ipv4: Plumb support for nexthop object in a fib_info

Add 'struct nexthop' and nh_list list_head to fib_info. nh_list is the
fib_info side of the nexthop <-> fib_info relationship.

Add fi_list list_head to 'struct nexthop' to track fib_info entries
using a nexthop instance. Add __remove_nexthop_fib and add it to
__remove_nexthop to walk the new list_head and mark those fib entries
as dead when the nexthop is deleted.

Add a few nexthop helpers for use when a nexthop is added to fib_info:
- nexthop_cmp to determine if 2 nexthops are the same
- nexthop_path_fib_result to select a path for a multipath
  'struct nexthop'
- nexthop_fib_nhc to select a specific fib_nh_common within a
  multipath 'struct nexthop'

Update existing fib_info_nhc to use nexthop_fib_nhc if a fib_info uses
a 'struct nexthop', and mark fib_info_nh as only used for the non-nexthop
case.

Update the fib_info functions to check for fi->nh and take a different
path as needed:
- free_fib_info_rcu - put the nexthop object reference
- fib_release_info - remove the fib_info from the nexthop's fi_list
- nh_comp - use nexthop_cmp when either fib_info references a nexthop
  object
- fib_info_hashfn - use the nexthop id for the hashing vs the oif of
  each fib_nh in a fib_info
- fib_nlmsg_size - add space for the RTA_NH_ID attribute
- fib_create_info - verify nexthop reference can be taken, verify
  nexthop spec is valid for fib entry, and add fib_info to fi_list for
  a nexthop
- fib_select_multipath - use the new nexthop_path_fib_result to select a
  path when nexthop objects are used
- fib_table_lookup - if the 'struct nexthop' is a blackhole nexthop, treat
  it the same as a fib entry using 'blackhole'

The bulk of the changes are in fib_semantics.c and most of that is
moving the existing change_nexthops into an else branch.

Update the nexthop code to walk fi_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, 64 insertions, 0 deletions

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index aec4ecb145a0..63cbb04f697f 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -105,6 +105,7 @@ 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->grp_list);
 	}
 	return nh;
@@ -515,6 +516,54 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
 }
 EXPORT_SYMBOL_GPL(nexthop_select_path);
 
+static int nexthop_check_scope(struct nexthop *nh, u8 scope,
+			       struct netlink_ext_ack *extack)
+{
+	struct nh_info *nhi;
+
+	nhi = rtnl_dereference(nh->nh_info);
+	if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) {
+		NL_SET_ERR_MSG(extack,
+			       "Route with host scope can not have a gateway");
+		return -EINVAL;
+	}
+
+	if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) {
+		NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Invoked by fib add code to verify nexthop by id is ok with
+ * config for prefix; parts of fib_check_nh not done when nexthop
+ * object is used.
+ */
+int fib_check_nexthop(struct nexthop *nh, u8 scope,
+		      struct netlink_ext_ack *extack)
+{
+	int err = 0;
+
+	if (nh->is_group) {
+		struct nh_group *nhg;
+
+		if (scope == RT_SCOPE_HOST) {
+			NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops");
+			err = -EINVAL;
+			goto out;
+		}
+
+		nhg = rtnl_dereference(nh->nh_grp);
+		/* all nexthops in a group have the same scope */
+		err = nexthop_check_scope(nhg->nh_entries[0].nh, scope, extack);
+	} else {
+		err = nexthop_check_scope(nh, scope, extack);
+	}
+out:
+	return err;
+}
+
 static void nh_group_rebalance(struct nh_group *nhg)
 {
 	int total = 0;
@@ -607,9 +656,24 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
 	}
 }
 
+static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
+{
+	bool do_flush = false;
+	struct fib_info *fi;
+
+	list_for_each_entry(fi, &nh->fi_list, nh_list) {
+		fi->fib_flags |= RTNH_F_DEAD;
+		do_flush = true;
+	}
+	if (do_flush)
+		fib_flush(net);
+}
+
 static void __remove_nexthop(struct net *net, struct nexthop *nh,
 			     struct nl_info *nlinfo)
 {
+	__remove_nexthop_fib(net, nh);
+
 	if (nh->is_group) {
 		remove_nexthop_group(nh, nlinfo);
 	} else {