Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Several cases of bug fixes in 'net' overlapping other changes in
'net-next-.

Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/af_inet.c

@@ -533,9 +533,9 @@ EXPORT_SYMBOL(inet_dgram_connect);
 
 static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 {
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	add_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending += writebias;
 
 	/* Basic assumption: if someone sets sk->sk_err, he _must_
@@ -545,13 +545,12 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 	 */
 	while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		release_sock(sk);
-		timeo = schedule_timeout(timeo);
+		timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
 		lock_sock(sk);
 		if (signal_pending(current) || !timeo)
 			break;
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	}
-	finish_wait(sk_sleep(sk), &wait);
+	remove_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending -= writebias;
 	return timeo;
 }

net/ipv4/fib_trie.c

@@ -2413,22 +2413,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	struct key_vector *l, **tp = &iter->tnode;
 	t_key key;
 
-	/* use cache location of next-to-find key */
+	/* use cached location of previously found key */
 	if (iter->pos > 0 && pos >= iter->pos) {
-		pos -= iter->pos;
 		key = iter->key;
 	} else {
-		iter->pos = 0;
+		iter->pos = 1;
 		key = 0;
 	}
 
-	while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+	pos -= iter->pos;
+
+	while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
 		key = l->key + 1;
 		iter->pos++;
-
-		if (--pos <= 0)
-			break;
-
 		l = NULL;
 
 		/* handle unlikely case of a key wrap */
@@ -2437,7 +2434,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	}
 
 	if (l)
-		iter->key = key;	/* remember it */
+		iter->key = l->key;	/* remember it */
 	else
 		iter->pos = 0;		/* forget it */
 
@@ -2465,7 +2462,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
 		return fib_route_get_idx(iter, *pos);
 
 	iter->pos = 0;
-	iter->key = 0;
+	iter->key = KEY_MAX;
 
 	return SEQ_START_TOKEN;
 }
@@ -2474,7 +2471,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct fib_route_iter *iter = seq->private;
 	struct key_vector *l = NULL;
-	t_key key = iter->key;
+	t_key key = iter->key + 1;
 
 	++*pos;
 
@@ -2483,7 +2480,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		l = leaf_walk_rcu(&iter->tnode, key);
 
 	if (l) {
-		iter->key = l->key + 1;
+		iter->key = l->key;
 		iter->pos++;
 	} else {
 		iter->pos = 0;

net/ipv4/icmp.c

@@ -479,7 +479,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
-	fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
+	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
 	rt = __ip_route_output_key_hash(net, fl4,
@@ -504,7 +504,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	if (err)
 		goto relookup_failed;
 
-	if (inet_addr_type_dev_table(net, skb_in->dev,
+	if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
 				     fl4_dec.saddr) == RTN_LOCAL) {
 		rt2 = __ip_route_output_key(net, &fl4_dec);
 		if (IS_ERR(rt2))

net/ipv4/ip_forward.c

@@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
 	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
 	if (ip_exceeds_mtu(skb, mtu)) {
 		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);

net/ipv4/ip_output.c

@@ -239,19 +239,23 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 	struct sk_buff *segs;
 	int ret = 0;
 
-	/* common case: fragmentation of segments is not allowed,
-	 * or seglen is <= mtu
+	/* common case: seglen is <= mtu
 	 */
-	if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) ||
-	      skb_gso_validate_mtu(skb, mtu))
+	if (skb_gso_validate_mtu(skb, mtu))
 		return ip_finish_output2(net, sk, skb);
 
-	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	/* Slowpath -  GSO segment length exceeds the egress MTU.
 	 *
-	 * This can happen in two cases:
-	 * 1) TCP GRO packet, DF bit not set
-	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
-	 * from host network stack.
+	 * This can happen in several cases:
+	 *  - Forwarding of a TCP GRO skb, when DF flag is not set.
+	 *  - Forwarding of an skb that arrived on a virtualization interface
+	 *    (virtio-net/vhost/tap) with TSO/GSO size set by other network
+	 *    stack.
+	 *  - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
+	 *    interface with a smaller MTU.
+	 *  - Arriving GRO skb (or GSO skb in a virtualized environment) that is
+	 *    bridged to a NETIF_F_TSO tunnel stacked over an interface with an
+	 *    insufficent MTU.
 	 */
 	features = netif_skb_features(skb);
 	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
@@ -1579,7 +1583,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	}
 
 	oif = arg->bound_dev_if;
-	oif = oif ? : skb->skb_iif;
+	if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+		oif = skb->skb_iif;
 
 	flowi4_init_output(&fl4, oif,
 			   IP4_REPLY_MARK(net, skb->mark),

net/ipv4/ip_tunnel_core.c

@@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	int pkt_len = skb->len - skb_inner_network_offset(skb);
 	struct net *net = dev_net(rt->dst.dev);
 	struct net_device *dev = skb->dev;
-	int skb_iif = skb->skb_iif;
 	struct iphdr *iph;
 	int err;
 
@@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	skb_dst_set(skb, &rt->dst);
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-	if (skb_iif && !(df & htons(IP_DF))) {
-		/* Arrived from an ingress interface, got encapsulated, with
-		 * fragmentation of encapulating frames allowed.
-		 * If skb is gso, the resulting encapsulated network segments
-		 * may exceed dst mtu.
-		 * Allow IP Fragmentation of segments.
-		 */
-		IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
-	}
-
 	/* Push down and install the IP header. */
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);

net/ipv4/ipmr.c

@@ -1754,7 +1754,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		vif->dev->stats.tx_bytes += skb->len;
 	}
 
-	IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
 
 	/* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
 	 * not only before forwarding, but after forwarding on all output

net/ipv4/netfilter/nft_dup_ipv4.c

@@ -28,7 +28,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr,
 	struct in_addr gw = {
 		.s_addr = (__force __be32)regs->data[priv->sreg_addr],
 	};
-	int oif = regs->data[priv->sreg_dev];
+	int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
 
 	nf_dup_ipv4(nft_net(pkt), pkt->skb, nft_hook(pkt), &gw, oif);
 }
@@ -59,7 +59,9 @@ static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
 
-	if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+	if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+		goto nla_put_failure;
+	if (priv->sreg_dev &&
 	    nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
 		goto nla_put_failure;
 

net/ipv4/route.c

@@ -755,7 +755,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			goto reject_redirect;
 	}
 
-	n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
+	n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+	if (!n)
+		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);

net/ipv4/tcp.c

@@ -1162,7 +1162,7 @@ restart:
 
 	err = -EPIPE;
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
-		goto out_err;
+		goto do_error;
 
 	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
@@ -1239,7 +1239,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == sysctl_max_skb_frags || !sg) {
+				if (i >= sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}

net/ipv4/tcp_dctcp.c

@@ -56,6 +56,7 @@ struct dctcp {
 	u32 next_seq;
 	u32 ce_state;
 	u32 delayed_ack_reserved;
+	u32 loss_cwnd;
 };
 
 static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
@@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk)
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
 		ca->delayed_ack_reserved = 0;
+		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
 		dctcp_reset(tp, ca);
@@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk)
 
 static u32 dctcp_ssthresh(struct sock *sk)
 {
-	const struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	ca->loss_cwnd = tp->snd_cwnd;
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
 }
 
@@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 	return 0;
 }
 
+static u32 dctcp_cwnd_undo(struct sock *sk)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
 static struct tcp_congestion_ops dctcp __read_mostly = {
 	.init		= dctcp_init,
 	.in_ack_event   = dctcp_update_alpha,
 	.cwnd_event	= dctcp_cwnd_event,
 	.ssthresh	= dctcp_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
+	.undo_cwnd	= dctcp_cwnd_undo,
 	.set_state	= dctcp_state,
 	.get_info	= dctcp_get_info,
 	.flags		= TCP_CONG_NEEDS_ECN,

net/ipv4/tcp_ipv4.c

@@ -1567,6 +1567,21 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_add_backlog);
 
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcphdr *th = (struct tcphdr *)skb->data;
+	unsigned int eaten = skb->len;
+	int err;
+
+	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+	if (!err) {
+		eaten -= skb->len;
+		TCP_SKB_CB(skb)->end_seq -= eaten;
+	}
+	return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
 /*
  *	From tcp_input.c
  */
@@ -1679,8 +1694,10 @@ process:
 
 	nf_reset(skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	iph = ip_hdr(skb);
 
 	skb->dev = NULL;