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>

1 files changed, 18 insertions, 4 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cdfb8500ccae..02feda73a98e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -159,6 +159,7 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 	if (!f6i)
 		return NULL;
 
+	/* fib6_siblings is a union with nh_list, so this initializes both */
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
@@ -171,7 +172,11 @@ void fib6_info_destroy_rcu(struct rcu_head *head)
 
 	WARN_ON(f6i->fib6_node);
 
-	fib6_nh_release(f6i->fib6_nh);
+	if (f6i->nh)
+		nexthop_put(f6i->nh);
+	else
+		fib6_nh_release(f6i->fib6_nh);
+
 	ip_fib_metrics_put(f6i->fib6_metrics);
 	kfree(f6i);
 }
@@ -927,6 +932,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 
 	fib6_drop_pcpu_from(rt, table);
 
+	if (rt->nh && !list_empty(&rt->nh_list))
+		list_del_init(&rt->nh_list);
+
 	if (refcount_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
@@ -1334,6 +1342,8 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 
 	err = fib6_add_rt2node(fn, rt, info, extack);
 	if (!err) {
+		if (rt->nh)
+			list_add(&rt->nh_list, &rt->nh->f6i_list);
 		__fib6_update_sernum_upto_root(rt, sernum);
 		fib6_start_gc(info->nl_net, rt);
 	}
@@ -2295,9 +2305,13 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 {
 	struct fib6_info *rt = v;
 	struct ipv6_route_iter *iter = seq->private;
+	struct fib6_nh *fib6_nh = rt->fib6_nh;
 	unsigned int flags = rt->fib6_flags;
 	const struct net_device *dev;
 
+	if (rt->nh)
+		fib6_nh = nexthop_fib6_nh(rt->nh);
+
 	seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -2305,14 +2319,14 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 #else
 	seq_puts(seq, "00000000000000000000000000000000 00 ");
 #endif
-	if (rt->fib6_nh->fib_nh_gw_family) {
+	if (fib6_nh->fib_nh_gw_family) {
 		flags |= RTF_GATEWAY;
-		seq_printf(seq, "%pi6", &rt->fib6_nh->fib_nh_gw6);
+		seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6);
 	} else {
 		seq_puts(seq, "00000000000000000000000000000000");
 	}
 
-	dev = rt->fib6_nh->fib_nh_dev;
+	dev = fib6_nh->fib_nh_dev;
 	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
 		   rt->fib6_metric, refcount_read(&rt->fib6_ref), 0,
 		   flags, dev ? dev->name : "");