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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 61 insertions, 11 deletions

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index b919e89a9b932..750eaa53bf0ce 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -36,6 +36,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
 #define GENEVE_VER 0
 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
+#define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN)
+#define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN)
 
 /* per-network namespace private data for this module */
 struct geneve_net {
@@ -826,8 +828,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		return PTR_ERR(rt);
 
 	if (skb_dst(skb)) {
-		int mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr) -
-			  GENEVE_BASE_HLEN - info->options_len - 14;
+		int mtu = dst_mtu(&rt->dst) - GENEVE_IPV4_HLEN -
+			  info->options_len;
 
 		skb_dst_update_pmtu(skb, mtu);
 	}
@@ -872,8 +874,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		return PTR_ERR(dst);
 
 	if (skb_dst(skb)) {
-		int mtu = dst_mtu(dst) - sizeof(struct ipv6hdr) -
-			  GENEVE_BASE_HLEN - info->options_len - 14;
+		int mtu = dst_mtu(dst) - GENEVE_IPV6_HLEN - info->options_len;
 
 		skb_dst_update_pmtu(skb, mtu);
 	}
@@ -941,11 +942,10 @@ tx_error:
 
 static int geneve_change_mtu(struct net_device *dev, int new_mtu)
 {
-	/* Only possible if called internally, ndo_change_mtu path's new_mtu
-	 * is guaranteed to be between dev->min_mtu and dev->max_mtu.
-	 */
 	if (new_mtu > dev->max_mtu)
 		new_mtu = dev->max_mtu;
+	else if (new_mtu < dev->min_mtu)
+		new_mtu = dev->min_mtu;
 
 	dev->mtu = new_mtu;
 	return 0;
@@ -1261,7 +1261,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 	}
 
 	if (data[IFLA_GENEVE_REMOTE6]) {
- #if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IPV6)
 		if (changelink && (ip_tunnel_info_af(info) == AF_INET)) {
 			attrtype = IFLA_GENEVE_REMOTE6;
 			goto change_notsup;
@@ -1387,6 +1387,48 @@ change_notsup:
 	return -EOPNOTSUPP;
 }
 
+static void geneve_link_config(struct net_device *dev,
+			       struct ip_tunnel_info *info, struct nlattr *tb[])
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	int ldev_mtu = 0;
+
+	if (tb[IFLA_MTU]) {
+		geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
+		return;
+	}
+
+	switch (ip_tunnel_info_af(info)) {
+	case AF_INET: {
+		struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst };
+		struct rtable *rt = ip_route_output_key(geneve->net, &fl4);
+
+		if (!IS_ERR(rt) && rt->dst.dev) {
+			ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN;
+			ip_rt_put(rt);
+		}
+		break;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6: {
+		struct rt6_info *rt = rt6_lookup(geneve->net,
+						 &info->key.u.ipv6.dst, NULL, 0,
+						 NULL, 0);
+
+		if (rt && rt->dst.dev)
+			ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN;
+		ip6_rt_put(rt);
+		break;
+	}
+#endif
+	}
+
+	if (ldev_mtu <= 0)
+		return;
+
+	geneve_change_mtu(dev, ldev_mtu - info->options_len);
+}
+
 static int geneve_newlink(struct net *net, struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[],
 			  struct netlink_ext_ack *extack)
@@ -1402,8 +1444,14 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 	if (err)
 		return err;
 
-	return geneve_configure(net, dev, extack, &info, metadata,
-				use_udp6_rx_checksums);
+	err = geneve_configure(net, dev, extack, &info, metadata,
+			       use_udp6_rx_checksums);
+	if (err)
+		return err;
+
+	geneve_link_config(dev, &info, tb);
+
+	return 0;
 }
 
 /* Quiesces the geneve device data path for both TX and RX.
@@ -1477,8 +1525,10 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (err)
 		return err;
 
-	if (!geneve_dst_addr_equal(&geneve->info, &info))
+	if (!geneve_dst_addr_equal(&geneve->info, &info)) {
 		dst_cache_reset(&info.dst_cache);
+		geneve_link_config(dev, &info, tb);
+	}
 
 	geneve_quiesce(geneve, &gs4, &gs6);
 	geneve->info = info;