Merge branch 'for-2.6.30' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.30' of git://linux-nfs.org/~bfields/linux: (81 commits)
  nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4
  nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drc
  nfsd41: Documentation/filesystems/nfs41-server.txt
  nfsd41: CREATE_EXCLUSIVE4_1
  nfsd41: SUPPATTR_EXCLCREAT attribute
  nfsd41: support for 3-word long attribute bitmask
  nfsd: dynamically skip encoded fattr bitmap in _nfsd4_verify
  nfsd41: pass writable attrs mask to nfsd4_decode_fattr
  nfsd41: provide support for minor version 1 at rpc level
  nfsd41: control nfsv4.1 svc via /proc/fs/nfsd/versions
  nfsd41: add OPEN4_SHARE_ACCESS_WANT nfs4_stateid bmap
  nfsd41: access_valid
  nfsd41: clientid handling
  nfsd41: check encode size for sessions maxresponse cached
  nfsd41: stateid handling
  nfsd: pass nfsd4_compound_state* to nfs4_preprocess_{state,seq}id_op
  nfsd41: destroy_session operation
  nfsd41: non-page DRC for solo sequence responses
  nfsd41: Add a create session replay cache
  nfsd41: create_session operation
  ...

3 files changed, 127 insertions, 38 deletions

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9b49a6ab..8847add 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1008,6 +1008,8 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_len = 0;
 	/* Will be turned off only in gss privacy case: */
 	rqstp->rq_splice_ok = 1;
+	/* Will be turned off only when NFSv4 Sessions are used */
+	rqstp->rq_usedeferral = 1;
 
 	/* Setup reply header */
 	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1078,7 +1080,6 @@ svc_process(struct svc_rqst *rqstp)
 	procp = versp->vs_proc + proc;
 	if (proc >= versp->vs_nproc || !procp->pc_func)
 		goto err_bad_proc;
-	rqstp->rq_server   = serv;
 	rqstp->rq_procinfo = procp;
 
 	/* Syntactic check complete */
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 2819ee0..c200d92 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -14,6 +14,8 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+#define SVC_MAX_WAKING 5
+
 static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
 static int svc_deferred_recv(struct svc_rqst *rqstp);
 static struct cache_deferred_req *svc_defer(struct cache_req *req);
@@ -301,6 +303,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	struct svc_pool *pool;
 	struct svc_rqst	*rqstp;
 	int cpu;
+	int thread_avail;
 
 	if (!(xprt->xpt_flags &
 	      ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
@@ -312,18 +315,14 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 
 	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");
-
 	if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
 		/* Don't enqueue dead transports */
 		dprintk("svc: transport %p is dead, not enqueued\n", xprt);
 		goto out_unlock;
 	}
 
+	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
@@ -356,7 +355,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	}
 
  process:
-	if (!list_empty(&pool->sp_threads)) {
+	/* Work out whether threads are available */
+	thread_avail = !list_empty(&pool->sp_threads);	/* threads are asleep */
+	if (pool->sp_nwaking >= SVC_MAX_WAKING) {
+		/* too many threads are runnable and trying to wake up */
+		thread_avail = 0;
+		pool->sp_stats.overloads_avoided++;
+	}
+
+	if (thread_avail) {
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
 				   rq_list);
@@ -371,11 +378,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+		rqstp->rq_waking = 1;
+		pool->sp_nwaking++;
+		pool->sp_stats.threads_woken++;
 		BUG_ON(xprt->xpt_pool != pool);
 		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++;
 		BUG_ON(xprt->xpt_pool != pool);
 	}
 
@@ -588,6 +599,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	int			pages;
 	struct xdr_buf		*arg;
 	DECLARE_WAITQUEUE(wait, current);
+	long			time_left;
 
 	dprintk("svc: server %p waiting for data (to = %ld)\n",
 		rqstp, timeout);
@@ -636,6 +648,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		return -EINTR;
 
 	spin_lock_bh(&pool->sp_lock);
+	if (rqstp->rq_waking) {
+		rqstp->rq_waking = 0;
+		pool->sp_nwaking--;
+		BUG_ON(pool->sp_nwaking < 0);
+	}
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
 		rqstp->rq_xprt = xprt;
@@ -668,12 +685,14 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		add_wait_queue(&rqstp->rq_wait, &wait);
 		spin_unlock_bh(&pool->sp_lock);
 
-		schedule_timeout(timeout);
+		time_left = schedule_timeout(timeout);
 
 		try_to_freeze();
 
 		spin_lock_bh(&pool->sp_lock);
 		remove_wait_queue(&rqstp->rq_wait, &wait);
+		if (!time_left)
+			pool->sp_stats.threads_timedout++;
 
 		xprt = rqstp->rq_xprt;
 		if (!xprt) {
@@ -958,7 +977,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
 	struct svc_deferred_req *dr;
 
