import pacemaker-2.1.5-6.el8

SOURCES/004-g_source_remove.patch

@@ -0,0 +1,61 @@
+From 45617b727e280cac384a28ae3d96145e066e6197 Mon Sep 17 00:00:00 2001
+From: Reid Wahl <nrwahl@protonmail.com>
+Date: Fri, 3 Feb 2023 12:08:57 -0800
+Subject: [PATCH] Fix: fencer: Prevent double g_source_remove of op_timer_one
+
+QE observed a rarely reproducible core dump in the fencer during
+Pacemaker shutdown, in which we try to g_source_remove() an op timer
+that's already been removed.
+
+free_stonith_remote_op_list()
+-> g_hash_table_destroy()
+-> g_hash_table_remove_all_nodes()
+-> clear_remote_op_timers()
+-> g_source_remove()
+-> crm_glib_handler()
+-> "Source ID 190 was not found when attempting to remove it"
+
+The likely cause is that request_peer_fencing() doesn't set
+op->op_timer_one to 0 after calling g_source_remove() on it, so if that
+op is still in the stonith_remote_op_list at shutdown with the same
+timer, clear_remote_op_timers() tries to remove the source for
+op_timer_one again.
+
+There are only five locations that call g_source_remove() on a
+remote_fencing_op_t timer.
+* Three of them are in clear_remote_op_timers(), which first 0-checks
+  the timer and then sets it to 0 after g_source_remove().
+* One is in remote_op_query_timeout(), which does the same.
+* The last is the one we fix here in request_peer_fencing().
+
+I don't know all the conditions of QE's test scenario at this point.
+What I do know:
+* have-watchdog=true
+* stonith-watchdog-timeout=10
+* no explicit topology
+* fence agent script is missing for the configured fence device
+* requested fencing of one node
+* cluster shutdown
+
+Fixes RHBZ2166967
+
+Signed-off-by: Reid Wahl <nrwahl@protonmail.com>
+---
+ daemons/fenced/fenced_remote.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/daemons/fenced/fenced_remote.c b/daemons/fenced/fenced_remote.c
+index d61b5bd..b7426ff 100644
+--- a/daemons/fenced/fenced_remote.c
++++ b/daemons/fenced/fenced_remote.c
+@@ -1825,6 +1825,7 @@ request_peer_fencing(remote_fencing_op_t *op, peer_device_info_t *peer)
+         op->state = st_exec;
+         if (op->op_timer_one) {
+             g_source_remove(op->op_timer_one);
++            op->op_timer_one = 0;
+         }
+ 
+         if (!((stonith_watchdog_timeout_ms > 0)
+-- 
+2.31.1
+

SPECS/pacemaker.spec

@@ -36,7 +36,7 @@
 ## can be incremented to build packages reliably considered "newer"
 ## than previously built packages with the same pcmkversion)
 %global pcmkversion 2.1.5
-%global specversion 5
+%global specversion 6
 
 ## Upstream commit (full commit ID, abbreviated commit ID, or tag) to build
 %global commit a3f44794f94e1571c6ba0042915ade369b4ce4b1
@@ -271,6 +271,8 @@ Source1:       nagios-agents-metadata-%{nagios_hash}.tar.gz
 # upstream commits
 Patch001:      001-sync-points.patch
 Patch002:      002-remote-regression.patch
+Patch003:      003-history-cleanup.patch
+Patch004:      004-g_source_remove.patch
 
 # downstream-only commits
 #Patch1xx:      1xx-xxxx.patch
@@ -964,6 +966,12 @@ exit 0
 %license %{nagios_name}-%{nagios_hash}/COPYING
 
 %changelog
+* Wed Feb 8 2023 Chris Lumens <clumens@redhat.com> - 2.1.5-6
+- Backport fix for migration history cleanup causing resource recovery
+- Backport fix for SIGABRT during pacemaker-fenced shutdown
+- Resolves: rhbz2166388
+- Resolves: rhbz2168249
+
 * Tue Jan 24 2023 Ken Gaillot <kgaillot@redhat.com> - 2.1.5-5
 - Backport fix for remote node shutdown regression
 - Resolves: rhbz2163567