From ed51e3f54898128e68330de395736c80868100e8 Mon Sep 17 00:00:00 2001
From: Paul Holzinger <pholzing@redhat.com>
Date: Fri, 2 Jul 2021 15:57:45 +0200
Subject: podman service reaper

Add a new service reaper package. Podman currently does not reap all
child processes. The slirp4netns and rootlesskit processes are not
reaped. The is not a problem for local podman since the podman process
dies before the other processes and then init will reap them for us.

However with podman system service it is possible that the podman
process is still alive after slirp died. In this case podman has to reap
it or the slirp process will be a zombie until the service is stopped.

The service reaper will listen in an extra goroutine on SIGCHLD. Once it
receives this signal it will try to reap all pids that were added with
`AddPID()`. While I would like to just reap all children this is not
possible because many parts of the code use `os/exec` with `cmd.Wait()`.
If we reap before `cmd.Wait()` things can break, so reaping everything
is not an option.

[NO TESTS NEEDED]

Fixes #9777

Signed-off-by: Paul Holzinger <pholzing@redhat.com>
---
 pkg/servicereaper/service.go | 64 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)
 create mode 100644 pkg/servicereaper/service.go

(limited to 'pkg/servicereaper/service.go')

diff --git a/pkg/servicereaper/service.go b/pkg/servicereaper/service.go
new file mode 100644
index 000000000..e9c4fe908
--- /dev/null
+++ b/pkg/servicereaper/service.go
@@ -0,0 +1,64 @@
+//+build linux
+
+package servicereaper
+
+import (
+	"os"
+	"os/signal"
+	"sync"
+	"syscall"
+
+	"github.com/sirupsen/logrus"
+)
+
+type service struct {
+	pidMap map[int]bool
+	mutex  *sync.Mutex
+}
+
+var s = service{
+	pidMap: map[int]bool{},
+	mutex:  &sync.Mutex{},
+}
+
+func AddPID(pid int) {
+	s.mutex.Lock()
+	s.pidMap[pid] = true
+	s.mutex.Unlock()
+}
+
+func Start() {
+	// create signal channel and only wait for SIGCHLD
+	sigc := make(chan os.Signal, 1)
+	signal.Notify(sigc, syscall.SIGCHLD)
+	// wait and reap in an  extra goroutine
+	go reaper(sigc)
+}
+
+func reaper(sigc chan os.Signal) {
+	for {
+		// block until we receive SIGCHLD
+		<-sigc
+		s.mutex.Lock()
+		for pid := range s.pidMap {
+			var status syscall.WaitStatus
+			waitpid, err := syscall.Wait4(pid, &status, syscall.WNOHANG, nil)
+			if err != nil {
+				// do not log error for ECHILD
+				if err != syscall.ECHILD {
+					logrus.Warnf("wait for pid %d failed: %v ", pid, err)
+				}
+				delete(s.pidMap, pid)
+				continue
+			}
+			// if pid == 0 nothing happened
+			if waitpid == 0 {
+				continue
+			}
+			if status.Exited() {
+				delete(s.pidMap, pid)
+			}
+		}
+		s.mutex.Unlock()
+	}
+}
-- 
cgit v1.2.3-54-g00ecf