = ovl_open_maybe_copy_up(dentry, open_flags);
+
+                if (err)
+                        return ERR_PTR(err);
+        }
+
         real = ovl_dentry_upper(dentry);
         if (real && (!inode || inode == d_inode(real)))
                 return real;
@@ -326,9 +338,7 @@ static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode)
                 return real;
 
         /* Handle recursion */
-        if (real->d_flags & DCACHE_OP_REAL)
-                return real->d_op->d_real(real, inode);
-
+        return d_real(real, inode, open_flags);
 bug:
         WARN(1, "ovl_d_real(%pd4, %s:%lu\n): real dentry not found\n", dentry,
              inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0);
@@ -378,13 +388,11 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
 
 static const struct dentry_operations ovl_dentry_operations = {
         .d_release = ovl_dentry_release,
-        .d_select_inode = ovl_d_select_inode,
         .d_real = ovl_d_real,
 };
 
 static const struct dentry_operations ovl_reval_dentry_operations = {
         .d_release = ovl_dentry_release,
-        .d_select_inode = ovl_d_select_inode,
         .d_real = ovl_d_real,
         .d_revalidate = ovl_dentry_revalidate,
         .d_weak_revalidate = ovl_dentry_weak_revalidate,
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index f53fa055021a..14df83609c7f 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -139,8 +139,8 @@ struct dentry_operations {
         char *(*d_dname)(struct dentry *, char *, int);
         struct vfsmount *(*d_automount)(struct path *);
         int (*d_manage)(struct dentry *, bool);
-        struct inode *(*d_select_inode)(struct dentry *, unsigned);
-        struct dentry *(*d_real)(struct dentry *, struct inode *);
+        struct dentry *(*d_real)(struct dentry *, const struct inode *,
+                                 unsigned int);
 } ____cacheline_aligned;
 
 /*
@@ -206,10 +206,8 @@ struct dentry_operations {
 
 #define DCACHE_MAY_FREE                 0x00800000
 #define DCACHE_FALLTHRU                 0x01000000 /* Fall through to lower layer */
-#define DCACHE_OP_SELECT_INODE          0x02000000 /* Unioned entry: dcache op selects inode */
-
-#define DCACHE_ENCRYPTED_WITH_KEY       0x04000000 /* dir is encrypted with a valid key */
-#define DCACHE_OP_REAL                  0x08000000
+#define DCACHE_ENCRYPTED_WITH_KEY       0x02000000 /* dir is encrypted with a valid key */
+#define DCACHE_OP_REAL                  0x04000000
 
 #define DCACHE_PAR_LOOKUP               0x10000000 /* being looked up (with parent locked shared) */
 #define DCACHE_DENTRY_CURSOR            0x20000000
@@ -557,25 +555,27 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper)
         return upper;
 }
 
-static inline struct dentry *d_real(struct dentry *dentry)
+/**
+ * d_real - Return the real dentry
+ * @dentry: the dentry to query
+ * @inode: inode to select the dentry from multiple layers (can be NULL)
+ * @flags: open flags to control copy-up behavior
+ *
+ * If dentry is on an union/overlay, then return the underlying, real dentry.
+ * Otherwise return the dentry itself.
+ *
+ * See also: Documentation/filesystems/vfs.txt
+ */
+static inline struct dentry *d_real(struct dentry *dentry,
+                                    const struct inode *inode,
+                                    unsigned int flags)
 {
         if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
-                return dentry->d_op->d_real(dentry, NULL);
+                return dentry->d_op->d_real(dentry, inode, flags);
         else
                 return dentry;
 }
 
-static inline struct inode *vfs_select_inode(struct dentry *dentry,
-                                             unsigned open_flags)
-{
-        struct inode *inode = d_inode(dentry);
-
-        if (inode && unlikely(dentry->d_flags & DCACHE_OP_SELECT_INODE))
-                inode = dentry->d_op->d_select_inode(dentry, open_flags);
-
-        return inode;
-}
-
 /**
  * d_real_inode - Return the real inode
  * @dentry: The dentry to query
@@ -585,7 +585,7 @@ static inline struct inode *vfs_select_inode(struct dentry *dentry,
  */
 static inline struct inode *d_real_inode(struct dentry *dentry)
 {
-        return d_backing_inode(d_real(dentry));
+        return d_backing_inode(d_real(dentry, NULL, 0));
 }
 
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dd288148a6b1..bacc0733663c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1272,12 +1272,7 @@ static inline struct inode *file_inode(const struct file *f)
 
 static inline struct dentry *file_dentry(const struct file *file)
 {
-        struct dentry *dentry = file->f_path.dentry;
-
-        if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
-                return dentry->d_op->d_real(dentry, file_inode(file));
-        else
-                return dentry;
+        return d_real(file->f_path.dentry, file_inode(file), 0);
 }
 
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)