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>

5 files changed, 226 insertions, 16 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..188cc586e7ff 100644
--- a/net/ipv4/ip_output.c
+++ b/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 @@ packet_routed:
 	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 @@ no_route:
 	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)
 {
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5d5a16204d50..297d9cf960b9 100644
--- a/net/sctp/associola.c
+++ b/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.
 	 */
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0cd2e764f47f..fc6c5e4bffa5 100644
--- a/net/sctp/ipv6.c
+++ b/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);
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 67f73d3a1356..e948db29ab53 100644
--- a/net/sctp/protocol.c
+++ b/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;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 0e4c8332771a..502c0d7cb105 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1697,6 +1697,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 	struct sctp_association *asoc;
 	enum sctp_scope scope;
 	struct cmsghdr *cmsg;
+	__be32 flowinfo = 0;
 	struct sctp_af *af;
 	int err;
 
@@ -1781,6 +1782,9 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 	if (!cmsgs->addrs_msg)
 		return 0;
 
+	if (daddr->sa.sa_family == AF_INET6)
+		flowinfo = daddr->v6.sin6_flowinfo;
+
 	/* sendv addr list parse */
 	for_each_cmsghdr(cmsg, cmsgs->addrs_msg) {
 		struct sctp_transport *transport;
@@ -1813,6 +1817,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 			}
 
 			dlen = sizeof(struct in6_addr);
+			daddr->v6.sin6_flowinfo = flowinfo;
 			daddr->v6.sin6_family = AF_INET6;
 			daddr->v6.sin6_port = htons(asoc->peer.port);
 			memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen);
@@ -2393,6 +2398,8 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
  *     uint32_t                spp_pathmtu;
  *     uint32_t                spp_sackdelay;
  *     uint32_t                spp_flags;
+ *     uint32_t                spp_ipv6_flowlabel;
+ *     uint8_t                 spp_dscp;
  * };
  *
  *   spp_assoc_id    - (one-to-many style socket) This is filled in the
@@ -2472,6 +2479,45 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
  *                     also that this field is mutually exclusive to
  *                     SPP_SACKDELAY_ENABLE, setting both will have undefined
  *                     results.
+ *
+ *                     SPP_IPV6_FLOWLABEL:  Setting this flag enables the
+ *                     setting of the IPV6 flow label value.  The value is
+ *                     contained in the spp_ipv6_flowlabel field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_ipv6_flowlabel field has a valid value returned.
+ *                     If a specific destination address is set (in the
+ *                     spp_address field), then the value returned is that of
+ *                     the address.  If just an association is specified (and
+ *                     no address), then the association's default flow label
+ *                     is returned.  If neither an association nor a destination
+ *                     is specified, then the socket's default flow label is
+ *                     returned.  For non-IPv6 sockets, this flag will be left
+ *                     cleared.
+ *
+ *                     SPP_DSCP:  Setting this flag enables the setting of the
+ *                     Differentiated Services Code Point (DSCP) value
+ *                     associated with either the association or a specific
+ *                     address.  The value is obtained in the spp_dscp field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_dscp field has a valid value returned.  If a
+ *                     specific destination address is set when called (in the
+ *                     spp_address field), then that specific destination
+ *                     address's DSCP value is returned.  If just an association
+ *                     is specified, then the association's default DSCP is
+ *                     returned.  If neither an association nor a destination is
+ *                     specified, then the socket's default DSCP is returned.
+ *
+ *   spp_ipv6_flowlabel
+ *                   - This field is used in conjunction with the
+ *                     SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label.
+ *                     The 20 least significant bits are used for the flow
+ *                     label.  This setting has precedence over any IPv6-layer
+ *                     setting.
+ *
+ *   spp_dscp        - This field is used in conjunction with the SPP_DSCP flag
+ *                     and contains the DSCP.  The 6 most significant bits are
+ *                     used for the DSCP.  This setting has precedence over any
+ *                     IPv4- or IPv6- layer setting.
  */
 static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 				       struct sctp_transport   *trans,
@@ -2611,6 +2657,51 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 		}
 	}
 
