1 files changed, 406 insertions, 236 deletions

diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9647b0f7bc0..1879e43f286 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/nfssvc.c
- *
  * Central processing for nfsd.
  *
  * Authors:	Olaf Kirch (okir@monad.swb.de)
@@ -8,55 +6,61 @@
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/nfs.h>
-#include <linux/in.h>
-#include <linux/uio.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/freezer.h>
+#include <linux/module.h>
 #include <linux/fs_struct.h>
+#include <linux/swap.h>
 
-#include <linux/sunrpc/types.h>
 #include <linux/sunrpc/stats.h>
-#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
-#include <linux/sunrpc/cache.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/stats.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/syscall.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
+#include <linux/seq_file.h>
+#include <net/net_namespace.h>
+#include "nfsd.h"
+#include "cache.h"
+#include "vfs.h"
+#include "netns.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
-/* these signals will be delivered to an nfsd thread 
- * when handling a request
- */
-#define ALLOWED_SIGS	(sigmask(SIGKILL))
-/* these signals will be delivered to an nfsd thread
- * when not handling a request. i.e. when waiting
- */
-#define SHUTDOWN_SIGS	(sigmask(SIGKILL) | sigmask(SIGHUP) | sigmask(SIGINT) | sigmask(SIGQUIT))
-/* if the last thread dies with SIGHUP, then the exports table is
- * left unchanged ( like 2.4-{0-9} ).  Any other signal will clear
- * the exports table (like 2.2).
+extern struct svc_program	nfsd_program;
+static int			nfsd(void *vrqstp);
+
+/*
+ * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members
+ * of the svc_serv struct. In particular, ->sv_nrthreads but also to some
+ * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt
+ *
+ * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
+ * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number
+ * of nfsd threads must exist and each must listed in ->sp_all_threads in each
+ * entry of ->sv_pools[].
+ *
+ * Transitions of the thread count between zero and non-zero are of particular
+ * interest since the svc_serv needs to be created and initialized at that
+ * point, or freed.
+ *
+ * Finally, the nfsd_mutex also protects some of the global variables that are
+ * accessed when nfsd starts and that are settable via the write_* routines in
+ * nfsctl.c. In particular:
+ *
+ *	user_recovery_dirname
+ *	user_lease_time
+ *	nfsd_versions
  */
-#define	SIG_NOCLEAN	SIGHUP
+DEFINE_MUTEX(nfsd_mutex);
 
-extern struct svc_program	nfsd_program;
-static void			nfsd(struct svc_rqst *rqstp);
-struct timeval			nfssvc_boot;
-       struct svc_serv 		*nfsd_serv;
-static atomic_t			nfsd_busy;
-static unsigned long		nfsd_last_call;
-static DEFINE_SPINLOCK(nfsd_call_lock);
+/*
+ * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
+ * nfsd_drc_max_pages limits the total amount of memory available for
+ * version 4.1 DRC caches.
+ * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
+ */
+spinlock_t	nfsd_drc_lock;
+unsigned long	nfsd_drc_max_mem;
+unsigned long	nfsd_drc_mem_used;
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
@@ -112,10 +116,15 @@ struct svc_program		nfsd_program = {
 
 };
 
+static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = {
+	[0] = 1,
+	[1] = 1,
+};
+
 int nfsd_vers(int vers, enum vers_op change)
 {
 	if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS)
-		return -1;
+		return 0;
 	switch(change) {
 	case NFSD_SET:
 		nfsd_versions[vers] = nfsd_version[vers];
@@ -138,35 +147,180 @@ int nfsd_vers(int vers, enum vers_op change)
 	}
 	return 0;
 }
+
+int nfsd_minorversion(u32 minorversion, enum vers_op change)
+{
+	if (minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+		return -1;
+	switch(change) {
+	case NFSD_SET:
+		nfsd_supported_minorversions[minorversion] = true;
+		break;
+	case NFSD_CLEAR:
+		nfsd_supported_minorversions[minorversion] = false;
+		break;
+	case NFSD_TEST:
+		return nfsd_supported_minorversions[minorversion];
+	case NFSD_AVAIL:
+		return minorversion <= NFSD_SUPPORTED_MINOR_VERSION;
+	}
+	return 0;
+}
+
 /*
  * Maximum number of nfsd processes
  */
 #define	NFSD_MAXSERVS		8192
 
