Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 143 insertions, 104 deletions

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4703b09808d0..821d96c720b9 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -89,6 +89,11 @@ struct ip6_tnl_net {
 	struct ip6_tnl __rcu *collect_md_tun;
 };
 
+static inline int ip6_tnl_mpls_supported(void)
+{
+	return IS_ENABLED(CONFIG_MPLS);
+}
+
 static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 {
 	struct pcpu_sw_netstats tmp, sum = { 0 };
@@ -718,6 +723,20 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	return 0;
 }
 
+static int
+mplsip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+	    u8 type, u8 code, int offset, __be32 info)
+{
+	__u32 rel_info = ntohl(info);
+	int err, rel_msg = 0;
+	u8 rel_type = type;
+	u8 rel_code = code;
+
+	err = ip6_tnl_err(skb, IPPROTO_MPLS, opt, &rel_type, &rel_code,
+			  &rel_msg, &rel_info, offset);
+	return err;
+}
+
 static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
 				       const struct ipv6hdr *ipv6h,
 				       struct sk_buff *skb)
@@ -740,6 +759,14 @@ static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
 	return IP6_ECN_decapsulate(ipv6h, skb);
 }
 
+static inline int mplsip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
+					       const struct ipv6hdr *ipv6h,
+					       struct sk_buff *skb)
+{
+	/* ECN is not supported in AF_MPLS */
+	return 0;
+}
+
 __u32 ip6_tnl_get_cap(struct ip6_tnl *t,
 			     const struct in6_addr *laddr,
 			     const struct in6_addr *raddr)
@@ -901,6 +928,11 @@ static const struct tnl_ptk_info tpi_v4 = {
 	.proto = htons(ETH_P_IP),
 };
 
+static const struct tnl_ptk_info tpi_mpls = {
+	/* no tunnel info required for mplsip6. */
+	.proto = htons(ETH_P_MPLS_UC),
+};
+
 static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 		      const struct tnl_ptk_info *tpi,
 		      int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
@@ -958,6 +990,12 @@ static int ip6ip6_rcv(struct sk_buff *skb)
 			  ip6ip6_dscp_ecn_decapsulate);
 }
 
+static int mplsip6_rcv(struct sk_buff *skb)
+{
+	return ipxip6_rcv(skb, IPPROTO_MPLS, &tpi_mpls,
+			  mplsip6_dscp_ecn_decapsulate);
+}
+
 struct ipv6_tel_txoption {
 	struct ipv6_txoptions ops;
 	__u8 dst_opt[8];
@@ -1232,6 +1270,8 @@ route_lookup:
 		ipv6_push_frag_opts(skb, &opt.ops, &proto);
 	}
 
+	skb_set_inner_ipproto(skb, proto);
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
@@ -1253,22 +1293,22 @@ tx_err_dst_release:
 EXPORT_SYMBOL(ip6_tnl_xmit);
 
 static inline int
-ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
+ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev,
+		u8 protocol)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
+	struct ipv6hdr *ipv6h;
 	const struct iphdr  *iph;
 	int encap_limit = -1;
+	__u16 offset;
 	struct flowi6 fl6;
-	__u8 dsfield;
+	__u8 dsfield, orig_dsfield;
 	__u32 mtu;
 	u8 tproto;
 	int err;
 
-	iph = ip_hdr(skb);
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-
 	tproto = READ_ONCE(t->parms.proto);
-	if (tproto != IPPROTO_IPIP && tproto != 0)
+	if (tproto != protocol && tproto != 0)
 		return -1;
 
