Merge tag 'v4.11-rc6' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 66 insertions, 64 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 42bfd08109dd..8f2133ffc2ff 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1083,7 +1083,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+	    skb->len < nlh->nlmsg_len ||
 	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbe7f72db9c1..b3cdeec85f1f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -198,6 +198,7 @@ static void ip_expire(unsigned long arg)
 	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
 
+	rcu_read_lock();
 	spin_lock(&qp->q.lock);
 
 	if (qp->q.flags & INET_FRAG_COMPLETE)
@@ -207,7 +208,7 @@ static void ip_expire(unsigned long arg)
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 
 	if (!inet_frag_evicting(&qp->q)) {
-		struct sk_buff *head = qp->q.fragments;
+		struct sk_buff *clone, *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
 
@@ -216,32 +217,40 @@ static void ip_expire(unsigned long arg)
 		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
 			goto out;
 
-		rcu_read_lock();
 		head->dev = dev_get_by_index_rcu(net, qp->iif);
 		if (!head->dev)
-			goto out_rcu_unlock;
+			goto out;
+
 
 		/* skb has no dst, perform route lookup again */
 		iph = ip_hdr(head);
 		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
 		if (err)
-			goto out_rcu_unlock;
+			goto out;
 
 		/* Only an end host needs to send an ICMP
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (frag_expire_skip_icmp(qp->user) &&
 		    (skb_rtable(head)->rt_type != RTN_LOCAL))
-			goto out_rcu_unlock;
+			goto out;
+
+		clone = skb_clone(head, GFP_ATOMIC);
 
 		/* Send an ICMP "Fragment Reassembly Timeout" message. */
-		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
-out_rcu_unlock:
-		rcu_read_unlock();
+		if (clone) {
+			spin_unlock(&qp->q.lock);
+			icmp_send(clone, ICMP_TIME_EXCEEDED,
+				  ICMP_EXC_FRAGTIME, 0);
+			consume_skb(clone);
+			goto out_rcu_unlock;
+		}
 	}
 out:
 	spin_unlock(&qp->q.lock);
+out_rcu_unlock:
+	rcu_read_unlock();
 	ipq_put(qp);
 }
 
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index fd9f34bbd740..dfb2ab2dd3c8 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -306,7 +306,7 @@ static void __init ic_close_devs(void)
 	while ((d = next)) {
 		next = d->next;
 		dev = d->dev;
-		if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) {
+		if (d != ic_dev && !netdev_uses_dsa(dev)) {
 			pr_debug("IP-Config: Downing %s\n", dev->name);
 			dev_change_flags(dev, d->flags);
 		}
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index bc1486f2c064..2e14ed11a35c 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -165,6 +165,10 @@ static unsigned int ipv4_conntrack_local(void *priv,
 	if (skb->len < sizeof(struct iphdr) ||
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
+
+	if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+		return NF_ACCEPT;
+
 	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
 }
 
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index f8aad03d674b..6f5e8d01b876 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -255,11 +255,6 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 	/* maniptype == SRC for postrouting. */
 	enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
 
-	/* We never see fragments: conntrack defrags on pre-routing
-	 * and local-out, and nf_nat_out protects post-routing.
-	 */
-	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
 	ct = nf_ct_get(skb, &ctinfo);
 	/* Can't track?  It's not due to stress, or conntrack would
 	 * have dropped it.  Hence it's the user's responsibilty to
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index c9b52c361da2..53e49f5011d3 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1260,16 +1260,6 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = {
 	.timeout	= 180,
 };
 
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
-	.me			= THIS_MODULE,
-	.help			= help,
-	.expect_policy		= &snmp_exp_policy,
-	.name			= "snmp",
-	.tuple.src.l3num	= AF_INET,
-	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
-	.tuple.dst.protonum	= IPPROTO_UDP,
-};
-
 static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
 	.me			= THIS_MODULE,
 	.help			= help,
@@ -1288,22 +1278,16 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
 
 static int __init nf_nat_snmp_basic_init(void)
 {
-	int ret = 0;
-
 	BUG_ON(nf_nat_snmp_hook != NULL);
 	RCU_INIT_POINTER(nf_nat_snmp_hook, help);
 