-int nfsd_nrthreads(void)
+int nfsd_nrthreads(struct net *net)
 {
-	if (nfsd_serv == NULL)
+	int rv = 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	mutex_lock(&nfsd_mutex);
+	if (nn->nfsd_serv)
+		rv = nn->nfsd_serv->sv_nrthreads;
+	mutex_unlock(&nfsd_mutex);
+	return rv;
+}
+
+static int nfsd_init_socks(struct net *net)
+{
+	int error;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (!list_empty(&nn->nfsd_serv->sv_permsocks))
 		return 0;
-	else
-		return nfsd_serv->sv_nrthreads;
+
+	error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT,
+					SVC_SOCK_DEFAULTS);
+	if (error < 0)
+		return error;
+
+	error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT,
+					SVC_SOCK_DEFAULTS);
+	if (error < 0)
+		return error;
+
+	return 0;
 }
 
-static int killsig;	/* signal that was used to kill last nfsd */
-static void nfsd_last_thread(struct svc_serv *serv)
+static int nfsd_users = 0;
+
+static int nfsd_startup_generic(int nrservs)
 {
-	/* When last nfsd thread exits we need to do some clean-up */
-	struct svc_xprt *xprt;
-	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list)
-		lockd_down();
-	nfsd_serv = NULL;
+	int ret;
+
+	if (nfsd_users++)
+		return 0;
+
+	/*
+	 * Readahead param cache - will no-op if it already exists.
+	 * (Note therefore results will be suboptimal if number of
+	 * threads is modified after nfsd start.)
+	 */
+	ret = nfsd_racache_init(2*nrservs);
+	if (ret)
+		return ret;
+	ret = nfs4_state_start();
+	if (ret)
+		goto out_racache;
+	return 0;
+
+out_racache:
 	nfsd_racache_shutdown();
+	return ret;
+}
+
+static void nfsd_shutdown_generic(void)
+{
+	if (--nfsd_users)
+		return;
+
 	nfs4_state_shutdown();
+	nfsd_racache_shutdown();
+}
+
+static bool nfsd_needs_lockd(void)
+{
+#if defined(CONFIG_NFSD_V3)
+	return (nfsd_versions[2] != NULL) || (nfsd_versions[3] != NULL);
+#else
+	return (nfsd_versions[2] != NULL);
+#endif
+}
+
+static int nfsd_startup_net(int nrservs, struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int ret;
+
+	if (nn->nfsd_net_up)
+		return 0;
+
+	ret = nfsd_startup_generic(nrservs);
+	if (ret)
+		return ret;
+	ret = nfsd_init_socks(net);
+	if (ret)
+		goto out_socks;
+
+	if (nfsd_needs_lockd() && !nn->lockd_up) {
+		ret = lockd_up(net);
+		if (ret)
+			goto out_socks;
+		nn->lockd_up = 1;
+	}
+
+	ret = nfs4_state_start_net(net);
+	if (ret)
+		goto out_lockd;
 
-	printk(KERN_WARNING "nfsd: last server has exited\n");
-	if (killsig != SIG_NOCLEAN) {
-		printk(KERN_WARNING "nfsd: unexporting all filesystems\n");
-		nfsd_export_flush();
+	nn->nfsd_net_up = true;
+	return 0;
+
+out_lockd:
+	if (nn->lockd_up) {
+		lockd_down(net);
+		nn->lockd_up = 0;
 	}
+out_socks:
+	nfsd_shutdown_generic();
+	return ret;
+}
+
+static void nfsd_shutdown_net(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nfs4_state_shutdown_net(net);
+	if (nn->lockd_up) {
+		lockd_down(net);
+		nn->lockd_up = 0;
+	}
+	nn->nfsd_net_up = false;
+	nfsd_shutdown_generic();
+}
+
+static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	/*
+	 * write_ports can create the server without actually starting
+	 * any threads--if we get shut down before any threads are
+	 * started, then nfsd_last_thread will be run before any of this
+	 * other initialization has been done.
+	 */
+	if (!nn->nfsd_net_up)
+		return;
+	nfsd_shutdown_net(net);
+
+	svc_rpcb_cleanup(serv, net);
+
+	printk(KERN_WARNING "nfsd: last server has exited, flushing export "
+			    "cache\n");
+	nfsd_export_flush(net);
 }
 
 void nfsd_reset_versions(void)
@@ -190,105 +344,127 @@ void nfsd_reset_versions(void)
 	}
 }
 
