1 files changed, 90 insertions, 79 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 61d403ee1031..e6a7bd15b9b7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -55,8 +55,9 @@
 #include <net/xfrm.h>
 #include <net/checksum.h>
 #include <linux/mroute6.h>
+#include <net/l3mdev.h>
 
-static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
@@ -71,7 +72,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
 		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
-		    ((mroute6_socket(dev_net(dev), skb) &&
+		    ((mroute6_socket(net, skb) &&
 		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
 		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
 					 &ipv6_hdr(skb)->saddr))) {
@@ -82,19 +83,18 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
 			 */
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
-					sk, newskb, NULL, newskb->dev,
+					net, sk, newskb, NULL, newskb->dev,
 					dev_loopback_xmit);
 
 			if (ipv6_hdr(skb)->hop_limit == 0) {
-				IP6_INC_STATS(dev_net(dev), idev,
+				IP6_INC_STATS(net, idev,
 					      IPSTATS_MIB_OUTDISCARDS);
 				kfree_skb(skb);
 				return 0;
 			}
 		}
 
-		IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
-				skb->len);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len);
 
 		if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
 		    IPV6_ADDR_SCOPE_NODELOCAL &&
@@ -116,48 +116,49 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
 	}
 	rcu_read_unlock_bh();
 
-	IP6_INC_STATS(dev_net(dst->dev),
-		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 	kfree_skb(skb);
 	return -EINVAL;
 }
 
-static int ip6_finish_output(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
-		return ip6_fragment(sk, skb, ip6_finish_output2);
+		return ip6_fragment(net, sk, skb, ip6_finish_output2);
 	else
-		return ip6_finish_output2(sk, skb);
+		return ip6_finish_output2(net, sk, skb);
 }
 
-int ip6_output(struct sock *sk, struct sk_buff *skb)
+int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
 	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+
 	if (unlikely(idev->cnf.disable_ipv6)) {
-		IP6_INC_STATS(dev_net(dev), idev,
-			      IPSTATS_MIB_OUTDISCARDS);
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 		return 0;
 	}
 
-	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb,
-			    NULL, dev,
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+			    net, sk, skb, NULL, dev,
 			    ip6_finish_output,
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
 /*
- *	xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * Note : socket lock is not held for SYNACK packets, but might be modified
+ * by calls to skb_set_owner_w() and ipv6_local_error(),
+ * which are using proper atomic operations or spinlocks.
  */
-
-int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
+int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	     struct ipv6_txoptions *opt, int tclass)
 {
 	struct net *net = sock_net(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
+	const struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr;
@@ -186,7 +187,10 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 			}
 			consume_skb(skb);
 			skb = skb2;
-			skb_set_owner_w(skb, sk);
+			/* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
+			 * it is safe to call in our context (socket lock not held)
+			 */
+			skb_set_owner_w(skb, (struct sock *)sk);
 		}
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
@@ -224,12 +228,20 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
 		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_OUT, skb->len);
-		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
-			       NULL, dst->dev, dst_output_sk);
+		/* hooks should never assume socket lock is held.
+		 * we promote our socket to non const
+		 */
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+			       net, (struct sock *)sk, skb, NULL, dst->dev,
+			       dst_output);
 	}
 
 	skb->dev = dst->dev;
-	ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
+	/* ipv6_local_error() does not require socket lock,
+	 * we promote our socket to non const
+	 */
+	ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);
+
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
 	kfree_skb(skb);
 	return -EMSGSIZE;
@@ -317,10 +329,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 	return 0;
 }
 
-static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb)
+static inline int ip6_forward_finish(struct net *net, struct sock *sk,
+				     struct sk_buff *skb)
 {
 	skb_sender_cpu_clear(skb);
-	return dst_output_sk(sk, skb);
+	return dst_output(net, sk, skb);
 }
 
 static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
@@ -515,8 +528,8 @@ int ip6_forward(struct sk_buff *skb)
 
 	IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
 	IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb,
-		       skb->dev, dst->dev,
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
+		       net, NULL, skb, skb->dev, dst->dev,
 		       ip6_forward_finish);
 
 error:
@@ -543,8 +556,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
-int ip6_fragment(struct sock *sk, struct sk_buff *skb,
-		 int (*output)(struct sock *, struct sk_buff *))
+int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		 int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
@@ -557,7 +570,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 	__be32 frag_id;
 	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	hlen = ip6_find_1stfragopt(skb, &prevhdr);
 	nexthdr = *prevhdr;
@@ -584,11 +596,17 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 		if (np->frag_size)
 			mtu = np->frag_size;
 	}
+	if (mtu < hlen + sizeof(struct frag_hdr) + 8)
+		goto fail_toobig;
 	mtu -= hlen + sizeof(struct frag_hdr);
 
 	frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
 				    &ipv6_hdr(skb)->saddr);
 
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (err = skb_checksum_help(skb)))
+		goto fail;
+
 	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		int first_len = skb_pagelen(skb);
@@ -677,7 +695,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 				ip6_copy_metadata(frag, skb);
 			}
 
