[PATCH v2 2/7] fs: support FD_FAILFS_ROOT in fchdir()

[Christian Brauner]

Add a new file descriptor sentinel FD_FAILFS_ROOT following
FD_PIDFS_ROOT and FD_NSFS_ROOT and teach fchdir() to accept it. A
process calling fchdir(FD_FAILFS_ROOT) moves its working directory
into failfs. Every AT_FDCWD-relative lookup afterwards fails with
EOPNOTSUPP including "." and ".." and getcwd() reports the working
directory as unreachable from the process root by returning a path
prefixed with "(unreachable)". Lookups relative to explicit directory
file descriptors are unaffected.

The sentinel is the only way in. No privilege or gating is required.
Setting the working directory to a directory in which every operation
fails grants nothing and loses nothing that closing file descriptors
couldn't lose. An unlinked working directory behaves the same way today
modulo errno. The working directory also plays no role in confining ".."
resolution so no boundary is weakened.

Signed-off-by: Christian Brauner (Amutable) <brauner@xxxxxxxxxx>
---
 fs/failfs.c                | 11 +++++++++++
 fs/internal.h              |  1 +
 fs/open.c                  |  5 ++++-
 include/uapi/linux/fcntl.h |  1 +
 4 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/fs/failfs.c b/fs/failfs.c
index d0ca1fc6c459..66a36da3d236 100644
--- a/fs/failfs.c
+++ b/fs/failfs.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/fs/super_types.h>
 #include <linux/fs_context.h>
+#include <linux/fs_struct.h>
 #include <linux/magic.h>
 #include <linux/mount.h>
 
@@ -135,6 +136,16 @@ static int failfs_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+int failfs_current_chdir(void)
+{
+	struct path path;
+
+	failfs_get_root(&path);
+	set_fs_pwd(current->fs, &path);
+	path_put(&path);
+	return 0;
+}
+
 static struct file_system_type failfs_fs_type = {
 	.name			= "failfs",
 	.init_fs_context	= failfs_init_fs_context,
diff --git a/fs/internal.h b/fs/internal.h
index ce7f12c5a65b..67aa0444351b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -365,3 +365,4 @@ void nsfs_get_root(struct path *path);
 void failfs_get_root(struct path *path);
 void __init failfs_init(void);
 bool failfs_mnt(const struct vfsmount *mnt);
+int failfs_current_chdir(void);
diff --git a/fs/open.c b/fs/open.c
index 408925d7bd0b..56b6032d4d81 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -570,9 +570,12 @@ SYSCALL_DEFINE1(chdir, const char __user *, filename)
 
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
-	CLASS(fd_raw, f)(fd);
 	int error;
 
+	if ((int)fd == FD_FAILFS_ROOT)
+		return failfs_current_chdir();
+
+	CLASS(fd_raw, f)(fd);
 	if (fd_empty(f))
 		return -EBADF;
 
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index aadfbf6e0cb3..e43e3de3e9ee 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -124,6 +124,7 @@ struct delegation {
 
 #define FD_PIDFS_ROOT			-10002 /* Root of the pidfs filesystem */
 #define FD_NSFS_ROOT			-10003 /* Root of the nsfs filesystem */
+#define FD_FAILFS_ROOT			-10004 /* Root of the failfs filesystem */
 #define FD_INVALID			-10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */
 
 /* Generic flags for the *at(2) family of syscalls. */

-- 
2.53.0