+	if (params->spp_flags & SPP_IPV6_FLOWLABEL) {
+		if (trans && trans->ipaddr.sa.sa_family == AF_INET6) {
+			trans->flowlabel = params->spp_ipv6_flowlabel &
+					   SCTP_FLOWLABEL_VAL_MASK;
+			trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		} else if (asoc) {
+			list_for_each_entry(trans,
+					    &asoc->peer.transport_addr_list,
+					    transports) {
+				if (trans->ipaddr.sa.sa_family != AF_INET6)
+					continue;
+				trans->flowlabel = params->spp_ipv6_flowlabel &
+						   SCTP_FLOWLABEL_VAL_MASK;
+				trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+			}
+			asoc->flowlabel = params->spp_ipv6_flowlabel &
+					  SCTP_FLOWLABEL_VAL_MASK;
+			asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		} else if (sctp_opt2sk(sp)->sk_family == AF_INET6) {
+			sp->flowlabel = params->spp_ipv6_flowlabel &
+					SCTP_FLOWLABEL_VAL_MASK;
+			sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		}
+	}
+
+	if (params->spp_flags & SPP_DSCP) {
+		if (trans) {
+			trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+			trans->dscp |= SCTP_DSCP_SET_MASK;
+		} else if (asoc) {
+			list_for_each_entry(trans,
+					    &asoc->peer.transport_addr_list,
+					    transports) {
+				trans->dscp = params->spp_dscp &
+					      SCTP_DSCP_VAL_MASK;
+				trans->dscp |= SCTP_DSCP_SET_MASK;
+			}
+			asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+			asoc->dscp |= SCTP_DSCP_SET_MASK;
+		} else {
+			sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+			sp->dscp |= SCTP_DSCP_SET_MASK;
+		}
+	}
+
 	return 0;
 }
 
@@ -2625,11 +2716,18 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
 	int error;
 	int hb_change, pmtud_change, sackdelay_change;
 
-	if (optlen != sizeof(struct sctp_paddrparams))
+	if (optlen == sizeof(params)) {
+		if (copy_from_user(&params, optval, optlen))
+			return -EFAULT;
+	} else if (optlen == ALIGN(offsetof(struct sctp_paddrparams,
+					    spp_ipv6_flowlabel), 4)) {
+		if (copy_from_user(&params, optval, optlen))
+			return -EFAULT;
+		if (params.spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL))
+			return -EINVAL;
+	} else {
 		return -EINVAL;
-
-	if (copy_from_user(&params, optval, optlen))
-		return -EFAULT;
+	}
 
