Improve NTP / kernel time change event handling

clib_time_verify_frequency(...) rejects clock frequency changes
greater than 1%.

vlib_worker_thread_barrier_sync_int (...) continuously checks that the
barrier hold-down timer is not unreasonably far in the future.

Change-Id: I00ecb4c20e44de5d6a9c1499fa933e3dd834d11a
Signed-off-by: Dave Barach <dbarach@cisco.com>

2 files changed, 34 insertions, 2 deletions

diff --git a/src/vlib/threads.c b/src/vlib/threads.c
index 8e75592c0e2..1972886a78b 100644
--- a/src/vlib/threads.c
+++ b/src/vlib/threads.c
@@ -1466,9 +1466,21 @@ vlib_worker_thread_barrier_sync_int (vlib_main_t * vm)
 
   /* Enforce minimum barrier open time to minimize packet loss */
   ASSERT (vm->barrier_no_close_before <= (now + BARRIER_MINIMUM_OPEN_LIMIT));
-  while ((now = vlib_time_now (vm)) < vm->barrier_no_close_before)
-    ;
 
+  while (1)
+    {
+      now = vlib_time_now (vm);
+      /* Barrier hold-down timer expired? */
+      if (now >= vm->barrier_no_close_before)
+	break;
+      if ((vm->barrier_no_close_before - now)
+	  > (2.0 * BARRIER_MINIMUM_OPEN_LIMIT))
+	{
+	  clib_warning ("clock change: would have waited for %.4f seconds",
+			(vm->barrier_no_close_before - now));
+	  break;
+	}
+    }
   /* Record time of closure */
   t_open = now - vm->barrier_epoch;
   vm->barrier_epoch = now;
diff --git a/src/vppinfra/time.c b/src/vppinfra/time.c
index e9a764bcd31..d647e670dad 100644
--- a/src/vppinfra/time.c
+++ b/src/vppinfra/time.c
@@ -197,6 +197,7 @@ clib_time_verify_frequency (clib_time_t * c)
   f64 dtr = now_reference - c->last_verify_reference_time;
   f64 dtr_max;
   u64 dtc = c->last_cpu_time - c->last_verify_cpu_time;
+  f64 new_clocks_per_second, delta;
   f64 round_units = 100e5;
 
   c->last_verify_cpu_time = c->last_cpu_time;
@@ -217,6 +218,25 @@ clib_time_verify_frequency (clib_time_t * c)
       return;
     }
 
+  /*
+   * Reject large frequency changes, another consequence of
+   * system clock changes particularly with old kernels.
+   */
+  new_clocks_per_second =
+    flt_round_nearest ((f64) dtc / (dtr * round_units)) * round_units;
+
+  delta = new_clocks_per_second - c->clocks_per_second;
+  if (delta < 0.0)
+    delta = -delta;
+
+  if (PREDICT_FALSE ((delta / c->clocks_per_second) > .01))
+    {
+      clib_warning ("Rejecting large frequency change of %.2f%%",
+		    (delta / c->clocks_per_second) * 100.0);
+      c->log2_clocks_per_frequency_verify = c->log2_clocks_per_second;
+      return;
+    }
+
   c->clocks_per_second =
     flt_round_nearest ((f64) dtc / (dtr * round_units)) * round_units;
   c->seconds_per_clock = 1 / c->clocks_per_second;