-int nfsd_create_serv(void)
+/*
+ * Each session guarantees a negotiated per slot memory cache for replies
+ * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated
+ * NFSv4.1 server might want to use more memory for a DRC than a machine
+ * with mutiple services.
+ *
+ * Impose a hard limit on the number of pages for the DRC which varies
+ * according to the machines free pages. This is of course only a default.
+ *
+ * For now this is a #defined shift which could be under admin control
+ * in the future.
+ */
+static void set_max_drc(void)
 {
-	int err = 0;
-	lock_kernel();
-	if (nfsd_serv) {
-		svc_get(nfsd_serv);
-		unlock_kernel();
-		return 0;
-	}
-	if (nfsd_max_blksize == 0) {
-		/* choose a suitable default */
-		struct sysinfo i;
-		si_meminfo(&i);
-		/* Aim for 1/4096 of memory per thread
-		 * This gives 1MB on 4Gig machines
-		 * But only uses 32K on 128M machines.
-		 * Bottom out at 8K on 32M and smaller.
-		 * Of course, this is only a default.
-		 */
-		nfsd_max_blksize = NFSSVC_MAXBLKSIZE;
-		i.totalram <<= PAGE_SHIFT - 12;
-		while (nfsd_max_blksize > i.totalram &&
-		       nfsd_max_blksize >= 8*1024*2)
-			nfsd_max_blksize /= 2;
-	}
+	#define NFSD_DRC_SIZE_SHIFT	10
+	nfsd_drc_max_mem = (nr_free_buffer_pages()
+					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
+	nfsd_drc_mem_used = 0;
+	spin_lock_init(&nfsd_drc_lock);
+	dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
+}
 
-	atomic_set(&nfsd_busy, 0);
-	nfsd_serv = svc_create_pooled(&nfsd_program,
-				      nfsd_max_blksize,
-				      nfsd_last_thread,
-				      nfsd, SIG_NOCLEAN, THIS_MODULE);
-	if (nfsd_serv == NULL)
-		err = -ENOMEM;
-	unlock_kernel();
-	do_gettimeofday(&nfssvc_boot);		/* record boot time */
-	return err;
+static int nfsd_get_default_max_blksize(void)
+{
+	struct sysinfo i;
+	unsigned long long target;
+	unsigned long ret;
+
+	si_meminfo(&i);
+	target = (i.totalram - i.totalhigh) << PAGE_SHIFT;
+	/*
+	 * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
+	 * machines, but only uses 32K on 128M machines.  Bottom out at
+	 * 8K on 32M and smaller.  Of course, this is only a default.
+	 */
+	target >>= 12;
+
+	ret = NFSSVC_MAXBLKSIZE;
+	while (ret > target && ret >= 8*1024*2)
+		ret /= 2;
+	return ret;
 }
 
-static int nfsd_init_socks(int port)
+int nfsd_create_serv(struct net *net)
 {
 	int error;
-	if (!list_empty(&nfsd_serv->sv_permsocks))
-		return 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	error = lockd_up(IPPROTO_UDP);
-	if (error >= 0) {
-		error = svc_create_xprt(nfsd_serv, "udp", port,
-					SVC_SOCK_DEFAULTS);
-		if (error < 0)
-			lockd_down();
+	WARN_ON(!mutex_is_locked(&nfsd_mutex));
+	if (nn->nfsd_serv) {
+		svc_get(nn->nfsd_serv);
+		return 0;
 	}
-	if (error < 0)
+	if (nfsd_max_blksize == 0)
+		nfsd_max_blksize = nfsd_get_default_max_blksize();
+	nfsd_reset_versions();
+	nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
+				      nfsd_last_thread, nfsd, THIS_MODULE);
+	if (nn->nfsd_serv == NULL)
+		return -ENOMEM;
+
+	error = svc_bind(nn->nfsd_serv, net);
+	if (error < 0) {
+		svc_destroy(nn->nfsd_serv);
 		return error;
-
-#ifdef CONFIG_NFSD_TCP
-	error = lockd_up(IPPROTO_TCP);
-	if (error >= 0) {
-		error = svc_create_xprt(nfsd_serv, "tcp", port,
-					SVC_SOCK_DEFAULTS);
-		if (error < 0)
-			lockd_down();
 	}
-	if (error < 0)
-		return error;
-#endif
+
+	set_max_drc();
+	do_gettimeofday(&nn->nfssvc_boot);		/* record boot time */
 	return 0;
 }
 
