Merge branch 'nfs-for-2.6.37' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* 'nfs-for-2.6.37' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (67 commits)
  SUNRPC: Cleanup duplicate assignment in rpcauth_refreshcred
  nfs: fix unchecked value
  Ask for time_delta during fsinfo probe
  Revalidate caches on lock
  SUNRPC: After calling xprt_release(), we must restart from call_reserve
  NFSv4: Fix up the 'dircount' hint in encode_readdir
  NFSv4: Clean up nfs4_decode_dirent
  NFSv4: nfs4_decode_dirent must clear entry->fattr->valid
  NFSv4: Fix a regression in decode_getfattr
  NFSv4: Fix up decode_attr_filehandle() to handle the case of empty fh pointer
  NFS: Ensure we check all allocation return values in new readdir code
  NFS: Readdir plus in v4
  NFS: introduce generic decode_getattr function
  NFS: check xdr_decode for errors
  NFS: nfs_readdir_filler catch all errors
  NFS: readdir with vmapped pages
  NFS: remove page size checking code
  NFS: decode_dirent should use an xdr_stream
  SUNRPC: Add a helper function xdr_inline_peek
  NFS: remove readdir plus limit
  ...

Documentation/filesystems/nfs/00-INDEX

@@ -14,3 +14,5 @@ nfsroot.txt
 	- short guide on setting up a diskless box with NFS root filesystem.
 rpc-cache.txt
 	- introduction to the caching mechanisms in the sunrpc layer.
+idmapper.txt
+	- information for configuring request-keys to be used by idmapper

Documentation/filesystems/nfs/idmapper.txt

+
+=========
+ID Mapper
+=========
+Id mapper is used by NFS to translate user and group ids into names, and to
+translate user and group names into ids.  Part of this translation involves
+performing an upcall to userspace to request the information.  Id mapper will
+user request-key to perform this upcall and cache the result.  The program
+/usr/sbin/nfs.upcall should be called by request-key, and will perform the
+translation and initialize a key with the resulting information.
+
+ NFS_USE_NEW_IDMAPPER must be selected when configuring the kernel to use this
+ feature.
+
+===========
+Configuring
+===========
+The file /etc/request-key.conf will need to be modified so /sbin/request-key can
+direct the upcall.  The following line should be added:
+
+#OP	TYPE	DESCRIPTION	CALLOUT INFO	PROGRAM ARG1 ARG2 ARG3 ...
+#======	=======	===============	===============	===============================
+create	id_resolver	*	*		/usr/sbin/nfs.upcall %k %d 600
+
+This will direct all id_resolver requests to the program /usr/sbin/nfs.upcall.
+The last parameter, 600, defines how many seconds into the future the key will
+expire.  This parameter is optional for /usr/sbin/nfs.upcall.  When the timeout
+is not specified, nfs.upcall will default to 600 seconds.
+
+id mapper uses for key descriptions:
+	  uid:  Find the UID for the given user
+	  gid:  Find the GID for the given group
+	 user:  Find the user  name for the given UID
+	group:  Find the group name for the given GID
+
+You can handle any of these individually, rather than using the generic upcall
+program.  If you would like to use your own program for a uid lookup then you
+would edit your request-key.conf so it look similar to this:
+
+#OP	TYPE	DESCRIPTION	CALLOUT INFO	PROGRAM ARG1 ARG2 ARG3 ...
+#======	=======	===============	===============	===============================
+create	id_resolver	uid:*	*		/some/other/program  %k %d 600
+create	id_resolver	*	*		/usr/sbin/nfs.upcall %k %d 600
+
+Notice that the new line was added above the line for the generic program.
+request-key will find the first matching line and corresponding program.  In
+this case, /some/other/program will handle all uid lookups and
+/usr/sbin/nfs.upcall will handle gid, user, and group lookups.
+
+See <file:Documentation/keys-request-keys.txt> for more information about the
+request-key function.
+
+
+==========
+nfs.upcall
+==========
+nfs.upcall is designed to be called by request-key, and should not be run "by
+hand".  This program takes two arguments, a serialized key and a key
+description.  The serialized key is first converted into a key_serial_t, and
+then passed as an argument to keyctl_instantiate (both are part of keyutils.h).
+
+The actual lookups are performed by functions found in nfsidmap.h.  nfs.upcall
+determines the correct function to call by looking at the first part of the
+description string.  For example, a uid lookup description will appear as
+"uid:user@domain".
+
+nfs.upcall will return 0 if the key was instantiated, and non-zero otherwise.

Documentation/filesystems/nfs/nfsroot.txt

@@ -159,6 +159,28 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>
                 Default: any
 
 
+nfsrootdebug
+
+  This parameter enables debugging messages to appear in the kernel
+  log at boot time so that administrators can verify that the correct
+  NFS mount options, server address, and root path are passed to the
+  NFS client.
+
+
+rdinit=<executable file>
+
+  To specify which file contains the program that starts system
+  initialization, administrators can use this command line parameter.
+  The default value of this parameter is "/init".  If the specified
+  file exists and the kernel can execute it, root filesystem related
+  kernel command line parameters, including `nfsroot=', are ignored.
+
+  A description of the process of mounting the root file system can be
+  found in:
+
+    Documentation/early-userspace/README
+
+
 
 
 3.) Boot Loader

Documentation/kernel-parameters.txt

@@ -1541,12 +1541,15 @@ and is between 256 and 4096 characters. It is defined in the file
 			1 to enable accounting
 			Default value is 0.
 
-	nfsaddrs=	[NFS]
+	nfsaddrs=	[NFS] Deprecated.  Use ip= instead.
 			See Documentation/filesystems/nfs/nfsroot.txt.
 
 	nfsroot=	[NFS] nfs root filesystem for disk-less boxes.
 			See Documentation/filesystems/nfs/nfsroot.txt.
 
+	nfsrootdebug	[NFS] enable nfsroot debugging messages.
+			See Documentation/filesystems/nfs/nfsroot.txt.
+
 	nfs.callback_tcpport=
 			[NFS] set the TCP port on which the NFSv4 callback
 			channel should listen.

fs/lockd/clntlock.c

@@ -42,6 +42,7 @@ struct nlm_wait {
 };
 
 static LIST_HEAD(nlm_blocked);
+static DEFINE_SPINLOCK(nlm_blocked_lock);
 
 /**
  * nlmclnt_init - Set up per-NFS mount point lockd data structures
@@ -97,7 +98,10 @@ struct nlm_wait *nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *
 		block->b_lock = fl;
 		init_waitqueue_head(&block->b_wait);
 		block->b_status = nlm_lck_blocked;
+
+		spin_lock(&nlm_blocked_lock);
 		list_add(&block->b_list, &nlm_blocked);
+		spin_unlock(&nlm_blocked_lock);
 	}
 	return block;
 }
@@ -106,7 +110,9 @@ void nlmclnt_finish_block(struct nlm_wait *block)
 {
 	if (block == NULL)
 		return;
+	spin_lock(&nlm_blocked_lock);
 	list_del(&block->b_list);
+	spin_unlock(&nlm_blocked_lock);
 	kfree(block);
 }
 
@@ -154,6 +160,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 	 * Look up blocked request based on arguments. 
 	 * Warning: must not use cookie to match it!
 	 */
+	spin_lock(&nlm_blocked_lock);
 	list_for_each_entry(block, &nlm_blocked, b_list) {
 		struct file_lock *fl_blocked = block->b_lock;
 
@@ -178,6 +185,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 		wake_up(&block->b_wait);
 		res = nlm_granted;
 	}
+	spin_unlock(&nlm_blocked_lock);
 	return res;
 }
 
@@ -216,10 +224,6 @@ reclaimer(void *ptr)
 	allow_signal(SIGKILL);
 
 	down_write(&host->h_rwsem);
-
-	/* This one ensures that our parent doesn't terminate while the
-	 * reclaim is in progress */
-	lock_kernel();
 	lockd_up();	/* note: this cannot fail as lockd is already running */
 
 	dprintk("lockd: reclaiming locks for host %s\n", host->h_name);
@@ -260,16 +264,17 @@ reclaimer(void *ptr)
 	dprintk("NLM: done reclaiming locks for host %s\n", host->h_name);
 
 	/* Now, wake up all processes that sleep on a blocked lock */
+	spin_lock(&nlm_blocked_lock);
 	list_for_each_entry(block, &nlm_blocked, b_list) {
 		if (block->b_host == host) {
 			block->b_status = nlm_lck_denied_grace_period;
 			wake_up(&block->b_wait);
 		}
 	}
+	spin_unlock(&nlm_blocked_lock);
 
