Merge branch 'sctp-fully-support-for-dscp-and-flowlabel-per-transport'

Xin Long says:

====================
sctp: fully support for dscp and flowlabel per transport

Now dscp and flowlabel are set from sock when sending the packets,
but being multi-homing, sctp also supports for dscp and flowlabel
per transport, which is described in section 8.1.12 in RFC6458.

v1->v2:
  - define ip_queue_xmit as inline in net/ip.h, instead of exporting
    it in Patch 1/5 according to David's suggestion.
  - fix the param len check in sctp_s/getsockopt_peer_addr_params()
    in Patch 3/5 to guarantee that an old app built with old kernel
    headers could work on the newer kernel per Marcelo's point.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/sctp.h

@@ -801,4 +801,11 @@ struct sctp_strreset_resptsn {
 	__be32 receivers_next_tsn;
 };
 
+enum {
+	SCTP_DSCP_SET_MASK = 0x1,
+	SCTP_DSCP_VAL_MASK = 0xfc,
+	SCTP_FLOWLABEL_SET_MASK = 0x100000,
+	SCTP_FLOWLABEL_VAL_MASK = 0xfffff
+};
+
 #endif /* __LINUX_SCTP_H__ */

include/net/ip.h

@@ -148,7 +148,8 @@ void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 
-int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
+int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+		    __u8 tos);
 void ip_init(void);
 int ip_append_data(struct sock *sk, struct flowi4 *fl4,
 		   int getfrag(void *from, char *to, int offset, int len,
@@ -174,6 +175,12 @@ struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
 			    struct ipcm_cookie *ipc, struct rtable **rtp,
 			    struct inet_cork *cork, unsigned int flags);
 
+static inline int ip_queue_xmit(struct sock *sk, struct sk_buff *skb,
+				struct flowi *fl)
+{
+	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+}
+
 static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 {
 	return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);

include/net/sctp/structs.h

@@ -193,6 +193,9 @@ struct sctp_sock {
 	/* This is the max_retrans value for new associations. */
 	__u16 pathmaxrxt;
 
+	__u32 flowlabel;
+	__u8  dscp;
+
 	/* The initial Path MTU to use for new associations. */
 	__u32 pathmtu;
 
@@ -895,6 +898,9 @@ struct sctp_transport {
 	 */
 	__u16 pathmaxrxt;
 
+	__u32 flowlabel;
+	__u8  dscp;
+
 	/* This is the partially failed retrans value for the transport
 	 * and will be initialized from the assocs value.  This can be changed
 	 * using the SCTP_PEER_ADDR_THLDS socket option
@@ -1772,6 +1778,9 @@ struct sctp_association {
 	 */
 	__u16 pathmaxrxt;
 
+	__u32 flowlabel;
+	__u8  dscp;
+
 	/* Flag that path mtu update is pending */
 	__u8   pmtu_pending;
 

include/uapi/linux/sctp.h

@@ -763,6 +763,8 @@ enum  sctp_spp_flags {
 	SPP_SACKDELAY_DISABLE = 1<<6,	/*Disable SACK*/
 	SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE,
 	SPP_HB_TIME_IS_ZERO = 1<<7,	/* Set HB delay to 0 */
+	SPP_IPV6_FLOWLABEL = 1<<8,
+	SPP_DSCP = 1<<9,
 };
 
 struct sctp_paddrparams {
@@ -773,6 +775,8 @@ struct sctp_paddrparams {
 	__u32			spp_pathmtu;
 	__u32			spp_sackdelay;
 	__u32			spp_flags;
+	__u32			spp_ipv6_flowlabel;
+	__u8			spp_dscp;
 } __attribute__((packed, aligned(4)));
 
 /*

net/ipv4/ip_output.c

@@ -423,7 +423,8 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
 }
 
 /* Note: skb->sk can be different from sk, in case of tunnels */
-int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
+int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+		    __u8 tos)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
@@ -462,7 +463,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 					   inet->inet_dport,
 					   inet->inet_sport,
 					   sk->sk_protocol,
-					   RT_CONN_FLAGS(sk),
+					   RT_CONN_FLAGS_TOS(sk, tos),
 					   sk->sk_bound_dev_if);
 		if (IS_ERR(rt))
 			goto no_route;
@@ -478,7 +479,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 	skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
-	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
+	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff));
 	if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
 		iph->frag_off = htons(IP_DF);
 	else
@@ -511,7 +512,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 	kfree_skb(skb);
 	return -EHOSTUNREACH;
 }
-EXPORT_SYMBOL(ip_queue_xmit);
+EXPORT_SYMBOL(__ip_queue_xmit);
 
 static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 {

net/sctp/associola.c

@@ -115,6 +115,9 @@ static struct sctp_association *sctp_association_init(
 	/* Initialize path max retrans value. */
 	asoc->pathmaxrxt = sp->pathmaxrxt;
 
