net: avoid a pair of dst_hold()/dst_release() in ip_append_data()

We can reduce pressure on dst entry refcount that slowdown UDP transmit
path on SMP machines. This pressure is visible on RTP servers when
delivering content to mediagateways, especially big ones, handling
thousand of streams. Several cpus send UDP frames to the same
destination, hence use the same dst entry.

This patch makes ip_append_data() eventually steal the refcount its
callers had to take on the dst entry.

This doesnt avoid all refcounting, but still gives speedups on SMP,
on UDP/RAW transmit path

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip.h

@@ -110,7 +110,7 @@ extern int		ip_append_data(struct sock *sk,
 						   int odd, struct sk_buff *skb),
 				void *from, int len, int protolen,
 				struct ipcm_cookie *ipc,
-				struct rtable *rt,
+				struct rtable **rt,
 				unsigned int flags);
 extern int		ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb);
 extern ssize_t		ip_append_page(struct sock *sk, struct page *page,

net/ipv4/icmp.c

@@ -321,12 +321,12 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
 }
 
 static void icmp_push_reply(struct icmp_bxm *icmp_param,
-			    struct ipcm_cookie *ipc, struct rtable *rt)
+			    struct ipcm_cookie *ipc, struct rtable **rt)
 {
 	struct sock *sk;
 	struct sk_buff *skb;
 
-	sk = icmp_sk(dev_net(rt->u.dst.dev));
+	sk = icmp_sk(dev_net((*rt)->u.dst.dev));
 	if (ip_append_data(sk, icmp_glue_bits, icmp_param,
 			   icmp_param->data_len+icmp_param->head_len,
 			   icmp_param->head_len,
@@ -392,7 +392,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	}
 	if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type,
 			       icmp_param->data.icmph.code))
-		icmp_push_reply(icmp_param, &ipc, rt);
+		icmp_push_reply(icmp_param, &ipc, &rt);
 	ip_rt_put(rt);
 out_unlock:
 	icmp_xmit_unlock(sk);
@@ -635,7 +635,7 @@ route_done:
 		icmp_param.data_len = room;
 	icmp_param.head_len = sizeof(struct icmphdr);
 
-	icmp_push_reply(&icmp_param, &ipc, rt);
+	icmp_push_reply(&icmp_param, &ipc, &rt);
 ende:
 	ip_rt_put(rt);
 out_unlock:

net/ipv4/ip_output.c

@@ -778,7 +778,7 @@ int ip_append_data(struct sock *sk,
 		   int getfrag(void *from, char *to, int offset, int len,
 			       int odd, struct sk_buff *skb),
 		   void *from, int length, int transhdrlen,
-		   struct ipcm_cookie *ipc, struct rtable *rt,
+		   struct ipcm_cookie *ipc, struct rtable **rtp,
 		   unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -793,6 +793,7 @@ int ip_append_data(struct sock *sk,
 	int offset = 0;
 	unsigned int maxfraglen, fragheaderlen;
 	int csummode = CHECKSUM_NONE;
+	struct rtable *rt;
 
 	if (flags&MSG_PROBE)
 		return 0;
@@ -812,7 +813,11 @@ int ip_append_data(struct sock *sk,
 			inet->cork.flags |= IPCORK_OPT;
 			inet->cork.addr = ipc->addr;
 		}
-		dst_hold(&rt->u.dst);
+		rt = *rtp;
+		/*
+		 * We steal reference to this route, caller should not release it
+		 */
+		*rtp = NULL;
 		inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ?
 					    rt->u.dst.dev->mtu :
 					    dst_mtu(rt->u.dst.path);
@@ -1391,7 +1396,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	ip_append_data(sk, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
-		       &ipc, rt, MSG_DONTWAIT);
+		       &ipc, &rt, MSG_DONTWAIT);
 	if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
 		if (arg->csumoffset >= 0)
 			*((__sum16 *)skb_transport_header(skb) +

net/ipv4/raw.c

@@ -572,7 +572,7 @@ back_from_confirm:
 			ipc.addr = rt->rt_dst;
 		lock_sock(sk);
 		err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,
-					&ipc, rt, msg->msg_flags);
+					&ipc, &rt, msg->msg_flags);
 		if (err)
 			ip_flush_pending_frames(sk);
 		else if (!(msg->msg_flags & MSG_MORE))

net/ipv4/udp.c

@@ -719,7 +719,7 @@ do_append_data:
 	up->len += ulen;
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
 	err = ip_append_data(sk, getfrag, msg->msg_iov, ulen,
-			sizeof(struct udphdr), &ipc, rt,
+			sizeof(struct udphdr), &ipc, &rt,
 			corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
 	if (err)
 		udp_flush_pending_frames(sk);