 	/* Release host handle after use */
 	nlm_release_host(host);
 	lockd_down();
-	unlock_kernel();
 	return 0;
 }

fs/lockd/clntproc.c

@@ -166,7 +166,6 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 	/* Set up the argument struct */
 	nlmclnt_setlockargs(call, fl);
 
-	lock_kernel();
 	if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
 		if (fl->fl_type != F_UNLCK) {
 			call->a_args.block = IS_SETLKW(cmd) ? 1 : 0;
@@ -177,10 +176,8 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 		status = nlmclnt_test(call, fl);
 	else
 		status = -EINVAL;
-
 	fl->fl_ops->fl_release_private(fl);
 	fl->fl_ops = NULL;
-	unlock_kernel();
 
 	dprintk("lockd: clnt proc returns %d\n", status);
 	return status;
@@ -226,9 +223,7 @@ void nlm_release_call(struct nlm_rqst *call)
 
 static void nlmclnt_rpc_release(void *data)
 {
-	lock_kernel();
 	nlm_release_call(data);
-	unlock_kernel();
 }
 
 static int nlm_wait_on_grace(wait_queue_head_t *queue)
@@ -448,14 +443,18 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl)
 
 static void nlmclnt_locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
+	spin_lock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 	new->fl_u.nfs_fl.state = fl->fl_u.nfs_fl.state;
 	new->fl_u.nfs_fl.owner = nlm_get_lockowner(fl->fl_u.nfs_fl.owner);
 	list_add_tail(&new->fl_u.nfs_fl.list, &fl->fl_u.nfs_fl.owner->host->h_granted);
+	spin_unlock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 }
 
 static void nlmclnt_locks_release_private(struct file_lock *fl)
 {
+	spin_lock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 	list_del(&fl->fl_u.nfs_fl.list);
+	spin_unlock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 	nlm_put_lockowner(fl->fl_u.nfs_fl.owner);
 }
 
@@ -721,9 +720,7 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 die:
 	return;
  retry_rebind:
-	lock_kernel();
 	nlm_rebind_host(req->a_host);
-	unlock_kernel();
  retry_unlock:
 	rpc_restart_call(task);
 }
@@ -801,9 +798,7 @@ static void nlmclnt_cancel_callback(struct rpc_task *task, void *data)
 	/* Don't ever retry more than 3 times */
 	if (req->a_retries++ >= NLMCLNT_MAX_RETRIES)
 		goto die;
-	lock_kernel();
 	nlm_rebind_host(req->a_host);
-	unlock_kernel();
 	rpc_restart_call(task);
 	rpc_delay(task, 30 * HZ);
 }

fs/nfs/Kconfig

@@ -118,3 +118,14 @@ config NFS_USE_KERNEL_DNS
 	select DNS_RESOLVER
 	select KEYS
 	default y
+
+config NFS_USE_NEW_IDMAPPER
+	bool "Use the new idmapper upcall routine"
+	depends on NFS_V4 && KEYS
+	help
+	  Say Y here if you want NFS to use the new idmapper upcall functions.
+	  You will need /sbin/request-key (usually provided by the keyutils
+	  package).  For details, read
+	  <file:Documentation/filesystems/nfs/idmapper.txt>.
+
+	  If you are unsure, say N.

fs/nfs/client.c

@@ -635,7 +635,8 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
  */
 static void nfs_destroy_server(struct nfs_server *server)
 {
-	if (!(server->flags & NFS_MOUNT_NONLM))
+	if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) ||
+			!(server->flags & NFS_MOUNT_LOCAL_FCNTL))
 		nlmclnt_done(server->nlm_host);
 }
 
@@ -657,7 +658,8 @@ static int nfs_start_lockd(struct nfs_server *server)
 
 	if (nlm_init.nfs_version > 3)
 		return 0;
-	if (server->flags & NFS_MOUNT_NONLM)
+	if ((server->flags & NFS_MOUNT_LOCAL_FLOCK) &&
+			(server->flags & NFS_MOUNT_LOCAL_FCNTL))
 		return 0;
 
 	switch (clp->cl_proto) {
@@ -901,8 +903,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 	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 > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES)
+		server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES;
 	if (server->dtsize > server->rsize)
 		server->dtsize = server->rsize;
 
@@ -913,6 +915,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 
 	server->maxfilesize = fsinfo->maxfilesize;
 
+	server->time_delta = fsinfo->time_delta;
+
 	/* We're airborne Set socket buffersize */
 	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
 }
@@ -1356,8 +1360,9 @@ static int nfs4_init_server(struct nfs_server *server,
 
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|
-		NFS_CAP_POSIX_LOCK;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
 	server->options = data->options;
 
 	/* Get a client record */

fs/nfs/file.c

@@ -551,7 +551,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct file *filp = vma->vm_file;
 	struct dentry *dentry = filp->f_path.dentry;
 	unsigned pagelen;
-	int ret = -EINVAL;
+	int ret = VM_FAULT_NOPAGE;
 	struct address_space *mapping;
 
 	dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n",
@@ -567,21 +567,20 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (mapping != dentry->d_inode->i_mapping)
 		goto out_unlock;
 
-	ret = 0;
 	pagelen = nfs_page_length(page);
 	if (pagelen == 0)
 		goto out_unlock;
 
-	ret = nfs_flush_incompatible(filp, page);
-	if (ret != 0)
-		goto out_unlock;
+	ret = VM_FAULT_LOCKED;
+	if (nfs_flush_incompatible(filp, page) == 0 &&
+	    nfs_updatepage(filp, page, 0, pagelen) == 0)
+		goto out;
 
-	ret = nfs_updatepage(filp, page, 0, pagelen);
+	ret = VM_FAULT_SIGBUS;
 out_unlock:
-	if (!ret)
-		return VM_FAULT_LOCKED;
 	unlock_page(page);
-	return VM_FAULT_SIGBUS;
+out:
+	return ret;
 }
 
 static const struct vm_operations_struct nfs_file_vm_ops = {
@@ -684,7 +683,8 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
 	return ret;
 }
 
-static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
+static int
+do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int status = 0;
@@ -699,7 +699,7 @@ static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
 	if (nfs_have_delegation(inode, FMODE_READ))
 		goto out_noconflict;
 
-	if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)
+	if (is_local)
 		goto out_noconflict;
 
 	status = NFS_PROTO(inode)->lock(filp, cmd, fl);
@@ -726,7 +726,8 @@ static int do_vfs_lock(struct file *file, struct file_lock *fl)
 	return res;
 }
 
-static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
+static int
+do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int status;
@@ -741,15 +742,24 @@ static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
 	 * 	If we're signalled while cleaning up locks on process exit, we
 	 * 	still need to complete the unlock.
 	 */
-	/* Use local locking if mounted with "-onolock" */
-	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+	/*
+	 * Use local locking if mounted with "-onolock" or with appropriate
+	 * "-olocal_lock="
+	 */
+	if (!is_local)
 		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
 	else
 		status = do_vfs_lock(filp, fl);
 	return status;
 }
 
-static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
+static int
+is_time_granular(struct timespec *ts) {
+	return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000));
+}
+
+static int
+do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int status;
@@ -762,20 +772,31 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
 	if (status != 0)
 		goto out;
 
-	/* Use local locking if mounted with "-onolock" */
-	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+	/*
+	 * Use local locking if mounted with "-onolock" or with appropriate
+	 * "-olocal_lock="
+	 */
+	if (!is_local)
 		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
 	else
 		status = do_vfs_lock(filp, fl);
 	if (status < 0)
 		goto out;
+
 	/*
-	 * Make sure we clear the cache whenever we try to get the lock.
+	 * Revalidate the cache if the server has time stamps granular
+	 * enough to detect subsecond changes.  Otherwise, clear the
+	 * cache to prevent missing any changes.
+	 *
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	if (!nfs_have_delegation(inode, FMODE_READ))
-		nfs_zap_caches(inode);
+	if (!nfs_have_delegation(inode, FMODE_READ)) {
+		if (is_time_granular(&NFS_SERVER(inode)->time_delta))
+			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
+		else
+			nfs_zap_caches(inode);
+	}
 out:
 	return status;
 }
@@ -787,6 +808,7 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int ret = -ENOLCK;
+	int is_local = 0;
 
 	dprintk("NFS: lock(%s/%s, t=%x, fl=%x, r=%lld:%lld)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
@@ -800,6 +822,9 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
 		goto out_err;
 
+	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
+		is_local = 1;
+
 	if (NFS_PROTO(inode)->lock_check_bounds != NULL) {
 		ret = NFS_PROTO(inode)->lock_check_bounds(fl);
 		if (ret < 0)
@@ -807,11 +832,11 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	}
 
 	if (IS_GETLK(cmd))
-		ret = do_getlk(filp, cmd, fl);
+		ret = do_getlk(filp, cmd, fl, is_local);
 	else if (fl->fl_type == F_UNLCK)
-		ret = do_unlk(filp, cmd, fl);
+		ret = do_unlk(filp, cmd, fl, is_local);
 	else
-		ret = do_setlk(filp, cmd, fl);
+		ret = do_setlk(filp, cmd, fl, is_local);
 out_err:
 	return ret;
 }
@@ -821,6 +846,9 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
  */
 static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 {
+	struct inode *inode = filp->f_mapping->host;
+	int is_local = 0;
+
 	dprintk("NFS: flock(%s/%s, t=%x, fl=%x)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
 			filp->f_path.dentry->d_name.name,
@@ -829,14 +857,17 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 
+	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
+		is_local = 1;
+
 	/* We're simulating flock() locks using posix locks on the server */
 	fl->fl_owner = (fl_owner_t)filp;
 	fl->fl_start = 0;
 	fl->fl_end = OFFSET_MAX;
 
 	if (fl->fl_type == F_UNLCK)
-		return do_unlk(filp, cmd, fl);
-	return do_setlk(filp, cmd, fl);
+		return do_unlk(filp, cmd, fl, is_local);
+	return do_setlk(filp, cmd, fl, is_local);
 }
 
 /*

fs/nfs/idmap.c

@@ -34,6 +34,212 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#ifdef CONFIG_NFS_USE_NEW_IDMAPPER
+
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/nfs_idmap.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include <keys/user-type.h>
+
+#define NFS_UINT_MAXLEN 11
+
+const struct cred *id_resolver_cache;
+
+struct key_type key_type_id_resolver = {
+	.name		= "id_resolver",
+	.instantiate	= user_instantiate,
+	.match		= user_match,
+	.revoke		= user_revoke,
+	.destroy	= user_destroy,
+	.describe	= user_describe,
+	.read		= user_read,
+};
+
+int nfs_idmap_init(void)
+{
+	struct cred *cred;
+	struct key *keyring;
+	int ret = 0;
+
+	printk(KERN_NOTICE "Registering the %s key type\n", key_type_id_resolver.name);
+
+	cred = prepare_kernel_cred(NULL);
+	if (!cred)
+		return -ENOMEM;
+
+	keyring = key_alloc(&key_type_keyring, ".id_resolver", 0, 0, cred,
+			     (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+			     KEY_USR_VIEW | KEY_USR_READ,
+			     KEY_ALLOC_NOT_IN_QUOTA);
+	if (IS_ERR(keyring)) {
+		ret = PTR_ERR(keyring);
+		goto failed_put_cred;
+	}
+
+	ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL);
+	if (ret < 0)
+		goto failed_put_key;
+
+	ret = register_key_type(&key_type_id_resolver);
+	if (ret < 0)
+		goto failed_put_key;
+
+	cred->thread_keyring = keyring;
+	cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+	id_resolver_cache = cred;
+	return 0;
+
+failed_put_key:
+	key_put(keyring);
+failed_put_cred:
+	put_cred(cred);
+	return ret;
+}
+
+void nfs_idmap_quit(void)
+{
+	key_revoke(id_resolver_cache->thread_keyring);
+	unregister_key_type(&key_type_id_resolver);
+	put_cred(id_resolver_cache);
+}
+
+/*
+ * Assemble the description to pass to request_key()
+ * This function will allocate a new string and update dest to point
+ * at it.  The caller is responsible for freeing dest.
+ *
+ * On error 0 is returned.  Otherwise, the length of dest is returned.
+ */
+static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen,
+				const char *type, size_t typelen, char **desc)
+{
+	char *cp;
+	size_t desclen = typelen + namelen + 2;
+
+	*desc = kmalloc(desclen, GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	cp = *desc;
+	memcpy(cp, type, typelen);
+	cp += typelen;
+	*cp++ = ':';
+
+	memcpy(cp, name, namelen);
+	cp += namelen;
+	*cp = '\0';
+	return desclen;
+}
+
+static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
+		const char *type, void *data, size_t data_size)
+{
+	const struct cred *saved_cred;
+	struct key *rkey;
+	char *desc;
+	struct user_key_payload *payload;
+	ssize_t ret;
+
+	ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc);
+	if (ret <= 0)
+		goto out;
+
+	saved_cred = override_creds(id_resolver_cache);
+	rkey = request_key(&key_type_id_resolver, desc, "");
+	revert_creds(saved_cred);
+	kfree(desc);
+	if (IS_ERR(rkey)) {
+		ret = PTR_ERR(rkey);
+		goto out;
+	}
+
+	rcu_read_lock();
+	rkey->perm |= KEY_USR_VIEW;
+
+	ret = key_validate(rkey);
+	if (ret < 0)
+		goto out_up;
+
+	payload = rcu_dereference(rkey->payload.data);
+	if (IS_ERR_OR_NULL(payload)) {
+		ret = PTR_ERR(payload);
+		goto out_up;
+	}
+
+	ret = payload->datalen;
+	if (ret > 0 && ret <= data_size)
+		memcpy(data, payload->data, ret);
+	else
+		ret = -EINVAL;
+
+out_up:
+	rcu_read_unlock();
+	key_put(rkey);
+out:
+	return ret;
+}
+
+
+/* ID -> Name */
+static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen)
+{
+	char id_str[NFS_UINT_MAXLEN];
+	int id_len;
+	ssize_t ret;
+
+	id_len = snprintf(id_str, sizeof(id_str), "%u", id);
+	ret = nfs_idmap_request_key(id_str, id_len, type, buf, buflen);
+	if (ret < 0)
+		return -EINVAL;
+	return ret;
+}
+
+/* Name -> ID */
+static int nfs_idmap_lookup_id(const char *name, size_t namelen,
+				const char *type, __u32 *id)
+{
+	char id_str[NFS_UINT_MAXLEN];
+	long id_long;
+	ssize_t data_size;
+	int ret = 0;
+
+	data_size = nfs_idmap_request_key(name, namelen, type, id_str, NFS_UINT_MAXLEN);
+	if (data_size <= 0) {
+		ret = -EINVAL;
+	} else {
+		ret = strict_strtol(id_str, 10, &id_long);
+		*id = (__u32)id_long;
+	}
+	return ret;
+}
+
+int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
+{
+	return nfs_idmap_lookup_id(name, namelen, "uid", uid);
+}
+
+int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *gid)
+{
+	return nfs_idmap_lookup_id(name, namelen, "gid", gid);
+}
+
+int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
+{
+	return nfs_idmap_lookup_name(uid, "user", buf, buflen);
+}
+int nfs_map_gid_to_group(struct nfs_client *clp, __u32 gid, char *buf, size_t buflen)
+{
+	return nfs_idmap_lookup_name(gid, "group", buf, buflen);
+}
+
+#else  /* CONFIG_NFS_USE_IDMAPPER not defined */
+
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
@@ -503,16 +709,17 @@ int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namele
 	return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
 }
 
-int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf)
+int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
 }
-int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf)
+int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
 }
 
+#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */

fs/nfs/inode.c

@@ -234,9 +234,6 @@ nfs_init_locked(struct inode *inode, void *opaque)
 	return 0;
 }
 
-/* Don't use READDIRPLUS on directories that we believe are too large */
-#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE)
-
 /*
  * This is our front-end to iget that looks up inodes by file handle
  * instead of inode number.
@@ -291,8 +288,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		} else if (S_ISDIR(inode->i_mode)) {
 			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)
+			if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS))
 				set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
 			/* Deal with crossing mountpoints */
 			if ((fattr->valid & NFS_ATTR_FATTR_FSID)
@@ -623,7 +619,7 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 	nfs_revalidate_inode(server, inode);
 }
 
-static struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred)
+struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred, fmode_t f_mode)
 {
 	struct nfs_open_context *ctx;
 
@@ -633,11 +629,13 @@ static struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct
 		path_get(&ctx->path);
 		ctx->cred = get_rpccred(cred);
 		ctx->state = NULL;
+		ctx->mode = f_mode;
 		ctx->flags = 0;
 		ctx->error = 0;
 		ctx->dir_cookie = 0;
 		nfs_init_lock_context(&ctx->lock_context);
 		ctx->lock_context.open_context = ctx;
+		INIT_LIST_HEAD(&ctx->list);
 	}
 	return ctx;
 }
@@ -653,11 +651,15 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 {
 	struct inode *inode = ctx->path.dentry->d_inode;
 
-	if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
+	if (!list_empty(&ctx->list)) {
+		if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
+			return;
+		list_del(&ctx->list);
+		spin_unlock(&inode->i_lock);
+	} else if (!atomic_dec_and_test(&ctx->lock_context.count))
 		return;
-	list_del(&ctx->list);
-	spin_unlock(&inode->i_lock);
-	NFS_PROTO(inode)->close_context(ctx, is_sync);
+	if (inode != NULL)
+		NFS_PROTO(inode)->close_context(ctx, is_sync);
 	if (ctx->cred != NULL)
 		put_rpccred(ctx->cred);
 	path_put(&ctx->path);
@@ -673,7 +675,7 @@ void put_nfs_open_context(struct nfs_open_context *ctx)
  * Ensure that mmap has a recent RPC credential for use when writing out
  * shared pages
  */
-static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
+void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
 {
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -730,11 +732,10 @@ int nfs_open(struct inode *inode, struct file *filp)
 	cred = rpc_lookup_cred();
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
-	ctx = alloc_nfs_open_context(&filp->f_path, cred);
+	ctx = alloc_nfs_open_context(&filp->f_path, cred, filp->f_mode);
 	put_rpccred(cred);
 	if (ctx == NULL)
 		return -ENOMEM;
-	ctx->mode = filp->f_mode;
 	nfs_file_set_open_context(filp, ctx);
 	put_nfs_open_context(ctx);
 	nfs_fscache_set_inode_cookie(inode, filp);
@@ -1493,7 +1494,7 @@ static int nfsiod_start(void)
 {
 	struct workqueue_struct *wq;
 	dprintk("RPC:       creating workqueue nfsiod\n");
-	wq = create_singlethread_workqueue("nfsiod");
+	wq = alloc_workqueue("nfsiod", WQ_RESCUER, 0);
 	if (wq == NULL)
 		return -ENOMEM;
 	nfsiod_workqueue = wq;
@@ -1521,6 +1522,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_idmap_init();
+	if (err < 0)
+		goto out9;
+
 	err = nfs_dns_resolver_init();
 	if (err < 0)
 		goto out8;
@@ -1585,6 +1590,8 @@ static int __init init_nfs_fs(void)
 out7:
 	nfs_dns_resolver_destroy();
 out8:
+	nfs_idmap_quit();
+out9:
 	return err;
 }
 
@@ -1597,6 +1604,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_nfspagecache();
 	nfs_fscache_unregister();
 	nfs_dns_resolver_destroy();
+	nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister("nfs");
 #endif

fs/nfs/internal.h

@@ -62,6 +62,12 @@ struct nfs_clone_mount {
  */
 #define NFS_UNSPEC_PORT		(-1)
 
+/*
+ * Maximum number of pages that readdir can use for creating
+ * a vmapped array of pages.
+ */
+#define NFS_MAX_READDIR_PAGES 8
+
 /*
  * In-kernel mount arguments
  */
@@ -181,15 +187,15 @@ extern void nfs_destroy_directcache(void);
 /* nfs2xdr.c */
 extern int nfs_stat_to_errno(int);
 extern struct rpc_procinfo nfs_procedures[];
-extern __be32 * nfs_decode_dirent(__be32 *, struct nfs_entry *, int);
+extern __be32 *nfs_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int);
 
 /* nfs3xdr.c */
 extern struct rpc_procinfo nfs3_procedures[];
-extern __be32 *nfs3_decode_dirent(__be32 *, struct nfs_entry *, int);
+extern __be32 *nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int);
 
 /* nfs4xdr.c */
 #ifdef CONFIG_NFS_V4
-extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
+extern __be32 *nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int);
 #endif
 #ifdef CONFIG_NFS_V4_1
 extern const u32 nfs41_maxread_overhead;

fs/nfs/mount_clnt.c

@@ -436,7 +436,7 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res)
 
 	for (i = 0; i < entries; i++) {
 		flavors[i] = ntohl(*p++);
-		dprintk("NFS:\tflavor %u: %d\n", i, flavors[i]);
+		dprintk("NFS:   auth flavor[%u]: %d\n", i, flavors[i]);
 	}
 	*count = i;
 

fs/nfs/nfs2xdr.c

@@ -337,10 +337,10 @@ nfs_xdr_createargs(struct rpc_rqst *req, __be32 *p, struct nfs_createargs *args)
 static int
 nfs_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs_renameargs *args)
 {
-	p = xdr_encode_fhandle(p, args->fromfh);
-	p = xdr_encode_array(p, args->fromname, args->fromlen);
-	p = xdr_encode_fhandle(p, args->tofh);
-	p = xdr_encode_array(p, args->toname, args->tolen);
+	p = xdr_encode_fhandle(p, args->old_dir);
+	p = xdr_encode_array(p, args->old_name->name, args->old_name->len);
+	p = xdr_encode_fhandle(p, args->new_dir);
+	p = xdr_encode_array(p, args->new_name->name, args->new_name->len);
 	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
 	return 0;
 }
@@ -423,9 +423,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
 	struct page **page;
 	size_t hdrlen;
 	unsigned int pglen, recvd;
-	u32 len;
 	int status, nr = 0;
-	__be32 *end, *entry, *kaddr;
 
 	if ((status = ntohl(*p++)))
 		return nfs_stat_to_errno(status);
@@ -445,80 +443,59 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
 	if (pglen > recvd)
 		pglen = recvd;
 	page = rcvbuf->pages;
-	kaddr = p = kmap_atomic(*page, KM_USER0);
-	end = (__be32 *)((char *)p + pglen);
-	entry = p;
-
-	/* Make sure the packet actually has a value_follows and EOF entry */
-	if ((entry + 1) > end)
-		goto short_pkt;
-
-	for (; *p++; nr++) {
-		if (p + 2 > end)
-			goto short_pkt;
-		p++; /* fileid */
-		len = ntohl(*p++);
-		p += XDR_QUADLEN(len) + 1;	/* name plus cookie */
-		if (len > NFS2_MAXNAMLEN) {
-			dprintk("NFS: giant filename in readdir (len 0x%x)!\n",
-						len);
-			goto err_unmap;
-		}
-		if (p + 2 > end)
-			goto short_pkt;
-		entry = p;
-	}
-
-	/*
-	 * Apparently some server sends responses that are a valid size, but
-	 * contain no entries, and have value_follows==0 and EOF==0. For
-	 * those, just set the EOF marker.
-	 */
-	if (!nr && entry[1] == 0) {
-		dprintk("NFS: readdir reply truncated!\n");
-		entry[1] = 1;
-	}
- out:
-	kunmap_atomic(kaddr, KM_USER0);
 	return nr;
- short_pkt:
-	/*
-	 * When we get a short packet there are 2 possibilities. We can
-	 * return an error, or fix up the response to look like a valid
-	 * response and return what we have so far. If there are no
-	 * entries and the packet was short, then return -EIO. If there
-	 * are valid entries in the response, return them and pretend that
-	 * the call was successful, but incomplete. The caller can retry the
-	 * readdir starting at the last cookie.
-	 */
-	entry[0] = entry[1] = 0;
-	if (!nr)
-		nr = -errno_NFSERR_IO;
-	goto out;
-err_unmap:
-	nr = -errno_NFSERR_IO;
-	goto out;
+}
+
+static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
+{
+	dprintk("nfs: %s: prematurely hit end of receive buffer. "
+		"Remaining buffer length is %tu words.\n",
+		func, xdr->end - xdr->p);
 }
 
 __be32 *
-nfs_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
+nfs_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_server *server, int plus)
 {
-	if (!*p++) {
-		if (!*p)
+	__be32 *p;
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	if (!ntohl(*p++)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
+		if (!ntohl(*p++))
 			return ERR_PTR(-EAGAIN);
 		entry->eof = 1;
 		return ERR_PTR(-EBADCOOKIE);
 	}
 
