Merge tag 'nfs-for-4.2-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable patches:
   - Fix a crash in the NFSv4 file locking code.
   - Fix an fsync() regression, where we were failing to retry I/O in
     some circumstances.
   - Fix an infinite loop in NFSv4.0 OPEN stateid recovery
   - Fix a memory leak when an attempted pnfs fails.
   - Fix a memory leak in the backchannel code
   - Large hostnames were not supported correctly in NFSv4.1
   - Fix a pNFS/flexfiles bug that was impeding error reporting on I/O.
   - Fix a couple of credential issues in pNFS/flexfiles

  Bugfixes + cleanups:
   - Open flag sanity checks in the NFSv4 atomic open codepath
   - More NFSv4 delegation related bugfixes
   - Various NFSv4.1 backchannel bugfixes and cleanups
   - Fix the NFS swap socket code
   - Various cleanups of the NFSv4 SETCLIENTID and EXCHANGE_ID code
   - Fix a UDP transport deadlock issue

  Features:
   - More RDMA client transport improvements
   - NFSv4.2 LAYOUTSTATS functionality for pnfs flexfiles"

* tag 'nfs-for-4.2-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (87 commits)
  nfs: Remove invalid tk_pid from debug message
  nfs: Remove invalid NFS_ATTR_FATTR_V4_REFERRAL checking in nfs4_get_rootfh
  nfs: Drop bad comment in nfs41_walk_client_list()
  nfs: Remove unneeded micro checking of CONFIG_PROC_FS
  nfs: Don't setting FILE_CREATED flags always
  nfs: Use remove_proc_subtree() instead remove_proc_entry()
  nfs: Remove unused argument in nfs_server_set_fsinfo()
  nfs: Fix a memory leak when meeting an unsupported state protect
  nfs: take extra reference to fl->fl_file when running a LOCKU operation
  NFSv4: When returning a delegation, don't reclaim an incompatible open mode.
  NFSv4.2: LAYOUTSTATS is optional to implement
  NFSv4.2: Fix up a decoding error in layoutstats
  pNFS/flexfiles: Fix the reset of struct pgio_header when resending
  pNFS/flexfiles: Turn off layoutcommit for servers that don't need it
  pnfs/flexfiles: protect ktime manipulation with mirror lock
  nfs: provide pnfs_report_layoutstat when NFS42 is disabled
  nfs: verify open flags before allowing open
  nfs: always update creds in mirror, even when we have an already connected ds
  nfs: fix potential credential leak in ff_layout_update_mirror_cred
  pnfs/flexfiles: report layoutstat regularly
  ...

1 files changed, 108 insertions, 43 deletions

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index b0517287075b..e193c2b5476b 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -623,24 +623,6 @@ process_status:
 }
 
 /**
- * xs_tcp_shutdown - gracefully shut down a TCP socket
- * @xprt: transport
- *
- * Initiates a graceful shutdown of the TCP socket by calling the
- * equivalent of shutdown(SHUT_RDWR);
- */
-static void xs_tcp_shutdown(struct rpc_xprt *xprt)
-{
-	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
-	struct socket *sock = transport->sock;
-
-	if (sock != NULL) {
-		kernel_sock_shutdown(sock, SHUT_RDWR);
-		trace_rpc_socket_shutdown(xprt, sock);
-	}
-}
-
-/**
  * xs_tcp_send_request - write an RPC request to a TCP socket
  * @task: address of RPC task that manages the state of an RPC request
  *
@@ -786,6 +768,7 @@ 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);
 }
 
 /**
@@ -827,6 +810,9 @@ static void xs_reset_transport(struct sock_xprt *transport)
 	if (sk == NULL)
 		return;
 
+	if (atomic_read(&transport->xprt.swapper))
+		sk_clear_memalloc(sk);
+
 	write_lock_bh(&sk->sk_callback_lock);
 	transport->inet = NULL;
 	transport->sock = NULL;
@@ -863,6 +849,13 @@ static void xs_close(struct rpc_xprt *xprt)
 	xprt_disconnect_done(xprt);
 }
 
+static void xs_inject_disconnect(struct rpc_xprt *xprt)
+{
+	dprintk("RPC:       injecting transport disconnect on xprt=%p\n",
+		xprt);
+	xprt_disconnect_done(xprt);
+}
+
 static void xs_xprt_free(struct rpc_xprt *xprt)
 {
 	xs_free_peer_addresses(xprt);
@@ -901,7 +894,6 @@ static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 /**
  * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets
  * @sk: socket with data to read
- * @len: how much data to read
  *
  * Currently this assumes we can read the whole reply in a single gulp.
  */
@@ -965,7 +957,6 @@ static void xs_local_data_ready(struct sock *sk)
 /**
  * xs_udp_data_ready - "data ready" callback for UDP sockets
  * @sk: socket with data to read
- * @len: how much data to read
  *
  */
 static void xs_udp_data_ready(struct sock *sk)
@@ -1389,7 +1380,6 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
 /**
  * xs_tcp_data_ready - "data ready" callback for TCP sockets
  * @sk: socket with data to read
- * @bytes: how much data to read
  *
  */
 static void xs_tcp_data_ready(struct sock *sk)
@@ -1886,9 +1876,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
 
 /**
  * xs_local_setup_socket - create AF_LOCAL socket, connect to a local endpoint
- * @xprt: RPC transport to connect
  * @transport: socket transport to connect
- * @create_sock: function to create a socket of the correct type
  */
 static int xs_local_setup_socket(struct sock_xprt *transport)
 {
@@ -1960,43 +1948,84 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 		msleep_interruptible(15000);
 }
 
