Merge commit 'v2.6.28-rc3' into tracing/ftrace

15 files changed, 147 insertions, 36 deletions

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f1d07b5c1e1..1895a4ca9c4 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -325,6 +325,38 @@ void unregister_pernet_subsys(struct pernet_operations *module)
 }
 EXPORT_SYMBOL_GPL(unregister_pernet_subsys);
 
+int register_pernet_gen_subsys(int *id, struct pernet_operations *ops)
+{
+	int rv;
+
+	mutex_lock(&net_mutex);
+again:
+	rv = ida_get_new_above(&net_generic_ids, 1, id);
+	if (rv < 0) {
+		if (rv == -EAGAIN) {
+			ida_pre_get(&net_generic_ids, GFP_KERNEL);
+			goto again;
+		}
+		goto out;
+	}
+	rv = register_pernet_operations(first_device, ops);
+	if (rv < 0)
+		ida_remove(&net_generic_ids, *id);
+	mutex_unlock(&net_mutex);
+out:
+	return rv;
+}
+EXPORT_SYMBOL_GPL(register_pernet_gen_subsys);
+
+void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops)
+{
+	mutex_lock(&net_mutex);
+	unregister_pernet_operations(ops);
+	ida_remove(&net_generic_ids, id);
+	mutex_unlock(&net_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys);
+
 /**
  *      register_pernet_device - register a network namespace device
  *	@ops:  pernet operations structure for the subsystem
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4e22e3a3535..ebb6b94f8af 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -449,6 +449,18 @@ void kfree_skb(struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
+/**
+ *	skb_recycle_check - check if skb can be reused for receive
+ *	@skb: buffer
+ *	@skb_size: minimum receive buffer size
+ *
+ *	Checks that the skb passed in is not shared or cloned, and
+ *	that it is linear and its head portion at least as large as
+ *	skb_size so that it can be recycled as a receive buffer.
+ *	If these conditions are met, this function does any necessary
+ *	reference count dropping and cleans up the skbuff as if it
+ *	just came from __alloc_skb().
+ */
 int skb_recycle_check(struct sk_buff *skb, int skb_size)
 {
 	struct skb_shared_info *shinfo;
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 490e035c6d9..2e78f6bd977 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -2063,9 +2063,10 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb,
 	u32 opt_len;
 	int len_delta;
 
-	buf_len = cipso_v4_genopt(buf, buf_len, doi_def, secattr);
-	if (buf_len < 0)
-		return buf_len;
+	ret_val = cipso_v4_genopt(buf, buf_len, doi_def, secattr);
+	if (ret_val < 0)
+		return ret_val;
+	buf_len = ret_val;
 	opt_len = (buf_len + 3) & ~3;
 
 	/* we overwrite any existing options to ensure that we have enough
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2095abc3cab..cf02701ced4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -284,7 +284,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 }
 EXPORT_SYMBOL_GPL(udp4_lib_lookup);
 
-static inline struct sock *udp_v4_mcast_next(struct sock *sk,
+static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
 					     __be16 loc_port, __be32 loc_addr,
 					     __be16 rmt_port, __be32 rmt_addr,
 					     int dif)
@@ -296,7 +296,8 @@ static inline struct sock *udp_v4_mcast_next(struct sock *sk,
 	sk_for_each_from(s, node) {
 		struct inet_sock *inet = inet_sk(s);
 
-		if (s->sk_hash != hnum					||
+		if (!net_eq(sock_net(s), net)				||
+		    s->sk_hash != hnum					||
 		    (inet->daddr && inet->daddr != rmt_addr)		||
 		    (inet->dport != rmt_port && inet->dport)		||
 		    (inet->rcv_saddr && inet->rcv_saddr != loc_addr)	||
@@ -1079,15 +1080,16 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	read_lock(&udp_hash_lock);
 	sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]);
 	dif = skb->dev->ifindex;
-	sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
+	sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
 	if (sk) {
 		struct sock *sknext = NULL;
 
 		do {
 			struct sk_buff *skb1 = skb;
 
