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

@@ -0,0 +1,67 @@
+
+=========
+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 @@ restart:
 	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 @@ out:
 
 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 @@ retry_cancel:
 	/* 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/dir.c

@@ -33,11 +33,12 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/sched.h>
+#include <linux/vmalloc.h>
 
-#include "nfs4_fs.h"
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 /* #define NFS_DEBUG_VERBOSE 1 */
 
@@ -55,6 +56,7 @@ static int nfs_rename(struct inode *, struct dentry *,
 		      struct inode *, struct dentry *);
 static int nfs_fsync_dir(struct file *, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
+static int nfs_readdir_clear_array(struct page*, gfp_t);
 
 const struct file_operations nfs_dir_operations = {
 	.llseek		= nfs_llseek_dir,
@@ -80,6 +82,10 @@ const struct inode_operations nfs_dir_inode_operations = {
 	.setattr	= nfs_setattr,
 };
 
+const struct address_space_operations nfs_dir_addr_space_ops = {
+	.releasepage = nfs_readdir_clear_array,
+};
+
 #ifdef CONFIG_NFS_V3
 const struct inode_operations nfs3_dir_inode_operations = {
 	.create		= nfs_create,
@@ -104,8 +110,9 @@ const struct inode_operations nfs3_dir_inode_operations = {
 #ifdef CONFIG_NFS_V4
 
 static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *);
+static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd);
 const struct inode_operations nfs4_dir_inode_operations = {
-	.create		= nfs_create,
+	.create		= nfs_open_create,
 	.lookup		= nfs_atomic_lookup,
 	.link		= nfs_link,
 	.unlink		= nfs_unlink,
@@ -150,51 +157,197 @@ nfs_opendir(struct inode *inode, struct file *filp)
 	return res;
 }
 
-typedef __be32 * (*decode_dirent_t)(__be32 *, struct nfs_entry *, int);
+struct nfs_cache_array_entry {
+	u64 cookie;
+	u64 ino;
+	struct qstr string;
+};
+
+struct nfs_cache_array {
+	unsigned int size;
+	int eof_index;
+	u64 last_cookie;
+	struct nfs_cache_array_entry array[0];
+};
+
+#define MAX_READDIR_ARRAY ((PAGE_SIZE - sizeof(struct nfs_cache_array)) / sizeof(struct nfs_cache_array_entry))
+
+typedef __be32 * (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int);
 typedef struct {
 	struct file	*file;
 	struct page	*page;
 	unsigned long	page_index;
-	__be32		*ptr;
 	u64		*dir_cookie;
 	loff_t		current_index;
-	struct nfs_entry *entry;
 	decode_dirent_t	decode;
-	int		plus;
+
 	unsigned long	timestamp;
 	unsigned long	gencount;
-	int		timestamp_valid;
+	unsigned int	cache_entry_index;
+	unsigned int	plus:1;
+	unsigned int	eof:1;
 } nfs_readdir_descriptor_t;
 
-/* Now we cache directories properly, by stuffing the dirent
- * data directly in the page cache.
- *
- * Inode invalidation due to refresh etc. takes care of
- * _everything_, no sloppy entry flushing logic, no extraneous
- * copying, network direct to page cache, the way it was meant
- * to be.
- *
- * NOTE: Dirent information verification is done always by the
- *	 page-in of the RPC reply, nowhere else, this simplies
- *	 things substantially.
+/*
+ * The caller is responsible for calling nfs_readdir_release_array(page)
  */
 static
-int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
+struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
+{
+	if (page == NULL)
+		return ERR_PTR(-EIO);
+	return (struct nfs_cache_array *)kmap(page);
+}
+
+static
+void nfs_readdir_release_array(struct page *page)
+{
+	kunmap(page);
+}
+
+/*
+ * we are freeing strings created by nfs_add_to_readdir_array()
+ */
+static
+int nfs_readdir_clear_array(struct page *page, gfp_t mask)
+{
+	struct nfs_cache_array *array = nfs_readdir_get_array(page);
+	int i;
+	for (i = 0; i < array->size; i++)
+		kfree(array->array[i].string.name);
+	nfs_readdir_release_array(page);
+	return 0;
+}
+
+/*
+ * the caller is responsible for freeing qstr.name
+ * when called by nfs_readdir_add_to_array, the strings will be freed in
+ * nfs_clear_readdir_array()
+ */
+static
+int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len)
+{
+	string->len = len;
+	string->name = kmemdup(name, len, GFP_KERNEL);
+	if (string->name == NULL)
+		return -ENOMEM;
+	string->hash = full_name_hash(name, len);
+	return 0;
+}
+
+static
+int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
+{
+	struct nfs_cache_array *array = nfs_readdir_get_array(page);
+	struct nfs_cache_array_entry *cache_entry;
+	int ret;
+
+	if (IS_ERR(array))
+		return PTR_ERR(array);
+	ret = -EIO;
+	if (array->size >= MAX_READDIR_ARRAY)
+		goto out;
+
+	cache_entry = &array->array[array->size];
+	cache_entry->cookie = entry->prev_cookie;
+	cache_entry->ino = entry->ino;
+	ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len);
+	if (ret)
+		goto out;
+	array->last_cookie = entry->cookie;
+	if (entry->eof == 1)
+		array->eof_index = array->size;
+	array->size++;
+out:
+	nfs_readdir_release_array(page);
+	return ret;
+}
+
+static
+int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
+{
+	loff_t diff = desc->file->f_pos - desc->current_index;
+	unsigned int index;
+
+	if (diff < 0)
+		goto out_eof;
+	if (diff >= array->size) {
+		if (array->eof_index > 0)
+			goto out_eof;
+		desc->current_index += array->size;
+		return -EAGAIN;
+	}
+
+	index = (unsigned int)diff;
+	*desc->dir_cookie = array->array[index].cookie;
+	desc->cache_entry_index = index;
+	if (index == array->eof_index)
+		desc->eof = 1;
+	return 0;
+out_eof:
+	desc->eof = 1;
+	return -EBADCOOKIE;
+}
+
+static
+int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
+{
+	int i;
+	int status = -EAGAIN;
+
+	for (i = 0; i < array->size; i++) {
+		if (i == array->eof_index) {
+			desc->eof = 1;
+			status = -EBADCOOKIE;
+		}
+		if (array->array[i].cookie == *desc->dir_cookie) {
+			desc->cache_entry_index = i;
+			status = 0;
+			break;
+		}
+	}
+
+	return status;
+}
+
+static
+int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
+{
+	struct nfs_cache_array *array;
+	int status = -EBADCOOKIE;
+
+	if (desc->dir_cookie == NULL)
+		goto out;
+
+	array = nfs_readdir_get_array(desc->page);
+	if (IS_ERR(array)) {
+		status = PTR_ERR(array);
+		goto out;
+	}
+
+	if (*desc->dir_cookie == 0)
+		status = nfs_readdir_search_for_pos(array, desc);
+	else
+		status = nfs_readdir_search_for_cookie(array, desc);
+
+	nfs_readdir_release_array(desc->page);
+out:
+	return status;
+}
+
+/* Fill a page with xdr information before transferring to the cache page */
+static
+int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
+			struct nfs_entry *entry, struct file *file, struct inode *inode)
 {
-	struct file	*file = desc->file;
-	struct inode	*inode = file->f_path.dentry->d_inode;
 	struct rpc_cred	*cred = nfs_file_cred(file);
 	unsigned long	timestamp, gencount;
 	int		error;
 
-	dfprintk(DIRCACHE, "NFS: %s: reading cookie %Lu into page %lu\n",
-			__func__, (long long)desc->entry->cookie,
-			page->index);
-
  again:
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
-	error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, desc->entry->cookie, page,
+	error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages,
 					  NFS_SERVER(inode)->dtsize, desc->plus);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
@@ -208,190 +361,292 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
 	}
 	desc->timestamp = timestamp;
 	desc->gencount = gencount;
-	desc->timestamp_valid = 1;
-	SetPageUptodate(page);
-	/* Ensure consistent page alignment of the data.
-	 * Note: assumes we have exclusive access to this mapping either
-	 *	 through inode->i_mutex or some other mechanism.
-	 */
-	if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
-		/* Should never happen */
-		nfs_zap_mapping(inode, inode->i_mapping);
-	}
-	unlock_page(page);
-	return 0;
- error:
-	unlock_page(page);
-	return -EIO;
+error:
+	return error;
 }
 
-static inline
-int dir_decode(nfs_readdir_descriptor_t *desc)
+/* Fill in an entry based on the xdr code stored in desc->page */
+static
+int xdr_decode(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct xdr_stream *stream)
 {
-	__be32	*p = desc->ptr;
-	p = desc->decode(p, desc->entry, desc->plus);
+	__be32 *p = desc->decode(stream, entry, NFS_SERVER(desc->file->f_path.dentry->d_inode), desc->plus);
 	if (IS_ERR(p))
 		return PTR_ERR(p);
-	desc->ptr = p;
-	if (desc->timestamp_valid) {
-		desc->entry->fattr->time_start = desc->timestamp;
-		desc->entry->fattr->gencount = desc->gencount;
-	} else
-		desc->entry->fattr->valid &= ~NFS_ATTR_FATTR;
+
+	entry->fattr->time_start = desc->timestamp;
+	entry->fattr->gencount = desc->gencount;
 	return 0;
 }
 
-static inline
-void dir_page_release(nfs_readdir_descriptor_t *desc)
+static
+int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 {
-	kunmap(desc->page);
-	page_cache_release(desc->page);
-	desc->page = NULL;
-	desc->ptr = NULL;
+	struct nfs_inode *node;
+	if (dentry->d_inode == NULL)
+		goto different;
+	node = NFS_I(dentry->d_inode);
+	if (node->fh.size != entry->fh->size)
+		goto different;
+	if (strncmp(node->fh.data, entry->fh->data, node->fh.size) != 0)
+		goto different;
+	return 1;
+different:
+	return 0;
 }
 
-/*
- * Given a pointer to a buffer that has already been filled by a call
- * to readdir, find the next entry with cookie '*desc->dir_cookie'.
- *
- * If the end of the buffer has been reached, return -EAGAIN, if not,
- * return the offset within the buffer of the next entry to be
- * read.
- */
-static inline
-int find_dirent(nfs_readdir_descriptor_t *desc)
+static
+void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
-	struct nfs_entry *entry = desc->entry;
-	int		loop_count = 0,
-			status;
+	struct qstr filename = {
+		.len = entry->len,
+		.name = entry->name,
+	};
+	struct dentry *dentry;
+	struct dentry *alias;
+	struct inode *dir = parent->d_inode;
+	struct inode *inode;
 
-	while((status = dir_decode(desc)) == 0) {
-		dfprintk(DIRCACHE, "NFS: %s: examining cookie %Lu\n",
-				__func__, (unsigned long long)entry->cookie);
-		if (entry->prev_cookie == *desc->dir_cookie)
-			break;
-		if (loop_count++ > 200) {
-			loop_count = 0;
-			schedule();
+	if (filename.name[0] == '.') {
+		if (filename.len == 1)
+			return;
+		if (filename.len == 2 && filename.name[1] == '.')
+			return;
+	}
+	filename.hash = full_name_hash(filename.name, filename.len);
+
+	dentry = d_lookup(parent, &filename);
+	if (dentry != NULL) {
+		if (nfs_same_file(dentry, entry)) {
+			nfs_refresh_inode(dentry->d_inode, entry->fattr);
+			goto out;
+		} else {
+			d_drop(dentry);
+			dput(dentry);
 		}
 	}
-	return status;
+
+	dentry = d_alloc(parent, &filename);
+	if (dentry == NULL)
+		return;
+
+	dentry->d_op = NFS_PROTO(dir)->dentry_ops;
+	inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
+	if (IS_ERR(inode))
+		goto out;
+
+	alias = d_materialise_unique(dentry, inode);
+	if (IS_ERR(alias))
+		goto out;
+	else if (alias) {
+		nfs_set_verifier(alias, nfs_save_change_attribute(dir));
+		dput(alias);
+	} else
+		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+
+out:
+	dput(dentry);
+}
+
+/* Perform conversion from xdr to cache array */
+static
+void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
+				void *xdr_page, struct page *page, unsigned int buflen)
+{
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	__be32 *ptr = xdr_page;
+	int status;
+	struct nfs_cache_array *array;
+
+	buf.head->iov_base = xdr_page;
+	buf.head->iov_len = buflen;
+	buf.tail->iov_len = 0;
+	buf.page_base = 0;
+	buf.page_len = 0;
+	buf.buflen = buf.head->iov_len;
+	buf.len = buf.head->iov_len;
+
+	xdr_init_decode(&stream, &buf, ptr);
+
+
+	do {
+		status = xdr_decode(desc, entry, &stream);
+		if (status != 0)
+			break;
+
+		if (nfs_readdir_add_to_array(entry, page) == -1)
+			break;
+		if (desc->plus == 1)
+			nfs_prime_dcache(desc->file->f_path.dentry, entry);
+	} while (!entry->eof);
+
+	if (status == -EBADCOOKIE && entry->eof) {
+		array = nfs_readdir_get_array(page);
+		array->eof_index = array->size - 1;
+		status = 0;
+		nfs_readdir_release_array(page);
+	}
+}
+
+static
+void nfs_readdir_free_pagearray(struct page **pages, unsigned int npages)
+{
+	unsigned int i;
+	for (i = 0; i < npages; i++)
+		put_page(pages[i]);
+}
+
+static
+void nfs_readdir_free_large_page(void *ptr, struct page **pages,
+		unsigned int npages)
+{
+	vm_unmap_ram(ptr, npages);
+	nfs_readdir_free_pagearray(pages, npages);
 }
 
 /*
- * Given a pointer to a buffer that has already been filled by a call
- * to readdir, find the entry at offset 'desc->file->f_pos'.
- *
- * If the end of the buffer has been reached, return -EAGAIN, if not,
- * return the offset within the buffer of the next entry to be
- * read.
+ * nfs_readdir_large_page will allocate pages that must be freed with a call
+ * to nfs_readdir_free_large_page
  */
-static inline
-int find_dirent_index(nfs_readdir_descriptor_t *desc)
+static
+void *nfs_readdir_large_page(struct page **pages, unsigned int npages)
 {
-	struct nfs_entry *entry = desc->entry;
-	int		loop_count = 0,
-			status;
+	void *ptr;
+	unsigned int i;
+
+	for (i = 0; i < npages; i++) {
+		struct page *page = alloc_page(GFP_KERNEL);
+		if (page == NULL)
+			goto out_freepages;
+		pages[i] = page;
+	}
 
-	for(;;) {
-		status = dir_decode(desc);
-		if (status)
-			break;
+	ptr = vm_map_ram(pages, npages, 0, PAGE_KERNEL);
+	if (!IS_ERR_OR_NULL(ptr))
+		return ptr;
+out_freepages:
+	nfs_readdir_free_pagearray(pages, i);
+	return NULL;
+}
+
+static
+int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode)
+{
+	struct page *pages[NFS_MAX_READDIR_PAGES];
+	void *pages_ptr = NULL;
+	struct nfs_entry entry;
+	struct file	*file = desc->file;
+	struct nfs_cache_array *array;
+	int status = 0;
+	unsigned int array_size = ARRAY_SIZE(pages);
+
+	entry.prev_cookie = 0;
+	entry.cookie = *desc->dir_cookie;
+	entry.eof = 0;
+	entry.fh = nfs_alloc_fhandle();
+	entry.fattr = nfs_alloc_fattr();
+	if (entry.fh == NULL || entry.fattr == NULL)
+		goto out;
 
