diff --git a/SOURCES/bz2112924-fix-dst_seq_num_init-race.patch b/SOURCES/bz2112924-fix-dst_seq_num_init-race.patch
new file mode 100644
index 0000000..4aa76ba
--- /dev/null
+++ b/SOURCES/bz2112924-fix-dst_seq_num_init-race.patch
@@ -0,0 +1,44 @@
+commit 62271c5c0b08041b24930310c04e3933720917c6
+Author: Fabio M. Di Nitto <fdinitto@redhat.com>
+Date: Mon Nov 8 09:14:22 2021 +0100
+
+ [host] fix dst_seq_num initialization race condition
+
+ There is a potential race condition where the sender
+ is overloaded, sending data packets before pings
+ can kick in and set the correct dst_seq_num.
+
+ if this node is starting up (dst_seq_num = 0),
+ it can start rejecing valid packets and get stuck.
+
+ Set the dst_seq_num to the first seen packet and
+ use that as reference instead.
+
+ Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
+
+diff --git a/libknet/host.c b/libknet/host.c
+index f02ef02..54061fd 100644
+--- a/libknet/host.c
++++ b/libknet/host.c
+@@ -617,6 +617,21 @@ int _seq_num_lookup(knet_handle_t knet_h, struct knet_host *host, seq_num_t seq_
+ char *dst_cbuf_defrag = host->circular_buffer_defrag;
+ seq_num_t *dst_seq_num = &host->rx_seq_num;
+
++ /*
++ * There is a potential race condition where the sender
++ * is overloaded, sending data packets before pings
++ * can kick in and set the correct dst_seq_num.
++ *
++ * if this node is starting up (dst_seq_num = 0),
++ * it can start rejecing valid packets and get stuck.
++ *
++ * Set the dst_seq_num to the first seen packet and
++ * use that as reference instead.
++ */
++ if (!*dst_seq_num) {
++ *dst_seq_num = seq_num;
++ }
++
+ if (clear_buf) {
+ _clear_cbuffers(host, seq_num);
+ }
diff --git a/SOURCES/bz2112924-icmp-faster-link-down-detection.patch b/SOURCES/bz2112924-icmp-faster-link-down-detection.patch
new file mode 100644
index 0000000..cf8f99b
--- /dev/null
+++ b/SOURCES/bz2112924-icmp-faster-link-down-detection.patch
@@ -0,0 +1,82 @@
+commit 28ddb87a2f4562c5d1752a778744cc56136f81c1
+Author: Fabio M. Di Nitto <fdinitto@redhat.com>
+Date: Sun Nov 7 17:02:05 2021 +0100
+
+ [udp] use ICMP error messages to trigger faster link down detection
+
+ this solves a possible race condition when:
+
+ - node1 is running
+ - node2 very fast
+ - node1 does NOT have enough time to detect that node2 has gone
+ and reset the local seq numbers / buffers
+ - node1 will start rejecting valid packets from node2
+
+ There is still a potential minor race condition where app
+ can restart so fast that kernel / network don't have time
+ to generate an ICMP error. This will be addressed using
+ instance id in onwire v2 protocol, as suggested by Jan F.
