1 files changed, 185 insertions, 38 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 026f309c51e9..1b0e7d1f5217 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -84,25 +84,114 @@
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
-static BLOCKING_NOTIFIER_HEAD(fib_chain);
+static unsigned int fib_seq_sum(void)
+{
+	unsigned int fib_seq = 0;
+	struct net *net;
+
+	rtnl_lock();
+	for_each_net(net)
+		fib_seq += net->ipv4.fib_seq;
+	rtnl_unlock();
+
+	return fib_seq;
+}
+
+static ATOMIC_NOTIFIER_HEAD(fib_chain);
+
+static int call_fib_notifier(struct notifier_block *nb, struct net *net,
+			     enum fib_event_type event_type,
+			     struct fib_notifier_info *info)
+{
+	info->net = net;
+	return nb->notifier_call(nb, event_type, info);
+}
+
+static void fib_rules_notify(struct net *net, struct notifier_block *nb,
+			     enum fib_event_type event_type)
+{
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+	struct fib_notifier_info info;
+
+	if (net->ipv4.fib_has_custom_rules)
+		call_fib_notifier(nb, net, event_type, &info);
+#endif
+}
+
+static void fib_notify(struct net *net, struct notifier_block *nb,
+		       enum fib_event_type event_type);
 
-int register_fib_notifier(struct notifier_block *nb)
+static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
+				   enum fib_event_type event_type, u32 dst,
+				   int dst_len, struct fib_info *fi,
+				   u8 tos, u8 type, u32 tb_id, u32 nlflags)
 {
-	return blocking_notifier_chain_register(&fib_chain, nb);
+	struct fib_entry_notifier_info info = {
+		.dst = dst,
+		.dst_len = dst_len,
+		.fi = fi,
+		.tos = tos,
+		.type = type,
+		.tb_id = tb_id,
+		.nlflags = nlflags,
+	};
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static bool fib_dump_is_consistent(struct notifier_block *nb,
+				   void (*cb)(struct notifier_block *nb),
+				   unsigned int fib_seq)
+{
+	atomic_notifier_chain_register(&fib_chain, nb);
+	if (fib_seq == fib_seq_sum())
+		return true;
+	atomic_notifier_chain_unregister(&fib_chain, nb);
+	if (cb)
+		cb(nb);
+	return false;
+}
+
+#define FIB_DUMP_MAX_RETRIES 5
+int register_fib_notifier(struct notifier_block *nb,
+			  void (*cb)(struct notifier_block *nb))
+{
+	int retries = 0;
+
+	do {
+		unsigned int fib_seq = fib_seq_sum();
+		struct net *net;
+
+		/* Mutex semantics guarantee that every change done to
+		 * FIB tries before we read the change sequence counter
+		 * is now visible to us.
+		 */
+		rcu_read_lock();
+		for_each_net_rcu(net) {
+			fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD);
+			fib_notify(net, nb, FIB_EVENT_ENTRY_ADD);
+		}
+		rcu_read_unlock();
+
+		if (fib_dump_is_consistent(nb, cb, fib_seq))
+			return 0;
+	} while (++retries < FIB_DUMP_MAX_RETRIES);
+
+	return -EBUSY;
 }
 EXPORT_SYMBOL(register_fib_notifier);
 
 int unregister_fib_notifier(struct notifier_block *nb)
 {
-	return blocking_notifier_chain_unregister(&fib_chain, nb);
+	return atomic_notifier_chain_unregister(&fib_chain, nb);
 }
 EXPORT_SYMBOL(unregister_fib_notifier);
 
 int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
 		       struct fib_notifier_info *info)
 {
+	net->ipv4.fib_seq++;
 	info->net = net;
-	return blocking_notifier_call_chain(&fib_chain, event_type, info);
+	return atomic_notifier_call_chain(&fib_chain, event_type, info);
 }
 
 static int call_fib_entry_notifiers(struct net *net,
@@ -719,6 +808,13 @@ static unsigned char update_suffix(struct key_vector *tn)
 {
 	unsigned char slen = tn->pos;
 	unsigned long stride, i;
+	unsigned char slen_max;
+
+	/* only vector 0 can have a suffix length greater than or equal to
+	 * tn->pos + tn->bits, the second highest node will have a suffix
+	 * length at most of tn->pos + tn->bits - 1
+	 */
+	slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen);
 
 	/* search though the list of children looking for nodes that might
 	 * have a suffix greater than the one we currently have.  This is
@@ -736,12 +832,8 @@ static unsigned char update_suffix(struct key_vector *tn)
 		slen = n->slen;
 		i &= ~(stride - 1);
 
-		/* if slen covers all but the last bit we can stop here
-		 * there will be nothing longer than that since only node
-		 * 0 and 1 << (bits - 1) could have that as their suffix
-		 * length.
-		 */
-		if ((slen + 1) >= (tn->pos + tn->bits))
+		/* stop searching if we have hit the maximum possible value */
+		if (slen >= slen_max)
 			break;
 	}
 
@@ -913,39 +1005,27 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn)
 		return collapse(t, tn);
 
