Merge branch 'ipv6-udp-set-dst-cache-for-a-connected-sk-if-current-not-valid'

Alexey Kodanev says:

====================
ipv6: udp: set dst cache for a connected sk if current not valid

A new RTF_CACHE route can be created with the socket's dst cache
update between the below calls in udpv6_sendmsg(), when datagram
sending results to ICMPV6_PKT_TOOBIG error:

   dst = ip6_sk_dst_lookup_flow(...)
   ...
release_dst:
    if (dst) {
        if (connected) {
            ip6_dst_store(sk, dst)

Therefore, the new socket's dst cache reset to the old one on
"release_dst:".

The first three patches prepare the code to store dst cache
with ip6_sk_dst_lookup_flow():

  * the first patch adds ip6_sk_dst_store_flow() function with
    commonly used source and destiantion addresses checks using
    the flow information.

  * the second patch adds a new argument to ip6_sk_dst_lookup_flow()
    and ability to store dst in the socket's cache. Also, the two
    users of the function are updated without enabling the new
    behavior: pingv6_sendmsg() and udpv6_sendmsg().

  * the third patch makes 'connected' variable in udpv6_sendmsg()
    to be consistent with ip6_sk_dst_store_flow(), changes its type
    from int to bool.

The last patch contains the actual fix that removes sk dst cache
update in the end of udpv6_sendmsg(), and allows to do it in
ip6_sk_dst_lookup_flow().

v6: * use bool type for a new parameter in ip_sk_dst_lookup_flow()
    * add one more patch to convert 'connected' variable in
      udpv6_sendmsg() from int to bool type. If it shouldn't be
      here I will resend it when the net-next is opened.

v5: * relocate ip6_sk_dst_store_flow() to net/ipv6/route.c and
      rename ip6_dst_store_flow() to ip6_sk_dst_store_flow() as
      suggested by Martin

v4: * fix the error in the build of ip_dst_store_flow() reported by
      kbuild test robot due to missing checks for CONFIG_IPV6: add
      new function to ip6_output.c instead of ip6_route.h
    * add 'const' to struct flowi6 in ip6_dst_store_flow()
    * minor commit messages fixes

v3: * instead of moving ip6_dst_store() above udp_v6_send_skb(),
      update socket's dst cache inside ip6_sk_dst_lookup_flow()
      if the current one is invalid
    * the issue not reproduced in 4.1, but starting from 4.2. Add
      one more 'Fixes:' commit that creates new RTF_CACHE route.
      Though, it is also mentioned in the first one
====================

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 43 insertions, 37 deletions

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 0084013d6bed..08b132381984 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -214,6 +214,9 @@ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
 #endif
 }
 
+void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst,
+			   const struct flowi6 *fl6);
+
 static inline bool ipv6_unicast_destination(const struct sk_buff *skb)
 {
 	struct rt6_info *rt = (struct rt6_info *) skb_dst(skb);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 9b6e7f51b1d4..836f31af1369 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -965,7 +965,8 @@ int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
 struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst);
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
-					 const struct in6_addr *final_dst);
+					 const struct in6_addr *final_dst,
+					 bool connected);
 struct dst_entry *ip6_blackhole_route(struct net *net,
 				      struct dst_entry *orig_dst);
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 88bc2ef7c7a8..a02ad100f0d7 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -106,14 +106,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
 		}
 	}
 
