Merge db50a2b55c into f6793bbcf0

"nsenter -a" doesn't migrate the specified process into the target
cgroup (it really should). Thus the cgroup will remain in a cgroup
that is (due to cgroup ns) outside our visibility. The kernel will
report the cgroup path of such cgroups as starting with "/../". Detect
that and print a reasonably error message instead of trying to resolve
that.

man/systemd-soft-reboot.service.xml

@@ -106,7 +106,10 @@
       normal shutdown, reboot and maintenance mode. Finally, they have to be ordered after
       <constant>basic.target</constant> to ensure correct ordering on boot. Note that in case any new or
       custom units are used to isolate to, or that implement an equivalent shutdown functionality, they will
-      also have to be configured manually for correct ordering and conflicting. For example:</para>
+      also have to be configured manually for correct ordering and conflicting. In addition, to ensure the
+      service is disconnected from the rootfs resources (see next paragraph), it should run from a separate
+      image, but with the journal sockets mounted so that it is still allowed to log to the system journal.
+      For example:</para>
 
       <programlisting>[Unit]
 Description=My Surviving Service
@@ -118,7 +121,9 @@ Conflicts=reboot.target kexec.target poweroff.target halt.target rescue.target e
 Before=shutdown.target rescue.target emergency.target
 
 [Service]
-Type=oneshot
+RootImage=/var/lib/root.raw
+TemporaryFileSystem=/run
+BindReadOnlyPaths=/run/systemd/journal/socket /run/systemd/journal/stdout
 ExecStart=sleep infinity</programlisting>
       </listitem>
 

src/basic/cgroup-util.c

@@ -803,6 +803,10 @@ int cg_pid_get_path(const char *controller, pid_t pid, char **ret_path) {
                 if (!path)
                         return -ENOMEM;
 
+                /* Refuse cgroup paths from outside our cgroup namespace */
+                if (startswith(path, "/../"))
+                        return -EUNATCH;
+
                 /* Truncate suffix indicating the process is a zombie */
                 e = endswith(path, " (deleted)");
                 if (e)

src/basic/process-util.c

@@ -102,8 +102,8 @@ int pid_get_comm(pid_t pid, char **ret) {
         _cleanup_free_ char *escaped = NULL, *comm = NULL;
         int r;
 
-        assert(ret);
         assert(pid >= 0);
+        assert(ret);
 
         if (pid == 0 || pid == getpid_cached()) {
                 comm = new0(char, TASK_COMM_LEN + 1); /* Must fit in 16 byte according to prctl(2) */
@@ -143,6 +143,9 @@ int pidref_get_comm(const PidRef *pid, char **ret) {
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         r = pid_get_comm(pid->pid, &comm);
         if (r < 0)
                 return r;
@@ -289,6 +292,9 @@ int pidref_get_cmdline(const PidRef *pid, size_t max_columns, ProcessCmdlineFlag
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         r = pid_get_cmdline(pid->pid, max_columns, flags, &s);
         if (r < 0)
                 return r;
@@ -331,6 +337,9 @@ int pidref_get_cmdline_strv(const PidRef *pid, ProcessCmdlineFlags flags, char *
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         r = pid_get_cmdline_strv(pid->pid, flags, &args);
         if (r < 0)
                 return r;
@@ -477,6 +486,9 @@ int pidref_is_kernel_thread(const PidRef *pid) {
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         result = pid_is_kernel_thread(pid->pid);
         if (result < 0)
                 return result;
@@ -594,6 +606,9 @@ int pidref_get_uid(const PidRef *pid, uid_t *ret) {
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         r = pid_get_uid(pid->pid, &uid);
         if (r < 0)
                 return r;
@@ -794,6 +809,9 @@ int pidref_get_start_time(const PidRef *pid, usec_t *ret) {
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         r = pid_get_start_time(pid->pid, ret ? &t : NULL);
         if (r < 0)
                 return r;
@@ -1093,6 +1111,9 @@ int pidref_is_my_child(const PidRef *pid) {
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         result = pid_is_my_child(pid->pid);
         if (result < 0)
                 return result;
@@ -1128,6 +1149,9 @@ int pidref_is_unwaited(const PidRef *pid) {
         if (!pidref_is_set(pid))
                 return -ESRCH;
 
