Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "I'm sending a pull request of these lingering bug fixes for networking
  before the normal merge window material because some of this stuff I'd
  like to get to -stable ASAP"

 1) cxgb3 stopped working on 32-bit machines, fix from Ben Hutchings.

 2) Structures passed via netlink for netfilter logging are not fully
    initialized.  From Mathias Krause.

 3) Properly unlink upper openvswitch device during notifications, from
    Alexei Starovoitov.

 4) Fix race conditions involving access to the IP compression scratch
    buffer, from Michal Kubrecek.

 5) We don't handle the expiration of MTU information contained in ipv6
    routes sometimes, fix from Hannes Frederic Sowa.

 6) With Fast Open we can miscompute the TCP SYN/ACK RTT, from Yuchung
    Cheng.

 7) Don't take TCP RTT sample when an ACK doesn't acknowledge new data,
    also from Yuchung Cheng.

 8) The decreased IPSEC garbage collection threshold causes problems for
    some people, bump it back up.  From Steffen Klassert.

 9) Fix skb->truesize calculated by tcp_tso_segment(), from Eric
    Dumazet.

10) flow_dissector doesn't validate packet lengths sufficiently, from
    Jason Wang

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
  net/mlx4_core: Fix call to __mlx4_unregister_mac
  net: sctp: do not trigger BUG_ON in sctp_cmd_delete_tcb
  net: flow_dissector: fail on evil iph->ihl
  xfrm: Fix null pointer dereference when decoding sessions
  can: kvaser_usb: fix usb endpoints detection
  can: c_can: Fix RX message handling, handle lost message before EOB
  doc:net: Fix typo in Documentation/networking
  bgmac: don't update slot on skb alloc/dma mapping error
  ibm emac: Fix locking for enable/disable eob irq
  ibm emac: Don't call napi_complete if napi_reschedule failed
  virtio-net: correctly handle cpu hotplug notifier during resuming
  bridge: pass correct vlan id to multicast code
  net: x25: Fix dead URLs in Kconfig
  netfilter: xt_NFQUEUE: fix --queue-bypass regression
  xen-netback: use jiffies_64 value to calculate credit timeout
  cxgb3: Fix length calculation in write_ofld_wr() on 32-bit architectures
  bnx2x: Disable VF access on PF removal
  bnx2x: prevent FW assert on low mem during unload
  tcp: gso: fix truesize tracking
  xfrm: Increase the garbage collector threshold
  ...

6 files changed, 47 insertions, 25 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 85a4f21aac1a..59da7cde0724 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -271,6 +271,11 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
 	private = table->private;
+	/*
+	 * Ensure we load private-> members after we've fetched the base
+	 * pointer.
+	 */
+	smp_read_barrier_depends();
 	table_base = private->entries[smp_processor_id()];
 
 	e = get_entry(table_base, private->hook_entry[hook]);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index d23118d95ff9..718dfbd30cbe 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -327,6 +327,11 @@ ipt_do_table(struct sk_buff *skb,
 	addend = xt_write_recseq_begin();
 	private = table->private;
 	cpu        = smp_processor_id();
+	/*
+	 * Ensure we load private-> members after we've fetched the base
+	 * pointer.
+	 */
+	smp_read_barrier_depends();
 	table_base = private->entries[cpu];
 	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
 	stackptr   = per_cpu_ptr(private->stackptr, cpu);
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index cbc22158af49..9cb993cd224b 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net,
 	ub->qlen++;
 
 	pm = nlmsg_data(nlh);
+	memset(pm, 0, sizeof(*pm));
 
 	/* We might not have a timestamp, get one */
 	if (skb->tstamp.tv64 == 0)
@@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net,
 	}
 	else if (loginfo->prefix[0] != '\0')
 		strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix));
-	else
-		*(pm->prefix) = '\0';
 
 	if (in && in->hard_header_len > 0 &&
 	    skb->mac_header != skb->network_header &&
@@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net,
 
 	if (in)
 		strncpy(pm->indev_name, in->name, sizeof(pm->indev_name));
-	else
-		pm->indev_name[0] = '\0';
 
 	if (out)
 		strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
-	else
-		pm->outdev_name[0] = '\0';
 
 	/* copy_len <= skb->len, so can't fail. */
 	if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a16b01b537ba..068c8fb0d158 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2856,7 +2856,8 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * left edge of the send window.
 	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
 	 */
-	if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
+	if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
+	    flag & FLAG_ACKED)
 		seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
 
 	if (seq_rtt < 0)
@@ -2871,14 +2872,19 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 }
 
 /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
-static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
+static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	s32 seq_rtt = -1;
 
