Merge branch 'for-3.18' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - support the NFSv4.2 SEEK operation (allowing clients to support
     SEEK_HOLE/SEEK_DATA), thanks to Anna.
   - end the grace period early in a number of cases, mitigating a
     long-standing annoyance, thanks to Jeff
   - improve SMP scalability, thanks to Trond"

* 'for-3.18' of git://linux-nfs.org/~bfields/linux: (55 commits)
  nfsd: eliminate "to_delegation" define
  NFSD: Implement SEEK
  NFSD: Add generic v4.2 infrastructure
  svcrdma: advertise the correct max payload
  nfsd: introduce nfsd4_callback_ops
  nfsd: split nfsd4_callback initialization and use
  nfsd: introduce a generic nfsd4_cb
  nfsd: remove nfsd4_callback.cb_op
  nfsd: do not clear rpc_resp in nfsd4_cb_done_sequence
  nfsd: fix nfsd4_cb_recall_done error handling
  nfsd4: clarify how grace period ends
  nfsd4: stop grace_time update at end of grace period
  nfsd: skip subsequent UMH "create" operations after the first one for v4.0 clients
  nfsd: set and test NFSD4_CLIENT_STABLE bit to reduce nfsdcltrack upcalls
  nfsd: serialize nfsdcltrack upcalls for a particular client
  nfsd: pass extra info in env vars to upcalls to allow for early grace period end
  nfsd: add a v4_end_grace file to /proc/fs/nfsd
  lockd: add a /proc/fs/lockd/nlm_end_grace file
  nfsd: reject reclaim request when client has already sent RECLAIM_COMPLETE
  nfsd: remove redundant boot_time parm from grace_done client tracking op
  ...

5 files changed, 48 insertions, 69 deletions

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 1db5007ddbce..ca8a7958f4e6 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -612,8 +612,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp)
 		goto out_enomem;
 
-	init_waitqueue_head(&rqstp->rq_wait);
-
 	serv->sv_nrthreads++;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 6666c6745858..c179ca2a5aa4 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -346,20 +346,6 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	if (!svc_xprt_has_something_to_do(xprt))
 		return;
 
-	cpu = get_cpu();
-	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
-
-	spin_lock_bh(&pool->sp_lock);
-
-	if (!list_empty(&pool->sp_threads) &&
-	    !list_empty(&pool->sp_sockets))
-		printk(KERN_ERR
-		       "svc_xprt_enqueue: "
-		       "threads and transports both waiting??\n");
-
-	pool->sp_stats.packets++;
-
 	/* Mark transport as busy. It will remain in this state until
 	 * the provider calls svc_xprt_received. We update XPT_BUSY
 	 * atomically because it also guards against trying to enqueue
@@ -368,9 +354,15 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
 		/* Don't enqueue transport while already enqueued */
 		dprintk("svc: transport %p busy, not enqueued\n", xprt);
-		goto out_unlock;
+		return;
 	}
 
+	cpu = get_cpu();
+	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
+	spin_lock_bh(&pool->sp_lock);
+
+	pool->sp_stats.packets++;
+
 	if (!list_empty(&pool->sp_threads)) {
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
@@ -382,18 +374,23 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 			printk(KERN_ERR
 				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
 				rqstp, rqstp->rq_xprt);
-		rqstp->rq_xprt = xprt;
+		/* Note the order of the following 3 lines:
+		 * We want to assign xprt to rqstp->rq_xprt only _after_
+		 * we've woken up the process, so that we don't race with
+		 * the lockless check in svc_get_next_xprt().
+		 */
 		svc_xprt_get(xprt);
+		wake_up_process(rqstp->rq_task);
+		rqstp->rq_xprt = xprt;
 		pool->sp_stats.threads_woken++;
-		wake_up(&rqstp->rq_wait);
 	} else {
 		dprintk("svc: transport %p put into queue\n", xprt);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
 		pool->sp_stats.sockets_queued++;
 	}
 
-out_unlock:
 	spin_unlock_bh(&pool->sp_lock);
+	put_cpu();
 }
 
 /*
@@ -509,7 +506,7 @@ void svc_wake_up(struct svc_serv *serv)
 			svc_thread_dequeue(pool, rqstp);
 			rqstp->rq_xprt = NULL;
 			 */
-			wake_up(&rqstp->rq_wait);
+			wake_up_process(rqstp->rq_task);
 		} else
 			pool->sp_task_pending = 1;
 		spin_unlock_bh(&pool->sp_lock);
@@ -628,8 +625,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 {
 	struct svc_xprt *xprt;
 	struct svc_pool		*pool = rqstp->rq_pool;
-	DECLARE_WAITQUEUE(wait, current);
-	long			time_left;
+	long			time_left = 0;
 