-#ifdef CONFIG_SUNRPC_SWAP
+#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
+/*
+ * Note that this should be called with XPRT_LOCKED held (or when we otherwise
+ * know that we have exclusive access to the socket), to guard against
+ * races with xs_reset_transport.
+ */
 static void xs_set_memalloc(struct rpc_xprt *xprt)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
 			xprt);
 
-	if (xprt->swapper)
+	/*
+	 * If there's no sock, then we have nothing to set. The
+	 * reconnecting process will get it for us.
+	 */
+	if (!transport->inet)
+		return;
+	if (atomic_read(&xprt->swapper))
 		sk_set_memalloc(transport->inet);
 }
 
 /**
- * xs_swapper - Tag this transport as being used for swap.
+ * xs_enable_swap - Tag this transport as being used for swap.
  * @xprt: transport to tag
- * @enable: enable/disable
  *
+ * Take a reference to this transport on behalf of the rpc_clnt, and
+ * optionally mark it for swapping if it wasn't already.
  */
-int xs_swapper(struct rpc_xprt *xprt, int enable)
+static int
+xs_enable_swap(struct rpc_xprt *xprt)
 {
-	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
-			xprt);
-	int err = 0;
+	struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt);
 
-	if (enable) {
-		xprt->swapper++;
-		xs_set_memalloc(xprt);
-	} else if (xprt->swapper) {
-		xprt->swapper--;
-		sk_clear_memalloc(transport->inet);
-	}
+	if (atomic_inc_return(&xprt->swapper) != 1)
+		return 0;
+	if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE))
+		return -ERESTARTSYS;
+	if (xs->inet)
+		sk_set_memalloc(xs->inet);
+	xprt_release_xprt(xprt, NULL);
+	return 0;
+}
 
-	return err;
+/**
+ * xs_disable_swap - Untag this transport as being used for swap.
+ * @xprt: transport to tag
+ *
+ * Drop a "swapper" reference to this xprt on behalf of the rpc_clnt. If the
+ * swapper refcount goes to 0, untag the socket as a memalloc socket.
+ */
+static void
+xs_disable_swap(struct rpc_xprt *xprt)
+{
+	struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt);
+
+	if (!atomic_dec_and_test(&xprt->swapper))
+		return;
+	if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE))
+		return;
+	if (xs->inet)
+		sk_clear_memalloc(xs->inet);
+	xprt_release_xprt(xprt, NULL);
 }
-EXPORT_SYMBOL_GPL(xs_swapper);
 #else
 static void xs_set_memalloc(struct rpc_xprt *xprt)
 {
 }
+
+static int
+xs_enable_swap(struct rpc_xprt *xprt)
+{
+	return -EINVAL;
+}
+
+static void
+xs_disable_swap(struct rpc_xprt *xprt)
+{
+}
 #endif
 
 static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
@@ -2057,6 +2086,27 @@ out:
 	xprt_wake_pending_tasks(xprt, status);
 }
 
+/**
+ * xs_tcp_shutdown - gracefully shut down a TCP socket
+ * @xprt: transport
+ *
+ * Initiates a graceful shutdown of the TCP socket by calling the
+ * equivalent of shutdown(SHUT_RDWR);
+ */
+static void xs_tcp_shutdown(struct rpc_xprt *xprt)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct socket *sock = transport->sock;
+
+	if (sock == NULL)
+		return;
+	if (xprt_connected(xprt)) {
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		trace_rpc_socket_shutdown(xprt, sock);
+	} else
+		xs_reset_transport(transport);
+}
+
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -2067,6 +2117,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		unsigned int keepidle = xprt->timeout->to_initval / HZ;
 		unsigned int keepcnt = xprt->timeout->to_retries + 1;
 		unsigned int opt_on = 1;
+		unsigned int timeo;
 
 		/* TCP Keepalive options */
 		kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
@@ -2078,6 +2129,12 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
 				(char *)&keepcnt, sizeof(keepcnt));
 
+		/* TCP user timeout (see RFC5482) */
+		timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
+			(xprt->timeout->to_retries + 1);
+		kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+				(char *)&timeo, sizeof(timeo));
+
 		write_lock_bh(&sk->sk_callback_lock);
 
 		xs_save_old_callbacks(transport, sk);
@@ -2125,9 +2182,6 @@ out:
 
 /**
  * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint
- * @xprt: RPC transport to connect
- * @transport: socket transport to connect
- * @create_sock: function to create a socket of the correct type
  *
  * Invoked by a work queue tasklet.
  */
@@ -2463,6 +2517,8 @@ static struct rpc_xprt_ops xs_local_ops = {
 	.close			= xs_close,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_local_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
 };
 
 static struct rpc_xprt_ops xs_udp_ops = {
@@ -2482,6 +2538,9 @@ static struct rpc_xprt_ops xs_udp_ops = {
 	.close			= xs_close,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_udp_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
+	.inject_disconnect	= xs_inject_disconnect,
 };
 
 static struct rpc_xprt_ops xs_tcp_ops = {
@@ -2498,6 +2557,9 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 	.close			= xs_tcp_shutdown,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_tcp_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
+	.inject_disconnect	= xs_inject_disconnect,
 };
 
 /*
@@ -2515,6 +2577,9 @@ static struct rpc_xprt_ops bc_tcp_ops = {
 	.close			= bc_close,
 	.destroy		= bc_destroy,
 	.print_stats		= xs_tcp_print_stats,
+	.enable_swap		= xs_enable_swap,
+	.disable_swap		= xs_disable_swap,
+	.inject_disconnect	= xs_inject_disconnect,
 };
 
 static int xs_init_anyaddr(const int family, struct sockaddr *sap)