[IPV6]: Support IPV6_{RECV,}TCLASS socket options / ancillary data.

Based on patch from David L Stevens <dlstevens@us.ibm.com>

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

11 files changed, 104 insertions, 24 deletions

diff --git a/include/linux/in6.h b/include/linux/in6.h
index c11022f..bd32b79 100644
--- a/include/linux/in6.h
+++ b/include/linux/in6.h
@@ -219,9 +219,7 @@ struct in6_flowlabel_req
 #define IPV6_DSTOPTS		63
 #define IPV6_RECVHOPLIMIT	64
 #define IPV6_HOPLIMIT		65
-#if 0
 #define IPV6_RECVTCLASS		66
 #define IPV6_TCLASS		67
-#endif
 
 #endif
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 2581f1c..6c5f7b3 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -245,7 +245,8 @@ struct ipv6_pinfo {
 				ohopopts:1,
 				dstopts:1,
 				odstopts:1,
-                                rxflow:1;
+                                rxflow:1,
+				rxtclass:1;
 		} bits;
 		__u16		all;
 	} rxopt;
@@ -256,6 +257,7 @@ struct ipv6_pinfo {
 	                        sndflow:1,
 				pmtudisc:2,
 				ipv6only:1;
+	__u8			tclass;
 
 	__u32			dst_cookie;
 
@@ -269,6 +271,7 @@ struct ipv6_pinfo {
 		struct ipv6_txoptions *opt;
 		struct rt6_info	*rt;
 		int hop_limit;
+		int tclass;
 	} cork;
 };
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8a9fe94..65ec866 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -377,6 +377,7 @@ extern int			ip6_append_data(struct sock *sk,
 						int length,
 						int transhdrlen,
 		      				int hlimit,
+		      				int tclass,
 						struct ipv6_txoptions *opt,
 						struct flowi *fl,
 						struct rt6_info *rt,
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index 8b075ab..4e86f2d 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -37,7 +37,7 @@ extern int			datagram_recv_ctl(struct sock *sk,
 extern int			datagram_send_ctl(struct msghdr *msg,
 						  struct flowi *fl,
 						  struct ipv6_txoptions *opt,
-						  int *hlimit);
+						  int *hlimit, int *tclass);
 
 #define		LOOPBACK4_IPV6		__constant_htonl(0x7f000006)
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 832476b..157cec6 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -390,6 +390,11 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 		put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
 	}
 
+	if (np->rxopt.bits.rxtclass) {
+		int tclass = (ntohl(*(u32 *)skb->nh.ipv6h) >> 20) & 0xff;
+		put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
+	}
+
 	if (np->rxopt.bits.rxflow && (*(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK)) {
 		u32 flowinfo = *(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK;
 		put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo);
@@ -479,7 +484,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 
 int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
 		      struct ipv6_txoptions *opt,
-		      int *hlimit)
+		      int *hlimit, int *tclass)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
@@ -682,6 +687,24 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
 			*hlimit = *(int *)CMSG_DATA(cmsg);
 			break;
 
+		case IPV6_TCLASS:
+		    {
+			int tc;
+
+			err = -EINVAL;
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
+				goto exit_f;
+			}
+
+			tc = *(int *)CMSG_DATA(cmsg);
+			if (tc < 0 || tc > 0xff)
+				goto exit_f;
+
+			err = 0;
+			*tclass = tc;
+
+			break;
+		    }
 		default:
 			LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
 			               cmsg->cmsg_type);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index fa8f1bb..34e99c5 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -287,7 +287,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	int iif = 0;
 	int addr_type = 0;
 	int len;
-	int hlimit;
+	int hlimit, tclass;
 	int err = 0;
 
 	if ((u8*)hdr < skb->head || (u8*)(hdr+1) > skb->tail)
@@ -385,6 +385,10 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	if (hlimit < 0)
 		hlimit = ipv6_get_hoplimit(dst->dev);
 
+	tclass = np->cork.tclass;
+	if (tclass < 0)
+		tclass = 0;
+
 	msg.skb = skb;
 	msg.offset = skb->nh.raw - skb->data;
 
@@ -400,7 +404,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
 			      len + sizeof(struct icmp6hdr),
 			      sizeof(struct icmp6hdr),
-			      hlimit, NULL, &fl, (struct rt6_info*)dst,
+			      hlimit, tclass, NULL, &fl, (struct rt6_info*)dst,
 			      MSG_DONTWAIT);
 	if (err) {
 		ip6_flush_pending_frames(sk);
@@ -434,6 +438,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int err = 0;
 	int hlimit;
+	int tclass;
 
 	saddr = &skb->nh.ipv6h->daddr;
 
@@ -475,13 +480,17 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (hlimit < 0)
 		hlimit = ipv6_get_hoplimit(dst->dev);
 
+	tclass = np->cork.tclass;
+	if (tclass < 0)
+		tclass = 0;
+
 	idev = in6_dev_get(skb->dev);
 
 	msg.skb = skb;
 	msg.offset = 0;
 
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
-				sizeof(struct icmp6hdr), hlimit, NULL, &fl,
+				sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl,
 				(struct rt6_info*)dst, MSG_DONTWAIT);
 
 	if (err) {
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 2d5ce37..a7db762 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -314,7 +314,7 @@ fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *
 		msg.msg_control = (void*)(fl->opt+1);
 		flowi.oif = 0;
 