-		dfprintk(DIRCACHE, "NFS: found cookie %Lu at index %Ld\n",
-				(unsigned long long)entry->cookie, desc->current_index);
+	array = nfs_readdir_get_array(page);
+	memset(array, 0, sizeof(struct nfs_cache_array));
+	array->eof_index = -1;
 
-		if (desc->file->f_pos == desc->current_index) {
-			*desc->dir_cookie = entry->cookie;
+	pages_ptr = nfs_readdir_large_page(pages, array_size);
+	if (!pages_ptr)
+		goto out_release_array;
+	do {
+		status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
+
+		if (status < 0)
 			break;
-		}
-		desc->current_index++;
-		if (loop_count++ > 200) {
-			loop_count = 0;
-			schedule();
-		}
-	}
+		nfs_readdir_page_filler(desc, &entry, pages_ptr, page, array_size * PAGE_SIZE);
+	} while (array->eof_index < 0 && array->size < MAX_READDIR_ARRAY);
+
+	nfs_readdir_free_large_page(pages_ptr, pages, array_size);
+out_release_array:
+	nfs_readdir_release_array(page);
+out:
+	nfs_free_fattr(entry.fattr);
+	nfs_free_fhandle(entry.fh);
 	return status;
 }
 
 /*
- * Find the given page, and call find_dirent() or find_dirent_index in
- * order to try to return the next entry.
+ * Now we cache directories properly, by converting xdr information
+ * to an array that can be used for lookups later.  This results in
+ * fewer cache pages, since we can store more information on each page.
+ * We only need to convert from xdr once so future lookups are much simpler
  */
-static inline
-int find_dirent_page(nfs_readdir_descriptor_t *desc)
+static
+int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
 {
 	struct inode	*inode = desc->file->f_path.dentry->d_inode;
-	struct page	*page;
-	int		status;
 
-	dfprintk(DIRCACHE, "NFS: %s: searching page %ld for target %Lu\n",
-			__func__, desc->page_index,
-			(long long) *desc->dir_cookie);
+	if (nfs_readdir_xdr_to_array(desc, page, inode) < 0)
+		goto error;
+	SetPageUptodate(page);
 
-	/* If we find the page in the page_cache, we cannot be sure
-	 * how fresh the data is, so we will ignore readdir_plus attributes.
-	 */
-	desc->timestamp_valid = 0;
-	page = read_cache_page(inode->i_mapping, desc->page_index,
-			       (filler_t *)nfs_readdir_filler, desc);
-	if (IS_ERR(page)) {
-		status = PTR_ERR(page);
-		goto out;
+	if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
+		/* Should never happen */
+		nfs_zap_mapping(inode, inode->i_mapping);
 	}
+	unlock_page(page);
+	return 0;
+ error:
+	unlock_page(page);
+	return -EIO;
+}
 
-	/* NOTE: Someone else may have changed the READDIRPLUS flag */
-	desc->page = page;
-	desc->ptr = kmap(page);		/* matching kunmap in nfs_do_filldir */
-	if (*desc->dir_cookie != 0)
-		status = find_dirent(desc);
-	else
-		status = find_dirent_index(desc);
-	if (status < 0)
-		dir_page_release(desc);
- out:
-	dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
-	return status;
+static
+void cache_page_release(nfs_readdir_descriptor_t *desc)
+{
+	page_cache_release(desc->page);
+	desc->page = NULL;
+}
+
+static
+struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
+{
+	struct page *page;
+	page = read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
+			desc->page_index, (filler_t *)nfs_readdir_filler, desc);
+	if (IS_ERR(page))
+		desc->eof = 1;
+	return page;
 }
 
 /*
- * Recurse through the page cache pages, and return a
- * filled nfs_entry structure of the next directory entry if possible.
- *
- * The target for the search is '*desc->dir_cookie' if non-0,
- * 'desc->file->f_pos' otherwise
+ * Returns 0 if desc->dir_cookie was found on page desc->page_index
  */
+static
+int find_cache_page(nfs_readdir_descriptor_t *desc)
+{
+	int res;
+
+	desc->page = get_cache_page(desc);
+	if (IS_ERR(desc->page))
+		return PTR_ERR(desc->page);
+
+	res = nfs_readdir_search_array(desc);
+	if (res == 0)
+		return 0;
+	cache_page_release(desc);
+	return res;
+}
+
+/* Search for desc->dir_cookie from the beginning of the page cache */
 static inline
 int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
 {
-	int		loop_count = 0;
-	int		res;
-
-	/* Always search-by-index from the beginning of the cache */
-	if (*desc->dir_cookie == 0) {
-		dfprintk(DIRCACHE, "NFS: readdir_search_pagecache() searching for offset %Ld\n",
-				(long long)desc->file->f_pos);
-		desc->page_index = 0;
-		desc->entry->cookie = desc->entry->prev_cookie = 0;
-		desc->entry->eof = 0;
-		desc->current_index = 0;
-	} else
-		dfprintk(DIRCACHE, "NFS: readdir_search_pagecache() searching for cookie %Lu\n",
-				(unsigned long long)*desc->dir_cookie);
+	int res = -EAGAIN;
 
-	for (;;) {
-		res = find_dirent_page(desc);
+	while (1) {
+		res = find_cache_page(desc);
 		if (res != -EAGAIN)
 			break;
-		/* Align to beginning of next page */
-		desc->page_index ++;
-		if (loop_count++ > 200) {
-			loop_count = 0;
-			schedule();
-		}
+		desc->page_index++;
 	}
-
-	dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, res);
 	return res;
 }
 
@@ -400,8 +655,6 @@ static inline unsigned int dt_type(struct inode *inode)
 	return (inode->i_mode >> 12) & 15;
 }
 
-static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc);
-
 /*
  * Once we've found the start of the dirent within a page: fill 'er up...
  */
@@ -410,49 +663,36 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
 		   filldir_t filldir)
 {
 	struct file	*file = desc->file;
-	struct nfs_entry *entry = desc->entry;
-	struct dentry	*dentry = NULL;
-	u64		fileid;
-	int		loop_count = 0,
-			res;
-
-	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling starting @ cookie %Lu\n",
-			(unsigned long long)entry->cookie);
-
-	for(;;) {
-		unsigned d_type = DT_UNKNOWN;
-		/* Note: entry->prev_cookie contains the cookie for
-		 *	 retrieving the current dirent on the server */
-		fileid = entry->ino;
-
-		/* Get a dentry if we have one */
-		if (dentry != NULL)
-			dput(dentry);
-		dentry = nfs_readdir_lookup(desc);
+	int i = 0;
+	int res = 0;
+	struct nfs_cache_array *array = NULL;
+	unsigned int d_type = DT_UNKNOWN;
+	struct dentry *dentry = NULL;
 
-		/* Use readdirplus info */
-		if (dentry != NULL && dentry->d_inode != NULL) {
-			d_type = dt_type(dentry->d_inode);
-			fileid = NFS_FILEID(dentry->d_inode);
-		}
+	array = nfs_readdir_get_array(desc->page);
 
-		res = filldir(dirent, entry->name, entry->len, 
-			      file->f_pos, nfs_compat_user_ino64(fileid),
-			      d_type);
+	for (i = desc->cache_entry_index; i < array->size; i++) {
+		d_type = DT_UNKNOWN;
+
+		res = filldir(dirent, array->array[i].string.name,
+			array->array[i].string.len, file->f_pos,
+			nfs_compat_user_ino64(array->array[i].ino), d_type);
 		if (res < 0)
 			break;
 		file->f_pos++;
-		*desc->dir_cookie = entry->cookie;
-		if (dir_decode(desc) != 0) {
-			desc->page_index ++;
+		desc->cache_entry_index = i;
+		if (i < (array->size-1))
+			*desc->dir_cookie = array->array[i+1].cookie;
+		else
+			*desc->dir_cookie = array->last_cookie;
+		if (i == array->eof_index) {
+			desc->eof = 1;
 			break;
 		}
-		if (loop_count++ > 200) {
-			loop_count = 0;
-			schedule();
-		}
 	}
-	dir_page_release(desc);
+
+	nfs_readdir_release_array(desc->page);
+	cache_page_release(desc);
 	if (dentry != NULL)
 		dput(dentry);
 	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
@@ -476,12 +716,9 @@ static inline
 int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 		     filldir_t filldir)
 {
-	struct file	*file = desc->file;
-	struct inode	*inode = file->f_path.dentry->d_inode;
-	struct rpc_cred	*cred = nfs_file_cred(file);
 	struct page	*page = NULL;
 	int		status;
-	unsigned long	timestamp, gencount;
+	struct inode *inode = desc->file->f_path.dentry->d_inode;
 
 	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
 			(unsigned long long)*desc->dir_cookie);
@@ -491,38 +728,22 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 		status = -ENOMEM;
 		goto out;
 	}
-	timestamp = jiffies;
-	gencount = nfs_inc_attr_generation_counter();
-	status = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred,
-						*desc->dir_cookie, page,
-						NFS_SERVER(inode)->dtsize,
-						desc->plus);
-	desc->page = page;
-	desc->ptr = kmap(page);		/* matching kunmap in nfs_do_filldir */
-	if (status >= 0) {
-		desc->timestamp = timestamp;
-		desc->gencount = gencount;
-		desc->timestamp_valid = 1;
-		if ((status = dir_decode(desc)) == 0)
-			desc->entry->prev_cookie = *desc->dir_cookie;
-	} else
+
+	if (nfs_readdir_xdr_to_array(desc, page, inode) == -1) {
 		status = -EIO;
-	if (status < 0)
 		goto out_release;
+	}
 
+	desc->page_index = 0;
+	desc->page = page;
 	status = nfs_do_filldir(desc, dirent, filldir);
 
-	/* Reset read descriptor so it searches the page cache from
-	 * the start upon the next call to readdir_search_pagecache() */
-	desc->page_index = 0;
-	desc->entry->cookie = desc->entry->prev_cookie = 0;
-	desc->entry->eof = 0;
  out:
 	dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
 			__func__, status);
 	return status;
  out_release:
-	dir_page_release(desc);
+	cache_page_release(desc);
 	goto out;
 }
 
@@ -536,7 +757,6 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	struct inode	*inode = dentry->d_inode;
 	nfs_readdir_descriptor_t my_desc,
 			*desc = &my_desc;
-	struct nfs_entry my_entry;
 	int res = -ENOMEM;
 
 	dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n",
@@ -557,26 +777,17 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	desc->decode = NFS_PROTO(inode)->decode_dirent;
 	desc->plus = NFS_USE_READDIRPLUS(inode);
 
-	my_entry.cookie = my_entry.prev_cookie = 0;
-	my_entry.eof = 0;
-	my_entry.fh = nfs_alloc_fhandle();
-	my_entry.fattr = nfs_alloc_fattr();
-	if (my_entry.fh == NULL || my_entry.fattr == NULL)
-		goto out_alloc_failed;
-
-	desc->entry = &my_entry;
-
 	nfs_block_sillyrename(dentry);
 	res = nfs_revalidate_mapping(inode, filp->f_mapping);
 	if (res < 0)
 		goto out;
 
-	while(!desc->entry->eof) {
+	while (desc->eof != 1) {
 		res = readdir_search_pagecache(desc);
 
 		if (res == -EBADCOOKIE) {
 			/* This means either end of directory */
-			if (*desc->dir_cookie && desc->entry->cookie != *desc->dir_cookie) {
+			if (*desc->dir_cookie && desc->eof == 0) {
 				/* Or that the server has 'lost' a cookie */
 				res = uncached_readdir(desc, dirent, filldir);
 				if (res >= 0)
@@ -588,8 +799,9 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		if (res == -ETOOSMALL && desc->plus) {
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
 			nfs_zap_caches(inode);
+			desc->page_index = 0;
 			desc->plus = 0;
-			desc->entry->eof = 0;
+			desc->eof = 0;
 			continue;
 		}
 		if (res < 0)
@@ -605,9 +817,6 @@ out:
 	nfs_unblock_sillyrename(dentry);
 	if (res > 0)
 		res = 0;
-out_alloc_failed:
-	nfs_free_fattr(my_entry.fattr);
-	nfs_free_fhandle(my_entry.fh);
 	dfprintk(FILE, "NFS: readdir(%s/%s) returns %d\n",
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			res);
@@ -1029,10 +1238,63 @@ static int is_atomic_open(struct nameidata *nd)
 	return 1;
 }
 
+static struct nfs_open_context *nameidata_to_nfs_open_context(struct dentry *dentry, struct nameidata *nd)
+{
+	struct path path = {
+		.mnt = nd->path.mnt,
+		.dentry = dentry,
+	};
+	struct nfs_open_context *ctx;
+	struct rpc_cred *cred;
+	fmode_t fmode = nd->intent.open.flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
+
+	cred = rpc_lookup_cred();
+	if (IS_ERR(cred))
+		return ERR_CAST(cred);
+	ctx = alloc_nfs_open_context(&path, cred, fmode);
+	put_rpccred(cred);
+	if (ctx == NULL)
+		return ERR_PTR(-ENOMEM);
+	return ctx;
+}
+
+static int do_open(struct inode *inode, struct file *filp)
+{
+	nfs_fscache_set_inode_cookie(inode, filp);
+	return 0;
+}
+
+static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx)
+{
+	struct file *filp;
+	int ret = 0;
+
+	/* If the open_intent is for execute, we have an extra check to make */
+	if (ctx->mode & FMODE_EXEC) {
+		ret = nfs_may_open(ctx->path.dentry->d_inode,
+				ctx->cred,
+				nd->intent.open.flags);
+		if (ret < 0)
+			goto out;
+	}
+	filp = lookup_instantiate_filp(nd, ctx->path.dentry, do_open);
+	if (IS_ERR(filp))
+		ret = PTR_ERR(filp);
+	else
+		nfs_file_set_open_context(filp, ctx);
+out:
+	put_nfs_open_context(ctx);
+	return ret;
+}
+
 static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
+	struct nfs_open_context *ctx;
+	struct iattr attr;
 	struct dentry *res = NULL;
-	int error;
+	struct inode *inode;
+	int open_flags;
+	int err;
 
 	dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1054,13 +1316,32 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 		goto out;
 	}
 
