Merge bf2328c714 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.exec.xml

@@ -562,6 +562,13 @@
         To disable the safety check that the extension-release file name matches the image file name, the
         <varname>x-systemd.relax-extension-release-check</varname> mount option may be appended.</para>
 
+        <para>This option can be used together with a <option>notify-reload</option> service type and
+        <citerefentry><refentrytitle>systemd.v</refentrytitle><manvolnum>7</manvolnum></citerefentry>
+        to manage configuration updates. When such a service carrying confext images is reloaded, the confext
+        itself will also be reloaded to pick up any changes. This only applies to confext extensions. See
+        <citerefentry><refentrytitle>systemd.service</refentrytitle><manvolnum>5</manvolnum></citerefentry>
+        also for details.</para>
+
         <para>When <varname>DevicePolicy=</varname> is set to <literal>closed</literal> or
         <literal>strict</literal>, or set to <literal>auto</literal> and <varname>DeviceAllow=</varname> is
         set, then this setting adds <filename>/dev/loop-control</filename> with <constant>rw</constant> mode,
@@ -606,6 +613,14 @@
         or the host. See:
         <citerefentry><refentrytitle>os-release</refentrytitle><manvolnum>5</manvolnum></citerefentry>.</para>
 
+        <para>This option can be used together with a <option>notify-reload</option> service type and
+        <citerefentry><refentrytitle>systemd.v</refentrytitle><manvolnum>7</manvolnum></citerefentry>
+        to manage configuration updates. When such a system service carrying confext directories is reloaded,
+        the confext itself will also be reloaded to pick up any changes. This only applies to confext
+        extensions. See
+        <citerefentry><refentrytitle>systemd.service</refentrytitle><manvolnum>5</manvolnum></citerefentry>
+        also for details.</para>
+
         <para>Note that usage from user units requires overlayfs support in unprivileged user namespaces,
         which was first introduced in kernel v5.11.</para>
 

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) &&
-                             (empty_or_root(p->pw_dir) ||
-                              !path_is_valid(p->pw_dir) ||
-                              !path_is_absolute(p->pw_dir))) ? NULL : p->pw_dir;
+                *ret_home = (FLAGS_SET(flags, USER_CREDS_SUPPRESS_PLACEHOLDER) && empty_or_root(p->pw_dir)) ||
+                            (FLAGS_SET(flags, USER_CREDS_CLEAN) && (!path_is_valid(p->pw_dir) || !path_is_absolute(p->pw_dir)))
+                            ? NULL : p->pw_dir;
 
         if (ret_shell)
-                *ret_shell = (FLAGS_SET(flags, USER_CREDS_CLEAN) &&
-                              (isempty(p->pw_shell) ||
-                               !path_is_valid(p->pw_shell) ||
-                               !path_is_absolute(p->pw_shell) ||
-                               is_nologin_shell(p->pw_shell))) ? NULL : p->pw_shell;
+                *ret_shell = (FLAGS_SET(flags, USER_CREDS_SUPPRESS_PLACEHOLDER) && shell_is_placeholder(p->pw_shell)) ||
+                             (FLAGS_SET(flags, USER_CREDS_CLEAN) && (!path_is_valid(p->pw_shell) || !path_is_absolute(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_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_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_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,
-                int *exit_status) {
+                const char *home) {
 
         const char *wd;
         int r;
 
         assert(context);
-        assert(exit_status);
 
         if (context->working_directory_home) {
-                if (!home) {
-                        *exit_status = EXIT_CHDIR;
+                if (!home)
                         return -ENXIO;
-                }
 
                 wd = home;
         } else
@@ -3503,13 +3499,7 @@ static int apply_working_directory(
                 if (r >= 0)
                         r = RET_NERRNO(fchdir(dfd));
         }
-
-        if (r < 0 && !context->working_directory_missing_ok) {
-                *exit_status = EXIT_CHDIR;
-                return r;
-        }
-
-        return 0;
+        return context->working_directory_missing_ok ? 0 : r;
 }
 
 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);
-        if (r < 0)
+        r = apply_working_directory(context, params, runtime, home);
+        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/core/execute.c

