1 files changed, 76 insertions, 22 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 8184076a39..1ace4ac3ee 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
+	INIT_HLIST_NODE(&f6i->gc_link);
+
 	return f6i;
 }
 
@@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
+		INIT_HLIST_HEAD(&table->tb6_gc_hlist);
 	}
 
 	return table;
@@ -617,8 +620,11 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 
 static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true,
-					 .filter.dump_routes = true };
+	struct rt6_rtnl_dump_arg arg = {
+		.filter.dump_exceptions = true,
+		.filter.dump_routes = true,
+		.filter.rtnl_held = true,
+	};
 	const struct nlmsghdr *nlh = cb->nlh;
 	struct net *net = sock_net(skb->sk);
 	unsigned int h, s_h;
@@ -751,8 +757,6 @@ static struct fib6_node *fib6_add_1(struct net *net,
 	int	bit;
 	__be32	dir = 0;
 
-	RT6_TRACE("fib6_add_1\n");
-
 	/* insert node in tree */
 
 	fn = root;
@@ -961,6 +965,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 	if (!fib6_nh->rt6i_pcpu)
 		return;
 
+	rcu_read_lock();
 	/* release the reference to this fib entry from
 	 * all of its cached pcpu routes
 	 */
@@ -969,7 +974,9 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 		struct rt6_info *pcpu_rt;
 
 		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
-		pcpu_rt = *ppcpu_rt;
+
+		/* Paired with xchg() in rt6_get_pcpu_route() */
+		pcpu_rt = READ_ONCE(*ppcpu_rt);
 
 		/* only dropping the 'from' reference if the cached route
 		 * is using 'match'. The cached pcpu_rt->from only changes
@@ -983,6 +990,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
 			fib6_info_release(from);
 		}
 	}
+	rcu_read_unlock();
 }
 
 struct fib6_nh_pcpu_arg {
@@ -1057,6 +1065,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
+
+	fib6_clean_expires(rt);
+	fib6_remove_gc_list(rt);
 }
 
 /*
@@ -1117,10 +1128,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 					rt->fib6_nsiblings = 0;
 				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
-				if (!(rt->fib6_flags & RTF_EXPIRES))
+				if (!(rt->fib6_flags & RTF_EXPIRES)) {
 					fib6_clean_expires(iter);
-				else
+					fib6_remove_gc_list(iter);
+				} else {
 					fib6_set_expires(iter, rt->expires);
+					fib6_add_gc_list(iter);
+				}
 
 				if (rt->fib6_pmtu)
 					fib6_metric_set(iter, RTAX_MTU,
@@ -1482,6 +1496,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 		if (rt->nh)
 			list_add(&rt->nh_list, &rt->nh->f6i_list);
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
+
+		if (rt->fib6_flags & RTF_EXPIRES)
+			fib6_add_gc_list(rt);
+
 		fib6_start_gc(info->nl_net, rt);
 	}
 
@@ -1806,7 +1824,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 					    lockdep_is_held(&table->tb6_lock));
 		struct fib6_info *new_fn_leaf;
 
-		RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
+		pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
 		iter++;
 
 		WARN_ON(fn->fn_flags & RTN_RTINFO);
@@ -1869,7 +1887,8 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		FOR_WALKERS(net, w) {
 			if (!child) {
 				if (w->node == fn) {
-					RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate);
+					pr_debug("W %p adjusted by delnode 1, s=%d/%d\n",
+						 w, w->state, nstate);
 					w->node = pn;
 					w->state = nstate;
 				}
@@ -1877,10 +1896,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 				if (w->node == fn) {
 					w->node = child;
 					if (children&2) {
-						RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
+						pr_debug("W %p adjusted by delnode 2, s=%d\n",
+							 w, w->state);
 						w->state = w->state >= FWS_R ? FWS_U : FWS_INIT;
 					} else {
-						RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
+						pr_debug("W %p adjusted by delnode 2, s=%d\n",
+							 w, w->state);
 						w->state = w->state >= FWS_C ? FWS_U : FWS_INIT;
 					}
 				}
@@ -1908,8 +1929,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	struct net *net = info->nl_net;
 	bool notify_del = false;
 
-	RT6_TRACE("fib6_del_route\n");
-
 	/* If the deleted route is the first in the node and it is not part of
 	 * a multipath route, then we need to replace it with the next route
 	 * in the node, if exists.
@@ -1958,7 +1977,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	read_lock(&net->ipv6.fib6_walker_lock);
 	FOR_WALKERS(net, w) {
 		if (w->state == FWS_C && w->leaf == rt) {
-			RT6_TRACE("walker %p adjusted by delroute\n", w);
+			pr_debug("walker %p adjusted by delroute\n", w);
 			w->leaf = rcu_dereference_protected(rt->fib6_next,
 					    lockdep_is_held(&table->tb6_lock));
 			if (!w->leaf)
@@ -2284,9 +2303,8 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-static int fib6_age(struct fib6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 {
-	struct fib6_gc_args *gc_args = arg;
 	unsigned long now = jiffies;
 
 	/*
@@ -2296,7 +2314,7 @@ static int fib6_age(struct fib6_info *rt, void *arg)
 
 	if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
 		if (time_after(now, rt->expires)) {
-			RT6_TRACE("expiring %p\n", rt);
+			pr_debug("expiring %p\n", rt);
 			return -1;
 		}
 		gc_args->more++;
@@ -2311,6 +2329,42 @@ static int fib6_age(struct fib6_info *rt, void *arg)
 	return 0;
 }
 
+static void fib6_gc_table(struct net *net,
+			  struct fib6_table *tb6,
+			  struct fib6_gc_args *gc_args)
+{
+	struct fib6_info *rt;
+	struct hlist_node *n;
+	struct nl_info info = {
+		.nl_net = net,
+		.skip_notify = false,
+	};
+
+	hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
+		if (fib6_age(rt, gc_args) == -1)
+			fib6_del(rt, &info);
+}
+
+static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
+{
+	struct fib6_table *table;
+	struct hlist_head *head;
+	unsigned int h;
+
+	rcu_read_lock();
+	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+		head = &net->ipv6.fib_table_hash[h];
+		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+			spin_lock_bh(&table->tb6_lock);
+
+			fib6_gc_table(net, table, gc_args);
+
+			spin_unlock_bh(&table->tb6_lock);
+		}
+	}
+	rcu_read_unlock();
+}
+
 void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
 	struct fib6_gc_args gc_args;
@@ -2326,7 +2380,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 			  net->ipv6.sysctl.ip6_rt_gc_interval;
 	gc_args.more = 0;
 
-	fib6_clean_all(net, fib6_age, &gc_args);
+	fib6_gc_all(net, &gc_args);
 	now = jiffies;
 	net->ipv6.ip6_rt_last_gc = now;
 
@@ -2386,6 +2440,7 @@ static int __net_init fib6_net_init(struct net *net)
 	net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
+	INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
@@ -2398,6 +2453,7 @@ static int __net_init fib6_net_init(struct net *net)
 	net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
+	INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist);
 #endif
 	fib6_tables_init(net);
 
@@ -2447,10 +2503,8 @@ int __init fib6_init(void)
 {
 	int ret = -ENOMEM;
 
-	fib6_node_kmem = kmem_cache_create("fib6_nodes",
-					   sizeof(struct fib6_node), 0,
-					   SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT,
-					   NULL);
+	fib6_node_kmem = KMEM_CACHE(fib6_node,
+				    SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT);
 	if (!fib6_node_kmem)
 		goto out;