+	ctx = nameidata_to_nfs_open_context(dentry, nd);
+	res = ERR_CAST(ctx);
+	if (IS_ERR(ctx))
+		goto out;
+
+	open_flags = nd->intent.open.flags;
+	if (nd->flags & LOOKUP_CREATE) {
+		attr.ia_mode = nd->intent.open.create_mode;
+		attr.ia_valid = ATTR_MODE;
+		if (!IS_POSIXACL(dir))
+			attr.ia_mode &= ~current_umask();
+	} else {
+		open_flags &= ~(O_EXCL | O_CREAT);
+		attr.ia_valid = 0;
+	}
+
 	/* Open the file on the server */
-	res = nfs4_atomic_open(dir, dentry, nd);
-	if (IS_ERR(res)) {
-		error = PTR_ERR(res);
-		switch (error) {
+	nfs_block_sillyrename(dentry->d_parent);
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
+	if (IS_ERR(inode)) {
+		nfs_unblock_sillyrename(dentry->d_parent);
+		put_nfs_open_context(ctx);
+		switch (PTR_ERR(inode)) {
 			/* Make a negative dentry */
 			case -ENOENT:
+				d_add(dentry, NULL);
 				res = NULL;
 				goto out;
 			/* This turned out not to be a regular file */
@@ -1072,11 +1353,25 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 					goto no_open;
 			/* case -EINVAL: */
 			default:
+				res = ERR_CAST(inode);
 				goto out;
 		}
-	} else if (res != NULL)
+	}
+	res = d_add_unique(dentry, inode);
+	nfs_unblock_sillyrename(dentry->d_parent);
+	if (res != NULL) {
+		dput(ctx->path.dentry);
+		ctx->path.dentry = dget(res);
 		dentry = res;
+	}
+	err = nfs_intent_set_file(nd, ctx);
+	if (err < 0) {
+		if (res != NULL)
+			dput(res);
+		return ERR_PTR(err);
+	}
 out:
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	return res;
 no_open:
 	return nfs_lookup(dir, dentry, nd);
@@ -1087,12 +1382,15 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct dentry *parent = NULL;
 	struct inode *inode = dentry->d_inode;
 	struct inode *dir;
+	struct nfs_open_context *ctx;
 	int openflags, ret = 0;
 
 	if (!is_atomic_open(nd) || d_mountpoint(dentry))
 		goto no_open;
+
 	parent = dget_parent(dentry);
 	dir = parent->d_inode;
+
 	/* We can't create new files in nfs_open_revalidate(), so we
 	 * optimize away revalidation of negative dentries.
 	 */
@@ -1112,99 +1410,96 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	/* We can't create new files, or truncate existing ones here */
 	openflags &= ~(O_CREAT|O_EXCL|O_TRUNC);
 
+	ctx = nameidata_to_nfs_open_context(dentry, nd);
+	ret = PTR_ERR(ctx);
+	if (IS_ERR(ctx))
+		goto out;
 	/*
 	 * Note: we're not holding inode->i_mutex and so may be racing with
 	 * operations that change the directory. We therefore save the
 	 * change attribute *before* we do the RPC call.
 	 */
-	ret = nfs4_open_revalidate(dir, dentry, openflags, nd);
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		switch (ret) {
+		case -EPERM:
+		case -EACCES:
+		case -EDQUOT:
+		case -ENOSPC:
+		case -EROFS:
+			goto out_put_ctx;
+		default:
+			goto out_drop;
+		}
+	}
+	iput(inode);
+	if (inode != dentry->d_inode)
+		goto out_drop;
+
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	ret = nfs_intent_set_file(nd, ctx);
+	if (ret >= 0)
+		ret = 1;
 out:
 	dput(parent);
-	if (!ret)
-		d_drop(dentry);
 	return ret;
+out_drop:
+	d_drop(dentry);
+	ret = 0;
+out_put_ctx:
+	put_nfs_open_context(ctx);
+	goto out;
+
 no_open_dput:
 	dput(parent);
 no_open:
 	return nfs_lookup_revalidate(dentry, nd);
 }
-#endif /* CONFIG_NFSV4 */
 
-static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc)
+static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode,
+		struct nameidata *nd)
 {
-	struct dentry *parent = desc->file->f_path.dentry;
-	struct inode *dir = parent->d_inode;
-	struct nfs_entry *entry = desc->entry;
-	struct dentry *dentry, *alias;
-	struct qstr name = {
-		.name = entry->name,
-		.len = entry->len,
-	};
-	struct inode *inode;
-	unsigned long verf = nfs_save_change_attribute(dir);
+	struct nfs_open_context *ctx = NULL;
+	struct iattr attr;
+	int error;
+	int open_flags = 0;
 
-	switch (name.len) {
-		case 2:
-			if (name.name[0] == '.' && name.name[1] == '.')
-				return dget_parent(parent);
-			break;
-		case 1:
-			if (name.name[0] == '.')
-				return dget(parent);
-	}
+	dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
+			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
 
-	spin_lock(&dir->i_lock);
-	if (NFS_I(dir)->cache_validity & NFS_INO_INVALID_DATA) {
-		spin_unlock(&dir->i_lock);
-		return NULL;
-	}
-	spin_unlock(&dir->i_lock);
+	attr.ia_mode = mode;
+	attr.ia_valid = ATTR_MODE;
 
-	name.hash = full_name_hash(name.name, name.len);
-	dentry = d_lookup(parent, &name);
-	if (dentry != NULL) {
-		/* Is this a positive dentry that matches the readdir info? */
-		if (dentry->d_inode != NULL &&
-				(NFS_FILEID(dentry->d_inode) == entry->ino ||
-				d_mountpoint(dentry))) {
-			if (!desc->plus || entry->fh->size == 0)
-				return dentry;
-			if (nfs_compare_fh(NFS_FH(dentry->d_inode),
-						entry->fh) == 0)
-				goto out_renew;
-		}
-		/* No, so d_drop to allow one to be created */
-		d_drop(dentry);
-		dput(dentry);
-	}
-	if (!desc->plus || !(entry->fattr->valid & NFS_ATTR_FATTR))
-		return NULL;
-	if (name.len > NFS_SERVER(dir)->namelen)
-		return NULL;
-	/* Note: caller is already holding the dir->i_mutex! */
-	dentry = d_alloc(parent, &name);
-	if (dentry == NULL)
-		return NULL;
-	dentry->d_op = NFS_PROTO(dir)->dentry_ops;
-	inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
-	if (IS_ERR(inode)) {
-		dput(dentry);
-		return NULL;
-	}
+	if ((nd->flags & LOOKUP_CREATE) != 0) {
+		open_flags = nd->intent.open.flags;
 
-	alias = d_materialise_unique(dentry, inode);
-	if (alias != NULL) {
-		dput(dentry);
-		if (IS_ERR(alias))
-			return NULL;
-		dentry = alias;
+		ctx = nameidata_to_nfs_open_context(dentry, nd);
+		error = PTR_ERR(ctx);
+		if (IS_ERR(ctx))
+			goto out_err_drop;
 	}
 
-out_renew:
-	nfs_set_verifier(dentry, verf);
-	return dentry;
+	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx);
+	if (error != 0)
+		goto out_put_ctx;
+	if (ctx != NULL) {
+		error = nfs_intent_set_file(nd, ctx);
+		if (error < 0)
+			goto out_err;
+	}
+	return 0;
+out_put_ctx:
+	if (ctx != NULL)
+		put_nfs_open_context(ctx);
+out_err_drop:
+	d_drop(dentry);
+out_err:
+	return error;
 }
 
+#endif /* CONFIG_NFSV4 */
+
 /*
  * Code common to create, mkdir, and mknod.
  */
@@ -1258,7 +1553,6 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 {
 	struct iattr attr;
 	int error;
-	int open_flags = 0;
 
 	dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1266,10 +1560,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
-	if ((nd->flags & LOOKUP_CREATE) != 0)
-		open_flags = nd->intent.open.flags;
-
-	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, nd);
+	error = NFS_PROTO(dir)->create(dir, dentry, &attr, 0, NULL);
 	if (error != 0)
 		goto out_err;
 	return 0;
@@ -1351,76 +1642,6 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 	return error;
 }
 
-static int nfs_sillyrename(struct inode *dir, struct dentry *dentry)
-{
-	static unsigned int sillycounter;
-	const int      fileidsize  = sizeof(NFS_FILEID(dentry->d_inode))*2;
-	const int      countersize = sizeof(sillycounter)*2;
-	const int      slen        = sizeof(".nfs")+fileidsize+countersize-1;
-	char           silly[slen+1];
-	struct qstr    qsilly;
-	struct dentry *sdentry;
-	int            error = -EIO;
-
-	dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name, 
-		atomic_read(&dentry->d_count));
-	nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
-
-	/*
-	 * We don't allow a dentry to be silly-renamed twice.
-	 */
-	error = -EBUSY;
-	if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
-		goto out;
-
-	sprintf(silly, ".nfs%*.*Lx",
-		fileidsize, fileidsize,
-		(unsigned long long)NFS_FILEID(dentry->d_inode));
-
-	/* Return delegation in anticipation of the rename */
-	nfs_inode_return_delegation(dentry->d_inode);
-
-	sdentry = NULL;
-	do {
-		char *suffix = silly + slen - countersize;
-
-		dput(sdentry);
-		sillycounter++;
-		sprintf(suffix, "%*.*x", countersize, countersize, sillycounter);
-
-		dfprintk(VFS, "NFS: trying to rename %s to %s\n",
-				dentry->d_name.name, silly);
-		
-		sdentry = lookup_one_len(silly, dentry->d_parent, slen);
-		/*
-		 * N.B. Better to return EBUSY here ... it could be
-		 * dangerous to delete the file while it's in use.
-		 */
-		if (IS_ERR(sdentry))
-			goto out;
-	} while(sdentry->d_inode != NULL); /* need negative lookup */
-
-	qsilly.name = silly;
-	qsilly.len  = strlen(silly);
-	if (dentry->d_inode) {
-		error = NFS_PROTO(dir)->rename(dir, &dentry->d_name,
-				dir, &qsilly);
-		nfs_mark_for_revalidate(dentry->d_inode);
-	} else
-		error = NFS_PROTO(dir)->rename(dir, &dentry->d_name,
-				dir, &qsilly);
-	if (!error) {
-		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-		d_move(dentry, sdentry);
-		error = nfs_async_unlink(dir, dentry);
- 		/* If we return 0 we don't unlink */
-	}
-	dput(sdentry);
-out:
-	return error;
-}
-
 /*
  * Remove a file after making sure there are no pending writes,
  * and after checking that the file has only one user. 
@@ -1711,14 +1932,14 @@ static void nfs_access_free_list(struct list_head *head)
 int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
 {
 	LIST_HEAD(head);
-	struct nfs_inode *nfsi;
+	struct nfs_inode *nfsi, *next;
 	struct nfs_access_entry *cache;
 
 	if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
 		return (nr_to_scan == 0) ? 0 : -1;
 
 	spin_lock(&nfs_access_lru_lock);
-	list_for_each_entry(nfsi, &nfs_access_lru_list, access_cache_inode_lru) {
+	list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
 		struct inode *inode;
 
 		if (nr_to_scan-- == 0)

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 @@ out_err:
  */
 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 @@ out6:
 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 @@ out:
  */
 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/nfs4proc.c

@@ -129,7 +129,7 @@ const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD0_MAXREAD
 			| FATTR4_WORD0_MAXWRITE
 			| FATTR4_WORD0_LEASE_TIME,
-			0
+			FATTR4_WORD1_TIME_DELTA
 };
 
 const u32 nfs4_fs_locations_bitmap[2] = {
@@ -255,9 +255,6 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 			nfs4_state_mark_reclaim_nograce(clp, state);
 			goto do_state_recovery;
 		case -NFS4ERR_STALE_STATEID:
-			if (state == NULL)
-				break;
-			nfs4_state_mark_reclaim_reboot(clp, state);
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
 			goto do_state_recovery;
@@ -334,10 +331,12 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
  * Must be called while holding tbl->slot_tbl_lock
  */
 static void
-nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
+nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *free_slot)
 {
+	int free_slotid = free_slot - tbl->slots;
 	int slotid = free_slotid;
 
+	BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE);
 	/* clear used bit in bitmap */
 	__clear_bit(slotid, tbl->used_slots);
 
@@ -379,7 +378,7 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 	struct nfs4_slot_table *tbl;
 
 	tbl = &res->sr_session->fc_slot_table;
-	if (res->sr_slotid == NFS4_MAX_SLOT_TABLE) {
+	if (!res->sr_slot) {
 		/* just wake up the next guy waiting since
 		 * we may have not consumed a slot after all */
 		dprintk("%s: No slot\n", __func__);
@@ -387,17 +386,15 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 	}
 
 	spin_lock(&tbl->slot_tbl_lock);
-	nfs4_free_slot(tbl, res->sr_slotid);
+	nfs4_free_slot(tbl, res->sr_slot);
 	nfs41_check_drain_session_complete(res->sr_session);
 	spin_unlock(&tbl->slot_tbl_lock);
-	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+	res->sr_slot = NULL;
 }
 
 static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
 	unsigned long timestamp;
-	struct nfs4_slot_table *tbl;
-	struct nfs4_slot *slot;
 	struct nfs_client *clp;
 
 	/*
@@ -410,17 +407,14 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		res->sr_status = NFS_OK;
 
 	/* -ERESTARTSYS can result in skipping nfs41_sequence_setup */
-	if (res->sr_slotid == NFS4_MAX_SLOT_TABLE)
+	if (!res->sr_slot)
 		goto out;
 
-	tbl = &res->sr_session->fc_slot_table;
-	slot = tbl->slots + res->sr_slotid;
-
 	/* Check the SEQUENCE operation status */
 	switch (res->sr_status) {
 	case 0:
 		/* Update the slot's sequence and clientid lease timer */
-		++slot->seq_nr;
+		++res->sr_slot->seq_nr;
 		timestamp = res->sr_renewal_time;
 		clp = res->sr_session->clp;
 		do_renew_lease(clp, timestamp);
@@ -433,12 +427,14 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		 * returned NFS4ERR_DELAY as per Section 2.10.6.2
 		 * of RFC5661.
 		 */
-		dprintk("%s: slot=%d seq=%d: Operation in progress\n",
-				__func__, res->sr_slotid, slot->seq_nr);
+		dprintk("%s: slot=%ld seq=%d: Operation in progress\n",
+			__func__,
+			res->sr_slot - res->sr_session->fc_slot_table.slots,
+			res->sr_slot->seq_nr);
 		goto out_retry;
 	default:
 		/* Just update the slot sequence no. */
-		++slot->seq_nr;
+		++res->sr_slot->seq_nr;
 	}
 out:
 	/* The session may be reset by one of the error handlers. */
@@ -505,10 +501,9 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
 
 	dprintk("--> %s\n", __func__);
 	/* slot already allocated? */
-	if (res->sr_slotid != NFS4_MAX_SLOT_TABLE)
+	if (res->sr_slot != NULL)
 		return 0;
 
-	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
 	tbl = &session->fc_slot_table;
 
 	spin_lock(&tbl->slot_tbl_lock);
@@ -550,7 +545,7 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
 	dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
 
 	res->sr_session = session;
-	res->sr_slotid = slotid;
+	res->sr_slot = slot;
 	res->sr_renewal_time = jiffies;
 	res->sr_status_flags = 0;
 	/*
@@ -576,8 +571,9 @@ int nfs4_setup_sequence(const struct nfs_server *server,
 		goto out;
 	}
 