@@ -71,6 +71,7 @@
 #include "unit-serialize.h"
 #include "user-util.h"
 #include "utmp-wtmp.h"
+#include "vpick.h"
 
 static bool is_terminal_input(ExecInput i) {
         return IN_SET(i,
@@ -1938,6 +1939,25 @@ char** exec_context_get_restrict_filesystems(const ExecContext *c) {
         return l ? TAKE_PTR(l) : strv_new(NULL);
 }
 
+int exec_context_has_vpicked_extensions(const ExecContext *context) {
+        int r;
+
+        assert(context);
+
+        FOREACH_ARRAY(mi, context->extension_images, context->n_extension_images) {
+                r = path_uses_vpick(mi->source);
+                if (r != 0)
+                        return r;
+        }
+        STRV_FOREACH(ed, context->extension_directories) {
+                r = path_uses_vpick(*ed);
+                if (r != 0)
+                        return r;
+        }
+
+        return 0;
+}
+
 void exec_status_start(ExecStatus *s, pid_t pid, const dual_timestamp *ts) {
         assert(s);
 

src/core/execute.h

@@ -559,6 +559,8 @@ char** exec_context_get_syscall_log(const ExecContext *c);
 char** exec_context_get_address_families(const ExecContext *c);
 char** exec_context_get_restrict_filesystems(const ExecContext *c);
 
+int exec_context_has_vpicked_extensions(const ExecContext *context);
+
 void exec_status_start(ExecStatus *s, pid_t pid, const dual_timestamp *ts);
 void exec_status_exit(ExecStatus *s, const ExecContext *context, pid_t pid, int code, int status);
 void exec_status_handoff(ExecStatus *s, const struct ucred *ucred, const dual_timestamp *ts);

src/core/namespace.c

@@ -37,6 +37,8 @@
 #include "nulstr-util.h"
 #include "os-util.h"
 #include "path-util.h"
+#include "pidref.h"
+#include "process-util.h"
 #include "selinux-util.h"
 #include "socket-util.h"
 #include "sort-util.h"
@@ -3296,6 +3298,117 @@ bool ns_type_supported(NamespaceType type) {
         return access(ns_proc, F_OK) == 0;
 }
 
