Merge commit 'v2.6.27-rc1' into x86/urgent

13 files changed, 100 insertions, 68 deletions

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 743d85fcd65..1c2e3ec2eb5 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -226,7 +226,7 @@ static inline void dccp_csum_outgoing(struct sk_buff *skb)
 
 extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb);
 
-extern int  dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb);
+extern int  dccp_retransmit_skb(struct sock *sk);
 
 extern void dccp_send_ack(struct sock *sk);
 extern void dccp_reqsk_send_ack(struct sk_buff *sk, struct request_sock *rsk);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index a835b88237c..882c5c4de69 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -196,8 +196,8 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk,
 static void dccp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data +
-							(iph->ihl << 2));
+	const u8 offset = iph->ihl << 2;
+	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
 	struct dccp_sock *dp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
@@ -207,7 +207,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < (iph->ihl << 2) + 8) {
+	if (skb->len < offset + sizeof(*dh) ||
+	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
 		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		return;
 	}
@@ -238,7 +239,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	dp = dccp_sk(sk);
 	seq = dccp_hdr_seq(dh);
 	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
-	    !between48(seq, dp->dccps_swl, dp->dccps_swh)) {
+	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index da509127e00..5e1ee0da2c4 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -89,12 +89,19 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 {
 	struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data;
 	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
 	struct sock *sk;
 	int err;
 	__u64 seq;
 	struct net *net = dev_net(skb->dev);
 
+	if (skb->len < offset + sizeof(*dh) ||
+	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
+		ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+		return;
+	}
+
 	sk = inet6_lookup(net, &dccp_hashinfo,
 			&hdr->daddr, dh->dccph_dport,
 			&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
@@ -116,6 +123,14 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (sk->sk_state == DCCP_CLOSED)
 		goto out;
 
+	dp = dccp_sk(sk);
+	seq = dccp_hdr_seq(dh);
+	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
+	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
+		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
+		goto out;
+	}
+
 	np = inet6_sk(sk);
 
 	if (type == ICMPV6_PKT_TOOBIG) {
@@ -168,7 +183,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	icmpv6_err_convert(type, code, &err);
 
-	seq = dccp_hdr_seq(dh);
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
 		struct request_sock *req, **prev;
diff --git a/net/dccp/output.c b/net/dccp/output.c
index fe20068c5d8..d06945c7d3d 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -53,8 +53,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 					  dccp_packet_hdr_len(dcb->dccpd_type);
 		int err, set_ack = 1;
 		u64 ackno = dp->dccps_gsr;
-
-		dccp_inc_seqno(&dp->dccps_gss);
+		/*
+		 * Increment GSS here already in case the option code needs it.
+		 * Update GSS for real only if option processing below succeeds.
+		 */
+		dcb->dccpd_seq = ADD48(dp->dccps_gss, 1);
 
 		switch (dcb->dccpd_type) {
 		case DCCP_PKT_DATA:
@@ -66,6 +69,9 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		case DCCP_PKT_REQUEST:
 			set_ack = 0;
+			/* Use ISS on the first (non-retransmitted) Request. */
+			if (icsk->icsk_retransmits == 0)
+				dcb->dccpd_seq = dp->dccps_iss;
 			/* fall through */
 
 		case DCCP_PKT_SYNC:
@@ -84,8 +90,6 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 			break;
 		}
 
-		dcb->dccpd_seq = dp->dccps_gss;
-
 		if (dccp_insert_options(sk, skb)) {
 			kfree_skb(skb);
 			return -EPROTO;
@@ -103,7 +107,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 		/* XXX For now we're using only 48 bits sequence numbers */
 		dh->dccph_x	= 1;
 
-		dp->dccps_awh = dp->dccps_gss;
+		dccp_update_gss(sk, dcb->dccpd_seq);
 		dccp_hdr_set_seq(dh, dp->dccps_gss);
 		if (set_ack)
 			dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
@@ -112,6 +116,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 		case DCCP_PKT_REQUEST:
 			dccp_hdr_request(skb)->dccph_req_service =
 							dp->dccps_service;
+			/*
+			 * Limit Ack window to ISS <= P.ackno <= GSS, so that
+			 * only Responses to Requests we sent are considered.
+			 */
+			dp->dccps_awl = dp->dccps_iss;
 			break;
 		case DCCP_PKT_RESET:
 			dccp_hdr_reset(skb)->dccph_reset_code =
@@ -284,14 +293,26 @@ void dccp_write_xmit(struct sock *sk, int block)
 	}
 }
 