-	dprintk("--> %s clp %p session %p sr_slotid %d\n",
-		__func__, session->clp, session, res->sr_slotid);
+	dprintk("--> %s clp %p session %p sr_slot %ld\n",
+		__func__, session->clp, session, res->sr_slot ?
+			res->sr_slot - session->fc_slot_table.slots : -1);
 
 	ret = nfs41_setup_sequence(session, args, res, cache_reply,
 				   task);
@@ -650,7 +646,7 @@ static int nfs4_call_sync_sequence(struct nfs_server *server,
 		.callback_data = &data
 	};
 
-	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+	res->sr_slot = NULL;
 	if (privileged)
 		task_setup.callback_ops = &nfs41_call_priv_sync_ops;
 	task = rpc_run_task(&task_setup);
@@ -735,7 +731,6 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 	p->o_res.server = p->o_arg.server;
 	nfs_fattr_init(&p->f_attr);
 	nfs_fattr_init(&p->dir_attr);
-	p->o_res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 }
 
 static struct nfs4_opendata *nfs4_opendata_alloc(struct path *path,
@@ -1120,6 +1115,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
 	clear_bit(NFS_DELEGATED_STATE, &state->flags);
 	smp_rmb();
 	if (state->n_rdwr != 0) {
+		clear_bit(NFS_O_RDWR_STATE, &state->flags);
 		ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
 		if (ret != 0)
 			return ret;
@@ -1127,6 +1123,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
 			return -ESTALE;
 	}
 	if (state->n_wronly != 0) {
+		clear_bit(NFS_O_WRONLY_STATE, &state->flags);
 		ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
 		if (ret != 0)
 			return ret;
@@ -1134,6 +1131,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
 			return -ESTALE;
 	}
 	if (state->n_rdonly != 0) {
+		clear_bit(NFS_O_RDONLY_STATE, &state->flags);
 		ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
 		if (ret != 0)
 			return ret;
@@ -1188,7 +1186,7 @@ static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state
 	int err;
 	do {
 		err = _nfs4_do_open_reclaim(ctx, state);
-		if (err != -NFS4ERR_DELAY && err != -EKEYEXPIRED)
+		if (err != -NFS4ERR_DELAY)
 			break;
 		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
@@ -1258,6 +1256,13 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_BAD_STATEID:
 				nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+			case -EKEYEXPIRED:
+				/*
+				 * User RPCSEC_GSS context has expired.
+				 * We cannot recover this stateid now, so
+				 * skip it and allow recovery thread to
+				 * proceed.
+				 */
 			case -ENOMEM:
 				err = 0;
 				goto out;
@@ -1605,7 +1610,6 @@ static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state
 			goto out;
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
-		case -EKEYEXPIRED:
 			nfs4_handle_exception(server, err, &exception);
 			err = 0;
 		}
@@ -1975,7 +1979,6 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, i
 	calldata->res.fattr = &calldata->fattr;
 	calldata->res.seqid = calldata->arg.seqid;
 	calldata->res.server = server;
-	calldata->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	path_get(path);
 	calldata->path = *path;
 
@@ -1998,120 +2001,17 @@ out:
 	return status;
 }
 
-static int nfs4_intent_set_file(struct nameidata *nd, struct path *path, struct nfs4_state *state, fmode_t fmode)
-{
-	struct file *filp;
-	int ret;
-
-	/* If the open_intent is for execute, we have an extra check to make */
-	if (fmode & FMODE_EXEC) {
-		ret = nfs_may_open(state->inode,
-				state->owner->so_cred,
-				nd->intent.open.flags);
-		if (ret < 0)
-			goto out_close;
-	}
-	filp = lookup_instantiate_filp(nd, path->dentry, NULL);
-	if (!IS_ERR(filp)) {
-		struct nfs_open_context *ctx;
-		ctx = nfs_file_open_context(filp);
-		ctx->state = state;
-		return 0;
-	}
-	ret = PTR_ERR(filp);
-out_close:
-	nfs4_close_sync(path, state, fmode & (FMODE_READ|FMODE_WRITE));
-	return ret;
-}
-
-struct dentry *
-nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct inode *
+nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags, struct iattr *attr)
 {
-	struct path path = {
-		.mnt = nd->path.mnt,
-		.dentry = dentry,
-	};
-	struct dentry *parent;
-	struct iattr attr;
-	struct rpc_cred *cred;
 	struct nfs4_state *state;
-	struct dentry *res;
-	int open_flags = nd->intent.open.flags;
-	fmode_t fmode = open_flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
-
-	if (nd->flags & LOOKUP_CREATE) {
-		attr.ia_mode = nd->intent.open.create_mode;
-		attr.ia_valid = ATTR_MODE;
-		if (!IS_POSIXACL(dir))
-			attr.ia_mode &= ~current_umask();
-	} else {
-		open_flags &= ~O_EXCL;
-		attr.ia_valid = 0;
-		BUG_ON(open_flags & O_CREAT);
-	}
 
-	cred = rpc_lookup_cred();
-	if (IS_ERR(cred))
-		return (struct dentry *)cred;
-	parent = dentry->d_parent;
 	/* Protect against concurrent sillydeletes */
-	nfs_block_sillyrename(parent);
-	state = nfs4_do_open(dir, &path, fmode, open_flags, &attr, cred);
-	put_rpccred(cred);
-	if (IS_ERR(state)) {
-		if (PTR_ERR(state) == -ENOENT) {
-			d_add(dentry, NULL);
-			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-		}
-		nfs_unblock_sillyrename(parent);
-		return (struct dentry *)state;
-	}
-	res = d_add_unique(dentry, igrab(state->inode));
-	if (res != NULL)
-		path.dentry = res;
-	nfs_set_verifier(path.dentry, nfs_save_change_attribute(dir));
-	nfs_unblock_sillyrename(parent);
-	nfs4_intent_set_file(nd, &path, state, fmode);
-	return res;
-}
-
-int
-nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, struct nameidata *nd)
-{
-	struct path path = {
-		.mnt = nd->path.mnt,
-		.dentry = dentry,
-	};
-	struct rpc_cred *cred;
-	struct nfs4_state *state;
-	fmode_t fmode = openflags & (FMODE_READ | FMODE_WRITE);
-
-	cred = rpc_lookup_cred();
-	if (IS_ERR(cred))
-		return PTR_ERR(cred);
-	state = nfs4_do_open(dir, &path, fmode, openflags, NULL, cred);
-	put_rpccred(cred);
-	if (IS_ERR(state)) {
-		switch (PTR_ERR(state)) {
-			case -EPERM:
-			case -EACCES:
-			case -EDQUOT:
-			case -ENOSPC:
-			case -EROFS:
-				return PTR_ERR(state);
-			default:
-				goto out_drop;
-		}
-	}
-	if (state->inode == dentry->d_inode) {
-		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-		nfs4_intent_set_file(nd, &path, state, fmode);
-		return 1;
-	}
-	nfs4_close_sync(&path, state, fmode);
-out_drop:
-	d_drop(dentry);
-	return 0;
+	state = nfs4_do_open(dir, &ctx->path, ctx->mode, open_flags, attr, ctx->cred);
+	if (IS_ERR(state))
+		return ERR_CAST(state);
+	ctx->state = state;
+	return igrab(state->inode);
 }
 
 static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
@@ -2568,36 +2468,34 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page,
 
 static int
 nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-                 int flags, struct nameidata *nd)
+                 int flags, struct nfs_open_context *ctx)
 {
-	struct path path = {
-		.mnt = nd->path.mnt,
+	struct path my_path = {
 		.dentry = dentry,
 	};
+	struct path *path = &my_path;
 	struct nfs4_state *state;
-	struct rpc_cred *cred;
-	fmode_t fmode = flags & (FMODE_READ | FMODE_WRITE);
+	struct rpc_cred *cred = NULL;
+	fmode_t fmode = 0;
 	int status = 0;
 
-	cred = rpc_lookup_cred();
-	if (IS_ERR(cred)) {
-		status = PTR_ERR(cred);
-		goto out;
+	if (ctx != NULL) {
+		cred = ctx->cred;
+		path = &ctx->path;
+		fmode = ctx->mode;
 	}
-	state = nfs4_do_open(dir, &path, fmode, flags, sattr, cred);
+	state = nfs4_do_open(dir, path, fmode, flags, sattr, cred);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
 		status = PTR_ERR(state);
-		goto out_putcred;
+		goto out;
 	}
 	d_add(dentry, igrab(state->inode));
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-	if (status == 0 && (nd->flags & LOOKUP_OPEN) != 0)
-		status = nfs4_intent_set_file(nd, &path, state, fmode);
+	if (ctx != NULL)
+		ctx->state = state;
 	else
-		nfs4_close_sync(&path, state, fmode);
-out_putcred:
-	put_rpccred(cred);
+		nfs4_close_sync(path, state, fmode);
 out:
 	return status;
 }
@@ -2655,6 +2553,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 
 	args->bitmask = server->cache_consistency_bitmask;
 	res->server = server;
+	res->seq_res.sr_slot = NULL;
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE];
 }
 
@@ -2671,18 +2570,46 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 	return 1;
 }
 
+static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
+{
+	struct nfs_server *server = NFS_SERVER(dir);
+	struct nfs_renameargs *arg = msg->rpc_argp;
+	struct nfs_renameres *res = msg->rpc_resp;
+
+	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME];
+	arg->bitmask = server->attr_bitmask;
+	res->server = server;
+}
+
+static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
+				 struct inode *new_dir)
+{
+	struct nfs_renameres *res = task->tk_msg.rpc_resp;
+
+	if (!nfs4_sequence_done(task, &res->seq_res))
+		return 0;
+	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+		return 0;
+
+	update_changeattr(old_dir, &res->old_cinfo);
+	nfs_post_op_update_inode(old_dir, res->old_fattr);
+	update_changeattr(new_dir, &res->new_cinfo);
+	nfs_post_op_update_inode(new_dir, res->new_fattr);
+	return 1;
+}
+
 static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
 		struct inode *new_dir, struct qstr *new_name)
 {
 	struct nfs_server *server = NFS_SERVER(old_dir);
-	struct nfs4_rename_arg arg = {
+	struct nfs_renameargs arg = {
 		.old_dir = NFS_FH(old_dir),
 		.new_dir = NFS_FH(new_dir),
 		.old_name = old_name,
 		.new_name = new_name,
 		.bitmask = server->attr_bitmask,
 	};
-	struct nfs4_rename_res res = {
+	struct nfs_renameres res = {
 		.server = server,
 	};
 	struct rpc_message msg = {
@@ -2896,15 +2823,16 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 }
 
 static int _nfs4_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 nfs4_readdir_arg args = {
 		.fh = NFS_FH(dir),
-		.pages = &page,
+		.pages = pages,
 		.pgbase = 0,
 		.count = count,
 		.bitmask = NFS_SERVER(dentry->d_inode)->attr_bitmask,
+		.plus = plus,
 	};
 	struct nfs4_readdir_res res;
 	struct rpc_message msg = {
@@ -2932,14 +2860,14 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 }
 
 static int nfs4_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 nfs4_exception exception = { };
 	int err;
 	do {
 		err = nfs4_handle_exception(NFS_SERVER(dentry->d_inode),
 				_nfs4_proc_readdir(dentry, cred, cookie,
-					page, count, plus),
+					pages, count, plus),
 				&exception);
 	} while (exception.retry);
 	return err;
@@ -3490,9 +3418,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			nfs4_state_mark_reclaim_nograce(clp, state);
 			goto do_state_recovery;
 		case -NFS4ERR_STALE_STATEID:
-			if (state == NULL)
-				break;
-			nfs4_state_mark_reclaim_reboot(clp, state);
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
 			goto do_state_recovery;
@@ -3626,7 +3551,6 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 			case -NFS4ERR_RESOURCE:
 				/* The IBM lawyers misread another document! */
 			case -NFS4ERR_DELAY:
-			case -EKEYEXPIRED:
 				err = nfs4_delay(clp->cl_rpcclient, &timeout);
 		}
 	} while (err == 0);
@@ -3721,7 +3645,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	memcpy(&data->stateid, stateid, sizeof(data->stateid));
 	data->res.fattr = &data->fattr;
 	data->res.server = server;
-	data->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	nfs_fattr_init(data->res.fattr);
 	data->timestamp = jiffies;
 	data->rpc_status = 0;
@@ -3874,7 +3797,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	p->arg.fl = &p->fl;
 	p->arg.seqid = seqid;
 	p->res.seqid = seqid;
-	p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	p->arg.stateid = &lsp->ls_stateid;
 	p->lsp = lsp;
 	atomic_inc(&lsp->ls_count);
@@ -4054,7 +3976,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
 	p->arg.lock_owner.id = lsp->ls_id.id;
 	p->res.lock_seqid = p->arg.lock_seqid;
-	p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	p->lsp = lsp;
 	p->server = server;
 	atomic_inc(&lsp->ls_count);
@@ -4241,7 +4162,7 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
 		if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
 			return 0;
 		err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM);
-		if (err != -NFS4ERR_DELAY && err != -EKEYEXPIRED)
+		if (err != -NFS4ERR_DELAY)
 			break;
 		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
@@ -4266,7 +4187,6 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
 			goto out;
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
-		case -EKEYEXPIRED:
 			nfs4_handle_exception(server, err, &exception);
 			err = 0;
 		}
@@ -4412,13 +4332,21 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 				nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
 				err = 0;
 				goto out;
+			case -EKEYEXPIRED:
+				/*
+				 * User RPCSEC_GSS context has expired.
+				 * We cannot recover this stateid now, so
+				 * skip it and allow recovery thread to
+				 * proceed.
+				 */
+				err = 0;
+				goto out;
 			case -ENOMEM:
 			case -NFS4ERR_DENIED:
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 				err = 0;
 				goto out;
 			case -NFS4ERR_DELAY:
-			case -EKEYEXPIRED:
 				break;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
@@ -4647,7 +4575,6 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case -NFS4ERR_DELAY:
 	case -NFS4ERR_GRACE:
-	case -EKEYEXPIRED:
 		dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status);
 		rpc_delay(task, NFS4_POLL_RETRY_MIN);
 		task->tk_status = 0;
@@ -4687,7 +4614,6 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	};
 	int status;
 
-	res.lr_seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	dprintk("--> %s\n", __func__);
 	task = rpc_run_task(&task_setup);
 
