Merge branch 'rhashtable-next'

Herbert Xu says:

====================
rhashtable: Add iterators and use them

The first patch fixes a potential crash with nft_hash destroying
the table during a shrinking process.  While the next patch adds
rhashtable iterators to replace current manual walks used by
netlink and netfilter.  The final two patches make use of these
iterators in netlink and netfilter.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 100 insertions, 83 deletions

diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 75887d7d2c6a..61e6c407476a 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -130,31 +130,50 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
 	struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl;
 	const struct nft_hash_elem *he;
+	struct rhashtable_iter hti;
 	struct nft_set_elem elem;
-	unsigned int i;
+	int err;
 
-	tbl = rht_dereference_rcu(priv->tbl, priv);
-	for (i = 0; i < tbl->size; i++) {
-		struct rhash_head *pos;
+	err = rhashtable_walk_init(priv, &hti);
+	iter->err = err;
+	if (err)
+		return;
+
+	err = rhashtable_walk_start(&hti);
+	if (err && err != -EAGAIN) {
+		iter->err = err;
+		goto out;
+	}
 
-		rht_for_each_entry_rcu(he, pos, tbl, i, node) {
-			if (iter->count < iter->skip)
-				goto cont;
+	while ((he = rhashtable_walk_next(&hti))) {
+		if (IS_ERR(he)) {
+			err = PTR_ERR(he);
+			if (err != -EAGAIN) {
+				iter->err = err;
+				goto out;
+			}
+		}
+
+		if (iter->count < iter->skip)
+			goto cont;
+
+		memcpy(&elem.key, &he->key, sizeof(elem.key));
+		if (set->flags & NFT_SET_MAP)
+			memcpy(&elem.data, he->data, sizeof(elem.data));
+		elem.flags = 0;
 
-			memcpy(&elem.key, &he->key, sizeof(elem.key));
-			if (set->flags & NFT_SET_MAP)
-				memcpy(&elem.data, he->data, sizeof(elem.data));
-			elem.flags = 0;
+		iter->err = iter->fn(ctx, set, iter, &elem);
+		if (iter->err < 0)
+			goto out;
 
-			iter->err = iter->fn(ctx, set, iter, &elem);
-			if (iter->err < 0)
-				return;
 cont:
-			iter->count++;
-		}
+		iter->count++;
 	}
+
+out:
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
 }
 
 static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a36777b7cfb6..155854802d44 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2886,99 +2886,97 @@ EXPORT_SYMBOL(nlmsg_notify);
 #ifdef CONFIG_PROC_FS
 struct nl_seq_iter {
 	struct seq_net_private p;
+	struct rhashtable_iter hti;
 	int link;
-	int hash_idx;
 };
 
-static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
+static int netlink_walk_start(struct nl_seq_iter *iter)
 {
-	struct nl_seq_iter *iter = seq->private;
-	int i, j;
-	struct netlink_sock *nlk;
-	struct sock *s;
-	loff_t off = 0;
-
-	for (i = 0; i < MAX_LINKS; i++) {
-		struct rhashtable *ht = &nl_table[i].hash;
-		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
-
-		for (j = 0; j < tbl->size; j++) {
-			struct rhash_head *node;
-
-			rht_for_each_entry_rcu(nlk, node, tbl, j, node) {
-				s = (struct sock *)nlk;
+	int err;
 
-				if (sock_net(s) != seq_file_net(seq))
-					continue;
-				if (off == pos) {
-					iter->link = i;
-					iter->hash_idx = j;
-					return s;
-				}
-				++off;
-			}
-		}
+	err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti);
+	if (err) {
+		iter->link = MAX_LINKS;
+		return err;
 	}
-	return NULL;
+
+	err = rhashtable_walk_start(&iter->hti);
+	return err == -EAGAIN ? 0 : err;
 }
 
-static void *netlink_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(RCU)
+static void netlink_walk_stop(struct nl_seq_iter *iter)
 {
-	rcu_read_lock();
-	return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+	rhashtable_walk_stop(&iter->hti);
+	rhashtable_walk_exit(&iter->hti);
 }
 
-static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *__netlink_seq_next(struct seq_file *seq)
 {
-	struct rhashtable *ht;
-	const struct bucket_table *tbl;
-	struct rhash_head *node;
+	struct nl_seq_iter *iter = seq->private;
 	struct netlink_sock *nlk;
-	struct nl_seq_iter *iter;
-	struct net *net;
-	int i, j;
 
-	++*pos;
+	do {
+		for (;;) {
+			int err;
 
-	if (v == SEQ_START_TOKEN)
-		return netlink_seq_socket_idx(seq, 0);
+			nlk = rhashtable_walk_next(&iter->hti);
 
-	net = seq_file_net(seq);
-	iter = seq->private;
-	nlk = v;
+			if (IS_ERR(nlk)) {
+				if (PTR_ERR(nlk) == -EAGAIN)
+					continue;
 
-	i = iter->link;
-	ht = &nl_table[i].hash;
-	tbl = rht_dereference_rcu(ht->tbl, ht);
-	rht_for_each_entry_rcu_continue(nlk, node, nlk->node.next, tbl, iter->hash_idx, node)
-		if (net_eq(sock_net((struct sock *)nlk), net))
-			return nlk;
+				return nlk;
+			}
 
-	j = iter->hash_idx + 1;
+			if (nlk)
+				break;
 
-	do {
+			netlink_walk_stop(iter);
+			if (++iter->link >= MAX_LINKS)
+				return NULL;
 
-		for (; j < tbl->size; j++) {
-			rht_for_each_entry_rcu(nlk, node, tbl, j, node) {
-				if (net_eq(sock_net((struct sock *)nlk), net)) {
-					iter->link = i;
-					iter->hash_idx = j;
-					return nlk;
-				}
-			}
+			err = netlink_walk_start(iter);
+			if (err)
+				return ERR_PTR(err);
 		}
+	} while (sock_net(&nlk->sk) != seq_file_net(seq));
 
-		j = 0;
-	} while (++i < MAX_LINKS);
+	return nlk;
+}
 
-	return NULL;
+static void *netlink_seq_start(struct seq_file *seq, loff_t *posp)
+{
+	struct nl_seq_iter *iter = seq->private;
+	void *obj = SEQ_START_TOKEN;
+	loff_t pos;
+	int err;
+
+	iter->link = 0;
+
+	err = netlink_walk_start(iter);
+	if (err)
+		return ERR_PTR(err);
+
+	for (pos = *posp; pos && obj && !IS_ERR(obj); pos--)
+		obj = __netlink_seq_next(seq);
+
+	return obj;
+}
+
+static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return __netlink_seq_next(seq);
 }
 
 static void netlink_seq_stop(struct seq_file *seq, void *v)
-	__releases(RCU)
 {
-	rcu_read_unlock();
+	struct nl_seq_iter *iter = seq->private;
+
+	if (iter->link >= MAX_LINKS)
+		return;
+
+	netlink_walk_stop(iter);
 }