+        if (pidref_is_remote(pid))
+                return -EREMOTE;
+
         if (pid->pid == 1 || pidref_is_self(pid))
                 return true;
 
@@ -1169,6 +1193,9 @@ int pidref_is_alive(const PidRef *pidref) {
         if (!pidref_is_set(pidref))
                 return -ESRCH;
 
+        if (pidref_is_remote(pidref))
+                return -EREMOTE;
+
         result = pid_is_alive(pidref->pid);
         if (result < 0) {
                 assert(result != -ESRCH);

src/basic/user-util.c

@@ -220,9 +220,9 @@ static int synthesize_user_creds(
                 if (ret_gid)
                         *ret_gid = GID_NOBODY;
                 if (ret_home)
-                        *ret_home = FLAGS_SET(flags, USER_CREDS_CLEAN) ? NULL : "/";
+                        *ret_home = FLAGS_SET(flags, USER_CREDS_SUPPRESS_PLACEHOLDER) ? NULL : "/";
                 if (ret_shell)
-                        *ret_shell = FLAGS_SET(flags, USER_CREDS_CLEAN) ? NULL : NOLOGIN;
+                        *ret_shell = FLAGS_SET(flags, USER_CREDS_SUPPRESS_PLACEHOLDER) ? NULL : NOLOGIN;
 
                 return 0;
         }
@@ -244,6 +244,7 @@ int get_user_creds(
 
         assert(username);
         assert(*username);
+        assert((ret_home || ret_shell) || !(flags & (USER_CREDS_SUPPRESS_PLACEHOLDER|USER_CREDS_CLEAN)));
 
         if (!FLAGS_SET(flags, USER_CREDS_PREFER_NSS) ||
             (!ret_home && !ret_shell)) {
@@ -315,17 +316,14 @@ int get_user_creds(
 
         if (ret_home)
                 /* Note: we don't insist on normalized paths, since there are setups that have /./ in the path */
-                *ret_home = (FLAGS_SET(flags, USER_CREDS_CLEAN) &&
+                *ret_home = (FLAGS_SET(flags, USER_CREDS_SUPPRESS_PLACEHOLDER) && empty_or_root(p->pw_dir)) ||
-                             (empty_or_root(p->pw_dir) ||
+                            (FLAGS_SET(flags, USER_CREDS_CLEAN) && (!path_is_valid(p->pw_dir) || !path_is_absolute(p->pw_dir)))
-                              !path_is_valid(p->pw_dir) ||
+                            ? NULL : p->pw_dir;
-                              !path_is_absolute(p->pw_dir))) ? NULL : p->pw_dir;
 
         if (ret_shell)
-                *ret_shell = (FLAGS_SET(flags, USER_CREDS_CLEAN) &&
+                *ret_shell = (FLAGS_SET(flags, USER_CREDS_SUPPRESS_PLACEHOLDER) && shell_is_placeholder(p->pw_shell)) ||
-                              (isempty(p->pw_shell) ||
+                             (FLAGS_SET(flags, USER_CREDS_CLEAN) && (!path_is_valid(p->pw_shell) || !path_is_absolute(p->pw_shell)))
-                               !path_is_valid(p->pw_shell) ||
+                             ? NULL : p->pw_shell;
-                               !path_is_absolute(p->pw_shell) ||
-                               is_nologin_shell(p->pw_shell))) ? NULL : p->pw_shell;
 
         if (patch_username)
                 *username = p->pw_name;

src/basic/user-util.h

@@ -12,6 +12,8 @@
 #include <sys/types.h>
 #include <unistd.h>
 
+#include "string-util.h"
+
 /* Users managed by systemd-homed. See https://systemd.io/UIDS-GIDS for details how this range fits into the rest of the world */
 #define HOME_UID_MIN ((uid_t) 60001)
 #define HOME_UID_MAX ((uid_t) 60513)
@@ -36,10 +38,20 @@ static inline int parse_gid(const char *s, gid_t *ret_gid) {
 char* getlogname_malloc(void);
 char* getusername_malloc(void);
 
