1 files changed, 55 insertions, 30 deletions

diff --git a/net/rds/bind.c b/net/rds/bind.c
index dd666fb..6192566 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -38,48 +38,50 @@
 #include <linux/ratelimit.h>
 #include "rds.h"
 
+struct bind_bucket {
+	rwlock_t                lock;
+	struct hlist_head	head;
+};
+
 #define BIND_HASH_SIZE 1024
-static struct hlist_head bind_hash_table[BIND_HASH_SIZE];
-static DEFINE_SPINLOCK(rds_bind_lock);
+static struct bind_bucket bind_hash_table[BIND_HASH_SIZE];
 
-static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
+static struct bind_bucket *hash_to_bucket(__be32 addr, __be16 port)
 {
 	return bind_hash_table + (jhash_2words((u32)addr, (u32)port, 0) &
 				  (BIND_HASH_SIZE - 1));
 }
 
-static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
+/* must hold either read or write lock (write lock for insert != NULL) */
+static struct rds_sock *rds_bind_lookup(struct bind_bucket *bucket,
+					__be32 addr, __be16 port,
 					struct rds_sock *insert)
 {
 	struct rds_sock *rs;
-	struct hlist_head *head = hash_to_bucket(addr, port);
+	struct hlist_head *head = &bucket->head;
 	u64 cmp;
 	u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port);
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(rs, head, rs_bound_node) {
+	hlist_for_each_entry(rs, head, rs_bound_node) {
 		cmp = ((u64)be32_to_cpu(rs->rs_bound_addr) << 32) |
 		      be16_to_cpu(rs->rs_bound_port);
 
 		if (cmp == needle) {
-			rcu_read_unlock();
+			rds_sock_addref(rs);
 			return rs;
 		}
 	}
-	rcu_read_unlock();
 
 	if (insert) {
 		/*
 		 * make sure our addr and port are set before
-		 * we are added to the list, other people
-		 * in rcu will find us as soon as the
-		 * hlist_add_head_rcu is done
+		 * we are added to the list.
 		 */
 		insert->rs_bound_addr = addr;
 		insert->rs_bound_port = port;
 		rds_sock_addref(insert);
 
-		hlist_add_head_rcu(&insert->rs_bound_node, head);
+		hlist_add_head(&insert->rs_bound_node, head);
 	}
 	return NULL;
 }
@@ -93,16 +95,21 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
 struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
 {
 	struct rds_sock *rs;
+	unsigned long flags;
+	struct bind_bucket *bucket = hash_to_bucket(addr, port);
 
-	rs = rds_bind_lookup(addr, port, NULL);
+	read_lock_irqsave(&bucket->lock, flags);
+	rs = rds_bind_lookup(bucket, addr, port, NULL);
+	read_unlock_irqrestore(&bucket->lock, flags);
 
-	if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
-		rds_sock_addref(rs);
-	else
+	if (rs && sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) {
+		rds_sock_put(rs);
 		rs = NULL;
+	}
 
 	rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr,
 		ntohs(port));
+
 	return rs;
 }
 
@@ -112,6 +119,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 	unsigned long flags;
 	int ret = -EADDRINUSE;
 	u16 rover, last;
+	struct bind_bucket *bucket;
 
 	if (*port != 0) {
 		rover = be16_to_cpu(*port);
@@ -121,42 +129,48 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 		last = rover - 1;
 	}
 
-	spin_lock_irqsave(&rds_bind_lock, flags);
-
 	do {
+		struct rds_sock *rrs;
 		if (rover == 0)
 			rover++;
-		if (!rds_bind_lookup(addr, cpu_to_be16(rover), rs)) {
+
+		bucket = hash_to_bucket(addr, cpu_to_be16(rover));
+		write_lock_irqsave(&bucket->lock, flags);
+		rrs = rds_bind_lookup(bucket, addr, cpu_to_be16(rover), rs);
+		write_unlock_irqrestore(&bucket->lock, flags);
+		if (!rrs) {
 			*port = rs->rs_bound_port;
 			ret = 0;
 			rdsdebug("rs %p binding to %pI4:%d\n",
 			  rs, &addr, (int)ntohs(*port));
 			break;
+		} else {
+			rds_sock_put(rrs);
 		}
 	} while (rover++ != last);
 
-	spin_unlock_irqrestore(&rds_bind_lock, flags);
-
 	return ret;
 }
 
 void rds_remove_bound(struct rds_sock *rs)
 {
 	unsigned long flags;
+	struct bind_bucket *bucket =
+		hash_to_bucket(rs->rs_bound_addr, rs->rs_bound_port);
 
-	spin_lock_irqsave(&rds_bind_lock, flags);
+	write_lock_irqsave(&bucket->lock, flags);
 
 	if (rs->rs_bound_addr) {
 		rdsdebug("rs %p unbinding from %pI4:%d\n",
 		  rs, &rs->rs_bound_addr,
 		  ntohs(rs->rs_bound_port));
 
-		hlist_del_init_rcu(&rs->rs_bound_node);
+		hlist_del_init(&rs->rs_bound_node);
 		rds_sock_put(rs);
 		rs->rs_bound_addr = 0;
 	}
 
-	spin_unlock_irqrestore(&rds_bind_lock, flags);
+	write_unlock_irqrestore(&bucket->lock, flags);
 }
 
 int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
@@ -182,7 +196,14 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 
 	if (rs->rs_transport) { /* previously bound */
-		ret = 0;
+		trans = rs->rs_transport;
+		if (trans->laddr_check(sock_net(sock->sk),
+				       sin->sin_addr.s_addr) != 0) {
+			ret = -ENOPROTOOPT;
+			rds_remove_bound(rs);
+		} else {
+			ret = 0;
+		}
 		goto out;
 	}
 	trans = rds_trans_get_preferred(sock_net(sock->sk),
@@ -200,9 +221,13 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 out:
 	release_sock(sk);
-
-	/* we might have called rds_remove_bound on error */
-	if (ret)
-		synchronize_rcu();
 	return ret;
 }
+
+void rds_bind_lock_init(void)
+{
+	int i;
+
+	for (i = 0; i < BIND_HASH_SIZE; i++)
+		rwlock_init(&bind_hash_table[i].lock);
+}