Merge branch 'linus' into x86/apic-cleanups

Conflicts:
	arch/x86/include/asm/io_apic.h

Merge reason: Resolve the conflict, update to a more recent -rc base

Signed-off-by: Ingo Molnar <mingo@elte.hu>

13 files changed, 61 insertions, 35 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eb6f69a8f27a..c19c1f739fba 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -163,13 +163,19 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 				.daddr = addr
 			}
 		},
-		.flags = FLOWI_FLAG_MATCH_ANY_IIF
 	};
 	struct fib_result res = { 0 };
 	struct net_device *dev = NULL;
+	struct fib_table *local_table;
+
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+	res.r = NULL;
+#endif
 
 	rcu_read_lock();
-	if (fib_lookup(net, &fl, &res)) {
+	local_table = fib_get_table(net, RT_TABLE_LOCAL);
+	if (!local_table ||
+	    fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) {
 		rcu_read_unlock();
 		return NULL;
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 200eb538fbb3..0f280348e0fd 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 96bc7f9475a3..e5d1a44bcbdf 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/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 1b344f30b463..3c0369a3a663 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 1b48eb1ed453..b14ec7d03b6e 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -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/route.c b/net/ipv4/route.c
index 987bf9adb318..93bfd95584f4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2585,9 +2585,10 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 			goto out;
 
 		/* RACE: Check return value of inet_select_addr instead. */
-		if (rcu_dereference(dev_out->ip_ptr) == NULL)
-			goto out;	/* Wrong error code */
-
+		if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
+			err = -ENETUNREACH;
+			goto out;
+		}
 		if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
 		    ipv4_is_lbcast(oldflp->fl4_dst)) {
 			if (!fl.fl4_src)
@@ -2648,8 +2649,12 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 	}
 
 	if (res.type == RTN_LOCAL) {
-		if (!fl.fl4_src)
-			fl.fl4_src = fl.fl4_dst;
+		if (!fl.fl4_src) {
+			if (res.fi->fib_prefsrc)
+				fl.fl4_src = res.fi->fib_prefsrc;
+			else
+				fl.fl4_src = fl.fl4_dst;
+		}
 		dev_out = net->loopback_dev;
 		fl.oif = dev_out->ifindex;
 		res.fi = NULL;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e91911d7aae2..1b4ec21497a4 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])
@@ -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",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 081419969485..f15c36a706ec 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -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 < 64 || val > MAX_TCP_WINDOW) {
+		if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
 			err = -EINVAL;
 			break;
 		}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 69ccbc1dde9c..d978bb2f748b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2030,7 +2030,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 get_req:
 			req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
 		}
-		sk	  = sk_next(st->syn_wait_sk);
+		sk	  = sk_nulls_next(st->syn_wait_sk);
 		st->state = TCP_SEQ_STATE_LISTENING;
 		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 	} else {
@@ -2039,11 +2039,13 @@ get_req:
 		if (reqsk_queue_len(&icsk->icsk_accept_queue))
 			goto start_req;
 		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
-		sk = sk_next(sk);
+		sk = sk_nulls_next(sk);
 	}
 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 43cf901d7659..a66735f75963 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 05b1ecf36763..61c2463e2753 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 5e0a3a582a59..2d3ded4d0786 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1899,6 +1899,7 @@ struct proto udp_prot = {
 	.compat_setsockopt = compat_udp_setsockopt,
 	.compat_getsockopt = compat_udp_getsockopt,
 #endif
+	.clear_sk	   = sk_prot_clear_portaddr_nulls,
 };
 EXPORT_SYMBOL(udp_prot);
 
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index ab76aa928fa9..aee9963f7f5a 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -57,6 +57,7 @@ struct proto 	udplite_prot = {
 	.compat_setsockopt = compat_udp_setsockopt,
 	.compat_getsockopt = compat_udp_getsockopt,
 #endif
+	.clear_sk	   = sk_prot_clear_portaddr_nulls,
 };
 EXPORT_SYMBOL(udplite_prot);