-	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
-		      &sk->sk_v6_daddr : NULL,
-#ifdef CONFIG_IPV6_SUBTREES
-		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
-		      &np->saddr :
-#endif
-		      NULL);
+	ip6_sk_dst_store_flow(sk, dst, &fl6);
 
 out:
 	fl6_sock_release(flowlabel);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e6eaa4dd9f60..66a768b7b8fb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1105,23 +1105,32 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *	@sk: socket which provides the dst cache and route info
  *	@fl6: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
+ *	@connected: whether @sk is connected or not
  *
  *	This function performs a route lookup on the given flow with the
  *	possibility of using the cached route in the socket if it is valid.
  *	It will take the socket dst lock when operating on the dst cache.
  *	As a result, this function can only be used in process context.
  *
+ *	In addition, for a connected socket, cache the dst in the socket
+ *	if the current cache is not valid.
+ *
  *	It returns a valid dst pointer on success, or a pointer encoded
  *	error code.
  */
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
-					 const struct in6_addr *final_dst)
+					 const struct in6_addr *final_dst,
+					 bool connected)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
-	if (!dst)
-		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
+	if (dst)
+		return dst;
+
+	dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
+	if (connected && !IS_ERR(dst))
+		ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6);
 
 	return dst;
 }
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index d12c55dad7d1..746eeae7f581 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -121,7 +121,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.tclass = np->tclass;
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
-	dst = ip6_sk_dst_lookup_flow(sk, &fl6,  daddr);
+	dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 	rt = (struct rt6_info *) dst;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f239f91d2efb..49b954d6d0fa 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2229,6 +2229,23 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
 
+void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst,
+			   const struct flowi6 *fl6)
+{
+#ifdef CONFIG_IPV6_SUBTREES
+	struct ipv6_pinfo *np = inet6_sk(sk);
+#endif
+
+	ip6_dst_store(sk, dst,
+		      ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr) ?
+		      &sk->sk_v6_daddr : NULL,
+#ifdef CONFIG_IPV6_SUBTREES
+		      ipv6_addr_equal(&fl6->saddr, &np->saddr) ?
+		      &np->saddr :
+#endif
+		      NULL);
+}
+
 /* Handle redirects */
 struct ip6rd_flowi {
 	struct flowi6 fl6;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6861ed479469..4ec76a87aeb8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1116,10 +1116,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct dst_entry *dst;
 	struct ipcm6_cookie ipc6;
 	int addr_len = msg->msg_namelen;
+	bool connected = false;
 	int ulen = len;
 	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
 	int err;
-	int connected = 0;
 	int is_udplite = IS_UDPLITE(sk);
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
 	struct sockcm_cookie sockc;
@@ -1241,7 +1241,7 @@ do_udp_sendmsg:
 		fl6.fl6_dport = inet->inet_dport;
 		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
-		connected = 1;
+		connected = true;
 	}
 
 	if (!fl6.flowi6_oif)
@@ -1271,7 +1271,7 @@ do_udp_sendmsg:
 		}
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
-		connected = 0;
+		connected = false;
 	}
 	if (!opt) {
 		opt = txopt_get(np);
@@ -1293,11 +1293,11 @@ do_udp_sendmsg:
 
 	final_p = fl6_update_dst(&fl6, opt, &final);
 	if (final_p)
-		connected = 0;
+		connected = false;
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) {
 		fl6.flowi6_oif = np->mcast_oif;
-		connected = 0;
+		connected = false;
 	} else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
@@ -1308,7 +1308,7 @@ do_udp_sendmsg:
 
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
-	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
@@ -1333,7 +1333,7 @@ back_from_confirm:
 		err = PTR_ERR(skb);
 		if (!IS_ERR_OR_NULL(skb))
 			err = udp_v6_send_skb(skb, &fl6);
-		goto release_dst;
+		goto out;
 	}
 
 	lock_sock(sk);
@@ -1367,23 +1367,6 @@ do_append_data:
 		err = np->recverr ? net_xmit_errno(err) : 0;
 	release_sock(sk);
 
-release_dst:
-	if (dst) {
-		if (connected) {
-			ip6_dst_store(sk, dst,
-				      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
-				      &sk->sk_v6_daddr : NULL,
-#ifdef CONFIG_IPV6_SUBTREES
-				      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
-				      &np->saddr :
-#endif
-				      NULL);
-		} else {
-			dst_release(dst);
-		}
-		dst = NULL;
-	}
-
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);