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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 49 insertions, 58 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 946880ad48ac..c8bc9b4ac328 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -61,6 +61,7 @@
 #include <net/nexthop.h>
 #include <net/lwtunnel.h>
 #include <net/ip_tunnels.h>
+#include <net/l3mdev.h>
 
 #include <asm/uaccess.h>
 
@@ -86,9 +87,9 @@ static void		ip6_dst_ifdown(struct dst_entry *,
 static int		 ip6_dst_gc(struct dst_ops *ops);
 
 static int		ip6_pkt_discard(struct sk_buff *skb);
-static int		ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb);
+static int		ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static int		ip6_pkt_prohibit(struct sk_buff *skb);
-static int		ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb);
+static int		ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu);
@@ -303,7 +304,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
 		.obsolete	= DST_OBSOLETE_FORCE_CHK,
 		.error		= -EINVAL,
 		.input		= dst_discard,
-		.output		= dst_discard_sk,
+		.output		= dst_discard_out,
 	},
 	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
 	.rt6i_protocol  = RTPROT_KERNEL,
@@ -421,31 +422,7 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 static int rt6_info_hash_nhsfn(unsigned int candidate_count,
 			       const struct flowi6 *fl6)
 {
-	unsigned int val = fl6->flowi6_proto;
-
-	val ^= ipv6_addr_hash(&fl6->daddr);
-	val ^= ipv6_addr_hash(&fl6->saddr);
-
-	/* Work only if this not encapsulated */
-	switch (fl6->flowi6_proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_SCTP:
-		val ^= (__force u16)fl6->fl6_sport;
-		val ^= (__force u16)fl6->fl6_dport;
-		break;
-
-	case IPPROTO_ICMPV6:
-		val ^= (__force u16)fl6->fl6_icmp_type;
-		val ^= (__force u16)fl6->fl6_icmp_code;
-		break;
-	}
-	/* RFC6438 recommands to use flowlabel */
-	val ^= (__force u32)fl6->flowlabel;
-
-	/* Perhaps, we need to tune, this function? */
-	val = val ^ (val >> 7) ^ (val >> 12);
-	return val % candidate_count;
+	return get_hash_from_flowi6(fl6) % candidate_count;
 }
 
 static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
@@ -498,10 +475,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
 			if (dev->flags & IFF_LOOPBACK) {
 				if (!sprt->rt6i_idev ||
 				    sprt->rt6i_idev->dev->ifindex != oif) {
-					if (flags & RT6_LOOKUP_F_IFACE && oif)
+					if (flags & RT6_LOOKUP_F_IFACE)
 						continue;
-					if (local && (!oif ||
-						      local->rt6i_idev->dev->ifindex == oif))
+					if (local &&
+					    local->rt6i_idev->dev->ifindex == oif)
 						continue;
 				}
 				local = sprt;
@@ -538,7 +515,7 @@ static void rt6_probe_deferred(struct work_struct *w)
 		container_of(w, struct __rt6_probe_work, work);
 
 	addrconf_addr_solict_mult(&work->target, &mcaddr);
-	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
+	ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL);
 	dev_put(work->dev);
 	kfree(work);
 }
@@ -1168,7 +1145,7 @@ void ip6_route_input(struct sk_buff *skb)
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct ip_tunnel_info *tun_info;
 	struct flowi6 fl6 = {
-		.flowi6_iif = skb->dev->ifindex,
+		.flowi6_iif = l3mdev_fib_oif(skb->dev),
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 		.flowlabel = ip6_flowinfo(iph),
@@ -1192,9 +1169,14 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 				    struct flowi6 *fl6)
 {
+	struct dst_entry *dst;
 	int flags = 0;
 	bool any_src;
 
+	dst = l3mdev_rt6_dst_by_oif(net, fl6);
+	if (dst)
+		return dst;
+
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
 	any_src = ipv6_addr_any(&fl6->saddr);
@@ -1223,7 +1205,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 		new = &rt->dst;
 		new->__use = 1;
 		new->input = dst_discard;
-		new->output = dst_discard_sk;
+		new->output = dst_discard_out;
 
 		dst_copy_metrics(new, &ort->dst);
 		rt->rt6i_idev = ort->rt6i_idev;
@@ -1749,21 +1731,21 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 	return -EINVAL;
 }
 
