Merge commit 'v2.6.37-rc7' into spi/next

12 files changed, 60 insertions, 49 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 200eb538fbb..0f280348e0f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -365,7 +365,7 @@ static struct tnode *tnode_alloc(size_t size)
 	if (size <= PAGE_SIZE)
 		return kzalloc(size, GFP_KERNEL);
 	else
-		return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
+		return vzalloc(size);
 }
 
 static void __tnode_vfree(struct work_struct *arg)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 96bc7f9475a..e5d1a44bcbd 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -569,6 +569,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		/* No need to clone since we're just using its address. */
 		rt2 = rt;
 
+		if (!fl.nl_u.ip4_u.saddr)
+			fl.nl_u.ip4_u.saddr = rt->rt_src;
+
 		err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0);
 		switch (err) {
 		case 0:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c8877c6c721..3c53c2d89e3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2306,10 +2306,8 @@ void ip_mc_drop_socket(struct sock *sk)
 
 		in_dev = inetdev_by_index(net, iml->multi.imr_ifindex);
 		(void) ip_mc_leave_src(sk, iml, in_dev);
-		if (in_dev != NULL) {
+		if (in_dev != NULL)
 			ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr);
-			in_dev_put(in_dev);
-		}
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
 		call_rcu(&iml->rcu, ip_mc_socklist_reclaim);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 1b344f30b46..3c0369a3a66 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -133,8 +133,7 @@ int __inet_inherit_port(struct sock *sk, struct sock *child)
 			}
 		}
 	}
-	sk_add_bind_node(child, &tb->owners);
-	inet_csk(child)->icsk_bind_hash = tb;
+	inet_bind_hash(child, tb, port);
 	spin_unlock(&head->lock);
 
 	return 0;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4ae1f203f7c..b14ec7d03b6 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -59,13 +59,13 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 	local_bh_enable();
 
 	socket_seq_show(seq);
-	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
+	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
 		   sock_prot_inuse_get(net, &tcp_prot), orphans,
 		   tcp_death_row.tw_count, sockets,
-		   atomic_read(&tcp_memory_allocated));
-	seq_printf(seq, "UDP: inuse %d mem %d\n",
+		   atomic_long_read(&tcp_memory_allocated));
+	seq_printf(seq, "UDP: inuse %d mem %ld\n",
 		   sock_prot_inuse_get(net, &udp_prot),
-		   atomic_read(&udp_memory_allocated));
+		   atomic_long_read(&udp_memory_allocated));
 	seq_printf(seq, "UDPLITE: inuse %d\n",
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
@@ -253,6 +253,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP),
 	SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP),
 	SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER),
+	SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d96c1da4b17..1b4ec21497a 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -26,6 +26,8 @@ static int zero;
 static int tcp_retr1_max = 255;
 static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
+static int tcp_adv_win_scale_min = -31;
+static int tcp_adv_win_scale_max = 31;
 
 /* Update system visible IP port range */
 static void set_local_port_range(int range[2])
@@ -398,7 +400,7 @@ static struct ctl_table ipv4_table[] = {
 		.data		= &sysctl_tcp_mem,
 		.maxlen		= sizeof(sysctl_tcp_mem),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_doulongvec_minmax
 	},
 	{
 		.procname	= "tcp_wmem",
@@ -426,7 +428,9 @@ static struct ctl_table ipv4_table[] = {
 		.data		= &sysctl_tcp_adv_win_scale,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_adv_win_scale_min,
+		.extra2		= &tcp_adv_win_scale_max,
 	},
 	{
 		.procname	= "tcp_tw_reuse",
@@ -602,8 +606,7 @@ static struct ctl_table ipv4_table[] = {
 		.data		= &sysctl_udp_mem,
 		.maxlen		= sizeof(sysctl_udp_mem),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "udp_rmem_min",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1664a0590bb..f15c36a706e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,7 +282,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
-int sysctl_tcp_mem[3] __read_mostly;
+long sysctl_tcp_mem[3] __read_mostly;
 int sysctl_tcp_wmem[3] __read_mostly;
 int sysctl_tcp_rmem[3] __read_mostly;
 
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
-atomic_t tcp_memory_allocated;	/* Current allocated memory. */
+atomic_long_t tcp_memory_allocated;	/* Current allocated memory. */
 EXPORT_SYMBOL(tcp_memory_allocated);
 
 /*
@@ -2246,7 +2246,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		/* Values greater than interface MTU won't take effect. However
 		 * at the point when this call is done we typically don't yet
 		 * know which interface is going to be used */
-		if (val < 8 || val > MAX_TCP_WINDOW) {
+		if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
 			err = -EINVAL;
 			break;
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3357f69e353..6d8ab1c4efc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -259,8 +259,11 @@ static void tcp_fixup_sndbuf(struct sock *sk)
 	int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 +
 		     sizeof(struct sk_buff);
 
