Merge branch 'rhashtable-allocation-failure-during-insertion'

Herbert Xu says:

====================
rhashtable: Handle table allocation failure during insertion

v2 -

Added Ack to patch 2.
Fixed RCU annotation in code path executed by rehasher by using
rht_dereference_bucket.

v1 -

This series tackles the problem of table allocation failures during
insertion.  The issue is that we cannot vmalloc during insertion.
This series deals with this by introducing nested tables.

The first two patches removes manual hash table walks which cannot
work on a nested table.

The final patch introduces nested tables.

I've tested this with test_rhashtable and it appears to work.
====================

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

2 files changed, 23 insertions, 11 deletions

diff --git a/net/tipc/net.c b/net/tipc/net.c
index 28bf4feeb81c..ab8a2d5d1e32 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -110,6 +110,10 @@ int tipc_net_start(struct net *net, u32 addr)
 	char addr_string[16];
 
 	tn->own_addr = addr;
+
+	/* Ensure that the new address is visible before we reinit. */
+	smp_mb();
+
 	tipc_named_reinit(net);
 	tipc_sk_reinit(net);
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 800caaa699a1..370a5912bcb5 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -384,8 +384,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	INIT_LIST_HEAD(&tsk->publications);
 	msg = &tsk->phdr;
 	tn = net_generic(sock_net(sk), tipc_net_id);
-	tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
-		      NAMED_H_SIZE, 0);
 
 	/* Finish initializing socket data structures */
 	sock->ops = ops;
@@ -395,6 +393,13 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 		pr_warn("Socket create failed; port number exhausted\n");
 		return -EINVAL;
 	}
+
+	/* Ensure tsk is visible before we read own_addr. */
+	smp_mb();
+
+	tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
+		      NAMED_H_SIZE, 0);
+
 	msg_set_origport(msg, tsk->portid);
 	setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
 	sk->sk_shutdown = 0;
@@ -2269,24 +2274,27 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 void tipc_sk_reinit(struct net *net)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	const struct bucket_table *tbl;
-	struct rhash_head *pos;
+	struct rhashtable_iter iter;
 	struct tipc_sock *tsk;
 	struct tipc_msg *msg;
-	int i;
 
-	rcu_read_lock();
-	tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht);
-	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_rcu(tsk, pos, tbl, i, node) {
+	rhashtable_walk_enter(&tn->sk_rht, &iter);
+
+	do {
+		tsk = ERR_PTR(rhashtable_walk_start(&iter));
+		if (tsk)
+			continue;
+
+		while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
 			spin_lock_bh(&tsk->sk.sk_lock.slock);
 			msg = &tsk->phdr;
 			msg_set_prevnode(msg, tn->own_addr);
 			msg_set_orignode(msg, tn->own_addr);
 			spin_unlock_bh(&tsk->sk.sk_lock.slock);
 		}
-	}
-	rcu_read_unlock();
+
+		rhashtable_walk_stop(&iter);
+	} while (tsk == ERR_PTR(-EAGAIN));
 }
 
 static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)