systemd: add hardware watchdog support

This adds minimal hardware watchdog support to PID 1. The idea is that
PID 1 supervises and watchdogs system services, while the hardware
watchdog is used to supervise PID 1.

This adds two hardware watchdog configuration options, for the runtime
watchdog and for a shutdown watchdog. The former is active during normal
operation, the latter only at reboots to ensure that if a clean reboot
times out we reboot nonetheless.

If the runtime watchdog is enabled PID 1 will automatically wake up at
half the configured interval and write to the watchdog daemon.

By default we enable the shutdown watchdog, but leave the runtime
watchdog disabled in order not to break independent hardware watchdog
daemons people might be using.

This is only the most basic hookup. If necessary we can later on hook
up the watchdog ping more closely with services deemed crucial.

1 files changed, 7 insertions, 1 deletions

diff --git a/src/shutdown.c b/src/shutdown.c
index d157e0fbf..9f65b1dab 100644
--- a/src/shutdown.c
+++ b/src/shutdown.c
@@ -42,6 +42,7 @@
 #include "umount.h"
 #include "util.h"
 #include "virt.h"
+#include "watchdog.h"
 
 #define TIMEOUT_USEC (5 * USEC_PER_SEC)
 #define FINALIZE_ATTEMPTS 50
@@ -306,7 +307,7 @@ int main(int argc, char *argv[]) {
         int cmd, r;
         unsigned retries;
         bool need_umount = true, need_swapoff = true, need_loop_detach = true, need_dm_detach = true;
-        bool killed_everbody = false, in_container;
+        bool killed_everbody = false, in_container, use_watchdog = false;
 
         log_parse_environment();
         log_set_target(LOG_TARGET_CONSOLE); /* syslog will die if not gone yet */
@@ -342,6 +343,8 @@ int main(int argc, char *argv[]) {
                 goto error;
         }
 
+        use_watchdog = !!getenv("WATCHDOG_USEC");
+
         /* lock us into memory */
         if (mlockall(MCL_CURRENT|MCL_FUTURE) != 0)
                 log_warning("Cannot lock process memory: %m");
@@ -359,6 +362,9 @@ int main(int argc, char *argv[]) {
         for (retries = 0; retries < FINALIZE_ATTEMPTS; retries++) {
                 bool changed = false;
 
+                if (use_watchdog)
+                        watchdog_ping();
+
                 if (need_umount) {
                         log_info("Unmounting file systems.");
                         r = umount_all(&changed);