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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 35 insertions, 31 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 217683d40f12..92b8d8c75eed 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -107,16 +107,13 @@ enum {
 
 void fib6_update_sernum(struct rt6_info *rt)
 {
-	struct fib6_table *table = rt->rt6i_table;
 	struct net *net = dev_net(rt->dst.dev);
 	struct fib6_node *fn;
 
-	spin_lock_bh(&table->tb6_lock);
 	fn = rcu_dereference_protected(rt->rt6i_node,
-			lockdep_is_held(&table->tb6_lock));
+			lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	if (fn)
 		fn->fn_sernum = fib6_new_sernum(net);
-	spin_unlock_bh(&table->tb6_lock);
 }
 
 /*
@@ -804,12 +801,6 @@ insert_above:
 	return ln;
 }
 
-static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
-{
-	return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
-	       RTF_GATEWAY;
-}
-
 static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
 {
 	int i;
@@ -898,7 +889,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 	ins = &fn->leaf;
 
 	for (iter = leaf; iter;
-	     iter = rcu_dereference_protected(iter->dst.rt6_next,
+	     iter = rcu_dereference_protected(iter->rt6_next,
 				lockdep_is_held(&rt->rt6i_table->tb6_lock))) {
 		/*
 		 *	Search for duplicates
@@ -955,7 +946,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			break;
 
 next_iter:
-		ins = &iter->dst.rt6_next;
+		ins = &iter->rt6_next;
 	}
 
 	if (fallback_ins && !found) {
@@ -984,7 +975,7 @@ next_iter:
 					      &sibling->rt6i_siblings);
 				break;
 			}
-			sibling = rcu_dereference_protected(sibling->dst.rt6_next,
+			sibling = rcu_dereference_protected(sibling->rt6_next,
 				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 		}
 		/* For each sibling in the list, increment the counter of
@@ -999,6 +990,7 @@ next_iter:
 			rt6i_nsiblings++;
 		}
 		BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings);
+		rt6_multipath_rebalance(temp_sibling);
 	}
 
 	/*
@@ -1014,7 +1006,7 @@ add:
 		if (err)
 			return err;
 
-		rcu_assign_pointer(rt->dst.rt6_next, iter);
+		rcu_assign_pointer(rt->rt6_next, iter);
 		atomic_inc(&rt->rt6i_ref);
 		rcu_assign_pointer(rt->rt6i_node, fn);
 		rcu_assign_pointer(*ins, rt);
@@ -1045,7 +1037,7 @@ add:
 
 		atomic_inc(&rt->rt6i_ref);
 		rcu_assign_pointer(rt->rt6i_node, fn);
-		rt->dst.rt6_next = iter->dst.rt6_next;
+		rt->rt6_next = iter->rt6_next;
 		rcu_assign_pointer(*ins, rt);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE,
 					  rt, extack);
@@ -1064,14 +1056,14 @@ add:
 
 		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
-			ins = &rt->dst.rt6_next;
+			ins = &rt->rt6_next;
 			iter = rcu_dereference_protected(*ins,
 				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 			while (iter) {
 				if (iter->rt6i_metric > rt->rt6i_metric)
 					break;
 				if (rt6_qualify_for_ecmp(iter)) {
-					*ins = iter->dst.rt6_next;
+					*ins = iter->rt6_next;
 					iter->rt6i_node = NULL;
 					fib6_purge_rt(iter, fn, info->nl_net);
 					if (rcu_access_pointer(fn->rr_ptr) == iter)
@@ -1080,7 +1072,7 @@ add:
 					nsiblings--;
 					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
 				} else {
-					ins = &iter->dst.rt6_next;
+					ins = &iter->rt6_next;
 				}
 				iter = rcu_dereference_protected(*ins,
 					lockdep_is_held(&rt->rt6i_table->tb6_lock));
@@ -1107,8 +1099,8 @@ void fib6_force_start_gc(struct net *net)
 			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
 }
 
-static void fib6_update_sernum_upto_root(struct rt6_info *rt,
-					 int sernum)
+static void __fib6_update_sernum_upto_root(struct rt6_info *rt,
+					   int sernum)
 {
 	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
 				lockdep_is_held(&rt->rt6i_table->tb6_lock));
@@ -1122,6 +1114,11 @@ static void fib6_update_sernum_upto_root(struct rt6_info *rt,
 	}
 }
 