 	if (t->parms.collect_md) {
@@ -1281,129 +1321,100 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 			return -1;
 		key = &tun_info->key;
 		memset(&fl6, 0, sizeof(fl6));
-		fl6.flowi6_proto = IPPROTO_IPIP;
+		fl6.flowi6_proto = protocol;
 		fl6.saddr = key->u.ipv6.src;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
 		dsfield =  key->tos;
+		switch (protocol) {
+		case IPPROTO_IPIP:
+			iph = ip_hdr(skb);
+			orig_dsfield = ipv4_get_dsfield(iph);
+			break;
+		case IPPROTO_IPV6:
+			ipv6h = ipv6_hdr(skb);
+			orig_dsfield = ipv6_get_dsfield(ipv6h);
+			break;
+		default:
+			orig_dsfield = dsfield;
+			break;
+		}
 	} else {
 		if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 			encap_limit = t->parms.encap_limit;
+		if (protocol == IPPROTO_IPV6) {
+			offset = ip6_tnl_parse_tlv_enc_lim(skb,
+						skb_network_header(skb));
+			/* ip6_tnl_parse_tlv_enc_lim() might have
+			 * reallocated skb->head
+			 */
+			if (offset > 0) {
+				struct ipv6_tlv_tnl_enc_lim *tel;
 
-		memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-		fl6.flowi6_proto = IPPROTO_IPIP;
-
-		if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-			dsfield = ipv4_get_dsfield(iph);
-		else
-			dsfield = ip6_tclass(t->parms.flowinfo);
-		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
-			fl6.flowi6_mark = skb->mark;
-		else
-			fl6.flowi6_mark = t->parms.fwmark;
-	}
-
-	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
-	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
-
-	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
-		return -1;
-
-	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
-
-	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
-			   IPPROTO_IPIP);
-	if (err != 0) {
-		/* XXX: send ICMP error even if DF is not set. */
-		if (err == -EMSGSIZE)
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-				  htonl(mtu));
-		return -1;
-	}
-
-	return 0;
-}
-
-static inline int
-ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct ip6_tnl *t = netdev_priv(dev);
-	struct ipv6hdr *ipv6h;
-	int encap_limit = -1;
-	__u16 offset;
-	struct flowi6 fl6;
-	__u8 dsfield;
-	__u32 mtu;
-	u8 tproto;
-	int err;
-
-	ipv6h = ipv6_hdr(skb);
-	tproto = READ_ONCE(t->parms.proto);
-	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
-	    ip6_tnl_addr_conflict(t, ipv6h))
-		return -1;
-
-	if (t->parms.collect_md) {
-		struct ip_tunnel_info *tun_info;
-		const struct ip_tunnel_key *key;
-
-		tun_info = skb_tunnel_info(skb);
-		if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
-			     ip_tunnel_info_af(tun_info) != AF_INET6))
-			return -1;
-		key = &tun_info->key;
-		memset(&fl6, 0, sizeof(fl6));
-		fl6.flowi6_proto = IPPROTO_IPV6;
-		fl6.saddr = key->u.ipv6.src;
-		fl6.daddr = key->u.ipv6.dst;
-		fl6.flowlabel = key->label;
-		dsfield = key->tos;
-	} else {
-		offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
-		/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
-		ipv6h = ipv6_hdr(skb);
-		if (offset > 0) {
-			struct ipv6_tlv_tnl_enc_lim *tel;
-
-			tel = (void *)&skb_network_header(skb)[offset];
-			if (tel->encap_limit == 0) {
-				icmpv6_send(skb, ICMPV6_PARAMPROB,
-					    ICMPV6_HDR_FIELD, offset + 2);
-				return -1;
+				tel = (void *)&skb_network_header(skb)[offset];
+				if (tel->encap_limit == 0) {
+					icmpv6_send(skb, ICMPV6_PARAMPROB,
+						ICMPV6_HDR_FIELD, offset + 2);
+					return -1;
+				}
+				encap_limit = tel->encap_limit - 1;
 			}
-			encap_limit = tel->encap_limit - 1;
-		} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) {
-			encap_limit = t->parms.encap_limit;
 		}
 
 		memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-		fl6.flowi6_proto = IPPROTO_IPV6;
+		fl6.flowi6_proto = protocol;
 