+int refresh_extensions_in_namespace(
+                const PidRef *target,
+                const char *hierarchy_env,
+                const NamespaceParameters *p) {
+
+        const char *overlay_prefix = "/run/systemd/mount-rootfs";
+        _cleanup_(mount_list_done) MountList ml = {};
+        _cleanup_free_ char *extension_dir = NULL;
+        _cleanup_strv_free_ char **hierarchies = NULL;
+        MountInNamespaceFlags min_flags = 0;
+        int r;
+
+        assert(pidref_is_set(target));
+        assert(hierarchy_env);
+        assert(p);
+
+        log_debug("Refreshing extensions in-namespace for hierarchy '%s'", hierarchy_env);
+
+        extension_dir = path_join(p->private_namespace_dir, "unit-extensions");
+        if (!extension_dir)
+                return -ENOMEM;
+
+        min_flags |= MOUNT_IN_NAMESPACE_MAKE_FILE_OR_DIRECTORY;
+
+        r = parse_env_extension_hierarchies(&hierarchies, hierarchy_env);
+        if (r < 0)
+                return r;
+
+        r = append_extensions(
+                        &ml,
+                        overlay_prefix,
+                        p->private_namespace_dir,
+                        hierarchies,
+                        p->extension_images,
+                        p->n_extension_images,
+                        p->extension_directories);
+        if (r < 0)
+                return r;
+        if (ml.n_mounts == 0)
+                return 0;
+
+        r = safe_fork("(sd-ns-refresh-exts)",
+                        FORK_DEATHSIG_SIGTERM | FORK_WAIT | FORK_NEW_MOUNTNS | FORK_MOUNTNS_SLAVE,
+                        NULL);
+        if (r < 0)
+                return r;
+        if (r == 0) {
+                (void) mkdir_p_label(overlay_prefix, 0555);
+
+                /* This is effectively two rounds, since all the extensions come before overlays
+                * (setup_namespace() similarly relies on this property).
+                *
+                * (1) First, set up all the extension mounts in the child, which are not visible from the
+                * process. (2) Then, set up overlays for the sysext/confext hierarchies again using the new
+                * extension mounts as layers, and move them into the namespace. */
+                FOREACH_ARRAY(m, ml.mounts, ml.n_mounts) {
+                        if (IN_SET(m->mode, MOUNT_EXTENSION_DIRECTORY, MOUNT_EXTENSION_IMAGE)) {
+                                r = apply_one_mount(p->root_directory, m, p);
+                                if (r < 0) {
+                                        log_debug_errno(r, "Failed to apply extension mount: %m");
+                                        _exit(EXIT_FAILURE);
+                                }
+                        } else if (m->mode == MOUNT_OVERLAY) {
+                                _cleanup_free_ char *path_relative = NULL, *path_in_namespace = NULL;
+
+                                r = apply_one_mount(p->root_directory, m, p);
+                                if (r < 0)
+                                        _exit(EXIT_FAILURE);
+                                if (r == 0) {
+                                        /* Tried to mount overlay, but it is now empty - umount it then. */
+                                        min_flags |= MOUNT_IN_NAMESPACE_UMOUNT;
+                                }
+
+                                /* bind_mount_in_namespace takes a src on the outside and a dest evaluated
+                                * within the namespace. First, figure out where we want the overlay on top
+                                * of within the namespace.
+                                */
+                                r = path_make_relative(overlay_prefix, mount_entry_path(m), &path_relative);
+                                if (r < 0) {
+                                        log_debug_errno(r, "Failed to make path relative: %m");
+                                        _exit(EXIT_FAILURE);
+                                }
+                                r = asprintf(&path_in_namespace, "%s/%s", empty_to_root(p->root_directory), path_relative);
+                                if (r < 0) {
+                                        log_oom_debug();
+                                        _exit(EXIT_FAILURE);
+                                }
+
+                                r = bind_mount_in_namespace(
+                                                target,
+                                                p->propagate_dir,
+                                                p->incoming_dir,
+                                                /* src= */ mount_entry_path(m),
+                                                /* dest= */ path_in_namespace,
+                                                min_flags);
+                                if (r < 0) {
+                                        log_debug_errno(
+                                                        r,
+                                                        "Failed to move overlay within %s->%s: %m",
+                                                        mount_entry_path(m),
+                                                        path_in_namespace);
+                                        _exit(EXIT_FAILURE);
+                                }
+                        }
+                }
+                _exit(EXIT_SUCCESS);
+        }
+
+        return 0;
+}
+
 static const char *const protect_home_table[_PROTECT_HOME_MAX] = {
         [PROTECT_HOME_NO]        = "no",
         [PROTECT_HOME_YES]       = "yes",

src/core/namespace.h

@@ -16,6 +16,7 @@ typedef struct MountImage MountImage;
 #include "fs-util.h"
 #include "macro.h"
 #include "namespace-util.h"
+#include "pidref.h"
 #include "runtime-scope.h"
 #include "string-util.h"
 
@@ -250,3 +251,8 @@ const char* namespace_type_to_string(NamespaceType t) _const_;
 NamespaceType namespace_type_from_string(const char *s) _pure_;
 
 bool ns_type_supported(NamespaceType type);
+
+int refresh_extensions_in_namespace(
+                const PidRef *target,
+                const char *hierarchy_env,
+                const NamespaceParameters *p);

src/core/service.c

@@ -21,6 +21,7 @@
 #include "devnum-util.h"
 #include "env-util.h"
 #include "escape.h"
+#include "execute.h"
 #include "exec-credential.h"
 #include "exit-status.h"
 #include "fd-util.h"
@@ -33,11 +34,13 @@
 #include "manager.h"
 #include "missing_audit.h"
 #include "mount-util.h"
+#include "namespace.h"
 #include "open-file.h"
 #include "parse-util.h"
 #include "path-util.h"
 #include "process-util.h"
 #include "random-util.h"
+#include "runtime-scope.h"
 #include "selinux-util.h"
 #include "serialize.h"
 #include "service.h"
@@ -2709,6 +2712,67 @@ static void service_enter_reload_by_notify(Service *s) {
                 log_unit_warning(UNIT(s), "Failed to schedule propagation of reload, ignoring: %s", bus_error_message(&error, r));
 }
 
