From 02a38501fd2a888dd2041ac49211cb399fa5acaa Mon Sep 17 00:00:00 2001
From: Guillem Jover <gjover@sipwise.com>
Date: Thu, 6 Feb 2025 19:34:30 +0100
Subject: [PATCH] Fix crash in replicationCacheMaster() expecting a nullptr
 cached_master

The replicationCacheMaster() function expects the master pointer to be
non-nullptr and the cached_master to be nullptr. But if we happened to
get disconnected multiple times and thus also go multiple times through
replicationCreateMasterClient(), then we end up with both master and
cached_master being non-nullptr, which then triggers an assertion in
replicationCacheMaster() which crashes the server.

When we are recreating the master struct, mark cached_master for
asynchronous freeing, and reset its pointer.

Fixes: #849
---
 src/replication.cpp | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/replication.cpp b/src/replication.cpp
index e009731e8..8f3d043d0 100644
--- a/src/replication.cpp
+++ b/src/replication.cpp
@@ -2343,6 +2343,10 @@ void replicationEmptyDbCallback(void *privdata) {
 void replicationCreateMasterClient(redisMaster *mi, connection *conn, int dbid) {
     serverAssert(mi->master == nullptr);
     mi->master = createClient(conn, serverTL - g_pserver->rgthreadvar);
+    if (mi->cached_master != nullptr) {
+        freeClientAsync(mi->cached_master);
+        mi->cached_master = nullptr;
+    }
     if (conn)
     {
         serverAssert(connGetPrivateData(mi->master->conn) == mi->master);