From c5d125c9d015bf07ec7c579aa27ef724999c0b35 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Tue, 6 May 2025 10:16:30 +0200
Subject: [PATCH] refresh link status on faults (RHEL-89811)

Resolves: RHEL-89811
---
 linuxptp-rtnlinit.patch | 75 +++++++++++++++++++++++++++++++++++++++++
 linuxptp.spec           |  2 ++
 2 files changed, 77 insertions(+)
 create mode 100644 linuxptp-rtnlinit.patch

diff --git a/linuxptp-rtnlinit.patch b/linuxptp-rtnlinit.patch
new file mode 100644
index 0000000..60e011d
--- /dev/null
+++ b/linuxptp-rtnlinit.patch
@@ -0,0 +1,75 @@
+commit 01de33e91f9717d0cbae5af6eee2beb45deee219
+Author: Miroslav Lichvar <mlichvar@redhat.com>
+Date:   Tue Mar 4 15:53:37 2025 +0100
+
+    port: Refresh link status on faults.
+    
+    ptp4l gets the ENOBUFS error on the netlink socket when the kernel has
+    to drop messages due to full socket buffer. If ptp4l has a port in the
+    faulty state waiting for the link to go up and that event corresponds
+    to one of the dropped netlink messages, the port will be stuck in the
+    faulty state until the link goes down and up again.
+    
+    To prevent the port from getting stuck, request the current link status
+    when dispatching the EV_FAULT_DETECTED event. Also, reopen the socket to
+    get rid of the buffered messages when handling the fault and again when
+    reinitializing the port.
+    
+    Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
+    Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
+
+diff --git a/port.c b/port.c
+index 7f945ac..1bb407c 100644
+--- a/port.c
++++ b/port.c
+@@ -1975,6 +1975,20 @@ static int port_cmlds_initialize(struct port *p)
+ 	return port_cmlds_renew(p, now.tv_sec);
+ }
+ 
++static void port_rtnl_initialize(struct port *p)
++{
++	/* Reopen the socket to get rid of buffered messages */
++	if (p->fda.fd[FD_RTNL] >= 0) {
++		rtnl_close(p->fda.fd[FD_RTNL]);
++	}
++	p->fda.fd[FD_RTNL] = rtnl_open();
++	if (p->fda.fd[FD_RTNL] >= 0) {
++		rtnl_link_query(p->fda.fd[FD_RTNL], interface_name(p->iface));
++	}
++
++	clock_fda_changed(p->clock);
++}
++
+ void port_disable(struct port *p)
+ {
+ 	int i;
+@@ -2087,13 +2101,8 @@ int port_initialize(struct port *p)
+ 		if (p->bmca == BMCA_NOOP) {
+ 			port_set_delay_tmo(p);
+ 		}
+-		if (p->fda.fd[FD_RTNL] == -1) {
+-			p->fda.fd[FD_RTNL] = rtnl_open();
+-		}
+-		if (p->fda.fd[FD_RTNL] >= 0) {
+-			const char *ifname = interface_name(p->iface);
+-			rtnl_link_query(p->fda.fd[FD_RTNL], ifname);
+-		}
++
++		port_rtnl_initialize(p);
+ 	}
+ 
+ 	port_nrate_initialize(p);
+@@ -3768,6 +3777,13 @@ int port_state_update(struct port *p, enum fsm_event event, int mdiff)
+ 		if (port_link_status_get(p) && clear_fault_asap(&i)) {
+ 			pr_notice("%s: clearing fault immediately", p->log_name);
+ 			next = p->state_machine(next, EV_FAULT_CLEARED, 0);
++		} else if (event == EV_FAULT_DETECTED) {
++			/*
++			 * Reopen the netlink socket and refresh the link
++			 * status in case the fault was triggered by a missed
++			 * netlink message (ENOBUFS).
++			 */
++			port_rtnl_initialize(p);
+ 		}
+ 	}
+ 
diff --git a/linuxptp.spec b/linuxptp.spec
index 9968d6f..c6f22ec 100644
--- a/linuxptp.spec
+++ b/linuxptp.spec
@@ -39,6 +39,8 @@ Patch4:		linuxptp-nowait.patch
 Patch8:		linuxptp-externalpps.patch
 # add command to set external grandmaster properties
 Patch9:		linuxptp-externalgm.patch
+# refresh link status on faults
+Patch10:	linuxptp-rtnlinit.patch
 
 BuildRequires:	gcc gcc-c++ gnutls-devel make systemd