[d_path 1/7] Fix __d_path() for lazy unmounts and make it unambiguous

[Andreas Gruenbacher <agruen@suse.de>]

First, when __d_path() hits a lazily unmounted mount point, it tries to prepend
the name of the lazily unmounted dentry to the path name.  It gets this wrong,
and also overwrites the slash that separates the name from the following
pathname component. This patch fixes that; if a process was in directory
/foo/bar and /foo got lazily unmounted, the old result was ``foobar'' (note the
missing slash), while the new result with this patch is ``foo/bar''.

Second, it isn't always possible to tell from the __d_path() result whether the
specified root and rootmnt (i.e., the chroot) was reached.  We need an
unambiguous result for AppArmor at least though, so we make sure that paths
will only start with a slash if the path leads all the way up to the root.

We also add a @fail_deleted argument, which allows to get rid of some of the
mess in sys_getcwd().

This patch leaves getcwd() and d_path() as they were before for everything
except for bind-mounted directories; for them, it reports ``/foo/bar'' instead
of ``foobar'' in the example described above.  Subsequent patches propose to
make getcwd() fail instead of reporting unreachable paths like this one and
hide unreachable mount points from /proc/mounts.

Signed-off-by: Andreas Gruenbacher <agruen@suse.de>

---
 fs/dcache.c |  169 ++++++++++++++++++++++++++++++++++--------------------------
 1 file changed, 98 insertions(+), 71 deletions(-)

--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1732,52 +1732,51 @@ shouldnt_be_hashed:
 }
 
 /**
- * d_path - return the path of a dentry
+ * __d_path - return the path of a dentry
  * @dentry: dentry to report
  * @vfsmnt: vfsmnt to which the dentry belongs
  * @root: root dentry
  * @rootmnt: vfsmnt to which the root dentry belongs
  * @buffer: buffer to return value in
  * @buflen: buffer length
+ * @fail_deleted: what to return for deleted files
  *
- * Convert a dentry into an ASCII path name. If the entry has been deleted
+ * Convert a dentry into an ASCII path name. If the entry has been deleted,
+ * then if @fail_deleted is true, ERR_PTR(-ENOENT) is returned. Otherwise,
  * the string " (deleted)" is appended. Note that this is ambiguous.
  *
- * Returns the buffer or an error code if the path was too long.
+ * If @dentry is not connected to @root, the path returned will be relative
+ * (i.e., it will not start with a slash).
  *
- * "buflen" should be positive. Caller holds the dcache_lock.
+ * Returns the buffer or an error code.
  */
-static char * __d_path( struct dentry *dentry, struct vfsmount *vfsmnt,
-			struct dentry *root, struct vfsmount *rootmnt,
-			char *buffer, int buflen)
-{
-	char * end = buffer+buflen;
-	char * retval;
-	int namelen;
+static char *__d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
+		      struct dentry *root, struct vfsmount *rootmnt,
+		      char *buffer, int buflen, int fail_deleted)
+{
+	int namelen, is_slash;
+
+	if (buflen < 2)
+		return ERR_PTR(-ENAMETOOLONG);
+	buffer += --buflen;
+	*buffer = '\0';
 
-	*--end = '\0';
-	buflen--;
+	spin_lock(&dcache_lock);
 	if (!IS_ROOT(dentry) && d_unhashed(dentry)) {
-		buflen -= 10;
-		end -= 10;
-		if (buflen < 0)
+		if (fail_deleted) {
+			buffer = ERR_PTR(-ENOENT);
+			goto out;
+		}
+		if (buflen < 10)
 			goto Elong;
-		memcpy(end, " (deleted)", 10);
+		buflen -= 10;
+		buffer -= 10;
+		memcpy(buffer, " (deleted)", 10);
 	}
-
-	if (buflen < 1)
-		goto Elong;
-	/* Get '/' right */
-	retval = end-1;
-	*retval = '/';
-
-	for (;;) {
+	while (dentry != root || vfsmnt != rootmnt) {
 		struct dentry * parent;
 
-		if (dentry == root && vfsmnt == rootmnt)
-			break;
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
-			/* Global root? */
 			spin_lock(&vfsmount_lock);
 			if (vfsmnt->mnt_parent == vfsmnt) {
 				spin_unlock(&vfsmount_lock);
@@ -1791,33 +1790,72 @@ static char * __d_path( struct dentry *d
 		parent = dentry->d_parent;
 		prefetch(parent);
 		namelen = dentry->d_name.len;
-		buflen -= namelen + 1;
-		if (buflen < 0)
+		if (buflen < namelen + 1)
 			goto Elong;
-		end -= namelen;
-		memcpy(end, dentry->d_name.name, namelen);
-		*--end = '/';
-		retval = end;
+		buflen -= namelen + 1;
+		buffer -= namelen;
+		memcpy(buffer, dentry->d_name.name, namelen);
+		*--buffer = '/';
 		dentry = parent;
 	}
+	/* Get '/' right. */
+	if (*buffer != '/')
+		*--buffer = '/';
 