 	/* Validate flags and value parameters. */
 	hb_change        = params.spp_flags & SPP_HB;
@@ -5453,6 +5551,45 @@ out:
  *                     also that this field is mutually exclusive to
  *                     SPP_SACKDELAY_ENABLE, setting both will have undefined
  *                     results.
+ *
+ *                     SPP_IPV6_FLOWLABEL:  Setting this flag enables the
+ *                     setting of the IPV6 flow label value.  The value is
+ *                     contained in the spp_ipv6_flowlabel field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_ipv6_flowlabel field has a valid value returned.
+ *                     If a specific destination address is set (in the
+ *                     spp_address field), then the value returned is that of
+ *                     the address.  If just an association is specified (and
+ *                     no address), then the association's default flow label
+ *                     is returned.  If neither an association nor a destination
+ *                     is specified, then the socket's default flow label is
+ *                     returned.  For non-IPv6 sockets, this flag will be left
+ *                     cleared.
+ *
+ *                     SPP_DSCP:  Setting this flag enables the setting of the
+ *                     Differentiated Services Code Point (DSCP) value
+ *                     associated with either the association or a specific
+ *                     address.  The value is obtained in the spp_dscp field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_dscp field has a valid value returned.  If a
+ *                     specific destination address is set when called (in the
+ *                     spp_address field), then that specific destination
+ *                     address's DSCP value is returned.  If just an association
+ *                     is specified, then the association's default DSCP is
+ *                     returned.  If neither an association nor a destination is
+ *                     specified, then the socket's default DSCP is returned.
+ *
+ *   spp_ipv6_flowlabel
+ *                   - This field is used in conjunction with the
+ *                     SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label.
+ *                     The 20 least significant bits are used for the flow
+ *                     label.  This setting has precedence over any IPv6-layer
+ *                     setting.
+ *
+ *   spp_dscp        - This field is used in conjunction with the SPP_DSCP flag
+ *                     and contains the DSCP.  The 6 most significant bits are
+ *                     used for the DSCP.  This setting has precedence over any
+ *                     IPv4- or IPv6- layer setting.
  */
 static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 					    char __user *optval, int __user *optlen)
@@ -5462,9 +5599,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 	struct sctp_association *asoc = NULL;
 	struct sctp_sock        *sp = sctp_sk(sk);
 
-	if (len < sizeof(struct sctp_paddrparams))
+	if (len >= sizeof(params))
+		len = sizeof(params);
+	else if (len >= ALIGN(offsetof(struct sctp_paddrparams,
+				       spp_ipv6_flowlabel), 4))
+		len = ALIGN(offsetof(struct sctp_paddrparams,
+				     spp_ipv6_flowlabel), 4);
+	else
 		return -EINVAL;
-	len = sizeof(struct sctp_paddrparams);
+
 	if (copy_from_user(&params, optval, len))
 		return -EFAULT;
 
@@ -5499,6 +5642,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 
 		/*draft-11 doesn't say what to return in spp_flags*/
 		params.spp_flags      = trans->param_flags;
+		if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+			params.spp_ipv6_flowlabel = trans->flowlabel &
+						    SCTP_FLOWLABEL_VAL_MASK;
+			params.spp_flags |= SPP_IPV6_FLOWLABEL;
+		}
+		if (trans->dscp & SCTP_DSCP_SET_MASK) {
+			params.spp_dscp	= trans->dscp & SCTP_DSCP_VAL_MASK;
+			params.spp_flags |= SPP_DSCP;
+		}
 	} else if (asoc) {
 		/* Fetch association values. */
 		params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval);
@@ -5508,6 +5660,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 
 		/*draft-11 doesn't say what to return in spp_flags*/
 		params.spp_flags      = asoc->param_flags;
+		if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+			params.spp_ipv6_flowlabel = asoc->flowlabel &
+						    SCTP_FLOWLABEL_VAL_MASK;
+			params.spp_flags |= SPP_IPV6_FLOWLABEL;
+		}
+		if (asoc->dscp & SCTP_DSCP_SET_MASK) {
+			params.spp_dscp	= asoc->dscp & SCTP_DSCP_VAL_MASK;
+			params.spp_flags |= SPP_DSCP;
+		}
 	} else {
 		/* Fetch socket values. */
 		params.spp_hbinterval = sp->hbinterval;
@@ -5517,6 +5678,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 
 		/*draft-11 doesn't say what to return in spp_flags*/
 		params.spp_flags      = sp->param_flags;
+		if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+			params.spp_ipv6_flowlabel = sp->flowlabel &
+						    SCTP_FLOWLABEL_VAL_MASK;
+			params.spp_flags |= SPP_IPV6_FLOWLABEL;
+		}
+		if (sp->dscp & SCTP_DSCP_SET_MASK) {
+			params.spp_dscp	= sp->dscp & SCTP_DSCP_VAL_MASK;
+			params.spp_flags |= SPP_DSCP;
+		}
 	}
 
 	if (copy_to_user(optval, &params, len))