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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 64 insertions, 23 deletions

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index d7559c64795d..65c2e3458ff5 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -424,7 +424,7 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_DP_HASH]	 = { .len = sizeof(u32) },
 	[OVS_KEY_ATTR_TUNNEL]	 = { .len = OVS_ATTR_NESTED,
 				     .next = ovs_tunnel_key_lens, },
-	[OVS_KEY_ATTR_MPLS]	 = { .len = sizeof(struct ovs_key_mpls) },
+	[OVS_KEY_ATTR_MPLS]	 = { .len = OVS_ATTR_VARIABLE },
 	[OVS_KEY_ATTR_CT_STATE]	 = { .len = sizeof(u32) },
 	[OVS_KEY_ATTR_CT_ZONE]	 = { .len = sizeof(u16) },
 	[OVS_KEY_ATTR_CT_MARK]	 = { .len = sizeof(u32) },
@@ -1628,10 +1628,25 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 
 	if (attrs & (1 << OVS_KEY_ATTR_MPLS)) {
 		const struct ovs_key_mpls *mpls_key;
+		u32 hdr_len;
+		u32 label_count, label_count_mask, i;
 
 		mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
-		SW_FLOW_KEY_PUT(match, mpls.top_lse,
-				mpls_key->mpls_lse, is_mask);
+		hdr_len = nla_len(a[OVS_KEY_ATTR_MPLS]);
+		label_count = hdr_len / sizeof(struct ovs_key_mpls);
+
+		if (label_count == 0 || label_count > MPLS_LABEL_DEPTH ||
+		    hdr_len % sizeof(struct ovs_key_mpls))
+			return -EINVAL;
+
+		label_count_mask =  GENMASK(label_count - 1, 0);
+
+		for (i = 0 ; i < label_count; i++)
+			SW_FLOW_KEY_PUT(match, mpls.lse[i],
+					mpls_key[i].mpls_lse, is_mask);
+
+		SW_FLOW_KEY_PUT(match, mpls.num_labels_mask,
+				label_count_mask, is_mask);
 
 		attrs &= ~(1 << OVS_KEY_ATTR_MPLS);
 	 }
@@ -2114,13 +2129,18 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
 		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
 	} else if (eth_p_mpls(swkey->eth.type)) {
+		u8 i, num_labels;
 		struct ovs_key_mpls *mpls_key;
 
-		nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
+		num_labels = hweight_long(output->mpls.num_labels_mask);
+		nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS,
+				  num_labels * sizeof(*mpls_key));
 		if (!nla)
 			goto nla_put_failure;
+
 		mpls_key = nla_data(nla);
-		mpls_key->mpls_lse = output->mpls.top_lse;
+		for (i = 0; i < num_labels; i++)
+			mpls_key[i].mpls_lse = output->mpls.lse[i];
 	}
 
 	if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -2406,13 +2426,14 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  struct sw_flow_actions **sfa,
-				  __be16 eth_type, __be16 vlan_tci, bool log);
+				  __be16 eth_type, __be16 vlan_tci,
+				  u32 mpls_label_count, bool log);
 
 static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 				    const struct sw_flow_key *key,
 				    struct sw_flow_actions **sfa,
 				    __be16 eth_type, __be16 vlan_tci,
-				    bool log, bool last)
+				    u32 mpls_label_count, bool log, bool last)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -2463,7 +2484,7 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 		return err;
 
 	err = __ovs_nla_copy_actions(net, actions, key, sfa,
-				     eth_type, vlan_tci, log);
+				     eth_type, vlan_tci, mpls_label_count, log);
 
 	if (err)
 		return err;
@@ -2478,7 +2499,7 @@ static int validate_and_copy_clone(struct net *net,
 				   const struct sw_flow_key *key,
 				   struct sw_flow_actions **sfa,
 				   __be16 eth_type, __be16 vlan_tci,
-				   bool log, bool last)
+				   u32 mpls_label_count, bool log, bool last)
 {
 	int start, err;
 	u32 exec;
@@ -2498,7 +2519,7 @@ static int validate_and_copy_clone(struct net *net,
 		return err;
 
 	err = __ovs_nla_copy_actions(net, attr, key, sfa,
-				     eth_type, vlan_tci, log);
+				     eth_type, vlan_tci, mpls_label_count, log);
 	if (err)
 		return err;
 
