net: optimize napi_threaded_poll() vs RPS/RFS

We use napi_threaded_poll() in order to reduce our softirq dependency.

We can add a followup of 821eba9 ("net: optimize napi_schedule_rps()")
to further remove the need of firing NET_RX_SOFTIRQ whenever
RPS/RFS are used.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: edumazet

include/linux/netdevice.h

@@ -3194,7 +3194,10 @@ struct softnet_data {
 #ifdef CONFIG_RPS
 	struct softnet_data	*rps_ipi_list;
 #endif
+
 	bool			in_net_rx_action;
+	bool			in_napi_threaded_poll;
+
 #ifdef CONFIG_NET_FLOW_LIMIT
 	struct sd_flow_limit __rcu *flow_limit;
 #endif

net/core/dev.c

@@ -4603,10 +4603,10 @@ static void napi_schedule_rps(struct softnet_data *sd)
 		sd->rps_ipi_next = mysd->rps_ipi_list;
 		mysd->rps_ipi_list = sd;
 
-		/* If not called from net_rx_action()
+		/* If not called from net_rx_action() or napi_threaded_poll()
 		 * we have to raise NET_RX_SOFTIRQ.
 		 */
-		if (!mysd->in_net_rx_action)
+		if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll)
 			__raise_softirq_irqoff(NET_RX_SOFTIRQ);
 		return;
 	}
@@ -6631,11 +6631,19 @@ static int napi_threaded_poll(void *data)
 
 			local_bh_disable();
 			sd = this_cpu_ptr(&softnet_data);
+			sd->in_napi_threaded_poll = true;
 
 			have = netpoll_poll_lock(napi);
 			__napi_poll(napi, &repoll);
 			netpoll_poll_unlock(have);
 
+			sd->in_napi_threaded_poll = false;
+			barrier();
+
+			if (sd_has_rps_ipi_waiting(sd)) {
+				local_irq_disable();
+				net_rps_action_and_irq_enable(sd);
+			}
 			skb_defer_free_flush(sd);
 			local_bh_enable();