net: Use __this_cpu_inc() in fast path

This patch saves 224 bytes of text on my machine.

__this_cpu_inc() generates a single instruction, using no scratch
registers :

  65 ff 04 25 a8 30 01 00      incl   %gs:0x130a8

instead of :

  48 c7 c2 80 30 01 00         mov    $0x13080,%rdx
  65 48 8b 04 25 88 ea 00 00   mov    %gs:0xea88,%rax
  83 44 10 28 01               addl   $0x1,0x28(%rax,%rdx,1)

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

net/core/dev.c

@@ -2822,8 +2822,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 			skb->dev = master;
 	}
 
-	__get_cpu_var(softnet_data).processed++;
+	__this_cpu_inc(softnet_data.processed);
-
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
 	skb->mac_len = skb->network_header - skb->mac_header;

net/ipv4/route.c

@@ -253,8 +253,7 @@ static unsigned			rt_hash_mask __read_mostly;
 static unsigned int		rt_hash_log  __read_mostly;
 
 static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
-#define RT_CACHE_STAT_INC(field) \
+#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
-	(__raw_get_cpu_var(rt_cache_stat).field++)
 
 static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
 				   int genid)