Merge commit 'v2.6.36-rc7' into core/rcu

Merge reason: Update from -rc3 to -rc7.

Signed-off-by: Ingo Molnar <[email protected]>

net/ipv4/Kconfig

@@ -217,6 +217,7 @@ config NET_IPIP
 
 config NET_IPGRE
 	tristate "IP: GRE tunnels over IP"
+	depends on IPV6 || IPV6=n
 	help
 	  Tunneling means encapsulating data of one protocol type within
 	  another protocol and sending it over a channel that understands the

net/ipv4/datagram.c

@@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 	if (!inet->inet_saddr)
 		inet->inet_saddr = rt->rt_src;	/* Update source address */
-	if (!inet->inet_rcv_saddr)
+	if (!inet->inet_rcv_saddr) {
 		inet->inet_rcv_saddr = rt->rt_src;
+		if (sk->sk_prot->rehash)
+			sk->sk_prot->rehash(sk);
+	}
 	inet->inet_daddr = rt->rt_dst;
 	inet->inet_dport = usin->sin_port;
 	sk->sk_state = TCP_ESTABLISHED;

net/ipv4/fib_frontend.c

@@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 
 	struct fib_result res;
 	int no_addr, rpf, accept_local;
+	bool dev_match;
 	int ret;
 	struct net *net;
 
@@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 	}
 	*spec_dst = FIB_RES_PREFSRC(res);
 	fib_combine_itag(itag, &res);
+	dev_match = false;
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1)
+	for (ret = 0; ret < res.fi->fib_nhs; ret++) {
+		struct fib_nh *nh = &res.fi->fib_nh[ret];
+
+		if (nh->nh_dev == dev) {
+			dev_match = true;
+			break;
+		}
+	}
 #else
 	if (FIB_RES_DEV(res) == dev)
+		dev_match = true;
 #endif
-	{
+	if (dev_match) {
 		ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
 		fib_res_put(&res);
 		return ret;

net/ipv4/fib_trie.c

@@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node)
 {
 	struct tnode *ret = node_parent(node);
 
-	return rcu_dereference(ret);
+	return rcu_dereference_check(ret,
+				     rcu_read_lock_held() ||
+				     lockdep_rtnl_is_held());
 }
 
 /* Same as rcu_assign_pointer
@@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c)
 
 static struct leaf *trie_firstleaf(struct trie *t)
 {
-	struct tnode *n = (struct tnode *) rcu_dereference(t->trie);
+	struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie,
+							rcu_read_lock_held() ||
+							lockdep_rtnl_is_held());
 
 	if (!n)
 		return NULL;

net/ipv4/igmp.c

@@ -834,7 +834,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 	int			mark = 0;
 
 
-	if (len == 8) {
+	if (len == 8 || IGMP_V2_SEEN(in_dev)) {
 		if (ih->code == 0) {
 			/* Alas, old v1 router presents here. */
 

net/ipv4/ip_gre.c

@@ -45,7 +45,7 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
@@ -699,7 +699,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			if ((dst = rt->rt_gateway) == 0)
 				goto tx_error_icmp;
 		}
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
 			struct in6_addr *addr6;
 			int addr_type;
@@ -774,7 +774,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			goto tx_error;
 		}
 	}
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	else if (skb->protocol == htons(ETH_P_IPV6)) {
 		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
 
@@ -850,7 +850,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 	if ((iph->ttl = tiph->ttl) == 0) {
 		if (skb->protocol == htons(ETH_P_IP))
 			iph->ttl = old_iph->ttl;
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6))
 			iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
 #endif

net/ipv4/ip_output.c

@@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 * we can switch to copy when see the first bad fragment.
 	 */
 	if (skb_has_frags(skb)) {
-		struct sk_buff *frag;
+		struct sk_buff *frag, *frag2;
 		int first_len = skb_pagelen(skb);
-		int truesizes = 0;
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
@@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
 			    skb_headroom(frag) < hlen)
-			    goto slow_path;
+				goto slow_path_clean;
 
 			/* Partially cloned skb? */
 			if (skb_shared(frag))
-				goto slow_path;
+				goto slow_path_clean;
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
 			}
-			truesizes += frag->truesize;
+			skb->truesize -= frag->truesize;
 		}
 
 		/* Everything is OK. Generate! */
@@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		frag = skb_shinfo(skb)->frag_list;
 		skb_frag_list_init(skb);
 		skb->data_len = first_len - skb_headlen(skb);
-		skb->truesize -= truesizes;
 		skb->len = first_len;
 		iph->tot_len = htons(first_len);
 		iph->frag_off = htons(IP_MF);
@@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		}
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		return err;
+
+slow_path_clean:
+		skb_walk_frags(skb, frag2) {
+			if (frag2 == frag)
+				break;
+			frag2->sk = NULL;
+			frag2->destructor = NULL;
+			skb->truesize += frag2->truesize;
+		}
 	}
 
 slow_path:

net/ipv4/ip_sockglue.c

@@ -1129,6 +1129,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_HDRINCL:
 		val = inet->hdrincl;
 		break;
+	case IP_NODEFRAG:
+		val = inet->nodefrag;
+		break;
 	case IP_MTU_DISCOVER:
 		val = inet->pmtudisc;
 		break;

net/ipv4/netfilter/ipt_REJECT.c

@@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 	/* ip_route_me_harder expects skb->dst to be set */
 	skb_dst_set_noref(nskb, skb_dst(oldskb));
 
