1 files changed, 120 insertions, 62 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9180c8b6f764..1d16a01eccf5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -143,20 +143,19 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
+struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 {
 	struct fib6_info *f6i;
+	size_t sz = sizeof(*f6i);
 
-	f6i = kzalloc(sizeof(*f6i), gfp_flags);
+	if (with_fib6_nh)
+		sz += sizeof(struct fib6_nh);
+
+	f6i = kzalloc(sz, gfp_flags);
 	if (!f6i)
 		return NULL;
 
-	f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
-	if (!f6i->rt6i_pcpu) {
-		kfree(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);
 
@@ -166,36 +165,15 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
 void fib6_info_destroy_rcu(struct rcu_head *head)
 {
 	struct fib6_info *f6i = container_of(head, struct fib6_info, rcu);
-	struct rt6_exception_bucket *bucket;
 
 	WARN_ON(f6i->fib6_node);
 
-	bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
-	kfree(bucket);
-
-	if (f6i->rt6i_pcpu) {
-		int cpu;
-
-		for_each_possible_cpu(cpu) {
-			struct rt6_info **ppcpu_rt;
-			struct rt6_info *pcpu_rt;
-
-			ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
-			pcpu_rt = *ppcpu_rt;
-			if (pcpu_rt) {
-				dst_dev_put(&pcpu_rt->dst);
-				dst_release(&pcpu_rt->dst);
-				*ppcpu_rt = NULL;
-			}
-		}
-
-		free_percpu(f6i->rt6i_pcpu);
-	}
-
-	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);
 }
 EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu);
@@ -389,10 +367,10 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
 	return call_fib6_notifier(nb, net, event_type, &info.info);
 }
 
-static int call_fib6_entry_notifiers(struct net *net,
-				     enum fib_event_type event_type,
-				     struct fib6_info *rt,
-				     struct netlink_ext_ack *extack)
+int call_fib6_entry_notifiers(struct net *net,
+			      enum fib_event_type event_type,
+			      struct fib6_info *rt,
+			      struct netlink_ext_ack *extack)
 {
 	struct fib6_entry_notifier_info info = {
 		.info.extack = extack,
@@ -403,6 +381,22 @@ static int call_fib6_entry_notifiers(struct net *net,
 	return call_fib6_notifiers(net, event_type, &info.info);
 }
 
+int call_fib6_multipath_entry_notifiers(struct net *net,
+					enum fib_event_type event_type,
+					struct fib6_info *rt,
+					unsigned int nsiblings,
+					struct netlink_ext_ack *extack)
+{
+	struct fib6_entry_notifier_info info = {
+		.info.extack = extack,
+		.rt = rt,
+		.nsiblings = nsiblings,
+	};
+
+	rt->fib6_table->fib_seq++;
+	return call_fib6_notifiers(net, event_type, &info.info);
+}
+
 struct fib6_dump_arg {
 	struct net *net;
 	struct notifier_block *nb;
@@ -895,16 +889,14 @@ insert_above:
 	return ln;
 }
 
-static void fib6_drop_pcpu_from(struct fib6_info *f6i,
-				const struct fib6_table *table)
+static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
+				  const struct fib6_info *match,
+				  const struct fib6_table *table)
 {
 	int cpu;
 
-	/* Make sure rt6_make_pcpu_route() wont add other percpu routes
-	 * while we are cleaning them here.
-	 */
-	f6i->fib6_destroying = 1;
-	mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
+	if (!fib6_nh->rt6i_pcpu)
+		return;
 
 	/* release the reference to this fib entry from
 	 * all of its cached pcpu routes
@@ -913,9 +905,15 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		struct rt6_info **ppcpu_rt;
 		struct rt6_info *pcpu_rt;
 
-		ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
 		pcpu_rt = *ppcpu_rt;
-		if (pcpu_rt) {
+
+		/* only dropping the 'from' reference if the cached route
+		 * is using 'match'. The cached pcpu_rt->from only changes
+		 * from a fib6_info to NULL (ip6_dst_destroy); it can never
+		 * change from one fib6_info reference to another
+		 */
+		if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) {
 			struct fib6_info *from;
 
 			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
@@ -924,13 +922,53 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 	}
 }
 
+struct fib6_nh_pcpu_arg {
+	struct fib6_info	*from;
+	const struct fib6_table *table;
+};
+
+static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_pcpu_arg *arg = _arg;
+
+	__fib6_drop_pcpu_from(nh, arg->from, arg->table);
+	return 0;
+}
+
+static void fib6_drop_pcpu_from(struct fib6_info *f6i,
+				const struct fib6_table *table)
+{
+	/* Make sure rt6_make_pcpu_route() wont add other percpu routes
+	 * while we are cleaning them here.
+	 */
+	f6i->fib6_destroying = 1;
+	mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
+
+	if (f6i->nh) {
+		struct fib6_nh_pcpu_arg arg = {
+			.from = f6i,
+			.table = table
+		};
+
+		nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from,
+					 &arg);
+	} else {
+		struct fib6_nh *fib6_nh;
+
+		fib6_nh = f6i->fib6_nh;
+		__fib6_drop_pcpu_from(fib6_nh, f6i, table);
+	}
+}
+
 static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 			  struct net *net)
 {
 	struct fib6_table *table = rt->fib6_table;
 
-	if (rt->rt6i_pcpu)
-		fib6_drop_pcpu_from(rt, table);
+	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
@@ -1101,11 +1139,13 @@ next_iter:
 add:
 		nlflags |= NLM_F_CREATE;
 
-		err = call_fib6_entry_notifiers(info->nl_net,
-						FIB_EVENT_ENTRY_ADD,
-						rt, extack);
-		if (err)
-			return err;
+		if (!info->skip_notify_kernel) {
+			err = call_fib6_entry_notifiers(info->nl_net,
+							FIB_EVENT_ENTRY_ADD,
+							rt, extack);
+			if (err)
+				return err;
+		}
 
 		rcu_assign_pointer(rt->fib6_next, iter);
 		fib6_info_hold(rt);
@@ -1130,11 +1170,13 @@ add:
 			return -ENOENT;
 		}
 
-		err = call_fib6_entry_notifiers(info->nl_net,
-						FIB_EVENT_ENTRY_REPLACE,
-						rt, extack);
-		if (err)
-			return err;
+		if (!info->skip_notify_kernel) {
+			err = call_fib6_entry_notifiers(info->nl_net,
+							FIB_EVENT_ENTRY_REPLACE,
+							rt, extack);
+			if (err)
+				return err;
+		}
 
 		fib6_info_hold(rt);
 		rcu_assign_pointer(rt->fib6_node, fn);
@@ -1218,6 +1260,14 @@ void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt)
 	__fib6_update_sernum_upto_root(rt, fib6_new_sernum(net));
 }
 
+/* allow ipv4 to update sernum via ipv6_stub */
+void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i)
+{
+	spin_lock_bh(&f6i->fib6_table->tb6_lock);
+	fib6_update_sernum_upto_root(net, f6i);
+	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
+}
+
 /*
  *	Add routing information to the routing tree.
  *	<destination addr>/<source addr>
@@ -1331,6 +1381,8 @@ 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);
 	}
@@ -1807,9 +1859,11 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 
 	fib6_purge_rt(rt, fn, net);
 
-	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
+	if (!info->skip_notify_kernel)
+		call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
 	if (!info->skip_notify)
 		inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
+
 	fib6_info_release(rt);
 }
 
@@ -2292,9 +2346,13 @@ 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
@@ -2302,14 +2360,14 @@ 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 : "");