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

Pull networking fixes from David Miller:

 1) Use an appropriate TSQ pacing shift in mac80211, from Toke
    Høiland-Jørgensen.

 2) Just like ipv4's ip_route_me_harder(), we have to use skb_to_full_sk
    in ip6_route_me_harder, from Eric Dumazet.

 3) Fix several shutdown races and similar other problems in l2tp, from
    James Chapman.

 4) Handle missing XDP flush properly in tuntap, for real this time.
    From Jason Wang.

 5) Out-of-bounds access in powerpc ebpf tailcalls, from Daniel
    Borkmann.

 6) Fix phy_resume() locking, from Andrew Lunn.

 7) IFLA_MTU values are ignored on newlink for some tunnel types, fix
    from Xin Long.

 8) Revert F-RTO middle box workarounds, they only handle one dimension
    of the problem. From Yuchung Cheng.

 9) Fix socket refcounting in RDS, from Ka-Cheong Poon.

10) Don't allow ppp unit registration to an unregistered channel, from
    Guillaume Nault.

11) Various hv_netvsc fixes from Stephen Hemminger.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (98 commits)
  hv_netvsc: propagate rx filters to VF
  hv_netvsc: filter multicast/broadcast
  hv_netvsc: defer queue selection to VF
  hv_netvsc: use napi_schedule_irqoff
  hv_netvsc: fix race in napi poll when rescheduling
  hv_netvsc: cancel subchannel setup before halting device
  hv_netvsc: fix error unwind handling if vmbus_open fails
  hv_netvsc: only wake transmit queue if link is up
  hv_netvsc: avoid retry on send during shutdown
  virtio-net: re enable XDP_REDIRECT for mergeable buffer
  ppp: prevent unregistered channels from connecting to PPP units
  tc-testing: skbmod: fix match value of ethertype
  mlxsw: spectrum_switchdev: Check success of FDB add operation
  net: make skb_gso_*_seglen functions private
  net: xfrm: use skb_gso_validate_network_len() to check gso sizes
  net: sched: tbf: handle GSO_BY_FRAGS case in enqueue
  net: rename skb_gso_validate_mtu -> skb_gso_validate_network_len
  rds: Incorrect reference counting in TCP socket creation
  net: ethtool: don't ignore return from driver get_fecparam method
  vrf: check forwarding on the original netdevice when generating ICMP dest unreachable
  ...

5 files changed, 77 insertions, 166 deletions

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 194a7483bb93..83421c6f0bef 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -136,51 +136,6 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
 
 }
 
-/* Lookup the tunnel socket, possibly involving the fs code if the socket is
- * owned by userspace.  A struct sock returned from this function must be
- * released using l2tp_tunnel_sock_put once you're done with it.
- */
-static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
-{
-	int err = 0;
-	struct socket *sock = NULL;
-	struct sock *sk = NULL;
-
-	if (!tunnel)
-		goto out;
-
-	if (tunnel->fd >= 0) {
-		/* Socket is owned by userspace, who might be in the process
-		 * of closing it.  Look the socket up using the fd to ensure
-		 * consistency.
-		 */
-		sock = sockfd_lookup(tunnel->fd, &err);
-		if (sock)
-			sk = sock->sk;
-	} else {
-		/* Socket is owned by kernelspace */
-		sk = tunnel->sock;
-		sock_hold(sk);
-	}
-
-out:
-	return sk;
-}
-
-/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */
-static void l2tp_tunnel_sock_put(struct sock *sk)
-{
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
-	if (tunnel) {
-		if (tunnel->fd >= 0) {
-			/* Socket is owned by userspace */
-			sockfd_put(sk->sk_socket);
-		}
-		sock_put(sk);
-	}
-	sock_put(sk);
-}
-
 /* Session hash list.
  * The session_id SHOULD be random according to RFC2661, but several
  * L2TP implementations (Cisco and Microsoft) use incrementing
@@ -193,6 +148,13 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
 	return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)];
 }
 
+void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
+{
+	sock_put(tunnel->sock);
+	/* the tunnel is freed in the socket destructor */
+}
+EXPORT_SYMBOL(l2tp_tunnel_free);
+
 /* Lookup a tunnel. A new reference is held on the returned tunnel. */
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 {
@@ -345,13 +307,11 @@ int l2tp_session_register(struct l2tp_session *session,
 			}
 
 		l2tp_tunnel_inc_refcount(tunnel);
-		sock_hold(tunnel->sock);
 		hlist_add_head_rcu(&session->global_hlist, g_head);
 
 		spin_unlock_bh(&pn->l2tp_session_hlist_lock);
 	} else {
 		l2tp_tunnel_inc_refcount(tunnel);
-		sock_hold(tunnel->sock);
 	}
 
 	hlist_add_head(&session->hlist, head);
@@ -969,7 +929,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
-	tunnel = l2tp_sock_to_tunnel(sk);
+	tunnel = l2tp_tunnel(sk);
 	if (tunnel == NULL)
 		goto pass_up;
 
@@ -977,13 +937,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		 tunnel->name, skb->len);
 
 	if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook))
-		goto pass_up_put;
+		goto pass_up;
 
-	sock_put(sk);
 	return 0;
 
-pass_up_put:
-	sock_put(sk);
 pass_up:
 	return 1;
 }
@@ -1207,14 +1164,12 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
 static void l2tp_tunnel_destruct(struct sock *sk)
 {
 	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
-	struct l2tp_net *pn;
 
 	if (tunnel == NULL)
 		goto end;
 
 	l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name);
 
-
 	/* Disable udp encapsulation */
 	switch (tunnel->encap) {
 	case L2TP_ENCAPTYPE_UDP:
@@ -1231,18 +1186,11 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	sk->sk_destruct = tunnel->old_sk_destruct;
 	sk->sk_user_data = NULL;
 
-	/* Remove the tunnel struct from the tunnel list */
-	pn = l2tp_pernet(tunnel->l2tp_net);
-	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
-	list_del_rcu(&tunnel->list);
-	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-
-	tunnel->sock = NULL;
-	l2tp_tunnel_dec_refcount(tunnel);
-
 	/* Call the original destructor */
 	if (sk->sk_destruct)
 		(*sk->sk_destruct)(sk);
+
+	kfree_rcu(tunnel, rcu);
 end:
 	return;
 }
@@ -1303,49 +1251,43 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall);
 /* Tunnel socket destroy hook for UDP encapsulation */
 static void l2tp_udp_encap_destroy(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
-	if (tunnel) {
-		l2tp_tunnel_closeall(tunnel);
-		sock_put(sk);
-	}
+	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
+
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
 }
 
 /* Workqueue tunnel deletion function */
 static void l2tp_tunnel_del_work(struct work_struct *work)
 {
-	struct l2tp_tunnel *tunnel = NULL;
-	struct socket *sock = NULL;
-	struct sock *sk = NULL;
-
-	tunnel = container_of(work, struct l2tp_tunnel, del_work);
+	struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel,
+						  del_work);
+	struct sock *sk = tunnel->sock;
+	struct socket *sock = sk->sk_socket;
+	struct l2tp_net *pn;
 
 	l2tp_tunnel_closeall(tunnel);
 
-	sk = l2tp_tunnel_sock_lookup(tunnel);
-	if (!sk)
-		goto out;
-
-	sock = sk->sk_socket;
-
-	/* If the tunnel socket was created by userspace, then go through the
-	 * inet layer to shut the socket down, and let userspace close it.
-	 * Otherwise, if we created the socket directly within the kernel, use
+	/* If the tunnel socket was created within the kernel, use
 	 * the sk API to release it here.
-	 * In either case the tunnel resources are freed in the socket
-	 * destructor when the tunnel socket goes away.
 	 */
-	if (tunnel->fd >= 0) {
-		if (sock)
-			inet_shutdown(sock, 2);
-	} else {
+	if (tunnel->fd < 0) {
 		if (sock) {
 			kernel_sock_shutdown(sock, SHUT_RDWR);
 			sock_release(sock);
 		}
 	}
 
-	l2tp_tunnel_sock_put(sk);
-out:
+	/* Remove the tunnel struct from the tunnel list */
+	pn = l2tp_pernet(tunnel->l2tp_net);
+	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_del_rcu(&tunnel->list);
+	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+	/* drop initial ref */
+	l2tp_tunnel_dec_refcount(tunnel);
+
+	/* drop workqueue ref */
 	l2tp_tunnel_dec_refcount(tunnel);
 }
 
@@ -1598,13 +1540,22 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		sk->sk_user_data = tunnel;
 	}
 
+	/* Bump the reference count. The tunnel context is deleted
+	 * only when this drops to zero. A reference is also held on
+	 * the tunnel socket to ensure that it is not released while
+	 * the tunnel is extant. Must be done before sk_destruct is
+	 * set.
+	 */
+	refcount_set(&tunnel->ref_count, 1);
+	sock_hold(sk);
+	tunnel->sock = sk;
+	tunnel->fd = fd;
+
 	/* Hook on the tunnel socket destructor so that we can cleanup
 	 * if the tunnel socket goes away.
 	 */
 	tunnel->old_sk_destruct = sk->sk_destruct;
 	sk->sk_destruct = &l2tp_tunnel_destruct;
-	tunnel->sock = sk;
-	tunnel->fd = fd;
 	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
 
 	sk->sk_allocation = GFP_ATOMIC;
@@ -1614,11 +1565,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 
 	/* Add tunnel to our list */
 	INIT_LIST_HEAD(&tunnel->list);
-
-	/* Bump the reference count. The tunnel context is deleted
-	 * only when this drops to zero. Must be done before list insertion
-	 */
-	refcount_set(&tunnel->ref_count, 1);
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
@@ -1659,8 +1605,6 @@ void l2tp_session_free(struct l2tp_session *session)
 
 	if (tunnel) {
 		BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-		sock_put(tunnel->sock);
-		session->tunnel = NULL;
 		l2tp_tunnel_dec_refcount(tunnel);
 	}
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9bbee90e9963..a1aa9550f04e 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -214,27 +214,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 	return &session->priv[0];
 }
 
-static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk)
-{
-	struct l2tp_tunnel *tunnel;
-
-	if (sk == NULL)
-		return NULL;
-
-	sock_hold(sk);
-	tunnel = (struct l2tp_tunnel *)(sk->sk_user_data);
-	if (tunnel == NULL) {
-		sock_put(sk);
-		goto out;
-	}
-
-	BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-
-out:
-	return tunnel;
-}
-
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 struct l2tp_session *l2tp_session_get(const struct net *net,
 				      struct l2tp_tunnel *tunnel,
@@ -283,7 +264,7 @@ static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel)
 static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel)
 {
 	if (refcount_dec_and_test(&tunnel->ref_count))
-		kfree_rcu(tunnel, rcu);
+		l2tp_tunnel_free(tunnel);
 }
 
 /* Session reference counts. Incremented when code obtains a reference
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ff61124fdf59..3428fba6f2b7 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -234,17 +234,13 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 static void l2tp_ip_destroy_sock(struct sock *sk)
 {
 	struct sk_buff *skb;
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel = sk->sk_user_data;
 
 	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
 		kfree_skb(skb);
 
