Merge tag 'nfs-for-3.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable fixes:
   - fix an NFSv4.1 state renewal regression
   - fix open/lock state recovery error handling
   - fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
   - fix statd when reconnection fails
   - don't wake tasks during connection abort
   - don't start reboot recovery if lease check fails
   - fix duplicate proc entries

  Features:
  - pNFS block driver fixes and clean ups from Christoph
  - More code cleanups from Anna
  - Improve mmap() writeback performance
  - Replace use of PF_TRANS with a more generic mechanism for avoiding
    deadlocks in nfs_release_page"

* tag 'nfs-for-3.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (66 commits)
  NFSv4.1: Fix an NFSv4.1 state renewal regression
  NFSv4: fix open/lock state recovery error handling
  NFSv4: Fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
  NFS: Fabricate fscache server index key correctly
  SUNRPC: Add missing support for RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT
  NFSv3: Fix missing includes of nfs3_fs.h
  NFS/SUNRPC: Remove other deadlock-avoidance mechanisms in nfs_release_page()
  NFS: avoid waiting at all in nfs_release_page when congested.
  NFS: avoid deadlocks with loop-back mounted NFS filesystems.
  MM: export page_wakeup functions
  SCHED: add some "wait..on_bit...timeout()" interfaces.
  NFS: don't use STABLE writes during writeback.
  NFSv4: use exponential retry on NFS4ERR_DELAY for async requests.
  rpc: Add -EPERM processing for xs_udp_send_request()
  rpc: return sent and err from xs_sendpages()
  lockd: Try to reconnect if statd has moved
  SUNRPC: Don't wake tasks during connection abort
  Fixing lease renewal
  nfs: fix duplicate proc entries
  pnfs/blocklayout: Fix a 64-bit division/remainder issue in bl_map_stripe
  ...

4 files changed, 75 insertions, 55 deletions

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 488ddeed9363..9acd6ce88db7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -461,6 +461,8 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
 		clnt->cl_autobind = 1;
+	if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT)
+		clnt->cl_noretranstimeo = 1;
 	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
 		clnt->cl_discrtry = 1;
 	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
@@ -579,6 +581,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	/* Turn off autobind on clones */
 	new->cl_autobind = 0;
 	new->cl_softrtry = clnt->cl_softrtry;
+	new->cl_noretranstimeo = clnt->cl_noretranstimeo;
 	new->cl_discrtry = clnt->cl_discrtry;
 	new->cl_chatty = clnt->cl_chatty;
 	return new;
@@ -1913,6 +1916,7 @@ call_transmit_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+	case -EPERM:
 		if (RPC_IS_SOFTCONN(task)) {
 			xprt_end_transmit(task);
 			rpc_exit(task, task->tk_status);
@@ -2018,6 +2022,7 @@ call_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+	case -EPERM:
 		if (RPC_IS_SOFTCONN(task)) {
 			rpc_exit(task, status);
 			break;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 9358c79fd589..fe3441abdbe5 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -821,9 +821,7 @@ void rpc_execute(struct rpc_task *task)
 
 static void rpc_async_schedule(struct work_struct *work)
 {
-	current->flags |= PF_FSTRANS;
 	__rpc_execute(container_of(work, struct rpc_task, u.tk_work));
-	current->flags &= ~PF_FSTRANS;
 }
 
 /**
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 2faac4940563..6a4615dd0261 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -205,7 +205,6 @@ xprt_rdma_connect_worker(struct work_struct *work)
 	struct rpc_xprt *xprt = &r_xprt->xprt;
 	int rc = 0;
 
-	current->flags |= PF_FSTRANS;
 	xprt_clear_connected(xprt);
 
 	dprintk("RPC:       %s: %sconnect\n", __func__,
@@ -216,7 +215,6 @@ xprt_rdma_connect_worker(struct work_struct *work)
 
 	dprintk("RPC:       %s: exit\n", __func__);
 	xprt_clear_connecting(xprt);
-	current->flags &= ~PF_FSTRANS;
 }
 
 /*
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 43cd89eacfab..3b305ab17afe 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -399,13 +399,13 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen,
 	return kernel_sendmsg(sock, &msg, NULL, 0, 0);
 }
 
-static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy, int *sent_p)
 {
 	ssize_t (*do_sendpage)(struct socket *sock, struct page *page,
 			int offset, size_t size, int flags);
 	struct page **ppage;
 	unsigned int remainder;
-	int err, sent = 0;
+	int err;
 
 	remainder = xdr->page_len - base;
 	base += xdr->page_base;
@@ -424,15 +424,15 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
 		err = do_sendpage(sock, *ppage, base, len, flags);
 		if (remainder == 0 || err != len)
 			break;
-		sent += err;
+		*sent_p += err;
 		ppage++;
 		base = 0;
 	}
-	if (sent == 0)
-		return err;
-	if (err > 0)
-		sent += err;
-	return sent;
+	if (err > 0) {
+		*sent_p += err;
+		err = 0;
+	}
+	return err;
 }
 