-			err = output(sk, skb);
+			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 					      IPSTATS_MIB_FRAGCREATES);
@@ -717,10 +735,6 @@ slow_path_clean:
 	}
 
 slow_path:
-	if ((skb->ip_summed == CHECKSUM_PARTIAL) &&
-	    skb_checksum_help(skb))
-		goto fail;
-
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;			/* Where to start from */
 
@@ -805,7 +819,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		err = output(sk, frag);
+		err = output(net, sk, frag);
 		if (err)
 			goto fail;
 
@@ -877,7 +891,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 #ifdef CONFIG_IPV6_SUBTREES
 	    ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
 #endif
-	    (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
+	   (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) &&
+	      (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) {
 		dst_release(dst);
 		dst = NULL;
 	}
@@ -886,7 +901,7 @@ out:
 	return dst;
 }
 
-static int ip6_dst_lookup_tail(struct net *net, struct sock *sk,
+static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 			       struct dst_entry **dst, struct flowi6 *fl6)
 {
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
@@ -1017,7 +1032,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	It returns a valid dst pointer on success, or a pointer encoded
  *	error code.
  */
-struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = NULL;
@@ -1029,7 +1044,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (final_dst)
 		fl6->daddr = *final_dst;
 	if (!fl6->flowi6_oif)
-		fl6->flowi6_oif = dst->dev->ifindex;
+		fl6->flowi6_oif = l3mdev_fib_oif(dst->dev);
 
 	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
@@ -1255,6 +1270,7 @@ static int __ip6_append_data(struct sock *sk,
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
 	struct ipv6_txoptions *opt = v6_cork->opt;
 	int csummode = CHECKSUM_NONE;
+	unsigned int maxnonfragsize, headersize;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1272,38 +1288,43 @@ static int __ip6_append_data(struct sock *sk,
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
 		     sizeof(struct frag_hdr);
 
-	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
-		unsigned int maxnonfragsize, headersize;
-
-		headersize = sizeof(struct ipv6hdr) +
-			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
-			     (dst_allfrag(&rt->dst) ?
-			      sizeof(struct frag_hdr) : 0) +
-			     rt->rt6i_nfheader_len;
-
-		if (ip6_sk_ignore_df(sk))
-			maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
-		else
-			maxnonfragsize = mtu;
+	headersize = sizeof(struct ipv6hdr) +
+		     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
+		     (dst_allfrag(&rt->dst) ?
+		      sizeof(struct frag_hdr) : 0) +
+		     rt->rt6i_nfheader_len;
+
+	if (cork->length + length > mtu - headersize && dontfrag &&
+	    (sk->sk_protocol == IPPROTO_UDP ||
+	     sk->sk_protocol == IPPROTO_RAW)) {
+		ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+				sizeof(struct ipv6hdr));
+		goto emsgsize;
+	}
 
-		/* dontfrag active */
-		if ((cork->length + length > mtu - headersize) && dontfrag &&
-		    (sk->sk_protocol == IPPROTO_UDP ||
-		     sk->sk_protocol == IPPROTO_RAW)) {
-			ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
-						   sizeof(struct ipv6hdr));
-			goto emsgsize;
-		}
+	if (ip6_sk_ignore_df(sk))
+		maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+	else
+		maxnonfragsize = mtu;
 
-		if (cork->length + length > maxnonfragsize - headersize) {
+	if (cork->length + length > maxnonfragsize - headersize) {
 emsgsize:
-			ipv6_local_error(sk, EMSGSIZE, fl6,
-					 mtu - headersize +
-					 sizeof(struct ipv6hdr));
-			return -EMSGSIZE;
-		}
+		ipv6_local_error(sk, EMSGSIZE, fl6,
+				 mtu - headersize +
+				 sizeof(struct ipv6hdr));
+		return -EMSGSIZE;
 	}
 
+	/* CHECKSUM_PARTIAL only with no extension headers and when
+	 * we are not going to fragment
+	 */
+	if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
+	    headersize == sizeof(struct ipv6hdr) &&
+	    length < mtu - headersize &&
+	    !(flags & MSG_MORE) &&
+	    rt->dst.dev->features & NETIF_F_V6_CSUM)
+		csummode = CHECKSUM_PARTIAL;
+
 	if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
 		sock_tx_timestamp(sk, &tx_flags);
 		if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
@@ -1311,16 +1332,6 @@ emsgsize:
 			tskey = sk->sk_tskey++;
 	}
 
-	/* If this is the first and only packet and device
-	 * supports checksum offloading, let's use it.
-	 * Use transhdrlen, same as IPv4, because partial
-	 * sums only work when transhdrlen is set.
-	 */
-	if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
-	    length + fragheaderlen < mtu &&
-	    rt->dst.dev->features & NETIF_F_V6_CSUM &&
-	    !exthdrlen)
-		csummode = CHECKSUM_PARTIAL;
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1683,7 +1694,7 @@ int ip6_send_skb(struct sk_buff *skb)
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 	int err;
 
-	err = ip6_local_out(skb);
+	err = ip6_local_out(net, skb->sk, skb);
 	if (err) {
 		if (err > 0)
 			err = net_xmit_errno(err);