Re: 100% CPU load when generating traffic to destination network that nexthop is not reachable

On Tue, 2017-08-15 at 19:42 +0200, Paweł Staszewski wrote:

# To display the perf.data header info, please use 
--header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 1585571545969
#
# Children      Self  Command         Shared Object         Symbol
# ........  ........  ..............  .................... 
..............................................
#
      1.82%     0.00%  ksoftirqd/43    [kernel.vmlinux]      [k] 
__softirqentry_text_start
             |
              --1.82%--__softirqentry_text_start
                        |
                         --1.82%--net_rx_action
                                   |
                                    --1.82%--mlx5e_napi_poll
                                              |
--1.81%--mlx5e_poll_rx_cq
                                                         |
--1.81%--mlx5e_handle_rx_cqe
                                                                    |
--1.79%--napi_gro_receive
|
--1.78%--netif_receive_skb_internal
|
--1.78%--__netif_receive_skb
|
--1.78%--__netif_receive_skb_core
|
--1.78%--ip_rcv
|
--1.78%--ip_rcv_finish
|
--1.76%--ip_forward
|
--1.76%--ip_forward_finish
|
--1.76%--ip_output
|
--1.76%--ip_finish_output
|
--1.76%--ip_finish_output2
|
--1.73%--neigh_resolve_output
|
--1.73%--neigh_event_send
|
--1.73%--__neigh_event_send
|
--1.70%--_raw_write_lock_bh
queued_write_lock
queued_write_lock_slowpath
|
--1.67%--queued_spin_lock_slowpath

Please try this :

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 16a1a4c4eb57fa1147f230916e2e62e18ef89562..95e0d7702029b583de8229e3c3eb923f6395b072 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c

@@ -991,14 +991,18 @@ static void neigh_timer_handler(unsigned long arg)
 
 int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 {
-	int rc;
 	bool immediate_probe = false;
+	int rc;
+
+	/* We _should_ test this under write_lock_bh(&neigh->lock),
+	 * but this is too costly.
+	 */
+	if (READ_ONCE(neigh->nud_state) & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
+		return 0;
 
 	write_lock_bh(&neigh->lock);
 
 	rc = 0;
-	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
-		goto out_unlock_bh;
 	if (neigh->dead)
 		goto out_dead;