8 files changed, 52 insertions, 23 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 57c1d8431386..139cec29ed06 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -162,12 +162,19 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	if (ip_dont_fragment(sk, &rt->dst)) {
+	/* Do not bother generating IPID for small packets (eg SYNACK) */
+	if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) {
 		iph->frag_off = htons(IP_DF);
 		iph->id = 0;
 	} else {
 		iph->frag_off = 0;
-		__ip_select_ident(net, iph, 1);
+		/* TCP packets here are SYNACK with fat IPv4/TCP options.
+		 * Avoid using the hashed IP ident generator.
+		 */
+		if (sk->sk_protocol == IPPROTO_TCP)
+			iph->id = (__force __be16)prandom_u32();
+		else
+			__ip_select_ident(net, iph, 1);
 	}
 
 	if (opt && opt->opt.optlen) {
@@ -825,15 +832,24 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		/* Everything is OK. Generate! */
 		ip_fraglist_init(skb, iph, hlen, &iter);
 
-		if (iter.frag)
-			ip_options_fragment(iter.frag);
-
 		for (;;) {
 			/* Prepare header of the next frame,
 			 * before previous one went down. */
 			if (iter.frag) {
+				bool first_frag = (iter.offset == 0);
+
 				IPCB(iter.frag)->flags = IPCB(skb)->flags;
 				ip_fraglist_prepare(skb, &iter);
+				if (first_frag && IPCB(skb)->opt.optlen) {
+					/* ipcb->opt is not populated for frags
+					 * coming from __ip_make_skb(),
+					 * ip_options_fragment() needs optlen
+					 */
+					IPCB(iter.frag)->opt.optlen =
+						IPCB(skb)->opt.optlen;
+					ip_options_fragment(iter.frag);
+					ip_send_check(iter.iph);
+				}
 			}
 
 			skb->tstamp = tstamp;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 07274619b9ea..29bbe2b08ae9 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -256,7 +256,9 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return 0;
 
 err2:
+	rtnl_lock();
 	ipmr_free_table(mrt);
+	rtnl_unlock();
 err1:
 	fib_rules_unregister(ops);
 	return err;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 67087f95579f..aab384126f61 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -58,10 +58,6 @@ config NF_TABLES_ARP
 
 endif # NF_TABLES
 
-config NF_FLOW_TABLE_IPV4
-	tristate
-	select NF_FLOW_TABLE_INET
-
 config NF_DUP_IPV4
 	tristate "Netfilter IPv4 packet duplication to alternate destination"
 	depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 0e56df3a45e2..bcf7bc71cb56 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -220,7 +220,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 			continue;
 		}
 
-		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
+		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
+		    sk->sk_bound_dev_if != inet_sdif(skb))
 			continue;
 
 		sock_hold(sk);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9eb5fc247868..9f97b9cbf7b3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -722,6 +722,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int ret = -EINVAL;
 	int chk_addr_ret;
 
+	lock_sock(sk);
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
 		goto out;
 
@@ -741,7 +742,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		inet->inet_saddr = 0;  /* Use device */
 	sk_dst_reset(sk);
 	ret = 0;
-out:	return ret;
+out:
+	release_sock(sk);
+	return ret;
 }
 
 /*
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3b75836db19b..02cb275e5487 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -842,6 +842,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 	}
 
 	release_sock(sk);
+	sk_defer_free_flush(sk);
 
 	if (spliced)
 		return spliced;
@@ -936,6 +937,22 @@ void tcp_remove_empty_skb(struct sock *sk)
 	}
 }
 
+/* skb changing from pure zc to mixed, must charge zc */
+static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb)
+{
+	if (unlikely(skb_zcopy_pure(skb))) {
+		u32 extra = skb->truesize -
+			    SKB_TRUESIZE(skb_end_offset(skb));
+
+		if (!sk_wmem_schedule(sk, extra))
+			return -ENOMEM;
+
+		sk_mem_charge(sk, extra);
+		skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
+	}
+	return 0;
+}
+
 static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
 				      struct page *page, int offset, size_t *size)
 {
@@ -971,7 +988,7 @@ new_segment:
 		tcp_mark_push(tp, skb);
 		goto new_segment;
 	}
-	if (!sk_wmem_schedule(sk, copy))
+	if (tcp_downgrade_zcopy_pure(sk, skb) || !sk_wmem_schedule(sk, copy))
 		return NULL;
 
 	if (can_coalesce) {
@@ -1319,16 +1336,8 @@ new_segment:
 
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
-			/* skb changing from pure zc to mixed, must charge zc */
-			if (unlikely(skb_zcopy_pure(skb))) {
-				if (!sk_wmem_schedule(sk, skb->data_len))
-					goto wait_for_space;
-
-				sk_mem_charge(sk, skb->data_len);
-				skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
-			}
-
-			if (!sk_wmem_schedule(sk, copy))
+			if (tcp_downgrade_zcopy_pure(sk, skb) ||
+			    !sk_wmem_schedule(sk, copy))
 				goto wait_for_space;
 
 			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dc49a3d551eb..bfe4112e000c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1660,6 +1660,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	    (mss != tcp_skb_seglen(skb)))
 		goto out;
 
+	if (!tcp_skb_can_collapse(prev, skb))
+		goto out;
 	len = skb->len;
 	pcount = tcp_skb_pcount(skb);
 	if (tcp_skb_shift(prev, skb, pcount, len))
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b53476e78c84..fec656f5a39e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2095,7 +2095,7 @@ process:
 	nf_reset_ct(skb);
 
 	if (tcp_filter(sk, skb)) {
-		drop_reason = SKB_DROP_REASON_TCP_FILTER;
+		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		goto discard_and_relse;
 	}
 	th = (const struct tcphdr *)skb->data;