 	/* Normally we will wait up to 5 seconds for any required
 	 * cache information to be provided.
@@ -651,40 +647,32 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 	} else {
 		if (pool->sp_task_pending) {
 			pool->sp_task_pending = 0;
-			spin_unlock_bh(&pool->sp_lock);
-			return ERR_PTR(-EAGAIN);
+			xprt = ERR_PTR(-EAGAIN);
+			goto out;
 		}
-		/* No data pending. Go to sleep */
-		svc_thread_enqueue(pool, rqstp);
-
 		/*
 		 * We have to be able to interrupt this wait
 		 * to bring down the daemons ...
 		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 
-		/*
-		 * checking kthread_should_stop() here allows us to avoid
-		 * locking and signalling when stopping kthreads that call
-		 * svc_recv. If the thread has already been woken up, then
-		 * we can exit here without sleeping. If not, then it
-		 * it'll be woken up quickly during the schedule_timeout
-		 */
-		if (kthread_should_stop()) {
-			set_current_state(TASK_RUNNING);
-			spin_unlock_bh(&pool->sp_lock);
-			return ERR_PTR(-EINTR);
-		}
-
-		add_wait_queue(&rqstp->rq_wait, &wait);
+		/* No data pending. Go to sleep */
+		svc_thread_enqueue(pool, rqstp);
 		spin_unlock_bh(&pool->sp_lock);
 
-		time_left = schedule_timeout(timeout);
+		if (!(signalled() || kthread_should_stop())) {
+			time_left = schedule_timeout(timeout);
+			__set_current_state(TASK_RUNNING);
 
-		try_to_freeze();
+			try_to_freeze();
+
+			xprt = rqstp->rq_xprt;
+			if (xprt != NULL)
+				return xprt;
+		} else
+			__set_current_state(TASK_RUNNING);
 
 		spin_lock_bh(&pool->sp_lock);
-		remove_wait_queue(&rqstp->rq_wait, &wait);
 		if (!time_left)
 			pool->sp_stats.threads_timedout++;
 
@@ -699,6 +687,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 				return ERR_PTR(-EAGAIN);
 		}
 	}
+out:
 	spin_unlock_bh(&pool->sp_lock);
 	return xprt;
 }
@@ -744,7 +733,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 			svc_add_new_temp_xprt(serv, newxpt);
 		else
 			module_put(xprt->xpt_class->xcl_owner);
-	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
+	} else {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
 			rqstp, rqstp->rq_pool->sp_id, xprt,
@@ -781,10 +770,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		printk(KERN_ERR
 			"svc_recv: service %p, transport not NULL!\n",
 			 rqstp);
-	if (waitqueue_active(&rqstp->rq_wait))
-		printk(KERN_ERR
-			"svc_recv: service %p, wait queue active!\n",
-			 rqstp);
 
 	err = svc_alloc_arg(rqstp);
 	if (err)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index c24a8ff33f8f..3f959c681885 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -312,19 +312,6 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 }
 
 /*
- * Check input queue length
- */
-static int svc_recv_available(struct svc_sock *svsk)
-{
-	struct socket	*sock = svsk->sk_sock;
-	int		avail, err;
-
-	err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);
-
-	return (err >= 0)? avail : err;
-}
-
-/*
  * Generic recvfrom routine.
  */
 static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
@@ -339,8 +326,14 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
 
 	rqstp->rq_xprt_hlen = 0;
 
+	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
 				msg.msg_flags);
+	/* If we read a full record, then assume there may be more
+	 * data to read (stream based sockets only!)
+	 */
+	if (len == buflen)
+		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
 		svsk, iov[0].iov_base, iov[0].iov_len, len);
@@ -980,8 +973,6 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	unsigned int want;
 	int len;
 
-	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-
 	if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
 		struct kvec	iov;
 
@@ -1036,7 +1027,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 			"%s: Got unrecognized reply: "
 			"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
 			__func__, ntohl(calldir),
-			bc_xprt, xid);
+			bc_xprt, ntohl(xid));
 		return -EAGAIN;
 	}
 
@@ -1073,8 +1064,6 @@ static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
 static void svc_tcp_fragment_received(struct svc_sock *svsk)
 {
 	/* If we have more data, signal svc_xprt_enqueue() to try again */
-	if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
-		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	dprintk("svc: TCP %s record (%d bytes)\n",
 		svc_sock_final_rec(svsk) ? "final" : "nonfinal",
 		svc_sock_reclen(svsk));
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 374feb44afea..4e618808bc98 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_name = "rdma",
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_rdma_ops,
-	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA,
 	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
 
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index c419498b8f46..ac7fc9a31342 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -51,6 +51,7 @@
 #include <linux/sunrpc/clnt.h> 		/* rpc_xprt */
 #include <linux/sunrpc/rpc_rdma.h> 	/* RPC/RDMA protocol */
 #include <linux/sunrpc/xprtrdma.h> 	/* xprt parameters */
+#include <linux/sunrpc/svc.h>		/* RPCSVC_MAXPAYLOAD */
 
 #define RDMA_RESOLVE_TIMEOUT	(5000)	/* 5 seconds */
 #define RDMA_CONNECT_RETRY_MAX	(2)	/* retries if no listener backlog */
@@ -392,4 +393,10 @@ extern struct kmem_cache *svc_rdma_ctxt_cachep;
 /* Workqueue created in svc_rdma.c */
 extern struct workqueue_struct *svc_rdma_wq;
 
+#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
+#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
+#else
+#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
+#endif
+
 #endif				/* _LINUX_SUNRPC_XPRT_RDMA_H */