-	ret = nf_conntrack_helper_register(&snmp_trap_helper);
-	if (ret < 0) {
-		nf_conntrack_helper_unregister(&snmp_helper);
-		return ret;
-	}
-	return ret;
+	return nf_conntrack_helper_register(&snmp_trap_helper);
 }
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
 	RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+	synchronize_rcu();
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index a0ea8aad1bf1..f18677277119 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -26,10 +26,10 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
 	memset(&range, 0, sizeof(range));
 	range.flags = priv->flags;
 	if (priv->sreg_proto_min) {
-		range.min_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min];
-		range.max_proto.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 	}
 	regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
 						    &range, nft_out(pkt));
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index 1650ed23c15d..5120be1d3118 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -26,10 +26,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
 
 	memset(&mr, 0, sizeof(mr));
 	if (priv->sreg_proto_min) {
-		mr.range[0].min.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_min];
-		mr.range[0].max.all =
-			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		mr.range[0].min.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		mr.range[0].max.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
 		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2af6244b83e2..ccfbce13a633 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
 void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
+
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	write_lock_bh(&ping_table.lock);
 	if (sk_hashed(sk)) {
-		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
 		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-		write_unlock_bh(&ping_table.lock);
 	}
+	write_unlock_bh(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_unhash);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf4555581282..1e319a525d51 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2770,7 +2770,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 {
 	const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 now = tcp_time_stamp, intv;
+	u32 now, intv;
 	u64 rate64;
 	bool slow;
 	u32 rate;
@@ -2839,6 +2839,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_retrans = tp->retrans_out;
 	info->tcpi_fackets = tp->fackets_out;
 
+	now = tcp_time_stamp;
 	info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
 	info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
 	info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 39c393cc0fd3..2c1f59386a7b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -126,7 +126,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 #define REXMIT_LOST	1 /* retransmit packets marked lost */
 #define REXMIT_NEW	2 /* FRTO-style transmit of unsent/new packets */
 
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
+			     unsigned int len)
 {
 	static bool __once __read_mostly;
 
@@ -137,8 +138,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
 
 		rcu_read_lock();
 		dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
-		pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
-			dev ? dev->name : "Unknown driver");
+		if (!dev || len >= dev->mtu)
+			pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+				dev ? dev->name : "Unknown driver");
 		rcu_read_unlock();
 	}
 }
@@ -161,8 +163,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	if (len >= icsk->icsk_ack.rcv_mss) {
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
-		if (unlikely(icsk->icsk_ack.rcv_mss != len))
-			tcp_gro_dev_warn(sk, skb);
+		/* Account for possibly-removed options */
+		if (unlikely(len > icsk->icsk_ack.rcv_mss +
+				   MAX_TCP_OPTION_SPACE))
+			tcp_gro_dev_warn(sk, skb, len);
 	} else {
 		/* Otherwise, we make more careful check taking into account,
 		 * that SACKs block is variable.
@@ -874,22 +878,11 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 				  const int ts)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	if (metric > tp->reordering) {
-		int mib_idx;
+	int mib_idx;
 
+	if (metric > tp->reordering) {
 		tp->reordering = min(sysctl_tcp_max_reordering, metric);
 
-		/* This exciting event is worth to be remembered. 8) */
-		if (ts)
-			mib_idx = LINUX_MIB_TCPTSREORDER;
-		else if (tcp_is_reno(tp))
-			mib_idx = LINUX_MIB_TCPRENOREORDER;
-		else if (tcp_is_fack(tp))
-			mib_idx = LINUX_MIB_TCPFACKREORDER;
-		else
-			mib_idx = LINUX_MIB_TCPSACKREORDER;
-
-		NET_INC_STATS(sock_net(sk), mib_idx);
 #if FASTRETRANS_DEBUG > 1
 		pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
 			 tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
@@ -902,6 +895,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 	}
 
 	tp->rack.reord = 1;
+
+	/* This exciting event is worth to be remembered. 8) */
+	if (ts)
+		mib_idx = LINUX_MIB_TCPTSREORDER;
+	else if (tcp_is_reno(tp))
+		mib_idx = LINUX_MIB_TCPRENOREORDER;
+	else if (tcp_is_fack(tp))
+		mib_idx = LINUX_MIB_TCPFACKREORDER;
+	else
+		mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+	NET_INC_STATS(sock_net(sk), mib_idx);
 }
 
 /* This must be called before lost_out is incremented */
@@ -5541,6 +5546,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
+	icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5759,7 +5765,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 			tcp_enter_quickack_mode(sk);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7e16243cdb58..65c0f3d13eca 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -460,6 +460,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+		newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 4ecb38ae8504..d8acbd9f477a 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -12,7 +12,8 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 		/* Account for retransmits that are lost again */
 		TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
 		tp->retrans_out -= tcp_skb_pcount(skb);
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
+		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+			      tcp_skb_pcount(skb));
 	}
 }