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

Pull networking fixes from David Miller:
 "First batch of fixes in the new merge window:

   1) Double dst_cache free in act_tunnel_key, from Wenxu.

   2) Avoid NULL deref in IN_DEV_MFORWARD() by failing early in the
      ip_route_input_rcu() path, from Paolo Abeni.

   3) Fix appletalk compile regression, from Arnd Bergmann.

   4) If SLAB objects reach the TCP sendpage method we are in serious
      trouble, so put a debugging check there. From Vasily Averin.

   5) Memory leak in hsr layer, from Mao Wenan.

   6) Only test GSO type on GSO packets, from Willem de Bruijn.

   7) Fix crash in xsk_diag_put_umem(), from Eric Dumazet.

   8) Fix VNIC mailbox length in nfp, from Dirk van der Merwe.

   9) Fix race in ipv4 route exception handling, from Xin Long.

  10) Missing DMA memory barrier in hns3 driver, from Jian Shen.

  11) Use after free in __tcf_chain_put(), from Vlad Buslov.

  12) Handle inet_csk_reqsk_queue_add() failures, from Guillaume Nault.

  13) Return value correction when ip_mc_may_pull() fails, from Eric
      Dumazet.

  14) Use after free in x25_device_event(), also from Eric"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (72 commits)
  gro_cells: make sure device is up in gro_cells_receive()
  vxlan: test dev->flags & IFF_UP before calling gro_cells_receive()
  net/x25: fix use-after-free in x25_device_event()
  isdn: mISDNinfineon: fix potential NULL pointer dereference
  net: hns3: fix to stop multiple HNS reset due to the AER changes
  ip: fix ip_mc_may_pull() return value
  net: keep refcount warning in reqsk_free()
  net: stmmac: Avoid one more sometimes uninitialized Clang warning
  net: dsa: mv88e6xxx: Set correct interface mode for CPU/DSA ports
  rxrpc: Fix client call queueing, waiting for channel
  tcp: handle inet_csk_reqsk_queue_add() failures
  net: ethernet: sun: Zero initialize class in default case in niu_add_ethtool_tcam_entry
  8139too : Add support for U.S. Robotics USR997901A 10/100 Cardbus NIC
  fou, fou6: avoid uninit-value in gue_err() and gue6_err()
  net: sched: fix potential use-after-free in __tcf_chain_put()
  vhost: silence an unused-variable warning
  vsock/virtio: fix kernel panic from virtio_transport_reset_no_sock
  connector: fix unsafe usage of ->real_parent
  vxlan: do not need BH again in vxlan_cleanup()
  net: hns3: add dma_rmb() for rx description
  ...

6 files changed, 39 insertions, 11 deletions

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 437070d1ffb1..79e98e21cdd7 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -1024,7 +1024,7 @@ static int gue_err(struct sk_buff *skb, u32 info)
 	int ret;
 
 	len = sizeof(struct udphdr) + sizeof(struct guehdr);
-	if (!pskb_may_pull(skb, len))
+	if (!pskb_may_pull(skb, transport_offset + len))
 		return -EINVAL;
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
@@ -1059,7 +1059,7 @@ static int gue_err(struct sk_buff *skb, u32 info)
 
 	optlen = guehdr->hlen << 2;
 
-	if (!pskb_may_pull(skb, len + optlen))
+	if (!pskb_may_pull(skb, transport_offset + len + optlen))
 		return -EINVAL;
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 2756fb725bf0..a5d8cad18ead 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -515,9 +515,10 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 		mtu = dst_mtu(&rt->dst) - dev->hard_header_len
 					- sizeof(struct iphdr) - tunnel_hlen;
 	else
-		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
-	skb_dst_update_pmtu(skb, mtu);
+	if (skb_valid_dst(skb))
+		skb_dst_update_pmtu(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
@@ -530,9 +531,11 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (skb->protocol == htons(ETH_P_IPV6)) {
-		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
+		struct rt6_info *rt6;
 		__be32 daddr;
 
+		rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) :
+					   NULL;
 		daddr = md ? dst : tunnel->parms.iph.daddr;
 
 		if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 738ff0a1a048..a5da63e5faa2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1303,6 +1303,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 		if (fnhe->fnhe_daddr == daddr) {
 			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
 				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			/* set fnhe_daddr to 0 to ensure it won't bind with
+			 * new dsts in rt_bind_exception().
+			 */
+			fnhe->fnhe_daddr = 0;
 			fnhe_flush_routes(fnhe);
 			kfree_rcu(fnhe, rcu);
 			break;
@@ -2149,12 +2153,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		int our = 0;
 		int err = -EINVAL;
 
-		if (in_dev)
-			our = ip_check_mc_rcu(in_dev, daddr, saddr,
-					      ip_hdr(skb)->protocol);
+		if (!in_dev)
+			return err;
+		our = ip_check_mc_rcu(in_dev, daddr, saddr,
+				      ip_hdr(skb)->protocol);
 
 		/* check l3 master if no match yet */
-		if ((!in_dev || !our) && netif_is_l3_slave(dev)) {
+		if (!our && netif_is_l3_slave(dev)) {
 			struct in_device *l3_in_dev;
 
 			l3_in_dev = __in_dev_get_rcu(skb->dev);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 606f868d9f3f..e531344611a0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 		refcount_set(&req->rsk_refcnt, 1);
 		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
-		inet_csk_reqsk_queue_add(sk, req, child);
+		if (!inet_csk_reqsk_queue_add(sk, req, child)) {
+			bh_unlock_sock(child);
+			sock_put(child);
+			child = NULL;
+			reqsk_put(req);
+		}
 	} else {
 		reqsk_free(req);
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ad07dd71063d..6baa6dc1b13b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -943,6 +943,10 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 	ssize_t copied;
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
+	if (IS_ENABLED(CONFIG_DEBUG_VM) &&
+	    WARN_ONCE(PageSlab(page), "page must not be a Slab one"))
+		return -EINVAL;
+
 	/* Wait for a connection to finish. One exception is TCP Fast Open
 	 * (passive side) where data is allowed to be sent before a connection
 	 * is fully established.
@@ -1933,6 +1937,11 @@ static int tcp_inq_hint(struct sock *sk)
 		inq = tp->rcv_nxt - tp->copied_seq;
 		release_sock(sk);
 	}
+	/* After receiving a FIN, tell the user-space to continue reading
+	 * by returning a non-zero inq.
+	 */
+	if (inq == 0 && sock_flag(sk, SOCK_DONE))
+		inq = 1;
 	return inq;
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4eb0c8ca3c60..5def3c48870e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6498,7 +6498,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
 				    &foc, TCP_SYNACK_FASTOPEN);
 		/* Add the child socket directly into the accept queue */
-		inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
+		if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
+			reqsk_fastopen_remove(fastopen_sk, req, false);
+			bh_unlock_sock(fastopen_sk);
+			sock_put(fastopen_sk);
+			reqsk_put(req);
+			goto drop;
+		}
 		sk->sk_data_ready(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);