@@ -5111,7 +5037,6 @@ static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client
 {
 	switch(task->tk_status) {
 	case -NFS4ERR_DELAY:
-	case -EKEYEXPIRED:
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		return -EAGAIN;
 	default:
@@ -5180,12 +5105,11 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
 
 	if (!atomic_inc_not_zero(&clp->cl_count))
 		return ERR_PTR(-EIO);
-	calldata = kmalloc(sizeof(*calldata), GFP_NOFS);
+	calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
 	if (calldata == NULL) {
 		nfs_put_client(clp);
 		return ERR_PTR(-ENOMEM);
 	}
-	calldata->res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	msg.rpc_argp = &calldata->args;
 	msg.rpc_resp = &calldata->res;
 	calldata->clp = clp;
@@ -5254,7 +5178,6 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 	case -NFS4ERR_WRONG_CRED: /* What to do here? */
 		break;
 	case -NFS4ERR_DELAY:
-	case -EKEYEXPIRED:
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		return -EAGAIN;
 	default:
@@ -5317,7 +5240,6 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
 		goto out;
 	calldata->clp = clp;
 	calldata->arg.one_fs = 0;
-	calldata->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 
 	msg.rpc_argp = &calldata->arg;
 	msg.rpc_resp = &calldata->res;
@@ -5443,6 +5365,8 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.unlink_setup	= nfs4_proc_unlink_setup,
 	.unlink_done	= nfs4_proc_unlink_done,
 	.rename		= nfs4_proc_rename,
+	.rename_setup	= nfs4_proc_rename_setup,
+	.rename_done	= nfs4_proc_rename_done,
 	.link		= nfs4_proc_link,
 	.symlink	= nfs4_proc_symlink,
 	.mkdir		= nfs4_proc_mkdir,
@@ -5463,6 +5387,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.lock		= nfs4_proc_lock,
 	.clear_acl_cache = nfs4_zap_acl_attr,
 	.close_context  = nfs4_close_context,
+	.open_context	= nfs4_atomic_open,
 };
 
 /*

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 @@ restart:
 				/* 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/nfs4xdr.c

@@ -816,7 +816,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
 	if (iap->ia_valid & ATTR_MODE)
 		len += 4;
 	if (iap->ia_valid & ATTR_UID) {
-		owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name);
+		owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name, IDMAP_NAMESZ);
 		if (owner_namelen < 0) {
 			dprintk("nfs: couldn't resolve uid %d to string\n",
 					iap->ia_uid);
@@ -828,7 +828,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
 		len += 4 + (XDR_QUADLEN(owner_namelen) << 2);
 	}
 	if (iap->ia_valid & ATTR_GID) {
-		owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group);
+		owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group, IDMAP_NAMESZ);
 		if (owner_grouplen < 0) {
 			dprintk("nfs: couldn't resolve gid %d to string\n",
 					iap->ia_gid);
@@ -1385,24 +1385,35 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args,
 
 static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr)
 {
-	uint32_t attrs[2] = {
-		FATTR4_WORD0_RDATTR_ERROR|FATTR4_WORD0_FILEID,
-		FATTR4_WORD1_MOUNTED_ON_FILEID,
-	};
+	uint32_t attrs[2] = {0, 0};
+	uint32_t dircount = readdir->count >> 1;
 	__be32 *p;
 
+	if (readdir->plus) {
+		attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
+			FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE;
+		attrs[1] |= FATTR4_WORD1_MODE|FATTR4_WORD1_NUMLINKS|FATTR4_WORD1_OWNER|
+			FATTR4_WORD1_OWNER_GROUP|FATTR4_WORD1_RAWDEV|
+			FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
+			FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
+		dircount >>= 1;
+	}
+	attrs[0] |= FATTR4_WORD0_RDATTR_ERROR|FATTR4_WORD0_FILEID;
+	attrs[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID;
+	/* Switch to mounted_on_fileid if the server supports it */
+	if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)
+		attrs[0] &= ~FATTR4_WORD0_FILEID;
+	else
+		attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
+
 	p = reserve_space(xdr, 12+NFS4_VERIFIER_SIZE+20);
 	*p++ = cpu_to_be32(OP_READDIR);
 	p = xdr_encode_hyper(p, readdir->cookie);
 	p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE);
-	*p++ = cpu_to_be32(readdir->count >> 1);  /* We're not doing readdirplus */
+	*p++ = cpu_to_be32(dircount);
 	*p++ = cpu_to_be32(readdir->count);
 	*p++ = cpu_to_be32(2);
-	/* Switch to mounted_on_fileid if the server supports it */
-	if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)
-		attrs[0] &= ~FATTR4_WORD0_FILEID;
-	else
-		attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
+
 	*p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]);
 	*p = cpu_to_be32(attrs[1] & readdir->bitmask[1]);
 	hdr->nops++;
@@ -1823,7 +1834,7 @@ static int nfs4_xdr_enc_remove(struct rpc_rqst *req, __be32 *p, const struct nfs
 /*
  * Encode RENAME request
  */
-static int nfs4_xdr_enc_rename(struct rpc_rqst *req, __be32 *p, const struct nfs4_rename_arg *args)
+static int nfs4_xdr_enc_rename(struct rpc_rqst *req, __be32 *p, const struct nfs_renameargs *args)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
@@ -2676,7 +2687,10 @@ out_overflow:
 static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask)
 {
 	if (likely(bitmap[0] & FATTR4_WORD0_SUPPORTED_ATTRS)) {
-		decode_attr_bitmap(xdr, bitmask);
+		int ret;
+		ret = decode_attr_bitmap(xdr, bitmask);
+		if (unlikely(ret < 0))
+			return ret;
 		bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
 	} else
 		bitmask[0] = bitmask[1] = 0;
@@ -2848,6 +2862,56 @@ out_overflow:
 	return -EIO;
 }
 
+static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap)
+{
+	__be32 *p;
+
+	if (unlikely(bitmap[0] & (FATTR4_WORD0_RDATTR_ERROR - 1U)))
+		return -EIO;
+	if (likely(bitmap[0] & FATTR4_WORD0_RDATTR_ERROR)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
+		bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR;
+	}
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fh *fh)
+{
+	__be32 *p;
+	int len;
+
+	if (fh != NULL)
+		memset(fh, 0, sizeof(*fh));
+
+	if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEHANDLE - 1U)))
+		return -EIO;
+	if (likely(bitmap[0] & FATTR4_WORD0_FILEHANDLE)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
+		len = be32_to_cpup(p);
+		if (len > NFS4_FHSIZE)
+			return -EIO;
+		p = xdr_inline_decode(xdr, len);
+		if (unlikely(!p))
+			goto out_overflow;
+		if (fh != NULL) {
+			memcpy(fh->data, p, len);
+			fh->size = len;
+		}
+		bitmap[0] &= ~FATTR4_WORD0_FILEHANDLE;
+	}
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
 {
 	__be32 *p;
@@ -3521,6 +3585,24 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s
 	return status;
 }
 
+static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap,
+				  struct timespec *time)
+{
+	int status = 0;
+
+	time->tv_sec = 0;
+	time->tv_nsec = 0;
+	if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_DELTA - 1U)))
+		return -EIO;
+	if (likely(bitmap[1] & FATTR4_WORD1_TIME_DELTA)) {
+		status = decode_attr_time(xdr, time);
+		bitmap[1] &= ~FATTR4_WORD1_TIME_DELTA;
+	}
+	dprintk("%s: time_delta=%ld %ld\n", __func__, (long)time->tv_sec,
+		(long)time->tv_nsec);
+	return status;
+}
+
 static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
 {
 	int status = 0;
@@ -3744,29 +3826,14 @@ xdr_error:
 	return status;
 }
 
-static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
+		struct nfs_fattr *fattr, struct nfs_fh *fh,
 		const struct nfs_server *server, int may_sleep)
 {
-	__be32 *savep;
-	uint32_t attrlen,
-		 bitmap[2] = {0},
-		 type;
 	int status;
 	umode_t fmode = 0;
 	uint64_t fileid;
-
-	status = decode_op_hdr(xdr, OP_GETATTR);
-	if (status < 0)
-		goto xdr_error;
-
-	status = decode_attr_bitmap(xdr, bitmap);
-	if (status < 0)
-		goto xdr_error;
-
-	status = decode_attr_length(xdr, &attrlen, &savep);
-	if (status < 0)
-		goto xdr_error;
-
+	uint32_t type;
 
 	status = decode_attr_type(xdr, bitmap, &type);
 	if (status < 0)
@@ -3792,6 +3859,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
 		goto xdr_error;
 	fattr->valid |= status;
 
+	status = decode_attr_error(xdr, bitmap);
+	if (status < 0)
+		goto xdr_error;
+
+	status = decode_attr_filehandle(xdr, bitmap, fh);
+	if (status < 0)
+		goto xdr_error;
+
 	status = decode_attr_fileid(xdr, bitmap, &fattr->fileid);
 	if (status < 0)
 		goto xdr_error;
@@ -3862,12 +3937,46 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
 		fattr->valid |= status;
 	}
 
+xdr_error:
+	dprintk("%s: xdr returned %d\n", __func__, -status);
+	return status;
+}
+
+static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+		struct nfs_fh *fh, const struct nfs_server *server, int may_sleep)
+{
+	__be32 *savep;
+	uint32_t attrlen,
+		 bitmap[2] = {0};
+	int status;
+
+	status = decode_op_hdr(xdr, OP_GETATTR);
+	if (status < 0)
+		goto xdr_error;
+
+	status = decode_attr_bitmap(xdr, bitmap);
+	if (status < 0)
+		goto xdr_error;
+
+	status = decode_attr_length(xdr, &attrlen, &savep);
+	if (status < 0)
+		goto xdr_error;
+
+	status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server, may_sleep);
+	if (status < 0)
+		goto xdr_error;
+
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
 	dprintk("%s: xdr returned %d\n", __func__, -status);
 	return status;
 }
 
+static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+		const struct nfs_server *server, int may_sleep)
+{
+	return decode_getfattr_generic(xdr, fattr, NULL, server, may_sleep);
+}
 
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
@@ -3894,6 +4003,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0)
 		goto xdr_error;
 	fsinfo->wtpref = fsinfo->wtmax;
+	status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta);
+	if (status != 0)
+		goto xdr_error;
 
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
@@ -3950,13 +4062,13 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
 	__be32 *p;
 	uint32_t namelen, type;
 
-	p = xdr_inline_decode(xdr, 32);
+	p = xdr_inline_decode(xdr, 32); /* read 32 bytes */
 	if (unlikely(!p))
 		goto out_overflow;
-	p = xdr_decode_hyper(p, &offset);
+	p = xdr_decode_hyper(p, &offset); /* read 2 8-byte long words */
 	p = xdr_decode_hyper(p, &length);
-	type = be32_to_cpup(p++);
-	if (fl != NULL) {
+	type = be32_to_cpup(p++); /* 4 byte read */
+	if (fl != NULL) { /* manipulate file lock */
 		fl->fl_start = (loff_t)offset;
 		fl->fl_end = fl->fl_start + (loff_t)length - 1;
 		if (length == ~(uint64_t)0)
@@ -3966,9 +4078,9 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
 			fl->fl_type = F_RDLCK;
 		fl->fl_pid = 0;
 	}
-	p = xdr_decode_hyper(p, &clientid);
-	namelen = be32_to_cpup(p);
-	p = xdr_inline_decode(xdr, namelen);
+	p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */
+	namelen = be32_to_cpup(p); /* read 4 bytes */  /* have read all 32 bytes now */
+	p = xdr_inline_decode(xdr, namelen); /* variable size field */
 	if (likely(p))
 		return -NFS4ERR_DENIED;
 out_overflow:
@@ -4200,12 +4312,9 @@ out_overflow:
 static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir)
 {
 	struct xdr_buf	*rcvbuf = &req->rq_rcv_buf;
-	struct page	*page = *rcvbuf->pages;
 	struct kvec	*iov = rcvbuf->head;
 	size_t		hdrlen;
 	u32		recvd, pglen = rcvbuf->page_len;
-	__be32		*end, *entry, *p, *kaddr;
-	unsigned int	nr = 0;
 	int		status;
 
 	status = decode_op_hdr(xdr, OP_READDIR);
@@ -4225,71 +4334,8 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
 		pglen = recvd;
 	xdr_read_pages(xdr, pglen);
 
-	BUG_ON(pglen + readdir->pgbase > PAGE_CACHE_SIZE);
-	kaddr = p = kmap_atomic(page, KM_USER0);
-	end = p + ((pglen + readdir->pgbase) >> 2);
-	entry = p;
-
-	/* Make sure the packet actually has a value_follows and EOF entry */
-	if ((entry + 1) > end)
-		goto short_pkt;
-
-	for (; *p++; nr++) {
-		u32 len, attrlen, xlen;
-		if (end - p < 3)
-			goto short_pkt;
-		dprintk("cookie = %Lu, ", *((unsigned long long *)p));
-		p += 2;			/* cookie */
-		len = ntohl(*p++);	/* filename length */
-		if (len > NFS4_MAXNAMLEN) {
-			dprintk("NFS: giant filename in readdir (len 0x%x)\n",
-					len);
-			goto err_unmap;
-		}
-		xlen = XDR_QUADLEN(len);
-		if (end - p < xlen + 1)
-			goto short_pkt;
-		dprintk("filename = %*s\n", len, (char *)p);
-		p += xlen;
-		len = ntohl(*p++);	/* bitmap length */
-		if (end - p < len + 1)
-			goto short_pkt;
-		p += len;
-		attrlen = XDR_QUADLEN(ntohl(*p++));
-		if (end - p < attrlen + 2)
-			goto short_pkt;
-		p += attrlen;		/* attributes */
-		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 0;
-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.
-	 */
-	dprintk("%s: short packet at entry %d\n", __func__, nr);
-	entry[0] = entry[1] = 0;
-	if (nr)
-		goto out;
-err_unmap:
-	kunmap_atomic(kaddr, KM_USER0);
-	return -errno_NFSERR_IO;
 }
 
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
@@ -4299,7 +4345,6 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 	size_t hdrlen;
 	u32 len, recvd;
 	__be32 *p;
-	char *kaddr;
 	int status;
 
 	status = decode_op_hdr(xdr, OP_READLINK);
@@ -4330,9 +4375,7 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 	 * and and null-terminate the text (the VFS expects
 	 * null-termination).
 	 */
-	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;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -4668,7 +4711,6 @@ static int decode_sequence(struct xdr_stream *xdr,
 			   struct rpc_rqst *rqstp)
 {
 #if defined(CONFIG_NFS_V4_1)
-	struct nfs4_slot *slot;
 	struct nfs4_sessionid id;
 	u32 dummy;
 	int status;
@@ -4700,15 +4742,14 @@ static int decode_sequence(struct xdr_stream *xdr,
 		goto out_overflow;
 
 	/* seqid */
-	slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid];
 	dummy = be32_to_cpup(p++);
-	if (dummy != slot->seq_nr) {
+	if (dummy != res->sr_slot->seq_nr) {
 		dprintk("%s Invalid sequence number\n", __func__);
 		goto out_err;
 	}
 	/* slot id */
 	dummy = be32_to_cpup(p++);
-	if (dummy != res->sr_slotid) {
+	if (dummy != res->sr_slot - res->sr_session->fc_slot_table.slots) {
 		dprintk("%s Invalid slot id\n", __func__);
 		goto out_err;
 	}
@@ -4873,7 +4914,7 @@ out:
 /*
  * Decode RENAME response
  */
-static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_rename_res *res)
+static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs_renameres *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -5760,23 +5801,35 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, uint32_t *p,
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-__be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
+__be32 *nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
+			   struct nfs_server *server, int plus)
 {
 	uint32_t bitmap[2] = {0};
 	uint32_t len;
-
-	if (!*p++) {
-		if (!*p)
+	__be32 *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;
 	entry->prev_cookie = entry->cookie;
 	p = xdr_decode_hyper(p, &entry->cookie);
 	entry->len = ntohl(*p++);
+
+	p = xdr_inline_decode(xdr, entry->len);
+	if (unlikely(!p))
+		goto out_overflow;
 	entry->name = (const char *) p;
-	p += XDR_QUADLEN(entry->len);
 