-	if (rqstp->rq_arg.page_len)
+	if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
 		return NULL; /* if more than a page, give up FIXME */
 	if (rqstp->rq_deferred) {
 		dr = rqstp->rq_deferred;
@@ -1112,3 +1131,93 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen)
 	return totlen;
 }
 EXPORT_SYMBOL_GPL(svc_xprt_names);
+
+
+/*----------------------------------------------------------------------------*/
+
+static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
+{
+	unsigned int pidx = (unsigned int)*pos;
+	struct svc_serv *serv = m->private;
+
+	dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
+
+	lock_kernel();
+	/* bump up the pseudo refcount while traversing */
+	svc_get(serv);
+	unlock_kernel();
+
+	if (!pidx)
+		return SEQ_START_TOKEN;
+	return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
+}
+
+static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct svc_pool *pool = p;
+	struct svc_serv *serv = m->private;
+
+	dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
+
+	if (p == SEQ_START_TOKEN) {
+		pool = &serv->sv_pools[0];
+	} else {
+		unsigned int pidx = (pool - &serv->sv_pools[0]);
+		if (pidx < serv->sv_nrpools-1)
+			pool = &serv->sv_pools[pidx+1];
+		else
+			pool = NULL;
+	}
+	++*pos;
+	return pool;
+}
+
+static void svc_pool_stats_stop(struct seq_file *m, void *p)
+{
+	struct svc_serv *serv = m->private;
+
+	lock_kernel();
+	/* this function really, really should have been called svc_put() */
+	svc_destroy(serv);
+	unlock_kernel();
+}
+
+static int svc_pool_stats_show(struct seq_file *m, void *p)
+{
+	struct svc_pool *pool = p;
+
+	if (p == SEQ_START_TOKEN) {
+		seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n");
+		return 0;
+	}
+
+	seq_printf(m, "%u %lu %lu %lu %lu %lu\n",
+		pool->sp_id,
+		pool->sp_stats.packets,
+		pool->sp_stats.sockets_queued,
+		pool->sp_stats.threads_woken,
+		pool->sp_stats.overloads_avoided,
+		pool->sp_stats.threads_timedout);
+
+	return 0;
+}
+
+static const struct seq_operations svc_pool_stats_seq_ops = {
+	.start	= svc_pool_stats_start,
+	.next	= svc_pool_stats_next,
+	.stop	= svc_pool_stats_stop,
+	.show	= svc_pool_stats_show,
+};
+
+int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
+{
+	int err;
+
+	err = seq_open(file, &svc_pool_stats_seq_ops);
+	if (!err)
+		((struct seq_file *) file->private_data)->private = serv;
+	return err;
+}
+EXPORT_SYMBOL(svc_pool_stats_open);
+
+/*----------------------------------------------------------------------------*/
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 9d50423..af31988 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -345,7 +345,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 	lock_sock(sock->sk);
 	sock->sk->sk_sndbuf = snd * 2;
 	sock->sk->sk_rcvbuf = rcv * 2;
-	sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
 	release_sock(sock->sk);
 #endif
 }
@@ -797,23 +796,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
 		test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
 
-	if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
-		/* sndbuf needs to have room for one request
-		 * per thread, otherwise we can stall even when the
-		 * network isn't a bottleneck.
-		 *
-		 * We count all threads rather than threads in a
-		 * particular pool, which provides an upper bound
-		 * on the number of threads which will access the socket.
-		 *
-		 * rcvbuf just needs to be able to hold a few requests.
-		 * Normally they will be removed from the queue
-		 * as soon a a complete request arrives.
-		 */
-		svc_sock_setbufsize(svsk->sk_sock,
-				    (serv->sv_nrthreads+3) * serv->sv_max_mesg,
-				    3 * serv->sv_max_mesg);
-
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	/* Receive data. If we haven't got the record length yet, get
@@ -1061,15 +1043,6 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 
 		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
 
-		/* initialise setting must have enough space to
-		 * receive and respond to one request.
-		 * svc_tcp_recvfrom will re-adjust if necessary
-		 */
-		svc_sock_setbufsize(svsk->sk_sock,
-				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
-				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
-
-		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		if (sk->sk_state != TCP_ESTABLISHED)
 			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
@@ -1139,8 +1112,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	/* Initialize the socket */
 	if (sock->type == SOCK_DGRAM)
 		svc_udp_init(svsk, serv);
-	else
+	else {
+		/* initialise setting must have enough space to
+		 * receive and respond to one request.
+		 */
+		svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg,
+					4 * serv->sv_max_mesg);
 		svc_tcp_init(svsk, serv);
+	}
 
 	dprintk("svc: svc_setup_socket created %p (inet %p)\n",
 				svsk, svsk->sk_sk);