12 files changed, 74 insertions, 42 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 300b06888fdf..b54b3ca939db 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -715,6 +715,7 @@ config DEFAULT_TCP_CONG
 	default "reno" if DEFAULT_RENO
 	default "dctcp" if DEFAULT_DCTCP
 	default "cdg" if DEFAULT_CDG
+	default "bbr" if DEFAULT_BBR
 	default "cubic"
 
 config TCP_MD5SIG
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5ddf5cda07f4..215143246e4b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1233,7 +1233,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
 
 		/* fixed ID is invalid if DF bit is not set */
-		if (fixedid && !(iph->frag_off & htons(IP_DF)))
+		if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF)))
 			goto out;
 	}
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index d95631d09248..20fb25e3027b 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -476,7 +476,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		esph = (void *)skb_push(skb, 4);
 		*seqhi = esph->spi;
 		esph->spi = esph->seq_no;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
 		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
 	}
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 026f309c51e9..e3665bf7a7f3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -719,6 +719,13 @@ static unsigned char update_suffix(struct key_vector *tn)
 {
 	unsigned char slen = tn->pos;
 	unsigned long stride, i;
+	unsigned char slen_max;
+
+	/* only vector 0 can have a suffix length greater than or equal to
+	 * tn->pos + tn->bits, the second highest node will have a suffix
+	 * length at most of tn->pos + tn->bits - 1
+	 */
+	slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen);
 
 	/* search though the list of children looking for nodes that might
 	 * have a suffix greater than the one we currently have.  This is
@@ -736,12 +743,8 @@ static unsigned char update_suffix(struct key_vector *tn)
 		slen = n->slen;
 		i &= ~(stride - 1);
 
-		/* if slen covers all but the last bit we can stop here
-		 * there will be nothing longer than that since only node
-		 * 0 and 1 << (bits - 1) could have that as their suffix
-		 * length.
-		 */
-		if ((slen + 1) >= (tn->pos + tn->bits))
+		/* stop searching if we have hit the maximum possible value */
+		if (slen >= slen_max)
 			break;
 	}
 
@@ -913,39 +916,27 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn)
 		return collapse(t, tn);
 
 	/* update parent in case halve failed */
-	tp = node_parent(tn);
-
-	/* Return if at least one deflate was run */
-	if (max_work != MAX_WORK)
-		return tp;
-
-	/* push the suffix length to the parent node */
-	if (tn->slen > tn->pos) {
-		unsigned char slen = update_suffix(tn);
-
-		if (slen > tp->slen)
-			tp->slen = slen;
-	}
-
-	return tp;
+	return node_parent(tn);
 }
 
-static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l)
+static void node_pull_suffix(struct key_vector *tn, unsigned char slen)
 {
-	while ((tp->slen > tp->pos) && (tp->slen > l->slen)) {
-		if (update_suffix(tp) > l->slen)
+	unsigned char node_slen = tn->slen;
+
+	while ((node_slen > tn->pos) && (node_slen > slen)) {
+		slen = update_suffix(tn);
+		if (node_slen == slen)
 			break;
-		tp = node_parent(tp);
+
+		tn = node_parent(tn);
+		node_slen = tn->slen;
 	}
 }
 
-static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l)
+static void node_push_suffix(struct key_vector *tn, unsigned char slen)
 {
-	/* if this is a new leaf then tn will be NULL and we can sort
-	 * out parent suffix lengths as a part of trie_rebalance
-	 */
-	while (tn->slen < l->slen) {
-		tn->slen = l->slen;
+	while (tn->slen < slen) {
+		tn->slen = slen;
 		tn = node_parent(tn);
 	}
 }
@@ -1066,6 +1057,7 @@ static int fib_insert_node(struct trie *t, struct key_vector *tp,
 	}
 
 	/* Case 3: n is NULL, and will just insert a new leaf */
+	node_push_suffix(tp, new->fa_slen);
 	NODE_INIT_PARENT(l, tp);
 	put_child_root(tp, key, l);
 	trie_rebalance(t, tp);
@@ -1107,7 +1099,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 	/* if we added to the tail node then we need to update slen */
 	if (l->slen < new->fa_slen) {
 		l->slen = new->fa_slen;
-		leaf_push_suffix(tp, l);
+		node_push_suffix(tp, new->fa_slen);
 	}
 
 	return 0;
@@ -1499,6 +1491,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 	 * out parent suffix lengths as a part of trie_rebalance
 	 */
 	if (hlist_empty(&l->leaf)) {
+		if (tp->slen == l->slen)
+			node_pull_suffix(tp, tp->pos);
 		put_child_root(tp, l->key, NULL);
 		node_free(l);
 		trie_rebalance(t, tp);
@@ -1511,7 +1505,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 
 	/* update the trie with the latest suffix length */
 	l->slen = fa->fa_slen;
-	leaf_pull_suffix(tp, l);
+	node_pull_suffix(tp, fa->fa_slen);
 }
 
 /* Caller must hold RTNL. */
@@ -1783,6 +1777,10 @@ void fib_table_flush_external(struct fib_table *tb)
 			if (IS_TRIE(pn))
 				break;
 
+			/* update the suffix to address pulled leaves */
+			if (pn->slen > pn->pos)
+				update_suffix(pn);
+
 			/* resize completed node */
 			pn = resize(t, pn);
 			cindex = get_index(pkey, pn);
@@ -1849,6 +1847,10 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 			if (IS_TRIE(pn))
 				break;
 
+			/* update the suffix to address pulled leaves */
+			if (pn->slen > pn->pos)
+				update_suffix(pn);
+
 			/* resize completed node */
 			pn = resize(t, pn);
 			cindex = get_index(pkey, pn);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 105908d841a3..877bdb02e887 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -107,6 +107,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (unlikely(!skb))
 		return 0;
 
+	skb->protocol = htons(ETH_P_IP);
+
 	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
 		       net, sk, skb, NULL, skb_dst(skb)->dev,
 		       dst_output);
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index c3776ff6749f..b3cc1335adbc 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -24,10 +24,11 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
 	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
 	if (addr_type == RTN_UNSPEC)
-		addr_type = inet_addr_type(net, saddr);
+		addr_type = inet_addr_type_dev_table(net, dev, saddr);
 	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
 		flags |= FLOWI_FLAG_ANYSRC;
 	else
@@ -40,6 +41,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	fl4.saddr = saddr;
 	fl4.flowi4_tos = RT_TOS(iph->tos);
 	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+	if (!fl4.flowi4_oif)
+		fl4.flowi4_oif = l3mdev_master_ifindex(dev);
 	fl4.flowi4_mark = skb->mark;
 	fl4.flowi4_flags = flags;
 	rt = ip_route_output_key(net, &fl4);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b31df597fd37..697538464e6e 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1201,8 +1201,8 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 
 	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
+		newinfo->hook_entry[i] = compatr->hook_entry[i];
+		newinfo->underflow[i] = compatr->underflow[i];
 	}
 	entry1 = newinfo->entries;
 	pos = entry1;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 205e2000d395..96b8e2b95731 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -657,6 +657,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
 
+	/* Must have at least a full ICMP header. */
+	if (len < icmph_len)
+		return -EINVAL;
+
 	/*
 	 *	Check the flags.
 	 */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a27b9c0e27c0..c71d49ce0c93 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -128,6 +128,23 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 #define REXMIT_LOST	1 /* retransmit packets marked lost */
 #define REXMIT_NEW	2 /* FRTO-style transmit of unsent/new packets */
 
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+{
+	static bool __once __read_mostly;
+
+	if (!__once) {
+		struct net_device *dev;
+
+		__once = true;
+
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+		pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+			dev ? dev->name : "Unknown driver");
+		rcu_read_unlock();
+	}
+}
+
 /* Adapt the MSS value used to make delayed ack decision to the
  * real world.
  */
@@ -144,7 +161,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	 */
 	len = skb_shinfo(skb)->gso_size ? : skb->len;
 	if (len >= icsk->icsk_ack.rcv_mss) {
-		icsk->icsk_ack.rcv_mss = len;
+		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
+					       tcp_sk(sk)->advmss);
+		if (unlikely(icsk->icsk_ack.rcv_mss != len))
+			tcp_gro_dev_warn(sk, skb);
 	} else {
 		/* Otherwise, we make more careful check taking into account,
 		 * that SACKs block is variable.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0de9d5d2b9ae..5bab6c3f7a2f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1455,7 +1455,7 @@ static void udp_v4_rehash(struct sock *sk)
 	udp_lib_rehash(sk, new_hash);
 }
 
-static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index 7e0fe4bdd967..feb50a16398d 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -25,7 +25,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		int flags, int *addr_len);
 int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
-int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 void udp_destroy_sock(struct sock *sk);
 
 #ifdef CONFIG_PROC_FS
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index af817158d830..ff450c2aad9b 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -50,7 +50,7 @@ struct proto 	udplite_prot = {
 	.sendmsg	   = udp_sendmsg,
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
-	.backlog_rcv	   = udp_queue_rcv_skb,
+	.backlog_rcv	   = __udp_queue_rcv_skb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v4_get_port,