 	/*
 	 * In case the server doesn't return an inode number,
@@ -5784,32 +5837,33 @@ __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
 	 * since glibc seems to choke on it...)
 	 */
 	entry->ino = 1;
+	entry->fattr->valid = 0;
 
-	len = ntohl(*p++);		/* bitmap length */
-	if (len-- > 0) {
-		bitmap[0] = ntohl(*p++);
-		if (len-- > 0) {
-			bitmap[1] = ntohl(*p++);
-			p += len;
-		}
-	}
-	len = XDR_QUADLEN(ntohl(*p++));	/* attribute buffer length */
-	if (len > 0) {
-		if (bitmap[0] & FATTR4_WORD0_RDATTR_ERROR) {
-			bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR;
-			/* Ignore the return value of rdattr_error for now */
-			p++;
-			len--;
-		}
-		if (bitmap[0] == 0 && bitmap[1] == FATTR4_WORD1_MOUNTED_ON_FILEID)
-			xdr_decode_hyper(p, &entry->ino);
-		else if (bitmap[0] == FATTR4_WORD0_FILEID)
-			xdr_decode_hyper(p, &entry->ino);
-		p += len;
-	}
+	if (decode_attr_bitmap(xdr, bitmap) < 0)
+		goto out_overflow;
+
+	if (decode_attr_length(xdr, &len, &p) < 0)
+		goto out_overflow;
+
+	if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh, server, 1) < 0)
+		goto out_overflow;
+	if (entry->fattr->valid & NFS_ATTR_FATTR_FILEID)
+		entry->ino = entry->fattr->fileid;
+
+	if (verify_attr_len(xdr, p, len) < 0)
+		goto out_overflow;
+
+	p = xdr_inline_peek(xdr, 8);
+	if (p != NULL)
+		entry->eof = !p[0] && p[1];
+	else
+		entry->eof = 0;
 
-	entry->eof = !p[0] && p[1];
 	return p;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return ERR_PTR(-EIO);
 }
 
 /*

fs/nfs/nfsroot.c

@@ -3,9 +3,10 @@
  *
  *  Allow an NFS filesystem to be mounted as root. The way this works is:
  *     (1) Use the IP autoconfig mechanism to set local IP addresses and routes.
- *     (2) Handle RPC negotiation with the system which replied to RARP or
- *         was reported as a boot server by BOOTP or manually.
- *     (3) The actual mounting is done later, when init() is running.
+ *     (2) Construct the device string and the options string using DHCP
+ *         option 17 and/or kernel command line options.
+ *     (3) When mount_root() sets up the root file system, pass these strings
+ *         to the NFS client's regular mount interface via sys_mount().
  *
  *
  *	Changes:
@@ -65,470 +66,243 @@
  *	Hua Qin		:	Support for mounting root file system via
  *				NFS over TCP.
  *	Fabian Frederick:	Option parser rebuilt (using parser lib)
-*/
+ *	Chuck Lever	:	Use super.c's text-based mount option parsing
+ *	Chuck Lever	:	Add "nfsrootdebug".
+ */
 
 #include <linux/types.h>
 #include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/fs.h>
 #include <linux/init.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprtsock.h>
 #include <linux/nfs.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_mount.h>
-#include <linux/in.h>
-#include <linux/major.h>
 #include <linux/utsname.h>
-#include <linux/inet.h>
 #include <linux/root_dev.h>
 #include <net/ipconfig.h>
-#include <linux/parser.h>
 
 #include "internal.h"
 
-/* Define this to allow debugging output */
-#undef NFSROOT_DEBUG
 #define NFSDBG_FACILITY NFSDBG_ROOT
 
-/* Default port to use if server is not running a portmapper */
-#define NFS_MNT_PORT	627
-
 /* Default path we try to mount. "%s" gets replaced by our IP address */
 #define NFS_ROOT		"/tftpboot/%s"
 
 /* Parameters passed from the kernel command line */
-static char nfs_root_name[256] __initdata = "";
+static char nfs_root_parms[256] __initdata = "";
+
+/* Text-based mount options passed to super.c */
+static char nfs_root_options[256] __initdata = "";
 
 /* Address of NFS server */
-static __be32 servaddr __initdata = 0;
+static __be32 servaddr __initdata = htonl(INADDR_NONE);
 
 /* Name of directory to mount */
-static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = { 0, };
-
-/* NFS-related data */
-static struct nfs_mount_data nfs_data __initdata = { 0, };/* NFS mount info */
-static int nfs_port __initdata = 0;		/* Port to connect to for NFS */
-static int mount_port __initdata = 0;		/* Mount daemon port number */
-
-
-/***************************************************************************
-
-			     Parsing of options
-
- ***************************************************************************/
-
-enum {
-	/* Options that take integer arguments */
-	Opt_port, Opt_rsize, Opt_wsize, Opt_timeo, Opt_retrans, Opt_acregmin,
-	Opt_acregmax, Opt_acdirmin, Opt_acdirmax,
-	/* Options that take no arguments */
-	Opt_soft, Opt_hard, Opt_intr,
-	Opt_nointr, Opt_posix, Opt_noposix, Opt_cto, Opt_nocto, Opt_ac, 
-	Opt_noac, Opt_lock, Opt_nolock, Opt_v2, Opt_v3, Opt_udp, Opt_tcp,
-	Opt_acl, Opt_noacl,
-	/* Error token */
-	Opt_err
-};
-
-static const match_table_t tokens __initconst = {
-	{Opt_port, "port=%u"},
-	{Opt_rsize, "rsize=%u"},
-	{Opt_wsize, "wsize=%u"},
-	{Opt_timeo, "timeo=%u"},
-	{Opt_retrans, "retrans=%u"},
-	{Opt_acregmin, "acregmin=%u"},
-	{Opt_acregmax, "acregmax=%u"},
-	{Opt_acdirmin, "acdirmin=%u"},
-	{Opt_acdirmax, "acdirmax=%u"},
-	{Opt_soft, "soft"},
-	{Opt_hard, "hard"},
-	{Opt_intr, "intr"},
-	{Opt_nointr, "nointr"},
-	{Opt_posix, "posix"},
-	{Opt_noposix, "noposix"},
-	{Opt_cto, "cto"},
-	{Opt_nocto, "nocto"},
-	{Opt_ac, "ac"},
-	{Opt_noac, "noac"},
-	{Opt_lock, "lock"},
-	{Opt_nolock, "nolock"},
-	{Opt_v2, "nfsvers=2"},
-	{Opt_v2, "v2"},
-	{Opt_v3, "nfsvers=3"},
-	{Opt_v3, "v3"},
-	{Opt_udp, "proto=udp"},
-	{Opt_udp, "udp"},
-	{Opt_tcp, "proto=tcp"},
-	{Opt_tcp, "tcp"},
-	{Opt_acl, "acl"},
-	{Opt_noacl, "noacl"},
-	{Opt_err, NULL}
-	
-};
+static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = "";
+
+/* server:export path string passed to super.c */
+static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = "";
 
 /*
- *  Parse option string.
+ * When the "nfsrootdebug" kernel command line option is specified,
+ * enable debugging messages for NFSROOT.
  */
-
-static int __init root_nfs_parse(char *name, char *buf)
+static int __init nfs_root_debug(char *__unused)
 {
-
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
-	int option;
-
-	if (!name)
-		return 1;
-
-	/* Set the NFS remote path */
-	p = strsep(&name, ",");
-	if (p[0] != '\0' && strcmp(p, "default") != 0)
-		strlcpy(buf, p, NFS_MAXPATHLEN);
-
-	while ((p = strsep (&name, ",")) != NULL) {
-		int token; 
-		if (!*p)
-			continue;
-		token = match_token(p, tokens, args);
-
-		/* %u tokens only. Beware if you add new tokens! */
-		if (token < Opt_soft && match_int(&args[0], &option))
-			return 0;
-		switch (token) {
-			case Opt_port:
-				nfs_port = option;
-				break;
-			case Opt_rsize:
-				nfs_data.rsize = option;
-				break;
-			case Opt_wsize:
-				nfs_data.wsize = option;
-				break;
-			case Opt_timeo:
-				nfs_data.timeo = option;
-				break;
-			case Opt_retrans:
-				nfs_data.retrans = option;
-				break;
-			case Opt_acregmin:
-				nfs_data.acregmin = option;
-				break;
-			case Opt_acregmax:
-				nfs_data.acregmax = option;
-				break;
-			case Opt_acdirmin:
-				nfs_data.acdirmin = option;
-				break;
-			case Opt_acdirmax:
-				nfs_data.acdirmax = option;
-				break;
-			case Opt_soft:
-				nfs_data.flags |= NFS_MOUNT_SOFT;
-				break;
-			case Opt_hard:
-				nfs_data.flags &= ~NFS_MOUNT_SOFT;
-				break;
-			case Opt_intr:
-			case Opt_nointr:
-				break;
-			case Opt_posix:
-				nfs_data.flags |= NFS_MOUNT_POSIX;
-				break;
-			case Opt_noposix:
-				nfs_data.flags &= ~NFS_MOUNT_POSIX;
-				break;
-			case Opt_cto:
-				nfs_data.flags &= ~NFS_MOUNT_NOCTO;
-				break;
-			case Opt_nocto:
-				nfs_data.flags |= NFS_MOUNT_NOCTO;
-				break;
-			case Opt_ac:
-				nfs_data.flags &= ~NFS_MOUNT_NOAC;
-				break;
-			case Opt_noac:
-				nfs_data.flags |= NFS_MOUNT_NOAC;
-				break;
-			case Opt_lock:
-				nfs_data.flags &= ~NFS_MOUNT_NONLM;
-				break;
-			case Opt_nolock:
-				nfs_data.flags |= NFS_MOUNT_NONLM;
-				break;
-			case Opt_v2:
-				nfs_data.flags &= ~NFS_MOUNT_VER3;
-				break;
-			case Opt_v3:
-				nfs_data.flags |= NFS_MOUNT_VER3;
-				break;
-			case Opt_udp:
-				nfs_data.flags &= ~NFS_MOUNT_TCP;
-				break;
-			case Opt_tcp:
-				nfs_data.flags |= NFS_MOUNT_TCP;
-				break;
-			case Opt_acl:
-				nfs_data.flags &= ~NFS_MOUNT_NOACL;
-				break;
-			case Opt_noacl:
-				nfs_data.flags |= NFS_MOUNT_NOACL;
-				break;
-			default:
-				printk(KERN_WARNING "Root-NFS: unknown "
-					"option: %s\n", p);
-				return 0;
-		}
-	}
-
+	nfs_debug |= NFSDBG_ROOT | NFSDBG_MOUNT;
 	return 1;
 }
 
+__setup("nfsrootdebug", nfs_root_debug);
+
 /*
- *  Prepare the NFS data structure and parse all options.
+ *  Parse NFS server and directory information passed on the kernel
+ *  command line.
+ *
+ *  nfsroot=[<server-ip>:]<root-dir>[,<nfs-options>]
+ *
+ *  If there is a "%s" token in the <root-dir> string, it is replaced
+ *  by the ASCII-representation of the client's IP address.
  */
-static int __init root_nfs_name(char *name)
+static int __init nfs_root_setup(char *line)
 {
-	static char buf[NFS_MAXPATHLEN] __initdata;
-	char *cp;
-
-	/* Set some default values */
-	memset(&nfs_data, 0, sizeof(nfs_data));
-	nfs_port          = -1;
-	nfs_data.version  = NFS_MOUNT_VERSION;
-	nfs_data.flags    = NFS_MOUNT_NONLM;	/* No lockd in nfs root yet */
-	nfs_data.rsize    = NFS_DEF_FILE_IO_SIZE;
-	nfs_data.wsize    = NFS_DEF_FILE_IO_SIZE;
-	nfs_data.acregmin = NFS_DEF_ACREGMIN;
-	nfs_data.acregmax = NFS_DEF_ACREGMAX;
-	nfs_data.acdirmin = NFS_DEF_ACDIRMIN;
-	nfs_data.acdirmax = NFS_DEF_ACDIRMAX;
-	strcpy(buf, NFS_ROOT);
-
-	/* Process options received from the remote server */
-	root_nfs_parse(root_server_path, buf);
-
-	/* Override them by options set on kernel command-line */
-	root_nfs_parse(name, buf);
-
-	cp = utsname()->nodename;
-	if (strlen(buf) + strlen(cp) > NFS_MAXPATHLEN) {
-		printk(KERN_ERR "Root-NFS: Pathname for remote directory too long.\n");
-		return -1;
+	ROOT_DEV = Root_NFS;
+
+	if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) {
+		strlcpy(nfs_root_parms, line, sizeof(nfs_root_parms));
+	} else {
+		size_t n = strlen(line) + sizeof(NFS_ROOT) - 1;
+		if (n >= sizeof(nfs_root_parms))
+			line[sizeof(nfs_root_parms) - sizeof(NFS_ROOT) - 2] = '\0';
+		sprintf(nfs_root_parms, NFS_ROOT, line);
 	}
-	sprintf(nfs_export_path, buf, cp);
+
+	/*
+	 * Extract the IP address of the NFS server containing our
+	 * root file system, if one was specified.
+	 *
+	 * Note: root_nfs_parse_addr() removes the server-ip from
+	 *	 nfs_root_parms, if it exists.
+	 */
+	root_server_addr = root_nfs_parse_addr(nfs_root_parms);
 
 	return 1;
 }
 
+__setup("nfsroot=", nfs_root_setup);
 
-/*
- *  Get NFS server address.
- */
-static int __init root_nfs_addr(void)
+static int __init root_nfs_copy(char *dest, const char *src,
+				     const size_t destlen)
 {
-	if ((servaddr = root_server_addr) == htonl(INADDR_NONE)) {
-		printk(KERN_ERR "Root-NFS: No NFS server available, giving up.\n");
+	if (strlcpy(dest, src, destlen) > destlen)
 		return -1;
-	}
+	return 0;
+}
 
-	snprintf(nfs_data.hostname, sizeof(nfs_data.hostname),
-		 "%pI4", &servaddr);
+static int __init root_nfs_cat(char *dest, const char *src,
+				  const size_t destlen)
+{
+	if (strlcat(dest, src, destlen) > destlen)
+		return -1;
 	return 0;
 }
 
