Merge branch 'tcp-cb-selinux-corruption'

Eric Dumazet says:

====================
tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()

James Morris reported kernel stack corruption bug that
we tracked back to commit 971f10eca186 ("tcp: better TCP_SKB_CB
layout to reduce cache line misses")

First patch needs to be backported to kernels >= 3.18,
while second patch needs to be backported to kernels >= 4.9, since
this was the time when inet_exact_dif_match appeared.
====================

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

3 files changed, 47 insertions, 25 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4e09398009c1..6998707e81f3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -844,12 +844,11 @@ static inline int tcp_v6_sdif(const struct sk_buff *skb)
 }
 #endif
 
-/* TCP_SKB_CB reference means this can not be used from early demux */
 static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
 	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
-	    skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+	    skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
 		return true;
 #endif
 	return false;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c6bc0c4d19c6..77ea45da0fe9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1591,6 +1591,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_filter);
 
+static void tcp_v4_restore_cb(struct sk_buff *skb)
+{
+	memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4,
+		sizeof(struct inet_skb_parm));
+}
+
+static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
+			   const struct tcphdr *th)
+{
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+		sizeof(struct inet_skb_parm));
+	barrier();
+
+	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+				    skb->len - th->doff * 4);
+	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
+	TCP_SKB_CB(skb)->sacked	 = 0;
+	TCP_SKB_CB(skb)->has_rxtstamp =
+			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+}
+
 /*
  *	From tcp_input.c
  */
@@ -1631,24 +1659,6 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
-	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
-	 * barrier() makes sure compiler wont play fool^Waliasing games.
-	 */
-	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
-		sizeof(struct inet_skb_parm));
-	barrier();
-
-	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
-	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
-				    skb->len - th->doff * 4);
-	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
-	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
-	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
-	TCP_SKB_CB(skb)->sacked	 = 0;
-	TCP_SKB_CB(skb)->has_rxtstamp =
-			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
-
 lookup:
 	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
 			       th->dest, sdif, &refcounted);
@@ -1679,14 +1689,19 @@ process:
 		sock_hold(sk);
 		refcounted = true;
 		nsk = NULL;
-		if (!tcp_filter(sk, skb))
+		if (!tcp_filter(sk, skb)) {
+			th = (const struct tcphdr *)skb->data;
+			iph = ip_hdr(skb);
+			tcp_v4_fill_cb(skb, iph, th);
 			nsk = tcp_check_req(sk, skb, req, false);
+		}
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
 		}
 		if (nsk == sk) {
 			reqsk_put(req);
+			tcp_v4_restore_cb(skb);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
 			goto discard_and_relse;
@@ -1712,6 +1727,7 @@ process:
 		goto discard_and_relse;
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
+	tcp_v4_fill_cb(skb, iph, th);
 
 	skb->dev = NULL;
 
@@ -1742,6 +1758,8 @@ no_tcp_socket:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard_it;
 
+	tcp_v4_fill_cb(skb, iph, th);
+
 	if (tcp_checksum_complete(skb)) {
 csum_error:
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
@@ -1768,6 +1786,8 @@ do_time_wait:
 		goto discard_it;
 	}
 
+	tcp_v4_fill_cb(skb, iph, th);
+
 	if (tcp_checksum_complete(skb)) {
 		inet_twsk_put(inet_twsk(sk));
 		goto csum_error;
@@ -1784,6 +1804,7 @@ do_time_wait:
 		if (sk2) {
 			inet_twsk_deschedule_put(inet_twsk(sk));
 			sk = sk2;
+			tcp_v4_restore_cb(skb);
 			refcounted = false;
 			goto process;
 		}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index be11dc13aa70..1f04ec0e4a7a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1454,7 +1454,6 @@ process:
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		tcp_v6_fill_cb(skb, hdr, th);
 		if (tcp_v6_inbound_md5_hash(sk, skb)) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
@@ -1467,8 +1466,12 @@ process:
 		sock_hold(sk);
 		refcounted = true;
 		nsk = NULL;
-		if (!tcp_filter(sk, skb))
+		if (!tcp_filter(sk, skb)) {
+			th = (const struct tcphdr *)skb->data;
+			hdr = ipv6_hdr(skb);
+			tcp_v6_fill_cb(skb, hdr, th);
 			nsk = tcp_check_req(sk, skb, req, false);
+		}
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
@@ -1492,8 +1495,6 @@ process:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	tcp_v6_fill_cb(skb, hdr, th);
-
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
@@ -1501,6 +1502,7 @@ process:
 		goto discard_and_relse;
 	th = (const struct tcphdr *)skb->data;
 	hdr = ipv6_hdr(skb);
+	tcp_v6_fill_cb(skb, hdr, th);
 
 	skb->dev = NULL;