From 92f3b11c944f2ec0d9589b5d7cae0842a9fd1240 Mon Sep 17 00:00:00 2001
From: ls <335814617@qq.com>
Date: Mon, 16 Jan 2023 14:45:37 +0800
Subject: [PATCH] runtime:all APIs are hang in the service.mu

When the vmm process exits abnormally, a goroutine sets s.monitor
to null in the 'watchSandbox' function without getting service.mu,
This will cause another goroutine to block when sending a message
to s.monitor, and it holds service.mu, which leads to a deadlock.
For example, the wait function in the file
.../pkg/containerd-shim-v2/wait.go will send a message to s.monitor
after obtaining service.mu, but s.monitor may be null at this time

Fixes: #6059

Signed-off-by: ls <335814617@qq.com>
(cherry picked from commit 69fc8de7123156477717803bbb30df19264975d9)
---
 src/runtime/pkg/containerd-shim-v2/wait.go | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/runtime/pkg/containerd-shim-v2/wait.go b/src/runtime/pkg/containerd-shim-v2/wait.go
index ebb742790d..ecf75b8c34 100644
--- a/src/runtime/pkg/containerd-shim-v2/wait.go
+++ b/src/runtime/pkg/containerd-shim-v2/wait.go
@@ -120,10 +120,12 @@ func watchSandbox(ctx context.Context, s *service) {
 	if err == nil {
 		return
 	}
-	s.monitor = nil
 
 	s.mu.Lock()
 	defer s.mu.Unlock()
+
+	s.monitor = nil
+
 	// sandbox malfunctioning, cleanup as much as we can
 	shimLog.WithError(err).Warn("sandbox stopped unexpectedly")
 	err = s.sandbox.Stop(ctx, true)