+	p = xdr_inline_decode(xdr, 8);
+	if (unlikely(!p))
+		goto out_overflow;
+
 	entry->ino	  = ntohl(*p++);
 	entry->len	  = ntohl(*p++);
+
+	p = xdr_inline_decode(xdr, entry->len + 4);
+	if (unlikely(!p))
+		goto out_overflow;
 	entry->name	  = (const char *) p;
 	p		 += XDR_QUADLEN(entry->len);
 	entry->prev_cookie	  = entry->cookie;
 	entry->cookie	  = ntohl(*p++);
-	entry->eof	  = !p[0] && p[1];
+
+	p = xdr_inline_peek(xdr, 8);
+	if (p != NULL)
+		entry->eof = !p[0] && p[1];
+	else
+		entry->eof = 0;
 
 	return p;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return ERR_PTR(-EIO);
 }
 
 /*
@@ -596,7 +573,6 @@ nfs_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, void *dummy)
 	struct kvec *iov = rcvbuf->head;
 	size_t hdrlen;
 	u32 len, recvd;
-	char	*kaddr;
 	int	status;
 
 	if ((status = ntohl(*p++)))
@@ -623,10 +599,7 @@ nfs_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, void *dummy)
 		return -EIO;
 	}
 
-	/* NULL terminate the string we got */
-	kaddr = (char *)kmap_atomic(rcvbuf->pages[0], KM_USER0);
-	kaddr[len+rcvbuf->page_base] = '\0';
-	kunmap_atomic(kaddr, KM_USER0);
+	xdr_terminate_string(rcvbuf, len);
 	return 0;
 }
 

fs/nfs/nfs3proc.c

@@ -313,7 +313,7 @@ static void nfs3_free_createdata(struct nfs3_createdata *data)
  */
 static int
 nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-		 int flags, struct nameidata *nd)
+		 int flags, struct nfs_open_context *ctx)
 {
 	struct nfs3_createdata *data;
 	mode_t mode = sattr->ia_mode;
@@ -438,19 +438,38 @@ nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 	return 1;
 }
 
+static void
+nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
+{
+	msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME];
+}
+
+static int
+nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
+		      struct inode *new_dir)
+{
+	struct nfs_renameres *res;
+
+	if (nfs3_async_handle_jukebox(task, old_dir))
+		return 0;
+	res = task->tk_msg.rpc_resp;
+
+	nfs_post_op_update_inode(old_dir, res->old_fattr);
+	nfs_post_op_update_inode(new_dir, res->new_fattr);
+	return 1;
+}
+
 static int
 nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
 		 struct inode *new_dir, struct qstr *new_name)
 {
-	struct nfs3_renameargs	arg = {
-		.fromfh		= NFS_FH(old_dir),
-		.fromname	= old_name->name,
-		.fromlen	= old_name->len,
-		.tofh		= NFS_FH(new_dir),
-		.toname		= new_name->name,
-		.tolen		= new_name->len
+	struct nfs_renameargs	arg = {
+		.old_dir	= NFS_FH(old_dir),
+		.old_name	= old_name,
+		.new_dir	= NFS_FH(new_dir),
+		.new_name	= new_name,
 	};
-	struct nfs3_renameres res;
+	struct nfs_renameres res;
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs3_procedures[NFS3PROC_RENAME],
 		.rpc_argp	= &arg,
@@ -460,17 +479,17 @@ nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
 
 	dprintk("NFS call  rename %s -> %s\n", old_name->name, new_name->name);
 
-	res.fromattr = nfs_alloc_fattr();
-	res.toattr = nfs_alloc_fattr();
-	if (res.fromattr == NULL || res.toattr == NULL)
+	res.old_fattr = nfs_alloc_fattr();
+	res.new_fattr = nfs_alloc_fattr();
+	if (res.old_fattr == NULL || res.new_fattr == NULL)
 		goto out;
 
 	status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
-	nfs_post_op_update_inode(old_dir, res.fromattr);
-	nfs_post_op_update_inode(new_dir, res.toattr);
+	nfs_post_op_update_inode(old_dir, res.old_fattr);
+	nfs_post_op_update_inode(new_dir, res.new_fattr);
 out:
-	nfs_free_fattr(res.toattr);
-	nfs_free_fattr(res.fromattr);
+	nfs_free_fattr(res.old_fattr);
+	nfs_free_fattr(res.new_fattr);
 	dprintk("NFS reply rename: %d\n", status);
 	return status;
 }
@@ -611,7 +630,7 @@ nfs3_proc_rmdir(struct inode *dir, struct qstr *name)
  */
 static int
 nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		  u64 cookie, struct page *page, unsigned int count, int plus)
+		  u64 cookie, struct page **pages, unsigned int count, int plus)
 {
 	struct inode		*dir = dentry->d_inode;
 	__be32			*verf = NFS_COOKIEVERF(dir);
@@ -621,7 +640,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 		.verf		= {verf[0], verf[1]},
 		.plus		= plus,
 		.count		= count,
-		.pages		= &page
+		.pages		= pages
 	};
 	struct nfs3_readdirres	res = {
 		.verf		= verf,
@@ -652,7 +671,8 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 
 	nfs_free_fattr(res.dir_attr);
 out:
-	dprintk("NFS reply readdir: %d\n", status);
+	dprintk("NFS reply readdir%s: %d\n",
+			plus? "plus" : "", status);
 	return status;
 }
 
@@ -722,7 +742,7 @@ nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
 	dprintk("NFS call  fsstat\n");
 	nfs_fattr_init(stat->fattr);
 	status = rpc_call_sync(server->client, &msg, 0);
-	dprintk("NFS reply statfs: %d\n", status);
+	dprintk("NFS reply fsstat: %d\n", status);
 	return status;
 }
 
@@ -844,6 +864,8 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.unlink_setup	= nfs3_proc_unlink_setup,
 	.unlink_done	= nfs3_proc_unlink_done,
 	.rename		= nfs3_proc_rename,
+	.rename_setup	= nfs3_proc_rename_setup,
+	.rename_done	= nfs3_proc_rename_done,
 	.link		= nfs3_proc_link,
 	.symlink	= nfs3_proc_symlink,
 	.mkdir		= nfs3_proc_mkdir,

fs/nfs/nfs3xdr.c

@@ -100,6 +100,13 @@ static const umode_t nfs_type2fmt[] = {
 	[NF3FIFO] = S_IFIFO,
 };
 
+static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
+{
+	dprintk("nfs: %s: prematurely hit end of receive buffer. "
+		"Remaining buffer length is %tu words.\n",
+		func, xdr->end - xdr->p);
+}
+
 /*
  * Common NFS XDR functions as inlines
  */
@@ -119,6 +126,29 @@ xdr_decode_fhandle(__be32 *p, struct nfs_fh *fh)
 	return NULL;
 }
 
+static inline __be32 *
+xdr_decode_fhandle_stream(struct xdr_stream *xdr, struct nfs_fh *fh)
+{
+	__be32 *p;
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	fh->size = ntohl(*p++);
+
+	if (fh->size <= NFS3_FHSIZE) {
+		p = xdr_inline_decode(xdr, fh->size);
+		if (unlikely(!p))
+			goto out_overflow;
+		memcpy(fh->data, p, fh->size);
+		return p + XDR_QUADLEN(fh->size);
+	}
+	return NULL;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return ERR_PTR(-EIO);
+}
+
 /*
  * Encode/decode time.
  */
@@ -240,6 +270,26 @@ xdr_decode_post_op_attr(__be32 *p, struct nfs_fattr *fattr)
 	return p;
 }
 
