commit 134dc3c4655fcd9f314a5e56cd50db2f87366f5a Author: davidjm via Linuxptp-devel Date: Wed Nov 23 15:50:30 2022 -0800 Don't re-arm fault clearing timer on unrelated netlink events Set the timer only when an event causes the port to transition to the FAULTY state, rather than potentially re-arming the timeout when an event occurs while the port was already FAULTY. Concretely this occurs when a port is in fault, perhaps due to a single time out while polling for tx-timestamp. If any other port in the system (including unrelated ones ptp4l does not even know about) cause netlink messages to be sent. As it stands, clock_poll() will note that the port is in fault (from before, not due to the current event) and reset the timeout to its original value. If such unrelated netlink messages arrive at a regular enough cadence the timeout may be repeatedly reset, not trigger on time (if at all) and the port may not get a chance to clear its fault, perhaps indefinitely. Signed-off-by: David Mirabito diff --git a/clock.c b/clock.c index eea7983..451473e 100644 --- a/clock.c +++ b/clock.c @@ -1586,6 +1586,7 @@ void clock_set_sde(struct clock *c, int sde) int clock_poll(struct clock *c) { int cnt, i; + enum port_state prior_state; enum fsm_event event; struct pollfd *cur; struct port *p; @@ -1609,6 +1610,7 @@ int clock_poll(struct clock *c) /* Let the ports handle their events. */ for (i = 0; i < N_POLLFD; i++) { if (cur[i].revents & (POLLIN|POLLPRI|POLLERR)) { + prior_state = port_state(p); if (cur[i].revents & POLLERR) { pr_err("port %d: unexpected socket error", port_number(p)); @@ -1624,7 +1626,7 @@ int clock_poll(struct clock *c) } port_dispatch(p, event, 0); /* Clear any fault after a little while. */ - if (PS_FAULTY == port_state(p)) { + if ((PS_FAULTY == port_state(p)) && (prior_state != PS_FAULTY)) { clock_fault_timeout(p, 1); break; }