-	if (tp->lsndtime && !tp->total_retrans)
-		seq_rtt = tcp_time_stamp - tp->lsndtime;
-	tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
+	if (synack_stamp && !tp->total_retrans)
+		seq_rtt = tcp_time_stamp - synack_stamp;
+
+	/* If the ACK acks both the SYNACK and the (Fast Open'd) data packets
+	 * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack()
+	 */
+	if (!tp->srtt)
+		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
 }
 
 static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
@@ -2981,6 +2987,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	s32 seq_rtt = -1;
 	s32 ca_seq_rtt = -1;
 	ktime_t last_ackt = net_invalid_timestamp();
+	bool rtt_update;
 
 	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
@@ -3057,14 +3064,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
 		flag |= FLAG_SACK_RENEGING;
 
-	if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) ||
-	    (flag & FLAG_ACKED))
-		tcp_rearm_rto(sk);
+	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt);
 
 	if (flag & FLAG_ACKED) {
 		const struct tcp_congestion_ops *ca_ops
 			= inet_csk(sk)->icsk_ca_ops;
 
+		tcp_rearm_rto(sk);
 		if (unlikely(icsk->icsk_mtup.probe_size &&
 			     !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
 			tcp_mtup_probe_success(sk);
@@ -3103,6 +3109,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 			ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
 		}
+	} else if (skb && rtt_update && sack_rtt >= 0 &&
+		   sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) {
+		/* Do not re-arm RTO if the sack RTT is measured from data sent
+		 * after when the head was last (re)transmitted. Otherwise the
+		 * timeout may continue to extend in loss recovery.
+		 */
+		tcp_rearm_rto(sk);
 	}
 
 #if FASTRETRANS_DEBUG > 0
@@ -5587,6 +5600,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	struct request_sock *req;
 	int queued = 0;
 	bool acceptable;
+	u32 synack_stamp;
 
 	tp->rx_opt.saw_tstamp = 0;
 
@@ -5669,9 +5683,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		 * so release it.
 		 */
 		if (req) {
+			synack_stamp = tcp_rsk(req)->snt_synack;
 			tp->total_retrans = req->num_retrans;
 			reqsk_fastopen_remove(sk, req, false);
 		} else {
+			synack_stamp = tp->lsndtime;
 			/* Make sure socket is routed, for correct metrics. */
 			icsk->icsk_af_ops->rebuild_header(sk);
 			tcp_init_congestion_control(sk);
@@ -5694,7 +5710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
 		tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
 		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
-		tcp_synack_rtt_meas(sk, req);
+		tcp_synack_rtt_meas(sk, synack_stamp);
 
 		if (tp->rx_opt.tstamp_ok)
 			tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 3a7525e6c086..533c58a5cfb7 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -18,6 +18,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 				netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int sum_truesize = 0;
 	struct tcphdr *th;
 	unsigned int thlen;
 	unsigned int seq;
@@ -102,13 +103,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 		if (copy_destructor) {
 			skb->destructor = gso_skb->destructor;
 			skb->sk = gso_skb->sk;
-			/* {tcp|sock}_wfree() use exact truesize accounting :
-			 * sum(skb->truesize) MUST be exactly be gso_skb->truesize
-			 * So we account mss bytes of 'true size' for each segment.
-			 * The last segment will contain the remaining.
-			 */
-			skb->truesize = mss;
-			gso_skb->truesize -= mss;
+			sum_truesize += skb->truesize;
 		}
 		skb = skb->next;
 		th = tcp_hdr(skb);
@@ -125,7 +120,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 	if (copy_destructor) {
 		swap(gso_skb->sk, skb->sk);
 		swap(gso_skb->destructor, skb->destructor);
-		swap(gso_skb->truesize, skb->truesize);
+		sum_truesize += skb->truesize;
+		atomic_add(sum_truesize - gso_skb->truesize,
+			   &skb->sk->sk_wmem_alloc);
 	}
 
 	delta = htonl(oldlen + (skb_tail_pointer(skb) -
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index ccde54248c8c..e1a63930a967 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -104,10 +104,14 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 	const struct iphdr *iph = ip_hdr(skb);
 	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
+	int oif = 0;
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl4, 0, sizeof(struct flowi4));
 	fl4->flowi4_mark = skb->mark;
-	fl4->flowi4_oif = skb_dst(skb)->dev->ifindex;
+	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
 
 	if (!ip_is_fragment(iph)) {
 		switch (iph->protocol) {
@@ -236,7 +240,7 @@ static struct dst_ops xfrm4_dst_ops = {
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
 	.local_out =		__ip_local_out,
-	.gc_thresh =		1024,
+	.gc_thresh =		32768,
 };
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {