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

Pull networking fixes from David Miller:

 1) Handle stations tied to AP_VLANs properly during mac80211 hw
    reconfig. From Manikanta Pubbisetty.

 2) Fix jump stack depth validation in nf_tables, from Taehee Yoo.

 3) Fix quota handling in aRFS flow expiration of mlx5 driver, from Eran
    Ben Elisha.

 4) Exit path handling fix in powerpc64 BPF JIT, from Daniel Borkmann.

 5) Use ptr_ring_consume_bh() in page pool code, from Tariq Toukan.

 6) Fix cached netdev name leak in nf_tables, from Florian Westphal.

 7) Fix memory leaks on chain rename, also from Florian Westphal.

 8) Several fixes to DCTCP congestion control ACK handling, from Yuchunk
    Cheng.

 9) Missing rcu_read_unlock() in CAIF protocol code, from Yue Haibing.

10) Fix link local address handling with VRF, from David Ahern.

11) Don't clobber 'err' on a successful call to __skb_linearize() in
    skb_segment(). From Eric Dumazet.

12) Fix vxlan fdb notification races, from Roopa Prabhu.

13) Hash UDP fragments consistently, from Paolo Abeni.

14) If TCP receives lots of out of order tiny packets, we do really
    silly stuff. Make the out-of-order queue ending more robust to this
    kind of behavior, from Eric Dumazet.

15) Don't leak netlink dump state in nf_tables, from Florian Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (76 commits)
  net: axienet: Fix double deregister of mdio
  qmi_wwan: fix interface number for DW5821e production firmware
  ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull
  bnx2x: Fix invalid memory access in rss hash config path.
  net/mlx4_core: Save the qpn from the input modifier in RST2INIT wrapper
  r8169: restore previous behavior to accept BIOS WoL settings
  cfg80211: never ignore user regulatory hint
  sock: fix sg page frag coalescing in sk_alloc_sg
  netfilter: nf_tables: move dumper state allocation into ->start
  tcp: add tcp_ooo_try_coalesce() helper
  tcp: call tcp_drop() from tcp_data_queue_ofo()
  tcp: detect malicious patterns in tcp_collapse_ofo_queue()
  tcp: avoid collapses in tcp_prune_queue() if possible
  tcp: free batches of packets in tcp_prune_ofo_queue()
  ip: hash fragments consistently
  ipv6: use fib6_info_hold_safe() when necessary
  can: xilinx_can: fix power management handling
  can: xilinx_can: fix incorrect clear of non-processed interrupts
  can: xilinx_can: fix RX overflow interrupt not being enabled
  can: xilinx_can: keep only 1-2 frames in TX FIFO to fix TX accounting
  ...

6 files changed, 100 insertions, 61 deletions

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b3c899a630a0..28fef7d15959 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1200,8 +1200,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	spin_lock_bh(&im->lock);
 	if (pmc) {
 		im->interface = pmc->interface;
-		im->sfmode = pmc->sfmode;
-		if (pmc->sfmode == MCAST_INCLUDE) {
+		if (im->sfmode == MCAST_INCLUDE) {
 			im->tomb = pmc->tomb;
 			im->sources = pmc->sources;
 			for (psf = im->sources; psf; psf = psf->sf_next)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..0e3edd25f881 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 64c76dcf7386..c0fe5ad996f2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
 	const struct iphdr *iph = ip_hdr(skb);
-	__be16 *ports = (__be16 *)skb_transport_header(skb);
+	__be16 *ports;
+	int end;
 
-	if (skb_transport_offset(skb) + 4 > (int)skb->len)
+	end = skb_transport_offset(skb) + 4;
+	if (end > 0 && !pskb_may_pull(skb, end))
 		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
+	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = iph->daddr;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5869f89ca656..8b637f9f23a2 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -129,24 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=0 to CE=1 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (!ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=0. */
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
+	if (!ca->ce_state) {
+		/* State has changed from CE=0 to CE=1, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -160,24 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=1 to CE=0 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=1. */
-		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
+	if (ca->ce_state) {
+		/* State has changed from CE=1 to CE=0, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8e5522c6833a..3bcd30a2ba06 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 		icsk->icsk_ack.quick = quickacks;
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
@@ -4357,6 +4358,23 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+	/* In case tcp_drop() is called later, update to->gso_segs */
+	if (res) {
+		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+	}
+	return res;
+}
+
 static void tcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -4480,8 +4498,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
-			     skb, &fragstolen)) {
+	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+				 skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4509,7 +4527,7 @@ coalesce_done:
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb);
+				tcp_drop(sk, skb);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4528,11 +4546,11 @@ coalesce_done:
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb1);
+				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1,
-					    skb, &fragstolen)) {
+		} else if (tcp_ooo_try_coalesce(sk, skb1,
+						skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
@@ -4901,6 +4919,7 @@ end:
 static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
 	u32 start, end;
 
@@ -4912,6 +4931,7 @@ new_range:
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
+	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
 		skb = skb_rb_next(skb);
@@ -4922,11 +4942,20 @@ new_range:
 		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
-			tcp_collapse(sk, NULL, &tp->out_of_order_queue,
-				     head, skb, start, end);
+			/* Do not attempt collapsing tiny skbs */
+			if (range_truesize != head->truesize ||
+			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+					     head, skb, start, end);
+			} else {
+				sum_tiny += range_truesize;
+				if (sum_tiny > sk->sk_rcvbuf >> 3)
+					return;
+			}
 			goto new_range;
 		}
 
+		range_truesize += skb->truesize;
 		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
 			start = TCP_SKB_CB(skb)->seq;
 		if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4941,6 +4970,7 @@ new_range:
  * 2) not add too big latencies if thousands of packets sit there.
  *    (But if application shrinks SO_RCVBUF, we could still end up
  *     freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
  *
  * Return true if queue has shrunk.
  */
@@ -4948,20 +4978,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct rb_node *node, *prev;
+	int goal;
 
 	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		return false;
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+	goal = sk->sk_rcvbuf >> 3;
 	node = &tp->ooo_last_skb->rbnode;
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
+		goal -= rb_to_skb(node)->truesize;
 		tcp_drop(sk, rb_to_skb(node));
-		sk_mem_reclaim(sk);
-		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-		    !tcp_under_memory_pressure(sk))
-			break;
+		if (!prev || goal <= 0) {
+			sk_mem_reclaim(sk);
+			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			    !tcp_under_memory_pressure(sk))
+				break;
+			goal = sk->sk_rcvbuf >> 3;
+		}
 		node = prev;
 	} while (node);
 	tp->ooo_last_skb = rb_to_skb(prev);
@@ -4996,6 +5032,9 @@ static int tcp_prune_queue(struct sock *sk)
 	else if (tcp_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
+	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+		return 0;
+
 	tcp_collapse_ofo_queue(sk);
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		tcp_collapse(sk, &sk->sk_receive_queue, NULL,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 00e5a300ddb9..c4172c1fb198 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return err;
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3571,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3604,9 +3615,14 @@ void tcp_send_ack(struct sock *sk)
 	skb_set_tcp_pure_ack(buff);
 
 	/* Send it off, this clears delayed acks for us. */
-	tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.