net: Require exact match for TCP socket lookups if dif is l3mdev

Currently, socket lookups for l3mdev (vrf) use cases can match a socket
that is bound to a port but not a device (ie., a global socket). If the
sysctl tcp_l3mdev_accept is not set this leads to ack packets going out
based on the main table even though the packet came in from an L3 domain.
The end result is that the connection does not establish creating
confusion for users since the service is running and a socket shows in
ss output. Fix by requiring an exact dif to sk_bound_dev_if match if the
skb came through an interface enslaved to an l3mdev device and the
tcp_l3mdev_accept is not set.

skb's through an l3mdev interface are marked by setting a flag in
inet{6}_skb_parm. The IPv6 variant is already set; this patch adds the
flag for IPv4. Using an skb flag avoids a device lookup on the dif. The
flag is set in the VRF driver using the IP{6}CB macros. For IPv4, the
inet_skb_parm struct is moved in the cb per commit 971f10eca186, so the
match function in the TCP stack needs to use TCP_SKB_CB. For IPv6, the
move is done after the socket lookup, so IP6CB is used.

The flags field in inet_skb_parm struct needs to be increased to add
another flag. There is currently a 1-byte hole following the flags,
so it can be expanded to u16 without increasing the size of the struct.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 33 insertions, 5 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7e9a789be5e0..ca1ad9ebbc92 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -123,12 +123,12 @@ struct inet6_skb_parm {
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
 {
 	return flags & IP6SKB_L3SLAVE;
 }
 #else
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
 {
 	return false;
 }
@@ -139,11 +139,22 @@ static inline bool skb_l3mdev_slave(__u16 flags)
 
 static inline int inet6_iif(const struct sk_buff *skb)
 {
-	bool l3_slave = skb_l3mdev_slave(IP6CB(skb)->flags);
+	bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags);
 
 	return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
 }
 
+/* can not be used in TCP layer after tcp_v6_fill_cb */
+static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if defined(CONFIG_NET_L3_MASTER_DEV)
+	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+	    ipv6_l3mdev_skb(IP6CB(skb)->flags))
+		return true;
+#endif
+	return false;
+}
+
 struct tcp6_request_sock {
 	struct tcp_request_sock	  tcp6rsk_tcp;
 };
diff --git a/include/net/ip.h b/include/net/ip.h
index bc43c0fcae12..c9d07988911e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -38,7 +38,7 @@ struct sock;
 struct inet_skb_parm {
 	int			iif;
 	struct ip_options	opt;		/* Compiled IP options		*/
-	unsigned char		flags;
+	u16			flags;
 
 #define IPSKB_FORWARDED		BIT(0)
 #define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
@@ -48,10 +48,16 @@ struct inet_skb_parm {
 #define IPSKB_DOREDIRECT	BIT(5)
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_FRAG_SEGS		BIT(7)
+#define IPSKB_L3SLAVE		BIT(8)
 
 	u16			frag_max_size;
 };
 
+static inline bool ipv4_l3mdev_skb(u16 flags)
+{
+	return !!(flags & IPSKB_L3SLAVE);
+}
+
 static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
 {
 	return ip_hdr(skb)->ihl * 4;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f83b7f220a65..5b82d4d94834 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -794,12 +794,23 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
-	bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
 	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
 #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 &&
+	    ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+		return true;
+#endif
+	return false;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */