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

Pull networking fixes from David Miller:1) Use after free in __dev_map_entry_free(), from Eric Dumazet.

 1) Use after free in __dev_map_entry_free(), from Eric Dumazet.

 2) Fix TCP retransmission timestamps on passive Fast Open, from Yuchung
    Cheng.

 3) Orphan NFC, we'll take the patches directly into my tree. From
    Johannes Berg.

 4) We can't recycle cloned TCP skbs, from Eric Dumazet.

 5) Some flow dissector bpf test fixes, from Stanislav Fomichev.

 6) Fix RCU marking and warnings in rhashtable, from Herbert Xu.

 7) Fix some potential fib6 leaks, from Eric Dumazet.

 8) Fix a _decode_session4 uninitialized memory read bug fix that got
    lost in a merge. From Florian Westphal.

 9) Fix ipv6 source address routing wrt. exception route entries, from
    Wei Wang.

10) The netdev_xmit_more() conversion was not done %100 properly in mlx5
    driver, fix from Tariq Toukan.

11) Clean up botched merge on netfilter kselftest, from Florian
    Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (74 commits)
  of_net: fix of_get_mac_address retval if compiled without CONFIG_OF
  net: fix kernel-doc warnings for socket.c
  net: Treat sock->sk_drops as an unsigned int when printing
  kselftests: netfilter: fix leftover net/net-next merge conflict
  mlxsw: core: Prevent reading unsupported slave address from SFP EEPROM
  mlxsw: core: Prevent QSFP module initialization for old hardware
  vsock/virtio: Initialize core virtio vsock before registering the driver
  net/mlx5e: Fix possible modify header actions memory leak
  net/mlx5e: Fix no rewrite fields with the same match
  net/mlx5e: Additional check for flow destination comparison
  net/mlx5e: Add missing ethtool driver info for representors
  net/mlx5e: Fix number of vports for ingress ACL configuration
  net/mlx5e: Fix ethtool rxfh commands when CONFIG_MLX5_EN_RXNFC is disabled
  net/mlx5e: Fix wrong xmit_more application
  net/mlx5: Fix peer pf disable hca command
  net/mlx5: E-Switch, Correct type to u16 for vport_num and int for vport_index
  net/mlx5: Add meaningful return codes to status_to_err function
  net/mlx5: Imply MLXFW in mlx5_core
  Revert "tipc: fix modprobe tipc failed after switch order of device registration"
  vsock/virtio: free packets during the socket release
  ...

1 files changed, 77 insertions, 31 deletions

diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index a827547aa102..982a8dc49e03 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -35,6 +35,9 @@
 /* The MTU is 16KB per the host side's design */
 #define HVS_MTU_SIZE		(1024 * 16)
 
+/* How long to wait for graceful shutdown of a connection */
+#define HVS_CLOSE_TIMEOUT (8 * HZ)
+
 struct vmpipe_proto_header {
 	u32 pkt_type;
 	u32 data_size;
@@ -305,19 +308,32 @@ static void hvs_channel_cb(void *ctx)
 		sk->sk_write_space(sk);
 }
 
-static void hvs_close_connection(struct vmbus_channel *chan)
+static void hvs_do_close_lock_held(struct vsock_sock *vsk,
+				   bool cancel_timeout)
 {
-	struct sock *sk = get_per_channel_state(chan);
-	struct vsock_sock *vsk = vsock_sk(sk);
-
-	lock_sock(sk);
+	struct sock *sk = sk_vsock(vsk);
 
-	sk->sk_state = TCP_CLOSE;
 	sock_set_flag(sk, SOCK_DONE);
-	vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN;
-
+	vsk->peer_shutdown = SHUTDOWN_MASK;
+	if (vsock_stream_has_data(vsk) <= 0)
+		sk->sk_state = TCP_CLOSING;
 	sk->sk_state_change(sk);
+	if (vsk->close_work_scheduled &&
+	    (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
+		vsk->close_work_scheduled = false;
+		vsock_remove_sock(vsk);
 
+		/* Release the reference taken while scheduling the timeout */
+		sock_put(sk);
+	}
+}
+
+static void hvs_close_connection(struct vmbus_channel *chan)
+{
+	struct sock *sk = get_per_channel_state(chan);
+
+	lock_sock(sk);
+	hvs_do_close_lock_held(vsock_sk(sk), true);
 	release_sock(sk);
 }
 
@@ -452,50 +468,80 @@ static int hvs_connect(struct vsock_sock *vsk)
 	return vmbus_send_tl_connect_request(&h->vm_srv_id, &h->host_srv_id);
 }
 
+static void hvs_shutdown_lock_held(struct hvsock *hvs, int mode)
+{
+	struct vmpipe_proto_header hdr;
+
+	if (hvs->fin_sent || !hvs->chan)
+		return;
+
+	/* It can't fail: see hvs_channel_writable_bytes(). */
+	(void)hvs_send_data(hvs->chan, (struct hvs_send_buf *)&hdr, 0);
+	hvs->fin_sent = true;
+}
+
 static int hvs_shutdown(struct vsock_sock *vsk, int mode)
 {
 	struct sock *sk = sk_vsock(vsk);
-	struct vmpipe_proto_header hdr;
-	struct hvs_send_buf *send_buf;
-	struct hvsock *hvs;
 
 	if (!(mode & SEND_SHUTDOWN))
 		return 0;
 
 	lock_sock(sk);
+	hvs_shutdown_lock_held(vsk->trans, mode);
+	release_sock(sk);
+	return 0;
+}
 
-	hvs = vsk->trans;
-	if (hvs->fin_sent)
-		goto out;
-
-	send_buf = (struct hvs_send_buf *)&hdr;
+static void hvs_close_timeout(struct work_struct *work)
+{
+	struct vsock_sock *vsk =
+		container_of(work, struct vsock_sock, close_work.work);
+	struct sock *sk = sk_vsock(vsk);
 
-	/* It can't fail: see hvs_channel_writable_bytes(). */
-	(void)hvs_send_data(hvs->chan, send_buf, 0);
+	sock_hold(sk);
+	lock_sock(sk);
+	if (!sock_flag(sk, SOCK_DONE))
+		hvs_do_close_lock_held(vsk, false);
 
-	hvs->fin_sent = true;
-out:
+	vsk->close_work_scheduled = false;
 	release_sock(sk);
-	return 0;
+	sock_put(sk);
 }
 
-static void hvs_release(struct vsock_sock *vsk)
+/* Returns true, if it is safe to remove socket; false otherwise */
+static bool hvs_close_lock_held(struct vsock_sock *vsk)
 {
 	struct sock *sk = sk_vsock(vsk);
-	struct hvsock *hvs = vsk->trans;
-	struct vmbus_channel *chan;
 
-	lock_sock(sk);
+	if (!(sk->sk_state == TCP_ESTABLISHED ||
+	      sk->sk_state == TCP_CLOSING))
+		return true;
 
-	sk->sk_state = TCP_CLOSING;
-	vsock_remove_sock(vsk);
+	if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
+		hvs_shutdown_lock_held(vsk->trans, SHUTDOWN_MASK);
 
-	release_sock(sk);
+	if (sock_flag(sk, SOCK_DONE))
+		return true;
 
-	chan = hvs->chan;
-	if (chan)
-		hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN);
+	/* This reference will be dropped by the delayed close routine */
+	sock_hold(sk);
+	INIT_DELAYED_WORK(&vsk->close_work, hvs_close_timeout);
+	vsk->close_work_scheduled = true;
+	schedule_delayed_work(&vsk->close_work, HVS_CLOSE_TIMEOUT);
+	return false;
+}
 
+static void hvs_release(struct vsock_sock *vsk)
+{
+	struct sock *sk = sk_vsock(vsk);
+	bool remove_sock;
+
+	lock_sock(sk);
+	remove_sock = hvs_close_lock_held(vsk);
+	release_sock(sk);
+	if (remove_sock)
+		vsock_remove_sock(vsk);
 }
 
 static void hvs_destruct(struct vsock_sock *vsk)