+static inline __be32 *
+xdr_decode_post_op_attr_stream(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+{
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	if (ntohl(*p++)) {
+		p = xdr_inline_decode(xdr, 84);
+		if (unlikely(!p))
+			goto out_overflow;
+		p = xdr_decode_fattr(p, fattr);
+	}
+	return p;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return ERR_PTR(-EIO);
+}
+
 static inline __be32 *
 xdr_decode_pre_op_attr(__be32 *p, struct nfs_fattr *fattr)
 {
@@ -442,12 +492,12 @@ nfs3_xdr_mknodargs(struct rpc_rqst *req, __be32 *p, struct nfs3_mknodargs *args)
  * Encode RENAME arguments
  */
 static int
-nfs3_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs3_renameargs *args)
+nfs3_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs_renameargs *args)
 {
-	p = xdr_encode_fhandle(p, args->fromfh);
-	p = xdr_encode_array(p, args->fromname, args->fromlen);
-	p = xdr_encode_fhandle(p, args->tofh);
-	p = xdr_encode_array(p, args->toname, args->tolen);
+	p = xdr_encode_fhandle(p, args->old_dir);
+	p = xdr_encode_array(p, args->old_name->name, args->old_name->len);
+	p = xdr_encode_fhandle(p, args->new_dir);
+	p = xdr_encode_array(p, args->new_name->name, args->new_name->len);
 	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
 	return 0;
 }
@@ -504,9 +554,8 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res
 	struct kvec *iov = rcvbuf->head;
 	struct page **page;
 	size_t hdrlen;
-	u32 len, recvd, pglen;
+	u32 recvd, pglen;
 	int status, nr = 0;
-	__be32 *entry, *end, *kaddr;
 
 	status = ntohl(*p++);
 	/* Decode post_op_attrs */
@@ -536,99 +585,38 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res
 	if (pglen > recvd)
 		pglen = recvd;
 	page = rcvbuf->pages;
-	kaddr = p = kmap_atomic(*page, KM_USER0);
-	end = (__be32 *)((char *)p + pglen);
-	entry = p;
-
-	/* Make sure the packet actually has a value_follows and EOF entry */
-	if ((entry + 1) > end)
-		goto short_pkt;
-
-	for (; *p++; nr++) {
-		if (p + 3 > end)
-			goto short_pkt;
-		p += 2;				/* inode # */
-		len = ntohl(*p++);		/* string length */
-		p += XDR_QUADLEN(len) + 2;	/* name + cookie */
-		if (len > NFS3_MAXNAMLEN) {
-			dprintk("NFS: giant filename in readdir (len 0x%x)!\n",
-						len);
-			goto err_unmap;
-		}
 
-		if (res->plus) {
-			/* post_op_attr */
-			if (p + 2 > end)
-				goto short_pkt;
-			if (*p++) {
-				p += 21;
-				if (p + 1 > end)
-					goto short_pkt;
-			}
-			/* post_op_fh3 */
-			if (*p++) {
-				if (p + 1 > end)
-					goto short_pkt;
-				len = ntohl(*p++);
-				if (len > NFS3_FHSIZE) {
-					dprintk("NFS: giant filehandle in "
-						"readdir (len 0x%x)!\n", len);
-					goto err_unmap;
-				}
-				p += XDR_QUADLEN(len);
-			}
-		}
-
-		if (p + 2 > end)
-			goto short_pkt;
-		entry = p;
-	}
-
-	/*
-	 * Apparently some server sends responses that are a valid size, but
-	 * contain no entries, and have value_follows==0 and EOF==0. For
-	 * those, just set the EOF marker.
-	 */
-	if (!nr && entry[1] == 0) {
-		dprintk("NFS: readdir reply truncated!\n");
-		entry[1] = 1;
-	}
- out:
-	kunmap_atomic(kaddr, KM_USER0);
 	return nr;
- short_pkt:
-	/*
-	 * When we get a short packet there are 2 possibilities. We can
-	 * return an error, or fix up the response to look like a valid
-	 * response and return what we have so far. If there are no
-	 * entries and the packet was short, then return -EIO. If there
-	 * are valid entries in the response, return them and pretend that
-	 * the call was successful, but incomplete. The caller can retry the
-	 * readdir starting at the last cookie.
-	 */
-	entry[0] = entry[1] = 0;
-	if (!nr)
-		nr = -errno_NFSERR_IO;
-	goto out;
-err_unmap:
-	nr = -errno_NFSERR_IO;
-	goto out;
 }
 
 __be32 *
-nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
+nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_server *server, int plus)
 {
+	__be32 *p;
 	struct nfs_entry old = *entry;
 
-	if (!*p++) {
-		if (!*p)
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	if (!ntohl(*p++)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
+		if (!ntohl(*p++))
 			return ERR_PTR(-EAGAIN);
 		entry->eof = 1;
 		return ERR_PTR(-EBADCOOKIE);
 	}
 
+	p = xdr_inline_decode(xdr, 12);
+	if (unlikely(!p))
+		goto out_overflow;
 	p = xdr_decode_hyper(p, &entry->ino);
 	entry->len  = ntohl(*p++);
+
+	p = xdr_inline_decode(xdr, entry->len + 8);
+	if (unlikely(!p))
+		goto out_overflow;
 	entry->name = (const char *) p;
 	p += XDR_QUADLEN(entry->len);
 	entry->prev_cookie = entry->cookie;
@@ -636,10 +624,17 @@ nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
 
 	if (plus) {
 		entry->fattr->valid = 0;
-		p = xdr_decode_post_op_attr(p, entry->fattr);
+		p = xdr_decode_post_op_attr_stream(xdr, entry->fattr);
+		if (IS_ERR(p))
+			goto out_overflow_exit;
 		/* In fact, a post_op_fh3: */
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
 		if (*p++) {
-			p = xdr_decode_fhandle(p, entry->fh);
+			p = xdr_decode_fhandle_stream(xdr, entry->fh);
+			if (IS_ERR(p))
+				goto out_overflow_exit;
 			/* Ugh -- server reply was truncated */
 			if (p == NULL) {
 				dprintk("NFS: FH truncated\n");
@@ -650,8 +645,18 @@ nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
 			memset((u8*)(entry->fh), 0, sizeof(*entry->fh));
 	}
 
-	entry->eof = !p[0] && p[1];
+	p = xdr_inline_peek(xdr, 8);
+	if (p != NULL)
+		entry->eof = !p[0] && p[1];
+	else
+		entry->eof = 0;
+
 	return p;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+out_overflow_exit:
+	return ERR_PTR(-EIO);
 }
 
 /*
@@ -824,7 +829,6 @@ nfs3_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
 	struct kvec *iov = rcvbuf->head;
 	size_t hdrlen;
 	u32 len, recvd;
-	char	*kaddr;
 	int	status;
 
 	status = ntohl(*p++);
@@ -857,10 +861,7 @@ nfs3_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
 		return -EIO;
 	}
 
-	/* NULL terminate the string we got */
-	kaddr = (char*)kmap_atomic(rcvbuf->pages[0], KM_USER0);
-	kaddr[len+rcvbuf->page_base] = '\0';
-	kunmap_atomic(kaddr, KM_USER0);
+	xdr_terminate_string(rcvbuf, len);
 	return 0;
 }
 
@@ -970,14 +971,14 @@ nfs3_xdr_createres(struct rpc_rqst *req, __be32 *p, struct nfs3_diropres *res)
  * Decode RENAME reply
  */
 static int
-nfs3_xdr_renameres(struct rpc_rqst *req, __be32 *p, struct nfs3_renameres *res)
+nfs3_xdr_renameres(struct rpc_rqst *req, __be32 *p, struct nfs_renameres *res)
 {
 	int	status;
 
 	if ((status = ntohl(*p++)) != 0)
 		status = nfs_stat_to_errno(status);
-	p = xdr_decode_wcc_data(p, res->fromattr);
-	p = xdr_decode_wcc_data(p, res->toattr);
+	p = xdr_decode_wcc_data(p, res->old_fattr);
+	p = xdr_decode_wcc_data(p, res->new_fattr);
 	return status;
 }
 
@@ -1043,8 +1044,9 @@ nfs3_xdr_fsinfores(struct rpc_rqst *req, __be32 *p, struct nfs_fsinfo *res)
 	res->wtmult = ntohl(*p++);
 	res->dtpref = ntohl(*p++);
 	p = xdr_decode_hyper(p, &res->maxfilesize);
+	p = xdr_decode_time3(p, &res->time_delta);
 
-	/* ignore time_delta and properties */
+	/* ignore properties */
 	res->lease_time = 0;
 	return 0;
 }

fs/nfs/nfs4_fs.h

@@ -242,8 +242,6 @@ extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, int wait);
-extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
-extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *);
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 		struct nfs4_fs_locations *fs_locations, struct page *page);
@@ -333,7 +331,7 @@ extern void nfs_free_seqid(struct nfs_seqid *seqid);
 extern const nfs4_stateid zero_stateid;
 
