Add cleanup:script support, runs at service removal

Signed-off-by: Joachim Wiberg <troglobit@gmail.com>

doc/config.md

@@ -899,19 +899,20 @@ e.g., `halt:SIGPWR`.  To change the delay between the stop signal and
 KILL, use the option `kill:<1-60>`, e.g., `kill:10` to wait 10 seconds
 before sending `SIGKILL`.
 
-Services, including the `sysv` variant, support pre/post/ready scripts:
+Services, including the `sysv` variant, support pre/post/ready and
+cleanup scripts:
 
-  * `pre:[0-3600,]script`
-  * `post:[0-3600,]script`
-  * `ready:[0-3600,]script`
+  * `pre:[0-3600,]script` -- called before the sysv/service is stated
+  * `post:[0-3600,]script` -- called after the sysv/service has stopped
+  * `ready:[0-3600,]script` -- called when the sysv/service is ready
+  * `cleanup:[0-3600,]script` -- called when run/task/sysv/service is removed
 
 The optional number (0-3600) is the timeout before Finit kills the
 script, it defaults to the kill delay value and can be disabled by
 setting it to zero.  These scripts run as the same `@USER:GROUP` as the
-service itself, with any `env:file` sourced.  The scripts must use an
-absolute path, but are executed from the `$HOME` of the given user.  The
-scripts are not called with any argument, but get a set of environment
-variables:
+service itself, with any `env:file` sourced.  The scripts are executed
+from the `$HOME` of the given user.  The scripts are not called with any
+argument, but get a set of environment variables:
 
   * `SERVICE_IDENT=foo:1`
   * `SERVICE_NAME=foo`
@@ -925,6 +926,11 @@ variables:
    the program, if it exited normally, or the signal name (`HUP`,
    `TERM`, etc.) if it exited due to signal
 
+When a run/task/sys/service is removed (disable + reload) it is first
+stopped and then removed from the runlevel.  The `post:script` always
+runs when the process has stopped, and the `cleanup:script` runs when
+the the stanza has been removed from the runlevel.
+
 > [!IMPORTANT]
 > These script actions are intended for setup, cleanup, and readiness
 > notification.  It is up to the user to ensure the scripts terminate.

src/service.c

@@ -1524,6 +1524,7 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 	char *id = NULL, *env = NULL, *cgroup = NULL;
 	char *pre_script = NULL, *post_script = NULL;
 	char *ready_script = NULL, *conflict = NULL;
+	char *cleanup_script = NULL;
 	char ident[MAX_IDENT_LEN];
 	char *ifstmt = NULL;
 	char *notify = NULL;
@@ -1630,6 +1631,8 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 			post_script = arg;
 		else if (MATCH_CMD(cmd, "ready:", arg))
 			ready_script = arg;
+		else if (MATCH_CMD(cmd, "cleanup:", arg))
+			cleanup_script = arg;
 		else if (MATCH_CMD(cmd, "env:", arg))
 			env = arg;
 		/* catch both cgroup: and cgroup. handled in parse_cgroup() */
@@ -1817,6 +1820,11 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 		parse_script(svc, "ready", ready_script, &svc->ready_tmo, svc->ready_script, sizeof(svc->ready_script));
 	else
 		memset(svc->ready_script, 0, sizeof(svc->ready_script));
+	if (cleanup_script)
+		parse_script(svc, "cleanup", cleanup_script, &svc->cleanup_tmo, svc->cleanup_script, sizeof(svc->cleanup_script));
+	else
+		memset(svc->cleanup_script, 0, sizeof(svc->cleanup_script));
+
 	if (!svc_is_tty(svc)) {
 		if (log)
 			parse_log(svc, log);
@@ -1916,8 +1924,8 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 }
 
 /*
- * This function is called when cleaning up lingering (stopped) services
- * after a .conf reload.
+ * This function is called at the end of a runlevel change or reload
+ * command to delete all remnants of removed services.
  *
  * We need to ensure we properly stop the service before removing it,
  * including stopping any pending restart or SIGKILL timers before we
@@ -1962,10 +1970,14 @@ void service_monitor(pid_t lost, int status)
 		/* If the setup phase fails, drive svc to crashed. */
 		svc->status = status;
 		/* fallthrough */
+	case SVC_TEARDOWN_STATE:
 	case SVC_CLEANUP_STATE:
 		dbg("collected script %s(%d), normal exit: %d, signaled: %d, exit code: %d",
-		   svc->state == SVC_CLEANUP_STATE ? svc->post_script : svc->pre_script,
-		   lost, ok, sig, rc);
+		    (svc->state == SVC_TEARDOWN_STATE
+		     ? svc->post_script
+		     : (svc->state == SVC_CLEANUP_STATE
+			? svc->cleanup_script
+			: svc->pre_script)), lost, ok, sig, rc);
 		/* Kill all children in the same proess group, e.g. logit */
 		dbg("Killing lingering children in same process group ...");
 		kill(-svc->pid, SIGKILL);
@@ -2245,6 +2257,41 @@ void service_ready_script(svc_t *svc)
 	service_script_add(svc, pid, svc->ready_tmo);
 }
 
+static void service_cleanup_script(svc_t *svc)
+{
+	svc->pid = service_fork(svc);
+	if (svc->pid < 0) {
+		err(1, "Failed forking off %s cleanup:script %s", svc_ident(svc, NULL, 0), svc->cleanup_script);
+		return;
+	}
+
+	if (svc->pid == 0) {
+		char buf[CMD_SIZE];
+		char *argv[4] = {
+			"sh",
+			"-ac",
+			buf,
+			NULL
+		};
+		char *env_file;
+
+		redirect(svc);
+
+		env_file = svc_getenv(svc);
+		if (env_file)
+			snprintf(buf, sizeof(buf), ". %s; exec %s", env_file, svc->cleanup_script);
+		else
+			strlcpy(buf, svc->cleanup_script, sizeof(buf));
+
+		set_pre_post_envs(svc, "cleanup");
+		execvp(_PATH_BSHELL, argv);
+		_exit(EX_OSERR);
+	}
+
+	dbg("%s: cleanup:script %s started as PID %d", svc_ident(svc, NULL, 0), svc->cleanup_script, svc->pid);
+	service_timeout_after(svc, svc->cleanup_tmo, service_kill_script);
+}
+
 static void service_retry(svc_t *svc)
 {
 	char *restart_cnt = (char *)&svc->restart_cnt;
@@ -2431,6 +2478,11 @@ restart:
 	   condstr(cond_get_agg(svc->cond)));
 
 	switch (svc->state) {
+	case SVC_CLEANUP_STATE:
+		if (!svc->pid)
+			svc_set_state(svc, SVC_HALTED_STATE);
+		break;
+
 	case SVC_HALTED_STATE:
 		if (enabled)
 			svc_set_state(svc, SVC_WAITING_STATE);
@@ -2469,7 +2521,7 @@ restart:
 			case SVC_TYPE_SYSV:
 			case SVC_TYPE_TTY:
 				if (svc_has_post(svc)) {
-					svc_set_state(svc, SVC_CLEANUP_STATE);
+					svc_set_state(svc, SVC_TEARDOWN_STATE);
 					service_post_script(svc);
 				} else
 					svc_set_state(svc, SVC_HALTED_STATE);
@@ -2489,9 +2541,14 @@ restart:
 		}
 		break;
 
-	case SVC_CLEANUP_STATE:
-		if (!svc->pid)
-			svc_set_state(svc, SVC_HALTED_STATE);
+	case SVC_TEARDOWN_STATE:
+		if (!svc->pid) {
+			if (svc_is_removed(svc) && svc_has_cleanup(svc)) {
+				svc_set_state(svc, SVC_CLEANUP_STATE);
+				service_cleanup_script(svc);
+			} else
+				svc_set_state(svc, SVC_HALTED_STATE);
+		}
 		break;
 
 	case SVC_SETUP_STATE:

src/svc.h

@@ -59,8 +59,9 @@ typedef enum {
 	SVC_HALTED_STATE = 0,	/* Not allowed in runlevel, or not enabled. */
 	SVC_DONE_STATE,		/* Task/Run job has been run */
 	SVC_STOPPING_STATE,	/* Waiting to collect the child process */
-	SVC_CLEANUP_STATE,	/* Running post: script */
 	SVC_SETUP_STATE,	/* Running pre: script */
+	SVC_TEARDOWN_STATE,	/* Running post: script */
+	SVC_CLEANUP_STATE,	/* Running cleanup: script */
 	SVC_PAUSED_STATE,	/* Condition is in flux, process SIGSTOPed */
 	SVC_WAITING_STATE,	/* Enabled but condition not satisfied */
 	SVC_STARTING_STATE,	/* Conditions OK and pre: script done, start */
@@ -196,13 +197,19 @@ typedef struct svc {
 	char           conflict[MAX_ARG_LEN];
 	char	       desc[MAX_STR_LEN];
 	char	       env[MAX_CMD_LEN];
+
 	char	       pre_script[MAX_CMD_LEN];
 	int	       pre_tmo;
+
 	char	       post_script[MAX_CMD_LEN];
 	int	       post_tmo;
+
 	char	       ready_script[MAX_CMD_LEN];
 	int	       ready_tmo;
 
+	char	       cleanup_script[MAX_CMD_LEN];
+	int	       cleanup_tmo;
+
 	/*
 	 * Used to forcefully kill services that won't shutdown on
 	 * termination and to delay restarts of crashing services.
@@ -270,6 +277,7 @@ static inline int svc_has_pidfile  (svc_t *svc) { return svc_is_daemon(svc) && s
 static inline int svc_has_pre      (svc_t *svc) { return svc->pre_script[0];  }
 static inline int svc_has_post     (svc_t *svc) { return svc->post_script[0]; }
 static inline int svc_has_ready    (svc_t *svc) { return svc->ready_script[0];}
+static inline int svc_has_cleanup  (svc_t *svc) { return svc->cleanup_script[0]; }
 
 static inline void svc_starting    (svc_t *svc) { if (svc) svc->starting = 1;       }
 static inline void svc_started     (svc_t *svc) { if (svc) svc->starting = 0;       }
@@ -390,12 +398,15 @@ static inline char *svc_status(svc_t *svc)
 			return "stopping";
 		}
 
-	case SVC_CLEANUP_STATE:
-		return "cleanup";
+	case SVC_TEARDOWN_STATE:
+		return "teardown";
 
 	case SVC_SETUP_STATE:
 		return "setup";
 
+	case SVC_CLEANUP_STATE:
+		return "setup";
+
 	case SVC_PAUSED_STATE:
 		return "paused";