core: use an AF_UNIX/SOCK_DGRAM socket for cgroup agent notification

dbus-daemon currently uses a backlog of 30 on its D-bus system bus socket. On
overloaded systems this means that only 30 connections may be queued without
dbus-daemon processing them before further connection attempts fail. Our
cgroups-agent binary so far used D-Bus for its messaging, and hitting this
limit hence may result in us losing cgroup empty messages.

This patch adds a seperate cgroup agent socket of type AF_UNIX/SOCK_DGRAM.
Since sockets of these types need no connection set up, no listen() backlog
applies. Our cgroup-agent binary will hence simply block as long as it can't
enqueue its datagram message, so that we won't lose cgroup empty messages as
likely anymore.

This also rearranges the ordering of the processing of SIGCHLD signals, service
notification messages (sd_notify()...) and the two types of cgroup
notifications (inotify for the unified hierarchy support, and agent for the
classic hierarchy support). We now always process events for these in the
following order:

  1. service notification messages  (SD_EVENT_PRIORITY_NORMAL-7)
  2. SIGCHLD signals (SD_EVENT_PRIORITY_NORMAL-6)
  3. cgroup inotify and cgroup agent (SD_EVENT_PRIORITY_NORMAL-5)

This is because when receiving SIGCHLD we invalidate PID information, which we
need to process the service notification messages which are bound to PIDs.
Hence the order between the first two items. And we want to process SIGCHLD
metadata to detect whether a service is gone, before using cgroup
notifications, to decide when a service is gone, since the former carries more
useful metadata.

Related to this:
https://bugs.freedesktop.org/show_bug.cgi?id=95264
https://github.com/systemd/systemd/issues/1961

1 files changed, 25 insertions, 23 deletions

diff --git a/src/cgroups-agent/cgroups-agent.c b/src/cgroups-agent/cgroups-agent.c
index aadfba0707..333ce110d3 100644
--- a/src/cgroups-agent/cgroups-agent.c
+++ b/src/cgroups-agent/cgroups-agent.c
@@ -18,15 +18,22 @@
 ***/
 
 #include <stdlib.h>
+#include <sys/socket.h>
 
-#include "sd-bus.h"
-
-#include "bus-util.h"
+#include "fd-util.h"
 #include "log.h"
+#include "socket-util.h"
 
 int main(int argc, char *argv[]) {
-        _cleanup_(sd_bus_flush_close_unrefp) sd_bus *bus = NULL;
-        int r;
+
+        static const union sockaddr_union sa = {
+                .un.sun_family = AF_UNIX,
+                .un.sun_path = "/run/systemd/cgroups-agent",
+        };
+
+        _cleanup_close_ int fd = -1;
+        ssize_t n;
+        size_t l;
 
         if (argc != 2) {
                 log_error("Incorrect number of arguments.");
@@ -37,27 +44,22 @@ int main(int argc, char *argv[]) {
         log_parse_environment();
         log_open();
 
-        /* We send this event to the private D-Bus socket and then the
-         * system instance will forward this to the system bus. We do
-         * this to avoid an activation loop when we start dbus when we
-         * are called when the dbus service is shut down. */
-
-        r = bus_connect_system_systemd(&bus);
-        if (r < 0) {
-                /* If we couldn't connect we assume this was triggered
-                 * while systemd got restarted/transitioned from
-                 * initrd to the system, so let's ignore this */
-                log_debug_errno(r, "Failed to get D-Bus connection: %m");
+        fd = socket(AF_UNIX, SOCK_DGRAM|SOCK_CLOEXEC, 0);
+        if (fd < 0) {
+                log_debug_errno(errno, "Failed to allocate socket: %m");
+                return EXIT_FAILURE;
+        }
+
+        l = strlen(argv[1]);
+
+        n = sendto(fd, argv[1], l, 0, &sa.sa, offsetof(struct sockaddr_un, sun_path) + strlen(sa.un.sun_path));
+        if (n < 0) {
+                log_debug_errno(errno, "Failed to send cgroups agent message: %m");
                 return EXIT_FAILURE;
         }
 
-        r = sd_bus_emit_signal(bus,
-                               "/org/freedesktop/systemd1/agent",
-                               "org.freedesktop.systemd1.Agent",
-                               "Released",
-                               "s", argv[1]);
-        if (r < 0) {
-                log_debug_errno(r, "Failed to send signal message on private connection: %m");
+        if ((size_t) n != l) {
+                log_debug("Datagram size mismatch");
                 return EXIT_FAILURE;
         }