-		if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-			dsfield = ipv6_get_dsfield(ipv6h);
-		else
-			dsfield = ip6_tclass(t->parms.flowinfo);
-		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
-			fl6.flowlabel |= ip6_flowlabel(ipv6h);
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 			fl6.flowi6_mark = skb->mark;
 		else
 			fl6.flowi6_mark = t->parms.fwmark;
+		switch (protocol) {
+		case IPPROTO_IPIP:
+			iph = ip_hdr(skb);
+			orig_dsfield = ipv4_get_dsfield(iph);
+			if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+				dsfield = orig_dsfield;
+			else
+				dsfield = ip6_tclass(t->parms.flowinfo);
+			break;
+		case IPPROTO_IPV6:
+			ipv6h = ipv6_hdr(skb);
+			orig_dsfield = ipv6_get_dsfield(ipv6h);
+			if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+				dsfield = orig_dsfield;
+			else
+				dsfield = ip6_tclass(t->parms.flowinfo);
+			if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+				fl6.flowlabel |= ip6_flowlabel(ipv6h);
+			break;
+		default:
+			orig_dsfield = dsfield = ip6_tclass(t->parms.flowinfo);
+			break;
+		}
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
-	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
+	dsfield = INET_ECN_encapsulate(dsfield, orig_dsfield);
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
-
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
-			   IPPROTO_IPV6);
+			   protocol);
 	if (err != 0) {
+		/* XXX: send ICMP error even if DF is not set. */
 		if (err == -EMSGSIZE)
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			switch (protocol) {
+			case IPPROTO_IPIP:
+				icmp_send(skb, ICMP_DEST_UNREACH,
+					  ICMP_FRAG_NEEDED, htonl(mtu));
+				break;
+			case IPPROTO_IPV6:
+				icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+				break;
+			default:
+				break;
+			}
 		return -1;
 	}
 
@@ -1415,6 +1426,7 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net_device_stats *stats = &t->dev->stats;
+	u8 ipproto;
 	int ret;
 
 	if (!pskb_inet_may_pull(skb))
@@ -1422,15 +1434,21 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ret = ip4ip6_tnl_xmit(skb, dev);
+		ipproto = IPPROTO_IPIP;
 		break;
 	case htons(ETH_P_IPV6):
-		ret = ip6ip6_tnl_xmit(skb, dev);
+		if (ip6_tnl_addr_conflict(t, ipv6_hdr(skb)))
+			goto tx_err;
+		ipproto = IPPROTO_IPV6;
+		break;
+	case htons(ETH_P_MPLS_UC):
+		ipproto = IPPROTO_MPLS;
 		break;
 	default:
 		goto tx_err;
 	}
 
+	ret = ipxip6_tnl_xmit(skb, dev, ipproto);
 	if (ret < 0)
 		goto tx_err;
 
@@ -2218,6 +2236,12 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
 	.priority	=	1,
 };
 
+static struct xfrm6_tunnel mplsip6_handler __read_mostly = {
+	.handler	= mplsip6_rcv,
+	.err_handler	= mplsip6_err,
+	.priority	=	1,
+};
+
 static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
@@ -2332,6 +2356,15 @@ static int __init ip6_tunnel_init(void)
 		pr_err("%s: can't register ip6ip6\n", __func__);
 		goto out_ip6ip6;
 	}
+
+	if (ip6_tnl_mpls_supported()) {
+		err = xfrm6_tunnel_register(&mplsip6_handler, AF_MPLS);
+		if (err < 0) {
+			pr_err("%s: can't register mplsip6\n", __func__);
+			goto out_mplsip6;
+		}
+	}
+
 	err = rtnl_link_register(&ip6_link_ops);
 	if (err < 0)
 		goto rtnl_link_failed;
@@ -2339,6 +2372,9 @@ static int __init ip6_tunnel_init(void)
 	return 0;
 
 rtnl_link_failed:
+	if (ip6_tnl_mpls_supported())
+		xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS);
+out_mplsip6:
 	xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6);
 out_ip6ip6:
 	xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
@@ -2361,6 +2397,9 @@ static void __exit ip6_tunnel_cleanup(void)
 	if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6))
 		pr_info("%s: can't deregister ip6ip6\n", __func__);
 
+	if (ip6_tnl_mpls_supported() &&
+	    xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS))
+		pr_info("%s: can't deregister mplsip6\n", __func__);
 	unregister_pernet_device(&ip6_tnl_net_ops);
 }