 /*
- *  Tell the user what's going on.
+ * Parse out root export path and mount options from
+ * passed-in string @incoming.
+ *
+ * Copy the export path into @exppath.
  */
-#ifdef NFSROOT_DEBUG
-static void __init root_nfs_print(void)
+static int __init root_nfs_parse_options(char *incoming, char *exppath,
+					 const size_t exppathlen)
 {
-	printk(KERN_NOTICE "Root-NFS: Mounting %s on server %s as root\n",
-		nfs_export_path, nfs_data.hostname);
-	printk(KERN_NOTICE "Root-NFS:     rsize = %d, wsize = %d, timeo = %d, retrans = %d\n",
-		nfs_data.rsize, nfs_data.wsize, nfs_data.timeo, nfs_data.retrans);
-	printk(KERN_NOTICE "Root-NFS:     acreg (min,max) = (%d,%d), acdir (min,max) = (%d,%d)\n",
-		nfs_data.acregmin, nfs_data.acregmax,
-		nfs_data.acdirmin, nfs_data.acdirmax);
-	printk(KERN_NOTICE "Root-NFS:     nfsd port = %d, mountd port = %d, flags = %08x\n",
-		nfs_port, mount_port, nfs_data.flags);
-}
-#endif
-
+	char *p;
 
-static int __init root_nfs_init(void)
-{
-#ifdef NFSROOT_DEBUG
-	nfs_debug |= NFSDBG_ROOT;
-#endif
+	/*
+	 * Set the NFS remote path
+	 */
+	p = strsep(&incoming, ",");
+	if (*p != '\0' && strcmp(p, "default") != 0)
+		if (root_nfs_copy(exppath, p, exppathlen))
+			return -1;
 
 	/*
-	 * Decode the root directory path name and NFS options from
-	 * the kernel command line. This has to go here in order to
-	 * be able to use the client IP address for the remote root
-	 * directory (necessary for pure RARP booting).
+	 * @incoming now points to the rest of the string; if it
+	 * contains something, append it to our root options buffer
 	 */
-	if (root_nfs_name(nfs_root_name) < 0 ||
-	    root_nfs_addr() < 0)
-		return -1;
+	if (incoming != NULL && *incoming != '\0')
+		if (root_nfs_cat(nfs_root_options, incoming,
+						sizeof(nfs_root_options)))
+			return -1;
 
-#ifdef NFSROOT_DEBUG
-	root_nfs_print();
-#endif
+	/*
+	 * Possibly prepare for more options to be appended
+	 */
+	if (nfs_root_options[0] != '\0' &&
+	    nfs_root_options[strlen(nfs_root_options)] != ',')
+		if (root_nfs_cat(nfs_root_options, ",",
+						sizeof(nfs_root_options)))
+			return -1;
 
 	return 0;
 }
 
-
 /*
- *  Parse NFS server and directory information passed on the kernel
- *  command line.
+ *  Decode the export directory path name and NFS options from
+ *  the kernel command line.  This has to be done late in order to
+ *  use a dynamically acquired client IP address for the remote
+ *  root directory path.
+ *
+ *  Returns zero if successful; otherwise -1 is returned.
  */
-static int __init nfs_root_setup(char *line)
+static int __init root_nfs_data(char *cmdline)
 {
-	ROOT_DEV = Root_NFS;
-	if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) {
-		strlcpy(nfs_root_name, line, sizeof(nfs_root_name));
-	} else {
-		int n = strlen(line) + sizeof(NFS_ROOT) - 1;
-		if (n >= sizeof(nfs_root_name))
-			line[sizeof(nfs_root_name) - sizeof(NFS_ROOT) - 2] = '\0';
-		sprintf(nfs_root_name, NFS_ROOT, line);
+	char addr_option[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1];
+	int len, retval = -1;
+	char *tmp = NULL;
+	const size_t tmplen = sizeof(nfs_export_path);
+
+	tmp = kzalloc(tmplen, GFP_KERNEL);
+	if (tmp == NULL)
+		goto out_nomem;
+	strcpy(tmp, NFS_ROOT);
+
+	if (root_server_path[0] != '\0') {
+		dprintk("Root-NFS: DHCPv4 option 17: %s\n",
+			root_server_path);
+		if (root_nfs_parse_options(root_server_path, tmp, tmplen))
+			goto out_optionstoolong;
 	}
-	root_server_addr = root_nfs_parse_addr(nfs_root_name);
-	return 1;
-}
 
-__setup("nfsroot=", nfs_root_setup);
-
-/***************************************************************************
-
-	       Routines to actually mount the root directory
+	if (cmdline[0] != '\0') {
+		dprintk("Root-NFS: nfsroot=%s\n", cmdline);
+		if (root_nfs_parse_options(cmdline, tmp, tmplen))
+			goto out_optionstoolong;
+	}
 
- ***************************************************************************/
+	/*
+	 * Append mandatory options for nfsroot so they override
+	 * what has come before
+	 */
+	snprintf(addr_option, sizeof(addr_option), "nolock,addr=%pI4",
+			&servaddr);
+	if (root_nfs_cat(nfs_root_options, addr_option,
+						sizeof(nfs_root_options)))
+		goto out_optionstoolong;
 
-/*
- *  Construct sockaddr_in from address and port number.
- */
-static inline void
-set_sockaddr(struct sockaddr_in *sin, __be32 addr, __be16 port)
-{
-	sin->sin_family = AF_INET;
-	sin->sin_addr.s_addr = addr;
-	sin->sin_port = port;
-}
+	/*
+	 * Set up nfs_root_device.  For NFS mounts, this looks like
+	 *
+	 *	server:/path
+	 *
+	 * At this point, utsname()->nodename contains our local
+	 * IP address or hostname, set by ipconfig.  If "%s" exists
+	 * in tmp, substitute the nodename, then shovel the whole
+	 * mess into nfs_root_device.
+	 */
+	len = snprintf(nfs_export_path, sizeof(nfs_export_path),
+				tmp, utsname()->nodename);
+	if (len > (int)sizeof(nfs_export_path))
+		goto out_devnametoolong;
+	len = snprintf(nfs_root_device, sizeof(nfs_root_device),
+				"%pI4:%s", &servaddr, nfs_export_path);
+	if (len > (int)sizeof(nfs_root_device))
+		goto out_devnametoolong;
 
-/*
- *  Query server portmapper for the port of a daemon program.
- */
-static int __init root_nfs_getport(int program, int version, int proto)
-{
-	struct sockaddr_in sin;
+	retval = 0;
 
-	printk(KERN_NOTICE "Looking up port of RPC %d/%d on %pI4\n",
-		program, version, &servaddr);
-	set_sockaddr(&sin, servaddr, 0);
-	return rpcb_getport_sync(&sin, program, version, proto);
+out:
+	kfree(tmp);
+	return retval;
+out_nomem:
+	printk(KERN_ERR "Root-NFS: could not allocate memory\n");
+	goto out;
+out_optionstoolong:
+	printk(KERN_ERR "Root-NFS: mount options string too long\n");
+	goto out;
+out_devnametoolong:
+	printk(KERN_ERR "Root-NFS: root device name too long.\n");
+	goto out;
 }
 
-
-/*
- *  Use portmapper to find mountd and nfsd port numbers if not overriden
- *  by the user. Use defaults if portmapper is not available.
- *  XXX: Is there any nfs server with no portmapper?
+/**
+ * nfs_root_data - Return prepared 'data' for NFSROOT mount
+ * @root_device: OUT: address of string containing NFSROOT device
+ * @root_data: OUT: address of string containing NFSROOT mount options
+ *
+ * Returns zero and sets @root_device and @root_data if successful,
+ * otherwise -1 is returned.
  */
-static int __init root_nfs_ports(void)
+int __init nfs_root_data(char **root_device, char **root_data)
 {
-	int port;
-	int nfsd_ver, mountd_ver;
-	int nfsd_port, mountd_port;
-	int proto;
-
-	if (nfs_data.flags & NFS_MOUNT_VER3) {
-		nfsd_ver = NFS3_VERSION;
-		mountd_ver = NFS_MNT3_VERSION;
-		nfsd_port = NFS_PORT;
-		mountd_port = NFS_MNT_PORT;
-	} else {
-		nfsd_ver = NFS2_VERSION;
-		mountd_ver = NFS_MNT_VERSION;
-		nfsd_port = NFS_PORT;
-		mountd_port = NFS_MNT_PORT;
-	}
-
-	proto = (nfs_data.flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;
-
-	if (nfs_port < 0) {
-		if ((port = root_nfs_getport(NFS_PROGRAM, nfsd_ver, proto)) < 0) {
-			printk(KERN_ERR "Root-NFS: Unable to get nfsd port "
-					"number from server, using default\n");
-			port = nfsd_port;
-		}
-		nfs_port = port;
-		dprintk("Root-NFS: Portmapper on server returned %d "
-			"as nfsd port\n", port);
+	servaddr = root_server_addr;
+	if (servaddr == htonl(INADDR_NONE)) {
+		printk(KERN_ERR "Root-NFS: no NFS server address\n");
+		return -1;
 	}
 
-	if ((port = root_nfs_getport(NFS_MNT_PROGRAM, mountd_ver, proto)) < 0) {
-		printk(KERN_ERR "Root-NFS: Unable to get mountd port "
-				"number from server, using default\n");
-		port = mountd_port;
-	}
-	mount_port = port;
-	dprintk("Root-NFS: mountd port is %d\n", port);
+	if (root_nfs_data(nfs_root_parms) < 0)
+		return -1;
 
+	*root_device = nfs_root_device;
+	*root_data = nfs_root_options;
 	return 0;
 }
-
-
-/*
- *  Get a file handle from the server for the directory which is to be
- *  mounted.
- */
-static int __init root_nfs_get_handle(void)
-{
-	struct sockaddr_in sin;
-	unsigned int auth_flav_len = 0;
-	struct nfs_mount_request request = {
-		.sap		= (struct sockaddr *)&sin,
-		.salen		= sizeof(sin),
-		.dirpath	= nfs_export_path,
-		.version	= (nfs_data.flags & NFS_MOUNT_VER3) ?
-					NFS_MNT3_VERSION : NFS_MNT_VERSION,
-		.protocol	= (nfs_data.flags & NFS_MOUNT_TCP) ?
-					XPRT_TRANSPORT_TCP : XPRT_TRANSPORT_UDP,
-		.auth_flav_len	= &auth_flav_len,
-	};
-	int status = -ENOMEM;
-
-	request.fh = nfs_alloc_fhandle();
-	if (!request.fh)
-		goto out;
-	set_sockaddr(&sin, servaddr, htons(mount_port));
-	status = nfs_mount(&request);
-	if (status < 0)
-		printk(KERN_ERR "Root-NFS: Server returned error %d "
-				"while mounting %s\n", status, nfs_export_path);
-	else {
-		nfs_data.root.size = request.fh->size;
-		memcpy(&nfs_data.root.data, request.fh->data, request.fh->size);
-	}
-	nfs_free_fhandle(request.fh);
-out:
-	return status;
-}
-
-/*
- *  Get the NFS port numbers and file handle, and return the prepared 'data'
- *  argument for mount() if everything went OK. Return NULL otherwise.
- */
-void * __init nfs_root_data(void)
-{
-	if (root_nfs_init() < 0
-	 || root_nfs_ports() < 0
-	 || root_nfs_get_handle() < 0)
-		return NULL;
-	set_sockaddr((struct sockaddr_in *) &nfs_data.addr, servaddr, htons(nfs_port));
-	return (void*)&nfs_data;
-}

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/unlink.c

@@ -13,9 +13,12 @@
 #include <linux/nfs_fs.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/namei.h>
 
 #include "internal.h"
 #include "nfs4_fs.h"
+#include "iostat.h"
+#include "delegation.h"
 
 struct nfs_unlinkdata {
 	struct hlist_node list;
@@ -244,7 +247,7 @@ void nfs_unblock_sillyrename(struct dentry *dentry)
  * @dir: parent directory of dentry
  * @dentry: dentry to unlink
  */
-int
+static int
 nfs_async_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct nfs_unlinkdata *data;
@@ -259,7 +262,6 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry)
 		status = PTR_ERR(data->cred);
 		goto out_free;
 	}
-	data->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	data->res.dir_attr = &data->dir_attr;
 