+static bool service_should_reload_extensions(Service *s) {
+        int r;
+
+        assert(s);
+
+        /* Only support this for notify-reload service types. */
+        if (s->type != SERVICE_NOTIFY_RELOAD)
+                return false;
+
+        /* TODO: Add support for user services, which can use
+         * ExtensionDirectories= + notify-reload. For now, skip for user
+         * services. */
+        if (UNIT(s)->manager->runtime_scope != RUNTIME_SCOPE_SYSTEM) {
+                log_unit_debug(UNIT(s), "Not reloading extensions for user services.");
+                return false;
+        }
+
+        r = exec_context_has_vpicked_extensions(&s->exec_context);
+        if (r < 0) {
+                log_unit_warning_errno(UNIT(s), r, "Failed to determine if service should reload extensions, assuming false: %m");
+                return false;
+        }
+        return r > 0;
+}
+
+static int service_reload_extensions(Service *s) {
+        /* TODO: do this asynchronously */
+        _cleanup_free_ char *propagate_dir = NULL;
+
+        assert(s);
+
+        /* TODO: remove after adding support for user services */
+        assert(UNIT(s)->manager->runtime_scope == RUNTIME_SCOPE_SYSTEM);
+
+        if (!service_should_reload_extensions(s))
+                return 0;
+
+        propagate_dir = path_join("/run/systemd/propagate/", UNIT(s)->id);
+        if (!propagate_dir)
+                return -ENOMEM;
+
+        NamespaceParameters p = {
+                .private_namespace_dir = "/run/systemd",
+                .incoming_dir = "/run/systemd/incoming",
+                .propagate_dir = propagate_dir,
+                .runtime_scope = UNIT(s)->manager->runtime_scope,
+                .root_directory =  s->exec_context.root_directory,
+                .extension_images = s->exec_context.extension_images,
+                .n_extension_images = s->exec_context.n_extension_images,
+                .extension_directories = s->exec_context.extension_directories,
+                .extension_image_policy = s->exec_context.extension_image_policy
+        };
+
+        /* Only reload confext, and not sysext, because it doesn't make sense
+        for program code to be swapped at reload. */
+        return refresh_extensions_in_namespace(
+                        unit_main_pid(UNIT(s)),
+                        "SYSTEMD_CONFEXT_HIERARCHIES",
+                        &p);
+}
+
 static void service_enter_reload(Service *s) {
         bool killed = false;
         int r;
@@ -2720,6 +2784,14 @@ static void service_enter_reload(Service *s) {
 
         usec_t ts = now(CLOCK_MONOTONIC);
 
+        /* If we have confexts extensions, try to reload vpick'd confext extensions, which is particularly
+         * beneficial for notify-reload services that could potentially pick up a new version of its
+         * configuration.
+         */
+        r = service_reload_extensions(s);
+        if (r < 0)
+                log_unit_warning_errno(UNIT(s), r, "Failed to reload confexts, ignoring: %m");
+
         if (s->type == SERVICE_NOTIFY_RELOAD && pidref_is_set(&s->main_pid)) {
                 r = pidref_kill_and_sigcont(&s->main_pid, s->reload_signal);
                 if (r < 0) {

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/shared/mount-util.c

@@ -1132,7 +1132,7 @@ static int mount_in_namespace(
         _cleanup_close_pair_ int errno_pipe_fd[2] = EBADF_PAIR;
         pid_t child;
 
-        if (flags & MOUNT_IN_NAMESPACE_IS_IMAGE) {
+        if (!(flags & MOUNT_IN_NAMESPACE_UMOUNT) && flags & MOUNT_IN_NAMESPACE_IS_IMAGE) {
                 r = verity_dissect_and_mount(
                                 chased_src_fd,
                                 chased_src_path,
@@ -1150,7 +1150,7 @@ static int mount_in_namespace(
                         return log_debug_errno(r,
                                                "Failed to dissect and mount image '%s': %m",
                                                chased_src_path);
-        } else {
+        } else if (!(flags & MOUNT_IN_NAMESPACE_UMOUNT)) {
                 new_mount_fd = open_tree(
                                 chased_src_fd,
                                 "",
@@ -1189,6 +1189,18 @@ static int mount_in_namespace(
         if (r == 0) {
                 errno_pipe_fd[0] = safe_close(errno_pipe_fd[0]);
 