 /* nfs4xdr.c */
-extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
+extern __be32 *nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int);
 extern struct rpc_procinfo nfs4_procedures[];
 
 struct nfs4_mount_data;

fs/nfs/nfs4state.c

@@ -46,6 +46,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/ratelimit.h>
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 
@@ -1063,6 +1064,14 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 				/* Mark the file as being 'closed' */
 				state->state = 0;
 				break;
+			case -EKEYEXPIRED:
+				/*
+				 * User RPCSEC_GSS context has expired.
+				 * We cannot recover this stateid now, so
+				 * skip it and allow recovery thread to
+				 * proceed.
+				 */
+				break;
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_BAD_STATEID:
@@ -1138,16 +1147,14 @@ static void nfs4_reclaim_complete(struct nfs_client *clp,
 		(void)ops->reclaim_complete(clp);
 }
 
-static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
+static int nfs4_state_clear_reclaim_reboot(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 	struct rb_node *pos;
 	struct nfs4_state *state;
 
 	if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
-		return;
-
-	nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
+		return 0;
 
 	for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
 		sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
@@ -1161,6 +1168,14 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
 	}
 
 	nfs_delegation_reap_unclaimed(clp);
+	return 1;
+}
+
+static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
+{
+	if (!nfs4_state_clear_reclaim_reboot(clp))
+		return;
+	nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
 }
 
 static void nfs_delegation_clear_all(struct nfs_client *clp)
@@ -1175,6 +1190,14 @@ static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp)
 	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
 }
 
+static void nfs4_warn_keyexpired(const char *s)
+{
+	printk_ratelimited(KERN_WARNING "Error: state manager"
+			" encountered RPCSEC_GSS session"
+			" expired against NFSv4 server %s.\n",
+			s);
+}
+
 static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 {
 	switch (error) {
@@ -1187,7 +1210,7 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_LEASE_MOVED:
 			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-			nfs4_state_end_reclaim_reboot(clp);
+			nfs4_state_clear_reclaim_reboot(clp);
 			nfs4_state_start_reclaim_reboot(clp);
 			break;
 		case -NFS4ERR_EXPIRED:
@@ -1204,6 +1227,10 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 			set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 			/* Zero session reset errors */
 			return 0;
+		case -EKEYEXPIRED:
+			/* Nothing we can do */
+			nfs4_warn_keyexpired(clp->cl_hostname);
+			return 0;
 	}
 	return error;
 }
@@ -1414,9 +1441,10 @@ static void nfs4_set_lease_expired(struct nfs_client *clp, int status)
 		case -NFS4ERR_DELAY:
 		case -NFS4ERR_CLID_INUSE:
 		case -EAGAIN:
-		case -EKEYEXPIRED:
 			break;
 
+		case -EKEYEXPIRED:
+			nfs4_warn_keyexpired(clp->cl_hostname);
 		case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
 					 * in nfs4_exchange_id */
 		default:

fs/nfs/proc.c

@@ -258,7 +258,7 @@ static void nfs_free_createdata(const struct nfs_createdata *data)
 
 static int
 nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-		int flags, struct nameidata *nd)
+		int flags, struct nfs_open_context *ctx)
 {
 	struct nfs_createdata *data;
 	struct rpc_message msg = {
@@ -365,17 +365,32 @@ static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 	return 1;
 }
 
+static void
+nfs_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
+{
+	msg->rpc_proc = &nfs_procedures[NFSPROC_RENAME];
+}
+
+static int
+nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
+		     struct inode *new_dir)
+{
+	if (nfs_async_handle_expired_key(task))
+		return 0;
+	nfs_mark_for_revalidate(old_dir);
+	nfs_mark_for_revalidate(new_dir);
+	return 1;
+}
+
 static int
 nfs_proc_rename(struct inode *old_dir, struct qstr *old_name,
 		struct inode *new_dir, struct qstr *new_name)
 {
 	struct nfs_renameargs	arg = {
-		.fromfh		= NFS_FH(old_dir),
-		.fromname	= old_name->name,
-		.fromlen	= old_name->len,
-		.tofh		= NFS_FH(new_dir),
-		.toname		= new_name->name,
-		.tolen		= new_name->len
+		.old_dir	= NFS_FH(old_dir),
+		.old_name	= old_name,
+		.new_dir	= NFS_FH(new_dir),
+		.new_name	= new_name,
 	};
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs_procedures[NFSPROC_RENAME],
@@ -519,14 +534,14 @@ nfs_proc_rmdir(struct inode *dir, struct qstr *name)
  */
 static int
 nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		 u64 cookie, struct page *page, unsigned int count, int plus)
+		 u64 cookie, struct page **pages, unsigned int count, int plus)
 {
 	struct inode		*dir = dentry->d_inode;
 	struct nfs_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
 		.cookie		= cookie,
 		.count		= count,
-		.pages		= &page,
+		.pages		= pages,
 	};
 	struct rpc_message	msg = {
 		.rpc_proc	= &nfs_procedures[NFSPROC_READDIR],
@@ -705,6 +720,8 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.unlink_setup	= nfs_proc_unlink_setup,
 	.unlink_done	= nfs_proc_unlink_done,
 	.rename		= nfs_proc_rename,
+	.rename_setup	= nfs_proc_rename_setup,
+	.rename_done	= nfs_proc_rename_done,
 	.link		= nfs_proc_link,
 	.symlink	= nfs_proc_symlink,
 	.mkdir		= nfs_proc_mkdir,

fs/nfs/read.c

@@ -46,7 +46,6 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
 		p->npages = pagecount;
-		p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 		if (pagecount <= ARRAY_SIZE(p->page_array))
 			p->pagevec = p->page_array;
 		else {

fs/nfs/super.c

@@ -100,6 +100,7 @@ enum {
 	Opt_addr, Opt_mountaddr, Opt_clientaddr,
 	Opt_lookupcache,
 	Opt_fscache_uniq,
+	Opt_local_lock,
 
 	/* Special mount options */
 	Opt_userspace, Opt_deprecated, Opt_sloppy,
@@ -171,6 +172,7 @@ static const match_table_t nfs_mount_option_tokens = {
 
 	{ Opt_lookupcache, "lookupcache=%s" },
 	{ Opt_fscache_uniq, "fsc=%s" },
+	{ Opt_local_lock, "local_lock=%s" },
 
 	{ Opt_err, NULL }
 };
@@ -236,6 +238,22 @@ static match_table_t nfs_lookupcache_tokens = {
 	{ Opt_lookupcache_err, NULL }
 };
 
+enum {
+	Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix,
+	Opt_local_lock_none,
+
+	Opt_local_lock_err
+};
+
+static match_table_t nfs_local_lock_tokens = {
+	{ Opt_local_lock_all, "all" },
+	{ Opt_local_lock_flock, "flock" },
+	{ Opt_local_lock_posix, "posix" },
+	{ Opt_local_lock_none, "none" },
+
+	{ Opt_local_lock_err, NULL }
+};
+
 
 static void nfs_umount_begin(struct super_block *);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
@@ -622,6 +640,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	const struct proc_nfs_info *nfs_infop;
 	struct nfs_client *clp = nfss->nfs_client;
 	u32 version = clp->rpc_ops->version;
+	int local_flock, local_fcntl;
 
 	seq_printf(m, ",vers=%u", version);
 	seq_printf(m, ",rsize=%u", nfss->rsize);
@@ -670,6 +689,18 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		else
 			seq_printf(m, ",lookupcache=pos");
 	}
+
+	local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK;
+	local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL;
+
+	if (!local_flock && !local_fcntl)
+		seq_printf(m, ",local_lock=none");
+	else if (local_flock && local_fcntl)
+		seq_printf(m, ",local_lock=all");
+	else if (local_flock)
+		seq_printf(m, ",local_lock=flock");
+	else
+		seq_printf(m, ",local_lock=posix");
 }
 