-int nfsd_nrpools(void)
+int nfsd_nrpools(struct net *net)
 {
-	if (nfsd_serv == NULL)
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (nn->nfsd_serv == NULL)
 		return 0;
 	else
-		return nfsd_serv->sv_nrpools;
+		return nn->nfsd_serv->sv_nrpools;
 }
 
-int nfsd_get_nrthreads(int n, int *nthreads)
+int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 {
 	int i = 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	if (nfsd_serv != NULL) {
-		for (i = 0; i < nfsd_serv->sv_nrpools && i < n; i++)
-			nthreads[i] = nfsd_serv->sv_pools[i].sp_nrthreads;
+	if (nn->nfsd_serv != NULL) {
+		for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++)
+			nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads;
 	}
 
 	return 0;
 }
 
-int nfsd_set_nrthreads(int n, int *nthreads)
+void nfsd_destroy(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int destroy = (nn->nfsd_serv->sv_nrthreads == 1);
+
+	if (destroy)
+		svc_shutdown_net(nn->nfsd_serv, net);
+	svc_destroy(nn->nfsd_serv);
+	if (destroy)
+		nn->nfsd_serv = NULL;
+}
+
+int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 {
 	int i = 0;
 	int tot = 0;
 	int err = 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	if (nfsd_serv == NULL || n <= 0)
+	WARN_ON(!mutex_is_locked(&nfsd_mutex));
+
+	if (nn->nfsd_serv == NULL || n <= 0)
 		return 0;
 
-	if (n > nfsd_serv->sv_nrpools)
-		n = nfsd_serv->sv_nrpools;
+	if (n > nn->nfsd_serv->sv_nrpools)
+		n = nn->nfsd_serv->sv_nrpools;
 
 	/* enforce a global maximum number of threads */
 	tot = 0;
@@ -318,178 +494,140 @@ int nfsd_set_nrthreads(int n, int *nthreads)
 		nthreads[0] = 1;
 
 	/* apply the new numbers */
-	lock_kernel();
-	svc_get(nfsd_serv);
+	svc_get(nn->nfsd_serv);
 	for (i = 0; i < n; i++) {
-		err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i],
+		err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i],
 				    	  nthreads[i]);
 		if (err)
 			break;
 	}
-	svc_destroy(nfsd_serv);
-	unlock_kernel();
-
+	nfsd_destroy(net);
 	return err;
 }
 
+/*
+ * Adjust the number of threads and return the new number of threads.
+ * This is also the function that starts the server if necessary, if
+ * this is the first time nrservs is nonzero.
+ */
 int
-nfsd_svc(unsigned short port, int nrservs)
+nfsd_svc(int nrservs, struct net *net)
 {
 	int	error;
-	
-	lock_kernel();
+	bool	nfsd_up_before;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	mutex_lock(&nfsd_mutex);
 	dprintk("nfsd: creating service\n");
-	error = -EINVAL;
 	if (nrservs <= 0)
 		nrservs = 0;
 	if (nrservs > NFSD_MAXSERVS)
 		nrservs = NFSD_MAXSERVS;
-	
-	/* Readahead param cache - will no-op if it already exists */
-	error =	nfsd_racache_init(2*nrservs);
-	if (error<0)
+	error = 0;
+	if (nrservs == 0 && nn->nfsd_serv == NULL)
 		goto out;
-	nfs4_state_start();
 
-	nfsd_reset_versions();
+	error = nfsd_create_serv(net);
+	if (error)
+		goto out;
 
-	error = nfsd_create_serv();
+	nfsd_up_before = nn->nfsd_net_up;
 