-			sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
-						   uh->source, saddr, dif);
+			sknext = udp_v4_mcast_next(net, sk_next(sk), uh->dest,
+						   daddr, uh->source, saddr,
+						   dif);
 			if (sknext)
 				skb1 = skb_clone(skb, GFP_ATOMIC);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e51da8c092f..71e259e866a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -328,7 +328,7 @@ drop:
 	return -1;
 }
 
-static struct sock *udp_v6_mcast_next(struct sock *sk,
+static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 				      __be16 loc_port, struct in6_addr *loc_addr,
 				      __be16 rmt_port, struct in6_addr *rmt_addr,
 				      int dif)
@@ -340,7 +340,7 @@ static struct sock *udp_v6_mcast_next(struct sock *sk,
 	sk_for_each_from(s, node) {
 		struct inet_sock *inet = inet_sk(s);
 
-		if (sock_net(s) != sock_net(sk))
+		if (!net_eq(sock_net(s), net))
 			continue;
 
 		if (s->sk_hash == num && s->sk_family == PF_INET6) {
@@ -383,14 +383,14 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	read_lock(&udp_hash_lock);
 	sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]);
 	dif = inet6_iif(skb);
-	sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
+	sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
 	if (!sk) {
 		kfree_skb(skb);
 		goto out;
 	}
 
 	sk2 = sk;
-	while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr,
+	while ((sk2 = udp_v6_mcast_next(net, sk_next(sk2), uh->dest, daddr,
 					uh->source, saddr, dif))) {
 		struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
 		if (buff) {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index e55e0441e4d..3440a4637f0 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2075,7 +2075,6 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, in
 			req_size += socklen * 2;
 		} else {
 			size -= 2*socklen;
-			socklen = 0;
 		}
 		rq = (void*)skb_put(skb, req_size);
 		pol->sadb_x_policy_len += req_size/8;
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index a2cdbcbf64c..4ab62ad85dd 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -335,7 +335,7 @@ static int __init nf_ct_proto_gre_init(void)
 	rv = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_gre4);
 	if (rv < 0)
 		return rv;
-	rv = register_pernet_gen_device(&proto_gre_net_id, &proto_gre_net_ops);
+	rv = register_pernet_gen_subsys(&proto_gre_net_id, &proto_gre_net_ops);
 	if (rv < 0)
 		nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4);
 	return rv;
@@ -344,7 +344,7 @@ static int __init nf_ct_proto_gre_init(void)
 static void nf_ct_proto_gre_fini(void)
 {
 	nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4);
-	unregister_pernet_gen_device(proto_gre_net_id, &proto_gre_net_ops);
+	unregister_pernet_gen_subsys(proto_gre_net_id, &proto_gre_net_ops);
 }
 
 module_init(nf_ct_proto_gre_init);
diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c
index b0925a30335..249f6b92f15 100644
--- a/net/netlabel/netlabel_addrlist.c
+++ b/net/netlabel/netlabel_addrlist.c
@@ -315,6 +315,7 @@ struct netlbl_af6list *netlbl_af6list_remove(const struct in6_addr *addr,
  * Audit Helper Functions
  */
 
