ipv6: Plumb support for nexthop object in a fib6_info

Add struct nexthop and nh_list list_head to fib6_info. nh_list is the
fib6_info side of the nexthop <-> fib_info relationship. Since a fib6_info
referencing a nexthop object can not have 'sibling' entries (the old way
of doing multipath routes), the nh_list is a union with fib6_siblings.

Add f6i_list list_head to 'struct nexthop' to track fib6_info entries
using a nexthop instance. Update __remove_nexthop_fib to walk f6_list
and delete fib entries using the nexthop.

Add a few nexthop helpers for use when a nexthop is added to fib6_info:
- nexthop_fib6_nh - return first fib6_nh in a nexthop object
- fib6_info_nh_dev moved to nexthop.h and updated to use nexthop_fib6_nh
  if the fib6_info references a nexthop object
- nexthop_path_fib6_result - similar to ipv4, select a path within a
  multipath nexthop object. If the nexthop is a blackhole, set
  fib6_result type to RTN_BLACKHOLE, and set the REJECT flag

Update the fib6_info references to check for nh and take a different path
as needed:
- rt6_qualify_for_ecmp - if a fib entry uses a nexthop object it can NOT
  be coalesced with other fib entries into a multipath route
- rt6_duplicate_nexthop - use nexthop_cmp if either fib6_info references
  a nexthop
- addrconf (host routes), RA's and info entries (anything configured via
  ndisc) does not use nexthop objects
- fib6_info_destroy_rcu - put reference to nexthop object
- fib6_purge_rt - drop fib6_info from f6i_list
- fib6_select_path - update to use the new nexthop_path_fib6_result when
  fib entry uses a nexthop object
- rt6_device_match - update to catch use of nexthop object as a blackhole
  and set fib6_type and flags.
- ip6_route_info_create - don't add space for fib6_nh if fib entry is
  going to reference a nexthop object, take a reference to nexthop object,
  disallow use of source routing
- rt6_nlmsg_size - add space for RTA_NH_ID
- add rt6_fill_node_nexthop to add nexthop data on a dump

As with ipv4, most of the changes push existing code into the else branch
of whether the fib entry uses a nexthop object.

Update the nexthop code to walk f6i_list on a nexthop deleted to remove
fib entries referencing it.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/nexthop.c

@@ -106,6 +106,7 @@ static struct nexthop *nexthop_alloc(void)
 	nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL);
 	if (nh) {
 		INIT_LIST_HEAD(&nh->fi_list);
+		INIT_LIST_HEAD(&nh->f6i_list);
 		INIT_LIST_HEAD(&nh->grp_list);
 	}
 	return nh;
@@ -516,6 +517,41 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
 }
 EXPORT_SYMBOL_GPL(nexthop_select_path);
 
+int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
+		       struct netlink_ext_ack *extack)
+{
+	struct nh_info *nhi;
+
+	/* fib6_src is unique to a fib6_info and limits the ability to cache
+	 * routes in fib6_nh within a nexthop that is potentially shared
+	 * across multiple fib entries. If the config wants to use source
+	 * routing it can not use nexthop objects. mlxsw also does not allow
+	 * fib6_src on routes.
+	 */
+	if (!ipv6_addr_any(&cfg->fc_src)) {
+		NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects");
+		return -EINVAL;
+	}
+
+	if (nh->is_group) {
+		struct nh_group *nhg;
+
+		nhg = rtnl_dereference(nh->nh_grp);
+		if (nhg->has_v4)
+			goto no_v4_nh;
+	} else {
+		nhi = rtnl_dereference(nh->nh_info);
+		if (nhi->family == AF_INET)
+			goto no_v4_nh;
+	}
+
+	return 0;
+no_v4_nh:
+	NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop");
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(fib6_check_nexthop);
+
 static int nexthop_check_scope(struct nexthop *nh, u8 scope,
 			       struct netlink_ext_ack *extack)
 {
@@ -658,6 +694,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
 
 static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 {
+	struct fib6_info *f6i, *tmp;
 	bool do_flush = false;
 	struct fib_info *fi;
 
@@ -667,6 +704,13 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 	}
 	if (do_flush)
 		fib_flush(net);
+
+	/* ip6_del_rt removes the entry from this list hence the _safe */
+	list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) {
+		/* __ip6_del_rt does a release, so do a hold here */
+		fib6_info_hold(f6i);
+		ipv6_stub->ip6_del_rt(net, f6i);
+	}
 }
 
 static void __remove_nexthop(struct net *net, struct nexthop *nh,