+	asoc->flowlabel = sp->flowlabel;
+	asoc->dscp = sp->dscp;
+
 	/* Initialize default path MTU. */
 	asoc->pathmtu = sp->pathmtu;
 
@@ -647,6 +650,18 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	peer->sackdelay = asoc->sackdelay;
 	peer->sackfreq = asoc->sackfreq;
 
+	if (addr->sa.sa_family == AF_INET6) {
+		__be32 info = addr->v6.sin6_flowinfo;
+
+		if (info) {
+			peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK);
+			peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		} else {
+			peer->flowlabel = asoc->flowlabel;
+		}
+	}
+	peer->dscp = asoc->dscp;
+
 	/* Enable/disable heartbeat, SACK delay, and path MTU discovery
 	 * based on association setting.
 	 */

net/sctp/ipv6.c

@@ -209,12 +209,17 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct flowi6 *fl6 = &transport->fl.u.ip6;
+	__u8 tclass = np->tclass;
 	int res;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
 		 skb->len, &fl6->saddr, &fl6->daddr);
 
-	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
+	if (transport->dscp & SCTP_DSCP_SET_MASK)
+		tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
+
+	if (INET_ECN_is_capable(tclass))
+		IP6_ECN_flow_xmit(sk, fl6->flowlabel);
 
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
 		skb->ignore_df = 1;
@@ -223,7 +228,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 
 	rcu_read_lock();
 	res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
-		       np->tclass);
+		       tclass);
 	rcu_read_unlock();
 	return res;
 }
@@ -254,6 +259,17 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl6->flowi6_oif = daddr->v6.sin6_scope_id;
 	else if (asoc)
 		fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if;
+	if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK)
+		fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK);
+
+	if (np->sndflow && (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) {
+		struct ip6_flowlabel *flowlabel;
+
+		flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
+		if (!flowlabel)
+			goto out;
+		fl6_sock_release(flowlabel);
+	}
 
 	pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr);
 

net/sctp/protocol.c

@@ -426,13 +426,16 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct dst_entry *dst = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
+	__u8 tos = inet_sk(sk)->tos;
 
+	if (t->dscp & SCTP_DSCP_SET_MASK)
+		tos = t->dscp & SCTP_DSCP_VAL_MASK;
 	memset(fl4, 0x0, sizeof(struct flowi4));
 	fl4->daddr  = daddr->v4.sin_addr.s_addr;
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
-		fl4->flowi4_tos = RT_CONN_FLAGS(asoc->base.sk);
+		fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
 		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
 		fl4->fl4_sport = htons(asoc->base.bind_addr.port);
 	}
@@ -495,7 +498,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl4->fl4_sport = laddr->a.v4.sin_port;
 		flowi4_update_output(fl4,
 				     asoc->base.sk->sk_bound_dev_if,
-				     RT_CONN_FLAGS(asoc->base.sk),
+				     RT_CONN_FLAGS_TOS(asoc->base.sk, tos),
 				     daddr->v4.sin_addr.s_addr,
 				     laddr->a.v4.sin_addr.s_addr);
 
@@ -971,16 +974,21 @@ static inline int sctp_v4_xmit(struct sk_buff *skb,
 			       struct sctp_transport *transport)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
+	__u8 dscp = inet->tos;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
-		 skb->len, &transport->fl.u.ip4.saddr, &transport->fl.u.ip4.daddr);
+		 skb->len, &transport->fl.u.ip4.saddr,
+		 &transport->fl.u.ip4.daddr);
+
+	if (transport->dscp & SCTP_DSCP_SET_MASK)
+		dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
 
 	inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
 			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
 
 	SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
 
-	return ip_queue_xmit(&inet->sk, skb, &transport->fl);
+	return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
 }
 
 static struct sctp_af sctp_af_inet;