Use pivot_root in addition to chroot when possible

chroot only changes the process root directory, not the mount namespace root
directory, and it is well-known that any process with chroot capability can
break out of a chroot "jail". By using pivot_root as well, and unmounting the
original mount namespace root directory, breaking out becomes impossible.

Non-root processes typically have no ability to use chroot() anyway, but they
can gain that capability through the use of clone() or unshare(). For security
reasons, these syscalls are limited in functionality when used inside a normal
chroot environment. Using pivot_root() this way does allow those syscalls to be
put to their full use.

2 files changed, 29 insertions, 7 deletions

diff --git a/configure.ac b/configure.ac
index be77975bd3ab..756b2f22729c 100644
--- a/configure.ac
+++ b/configure.ac
@@ -87,6 +87,7 @@ AC_CHECK_HEADERS([sys/mount.h], [], [],
 # include <sys/param.h>
 # endif
 ])
+AC_CHECK_HEADERS([sys/syscall.h])
 
 
 # Check for lutimes, optionally used for changing the mtime of
diff --git a/src/libstore/build.cc b/src/libstore/build.cc
index 259324734fd1..4841c9373ede 100644
--- a/src/libstore/build.cc
+++ b/src/libstore/build.cc
@@ -38,6 +38,9 @@
 #if HAVE_SYS_MOUNT_H
 #include <sys/mount.h>
 #endif
+#if HAVE_SYS_SYSCALL_H
+#include <sys/syscall.h>
+#endif
 #if HAVE_SCHED_H
 #include <sched.h>
 #endif
@@ -48,7 +51,7 @@
 #include <linux/fs.h>
 #endif
 
-#define CHROOT_ENABLED HAVE_CHROOT && HAVE_UNSHARE && HAVE_SYS_MOUNT_H && defined(MS_BIND) && defined(MS_PRIVATE) && defined(CLONE_NEWNS)
+#define CHROOT_ENABLED HAVE_CHROOT && HAVE_UNSHARE && HAVE_SYS_MOUNT_H && defined(MS_BIND) && defined(MS_PRIVATE) && defined(CLONE_NEWNS) && defined(SYS_pivot_root)
 
 /* chroot-like behavior from Apple's sandbox */
 #if __APPLE__
@@ -2059,6 +2062,11 @@ void DerivationGoal::runChild()
                     throw SysError(format("unable to make filesystem ‘%1%’ private") % fs);
             }
 
+            /* Bind-mount chroot directory to itself, to treat it as a
+               different filesystem from /, as needed for pivot_root. */
+            if (mount(chrootRootDir.c_str(), chrootRootDir.c_str(), 0, MS_BIND, 0) == -1)
+                throw SysError(format("unable to bind mount ‘%1%’") % chrootRootDir);
+
             /* Set up a nearly empty /dev, unless the user asked to
                bind-mount the host /dev. */
             if (dirsInChroot.find("/dev") == dirsInChroot.end()) {
@@ -2130,13 +2138,26 @@ void DerivationGoal::runChild()
                 chmod_(chrootRootDir + "/dev/pts/ptmx", 0666);
             }
 
-            /* Do the chroot().  Below we do a chdir() to the
-               temporary build directory to make sure the current
-               directory is in the chroot.  (Actually the order
-               doesn't matter, since due to the bind mount tmpDir and
-               tmpRootDit/tmpDir are the same directories.) */
-            if (chroot(chrootRootDir.c_str()) == -1)
+            /* Do the chroot(). */
+            if (chdir(chrootRootDir.c_str()) == -1)
+                throw SysError(format("cannot change directory to ‘%1%’") % chrootRootDir);
+
+            if (mkdir("real-root", 0) == -1)
+                throw SysError("cannot create real-root directory");
+
+#define pivot_root(new_root, put_old) (syscall(SYS_pivot_root, new_root, put_old))
+            if (pivot_root(".", "real-root") == -1)
+                throw SysError(format("cannot pivot old root directory onto ‘%1%’") % (chrootRootDir + "/real-root"));
+#undef pivot_root
+
+            if (chroot(".") == -1)
                 throw SysError(format("cannot change root directory to ‘%1%’") % chrootRootDir);
+
+            if (umount2("real-root", MNT_DETACH) == -1)
+                throw SysError("cannot unmount real root filesystem");
+
+            if (rmdir("real-root") == -1)
+                throw SysError("cannot remove real-root directory");
         }
 #endif