+const char* default_root_shell_at(int rfd);
+const char* default_root_shell(const char *root);
+
+bool is_nologin_shell(const char *shell);
+
+static inline bool shell_is_placeholder(const char *shell) {
+        return isempty(shell) || is_nologin_shell(shell);
+}
+
 typedef enum UserCredsFlags {
-        USER_CREDS_PREFER_NSS    = 1 << 0,  /* if set, only synthesize user records if database lacks them. Normally we bypass the userdb entirely for the records we can synthesize */
+        USER_CREDS_PREFER_NSS           = 1 << 0,  /* if set, only synthesize user records if database lacks them. Normally we bypass the userdb entirely for the records we can synthesize */
-        USER_CREDS_ALLOW_MISSING = 1 << 1,  /* if a numeric UID string is resolved, be OK if there's no record for it */
+        USER_CREDS_ALLOW_MISSING        = 1 << 1,  /* if a numeric UID string is resolved, be OK if there's no record for it */
-        USER_CREDS_CLEAN         = 1 << 2,  /* try to clean up shell and home fields with invalid data */
+        USER_CREDS_CLEAN                = 1 << 2,  /* try to clean up shell and home fields with invalid data */
+        USER_CREDS_SUPPRESS_PLACEHOLDER = 1 << 3,  /* suppress home and/or shell fields if value is placeholder (root/empty/nologin) */
 } UserCredsFlags;
 
 int get_user_creds(const char **username, uid_t *ret_uid, gid_t *ret_gid, const char **ret_home, const char **ret_shell, UserCredsFlags flags);
@@ -125,10 +137,6 @@ int fgetsgent_sane(FILE *stream, struct sgrp **sg);
 int putsgent_sane(const struct sgrp *sg, FILE *stream);
 #endif
 
-bool is_nologin_shell(const char *shell);
-const char* default_root_shell_at(int rfd);
-const char* default_root_shell(const char *root);
-
 int is_this_me(const char *username);
 
 const char* get_home_root(void);

src/core/exec-invoke.c

@@ -855,9 +855,6 @@ static int get_fixed_user(
         assert(user_or_uid);
         assert(ret_username);
 
-        /* Note that we don't set $HOME or $SHELL if they are not particularly enlightening anyway
-         * (i.e. are "/" or "/bin/nologin"). */
-
         r = get_user_creds(&user_or_uid, ret_uid, ret_gid, ret_home, ret_shell, USER_CREDS_CLEAN);
         if (r < 0)
                 return r;
@@ -1883,7 +1880,10 @@ static int build_environment(
                 }
         }
 
-        if (home && set_user_login_env) {
+        /* Note that we don't set $HOME or $SHELL if they are not particularly enlightening anyway
+         * (i.e. are "/" or "/bin/nologin"). */
+
+        if (home && set_user_login_env && !empty_or_root(home)) {
                 x = strjoin("HOME=", home);
                 if (!x)
                         return -ENOMEM;
@@ -1892,7 +1892,7 @@ static int build_environment(
                 our_env[n_env++] = x;
         }
 
-        if (shell && set_user_login_env) {
+        if (shell && set_user_login_env && !shell_is_placeholder(shell)) {
                 x = strjoin("SHELL=", shell);
                 if (!x)
                         return -ENOMEM;
@@ -3471,20 +3471,16 @@ static int apply_working_directory(
                 const ExecContext *context,
                 const ExecParameters *params,
                 ExecRuntime *runtime,
-                const char *home,
+                const char *home) {
-                int *exit_status) {
 
         const char *wd;
         int r;
 
         assert(context);
-        assert(exit_status);
 