 /*
@@ -1017,9 +1048,13 @@ static int nfs_parse_mount_options(char *raw,
 			break;
 		case Opt_lock:
 			mnt->flags &= ~NFS_MOUNT_NONLM;
+			mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
+					NFS_MOUNT_LOCAL_FCNTL);
 			break;
 		case Opt_nolock:
 			mnt->flags |= NFS_MOUNT_NONLM;
+			mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
+				       NFS_MOUNT_LOCAL_FCNTL);
 			break;
 		case Opt_v2:
 			mnt->flags &= ~NFS_MOUNT_VER3;
@@ -1420,6 +1455,34 @@ static int nfs_parse_mount_options(char *raw,
 			mnt->fscache_uniq = string;
 			mnt->options |= NFS_OPTION_FSCACHE;
 			break;
+		case Opt_local_lock:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			token = match_token(string, nfs_local_lock_tokens,
+					args);
+			kfree(string);
+			switch (token) {
+			case Opt_local_lock_all:
+				mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
+					       NFS_MOUNT_LOCAL_FCNTL);
+				break;
+			case Opt_local_lock_flock:
+				mnt->flags |= NFS_MOUNT_LOCAL_FLOCK;
+				break;
+			case Opt_local_lock_posix:
+				mnt->flags |= NFS_MOUNT_LOCAL_FCNTL;
+				break;
+			case Opt_local_lock_none:
+				mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
+						NFS_MOUNT_LOCAL_FCNTL);
+				break;
+			default:
+				dfprintk(MOUNT, "NFS:	invalid	"
+						"local_lock argument\n");
+				return 0;
+			};
+			break;
 
 		/*
 		 * Special options
@@ -1825,6 +1888,12 @@ static int nfs_validate_mount_data(void *options,
 		if (!args->nfs_server.hostname)
 			goto out_nomem;
 
+		if (!(data->flags & NFS_MOUNT_NONLM))
+			args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK|
+					 NFS_MOUNT_LOCAL_FCNTL);
+		else
+			args->flags |= (NFS_MOUNT_LOCAL_FLOCK|
+					NFS_MOUNT_LOCAL_FCNTL);
 		/*
 		 * The legacy version 6 binary mount data from userspace has a
 		 * field used only to transport selinux information into the
@@ -2441,7 +2510,8 @@ static void nfs4_fill_super(struct super_block *sb)
 
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 {
-	args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3);
+	args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3|
+			 NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL);
 }
 
 static int nfs4_validate_text_mount_data(void *options,

fs/nfs/sysctl.c

@@ -32,6 +32,7 @@ static ctl_table nfs_cb_sysctls[] = {
 		.extra1 = (int *)&nfs_set_port_min,
 		.extra2 = (int *)&nfs_set_port_max,
 	},
+#ifndef CONFIG_NFS_USE_NEW_IDMAPPER
 	{
 		.procname = "idmap_cache_timeout",
 		.data = &nfs_idmap_cache_timeout,
@@ -39,6 +40,7 @@ static ctl_table nfs_cb_sysctls[] = {
 		.mode = 0644,
 		.proc_handler = proc_dointvec_jiffies,
 	},
+#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
 #endif
 	{
 		.procname	= "nfs_mountpoint_timeout",

fs/nfs/write.c

@@ -55,7 +55,6 @@ struct nfs_write_data *nfs_commitdata_alloc(void)
 	if (p) {
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
-		p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	}
 	return p;
 }
@@ -75,7 +74,6 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
 		p->npages = pagecount;
-		p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 		if (pagecount <= ARRAY_SIZE(p->page_array))
 			p->pagevec = p->page_array;
 		else {
@@ -1433,15 +1431,17 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
-	/* Don't commit yet if this is a non-blocking flush and there are
-	 * lots of outstanding writes for this mapping.
-	 */
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    nfsi->ncommit <= (nfsi->npages >> 1))
-		goto out_mark_dirty;
+	if (wbc->sync_mode == WB_SYNC_NONE) {
+		/* Don't commit yet if this is a non-blocking flush and there
+		 * are a lot of outstanding writes for this mapping.
+		 */
+		if (nfsi->ncommit <= (nfsi->npages >> 1))
+			goto out_mark_dirty;
 
-	if (wbc->nonblocking || wbc->for_background)
+		/* don't wait for the COMMIT response */
 		flags = 0;
+	}
+
 	ret = nfs_commit_inode(inode, flags);
 	if (ret >= 0) {
 		if (wbc->sync_mode == WB_SYNC_NONE) {

include/linux/nfs_fs.h

@@ -360,10 +360,13 @@ extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr);
 extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
 extern void put_nfs_open_context(struct nfs_open_context *ctx);
 extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode);
+extern struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred, fmode_t f_mode);
+extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx);
 extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx);
 extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
 extern u64 nfs_compat_user_ino64(u64 fileid);
 extern void nfs_fattr_init(struct nfs_fattr *fattr);
+extern unsigned long nfs_inc_attr_generation_counter(void);
 
 extern struct nfs_fattr *nfs_alloc_fattr(void);
 
@@ -379,9 +382,12 @@ static inline void nfs_free_fhandle(const struct nfs_fh *fh)
 	kfree(fh);
 }
 
+/*
+ * linux/fs/nfs/nfsroot.c
+ */
+extern int  nfs_root_data(char **root_device, char **root_data); /*__init*/
 /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */
 extern __be32 root_nfs_parse_addr(char *name); /*__init*/
-extern unsigned long nfs_inc_attr_generation_counter(void);
 
 /*
  * linux/fs/nfs/file.c
@@ -479,10 +485,10 @@ extern void nfs_release_automount_timer(void);
 /*
  * linux/fs/nfs/unlink.c
  */
-extern int  nfs_async_unlink(struct inode *dir, struct dentry *dentry);
 extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
 extern void nfs_block_sillyrename(struct dentry *dentry);
 extern void nfs_unblock_sillyrename(struct dentry *dentry);
+extern int  nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 
 /*
  * linux/fs/nfs/write.c
@@ -584,10 +590,6 @@ nfs_fileid_to_ino_t(u64 fileid)
 	return ino;
 }
 
-/* NFS root */
-
-extern void * nfs_root_data(void);
-
 #define nfs_wait_event(clnt, wq, condition)				\
 ({									\
 	int __retval = wait_event_killable(wq, condition);		\

include/linux/nfs_fs_sb.h

@@ -124,6 +124,7 @@ struct nfs_server {
 
 	struct nfs_fsid		fsid;
 	__u64			maxfilesize;	/* maximum file size */
+	struct timespec		time_delta;	/* smallest time granularity */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	dev_t			s_dev;		/* superblock dev numbers */
 

include/linux/nfs_idmap.h

@@ -66,13 +66,40 @@ struct idmap_msg {
 /* Forward declaration to make this header independent of others */
 struct nfs_client;
 
+#ifdef CONFIG_NFS_USE_NEW_IDMAPPER
+
+int nfs_idmap_init(void);
+void nfs_idmap_quit(void);
+
+static inline int nfs_idmap_new(struct nfs_client *clp)
+{
+	return 0;
+}
+
+static inline void nfs_idmap_delete(struct nfs_client *clp)
+{
+}
+
+#else /* CONFIG_NFS_USE_NEW_IDMAPPER not set */
+
+static inline int nfs_idmap_init(void)
+{
+	return 0;
+}
+
+static inline void nfs_idmap_quit(void)
+{
+}
+
 int nfs_idmap_new(struct nfs_client *);
 void nfs_idmap_delete(struct nfs_client *);
 
+#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
+
 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 *);
+int nfs_map_uid_to_name(struct nfs_client *, __u32, char *, size_t);
+int nfs_map_gid_to_group(struct nfs_client *, __u32, char *, size_t);
 
 extern unsigned int nfs_idmap_cache_timeout;
 #endif /* __KERNEL__ */

include/linux/nfs_mount.h

@@ -71,4 +71,7 @@ struct nfs_mount_data {
 #define NFS_MOUNT_NORESVPORT		0x40000
 #define NFS_MOUNT_LEGACY_INTERFACE	0x80000
 
+#define NFS_MOUNT_LOCAL_FLOCK	0x100000
+#define NFS_MOUNT_LOCAL_FCNTL	0x200000
+
 #endif

include/linux/sunrpc/clnt.h

@@ -137,7 +137,6 @@ int		rpcb_register(u32, u32, int, unsigned short);
 int		rpcb_v4_register(const u32 program, const u32 version,
 				 const struct sockaddr *address,
 				 const char *netid);
-int		rpcb_getport_sync(struct sockaddr_in *, u32, u32, int);
 void		rpcb_getport_async(struct rpc_task *);
 
 void		rpc_call_start(struct rpc_task *);

include/linux/sunrpc/xdr.h

@@ -108,6 +108,7 @@ void	xdr_encode_pages(struct xdr_buf *, struct page **, unsigned int,
 			 unsigned int);
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
+void	xdr_terminate_string(struct xdr_buf *, const u32);
 
 static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len)
 {
@@ -200,6 +201,7 @@ extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
+extern __be32 *xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes);
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);