net: rps: fix cpu unplug

commit ac64da0b upstream.

softnet_data.input_pkt_queue is protected by a spinlock that
we must hold when transferring packets from victim queue to an active
one. This is because other cpus could still be trying to enqueue packets
into victim queue.

A second problem is that when we transfert the NAPI poll_list from
victim to current cpu, we absolutely need to special case the percpu
backlog, because we do not want to add complex locking to protect
process_queue : Only owner cpu is allowed to manipulate it, unless cpu
is offline.

Based on initial patch from Prasad Sodagudi & Subash Abhinov
Kasiviswanathan.

This version is better because we do not slow down packet processing,
only make migration safer.
Reported-by: Prasad Sodagudi <psodagud@codeaurora.org>
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>

net/core/dev.c

@@ -6903,10 +6903,20 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
-	/* Append NAPI poll list from offline CPU. */
-	if (!list_empty(&oldsd->poll_list)) {
-		list_splice_init(&oldsd->poll_list, &sd->poll_list);
-		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	/* Append NAPI poll list from offline CPU, with one exception :
+	 * process_backlog() must be called by cpu owning percpu backlog.
+	 * We properly handle process_queue & input_pkt_queue later.
+	 */
+	while (!list_empty(&oldsd->poll_list)) {
+		struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+							    struct napi_struct,
+							    poll_list);
+
+		list_del_init(&napi->poll_list);
+		if (napi->poll == process_backlog)
+			napi->state = 0;
+		else
+			____napi_schedule(sd, napi);
 	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6917,7 +6927,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
-	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+	while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
 		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}