-	if (tunnel) {
-		l2tp_tunnel_closeall(tunnel);
-		sock_put(sk);
-	}
-
-	sk_refcnt_debug_dec(sk);
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
 }
 
 static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 192344688c06..6f009eaa5fbe 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -248,16 +248,14 @@ static void l2tp_ip6_close(struct sock *sk, long timeout)
 
 static void l2tp_ip6_destroy_sock(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel = sk->sk_user_data;
 
 	lock_sock(sk);
 	ip6_flush_pending_frames(sk);
 	release_sock(sk);
 
-	if (tunnel) {
-		l2tp_tunnel_closeall(tunnel);
-		sock_put(sk);
-	}
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
 
 	inet6_destroy_sock(sk);
 }
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 59f246d7b290..3b02f24ea9ec 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -416,20 +416,28 @@ abort:
  * Session (and tunnel control) socket create/destroy.
  *****************************************************************************/
 
+static void pppol2tp_put_sk(struct rcu_head *head)
+{
+	struct pppol2tp_session *ps;
+
+	ps = container_of(head, typeof(*ps), rcu);
+	sock_put(ps->__sk);
+}
+
 /* Called by l2tp_core when a session socket is being closed.
  */
 static void pppol2tp_session_close(struct l2tp_session *session)
 {
-	struct sock *sk;
-
-	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+	struct pppol2tp_session *ps;
 
-	sk = pppol2tp_session_get_sock(session);
-	if (sk) {
-		if (sk->sk_socket)
-			inet_shutdown(sk->sk_socket, SEND_SHUTDOWN);
-		sock_put(sk);
-	}
+	ps = l2tp_session_priv(session);
+	mutex_lock(&ps->sk_lock);
+	ps->__sk = rcu_dereference_protected(ps->sk,
+					     lockdep_is_held(&ps->sk_lock));
+	RCU_INIT_POINTER(ps->sk, NULL);
+	if (ps->__sk)
+		call_rcu(&ps->rcu, pppol2tp_put_sk);
+	mutex_unlock(&ps->sk_lock);
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -449,14 +457,6 @@ static void pppol2tp_session_destruct(struct sock *sk)
 	}
 }
 
-static void pppol2tp_put_sk(struct rcu_head *head)
-{
-	struct pppol2tp_session *ps;
-
-	ps = container_of(head, typeof(*ps), rcu);
-	sock_put(ps->__sk);
-}
-
 /* Called when the PPPoX socket (session) is closed.
  */
 static int pppol2tp_release(struct socket *sock)
@@ -480,26 +480,17 @@ static int pppol2tp_release(struct socket *sock)
 	sock_orphan(sk);
 	sock->sk = NULL;
 
+	/* If the socket is associated with a session,
+	 * l2tp_session_delete will call pppol2tp_session_close which
+	 * will drop the session's ref on the socket.
+	 */
 	session = pppol2tp_sock_to_session(sk);
-
-	if (session != NULL) {
-		struct pppol2tp_session *ps;
-
+	if (session) {
 		l2tp_session_delete(session);
-
-		ps = l2tp_session_priv(session);
-		mutex_lock(&ps->sk_lock);
-		ps->__sk = rcu_dereference_protected(ps->sk,
-						     lockdep_is_held(&ps->sk_lock));
-		RCU_INIT_POINTER(ps->sk, NULL);
-		mutex_unlock(&ps->sk_lock);
-		call_rcu(&ps->rcu, pppol2tp_put_sk);
-
-		/* Rely on the sock_put() call at the end of the function for
-		 * dropping the reference held by pppol2tp_sock_to_session().
-		 * The last reference will be dropped by pppol2tp_put_sk().
-		 */
+		/* drop the ref obtained by pppol2tp_sock_to_session */
+		sock_put(sk);
 	}
+
 	release_sock(sk);
 
 	/* This will delete the session context via
@@ -796,6 +787,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 out_no_ppp:
 	/* This is how we get the session context from the socket. */
+	sock_hold(sk);
 	sk->sk_user_data = session;
 	rcu_assign_pointer(ps->sk, sk);
 	mutex_unlock(&ps->sk_lock);