 	/* update parent in case halve failed */
-	tp = node_parent(tn);
-
-	/* Return if at least one deflate was run */
-	if (max_work != MAX_WORK)
-		return tp;
-
-	/* push the suffix length to the parent node */
-	if (tn->slen > tn->pos) {
-		unsigned char slen = update_suffix(tn);
-
-		if (slen > tp->slen)
-			tp->slen = slen;
-	}
-
-	return tp;
+	return node_parent(tn);
 }
 
-static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l)
+static void node_pull_suffix(struct key_vector *tn, unsigned char slen)
 {
-	while ((tp->slen > tp->pos) && (tp->slen > l->slen)) {
-		if (update_suffix(tp) > l->slen)
+	unsigned char node_slen = tn->slen;
+
+	while ((node_slen > tn->pos) && (node_slen > slen)) {
+		slen = update_suffix(tn);
+		if (node_slen == slen)
 			break;
-		tp = node_parent(tp);
+
+		tn = node_parent(tn);
+		node_slen = tn->slen;
 	}
 }
 
-static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l)
+static void node_push_suffix(struct key_vector *tn, unsigned char slen)
 {
-	/* if this is a new leaf then tn will be NULL and we can sort
-	 * out parent suffix lengths as a part of trie_rebalance
-	 */
-	while (tn->slen < l->slen) {
-		tn->slen = l->slen;
+	while (tn->slen < slen) {
+		tn->slen = slen;
 		tn = node_parent(tn);
 	}
 }
@@ -1066,6 +1146,7 @@ static int fib_insert_node(struct trie *t, struct key_vector *tp,
 	}
 
 	/* Case 3: n is NULL, and will just insert a new leaf */
+	node_push_suffix(tp, new->fa_slen);
 	NODE_INIT_PARENT(l, tp);
 	put_child_root(tp, key, l);
 	trie_rebalance(t, tp);
@@ -1107,7 +1188,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 	/* if we added to the tail node then we need to update slen */
 	if (l->slen < new->fa_slen) {
 		l->slen = new->fa_slen;
-		leaf_push_suffix(tp, l);
+		node_push_suffix(tp, new->fa_slen);
 	}
 
 	return 0;
@@ -1499,6 +1580,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 	 * out parent suffix lengths as a part of trie_rebalance
 	 */
 	if (hlist_empty(&l->leaf)) {
+		if (tp->slen == l->slen)
+			node_pull_suffix(tp, tp->pos);
 		put_child_root(tp, l->key, NULL);
 		node_free(l);
 		trie_rebalance(t, tp);
@@ -1511,7 +1594,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 
 	/* update the trie with the latest suffix length */
 	l->slen = fa->fa_slen;
-	leaf_pull_suffix(tp, l);
+	node_pull_suffix(tp, fa->fa_slen);
 }
 
 /* Caller must hold RTNL. */
@@ -1783,6 +1866,10 @@ void fib_table_flush_external(struct fib_table *tb)
 			if (IS_TRIE(pn))
 				break;
 
+			/* update the suffix to address pulled leaves */
+			if (pn->slen > pn->pos)
+				update_suffix(pn);
+
 			/* resize completed node */
 			pn = resize(t, pn);
 			cindex = get_index(pkey, pn);
@@ -1849,6 +1936,10 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 			if (IS_TRIE(pn))
 				break;
 
+			/* update the suffix to address pulled leaves */
+			if (pn->slen > pn->pos)
+				update_suffix(pn);
+
 			/* resize completed node */
 			pn = resize(t, pn);
 			cindex = get_index(pkey, pn);
@@ -1901,6 +1992,62 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 	return found;
 }
 
+static void fib_leaf_notify(struct net *net, struct key_vector *l,
+			    struct fib_table *tb, struct notifier_block *nb,
+			    enum fib_event_type event_type)
+{
+	struct fib_alias *fa;
+
+	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		struct fib_info *fi = fa->fa_info;
+
+		if (!fi)
+			continue;
+
+		/* local and main table can share the same trie,
+		 * so don't notify twice for the same entry.
+		 */
+		if (tb->tb_id != fa->tb_id)
+			continue;
+
+		call_fib_entry_notifier(nb, net, event_type, l->key,
+					KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
+					fa->fa_type, fa->tb_id, 0);
+	}
+}
+
+static void fib_table_notify(struct net *net, struct fib_table *tb,
+			     struct notifier_block *nb,
+			     enum fib_event_type event_type)
+{
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct key_vector *l, *tp = t->kv;
+	t_key key = 0;
+
+	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
+		fib_leaf_notify(net, l, tb, nb, event_type);
+
+		key = l->key + 1;
+		/* stop in case of wrap around */
+		if (key < l->key)
+			break;
+	}
+}
+
+static void fib_notify(struct net *net, struct notifier_block *nb,
+		       enum fib_event_type event_type)
+{
+	unsigned int h;
+
+	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
+		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
+		struct fib_table *tb;
+
+		hlist_for_each_entry_rcu(tb, head, tb_hlist)
+			fib_table_notify(net, tb, nb, event_type);
+	}
+}
+
 static void __trie_free_rcu(struct rcu_head *head)
 {
 	struct fib_table *tb = container_of(head, struct fib_table, rcu);