+void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
+{
+	__fib6_update_sernum_upto_root(rt, fib6_new_sernum(net));
+}
+
 /*
  *	Add routing information to the routing tree.
  *	<destination addr>/<source addr>
@@ -1241,7 +1238,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 	err = fib6_add_rt2node(fn, rt, info, mxc, extack);
 	if (!err) {
-		fib6_update_sernum_upto_root(rt, sernum);
+		__fib6_update_sernum_upto_root(rt, sernum);
 		fib6_start_gc(info->nl_net, rt);
 	}
 
@@ -1670,7 +1667,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
 
 	/* Unlink it */
-	*rtp = rt->dst.rt6_next;
+	*rtp = rt->rt6_next;
 	rt->rt6i_node = NULL;
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
@@ -1691,6 +1688,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 			sibling->rt6i_nsiblings--;
 		rt->rt6i_nsiblings = 0;
 		list_del_init(&rt->rt6i_siblings);
+		rt6_multipath_rebalance(next_sibling);
 	}
 
 	/* Adjust walkers */
@@ -1698,7 +1696,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	FOR_WALKERS(net, w) {
 		if (w->state == FWS_C && w->leaf == rt) {
 			RT6_TRACE("walker %p adjusted by delroute\n", w);
-			w->leaf = rcu_dereference_protected(rt->dst.rt6_next,
+			w->leaf = rcu_dereference_protected(rt->rt6_next,
 					    lockdep_is_held(&table->tb6_lock));
 			if (!w->leaf)
 				w->state = FWS_U;
@@ -1762,7 +1760,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 			fib6_del_route(table, fn, rtp, info);
 			return 0;
 		}
-		rtp_next = &cur->dst.rt6_next;
+		rtp_next = &cur->rt6_next;
 	}
 	return -ENOENT;
 }
@@ -1918,7 +1916,7 @@ static int fib6_clean_node(struct fib6_walker *w)
 
 	for_each_fib6_walker_rt(w) {
 		res = c->func(rt, c->arg);
-		if (res < 0) {
+		if (res == -1) {
 			w->leaf = rt;
 			res = fib6_del(rt, &info);
 			if (res) {
@@ -1931,6 +1929,12 @@ static int fib6_clean_node(struct fib6_walker *w)
 				continue;
 			}
 			return 0;
+		} else if (res == -2) {
+			if (WARN_ON(!rt->rt6i_nsiblings))
+				continue;
+			rt = list_last_entry(&rt->rt6i_siblings,
+					     struct rt6_info, rt6i_siblings);
+			continue;
 		}
 		WARN_ON(res != 0);
 	}
@@ -1942,7 +1946,8 @@ static int fib6_clean_node(struct fib6_walker *w)
  *	Convenient frontend to tree walker.
  *
  *	func is called on each route.
- *		It may return -1 -> delete this route.
+ *		It may return -2 -> skip multipath route.
+ *			      -1 -> delete this route.
  *		              0  -> continue walking
  */
 
@@ -2134,7 +2139,6 @@ static void fib6_net_exit(struct net *net)
 {
 	unsigned int i;
 
-	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
 	for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
@@ -2173,8 +2177,8 @@ int __init fib6_init(void)
 	if (ret)
 		goto out_kmem_cache_create;
 
-	ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib,
-			      0);
+	ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL,
+				   inet6_dump_fib, 0);
 	if (ret)
 		goto out_unregister_subsys;
 
@@ -2239,7 +2243,7 @@ static int ipv6_route_yield(struct fib6_walker *w)
 
 	do {
 		iter->w.leaf = rcu_dereference_protected(
-				iter->w.leaf->dst.rt6_next,
+				iter->w.leaf->rt6_next,
 				lockdep_is_held(&iter->tbl->tb6_lock));
 		iter->skip--;
 		if (!iter->skip && iter->w.leaf)
@@ -2305,7 +2309,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (!v)
 		goto iter_table;
 
-	n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next);
+	n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next);
 	if (n) {
 		++*pos;
 		return n;