         if (context->working_directory_home) {
-                if (!home) {
+                if (!home)
-                        *exit_status = EXIT_CHDIR;
                         return -ENXIO;
-                }
 
                 wd = home;
         } else
@@ -3503,13 +3499,7 @@ static int apply_working_directory(
                 if (r >= 0)
                         r = RET_NERRNO(fchdir(dfd));
         }
-
+        return context->working_directory_missing_ok ? 0 : r;
-        if (r < 0 && !context->working_directory_missing_ok) {
-                *exit_status = EXIT_CHDIR;
-                return r;
-        }
-
-        return 0;
 }
 
 static int apply_root_directory(
@@ -3785,7 +3775,7 @@ static int acquire_home(const ExecContext *c, const char **home, char **ret_buf)
         if (!c->working_directory_home)
                 return 0;
 
-        if (c->dynamic_user)
+        if (c->dynamic_user || (c->user && is_this_me(c->user) <= 0))
                 return -EADDRNOTAVAIL;
 
         r = get_home_dir(ret_buf);
@@ -4543,7 +4533,7 @@ int exec_invoke(
         r = acquire_home(context, &home, &home_buffer);
         if (r < 0) {
                 *exit_status = EXIT_CHDIR;
-                return log_exec_error_errno(context, params, r, "Failed to determine $HOME for user: %m");
+                return log_exec_error_errno(context, params, r, "Failed to determine $HOME for the invoking user: %m");
         }
 
         /* If a socket is connected to STDIN/STDOUT/STDERR, we must drop O_NONBLOCK */
@@ -5382,9 +5372,11 @@ int exec_invoke(
          * running this service might have the correct privilege to change to the working directory. Also, it
          * is absolutely 💣 crucial 💣 we applied all mount namespacing rearrangements before this, so that
          * the cwd cannot be used to pin directories outside of the sandbox. */
-        r = apply_working_directory(context, params, runtime, home, exit_status);
+        r = apply_working_directory(context, params, runtime, home);
-        if (r < 0)
+        if (r < 0) {
+                *exit_status = EXIT_CHDIR;
                 return log_exec_error_errno(context, params, r, "Changing to the requested working directory failed: %m");
+        }
 
         if (needs_sandboxing) {
                 /* Apply other MAC contexts late, but before seccomp syscall filtering, as those should really be last to

src/cryptenroll/cryptenroll-fido2.c

@@ -193,7 +193,7 @@ int enroll_fido2(
                 fflush(stdout);
 
                 fprintf(stderr,
-                        "\nPlease save this FIDO2 credential ID. It is required when unloocking the volume\n"
+                        "\nPlease save this FIDO2 credential ID. It is required when unlocking the volume\n"
                         "using the associated FIDO2 keyslot which we just created. To configure automatic\n"
                         "unlocking using this FIDO2 token, add an appropriate entry to your /etc/crypttab\n"
                         "file, see %s for details.\n", link);

src/run/run.c

@@ -2297,7 +2297,8 @@ static int start_transient_scope(sd_bus *bus) {
                 uid_t uid;
                 gid_t gid;
 
-                r = get_user_creds(&arg_exec_user, &uid, &gid, &home, &shell, USER_CREDS_CLEAN|USER_CREDS_PREFER_NSS);
+                r = get_user_creds(&arg_exec_user, &uid, &gid, &home, &shell,
+                                   USER_CREDS_CLEAN|USER_CREDS_SUPPRESS_PLACEHOLDER|USER_CREDS_PREFER_NSS);
                 if (r < 0)
                         return log_error_errno(r, "Failed to resolve user %s: %m", arg_exec_user);
 

src/shared/killall.c

@@ -46,13 +46,17 @@ static bool argv_has_at(pid_t pid) {
         return c == '@';
 }
 