 /**
@@ -443,12 +443,14 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
  * @xdr: buffer containing this request
  * @base: starting position in the buffer
  * @zerocopy: true if it is safe to use sendpage()
+ * @sent_p: return the total number of bytes successfully queued for sending
  *
  */
-static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy, int *sent_p)
 {
 	unsigned int remainder = xdr->len - base;
-	int err, sent = 0;
+	int err = 0;
+	int sent = 0;
 
 	if (unlikely(!sock))
 		return -ENOTSOCK;
@@ -465,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 		err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
 		if (remainder == 0 || err != len)
 			goto out;
-		sent += err;
+		*sent_p += err;
 		base = 0;
 	} else
 		base -= xdr->head[0].iov_len;
@@ -473,23 +475,23 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 	if (base < xdr->page_len) {
 		unsigned int len = xdr->page_len - base;
 		remainder -= len;
-		err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy);
-		if (remainder == 0 || err != len)
+		err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy, &sent);
+		*sent_p += sent;
+		if (remainder == 0 || sent != len)
 			goto out;
-		sent += err;
 		base = 0;
 	} else
 		base -= xdr->page_len;
 
 	if (base >= xdr->tail[0].iov_len)
-		return sent;
+		return 0;
 	err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);
 out:
-	if (sent == 0)
-		return err;
-	if (err > 0)
-		sent += err;
-	return sent;
+	if (err > 0) {
+		*sent_p += err;
+		err = 0;
+	}
+	return err;
 }
 
 static void xs_nospace_callback(struct rpc_task *task)
@@ -573,19 +575,20 @@ static int xs_local_send_request(struct rpc_task *task)
 				container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *xdr = &req->rq_snd_buf;
 	int status;
+	int sent = 0;
 
 	xs_encode_stream_record_marker(&req->rq_snd_buf);
 
 	xs_pktdump("packet data:",
 			req->rq_svec->iov_base, req->rq_svec->iov_len);
 
-	status = xs_sendpages(transport->sock, NULL, 0,
-						xdr, req->rq_bytes_sent, true);
+	status = xs_sendpages(transport->sock, NULL, 0, xdr, req->rq_bytes_sent,
+			      true, &sent);
 	dprintk("RPC:       %s(%u) = %d\n",
 			__func__, xdr->len - req->rq_bytes_sent, status);
-	if (likely(status >= 0)) {
-		req->rq_bytes_sent += status;
-		req->rq_xmit_bytes_sent += status;
+	if (likely(sent > 0) || status == 0) {
+		req->rq_bytes_sent += sent;
+		req->rq_xmit_bytes_sent += sent;
 		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
 			req->rq_bytes_sent = 0;
 			return 0;
@@ -626,6 +629,7 @@ static int xs_udp_send_request(struct rpc_task *task)
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *xdr = &req->rq_snd_buf;
+	int sent = 0;
 	int status;
 
 	xs_pktdump("packet data:",
@@ -634,22 +638,25 @@ static int xs_udp_send_request(struct rpc_task *task)
 
 	if (!xprt_bound(xprt))
 		return -ENOTCONN;
-	status = xs_sendpages(transport->sock,
-			      xs_addr(xprt),
-			      xprt->addrlen, xdr,
-			      req->rq_bytes_sent, true);
+	status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen,
+			      xdr, req->rq_bytes_sent, true, &sent);
 
 	dprintk("RPC:       xs_udp_send_request(%u) = %d\n",
 			xdr->len - req->rq_bytes_sent, status);
 
-	if (status >= 0) {
-		req->rq_xmit_bytes_sent += status;
-		if (status >= req->rq_slen)
+	/* firewall is blocking us, don't return -EAGAIN or we end up looping */
+	if (status == -EPERM)
+		goto process_status;
+
+	if (sent > 0 || status == 0) {
+		req->rq_xmit_bytes_sent += sent;
+		if (sent >= req->rq_slen)
 			return 0;
 		/* Still some bytes left; set up for a retry later. */
 		status = -EAGAIN;
 	}
 
+process_status:
 	switch (status) {
 	case -ENOTSOCK:
 		status = -ENOTCONN;
@@ -665,6 +672,7 @@ static int xs_udp_send_request(struct rpc_task *task)
 	case -ENOBUFS:
 	case -EPIPE:
 	case -ECONNREFUSED:
+	case -EPERM:
 		/* When the server has died, an ICMP port unreachable message
 		 * prompts ECONNREFUSED. */
 		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
@@ -713,6 +721,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	struct xdr_buf *xdr = &req->rq_snd_buf;
 	bool zerocopy = true;
 	int status;
+	int sent;
 
 	xs_encode_stream_record_marker(&req->rq_snd_buf);
 
