Merge git://git.linux-nfs.org/pub/linux/nfs-2.6

* git://git.linux-nfs.org/pub/linux/nfs-2.6: (74 commits)
  NFS: unmark NFS direct I/O as experimental
  NFS: add comments clarifying the use of nfs_post_op_update()
  NFSv4: rpc_mkpipe creating socket inodes w/out sk buffers
  NFS: Use SEEK_END instead of hardcoded value
  NFSv4: When mounting with a port=0 argument, substitute port=2049
  NFSv4: Poll more aggressively when handling NFS4ERR_DELAY
  NFSv4: Handle the condition NFS4ERR_FILE_OPEN
  NFSv4: Retry lease recovery if it failed during a synchronous operation.
  NFS: Don't invalidate the symlink we just stuffed into the cache
  NFS: Make read() return an ESTALE if the file has been deleted
  NFSv4: It's perfectly legal for clp to be NULL here....
  NFS: nfs_lookup - don't hash dentry when optimising away the lookup
  SUNRPC: Fix Oops in pmap_getport_done
  SUNRPC: Add refcounting to the struct rpc_xprt
  SUNRPC: Clean up soft task error handling
  SUNRPC: Handle ENETUNREACH, EHOSTUNREACH and EHOSTDOWN socket errors
  SUNRPC: rpc_delay() should not clobber the rpc_task->tk_status
  Fix a referral error Oops
  NFS: NFS_ROOT should use the new rpc_create API
  NFS: Fix up compiler warnings on 64-bit platforms in client.c
  ...

Manually resolved conflict in net/sunrpc/xprtsock.c

block/ll_rw_blk.c

@@ -2734,6 +2734,18 @@ long blk_congestion_wait(int rw, long timeout)
 
 EXPORT_SYMBOL(blk_congestion_wait);
 
+/**
+ * blk_congestion_end - wake up sleepers on a congestion queue
+ * @rw: READ or WRITE
+ */
+void blk_congestion_end(int rw)
+{
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+
 /*
  * Has to be called with the request spinlock acquired
  */

fs/Kconfig

@@ -1471,8 +1471,8 @@ config NFS_V4
 	  If unsure, say N.
 
 config NFS_DIRECTIO
-	bool "Allow direct I/O on NFS files (EXPERIMENTAL)"
-	depends on NFS_FS && EXPERIMENTAL
+	bool "Allow direct I/O on NFS files"
+	depends on NFS_FS
 	help
 	  This option enables applications to perform uncached I/O on files
 	  in NFS file systems using the O_DIRECT open() flag.  When O_DIRECT

fs/dcache.c

@@ -828,17 +828,19 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
  * (or otherwise set) by the caller to indicate that it is now
  * in use by the dcache.
  */
-struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
+static struct dentry *__d_instantiate_unique(struct dentry *entry,
+					     struct inode *inode)
 {
 	struct dentry *alias;
 	int len = entry->d_name.len;
 	const char *name = entry->d_name.name;
 	unsigned int hash = entry->d_name.hash;
 
-	BUG_ON(!list_empty(&entry->d_alias));
-	spin_lock(&dcache_lock);
-	if (!inode)
-		goto do_negative;
+	if (!inode) {
+		entry->d_inode = NULL;
+		return NULL;
+	}
+
 	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
 		struct qstr *qstr = &alias->d_name;
 
@@ -851,19 +853,35 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 		if (memcmp(qstr->name, name, len))
 			continue;
 		dget_locked(alias);
-		spin_unlock(&dcache_lock);
-		BUG_ON(!d_unhashed(alias));
-		iput(inode);
 		return alias;
 	}
+
 	list_add(&entry->d_alias, &inode->i_dentry);
-do_negative:
 	entry->d_inode = inode;
 	fsnotify_d_instantiate(entry, inode);
-	spin_unlock(&dcache_lock);
-	security_d_instantiate(entry, inode);
 	return NULL;
 }
+
+struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
+{
+	struct dentry *result;
+
+	BUG_ON(!list_empty(&entry->d_alias));
+
+	spin_lock(&dcache_lock);
+	result = __d_instantiate_unique(entry, inode);
+	spin_unlock(&dcache_lock);
+
+	if (!result) {
+		security_d_instantiate(entry, inode);
+		return NULL;
+	}
+
+	BUG_ON(!d_unhashed(result));
+	iput(inode);
+	return result;
+}
+
 EXPORT_SYMBOL(d_instantiate_unique);
 
 /**
@@ -1235,6 +1253,11 @@ static void __d_rehash(struct dentry * entry, struct hlist_head *list)
  	hlist_add_head_rcu(&entry->d_hash, list);
 }
 
+static void _d_rehash(struct dentry * entry)
+{
+	__d_rehash(entry, d_hash(entry->d_parent, entry->d_name.hash));
+}
+
 /**
  * d_rehash	- add an entry back to the hash
  * @entry: dentry to add to the hash
@@ -1244,11 +1267,9 @@ static void __d_rehash(struct dentry * entry, struct hlist_head *list)
  
 void d_rehash(struct dentry * entry)
 {
-	struct hlist_head *list = d_hash(entry->d_parent, entry->d_name.hash);
-
 	spin_lock(&dcache_lock);
 	spin_lock(&entry->d_lock);
-	__d_rehash(entry, list);
+	_d_rehash(entry);
 	spin_unlock(&entry->d_lock);
 	spin_unlock(&dcache_lock);
 }
@@ -1386,6 +1407,120 @@ already_unhashed:
 	spin_unlock(&dcache_lock);
 }
 
+/*
+ * Prepare an anonymous dentry for life in the superblock's dentry tree as a
+ * named dentry in place of the dentry to be replaced.
+ */
+static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
+{
+	struct dentry *dparent, *aparent;
+
+	switch_names(dentry, anon);
+	do_switch(dentry->d_name.len, anon->d_name.len);
+	do_switch(dentry->d_name.hash, anon->d_name.hash);
+
+	dparent = dentry->d_parent;
+	aparent = anon->d_parent;
+
+	dentry->d_parent = (aparent == anon) ? dentry : aparent;
+	list_del(&dentry->d_u.d_child);
+	if (!IS_ROOT(dentry))
+		list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+	else
+		INIT_LIST_HEAD(&dentry->d_u.d_child);
+
+	anon->d_parent = (dparent == dentry) ? anon : dparent;
+	list_del(&anon->d_u.d_child);
+	if (!IS_ROOT(anon))
+		list_add(&anon->d_u.d_child, &anon->d_parent->d_subdirs);
+	else
+		INIT_LIST_HEAD(&anon->d_u.d_child);
+
+	anon->d_flags &= ~DCACHE_DISCONNECTED;
+}
+
+/**
+ * d_materialise_unique - introduce an inode into the tree
+ * @dentry: candidate dentry
+ * @inode: inode to bind to the dentry, to which aliases may be attached
+ *
+ * Introduces an dentry into the tree, substituting an extant disconnected
+ * root directory alias in its place if there is one
+ */
+struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
+{
+	struct dentry *alias, *actual;
+
+	BUG_ON(!d_unhashed(dentry));
+
+	spin_lock(&dcache_lock);
+
+	if (!inode) {
+		actual = dentry;
+		dentry->d_inode = NULL;
+		goto found_lock;
+	}
+
+	/* See if a disconnected directory already exists as an anonymous root
+	 * that we should splice into the tree instead */
+	if (S_ISDIR(inode->i_mode) && (alias = __d_find_alias(inode, 1))) {
+		spin_lock(&alias->d_lock);
+
+		/* Is this a mountpoint that we could splice into our tree? */
+		if (IS_ROOT(alias))
+			goto connect_mountpoint;
+
+		if (alias->d_name.len == dentry->d_name.len &&
+		    alias->d_parent == dentry->d_parent &&
+		    memcmp(alias->d_name.name,
+			   dentry->d_name.name,
+			   dentry->d_name.len) == 0)
+			goto replace_with_alias;
+
+		spin_unlock(&alias->d_lock);
+
+		/* Doh! Seem to be aliasing directories for some reason... */
+		dput(alias);
+	}
+
+	/* Add a unique reference */
+	actual = __d_instantiate_unique(dentry, inode);
+	if (!actual)
+		actual = dentry;
+	else if (unlikely(!d_unhashed(actual)))
+		goto shouldnt_be_hashed;
+
+found_lock:
+	spin_lock(&actual->d_lock);
+found:
+	_d_rehash(actual);
+	spin_unlock(&actual->d_lock);
+	spin_unlock(&dcache_lock);
+
+	if (actual == dentry) {
+		security_d_instantiate(dentry, inode);
+		return NULL;
+	}
+
+	iput(inode);
+	return actual;
+
+	/* Convert the anonymous/root alias into an ordinary dentry */
+connect_mountpoint:
+	__d_materialise_dentry(dentry, alias);
+
+	/* Replace the candidate dentry with the alias in the tree */
+replace_with_alias:
+	__d_drop(alias);
+	actual = alias;
+	goto found;
+
+shouldnt_be_hashed:
+	spin_unlock(&dcache_lock);
+	BUG();
+	goto shouldnt_be_hashed;
+}
+
 /**
  * d_path - return the path of a dentry
  * @dentry: dentry to report
@@ -1784,6 +1919,7 @@ EXPORT_SYMBOL(d_instantiate);
 EXPORT_SYMBOL(d_invalidate);
 EXPORT_SYMBOL(d_lookup);
 EXPORT_SYMBOL(d_move);
+EXPORT_SYMBOL_GPL(d_materialise_unique);
 EXPORT_SYMBOL(d_path);
 EXPORT_SYMBOL(d_prune_aliases);
 EXPORT_SYMBOL(d_rehash);

fs/lockd/clntproc.c

@@ -151,11 +151,13 @@ static void nlmclnt_release_lockargs(struct nlm_rqst *req)
 int
 nlmclnt_proc(struct inode *inode, int cmd, struct file_lock *fl)
 {
+	struct rpc_clnt		*client = NFS_CLIENT(inode);
+	struct sockaddr_in	addr;
 	struct nlm_host		*host;
 	struct nlm_rqst		*call;
 	sigset_t		oldset;
 	unsigned long		flags;
-	int			status, proto, vers;
+	int			status, vers;
 
 	vers = (NFS_PROTO(inode)->version == 3) ? 4 : 1;
 	if (NFS_PROTO(inode)->version > 3) {
@@ -163,10 +165,8 @@ nlmclnt_proc(struct inode *inode, int cmd, struct file_lock *fl)
 		return -ENOLCK;
 	}
 
-	/* Retrieve transport protocol from NFS client */
-	proto = NFS_CLIENT(inode)->cl_xprt->prot;
-
-	host = nlmclnt_lookup_host(NFS_ADDR(inode), proto, vers);
+	rpc_peeraddr(client, (struct sockaddr *) &addr, sizeof(addr));
+	host = nlmclnt_lookup_host(&addr, client->cl_xprt->prot, vers);
 	if (host == NULL)
 		return -ENOLCK;
 

fs/lockd/host.c

@@ -26,7 +26,6 @@
 #define NLM_HOST_REBIND		(60 * HZ)
 #define NLM_HOST_EXPIRE		((nrhosts > NLM_HOST_MAX)? 300 * HZ : 120 * HZ)
 #define NLM_HOST_COLLECT	((nrhosts > NLM_HOST_MAX)? 120 * HZ :  60 * HZ)
-#define NLM_HOST_ADDR(sv)	(&(sv)->s_nlmclnt->cl_xprt->addr)
 
 static struct nlm_host *	nlm_hosts[NLM_HOST_NRHASH];
 static unsigned long		next_gc;
@@ -167,7 +166,6 @@ struct rpc_clnt *
 nlm_bind_host(struct nlm_host *host)
 {
 	struct rpc_clnt	*clnt;
-	struct rpc_xprt	*xprt;
 
 	dprintk("lockd: nlm_bind_host(%08x)\n",
 			(unsigned)ntohl(host->h_addr.sin_addr.s_addr));
@@ -179,7 +177,6 @@ nlm_bind_host(struct nlm_host *host)
 	 * RPC rebind is required
 	 */
 	if ((clnt = host->h_rpcclnt) != NULL) {
-		xprt = clnt->cl_xprt;
 		if (time_after_eq(jiffies, host->h_nextrebind)) {
 			rpc_force_rebind(clnt);
 			host->h_nextrebind = jiffies + NLM_HOST_REBIND;
@@ -187,31 +184,37 @@ nlm_bind_host(struct nlm_host *host)
 					host->h_nextrebind - jiffies);
 		}
 	} else {
-		xprt = xprt_create_proto(host->h_proto, &host->h_addr, NULL);
-		if (IS_ERR(xprt))
-			goto forgetit;
-
-		xprt_set_timeout(&xprt->timeout, 5, nlmsvc_timeout);
-		xprt->resvport = 1;	/* NLM requires a reserved port */
-
-		/* Existing NLM servers accept AUTH_UNIX only */
-		clnt = rpc_new_client(xprt, host->h_name, &nlm_program,
-					host->h_version, RPC_AUTH_UNIX);
-		if (IS_ERR(clnt))
-			goto forgetit;
-		clnt->cl_autobind = 1;	/* turn on pmap queries */
-		clnt->cl_softrtry = 1; /* All queries are soft */
-
-		host->h_rpcclnt = clnt;
+		unsigned long increment = nlmsvc_timeout * HZ;
+		struct rpc_timeout timeparms = {
+			.to_initval	= increment,
+			.to_increment	= increment,
+			.to_maxval	= increment * 6UL,
+			.to_retries	= 5U,
+		};
+		struct rpc_create_args args = {
+			.protocol	= host->h_proto,
+			.address	= (struct sockaddr *)&host->h_addr,
+			.addrsize	= sizeof(host->h_addr),
+			.timeout	= &timeparms,
+			.servername	= host->h_name,
+			.program	= &nlm_program,
+			.version	= host->h_version,
+			.authflavor	= RPC_AUTH_UNIX,
+			.flags		= (RPC_CLNT_CREATE_HARDRTRY |
+					   RPC_CLNT_CREATE_AUTOBIND),
+		};
+
+		clnt = rpc_create(&args);
+		if (!IS_ERR(clnt))
+			host->h_rpcclnt = clnt;
+		else {
+			printk("lockd: couldn't create RPC handle for %s\n", host->h_name);
+			clnt = NULL;
+		}
 	}
 
 	mutex_unlock(&host->h_mutex);
 	return clnt;
-
-forgetit:
-	printk("lockd: couldn't create RPC handle for %s\n", host->h_name);
-	mutex_unlock(&host->h_mutex);
-	return NULL;
 }
 
 /*

fs/lockd/mon.c

@@ -109,30 +109,23 @@ nsm_unmonitor(struct nlm_host *host)
 static struct rpc_clnt *
 nsm_create(void)
 {
-	struct rpc_xprt		*xprt;
-	struct rpc_clnt		*clnt;
-	struct sockaddr_in	sin;
-
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	sin.sin_port = 0;
-
-	xprt = xprt_create_proto(IPPROTO_UDP, &sin, NULL);
-	if (IS_ERR(xprt))
-		return (struct rpc_clnt *)xprt;
-	xprt->resvport = 1;	/* NSM requires a reserved port */
-
-	clnt = rpc_create_client(xprt, "localhost",
-				&nsm_program, SM_VERSION,
-				RPC_AUTH_NULL);
-	if (IS_ERR(clnt))
-		goto out_err;
-	clnt->cl_softrtry = 1;
-	clnt->cl_oneshot  = 1;
-	return clnt;
-
-out_err:
-	return clnt;
+	struct sockaddr_in	sin = {
+		.sin_family	= AF_INET,
+		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
+		.sin_port	= 0,
+	};
+	struct rpc_create_args args = {
+		.protocol	= IPPROTO_UDP,
+		.address	= (struct sockaddr *)&sin,
+		.addrsize	= sizeof(sin),
+		.servername	= "localhost",
+		.program	= &nsm_program,
+		.version	= SM_VERSION,
+		.authflavor	= RPC_AUTH_NULL,
+		.flags		= (RPC_CLNT_CREATE_ONESHOT),
+	};
+
+	return rpc_create(&args);
 }
 
 /*

fs/nfs/Makefile

@@ -4,9 +4,9 @@
 
 obj-$(CONFIG_NFS_FS) += nfs.o
 
-nfs-y 			:= dir.o file.o inode.o super.o nfs2xdr.o pagelist.o \
-			   proc.o read.o symlink.o unlink.o write.o \
-			   namespace.o
+nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \
+			   pagelist.o proc.o read.o symlink.o unlink.o \
+			   write.o namespace.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o mount_clnt.o      
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o

fs/nfs/callback.c

@@ -19,6 +19,7 @@
 
 #include "nfs4_fs.h"
 #include "callback.h"
+#include "internal.h"
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
@@ -36,6 +37,21 @@ static struct svc_program nfs4_callback_program;
 
 unsigned int nfs_callback_set_tcpport;
 unsigned short nfs_callback_tcpport;
+static const int nfs_set_port_min = 0;
+static const int nfs_set_port_max = 65535;
+
+static int param_set_port(const char *val, struct kernel_param *kp)
+{
+	char *endp;
+	int num = simple_strtol(val, &endp, 0);
+	if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
+		return -EINVAL;
+	*((int *)kp->arg) = num;
+	return 0;
+}
+
+module_param_call(callback_tcpport, param_set_port, param_get_int,
+		 &nfs_callback_set_tcpport, 0644);
 
 /*
  * This is the callback kernel thread.
@@ -134,10 +150,8 @@ out_err:
 /*
  * Kill the server process if it is not already up.
  */
-int nfs_callback_down(void)
+void nfs_callback_down(void)
 {
-	int ret = 0;
-
 	lock_kernel();
 	mutex_lock(&nfs_callback_mutex);
 	nfs_callback_info.users--;
@@ -149,20 +163,19 @@ int nfs_callback_down(void)
 	} while (wait_for_completion_timeout(&nfs_callback_info.stopped, 5*HZ) == 0);
 	mutex_unlock(&nfs_callback_mutex);
 	unlock_kernel();
-	return ret;
 }
 
 static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 {
-	struct in_addr *addr = &rqstp->rq_addr.sin_addr;
-	struct nfs4_client *clp;
+	struct sockaddr_in *addr = &rqstp->rq_addr;
+	struct nfs_client *clp;
 
 	/* Don't talk to strangers */
-	clp = nfs4_find_client(addr);
+	clp = nfs_find_client(addr, 4);
 	if (clp == NULL)
 		return SVC_DROP;
-	dprintk("%s: %u.%u.%u.%u NFSv4 callback!\n", __FUNCTION__, NIPQUAD(addr));
-	nfs4_put_client(clp);
+	dprintk("%s: %u.%u.%u.%u NFSv4 callback!\n", __FUNCTION__, NIPQUAD(addr->sin_addr));
+	nfs_put_client(clp);
 	switch (rqstp->rq_authop->flavour) {
 		case RPC_AUTH_NULL:
 			if (rqstp->rq_proc != CB_NULL)

fs/nfs/callback.h

@@ -62,8 +62,13 @@ struct cb_recallargs {
 extern unsigned nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res);
 extern unsigned nfs4_callback_recall(struct cb_recallargs *args, void *dummy);
 
+#ifdef CONFIG_NFS_V4
 extern int nfs_callback_up(void);
-extern int nfs_callback_down(void);
+extern void nfs_callback_down(void);
+#else
+#define nfs_callback_up()	(0)
+#define nfs_callback_down()	do {} while(0)
+#endif
 
 extern unsigned int nfs_callback_set_tcpport;
 extern unsigned short nfs_callback_tcpport;

fs/nfs/callback_proc.c

@@ -10,19 +10,20 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
+#include "internal.h"
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
  
 unsigned nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res)
 {
-	struct nfs4_client *clp;
+	struct nfs_client *clp;
 	struct nfs_delegation *delegation;
 	struct nfs_inode *nfsi;
 	struct inode *inode;
 	
 	res->bitmap[0] = res->bitmap[1] = 0;
 	res->status = htonl(NFS4ERR_BADHANDLE);
-	clp = nfs4_find_client(&args->addr->sin_addr);
+	clp = nfs_find_client(args->addr, 4);
 	if (clp == NULL)
 		goto out;
 	inode = nfs_delegation_find_inode(clp, &args->fh);
@@ -48,7 +49,7 @@ out_iput:
 	up_read(&nfsi->rwsem);
 	iput(inode);
 out_putclient:
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 out:
 	dprintk("%s: exit with status = %d\n", __FUNCTION__, ntohl(res->status));
 	return res->status;
@@ -56,12 +57,12 @@ out:
 
 unsigned nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 {
-	struct nfs4_client *clp;
+	struct nfs_client *clp;
 	struct inode *inode;
 	unsigned res;
 	
 	res = htonl(NFS4ERR_BADHANDLE);
-	clp = nfs4_find_client(&args->addr->sin_addr);
+	clp = nfs_find_client(args->addr, 4);
 	if (clp == NULL)
 		goto out;
 	inode = nfs_delegation_find_inode(clp, &args->fh);
@@ -80,7 +81,7 @@ unsigned nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 	}
 	iput(inode);
 out_putclient:
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 out:
 	dprintk("%s: exit with status = %d\n", __FUNCTION__, ntohl(res));
 	return res;

fs/nfs/client.c

@@ -0,0 +1,1448 @@
+/* client.c: NFS client sharing and management code
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/metrics.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/smp_lock.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/nfs_idmap.h>
+#include <linux/vfs.h>
+#include <linux/inet.h>
+#include <linux/nfs_xdr.h>
+
+#include <asm/system.h>
+
+#include "nfs4_fs.h"
+#include "callback.h"
+#include "delegation.h"
+#include "iostat.h"
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+static DEFINE_SPINLOCK(nfs_client_lock);
+static LIST_HEAD(nfs_client_list);
+static LIST_HEAD(nfs_volume_list);
+static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
+
+/*
+ * RPC cruft for NFS
+ */
+static struct rpc_version *nfs_version[5] = {
+	[2]			= &nfs_version2,
+#ifdef CONFIG_NFS_V3
+	[3]			= &nfs_version3,
+#endif
+#ifdef CONFIG_NFS_V4
+	[4]			= &nfs_version4,
+#endif
+};
+
+struct rpc_program nfs_program = {
+	.name			= "nfs",
+	.number			= NFS_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfs_version),
+	.version		= nfs_version,
+	.stats			= &nfs_rpcstat,
+	.pipe_dir_name		= "/nfs",
+};
+
+struct rpc_stat nfs_rpcstat = {
+	.program		= &nfs_program
+};
+
+
+#ifdef CONFIG_NFS_V3_ACL
+static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
+static struct rpc_version *	nfsacl_version[] = {
+	[3]			= &nfsacl_version3,
+};
+
+struct rpc_program		nfsacl_program = {
+	.name			= "nfsacl",
+	.number			= NFS_ACL_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfsacl_version),
+	.version		= nfsacl_version,
+	.stats			= &nfsacl_rpcstat,
+};
+#endif  /* CONFIG_NFS_V3_ACL */
+
+/*
+ * Allocate a shared client record
+ *
+ * Since these are allocated/deallocated very rarely, we don't
+ * bother putting them in a slab cache...
+ */
+static struct nfs_client *nfs_alloc_client(const char *hostname,
+					   const struct sockaddr_in *addr,
+					   int nfsversion)
+{
+	struct nfs_client *clp;
+	int error;
+
+	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
+		goto error_0;
+
+	error = rpciod_up();
+	if (error < 0) {
+		dprintk("%s: couldn't start rpciod! Error = %d\n",
+				__FUNCTION__, error);
+		goto error_1;
+	}
+	__set_bit(NFS_CS_RPCIOD, &clp->cl_res_state);
+
+	if (nfsversion == 4) {
+		if (nfs_callback_up() < 0)
+			goto error_2;
+		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
+	}
+
+	atomic_set(&clp->cl_count, 1);
+	clp->cl_cons_state = NFS_CS_INITING;
+
+	clp->cl_nfsversion = nfsversion;
+	memcpy(&clp->cl_addr, addr, sizeof(clp->cl_addr));
+
+	if (hostname) {
+		clp->cl_hostname = kstrdup(hostname, GFP_KERNEL);
+		if (!clp->cl_hostname)
+			goto error_3;
+	}
+
+	INIT_LIST_HEAD(&clp->cl_superblocks);
+	clp->cl_rpcclient = ERR_PTR(-EINVAL);
+
+#ifdef CONFIG_NFS_V4
+	init_rwsem(&clp->cl_sem);
+	INIT_LIST_HEAD(&clp->cl_delegations);
+	INIT_LIST_HEAD(&clp->cl_state_owners);
+	INIT_LIST_HEAD(&clp->cl_unused);
+	spin_lock_init(&clp->cl_lock);
+	INIT_WORK(&clp->cl_renewd, nfs4_renew_state, clp);
+	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
+	clp->cl_boot_time = CURRENT_TIME;
+	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
+#endif
+
+	return clp;
+
+error_3:
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down();
+error_2:
+	rpciod_down();
+	__clear_bit(NFS_CS_RPCIOD, &clp->cl_res_state);
+error_1:
+	kfree(clp);
+error_0:
+	return NULL;
+}
+
+static void nfs4_shutdown_client(struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4
+	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
+		nfs4_kill_renewd(clp);
+	while (!list_empty(&clp->cl_unused)) {
+		struct nfs4_state_owner *sp;
+
+		sp = list_entry(clp->cl_unused.next,
+				struct nfs4_state_owner,
+				so_list);
+		list_del(&sp->so_list);
+		kfree(sp);
+	}
+	BUG_ON(!list_empty(&clp->cl_state_owners));
+	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
+		nfs_idmap_delete(clp);
+#endif
+}
+
+/*
+ * Destroy a shared client record
+ */
+static void nfs_free_client(struct nfs_client *clp)
+{
+	dprintk("--> nfs_free_client(%d)\n", clp->cl_nfsversion);
+
+	nfs4_shutdown_client(clp);
+
+	/* -EIO all pending I/O */
+	if (!IS_ERR(clp->cl_rpcclient))
+		rpc_shutdown_client(clp->cl_rpcclient);
+
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down();
+
+	if (__test_and_clear_bit(NFS_CS_RPCIOD, &clp->cl_res_state))
+		rpciod_down();
+
+	kfree(clp->cl_hostname);
+	kfree(clp);
+
+	dprintk("<-- nfs_free_client()\n");
+}
+
+/*
+ * Release a reference to a shared client record
+ */
+void nfs_put_client(struct nfs_client *clp)
+{
+	if (!clp)
+		return;
+
+	dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
+
+	if (atomic_dec_and_lock(&clp->cl_count, &nfs_client_lock)) {
+		list_del(&clp->cl_share_link);
+		spin_unlock(&nfs_client_lock);
+
+		BUG_ON(!list_empty(&clp->cl_superblocks));
+
+		nfs_free_client(clp);
+	}
+}
+
+/*
+ * Find a client by address
+ * - caller must hold nfs_client_lock
+ */
+static struct nfs_client *__nfs_find_client(const struct sockaddr_in *addr, int nfsversion)
+{
+	struct nfs_client *clp;
+
+	list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+		/* Different NFS versions cannot share the same nfs_client */
+		if (clp->cl_nfsversion != nfsversion)
+			continue;
+
+		if (memcmp(&clp->cl_addr.sin_addr, &addr->sin_addr,
+			   sizeof(clp->cl_addr.sin_addr)) != 0)
+			continue;
+
+		if (clp->cl_addr.sin_port == addr->sin_port)
+			goto found;
+	}
+
+	return NULL;
+
+found:
+	atomic_inc(&clp->cl_count);
+	return clp;
+}
+
+/*
+ * Find a client by IP address and protocol version
+ * - returns NULL if no such client
+ */
+struct nfs_client *nfs_find_client(const struct sockaddr_in *addr, int nfsversion)
+{
+	struct nfs_client *clp;
+
+	spin_lock(&nfs_client_lock);
+	clp = __nfs_find_client(addr, nfsversion);
+	spin_unlock(&nfs_client_lock);
+
+	BUG_ON(clp && clp->cl_cons_state == 0);
+
+	return clp;
+}
+
+/*
+ * Look up a client by IP address and protocol version
+ * - creates a new record if one doesn't yet exist
+ */
+static struct nfs_client *nfs_get_client(const char *hostname,
+					 const struct sockaddr_in *addr,
+					 int nfsversion)
+{
+	struct nfs_client *clp, *new = NULL;
+	int error;
+
+	dprintk("--> nfs_get_client(%s,"NIPQUAD_FMT":%d,%d)\n",
+		hostname ?: "", NIPQUAD(addr->sin_addr),
+		addr->sin_port, nfsversion);
+
+	/* see if the client already exists */
+	do {
+		spin_lock(&nfs_client_lock);
+
+		clp = __nfs_find_client(addr, nfsversion);
+		if (clp)
+			goto found_client;
+		if (new)
+			goto install_client;
+
+		spin_unlock(&nfs_client_lock);
+
+		new = nfs_alloc_client(hostname, addr, nfsversion);
+	} while (new);
+
+	return ERR_PTR(-ENOMEM);
+
+	/* install a new client and return with it unready */
+install_client:
+	clp = new;
+	list_add(&clp->cl_share_link, &nfs_client_list);
+	spin_unlock(&nfs_client_lock);
+	dprintk("--> nfs_get_client() = %p [new]\n", clp);
+	return clp;
+
+	/* found an existing client
+	 * - make sure it's ready before returning
+	 */
+found_client:
+	spin_unlock(&nfs_client_lock);
+
+	if (new)
+		nfs_free_client(new);
+
+	if (clp->cl_cons_state == NFS_CS_INITING) {
+		DECLARE_WAITQUEUE(myself, current);
+
+		add_wait_queue(&nfs_client_active_wq, &myself);
+
+		for (;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			if (signal_pending(current) ||
+			    clp->cl_cons_state > NFS_CS_READY)
+				break;
+			schedule();
+		}
+
+		remove_wait_queue(&nfs_client_active_wq, &myself);
+
+		if (signal_pending(current)) {
+			nfs_put_client(clp);
+			return ERR_PTR(-ERESTARTSYS);
+		}
+	}
+
+	if (clp->cl_cons_state < NFS_CS_READY) {
+		error = clp->cl_cons_state;
+		nfs_put_client(clp);
+		return ERR_PTR(error);
+	}
+
+	BUG_ON(clp->cl_cons_state != NFS_CS_READY);
+
+	dprintk("--> nfs_get_client() = %p [share]\n", clp);
+	return clp;
+}
+
+/*
+ * Mark a server as ready or failed
+ */
+static void nfs_mark_client_ready(struct nfs_client *clp, int state)
+{
+	clp->cl_cons_state = state;
+	wake_up_all(&nfs_client_active_wq);
+}
+
+/*
+ * Initialise the timeout values for a connection
+ */
+static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
+				    unsigned int timeo, unsigned int retrans)
+{
+	to->to_initval = timeo * HZ / 10;
+	to->to_retries = retrans;
+	if (!to->to_retries)
+		to->to_retries = 2;
+
+	switch (proto) {
+	case IPPROTO_TCP:
+		if (!to->to_initval)
+			to->to_initval = 60 * HZ;
+		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
+			to->to_initval = NFS_MAX_TCP_TIMEOUT;
+		to->to_increment = to->to_initval;
+		to->to_maxval = to->to_initval + (to->to_increment * to->to_retries);
+		to->to_exponential = 0;
+		break;
+	case IPPROTO_UDP:
+	default:
+		if (!to->to_initval)
+			to->to_initval = 11 * HZ / 10;
+		if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
+			to->to_initval = NFS_MAX_UDP_TIMEOUT;
+		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
+		to->to_exponential = 1;
+		break;
+	}
+}
+
+/*
+ * Create an RPC client handle
+ */
+static int nfs_create_rpc_client(struct nfs_client *clp, int proto,
+						unsigned int timeo,
+						unsigned int retrans,
+						rpc_authflavor_t flavor)
+{
+	struct rpc_timeout	timeparms;
+	struct rpc_clnt		*clnt = NULL;
+	struct rpc_create_args args = {
+		.protocol	= proto,
+		.address	= (struct sockaddr *)&clp->cl_addr,
+		.addrsize	= sizeof(clp->cl_addr),
+		.timeout	= &timeparms,
+		.servername	= clp->cl_hostname,
+		.program	= &nfs_program,
+		.version	= clp->rpc_ops->version,
+		.authflavor	= flavor,
+	};
+
+	if (!IS_ERR(clp->cl_rpcclient))
+		return 0;
+
+	nfs_init_timeout_values(&timeparms, proto, timeo, retrans);
+	clp->retrans_timeo = timeparms.to_initval;
+	clp->retrans_count = timeparms.to_retries;
+
+	clnt = rpc_create(&args);
+	if (IS_ERR(clnt)) {
+		dprintk("%s: cannot create RPC client. Error = %ld\n",
+				__FUNCTION__, PTR_ERR(clnt));
+		return PTR_ERR(clnt);
+	}
+
+	clp->cl_rpcclient = clnt;
+	return 0;
+}
+
+/*
+ * Version 2 or 3 client destruction
+ */
+static void nfs_destroy_server(struct nfs_server *server)
+{
+	if (!IS_ERR(server->client_acl))
+		rpc_shutdown_client(server->client_acl);
+
+	if (!(server->flags & NFS_MOUNT_NONLM))
+		lockd_down();	/* release rpc.lockd */
+}
+
+/*
+ * Version 2 or 3 lockd setup
+ */
+static int nfs_start_lockd(struct nfs_server *server)
+{
+	int error = 0;
+
+	if (server->nfs_client->cl_nfsversion > 3)
+		goto out;
+	if (server->flags & NFS_MOUNT_NONLM)
+		goto out;
+	error = lockd_up();
+	if (error < 0)
+		server->flags |= NFS_MOUNT_NONLM;
+	else
+		server->destroy = nfs_destroy_server;
+out:
+	return error;
+}
+
+/*
+ * Initialise an NFSv3 ACL client connection
+ */
+#ifdef CONFIG_NFS_V3_ACL
+static void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	if (server->nfs_client->cl_nfsversion != 3)
+		goto out_noacl;
+	if (server->flags & NFS_MOUNT_NOACL)
+		goto out_noacl;
+
+	server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
+	if (IS_ERR(server->client_acl))
+		goto out_noacl;
+
+	/* No errors! Assume that Sun nfsacls are supported */
+	server->caps |= NFS_CAP_ACLS;
+	return;
+
+out_noacl:
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#else
+static inline void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	server->flags &= ~NFS_MOUNT_NOACL;
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#endif
+
+/*
+ * Create a general RPC client
+ */
+static int nfs_init_server_rpcclient(struct nfs_server *server, rpc_authflavor_t pseudoflavour)
+{
+	struct nfs_client *clp = server->nfs_client;
+
+	server->client = rpc_clone_client(clp->cl_rpcclient);
+	if (IS_ERR(server->client)) {
+		dprintk("%s: couldn't create rpc_client!\n", __FUNCTION__);
+		return PTR_ERR(server->client);
+	}
+
+	if (pseudoflavour != clp->cl_rpcclient->cl_auth->au_flavor) {
+		struct rpc_auth *auth;
+
+		auth = rpcauth_create(pseudoflavour, server->client);
+		if (IS_ERR(auth)) {
+			dprintk("%s: couldn't create credcache!\n", __FUNCTION__);
+			return PTR_ERR(auth);
+		}
+	}
+	server->client->cl_softrtry = 0;
+	if (server->flags & NFS_MOUNT_SOFT)
+		server->client->cl_softrtry = 1;
+
+	server->client->cl_intr = 0;
+	if (server->flags & NFS4_MOUNT_INTR)
+		server->client->cl_intr = 1;
+
+	return 0;
+}
+
+/*
+ * Initialise an NFS2 or NFS3 client
+ */
+static int nfs_init_client(struct nfs_client *clp, const struct nfs_mount_data *data)
+{
+	int proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is already initialised */
+		dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp);
+		return 0;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v2_clientops;
+#ifdef CONFIG_NFS_V3
+	if (clp->cl_nfsversion == 3)
+		clp->rpc_ops = &nfs_v3_clientops;
+#endif
+	/*
+	 * Create a client RPC handle for doing FSSTAT with UNIX auth only
+	 * - RFC 2623, sec 2.3.2
+	 */
+	error = nfs_create_rpc_client(clp, proto, data->timeo, data->retrans,
+			RPC_AUTH_UNIX);
+	if (error < 0)
+		goto error;
+	nfs_mark_client_ready(clp, NFS_CS_READY);
+	return 0;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	dprintk("<-- nfs_init_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 2 or 3 client
+ */
+static int nfs_init_server(struct nfs_server *server, const struct nfs_mount_data *data)
+{
+	struct nfs_client *clp;
+	int error, nfsvers = 2;
+
+	dprintk("--> nfs_init_server()\n");
+
+#ifdef CONFIG_NFS_V3
+	if (data->flags & NFS_MOUNT_VER3)
+		nfsvers = 3;
+#endif
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(data->hostname, &data->addr, nfsvers);
+	if (IS_ERR(clp)) {
+		dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
+		return PTR_ERR(clp);
+	}
+
+	error = nfs_init_client(clp, data);
+	if (error < 0)
+		goto error;
+
+	server->nfs_client = clp;
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	/* Start lockd here, before we might error out */
+	error = nfs_start_lockd(server);
+	if (error < 0)
+		goto error;
+
+	error = nfs_init_server_rpcclient(server, data->pseudoflavor);
+	if (error < 0)
+		goto error;
+
+	server->namelen  = data->namlen;
+	/* Create a client RPC handle for the NFSv3 ACL management interface */
+	nfs_init_server_aclclient(server);
+	if (clp->cl_nfsversion == 3) {
+		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
+			server->namelen = NFS3_MAXNAMLEN;
+		server->caps |= NFS_CAP_READDIRPLUS;
+	} else {
+		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
+			server->namelen = NFS2_MAXNAMLEN;
+	}
+
+	dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
+	return 0;
+
+error:
+	server->nfs_client = NULL;
+	nfs_put_client(clp);
+	dprintk("<-- nfs_init_server() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Load up the server record from information gained in an fsinfo record
+ */
+static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo)
+{
+	unsigned long max_rpc_payload;
+
+	/* Work out a lot of parameters */
+	if (server->rsize == 0)
+		server->rsize = nfs_block_size(fsinfo->rtpref, NULL);
+	if (server->wsize == 0)
+		server->wsize = nfs_block_size(fsinfo->wtpref, NULL);
+
+	if (fsinfo->rtmax >= 512 && server->rsize > fsinfo->rtmax)
+		server->rsize = nfs_block_size(fsinfo->rtmax, NULL);
+	if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax)
+		server->wsize = nfs_block_size(fsinfo->wtmax, NULL);
+
+	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
+	if (server->rsize > max_rpc_payload)
+		server->rsize = max_rpc_payload;
+	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
+		server->rsize = NFS_MAX_FILE_IO_SIZE;
+	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
+
+	if (server->wsize > max_rpc_payload)
+		server->wsize = max_rpc_payload;
+	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
+		server->wsize = NFS_MAX_FILE_IO_SIZE;
+	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
+
+	server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
+	if (server->dtsize > PAGE_CACHE_SIZE)
+		server->dtsize = PAGE_CACHE_SIZE;
+	if (server->dtsize > server->rsize)
+		server->dtsize = server->rsize;
+
+	if (server->flags & NFS_MOUNT_NOAC) {
+		server->acregmin = server->acregmax = 0;
+		server->acdirmin = server->acdirmax = 0;
+	}
+
+	server->maxfilesize = fsinfo->maxfilesize;
+
+	/* We're airborne Set socket buffersize */
+	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
+}
+
+/*
+ * Probe filesystem information, including the FSID on v2/v3
+ */
+static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
+{
+	struct nfs_fsinfo fsinfo;
+	struct nfs_client *clp = server->nfs_client;
+	int error;
+
+	dprintk("--> nfs_probe_fsinfo()\n");
+
+	if (clp->rpc_ops->set_capabilities != NULL) {
+		error = clp->rpc_ops->set_capabilities(server, mntfh);
+		if (error < 0)
+			goto out_error;
+	}
+
+	fsinfo.fattr = fattr;
+	nfs_fattr_init(fattr);
+	error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
+	if (error < 0)
+		goto out_error;
+
+	nfs_server_set_fsinfo(server, &fsinfo);
+
+	/* Get some general file system info */
+	if (server->namelen == 0) {
+		struct nfs_pathconf pathinfo;
+
+		pathinfo.fattr = fattr;
+		nfs_fattr_init(fattr);
+
+		if (clp->rpc_ops->pathconf(server, mntfh, &pathinfo) >= 0)
+			server->namelen = pathinfo.max_namelen;
+	}
+
+	dprintk("<-- nfs_probe_fsinfo() = 0\n");
+	return 0;
+
+out_error:
+	dprintk("nfs_probe_fsinfo: error = %d\n", -error);
+	return error;
+}
+
+/*
+ * Copy useful information when duplicating a server record
+ */
+static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
+{
+	target->flags = source->flags;
+	target->acregmin = source->acregmin;
+	target->acregmax = source->acregmax;
+	target->acdirmin = source->acdirmin;
+	target->acdirmax = source->acdirmax;
+	target->caps = source->caps;
+}
+
+/*
+ * Allocate and initialise a server record
+ */
+static struct nfs_server *nfs_alloc_server(void)
+{
+	struct nfs_server *server;
+
+	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
+	if (!server)
+		return NULL;
+
+	server->client = server->client_acl = ERR_PTR(-EINVAL);
+
+	/* Zero out the NFS state stuff */
+	INIT_LIST_HEAD(&server->client_link);
+	INIT_LIST_HEAD(&server->master_link);
+
+	server->io_stats = nfs_alloc_iostats();
+	if (!server->io_stats) {
+		kfree(server);
+		return NULL;
+	}
+
+	return server;
+}
+
+/*
+ * Free up a server record
+ */
+void nfs_free_server(struct nfs_server *server)
+{
+	dprintk("--> nfs_free_server()\n");
+
+	spin_lock(&nfs_client_lock);
+	list_del(&server->client_link);
+	list_del(&server->master_link);
+	spin_unlock(&nfs_client_lock);
+
+	if (server->destroy != NULL)
+		server->destroy(server);
+	if (!IS_ERR(server->client))
+		rpc_shutdown_client(server->client);
+
+	nfs_put_client(server->nfs_client);
+
+	nfs_free_iostats(server->io_stats);
+	kfree(server);
+	nfs_release_automount_timer();
+	dprintk("<-- nfs_free_server()\n");
+}
+
+/*
+ * Create a version 2 or 3 volume record
+ * - keyed on server and FSID
+ */
+struct nfs_server *nfs_create_server(const struct nfs_mount_data *data,
+				     struct nfs_fh *mntfh)
+{
+	struct nfs_server *server;
+	struct nfs_fattr fattr;
+	int error;
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* Get a client representation */
+	error = nfs_init_server(server, data);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* Probe the root fh to retrieve its FSID */
+	error = nfs_probe_fsinfo(server, mntfh, &fattr);
+	if (error < 0)
+		goto error;
+	if (!(fattr.valid & NFS_ATTR_FATTR)) {
+		error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
+		if (error < 0) {
+			dprintk("nfs_create_server: getattr error = %d\n", -error);
+			goto error;
+		}
+	}
+	memcpy(&server->fsid, &fattr.fsid, sizeof(server->fsid));
+
+	dprintk("Server FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+	return server;
+
+error:
+	nfs_free_server(server);
+	return ERR_PTR(error);
+}
+
+#ifdef CONFIG_NFS_V4
+/*
+ * Initialise an NFS4 client record
+ */
+static int nfs4_init_client(struct nfs_client *clp,
+		int proto, int timeo, int retrans,
+		rpc_authflavor_t authflavour)
+{
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is initialised already */
+		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
+		return 0;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v4_clientops;
+
+	error = nfs_create_rpc_client(clp, proto, timeo, retrans, authflavour);
+	if (error < 0)
+		goto error;
+
+	error = nfs_idmap_new(clp);
+	if (error < 0) {
+		dprintk("%s: failed to create idmapper. Error = %d\n",
+			__FUNCTION__, error);
+		goto error;
+	}
+	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
+
+	nfs_mark_client_ready(clp, NFS_CS_READY);
+	return 0;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Set up an NFS4 client
+ */
+static int nfs4_set_client(struct nfs_server *server,
+		const char *hostname, const struct sockaddr_in *addr,
+		rpc_authflavor_t authflavour,
+		int proto, int timeo, int retrans)
+{
+	struct nfs_client *clp;
+	int error;
+
+	dprintk("--> nfs4_set_client()\n");
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(hostname, addr, 4);
+	if (IS_ERR(clp)) {
+		error = PTR_ERR(clp);
+		goto error;
+	}
+	error = nfs4_init_client(clp, proto, timeo, retrans, authflavour);
+	if (error < 0)
+		goto error_put;
+
+	server->nfs_client = clp;
+	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
+	return 0;
+
+error_put:
+	nfs_put_client(clp);
+error:
+	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ */
+static int nfs4_init_server(struct nfs_server *server,
+		const struct nfs4_mount_data *data, rpc_authflavor_t authflavour)
+{
+	int error;
+
+	dprintk("--> nfs4_init_server()\n");
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+	server->caps |= NFS_CAP_ATOMIC_OPEN;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	error = nfs_init_server_rpcclient(server, authflavour);
+
+	/* Done */
+	dprintk("<-- nfs4_init_server() = %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ * - keyed on server and FSID
+ */
+struct nfs_server *nfs4_create_server(const struct nfs4_mount_data *data,
+				      const char *hostname,
+				      const struct sockaddr_in *addr,
+				      const char *mntpath,
+				      const char *ip_addr,
+				      rpc_authflavor_t authflavour,
+				      struct nfs_fh *mntfh)
+{
+	struct nfs_fattr fattr;
+	struct nfs_server *server;
+	int error;
+
+	dprintk("--> nfs4_create_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* Get a client record */
+	error = nfs4_set_client(server, hostname, addr, authflavour,
+			data->proto, data->timeo, data->retrans);
+	if (error < 0)
+		goto error;
+
+	/* set up the general RPC client */
+	error = nfs4_init_server(server, data, authflavour);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* Probe the root fh to retrieve its FSID */
+	error = nfs4_path_walk(server, mntfh, mntpath);
+	if (error < 0)
+		goto error;
+
+	dprintk("Server FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+	dprintk("Mount FH: %d\n", mntfh->size);
+
+	error = nfs_probe_fsinfo(server, mntfh, &fattr);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+	dprintk("<-- nfs4_create_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+/*
+ * Create an NFS4 referral server record
+ */
+struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
+					       struct nfs_fh *fh)
+{
+	struct nfs_client *parent_client;
+	struct nfs_server *server, *parent_server;
+	struct nfs_fattr fattr;
+	int error;
+
+	dprintk("--> nfs4_create_referral_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	parent_server = NFS_SB(data->sb);
+	parent_client = parent_server->nfs_client;
+
+	/* Get a client representation.
+	 * Note: NFSv4 always uses TCP, */
+	error = nfs4_set_client(server, data->hostname, data->addr,
+			data->authflavor,
+			parent_server->client->cl_xprt->prot,
+			parent_client->retrans_timeo,
+			parent_client->retrans_count);
+	if (error < 0)
+		goto error;
+
+	/* Initialise the client representation from the parent server */
+	nfs_server_copy_userdata(server, parent_server);
+	server->caps |= NFS_CAP_ATOMIC_OPEN;
+
+	error = nfs_init_server_rpcclient(server, data->authflavor);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* probe the filesystem info for this server filesystem */
+	error = nfs_probe_fsinfo(server, fh, &fattr);
+	if (error < 0)
+		goto error;
+
+	dprintk("Referral FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+
+	dprintk("<-- nfs_create_referral_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+#endif /* CONFIG_NFS_V4 */
+
+/*
+ * Clone an NFS2, NFS3 or NFS4 server record
+ */
+struct nfs_server *nfs_clone_server(struct nfs_server *source,
+				    struct nfs_fh *fh,
+				    struct nfs_fattr *fattr)
+{
+	struct nfs_server *server;
+	struct nfs_fattr fattr_fsinfo;
+	int error;
+
+	dprintk("--> nfs_clone_server(,%llx:%llx,)\n",
+		(unsigned long long) fattr->fsid.major,
+		(unsigned long long) fattr->fsid.minor);
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* Copy data from the source */
+	server->nfs_client = source->nfs_client;
+	atomic_inc(&server->nfs_client->cl_count);
+	nfs_server_copy_userdata(server, source);
+
+	server->fsid = fattr->fsid;
+
+	error = nfs_init_server_rpcclient(server, source->client->cl_auth->au_flavor);
+	if (error < 0)
+		goto out_free_server;
+	if (!IS_ERR(source->client_acl))
+		nfs_init_server_aclclient(server);
+
+	/* probe the filesystem info for this server filesystem */
+	error = nfs_probe_fsinfo(server, fh, &fattr_fsinfo);
+	if (error < 0)
+		goto out_free_server;
+
+	dprintk("Cloned FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+
+	error = nfs_start_lockd(server);
+	if (error < 0)
+		goto out_free_server;
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+
+	dprintk("<-- nfs_clone_server() = %p\n", server);
+	return server;
+
+out_free_server:
+	nfs_free_server(server);
+	dprintk("<-- nfs_clone_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+#ifdef CONFIG_PROC_FS
+static struct proc_dir_entry *proc_fs_nfs;
+
+static int nfs_server_list_open(struct inode *inode, struct file *file);
+static void *nfs_server_list_start(struct seq_file *p, loff_t *pos);
+static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos);
+static void nfs_server_list_stop(struct seq_file *p, void *v);
+static int nfs_server_list_show(struct seq_file *m, void *v);
+
+static struct seq_operations nfs_server_list_ops = {
+	.start	= nfs_server_list_start,
+	.next	= nfs_server_list_next,
+	.stop	= nfs_server_list_stop,
+	.show	= nfs_server_list_show,
+};
+
+static struct file_operations nfs_server_list_fops = {
+	.open		= nfs_server_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int nfs_volume_list_open(struct inode *inode, struct file *file);
+static void *nfs_volume_list_start(struct seq_file *p, loff_t *pos);
+static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos);
+static void nfs_volume_list_stop(struct seq_file *p, void *v);
+static int nfs_volume_list_show(struct seq_file *m, void *v);
+
+static struct seq_operations nfs_volume_list_ops = {
+	.start	= nfs_volume_list_start,
+	.next	= nfs_volume_list_next,
+	.stop	= nfs_volume_list_stop,
+	.show	= nfs_volume_list_show,
+};
+
+static struct file_operations nfs_volume_list_fops = {
+	.open		= nfs_volume_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * open "/proc/fs/nfsfs/servers" which provides a summary of servers with which
+ * we're dealing
+ */
+static int nfs_server_list_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &nfs_server_list_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = PDE(inode)->data;
+
+	return 0;
+}
+
+/*
+ * set up the iterator to start reading from the server list and return the first item
+ */
+static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *_p;
+	loff_t pos = *_pos;
+
+	/* lock the list against modification */
+	spin_lock(&nfs_client_lock);
+
+	/* allow for the header line */
+	if (!pos)
+		return SEQ_START_TOKEN;
+	pos--;
+
+	/* find the n'th element in the list */
+	list_for_each(_p, &nfs_client_list)
+		if (!pos--)
+			break;
+
+	return _p != &nfs_client_list ? _p : NULL;
+}
+
+/*
+ * move to next server
+ */
+static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
+{
+	struct list_head *_p;
+
+	(*pos)++;
+
+	_p = v;
+	_p = (v == SEQ_START_TOKEN) ? nfs_client_list.next : _p->next;
+
+	return _p != &nfs_client_list ? _p : NULL;
+}
+
+/*
+ * clean up after reading from the transports list
+ */
+static void nfs_server_list_stop(struct seq_file *p, void *v)
+{
+	spin_unlock(&nfs_client_lock);
+}
+
+/*
+ * display a header line followed by a load of call lines
+ */
+static int nfs_server_list_show(struct seq_file *m, void *v)
+{
+	struct nfs_client *clp;
+
+	/* display header on line 1 */
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(m, "NV SERVER   PORT USE HOSTNAME\n");
+		return 0;
+	}
+
+	/* display one transport per line on subsequent lines */
+	clp = list_entry(v, struct nfs_client, cl_share_link);
+
+	seq_printf(m, "v%d %02x%02x%02x%02x %4hx %3d %s\n",
+		   clp->cl_nfsversion,
+		   NIPQUAD(clp->cl_addr.sin_addr),
+		   ntohs(clp->cl_addr.sin_port),
+		   atomic_read(&clp->cl_count),
+		   clp->cl_hostname);
+
+	return 0;
+}
+
+/*
+ * open "/proc/fs/nfsfs/volumes" which provides a summary of extant volumes
+ */
+static int nfs_volume_list_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &nfs_volume_list_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = PDE(inode)->data;
+
+	return 0;
+}
+
+/*
+ * set up the iterator to start reading from the volume list and return the first item
+ */
+static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *_p;
+	loff_t pos = *_pos;
+
+	/* lock the list against modification */
+	spin_lock(&nfs_client_lock);
+
+	/* allow for the header line */
+	if (!pos)
+		return SEQ_START_TOKEN;
+	pos--;
+
+	/* find the n'th element in the list */
+	list_for_each(_p, &nfs_volume_list)
+		if (!pos--)
+			break;
+
+	return _p != &nfs_volume_list ? _p : NULL;
+}
+
+/*
+ * move to next volume
+ */
+static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
+{
+	struct list_head *_p;
+
+	(*pos)++;
+
+	_p = v;
+	_p = (v == SEQ_START_TOKEN) ? nfs_volume_list.next : _p->next;
+
+	return _p != &nfs_volume_list ? _p : NULL;
+}
+
+/*
+ * clean up after reading from the transports list
+ */
+static void nfs_volume_list_stop(struct seq_file *p, void *v)
+{
+	spin_unlock(&nfs_client_lock);
+}
+
+/*
+ * display a header line followed by a load of call lines
+ */
+static int nfs_volume_list_show(struct seq_file *m, void *v)
+{
+	struct nfs_server *server;
+	struct nfs_client *clp;
+	char dev[8], fsid[17];
+
+	/* display header on line 1 */
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(m, "NV SERVER   PORT DEV     FSID\n");
+		return 0;
+	}
+	/* display one transport per line on subsequent lines */
+	server = list_entry(v, struct nfs_server, master_link);
+	clp = server->nfs_client;
+
+	snprintf(dev, 8, "%u:%u",
+		 MAJOR(server->s_dev), MINOR(server->s_dev));
+
+	snprintf(fsid, 17, "%llx:%llx",
+		 (unsigned long long) server->fsid.major,
+		 (unsigned long long) server->fsid.minor);
+
+	seq_printf(m, "v%d %02x%02x%02x%02x %4hx %-7s %-17s\n",
+		   clp->cl_nfsversion,
+		   NIPQUAD(clp->cl_addr.sin_addr),
+		   ntohs(clp->cl_addr.sin_port),
+		   dev,
+		   fsid);
+
+	return 0;
+}
+
+/*
+ * initialise the /proc/fs/nfsfs/ directory
+ */
+int __init nfs_fs_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	proc_fs_nfs = proc_mkdir("nfsfs", proc_root_fs);
+	if (!proc_fs_nfs)
+		goto error_0;
+
+	proc_fs_nfs->owner = THIS_MODULE;
+
+	/* a file of servers with which we're dealing */
+	p = create_proc_entry("servers", S_IFREG|S_IRUGO, proc_fs_nfs);
+	if (!p)
+		goto error_1;
+
+	p->proc_fops = &nfs_server_list_fops;
+	p->owner = THIS_MODULE;
+
+	/* a file of volumes that we have mounted */
+	p = create_proc_entry("volumes", S_IFREG|S_IRUGO, proc_fs_nfs);
+	if (!p)
+		goto error_2;
+
+	p->proc_fops = &nfs_volume_list_fops;
+	p->owner = THIS_MODULE;
+	return 0;
+
+error_2:
+	remove_proc_entry("servers", proc_fs_nfs);
+error_1:
+	remove_proc_entry("nfsfs", proc_root_fs);
+error_0:
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/nfsfs/ directory
+ */
+void nfs_fs_proc_exit(void)
+{
+	remove_proc_entry("volumes", proc_fs_nfs);
+	remove_proc_entry("servers", proc_fs_nfs);
+	remove_proc_entry("nfsfs", proc_root_fs);
+}
+
+#endif /* CONFIG_PROC_FS */

fs/nfs/delegation.c

@@ -18,6 +18,7 @@
 
 #include "nfs4_fs.h"
 #include "delegation.h"
+#include "internal.h"
 
 static struct nfs_delegation *nfs_alloc_delegation(void)
 {
@@ -52,7 +53,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 			case -NFS4ERR_EXPIRED:
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 			case -NFS4ERR_STALE_CLIENTID:
-				nfs4_schedule_state_recovery(NFS_SERVER(inode)->nfs4_state);
+				nfs4_schedule_state_recovery(NFS_SERVER(inode)->nfs_client);
 				goto out_err;
 		}
 	}
@@ -114,7 +115,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, st
  */
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
 {
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 	int status = 0;
@@ -145,7 +146,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 					sizeof(delegation->stateid)) != 0 ||
 				delegation->type != nfsi->delegation->type) {
 			printk("%s: server %u.%u.%u.%u, handed out a duplicate delegation!\n",
-					__FUNCTION__, NIPQUAD(clp->cl_addr));
+					__FUNCTION__, NIPQUAD(clp->cl_addr.sin_addr));
 			status = -EIO;
 		}
 	}
@@ -176,7 +177,7 @@ static void nfs_msync_inode(struct inode *inode)
  */
 int __nfs_inode_return_delegation(struct inode *inode)
 {
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 	int res = 0;
@@ -208,7 +209,7 @@ int __nfs_inode_return_delegation(struct inode *inode)
  */
 void nfs_return_all_delegations(struct super_block *sb)
 {
-	struct nfs4_client *clp = NFS_SB(sb)->nfs4_state;
+	struct nfs_client *clp = NFS_SB(sb)->nfs_client;
 	struct nfs_delegation *delegation;
 	struct inode *inode;
 
@@ -232,7 +233,7 @@ restart:
 
 int nfs_do_expire_all_delegations(void *ptr)
 {
-	struct nfs4_client *clp = ptr;
+	struct nfs_client *clp = ptr;
 	struct nfs_delegation *delegation;
 	struct inode *inode;
 
@@ -254,11 +255,11 @@ restart:
 	}
 out:
 	spin_unlock(&clp->cl_lock);
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put_and_exit(0);
 }
 
-void nfs_expire_all_delegations(struct nfs4_client *clp)
+void nfs_expire_all_delegations(struct nfs_client *clp)
 {
 	struct task_struct *task;
 
@@ -266,17 +267,17 @@ void nfs_expire_all_delegations(struct nfs4_client *clp)
 	atomic_inc(&clp->cl_count);
 	task = kthread_run(nfs_do_expire_all_delegations, clp,
 			"%u.%u.%u.%u-delegreturn",
-			NIPQUAD(clp->cl_addr));
+			NIPQUAD(clp->cl_addr.sin_addr));
 	if (!IS_ERR(task))
 		return;
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put(THIS_MODULE);
 }
 
 /*
  * Return all delegations following an NFS4ERR_CB_PATH_DOWN error.
  */
-void nfs_handle_cb_pathdown(struct nfs4_client *clp)
+void nfs_handle_cb_pathdown(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation;
 	struct inode *inode;
@@ -299,7 +300,7 @@ restart:
 
 struct recall_threadargs {
 	struct inode *inode;
-	struct nfs4_client *clp;
+	struct nfs_client *clp;
 	const nfs4_stateid *stateid;
 
 	struct completion started;
@@ -310,7 +311,7 @@ static int recall_thread(void *data)
 {
 	struct recall_threadargs *args = (struct recall_threadargs *)data;
 	struct inode *inode = igrab(args->inode);
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 
@@ -371,7 +372,7 @@ out_module_put:
 /*
  * Retrieve the inode associated with a delegation
  */
-struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nfs_fh *fhandle)
+struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle)
 {
 	struct nfs_delegation *delegation;
 	struct inode *res = NULL;
@@ -389,7 +390,7 @@ struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nf
 /*
  * Mark all delegations as needing to be reclaimed
  */
-void nfs_delegation_mark_reclaim(struct nfs4_client *clp)
+void nfs_delegation_mark_reclaim(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation;
 	spin_lock(&clp->cl_lock);
@@ -401,7 +402,7 @@ void nfs_delegation_mark_reclaim(struct nfs4_client *clp)
 /*
  * Reap all unclaimed delegations after reboot recovery is done
  */
-void nfs_delegation_reap_unclaimed(struct nfs4_client *clp)
+void nfs_delegation_reap_unclaimed(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation, *n;
 	LIST_HEAD(head);
@@ -423,7 +424,7 @@ void nfs_delegation_reap_unclaimed(struct nfs4_client *clp)
 
 int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
 {
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 	int res = 0;

fs/nfs/delegation.h

@@ -29,13 +29,13 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, st
 int __nfs_inode_return_delegation(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 
-struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nfs_fh *fhandle);
+struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
 void nfs_return_all_delegations(struct super_block *sb);
-void nfs_expire_all_delegations(struct nfs4_client *clp);
-void nfs_handle_cb_pathdown(struct nfs4_client *clp);
+void nfs_expire_all_delegations(struct nfs_client *clp);
+void nfs_handle_cb_pathdown(struct nfs_client *clp);
 
-void nfs_delegation_mark_reclaim(struct nfs4_client *clp);
-void nfs_delegation_reap_unclaimed(struct nfs4_client *clp);
+void nfs_delegation_mark_reclaim(struct nfs_client *clp);
+void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 
 /* NFSv4 delegation-related procedures */
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid);

fs/nfs/dir.c

@@ -30,7 +30,9 @@
 #include <linux/nfs_mount.h>
 #include <linux/pagemap.h>
 #include <linux/smp_lock.h>
+#include <linux/pagevec.h>
 #include <linux/namei.h>
+#include <linux/mount.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -870,14 +872,14 @@ int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
 	return (nd->intent.open.flags & O_EXCL) != 0;
 }
 
-static inline int nfs_reval_fsid(struct inode *dir,
-		struct nfs_fh *fh, struct nfs_fattr *fattr)
+static inline int nfs_reval_fsid(struct vfsmount *mnt, struct inode *dir,
+				 struct nfs_fh *fh, struct nfs_fattr *fattr)
 {
 	struct nfs_server *server = NFS_SERVER(dir);
 
 	if (!nfs_fsid_equal(&server->fsid, &fattr->fsid))
 		/* Revalidate fsid on root dir */
-		return __nfs_revalidate_inode(server, dir->i_sb->s_root->d_inode);
+		return __nfs_revalidate_inode(server, mnt->mnt_root->d_inode);
 	return 0;
 }
 
@@ -902,9 +904,15 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 
 	lock_kernel();
 
-	/* If we're doing an exclusive create, optimize away the lookup */
-	if (nfs_is_exclusive_create(dir, nd))
-		goto no_entry;
+	/*
+	 * If we're doing an exclusive create, optimize away the lookup
+	 * but don't hash the dentry.
+	 */
+	if (nfs_is_exclusive_create(dir, nd)) {
+		d_instantiate(dentry, NULL);
+		res = NULL;
+		goto out_unlock;
+	}
 
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, &fhandle, &fattr);
 	if (error == -ENOENT)
@@ -913,7 +921,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 		res = ERR_PTR(error);
 		goto out_unlock;
 	}
-	error = nfs_reval_fsid(dir, &fhandle, &fattr);
+	error = nfs_reval_fsid(nd->mnt, dir, &fhandle, &fattr);
 	if (error < 0) {
 		res = ERR_PTR(error);
 		goto out_unlock;
@@ -922,8 +930,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	res = (struct dentry *)inode;
 	if (IS_ERR(res))
 		goto out_unlock;
+
 no_entry:
-	res = d_add_unique(dentry, inode);
+	res = d_materialise_unique(dentry, inode);
 	if (res != NULL)
 		dentry = res;
 	nfs_renew_times(dentry);
@@ -1117,11 +1126,13 @@ static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc)
 		dput(dentry);
 		return NULL;
 	}
-	alias = d_add_unique(dentry, inode);
+
+	alias = d_materialise_unique(dentry, inode);
 	if (alias != NULL) {
 		dput(dentry);
 		dentry = alias;
 	}
+
 	nfs_renew_times(dentry);
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	return dentry;
@@ -1143,23 +1154,22 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 		struct inode *dir = dentry->d_parent->d_inode;
 		error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
 		if (error)
-			goto out_err;
+			return error;
 	}
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
 		struct nfs_server *server = NFS_SB(dentry->d_sb);
-		error = server->rpc_ops->getattr(server, fhandle, fattr);
+		error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr);
 		if (error < 0)
-			goto out_err;
+			return error;
 	}
 	inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
 	error = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		goto out_err;
+		return error;
 	d_instantiate(dentry, inode);
+	if (d_unhashed(dentry))
+		d_rehash(dentry);
 	return 0;
-out_err:
-	d_drop(dentry);
-	return error;
 }
 
 /*
@@ -1440,48 +1450,82 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 	return error;
 }
 
-static int
-nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+/*
+ * To create a symbolic link, most file systems instantiate a new inode,
+ * add a page to it containing the path, then write it out to the disk
+ * using prepare_write/commit_write.
+ *
+ * Unfortunately the NFS client can't create the in-core inode first
+ * because it needs a file handle to create an in-core inode (see
+ * fs/nfs/inode.c:nfs_fhget).  We only have a file handle *after* the
+ * symlink request has completed on the server.
+ *
+ * So instead we allocate a raw page, copy the symname into it, then do
+ * the SYMLINK request with the page as the buffer.  If it succeeds, we
+ * now have a new file handle and can instantiate an in-core NFS inode
+ * and move the raw page into its mapping.
+ */
+static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
+	struct pagevec lru_pvec;
+	struct page *page;
+	char *kaddr;
 	struct iattr attr;
-	struct nfs_fattr sym_attr;
-	struct nfs_fh sym_fh;
-	struct qstr qsymname;
+	unsigned int pathlen = strlen(symname);
 	int error;
 
 	dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry->d_name.name, symname);
 
-#ifdef NFS_PARANOIA
-if (dentry->d_inode)
-printk("nfs_proc_symlink: %s/%s not negative!\n",
-dentry->d_parent->d_name.name, dentry->d_name.name);
-#endif
-	/*
-	 * Fill in the sattr for the call.
- 	 * Note: SunOS 4.1.2 crashes if the mode isn't initialized!
-	 */
-	attr.ia_valid = ATTR_MODE;
-	attr.ia_mode = S_IFLNK | S_IRWXUGO;
+	if (pathlen > PAGE_SIZE)
+		return -ENAMETOOLONG;
 
-	qsymname.name = symname;
-	qsymname.len  = strlen(symname);
+	attr.ia_mode = S_IFLNK | S_IRWXUGO;
+	attr.ia_valid = ATTR_MODE;
 
 	lock_kernel();
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page) {
+		unlock_kernel();
+		return -ENOMEM;
+	}
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(kaddr, symname, pathlen);
+	if (pathlen < PAGE_SIZE)
+		memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);
+	kunmap_atomic(kaddr, KM_USER0);
+
 	nfs_begin_data_update(dir);
-	error = NFS_PROTO(dir)->symlink(dir, &dentry->d_name, &qsymname,
-					  &attr, &sym_fh, &sym_attr);
+	error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
 	nfs_end_data_update(dir);
-	if (!error) {
-		error = nfs_instantiate(dentry, &sym_fh, &sym_attr);
-	} else {
-		if (error == -EEXIST)
-			printk("nfs_proc_symlink: %s/%s already exists??\n",
-			       dentry->d_parent->d_name.name, dentry->d_name.name);
+	if (error != 0) {
+		dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s) error %d\n",
+			dir->i_sb->s_id, dir->i_ino,
+			dentry->d_name.name, symname, error);
 		d_drop(dentry);
+		__free_page(page);
+		unlock_kernel();
+		return error;
 	}
+
+	/*
+	 * No big deal if we can't add this page to the page cache here.
+	 * READLINK will get the missing page from the server if needed.
+	 */
+	pagevec_init(&lru_pvec, 0);
+	if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
+							GFP_KERNEL)) {
+		if (!pagevec_add(&lru_pvec, page))
+			__pagevec_lru_add(&lru_pvec);
+		SetPageUptodate(page);
+		unlock_page(page);
+	} else
+		__free_page(page);
+
 	unlock_kernel();
-	return error;
+	return 0;
 }
 
 static int 
@@ -1638,35 +1682,211 @@ out:
 	return error;
 }
 
+static DEFINE_SPINLOCK(nfs_access_lru_lock);
+static LIST_HEAD(nfs_access_lru_list);
+static atomic_long_t nfs_access_nr_entries;
+
+static void nfs_access_free_entry(struct nfs_access_entry *entry)
+{
+	put_rpccred(entry->cred);
+	kfree(entry);
+	smp_mb__before_atomic_dec();
+	atomic_long_dec(&nfs_access_nr_entries);
+	smp_mb__after_atomic_dec();
+}
+
+int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask)
+{
+	LIST_HEAD(head);
+	struct nfs_inode *nfsi;
+	struct nfs_access_entry *cache;
+
+	spin_lock(&nfs_access_lru_lock);
+restart:
+	list_for_each_entry(nfsi, &nfs_access_lru_list, access_cache_inode_lru) {
+		struct inode *inode;
+
+		if (nr_to_scan-- == 0)
+			break;
+		inode = igrab(&nfsi->vfs_inode);
+		if (inode == NULL)
+			continue;
+		spin_lock(&inode->i_lock);
+		if (list_empty(&nfsi->access_cache_entry_lru))
+			goto remove_lru_entry;
+		cache = list_entry(nfsi->access_cache_entry_lru.next,
+				struct nfs_access_entry, lru);
+		list_move(&cache->lru, &head);
+		rb_erase(&cache->rb_node, &nfsi->access_cache);
+		if (!list_empty(&nfsi->access_cache_entry_lru))
+			list_move_tail(&nfsi->access_cache_inode_lru,
+					&nfs_access_lru_list);
+		else {
+remove_lru_entry:
+			list_del_init(&nfsi->access_cache_inode_lru);
+			clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
+		}
+		spin_unlock(&inode->i_lock);
+		iput(inode);
+		goto restart;
+	}
+	spin_unlock(&nfs_access_lru_lock);
+	while (!list_empty(&head)) {
+		cache = list_entry(head.next, struct nfs_access_entry, lru);
+		list_del(&cache->lru);
+		nfs_access_free_entry(cache);
+	}
+	return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure;
+}
+
+static void __nfs_access_zap_cache(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct rb_root *root_node = &nfsi->access_cache;
+	struct rb_node *n, *dispose = NULL;
+	struct nfs_access_entry *entry;
+
+	/* Unhook entries from the cache */
+	while ((n = rb_first(root_node)) != NULL) {
+		entry = rb_entry(n, struct nfs_access_entry, rb_node);
+		rb_erase(n, root_node);
+		list_del(&entry->lru);
+		n->rb_left = dispose;
+		dispose = n;
+	}
+	nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS;
+	spin_unlock(&inode->i_lock);
+
+	/* Now kill them all! */
+	while (dispose != NULL) {
+		n = dispose;
+		dispose = n->rb_left;
+		nfs_access_free_entry(rb_entry(n, struct nfs_access_entry, rb_node));
+	}
+}
+
+void nfs_access_zap_cache(struct inode *inode)
+{
+	/* Remove from global LRU init */
+	if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_FLAGS(inode))) {
+		spin_lock(&nfs_access_lru_lock);
+		list_del_init(&NFS_I(inode)->access_cache_inode_lru);
+		spin_unlock(&nfs_access_lru_lock);
+	}
+
+	spin_lock(&inode->i_lock);
+	/* This will release the spinlock */
+	__nfs_access_zap_cache(inode);
+}
+
+static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
+{
+	struct rb_node *n = NFS_I(inode)->access_cache.rb_node;
+	struct nfs_access_entry *entry;
+
+	while (n != NULL) {
+		entry = rb_entry(n, struct nfs_access_entry, rb_node);
+
+		if (cred < entry->cred)
+			n = n->rb_left;
+		else if (cred > entry->cred)
+			n = n->rb_right;
+		else
+			return entry;
+	}
+	return NULL;
+}
+
 int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_access_entry *cache = &nfsi->cache_access;
+	struct nfs_access_entry *cache;
+	int err = -ENOENT;
 
-	if (cache->cred != cred
-			|| time_after(jiffies, cache->jiffies + NFS_ATTRTIMEO(inode))
-			|| (nfsi->cache_validity & NFS_INO_INVALID_ACCESS))
-		return -ENOENT;
-	memcpy(res, cache, sizeof(*res));
-	return 0;
+	spin_lock(&inode->i_lock);
+	if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
+		goto out_zap;
+	cache = nfs_access_search_rbtree(inode, cred);
+	if (cache == NULL)
+		goto out;
+	if (time_after(jiffies, cache->jiffies + NFS_ATTRTIMEO(inode)))
+		goto out_stale;
+	res->jiffies = cache->jiffies;
+	res->cred = cache->cred;
+	res->mask = cache->mask;
+	list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru);
+	err = 0;
+out:
+	spin_unlock(&inode->i_lock);
+	return err;
+out_stale:
+	rb_erase(&cache->rb_node, &nfsi->access_cache);
+	list_del(&cache->lru);
+	spin_unlock(&inode->i_lock);
+	nfs_access_free_entry(cache);
+	return -ENOENT;
+out_zap:
+	/* This will release the spinlock */
+	__nfs_access_zap_cache(inode);
+	return -ENOENT;
 }
 
-void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_access_entry *cache = &nfsi->cache_access;
+	struct rb_root *root_node = &nfsi->access_cache;
+	struct rb_node **p = &root_node->rb_node;
+	struct rb_node *parent = NULL;
+	struct nfs_access_entry *entry;
 
-	if (cache->cred != set->cred) {
-		if (cache->cred)
-			put_rpccred(cache->cred);
-		cache->cred = get_rpccred(set->cred);
-	}
-	/* FIXME: replace current access_cache BKL reliance with inode->i_lock */
 	spin_lock(&inode->i_lock);
-	nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS;
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct nfs_access_entry, rb_node);
+
+		if (set->cred < entry->cred)
+			p = &parent->rb_left;
+		else if (set->cred > entry->cred)
+			p = &parent->rb_right;
+		else
+			goto found;
+	}
+	rb_link_node(&set->rb_node, parent, p);
+	rb_insert_color(&set->rb_node, root_node);
+	list_add_tail(&set->lru, &nfsi->access_cache_entry_lru);
 	spin_unlock(&inode->i_lock);
+	return;
+found:
+	rb_replace_node(parent, &set->rb_node, root_node);
+	list_add_tail(&set->lru, &nfsi->access_cache_entry_lru);
+	list_del(&entry->lru);
+	spin_unlock(&inode->i_lock);
+	nfs_access_free_entry(entry);
+}
+
+void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+{
+	struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
+	if (cache == NULL)
+		return;
+	RB_CLEAR_NODE(&cache->rb_node);
 	cache->jiffies = set->jiffies;
+	cache->cred = get_rpccred(set->cred);
 	cache->mask = set->mask;
+
+	nfs_access_add_rbtree(inode, cache);
+
+	/* Update accounting */
+	smp_mb__before_atomic_inc();
+	atomic_long_inc(&nfs_access_nr_entries);
+	smp_mb__after_atomic_inc();
+
+	/* Add inode to global LRU list */
+	if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_FLAGS(inode))) {
+		spin_lock(&nfs_access_lru_lock);
+		list_add_tail(&NFS_I(inode)->access_cache_inode_lru, &nfs_access_lru_list);
+		spin_unlock(&nfs_access_lru_lock);
+	}
 }
 
 static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)

fs/nfs/file.c

@@ -111,7 +111,7 @@ nfs_file_open(struct inode *inode, struct file *filp)
 
 	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
 	lock_kernel();
-	res = NFS_SERVER(inode)->rpc_ops->file_open(inode, filp);
+	res = NFS_PROTO(inode)->file_open(inode, filp);
 	unlock_kernel();
 	return res;
 }
@@ -157,7 +157,7 @@ force_reval:
 static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 {
 	/* origin == SEEK_END => we must revalidate the cached file length */
-	if (origin == 2) {
+	if (origin == SEEK_END) {
 		struct inode *inode = filp->f_mapping->host;
 		int retval = nfs_revalidate_file_size(inode, filp);
 		if (retval < 0)

fs/nfs/getroot.c

@@ -0,0 +1,311 @@
+/* getroot.c: get the root dentry for an NFS mount
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/smp_lock.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/nfs_idmap.h>
+#include <linux/vfs.h>
+#include <linux/namei.h>
+#include <linux/namespace.h>
+#include <linux/security.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+
+#include "nfs4_fs.h"
+#include "delegation.h"
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+#define NFS_PARANOIA 1
+
+/*
+ * get an NFS2/NFS3 root dentry from the root filehandle
+ */
+struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
+{
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_fsinfo fsinfo;
+	struct nfs_fattr fattr;
+	struct dentry *mntroot;
+	struct inode *inode;
+	int error;
+
+	/* create a dummy root dentry with dummy inode for this superblock */
+	if (!sb->s_root) {
+		struct nfs_fh dummyfh;
+		struct dentry *root;
+		struct inode *iroot;
+
+		memset(&dummyfh, 0, sizeof(dummyfh));
+		memset(&fattr, 0, sizeof(fattr));
+		nfs_fattr_init(&fattr);
+		fattr.valid = NFS_ATTR_FATTR;
+		fattr.type = NFDIR;
+		fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR;
+		fattr.nlink = 2;
+
+		iroot = nfs_fhget(sb, &dummyfh, &fattr);
+		if (IS_ERR(iroot))
+			return ERR_PTR(PTR_ERR(iroot));
+
+		root = d_alloc_root(iroot);
+		if (!root) {
+			iput(iroot);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		sb->s_root = root;
+	}
+
+	/* get the actual root for this mount */
+	fsinfo.fattr = &fattr;
+
+	error = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		return ERR_PTR(error);
+	}
+
+	inode = nfs_fhget(sb, mntfh, fsinfo.fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		return ERR_PTR(PTR_ERR(inode));
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	mntroot = d_alloc_anon(inode);
+	if (!mntroot) {
+		iput(inode);
+		dprintk("nfs_get_root: get root dentry failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	security_d_instantiate(mntroot, inode);
+
+	if (!mntroot->d_op)
+		mntroot->d_op = server->nfs_client->rpc_ops->dentry_ops;
+
+	return mntroot;
+}
+
+#ifdef CONFIG_NFS_V4
+
+/*
+ * Do a simple pathwalk from the root FH of the server to the nominated target
+ * of the mountpoint
+ * - give error on symlinks
+ * - give error on ".." occurring in the path
+ * - follow traversals
+ */
+int nfs4_path_walk(struct nfs_server *server,
+		   struct nfs_fh *mntfh,
+		   const char *path)
+{
+	struct nfs_fsinfo fsinfo;
+	struct nfs_fattr fattr;
+	struct nfs_fh lastfh;
+	struct qstr name;
+	int ret;
+	//int referral_count = 0;
+
+	dprintk("--> nfs4_path_walk(,,%s)\n", path);
+
+	fsinfo.fattr = &fattr;
+	nfs_fattr_init(&fattr);
+
+	if (*path++ != '/') {
+		dprintk("nfs4_get_root: Path does not begin with a slash\n");
+		return -EINVAL;
+	}
+
+	/* Start by getting the root filehandle from the server */
+	ret = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
+	if (ret < 0) {
+		dprintk("nfs4_get_root: getroot error = %d\n", -ret);
+		return ret;
+	}
+
+	if (fattr.type != NFDIR) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " getroot encountered non-directory\n");
+		return -ENOTDIR;
+	}
+
+	if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " getroot obtained referral\n");
+		return -EREMOTE;
+	}
+
+next_component:
+	dprintk("Next: %s\n", path);
+
+	/* extract the next bit of the path */
+	if (!*path)
+		goto path_walk_complete;
+
+	name.name = path;
+	while (*path && *path != '/')
+		path++;
+	name.len = path - (const char *) name.name;
+
+eat_dot_dir:
+	while (*path == '/')
+		path++;
+
+	if (path[0] == '.' && (path[1] == '/' || !path[1])) {
+		path += 2;
+		goto eat_dot_dir;
+	}
+
+	if (path[0] == '.' && path[1] == '.' && (path[2] == '/' || !path[2])
+	    ) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " Mount path contains reference to \"..\"\n");
+		return -EINVAL;
+	}
+
+	/* lookup the next FH in the sequence */
+	memcpy(&lastfh, mntfh, sizeof(lastfh));
+
+	dprintk("LookupFH: %*.*s [%s]\n", name.len, name.len, name.name, path);
+
+	ret = server->nfs_client->rpc_ops->lookupfh(server, &lastfh, &name,
+						    mntfh, &fattr);
+	if (ret < 0) {
+		dprintk("nfs4_get_root: getroot error = %d\n", -ret);
+		return ret;
+	}
+
+	if (fattr.type != NFDIR) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " lookupfh encountered non-directory\n");
+		return -ENOTDIR;
+	}
+
+	if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " lookupfh obtained referral\n");
+		return -EREMOTE;
+	}
+
+	goto next_component;
+
+path_walk_complete:
+	memcpy(&server->fsid, &fattr.fsid, sizeof(server->fsid));
+	dprintk("<-- nfs4_path_walk() = 0\n");
+	return 0;
+}
+
+/*
+ * get an NFS4 root dentry from the root filehandle
+ */
+struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
+{
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_fattr fattr;
+	struct dentry *mntroot;
+	struct inode *inode;
+	int error;
+
+	dprintk("--> nfs4_get_root()\n");
+
+	/* create a dummy root dentry with dummy inode for this superblock */
+	if (!sb->s_root) {
+		struct nfs_fh dummyfh;
+		struct dentry *root;
+		struct inode *iroot;
+
+		memset(&dummyfh, 0, sizeof(dummyfh));
+		memset(&fattr, 0, sizeof(fattr));
+		nfs_fattr_init(&fattr);
+		fattr.valid = NFS_ATTR_FATTR;
+		fattr.type = NFDIR;
+		fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR;
+		fattr.nlink = 2;
+
+		iroot = nfs_fhget(sb, &dummyfh, &fattr);
+		if (IS_ERR(iroot))
+			return ERR_PTR(PTR_ERR(iroot));
+
+		root = d_alloc_root(iroot);
+		if (!root) {
+			iput(iroot);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		sb->s_root = root;
+	}
+
+	/* get the info about the server and filesystem */
+	error = nfs4_server_capabilities(server, mntfh);
+	if (error < 0) {
+		dprintk("nfs_get_root: getcaps error = %d\n",
+			-error);
+		return ERR_PTR(error);
+	}
+
+	/* get the actual root for this mount */
+	error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		return ERR_PTR(error);
+	}
+
+	inode = nfs_fhget(sb, mntfh, &fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		return ERR_PTR(PTR_ERR(inode));
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	mntroot = d_alloc_anon(inode);
+	if (!mntroot) {
+		iput(inode);
+		dprintk("nfs_get_root: get root dentry failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	security_d_instantiate(mntroot, inode);
+
+	if (!mntroot->d_op)
+		mntroot->d_op = server->nfs_client->rpc_ops->dentry_ops;
+
+	dprintk("<-- nfs4_get_root()\n");
+	return mntroot;
+}
+
+#endif /* CONFIG_NFS_V4 */

fs/nfs/idmap.c

@@ -57,6 +57,20 @@
 /* Default cache timeout is 10 minutes */
 unsigned int nfs_idmap_cache_timeout = 600 * HZ;
 
+static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
+{
+	char *endp;
+	int num = simple_strtol(val, &endp, 0);
+	int jif = num * HZ;
+	if (endp == val || *endp || num < 0 || jif < num)
+		return -EINVAL;
+	*((int *)kp->arg) = jif;
+	return 0;
+}
+
+module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
+		 &nfs_idmap_cache_timeout, 0644);
+
 struct idmap_hashent {
 	unsigned long ih_expires;
 	__u32 ih_id;
@@ -70,7 +84,6 @@ struct idmap_hashtable {
 };
 
 struct idmap {
-	char                  idmap_path[48];
 	struct dentry        *idmap_dentry;
 	wait_queue_head_t     idmap_wq;
 	struct idmap_msg      idmap_im;
@@ -94,24 +107,23 @@ static struct rpc_pipe_ops idmap_upcall_ops = {
         .destroy_msg    = idmap_pipe_destroy_msg,
 };
 
-void
-nfs_idmap_new(struct nfs4_client *clp)
+int
+nfs_idmap_new(struct nfs_client *clp)
 {
 	struct idmap *idmap;
+	int error;
 
-	if (clp->cl_idmap != NULL)
-		return;
-        if ((idmap = kzalloc(sizeof(*idmap), GFP_KERNEL)) == NULL)
-                return;
+	BUG_ON(clp->cl_idmap != NULL);
 
-	snprintf(idmap->idmap_path, sizeof(idmap->idmap_path),
-	    "%s/idmap", clp->cl_rpcclient->cl_pathname);
+        if ((idmap = kzalloc(sizeof(*idmap), GFP_KERNEL)) == NULL)
+                return -ENOMEM;
 
-        idmap->idmap_dentry = rpc_mkpipe(idmap->idmap_path,
+        idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_dentry, "idmap",
 	    idmap, &idmap_upcall_ops, 0);
         if (IS_ERR(idmap->idmap_dentry)) {
+		error = PTR_ERR(idmap->idmap_dentry);
 		kfree(idmap);
-		return;
+		return error;
 	}
 
         mutex_init(&idmap->idmap_lock);
@@ -121,10 +133,11 @@ nfs_idmap_new(struct nfs4_client *clp)
 	idmap->idmap_group_hash.h_type = IDMAP_TYPE_GROUP;
 
 	clp->cl_idmap = idmap;
+	return 0;
 }
 
 void
-nfs_idmap_delete(struct nfs4_client *clp)
+nfs_idmap_delete(struct nfs_client *clp)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
@@ -477,27 +490,27 @@ static unsigned int fnvhash32(const void *buf, size_t buflen)
 	return (hash);
 }
 
-int nfs_map_name_to_uid(struct nfs4_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_id(idmap, &idmap->idmap_user_hash, name, namelen, uid);
 }
 
-int nfs_map_group_to_gid(struct nfs4_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
 }
 
-int nfs_map_uid_to_name(struct nfs4_client *clp, __u32 uid, char *buf)
+int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
 }
-int nfs_map_gid_to_group(struct nfs4_client *clp, __u32 uid, char *buf)
+int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf)
 {
 	struct idmap *idmap = clp->cl_idmap;
 

fs/nfs/inode.c

@@ -76,19 +76,14 @@ int nfs_write_inode(struct inode *inode, int sync)
 
 void nfs_clear_inode(struct inode *inode)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
-	struct rpc_cred *cred;
-
 	/*
 	 * The following should never happen...
 	 */
 	BUG_ON(nfs_have_writebacks(inode));
-	BUG_ON (!list_empty(&nfsi->open_files));
+	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
+	BUG_ON(atomic_read(&NFS_I(inode)->data_updates) != 0);
 	nfs_zap_acl_cache(inode);
-	cred = nfsi->cache_access.cred;
-	if (cred)
-		put_rpccred(cred);
-	BUG_ON(atomic_read(&nfsi->data_updates) != 0);
+	nfs_access_zap_cache(inode);
 }
 
 /**
@@ -242,13 +237,13 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		/* Why so? Because we want revalidate for devices/FIFOs, and
 		 * that's precisely what we have in nfs_file_inode_operations.
 		 */
-		inode->i_op = NFS_SB(sb)->rpc_ops->file_inode_ops;
+		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
 		if (S_ISREG(inode->i_mode)) {
 			inode->i_fop = &nfs_file_operations;
 			inode->i_data.a_ops = &nfs_file_aops;
 			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
-			inode->i_op = NFS_SB(sb)->rpc_ops->dir_inode_ops;
+			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
 			if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
 			    && fattr->size <= NFS_LIMIT_READDIRPLUS)
@@ -290,7 +285,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = jiffies;
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
-		nfsi->cache_access.cred = NULL;
+		nfsi->access_cache = RB_ROOT;
 
 		unlock_new_inode(inode);
 	} else
@@ -722,13 +717,11 @@ void nfs_end_data_update(struct inode *inode)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	if (!nfs_have_delegation(inode, FMODE_READ)) {
-		/* Directories and symlinks: invalidate page cache */
-		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
-			spin_lock(&inode->i_lock);
-			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
-			spin_unlock(&inode->i_lock);
-		}
+	/* Directories: invalidate page cache */
+	if (S_ISDIR(inode->i_mode)) {
+		spin_lock(&inode->i_lock);
+		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		spin_unlock(&inode->i_lock);
 	}
 	nfsi->cache_change_attribute = jiffies;
 	atomic_dec(&nfsi->data_updates);
@@ -847,6 +840,12 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
  *
  * After an operation that has changed the inode metadata, mark the
  * attribute cache as being invalid, then try to update it.
+ *
+ * NB: if the server didn't return any post op attributes, this
+ * function will force the retrieval of attributes before the next
+ * NFS request.  Thus it should be used only for operations that
+ * are expected to change one or more attributes, to avoid
+ * unnecessary NFS requests and trips through nfs_update_inode().
  */
 int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
@@ -1025,7 +1024,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  out_fileid:
 	printk(KERN_ERR "NFS: server %s error: fileid changed\n"
 		"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
-		NFS_SERVER(inode)->hostname, inode->i_sb->s_id,
+		NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
 		(long long)nfsi->fileid, (long long)fattr->fileid);
 	goto out_err;
 }
@@ -1109,6 +1108,8 @@ static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
 		INIT_LIST_HEAD(&nfsi->dirty);
 		INIT_LIST_HEAD(&nfsi->commit);
 		INIT_LIST_HEAD(&nfsi->open_files);
+		INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
+		INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
 		INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
 		atomic_set(&nfsi->data_updates, 0);
 		nfsi->ndirty = 0;
@@ -1144,6 +1145,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_fs_proc_init();
+	if (err)
+		goto out5;
+
 	err = nfs_init_nfspagecache();
 	if (err)
 		goto out4;
@@ -1184,6 +1189,8 @@ out2:
 out3:
 	nfs_destroy_nfspagecache();
 out4:
+	nfs_fs_proc_exit();
+out5:
 	return err;
 }
 
@@ -1198,6 +1205,7 @@ static void __exit exit_nfs_fs(void)
 	rpc_proc_unregister("nfs");
 #endif
 	unregister_nfs_fs();
+	nfs_fs_proc_exit();
 }
 
 /* Not quite true; I just maintain it */

fs/nfs/internal.h

@@ -4,6 +4,18 @@
 
 #include <linux/mount.h>
 
+struct nfs_string;
+struct nfs_mount_data;
+struct nfs4_mount_data;
+
+/* Maximum number of readahead requests
+ * FIXME: this should really be a sysctl so that users may tune it to suit
+ *        their needs. People that do NFS over a slow network, might for
+ *        instance want to reduce it to something closer to 1 for improved
+ *        interactive response.
+ */
+#define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)
+
 struct nfs_clone_mount {
 	const struct super_block *sb;
 	const struct dentry *dentry;
@@ -15,7 +27,40 @@ struct nfs_clone_mount {
 	rpc_authflavor_t authflavor;
 };
 
-/* namespace-nfs4.c */
+/* client.c */
+extern struct rpc_program nfs_program;
+
+extern void nfs_put_client(struct nfs_client *);
+extern struct nfs_client *nfs_find_client(const struct sockaddr_in *, int);
+extern struct nfs_server *nfs_create_server(const struct nfs_mount_data *,
+					    struct nfs_fh *);
+extern struct nfs_server *nfs4_create_server(const struct nfs4_mount_data *,
+					     const char *,
+					     const struct sockaddr_in *,
+					     const char *,
+					     const char *,
+					     rpc_authflavor_t,
+					     struct nfs_fh *);
+extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
+						      struct nfs_fh *);
+extern void nfs_free_server(struct nfs_server *server);
+extern struct nfs_server *nfs_clone_server(struct nfs_server *,
+					   struct nfs_fh *,
+					   struct nfs_fattr *);
+#ifdef CONFIG_PROC_FS
+extern int __init nfs_fs_proc_init(void);
+extern void nfs_fs_proc_exit(void);
+#else
+static inline int nfs_fs_proc_init(void)
+{
+	return 0;
+}
+static inline void nfs_fs_proc_exit(void)
+{
+}
+#endif
+
+/* nfs4namespace.c */
 #ifdef CONFIG_NFS_V4
 extern struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry);
 #else
@@ -46,6 +91,7 @@ extern void nfs_destroy_directcache(void);
 #endif
 
 /* nfs2xdr.c */
+extern int nfs_stat_to_errno(int);
 extern struct rpc_procinfo nfs_procedures[];
 extern u32 * nfs_decode_dirent(u32 *, struct nfs_entry *, int);
 
@@ -54,8 +100,9 @@ extern struct rpc_procinfo nfs3_procedures[];
 extern u32 *nfs3_decode_dirent(u32 *, struct nfs_entry *, int);
 
 /* nfs4xdr.c */
-extern int nfs_stat_to_errno(int);
+#ifdef CONFIG_NFS_V4
 extern u32 *nfs4_decode_dirent(u32 *p, struct nfs_entry *entry, int plus);
+#endif
 
 /* nfs4proc.c */
 #ifdef CONFIG_NFS_V4
@@ -66,6 +113,9 @@ extern int nfs4_proc_fs_locations(struct inode *dir, struct dentry *dentry,
 				  struct page *page);
 #endif
 
+/* dir.c */
+extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask);
+
 /* inode.c */
 extern struct inode *nfs_alloc_inode(struct super_block *sb);
 extern void nfs_destroy_inode(struct inode *);
@@ -76,10 +126,10 @@ extern void nfs4_clear_inode(struct inode *);
 #endif
 
 /* super.c */
-extern struct file_system_type nfs_referral_nfs4_fs_type;
-extern struct file_system_type clone_nfs_fs_type;
+extern struct file_system_type nfs_xdev_fs_type;
 #ifdef CONFIG_NFS_V4
-extern struct file_system_type clone_nfs4_fs_type;
+extern struct file_system_type nfs4_xdev_fs_type;
+extern struct file_system_type nfs4_referral_fs_type;
 #endif
 
 extern struct rpc_stat nfs_rpcstat;
@@ -88,30 +138,30 @@ extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
 
 /* namespace.c */
-extern char *nfs_path(const char *base, const struct dentry *dentry,
+extern char *nfs_path(const char *base,
+		      const struct dentry *droot,
+		      const struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 
-/*
- * Determine the mount path as a string
- */
-static inline char *
-nfs4_path(const struct dentry *dentry, char *buffer, ssize_t buflen)
-{
+/* getroot.c */
+extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *);
 #ifdef CONFIG_NFS_V4
-	return nfs_path(NFS_SB(dentry->d_sb)->mnt_path, dentry, buffer, buflen);
-#else
-	return NULL;
+extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *);
+
+extern int nfs4_path_walk(struct nfs_server *server,
+			  struct nfs_fh *mntfh,
+			  const char *path);
 #endif
-}
 
 /*
  * Determine the device name as a string
  */
 static inline char *nfs_devname(const struct vfsmount *mnt_parent,
-			 const struct dentry *dentry,
-			 char *buffer, ssize_t buflen)
+				const struct dentry *dentry,
+				char *buffer, ssize_t buflen)
 {
-	return nfs_path(mnt_parent->mnt_devname, dentry, buffer, buflen);
+	return nfs_path(mnt_parent->mnt_devname, mnt_parent->mnt_root,
+			dentry, buffer, buflen);
 }
 
 /*
@@ -167,20 +217,3 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
 	if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0)
 		sb->s_maxbytes = MAX_LFS_FILESIZE;
 }
-
-/*
- * Check if the string represents a "valid" IPv4 address
- */
-static inline int valid_ipaddr4(const char *buf)
-{
-	int rc, count, in[4];
-
-	rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
-	if (rc != 4)
-		return -EINVAL;
-	for (count = 0; count < 4; count++) {
-		if (in[count] > 255)
-			return -EINVAL;
-	}
-	return 0;
-}

fs/nfs/mount_clnt.c

@@ -14,7 +14,6 @@
 #include <linux/net.h>
 #include <linux/in.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs_fs.h>
 
@@ -77,22 +76,19 @@ static struct rpc_clnt *
 mnt_create(char *hostname, struct sockaddr_in *srvaddr, int version,
 		int protocol)
 {
-	struct rpc_xprt	*xprt;
-	struct rpc_clnt	*clnt;
-
-	xprt = xprt_create_proto(protocol, srvaddr, NULL);
-	if (IS_ERR(xprt))
-		return (struct rpc_clnt *)xprt;
-
-	clnt = rpc_create_client(xprt, hostname,
-				&mnt_program, version,
-				RPC_AUTH_UNIX);
-	if (!IS_ERR(clnt)) {
-		clnt->cl_softrtry = 1;
-		clnt->cl_oneshot  = 1;
-		clnt->cl_intr = 1;
-	}
-	return clnt;
+	struct rpc_create_args args = {
+		.protocol	= protocol,
+		.address	= (struct sockaddr *)srvaddr,
+		.addrsize	= sizeof(*srvaddr),
+		.servername	= hostname,
+		.program	= &mnt_program,
+		.version	= version,
+		.authflavor	= RPC_AUTH_UNIX,
+		.flags		= (RPC_CLNT_CREATE_ONESHOT |
+				   RPC_CLNT_CREATE_INTR),
+	};
+
+	return rpc_create(&args);
 }
 
 /*

fs/nfs/namespace.c

@@ -2,6 +2,7 @@
  * linux/fs/nfs/namespace.c
  *
  * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
+ * - Modified by David Howells <dhowells@redhat.com>
  *
  * NFS namespace
  */
@@ -28,6 +29,7 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 /*
  * nfs_path - reconstruct the path given an arbitrary dentry
  * @base - arbitrary string to prepend to the path
+ * @droot - pointer to root dentry for mountpoint
  * @dentry - pointer to dentry
  * @buffer - result buffer
  * @buflen - length of buffer
@@ -38,7 +40,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  * This is mainly for use in figuring out the path on the
  * server side when automounting on top of an existing partition.
  */
-char *nfs_path(const char *base, const struct dentry *dentry,
+char *nfs_path(const char *base,
+	       const struct dentry *droot,
+	       const struct dentry *dentry,
 	       char *buffer, ssize_t buflen)
 {
 	char *end = buffer+buflen;
@@ -47,7 +51,7 @@ char *nfs_path(const char *base, const struct dentry *dentry,
 	*--end = '\0';
 	buflen--;
 	spin_lock(&dcache_lock);
-	while (!IS_ROOT(dentry)) {
+	while (!IS_ROOT(dentry) && dentry != droot) {
 		namelen = dentry->d_name.len;
 		buflen -= namelen + 1;
 		if (buflen < 0)
@@ -96,15 +100,18 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 	struct nfs_fattr fattr;
 	int err;
 
+	dprintk("--> nfs_follow_mountpoint()\n");
+
 	BUG_ON(IS_ROOT(dentry));
 	dprintk("%s: enter\n", __FUNCTION__);
 	dput(nd->dentry);
 	nd->dentry = dget(dentry);
-	if (d_mountpoint(nd->dentry))
-		goto out_follow;
+
 	/* Look it up again */
 	parent = dget_parent(nd->dentry);
-	err = server->rpc_ops->lookup(parent->d_inode, &nd->dentry->d_name, &fh, &fattr);
+	err = server->nfs_client->rpc_ops->lookup(parent->d_inode,
+						  &nd->dentry->d_name,
+						  &fh, &fattr);
 	dput(parent);
 	if (err != 0)
 		goto out_err;
@@ -132,6 +139,8 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
 out:
 	dprintk("%s: done, returned %d\n", __FUNCTION__, err);
+
+	dprintk("<-- nfs_follow_mountpoint() = %d\n", err);
 	return ERR_PTR(err);
 out_err:
 	path_release(nd);
@@ -172,22 +181,23 @@ void nfs_release_automount_timer(void)
 /*
  * Clone a mountpoint of the appropriate type
  */
-static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, char *devname,
+static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
+					   const char *devname,
 					   struct nfs_clone_mount *mountdata)
 {
 #ifdef CONFIG_NFS_V4
 	struct vfsmount *mnt = NULL;
-	switch (server->rpc_ops->version) {
+	switch (server->nfs_client->cl_nfsversion) {
 		case 2:
 		case 3:
-			mnt = vfs_kern_mount(&clone_nfs_fs_type, 0, devname, mountdata);
+			mnt = vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
 			break;
 		case 4:
-			mnt = vfs_kern_mount(&clone_nfs4_fs_type, 0, devname, mountdata);
+			mnt = vfs_kern_mount(&nfs4_xdev_fs_type, 0, devname, mountdata);
 	}
 	return mnt;
 #else
-	return vfs_kern_mount(&clone_nfs_fs_type, 0, devname, mountdata);
+	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
 #endif
 }
 
@@ -213,6 +223,8 @@ struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent,
 	char *page = (char *) __get_free_page(GFP_USER);
 	char *devname;
 
+	dprintk("--> nfs_do_submount()\n");
+
 	dprintk("%s: submounting on %s/%s\n", __FUNCTION__,
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name);
@@ -227,5 +239,7 @@ free_page:
 	free_page((unsigned long)page);
 out:
 	dprintk("%s: done\n", __FUNCTION__);
+
+	dprintk("<-- nfs_do_submount() = %p\n", mnt);
 	return mnt;
 }

fs/nfs/nfs2xdr.c

@@ -51,7 +51,7 @@
 #define NFS_createargs_sz	(NFS_diropargs_sz+NFS_sattr_sz)
 #define NFS_renameargs_sz	(NFS_diropargs_sz+NFS_diropargs_sz)
 #define NFS_linkargs_sz		(NFS_fhandle_sz+NFS_diropargs_sz)
-#define NFS_symlinkargs_sz	(NFS_diropargs_sz+NFS_path_sz+NFS_sattr_sz)
+#define NFS_symlinkargs_sz	(NFS_diropargs_sz+1+NFS_sattr_sz)
 #define NFS_readdirargs_sz	(NFS_fhandle_sz+2)
 
 #define NFS_attrstat_sz		(1+NFS_fattr_sz)
@@ -351,11 +351,26 @@ nfs_xdr_linkargs(struct rpc_rqst *req, u32 *p, struct nfs_linkargs *args)
 static int
 nfs_xdr_symlinkargs(struct rpc_rqst *req, u32 *p, struct nfs_symlinkargs *args)
 {
+	struct xdr_buf *sndbuf = &req->rq_snd_buf;
+	size_t pad;
+
 	p = xdr_encode_fhandle(p, args->fromfh);
 	p = xdr_encode_array(p, args->fromname, args->fromlen);
-	p = xdr_encode_array(p, args->topath, args->tolen);
+	*p++ = htonl(args->pathlen);
+	sndbuf->len = xdr_adjust_iovec(sndbuf->head, p);
+
+	xdr_encode_pages(sndbuf, args->pages, 0, args->pathlen);
+
+	/*
+	 * xdr_encode_pages may have added a few bytes to ensure the
+	 * pathname ends on a 4-byte boundary.  Start encoding the
+	 * attributes after the pad bytes.
+	 */
+	pad = sndbuf->tail->iov_len;
+	if (pad > 0)
+		p++;
 	p = xdr_encode_sattr(p, args->sattr);
-	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+	sndbuf->len += xdr_adjust_iovec(sndbuf->tail, p) - pad;
 	return 0;
 }
 

fs/nfs/nfs3proc.c

@@ -81,7 +81,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle,
 }
 
 /*
- * Bare-bones access to getattr: this is for nfs_read_super.
+ * Bare-bones access to getattr: this is for nfs_get_root/nfs_get_sb
  */
 static int
 nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -90,8 +90,8 @@ nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	int	status;
 
 	status = do_proc_get_root(server->client, fhandle, info);
-	if (status && server->client_sys != server->client)
-		status = do_proc_get_root(server->client_sys, fhandle, info);
+	if (status && server->nfs_client->cl_rpcclient != server->client)
+		status = do_proc_get_root(server->nfs_client->cl_rpcclient, fhandle, info);
 	return status;
 }
 
@@ -544,23 +544,23 @@ nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 }
 
 static int
-nfs3_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
-		  struct iattr *sattr, struct nfs_fh *fhandle,
-		  struct nfs_fattr *fattr)
+nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
+		  unsigned int len, struct iattr *sattr)
 {
-	struct nfs_fattr	dir_attr;
+	struct nfs_fh fhandle;
+	struct nfs_fattr fattr, dir_attr;
 	struct nfs3_symlinkargs	arg = {
 		.fromfh		= NFS_FH(dir),
-		.fromname	= name->name,
-		.fromlen	= name->len,
-		.topath		= path->name,
-		.tolen		= path->len,
+		.fromname	= dentry->d_name.name,
+		.fromlen	= dentry->d_name.len,
+		.pages		= &page,
+		.pathlen	= len,
 		.sattr		= sattr
 	};
 	struct nfs3_diropres	res = {
 		.dir_attr	= &dir_attr,
-		.fh		= fhandle,
-		.fattr		= fattr
+		.fh		= &fhandle,
+		.fattr		= &fattr
 	};
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs3_procedures[NFS3PROC_SYMLINK],
@@ -569,13 +569,19 @@ nfs3_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
 	};
 	int			status;
 
-	if (path->len > NFS3_MAXPATHLEN)
+	if (len > NFS3_MAXPATHLEN)
 		return -ENAMETOOLONG;
-	dprintk("NFS call  symlink %s -> %s\n", name->name, path->name);
+
+	dprintk("NFS call  symlink %s\n", dentry->d_name.name);
+
 	nfs_fattr_init(&dir_attr);
-	nfs_fattr_init(fattr);
+	nfs_fattr_init(&fattr);
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
 	nfs_post_op_update_inode(dir, &dir_attr);
+	if (status != 0)
+		goto out;
+	status = nfs_instantiate(dentry, &fhandle, &fattr);
+out:
 	dprintk("NFS reply symlink: %d\n", status);
 	return status;
 }
@@ -785,7 +791,7 @@ nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
 
 	dprintk("NFS call  fsinfo\n");
 	nfs_fattr_init(info->fattr);
-	status = rpc_call_sync(server->client_sys, &msg, 0);
+	status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
 	dprintk("NFS reply fsinfo: %d\n", status);
 	return status;
 }
@@ -886,7 +892,7 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return nlmclnt_proc(filp->f_dentry->d_inode, cmd, fl);
 }
 
-struct nfs_rpc_ops	nfs_v3_clientops = {
+const struct nfs_rpc_ops nfs_v3_clientops = {
 	.version	= 3,			/* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs3_dir_inode_operations,

fs/nfs/nfs3xdr.c

@@ -56,7 +56,7 @@
 #define NFS3_writeargs_sz	(NFS3_fh_sz+5)
 #define NFS3_createargs_sz	(NFS3_diropargs_sz+NFS3_sattr_sz)
 #define NFS3_mkdirargs_sz	(NFS3_diropargs_sz+NFS3_sattr_sz)
-#define NFS3_symlinkargs_sz	(NFS3_diropargs_sz+NFS3_path_sz+NFS3_sattr_sz)
+#define NFS3_symlinkargs_sz	(NFS3_diropargs_sz+1+NFS3_sattr_sz)
 #define NFS3_mknodargs_sz	(NFS3_diropargs_sz+2+NFS3_sattr_sz)
 #define NFS3_renameargs_sz	(NFS3_diropargs_sz+NFS3_diropargs_sz)
 #define NFS3_linkargs_sz		(NFS3_fh_sz+NFS3_diropargs_sz)
@@ -398,8 +398,11 @@ nfs3_xdr_symlinkargs(struct rpc_rqst *req, u32 *p, struct nfs3_symlinkargs *args
 	p = xdr_encode_fhandle(p, args->fromfh);
 	p = xdr_encode_array(p, args->fromname, args->fromlen);
 	p = xdr_encode_sattr(p, args->sattr);
-	p = xdr_encode_array(p, args->topath, args->tolen);
+	*p++ = htonl(args->pathlen);
 	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+
+	/* Copy the page */
+	xdr_encode_pages(&req->rq_snd_buf, args->pages, 0, args->pathlen);
 	return 0;
 }
 

fs/nfs/nfs4_fs.h

@@ -42,55 +42,6 @@ enum nfs4_client_state {
 	NFS4CLNT_LEASE_EXPIRED,
 };
 
-/*
- * The nfs4_client identifies our client state to the server.
- */
-struct nfs4_client {
-	struct list_head	cl_servers;	/* Global list of servers */
-	struct in_addr		cl_addr;	/* Server identifier */
-	u64			cl_clientid;	/* constant */
-	nfs4_verifier		cl_confirm;
-	unsigned long		cl_state;
-
-	u32			cl_lockowner_id;
-
-	/*
-	 * The following rwsem ensures exclusive access to the server
-	 * while we recover the state following a lease expiration.
-	 */
-	struct rw_semaphore	cl_sem;
-
-	struct list_head	cl_delegations;
-	struct list_head	cl_state_owners;
-	struct list_head	cl_unused;
-	int			cl_nunused;
-	spinlock_t		cl_lock;
-	atomic_t		cl_count;
-
-	struct rpc_clnt *	cl_rpcclient;
-
-	struct list_head	cl_superblocks;	/* List of nfs_server structs */
-
-	unsigned long		cl_lease_time;
-	unsigned long		cl_last_renewal;
-	struct work_struct	cl_renewd;
-	struct work_struct	cl_recoverd;
-
-	struct rpc_wait_queue	cl_rpcwaitq;
-
-	/* used for the setclientid verifier */
-	struct timespec		cl_boot_time;
-
-	/* idmapper */
-	struct idmap *		cl_idmap;
-
-	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the clientid, and the callback address.
-	 */
-	char			cl_ipaddr[16];
-	unsigned char		cl_id_uniquifier;
-};
-
 /*
  * struct rpc_sequence ensures that RPC calls are sent in the exact
  * order that they appear on the list.
@@ -127,7 +78,7 @@ static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status
 struct nfs4_state_owner {
 	spinlock_t	     so_lock;
 	struct list_head     so_list;	 /* per-clientid list of state_owners */
-	struct nfs4_client   *so_client;
+	struct nfs_client    *so_client;
 	u32                  so_id;      /* 32-bit identifier, unique */
 	atomic_t	     so_count;
 
@@ -210,10 +161,10 @@ extern ssize_t nfs4_listxattr(struct dentry *, char *, size_t);
 
 /* nfs4proc.c */
 extern int nfs4_map_errors(int err);
-extern int nfs4_proc_setclientid(struct nfs4_client *, u32, unsigned short, struct rpc_cred *);
-extern int nfs4_proc_setclientid_confirm(struct nfs4_client *, struct rpc_cred *);
-extern int nfs4_proc_async_renew(struct nfs4_client *, struct rpc_cred *);
-extern int nfs4_proc_renew(struct nfs4_client *, struct rpc_cred *);
+extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *);
+extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_async_renew(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct inode *inode, struct nfs4_state *state);
 extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
 extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *);
@@ -231,19 +182,14 @@ extern const u32 nfs4_fsinfo_bitmap[2];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
 /* nfs4renewd.c */
-extern void nfs4_schedule_state_renewal(struct nfs4_client *);
+extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
-extern void nfs4_kill_renewd(struct nfs4_client *);
+extern void nfs4_kill_renewd(struct nfs_client *);
 extern void nfs4_renew_state(void *);
 
 /* nfs4state.c */
-extern void init_nfsv4_state(struct nfs_server *);
-extern void destroy_nfsv4_state(struct nfs_server *);
-extern struct nfs4_client *nfs4_get_client(struct in_addr *);
-extern void nfs4_put_client(struct nfs4_client *clp);
-extern struct nfs4_client *nfs4_find_client(struct in_addr *);
-struct rpc_cred *nfs4_get_renew_cred(struct nfs4_client *clp);
-extern u32 nfs4_alloc_lockowner_id(struct nfs4_client *);
+struct rpc_cred *nfs4_get_renew_cred(struct nfs_client *clp);
+extern u32 nfs4_alloc_lockowner_id(struct nfs_client *);
 
 extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
@@ -252,7 +198,7 @@ extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state
 extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, mode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, mode_t);
-extern void nfs4_schedule_state_recovery(struct nfs4_client *);
+extern void nfs4_schedule_state_recovery(struct nfs_client *);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
 extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t);
@@ -276,10 +222,6 @@ extern struct svc_version nfs4_callback_version1;
 
 #else
 
-#define init_nfsv4_state(server)  do { } while (0)
-#define destroy_nfsv4_state(server)       do { } while (0)
-#define nfs4_put_state_owner(inode, owner) do { } while (0)
-#define nfs4_put_open_state(state) do { } while (0)
 #define nfs4_close_state(a, b) do { } while (0)
 
 #endif /* CONFIG_NFS_V4 */

fs/nfs/nfs4namespace.c

@@ -2,6 +2,7 @@
  * linux/fs/nfs/nfs4namespace.c
  *
  * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
+ * - Modified by David Howells <dhowells@redhat.com>
  *
  * NFSv4 namespace
  */
@@ -23,7 +24,7 @@
 /*
  * Check if fs_root is valid
  */
-static inline char *nfs4_pathname_string(struct nfs4_pathname *pathname,
+static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname,
 					 char *buffer, ssize_t buflen)
 {
 	char *end = buffer + buflen;
@@ -34,7 +35,7 @@ static inline char *nfs4_pathname_string(struct nfs4_pathname *pathname,
 
 	n = pathname->ncomponents;
 	while (--n >= 0) {
-		struct nfs4_string *component = &pathname->components[n];
+		const struct nfs4_string *component = &pathname->components[n];
 		buflen -= component->len + 1;
 		if (buflen < 0)
 			goto Elong;
@@ -47,6 +48,68 @@ Elong:
 	return ERR_PTR(-ENAMETOOLONG);
 }
 
+/*
+ * Determine the mount path as a string
+ */
+static char *nfs4_path(const struct vfsmount *mnt_parent,
+		       const struct dentry *dentry,
+		       char *buffer, ssize_t buflen)
+{
+	const char *srvpath;
+
+	srvpath = strchr(mnt_parent->mnt_devname, ':');
+	if (srvpath)
+		srvpath++;
+	else
+		srvpath = mnt_parent->mnt_devname;
+
+	return nfs_path(srvpath, mnt_parent->mnt_root, dentry, buffer, buflen);
+}
+
+/*
+ * Check that fs_locations::fs_root [RFC3530 6.3] is a prefix for what we
+ * believe to be the server path to this dentry
+ */
+static int nfs4_validate_fspath(const struct vfsmount *mnt_parent,
+				const struct dentry *dentry,
+				const struct nfs4_fs_locations *locations,
+				char *page, char *page2)
+{
+	const char *path, *fs_path;
+
+	path = nfs4_path(mnt_parent, dentry, page, PAGE_SIZE);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE);
+	if (IS_ERR(fs_path))
+		return PTR_ERR(fs_path);
+
+	if (strncmp(path, fs_path, strlen(fs_path)) != 0) {
+		dprintk("%s: path %s does not begin with fsroot %s\n",
+			__FUNCTION__, path, fs_path);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+/*
+ * Check if the string represents a "valid" IPv4 address
+ */
+static inline int valid_ipaddr4(const char *buf)
+{
+	int rc, count, in[4];
+
+	rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
+	if (rc != 4)
+		return -EINVAL;
+	for (count = 0; count < 4; count++) {
+		if (in[count] > 255)
+			return -EINVAL;
+	}
+	return 0;
+}
 
 /**
  * nfs_follow_referral - set up mountpoint when hitting a referral on moved error
@@ -60,7 +123,7 @@ Elong:
  */
 static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 					    const struct dentry *dentry,
-					    struct nfs4_fs_locations *locations)
+					    const struct nfs4_fs_locations *locations)
 {
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 	struct nfs_clone_mount mountdata = {
@@ -68,10 +131,9 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 		.dentry = dentry,
 		.authflavor = NFS_SB(mnt_parent->mnt_sb)->client->cl_auth->au_flavor,
 	};
-	char *page, *page2;
-	char *path, *fs_path;
+	char *page = NULL, *page2 = NULL;
 	char *devname;
-	int loc, s;
+	int loc, s, error;
 
 	if (locations == NULL || locations->nlocations <= 0)
 		goto out;
@@ -79,36 +141,30 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 	dprintk("%s: referral at %s/%s\n", __FUNCTION__,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	/* Ensure fs path is a prefix of current dentry path */
 	page = (char *) __get_free_page(GFP_USER);
-	if (page == NULL)
+	if (!page)
 		goto out;
+
 	page2 = (char *) __get_free_page(GFP_USER);
-	if (page2 == NULL)
+	if (!page2)
 		goto out;
 
-	path = nfs4_path(dentry, page, PAGE_SIZE);
-	if (IS_ERR(path))
-		goto out_free;
-
-	fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE);
-	if (IS_ERR(fs_path))
-		goto out_free;
-
-	if (strncmp(path, fs_path, strlen(fs_path)) != 0) {
-		dprintk("%s: path %s does not begin with fsroot %s\n", __FUNCTION__, path, fs_path);
-		goto out_free;
+	/* Ensure fs path is a prefix of current dentry path */
+	error = nfs4_validate_fspath(mnt_parent, dentry, locations, page, page2);
+	if (error < 0) {
+		mnt = ERR_PTR(error);
+		goto out;
 	}
 
 	devname = nfs_devname(mnt_parent, dentry, page, PAGE_SIZE);
 	if (IS_ERR(devname)) {
 		mnt = (struct vfsmount *)devname;
-		goto out_free;
+		goto out;
 	}
 
 	loc = 0;
 	while (loc < locations->nlocations && IS_ERR(mnt)) {
-		struct nfs4_fs_location *location = &locations->locations[loc];
+		const struct nfs4_fs_location *location = &locations->locations[loc];
 		char *mnt_path;
 
 		if (location == NULL || location->nservers <= 0 ||
@@ -140,7 +196,7 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 			addr.sin_port = htons(NFS_PORT);
 			mountdata.addr = &addr;
 
-			mnt = vfs_kern_mount(&nfs_referral_nfs4_fs_type, 0, devname, &mountdata);
+			mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, devname, &mountdata);
 			if (!IS_ERR(mnt)) {
 				break;
 			}
@@ -149,10 +205,9 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 		loc++;
 	}
 
-out_free:
-	free_page((unsigned long)page);
-	free_page((unsigned long)page2);
 out:
+	free_page((unsigned long) page);
+	free_page((unsigned long) page2);
 	dprintk("%s: done\n", __FUNCTION__);
 	return mnt;
 }
@@ -165,7 +220,7 @@ out:
  */
 struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry)
 {
-	struct vfsmount *mnt = ERR_PTR(-ENOENT);
+	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
 	struct dentry *parent;
 	struct nfs4_fs_locations *fs_locations = NULL;
 	struct page *page;
@@ -183,11 +238,16 @@ struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentr
 		goto out_free;
 
 	/* Get locations */
+	mnt = ERR_PTR(-ENOENT);
+
 	parent = dget_parent(dentry);
-	dprintk("%s: getting locations for %s/%s\n", __FUNCTION__, parent->d_name.name, dentry->d_name.name);
+	dprintk("%s: getting locations for %s/%s\n",
+		__FUNCTION__, parent->d_name.name, dentry->d_name.name);
+
 	err = nfs4_proc_fs_locations(parent->d_inode, dentry, fs_locations, page);
 	dput(parent);
-	if (err != 0 || fs_locations->nlocations <= 0 ||
+	if (err != 0 ||
+	    fs_locations->nlocations <= 0 ||
 	    fs_locations->fs_path.ncomponents <= 0)
 		goto out_free;
 

fs/nfs/nfs4proc.c

@@ -55,7 +55,7 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
-#define NFS4_POLL_RETRY_MIN	(1*HZ)
+#define NFS4_POLL_RETRY_MIN	(HZ/10)
 #define NFS4_POLL_RETRY_MAX	(15*HZ)
 
 struct nfs4_opendata;
@@ -64,7 +64,7 @@ static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinf
 static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *);
 static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry);
 static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception);
-static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs4_client *clp);
+static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs_client *clp);
 
 /* Prevent leaks of NFSv4 errors into userland */
 int nfs4_map_errors(int err)
@@ -195,7 +195,7 @@ static void nfs4_setup_readdir(u64 cookie, u32 *verifier, struct dentry *dentry,
 
 static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	spin_lock(&clp->cl_lock);
 	if (time_before(clp->cl_last_renewal,timestamp))
 		clp->cl_last_renewal = timestamp;
@@ -252,7 +252,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	atomic_inc(&sp->so_count);
 	p->o_arg.fh = NFS_FH(dir);
 	p->o_arg.open_flags = flags,
-	p->o_arg.clientid = server->nfs4_state->cl_clientid;
+	p->o_arg.clientid = server->nfs_client->cl_clientid;
 	p->o_arg.id = sp->so_id;
 	p->o_arg.name = &dentry->d_name;
 	p->o_arg.server = server;
@@ -550,7 +550,7 @@ int nfs4_open_delegation_recall(struct dentry *dentry, struct nfs4_state *state)
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
 				/* Don't recall a delegation if it was lost */
-				nfs4_schedule_state_recovery(server->nfs4_state);
+				nfs4_schedule_state_recovery(server->nfs_client);
 				return err;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
@@ -758,7 +758,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 	}
 	nfs_confirm_seqid(&data->owner->so_seqid, 0);
 	if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
-		return server->rpc_ops->getattr(server, &o_res->fh, o_res->f_attr);
+		return server->nfs_client->rpc_ops->getattr(server, &o_res->fh, o_res->f_attr);
 	return 0;
 }
 
@@ -792,11 +792,18 @@ out:
 
 int nfs4_recover_expired_lease(struct nfs_server *server)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
+	int ret;
 
-	if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+	for (;;) {
+		ret = nfs4_wait_clnt_recover(server->client, clp);
+		if (ret != 0)
+			return ret;
+		if (!test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+			break;
 		nfs4_schedule_state_recovery(clp);
-	return nfs4_wait_clnt_recover(server->client, clp);
+	}
+	return 0;
 }
 
 /*
@@ -867,7 +874,7 @@ static int _nfs4_open_delegated(struct inode *inode, int flags, struct rpc_cred
 {
 	struct nfs_delegation *delegation;
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs4_state_owner *sp = NULL;
 	struct nfs4_state *state = NULL;
@@ -953,7 +960,7 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, int flags, st
 	struct nfs4_state_owner  *sp;
 	struct nfs4_state     *state = NULL;
 	struct nfs_server       *server = NFS_SERVER(dir);
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_opendata *opendata;
 	int                     status;
 
@@ -1133,7 +1140,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			break;
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_EXPIRED:
-			nfs4_schedule_state_recovery(server->nfs4_state);
+			nfs4_schedule_state_recovery(server->nfs_client);
 			break;
 		default:
 			if (nfs4_async_handle_error(task, server) == -EAGAIN) {
@@ -1268,7 +1275,7 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 		BUG_ON(nd->intent.open.flags & O_CREAT);
 	}
 
-	cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(dir)->cl_auth, 0);
 	if (IS_ERR(cred))
 		return (struct dentry *)cred;
 	state = nfs4_do_open(dir, dentry, nd->intent.open.flags, &attr, cred);
@@ -1291,7 +1298,7 @@ nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, st
 	struct rpc_cred *cred;
 	struct nfs4_state *state;
 
-	cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(dir)->cl_auth, 0);
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
 	state = nfs4_open_delegated(dentry->d_inode, openflags, cred);
@@ -1393,70 +1400,19 @@ static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	return err;
 }
 
+/*
+ * get the file handle for the "/" directory on the server
+ */
 static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
-		struct nfs_fsinfo *info)
+			      struct nfs_fsinfo *info)
 {
-	struct nfs_fattr *	fattr = info->fattr;
-	unsigned char *		p;
-	struct qstr		q;
-	struct nfs4_lookup_arg args = {
-		.dir_fh = fhandle,
-		.name = &q,
-		.bitmask = nfs4_fattr_bitmap,
-	};
-	struct nfs4_lookup_res res = {
-		.server = server,
-		.fattr = fattr,
-		.fh = fhandle,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP],
-		.rpc_argp = &args,
-		.rpc_resp = &res,
-	};
 	int status;
 
-	/*
-	 * Now we do a separate LOOKUP for each component of the mount path.
-	 * The LOOKUPs are done separately so that we can conveniently
-	 * catch an ERR_WRONGSEC if it occurs along the way...
-	 */
 	status = nfs4_lookup_root(server, fhandle, info);
-	if (status)
-		goto out;
-
-	p = server->mnt_path;
-	for (;;) {
-		struct nfs4_exception exception = { };
-
-		while (*p == '/')
-			p++;
-		if (!*p)
-			break;
-		q.name = p;
-		while (*p && (*p != '/'))
-			p++;
-		q.len = p - q.name;
-
-		do {
-			nfs_fattr_init(fattr);
-			status = nfs4_handle_exception(server,
-					rpc_call_sync(server->client, &msg, 0),
-					&exception);
-		} while (exception.retry);
-		if (status == 0)
-			continue;
-		if (status == -ENOENT) {
-			printk(KERN_NOTICE "NFS: mount path %s does not exist!\n", server->mnt_path);
-			printk(KERN_NOTICE "NFS: suggestion: try mounting '/' instead.\n");
-		}
-		break;
-	}
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
 	if (status == 0)
 		status = nfs4_do_fsinfo(server, fhandle, info);
-out:
 	return nfs4_map_errors(status);
 }
 
@@ -1565,7 +1521,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 
 	nfs_fattr_init(fattr);
 	
-	cred = rpcauth_lookupcred(NFS_SERVER(inode)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
 
@@ -1583,6 +1539,52 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	return status;
 }
 
+static int _nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh,
+		struct qstr *name, struct nfs_fh *fhandle,
+		struct nfs_fattr *fattr)
+{
+	int		       status;
+	struct nfs4_lookup_arg args = {
+		.bitmask = server->attr_bitmask,
+		.dir_fh = dirfh,
+		.name = name,
+	};
+	struct nfs4_lookup_res res = {
+		.server = server,
+		.fattr = fattr,
+		.fh = fhandle,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+
+	nfs_fattr_init(fattr);
+
+	dprintk("NFS call  lookupfh %s\n", name->name);
+	status = rpc_call_sync(server->client, &msg, 0);
+	dprintk("NFS reply lookupfh: %d\n", status);
+	if (status == -NFS4ERR_MOVED)
+		status = -EREMOTE;
+	return status;
+}
+
+static int nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh,
+			      struct qstr *name, struct nfs_fh *fhandle,
+			      struct nfs_fattr *fattr)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_proc_lookupfh(server, dirfh, name,
+						    fhandle, fattr),
+				&exception);
+	} while (exception.retry);
+	return err;
+}
+
 static int _nfs4_proc_lookup(struct inode *dir, struct qstr *name,
 		struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
@@ -1881,7 +1883,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	struct rpc_cred *cred;
 	int status = 0;
 
-	cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(dir)->cl_auth, 0);
 	if (IS_ERR(cred)) {
 		status = PTR_ERR(cred);
 		goto out;
@@ -2089,24 +2091,24 @@ static int nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *n
 	return err;
 }
 
-static int _nfs4_proc_symlink(struct inode *dir, struct qstr *name,
-		struct qstr *path, struct iattr *sattr, struct nfs_fh *fhandle,
-		struct nfs_fattr *fattr)
+static int _nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
+		struct page *page, unsigned int len, struct iattr *sattr)
 {
 	struct nfs_server *server = NFS_SERVER(dir);
-	struct nfs_fattr dir_fattr;
+	struct nfs_fh fhandle;
+	struct nfs_fattr fattr, dir_fattr;
 	struct nfs4_create_arg arg = {
 		.dir_fh = NFS_FH(dir),
 		.server = server,
-		.name = name,
+		.name = &dentry->d_name,
 		.attrs = sattr,
 		.ftype = NF4LNK,
 		.bitmask = server->attr_bitmask,
 	};
 	struct nfs4_create_res res = {
 		.server = server,
-		.fh = fhandle,
-		.fattr = fattr,
+		.fh = &fhandle,
+		.fattr = &fattr,
 		.dir_fattr = &dir_fattr,
 	};
 	struct rpc_message msg = {
@@ -2116,29 +2118,32 @@ static int _nfs4_proc_symlink(struct inode *dir, struct qstr *name,
 	};
 	int			status;
 
-	if (path->len > NFS4_MAXPATHLEN)
+	if (len > NFS4_MAXPATHLEN)
 		return -ENAMETOOLONG;
-	arg.u.symlink = path;
-	nfs_fattr_init(fattr);
+
+	arg.u.symlink.pages = &page;
+	arg.u.symlink.len = len;
+	nfs_fattr_init(&fattr);
 	nfs_fattr_init(&dir_fattr);
 	
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	if (!status)
+	if (!status) {
 		update_changeattr(dir, &res.dir_cinfo);
-	nfs_post_op_update_inode(dir, res.dir_fattr);
+		nfs_post_op_update_inode(dir, res.dir_fattr);
+		status = nfs_instantiate(dentry, &fhandle, &fattr);
+	}
 	return status;
 }
 
-static int nfs4_proc_symlink(struct inode *dir, struct qstr *name,
-		struct qstr *path, struct iattr *sattr, struct nfs_fh *fhandle,
-		struct nfs_fattr *fattr)
+static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
+		struct page *page, unsigned int len, struct iattr *sattr)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
 		err = nfs4_handle_exception(NFS_SERVER(dir),
-				_nfs4_proc_symlink(dir, name, path, sattr,
-					fhandle, fattr),
+				_nfs4_proc_symlink(dir, dentry, page,
+							len, sattr),
 				&exception);
 	} while (exception.retry);
 	return err;
@@ -2521,7 +2526,7 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, int how)
  */
 static void nfs4_renew_done(struct rpc_task *task, void *data)
 {
-	struct nfs4_client *clp = (struct nfs4_client *)task->tk_msg.rpc_argp;
+	struct nfs_client *clp = (struct nfs_client *)task->tk_msg.rpc_argp;
 	unsigned long timestamp = (unsigned long)data;
 
 	if (task->tk_status < 0) {
@@ -2543,7 +2548,7 @@ static const struct rpc_call_ops nfs4_renew_ops = {
 	.rpc_call_done = nfs4_renew_done,
 };
 
-int nfs4_proc_async_renew(struct nfs4_client *clp, struct rpc_cred *cred)
+int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -2555,7 +2560,7 @@ int nfs4_proc_async_renew(struct nfs4_client *clp, struct rpc_cred *cred)
 			&nfs4_renew_ops, (void *)jiffies);
 }
 
-int nfs4_proc_renew(struct nfs4_client *clp, struct rpc_cred *cred)
+int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -2770,7 +2775,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		return -EOPNOTSUPP;
 	nfs_inode_return_delegation(inode);
 	buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
-	ret = rpc_call_sync(NFS_SERVER(inode)->client, &msg, 0);
+	ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (ret == 0)
 		nfs4_write_cached_acl(inode, buf, buflen);
 	return ret;
@@ -2791,7 +2796,7 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen
 static int
 nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 
 	if (!clp || task->tk_status >= 0)
 		return 0;
@@ -2828,7 +2833,7 @@ static int nfs4_wait_bit_interruptible(void *word)
 	return 0;
 }
 
-static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs4_client *clp)
+static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs_client *clp)
 {
 	sigset_t oldset;
 	int res;
@@ -2871,7 +2876,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
  */
 int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	int ret = errorcode;
 
 	exception->retry = 0;
@@ -2886,6 +2891,7 @@ int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct
 			if (ret == 0)
 				exception->retry = 1;
 			break;
+		case -NFS4ERR_FILE_OPEN:
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
 			ret = nfs4_delay(server->client, &exception->timeout);
@@ -2898,7 +2904,7 @@ int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct
 	return nfs4_map_errors(ret);
 }
 
-int nfs4_proc_setclientid(struct nfs4_client *clp, u32 program, unsigned short port, struct rpc_cred *cred)
+int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, unsigned short port, struct rpc_cred *cred)
 {
 	nfs4_verifier sc_verifier;
 	struct nfs4_setclientid setclientid = {
@@ -2922,7 +2928,7 @@ int nfs4_proc_setclientid(struct nfs4_client *clp, u32 program, unsigned short p
 	for(;;) {
 		setclientid.sc_name_len = scnprintf(setclientid.sc_name,
 				sizeof(setclientid.sc_name), "%s/%u.%u.%u.%u %s %u",
-				clp->cl_ipaddr, NIPQUAD(clp->cl_addr.s_addr),
+				clp->cl_ipaddr, NIPQUAD(clp->cl_addr.sin_addr),
 				cred->cr_ops->cr_name,
 				clp->cl_id_uniquifier);
 		setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
@@ -2945,7 +2951,7 @@ int nfs4_proc_setclientid(struct nfs4_client *clp, u32 program, unsigned short p
 	return status;
 }
 
-static int _nfs4_proc_setclientid_confirm(struct nfs4_client *clp, struct rpc_cred *cred)
+static int _nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct nfs_fsinfo fsinfo;
 	struct rpc_message msg = {
@@ -2969,7 +2975,7 @@ static int _nfs4_proc_setclientid_confirm(struct nfs4_client *clp, struct rpc_cr
 	return status;
 }
 
-int nfs4_proc_setclientid_confirm(struct nfs4_client *clp, struct rpc_cred *cred)
+int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	long timeout;
 	int err;
@@ -3077,7 +3083,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 		switch (err) {
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
-				nfs4_schedule_state_recovery(server->nfs4_state);
+				nfs4_schedule_state_recovery(server->nfs_client);
 			case 0:
 				return 0;
 		}
@@ -3106,7 +3112,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 {
 	struct inode *inode = state->inode;
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs_lockt_args arg = {
 		.fh = NFS_FH(inode),
 		.fl = request,
@@ -3231,7 +3237,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			break;
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_EXPIRED:
-			nfs4_schedule_state_recovery(calldata->server->nfs4_state);
+			nfs4_schedule_state_recovery(calldata->server->nfs_client);
 			break;
 		default:
 			if (nfs4_async_handle_error(task, calldata->server) == -EAGAIN) {
@@ -3343,7 +3349,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	if (p->arg.lock_seqid == NULL)
 		goto out_free;
 	p->arg.lock_stateid = &lsp->ls_stateid;
-	p->arg.lock_owner.clientid = server->nfs4_state->cl_clientid;
+	p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
 	p->arg.lock_owner.id = lsp->ls_id;
 	p->lsp = lsp;
 	atomic_inc(&lsp->ls_count);
@@ -3513,7 +3519,7 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
 
 static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
-	struct nfs4_client *clp = state->owner->so_client;
+	struct nfs_client *clp = state->owner->so_client;
 	unsigned char fl_flags = request->fl_flags;
 	int status;
 
@@ -3715,7 +3721,7 @@ static struct inode_operations nfs4_file_inode_operations = {
 	.listxattr	= nfs4_listxattr,
 };
 
-struct nfs_rpc_ops	nfs_v4_clientops = {
+const struct nfs_rpc_ops nfs_v4_clientops = {
 	.version	= 4,			/* protocol version */
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
@@ -3723,6 +3729,7 @@ struct nfs_rpc_ops	nfs_v4_clientops = {
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
+	.lookupfh	= nfs4_proc_lookupfh,
 	.lookup		= nfs4_proc_lookup,
 	.access		= nfs4_proc_access,
 	.readlink	= nfs4_proc_readlink,
@@ -3743,6 +3750,7 @@ struct nfs_rpc_ops	nfs_v4_clientops = {
 	.statfs		= nfs4_proc_statfs,
 	.fsinfo		= nfs4_proc_fsinfo,
 	.pathconf	= nfs4_proc_pathconf,
+	.set_capabilities = nfs4_server_capabilities,
 	.decode_dirent	= nfs4_decode_dirent,
 	.read_setup	= nfs4_proc_read_setup,
 	.read_done	= nfs4_read_done,

fs/nfs/nfs4renewd.c

@@ -61,7 +61,7 @@
 void
 nfs4_renew_state(void *data)
 {
-	struct nfs4_client *clp = (struct nfs4_client *)data;
+	struct nfs_client *clp = (struct nfs_client *)data;
 	struct rpc_cred *cred;
 	long lease, timeout;
 	unsigned long last, now;
@@ -108,7 +108,7 @@ out:
 
 /* Must be called with clp->cl_sem locked for writes */
 void
-nfs4_schedule_state_renewal(struct nfs4_client *clp)
+nfs4_schedule_state_renewal(struct nfs_client *clp)
 {
 	long timeout;
 
@@ -121,32 +121,20 @@ nfs4_schedule_state_renewal(struct nfs4_client *clp)
 			__FUNCTION__, (timeout + HZ - 1) / HZ);
 	cancel_delayed_work(&clp->cl_renewd);
 	schedule_delayed_work(&clp->cl_renewd, timeout);
+	set_bit(NFS_CS_RENEWD, &clp->cl_res_state);
 	spin_unlock(&clp->cl_lock);
 }
 
 void
 nfs4_renewd_prepare_shutdown(struct nfs_server *server)
 {
-	struct nfs4_client *clp = server->nfs4_state;
-
-	if (!clp)
-		return;
 	flush_scheduled_work();
-	down_write(&clp->cl_sem);
-	if (!list_empty(&server->nfs4_siblings))
-		list_del_init(&server->nfs4_siblings);
-	up_write(&clp->cl_sem);
 }
 
-/* Must be called with clp->cl_sem locked for writes */
 void
-nfs4_kill_renewd(struct nfs4_client *clp)
+nfs4_kill_renewd(struct nfs_client *clp)
 {
 	down_read(&clp->cl_sem);
-	if (!list_empty(&clp->cl_superblocks)) {
-		up_read(&clp->cl_sem);
-		return;
-	}
 	cancel_delayed_work(&clp->cl_renewd);
 	up_read(&clp->cl_sem);
 	flush_scheduled_work();

fs/nfs/nfs4state.c

@@ -50,149 +50,15 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
+#include "internal.h"
 
 #define OPENOWNER_POOL_SIZE	8
 
 const nfs4_stateid zero_stateid;
 
-static DEFINE_SPINLOCK(state_spinlock);
 static LIST_HEAD(nfs4_clientid_list);
 
-void
-init_nfsv4_state(struct nfs_server *server)
-{
-	server->nfs4_state = NULL;
-	INIT_LIST_HEAD(&server->nfs4_siblings);
-}
-
-void
-destroy_nfsv4_state(struct nfs_server *server)
-{
-	kfree(server->mnt_path);
-	server->mnt_path = NULL;
-	if (server->nfs4_state) {
-		nfs4_put_client(server->nfs4_state);
-		server->nfs4_state = NULL;
-	}
-}
-
-/*
- * nfs4_get_client(): returns an empty client structure
- * nfs4_put_client(): drops reference to client structure
- *
- * Since these are allocated/deallocated very rarely, we don't
- * bother putting them in a slab cache...
- */
-static struct nfs4_client *
-nfs4_alloc_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp;
-
-	if (nfs_callback_up() < 0)
-		return NULL;
-	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) {
-		nfs_callback_down();
-		return NULL;
-	}
-	memcpy(&clp->cl_addr, addr, sizeof(clp->cl_addr));
-	init_rwsem(&clp->cl_sem);
-	INIT_LIST_HEAD(&clp->cl_delegations);
-	INIT_LIST_HEAD(&clp->cl_state_owners);
-	INIT_LIST_HEAD(&clp->cl_unused);
-	spin_lock_init(&clp->cl_lock);
-	atomic_set(&clp->cl_count, 1);
-	INIT_WORK(&clp->cl_renewd, nfs4_renew_state, clp);
-	INIT_LIST_HEAD(&clp->cl_superblocks);
-	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS4 client");
-	clp->cl_rpcclient = ERR_PTR(-EINVAL);
-	clp->cl_boot_time = CURRENT_TIME;
-	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	return clp;
-}
-
-static void
-nfs4_free_client(struct nfs4_client *clp)
-{
-	struct nfs4_state_owner *sp;
-
-	while (!list_empty(&clp->cl_unused)) {
-		sp = list_entry(clp->cl_unused.next,
-				struct nfs4_state_owner,
-				so_list);
-		list_del(&sp->so_list);
-		kfree(sp);
-	}
-	BUG_ON(!list_empty(&clp->cl_state_owners));
-	nfs_idmap_delete(clp);
-	if (!IS_ERR(clp->cl_rpcclient))
-		rpc_shutdown_client(clp->cl_rpcclient);
-	kfree(clp);
-	nfs_callback_down();
-}
-
-static struct nfs4_client *__nfs4_find_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp;
-	list_for_each_entry(clp, &nfs4_clientid_list, cl_servers) {
-		if (memcmp(&clp->cl_addr, addr, sizeof(clp->cl_addr)) == 0) {
-			atomic_inc(&clp->cl_count);
-			return clp;
-		}
-	}
-	return NULL;
-}
-
-struct nfs4_client *nfs4_find_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp;
-	spin_lock(&state_spinlock);
-	clp = __nfs4_find_client(addr);
-	spin_unlock(&state_spinlock);
-	return clp;
-}
-
-struct nfs4_client *
-nfs4_get_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp, *new = NULL;
-
-	spin_lock(&state_spinlock);
-	for (;;) {
-		clp = __nfs4_find_client(addr);
-		if (clp != NULL)
-			break;
-		clp = new;
-		if (clp != NULL) {
-			list_add(&clp->cl_servers, &nfs4_clientid_list);
-			new = NULL;
-			break;
-		}
-		spin_unlock(&state_spinlock);
-		new = nfs4_alloc_client(addr);
-		spin_lock(&state_spinlock);
-		if (new == NULL)
-			break;
-	}
-	spin_unlock(&state_spinlock);
-	if (new)
-		nfs4_free_client(new);
-	return clp;
-}
-
-void
-nfs4_put_client(struct nfs4_client *clp)
-{
-	if (!atomic_dec_and_lock(&clp->cl_count, &state_spinlock))
-		return;
-	list_del(&clp->cl_servers);
-	spin_unlock(&state_spinlock);
-	BUG_ON(!list_empty(&clp->cl_superblocks));
-	rpc_wake_up(&clp->cl_rpcwaitq);
-	nfs4_kill_renewd(clp);
-	nfs4_free_client(clp);
-}
-
-static int nfs4_init_client(struct nfs4_client *clp, struct rpc_cred *cred)
+static int nfs4_init_client(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	int status = nfs4_proc_setclientid(clp, NFS4_CALLBACK,
 			nfs_callback_tcpport, cred);
@@ -204,13 +70,13 @@ static int nfs4_init_client(struct nfs4_client *clp, struct rpc_cred *cred)
 }
 
 u32
-nfs4_alloc_lockowner_id(struct nfs4_client *clp)
+nfs4_alloc_lockowner_id(struct nfs_client *clp)
 {
 	return clp->cl_lockowner_id ++;
 }
 
 static struct nfs4_state_owner *
-nfs4_client_grab_unused(struct nfs4_client *clp, struct rpc_cred *cred)
+nfs4_client_grab_unused(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct nfs4_state_owner *sp = NULL;
 
@@ -224,7 +90,7 @@ nfs4_client_grab_unused(struct nfs4_client *clp, struct rpc_cred *cred)
 	return sp;
 }
 
-struct rpc_cred *nfs4_get_renew_cred(struct nfs4_client *clp)
+struct rpc_cred *nfs4_get_renew_cred(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 	struct rpc_cred *cred = NULL;
@@ -238,7 +104,7 @@ struct rpc_cred *nfs4_get_renew_cred(struct nfs4_client *clp)
 	return cred;
 }
 
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs4_client *clp)
+struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 
@@ -251,7 +117,7 @@ struct rpc_cred *nfs4_get_setclientid_cred(struct nfs4_client *clp)
 }
 
 static struct nfs4_state_owner *
-nfs4_find_state_owner(struct nfs4_client *clp, struct rpc_cred *cred)
+nfs4_find_state_owner(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct nfs4_state_owner *sp, *res = NULL;
 
@@ -294,7 +160,7 @@ nfs4_alloc_state_owner(void)
 void
 nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 {
-	struct nfs4_client *clp = sp->so_client;
+	struct nfs_client *clp = sp->so_client;
 	spin_lock(&clp->cl_lock);
 	list_del_init(&sp->so_list);
 	spin_unlock(&clp->cl_lock);
@@ -306,7 +172,7 @@ nfs4_drop_state_owner(struct nfs4_state_owner *sp)
  */
 struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct rpc_cred *cred)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state_owner *sp, *new;
 
 	get_rpccred(cred);
@@ -337,7 +203,7 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct
  */
 void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 {
-	struct nfs4_client *clp = sp->so_client;
+	struct nfs_client *clp = sp->so_client;
 	struct rpc_cred *cred = sp->so_cred;
 
 	if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
@@ -540,7 +406,7 @@ __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 {
 	struct nfs4_lock_state *lsp;
-	struct nfs4_client *clp = state->owner->so_client;
+	struct nfs_client *clp = state->owner->so_client;
 
 	lsp = kzalloc(sizeof(*lsp), GFP_KERNEL);
 	if (lsp == NULL)
@@ -752,7 +618,7 @@ out:
 
 static int reclaimer(void *);
 
-static inline void nfs4_clear_recover_bit(struct nfs4_client *clp)
+static inline void nfs4_clear_recover_bit(struct nfs_client *clp)
 {
 	smp_mb__before_clear_bit();
 	clear_bit(NFS4CLNT_STATE_RECOVER, &clp->cl_state);
@@ -764,25 +630,25 @@ static inline void nfs4_clear_recover_bit(struct nfs4_client *clp)
 /*
  * State recovery routine
  */
-static void nfs4_recover_state(struct nfs4_client *clp)
+static void nfs4_recover_state(struct nfs_client *clp)
 {
 	struct task_struct *task;
 
 	__module_get(THIS_MODULE);
 	atomic_inc(&clp->cl_count);
 	task = kthread_run(reclaimer, clp, "%u.%u.%u.%u-reclaim",
-			NIPQUAD(clp->cl_addr));
+			NIPQUAD(clp->cl_addr.sin_addr));
 	if (!IS_ERR(task))
 		return;
 	nfs4_clear_recover_bit(clp);
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put(THIS_MODULE);
 }
 
 /*
  * Schedule a state recovery attempt
  */
-void nfs4_schedule_state_recovery(struct nfs4_client *clp)
+void nfs4_schedule_state_recovery(struct nfs_client *clp)
 {
 	if (!clp)
 		return;
@@ -879,7 +745,7 @@ out_err:
 	return status;
 }
 
-static void nfs4_state_mark_reclaim(struct nfs4_client *clp)
+static void nfs4_state_mark_reclaim(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 	struct nfs4_state *state;
@@ -903,7 +769,7 @@ static void nfs4_state_mark_reclaim(struct nfs4_client *clp)
 
 static int reclaimer(void *ptr)
 {
-	struct nfs4_client *clp = ptr;
+	struct nfs_client *clp = ptr;
 	struct nfs4_state_owner *sp;
 	struct nfs4_state_recovery_ops *ops;
 	struct rpc_cred *cred;
@@ -970,12 +836,12 @@ out:
 	if (status == -NFS4ERR_CB_PATH_DOWN)
 		nfs_handle_cb_pathdown(clp);
 	nfs4_clear_recover_bit(clp);
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put_and_exit(0);
 	return 0;
 out_error:
 	printk(KERN_WARNING "Error: state recovery failed on NFSv4 server %u.%u.%u.%u with error %d\n",
-				NIPQUAD(clp->cl_addr.s_addr), -status);
+				NIPQUAD(clp->cl_addr.sin_addr), -status);
 	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 	goto out;
 }

fs/nfs/nfs4xdr.c

@@ -58,7 +58,7 @@
 /* Mapping from NFS error code to "errno" error code. */
 #define errno_NFSERR_IO		EIO
 
-static int nfs_stat_to_errno(int);
+static int nfs4_stat_to_errno(int);
 
 /* NFSv4 COMPOUND tags are only wanted for debugging purposes */
 #ifdef DEBUG
@@ -128,7 +128,7 @@ static int nfs_stat_to_errno(int);
 #define decode_link_maxsz	(op_decode_hdr_maxsz + 5)
 #define encode_symlink_maxsz	(op_encode_hdr_maxsz + \
 				1 + nfs4_name_maxsz + \
-				nfs4_path_maxsz + \
+				1 + \
 				nfs4_fattr_maxsz)
 #define decode_symlink_maxsz	(op_decode_hdr_maxsz + 8)
 #define encode_create_maxsz	(op_encode_hdr_maxsz + \
@@ -529,7 +529,7 @@ static int encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const s
 	if (iap->ia_valid & ATTR_MODE)
 		len += 4;
 	if (iap->ia_valid & ATTR_UID) {
-		owner_namelen = nfs_map_uid_to_name(server->nfs4_state, iap->ia_uid, owner_name);
+		owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name);
 		if (owner_namelen < 0) {
 			printk(KERN_WARNING "nfs: couldn't resolve uid %d to string\n",
 			       iap->ia_uid);
@@ -541,7 +541,7 @@ static int encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const s
 		len += 4 + (XDR_QUADLEN(owner_namelen) << 2);
 	}
 	if (iap->ia_valid & ATTR_GID) {
-		owner_grouplen = nfs_map_gid_to_group(server->nfs4_state, iap->ia_gid, owner_group);
+		owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group);
 		if (owner_grouplen < 0) {
 			printk(KERN_WARNING "nfs4: couldn't resolve gid %d to string\n",
 			       iap->ia_gid);
@@ -673,9 +673,9 @@ static int encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *c
 
 	switch (create->ftype) {
 	case NF4LNK:
-		RESERVE_SPACE(4 + create->u.symlink->len);
-		WRITE32(create->u.symlink->len);
-		WRITEMEM(create->u.symlink->name, create->u.symlink->len);
+		RESERVE_SPACE(4);
+		WRITE32(create->u.symlink.len);
+		xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len);
 		break;
 
 	case NF4BLK: case NF4CHR:
@@ -1160,7 +1160,7 @@ static int encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, con
 	return 0;
 }
 
-static int encode_renew(struct xdr_stream *xdr, const struct nfs4_client *client_stateid)
+static int encode_renew(struct xdr_stream *xdr, const struct nfs_client *client_stateid)
 {
 	uint32_t *p;
 
@@ -1246,7 +1246,7 @@ static int encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclien
 	return 0;
 }
 
-static int encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4_client *client_state)
+static int encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_client *client_state)
 {
         uint32_t *p;
 
@@ -1945,7 +1945,7 @@ static int nfs4_xdr_enc_server_caps(struct rpc_rqst *req, uint32_t *p, const str
 /*
  * a RENEW request
  */
-static int nfs4_xdr_enc_renew(struct rpc_rqst *req, uint32_t *p, struct nfs4_client *clp)
+static int nfs4_xdr_enc_renew(struct rpc_rqst *req, uint32_t *p, struct nfs_client *clp)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
@@ -1975,7 +1975,7 @@ static int nfs4_xdr_enc_setclientid(struct rpc_rqst *req, uint32_t *p, struct nf
 /*
  * a SETCLIENTID_CONFIRM request
  */
-static int nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, uint32_t *p, struct nfs4_client *clp)
+static int nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, uint32_t *p, struct nfs_client *clp)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
@@ -2127,12 +2127,12 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 	}
 	READ32(nfserr);
 	if (nfserr != NFS_OK)
-		return -nfs_stat_to_errno(nfserr);
+		return -nfs4_stat_to_errno(nfserr);
 	return 0;
 }
 
 /* Dummy routine */
-static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs4_client *clp)
+static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp)
 {
 	uint32_t *p;
 	unsigned int strlen;
@@ -2636,7 +2636,7 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t
 	return 0;
 }
 
-static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_client *clp, int32_t *uid)
+static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, int32_t *uid)
 {
 	uint32_t len, *p;
 
@@ -2660,7 +2660,7 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
 	return 0;
 }
 
-static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_client *clp, int32_t *gid)
+static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, int32_t *gid)
 {
 	uint32_t len, *p;
 
@@ -3051,9 +3051,9 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons
 	fattr->mode |= fmode;
 	if ((status = decode_attr_nlink(xdr, bitmap, &fattr->nlink)) != 0)
 		goto xdr_error;
-	if ((status = decode_attr_owner(xdr, bitmap, server->nfs4_state, &fattr->uid)) != 0)
+	if ((status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid)) != 0)
 		goto xdr_error;
-	if ((status = decode_attr_group(xdr, bitmap, server->nfs4_state, &fattr->gid)) != 0)
+	if ((status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid)) != 0)
 		goto xdr_error;
 	if ((status = decode_attr_rdev(xdr, bitmap, &fattr->rdev)) != 0)
 		goto xdr_error;
@@ -3254,7 +3254,7 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
 			if (decode_space_limit(xdr, &res->maxsize) < 0)
 				return -EIO;
 	}
-	return decode_ace(xdr, NULL, res->server->nfs4_state);
+	return decode_ace(xdr, NULL, res->server->nfs_client);
 }
 
 static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
@@ -3565,7 +3565,7 @@ static int decode_setattr(struct xdr_stream *xdr, struct nfs_setattrres *res)
 	return 0;
 }
 
-static int decode_setclientid(struct xdr_stream *xdr, struct nfs4_client *clp)
+static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp)
 {
 	uint32_t *p;
 	uint32_t opnum;
@@ -3598,7 +3598,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs4_client *clp)
 		READ_BUF(len);
 		return -NFSERR_CLID_INUSE;
 	} else
-		return -nfs_stat_to_errno(nfserr);
+		return -nfs4_stat_to_errno(nfserr);
 
 	return 0;
 }
@@ -4256,7 +4256,7 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, uint32_t *p, struct nfs_fsi
 	if (!status)
 		status = decode_fsinfo(&xdr, fsinfo);
 	if (!status)
-		status = -nfs_stat_to_errno(hdr.status);
+		status = -nfs4_stat_to_errno(hdr.status);
 	return status;
 }
 
@@ -4335,7 +4335,7 @@ static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, uint32_t *p, void *dummy)
  * a SETCLIENTID request
  */
 static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, uint32_t *p,
-		struct nfs4_client *clp)
+		struct nfs_client *clp)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4346,7 +4346,7 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, uint32_t *p,
 	if (!status)
 		status = decode_setclientid(&xdr, clp);
 	if (!status)
-		status = -nfs_stat_to_errno(hdr.status);
+		status = -nfs4_stat_to_errno(hdr.status);
 	return status;
 }
 
@@ -4368,7 +4368,7 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, uint32_t *p, s
 	if (!status)
 		status = decode_fsinfo(&xdr, fsinfo);
 	if (!status)
-		status = -nfs_stat_to_errno(hdr.status);
+		status = -nfs4_stat_to_errno(hdr.status);
 	return status;
 }
 
@@ -4521,7 +4521,7 @@ static struct {
  * This one is used jointly by NFSv2 and NFSv3.
  */
 static int
-nfs_stat_to_errno(int stat)
+nfs4_stat_to_errno(int stat)
 {
 	int i;
 	for (i = 0; nfs_errtbl[i].stat != -1; i++) {

fs/nfs/proc.c

@@ -66,14 +66,14 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 
 	dprintk("%s: call getattr\n", __FUNCTION__);
 	nfs_fattr_init(fattr);
-	status = rpc_call_sync(server->client_sys, &msg, 0);
+	status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
 	dprintk("%s: reply getattr: %d\n", __FUNCTION__, status);
 	if (status)
 		return status;
 	dprintk("%s: call statfs\n", __FUNCTION__);
 	msg.rpc_proc = &nfs_procedures[NFSPROC_STATFS];
 	msg.rpc_resp = &fsinfo;
-	status = rpc_call_sync(server->client_sys, &msg, 0);
+	status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
 	dprintk("%s: reply statfs: %d\n", __FUNCTION__, status);
 	if (status)
 		return status;
@@ -425,16 +425,17 @@ nfs_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 }
 
 static int
-nfs_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
-		 struct iattr *sattr, struct nfs_fh *fhandle,
-		 struct nfs_fattr *fattr)
+nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
+		 unsigned int len, struct iattr *sattr)
 {
+	struct nfs_fh fhandle;
+	struct nfs_fattr fattr;
 	struct nfs_symlinkargs	arg = {
 		.fromfh		= NFS_FH(dir),
-		.fromname	= name->name,
-		.fromlen	= name->len,
-		.topath		= path->name,
-		.tolen		= path->len,
+		.fromname	= dentry->d_name.name,
+		.fromlen	= dentry->d_name.len,
+		.pages		= &page,
+		.pathlen	= len,
 		.sattr		= sattr
 	};
 	struct rpc_message msg = {
@@ -443,13 +444,25 @@ nfs_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
 	};
 	int			status;
 
-	if (path->len > NFS2_MAXPATHLEN)
+	if (len > NFS2_MAXPATHLEN)
 		return -ENAMETOOLONG;
-	dprintk("NFS call  symlink %s -> %s\n", name->name, path->name);
-	nfs_fattr_init(fattr);
-	fhandle->size = 0;
+
+	dprintk("NFS call  symlink %s\n", dentry->d_name.name);
+
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
 	nfs_mark_for_revalidate(dir);
+
+	/*
+	 * V2 SYMLINK requests don't return any attributes.  Setting the
+	 * filehandle size to zero indicates to nfs_instantiate that it
+	 * should fill in the data with a LOOKUP call on the wire.
+	 */
+	if (status == 0) {
+		nfs_fattr_init(&fattr);
+		fhandle.size = 0;
+		status = nfs_instantiate(dentry, &fhandle, &fattr);
+	}
+
 	dprintk("NFS reply symlink: %d\n", status);
 	return status;
 }
@@ -671,7 +684,7 @@ nfs_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 }
 
 
-struct nfs_rpc_ops	nfs_v2_clientops = {
+const struct nfs_rpc_ops nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs_dir_inode_operations,

fs/nfs/read.c

@@ -171,7 +171,7 @@ static int nfs_readpage_sync(struct nfs_open_context *ctx, struct inode *inode,
 		rdata->args.offset = page_offset(page) + rdata->args.pgbase;
 
 		dprintk("NFS: nfs_proc_read(%s, (%s/%Ld), %Lu, %u)\n",
-			NFS_SERVER(inode)->hostname,
+			NFS_SERVER(inode)->nfs_client->cl_hostname,
 			inode->i_sb->s_id,
 			(long long)NFS_FILEID(inode),
 			(unsigned long long)rdata->args.pgbase,
@@ -568,8 +568,13 @@ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
 
 	nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, resp->count);
 
-	/* Is this a short read? */
-	if (task->tk_status >= 0 && resp->count < argp->count && !resp->eof) {
+	if (task->tk_status < 0) {
+		if (task->tk_status == -ESTALE) {
+			set_bit(NFS_INO_STALE, &NFS_FLAGS(data->inode));
+			nfs_mark_for_revalidate(data->inode);
+		}
+	} else if (resp->count < argp->count && !resp->eof) {
+		/* This is a short read! */
 		nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
 		/* Has the server at least made some progress? */
 		if (resp->count != 0) {
@@ -616,6 +621,10 @@ int nfs_readpage(struct file *file, struct page *page)
 	if (error)
 		goto out_error;
 
+	error = -ESTALE;
+	if (NFS_STALE(inode))
+		goto out_error;
+
 	if (file == NULL) {
 		ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
 		if (ctx == NULL)
@@ -678,7 +687,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	};
 	struct inode *inode = mapping->host;
 	struct nfs_server *server = NFS_SERVER(inode);
-	int ret;
+	int ret = -ESTALE;
 
 	dprintk("NFS: nfs_readpages (%s/%Ld %d)\n",
 			inode->i_sb->s_id,
@@ -686,6 +695,9 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			nr_pages);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
 
+	if (NFS_STALE(inode))
+		goto out;
+
 	if (filp == NULL) {
 		desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
 		if (desc.ctx == NULL)
@@ -701,6 +713,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			ret = err;
 	}
 	put_nfs_open_context(desc.ctx);
+out:
 	return ret;
 }
 

fs/nfs/super.c

@@ -13,6 +13,11 @@
  *
  *  Split from inode.c by David Howells <dhowells@redhat.com>
  *
+ * - superblocks are indexed on server only - all inodes, dentries, etc. associated with a
+ *   particular server are held in the same superblock
+ * - NFS superblocks can have several effective roots to the dentry tree
+ * - directory type roots are spliced into the tree when a path from one root reaches the root
+ *   of another (see nfs_lookup())
  */
 
 #include <linux/config.h>
@@ -52,66 +57,12 @@
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
-/* Maximum number of readahead requests
- * FIXME: this should really be a sysctl so that users may tune it to suit
- *        their needs. People that do NFS over a slow network, might for
- *        instance want to reduce it to something closer to 1 for improved
- *        interactive response.
- */
-#define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)
-
-/*
- * RPC cruft for NFS
- */
-static struct rpc_version * nfs_version[] = {
-	NULL,
-	NULL,
-	&nfs_version2,
-#if defined(CONFIG_NFS_V3)
-	&nfs_version3,
-#elif defined(CONFIG_NFS_V4)
-	NULL,
-#endif
-#if defined(CONFIG_NFS_V4)
-	&nfs_version4,
-#endif
-};
-
-static struct rpc_program nfs_program = {
-	.name			= "nfs",
-	.number			= NFS_PROGRAM,
-	.nrvers			= ARRAY_SIZE(nfs_version),
-	.version		= nfs_version,
-	.stats			= &nfs_rpcstat,
-	.pipe_dir_name		= "/nfs",
-};
-
-struct rpc_stat nfs_rpcstat = {
-	.program		= &nfs_program
-};
-
-
-#ifdef CONFIG_NFS_V3_ACL
-static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
-static struct rpc_version *	nfsacl_version[] = {
-	[3]			= &nfsacl_version3,
-};
-
-struct rpc_program		nfsacl_program = {
-	.name =			"nfsacl",
-	.number =		NFS_ACL_PROGRAM,
-	.nrvers =		ARRAY_SIZE(nfsacl_version),
-	.version =		nfsacl_version,
-	.stats =		&nfsacl_rpcstat,
-};
-#endif  /* CONFIG_NFS_V3_ACL */
-
 static void nfs_umount_begin(struct vfsmount *, int);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
 static int  nfs_show_options(struct seq_file *, struct vfsmount *);
 static int  nfs_show_stats(struct seq_file *, struct vfsmount *);
 static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *);
-static int nfs_clone_nfs_sb(struct file_system_type *fs_type,
+static int nfs_xdev_get_sb(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
 static void nfs_kill_super(struct super_block *);
 
@@ -123,10 +74,10 @@ static struct file_system_type nfs_fs_type = {
 	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
 
-struct file_system_type clone_nfs_fs_type = {
+struct file_system_type nfs_xdev_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs",
-	.get_sb		= nfs_clone_nfs_sb,
+	.get_sb		= nfs_xdev_get_sb,
 	.kill_sb	= nfs_kill_super,
 	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -145,10 +96,10 @@ static struct super_operations nfs_sops = {
 #ifdef CONFIG_NFS_V4
 static int nfs4_get_sb(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
-static int nfs_clone_nfs4_sb(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
-static int nfs_referral_nfs4_sb(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
+static int nfs4_xdev_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
+static int nfs4_referral_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
 static void nfs4_kill_super(struct super_block *sb);
 
 static struct file_system_type nfs4_fs_type = {
@@ -159,18 +110,18 @@ static struct file_system_type nfs4_fs_type = {
 	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
 
-struct file_system_type clone_nfs4_fs_type = {
+struct file_system_type nfs4_xdev_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs4",
-	.get_sb		= nfs_clone_nfs4_sb,
+	.get_sb		= nfs4_xdev_get_sb,
 	.kill_sb	= nfs4_kill_super,
 	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
 
-struct file_system_type nfs_referral_nfs4_fs_type = {
+struct file_system_type nfs4_referral_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs4",
-	.get_sb		= nfs_referral_nfs4_sb,
+	.get_sb		= nfs4_referral_get_sb,
 	.kill_sb	= nfs4_kill_super,
 	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -187,39 +138,7 @@ static struct super_operations nfs4_sops = {
 };
 #endif
 
-#ifdef CONFIG_NFS_V4
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
-
-static int param_set_port(const char *val, struct kernel_param *kp)
-{
-	char *endp;
-	int num = simple_strtol(val, &endp, 0);
-	if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
-		return -EINVAL;
-	*((int *)kp->arg) = num;
-	return 0;
-}
-
-module_param_call(callback_tcpport, param_set_port, param_get_int,
-		 &nfs_callback_set_tcpport, 0644);
-#endif
-
-#ifdef CONFIG_NFS_V4
-static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
-{
-	char *endp;
-	int num = simple_strtol(val, &endp, 0);
-	int jif = num * HZ;
-	if (endp == val || *endp || num < 0 || jif < num)
-		return -EINVAL;
-	*((int *)kp->arg) = jif;
-	return 0;
-}
-
-module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
-		 &nfs_idmap_cache_timeout, 0644);
-#endif
+static struct shrinker *acl_shrinker;
 
 /*
  * Register the NFS filesystems
@@ -240,6 +159,7 @@ int __init register_nfs_fs(void)
 	if (ret < 0)
 		goto error_2;
 #endif
+	acl_shrinker = set_shrinker(DEFAULT_SEEKS, nfs_access_cache_shrinker);
 	return 0;
 
 #ifdef CONFIG_NFS_V4
@@ -257,6 +177,8 @@ error_0:
  */
 void __exit unregister_nfs_fs(void)
 {
+	if (acl_shrinker != NULL)
+		remove_shrinker(acl_shrinker);
 #ifdef CONFIG_NFS_V4
 	unregister_filesystem(&nfs4_fs_type);
 	nfs_unregister_sysctl();
@@ -269,11 +191,10 @@ void __exit unregister_nfs_fs(void)
  */
 static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct super_block *sb = dentry->d_sb;
-	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_server *server = NFS_SB(dentry->d_sb);
 	unsigned char blockbits;
 	unsigned long blockres;
-	struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode);
+	struct nfs_fh *fh = NFS_FH(dentry->d_inode);
 	struct nfs_fattr fattr;
 	struct nfs_fsstat res = {
 			.fattr = &fattr,
@@ -282,7 +203,7 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	lock_kernel();
 
-	error = server->rpc_ops->statfs(server, rootfh, &res);
+	error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
 	buf->f_type = NFS_SUPER_MAGIC;
 	if (error < 0)
 		goto out_err;
@@ -292,7 +213,7 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	 * case where f_frsize != f_bsize.  Eventually we want to
 	 * report the value of wtmult in this field.
 	 */
-	buf->f_frsize = sb->s_blocksize;
+	buf->f_frsize = dentry->d_sb->s_blocksize;
 
 	/*
 	 * On most *nix systems, f_blocks, f_bfree, and f_bavail
@@ -301,8 +222,8 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	 * thus historically Linux's sys_statfs reports these
 	 * fields in units of f_bsize.
 	 */
-	buf->f_bsize = sb->s_blocksize;
-	blockbits = sb->s_blocksize_bits;
+	buf->f_bsize = dentry->d_sb->s_blocksize;
+	blockbits = dentry->d_sb->s_blocksize_bits;
 	blockres = (1 << blockbits) - 1;
 	buf->f_blocks = (res.tbytes + blockres) >> blockbits;
 	buf->f_bfree = (res.fbytes + blockres) >> blockbits;
@@ -323,9 +244,12 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 }
 
+/*
+ * Map the security flavour number to a name
+ */
 static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
 {
-	static struct {
+	static const struct {
 		rpc_authflavor_t flavour;
 		const char *str;
 	} sec_flavours[] = {
@@ -356,10 +280,10 @@ static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
  */
 static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults)
 {
-	static struct proc_nfs_info {
+	static const struct proc_nfs_info {
 		int flag;
-		char *str;
-		char *nostr;
+		const char *str;
+		const char *nostr;
 	} nfs_info[] = {
 		{ NFS_MOUNT_SOFT, ",soft", ",hard" },
 		{ NFS_MOUNT_INTR, ",intr", "" },
@@ -369,11 +293,12 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		{ NFS_MOUNT_NOACL, ",noacl", "" },
 		{ 0, NULL, NULL }
 	};
-	struct proc_nfs_info *nfs_infop;
+	const struct proc_nfs_info *nfs_infop;
+	struct nfs_client *clp = nfss->nfs_client;
 	char buf[12];
-	char *proto;
+	const char *proto;
 
-	seq_printf(m, ",vers=%d", nfss->rpc_ops->version);
+	seq_printf(m, ",vers=%d", clp->rpc_ops->version);
 	seq_printf(m, ",rsize=%d", nfss->rsize);
 	seq_printf(m, ",wsize=%d", nfss->wsize);
 	if (nfss->acregmin != 3*HZ || showdefaults)
@@ -402,8 +327,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 			proto = buf;
 	}
 	seq_printf(m, ",proto=%s", proto);
-	seq_printf(m, ",timeo=%lu", 10U * nfss->retrans_timeo / HZ);
-	seq_printf(m, ",retrans=%u", nfss->retrans_count);
+	seq_printf(m, ",timeo=%lu", 10U * clp->retrans_timeo / HZ);
+	seq_printf(m, ",retrans=%u", clp->retrans_count);
 	seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor));
 }
 
@@ -417,7 +342,7 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
 	nfs_show_mount_options(m, nfss, 0);
 
 	seq_puts(m, ",addr=");
-	seq_escape(m, nfss->hostname, " \t\n\\");
+	seq_escape(m, nfss->nfs_client->cl_hostname, " \t\n\\");
 
 	return 0;
 }
@@ -454,7 +379,7 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 	seq_printf(m, ",namelen=%d", nfss->namelen);
 
 #ifdef CONFIG_NFS_V4
-	if (nfss->rpc_ops->version == 4) {
+	if (nfss->nfs_client->cl_nfsversion == 4) {
 		seq_printf(m, "\n\tnfsv4:\t");
 		seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
 		seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
@@ -501,782 +426,353 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 
 /*
  * Begin unmount by attempting to remove all automounted mountpoints we added
- * in response to traversals
+ * in response to xdev traversals and referrals
  */
 static void nfs_umount_begin(struct vfsmount *vfsmnt, int flags)
 {
-	struct nfs_server *server;
-	struct rpc_clnt	*rpc;
-
 	shrink_submounts(vfsmnt, &nfs_automount_list);
-	if (!(flags & MNT_FORCE))
-		return;
-	/* -EIO all pending I/O */
-	server = NFS_SB(vfsmnt->mnt_sb);
-	rpc = server->client;
-	if (!IS_ERR(rpc))
-		rpc_killall_tasks(rpc);
-	rpc = server->client_acl;
-	if (!IS_ERR(rpc))
-		rpc_killall_tasks(rpc);
 }
 
 /*
- * Obtain the root inode of the file system.
+ * Validate the NFS2/NFS3 mount data
+ * - fills in the mount root filehandle
  */
-static struct inode *
-nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo)
+static int nfs_validate_mount_data(struct nfs_mount_data *data,
+				   struct nfs_fh *mntfh)
 {
-	struct nfs_server	*server = NFS_SB(sb);
-	int			error;
-
-	error = server->rpc_ops->getroot(server, rootfh, fsinfo);
-	if (error < 0) {
-		dprintk("nfs_get_root: getattr error = %d\n", -error);
-		return ERR_PTR(error);
+	if (data == NULL) {
+		dprintk("%s: missing data argument\n", __FUNCTION__);
+		return -EINVAL;
 	}
 
-	server->fsid = fsinfo->fattr->fsid;
-	return nfs_fhget(sb, rootfh, fsinfo->fattr);
-}
-
-/*
- * Do NFS version-independent mount processing, and sanity checking
- */
-static int
-nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor)
-{
-	struct nfs_server	*server;
-	struct inode		*root_inode;
-	struct nfs_fattr	fattr;
-	struct nfs_fsinfo	fsinfo = {
-					.fattr = &fattr,
-				};
-	struct nfs_pathconf pathinfo = {
-			.fattr = &fattr,
-	};
-	int no_root_error = 0;
-	unsigned long max_rpc_payload;
-
-	/* We probably want something more informative here */
-	snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));
-
-	server = NFS_SB(sb);
+	if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) {
+		dprintk("%s: bad mount version\n", __FUNCTION__);
+		return -EINVAL;
+	}
 
-	sb->s_magic      = NFS_SUPER_MAGIC;
+	switch (data->version) {
+		case 1:
+			data->namlen = 0;
+		case 2:
+			data->bsize  = 0;
+		case 3:
+			if (data->flags & NFS_MOUNT_VER3) {
+				dprintk("%s: mount structure version %d does not support NFSv3\n",
+						__FUNCTION__,
+						data->version);
+				return -EINVAL;
+			}
+			data->root.size = NFS2_FHSIZE;
+			memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
+		case 4:
+			if (data->flags & NFS_MOUNT_SECFLAVOUR) {
+				dprintk("%s: mount structure version %d does not support strong security\n",
+						__FUNCTION__,
+						data->version);
+				return -EINVAL;
+			}
+		case 5:
+			memset(data->context, 0, sizeof(data->context));
+	}
 
-	server->io_stats = nfs_alloc_iostats();
-	if (server->io_stats == NULL)
-		return -ENOMEM;
+	/* Set the pseudoflavor */
+	if (!(data->flags & NFS_MOUNT_SECFLAVOUR))
+		data->pseudoflavor = RPC_AUTH_UNIX;
 
-	root_inode = nfs_get_root(sb, &server->fh, &fsinfo);
-	/* Did getting the root inode fail? */
-	if (IS_ERR(root_inode)) {
-		no_root_error = PTR_ERR(root_inode);
-		goto out_no_root;
-	}
-	sb->s_root = d_alloc_root(root_inode);
-	if (!sb->s_root) {
-		no_root_error = -ENOMEM;
-		goto out_no_root;
+#ifndef CONFIG_NFS_V3
+	/* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */
+	if (data->flags & NFS_MOUNT_VER3) {
+		dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__);
+		return -EPROTONOSUPPORT;
 	}
-	sb->s_root->d_op = server->rpc_ops->dentry_ops;
-
-	/* mount time stamp, in seconds */
-	server->mount_time = jiffies;
-
-	/* Get some general file system info */
-	if (server->namelen == 0 &&
-	    server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0)
-		server->namelen = pathinfo.max_namelen;
-	/* Work out a lot of parameters */
-	if (server->rsize == 0)
-		server->rsize = nfs_block_size(fsinfo.rtpref, NULL);
-	if (server->wsize == 0)
-		server->wsize = nfs_block_size(fsinfo.wtpref, NULL);
-
-	if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax)
-		server->rsize = nfs_block_size(fsinfo.rtmax, NULL);
-	if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax)
-		server->wsize = nfs_block_size(fsinfo.wtmax, NULL);
-
-	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
-	if (server->rsize > max_rpc_payload)
-		server->rsize = max_rpc_payload;
-	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
-		server->rsize = NFS_MAX_FILE_IO_SIZE;
-	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
-	if (server->wsize > max_rpc_payload)
-		server->wsize = max_rpc_payload;
-	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
-		server->wsize = NFS_MAX_FILE_IO_SIZE;
-	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+#endif /* CONFIG_NFS_V3 */
 
-	if (sb->s_blocksize == 0)
-		sb->s_blocksize = nfs_block_bits(server->wsize,
-							 &sb->s_blocksize_bits);
-	server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL);
-
-	server->dtsize = nfs_block_size(fsinfo.dtpref, NULL);
-	if (server->dtsize > PAGE_CACHE_SIZE)
-		server->dtsize = PAGE_CACHE_SIZE;
-	if (server->dtsize > server->rsize)
-		server->dtsize = server->rsize;
-
-	if (server->flags & NFS_MOUNT_NOAC) {
-		server->acregmin = server->acregmax = 0;
-		server->acdirmin = server->acdirmax = 0;
-		sb->s_flags |= MS_SYNCHRONOUS;
+	/* We now require that the mount process passes the remote address */
+	if (data->addr.sin_addr.s_addr == INADDR_ANY) {
+		dprintk("%s: mount program didn't pass remote address!\n",
+			__FUNCTION__);
+		return -EINVAL;
 	}
-	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
 
-	nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);
+	/* Prepare the root filehandle */
+	if (data->flags & NFS_MOUNT_VER3)
+		mntfh->size = data->root.size;
+	else
+		mntfh->size = NFS2_FHSIZE;
+
+	if (mntfh->size > sizeof(mntfh->data)) {
+		dprintk("%s: invalid root filehandle\n", __FUNCTION__);
+		return -EINVAL;
+	}
 
-	server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0;
-	server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0;
+	memcpy(mntfh->data, data->root.data, mntfh->size);
+	if (mntfh->size < sizeof(mntfh->data))
+		memset(mntfh->data + mntfh->size, 0,
+		       sizeof(mntfh->data) - mntfh->size);
 
-	/* We're airborne Set socket buffersize */
-	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
 	return 0;
-	/* Yargs. It didn't work out. */
-out_no_root:
-	dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error);
-	if (!IS_ERR(root_inode))
-		iput(root_inode);
-	return no_root_error;
 }
 
 /*
- * Initialise the timeout values for a connection
+ * Initialise the common bits of the superblock
  */
-static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans)
+static inline void nfs_initialise_sb(struct super_block *sb)
 {
-	to->to_initval = timeo * HZ / 10;
-	to->to_retries = retrans;
-	if (!to->to_retries)
-		to->to_retries = 2;
-
-	switch (proto) {
-	case IPPROTO_TCP:
-		if (!to->to_initval)
-			to->to_initval = 60 * HZ;
-		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
-			to->to_initval = NFS_MAX_TCP_TIMEOUT;
-		to->to_increment = to->to_initval;
-		to->to_maxval = to->to_initval + (to->to_increment * to->to_retries);
-		to->to_exponential = 0;
-		break;
-	case IPPROTO_UDP:
-	default:
-		if (!to->to_initval)
-			to->to_initval = 11 * HZ / 10;
-		if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
-			to->to_initval = NFS_MAX_UDP_TIMEOUT;
-		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
-		to->to_exponential = 1;
-		break;
-	}
-}
+	struct nfs_server *server = NFS_SB(sb);
 
-/*
- * Create an RPC client handle.
- */
-static struct rpc_clnt *
-nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data)
-{
-	struct rpc_timeout	timeparms;
-	struct rpc_xprt		*xprt = NULL;
-	struct rpc_clnt		*clnt = NULL;
-	int			proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;
-
-	nfs_init_timeout_values(&timeparms, proto, data->timeo, data->retrans);
-
-	server->retrans_timeo = timeparms.to_initval;
-	server->retrans_count = timeparms.to_retries;
-
-	/* create transport and client */
-	xprt = xprt_create_proto(proto, &server->addr, &timeparms);
-	if (IS_ERR(xprt)) {
-		dprintk("%s: cannot create RPC transport. Error = %ld\n",
-				__FUNCTION__, PTR_ERR(xprt));
-		return (struct rpc_clnt *)xprt;
-	}
-	clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
-				 server->rpc_ops->version, data->pseudoflavor);
-	if (IS_ERR(clnt)) {
-		dprintk("%s: cannot create RPC client. Error = %ld\n",
-				__FUNCTION__, PTR_ERR(xprt));
-		goto out_fail;
-	}
+	sb->s_magic = NFS_SUPER_MAGIC;
 
-	clnt->cl_intr     = 1;
-	clnt->cl_softrtry = 1;
+	/* We probably want something more informative here */
+	snprintf(sb->s_id, sizeof(sb->s_id),
+		 "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));
+
+	if (sb->s_blocksize == 0)
+		sb->s_blocksize = nfs_block_bits(server->wsize,
+						 &sb->s_blocksize_bits);
 
-	return clnt;
+	if (server->flags & NFS_MOUNT_NOAC)
+		sb->s_flags |= MS_SYNCHRONOUS;
 
-out_fail:
-	return clnt;
+	nfs_super_set_maxbytes(sb, server->maxfilesize);
 }
 
 /*
- * Clone a server record
+ * Finish setting up an NFS2/3 superblock
  */
-static struct nfs_server *nfs_clone_server(struct super_block *sb, struct nfs_clone_mount *data)
+static void nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data)
 {
 	struct nfs_server *server = NFS_SB(sb);
-	struct nfs_server *parent = NFS_SB(data->sb);
-	struct inode *root_inode;
-	struct nfs_fsinfo fsinfo;
-	void *err = ERR_PTR(-ENOMEM);
-
-	sb->s_op = data->sb->s_op;
-	sb->s_blocksize = data->sb->s_blocksize;
-	sb->s_blocksize_bits = data->sb->s_blocksize_bits;
-	sb->s_maxbytes = data->sb->s_maxbytes;
-
-	server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
-	server->io_stats = nfs_alloc_iostats();
-	if (server->io_stats == NULL)
-		goto out;
-
-	server->client = rpc_clone_client(parent->client);
-	if (IS_ERR((err = server->client)))
-		goto out;
-
-	if (!IS_ERR(parent->client_sys)) {
-		server->client_sys = rpc_clone_client(parent->client_sys);
-		if (IS_ERR((err = server->client_sys)))
-			goto out;
-	}
-	if (!IS_ERR(parent->client_acl)) {
-		server->client_acl = rpc_clone_client(parent->client_acl);
-		if (IS_ERR((err = server->client_acl)))
-			goto out;
-	}
-	root_inode = nfs_fhget(sb, data->fh, data->fattr);
-	if (!root_inode)
-		goto out;
-	sb->s_root = d_alloc_root(root_inode);
-	if (!sb->s_root)
-		goto out_put_root;
-	fsinfo.fattr = data->fattr;
-	if (NFS_PROTO(root_inode)->fsinfo(server, data->fh, &fsinfo) == 0)
-		nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);
-	sb->s_root->d_op = server->rpc_ops->dentry_ops;
-	sb->s_flags |= MS_ACTIVE;
-	return server;
-out_put_root:
-	iput(root_inode);
-out:
-	return err;
-}
 
-/*
- * Copy an existing superblock and attach revised data
- */
-static int nfs_clone_generic_sb(struct nfs_clone_mount *data,
-		struct super_block *(*fill_sb)(struct nfs_server *, struct nfs_clone_mount *),
-		struct nfs_server *(*fill_server)(struct super_block *, struct nfs_clone_mount *),
-		struct vfsmount *mnt)
-{
-	struct nfs_server *server;
-	struct nfs_server *parent = NFS_SB(data->sb);
-	struct super_block *sb = ERR_PTR(-EINVAL);
-	char *hostname;
-	int error = -ENOMEM;
-	int len;
-
-	server = kmalloc(sizeof(struct nfs_server), GFP_KERNEL);
-	if (server == NULL)
-		goto out_err;
-	memcpy(server, parent, sizeof(*server));
-	hostname = (data->hostname != NULL) ? data->hostname : parent->hostname;
-	len = strlen(hostname) + 1;
-	server->hostname = kmalloc(len, GFP_KERNEL);
-	if (server->hostname == NULL)
-		goto free_server;
-	memcpy(server->hostname, hostname, len);
-	error = rpciod_up();
-	if (error != 0)
-		goto free_hostname;
-
-	sb = fill_sb(server, data);
-	if (IS_ERR(sb)) {
-		error = PTR_ERR(sb);
-		goto kill_rpciod;
-	}
-		
-	if (sb->s_root)
-		goto out_rpciod_down;
+	sb->s_blocksize_bits = 0;
+	sb->s_blocksize = 0;
+	if (data->bsize)
+		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
 
-	server = fill_server(sb, data);
-	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
-		goto out_deactivate;
+	if (server->flags & NFS_MOUNT_VER3) {
+		/* The VFS shouldn't apply the umask to mode bits. We will do
+		 * so ourselves when necessary.
+		 */
+		sb->s_flags |= MS_POSIXACL;
+		sb->s_time_gran = 1;
 	}
-	return simple_set_mnt(mnt, sb);
-out_deactivate:
-	up_write(&sb->s_umount);
-	deactivate_super(sb);
-	return error;
-out_rpciod_down:
-	rpciod_down();
-	kfree(server->hostname);
-	kfree(server);
-	return simple_set_mnt(mnt, sb);
-kill_rpciod:
-	rpciod_down();
-free_hostname:
-	kfree(server->hostname);
-free_server:
-	kfree(server);
-out_err:
-	return error;
+
+	sb->s_op = &nfs_sops;
+ 	nfs_initialise_sb(sb);
 }
 
 /*
- * Set up an NFS2/3 superblock
- *
- * The way this works is that the mount process passes a structure
- * in the data argument which contains the server's IP address
- * and the root file handle obtained from the server's mount
- * daemon. We stash these away in the private superblock fields.
+ * Finish setting up a cloned NFS2/3 superblock
  */
-static int
-nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent)
+static void nfs_clone_super(struct super_block *sb,
+			    const struct super_block *old_sb)
 {
-	struct nfs_server	*server;
-	rpc_authflavor_t	authflavor;
+	struct nfs_server *server = NFS_SB(sb);
 
-	server           = NFS_SB(sb);
-	sb->s_blocksize_bits = 0;
-	sb->s_blocksize = 0;
-	if (data->bsize)
-		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
-	if (data->rsize)
-		server->rsize = nfs_block_size(data->rsize, NULL);
-	if (data->wsize)
-		server->wsize = nfs_block_size(data->wsize, NULL);
-	server->flags    = data->flags & NFS_MOUNT_FLAGMASK;
-
-	server->acregmin = data->acregmin*HZ;
-	server->acregmax = data->acregmax*HZ;
-	server->acdirmin = data->acdirmin*HZ;
-	server->acdirmax = data->acdirmax*HZ;
-
-	/* Start lockd here, before we might error out */
-	if (!(server->flags & NFS_MOUNT_NONLM))
-		lockd_up();
-
-	server->namelen  = data->namlen;
-	server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL);
-	if (!server->hostname)
-		return -ENOMEM;
-	strcpy(server->hostname, data->hostname);
-
-	/* Check NFS protocol revision and initialize RPC op vector
-	 * and file handle pool. */
-#ifdef CONFIG_NFS_V3
-	if (server->flags & NFS_MOUNT_VER3) {
-		server->rpc_ops = &nfs_v3_clientops;
-		server->caps |= NFS_CAP_READDIRPLUS;
-	} else {
-		server->rpc_ops = &nfs_v2_clientops;
-	}
-#else
-	server->rpc_ops = &nfs_v2_clientops;
-#endif
+	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
+	sb->s_blocksize = old_sb->s_blocksize;
+	sb->s_maxbytes = old_sb->s_maxbytes;
 
-	/* Fill in pseudoflavor for mount version < 5 */
-	if (!(data->flags & NFS_MOUNT_SECFLAVOUR))
-		data->pseudoflavor = RPC_AUTH_UNIX;
-	authflavor = data->pseudoflavor;	/* save for sb_init() */
-	/* XXX maybe we want to add a server->pseudoflavor field */
-
-	/* Create RPC client handles */
-	server->client = nfs_create_client(server, data);
-	if (IS_ERR(server->client))
-		return PTR_ERR(server->client);
-	/* RFC 2623, sec 2.3.2 */
-	if (authflavor != RPC_AUTH_UNIX) {
-		struct rpc_auth *auth;
-
-		server->client_sys = rpc_clone_client(server->client);
-		if (IS_ERR(server->client_sys))
-			return PTR_ERR(server->client_sys);
-		auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys);
-		if (IS_ERR(auth))
-			return PTR_ERR(auth);
-	} else {
-		atomic_inc(&server->client->cl_count);
-		server->client_sys = server->client;
-	}
 	if (server->flags & NFS_MOUNT_VER3) {
-#ifdef CONFIG_NFS_V3_ACL
-		if (!(server->flags & NFS_MOUNT_NOACL)) {
-			server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
-			/* No errors! Assume that Sun nfsacls are supported */
-			if (!IS_ERR(server->client_acl))
-				server->caps |= NFS_CAP_ACLS;
-		}
-#else
-		server->flags &= ~NFS_MOUNT_NOACL;
-#endif /* CONFIG_NFS_V3_ACL */
-		/*
-		 * The VFS shouldn't apply the umask to mode bits. We will
-		 * do so ourselves when necessary.
+		/* The VFS shouldn't apply the umask to mode bits. We will do
+		 * so ourselves when necessary.
 		 */
 		sb->s_flags |= MS_POSIXACL;
-		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
-			server->namelen = NFS3_MAXNAMLEN;
 		sb->s_time_gran = 1;
-	} else {
-		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
-			server->namelen = NFS2_MAXNAMLEN;
 	}
 
-	sb->s_op = &nfs_sops;
-	return nfs_sb_init(sb, authflavor);
+	sb->s_op = old_sb->s_op;
+ 	nfs_initialise_sb(sb);
 }
 
-static int nfs_set_super(struct super_block *s, void *data)
+static int nfs_set_super(struct super_block *s, void *_server)
 {
-	s->s_fs_info = data;
-	return set_anon_super(s, data);
+	struct nfs_server *server = _server;
+	int ret;
+
+	s->s_fs_info = server;
+	ret = set_anon_super(s, server);
+	if (ret == 0)
+		server->s_dev = s->s_dev;
+	return ret;
 }
 
 static int nfs_compare_super(struct super_block *sb, void *data)
 {
-	struct nfs_server *server = data;
-	struct nfs_server *old = NFS_SB(sb);
+	struct nfs_server *server = data, *old = NFS_SB(sb);
 
-	if (old->addr.sin_addr.s_addr != server->addr.sin_addr.s_addr)
+	if (old->nfs_client != server->nfs_client)
 		return 0;
-	if (old->addr.sin_port != server->addr.sin_port)
+	if (memcmp(&old->fsid, &server->fsid, sizeof(old->fsid)) != 0)
 		return 0;
-	return !nfs_compare_fh(&old->fh, &server->fh);
+	return 1;
 }
 
 static int nfs_get_sb(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
 {
-	int error;
 	struct nfs_server *server = NULL;
 	struct super_block *s;
-	struct nfs_fh *root;
+	struct nfs_fh mntfh;
 	struct nfs_mount_data *data = raw_data;
+	struct dentry *mntroot;
+	int error;
 
-	error = -EINVAL;
-	if (data == NULL) {
-		dprintk("%s: missing data argument\n", __FUNCTION__);
-		goto out_err_noserver;
-	}
-	if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) {
-		dprintk("%s: bad mount version\n", __FUNCTION__);
-		goto out_err_noserver;
-	}
-	switch (data->version) {
-		case 1:
-			data->namlen = 0;
-		case 2:
-			data->bsize  = 0;
-		case 3:
-			if (data->flags & NFS_MOUNT_VER3) {
-				dprintk("%s: mount structure version %d does not support NFSv3\n",
-						__FUNCTION__,
-						data->version);
-				goto out_err_noserver;
-			}
-			data->root.size = NFS2_FHSIZE;
-			memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
-		case 4:
-			if (data->flags & NFS_MOUNT_SECFLAVOUR) {
-				dprintk("%s: mount structure version %d does not support strong security\n",
-						__FUNCTION__,
-						data->version);
-				goto out_err_noserver;
-			}
-		case 5:
-			memset(data->context, 0, sizeof(data->context));
-	}
-#ifndef CONFIG_NFS_V3
-	/* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */
-	error = -EPROTONOSUPPORT;
-	if (data->flags & NFS_MOUNT_VER3) {
-		dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__);
-		goto out_err_noserver;
-	}
-#endif /* CONFIG_NFS_V3 */
+	/* Validate the mount data */
+	error = nfs_validate_mount_data(data, &mntfh);
+	if (error < 0)
+		return error;
 
-	error = -ENOMEM;
-	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
-	if (!server)
+	/* Get a volume representation */
+	server = nfs_create_server(data, &mntfh);
+	if (IS_ERR(server)) {
+		error = PTR_ERR(server);
 		goto out_err_noserver;
-	/* Zero out the NFS state stuff */
-	init_nfsv4_state(server);
-	server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
-
-	root = &server->fh;
-	if (data->flags & NFS_MOUNT_VER3)
-		root->size = data->root.size;
-	else
-		root->size = NFS2_FHSIZE;
-	error = -EINVAL;
-	if (root->size > sizeof(root->data)) {
-		dprintk("%s: invalid root filehandle\n", __FUNCTION__);
-		goto out_err;
-	}
-	memcpy(root->data, data->root.data, root->size);
-
-	/* We now require that the mount process passes the remote address */
-	memcpy(&server->addr, &data->addr, sizeof(server->addr));
-	if (server->addr.sin_addr.s_addr == INADDR_ANY) {
-		dprintk("%s: mount program didn't pass remote address!\n",
-				__FUNCTION__);
-		goto out_err;
-	}
-
-	/* Fire up rpciod if not yet running */
-	error = rpciod_up();
-	if (error < 0) {
-		dprintk("%s: couldn't start rpciod! Error = %d\n",
-				__FUNCTION__, error);
-		goto out_err;
 	}
 
+	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(fs_type, nfs_compare_super, nfs_set_super, server);
 	if (IS_ERR(s)) {
 		error = PTR_ERR(s);
-		goto out_err_rpciod;
+		goto out_err_nosb;
 	}
 
-	if (s->s_root)
-		goto out_rpciod_down;
+	if (s->s_fs_info != server) {
+		nfs_free_server(server);
+		server = NULL;
+	}
 
-	s->s_flags = flags;
+	if (!s->s_root) {
+		/* initial superblock/root creation */
+		s->s_flags = flags;
+		nfs_fill_super(s, data);
+	}
 
-	error = nfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
-	if (error) {
-		up_write(&s->s_umount);
-		deactivate_super(s);
-		return error;
+	mntroot = nfs_get_root(s, &mntfh);
+	if (IS_ERR(mntroot)) {
+		error = PTR_ERR(mntroot);
+		goto error_splat_super;
 	}
-	s->s_flags |= MS_ACTIVE;
-	return simple_set_mnt(mnt, s);
 
-out_rpciod_down:
-	rpciod_down();
-	kfree(server);
-	return simple_set_mnt(mnt, s);
+	s->s_flags |= MS_ACTIVE;
+	mnt->mnt_sb = s;
+	mnt->mnt_root = mntroot;
+	return 0;
 
-out_err_rpciod:
-	rpciod_down();
-out_err:
-	kfree(server);
+out_err_nosb:
+	nfs_free_server(server);
 out_err_noserver:
 	return error;
+
+error_splat_super:
+	up_write(&s->s_umount);
+	deactivate_super(s);
+	return error;
 }
 
+/*
+ * Destroy an NFS2/3 superblock
+ */
 static void nfs_kill_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
 	kill_anon_super(s);
-
-	if (!IS_ERR(server->client))
-		rpc_shutdown_client(server->client);
-	if (!IS_ERR(server->client_sys))
-		rpc_shutdown_client(server->client_sys);
-	if (!IS_ERR(server->client_acl))
-		rpc_shutdown_client(server->client_acl);
-
-	if (!(server->flags & NFS_MOUNT_NONLM))
-		lockd_down();	/* release rpc.lockd */
-
-	rpciod_down();		/* release rpciod */
-
-	nfs_free_iostats(server->io_stats);
-	kfree(server->hostname);
-	kfree(server);
-	nfs_release_automount_timer();
-}
-
-static struct super_block *nfs_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
-{
-	struct super_block *sb;
-
-	server->fsid = data->fattr->fsid;
-	nfs_copy_fh(&server->fh, data->fh);
-	sb = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
-	if (!IS_ERR(sb) && sb->s_root == NULL && !(server->flags & NFS_MOUNT_NONLM))
-		lockd_up();
-	return sb;
+	nfs_free_server(server);
 }
 
-static int nfs_clone_nfs_sb(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
+/*
+ * Clone an NFS2/3 server record on xdev traversal (FSID-change)
+ */
+static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags,
+			   const char *dev_name, void *raw_data,
+			   struct vfsmount *mnt)
 {
 	struct nfs_clone_mount *data = raw_data;
-	return nfs_clone_generic_sb(data, nfs_clone_sb, nfs_clone_server, mnt);
-}
+	struct super_block *s;
+	struct nfs_server *server;
+	struct dentry *mntroot;
+	int error;
 
-#ifdef CONFIG_NFS_V4
-static struct rpc_clnt *nfs4_create_client(struct nfs_server *server,
-	struct rpc_timeout *timeparms, int proto, rpc_authflavor_t flavor)
-{
-	struct nfs4_client *clp;
-	struct rpc_xprt *xprt = NULL;
-	struct rpc_clnt *clnt = NULL;
-	int err = -EIO;
-
-	clp = nfs4_get_client(&server->addr.sin_addr);
-	if (!clp) {
-		dprintk("%s: failed to create NFS4 client.\n", __FUNCTION__);
-		return ERR_PTR(err);
-	}
+	dprintk("--> nfs_xdev_get_sb()\n");
 
-	/* Now create transport and client */
-	down_write(&clp->cl_sem);
-	if (IS_ERR(clp->cl_rpcclient)) {
-		xprt = xprt_create_proto(proto, &server->addr, timeparms);
-		if (IS_ERR(xprt)) {
-			up_write(&clp->cl_sem);
-			err = PTR_ERR(xprt);
-			dprintk("%s: cannot create RPC transport. Error = %d\n",
-					__FUNCTION__, err);
-			goto out_fail;
-		}
-		/* Bind to a reserved port! */
-		xprt->resvport = 1;
-		clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
-				server->rpc_ops->version, flavor);
-		if (IS_ERR(clnt)) {
-			up_write(&clp->cl_sem);
-			err = PTR_ERR(clnt);
-			dprintk("%s: cannot create RPC client. Error = %d\n",
-					__FUNCTION__, err);
-			goto out_fail;
-		}
-		clnt->cl_intr     = 1;
-		clnt->cl_softrtry = 1;
-		clp->cl_rpcclient = clnt;
-		memcpy(clp->cl_ipaddr, server->ip_addr, sizeof(clp->cl_ipaddr));
-		nfs_idmap_new(clp);
-	}
-	list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks);
-	clnt = rpc_clone_client(clp->cl_rpcclient);
-	if (!IS_ERR(clnt))
-		server->nfs4_state = clp;
-	up_write(&clp->cl_sem);
-	clp = NULL;
-
-	if (IS_ERR(clnt)) {
-		dprintk("%s: cannot create RPC client. Error = %d\n",
-				__FUNCTION__, err);
-		return clnt;
+	/* create a new volume representation */
+	server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr);
+	if (IS_ERR(server)) {
+		error = PTR_ERR(server);
+		goto out_err_noserver;
 	}
 
-	if (server->nfs4_state->cl_idmap == NULL) {
-		dprintk("%s: failed to create idmapper.\n", __FUNCTION__);
-		return ERR_PTR(-ENOMEM);
+	/* Get a superblock - note that we may end up sharing one that already exists */
+	s = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
+	if (IS_ERR(s)) {
+		error = PTR_ERR(s);
+		goto out_err_nosb;
 	}
 
-	if (clnt->cl_auth->au_flavor != flavor) {
-		struct rpc_auth *auth;
-
-		auth = rpcauth_create(flavor, clnt);
-		if (IS_ERR(auth)) {
-			dprintk("%s: couldn't create credcache!\n", __FUNCTION__);
-			return (struct rpc_clnt *)auth;
-		}
+	if (s->s_fs_info != server) {
+		nfs_free_server(server);
+		server = NULL;
 	}
-	return clnt;
-
- out_fail:
-	if (clp)
-		nfs4_put_client(clp);
-	return ERR_PTR(err);
-}
-
-/*
- * Set up an NFS4 superblock
- */
-static int nfs4_fill_super(struct super_block *sb, struct nfs4_mount_data *data, int silent)
-{
-	struct nfs_server *server;
-	struct rpc_timeout timeparms;
-	rpc_authflavor_t authflavour;
-	int err = -EIO;
 
-	sb->s_blocksize_bits = 0;
-	sb->s_blocksize = 0;
-	server = NFS_SB(sb);
-	if (data->rsize != 0)
-		server->rsize = nfs_block_size(data->rsize, NULL);
-	if (data->wsize != 0)
-		server->wsize = nfs_block_size(data->wsize, NULL);
-	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
-	server->caps = NFS_CAP_ATOMIC_OPEN;
+	if (!s->s_root) {
+		/* initial superblock/root creation */
+		s->s_flags = flags;
+		nfs_clone_super(s, data->sb);
+	}
 
-	server->acregmin = data->acregmin*HZ;
-	server->acregmax = data->acregmax*HZ;
-	server->acdirmin = data->acdirmin*HZ;
-	server->acdirmax = data->acdirmax*HZ;
+	mntroot = nfs_get_root(s, data->fh);
+	if (IS_ERR(mntroot)) {
+		error = PTR_ERR(mntroot);
+		goto error_splat_super;
+	}
 
-	server->rpc_ops = &nfs_v4_clientops;
+	s->s_flags |= MS_ACTIVE;
+	mnt->mnt_sb = s;
+	mnt->mnt_root = mntroot;
 
-	nfs_init_timeout_values(&timeparms, data->proto, data->timeo, data->retrans);
+	dprintk("<-- nfs_xdev_get_sb() = 0\n");
+	return 0;
 
-	server->retrans_timeo = timeparms.to_initval;
-	server->retrans_count = timeparms.to_retries;
+out_err_nosb:
+	nfs_free_server(server);
+out_err_noserver:
+	dprintk("<-- nfs_xdev_get_sb() = %d [error]\n", error);
+	return error;
 
-	/* Now create transport and client */
-	authflavour = RPC_AUTH_UNIX;
-	if (data->auth_flavourlen != 0) {
-		if (data->auth_flavourlen != 1) {
-			dprintk("%s: Invalid number of RPC auth flavours %d.\n",
-					__FUNCTION__, data->auth_flavourlen);
-			err = -EINVAL;
-			goto out_fail;
-		}
-		if (copy_from_user(&authflavour, data->auth_flavours, sizeof(authflavour))) {
-			err = -EFAULT;
-			goto out_fail;
-		}
-	}
+error_splat_super:
+	up_write(&s->s_umount);
+	deactivate_super(s);
+	dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error);
+	return error;
+}
 
-	server->client = nfs4_create_client(server, &timeparms, data->proto, authflavour);
-	if (IS_ERR(server->client)) {
-		err = PTR_ERR(server->client);
-			dprintk("%s: cannot create RPC client. Error = %d\n",
-					__FUNCTION__, err);
-			goto out_fail;
-	}
+#ifdef CONFIG_NFS_V4
 
+/*
+ * Finish setting up a cloned NFS4 superblock
+ */
+static void nfs4_clone_super(struct super_block *sb,
+			    const struct super_block *old_sb)
+{
+	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
+	sb->s_blocksize = old_sb->s_blocksize;
+	sb->s_maxbytes = old_sb->s_maxbytes;
 	sb->s_time_gran = 1;
-
-	sb->s_op = &nfs4_sops;
-	err = nfs_sb_init(sb, authflavour);
-
- out_fail:
-	return err;
+	sb->s_op = old_sb->s_op;
+ 	nfs_initialise_sb(sb);
 }
 
-static int nfs4_compare_super(struct super_block *sb, void *data)
+/*
+ * Set up an NFS4 superblock
+ */
+static void nfs4_fill_super(struct super_block *sb)
 {
-	struct nfs_server *server = data;
-	struct nfs_server *old = NFS_SB(sb);
-
-	if (strcmp(server->hostname, old->hostname) != 0)
-		return 0;
-	if (strcmp(server->mnt_path, old->mnt_path) != 0)
-		return 0;
-	return 1;
+	sb->s_time_gran = 1;
+	sb->s_op = &nfs4_sops;
+	nfs_initialise_sb(sb);
 }
 
-static void *
-nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen)
+static void *nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen)
 {
 	void *p = NULL;
 
@@ -1297,14 +793,22 @@ nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen)
 	return dst;
 }
 
+/*
+ * Get the superblock for an NFS4 mountpoint
+ */
 static int nfs4_get_sb(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
 {
-	int error;
-	struct nfs_server *server;
-	struct super_block *s;
 	struct nfs4_mount_data *data = raw_data;
+	struct super_block *s;
+	struct nfs_server *server;
+	struct sockaddr_in addr;
+	rpc_authflavor_t authflavour;
+	struct nfs_fh mntfh;
+	struct dentry *mntroot;
+	char *mntpath = NULL, *hostname = NULL, ip_addr[16];
 	void *p;
+	int error;
 
 	if (data == NULL) {
 		dprintk("%s: missing data argument\n", __FUNCTION__);
@@ -1315,84 +819,112 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 		return -EINVAL;
 	}
 
-	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
-	if (!server)
-		return -ENOMEM;
-	/* Zero out the NFS state stuff */
-	init_nfsv4_state(server);
-	server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
+	/* We now require that the mount process passes the remote address */
+	if (data->host_addrlen != sizeof(addr))
+		return -EINVAL;
+
+	if (copy_from_user(&addr, data->host_addr, sizeof(addr)))
+		return -EFAULT;
+
+	if (addr.sin_family != AF_INET ||
+	    addr.sin_addr.s_addr == INADDR_ANY
+	    ) {
+		dprintk("%s: mount program didn't pass remote IP address!\n",
+				__FUNCTION__);
+		return -EINVAL;
+	}
+	/* RFC3530: The default port for NFS is 2049 */
+	if (addr.sin_port == 0)
+		addr.sin_port = NFS_PORT;
+
+	/* Grab the authentication type */
+	authflavour = RPC_AUTH_UNIX;
+	if (data->auth_flavourlen != 0) {
+		if (data->auth_flavourlen != 1) {
+			dprintk("%s: Invalid number of RPC auth flavours %d.\n",
+					__FUNCTION__, data->auth_flavourlen);
+			error = -EINVAL;
+			goto out_err_noserver;
+		}
+
+		if (copy_from_user(&authflavour, data->auth_flavours,
+				   sizeof(authflavour))) {
+			error = -EFAULT;
+			goto out_err_noserver;
+		}
+	}
 
 	p = nfs_copy_user_string(NULL, &data->hostname, 256);
 	if (IS_ERR(p))
 		goto out_err;
-	server->hostname = p;
+	hostname = p;
 
 	p = nfs_copy_user_string(NULL, &data->mnt_path, 1024);
 	if (IS_ERR(p))
 		goto out_err;
-	server->mnt_path = p;
+	mntpath = p;
+
+	dprintk("MNTPATH: %s\n", mntpath);
 
-	p = nfs_copy_user_string(server->ip_addr, &data->client_addr,
-			sizeof(server->ip_addr) - 1);
+	p = nfs_copy_user_string(ip_addr, &data->client_addr,
+				 sizeof(ip_addr) - 1);
 	if (IS_ERR(p))
 		goto out_err;
 
-	/* We now require that the mount process passes the remote address */
-	if (data->host_addrlen != sizeof(server->addr)) {
-		error = -EINVAL;
-		goto out_free;
-	}
-	if (copy_from_user(&server->addr, data->host_addr, sizeof(server->addr))) {
-		error = -EFAULT;
-		goto out_free;
-	}
-	if (server->addr.sin_family != AF_INET ||
-	    server->addr.sin_addr.s_addr == INADDR_ANY) {
-		dprintk("%s: mount program didn't pass remote IP address!\n",
-				__FUNCTION__);
-		error = -EINVAL;
-		goto out_free;
-	}
-
-	/* Fire up rpciod if not yet running */
-	error = rpciod_up();
-	if (error < 0) {
-		dprintk("%s: couldn't start rpciod! Error = %d\n",
-				__FUNCTION__, error);
-		goto out_free;
+	/* Get a volume representation */
+	server = nfs4_create_server(data, hostname, &addr, mntpath, ip_addr,
+				    authflavour, &mntfh);
+	if (IS_ERR(server)) {
+		error = PTR_ERR(server);
+		goto out_err_noserver;
 	}
 
-	s = sget(fs_type, nfs4_compare_super, nfs_set_super, server);
-
+	/* Get a superblock - note that we may end up sharing one that already exists */
+	s = sget(fs_type, nfs_compare_super, nfs_set_super, server);
 	if (IS_ERR(s)) {
 		error = PTR_ERR(s);
 		goto out_free;
 	}
 
-	if (s->s_root) {
-		kfree(server->mnt_path);
-		kfree(server->hostname);
-		kfree(server);
-		return simple_set_mnt(mnt, s);
+	if (s->s_fs_info != server) {
+		nfs_free_server(server);
+		server = NULL;
 	}
 
-	s->s_flags = flags;
+	if (!s->s_root) {
+		/* initial superblock/root creation */
+		s->s_flags = flags;
+		nfs4_fill_super(s);
+	}
 
-	error = nfs4_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
-	if (error) {
-		up_write(&s->s_umount);
-		deactivate_super(s);
-		return error;
+	mntroot = nfs4_get_root(s, &mntfh);
+	if (IS_ERR(mntroot)) {
+		error = PTR_ERR(mntroot);
+		goto error_splat_super;
 	}
+
 	s->s_flags |= MS_ACTIVE;
-	return simple_set_mnt(mnt, s);
+	mnt->mnt_sb = s;
+	mnt->mnt_root = mntroot;
+	kfree(mntpath);
+	kfree(hostname);
+	return 0;
+
 out_err:
 	error = PTR_ERR(p);
+	goto out_err_noserver;
+
 out_free:
-	kfree(server->mnt_path);
-	kfree(server->hostname);
-	kfree(server);
+	nfs_free_server(server);
+out_err_noserver:
+	kfree(mntpath);
+	kfree(hostname);
 	return error;
+
+error_splat_super:
+	up_write(&s->s_umount);
+	deactivate_super(s);
+	goto out_err_noserver;
 }
 
 static void nfs4_kill_super(struct super_block *sb)
@@ -1403,135 +935,140 @@ static void nfs4_kill_super(struct super_block *sb)
 	kill_anon_super(sb);
 
 	nfs4_renewd_prepare_shutdown(server);
+	nfs_free_server(server);
+}
+
+/*
+ * Clone an NFS4 server record on xdev traversal (FSID-change)
+ */
+static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags,
+			    const char *dev_name, void *raw_data,
+			    struct vfsmount *mnt)
+{
+	struct nfs_clone_mount *data = raw_data;
+	struct super_block *s;
+	struct nfs_server *server;
+	struct dentry *mntroot;
+	int error;
+
+	dprintk("--> nfs4_xdev_get_sb()\n");
+
+	/* create a new volume representation */
+	server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr);
+	if (IS_ERR(server)) {
+		error = PTR_ERR(server);
+		goto out_err_noserver;
+	}
+
+	/* Get a superblock - note that we may end up sharing one that already exists */
+	s = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
+	if (IS_ERR(s)) {
+		error = PTR_ERR(s);
+		goto out_err_nosb;
+	}
 
-	if (server->client != NULL && !IS_ERR(server->client))
-		rpc_shutdown_client(server->client);
+	if (s->s_fs_info != server) {
+		nfs_free_server(server);
+		server = NULL;
+	}
 
-	destroy_nfsv4_state(server);
+	if (!s->s_root) {
+		/* initial superblock/root creation */
+		s->s_flags = flags;
+		nfs4_clone_super(s, data->sb);
+	}
+
+	mntroot = nfs4_get_root(s, data->fh);
+	if (IS_ERR(mntroot)) {
+		error = PTR_ERR(mntroot);
+		goto error_splat_super;
+	}
 
-	rpciod_down();
+	s->s_flags |= MS_ACTIVE;
+	mnt->mnt_sb = s;
+	mnt->mnt_root = mntroot;
+
+	dprintk("<-- nfs4_xdev_get_sb() = 0\n");
+	return 0;
+
+out_err_nosb:
+	nfs_free_server(server);
+out_err_noserver:
+	dprintk("<-- nfs4_xdev_get_sb() = %d [error]\n", error);
+	return error;
 
-	nfs_free_iostats(server->io_stats);
-	kfree(server->hostname);
-	kfree(server);
-	nfs_release_automount_timer();
+error_splat_super:
+	up_write(&s->s_umount);
+	deactivate_super(s);
+	dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error);
+	return error;
 }
 
 /*
- * Constructs the SERVER-side path
+ * Create an NFS4 server record on referral traversal
  */
-static inline char *nfs4_dup_path(const struct dentry *dentry)
+static int nfs4_referral_get_sb(struct file_system_type *fs_type, int flags,
+				const char *dev_name, void *raw_data,
+				struct vfsmount *mnt)
 {
-	char *page = (char *) __get_free_page(GFP_USER);
-	char *path;
+	struct nfs_clone_mount *data = raw_data;
+	struct super_block *s;
+	struct nfs_server *server;
+	struct dentry *mntroot;
+	struct nfs_fh mntfh;
+	int error;
 
-	path = nfs4_path(dentry, page, PAGE_SIZE);
-	if (!IS_ERR(path)) {
-		int len = PAGE_SIZE + page - path;
-		char *tmp = path;
+	dprintk("--> nfs4_referral_get_sb()\n");
 
-		path = kmalloc(len, GFP_KERNEL);
-		if (path)
-			memcpy(path, tmp, len);
-		else
-			path = ERR_PTR(-ENOMEM);
+	/* create a new volume representation */
+	server = nfs4_create_referral_server(data, &mntfh);
+	if (IS_ERR(server)) {
+		error = PTR_ERR(server);
+		goto out_err_noserver;
 	}
-	free_page((unsigned long)page);
-	return path;
-}
 
-static struct super_block *nfs4_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
-{
-	const struct dentry *dentry = data->dentry;
-	struct nfs4_client *clp = server->nfs4_state;
-	struct super_block *sb;
-
-	server->fsid = data->fattr->fsid;
-	nfs_copy_fh(&server->fh, data->fh);
-	server->mnt_path = nfs4_dup_path(dentry);
-	if (IS_ERR(server->mnt_path)) {
-		sb = (struct super_block *)server->mnt_path;
-		goto err;
+	/* Get a superblock - note that we may end up sharing one that already exists */
+	s = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
+	if (IS_ERR(s)) {
+		error = PTR_ERR(s);
+		goto out_err_nosb;
 	}
-	sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server);
-	if (IS_ERR(sb) || sb->s_root)
-		goto free_path;
-	nfs4_server_capabilities(server, &server->fh);
-
-	down_write(&clp->cl_sem);
-	atomic_inc(&clp->cl_count);
-	list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks);
-	up_write(&clp->cl_sem);
-	return sb;
-free_path:
-	kfree(server->mnt_path);
-err:
-	server->mnt_path = NULL;
-	return sb;
-}
 
-static int nfs_clone_nfs4_sb(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
-{
-	struct nfs_clone_mount *data = raw_data;
-	return nfs_clone_generic_sb(data, nfs4_clone_sb, nfs_clone_server, mnt);
-}
+	if (s->s_fs_info != server) {
+		nfs_free_server(server);
+		server = NULL;
+	}
 
-static struct super_block *nfs4_referral_sb(struct nfs_server *server, struct nfs_clone_mount *data)
-{
-	struct super_block *sb = ERR_PTR(-ENOMEM);
-	int len;
-
-	len = strlen(data->mnt_path) + 1;
-	server->mnt_path = kmalloc(len, GFP_KERNEL);
-	if (server->mnt_path == NULL)
-		goto err;
-	memcpy(server->mnt_path, data->mnt_path, len);
-	memcpy(&server->addr, data->addr, sizeof(struct sockaddr_in));
-
-	sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server);
-	if (IS_ERR(sb) || sb->s_root)
-		goto free_path;
-	return sb;
-free_path:
-	kfree(server->mnt_path);
-err:
-	server->mnt_path = NULL;
-	return sb;
-}
+	if (!s->s_root) {
+		/* initial superblock/root creation */
+		s->s_flags = flags;
+		nfs4_fill_super(s);
+	}
 
-static struct nfs_server *nfs4_referral_server(struct super_block *sb, struct nfs_clone_mount *data)
-{
-	struct nfs_server *server = NFS_SB(sb);
-	struct rpc_timeout timeparms;
-	int proto, timeo, retrans;
-	void *err;
-
-	proto = IPPROTO_TCP;
-	/* Since we are following a referral and there may be alternatives,
-	   set the timeouts and retries to low values */
-	timeo = 2;
-	retrans = 1;
-	nfs_init_timeout_values(&timeparms, proto, timeo, retrans);
-
-	server->client = nfs4_create_client(server, &timeparms, proto, data->authflavor);
-	if (IS_ERR((err = server->client)))
-		goto out_err;
+	mntroot = nfs4_get_root(s, data->fh);
+	if (IS_ERR(mntroot)) {
+		error = PTR_ERR(mntroot);
+		goto error_splat_super;
+	}
 
-	sb->s_time_gran = 1;
-	sb->s_op = &nfs4_sops;
-	err = ERR_PTR(nfs_sb_init(sb, data->authflavor));
-	if (!IS_ERR(err))
-		return server;
-out_err:
-	return (struct nfs_server *)err;
-}
+	s->s_flags |= MS_ACTIVE;
+	mnt->mnt_sb = s;
+	mnt->mnt_root = mntroot;
 
-static int nfs_referral_nfs4_sb(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
-{
-	struct nfs_clone_mount *data = raw_data;
-	return nfs_clone_generic_sb(data, nfs4_referral_sb, nfs4_referral_server, mnt);
+	dprintk("<-- nfs4_referral_get_sb() = 0\n");
+	return 0;
+
+out_err_nosb:
+	nfs_free_server(server);
+out_err_noserver:
+	dprintk("<-- nfs4_referral_get_sb() = %d [error]\n", error);
+	return error;
+
+error_splat_super:
+	up_write(&s->s_umount);
+	deactivate_super(s);
+	dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error);
+	return error;
 }
 
-#endif
+#endif /* CONFIG_NFS_V4 */

fs/nfs/write.c

@@ -396,6 +396,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 out:
 	clear_bit(BDI_write_congested, &bdi->state);
 	wake_up_all(&nfs_write_congestion);
+	writeback_congestion_end();
 	return err;
 }
 
@@ -1252,7 +1253,13 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 	dprintk("NFS: %4d nfs_writeback_done (status %d)\n",
 		task->tk_pid, task->tk_status);
 
-	/* Call the NFS version-specific code */
+	/*
+	 * ->write_done will attempt to use post-op attributes to detect
+	 * conflicting writes by other clients.  A strict interpretation
+	 * of close-to-open would allow us to continue caching even if
+	 * another writer had changed the file, but some applications
+	 * depend on tighter cache coherency when writing.
+	 */
 	status = NFS_PROTO(data->inode)->write_done(task, data);
 	if (status != 0)
 		return status;
@@ -1273,7 +1280,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		if (time_before(complain, jiffies)) {
 			dprintk("NFS: faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
-				NFS_SERVER(data->inode)->hostname,
+				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
 				resp->verf->committed, argp->stable);
 			complain = jiffies + 300 * HZ;
 		}

fs/nfsd/nfs4callback.c

@@ -375,16 +375,28 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 {
 	struct sockaddr_in	addr;
 	struct nfs4_callback    *cb = &clp->cl_callback;
-	struct rpc_timeout	timeparms;
-	struct rpc_xprt *	xprt;
+	struct rpc_timeout	timeparms = {
+		.to_initval	= (NFSD_LEASE_TIME/4) * HZ,
+		.to_retries	= 5,
+		.to_maxval	= (NFSD_LEASE_TIME/2) * HZ,
+		.to_exponential	= 1,
+	};
 	struct rpc_program *	program = &cb->cb_program;
-	struct rpc_stat *	stat = &cb->cb_stat;
-	struct rpc_clnt *	clnt;
+	struct rpc_create_args args = {
+		.protocol	= IPPROTO_TCP,
+		.address	= (struct sockaddr *)&addr,
+		.addrsize	= sizeof(addr),
+		.timeout	= &timeparms,
+		.servername	= clp->cl_name.data,
+		.program	= program,
+		.version	= nfs_cb_version[1]->number,
+		.authflavor	= RPC_AUTH_UNIX,	/* XXX: need AUTH_GSS... */
+		.flags		= (RPC_CLNT_CREATE_NOPING),
+	};
 	struct rpc_message msg = {
 		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
 		.rpc_argp       = clp,
 	};
-	char                    hostname[32];
 	int status;
 
 	if (atomic_read(&cb->cb_set))
@@ -396,51 +408,27 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 	addr.sin_port = htons(cb->cb_port);
 	addr.sin_addr.s_addr = htonl(cb->cb_addr);
 
-	/* Initialize timeout */
-	timeparms.to_initval = (NFSD_LEASE_TIME/4) * HZ;
-	timeparms.to_retries = 0;
-	timeparms.to_maxval = (NFSD_LEASE_TIME/2) * HZ;
-	timeparms.to_exponential = 1;
-
-	/* Create RPC transport */
-	xprt = xprt_create_proto(IPPROTO_TCP, &addr, &timeparms);
-	if (IS_ERR(xprt)) {
-		dprintk("NFSD: couldn't create callback transport!\n");
-		goto out_err;
-	}
-
 	/* Initialize rpc_program */
 	program->name = "nfs4_cb";
 	program->number = cb->cb_prog;
 	program->nrvers = ARRAY_SIZE(nfs_cb_version);
 	program->version = nfs_cb_version;
-	program->stats = stat;
+	program->stats = &cb->cb_stat;
 
 	/* Initialize rpc_stat */
-	memset(stat, 0, sizeof(struct rpc_stat));
-	stat->program = program;
-
-	/* Create RPC client
- 	 *
-	 * XXX AUTH_UNIX only - need AUTH_GSS....
-	 */
-	sprintf(hostname, "%u.%u.%u.%u", NIPQUAD(addr.sin_addr.s_addr));
-	clnt = rpc_new_client(xprt, hostname, program, 1, RPC_AUTH_UNIX);
-	if (IS_ERR(clnt)) {
+	memset(program->stats, 0, sizeof(cb->cb_stat));
+	program->stats->program = program;
+
+	/* Create RPC client */
+	cb->cb_client = rpc_create(&args);
+	if (!cb->cb_client) {
 		dprintk("NFSD: couldn't create callback client\n");
 		goto out_err;
 	}
-	clnt->cl_intr = 0;
-	clnt->cl_softrtry = 1;
 
 	/* Kick rpciod, put the call on the wire. */
-
-	if (rpciod_up() != 0) {
-		dprintk("nfsd: couldn't start rpciod for callbacks!\n");
+	if (rpciod_up() != 0)
 		goto out_clnt;
-	}
-
-	cb->cb_client = clnt;
 
 	/* the task holds a reference to the nfs4_client struct */
 	atomic_inc(&clp->cl_count);
@@ -448,7 +436,7 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 	msg.rpc_cred = nfsd4_lookupcred(clp,0);
 	if (IS_ERR(msg.rpc_cred))
 		goto out_rpciod;
-	status = rpc_call_async(clnt, &msg, RPC_TASK_ASYNC, &nfs4_cb_null_ops, NULL);
+	status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_ASYNC, &nfs4_cb_null_ops, NULL);
 	put_rpccred(msg.rpc_cred);
 
 	if (status != 0) {
@@ -462,7 +450,7 @@ out_rpciod:
 	rpciod_down();
 	cb->cb_client = NULL;
 out_clnt:
-	rpc_shutdown_client(clnt);
+	rpc_shutdown_client(cb->cb_client);
 out_err:
 	dprintk("NFSD: warning: no callback path to client %.*s\n",
 		(int)clp->cl_name.len, clp->cl_name.data);

include/linux/blkdev.h

@@ -746,6 +746,7 @@ extern void blk_queue_free_tags(request_queue_t *);
 extern int blk_queue_resize_tags(request_queue_t *, int);
 extern void blk_queue_invalidate_tags(request_queue_t *);
 extern long blk_congestion_wait(int rw, long timeout);
+extern void blk_congestion_end(int rw);
 
 extern void blk_rq_bio_prep(request_queue_t *, struct request *, struct bio *);
 extern int blkdev_issue_flush(struct block_device *, sector_t *);

include/linux/dcache.h

@@ -221,6 +221,7 @@ static inline int dname_external(struct dentry *dentry)
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
+extern struct dentry * d_materialise_unique(struct dentry *, struct inode *);
 extern void d_delete(struct dentry *);
 
 /* allocate/de-allocate */

include/linux/nfs_fs.h

@@ -42,6 +42,7 @@
 #include <linux/in.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/rbtree.h>
 #include <linux/rwsem.h>
 #include <linux/wait.h>
 
@@ -69,6 +70,8 @@
  * NFSv3/v4 Access mode cache entry
  */
 struct nfs_access_entry {
+	struct rb_node		rb_node;
+	struct list_head	lru;
 	unsigned long		jiffies;
 	struct rpc_cred *	cred;
 	int			mask;
@@ -145,7 +148,9 @@ struct nfs_inode {
 	 */
 	atomic_t		data_updates;
 
-	struct nfs_access_entry	cache_access;
+	struct rb_root		access_cache;
+	struct list_head	access_cache_entry_lru;
+	struct list_head	access_cache_inode_lru;
 #ifdef CONFIG_NFS_V3_ACL
 	struct posix_acl	*acl_access;
 	struct posix_acl	*acl_default;
@@ -199,6 +204,7 @@ struct nfs_inode {
 #define NFS_INO_REVALIDATING	(0)		/* revalidating attrs */
 #define NFS_INO_ADVISE_RDPLUS	(1)		/* advise readdirplus */
 #define NFS_INO_STALE		(2)		/* possible stale inode */
+#define NFS_INO_ACL_LRU_SET	(3)		/* Inode is on the LRU list */
 
 static inline struct nfs_inode *NFS_I(struct inode *inode)
 {
@@ -209,8 +215,7 @@ static inline struct nfs_inode *NFS_I(struct inode *inode)
 #define NFS_FH(inode)			(&NFS_I(inode)->fh)
 #define NFS_SERVER(inode)		(NFS_SB(inode->i_sb))
 #define NFS_CLIENT(inode)		(NFS_SERVER(inode)->client)
-#define NFS_PROTO(inode)		(NFS_SERVER(inode)->rpc_ops)
-#define NFS_ADDR(inode)			(RPC_PEERADDR(NFS_CLIENT(inode)))
+#define NFS_PROTO(inode)		(NFS_SERVER(inode)->nfs_client->rpc_ops)
 #define NFS_COOKIEVERF(inode)		(NFS_I(inode)->cookieverf)
 #define NFS_READTIME(inode)		(NFS_I(inode)->read_cache_jiffies)
 #define NFS_CHANGE_ATTR(inode)		(NFS_I(inode)->change_attr)
@@ -297,6 +302,7 @@ extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int nfs_permission(struct inode *, int, struct nameidata *);
 extern int nfs_access_get_cached(struct inode *, struct rpc_cred *, struct nfs_access_entry *);
 extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
+extern void nfs_access_zap_cache(struct inode *inode);
 extern int nfs_open(struct inode *, struct file *);
 extern int nfs_release(struct inode *, struct file *);
 extern int nfs_attribute_timeout(struct inode *inode);
@@ -579,6 +585,7 @@ extern void * nfs_root_data(void);
 #define NFSDBG_FILE		0x0040
 #define NFSDBG_ROOT		0x0080
 #define NFSDBG_CALLBACK		0x0100
+#define NFSDBG_CLIENT		0x0200
 #define NFSDBG_ALL		0xFFFF
 
 #ifdef __KERNEL__

include/linux/nfs_fs_sb.h

@@ -6,14 +6,80 @@
 
 struct nfs_iostats;
 
+/*
+ * The nfs_client identifies our client state to the server.
+ */
+struct nfs_client {
+	atomic_t		cl_count;
+	int			cl_cons_state;	/* current construction state (-ve: init error) */
+#define NFS_CS_READY		0		/* ready to be used */
+#define NFS_CS_INITING		1		/* busy initialising */
+	int			cl_nfsversion;	/* NFS protocol version */
+	unsigned long		cl_res_state;	/* NFS resources state */
+#define NFS_CS_RPCIOD		0		/* - rpciod started */
+#define NFS_CS_CALLBACK		1		/* - callback started */
+#define NFS_CS_IDMAP		2		/* - idmap started */
+#define NFS_CS_RENEWD		3		/* - renewd started */
+	struct sockaddr_in	cl_addr;	/* server identifier */
+	char *			cl_hostname;	/* hostname of server */
+	struct list_head	cl_share_link;	/* link in global client list */
+	struct list_head	cl_superblocks;	/* List of nfs_server structs */
+
+	struct rpc_clnt *	cl_rpcclient;
+	const struct nfs_rpc_ops *rpc_ops;	/* NFS protocol vector */
+	unsigned long		retrans_timeo;	/* retransmit timeout */
+	unsigned int		retrans_count;	/* number of retransmit tries */
+
+#ifdef CONFIG_NFS_V4
+	u64			cl_clientid;	/* constant */
+	nfs4_verifier		cl_confirm;
+	unsigned long		cl_state;
+
+	u32			cl_lockowner_id;
+
+	/*
+	 * The following rwsem ensures exclusive access to the server
+	 * while we recover the state following a lease expiration.
+	 */
+	struct rw_semaphore	cl_sem;
+
+	struct list_head	cl_delegations;
+	struct list_head	cl_state_owners;
+	struct list_head	cl_unused;
+	int			cl_nunused;
+	spinlock_t		cl_lock;
+
+	unsigned long		cl_lease_time;
+	unsigned long		cl_last_renewal;
+	struct work_struct	cl_renewd;
+
+	struct rpc_wait_queue	cl_rpcwaitq;
+
+	/* used for the setclientid verifier */
+	struct timespec		cl_boot_time;
+
+	/* idmapper */
+	struct idmap *		cl_idmap;
+
+	/* Our own IP address, as a null-terminated string.
+	 * This is used to generate the clientid, and the callback address.
+	 */
+	char			cl_ipaddr[16];
+	unsigned char		cl_id_uniquifier;
+#endif
+};
+
 /*
  * NFS client parameters stored in the superblock.
  */
 struct nfs_server {
+	struct nfs_client *	nfs_client;	/* shared client and NFS4 state */
+	struct list_head	client_link;	/* List of other nfs_server structs
+						 * that share the same client
+						 */
+	struct list_head	master_link;	/* link in master servers list */
 	struct rpc_clnt *	client;		/* RPC client handle */
-	struct rpc_clnt *	client_sys;	/* 2nd handle for FSINFO */
 	struct rpc_clnt *	client_acl;	/* ACL RPC client handle */
-	struct nfs_rpc_ops *	rpc_ops;	/* NFS protocol vector */
 	struct nfs_iostats *	io_stats;	/* I/O statistics */
 	struct backing_dev_info	backing_dev_info;
 	int			flags;		/* various flags */
@@ -29,24 +95,14 @@ struct nfs_server {
 	unsigned int		acregmax;
 	unsigned int		acdirmin;
 	unsigned int		acdirmax;
-	unsigned long		retrans_timeo;	/* retransmit timeout */
-	unsigned int		retrans_count;	/* number of retransmit tries */
 	unsigned int		namelen;
-	char *			hostname;	/* remote hostname */
-	struct nfs_fh		fh;
-	struct sockaddr_in	addr;
+
 	struct nfs_fsid		fsid;
+	__u64			maxfilesize;	/* maximum file size */
 	unsigned long		mount_time;	/* when this fs was mounted */
+	dev_t			s_dev;		/* superblock dev numbers */
+
 #ifdef CONFIG_NFS_V4
-	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the clientid, and the callback address.
-	 */
-	char			ip_addr[16];
-	char *			mnt_path;
-	struct nfs4_client *	nfs4_state;	/* all NFSv4 state starts here */
-	struct list_head	nfs4_siblings;	/* List of other nfs_server structs
-						 * that share the same clientid
-						 */
 	u32			attr_bitmask[2];/* V4 bitmask representing the set
 						   of attributes supported on this
 						   filesystem */
@@ -54,6 +110,7 @@ struct nfs_server {
 						   that are supported on this
 						   filesystem */
 #endif
+	void (*destroy)(struct nfs_server *);
 };
 
 /* Server capabilities */

include/linux/nfs_idmap.h

@@ -62,15 +62,15 @@ struct idmap_msg {
 #ifdef __KERNEL__
 
 /* Forward declaration to make this header independent of others */
-struct nfs4_client;
+struct nfs_client;
 
-void nfs_idmap_new(struct nfs4_client *);
-void nfs_idmap_delete(struct nfs4_client *);
+int nfs_idmap_new(struct nfs_client *);
+void nfs_idmap_delete(struct nfs_client *);
 
-int nfs_map_name_to_uid(struct nfs4_client *, const char *, size_t, __u32 *);
-int nfs_map_group_to_gid(struct nfs4_client *, const char *, size_t, __u32 *);
-int nfs_map_uid_to_name(struct nfs4_client *, __u32, char *);
-int nfs_map_gid_to_group(struct nfs4_client *, __u32, char *);
+int nfs_map_name_to_uid(struct nfs_client *, const char *, size_t, __u32 *);
+int nfs_map_group_to_gid(struct nfs_client *, const char *, size_t, __u32 *);
+int nfs_map_uid_to_name(struct nfs_client *, __u32, char *);
+int nfs_map_gid_to_group(struct nfs_client *, __u32, char *);
 
 extern unsigned int nfs_idmap_cache_timeout;
 #endif /* __KERNEL__ */

include/linux/nfs_xdr.h

@@ -1,7 +1,6 @@
 #ifndef _LINUX_NFS_XDR_H
 #define _LINUX_NFS_XDR_H
 
-#include <linux/sunrpc/xprt.h>
 #include <linux/nfsacl.h>
 
 /*
@@ -359,8 +358,8 @@ struct nfs_symlinkargs {
 	struct nfs_fh *		fromfh;
 	const char *		fromname;
 	unsigned int		fromlen;
-	const char *		topath;
-	unsigned int		tolen;
+	struct page **		pages;
+	unsigned int		pathlen;
 	struct iattr *		sattr;
 };
 
@@ -435,8 +434,8 @@ struct nfs3_symlinkargs {
 	struct nfs_fh *		fromfh;
 	const char *		fromname;
 	unsigned int		fromlen;
-	const char *		topath;
-	unsigned int		tolen;
+	struct page **		pages;
+	unsigned int		pathlen;
 	struct iattr *		sattr;
 };
 
@@ -534,7 +533,10 @@ struct nfs4_accessres {
 struct nfs4_create_arg {
 	u32				ftype;
 	union {
-		struct qstr *		symlink;    /* NF4LNK */
+		struct {
+			struct page **	pages;
+			unsigned int	len;
+		} symlink;   /* NF4LNK */
 		struct {
 			u32		specdata1;
 			u32		specdata2;
@@ -770,6 +772,9 @@ struct nfs_rpc_ops {
 
 	int	(*getroot) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fsinfo *);
+	int	(*lookupfh)(struct nfs_server *, struct nfs_fh *,
+			    struct qstr *, struct nfs_fh *,
+			    struct nfs_fattr *);
 	int	(*getattr) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fattr *);
 	int	(*setattr) (struct dentry *, struct nfs_fattr *,
@@ -791,9 +796,8 @@ struct nfs_rpc_ops {
 	int	(*rename)  (struct inode *, struct qstr *,
 			    struct inode *, struct qstr *);
 	int	(*link)    (struct inode *, struct inode *, struct qstr *);
-	int	(*symlink) (struct inode *, struct qstr *, struct qstr *,
-			    struct iattr *, struct nfs_fh *,
-			    struct nfs_fattr *);
+	int	(*symlink) (struct inode *, struct dentry *, struct page *,
+			    unsigned int, struct iattr *);
 	int	(*mkdir)   (struct inode *, struct dentry *, struct iattr *);
 	int	(*rmdir)   (struct inode *, struct qstr *);
 	int	(*readdir) (struct dentry *, struct rpc_cred *,
@@ -806,6 +810,7 @@ struct nfs_rpc_ops {
 			    struct nfs_fsinfo *);
 	int	(*pathconf) (struct nfs_server *, struct nfs_fh *,
 			     struct nfs_pathconf *);
+	int	(*set_capabilities)(struct nfs_server *, struct nfs_fh *);
 	u32 *	(*decode_dirent)(u32 *, struct nfs_entry *, int plus);
 	void	(*read_setup)   (struct nfs_read_data *);
 	int	(*read_done)  (struct rpc_task *, struct nfs_read_data *);
@@ -829,9 +834,9 @@ struct nfs_rpc_ops {
 /*
  * Function vectors etc. for the NFS client
  */
-extern struct nfs_rpc_ops	nfs_v2_clientops;
-extern struct nfs_rpc_ops	nfs_v3_clientops;
-extern struct nfs_rpc_ops	nfs_v4_clientops;
+extern const struct nfs_rpc_ops	nfs_v2_clientops;
+extern const struct nfs_rpc_ops	nfs_v3_clientops;
+extern const struct nfs_rpc_ops	nfs_v4_clientops;
 extern struct rpc_version	nfs_version2;
 extern struct rpc_version	nfs_version3;
 extern struct rpc_version	nfs_version4;

include/linux/sunrpc/clnt.h

@@ -18,18 +18,6 @@
 #include <linux/sunrpc/timer.h>
 #include <asm/signal.h>
 
-/*
- * This defines an RPC port mapping
- */
-struct rpc_portmap {
-	__u32			pm_prog;
-	__u32			pm_vers;
-	__u32			pm_prot;
-	__u16			pm_port;
-	unsigned char		pm_binding : 1;	/* doing a getport() */
-	struct rpc_wait_queue	pm_bindwait;	/* waiting on getport() */
-};
-
 struct rpc_inode;
 
 /*
@@ -40,7 +28,9 @@ struct rpc_clnt {
 	atomic_t		cl_users;	/* number of references */
 	struct rpc_xprt *	cl_xprt;	/* transport */
 	struct rpc_procinfo *	cl_procinfo;	/* procedure info */
-	u32			cl_maxproc;	/* max procedure number */
+	u32			cl_prog,	/* RPC program number */
+				cl_vers,	/* RPC version number */
+				cl_maxproc;	/* max procedure number */
 
 	char *			cl_server;	/* server machine name */
 	char *			cl_protname;	/* protocol name */
@@ -55,7 +45,6 @@ struct rpc_clnt {
 				cl_dead     : 1;/* abandoned */
 
 	struct rpc_rtt *	cl_rtt;		/* RTO estimator data */
-	struct rpc_portmap *	cl_pmap;	/* port mapping */
 
 	int			cl_nodelen;	/* nodename length */
 	char 			cl_nodename[UNX_MAXNODENAME];
@@ -64,14 +53,8 @@ struct rpc_clnt {
 	struct dentry *		cl_dentry;	/* inode */
 	struct rpc_clnt *	cl_parent;	/* Points to parent of clones */
 	struct rpc_rtt		cl_rtt_default;
-	struct rpc_portmap	cl_pmap_default;
 	char			cl_inline_name[32];
 };
-#define cl_timeout		cl_xprt->timeout
-#define cl_prog			cl_pmap->pm_prog
-#define cl_vers			cl_pmap->pm_vers
-#define cl_port			cl_pmap->pm_port
-#define cl_prot			cl_pmap->pm_prot
 
 /*
  * General RPC program info
@@ -106,24 +89,36 @@ struct rpc_procinfo {
 	char *			p_name;		/* name of procedure */
 };
 
-#define RPC_CONGESTED(clnt)	(RPCXPRT_CONGESTED((clnt)->cl_xprt))
-#define RPC_PEERADDR(clnt)	(&(clnt)->cl_xprt->addr)
-
 #ifdef __KERNEL__
 
-struct rpc_clnt *rpc_create_client(struct rpc_xprt *xprt, char *servname,
-				struct rpc_program *info,
-				u32 version, rpc_authflavor_t authflavor);
-struct rpc_clnt *rpc_new_client(struct rpc_xprt *xprt, char *servname,
-				struct rpc_program *info,
-				u32 version, rpc_authflavor_t authflavor);
+struct rpc_create_args {
+	int			protocol;
+	struct sockaddr		*address;
+	size_t			addrsize;
+	struct rpc_timeout	*timeout;
+	char			*servername;
+	struct rpc_program	*program;
+	u32			version;
+	rpc_authflavor_t	authflavor;
+	unsigned long		flags;
+};
+
+/* Values for "flags" field */
+#define RPC_CLNT_CREATE_HARDRTRY	(1UL << 0)
+#define RPC_CLNT_CREATE_INTR		(1UL << 1)
+#define RPC_CLNT_CREATE_AUTOBIND	(1UL << 2)
+#define RPC_CLNT_CREATE_ONESHOT		(1UL << 3)
+#define RPC_CLNT_CREATE_NONPRIVPORT	(1UL << 4)
+#define RPC_CLNT_CREATE_NOPING		(1UL << 5)
+
+struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				struct rpc_program *, int);
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
 int		rpc_shutdown_client(struct rpc_clnt *);
 int		rpc_destroy_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
-void		rpc_getport(struct rpc_task *, struct rpc_clnt *);
+void		rpc_getport(struct rpc_task *);
 int		rpc_register(u32, u32, int, unsigned short, int *);
 
 void		rpc_call_setup(struct rpc_task *, struct rpc_message *, int);
@@ -140,6 +135,8 @@ void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 size_t		rpc_max_payload(struct rpc_clnt *);
 void		rpc_force_rebind(struct rpc_clnt *);
 int		rpc_ping(struct rpc_clnt *clnt, int flags);
+size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
+char *		rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
 
 /*
  * Helper function for NFSroot support

include/linux/sunrpc/rpc_pipe_fs.h

@@ -43,7 +43,7 @@ extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *);
 
 extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *);
 extern int rpc_rmdir(struct dentry *);
-extern struct dentry *rpc_mkpipe(char *, void *, struct rpc_pipe_ops *, int flags);
+extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, struct rpc_pipe_ops *, int flags);
 extern int rpc_unlink(struct dentry *);
 extern struct vfsmount *rpc_get_mount(void);
 extern void rpc_put_mount(void);

include/linux/sunrpc/sched.h

@@ -127,7 +127,6 @@ struct rpc_call_ops {
  */
 #define RPC_TASK_ASYNC		0x0001		/* is an async task */
 #define RPC_TASK_SWAPPER	0x0002		/* is swapping in/out */
-#define RPC_TASK_CHILD		0x0008		/* is child of other task */
 #define RPC_CALL_MAJORSEEN	0x0020		/* major timeout seen */
 #define RPC_TASK_ROOTCREDS	0x0040		/* force root creds */
 #define RPC_TASK_DYNAMIC	0x0080		/* task was kmalloc'ed */
@@ -136,7 +135,6 @@ struct rpc_call_ops {
 #define RPC_TASK_NOINTR		0x0400		/* uninterruptible task */
 
 #define RPC_IS_ASYNC(t)		((t)->tk_flags & RPC_TASK_ASYNC)
-#define RPC_IS_CHILD(t)		((t)->tk_flags & RPC_TASK_CHILD)
 #define RPC_IS_SWAPPER(t)	((t)->tk_flags & RPC_TASK_SWAPPER)
 #define RPC_DO_ROOTOVERRIDE(t)	((t)->tk_flags & RPC_TASK_ROOTCREDS)
 #define RPC_ASSASSINATED(t)	((t)->tk_flags & RPC_TASK_KILLED)
@@ -253,7 +251,6 @@ struct rpc_task *rpc_new_task(struct rpc_clnt *, int flags,
 				const struct rpc_call_ops *ops, void *data);
 struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags,
 				const struct rpc_call_ops *ops, void *data);
-struct rpc_task *rpc_new_child(struct rpc_clnt *, struct rpc_task *parent);
 void		rpc_init_task(struct rpc_task *task, struct rpc_clnt *clnt,
 				int flags, const struct rpc_call_ops *ops,
 				void *data);
@@ -261,8 +258,6 @@ void		rpc_release_task(struct rpc_task *);
 void		rpc_exit_task(struct rpc_task *);
 void		rpc_killall_tasks(struct rpc_clnt *);
 int		rpc_execute(struct rpc_task *);
-void		rpc_run_child(struct rpc_task *parent, struct rpc_task *child,
-					rpc_action action);
 void		rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *);
 void		rpc_init_wait_queue(struct rpc_wait_queue *, const char *);
 void		rpc_sleep_on(struct rpc_wait_queue *, struct rpc_task *,

include/linux/sunrpc/xprt.h

@@ -12,6 +12,7 @@
 #include <linux/uio.h>
 #include <linux/socket.h>
 #include <linux/in.h>
+#include <linux/kref.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xdr.h>
 
@@ -51,6 +52,14 @@ struct rpc_timeout {
 	unsigned char		to_exponential;
 };
 
+enum rpc_display_format_t {
+	RPC_DISPLAY_ADDR = 0,
+	RPC_DISPLAY_PORT,
+	RPC_DISPLAY_PROTO,
+	RPC_DISPLAY_ALL,
+	RPC_DISPLAY_MAX,
+};
+
 struct rpc_task;
 struct rpc_xprt;
 struct seq_file;
@@ -103,8 +112,10 @@ struct rpc_rqst {
 
 struct rpc_xprt_ops {
 	void		(*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize);
+	char *		(*print_addr)(struct rpc_xprt *xprt, enum rpc_display_format_t format);
 	int		(*reserve_xprt)(struct rpc_task *task);
 	void		(*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
+	void		(*rpcbind)(struct rpc_task *task);
 	void		(*set_port)(struct rpc_xprt *xprt, unsigned short port);
 	void		(*connect)(struct rpc_task *task);
 	void *		(*buf_alloc)(struct rpc_task *task, size_t size);
@@ -119,12 +130,14 @@ struct rpc_xprt_ops {
 };
 
 struct rpc_xprt {
+	struct kref		kref;		/* Reference count */
 	struct rpc_xprt_ops *	ops;		/* transport methods */
 	struct socket *		sock;		/* BSD socket layer */
 	struct sock *		inet;		/* INET layer */
 
 	struct rpc_timeout	timeout;	/* timeout parms */
-	struct sockaddr_in	addr;		/* server address */
+	struct sockaddr_storage	addr;		/* server address */
+	size_t			addrlen;	/* size of server address */
 	int			prot;		/* IP protocol */
 
 	unsigned long		cong;		/* current congestion */
@@ -138,6 +151,7 @@ struct rpc_xprt {
 	unsigned int		tsh_size;	/* size of transport specific
 						   header */
 
+	struct rpc_wait_queue	binding;	/* requests waiting on rpcbind */
 	struct rpc_wait_queue	sending;	/* requests waiting to send */
 	struct rpc_wait_queue	resend;		/* requests waiting to resend */
 	struct rpc_wait_queue	pending;	/* requests in flight */
@@ -205,6 +219,8 @@ struct rpc_xprt {
 	void			(*old_data_ready)(struct sock *, int);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
+
+	char *			address_strings[RPC_DISPLAY_MAX];
 };
 
 #define XPRT_LAST_FRAG		(1 << 0)
@@ -217,12 +233,12 @@ struct rpc_xprt {
 /*
  * Transport operations used by ULPs
  */
-struct rpc_xprt *	xprt_create_proto(int proto, struct sockaddr_in *addr, struct rpc_timeout *to);
 void			xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long incr);
 
 /*
  * Generic internal transport functions
  */
+struct rpc_xprt *	xprt_create_transport(int proto, struct sockaddr *addr, size_t size, struct rpc_timeout *toparms);
 void			xprt_connect(struct rpc_task *task);
 void			xprt_reserve(struct rpc_task *task);
 int			xprt_reserve_xprt(struct rpc_task *task);
@@ -234,7 +250,8 @@ int			xprt_adjust_timeout(struct rpc_rqst *req);
 void			xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_release(struct rpc_task *task);
-int			xprt_destroy(struct rpc_xprt *xprt);
+struct rpc_xprt *	xprt_get(struct rpc_xprt *xprt);
+void			xprt_put(struct rpc_xprt *xprt);
 
 static inline u32 *xprt_skip_transport_header(struct rpc_xprt *xprt, u32 *p)
 {
@@ -269,6 +286,8 @@ int			xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to);
 #define XPRT_CONNECTED		(1)
 #define XPRT_CONNECTING		(2)
 #define XPRT_CLOSE_WAIT		(3)
+#define XPRT_BOUND		(4)
+#define XPRT_BINDING		(5)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {
@@ -312,6 +331,33 @@ static inline int xprt_test_and_set_connecting(struct rpc_xprt *xprt)
 	return test_and_set_bit(XPRT_CONNECTING, &xprt->state);
 }
 
+static inline void xprt_set_bound(struct rpc_xprt *xprt)
+{
+	test_and_set_bit(XPRT_BOUND, &xprt->state);
+}
+
+static inline int xprt_bound(struct rpc_xprt *xprt)
+{
+	return test_bit(XPRT_BOUND, &xprt->state);
+}
+
+static inline void xprt_clear_bound(struct rpc_xprt *xprt)
+{
+	clear_bit(XPRT_BOUND, &xprt->state);
+}
+
+static inline void xprt_clear_binding(struct rpc_xprt *xprt)
+{
+	smp_mb__before_clear_bit();
+	clear_bit(XPRT_BINDING, &xprt->state);
+	smp_mb__after_clear_bit();
+}
+
+static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt)
+{
+	return test_and_set_bit(XPRT_BINDING, &xprt->state);
+}
+
 #endif /* __KERNEL__*/
 
 #endif /* _LINUX_SUNRPC_XPRT_H */

include/linux/writeback.h

@@ -85,6 +85,7 @@ int wakeup_pdflush(long nr_pages);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
 void throttle_vm_writeout(void);
+void writeback_congestion_end(void);
 
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;

mm/page-writeback.c

@@ -802,6 +802,15 @@ int test_set_page_writeback(struct page *page)
 }
 EXPORT_SYMBOL(test_set_page_writeback);
 
+/*
+ * Wakes up tasks that are being throttled due to writeback congestion
+ */
+void writeback_congestion_end(void)
+{
+	blk_congestion_end(WRITE);
+}
+EXPORT_SYMBOL(writeback_congestion_end);
+
 /*
  * Return true if any of the pages in the mapping are marged with the
  * passed tag.

net/sunrpc/auth_gss/auth_gss.c

@@ -88,7 +88,6 @@ struct gss_auth {
 	struct list_head upcalls;
 	struct rpc_clnt *client;
 	struct dentry *dentry;
-	char path[48];
 	spinlock_t lock;
 };
 
@@ -690,10 +689,8 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
 	if (err)
 		goto err_put_mech;
 
-	snprintf(gss_auth->path, sizeof(gss_auth->path), "%s/%s",
-			clnt->cl_pathname,
-			gss_auth->mech->gm_name);
-	gss_auth->dentry = rpc_mkpipe(gss_auth->path, clnt, &gss_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
+	gss_auth->dentry = rpc_mkpipe(clnt->cl_dentry, gss_auth->mech->gm_name,
+			clnt, &gss_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
 	if (IS_ERR(gss_auth->dentry)) {
 		err = PTR_ERR(gss_auth->dentry);
 		goto err_put_mech;

net/sunrpc/clnt.c

@@ -97,17 +97,7 @@ rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name)
 	}
 }
 
-/*
- * Create an RPC client
- * FIXME: This should also take a flags argument (as in task->tk_flags).
- * It's called (among others) from pmap_create_client, which may in
- * turn be called by an async task. In this case, rpciod should not be
- * made to sleep too long.
- */
-struct rpc_clnt *
-rpc_new_client(struct rpc_xprt *xprt, char *servname,
-		  struct rpc_program *program, u32 vers,
-		  rpc_authflavor_t flavor)
+static struct rpc_clnt * rpc_new_client(struct rpc_xprt *xprt, char *servname, struct rpc_program *program, u32 vers, rpc_authflavor_t flavor)
 {
 	struct rpc_version	*version;
 	struct rpc_clnt		*clnt = NULL;
@@ -147,16 +137,12 @@ rpc_new_client(struct rpc_xprt *xprt, char *servname,
 	clnt->cl_procinfo = version->procs;
 	clnt->cl_maxproc  = version->nrprocs;
 	clnt->cl_protname = program->name;
-	clnt->cl_pmap	  = &clnt->cl_pmap_default;
-	clnt->cl_port     = xprt->addr.sin_port;
 	clnt->cl_prog     = program->number;
 	clnt->cl_vers     = version->number;
-	clnt->cl_prot     = xprt->prot;
 	clnt->cl_stats    = program->stats;
 	clnt->cl_metrics  = rpc_alloc_iostats(clnt);
-	rpc_init_wait_queue(&clnt->cl_pmap_default.pm_bindwait, "bindwait");
 
-	if (!clnt->cl_port)
+	if (!xprt_bound(clnt->cl_xprt))
 		clnt->cl_autobind = 1;
 
 	clnt->cl_rtt = &clnt->cl_rtt_default;
@@ -191,40 +177,71 @@ out_no_path:
 		kfree(clnt->cl_server);
 	kfree(clnt);
 out_err:
-	xprt_destroy(xprt);
+	xprt_put(xprt);
 out_no_xprt:
 	return ERR_PTR(err);
 }
 
-/**
- * Create an RPC client
- * @xprt - pointer to xprt struct
- * @servname - name of server
- * @info - rpc_program
- * @version - rpc_program version
- * @authflavor - rpc_auth flavour to use
+/*
+ * rpc_create - create an RPC client and transport with one call
+ * @args: rpc_clnt create argument structure
  *
- * Creates an RPC client structure, then pings the server in order to
- * determine if it is up, and if it supports this program and version.
+ * Creates and initializes an RPC transport and an RPC client.
  *
- * This function should never be called by asynchronous tasks such as
- * the portmapper.
+ * It can ping the server in order to determine if it is up, and to see if
+ * it supports this program and version.  RPC_CLNT_CREATE_NOPING disables
+ * this behavior so asynchronous tasks can also use rpc_create.
  */
-struct rpc_clnt *rpc_create_client(struct rpc_xprt *xprt, char *servname,
-		struct rpc_program *info, u32 version, rpc_authflavor_t authflavor)
+struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 {
+	struct rpc_xprt *xprt;
 	struct rpc_clnt *clnt;
-	int err;
-	
-	clnt = rpc_new_client(xprt, servname, info, version, authflavor);
+
+	xprt = xprt_create_transport(args->protocol, args->address,
+					args->addrsize, args->timeout);
+	if (IS_ERR(xprt))
+		return (struct rpc_clnt *)xprt;
+
+	/*
+	 * By default, kernel RPC client connects from a reserved port.
+	 * CAP_NET_BIND_SERVICE will not be set for unprivileged requesters,
+	 * but it is always enabled for rpciod, which handles the connect
+	 * operation.
+	 */
+	xprt->resvport = 1;
+	if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT)
+		xprt->resvport = 0;
+
+	dprintk("RPC:       creating %s client for %s (xprt %p)\n",
+		args->program->name, args->servername, xprt);
+
+	clnt = rpc_new_client(xprt, args->servername, args->program,
+				args->version, args->authflavor);
 	if (IS_ERR(clnt))
 		return clnt;
-	err = rpc_ping(clnt, RPC_TASK_SOFT|RPC_TASK_NOINTR);
-	if (err == 0)
-		return clnt;
-	rpc_shutdown_client(clnt);
-	return ERR_PTR(err);
+
+	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
+		int err = rpc_ping(clnt, RPC_TASK_SOFT|RPC_TASK_NOINTR);
+		if (err != 0) {
+			rpc_shutdown_client(clnt);
+			return ERR_PTR(err);
+		}
+	}
+
+	clnt->cl_softrtry = 1;
+	if (args->flags & RPC_CLNT_CREATE_HARDRTRY)
+		clnt->cl_softrtry = 0;
+
+	if (args->flags & RPC_CLNT_CREATE_INTR)
+		clnt->cl_intr = 1;
+	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
+		clnt->cl_autobind = 1;
+	if (args->flags & RPC_CLNT_CREATE_ONESHOT)
+		clnt->cl_oneshot = 1;
+
+	return clnt;
 }
+EXPORT_SYMBOL_GPL(rpc_create);
 
 /*
  * This function clones the RPC client structure. It allows us to share the
@@ -244,8 +261,7 @@ rpc_clone_client(struct rpc_clnt *clnt)
 	atomic_set(&new->cl_users, 0);
 	new->cl_parent = clnt;
 	atomic_inc(&clnt->cl_count);
-	/* Duplicate portmapper */
-	rpc_init_wait_queue(&new->cl_pmap_default.pm_bindwait, "bindwait");
+	new->cl_xprt = xprt_get(clnt->cl_xprt);
 	/* Turn off autobind on clones */
 	new->cl_autobind = 0;
 	new->cl_oneshot = 0;
@@ -255,8 +271,7 @@ rpc_clone_client(struct rpc_clnt *clnt)
 	rpc_init_rtt(&new->cl_rtt_default, clnt->cl_xprt->timeout.to_initval);
 	if (new->cl_auth)
 		atomic_inc(&new->cl_auth->au_count);
-	new->cl_pmap		= &new->cl_pmap_default;
-	new->cl_metrics         = rpc_alloc_iostats(clnt);
+	new->cl_metrics = rpc_alloc_iostats(clnt);
 	return new;
 out_no_clnt:
 	printk(KERN_INFO "RPC: out of memory in %s\n", __FUNCTION__);
@@ -323,15 +338,12 @@ rpc_destroy_client(struct rpc_clnt *clnt)
 		rpc_rmdir(clnt->cl_dentry);
 		rpc_put_mount();
 	}
-	if (clnt->cl_xprt) {
-		xprt_destroy(clnt->cl_xprt);
-		clnt->cl_xprt = NULL;
-	}
 	if (clnt->cl_server != clnt->cl_inline_name)
 		kfree(clnt->cl_server);
 out_free:
 	rpc_free_iostats(clnt->cl_metrics);
 	clnt->cl_metrics = NULL;
+	xprt_put(clnt->cl_xprt);
 	kfree(clnt);
 	return 0;
 }
@@ -540,6 +552,40 @@ rpc_call_setup(struct rpc_task *task, struct rpc_message *msg, int flags)
 		task->tk_action = rpc_exit_task;
 }
 
+/**
+ * rpc_peeraddr - extract remote peer address from clnt's xprt
+ * @clnt: RPC client structure
+ * @buf: target buffer
+ * @size: length of target buffer
+ *
+ * Returns the number of bytes that are actually in the stored address.
+ */
+size_t rpc_peeraddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t bufsize)
+{
+	size_t bytes;
+	struct rpc_xprt *xprt = clnt->cl_xprt;
+
+	bytes = sizeof(xprt->addr);
+	if (bytes > bufsize)
+		bytes = bufsize;
+	memcpy(buf, &clnt->cl_xprt->addr, bytes);
+	return xprt->addrlen;
+}
+EXPORT_SYMBOL_GPL(rpc_peeraddr);
+
+/**
+ * rpc_peeraddr2str - return remote peer address in printable format
+ * @clnt: RPC client structure
+ * @format: address format
+ *
+ */
+char *rpc_peeraddr2str(struct rpc_clnt *clnt, enum rpc_display_format_t format)
+{
+	struct rpc_xprt *xprt = clnt->cl_xprt;
+	return xprt->ops->print_addr(xprt, format);
+}
+EXPORT_SYMBOL_GPL(rpc_peeraddr2str);
+
 void
 rpc_setbufsize(struct rpc_clnt *clnt, unsigned int sndsize, unsigned int rcvsize)
 {
@@ -560,7 +606,7 @@ size_t rpc_max_payload(struct rpc_clnt *clnt)
 {
 	return clnt->cl_xprt->max_payload;
 }
-EXPORT_SYMBOL(rpc_max_payload);
+EXPORT_SYMBOL_GPL(rpc_max_payload);
 
 /**
  * rpc_force_rebind - force transport to check that remote port is unchanged
@@ -570,9 +616,9 @@ EXPORT_SYMBOL(rpc_max_payload);
 void rpc_force_rebind(struct rpc_clnt *clnt)
 {
 	if (clnt->cl_autobind)
-		clnt->cl_port = 0;
+		xprt_clear_bound(clnt->cl_xprt);
 }
-EXPORT_SYMBOL(rpc_force_rebind);
+EXPORT_SYMBOL_GPL(rpc_force_rebind);
 
 /*
  * Restart an (async) RPC call. Usually called from within the
@@ -781,16 +827,16 @@ call_encode(struct rpc_task *task)
 static void
 call_bind(struct rpc_task *task)
 {
-	struct rpc_clnt	*clnt = task->tk_client;
+	struct rpc_xprt *xprt = task->tk_xprt;
 
 	dprintk("RPC: %4d call_bind (status %d)\n",
 				task->tk_pid, task->tk_status);
 
 	task->tk_action = call_connect;
-	if (!clnt->cl_port) {
+	if (!xprt_bound(xprt)) {
 		task->tk_action = call_bind_status;
-		task->tk_timeout = task->tk_xprt->bind_timeout;
-		rpc_getport(task, clnt);
+		task->tk_timeout = xprt->bind_timeout;
+		xprt->ops->rpcbind(task);
 	}
 }
 
@@ -815,15 +861,11 @@ call_bind_status(struct rpc_task *task)
 		dprintk("RPC: %4d remote rpcbind: RPC program/version unavailable\n",
 				task->tk_pid);
 		rpc_delay(task, 3*HZ);
-		goto retry_bind;
+		goto retry_timeout;
 	case -ETIMEDOUT:
 		dprintk("RPC: %4d rpcbind request timed out\n",
 				task->tk_pid);
-		if (RPC_IS_SOFT(task)) {
-			status = -EIO;
-			break;
-		}
-		goto retry_bind;
+		goto retry_timeout;
 	case -EPFNOSUPPORT:
 		dprintk("RPC: %4d remote rpcbind service unavailable\n",
 				task->tk_pid);
@@ -836,16 +878,13 @@ call_bind_status(struct rpc_task *task)
 		dprintk("RPC: %4d unrecognized rpcbind error (%d)\n",
 				task->tk_pid, -task->tk_status);
 		status = -EIO;
-		break;
 	}
 
 	rpc_exit(task, status);
 	return;
 
-retry_bind:
-	task->tk_status = 0;
-	task->tk_action = call_bind;
-	return;
+retry_timeout:
+	task->tk_action = call_timeout;
 }
 
 /*
@@ -893,14 +932,16 @@ call_connect_status(struct rpc_task *task)
 
 	switch (status) {
 	case -ENOTCONN:
-	case -ETIMEDOUT:
 	case -EAGAIN:
 		task->tk_action = call_bind;
-		break;
-	default:
-		rpc_exit(task, -EIO);
-		break;
+		if (!RPC_IS_SOFT(task))
+			return;
+		/* if soft mounted, test if we've timed out */
+	case -ETIMEDOUT:
+		task->tk_action = call_timeout;
+		return;
 	}
+	rpc_exit(task, -EIO);
 }
 
 /*
@@ -982,6 +1023,14 @@ call_status(struct rpc_task *task)
 
 	task->tk_status = 0;
 	switch(status) {
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+		/*
+		 * Delay any retries for 3 seconds, then handle as if it
+		 * were a timeout.
+		 */
+		rpc_delay(task, 3*HZ);
 	case -ETIMEDOUT:
 		task->tk_action = call_timeout;
 		break;
@@ -1001,7 +1050,6 @@ call_status(struct rpc_task *task)
 		printk("%s: RPC call returned error %d\n",
 			       clnt->cl_protname, -status);
 		rpc_exit(task, status);
-		break;
 	}
 }
 
@@ -1069,10 +1117,10 @@ call_decode(struct rpc_task *task)
 			clnt->cl_stats->rpcretrans++;
 			goto out_retry;
 		}
-		printk(KERN_WARNING "%s: too small RPC reply size (%d bytes)\n",
+		dprintk("%s: too small RPC reply size (%d bytes)\n",
 			clnt->cl_protname, task->tk_status);
-		rpc_exit(task, -EIO);
-		return;
+		task->tk_action = call_timeout;
+		goto out_retry;
 	}
 
 	/*

net/sunrpc/pmap_clnt.c

@@ -1,7 +1,9 @@
 /*
- * linux/net/sunrpc/pmap.c
+ * linux/net/sunrpc/pmap_clnt.c
  *
- * Portmapper client.
+ * In-kernel RPC portmapper client.
+ *
+ * Portmapper supports version 2 of the rpcbind protocol (RFC 1833).
  *
  * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
  */
@@ -13,7 +15,6 @@
 #include <linux/uio.h>
 #include <linux/in.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/sched.h>
 
 #ifdef RPC_DEBUG
@@ -24,80 +25,141 @@
 #define PMAP_UNSET		2
 #define PMAP_GETPORT		3
 
+struct portmap_args {
+	u32			pm_prog;
+	u32			pm_vers;
+	u32			pm_prot;
+	unsigned short		pm_port;
+	struct rpc_xprt *	pm_xprt;
+};
+
 static struct rpc_procinfo	pmap_procedures[];
 static struct rpc_clnt *	pmap_create(char *, struct sockaddr_in *, int, int);
-static void			pmap_getport_done(struct rpc_task *);
+static void			pmap_getport_done(struct rpc_task *, void *);
 static struct rpc_program	pmap_program;
-static DEFINE_SPINLOCK(pmap_lock);
 
-/*
- * Obtain the port for a given RPC service on a given host. This one can
- * be called for an ongoing RPC request.
- */
-void
-rpc_getport(struct rpc_task *task, struct rpc_clnt *clnt)
+static void pmap_getport_prepare(struct rpc_task *task, void *calldata)
 {
-	struct rpc_portmap *map = clnt->cl_pmap;
-	struct sockaddr_in *sap = &clnt->cl_xprt->addr;
+	struct portmap_args *map = calldata;
 	struct rpc_message msg = {
 		.rpc_proc	= &pmap_procedures[PMAP_GETPORT],
 		.rpc_argp	= map,
-		.rpc_resp	= &clnt->cl_port,
-		.rpc_cred	= NULL
+		.rpc_resp	= &map->pm_port,
 	};
+
+	rpc_call_setup(task, &msg, 0);
+}
+
+static inline struct portmap_args *pmap_map_alloc(void)
+{
+	return kmalloc(sizeof(struct portmap_args), GFP_NOFS);
+}
+
+static inline void pmap_map_free(struct portmap_args *map)
+{
+	kfree(map);
+}
+
+static void pmap_map_release(void *data)
+{
+	pmap_map_free(data);
+}
+
+static const struct rpc_call_ops pmap_getport_ops = {
+	.rpc_call_prepare	= pmap_getport_prepare,
+	.rpc_call_done		= pmap_getport_done,
+	.rpc_release		= pmap_map_release,
+};
+
+static inline void pmap_wake_portmap_waiters(struct rpc_xprt *xprt, int status)
+{
+	xprt_clear_binding(xprt);
+	rpc_wake_up_status(&xprt->binding, status);
+}
+
+/**
+ * rpc_getport - obtain the port for a given RPC service on a given host
+ * @task: task that is waiting for portmapper request
+ *
+ * This one can be called for an ongoing RPC request, and can be used in
+ * an async (rpciod) context.
+ */
+void rpc_getport(struct rpc_task *task)
+{
+	struct rpc_clnt *clnt = task->tk_client;
+	struct rpc_xprt *xprt = task->tk_xprt;
+	struct sockaddr_in addr;
+	struct portmap_args *map;
 	struct rpc_clnt	*pmap_clnt;
-	struct rpc_task	*child;
+	struct rpc_task *child;
+	int status;
 
-	dprintk("RPC: %4d rpc_getport(%s, %d, %d, %d)\n",
+	dprintk("RPC: %4d rpc_getport(%s, %u, %u, %d)\n",
 			task->tk_pid, clnt->cl_server,
-			map->pm_prog, map->pm_vers, map->pm_prot);
+			clnt->cl_prog, clnt->cl_vers, xprt->prot);
 
 	/* Autobind on cloned rpc clients is discouraged */
 	BUG_ON(clnt->cl_parent != clnt);
 
-	spin_lock(&pmap_lock);
-	if (map->pm_binding) {
-		rpc_sleep_on(&map->pm_bindwait, task, NULL, NULL);
-		spin_unlock(&pmap_lock);
+	if (xprt_test_and_set_binding(xprt)) {
+		task->tk_status = -EACCES;	/* tell caller to check again */
+		rpc_sleep_on(&xprt->binding, task, NULL, NULL);
 		return;
 	}
-	map->pm_binding = 1;
-	spin_unlock(&pmap_lock);
 
-	pmap_clnt = pmap_create(clnt->cl_server, sap, map->pm_prot, 0);
-	if (IS_ERR(pmap_clnt)) {
-		task->tk_status = PTR_ERR(pmap_clnt);
+	/* Someone else may have bound if we slept */
+	status = 0;
+	if (xprt_bound(xprt))
+		goto bailout_nofree;
+
+	status = -ENOMEM;
+	map = pmap_map_alloc();
+	if (!map)
+		goto bailout_nofree;
+	map->pm_prog = clnt->cl_prog;
+	map->pm_vers = clnt->cl_vers;
+	map->pm_prot = xprt->prot;
+	map->pm_port = 0;
+	map->pm_xprt = xprt_get(xprt);
+
+	rpc_peeraddr(clnt, (struct sockaddr *) &addr, sizeof(addr));
+	pmap_clnt = pmap_create(clnt->cl_server, &addr, map->pm_prot, 0);
+	status = PTR_ERR(pmap_clnt);
+	if (IS_ERR(pmap_clnt))
 		goto bailout;
-	}
-	task->tk_status = 0;
 
-	/*
-	 * Note: rpc_new_child will release client after a failure.
-	 */
-	if (!(child = rpc_new_child(pmap_clnt, task)))
+	status = -EIO;
+	child = rpc_run_task(pmap_clnt, RPC_TASK_ASYNC, &pmap_getport_ops, map);
+	if (IS_ERR(child))
 		goto bailout;
+	rpc_release_task(child);
 
-	/* Setup the call info struct */
-	rpc_call_setup(child, &msg, 0);
+	rpc_sleep_on(&xprt->binding, task, NULL, NULL);
 
-	/* ... and run the child task */
 	task->tk_xprt->stat.bind_count++;
-	rpc_run_child(task, child, pmap_getport_done);
 	return;
 
 bailout:
-	spin_lock(&pmap_lock);
-	map->pm_binding = 0;
-	rpc_wake_up(&map->pm_bindwait);
-	spin_unlock(&pmap_lock);
-	rpc_exit(task, -EIO);
+	pmap_map_free(map);
+	xprt_put(xprt);
+bailout_nofree:
+	task->tk_status = status;
+	pmap_wake_portmap_waiters(xprt, status);
 }
 
 #ifdef CONFIG_ROOT_NFS
-int
-rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
+/**
+ * rpc_getport_external - obtain the port for a given RPC service on a given host
+ * @sin: address of remote peer
+ * @prog: RPC program number to bind
+ * @vers: RPC version number to bind
+ * @prot: transport protocol to use to make this request
+ *
+ * This one is called from outside the RPC client in a synchronous task context.
+ */
+int rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
 {
-	struct rpc_portmap map = {
+	struct portmap_args map = {
 		.pm_prog	= prog,
 		.pm_vers	= vers,
 		.pm_prot	= prot,
@@ -112,7 +174,7 @@ rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
 	char		hostname[32];
 	int		status;
 
-	dprintk("RPC:      rpc_getport_external(%u.%u.%u.%u, %d, %d, %d)\n",
+	dprintk("RPC:      rpc_getport_external(%u.%u.%u.%u, %u, %u, %d)\n",
 			NIPQUAD(sin->sin_addr.s_addr), prog, vers, prot);
 
 	sprintf(hostname, "%u.%u.%u.%u", NIPQUAD(sin->sin_addr.s_addr));
@@ -132,45 +194,53 @@ rpc_getport_external(struct sockaddr_in *sin, __u32 prog, __u32 vers, int prot)
 }
 #endif
 
-static void
-pmap_getport_done(struct rpc_task *task)
+/*
+ * Portmapper child task invokes this callback via tk_exit.
+ */
+static void pmap_getport_done(struct rpc_task *child, void *data)
 {
-	struct rpc_clnt	*clnt = task->tk_client;
-	struct rpc_xprt *xprt = task->tk_xprt;
-	struct rpc_portmap *map = clnt->cl_pmap;
-
-	dprintk("RPC: %4d pmap_getport_done(status %d, port %d)\n",
-			task->tk_pid, task->tk_status, clnt->cl_port);
-
-	xprt->ops->set_port(xprt, 0);
-	if (task->tk_status < 0) {
-		/* Make the calling task exit with an error */
-		task->tk_action = rpc_exit_task;
-	} else if (clnt->cl_port == 0) {
-		/* Program not registered */
-		rpc_exit(task, -EACCES);
+	struct portmap_args *map = data;
+	struct rpc_xprt *xprt = map->pm_xprt;
+	int status = child->tk_status;
+
+	if (status < 0) {
+		/* Portmapper not available */
+		xprt->ops->set_port(xprt, 0);
+	} else if (map->pm_port == 0) {
+		/* Requested RPC service wasn't registered */
+		xprt->ops->set_port(xprt, 0);
+		status = -EACCES;
 	} else {
-		xprt->ops->set_port(xprt, clnt->cl_port);
-		clnt->cl_port = htons(clnt->cl_port);
+		/* Succeeded */
+		xprt->ops->set_port(xprt, map->pm_port);
+		xprt_set_bound(xprt);
+		status = 0;
 	}
-	spin_lock(&pmap_lock);
-	map->pm_binding = 0;
-	rpc_wake_up(&map->pm_bindwait);
-	spin_unlock(&pmap_lock);
+
+	dprintk("RPC: %4d pmap_getport_done(status %d, port %u)\n",
+			child->tk_pid, status, map->pm_port);
+
+	pmap_wake_portmap_waiters(xprt, status);
+	xprt_put(xprt);
 }
 
-/*
- * Set or unset a port registration with the local portmapper.
+/**
+ * rpc_register - set or unset a port registration with the local portmapper
+ * @prog: RPC program number to bind
+ * @vers: RPC version number to bind
+ * @prot: transport protocol to use to make this request
+ * @port: port value to register
+ * @okay: result code
+ *
  * port == 0 means unregister, port != 0 means register.
  */
-int
-rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
+int rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
 {
 	struct sockaddr_in	sin = {
 		.sin_family	= AF_INET,
 		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
 	};
-	struct rpc_portmap	map = {
+	struct portmap_args	map = {
 		.pm_prog	= prog,
 		.pm_vers	= vers,
 		.pm_prot	= prot,
@@ -184,7 +254,7 @@ rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
 	struct rpc_clnt		*pmap_clnt;
 	int error = 0;
 
-	dprintk("RPC: registering (%d, %d, %d, %d) with portmapper.\n",
+	dprintk("RPC: registering (%u, %u, %d, %u) with portmapper.\n",
 			prog, vers, prot, port);
 
 	pmap_clnt = pmap_create("localhost", &sin, IPPROTO_UDP, 1);
@@ -207,38 +277,32 @@ rpc_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
 	return error;
 }
 
-static struct rpc_clnt *
-pmap_create(char *hostname, struct sockaddr_in *srvaddr, int proto, int privileged)
+static struct rpc_clnt *pmap_create(char *hostname, struct sockaddr_in *srvaddr, int proto, int privileged)
 {
-	struct rpc_xprt	*xprt;
-	struct rpc_clnt	*clnt;
-
-	/* printk("pmap: create xprt\n"); */
-	xprt = xprt_create_proto(proto, srvaddr, NULL);
-	if (IS_ERR(xprt))
-		return (struct rpc_clnt *)xprt;
-	xprt->ops->set_port(xprt, RPC_PMAP_PORT);
+	struct rpc_create_args args = {
+		.protocol	= proto,
+		.address	= (struct sockaddr *)srvaddr,
+		.addrsize	= sizeof(*srvaddr),
+		.servername	= hostname,
+		.program	= &pmap_program,
+		.version	= RPC_PMAP_VERSION,
+		.authflavor	= RPC_AUTH_UNIX,
+		.flags		= (RPC_CLNT_CREATE_ONESHOT |
+				   RPC_CLNT_CREATE_NOPING),
+	};
+
+	srvaddr->sin_port = htons(RPC_PMAP_PORT);
 	if (!privileged)
-		xprt->resvport = 0;
-
-	/* printk("pmap: create clnt\n"); */
-	clnt = rpc_new_client(xprt, hostname,
-				&pmap_program, RPC_PMAP_VERSION,
-				RPC_AUTH_UNIX);
-	if (!IS_ERR(clnt)) {
-		clnt->cl_softrtry = 1;
-		clnt->cl_oneshot  = 1;
-	}
-	return clnt;
+		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+	return rpc_create(&args);
 }
 
 /*
  * XDR encode/decode functions for PMAP
  */
-static int
-xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct rpc_portmap *map)
+static int xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct portmap_args *map)
 {
-	dprintk("RPC: xdr_encode_mapping(%d, %d, %d, %d)\n",
+	dprintk("RPC: xdr_encode_mapping(%u, %u, %u, %u)\n",
 		map->pm_prog, map->pm_vers, map->pm_prot, map->pm_port);
 	*p++ = htonl(map->pm_prog);
 	*p++ = htonl(map->pm_vers);
@@ -249,15 +313,13 @@ xdr_encode_mapping(struct rpc_rqst *req, u32 *p, struct rpc_portmap *map)
 	return 0;
 }
 
-static int
-xdr_decode_port(struct rpc_rqst *req, u32 *p, unsigned short *portp)
+static int xdr_decode_port(struct rpc_rqst *req, u32 *p, unsigned short *portp)
 {
 	*portp = (unsigned short) ntohl(*p++);
 	return 0;
 }
 
-static int
-xdr_decode_bool(struct rpc_rqst *req, u32 *p, unsigned int *boolp)
+static int xdr_decode_bool(struct rpc_rqst *req, u32 *p, unsigned int *boolp)
 {
 	*boolp = (unsigned int) ntohl(*p++);
 	return 0;

net/sunrpc/rpc_pipe.c

@@ -327,10 +327,8 @@ rpc_show_info(struct seq_file *m, void *v)
 	seq_printf(m, "RPC server: %s\n", clnt->cl_server);
 	seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_protname,
 			clnt->cl_prog, clnt->cl_vers);
-	seq_printf(m, "address: %u.%u.%u.%u\n",
-			NIPQUAD(clnt->cl_xprt->addr.sin_addr.s_addr));
-	seq_printf(m, "protocol: %s\n",
-			clnt->cl_xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
+	seq_printf(m, "address: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR));
+	seq_printf(m, "protocol: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PROTO));
 	return 0;
 }
 
@@ -623,17 +621,13 @@ __rpc_rmdir(struct inode *dir, struct dentry *dentry)
 }
 
 static struct dentry *
-rpc_lookup_negative(char *path, struct nameidata *nd)
+rpc_lookup_create(struct dentry *parent, const char *name, int len)
 {
+	struct inode *dir = parent->d_inode;
 	struct dentry *dentry;
-	struct inode *dir;
-	int error;
 
-	if ((error = rpc_lookup_parent(path, nd)) != 0)
-		return ERR_PTR(error);
-	dir = nd->dentry->d_inode;
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_one_len(nd->last.name, nd->dentry, nd->last.len);
+	dentry = lookup_one_len(name, parent, len);
 	if (IS_ERR(dentry))
 		goto out_err;
 	if (dentry->d_inode) {
@@ -644,7 +638,20 @@ rpc_lookup_negative(char *path, struct nameidata *nd)
 	return dentry;
 out_err:
 	mutex_unlock(&dir->i_mutex);
-	rpc_release_path(nd);
+	return dentry;
+}
+
+static struct dentry *
+rpc_lookup_negative(char *path, struct nameidata *nd)
+{
+	struct dentry *dentry;
+	int error;
+
+	if ((error = rpc_lookup_parent(path, nd)) != 0)
+		return ERR_PTR(error);
+	dentry = rpc_lookup_create(nd->dentry, nd->last.name, nd->last.len);
+	if (IS_ERR(dentry))
+		rpc_release_path(nd);
 	return dentry;
 }
 
@@ -703,18 +710,17 @@ rpc_rmdir(struct dentry *dentry)
 }
 
 struct dentry *
-rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags)
+rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags)
 {
-	struct nameidata nd;
 	struct dentry *dentry;
 	struct inode *dir, *inode;
 	struct rpc_inode *rpci;
 
-	dentry = rpc_lookup_negative(path, &nd);
+	dentry = rpc_lookup_create(parent, name, strlen(name));
 	if (IS_ERR(dentry))
 		return dentry;
-	dir = nd.dentry->d_inode;
-	inode = rpc_get_inode(dir->i_sb, S_IFSOCK | S_IRUSR | S_IWUSR);
+	dir = parent->d_inode;
+	inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR);
 	if (!inode)
 		goto err_dput;
 	inode->i_ino = iunique(dir->i_sb, 100);
@@ -728,13 +734,13 @@ rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags)
 	dget(dentry);
 out:
 	mutex_unlock(&dir->i_mutex);
-	rpc_release_path(&nd);
 	return dentry;
 err_dput:
 	dput(dentry);
 	dentry = ERR_PTR(-ENOMEM);
-	printk(KERN_WARNING "%s: %s() failed to create pipe %s (errno = %d)\n",
-			__FILE__, __FUNCTION__, path, -ENOMEM);
+	printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n",
+			__FILE__, __FUNCTION__, parent->d_name.name, name,
+			-ENOMEM);
 	goto out;
 }
 

net/sunrpc/sched.c

@@ -21,7 +21,6 @@
 #include <linux/mutex.h>
 
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
 
 #ifdef RPC_DEBUG
 #define RPCDBG_FACILITY		RPCDBG_SCHED
@@ -44,12 +43,6 @@ static void			__rpc_default_timer(struct rpc_task *task);
 static void			rpciod_killall(void);
 static void			rpc_async_schedule(void *);
 
-/*
- * RPC tasks that create another task (e.g. for contacting the portmapper)
- * will wait on this queue for their child's completion
- */
-static RPC_WAITQ(childq, "childq");
-
 /*
  * RPC tasks sit here while waiting for conditions to improve.
  */
@@ -323,16 +316,6 @@ static void rpc_make_runnable(struct rpc_task *task)
 		wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED);
 }
 
-/*
- * Place a newly initialized task on the workqueue.
- */
-static inline void
-rpc_schedule_run(struct rpc_task *task)
-{
-	rpc_set_active(task);
-	rpc_make_runnable(task);
-}
-
 /*
  * Prepare for sleeping on a wait queue.
  * By always appending tasks to the list we ensure FIFO behavior.
@@ -559,24 +542,20 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 	spin_unlock_bh(&queue->lock);
 }
 
+static void __rpc_atrun(struct rpc_task *task)
+{
+	rpc_wake_up_task(task);
+}
+
 /*
  * Run a task at a later time
  */
-static void	__rpc_atrun(struct rpc_task *);
-void
-rpc_delay(struct rpc_task *task, unsigned long delay)
+void rpc_delay(struct rpc_task *task, unsigned long delay)
 {
 	task->tk_timeout = delay;
 	rpc_sleep_on(&delay_queue, task, NULL, __rpc_atrun);
 }
 
-static void
-__rpc_atrun(struct rpc_task *task)
-{
-	task->tk_status = 0;
-	rpc_wake_up_task(task);
-}
-
 /*
  * Helper to call task->tk_ops->rpc_call_prepare
  */
@@ -933,72 +912,6 @@ struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags,
 }
 EXPORT_SYMBOL(rpc_run_task);
 
-/**
- * rpc_find_parent - find the parent of a child task.
- * @child: child task
- * @parent: parent task
- *
- * Checks that the parent task is still sleeping on the
- * queue 'childq'. If so returns a pointer to the parent.
- * Upon failure returns NULL.
- *
- * Caller must hold childq.lock
- */
-static inline struct rpc_task *rpc_find_parent(struct rpc_task *child, struct rpc_task *parent)
-{
-	struct rpc_task	*task;
-	struct list_head *le;
-
-	task_for_each(task, le, &childq.tasks[0])
-		if (task == parent)
-			return parent;
-
-	return NULL;
-}
-
-static void rpc_child_exit(struct rpc_task *child, void *calldata)
-{
-	struct rpc_task	*parent;
-
-	spin_lock_bh(&childq.lock);
-	if ((parent = rpc_find_parent(child, calldata)) != NULL) {
-		parent->tk_status = child->tk_status;
-		__rpc_wake_up_task(parent);
-	}
-	spin_unlock_bh(&childq.lock);
-}
-
-static const struct rpc_call_ops rpc_child_ops = {
-	.rpc_call_done = rpc_child_exit,
-};
-
-/*
- * Note: rpc_new_task releases the client after a failure.
- */
-struct rpc_task *
-rpc_new_child(struct rpc_clnt *clnt, struct rpc_task *parent)
-{
-	struct rpc_task	*task;
-
-	task = rpc_new_task(clnt, RPC_TASK_ASYNC | RPC_TASK_CHILD, &rpc_child_ops, parent);
-	if (!task)
-		goto fail;
-	return task;
-
-fail:
-	parent->tk_status = -ENOMEM;
-	return NULL;
-}
-
-void rpc_run_child(struct rpc_task *task, struct rpc_task *child, rpc_action func)
-{
-	spin_lock_bh(&childq.lock);
-	/* N.B. Is it possible for the child to have already finished? */
-	__rpc_sleep_on(&childq, task, func, NULL);
-	rpc_schedule_run(child);
-	spin_unlock_bh(&childq.lock);
-}
-
 /*
  * Kill all tasks for the given client.
  * XXX: kill their descendants as well?

net/sunrpc/sunrpc_syms.c

@@ -36,8 +36,6 @@ EXPORT_SYMBOL(rpc_wake_up_status);
 EXPORT_SYMBOL(rpc_release_task);
 
 /* RPC client functions */
-EXPORT_SYMBOL(rpc_create_client);
-EXPORT_SYMBOL(rpc_new_client);
 EXPORT_SYMBOL(rpc_clone_client);
 EXPORT_SYMBOL(rpc_bind_new_program);
 EXPORT_SYMBOL(rpc_destroy_client);
@@ -57,7 +55,6 @@ EXPORT_SYMBOL(rpc_queue_upcall);
 EXPORT_SYMBOL(rpc_mkpipe);
 
 /* Client transport */
-EXPORT_SYMBOL(xprt_create_proto);
 EXPORT_SYMBOL(xprt_set_timeout);
 
 /* Client credential cache */

net/sunrpc/timer.c

@@ -19,8 +19,6 @@
 #include <linux/unistd.h>
 
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
-#include <linux/sunrpc/timer.h>
 
 #define RPC_RTO_MAX (60*HZ)
 #define RPC_RTO_INIT (HZ/5)

net/sunrpc/xprt.c

@@ -534,7 +534,7 @@ void xprt_connect(struct rpc_task *task)
 	dprintk("RPC: %4d xprt_connect xprt %p %s connected\n", task->tk_pid,
 			xprt, (xprt_connected(xprt) ? "is" : "is not"));
 
-	if (!xprt->addr.sin_port) {
+	if (!xprt_bound(xprt)) {
 		task->tk_status = -EIO;
 		return;
 	}
@@ -585,13 +585,6 @@ static void xprt_connect_status(struct rpc_task *task)
 				task->tk_pid, -task->tk_status, task->tk_client->cl_server);
 		xprt_release_write(xprt, task);
 		task->tk_status = -EIO;
-		return;
-	}
-
-	/* if soft mounted, just cause this RPC to fail */
-	if (RPC_IS_SOFT(task)) {
-		xprt_release_write(xprt, task);
-		task->tk_status = -EIO;
 	}
 }
 
@@ -829,6 +822,7 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt)
 	req->rq_bufsize = 0;
 	req->rq_xid     = xprt_alloc_xid(xprt);
 	req->rq_release_snd_buf = NULL;
+	xprt_reset_majortimeo(req);
 	dprintk("RPC: %4d reserved req %p xid %08x\n", task->tk_pid,
 			req, ntohl(req->rq_xid));
 }
@@ -887,16 +881,32 @@ void xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long i
 	to->to_exponential = 0;
 }
 
-static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc_timeout *to)
+/**
+ * xprt_create_transport - create an RPC transport
+ * @proto: requested transport protocol
+ * @ap: remote peer address
+ * @size: length of address
+ * @to: timeout parameters
+ *
+ */
+struct rpc_xprt *xprt_create_transport(int proto, struct sockaddr *ap, size_t size, struct rpc_timeout *to)
 {
 	int result;
 	struct rpc_xprt	*xprt;
 	struct rpc_rqst	*req;
 
-	if ((xprt = kzalloc(sizeof(struct rpc_xprt), GFP_KERNEL)) == NULL)
+	if ((xprt = kzalloc(sizeof(struct rpc_xprt), GFP_KERNEL)) == NULL) {
+		dprintk("RPC:      xprt_create_transport: no memory\n");
 		return ERR_PTR(-ENOMEM);
-
-	xprt->addr = *ap;
+	}
+	if (size <= sizeof(xprt->addr)) {
+		memcpy(&xprt->addr, ap, size);
+		xprt->addrlen = size;
+	} else {
+		kfree(xprt);
+		dprintk("RPC:      xprt_create_transport: address too large\n");
+		return ERR_PTR(-EBADF);
+	}
 
 	switch (proto) {
 	case IPPROTO_UDP:
@@ -908,14 +918,15 @@ static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc
 	default:
 		printk(KERN_ERR "RPC: unrecognized transport protocol: %d\n",
 				proto);
-		result = -EIO;
-		break;
+		return ERR_PTR(-EIO);
 	}
 	if (result) {
 		kfree(xprt);
+		dprintk("RPC:      xprt_create_transport: failed, %d\n", result);
 		return ERR_PTR(result);
 	}
 
+	kref_init(&xprt->kref);
 	spin_lock_init(&xprt->transport_lock);
 	spin_lock_init(&xprt->reserve_lock);
 
@@ -928,6 +939,7 @@ static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc
 	xprt->last_used = jiffies;
 	xprt->cwnd = RPC_INITCWND;
 
+	rpc_init_wait_queue(&xprt->binding, "xprt_binding");
 	rpc_init_wait_queue(&xprt->pending, "xprt_pending");
 	rpc_init_wait_queue(&xprt->sending, "xprt_sending");
 	rpc_init_wait_queue(&xprt->resend, "xprt_resend");
@@ -941,41 +953,43 @@ static struct rpc_xprt *xprt_setup(int proto, struct sockaddr_in *ap, struct rpc
 
 	dprintk("RPC:      created transport %p with %u slots\n", xprt,
 			xprt->max_reqs);
-	
-	return xprt;
-}
 
-/**
- * xprt_create_proto - create an RPC client transport
- * @proto: requested transport protocol
- * @sap: remote peer's address
- * @to: timeout parameters for new transport
- *
- */
-struct rpc_xprt *xprt_create_proto(int proto, struct sockaddr_in *sap, struct rpc_timeout *to)
-{
-	struct rpc_xprt	*xprt;
-
-	xprt = xprt_setup(proto, sap, to);
-	if (IS_ERR(xprt))
-		dprintk("RPC:      xprt_create_proto failed\n");
-	else
-		dprintk("RPC:      xprt_create_proto created xprt %p\n", xprt);
 	return xprt;
 }
 
 /**
  * xprt_destroy - destroy an RPC transport, killing off all requests.
- * @xprt: transport to destroy
+ * @kref: kref for the transport to destroy
  *
  */
-int xprt_destroy(struct rpc_xprt *xprt)
+static void xprt_destroy(struct kref *kref)
 {
+	struct rpc_xprt *xprt = container_of(kref, struct rpc_xprt, kref);
+
 	dprintk("RPC:      destroying transport %p\n", xprt);
 	xprt->shutdown = 1;
 	del_timer_sync(&xprt->timer);
 	xprt->ops->destroy(xprt);
 	kfree(xprt);
+}
 
-	return 0;
+/**
+ * xprt_put - release a reference to an RPC transport.
+ * @xprt: pointer to the transport
+ *
+ */
+void xprt_put(struct rpc_xprt *xprt)
+{
+	kref_put(&xprt->kref, xprt_destroy);
+}
+
+/**
+ * xprt_get - return a reference to an RPC transport.
+ * @xprt: pointer to the transport
+ *
+ */
+struct rpc_xprt *xprt_get(struct rpc_xprt *xprt)
+{
+	kref_get(&xprt->kref);
+	return xprt;
 }

net/sunrpc/xprtsock.c

@@ -125,6 +125,47 @@ static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)
 }
 #endif
 
+static void xs_format_peer_addresses(struct rpc_xprt *xprt)
+{
+	struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
+	char *buf;
+
+	buf = kzalloc(20, GFP_KERNEL);
+	if (buf) {
+		snprintf(buf, 20, "%u.%u.%u.%u",
+				NIPQUAD(addr->sin_addr.s_addr));
+	}
+	xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
+
+	buf = kzalloc(8, GFP_KERNEL);
+	if (buf) {
+		snprintf(buf, 8, "%u",
+				ntohs(addr->sin_port));
+	}
+	xprt->address_strings[RPC_DISPLAY_PORT] = buf;
+
+	if (xprt->prot == IPPROTO_UDP)
+		xprt->address_strings[RPC_DISPLAY_PROTO] = "udp";
+	else
+		xprt->address_strings[RPC_DISPLAY_PROTO] = "tcp";
+
+	buf = kzalloc(48, GFP_KERNEL);
+	if (buf) {
+		snprintf(buf, 48, "addr=%u.%u.%u.%u port=%u proto=%s",
+			NIPQUAD(addr->sin_addr.s_addr),
+			ntohs(addr->sin_port),
+			xprt->prot == IPPROTO_UDP ? "udp" : "tcp");
+	}
+	xprt->address_strings[RPC_DISPLAY_ALL] = buf;
+}
+
+static void xs_free_peer_addresses(struct rpc_xprt *xprt)
+{
+	kfree(xprt->address_strings[RPC_DISPLAY_ADDR]);
+	kfree(xprt->address_strings[RPC_DISPLAY_PORT]);
+	kfree(xprt->address_strings[RPC_DISPLAY_ALL]);
+}
+
 #define XS_SENDMSG_FLAGS	(MSG_DONTWAIT | MSG_NOSIGNAL)
 
 static inline int xs_send_head(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, unsigned int len)
@@ -295,7 +336,7 @@ static int xs_udp_send_request(struct rpc_task *task)
 
 	req->rq_xtime = jiffies;
 	status = xs_sendpages(xprt->sock, (struct sockaddr *) &xprt->addr,
-				sizeof(xprt->addr), xdr, req->rq_bytes_sent);
+				xprt->addrlen, xdr, req->rq_bytes_sent);
 
 	dprintk("RPC:      xs_udp_send_request(%u) = %d\n",
 			xdr->len - req->rq_bytes_sent, status);
@@ -485,6 +526,7 @@ static void xs_destroy(struct rpc_xprt *xprt)
 
 	xprt_disconnect(xprt);
 	xs_close(xprt);
+	xs_free_peer_addresses(xprt);
 	kfree(xprt->slot);
 }
 
@@ -959,6 +1001,19 @@ static unsigned short xs_get_random_port(void)
 	return rand + xprt_min_resvport;
 }
 
+/**
+ * xs_print_peer_address - format an IPv4 address for printing
+ * @xprt: generic transport
+ * @format: flags field indicating which parts of the address to render
+ */
+static char *xs_print_peer_address(struct rpc_xprt *xprt, enum rpc_display_format_t format)
+{
+	if (xprt->address_strings[format] != NULL)
+		return xprt->address_strings[format];
+	else
+		return "unprintable";
+}
+
 /**
  * xs_set_port - reset the port number in the remote endpoint address
  * @xprt: generic transport
@@ -967,8 +1022,11 @@ static unsigned short xs_get_random_port(void)
  */
 static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
 {
+	struct sockaddr_in *sap = (struct sockaddr_in *) &xprt->addr;
+
 	dprintk("RPC:      setting port for xprt %p to %u\n", xprt, port);
-	xprt->addr.sin_port = htons(port);
+
+	sap->sin_port = htons(port);
 }
 
 static int xs_bindresvport(struct rpc_xprt *xprt, struct socket *sock)
@@ -1011,11 +1069,9 @@ static void xs_udp_connect_worker(void *args)
 	struct socket *sock = xprt->sock;
 	int err, status = -EIO;
 
-	if (xprt->shutdown || xprt->addr.sin_port == 0)
+	if (xprt->shutdown || !xprt_bound(xprt))
 		goto out;
 
-	dprintk("RPC:      xs_udp_connect_worker for xprt %p\n", xprt);
-
 	/* Start by resetting any existing state */
 	xs_close(xprt);
 
@@ -1029,6 +1085,9 @@ static void xs_udp_connect_worker(void *args)
 		goto out;
 	}
 
+	dprintk("RPC:      worker connecting xprt %p to address: %s\n",
+			xprt, xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
 	if (!xprt->inet) {
 		struct sock *sk = sock->sk;
 
@@ -1094,11 +1153,9 @@ static void xs_tcp_connect_worker(void *args)
 	struct socket *sock = xprt->sock;
 	int err, status = -EIO;
 
-	if (xprt->shutdown || xprt->addr.sin_port == 0)
+	if (xprt->shutdown || !xprt_bound(xprt))
 		goto out;
 
-	dprintk("RPC:      xs_tcp_connect_worker for xprt %p\n", xprt);
-
 	if (!xprt->sock) {
 		/* start from scratch */
 		if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
@@ -1114,6 +1171,9 @@ static void xs_tcp_connect_worker(void *args)
 		/* "close" the socket, preserving the local port */
 		xs_tcp_reuse_connection(xprt);
 
+	dprintk("RPC:      worker connecting xprt %p to address: %s\n",
+			xprt, xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
 	if (!xprt->inet) {
 		struct sock *sk = sock->sk;
 
@@ -1147,7 +1207,7 @@ static void xs_tcp_connect_worker(void *args)
 	xprt->stat.connect_count++;
 	xprt->stat.connect_start = jiffies;
 	status = kernel_connect(sock, (struct sockaddr *) &xprt->addr,
-			sizeof(xprt->addr), O_NONBLOCK);
+			xprt->addrlen, O_NONBLOCK);
 	dprintk("RPC: %p  connect status %d connected %d sock state %d\n",
 			xprt, -status, xprt_connected(xprt), sock->sk->sk_state);
 	if (status < 0) {
@@ -1255,8 +1315,10 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 
 static struct rpc_xprt_ops xs_udp_ops = {
 	.set_buffer_size	= xs_udp_set_buffer_size,
+	.print_addr		= xs_print_peer_address,
 	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong,
+	.rpcbind		= rpc_getport,
 	.set_port		= xs_set_port,
 	.connect		= xs_connect,
 	.buf_alloc		= rpc_malloc,
@@ -1271,8 +1333,10 @@ static struct rpc_xprt_ops xs_udp_ops = {
 };
 
 static struct rpc_xprt_ops xs_tcp_ops = {
+	.print_addr		= xs_print_peer_address,
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xs_tcp_release_xprt,
+	.rpcbind		= rpc_getport,
 	.set_port		= xs_set_port,
 	.connect		= xs_connect,
 	.buf_alloc		= rpc_malloc,
@@ -1293,8 +1357,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 {
 	size_t slot_table_size;
-
-	dprintk("RPC:      setting up udp-ipv4 transport...\n");
+	struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
 
 	xprt->max_reqs = xprt_udp_slot_table_entries;
 	slot_table_size = xprt->max_reqs * sizeof(xprt->slot[0]);
@@ -1302,10 +1365,12 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 	if (xprt->slot == NULL)
 		return -ENOMEM;
 
-	xprt->prot = IPPROTO_UDP;
+	if (ntohs(addr->sin_port != 0))
+		xprt_set_bound(xprt);
 	xprt->port = xs_get_random_port();
+
+	xprt->prot = IPPROTO_UDP;
 	xprt->tsh_size = 0;
-	xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0;
 	/* XXX: header size can vary due to auth type, IPv6, etc. */
 	xprt->max_payload = (1U << 16) - (MAX_HEADER << 3);
 
@@ -1322,6 +1387,10 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 	else
 		xprt_set_timeout(&xprt->timeout, 5, 5 * HZ);
 
+	xs_format_peer_addresses(xprt);
+	dprintk("RPC:      set up transport to address %s\n",
+			xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
 	return 0;
 }
 
@@ -1334,8 +1403,7 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 {
 	size_t slot_table_size;
-
-	dprintk("RPC:      setting up tcp-ipv4 transport...\n");
+	struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
 
 	xprt->max_reqs = xprt_tcp_slot_table_entries;
 	slot_table_size = xprt->max_reqs * sizeof(xprt->slot[0]);
@@ -1343,10 +1411,12 @@ int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 	if (xprt->slot == NULL)
 		return -ENOMEM;
 
-	xprt->prot = IPPROTO_TCP;
+	if (ntohs(addr->sin_port) != 0)
+		xprt_set_bound(xprt);
 	xprt->port = xs_get_random_port();
+
+	xprt->prot = IPPROTO_TCP;
 	xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
-	xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0;
 	xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
 
 	INIT_WORK(&xprt->connect_worker, xs_tcp_connect_worker, xprt);
@@ -1362,5 +1432,9 @@ int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
 	else
 		xprt_set_timeout(&xprt->timeout, 2, 60 * HZ);
 
+	xs_format_peer_addresses(xprt);
+	dprintk("RPC:      set up transport to address %s\n",
+			xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+
 	return 0;
 }