[PATCH net-next v2 1/3] net: ipv6: Allow shorthand delete of all nexthops in multipath route

[David Ahern <dsa@cumulusnetworks.com>]

IPv4 allows multipath routes to be deleted using just the prefix and
length. For example:
    $ ip ro ls vrf red
    unreachable default metric 8192
    1.1.1.0/24
        nexthop via 10.100.1.254  dev eth1 weight 1
        nexthop via 10.11.200.2  dev eth11.200 weight 1
    10.11.200.0/24 dev eth11.200 proto kernel scope link src 10.11.200.3
    10.100.1.0/24 dev eth1 proto kernel scope link src 10.100.1.3

    $ ip ro del 1.1.1.0/24 vrf red

    $ ip ro ls vrf red
    unreachable default metric 8192
    10.11.200.0/24 dev eth11.200 proto kernel scope link src 10.11.200.3
    10.100.1.0/24 dev eth1 proto kernel scope link src 10.100.1.3

The same notation does not work with IPv6 because of how multipath routes
are implemented for IPv6. For IPv6 only the first nexthop of a multipath
route is deleted if the request contains only a prefix and length. This
leads to unnecessary complexity in userspace dealing with IPv6 multipath
routes.

This patch allows all nexthops to be deleted without specifying each one
in the delete request by passing a new flag, RTM_F_ALL_NEXTHOPS, in
rtm_flags. Internally, this is done by walking the sibling list of the
route matching the specifications given (prefix, length, metric, protocol,
etc).

With this patch (and an updated iproute2 command):
    $  ip -6 ro ls vrf red
    2001:db8::/120 via 2001:db8:1::62 dev eth1 metric 256  pref medium
    2001:db8::/120 via 2001:db8:1::61 dev eth1 metric 256  pref medium
    2001:db8::/120 via 2001:db8:1::60 dev eth1 metric 256  pref medium
    2001:db8:1::/120 dev eth1 proto kernel metric 256  pref medium
    ...

    $ ip -6 ro del vrf red 1111::1/120
    $ ip -6 ro ls vrf red
    2001:db8:1::/120 dev eth1 proto kernel metric 256  pref medium
    ...

The flag is added to fib6_config by converting fc_type to a u16 (as
noted fc_type only uses 8 bits). The new u16 hole is a bitmap with
fc_delete_all_nexthop as the first bit.

Suggested-by: Dinesh Dutt <ddutt@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v2
- switched example to rfc 3849 documentation address per request
- changed delete loop to explicitly look at siblings list for
  first route matching specs given (metric, protocol, etc)

 include/net/ip6_fib.h          |  4 +++-
 include/uapi/linux/rtnetlink.h |  1 +
 net/ipv6/route.c               | 28 +++++++++++++++++++++++++---
 3 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a74e2aa40ef4..11ab99e87c5f 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -37,7 +37,9 @@ struct fib6_config {
 	int		fc_ifindex;
 	u32		fc_flags;
 	u32		fc_protocol;
-	u32		fc_type;	/* only 8 bits are used */
+	u16		fc_type;	/* only 8 bits are used */
+	u16		fc_delete_all_nexthop : 1,
+			__unused : 15;
 
 	struct in6_addr	fc_dst;
 	struct in6_addr	fc_src;
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 8c93ad1ef9ab..7fb206bc42f9 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -276,6 +276,7 @@ enum rt_scope_t {
 #define RTM_F_EQUALIZE		0x400	/* Multipath equalizer: NI	*/
 #define RTM_F_PREFIX		0x800	/* Prefix addresses		*/
 #define RTM_F_LOOKUP_TABLE	0x1000	/* set rtm_table to FIB lookup result */
+#define RTM_F_ALL_NEXTHOPS	0x2000	/* delete all nexthops (IPv6) */
 
 /* Reserved table identifiers */
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ce5aaf448c54..c95e2f941468 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2143,6 +2143,26 @@ int ip6_del_rt(struct rt6_info *rt)
 	return __ip6_del_rt(rt, &info);
 }
 
+/* called with table lock held */
+static int __ip6_route_del(struct rt6_info *rt, struct fib6_config *cfg)
+{
+	int err;
+
+	if (rt->rt6i_nsiblings && cfg->fc_delete_all_nexthop) {
+		struct rt6_info *sibling, *next_sibling;
+
+		list_for_each_entry_safe(sibling, next_sibling,
+					 &rt->rt6i_siblings,
+					 rt6i_siblings) {
+			err = fib6_del(sibling, &cfg->fc_nlinfo);
+			if (err)
+				return err;
+		}
+	}
+
+	return fib6_del(rt, &cfg->fc_nlinfo);
+}
+
 static int ip6_route_del(struct fib6_config *cfg)
 {
 	struct fib6_table *table;
@@ -2176,10 +2196,9 @@ static int ip6_route_del(struct fib6_config *cfg)
 				continue;
 			if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol)
 				continue;
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
 
-			return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+			err = __ip6_route_del(rt, cfg);
+			break;
 		}
 	}
 	read_unlock_bh(&table->tb6_lock);
@@ -2849,6 +2868,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_flags & RTM_F_CLONED)
 		cfg->fc_flags |= RTF_CACHE;
 
+	if (rtm->rtm_flags & RTM_F_ALL_NEXTHOPS)
+		cfg->fc_delete_all_nexthop = 1;
+
 	cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
 	cfg->fc_nlinfo.nlh = nlh;
 	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
-- 
2.1.4