-int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
+static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 {
-	int err;
 	struct net *net = cfg->fc_nlinfo.nl_net;
 	struct rt6_info *rt = NULL;
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
 	int addr_type;
+	int err = -EINVAL;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
-		return -EINVAL;
+		goto out;
 #ifndef CONFIG_IPV6_SUBTREES
 	if (cfg->fc_src_len)
-		return -EINVAL;
+		goto out;
 #endif
 	if (cfg->fc_ifindex) {
 		err = -ENODEV;
@@ -1878,7 +1860,7 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
 		switch (cfg->fc_type) {
 		case RTN_BLACKHOLE:
 			rt->dst.error = -EINVAL;
-			rt->dst.output = dst_discard_sk;
+			rt->dst.output = dst_discard_out;
 			rt->dst.input = dst_discard;
 			break;
 		case RTN_PROHIBIT:
@@ -1983,9 +1965,7 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	*rt_ret = rt;
-
-	return 0;
+	return rt;
 out:
 	if (dev)
 		dev_put(dev);
@@ -1994,20 +1974,21 @@ out:
 	if (rt)
 		dst_free(&rt->dst);
 
-	*rt_ret = NULL;
-
-	return err;
+	return ERR_PTR(err);
 }
 
 int ip6_route_add(struct fib6_config *cfg)
 {
 	struct mx6_config mxc = { .mx = NULL, };
-	struct rt6_info *rt = NULL;
+	struct rt6_info *rt;
 	int err;
 
-	err = ip6_route_info_create(cfg, &rt);
-	if (err)
+	rt = ip6_route_info_create(cfg);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		rt = NULL;
 		goto out;
+	}
 
 	err = ip6_convert_metrics(&mxc, cfg);
 	if (err)
@@ -2099,7 +2080,6 @@ static int ip6_route_del(struct fib6_config *cfg)
 
 static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb->dev);
 	struct netevent_redirect netevent;
 	struct rt6_info *rt, *nrt = NULL;
 	struct ndisc_options ndopts;
@@ -2160,7 +2140,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	}
 
 	rt = (struct rt6_info *) dst;
-	if (rt == net->ipv6.ip6_null_entry) {
+	if (rt->rt6i_flags & RTF_REJECT) {
 		net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n");
 		return;
 	}
@@ -2289,7 +2269,6 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 					   unsigned int pref)
 {
 	struct fib6_config cfg = {
-		.fc_table	= RT6_TABLE_INFO,
 		.fc_metric	= IP6_RT_PRIO_USER,
 		.fc_ifindex	= ifindex,
 		.fc_dst_len	= prefixlen,
@@ -2300,6 +2279,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 		.fc_nlinfo.nl_net = net,
 	};
 
+	cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
 	cfg.fc_dst = *prefix;
 	cfg.fc_gateway = *gwaddr;
 
@@ -2340,7 +2320,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 				     unsigned int pref)
 {
 	struct fib6_config cfg = {
-		.fc_table	= RT6_TABLE_DFLT,
+		.fc_table	= l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
 		.fc_metric	= IP6_RT_PRIO_USER,
 		.fc_ifindex	= dev->ifindex,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2387,7 +2367,8 @@ static void rtmsg_to_fib6_config(struct net *net,
 {
 	memset(cfg, 0, sizeof(*cfg));
 
-	cfg->fc_table = RT6_TABLE_MAIN;
+	cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
+			 : RT6_TABLE_MAIN;
 	cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
 	cfg->fc_metric = rtmsg->rtmsg_metric;
 	cfg->fc_expires = rtmsg->rtmsg_info;
@@ -2471,7 +2452,7 @@ static int ip6_pkt_discard(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
 }
 
-static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb)
+static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
@@ -2482,7 +2463,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
 }
 
-static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb)
+static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
@@ -2496,6 +2477,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    const struct in6_addr *addr,
 				    bool anycast)
 {
+	u32 tb_id;
 	struct net *net = dev_net(idev->dev);
 	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
 					    DST_NOCOUNT);
@@ -2518,7 +2500,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	rt->rt6i_gateway  = *addr;
 	rt->rt6i_dst.addr = *addr;
 	rt->rt6i_dst.plen = 128;
-	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
+	tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
+	rt->rt6i_table = fib6_get_table(net, tb_id);
 	rt->dst.flags |= DST_NOCACHE;
 
 	atomic_set(&rt->dst.__refcnt, 1);
@@ -2897,9 +2880,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg)
 				r_cfg.fc_encap_type = nla_get_u16(nla);
 		}
 
-		err = ip6_route_info_create(&r_cfg, &rt);
-		if (err)
+		rt = ip6_route_info_create(&r_cfg);
+		if (IS_ERR(rt)) {
+			err = PTR_ERR(rt);
+			rt = NULL;
 			goto cleanup;
+		}
 
 		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
@@ -3278,6 +3264,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	} else {
 		fl6.flowi6_oif = oif;
 
+		if (netif_index_is_l3_master(net, oif)) {
+			fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC |
+					   FLOWI_FLAG_SKIP_NH_OIF;
+		}
+
 		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
 	}