+	error = nfsd_startup_net(nrservs, net);
 	if (error)
-		goto out;
-	error = nfsd_init_socks(port);
+		goto out_destroy;
+	error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
 	if (error)
-		goto failure;
-
-	error = svc_set_num_threads(nfsd_serv, NULL, nrservs);
- failure:
-	svc_destroy(nfsd_serv);		/* Release server */
- out:
-	unlock_kernel();
+		goto out_shutdown;
+	/* We are holding a reference to nn->nfsd_serv which
+	 * we don't want to count in the return value,
+	 * so subtract 1
+	 */
+	error = nn->nfsd_serv->sv_nrthreads - 1;
+out_shutdown:
+	if (error < 0 && !nfsd_up_before)
+		nfsd_shutdown_net(net);
+out_destroy:
+	nfsd_destroy(net);		/* Release server */
+out:
+	mutex_unlock(&nfsd_mutex);
 	return error;
 }
 
-static inline void
-update_thread_usage(int busy_threads)
-{
-	unsigned long prev_call;
-	unsigned long diff;
-	int decile;
-
-	spin_lock(&nfsd_call_lock);
-	prev_call = nfsd_last_call;
-	nfsd_last_call = jiffies;
-	decile = busy_threads*10/nfsdstats.th_cnt;
-	if (decile>0 && decile <= 10) {
-		diff = nfsd_last_call - prev_call;
-		if ( (nfsdstats.th_usage[decile-1] += diff) >= NFSD_USAGE_WRAP)
-			nfsdstats.th_usage[decile-1] -= NFSD_USAGE_WRAP;
-		if (decile == 10)
-			nfsdstats.th_fullcnt++;
-	}
-	spin_unlock(&nfsd_call_lock);
-}
 
 /*
  * This is the NFS server kernel thread
  */
-static void
-nfsd(struct svc_rqst *rqstp)
+static int
+nfsd(void *vrqstp)
 {
-	struct fs_struct *fsp;
-	int		err;
-	sigset_t shutdown_mask, allowed_mask;
+	struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
+	struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list);
+	struct net *net = perm_sock->xpt_net;
+	int err;
 
 	/* Lock module and set up kernel thread */
-	lock_kernel();
-	daemonize("nfsd");
+	mutex_lock(&nfsd_mutex);
 
-	/* After daemonize() this kernel thread shares current->fs
+	/* At this point, the thread shares current->fs
 	 * with the init process. We need to create files with a
 	 * umask of 0 instead of init's umask. */
-	fsp = copy_fs_struct(current->fs);
-	if (!fsp) {
+	if (unshare_fs_struct() < 0) {
 		printk("Unable to start nfsd thread: out of memory\n");
 		goto out;
 	}
-	exit_fs(current);
-	current->fs = fsp;
+
 	current->fs->umask = 0;
 
-	siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS);
-	siginitsetinv(&allowed_mask, ALLOWED_SIGS);
+	/*
+	 * thread is spawned with all signals set to SIG_IGN, re-enable
+	 * the ones that will bring down the thread
+	 */
+	allow_signal(SIGKILL);
+	allow_signal(SIGHUP);
+	allow_signal(SIGINT);
+	allow_signal(SIGQUIT);
 
 	nfsdstats.th_cnt++;
+	mutex_unlock(&nfsd_mutex);
 
-	rqstp->rq_task = current;
-
-	unlock_kernel();
-
-	/*
-	 * We want less throttling in balance_dirty_pages() so that nfs to
-	 * localhost doesn't cause nfsd to lock up due to all the client's
-	 * dirty pages.
-	 */
-	current->flags |= PF_LESS_THROTTLE;
 	set_freezable();
 
 	/*
 	 * The main request loop
 	 */
 	for (;;) {
-		/* Block all but the shutdown signals */
-		sigprocmask(SIG_SETMASK, &shutdown_mask, NULL);
-
 		/*
 		 * Find a socket with data available and call its
 		 * recvfrom routine.
 		 */
 		while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN)
 			;
-		if (err < 0)
+		if (err == -EINTR)
 			break;
-		update_thread_usage(atomic_read(&nfsd_busy));
-		atomic_inc(&nfsd_busy);
-
-		/* Lock the export hash tables for reading. */
-		exp_readlock();
-
-		/* Process request with signals blocked.  */
-		sigprocmask(SIG_SETMASK, &allowed_mask, NULL);
-
+		validate_process_creds();
 		svc_process(rqstp);
-
-		/* Unlock export hash tables */
-		exp_readunlock();
-		update_thread_usage(atomic_read(&nfsd_busy));
-		atomic_dec(&nfsd_busy);
+		validate_process_creds();
 	}
 
-	if (err != -EINTR) {
-		printk(KERN_WARNING "nfsd: terminating on error %d\n", -err);
-	} else {
-		unsigned int	signo;
-
-		for (signo = 1; signo <= _NSIG; signo++)
-			if (sigismember(&current->pending.signal, signo) &&
-			    !sigismember(&current->blocked, signo))
-				break;
-		killsig = signo;
-	}
 	/* Clear signals before calling svc_exit_thread() */
 	flush_signals(current);
 
-	lock_kernel();
-
+	mutex_lock(&nfsd_mutex);
 	nfsdstats.th_cnt --;
 
 out:
+	rqstp->rq_server = NULL;
+
 	/* Release the thread */
 	svc_exit_thread(rqstp);
 
+	nfsd_destroy(net);
+
 	/* Release module */
-	unlock_kernel();
+	mutex_unlock(&nfsd_mutex);
 	module_put_and_exit(0);
+	return 0;
 }
 
 static __be32 map_new_errors(u32 vers, __be32 nfserr)
@@ -513,27 +651,30 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 				rqstp->rq_vers, rqstp->rq_proc);
 	proc = rqstp->rq_procinfo;
 
-	/* Check whether we have this call in the cache. */
-	switch (nfsd_cache_lookup(rqstp, proc->pc_cachetype)) {
-	case RC_INTR:
-	case RC_DROPIT:
-		return 0;
-	case RC_REPLY:
-		return 1;
-	case RC_DOIT:;
-		/* do it */
-	}
-
+	/*
+	 * Give the xdr decoder a chance to change this if it wants
+	 * (necessary in the NFSv4.0 compound case)
+	 */
+	rqstp->rq_cachetype = proc->pc_cachetype;
 	/* Decode arguments */
 	xdr = proc->pc_decode;
 	if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base,
 			rqstp->rq_argp)) {
 		dprintk("nfsd: failed to decode arguments!\n");
-		nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
 		*statp = rpc_garbage_args;
 		return 1;
 	}
 
+	/* Check whether we have this call in the cache. */
+	switch (nfsd_cache_lookup(rqstp)) {
+	case RC_DROPIT:
+		return 0;
+	case RC_REPLY:
+		return 1;
+	case RC_DOIT:;
+		/* do it */
+	}
+
 	/* need to grab the location to store the status, as
 	 * nfsv4 does some encoding while processing 
 	 */
@@ -544,7 +685,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	/* Now call the procedure handler, and encode NFS status. */
 	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
-	if (nfserr == nfserr_dropit) {
+	if (nfserr == nfserr_dropit || rqstp->rq_dropme) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
 		nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
 		return 0;
@@ -569,6 +710,35 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	}
 
 	/* Store reply in cache. */
-	nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1);
+	nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1);
 	return 1;
 }
+
+int nfsd_pool_stats_open(struct inode *inode, struct file *file)
+{
+	int ret;
+	struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
+
+	mutex_lock(&nfsd_mutex);
+	if (nn->nfsd_serv == NULL) {
+		mutex_unlock(&nfsd_mutex);
+		return -ENODEV;
+	}
+	/* bump up the psudo refcount while traversing */
+	svc_get(nn->nfsd_serv);
+	ret = svc_pool_stats_open(nn->nfsd_serv, file);
+	mutex_unlock(&nfsd_mutex);
+	return ret;
+}
+
+int nfsd_pool_stats_release(struct inode *inode, struct file *file)
+{
+	int ret = seq_release(inode, file);
+	struct net *net = inode->i_sb->s_fs_info;
+
+	mutex_lock(&nfsd_mutex);
+	/* this function really, really should have been called svc_put() */
+	nfsd_destroy(net);
+	mutex_unlock(&nfsd_mutex);
+	return ret;
+}