core: add support for a configurable system-wide start-up timeout

When this system-wide start-up timeout is hit we execute one of the
failure actions already implemented for services that fail.

This should not only be useful on embedded devices, but also on laptops
which have the power-button reachable when the lid is closed. This
devices, when in a backpack might get powered on by accident due to the
easily reachable power button. We want to make sure that the system
turns itself off if it starts up due this after a while.

When the system manages to fully start-up logind will suspend the
machine by default if the lid is closed. However, in some cases we don't
even get as far as logind, and the boot hangs much earlier, for example
because we ask for a LUKS password that nobody ever enters.

Yeah, this is a real-life problem on my Yoga 13, which has one of those
easily accessible power buttons, even if the device is closed.

1 files changed, 39 insertions, 4 deletions

diff --git a/src/core/manager.c b/src/core/manager.c
index 7401817844..1bb0c9025f 100644
--- a/src/core/manager.c
+++ b/src/core/manager.c
@@ -435,6 +435,8 @@ int manager_new(SystemdRunningAs running_as, bool test_run, Manager **_m) {
         m->running_as = running_as;
         m->exit_code = _MANAGER_EXIT_CODE_INVALID;
         m->default_timer_accuracy_usec = USEC_PER_MINUTE;
+        m->start_timeout_usec = DEFAULT_MANAGER_START_TIMEOUT_USEC;
+        m->start_timeout_action = FAILURE_ACTION_REBOOT_FORCE;
 
         m->idle_pipe[0] = m->idle_pipe[1] = m->idle_pipe[2] = m->idle_pipe[3] = -1;
 
@@ -823,6 +825,9 @@ void manager_free(Manager *m) {
 
         manager_close_idle_pipe(m);
 
+        sd_event_source_unref(m->start_timeout_event_source);
+        free(m->start_timeout_reboot_arg);
+
         udev_unref(m->udev);
         sd_event_unref(m->event);
 
@@ -970,6 +975,20 @@ static int manager_distribute_fds(Manager *m, FDSet *fds) {
         return 0;
 }
 
+static int on_start_timeout(sd_event_source *s, usec_t usec, void *userdata) {
+        Manager *m = userdata;
+
+        assert(s);
+        assert(m);
+
+        m->start_timeout_event_source = sd_event_source_unref(m->start_timeout_event_source);
+
+        log_error("Startup timed out.");
+
+        failure_action(m, m->start_timeout_action, m->start_timeout_reboot_arg);
+        return 0;
+}
+
 int manager_startup(Manager *m, FILE *serialization, FDSet *fds) {
         int r, q;
 
@@ -1042,6 +1061,22 @@ int manager_startup(Manager *m, FILE *serialization, FDSet *fds) {
                 m->send_reloading_done = true;
         }
 
+        /* Possibly set up a start timeout */
+        if (!dual_timestamp_is_set(&m->finish_timestamp)) {
+                m->start_timeout_event_source = sd_event_source_unref(m->start_timeout_event_source);
+
+                if (m->start_timeout_usec) {
+                        r = sd_event_add_time(
+                                        m->event,
+                                        &m->start_timeout_event_source,
+                                        CLOCK_MONOTONIC,
+                                        now(CLOCK_MONOTONIC) + m->start_timeout_usec, 0,
+                                        on_start_timeout, m);
+                        if (r < 0)
+                                log_error("Failed to add start timeout event: %s", strerror(-r));
+                }
+        }
+
         return r;
 }
 
@@ -2462,10 +2497,8 @@ void manager_check_finished(Manager *m) {
 
         if (hashmap_size(m->jobs) > 0) {
 
-                if (m->jobs_in_progress_event_source) {
-                        sd_event_source_set_time(m->jobs_in_progress_event_source,
-                                                 now(CLOCK_MONOTONIC) + JOBS_IN_PROGRESS_WAIT_USEC);
-                }
+                if (m->jobs_in_progress_event_source)
+                        sd_event_source_set_time(m->jobs_in_progress_event_source, now(CLOCK_MONOTONIC) + JOBS_IN_PROGRESS_WAIT_USEC);
 
                 return;
         }
@@ -2487,6 +2520,8 @@ void manager_check_finished(Manager *m) {
 
         dual_timestamp_get(&m->finish_timestamp);
 
+        m->start_timeout_event_source = sd_event_source_unref(m->start_timeout_event_source);
+
         if (m->running_as == SYSTEMD_SYSTEM && detect_container(NULL) <= 0) {
 
                 /* Note that m->kernel_usec.monotonic is always at 0,