-int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
+/**
+ * dccp_retransmit_skb  -  Retransmit Request, Close, or CloseReq packets
+ * There are only four retransmittable packet types in DCCP:
+ * - Request  in client-REQUEST  state (sec. 8.1.1),
+ * - CloseReq in server-CLOSEREQ state (sec. 8.3),
+ * - Close    in   node-CLOSING  state (sec. 8.3),
+ * - Acks in client-PARTOPEN state (sec. 8.1.5, handled by dccp_delack_timer()).
+ * This function expects sk->sk_send_head to contain the original skb.
+ */
+int dccp_retransmit_skb(struct sock *sk)
 {
+	WARN_ON(sk->sk_send_head == NULL);
+
 	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0)
 		return -EHOSTUNREACH; /* Routing failure or similar. */
 
-	return dccp_transmit_skb(sk, (skb_cloned(skb) ?
-				      pskb_copy(skb, GFP_ATOMIC):
-				      skb_clone(skb, GFP_ATOMIC)));
+	/* this count is used to distinguish original and retransmitted skb */
+	inet_csk(sk)->icsk_retransmits++;
+
+	return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC));
 }
 
 struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
@@ -437,19 +458,7 @@ static inline void dccp_connect_init(struct sock *sk)
 
 	dccp_sync_mss(sk, dst_mtu(dst));
 
-	/*
-	 * SWL and AWL are initially adjusted so that they are not less than
-	 * the initial Sequence Numbers received and sent, respectively:
-	 *	SWL := max(GSR + 1 - floor(W/4), ISR),
-	 *	AWL := max(GSS - W' + 1, ISS).
-	 * These adjustments MUST be applied only at the beginning of the
-	 * connection.
-	 */
-	dccp_update_gss(sk, dp->dccps_iss);
-	dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss));
-
-	/* S.GAR - greatest valid acknowledgement number received on a non-Sync;
-	 *         initialized to S.ISS (sec. 8.5)                            */
+	/* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */
 	dp->dccps_gar = dp->dccps_iss;
 
 	icsk->icsk_retransmits = 0;
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 6a5b961b6f5..54b3c7e9e01 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -99,21 +99,11 @@ static void dccp_retransmit_timer(struct sock *sk)
 	}
 
 	/*
-	 * sk->sk_send_head has to have one skb with
-	 * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP
-	 * packet types. The only packets eligible for retransmission are:
-	 *	-- Requests in client-REQUEST  state (sec. 8.1.1)
-	 *	-- Acks     in client-PARTOPEN state (sec. 8.1.5)
-	 *	-- CloseReq in server-CLOSEREQ state (sec. 8.3)
-	 *	-- Close    in   node-CLOSING  state (sec. 8.3)                */
-	WARN_ON(sk->sk_send_head == NULL);
-
-	/*
 	 * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was
 	 * sent, no need to retransmit, this sock is dead.
 	 */
 	if (dccp_write_timeout(sk))
-		goto out;
+		return;
 
 	/*
 	 * We want to know the number of packets retransmitted, not the
@@ -122,30 +112,28 @@ static void dccp_retransmit_timer(struct sock *sk)
 	if (icsk->icsk_retransmits == 0)
 		DCCP_INC_STATS_BH(DCCP_MIB_TIMEOUTS);
 
-	if (dccp_retransmit_skb(sk, sk->sk_send_head) < 0) {
+	if (dccp_retransmit_skb(sk) != 0) {
 		/*
 		 * Retransmission failed because of local congestion,
 		 * do not backoff.
 		 */
-		if (icsk->icsk_retransmits == 0)
+		if (--icsk->icsk_retransmits == 0)
 			icsk->icsk_retransmits = 1;
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 					  min(icsk->icsk_rto,
 					      TCP_RESOURCE_PROBE_INTERVAL),
 					  DCCP_RTO_MAX);
-		goto out;
+		return;
 	}
 
 backoff:
 	icsk->icsk_backoff++;
-	icsk->icsk_retransmits++;
 
 	icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX);
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto,
 				  DCCP_RTO_MAX);
 	if (icsk->icsk_retransmits > sysctl_dccp_retries1)
 		__sk_dst_reset(sk);
-out:;
 }
 
 static void dccp_write_timer(unsigned long data)
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index a42b64d040c..38ccb6dfb02 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -104,9 +104,7 @@ out:
 
 static int ipcomp4_init_state(struct xfrm_state *x)
 {
-	int err;
-	struct ipcomp_data *ipcd;
-	struct xfrm_algo_desc *calg_desc;
+	int err = -EINVAL;
 
 	x->props.header_len = 0;
 	switch (x->props.mode) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a507c5e27d0..380d6474cf6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2914,7 +2914,7 @@ static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table,
 	return 0;
 }
 
-ctl_table ipv4_route_table[] = {
+static ctl_table ipv4_route_table[] = {
 	{
 		.ctl_name	= NET_IPV4_ROUTE_GC_THRESH,
 		.procname	= "gc_thresh",
@@ -3216,6 +3216,15 @@ int __init ip_rt_init(void)
 	return rc;
 }
 
