core: create per-user inaccessible node from the service manager

Previously, we'd create them from user-runtime-dir@.service. That has
one benefit: since this service runs privileged, we can create the full
set of device nodes. It has one major drawback though: it security-wise
problematic to create files/directories in directories as privileged
user in directories owned by unprivileged users, since they can use
symlinks to redirect what we want to do. As a general rule we hence
avoid this logic: only unpriv code should populate unpriv directories.

Hence, let's move this code to an appropriate place in the service
manager. This means we lose the inaccessible block device node, but
since there's already a fallback in place, this shouldn't be too bad.

(cherry picked from commit 3242980582d501ec2adbcc0f794c7161056812e8)

diff --git a/src/core/main.c b/src/core/main.c
index 4a376976e94f987c416a60fe26e6c3f48bb8d142..9a834a875e8f239cf5ef2f559e06b539196f05ad 100644 (file)
--- a/src/core/main.c
+++ b/src/core/main.c
@@ -32,6 +32,7 @@
 #include "dbus-manager.h"
 #include "dbus.h"
 #include "def.h"
+#include "dev-setup.h"
 #include "efi-random.h"
 #include "efivars.h"
 #include "emergency-action.h"
@@ -53,6 +54,7 @@
 #include "loopback-setup.h"
 #include "machine-id-setup.h"
 #include "manager.h"
+#include "mkdir.h"
 #include "mount-setup.h"
 #include "os-util.h"
 #include "pager.h"
@@ -2073,6 +2075,20 @@ static int initialize_runtime(
                         if (r < 0)
                                 log_warning_errno(r, "Failed to set watchdog device to %s, ignoring: %m", arg_watchdog_device);
                 }
+        } else {
+                _cleanup_free_ char *p = NULL;
+
+                /* Create the runtime directory and place the inaccessible device nodes there, if we run in
+                 * user mode. In system mode mount_setup() already did that. */
+
+                r = xdg_user_runtime_dir(&p, "/systemd");
+                if (r < 0) {
+                        *ret_error_message = "$XDG_RUNTIME_DIR is not set";
+                        return log_emergency_errno(r, "Failed to determine $XDG_RUNTIME_DIR path: %m");
+                }
+
+                (void) mkdir_p(p, 0755);
+                (void) make_inaccessible_nodes(p, UID_INVALID, GID_INVALID);
         }
 
         if (arg_timer_slack_nsec != NSEC_INFINITY)

diff --git a/src/login/user-runtime-dir.c b/src/login/user-runtime-dir.c
index fcddbc7df676aee3bb74d26ef58284479ef9330f..03c60f90b3d112f8c128e3b7c66f710294583f31 100644 (file)
--- a/src/login/user-runtime-dir.c
+++ b/src/login/user-runtime-dir.c
@@ -54,7 +54,6 @@ static int user_mkdir_runtime_path(
                 uint64_t runtime_dir_size,
                 uint64_t runtime_dir_inodes) {
 
-        const char *p;
         int r;
 
         assert(runtime_path);
@@ -89,7 +88,8 @@ static int user_mkdir_runtime_path(
                                 goto fail;
                         }
 
-                        log_debug_errno(errno, "Failed to mount per-user tmpfs directory %s.\n"
+                        log_debug_errno(errno,
+                                        "Failed to mount per-user tmpfs directory %s.\n"
                                         "Assuming containerized execution, ignoring: %m", runtime_path);
 
                         r = chmod_and_chown(runtime_path, 0700, uid, gid);
@@ -104,10 +104,6 @@ static int user_mkdir_runtime_path(
                         log_warning_errno(r, "Failed to fix label of \"%s\", ignoring: %m", runtime_path);
         }
 
-        /* Set up inaccessible nodes now so they're available if we decide to use them with user namespaces. */
-        p = strjoina(runtime_path, "/systemd");
-        (void) mkdir(p, 0755);
-        (void) make_inaccessible_nodes(p, uid, gid);
         return 0;
 
 fail: