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

3 files changed, 60 insertions, 34 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 73a62700b00a..1b0e7d1f5217 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -808,6 +808,13 @@ 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
@@ -825,12 +832,8 @@ 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;
 	}
 
@@ -1002,39 +1005,27 @@ 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);
 	}
 }
@@ -1155,6 +1146,7 @@ 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);
@@ -1196,7 +1188,7 @@ 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;
@@ -1588,6 +1580,8 @@ 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);
@@ -1600,7 +1594,7 @@ 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. */
@@ -1872,6 +1866,10 @@ 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);
@@ -1938,6 +1936,10 @@ 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/ping.c b/net/ipv4/ping.c
index d11129f1178d..5b2635e69a92 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 fe668c1b9ced..6c790754ae3e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -129,6 +129,23 @@ 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.
  */
@@ -145,7 +162,10 @@ 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.