-static bool is_survivor_cgroup(const PidRef *pid) {
+static bool is_in_survivor_cgroup(const PidRef *pid) {
         _cleanup_free_ char *cgroup_path = NULL;
         int r;
 
         assert(pidref_is_set(pid));
 
         r = cg_pidref_get_path(/* root= */ NULL, pid, &cgroup_path);
+        if (r == -EUNATCH) {
+                log_warning_errno(r, "Process " PID_FMT " appears to originate in foreign namespace, ignoring.", pid->pid);
+                return true;
+        }
         if (r < 0) {
                 log_warning_errno(r, "Failed to get cgroup path of process " PID_FMT ", ignoring: %m", pid->pid);
                 return false;
@@ -86,7 +90,7 @@ static bool ignore_proc(const PidRef *pid, bool warn_rootfs) {
                 return true; /* also ignore processes where we can't determine this */
 
         /* Ignore processes that are part of a cgroup marked with the user.survive_final_kill_signal xattr */
-        if (is_survivor_cgroup(pid))
+        if (is_in_survivor_cgroup(pid))
                 return true;
 
         r = pidref_get_uid(pid, &uid);

src/test/test-audit-util.c

@@ -7,24 +7,26 @@ TEST(audit_loginuid_from_pid) {
         _cleanup_(pidref_done) PidRef self = PIDREF_NULL, pid1 = PIDREF_NULL;
         int r;
 
-        assert_se(pidref_set_self(&self) >= 0);
+        ASSERT_OK(pidref_set_self(&self));
-        assert_se(pidref_set_pid(&pid1, 1) >= 0);
+        ASSERT_OK(pidref_set_pid(&pid1, 1));
 
         uid_t uid;
         r = audit_loginuid_from_pid(&self, &uid);
-        assert_se(r >= 0 || r == -ENODATA);
+        if (r != -ENODATA)
+                ASSERT_OK(r);
         if (r >= 0)
                 log_info("self audit login uid: " UID_FMT, uid);
 
-        assert_se(audit_loginuid_from_pid(&pid1, &uid) == -ENODATA);
+        ASSERT_ERROR(audit_loginuid_from_pid(&pid1, &uid), ENODATA);
 
         uint32_t sessionid;
         r = audit_session_from_pid(&self, &sessionid);
-        assert_se(r >= 0 || r == -ENODATA);
+        if (r != -ENODATA)
+                ASSERT_OK(r);
         if (r >= 0)
                 log_info("self audit session id: %" PRIu32, sessionid);
 
-        assert_se(audit_session_from_pid(&pid1, &sessionid) == -ENODATA);
+        ASSERT_ERROR(audit_session_from_pid(&pid1, &sessionid), ENODATA);
 }
 
 static int intro(void) {

test/units/TEST-07-PID1.working-directory.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: LGPL-2.1-or-later
+
+set -eux
+set -o pipefail
+
+# shellcheck source=test/units/util.sh
+. "$(dirname "$0")"/util.sh
+
+(! systemd-run --wait -p DynamicUser=yes \
+                      -p EnvironmentFile=-/usr/lib/systemd/systemd-asan-env \
+                      -p WorkingDirectory='~' true)
+
+assert_eq "$(systemd-run --pipe --uid=root -p WorkingDirectory='~' pwd)" "/root"
+assert_eq "$(systemd-run --pipe --uid=nobody -p WorkingDirectory='~' pwd)" "/"
+assert_eq "$(systemd-run --pipe --uid=testuser -p WorkingDirectory='~' pwd)" "/home/testuser"
+
+(! systemd-run --wait -p DynamicUser=yes -p User=testuser \
+                      -p EnvironmentFile=-/usr/lib/systemd/systemd-asan-env \
+                      -p WorkingDirectory='~' true)

units/systemd-confext.service

@@ -16,6 +16,7 @@ ConditionDirectoryNotEmpty=|/run/confexts
 ConditionDirectoryNotEmpty=|/var/lib/confexts
 ConditionDirectoryNotEmpty=|/usr/local/lib/confexts
 ConditionDirectoryNotEmpty=|/usr/lib/confexts
+ConditionDirectoryNotEmpty=|/.extra/confext
 
 DefaultDependencies=no
 After=local-fs.target