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 <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: dsahern

include/net/ip6_fib.h

@@ -146,7 +146,10 @@ struct fib6_info {
 	 * destination, but not the same gateway. nsiblings is just a cache
 	 * to speed up lookup.
 	 */
-	struct list_head		fib6_siblings;
+	union {
+		struct list_head	fib6_siblings;
+		struct list_head	nh_list;
+	};
 	unsigned int			fib6_nsiblings;
 
 	refcount_t			fib6_ref;
@@ -170,6 +173,7 @@ struct fib6_info {
 					unused:3;
 
 	struct rcu_head			rcu;
+	struct nexthop			*nh;
 	struct fib6_nh			fib6_nh[0];
 };
 
@@ -441,11 +445,6 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr)
 	rcu_read_unlock();
 }
 
-static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
-{
-	return f6i->fib6_nh->fib_nh_dev;
-}
-
 int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		 struct fib6_config *cfg, gfp_t gfp_flags,
 		 struct netlink_ext_ack *extack);

include/net/ip6_route.h

@@ -27,6 +27,7 @@ struct route_info {
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/route.h>
+#include <net/nexthop.h>
 
 #define RT6_LOOKUP_F_IFACE		0x00000001
 #define RT6_LOOKUP_F_REACHABLE		0x00000002
@@ -66,10 +67,13 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
 }
 
+/* fib entries using a nexthop object can not be coalesced into
+ * a multipath route
+ */
 static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
 {
 	/* the RTF_ADDRCONF flag filters out RA's */
-	return !(f6i->fib6_flags & RTF_ADDRCONF) &&
+	return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh &&
 		f6i->fib6_nh->fib_nh_gw_family;
 }
 
@@ -275,8 +279,13 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
 
 static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b)
 {
-	struct fib6_nh *nha = a->fib6_nh, *nhb = b->fib6_nh;
+	struct fib6_nh *nha, *nhb;
+
+	if (a->nh || b->nh)
+		return nexthop_cmp(a->nh, b->nh);
 
+	nha = a->fib6_nh;
+	nhb = b->fib6_nh;
 	return nha->fib_nh_dev == nhb->fib_nh_dev &&
 	       ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) &&
 	       !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws);

include/net/nexthop.h

@@ -10,6 +10,7 @@
 #define __LINUX_NEXTHOP_H
 
 #include <linux/netdevice.h>
+#include <linux/route.h>
 #include <linux/types.h>
 #include <net/ip_fib.h>
 #include <net/ip6_fib.h>
@@ -78,6 +79,7 @@ struct nh_group {
 struct nexthop {
 	struct rb_node		rb_node;    /* entry on netns rbtree */
 	struct list_head	fi_list;    /* v4 entries using nh */
+	struct list_head	f6i_list;   /* v6 entries using nh */
 	struct list_head	grp_list;   /* nh group entries using this nh */
 	struct net		*net;
 
@@ -255,4 +257,52 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel)
 
 	return &fi->fib_nh[nhsel];
 }
+
+/*
+ * IPv6 variants
+ */
+int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
+		       struct netlink_ext_ack *extack);
+
+static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
+{
+	struct nh_info *nhi;
+
+	if (nexthop_is_multipath(nh)) {
+		nh = nexthop_mpath_select(nh, 0);
+		if (!nh)
+			return NULL;
+	}
+
+	nhi = rcu_dereference_rtnl(nh->nh_info);
+	if (nhi->family == AF_INET6)
+		return &nhi->fib6_nh;
+
+	return NULL;
+}
+
+static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i)
+{
+	struct fib6_nh *fib6_nh;
+
+	fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh;
+	return fib6_nh->fib_nh_dev;
+}
+
+static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash)
+{
+	struct nexthop *nh = res->f6i->nh;
+	struct nh_info *nhi;
+
+	nh = nexthop_select_path(nh, hash);
+
+	nhi = rcu_dereference_rtnl(nh->nh_info);
+	if (nhi->reject_nh) {
+		res->fib6_type = RTN_BLACKHOLE;
+		res->fib6_flags |= RTF_REJECT;
+		res->nh = nexthop_fib6_nh(nh);
+	} else {
+		res->nh = &nhi->fib6_nh;
+	}
+}
 #endif

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,

net/ipv6/addrconf.c

@@ -2421,6 +2421,10 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
+		/* prefix routes only use builtin fib6_nh */
+		if (rt->nh)
+			continue;
+
 		if (rt->fib6_nh->fib_nh_dev->ifindex != dev->ifindex)
 			continue;
 		if (no_gw && rt->fib6_nh->fib_nh_gw_family)
@@ -6352,6 +6356,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
 		spin_lock(&ifa->lock);
 		if (ifa->rt) {
+			/* host routes only use builtin fib6_nh */
 			struct fib6_nh *nh = ifa->rt->fib6_nh;
 			int cpu;
 

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);
 	}
@@ -2295,24 +2305,28 @@ 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
 	seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen);
 #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 : "");

net/ipv6/ndisc.c

@@ -1289,9 +1289,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	    !in6_dev->cnf.accept_ra_rtr_pref)
 		pref = ICMPV6_ROUTER_PREF_MEDIUM;
 #endif
-
+	/* routes added from RAs do not use nexthop objects */
 	rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
-
 	if (rt) {
 		neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
 					 rt->fib6_nh->fib_nh_dev, NULL,