+                if (flags & MOUNT_IN_NAMESPACE_UMOUNT) {
+                        r = umount_verbose(LOG_DEBUG, dest, UMOUNT_NOFOLLOW);
+                        if (r < 0) {
+                                (void) write(errno_pipe_fd[1], &r, sizeof(r));
+                                errno_pipe_fd[1] = safe_close(errno_pipe_fd[1]);
+
+                                _exit(EXIT_FAILURE);
+                        }
+
+                        _exit(EXIT_SUCCESS);
+                }
+
                 if (flags & MOUNT_IN_NAMESPACE_MAKE_FILE_OR_DIRECTORY)
                         (void) mkdir_parents(dest, 0755);
 

src/shared/mount-util.h

@@ -119,6 +119,7 @@ typedef enum MountInNamespaceFlags {
         MOUNT_IN_NAMESPACE_READ_ONLY              = 1 << 0,
         MOUNT_IN_NAMESPACE_MAKE_FILE_OR_DIRECTORY = 1 << 1,
         MOUNT_IN_NAMESPACE_IS_IMAGE               = 1 << 2,
+        MOUNT_IN_NAMESPACE_UMOUNT                 = 1 << 3,
 } MountInNamespaceFlags;
 
 int bind_mount_in_namespace(

src/shared/vpick.c

@@ -681,6 +681,41 @@ int path_pick_update_warn(
         return 1;
 }
 
+int path_uses_vpick(const char *path) {
+        _cleanup_free_ char *dir = NULL, *parent = NULL, *fname = NULL;
+        int r;
+
+        assert(path);
+
+        r = path_extract_filename(path, &fname);
+        if (r == -EADDRNOTAVAIL)
+                return 0;
+        if (r < 0)
+                return r;
+
+        /* ...PATH/NAME.SUFFIX.v */
+        if (endswith(fname, ".v"))
+                return 1;
+
+        /* ...PATH.v/NAME___.SUFFIX */
+        if (!strrstr(fname, "___"))
+                return 0;
+
+        r = path_extract_directory(path, &dir);
+        if (IN_SET(r, -EDESTADDRREQ, -EADDRNOTAVAIL)) /* only filename specified (no dir), or root or "." */
+                return 0;
+        if (r < 0)
+                return r;
+
+        r = path_extract_filename(dir, &parent);
+        if (r == -EADDRNOTAVAIL)
+                return 0;
+        if (r < 0)
+                return r;
+
+        return !!endswith(parent, ".v");
+}
+
 const PickFilter pick_filter_image_raw = {
         .type_mask = (UINT32_C(1) << DT_REG) | (UINT32_C(1) << DT_BLK),
         .architecture = _ARCHITECTURE_INVALID,

src/shared/vpick.h

@@ -56,6 +56,8 @@ int path_pick_update_warn(
                 PickFlags flags,
                 PickResult *ret);
 
+int path_uses_vpick(const char *path);
+
 extern const PickFilter pick_filter_image_raw;
 extern const PickFilter pick_filter_image_dir;
 extern const PickFilter pick_filter_image_any;

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_se(pidref_set_pid(&pid1, 1) >= 0);
+        ASSERT_OK(pidref_set_self(&self));
+        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) {

src/test/test-vpick.c

@@ -168,4 +168,27 @@ TEST(path_pick) {
         assert_se(result.architecture == ARCHITECTURE_S390);
 }
 
+TEST(path_uses_vpick) {
+        assert_se(path_uses_vpick("foo.v") > 0);
+        assert_se(path_uses_vpick("path/to/foo.v") > 0);
+        assert_se(path_uses_vpick("./path/to/foo.v") > 0);
+        assert_se(path_uses_vpick("path/to.v/foo.v") > 0);
+        assert_se(path_uses_vpick("path/to/foo.raw.v") > 0);
+        assert_se(path_uses_vpick("/var/lib/machines/mymachine.raw.v/") > 0);
+        assert_se(path_uses_vpick("path/to.v/foo___.hi/a.v") > 0);
+        assert_se(!path_uses_vpick("path/to/foo.mp4.vtt"));
+        assert_se(!path_uses_vpick("path/to/foo.mp4.v.1"));
+        assert_se(!path_uses_vpick("path/to.v/a"));
+
+        assert_se(path_uses_vpick("to.v/foo___.raw") > 0);
+        assert_se(path_uses_vpick("path/to.v/foo___.raw") > 0);
+        assert_se(!path_uses_vpick("path/to/foo___.raw"));
+        assert_se(!path_uses_vpick("path/to.v/foo__"));
+        assert_se(!path_uses_vpick("foo___.raw"));
+
+        assert_se(path_uses_vpick("/") < 1);
+        assert_se(path_uses_vpick(".") < 1);
+        assert_se(path_uses_vpick("") < 1);
+}
+
 DEFINE_TEST_MAIN(LOG_DEBUG);

