nexthop: Add netlink defines and enumerators for resilient NH groups

- RTM_NEWNEXTHOP et.al. that handle resilient groups will have a new nested
attribute, NHA_RES_GROUP, whose elements are attributes NHA_RES_GROUP_*.

- RTM_NEWNEXTHOPBUCKET et.al. is a suite of new messages that will
currently serve only for dumping of individual buckets of resilient next
hop groups. For nexthop group buckets, these messages will carry a nested
attribute NHA_RES_BUCKET, whose elements are attributes NHA_RES_BUCKET_*.

There are several reasons why a new suite of messages is created for
nexthop buckets instead of overloading the information on the existing
RTM_{NEW,DEL,GET}NEXTHOP messages.

First, a nexthop group can contain a large number of nexthop buckets (4k
is not unheard of). This imposes limits on the amount of information that
can be encoded for each nexthop bucket given a netlink message is limited
to 64k bytes.

Second, while RTM_NEWNEXTHOPBUCKET is only used for notifications at
this point, in the future it can be extended to provide user space with
control over nexthop buckets configuration.

- The new group type is NEXTHOP_GRP_TYPE_RES. Note that nexthop code is
adjusted to bounce groups with that type for now.

Signed-off-by: Ido Schimmel <[e-mail]>
Reviewed-by: Petr Machata <[e-mail]>
Reviewed-by: David Ahern <[e-mail]>
Signed-off-by: Petr Machata <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/uapi/linux/nexthop.h

···
 };
 
 enum {
-	NEXTHOP_GRP_TYPE_MPATH,  /* default type if not specified */
+	NEXTHOP_GRP_TYPE_MPATH,  /* hash-threshold nexthop group
+				  * default type if not specified
+				  */
+	NEXTHOP_GRP_TYPE_RES,    /* resilient nexthop group */
 	__NEXTHOP_GRP_TYPE_MAX,
 };
 
···
 	NHA_FDB,	/* flag; nexthop belongs to a bridge fdb */
 	/* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
 
+	/* nested; resilient nexthop group attributes */
+	NHA_RES_GROUP,
+	/* nested; nexthop bucket attributes */
+	NHA_RES_BUCKET,
+
 	__NHA_MAX,
 };
 
 #define NHA_MAX	(__NHA_MAX - 1)
+
+enum {
+	NHA_RES_GROUP_UNSPEC,
+	/* Pad attribute for 64-bit alignment. */
+	NHA_RES_GROUP_PAD = NHA_RES_GROUP_UNSPEC,
+
+	/* u16; number of nexthop buckets in a resilient nexthop group */
+	NHA_RES_GROUP_BUCKETS,
+	/* clock_t as u32; nexthop bucket idle timer (per-group) */
+	NHA_RES_GROUP_IDLE_TIMER,
+	/* clock_t as u32; nexthop unbalanced timer */
+	NHA_RES_GROUP_UNBALANCED_TIMER,
+	/* clock_t as u64; nexthop unbalanced time */
+	NHA_RES_GROUP_UNBALANCED_TIME,
+
+	__NHA_RES_GROUP_MAX,
+};
+
+#define NHA_RES_GROUP_MAX	(__NHA_RES_GROUP_MAX - 1)
+
+enum {
+	NHA_RES_BUCKET_UNSPEC,
+	/* Pad attribute for 64-bit alignment. */
+	NHA_RES_BUCKET_PAD = NHA_RES_BUCKET_UNSPEC,
+
+	/* u16; nexthop bucket index */
+	NHA_RES_BUCKET_INDEX,
+	/* clock_t as u64; nexthop bucket idle time */
+	NHA_RES_BUCKET_IDLE_TIME,
+	/* u32; nexthop id assigned to the nexthop bucket */
+	NHA_RES_BUCKET_NH_ID,
+
+	__NHA_RES_BUCKET_MAX,
+};
+
+#define NHA_RES_BUCKET_MAX	(__NHA_RES_BUCKET_MAX - 1)
+
 #endif

include/uapi/linux/rtnetlink.h

···
 	RTM_GETVLAN,
 #define RTM_GETVLAN	RTM_GETVLAN
 
+	RTM_NEWNEXTHOPBUCKET = 116,
+#define RTM_NEWNEXTHOPBUCKET	RTM_NEWNEXTHOPBUCKET
+	RTM_DELNEXTHOPBUCKET,
+#define RTM_DELNEXTHOPBUCKET	RTM_DELNEXTHOPBUCKET
+	RTM_GETNEXTHOPBUCKET,
+#define RTM_GETNEXTHOPBUCKET	RTM_GETNEXTHOPBUCKET
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };

net/ipv4/nexthop.c

···
 	if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) {
 		nhg->mpath = 1;
 		nhg->is_multipath = true;
+	} else if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) {
+		goto out_no_nh;
 	}
 
 	WARN_ON_ONCE(nhg->mpath != 1);

security/selinux/nlmsgtab.c

···
 	{ RTM_NEWVLAN,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_DELVLAN,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_GETVLAN,		NETLINK_ROUTE_SOCKET__NLMSG_READ  },
+	{ RTM_NEWNEXTHOPBUCKET,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNEXTHOPBUCKET,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETNEXTHOPBUCKET,	NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 };
 
 static const struct nlmsg_perm nlmsg_tcpdiag_perms[] =
···
 		 * structures at the top of this file with the new mappings
 		 * before updating the BUILD_BUG_ON() macro!
 		 */
-		BUILD_BUG_ON(RTM_MAX != (RTM_NEWVLAN + 3));
+		BUILD_BUG_ON(RTM_MAX != (RTM_NEWNEXTHOPBUCKET + 3));
 		err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms,
 				 sizeof(nlmsg_route_perms));
 		break;