net: use jump_label to shortcut RPS if not setup

Most machines dont use RPS/RFS, and pay a fair amount of instructions in
netif_receive_skb() / netif_rx() / get_rps_cpu() just to discover
RPS/RFS is not setup.

Add a jump_label named rps_needed.

If no device rps_map or global rps_sock_flow_table is setup,
netif_receive_skb() / netif_rx() do a single instruction instead of many
ones, including conditional jumps.

jmp +0    (if CONFIG_JUMP_LABEL=y)

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -214,6 +214,11 @@ enum {
 #include <linux/cache.h>
 #include <linux/skbuff.h>
 
+#ifdef CONFIG_RPS
+#include <linux/jump_label.h>
+extern struct jump_label_key rps_needed;
+#endif
+
 struct neighbour;
 struct neigh_parms;
 struct sk_buff;

net/core/dev.c

@@ -2711,6 +2711,8 @@ EXPORT_SYMBOL(__skb_get_rxhash);
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
 
+struct jump_label_key rps_needed __read_mostly;
+
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
@@ -2994,7 +2996,7 @@ int netif_rx(struct sk_buff *skb)
 
 	trace_netif_rx(skb);
 #ifdef CONFIG_RPS
-	{
+	if (static_branch(&rps_needed))	{
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
@@ -3009,14 +3011,13 @@ int netif_rx(struct sk_buff *skb)
 
 		rcu_read_unlock();
 		preempt_enable();
-	}
-#else
+	} else
+#endif
 	{
 		unsigned int qtail;
 		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
 		put_cpu();
 	}
-#endif
 	return ret;
 }
 EXPORT_SYMBOL(netif_rx);
@@ -3359,7 +3360,7 @@ int netif_receive_skb(struct sk_buff *skb)
 		return NET_RX_SUCCESS;
 
 #ifdef CONFIG_RPS
-	{
+	if (static_branch(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu, ret;
 
@@ -3370,16 +3371,12 @@ int netif_receive_skb(struct sk_buff *skb)
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
-		} else {
-			rcu_read_unlock();
-			ret = __netif_receive_skb(skb);
+			return ret;
 		}
-
-		return ret;
+		rcu_read_unlock();
 	}
-#else
-	return __netif_receive_skb(skb);
 #endif
+	return __netif_receive_skb(skb);
 }
 EXPORT_SYMBOL(netif_receive_skb);
 

net/core/net-sysfs.c

@@ -606,9 +606,12 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	rcu_assign_pointer(queue->rps_map, map);
 	spin_unlock(&rps_map_lock);
 
-	if (old_map)
+	if (map)
+		jump_label_inc(&rps_needed);
+	if (old_map) {
 		kfree_rcu(old_map, rcu);
-
+		jump_label_dec(&rps_needed);
+	}
 	free_cpumask_var(mask);
 	return len;
 }

net/core/sysctl_net_core.c

@@ -68,8 +68,13 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write,
 
 		if (sock_table != orig_sock_table) {
 			rcu_assign_pointer(rps_sock_flow_table, sock_table);
-			synchronize_rcu();
-			vfree(orig_sock_table);
+			if (sock_table)
+				jump_label_inc(&rps_needed);
+			if (orig_sock_table) {
+				jump_label_dec(&rps_needed);
+				synchronize_rcu();
+				vfree(orig_sock_table);
+			}
 		}
 	}