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)

test/units/TEST-50-DISSECT.dissect.sh

@@ -518,6 +518,72 @@ rm -rf "$VDIR" "$EMPTY_VDIR"
 systemd-dissect --umount "$IMAGE_DIR/app0"
 systemd-dissect --umount "$IMAGE_DIR/app1"
 
+# Check reloading refreshes vpick extensions
+VBASE="vtest$RANDOM"
+VDIR="/tmp/${VBASE}.v"
+mkdir "$VDIR"
+cat >/run/systemd/system/testservice-50g.service <<EOF
+[Service]
+Type=notify-reload
+EnvironmentFile=-/usr/lib/systemd/systemd-asan-env
+ExtensionDirectories=${VDIR}
+ExecStart=bash -c ' \\
+    trap "{ \\
+        systemd-notify --reloading; \\
+        ls /etc | grep marker; \\
+        systemd-notify --ready; \\
+    }" SIGHUP; \\
+    systemd-notify --ready; \\
+    while true; do sleep 1; done; \\
+'
+EOF
+mkdir -p "$VDIR/${VBASE}_1/etc/extension-release.d/"
+echo "ID=_any" >"$VDIR/${VBASE}_1/etc/extension-release.d/extension-release.${VBASE}_1"
+touch "$VDIR/${VBASE}_1/etc/${VBASE}_1.marker"
+systemctl start testservice-50g.service
+systemctl is-active testservice-50g.service
+# First reload; at reload time, the marker file in /etc should be picked up.
+systemctl try-reload-or-restart testservice-50g.service
+journalctl -b -u testservice-50g | grep -q -F "${VBASE}_1.marker"
+# Make a version 2 and reload again; this time we should see the v2 marker
+mkdir -p "$VDIR/${VBASE}_2/etc/extension-release.d/"
+echo "ID=_any" >"$VDIR/${VBASE}_2/etc/extension-release.d/extension-release.${VBASE}_2"
+touch "$VDIR/${VBASE}_2/etc/${VBASE}_2.marker"
+systemctl try-reload-or-restart testservice-50g.service
+journalctl --sync
+journalctl -b -u testservice-50g | grep -q -F "${VBASE}_2.marker"
+# Do it for a couple more times (to make sure we're tearing down old overlays)
+for _ in {1..5}; do systemctl reload testservice-50g.service; done
+systemctl stop testservice-50g.service
+
+# Repeat the same vpick notify-reload test with ExtensionImages= (keeping the
+# same VBASE and reusing VDIR files for convenience, but using .raw extensions
+# this time)
+VDIR2="/tmp/${VBASE}.raw.v"
+mkdir "$VDIR2"
+cp /run/systemd/system/testservice-50g.service /run/systemd/system/testservice-50h.service
+sed -i "s%ExtensionDirectories=.*%ExtensionImages=$VDIR2%g" \
+    /run/systemd/system/testservice-50h.service
+mksquashfs "$VDIR/${VBASE}_1" "$VDIR2/${VBASE}_1.raw"
+systemctl start testservice-50h.service
+systemctl is-active testservice-50h.service
+# First reload should pick up the v1 marker
+systemctl try-reload-or-restart testservice-50h.service
+journalctl --sync
+journalctl -b -u testservice-50h | grep -q -F "${VBASE}_1.marker"
+# Second reload should pick up the v2 marker
+mksquashfs "$VDIR/${VBASE}_2" "$VDIR2/${VBASE}_2.raw"
+systemctl try-reload-or-restart testservice-50h.service
+journalctl --sync
+journalctl -b -u testservice-50h | grep -q -F "${VBASE}_2.marker"
+# Test that removing all the extensions don't cause any issues
+rm -rf "${VDIR2:?}"/*
+systemctl try-reload-or-restart testservice-50h.service
+systemctl is-active testservice-50h.service
+systemctl stop testservice-50h.service
+
+rm -rf "$VDIR" "$VDIR2"
+
 # Test that an extension consisting of an empty directory under /etc/extensions/ takes precedence
 mkdir -p /var/lib/extensions/
 ln -s /tmp/app-nodistro.raw /var/lib/extensions/app-nodistro.raw

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