overlayfs: Make f_path always point to the overlay and f_inode to the underlay

Make file->f_path always point to the overlay dentry so that the path in
/proc/pid/fd is correct and to ensure that label-based LSMs have access to the
overlay as well as the underlay (path-based LSMs probably don't need it).

Using my union testsuite to set things up, before the patch I see:

[root@andromeda union-testsuite]# bash 5</mnt/a/foo107
[root@andromeda union-testsuite]# ls -l /proc/$$/fd/
...
lr-x------. 1 root root 64 Jun 5 14:38 5 -> /a/foo107
[root@andromeda union-testsuite]# stat /mnt/a/foo107
...
Device: 23h/35d Inode: 13381 Links: 1
...
[root@andromeda union-testsuite]# stat -L /proc/$$/fd/5
...
Device: 23h/35d Inode: 13381 Links: 1
...

After the patch:

[root@andromeda union-testsuite]# bash 5</mnt/a/foo107
[root@andromeda union-testsuite]# ls -l /proc/$$/fd/
...
lr-x------. 1 root root 64 Jun 5 14:22 5 -> /mnt/a/foo107
[root@andromeda union-testsuite]# stat /mnt/a/foo107
...
Device: 23h/35d Inode: 40346 Links: 1
...
[root@andromeda union-testsuite]# stat -L /proc/$$/fd/5
...
Device: 23h/35d Inode: 40346 Links: 1
...

Note the change in where /proc/$$/fd/5 points to in the ls command. It was
pointing to /a/foo107 (which doesn't exist) and now points to /mnt/a/foo107
(which is correct).

The inode accessed, however, is the lower layer. The union layer is on device
25h/37d and the upper layer on 24h/36d.

Signed-off-by: David Howells <[e-mail]>
Signed-off-by: Al Viro <[e-mail]>

fs/dcache.c

···
 				DCACHE_OP_COMPARE	|
 				DCACHE_OP_REVALIDATE	|
 				DCACHE_OP_WEAK_REVALIDATE	|
-				DCACHE_OP_DELETE ));
+				DCACHE_OP_DELETE	|
+				DCACHE_OP_SELECT_INODE));
 	dentry->d_op = op;
 	if (!op)
 		return;
···
 		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;
 
 }
 EXPORT_SYMBOL(d_set_d_op);

fs/internal.h

···
 extern long do_handle_open(int mountdirfd,
 			   struct file_handle __user *ufh, int open_flag);
 extern int open_check_o_direct(struct file *f);
+extern int vfs_open(const struct path *, struct file *, const struct cred *);
 
 /*
  * inode.c

fs/open.c

···
 }
 
 static int do_dentry_open(struct file *f,
+			  struct inode *inode,
 			  int (*open)(struct inode *, struct file *),
 			  const struct cred *cred)
 {
 	static const struct file_operations empty_fops = {};
-	struct inode *inode;
 	int error;
 
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
 
 	path_get(&f->f_path);
-	inode = f->f_inode = f->f_path.dentry->d_inode;
+	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
 
 	if (unlikely(f->f_flags & O_PATH)) {
···
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, open, current_cred());
+	error = do_dentry_open(file, d_backing_inode(dentry), open,
+			       current_cred());
 	if (!error)
 		*opened |= FILE_OPENED;
 
···
 	return 1;
 }
 EXPORT_SYMBOL(finish_no_open);
+
+/**
+ * vfs_open - open the file at the given path
+ * @path: path to open
+ * @file: newly allocated file with f_flag initialized
+ * @cred: credentials to use
+ */
+int vfs_open(const struct path *path, struct file *file,
+	     const struct cred *cred)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = dentry->d_inode;
+
+	file->f_path = *path;
+	if (dentry->d_flags & DCACHE_OP_SELECT_INODE) {
+		inode = dentry->d_op->d_select_inode(dentry, file->f_flags);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+	}
+
+	return do_dentry_open(file, inode, NULL, cred);
+}
 
 struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *cred)
···
 	return f;
 }
 EXPORT_SYMBOL(dentry_open);
-
-/**
- * vfs_open - open the file at the given path
- * @path: path to open
- * @filp: newly allocated file with f_flag initialized
- * @cred: credentials to use
- */
-int vfs_open(const struct path *path, struct file *filp,
-	     const struct cred *cred)
-{
-	struct inode *inode = path->dentry->d_inode;
-
-	if (inode->i_op->dentry_open)
-		return inode->i_op->dentry_open(path->dentry, filp, cred);
-	else {
-		filp->f_path = *path;
-		return do_dentry_open(filp, NULL, cred);
-	}
-}
-EXPORT_SYMBOL(vfs_open);
 
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {

fs/overlayfs/inode.c

···
 	return true;
 }
 
-static int ovl_dentry_open(struct dentry *dentry, struct file *file,
-		    const struct cred *cred)
+struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags)
 {
 	int err;
 	struct path realpath;
 	enum ovl_path_type type;
 
 	type = ovl_path_real(dentry, &realpath);
-	if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) {
+	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
 		err = ovl_want_write(dentry);
 		if (err)
-			return err;
+			return ERR_PTR(err);
 
-		if (file->f_flags & O_TRUNC)
+		if (file_flags & O_TRUNC)
 			err = ovl_copy_up_last(dentry, NULL, true);
 		else
 			err = ovl_copy_up(dentry);
 		ovl_drop_write(dentry);
 		if (err)
-			return err;
+			return ERR_PTR(err);
 
 		ovl_path_upper(dentry, &realpath);
 	}
 
-	return vfs_open(&realpath, file, cred);
+	return d_backing_inode(realpath.dentry);
 }
 
 static const struct inode_operations ovl_file_inode_operations = {
···
 	.getxattr	= ovl_getxattr,
 	.listxattr	= ovl_listxattr,
 	.removexattr	= ovl_removexattr,
-	.dentry_open	= ovl_dentry_open,
 };
 
 static const struct inode_operations ovl_symlink_inode_operations = {

fs/overlayfs/overlayfs.h

···
 		     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);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 			    struct ovl_entry *oe);

fs/overlayfs/super.c

···
 
 static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
+	.d_select_inode = ovl_d_select_inode,
 };
 
 static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)

include/linux/dcache.h

···
 	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);
 } ____cacheline_aligned;
 
 /*
···
 
 #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 */
 
 extern seqlock_t rename_lock;
 

include/linux/fs.h

···
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 
 	/* WARNING: probably going away soon, do not use! */
-	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 } ____cacheline_aligned;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
···
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);