Merge tag 'nfs-for-4.3-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights include:

  Stable patches:
   - fix v4.2 SEEK on files over 2 gigs
   - Fix a layout segment reference leak when pNFS I/O falls back to inband I/O.
   - Fix recovery of recalled read delegations

  Bugfixes:
   - Fix a case where NFSv4 fails to send CLOSE after a server reboot
   - Fix sunrpc to wait for connections to complete before retrying
   - Fix sunrpc races between transport connect/disconnect and shutdown
   - Fix an infinite loop when layoutget fail with BAD_STATEID
   - nfs/filelayout: Fix NULL reference caused by double freeing of fh_array
   - Fix a bogus WARN_ON_ONCE() in O_DIRECT when layout commit_through_mds is set
   - Fix layoutreturn/close ordering issues"

* tag 'nfs-for-4.3-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS41: make close wait for layoutreturn
  NFS: Skip checking ds_cinfo.buckets when lseg's commit_through_mds is set
  NFSv4.x/pnfs: Don't try to recover stateids twice in layoutget
  NFSv4: Recovery of recalled read delegations is broken
  NFS: Fix an infinite loop when layoutget fail with BAD_STATEID
  NFS: Do cleanup before resetting pageio read/write to mds
  SUNRPC: xs_sock_mark_closed() does not need to trigger socket autoclose
  SUNRPC: Lock the transport layer on shutdown
  nfs/filelayout: Fix NULL reference caused by double freeing of fh_array
  SUNRPC: Ensure that we wait for connections to complete before retrying
  SUNRPC: drop null test before destroy functions
  nfs: fix v4.2 SEEK on files over 2 gigs
  SUNRPC: Fix races between socket connection and destroy code
  nfs: fix pg_test page count calculation
  Failing to send a CLOSE if file is opened WRONLY and server reboots on a 4.x mount

3 files changed, 21 insertions, 12 deletions

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 337ca851a350..f14f24ee9983 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -1092,14 +1092,10 @@ void
 rpc_destroy_mempool(void)
 {
 	rpciod_stop();
-	if (rpc_buffer_mempool)
-		mempool_destroy(rpc_buffer_mempool);
-	if (rpc_task_mempool)
-		mempool_destroy(rpc_task_mempool);
-	if (rpc_task_slabp)
-		kmem_cache_destroy(rpc_task_slabp);
-	if (rpc_buffer_slabp)
-		kmem_cache_destroy(rpc_buffer_slabp);
+	mempool_destroy(rpc_buffer_mempool);
+	mempool_destroy(rpc_task_mempool);
+	kmem_cache_destroy(rpc_task_slabp);
+	kmem_cache_destroy(rpc_buffer_slabp);
 	rpc_destroy_wait_queue(&delay_queue);
 }
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index ab5dd621ae0c..2e98f4a243e5 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -614,6 +614,7 @@ static void xprt_autoclose(struct work_struct *work)
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	xprt->ops->close(xprt);
 	xprt_release_write(xprt, NULL);
+	wake_up_bit(&xprt->state, XPRT_LOCKED);
 }
 
 /**
@@ -723,6 +724,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
 	xprt->ops->release_xprt(xprt, NULL);
 out:
 	spin_unlock_bh(&xprt->transport_lock);
+	wake_up_bit(&xprt->state, XPRT_LOCKED);
 }
 
 /**
@@ -1394,6 +1396,10 @@ out:
 static void xprt_destroy(struct rpc_xprt *xprt)
 {
 	dprintk("RPC:       destroying transport %p\n", xprt);
+
+	/* Exclude transport connect/disconnect handlers */
+	wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE);
+
 	del_timer_sync(&xprt->timer);
 
 	rpc_xprt_debugfs_unregister(xprt);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7be90bc1a7c2..1a85e0ed0b48 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -777,7 +777,6 @@ static void xs_sock_mark_closed(struct rpc_xprt *xprt)
 	xs_sock_reset_connection_flags(xprt);
 	/* Mark transport as closed and wake up all pending tasks */
 	xprt_disconnect_done(xprt);
-	xprt_force_disconnect(xprt);
 }
 
 /**
@@ -881,8 +880,11 @@ static void xs_xprt_free(struct rpc_xprt *xprt)
  */
 static void xs_destroy(struct rpc_xprt *xprt)
 {
+	struct sock_xprt *transport = container_of(xprt,
+			struct sock_xprt, xprt);
 	dprintk("RPC:       xs_destroy xprt %p\n", xprt);
 
+	cancel_delayed_work_sync(&transport->connect_worker);
 	xs_close(xprt);
 	xs_xprt_free(xprt);
 	module_put(THIS_MODULE);
@@ -1435,6 +1437,7 @@ out:
 static void xs_tcp_state_change(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
+	struct sock_xprt *transport;
 
 	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
@@ -1446,13 +1449,12 @@ static void xs_tcp_state_change(struct sock *sk)
 			sock_flag(sk, SOCK_ZAPPED),
 			sk->sk_shutdown);
 
+	transport = container_of(xprt, struct sock_xprt, xprt);
 	trace_rpc_socket_state_change(xprt, sk->sk_socket);
 	switch (sk->sk_state) {
 	case TCP_ESTABLISHED:
 		spin_lock(&xprt->transport_lock);
 		if (!xprt_test_and_set_connected(xprt)) {
-			struct sock_xprt *transport = container_of(xprt,
-					struct sock_xprt, xprt);
 
 			/* Reset TCP record info */
 			transport->tcp_offset = 0;
@@ -1461,6 +1463,8 @@ static void xs_tcp_state_change(struct sock *sk)
 			transport->tcp_flags =
 				TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;
 			xprt->connect_cookie++;
+			clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
+			xprt_clear_connecting(xprt);
 
 			xprt_wake_pending_tasks(xprt, -EAGAIN);
 		}
@@ -1496,6 +1500,9 @@ static void xs_tcp_state_change(struct sock *sk)
 		smp_mb__after_atomic();
 		break;
 	case TCP_CLOSE:
+		if (test_and_clear_bit(XPRT_SOCK_CONNECTING,
+					&transport->sock_state))
+			xprt_clear_connecting(xprt);
 		xs_sock_mark_closed(xprt);
 	}
  out:
@@ -2179,6 +2186,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 	/* Tell the socket layer to start connecting... */
 	xprt->stat.connect_count++;
 	xprt->stat.connect_start = jiffies;
+	set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
 	ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
 	switch (ret) {
 	case 0:
@@ -2240,7 +2248,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -EINPROGRESS:
 	case -EALREADY:
 		xprt_unlock_connect(xprt, transport);
-		xprt_clear_connecting(xprt);
 		return;
 	case -EINVAL:
 		/* Happens, for instance, if the user specified a link