+/*
+ * We really need to sanitize the damn ipv4 init order, then all
+ * this nonsense will go away.
+ */
+void __init ip_static_sysctl_init(void)
+{
+	register_sysctl_paths(ipv4_route_path, ipv4_route_table);
+}
+
 EXPORT_SYMBOL(__ip_select_ident);
 EXPORT_SYMBOL(ip_route_input);
 EXPORT_SYMBOL(ip_route_output_key);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d63e9388d92..770d827f5ab 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -401,13 +401,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= &ipv4_local_port_range,
 		.strategy	= &ipv4_sysctl_local_port_range,
 	},
-	{
-		.ctl_name	= NET_IPV4_ROUTE,
-		.procname	= "route",
-		.maxlen		= 0,
-		.mode		= 0555,
-		.child		= ipv4_route_table
-	},
 #ifdef CONFIG_IP_MULTICAST
 	{
 		.ctl_name	= NET_IPV4_IGMP_MAX_MEMBERSHIPS,
@@ -882,11 +875,4 @@ static __init int sysctl_ipv4_init(void)
 	return 0;
 }
 
-/* set enough of tree skeleton to get rid of ordering problems */
-void __init ip_static_sysctl_init(void)
-{
-	static ctl_table table[1];
-	register_sysctl_paths(net_ipv4_ctl_path, table);
-}
-
 __initcall(sysctl_ipv4_init);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c708ca84229..95055f8c3f3 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -934,6 +934,11 @@ static int __init inet6_init(void)
 	if (err)
 		goto out_unregister_sock;
 
+#ifdef CONFIG_SYSCTL
+	err = ipv6_static_sysctl_register();
+	if (err)
+		goto static_sysctl_fail;
+#endif
 	/*
 	 *	ipngwg API draft makes clear that the correct semantics
 	 *	for TCP and UDP is to consider one TCP and UDP instance
@@ -1058,6 +1063,10 @@ ipmr_fail:
 icmp_fail:
 	unregister_pernet_subsys(&inet6_net_ops);
 register_pernet_fail:
+#ifdef CONFIG_SYSCTL
+	ipv6_static_sysctl_unregister();
+static_sysctl_fail:
+#endif
 	cleanup_ipv6_mibs();
 out_unregister_sock:
 	sock_unregister(PF_INET6);
@@ -1113,6 +1122,9 @@ static void __exit inet6_exit(void)
 	rawv6_exit();
 
 	unregister_pernet_subsys(&inet6_net_ops);
+#ifdef CONFIG_SYSCTL
+	ipv6_static_sysctl_unregister();
+#endif
 	cleanup_ipv6_mibs();
 	proto_unregister(&rawv6_prot);
 	proto_unregister(&udplitev6_prot);
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 0cfcea42153..4545e430686 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -134,9 +134,7 @@ out:
 
 static int ipcomp6_init_state(struct xfrm_state *x)
 {
-	int err;
-	struct ipcomp_data *ipcd;
-	struct xfrm_algo_desc *calg_desc;
+	int err = -EINVAL;
 
 	x->props.header_len = 0;
 	switch (x->props.mode) {
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 5c99274558b..e6dfaeac6be 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -150,3 +150,19 @@ void ipv6_sysctl_unregister(void)
 	unregister_net_sysctl_table(ip6_header);
 	unregister_pernet_subsys(&ipv6_sysctl_net_ops);
 }
+
+static struct ctl_table_header *ip6_base;
+
+int ipv6_static_sysctl_register(void)
+{
+	static struct ctl_table empty[1];
+	ip6_base = register_net_sysctl_rotable(net_ipv6_ctl_path, empty);
+	if (ip6_base == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void ipv6_static_sysctl_unregister(void)
+{
+	unregister_net_sysctl_table(ip6_base);
+}
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 835d2741308..5a32cb7c4bb 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -310,8 +310,7 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
 	switch (m->mode) {
 	case SVC_POOL_PERCPU:
 	{
-		cpumask_of_cpu_ptr(cpumask, node);
-		set_cpus_allowed_ptr(task, cpumask);
+		set_cpus_allowed_ptr(task, &cpumask_of_cpu(node));
 		break;
 	}
 	case SVC_POOL_PERNODE:
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index cefbc367d8b..972201cd5fa 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -73,7 +73,9 @@ static struct ctl_table_root net_sysctl_ro_root = {
 
 static int sysctl_net_init(struct net *net)
 {
-	setup_sysctl_set(&net->sysctls, NULL, is_seen);
+	setup_sysctl_set(&net->sysctls,
+			 &net_sysctl_ro_root.default_set,
+			 is_seen);
 	return 0;
 }