+	nskb->protocol = htons(ETH_P_IP);
 	if (ip_route_me_harder(nskb, addr_type))
 		goto free_nskb;
 

net/ipv4/netfilter/nf_defrag_ipv4.c

@@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
 					  const struct net_device *out,
 					  int (*okfn)(struct sk_buff *))
 {
+	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(skb->sk);
 
-	if (inet && inet->nodefrag)
+	if (sk && (sk->sk_family == PF_INET) &&
+	    inet->nodefrag)
 		return NF_ACCEPT;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)

net/ipv4/netfilter/nf_nat_snmp_basic.c

@@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum,
 	unsigned char s[4];
 
 	if (offset & 1) {
-		s[0] = s[2] = 0;
+		s[0] = ~0;
 		s[1] = ~*optr;
+		s[2] = 0;
 		s[3] = *nptr;
 	} else {
-		s[1] = s[3] = 0;
 		s[0] = ~*optr;
+		s[1] = ~0;
 		s[2] = *nptr;
+		s[3] = 0;
 	}
 
 	*csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum)));

net/ipv4/route.c

@@ -1231,7 +1231,7 @@ restart:
 			}
 
 			if (net_ratelimit())
-				printk(KERN_WARNING "Neighbour table overflow.\n");
+				printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
 			rt_drop(rt);
 			return -ENOBUFS;
 		}
@@ -2738,6 +2738,11 @@ slow_output:
 }
 EXPORT_SYMBOL_GPL(__ip_route_output_key);
 
+static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
+
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
 }
@@ -2746,7 +2751,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 	.family			=	AF_INET,
 	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.destroy		=	ipv4_dst_destroy,
-	.check			=	ipv4_dst_check,
+	.check			=	ipv4_blackhole_dst_check,
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
 	.entries		=	ATOMIC_INIT(0),
 };

net/ipv4/tcp.c

@@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	 */
 
 	mask = 0;
-	if (sk->sk_err)
-		mask = POLLERR;
 
 	/*
 	 * POLLHUP is certainly not done right. But poll() doesn't
@@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
 	}
+	/* This barrier is coupled with smp_wmb() in tcp_reset() */
+	smp_rmb();
+	if (sk->sk_err)
+		mask |= POLLERR;
+
 	return mask;
 }
 EXPORT_SYMBOL(tcp_poll);
@@ -940,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	sg = sk->sk_route_caps & NETIF_F_SG;
 
 	while (--iovlen >= 0) {
-		int seglen = iov->iov_len;
+		size_t seglen = iov->iov_len;
 		unsigned char __user *from = iov->iov_base;
 
 		iov++;

net/ipv4/tcp_input.c

@@ -2545,7 +2545,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
 			cnt += tcp_skb_pcount(skb);
 
 		if (cnt > packets) {
-			if (tcp_is_sack(tp) || (oldcnt >= packets))
+			if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+			    (oldcnt >= packets))
 				break;
 
 			mss = skb_shinfo(skb)->gso_size;
@@ -4048,6 +4049,8 @@ static void tcp_reset(struct sock *sk)
 	default:
 		sk->sk_err = ECONNRESET;
 	}
+	/* This barrier is coupled with smp_rmb() in tcp_poll() */
+	smp_wmb();
 
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_error_report(sk);

net/ipv4/tcp_timer.c

@@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 
 /* This function calculates a "timeout" which is equivalent to the timeout of a
  * TCP connection after "boundary" unsuccessful, exponentially backed-off
- * retransmissions with an initial RTO of TCP_RTO_MIN.
+ * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
+ * syn_set flag is set.
  */
 static bool retransmits_timed_out(struct sock *sk,
-				  unsigned int boundary)
+				  unsigned int boundary,
+				  bool syn_set)
 {
 	unsigned int timeout, linear_backoff_thresh;
 	unsigned int start_ts;
+	unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
 
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
@@ -151,12 +154,12 @@ static bool retransmits_timed_out(struct sock *sk,
 	else
 		start_ts = tcp_sk(sk)->retrans_stamp;
 