+
+ Signed-off-by: Fabio M. Di Nitto <fdinitto@redhat.com>
+
+diff --git a/libknet/transport_udp.c b/libknet/transport_udp.c
+index 963340d..32dd032 100644
+--- a/libknet/transport_udp.c
++++ b/libknet/transport_udp.c
+@@ -364,6 +364,46 @@ static int read_errs_from_sock(knet_handle_t knet_h, int sockfd)
+ log_debug(knet_h, KNET_SUB_TRANSP_UDP, "Received ICMP error from %s: %s destination unknown", addr_str, strerror(sock_err->ee_errno));
+ } else {
+ log_debug(knet_h, KNET_SUB_TRANSP_UDP, "Received ICMP error from %s: %s %s", addr_str, strerror(sock_err->ee_errno), addr_remote_str);
++ if ((sock_err->ee_errno == ECONNREFUSED) || /* knet is not running on the other node */
++ (sock_err->ee_errno == ECONNABORTED) || /* local kernel closed the socket */
++ (sock_err->ee_errno == ENONET) || /* network does not exist */
++ (sock_err->ee_errno == ENETUNREACH) || /* network unreachable */
++ (sock_err->ee_errno == EHOSTUNREACH) || /* host unreachable */
++ (sock_err->ee_errno == EHOSTDOWN) || /* host down (from kernel/net/ipv4/icmp.c */
++ (sock_err->ee_errno == ENETDOWN)) { /* network down */
++ struct knet_host *host = NULL;
++ struct knet_link *kn_link = NULL;
++ int link_idx, found = 0;
++
++ for (host = knet_h->host_head; host != NULL; host = host->next) {
++ for (link_idx = 0; link_idx < KNET_MAX_LINK; link_idx++) {
++ kn_link = &host->link[link_idx];
++ if (kn_link->outsock == sockfd) {
++ if (!cmpaddr(&remote, &kn_link->dst_addr)) {
++ found = 1;
++ break;
++ }
++ }
++ }
++ if (found) {
++ break;
++ }
++ }
++
++ if ((host) && (kn_link) &&
++ (kn_link->status.connected)) {
++ log_debug(knet_h, KNET_SUB_TRANSP_UDP, "Setting down host %u link %i", host->host_id, kn_link->link_id);
++ /*
++ * setting transport_connected = 0 will trigger
++ * thread_heartbeat link_down process.
++ *
++ * the process terminates calling into transport_link_down
++ * below that will set transport_connected = 1
++ */
++ kn_link->transport_connected = 0;
++ }
++
++ }
+ }
+ }
+ break;
+@@ -436,5 +476,9 @@ int udp_transport_link_dyn_connect(knet_handle_t knet_h, int sockfd, struct knet
+
+ int udp_transport_link_is_down(knet_handle_t knet_h, struct knet_link *kn_link)
+ {
++ /*
++ * see comments about handling ICMP error messages
++ */
++ kn_link->transport_connected = 1;
+ return 0;
+ }
diff --git a/SPECS/kronosnet.spec b/SPECS/kronosnet.spec
index 864f339..4f0cb3b 100644
--- a/SPECS/kronosnet.spec
+++ b/SPECS/kronosnet.spec
@@ -83,11 +83,14 @@
Name: kronosnet
Summary: Multipoint-to-Multipoint VPN daemon
Version: 1.22
-Release: 1%{?dist}
+Release: 2%{?dist}
License: GPLv2+ and LGPLv2+
URL: http://www.kronosnet.org
Source0: http://www.kronosnet.org/releases/kronosnet-%{version}.tar.gz
+Patch0: bz2112924-fix-dst_seq_num_init-race.patch
+Patch1: bz2112924-icmp-faster-link-down-detection.patch
+
# Build dependencies
BuildRequires: gcc
# required to build man pages
@@ -135,6 +138,8 @@ BuildRequires: autoconf
%prep
%setup -q -n %{name}-%{version}
+%patch0 -p1 -b .bz2112924-fix-dst_seq_num_init-race
+%patch1 -p1 -b .bz2112924-icmp-faster-link-down-detection
%build
%if %{defined buildautogen}
@@ -508,7 +513,7 @@ meta package to install all of libknet1 plugins
%package -n kronosnet-tests
Group: System Environment/Libraries
Summary: kronosnet test suite
-Requires: libknet1 = %{version}-%{release}
+Requires: libknet1%{_isa} = %{version}-%{release}
Requires: libnozzle1%{_isa} = %{version}-%{release}
%description -n kronosnet-tests
@@ -525,6 +530,10 @@ Requires: libnozzle1%{_isa} = %{version}-%{release}
%endif
%changelog
+* Wed Aug 03 2022 Christine Caulfield <ccaulfie@redhat.com> - 1.22-2
+ Fix "node randomly not rejoining cluster after a pcs cluster stop/start"
+ Resolves: rhbz#2112924
+
* Thu Sep 16 2021 Christine Caulfield <ccaulfie@redhat.com> - 1.22-1
Rebase to 1.22
Resolves: rhbz#1999976