+#ifdef CONFIG_AUDIT
 /**
  * netlbl_af4list_audit_addr - Audit an IPv4 address
  * @audit_buf: audit buffer
@@ -386,3 +387,4 @@ void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf,
 	}
 }
 #endif /* IPv6 */
+#endif /* CONFIG_AUDIT */
diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h
index 0242bead405..07ae7fd82be 100644
--- a/net/netlabel/netlabel_addrlist.h
+++ b/net/netlabel/netlabel_addrlist.h
@@ -120,9 +120,19 @@ struct netlbl_af4list *netlbl_af4list_search(__be32 addr,
 struct netlbl_af4list *netlbl_af4list_search_exact(__be32 addr,
 						   __be32 mask,
 						   struct list_head *head);
+
+#ifdef CONFIG_AUDIT
 void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf,
 			       int src, const char *dev,
 			       __be32 addr, __be32 mask);
+#else
+static inline void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf,
+					     int src, const char *dev,
+					     __be32 addr, __be32 mask)
+{
+	return;
+}
+#endif
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 
@@ -179,11 +189,23 @@ struct netlbl_af6list *netlbl_af6list_search(const struct in6_addr *addr,
 struct netlbl_af6list *netlbl_af6list_search_exact(const struct in6_addr *addr,
 						   const struct in6_addr *mask,
 						   struct list_head *head);
+
+#ifdef CONFIG_AUDIT
 void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf,
 			       int src,
 			       const char *dev,
 			       const struct in6_addr *addr,
 			       const struct in6_addr *mask);
+#else
+static inline void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf,
+					     int src,
+					     const char *dev,
+					     const struct in6_addr *addr,
+					     const struct in6_addr *mask)
+{
+	return;
+}
+#endif
 #endif /* IPV6 */
 
 #endif
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index ee769ecaa13..0a0ef17b2a4 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -265,7 +265,7 @@ add_failure:
 static int netlbl_mgmt_listentry(struct sk_buff *skb,
 				 struct netlbl_dom_map *entry)
 {
-	int ret_val;
+	int ret_val = 0;
 	struct nlattr *nla_a;
 	struct nlattr *nla_b;
 	struct netlbl_af4list *iter4;
diff --git a/net/socket.c b/net/socket.c
index 2b7a4b5c9b7..57550c3bcab 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -990,7 +990,6 @@ static int sock_close(struct inode *inode, struct file *filp)
 		printk(KERN_DEBUG "sock_close: NULL inode\n");
 		return 0;
 	}
-	sock_fasync(-1, filp, 0);
 	sock_release(SOCKET_I(inode));
 	return 0;
 }
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 436bf1b4b76..cb216b2df66 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -228,19 +228,21 @@ static int
 rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
 {
 	spinlock_t *cache_lock;
-	struct rpc_cred *cred;
+	struct rpc_cred *cred, *next;
 	unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM;
 
-	while (!list_empty(&cred_unused)) {
-		cred = list_entry(cred_unused.next, struct rpc_cred, cr_lru);
+	list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) {
+
+		/* Enforce a 60 second garbage collection moratorium */
+		if (time_in_range(cred->cr_expire, expired, jiffies) &&
+		    test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0)
+			continue;
+
 		list_del_init(&cred->cr_lru);
 		number_cred_unused--;
 		if (atomic_read(&cred->cr_count) != 0)
 			continue;
-		/* Enforce a 5 second garbage collection moratorium */
-		if (time_in_range(cred->cr_expire, expired, jiffies) &&
-		    test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0)
-			continue;
+
 		cache_lock = &cred->cr_auth->au_credcache->lock;
 		spin_lock(cache_lock);
 		if (atomic_read(&cred->cr_count) == 0) {
@@ -453,7 +455,7 @@ need_lock:
 	}
 	if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0)
 		rpcauth_unhash_cred(cred);
-	else if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) {
+	if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) {
 		cred->cr_expire = jiffies;
 		list_add_tail(&cred->cr_lru, &cred_unused);
 		number_cred_unused++;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9a288d5eea6..0a50361e3d8 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -249,6 +249,7 @@ struct sock_xprt {
 	void			(*old_data_ready)(struct sock *, int);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
+	void			(*old_error_report)(struct sock *);
 };
 
 /*
@@ -698,8 +699,9 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	case -EAGAIN:
 		xs_nospace(task);
 		break;
-	case -ECONNREFUSED:
 	case -ECONNRESET:
+		xs_tcp_shutdown(xprt);
+	case -ECONNREFUSED:
 	case -ENOTCONN:
 	case -EPIPE:
 		status = -ENOTCONN;
@@ -742,6 +744,22 @@ out_release:
 	xprt_release_xprt(xprt, task);
 }
 
+static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
+{
+	transport->old_data_ready = sk->sk_data_ready;
+	transport->old_state_change = sk->sk_state_change;
+	transport->old_write_space = sk->sk_write_space;
+	transport->old_error_report = sk->sk_error_report;
+}
+
+static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
+{
+	sk->sk_data_ready = transport->old_data_ready;
+	sk->sk_state_change = transport->old_state_change;
+	sk->sk_write_space = transport->old_write_space;
+	sk->sk_error_report = transport->old_error_report;
+}
+
 /**
  * xs_close - close a socket
  * @xprt: transport
@@ -765,9 +783,8 @@ static void xs_close(struct rpc_xprt *xprt)
 	transport->sock = NULL;
 
 	sk->sk_user_data = NULL;
-	sk->sk_data_ready = transport->old_data_ready;
-	sk->sk_state_change = transport->old_state_change;
-	sk->sk_write_space = transport->old_write_space;
+
+	xs_restore_old_callbacks(transport, sk);
 	write_unlock_bh(&sk->sk_callback_lock);
 
 	sk->sk_no_check = 0;
@@ -1180,6 +1197,28 @@ static void xs_tcp_state_change(struct sock *sk)
 }
 
 /**
+ * xs_tcp_error_report - callback mainly for catching RST events
+ * @sk: socket
+ */
+static void xs_tcp_error_report(struct sock *sk)
+{
+	struct rpc_xprt *xprt;
+
+	read_lock(&sk->sk_callback_lock);
+	if (sk->sk_err != ECONNRESET || sk->sk_state != TCP_ESTABLISHED)
+		goto out;
+	if (!(xprt = xprt_from_sock(sk)))
+		goto out;
+	dprintk("RPC:       %s client %p...\n"
+			"RPC:       error %d\n",
+			__func__, xprt, sk->sk_err);
+
+	xprt_force_disconnect(xprt);
+out:
+	read_unlock(&sk->sk_callback_lock);
+}
+
+/**
  * xs_udp_write_space - callback invoked when socket buffer space
  *                             becomes available
  * @sk: socket whose state has changed
@@ -1454,10 +1493,9 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 
 		write_lock_bh(&sk->sk_callback_lock);
 
+		xs_save_old_callbacks(transport, sk);
+
 		sk->sk_user_data = xprt;
-		transport->old_data_ready = sk->sk_data_ready;
-		transport->old_state_change = sk->sk_state_change;
-		transport->old_write_space = sk->sk_write_space;
 		sk->sk_data_ready = xs_udp_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
 		sk->sk_no_check = UDP_CSUM_NORCV;
@@ -1589,13 +1627,13 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 
 		write_lock_bh(&sk->sk_callback_lock);
 
+		xs_save_old_callbacks(transport, sk);
+
 		sk->sk_user_data = xprt;
-		transport->old_data_ready = sk->sk_data_ready;
-		transport->old_state_change = sk->sk_state_change;
-		transport->old_write_space = sk->sk_write_space;
 		sk->sk_data_ready = xs_tcp_data_ready;
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
+		sk->sk_error_report = xs_tcp_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		/* socket options */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index dc504d308ec..4d3c6071b9a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2213,7 +2213,7 @@ static int unix_net_init(struct net *net)
 #endif
 	error = 0;
 out:
-	return 0;
+	return error;
 }
 
 static void unix_net_exit(struct net *net)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 832b47c1de8..25872747762 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1251,6 +1251,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl,
 				 -EINVAL : -EAGAIN);
 			xfrm_state_put(x);
 		}
+		else if (error == -ESRCH)
+			error = -EAGAIN;
 
 		if (!tmpl->optional)
 			goto fail;