-		err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk);
+		err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk);
 		if (err)
 			goto done;
 		err = -EINVAL;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 01ef94f..2f589f2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -166,7 +166,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	struct ipv6hdr *hdr;
 	u8  proto = fl->proto;
 	int seg_len = skb->len;
-	int hlimit;
+	int hlimit, tclass;
 	u32 mtu;
 
 	if (opt) {
@@ -202,7 +202,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	 *	Fill in the IPv6 header
 	 */
 
-	*(u32*)hdr = htonl(0x60000000) | fl->fl6_flowlabel;
 	hlimit = -1;
 	if (np)
 		hlimit = np->hop_limit;
@@ -211,6 +210,14 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	if (hlimit < 0)
 		hlimit = ipv6_get_hoplimit(dst->dev);
 
+	tclass = -1;
+	if (np)
+		tclass = np->tclass;
+	if (tclass < 0)
+		tclass = 0;
+
+	*(u32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;
+
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
 	hdr->hop_limit = hlimit;
@@ -762,10 +769,11 @@ out_err_release:
 	return err;
 }
 
-int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb),
-		    void *from, int length, int transhdrlen,
-		    int hlimit, struct ipv6_txoptions *opt, struct flowi *fl, struct rt6_info *rt,
-		    unsigned int flags)
+int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
+	int offset, int len, int odd, struct sk_buff *skb),
+	void *from, int length, int transhdrlen,
+	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
+	struct rt6_info *rt, unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -803,6 +811,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offse
 		np->cork.rt = rt;
 		inet->cork.fl = *fl;
 		np->cork.hop_limit = hlimit;
+		np->cork.tclass = tclass;
 		inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
 		if (dst_allfrag(rt->u.dst.path))
 			inet->cork.flags |= IPCORK_ALLFRAG;
@@ -1084,7 +1093,8 @@ int ip6_push_pending_frames(struct sock *sk)
 
 	skb->nh.ipv6h = hdr = (struct ipv6hdr*) skb_push(skb, sizeof(struct ipv6hdr));
 	
-	*(u32*)hdr = fl->fl6_flowlabel | htonl(0x60000000);
+	*(u32*)hdr = fl->fl6_flowlabel |
+		     htonl(0x60000000 | ((int)np->cork.tclass << 20));
 
 	if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN)
 		hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index dc1d991..8567873 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -264,6 +264,18 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		break;
 
+	case IPV6_TCLASS:
+		if (val < 0 || val > 0xff)
+			goto e_inval;
+		np->tclass = val;
+		retv = 0;
+		break;
+		
+	case IPV6_RECVTCLASS:
+		np->rxopt.bits.rxtclass = valbool;
+		retv = 0;
+		break;
+
 	case IPV6_FLOWINFO:
 		np->rxopt.bits.rxflow = valbool;
 		retv = 0;
@@ -364,7 +376,7 @@ sticky_done:
 		msg.msg_controllen = optlen;
 		msg.msg_control = (void*)(opt+1);
 
-		retv = datagram_send_ctl(&msg, &fl, opt, &junk);
+		retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk);
 		if (retv)
 			goto done;
 update:
@@ -787,6 +799,14 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 		val = np->rxopt.bits.odstopts;
 		break;
 
+	case IPV6_TCLASS:
+		val = np->tclass;
+		break;
+
+	case IPV6_RECVTCLASS:
+		val = np->rxopt.bits.rxtclass;
+		break;
+
 	case IPV6_FLOWINFO:
 		val = np->rxopt.bits.rxflow;
 		break;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index e527a16..2ad3789 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -655,6 +655,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct flowi fl;
 	int addr_len = msg->msg_namelen;
 	int hlimit = -1;
+	int tclass = -1;
 	u16 proto;
 	int err;
 
@@ -740,7 +741,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(msg, &fl, opt, &hlimit);
+		err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -797,6 +798,12 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			hlimit = ipv6_get_hoplimit(dst->dev);
 	}
 
+	if (tclass < 0) {
+		tclass = np->cork.tclass;
+		if (tclass < 0)
+			tclass = 0;
+	}
+
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 
@@ -805,8 +812,9 @@ back_from_confirm:
 		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl, (struct rt6_info*)dst, msg->msg_flags);
 	} else {
 		lock_sock(sk);
-		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,
-					hlimit, opt, &fl, (struct rt6_info*)dst, msg->msg_flags);
+		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
+			len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
+			msg->msg_flags);
 
 		if (err)
 			ip6_flush_pending_frames(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index aa6eaf3..dbd18a9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -637,6 +637,7 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	int addr_len = msg->msg_namelen;
 	int ulen = len;
 	int hlimit = -1;
+	int tclass = -1;
 	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
 	int err;
 
@@ -758,7 +759,7 @@ do_udp_sendmsg:
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(*opt);
 
-		err = datagram_send_ctl(msg, fl, opt, &hlimit);
+		err = datagram_send_ctl(msg, fl, opt, &hlimit, &tclass);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -814,6 +815,12 @@ do_udp_sendmsg:
 			hlimit = ipv6_get_hoplimit(dst->dev);
 	}
 
+	if (tclass < 0) {
+		tclass = np->tclass;
+		if (tclass < 0)
+			tclass = 0;
+	}
+
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 back_from_confirm:
@@ -833,9 +840,10 @@ back_from_confirm:
 
 do_append_data:
 	up->len += ulen;
-	err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, sizeof(struct udphdr),
-			      hlimit, opt, fl, (struct rt6_info*)dst,
-			      corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
+	err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen,
+		sizeof(struct udphdr), hlimit, tclass, opt, fl,
+		(struct rt6_info*)dst,
+		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
 	if (err)
 		udp_v6_flush_pending_frames(sk);
 	else if (!corkreq)