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, 138 insertions, 39 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 75fb8864be67..bf4e4adc2d00 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1341,6 +1341,37 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 	return NULL;
 }
 
+/* MTU selection:
+ * 1. mtu on route is locked - use it
+ * 2. mtu from nexthop exception
+ * 3. mtu from egress device
+ */
+
+u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
+{
+	struct fib_info *fi = res->fi;
+	struct fib_nh *nh = &fi->fib_nh[res->nh_sel];
+	struct net_device *dev = nh->nh_dev;
+	u32 mtu = 0;
+
+	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
+	    fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
+		mtu = fi->fib_mtu;
+
+	if (likely(!mtu)) {
+		struct fib_nh_exception *fnhe;
+
+		fnhe = find_exception(nh, daddr);
+		if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires))
+			mtu = fnhe->fnhe_pmtu;
+	}
+
+	if (likely(!mtu))
+		mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
+
+	return mtu - lwtunnel_headroom(nh->nh_lwtstate, mtu);
+}
+
 static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 			      __be32 daddr, const bool do_cache)
 {
@@ -2563,11 +2594,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 /* called with rcu_read_lock held */
-static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
-			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
-			u32 seq)
+static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+			struct rtable *rt, u32 table_id, struct flowi4 *fl4,
+			struct sk_buff *skb, u32 portid, u32 seq)
 {
-	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	unsigned long expires = 0;
@@ -2663,7 +2693,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 			}
 		} else
 #endif
-			if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
+			if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif))
 				goto nla_put_failure;
 	}
 
@@ -2678,43 +2708,93 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst,
+						   u8 ip_proto, __be16 sport,
+						   __be16 dport)
+{
+	struct sk_buff *skb;
+	struct iphdr *iph;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	/* Reserve room for dummy headers, this skb can pass
+	 * through good chunk of routing engine.
+	 */
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb->protocol = htons(ETH_P_IP);
+	iph = skb_put(skb, sizeof(struct iphdr));
+	iph->protocol = ip_proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->version = 0x4;
+	iph->frag_off = 0;
+	iph->ihl = 0x5;
+	skb_set_transport_header(skb, skb->len);
+
+	switch (iph->protocol) {
+	case IPPROTO_UDP: {
+		struct udphdr *udph;
+
+		udph = skb_put_zero(skb, sizeof(struct udphdr));
+		udph->source = sport;
+		udph->dest = dport;
+		udph->len = sizeof(struct udphdr);
+		udph->check = 0;
+		break;
+	}
+	case IPPROTO_TCP: {
+		struct tcphdr *tcph;
+
+		tcph = skb_put_zero(skb, sizeof(struct tcphdr));
+		tcph->source	= sport;
+		tcph->dest	= dport;
+		tcph->doff	= sizeof(struct tcphdr) / 4;
+		tcph->rst = 1;
+		tcph->check = ~tcp_v4_check(sizeof(struct tcphdr),
+					    src, dst, 0);
+		break;
+	}
+	case IPPROTO_ICMP: {
+		struct icmphdr *icmph;
+
+		icmph = skb_put_zero(skb, sizeof(struct icmphdr));
+		icmph->type = ICMP_ECHO;
+		icmph->code = 0;
+	}
+	}
+
+	return skb;
+}
+
 static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
-	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
+	u32 table_id = RT_TABLE_MAIN;
+	__be16 sport = 0, dport = 0;
 	struct fib_result res = {};
+	u8 ip_proto = IPPROTO_UDP;
 	struct rtable *rt = NULL;
+	struct sk_buff *skb;
+	struct rtmsg *rtm;
 	struct flowi4 fl4;
 	__be32 dst = 0;
 	__be32 src = 0;
+	kuid_t uid;
 	u32 iif;
 	int err;
 	int mark;
-	struct sk_buff *skb;
-	u32 table_id = RT_TABLE_MAIN;
-	kuid_t uid;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy,
 			  extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	rtm = nlmsg_data(nlh);
-
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb) {
-		err = -ENOBUFS;
-		goto errout;
-	}
-
-	/* Reserve room for dummy headers, this skb can pass
-	   through good chunk of routing engine.
-	 */
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
 	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
@@ -2724,14 +2804,22 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	else
 		uid = (iif ? INVALID_UID : current_uid());
 
-	/* Bugfix: need to give ip_route_input enough of an IP header to
-	 * not gag.
-	 */
-	ip_hdr(skb)->protocol = IPPROTO_UDP;
-	ip_hdr(skb)->saddr = src;
-	ip_hdr(skb)->daddr = dst;
+	if (tb[RTA_IP_PROTO]) {
+		err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
+						  &ip_proto, extack);
+		if (err)
+			return err;
+	}
 
-	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
+	if (tb[RTA_SPORT])
+		sport = nla_get_be16(tb[RTA_SPORT]);
+
+	if (tb[RTA_DPORT])
+		dport = nla_get_be16(tb[RTA_DPORT]);
+
+	skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport);
+	if (!skb)
+		return -ENOBUFS;
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
@@ -2740,6 +2828,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
+	if (sport)
+		fl4.fl4_sport = sport;
+	if (dport)
+		fl4.fl4_dport = dport;
+	fl4.flowi4_proto = ip_proto;
 
 	rcu_read_lock();
 
@@ -2749,10 +2842,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		dev = dev_get_by_index_rcu(net, iif);
 		if (!dev) {
 			err = -ENODEV;
-			goto errout_free;
+			goto errout_rcu;
 		}
 
-		skb->protocol	= htons(ETH_P_IP);
+		fl4.flowi4_iif = iif; /* for rt_fill_info */
 		skb->dev	= dev;
 		skb->mark	= mark;
 		err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
@@ -2772,7 +2865,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	if (err)
-		goto errout_free;
+		goto errout_rcu;
 
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
@@ -2780,34 +2873,40 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
 		table_id = res.table ? res.table->tb_id : 0;
 
+	/* reset skb for netlink reply msg */
+	skb_trim(skb, 0);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_reset_mac_header(skb);
+
 	if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
 		if (!res.fi) {
 			err = fib_props[res.type].error;
 			if (!err)
 				err = -EHOSTUNREACH;
-			goto errout_free;
+			goto errout_rcu;
 		}
 		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
 				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
 				    rt->rt_type, res.prefix, res.prefixlen,
 				    fl4.flowi4_tos, res.fi, 0);
 	} else {
-		err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
+		err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
 				   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
 	}
 	if (err < 0)
-		goto errout_free;
+		goto errout_rcu;
 
 	rcu_read_unlock();
 
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
-errout:
-	return err;
 
 errout_free:
+	return err;
+errout_rcu:
 	rcu_read_unlock();
 	kfree_skb(skb);
-	goto errout;
+	goto errout_free;
 }
 
 void ip_rt_multicast_event(struct in_device *in_dev)