-	return retval;
+out:
+	spin_unlock(&dcache_lock);
+	return buffer;
 
 global_root:
+	/*
+	 * We went past the (vfsmount, dentry) we were looking for and have
+	 * either hit a root dentry, a lazily unmounted dentry, an
+	 * unconnected dentry, or the file is on a pseudo filesystem.
+	 */
 	namelen = dentry->d_name.len;
-	buflen -= namelen;
-	if (buflen < 0)
+	is_slash = (namelen == 1 && *dentry->d_name.name == '/');
+	if (is_slash || (dentry->d_sb->s_flags & MS_NOUSER)) {
+		/*
+		 * Make sure we won't return a pathname starting with '/'.
+		 *
+		 * Historically, we also glue together the root dentry and
+		 * remaining name for pseudo filesystems like pipefs, which
+		 * have the MS_NOUSER flag set. This results in pathnames
+		 * like "pipe:[439336]".
+		 */
+		if (*buffer == '/') {
+			buffer++;
+			buflen++;
+		}
+		if (is_slash)
+			goto out;
+	}
+	if (buflen < namelen)
 		goto Elong;
-	retval -= namelen-1;	/* hit the slash */
-	memcpy(retval, dentry->d_name.name, namelen);
-	return retval;
+	buffer -= namelen;
+	memcpy(buffer, dentry->d_name.name, namelen);
+	goto out;
+
 Elong:
-	return ERR_PTR(-ENAMETOOLONG);
+	buffer = ERR_PTR(-ENAMETOOLONG);
+	goto out;
+}
+
+static char *__connect_d_path(char *path, char *buffer)
+{
+	if (!IS_ERR(path) && *path != '/') {
+		/* Pretend that disconnected paths are hanging off the root. */
+		if (path == buffer)
+			path = ERR_PTR(-ENAMETOOLONG);
+		else
+			*--path = '/';
+	}
+	return path;
 }
 
 /* write full pathname into buffer and return start of pathname */
-char * d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
-				char *buf, int buflen)
+char *d_path(struct dentry *dentry, struct vfsmount *vfsmnt, char *buf,
+	     int buflen)
 {
 	char *res;
 	struct vfsmount *rootmnt;
@@ -1827,9 +1865,8 @@ char * d_path(struct dentry *dentry, str
 	rootmnt = mntget(current->fs->rootmnt);
 	root = dget(current->fs->root);
 	read_unlock(&current->fs->lock);
-	spin_lock(&dcache_lock);
-	res = __d_path(dentry, vfsmnt, root, rootmnt, buf, buflen);
-	spin_unlock(&dcache_lock);
+	res = __d_path(dentry, vfsmnt, root, rootmnt, buf, buflen, 0);
+	res = __connect_d_path(res, buf);
 	dput(root);
 	mntput(rootmnt);
 	return res;
@@ -1855,10 +1892,10 @@ char * d_path(struct dentry *dentry, str
  */
 asmlinkage long sys_getcwd(char __user *buf, unsigned long size)
 {
-	int error;
+	int error, len;
 	struct vfsmount *pwdmnt, *rootmnt;
 	struct dentry *pwd, *root;
-	char *page = (char *) __get_free_page(GFP_USER);
+	char *page = (char *) __get_free_page(GFP_USER), *cwd;
 
 	if (!page)
 		return -ENOMEM;
@@ -1870,29 +1907,19 @@ asmlinkage long sys_getcwd(char __user *
 	root = dget(current->fs->root);
 	read_unlock(&current->fs->lock);
 
-	error = -ENOENT;
-	/* Has the current directory has been unlinked? */
-	spin_lock(&dcache_lock);
-	if (pwd->d_parent == pwd || !d_unhashed(pwd)) {
-		unsigned long len;
-		char * cwd;
-
-		cwd = __d_path(pwd, pwdmnt, root, rootmnt, page, PAGE_SIZE);
-		spin_unlock(&dcache_lock);
-
-		error = PTR_ERR(cwd);
-		if (IS_ERR(cwd))
-			goto out;
-
-		error = -ERANGE;
-		len = PAGE_SIZE + page - cwd;
-		if (len <= size) {
-			error = len;
-			if (copy_to_user(buf, cwd, len))
-				error = -EFAULT;
-		}
-	} else
-		spin_unlock(&dcache_lock);
+	cwd = __d_path(pwd, pwdmnt, root, rootmnt, page, PAGE_SIZE, 1);
+	cwd = __connect_d_path(cwd, page);
+	error = PTR_ERR(cwd);
+	if (IS_ERR(cwd))
+		goto out;
+
+	error = -ERANGE;
+	len = PAGE_SIZE + page - cwd;
+	if (len <= size) {
+		error = len;
+		if (copy_to_user(buf, cwd, len))
+			error = -EFAULT;
+	}
 
 out:
 	dput(pwd);

-- 
Andreas Gruenbacher <agruen@suse.de>
SUSE Labs, SUSE LINUX Products GmbH
GF: Markus Rex, HRB 16746 (AG Nuernberg)

GPG: AF77 FAD1 1819 D442 400F  4BC8 409A 6903 4FDD EE02

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/