net: implement IP_RECVTOS for IP_PKTOPTIONS

Currently, it is not easily possible to get TOS/DSCP value of packets from
an incoming TCP stream. The mechanism is there, IP_PKTOPTIONS getsockopt
with IP_RECVTOS set, the same way as incoming TTL can be queried. This is
not actually implemented for TOS, though.

This patch adds this functionality, both for IPv4 (IP_PKTOPTIONS) and IPv6
(IPV6_2292PKTOPTIONS). For IPv4, like in the IP_RECVTTL case, the value of
the TOS field is stored from the other party's ACK.

This is needed for proxies which require DSCP transparency. One such example
is at http://zph.bratcheda.org/.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 17 insertions, 1 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 4847a64d3c0..8260ef77976 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -366,7 +366,7 @@ struct ipv6_pinfo {
 				dontfrag:1;
 	__u8			min_hopcount;
 	__u8			tclass;
-	__u8			padding;
+	__u8			rcv_tclass;
 
 	__u32			dst_cookie;
 
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 022f772c0eb..ae17e1352d7 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -168,6 +168,7 @@ struct inet_sock {
 				transparent:1,
 				mc_all:1,
 				nodefrag:1;
+	__u8			rcv_tos;
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f7b5670744f..e588a34e85c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -381,6 +381,7 @@ lookup_protocol:
 	inet->mc_all	= 1;
 	inet->mc_index	= 0;
 	inet->mc_list	= NULL;
+	inet->rcv_tos	= 0;
 
 	sk_refcnt_debug_inc(sk);
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9125529dab9..ca50d9f9f8c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1289,6 +1289,10 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			int hlim = inet->mc_ttl;
 			put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
 		}
+		if (inet->cmsg_flags & IP_CMSG_TOS) {
+			int tos = inet->rcv_tos;
+			put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
+		}
 		len -= msg.msg_controllen;
 		return put_user(len, optlen);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4d6f81c818d..94abee8cf56 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1463,6 +1463,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	ireq->opt	      = NULL;
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
+	newinet->rcv_tos      = ip_hdr(skb)->tos;
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 273f48d1df2..5605f9dca87 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -214,6 +214,7 @@ lookup_protocol:
 	inet->mc_ttl	= 1;
 	inet->mc_index	= 0;
 	inet->mc_list	= NULL;
+	inet->rcv_tos	= 0;
 
 	if (ipv4_config.no_pmtu_disc)
 		inet->pmtudisc = IP_PMTUDISC_DONT;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 6d6b65fdaa1..63dd1f89ed7 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1017,6 +1017,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				int hlim = np->mcast_hops;
 				put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
 			}
+			if (np->rxopt.bits.rxtclass) {
+				int tclass = np->rcv_tclass;
+				put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
+			}
 			if (np->rxopt.bits.rxoinfo) {
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d16414cb342..12c6ece67f3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1282,6 +1282,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->opt	   = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
+		newnp->rcv_tclass  = ipv6_tclass(ipv6_hdr(skb));
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1360,6 +1361,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newnp->opt	  = NULL;
 	newnp->mcast_oif  = inet6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
+	newnp->rcv_tclass = ipv6_tclass(ipv6_hdr(skb));
 
 	/* Clone native IPv6 options from listening socket (if any)
 
@@ -1562,6 +1564,8 @@ ipv6_pktoptions:
 			np->mcast_oif = inet6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
+		if (np->rxopt.bits.rxtclass)
+			np->rcv_tclass = ipv6_tclass(ipv6_hdr(skb));
 		if (ipv6_opt_accepted(sk, opt_skb)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);