@@ -2864,6 +2885,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 					   const struct sw_flow_key *key,
 					   struct sw_flow_actions **sfa,
 					   __be16 eth_type, __be16 vlan_tci,
+					   u32 mpls_label_count,
 					   bool log, bool last)
 {
 	const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
@@ -2912,7 +2934,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 		return nested_acts_start;
 
 	err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
-				     eth_type, vlan_tci, log);
+				     eth_type, vlan_tci, mpls_label_count, log);
 
 	if (err)
 		return err;
@@ -2925,7 +2947,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 		return nested_acts_start;
 
 	err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
-				     eth_type, vlan_tci, log);
+				     eth_type, vlan_tci, mpls_label_count, log);
 
 	if (err)
 		return err;
@@ -2952,7 +2974,8 @@ static int copy_action(const struct nlattr *from,
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  struct sw_flow_actions **sfa,
-				  __be16 eth_type, __be16 vlan_tci, bool log)
+				  __be16 eth_type, __be16 vlan_tci,
+				  u32 mpls_label_count, bool log)
 {
 	u8 mac_proto = ovs_key_mac_proto(key);
 	const struct nlattr *a;
@@ -3065,25 +3088,36 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			     !eth_p_mpls(eth_type)))
 				return -EINVAL;
 			eth_type = mpls->mpls_ethertype;
+			mpls_label_count++;
 			break;
 		}
 
-		case OVS_ACTION_ATTR_POP_MPLS:
+		case OVS_ACTION_ATTR_POP_MPLS: {
+			__be16  proto;
 			if (vlan_tci & htons(VLAN_CFI_MASK) ||
 			    !eth_p_mpls(eth_type))
 				return -EINVAL;
 
-			/* Disallow subsequent L2.5+ set and mpls_pop actions
-			 * as there is no check here to ensure that the new
-			 * eth_type is valid and thus set actions could
-			 * write off the end of the packet or otherwise
-			 * corrupt it.
+			/* Disallow subsequent L2.5+ set actions and mpls_pop
+			 * actions once the last MPLS label in the packet is
+			 * is popped as there is no check here to ensure that
+			 * the new eth type is valid and thus set actions could
+			 * write off the end of the packet or otherwise corrupt
+			 * it.
 			 *
 			 * Support for these actions is planned using packet
 			 * recirculation.
 			 */
-			eth_type = htons(0);
+			proto = nla_get_be16(a);
+			mpls_label_count--;
+
+			if (!eth_p_mpls(proto) || !mpls_label_count)
+				eth_type = htons(0);
+			else
+				eth_type =  proto;
+
 			break;
+		}
 
 		case OVS_ACTION_ATTR_SET:
 			err = validate_set(a, key, sfa,
@@ -3106,6 +3140,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
 			err = validate_and_copy_sample(net, a, key, sfa,
 						       eth_type, vlan_tci,
+						       mpls_label_count,
 						       log, last);
 			if (err)
 				return err;
@@ -3176,6 +3211,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
 			err = validate_and_copy_clone(net, a, key, sfa,
 						      eth_type, vlan_tci,
+						      mpls_label_count,
 						      log, last);
 			if (err)
 				return err;
@@ -3188,8 +3224,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
 			err = validate_and_copy_check_pkt_len(net, a, key, sfa,
 							      eth_type,
-							      vlan_tci, log,
-							      last);
+							      vlan_tci,
+							      mpls_label_count,
+							      log, last);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3219,14 +3256,18 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			 struct sw_flow_actions **sfa, bool log)
 {
 	int err;
+	u32 mpls_label_count = 0;
 
 	*sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE));
 	if (IS_ERR(*sfa))
 		return PTR_ERR(*sfa);
 
+	if (eth_p_mpls(key->eth.type))
+		mpls_label_count = hweight_long(key->mpls.num_labels_mask);
+
 	(*sfa)->orig_len = nla_len(attr);
 	err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
-				     key->eth.vlan.tci, log);
+				     key->eth.vlan.tci, mpls_label_count, log);
 	if (err)
 		ovs_nla_free_flow_actions(*sfa);