-	if (sk->sk_sndbuf < 3 * sndmem)
-		sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]);
+	if (sk->sk_sndbuf < 3 * sndmem) {
+		sk->sk_sndbuf = 3 * sndmem;
+		if (sk->sk_sndbuf > sysctl_tcp_wmem[2])
+			sk->sk_sndbuf = sysctl_tcp_wmem[2];
+	}
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -396,7 +399,7 @@ static void tcp_clamp_window(struct sock *sk)
 	if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_memory_pressure &&
-	    atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+	    atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
 		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
 				    sysctl_tcp_rmem[2]);
 	}
@@ -4861,7 +4864,7 @@ static int tcp_should_expand_sndbuf(struct sock *sk)
 		return 0;
 
 	/* If we are under soft global TCP memory pressure, do not expand.  */
-	if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+	if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
 		return 0;
 
 	/* If we filled the congestion window, do not expand.  */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f8527d4168..e13da6de1fc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -415,6 +415,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		    !icsk->icsk_backoff)
 			break;
 
+		if (sock_owned_by_user(sk))
+			break;
+
 		icsk->icsk_backoff--;
 		inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) <<
 					 icsk->icsk_backoff;
@@ -429,11 +432,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (remaining) {
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 						  remaining, TCP_RTO_MAX);
-		} else if (sock_owned_by_user(sk)) {
-			/* RTO revert clocked out retransmission,
-			 * but socket is locked. Will defer. */
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-						  HZ/20, TCP_RTO_MAX);
 		} else {
 			/* RTO revert clocked out retransmission.
 			 * Will retransmit now */
@@ -2045,7 +2043,9 @@ get_req:
 	}
 get_sk:
 	sk_nulls_for_each_from(sk, node) {
-		if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		if (sk->sk_family == st->family) {
 			cur = sk;
 			goto out;
 		}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 43cf901d765..a66735f7596 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -347,7 +347,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		 * socket up.  We've got bigger problems than
 		 * non-graceful socket closings.
 		 */
-		LIMIT_NETDEBUG(KERN_INFO "TCP: time wait bucket table overflow\n");
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW);
 	}
 
 	tcp_update_metrics(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 05b1ecf3676..61c2463e275 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -231,11 +231,10 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		/* when initializing use the value from init_rcv_wnd
 		 * rather than the default from above
 		 */
-		if (init_rcv_wnd &&
-		    (*rcv_wnd > init_rcv_wnd * mss))
-			*rcv_wnd = init_rcv_wnd * mss;
-		else if (*rcv_wnd > init_cwnd * mss)
-			*rcv_wnd = init_cwnd * mss;
+		if (init_rcv_wnd)
+			*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
+		else
+			*rcv_wnd = min(*rcv_wnd, init_cwnd * mss);
 	}
 
 	/* Set the clamp no higher than max representable value */
@@ -386,27 +385,30 @@ struct tcp_out_options {
  */
 static u8 tcp_cookie_size_check(u8 desired)
 {
-	if (desired > 0) {
+	int cookie_size;
+
+	if (desired > 0)
 		/* previously specified */
 		return desired;
-	}
-	if (sysctl_tcp_cookie_size <= 0) {
+
+	cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size);
+	if (cookie_size <= 0)
 		/* no default specified */
 		return 0;
-	}
-	if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) {
+
+	if (cookie_size <= TCP_COOKIE_MIN)
 		/* value too small, specify minimum */
 		return TCP_COOKIE_MIN;
-	}
-	if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) {
+
+	if (cookie_size >= TCP_COOKIE_MAX)
 		/* value too large, specify maximum */
 		return TCP_COOKIE_MAX;
-	}
-	if (0x1 & sysctl_tcp_cookie_size) {
+
+	if (cookie_size & 1)
 		/* 8-bit multiple, illegal, fix it */
-		return (u8)(sysctl_tcp_cookie_size + 0x1);
-	}
-	return (u8)sysctl_tcp_cookie_size;
+		cookie_size++;
+
+	return (u8)cookie_size;
 }
 
 /* Write previously computed TCP options to the packet.
@@ -1513,6 +1515,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 send_win, cong_win, limit, in_flight;
+	int win_divisor;
 
 	if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN)
 		goto send_now;
@@ -1544,13 +1547,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 	if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
 		goto send_now;
 
-	if (sysctl_tcp_tso_win_divisor) {
+	win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
+	if (win_divisor) {
 		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
 
 		/* If at least some fraction of a window is available,
 		 * just use it.
 		 */
-		chunk /= sysctl_tcp_tso_win_divisor;
+		chunk /= win_divisor;
 		if (limit >= chunk)
 			goto send_now;
 	} else {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 28cb2d733a3..5e0a3a582a5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -110,7 +110,7 @@
 struct udp_table udp_table __read_mostly;
 EXPORT_SYMBOL(udp_table);
 
-int sysctl_udp_mem[3] __read_mostly;
+long sysctl_udp_mem[3] __read_mostly;
 EXPORT_SYMBOL(sysctl_udp_mem);
 
 int sysctl_udp_rmem_min __read_mostly;
@@ -119,7 +119,7 @@ EXPORT_SYMBOL(sysctl_udp_rmem_min);
 int sysctl_udp_wmem_min __read_mostly;
 EXPORT_SYMBOL(sysctl_udp_wmem_min);
 
-atomic_t udp_memory_allocated;
+atomic_long_t udp_memory_allocated;
 EXPORT_SYMBOL(udp_memory_allocated);
 
 #define MAX_UDP_PORTS 65536