@@ -730,26 +739,26 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	 * to cope with writespace callbacks arriving _after_ we have
 	 * called sendmsg(). */
 	while (1) {
-		status = xs_sendpages(transport->sock,
-					NULL, 0, xdr, req->rq_bytes_sent,
-					zerocopy);
+		sent = 0;
+		status = xs_sendpages(transport->sock, NULL, 0, xdr,
+				      req->rq_bytes_sent, zerocopy, &sent);
 
 		dprintk("RPC:       xs_tcp_send_request(%u) = %d\n",
 				xdr->len - req->rq_bytes_sent, status);
 
-		if (unlikely(status < 0))
+		if (unlikely(sent == 0 && status < 0))
 			break;
 
 		/* If we've sent the entire packet, immediately
 		 * reset the count of bytes sent. */
-		req->rq_bytes_sent += status;
-		req->rq_xmit_bytes_sent += status;
+		req->rq_bytes_sent += sent;
+		req->rq_xmit_bytes_sent += sent;
 		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
 			req->rq_bytes_sent = 0;
 			return 0;
 		}
 
-		if (status != 0)
+		if (sent != 0)
 			continue;
 		status = -EAGAIN;
 		break;
@@ -845,6 +854,8 @@ static void xs_error_report(struct sock *sk)
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
 			xprt, -err);
 	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state))
+		goto out;
 	xprt_wake_pending_tasks(xprt, err);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -1746,13 +1757,29 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
 	unsigned short port = xs_get_srcport(transport);
 	unsigned short last;
 
+	/*
+	 * If we are asking for any ephemeral port (i.e. port == 0 &&
+	 * transport->xprt.resvport == 0), don't bind.  Let the local
+	 * port selection happen implicitly when the socket is used
+	 * (for example at connect time).
+	 *
+	 * This ensures that we can continue to establish TCP
+	 * connections even when all local ephemeral ports are already
+	 * a part of some TCP connection.  This makes no difference
+	 * for UDP sockets, but also doens't harm them.
+	 *
+	 * If we're asking for any reserved port (i.e. port == 0 &&
+	 * transport->xprt.resvport == 1) xs_get_srcport above will
+	 * ensure that port is non-zero and we will bind as needed.
+	 */
+	if (port == 0)
+		return 0;
+
 	memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);
 	do {
 		rpc_set_port((struct sockaddr *)&myaddr, port);
 		err = kernel_bind(sock, (struct sockaddr *)&myaddr,
 				transport->xprt.addrlen);
-		if (port == 0)
-			break;
 		if (err == 0) {
 			transport->srcport = port;
 			break;
@@ -1927,8 +1954,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 	struct socket *sock;
 	int status = -EIO;
 
-	current->flags |= PF_FSTRANS;
-
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	status = __sock_create(xprt->xprt_net, AF_LOCAL,
 					SOCK_STREAM, 0, &sock, 1);
@@ -1968,7 +1993,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 out:
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
-	current->flags &= ~PF_FSTRANS;
 	return status;
 }
 
@@ -2071,8 +2095,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int status = -EIO;
 
-	current->flags |= PF_FSTRANS;
-
 	/* Start by resetting any existing state */
 	xs_reset_transport(transport);
 	sock = xs_create_sock(xprt, transport,
@@ -2092,7 +2114,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
 out:
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
-	current->flags &= ~PF_FSTRANS;
 }
 
 /*
@@ -2229,8 +2250,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	struct rpc_xprt *xprt = &transport->xprt;
 	int status = -EIO;
 
-	current->flags |= PF_FSTRANS;
-
 	if (!sock) {
 		clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 		sock = xs_create_sock(xprt, transport,
@@ -2245,7 +2264,9 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 		abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
 				&xprt->state);
 		/* "close" the socket, preserving the local port */
+		set_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 		xs_tcp_reuse_connection(transport);
+		clear_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 
 		if (abort_and_exit)
 			goto out_eagain;
@@ -2276,7 +2297,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -EINPROGRESS:
 	case -EALREADY:
 		xprt_clear_connecting(xprt);
-		current->flags &= ~PF_FSTRANS;
 		return;
 	case -EINVAL:
 		/* Happens, for instance, if the user specified a link
@@ -2294,7 +2314,6 @@ out_eagain:
 out:
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
-	current->flags &= ~PF_FSTRANS;
 }
 
 /**