6 files changed, 28 insertions, 22 deletions

diff --git a/include/net/ip.h b/include/net/ip.h
index eca0ef7a495e..fd1561e88a1a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -450,7 +450,7 @@ extern int ip_options_rcv_srr(struct sk_buff *skb);
  *      Functions provided by ip_sockglue.c
  */
 
-extern int      ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+extern void     ipv4_pktinfo_prepare(struct sk_buff *skb);
 extern void     ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
 extern int      ip_cmsg_send(struct net *net,
                              struct msghdr *msg, struct ipcm_cookie *ipc);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 09ff51bf16a4..80d5fa450210 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -55,20 +55,13 @@
 /*
  *      SOL_IP control messages.
  */
+#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb))
 
 static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 {
-        struct in_pktinfo info;
-        struct rtable *rt = skb_rtable(skb);
+        struct in_pktinfo info = *PKTINFO_SKB_CB(skb);
 
         info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
-        if (rt) {
-                info.ipi_ifindex = rt->rt_iif;
-                info.ipi_spec_dst.s_addr = rt->rt_spec_dst;
-        } else {
-                info.ipi_ifindex = 0;
-                info.ipi_spec_dst.s_addr = 0;
-        }
 
         put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
 }
@@ -992,20 +985,28 @@ e_inval:
 }
 
 /**
- * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * ipv4_pktinfo_prepare - transfert some info from rtable to skb
  * @sk: socket
  * @skb: buffer
  *
- * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option
- * is not set, we drop skb dst entry now, while dst cache line is hot.
+ * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst
+ * in skb->cb[] before dst drop.
+ * This way, receiver doesnt make cache line misses to read rtable.
  */
-int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(struct sk_buff *skb)
 {
-        if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
-                skb_dst_drop(skb);
-        return sock_queue_rcv_skb(sk, skb);
+        struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
+        const struct rtable *rt = skb_rtable(skb);
+
+        if (rt) {
+                pktinfo->ipi_ifindex = rt->rt_iif;
+                pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst;
+        } else {
+                pktinfo->ipi_ifindex = 0;
+                pktinfo->ipi_spec_dst.s_addr = 0;
+        }
+        skb_dst_drop(skb);
 }
-EXPORT_SYMBOL(ip_queue_rcv_skb);
 
 int ip_setsockopt(struct sock *sk, int level,
                 int optname, char __user *optval, unsigned int optlen)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 007e2eb769d3..7a8410d1b4b1 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -292,7 +292,8 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
 {
         /* Charge it to the socket. */
 
-        if (ip_queue_rcv_skb(sk, skb) < 0) {
+        ipv4_pktinfo_prepare(skb);
+        if (sock_queue_rcv_skb(sk, skb) < 0) {
                 kfree_skb(skb);
                 return NET_RX_DROP;
         }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ab0966df1e2a..6854f581313f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1357,7 +1357,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
         if (inet_sk(sk)->inet_daddr)
                 sock_rps_save_rxhash(sk, skb);
 
-        rc = ip_queue_rcv_skb(sk, skb);
+        rc = sock_queue_rcv_skb(sk, skb);
         if (rc < 0) {
                 int is_udplite = IS_UDPLITE(sk);
 
@@ -1473,6 +1473,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
         rc = 0;
 
+        ipv4_pktinfo_prepare(skb);
         bh_lock_sock(sk);
         if (!sock_owned_by_user(sk))
                 rc = __udp_queue_rcv_skb(sk, skb);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 331af3b882ac..204f2e833f04 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -383,7 +383,8 @@ static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb)
         }
 
         /* Charge it to the socket. */
-        if (ip_queue_rcv_skb(sk, skb) < 0) {
+        skb_dst_drop(skb);
+        if (sock_queue_rcv_skb(sk, skb) < 0) {
                 kfree_skb(skb);
                 return NET_RX_DROP;
         }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 846f4757eb8d..b4a4a15fa96f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -538,7 +538,9 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
                         goto drop;
         }
 
-        if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) {
+        skb_dst_drop(skb);
+        rc = sock_queue_rcv_skb(sk, skb);
+        if (rc < 0) {
                 /* Note that an ENOMEM error is charged twice */
                 if (rc == -ENOMEM)
                         UDP6_INC_STATS_BH(sock_net(sk),