1 files changed, 53 insertions, 118 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 54fc4c711f2c..a722a43dd668 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -117,6 +117,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 			return res;
 	}
 
+	IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
+
 	rcu_read_lock();
 	nexthop = rt6_nexthop((struct rt6_info *)dst, daddr);
 	neigh = __ipv6_neigh_lookup_noref(dev, nexthop);
@@ -162,7 +164,13 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
 		int err;
 
 		skb_mark_not_on_list(segs);
-		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		/* Last GSO segment can be smaller than gso_size (and MTU).
+		 * Adding a fragment header would produce an "atomic fragment",
+		 * which is considered harmful (RFC-8021). Avoid that.
+		 */
+		err = segs->len > mtu ?
+			ip6_fragment(net, sk, segs, ip6_finish_output2) :
+			ip6_finish_output2(net, sk, segs);
 		if (err && ret == 0)
 			ret = err;
 	}
@@ -170,6 +178,16 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
 	return ret;
 }
 
+static int ip6_finish_output_gso(struct net *net, struct sock *sk,
+				 struct sk_buff *skb, unsigned int mtu)
+{
+	if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	return ip6_finish_output2(net, sk, skb);
+}
+
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int mtu;
@@ -183,17 +201,14 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #endif
 
 	mtu = ip6_skb_dst_mtu(skb);
-	if (skb_is_gso(skb) &&
-	    !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
-	    !skb_gso_validate_network_len(skb, mtu))
-		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+	if (skb_is_gso(skb))
+		return ip6_finish_output_gso(net, sk, skb, mtu);
 
-	if ((skb->len > mtu && !skb_is_gso(skb)) ||
-	    dst_allfrag(skb_dst(skb)) ||
+	if (skb->len > mtu ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
-	else
-		return ip6_finish_output2(net, sk, skb);
+
+	return ip6_finish_output2(net, sk, skb);
 }
 
 static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -232,12 +247,11 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(ip6_output);
 
-bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+bool ip6_autoflowlabel(struct net *net, const struct sock *sk)
 {
-	if (!np->autoflowlabel_set)
+	if (!inet6_test_bit(AUTOFLOWLABEL_SET, sk))
 		return ip6_default_np_autolabel(net);
-	else
-		return np->autoflowlabel;
+	return inet6_test_bit(AUTOFLOWLABEL, sk);
 }
 
 /*
@@ -309,12 +323,12 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	 *	Fill in the IPv6 header
 	 */
 	if (np)
-		hlimit = np->hop_limit;
+		hlimit = READ_ONCE(np->hop_limit);
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 
 	ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
-				ip6_autoflowlabel(net, np), fl6));
+				ip6_autoflowlabel(net, sk), fl6));
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
@@ -329,7 +343,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 
 	mtu = dst_mtu(dst);
 	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
 
 		/* if egress device is enslaved to an L3 master device pass the
 		 * skb to its handler for processing
@@ -369,9 +383,8 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
 		if (sk && ra->sel == sel &&
 		    (!sk->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == skb->dev->ifindex)) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
-			if (np && np->rtalert_isolate &&
+			if (inet6_test_bit(RTALERT_ISOLATE, sk) &&
 			    !net_eq(sock_net(sk), dev_net(skb->dev))) {
 				continue;
 			}
@@ -448,10 +461,6 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 				     struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
-
-	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-
 #ifdef CONFIG_NET_SWITCHDEV
 	if (skb->offload_l3_fwd_mark) {
 		consume_skb(skb);
@@ -619,6 +628,8 @@ int ip6_forward(struct sk_buff *skb)
 		}
 	}
 
+	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+
 	mtu = ip6_dst_mtu_maybe_forward(dst, true);
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
@@ -881,9 +892,11 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			mtu = IPV6_MIN_MTU;
 	}
 
-	if (np && np->frag_size < mtu) {
-		if (np->frag_size)
-			mtu = np->frag_size;
+	if (np) {
+		u32 frag_size = READ_ONCE(np->frag_size);
+
+		if (frag_size && frag_size < mtu)
+			mtu = frag_size;
 	}
 	if (mtu < hlen + sizeof(struct frag_hdr) + 8)
 		goto fail_toobig;
@@ -1017,9 +1030,6 @@ slow_path:
 	return err;
 
 fail_toobig:
-	if (skb->sk && dst_allfrag(skb_dst(skb)))
-		sk_gso_disable(skb->sk);
-
 	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 	err = -EMSGSIZE;
 
@@ -1113,7 +1123,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		rcu_read_lock();
 		from = rt ? rcu_dereference(rt->from) : NULL;
 		err = ip6_route_get_saddr(net, from, &fl6->daddr,
-					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0,
 					  &fl6->saddr);
 		rcu_read_unlock();
 
@@ -1283,74 +1293,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
-/**
- *      ip6_dst_lookup_tunnel - perform route lookup on tunnel
- *      @skb: Packet for which lookup is done
- *      @dev: Tunnel device
- *      @net: Network namespace of tunnel device
- *      @sock: Socket which provides route info
- *      @saddr: Memory to store the src ip address
- *      @info: Tunnel information
- *      @protocol: IP protocol
- *      @use_cache: Flag to enable cache usage
- *      This function performs a route lookup on a tunnel
- *
- *      It returns a valid dst pointer and stores src address to be used in
- *      tunnel in param saddr on success, else a pointer encoded error code.
- */
-
-struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
-					struct net_device *dev,
-					struct net *net,
-					struct socket *sock,
-					struct in6_addr *saddr,
-					const struct ip_tunnel_info *info,
-					u8 protocol,
-					bool use_cache)
-{
-	struct dst_entry *dst = NULL;
-#ifdef CONFIG_DST_CACHE
-	struct dst_cache *dst_cache;
-#endif
-	struct flowi6 fl6;
-	__u8 prio;
-
-#ifdef CONFIG_DST_CACHE
-	dst_cache = (struct dst_cache *)&info->dst_cache;
-	if (use_cache) {
-		dst = dst_cache_get_ip6(dst_cache, saddr);
-		if (dst)
-			return dst;
-	}
-#endif
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_mark = skb->mark;
-	fl6.flowi6_proto = protocol;
-	fl6.daddr = info->key.u.ipv6.dst;
-	fl6.saddr = info->key.u.ipv6.src;
-	prio = info->key.tos;
-	fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label);
-
-	dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6,
-					      NULL);
-	if (IS_ERR(dst)) {
-		netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr);
-		return ERR_PTR(-ENETUNREACH);
-	}
-	if (dst->dev == dev) { /* is this necessary? */
-		netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr);
-		dst_release(dst);
-		return ERR_PTR(-ELOOP);
-	}
-#ifdef CONFIG_DST_CACHE
-	if (use_cache)
-		dst_cache_set_ip6(dst_cache, dst, &fl6.saddr);
-#endif
-	*saddr = fl6.saddr;
-	return dst;
-}
-EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel);
-
 static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
 					       gfp_t gfp)
 {
@@ -1392,7 +1334,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 			  struct rt6_info *rt)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	unsigned int mtu;
+	unsigned int mtu, frag_size;
 	struct ipv6_txoptions *nopt, *opt = ipc6->opt;
 
 	/* callers pass dst together with a reference, set it first so
@@ -1436,25 +1378,23 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	v6_cork->hop_limit = ipc6->hlimit;
 	v6_cork->tclass = ipc6->tclass;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
-		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
 	else
-		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 			READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst));
-	if (np->frag_size < mtu) {
-		if (np->frag_size)
-			mtu = np->frag_size;
-	}
+
+	frag_size = READ_ONCE(np->frag_size);
+	if (frag_size && frag_size < mtu)
+		mtu = frag_size;
+
 	cork->base.fragsize = mtu;
 	cork->base.gso_size = ipc6->gso_size;
 	cork->base.tx_flags = 0;
 	cork->base.mark = ipc6->sockc.mark;
 	sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
 
-	if (dst_allfrag(xfrm_dst_path(&rt->dst)))
-		cork->base.flags |= IPCORK_ALLFRAG;
 	cork->base.length = 0;
-
 	cork->base.transmit_time = ipc6->sockc.transmit_time;
 
 	return 0;
@@ -1511,8 +1451,6 @@ static int __ip6_append_data(struct sock *sk,
 
 	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 (mtu <= fragheaderlen ||
@@ -1622,7 +1560,7 @@ emsgsize:
 
 	while (length > 0) {
 		/* Check if the remaining data fits into current packet. */
-		copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
+		copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len;
 		if (copy < length)
 			copy = maxfraglen - skb->len;
 
@@ -1653,7 +1591,7 @@ alloc_new_skb:
 			 */
 			datalen = length + fraggap;
 
-			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+			if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			fraglen = datalen + fragheaderlen;
 			pagedlen = 0;
@@ -1902,7 +1840,6 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork)
 	struct dst_entry *dst = cork->base.dst;
 
 	cork->base.dst = NULL;
-	cork->base.flags &= ~IPCORK_ALLFRAG;
 	skb_dst_set(skb, dst);
 }
 
@@ -1923,7 +1860,6 @@ static void ip6_cork_release(struct inet_cork_full *cork,
 	if (cork->base.dst) {
 		dst_release(cork->base.dst);
 		cork->base.dst = NULL;
-		cork->base.flags &= ~IPCORK_ALLFRAG;
 	}
 }
 
@@ -1935,7 +1871,6 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
 	struct in6_addr *final_dst;
-	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
 	struct ipv6_txoptions *opt = v6_cork->opt;
@@ -1978,18 +1913,18 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
-					ip6_autoflowlabel(net, np), fl6));
+					ip6_autoflowlabel(net, sk), fl6));
 	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = cork->base.mark;
 	skb->tstamp = cork->base.transmit_time;
 
 	ip6_cork_steal_dst(skb, cork);
-	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
+	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 		u8 icmp6_type;
@@ -2091,7 +2026,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 		return ERR_PTR(err);
 	}
 	if (ipc6->dontfrag < 0)
-		ipc6->dontfrag = inet6_sk(sk)->dontfrag;
+		ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk);
 
 	err = __ip6_append_data(sk, &queue, cork, &v6_cork,
 				&current->task_frag, getfrag, from,