-	linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+	linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
 
 	if (boundary <= linear_backoff_thresh)
-		timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+		timeout = ((2 << boundary) - 1) * rto_base;
 	else
-		timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+		timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
 			  (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 
 	return (tcp_time_stamp - start_ts) >= timeout;
@@ -167,14 +170,15 @@ static int tcp_write_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int retry_until;
-	bool do_reset;
+	bool do_reset, syn_set = 0;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
 			dst_negative_advice(sk);
 		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+		syn_set = 1;
 	} else {
-		if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
+		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) {
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
@@ -187,14 +191,14 @@ static int tcp_write_timeout(struct sock *sk)
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
-				   !retransmits_timed_out(sk, retry_until);
+				   !retransmits_timed_out(sk, retry_until, 0);
 
 			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
 	}
 
-	if (retransmits_timed_out(sk, retry_until)) {
+	if (retransmits_timed_out(sk, retry_until, syn_set)) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);
 		return 1;
@@ -436,7 +440,7 @@ out_reset_timer:
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
-	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
+	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0))
 		__sk_dst_reset(sk);
 
 out:;

net/ipv4/udp.c

@@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk)
 }
 EXPORT_SYMBOL(udp_lib_unhash);
 
+/*
+ * inet_rcv_saddr was changed, we must rehash secondary hash
+ */
+void udp_lib_rehash(struct sock *sk, u16 newhash)
+{
+	if (sk_hashed(sk)) {
+		struct udp_table *udptable = sk->sk_prot->h.udp_table;
+		struct udp_hslot *hslot, *hslot2, *nhslot2;
+
+		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
+		nhslot2 = udp_hashslot2(udptable, newhash);
+		udp_sk(sk)->udp_portaddr_hash = newhash;
+		if (hslot2 != nhslot2) {
+			hslot = udp_hashslot(udptable, sock_net(sk),
+					     udp_sk(sk)->udp_port_hash);
+			/* we must lock primary chain too */
+			spin_lock_bh(&hslot->lock);
+
+			spin_lock(&hslot2->lock);
+			hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
+			hslot2->count--;
+			spin_unlock(&hslot2->lock);
+
+			spin_lock(&nhslot2->lock);
+			hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &nhslot2->head);
+			nhslot2->count++;
+			spin_unlock(&nhslot2->lock);
+
+			spin_unlock_bh(&hslot->lock);
+		}
+	}
+}
+EXPORT_SYMBOL(udp_lib_rehash);
+
+static void udp_v4_rehash(struct sock *sk)
+{
+	u16 new_hash = udp4_portaddr_hash(sock_net(sk),
+					  inet_sk(sk)->inet_rcv_saddr,
+					  inet_sk(sk)->inet_num);
+	udp_lib_rehash(sk, new_hash);
+}
+
 static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
@@ -1843,6 +1886,7 @@ struct proto udp_prot = {
 	.backlog_rcv	   = __udp_queue_rcv_skb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
+	.rehash		   = udp_v4_rehash,
 	.get_port	   = udp_v4_get_port,
 	.memory_allocated  = &udp_memory_allocated,
 	.sysctl_mem	   = sysctl_udp_mem,

net/ipv4/xfrm4_policy.c

@@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net,
 
 static int xfrm4_get_tos(struct flowi *fl)
 {
-	return fl->fl4_tos;
+	return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */
 }
 
 static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,

net/ipv4/xfrm4_state.c

@@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x)
 }
 
 static void
-__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl,
-		     struct xfrm_tmpl *tmpl,
-		     xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
+{
+	sel->daddr.a4 = fl->fl4_dst;
+	sel->saddr.a4 = fl->fl4_src;
+	sel->dport = xfrm_flowi_dport(fl);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET;
+	sel->prefixlen_d = 32;
+	sel->prefixlen_s = 32;
+	sel->proto = fl->proto;
+	sel->ifindex = fl->oif;
+}
+
+static void
+xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+		   xfrm_address_t *daddr, xfrm_address_t *saddr)
 {
-	x->sel.daddr.a4 = fl->fl4_dst;
-	x->sel.saddr.a4 = fl->fl4_src;
-	x->sel.dport = xfrm_flowi_dport(fl);
-	x->sel.dport_mask = htons(0xffff);
-	x->sel.sport = xfrm_flowi_sport(fl);
-	x->sel.sport_mask = htons(0xffff);
-	x->sel.family = AF_INET;
-	x->sel.prefixlen_d = 32;
-	x->sel.prefixlen_s = 32;
-	x->sel.proto = fl->proto;
-	x->sel.ifindex = fl->oif;
 	x->id = tmpl->id;
 	if (x->id.daddr.a4 == 0)
 		x->id.daddr.a4 = daddr->a4;
@@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
 	.owner			= THIS_MODULE,
 	.init_flags		= xfrm4_init_flags,
 	.init_tempsel		= __xfrm4_init_tempsel,
+	.init_temprop		= xfrm4_init_temprop,
 	.output			= xfrm4_output,
 	.extract_input		= xfrm4_extract_input,
 	.extract_output		= xfrm4_extract_output,