 	status = -EBUSY;
@@ -303,3 +305,256 @@ nfs_complete_unlink(struct dentry *dentry, struct inode *inode)
 	if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data)))
 		nfs_free_unlinkdata(data);
 }
+
+/* Cancel a queued async unlink. Called when a sillyrename run fails. */
+static void
+nfs_cancel_async_unlink(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
+		struct nfs_unlinkdata *data = dentry->d_fsdata;
+
+		dentry->d_flags &= ~DCACHE_NFSFS_RENAMED;
+		spin_unlock(&dentry->d_lock);
+		nfs_free_unlinkdata(data);
+		return;
+	}
+	spin_unlock(&dentry->d_lock);
+}
+
+struct nfs_renamedata {
+	struct nfs_renameargs	args;
+	struct nfs_renameres	res;
+	struct rpc_cred		*cred;
+	struct inode		*old_dir;
+	struct dentry		*old_dentry;
+	struct nfs_fattr	old_fattr;
+	struct inode		*new_dir;
+	struct dentry		*new_dentry;
+	struct nfs_fattr	new_fattr;
+};
+
+/**
+ * nfs_async_rename_done - Sillyrename post-processing
+ * @task: rpc_task of the sillyrename
+ * @calldata: nfs_renamedata for the sillyrename
+ *
+ * Do the directory attribute updates and the d_move
+ */
+static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs_renamedata *data = calldata;
+	struct inode *old_dir = data->old_dir;
+	struct inode *new_dir = data->new_dir;
+
+	if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
+		nfs_restart_rpc(task, NFS_SERVER(old_dir)->nfs_client);
+		return;
+	}
+
+	if (task->tk_status != 0) {
+		nfs_cancel_async_unlink(data->old_dentry);
+		return;
+	}
+
+	nfs_set_verifier(data->old_dentry, nfs_save_change_attribute(old_dir));
+	d_move(data->old_dentry, data->new_dentry);
+}
+
+/**
+ * nfs_async_rename_release - Release the sillyrename data.
+ * @calldata: the struct nfs_renamedata to be released
+ */
+static void nfs_async_rename_release(void *calldata)
+{
+	struct nfs_renamedata	*data = calldata;
+	struct super_block *sb = data->old_dir->i_sb;
+
+	if (data->old_dentry->d_inode)
+		nfs_mark_for_revalidate(data->old_dentry->d_inode);
+
+	dput(data->old_dentry);
+	dput(data->new_dentry);
+	iput(data->old_dir);
+	iput(data->new_dir);
+	nfs_sb_deactive(sb);
+	put_rpccred(data->cred);
+	kfree(data);
+}
+
+#if defined(CONFIG_NFS_V4_1)
+static void nfs_rename_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs_renamedata *data = calldata;
+	struct nfs_server *server = NFS_SERVER(data->old_dir);
+
+	if (nfs4_setup_sequence(server, &data->args.seq_args,
+				&data->res.seq_res, 1, task))
+		return;
+	rpc_call_start(task);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+static const struct rpc_call_ops nfs_rename_ops = {
+	.rpc_call_done = nfs_async_rename_done,
+	.rpc_release = nfs_async_rename_release,
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_rename_prepare,
+#endif /* CONFIG_NFS_V4_1 */
+};
+
+/**
+ * nfs_async_rename - perform an asynchronous rename operation
+ * @old_dir: directory that currently holds the dentry to be renamed
+ * @new_dir: target directory for the rename
+ * @old_dentry: original dentry to be renamed
+ * @new_dentry: dentry to which the old_dentry should be renamed
+ *
+ * It's expected that valid references to the dentries and inodes are held
+ */
+static struct rpc_task *
+nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
+		 struct dentry *old_dentry, struct dentry *new_dentry)
+{
+	struct nfs_renamedata *data;
+	struct rpc_message msg = { };
+	struct rpc_task_setup task_setup_data = {
+		.rpc_message = &msg,
+		.callback_ops = &nfs_rename_ops,
+		.workqueue = nfsiod_workqueue,
+		.rpc_client = NFS_CLIENT(old_dir),
+		.flags = RPC_TASK_ASYNC,
+	};
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (data == NULL)
+		return ERR_PTR(-ENOMEM);
+	task_setup_data.callback_data = data,
+
+	data->cred = rpc_lookup_cred();
+	if (IS_ERR(data->cred)) {
+		struct rpc_task *task = ERR_CAST(data->cred);
+		kfree(data);
+		return task;
+	}
+
+	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
+	msg.rpc_cred = data->cred;
+
+	/* set up nfs_renamedata */
+	data->old_dir = old_dir;
+	atomic_inc(&old_dir->i_count);
+	data->new_dir = new_dir;
+	atomic_inc(&new_dir->i_count);
+	data->old_dentry = dget(old_dentry);
+	data->new_dentry = dget(new_dentry);
+	nfs_fattr_init(&data->old_fattr);
+	nfs_fattr_init(&data->new_fattr);
+
+	/* set up nfs_renameargs */
+	data->args.old_dir = NFS_FH(old_dir);
+	data->args.old_name = &old_dentry->d_name;
+	data->args.new_dir = NFS_FH(new_dir);
+	data->args.new_name = &new_dentry->d_name;
+
+	/* set up nfs_renameres */
+	data->res.old_fattr = &data->old_fattr;
+	data->res.new_fattr = &data->new_fattr;
+
+	nfs_sb_active(old_dir->i_sb);
+
+	NFS_PROTO(data->old_dir)->rename_setup(&msg, old_dir);
+
+	return rpc_run_task(&task_setup_data);
+}
+
+/**
+ * nfs_sillyrename - Perform a silly-rename of a dentry
+ * @dir: inode of directory that contains dentry
+ * @dentry: dentry to be sillyrenamed
+ *
+ * NFSv2/3 is stateless and the server doesn't know when the client is
+ * holding a file open. To prevent application problems when a file is
+ * unlinked while it's still open, the client performs a "silly-rename".
+ * That is, it renames the file to a hidden file in the same directory,
+ * and only performs the unlink once the last reference to it is put.
+ *
+ * The final cleanup is done during dentry_iput.
+ */
+int
+nfs_sillyrename(struct inode *dir, struct dentry *dentry)
+{
+	static unsigned int sillycounter;
+	const int      fileidsize  = sizeof(NFS_FILEID(dentry->d_inode))*2;
+	const int      countersize = sizeof(sillycounter)*2;
+	const int      slen        = sizeof(".nfs")+fileidsize+countersize-1;
+	char           silly[slen+1];
+	struct dentry *sdentry;
+	struct rpc_task *task;
+	int            error = -EIO;
+
+	dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
+		dentry->d_parent->d_name.name, dentry->d_name.name,
+		atomic_read(&dentry->d_count));
+	nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
+
+	/*
+	 * We don't allow a dentry to be silly-renamed twice.
+	 */
+	error = -EBUSY;
+	if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
+		goto out;
+
+	sprintf(silly, ".nfs%*.*Lx",
+		fileidsize, fileidsize,
+		(unsigned long long)NFS_FILEID(dentry->d_inode));
+
+	/* Return delegation in anticipation of the rename */
+	nfs_inode_return_delegation(dentry->d_inode);
+
+	sdentry = NULL;
+	do {
+		char *suffix = silly + slen - countersize;
+
+		dput(sdentry);
+		sillycounter++;
+		sprintf(suffix, "%*.*x", countersize, countersize, sillycounter);
+
+		dfprintk(VFS, "NFS: trying to rename %s to %s\n",
+				dentry->d_name.name, silly);
+
+		sdentry = lookup_one_len(silly, dentry->d_parent, slen);
+		/*
+		 * N.B. Better to return EBUSY here ... it could be
+		 * dangerous to delete the file while it's in use.
+		 */
+		if (IS_ERR(sdentry))
+			goto out;
+	} while (sdentry->d_inode != NULL); /* need negative lookup */
+
+	/* queue unlink first. Can't do this from rpc_release as it
+	 * has to allocate memory
+	 */
+	error = nfs_async_unlink(dir, dentry);
+	if (error)
+		goto out_dput;
+
+	/* run the rename task, undo unlink if it fails */
+	task = nfs_async_rename(dir, dir, dentry, sdentry);
+	if (IS_ERR(task)) {
+		error = -EBUSY;
+		nfs_cancel_async_unlink(dentry);
+		goto out_dput;
+	}
+
+	/* wait for the RPC task to complete, unless a SIGKILL intervenes */
+	error = rpc_wait_for_completion_task(task);
+	if (error == 0)
+		error = task->tk_status;
+	rpc_put_task(task);
+out_dput:
+	dput(sdentry);
+out:
+	return error;
+}

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/nfs_xdr.h

@@ -112,6 +112,7 @@ struct nfs_fsinfo {
 	__u32			wtmult;	/* writes should be multiple of this */
 	__u32			dtpref;	/* pref. readdir transfer size */
 	__u64			maxfilesize;
+	struct timespec		time_delta; /* server time granularity */
 	__u32			lease_time; /* in seconds */
 };
 
@@ -170,7 +171,7 @@ struct nfs4_sequence_args {
 
 struct nfs4_sequence_res {
 	struct nfs4_session	*sr_session;
-	u8			sr_slotid;	/* slot used to send request */
+	struct nfs4_slot	*sr_slot;	/* slot used to send request */
 	int			sr_status;	/* sequence operation status */
 	unsigned long		sr_renewal_time;
 	u32			sr_status_flags;
@@ -399,6 +400,27 @@ struct nfs_removeres {
 	struct nfs4_sequence_res 	seq_res;
 };
 
+/*
+ * Common arguments to the rename call
+ */
+struct nfs_renameargs {
+	const struct nfs_fh		*old_dir;
+	const struct nfs_fh		*new_dir;
+	const struct qstr		*old_name;
+	const struct qstr		*new_name;
+	const u32			*bitmask;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs_renameres {
+	const struct nfs_server		*server;
+	struct nfs4_change_info		old_cinfo;
+	struct nfs_fattr		*old_fattr;
+	struct nfs4_change_info		new_cinfo;
+	struct nfs_fattr		*new_fattr;
+	struct nfs4_sequence_res	seq_res;
+};
+
 /*
  * Argument struct for decode_entry function
  */
@@ -434,15 +456,6 @@ struct nfs_createargs {
 	struct iattr *		sattr;
 };
 
-struct nfs_renameargs {
-	struct nfs_fh *		fromfh;
-	const char *		fromname;
-	unsigned int		fromlen;
-	struct nfs_fh *		tofh;
-	const char *		toname;
-	unsigned int		tolen;
-};
-
 struct nfs_setattrargs {
 	struct nfs_fh *                 fh;
 	nfs4_stateid                    stateid;
@@ -586,15 +599,6 @@ struct nfs3_mknodargs {
 	dev_t			rdev;
 };
 
-struct nfs3_renameargs {
-	struct nfs_fh *		fromfh;
-	const char *		fromname;
-	unsigned int		fromlen;
-	struct nfs_fh *		tofh;
-	const char *		toname;
-	unsigned int		tolen;
-};
-
 struct nfs3_linkargs {
 	struct nfs_fh *		fromfh;
 	struct nfs_fh *		tofh;
@@ -629,11 +633,6 @@ struct nfs3_readlinkargs {
 	struct page **		pages;
 };
 
-struct nfs3_renameres {
-	struct nfs_fattr *	fromattr;
-	struct nfs_fattr *	toattr;
-};
-
 struct nfs3_linkres {
 	struct nfs_fattr *	dir_attr;
 	struct nfs_fattr *	fattr;
@@ -780,6 +779,7 @@ struct nfs4_readdir_arg {
 	struct page **			pages;	/* zero-copy data */
 	unsigned int			pgbase;	/* zero-copy data */
 	const u32 *			bitmask;
+	int				plus;
 	struct nfs4_sequence_args	seq_args;
 };
 
@@ -801,24 +801,6 @@ struct nfs4_readlink_res {
 	struct nfs4_sequence_res	seq_res;
 };
 
-struct nfs4_rename_arg {
-	const struct nfs_fh *		old_dir;
-	const struct nfs_fh *		new_dir;
-	const struct qstr *		old_name;
-	const struct qstr *		new_name;
-	const u32 *			bitmask;
-	struct nfs4_sequence_args	seq_args;
-};
-
-struct nfs4_rename_res {
-	const struct nfs_server *	server;
-	struct nfs4_change_info		old_cinfo;
-	struct nfs_fattr *		old_fattr;
-	struct nfs4_change_info		new_cinfo;
-	struct nfs_fattr *		new_fattr;
-	struct nfs4_sequence_res	seq_res;
-};
-
 #define NFS4_SETCLIENTID_NAMELEN	(127)
 struct nfs4_setclientid {
 	const nfs4_verifier *		sc_verifier;
@@ -1032,19 +1014,21 @@ struct nfs_rpc_ops {
 	int	(*readlink)(struct inode *, struct page *, unsigned int,
 			    unsigned int);
 	int	(*create)  (struct inode *, struct dentry *,
-			    struct iattr *, int, struct nameidata *);
+			    struct iattr *, int, struct nfs_open_context *);
 	int	(*remove)  (struct inode *, struct qstr *);
 	void	(*unlink_setup)  (struct rpc_message *, struct inode *dir);
 	int	(*unlink_done) (struct rpc_task *, struct inode *);
 	int	(*rename)  (struct inode *, struct qstr *,
 			    struct inode *, struct qstr *);
+	void	(*rename_setup)  (struct rpc_message *msg, struct inode *dir);
+	int	(*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir);
 	int	(*link)    (struct inode *, struct inode *, struct qstr *);
 	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 *,
-			    u64, struct page *, unsigned int, int);
+			    u64, struct page **, unsigned int, int);
 	int	(*mknod)   (struct inode *, struct dentry *, struct iattr *,
 			    dev_t);
 	int	(*statfs)  (struct nfs_server *, struct nfs_fh *,
@@ -1054,7 +1038,7 @@ struct nfs_rpc_ops {
 	int	(*pathconf) (struct nfs_server *, struct nfs_fh *,
 			     struct nfs_pathconf *);
 	int	(*set_capabilities)(struct nfs_server *, struct nfs_fh *);
-	__be32 *(*decode_dirent)(__be32 *, struct nfs_entry *, int plus);
+	__be32 *(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int plus);
 	void	(*read_setup)   (struct nfs_read_data *, struct rpc_message *);
 	int	(*read_done)  (struct rpc_task *, struct nfs_read_data *);
 	void	(*write_setup)  (struct nfs_write_data *, struct rpc_message *);
@@ -1065,6 +1049,10 @@ struct nfs_rpc_ops {
 	int	(*lock_check_bounds)(const struct file_lock *);
 	void	(*clear_acl_cache)(struct inode *);
 	void	(*close_context)(struct nfs_open_context *ctx, int);
+	struct inode * (*open_context) (struct inode *dir,
+				struct nfs_open_context *ctx,
+				int open_flags,
+				struct iattr *iattr);
 };
 
 /*

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);

init/do_mounts.c

@@ -361,13 +361,13 @@ out:
 #ifdef CONFIG_ROOT_NFS
 static int __init mount_nfs_root(void)
 {
-	void *data = nfs_root_data();
+	char *root_dev, *root_data;
 
-	create_dev("/dev/root", ROOT_DEV);
-	if (data &&
-	    do_mount_root("/dev/root", "nfs", root_mountflags, data) == 0)
-		return 1;
-	return 0;
+	if (nfs_root_data(&root_dev, &root_data) != 0)
+		return 0;
+	if (do_mount_root(root_dev, "nfs", root_mountflags, root_data) != 0)
+		return 0;
+	return 1;
 }
 #endif
 

net/sunrpc/auth.c

@@ -595,7 +595,7 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
 int
 rpcauth_refreshcred(struct rpc_task *task)
 {
-	struct rpc_cred	*cred = task->tk_rqstp->rq_cred;
+	struct rpc_cred	*cred;
 	int err;
 
 	cred = task->tk_rqstp->rq_cred;

net/sunrpc/clnt.c

@@ -1675,7 +1675,7 @@ rpc_verify_header(struct rpc_task *task)
 			rpcauth_invalcred(task);
 			/* Ensure we obtain a new XID! */
 			xprt_release(task);
-			task->tk_action = call_refresh;
+			task->tk_action = call_reserve;
 			goto out_retry;
 		case RPC_AUTH_BADCRED:
 		case RPC_AUTH_BADVERF:

net/sunrpc/rpcb_clnt.c

@@ -211,8 +211,9 @@ static int rpcb_create_local(void)
 	 */
 	clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
 	if (IS_ERR(clnt4)) {
-		dprintk("RPC:       failed to create local rpcbind v4 "
-				"cleint (errno %ld).\n", PTR_ERR(clnt4));
+		dprintk("RPC:       failed to bind second program to "
+				"rpcbind v4 client (errno %ld).\n",
+				PTR_ERR(clnt4));
 		clnt4 = NULL;
 	}
 
@@ -475,57 +476,6 @@ int rpcb_v4_register(const u32 program, const u32 version,
 	return -EAFNOSUPPORT;
 }
 
-/**
- * rpcb_getport_sync - obtain the port for an 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
- *
- * Return value is the requested advertised port number,
- * or a negative errno value.
- *
- * Called from outside the RPC client in a synchronous task context.
- * Uses default timeout parameters specified by underlying transport.
- *
- * XXX: Needs to support IPv6
- */
-int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot)
-{
-	struct rpcbind_args map = {
-		.r_prog		= prog,
-		.r_vers		= vers,
-		.r_prot		= prot,
-		.r_port		= 0,
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &rpcb_procedures2[RPCBPROC_GETPORT],
-		.rpc_argp	= &map,
-		.rpc_resp	= &map,
-	};
-	struct rpc_clnt	*rpcb_clnt;
-	int status;
-
-	dprintk("RPC:       %s(%pI4, %u, %u, %d)\n",
-		__func__, &sin->sin_addr.s_addr, prog, vers, prot);
-
-	rpcb_clnt = rpcb_create(NULL, (struct sockaddr *)sin,
-				sizeof(*sin), prot, RPCBVERS_2);
-	if (IS_ERR(rpcb_clnt))
-		return PTR_ERR(rpcb_clnt);
-
-	status = rpc_call_sync(rpcb_clnt, &msg, 0);
-	rpc_shutdown_client(rpcb_clnt);
-
-	if (status >= 0) {
-		if (map.r_port != 0)
-			return map.r_port;
-		status = -EACCES;
-	}
-	return status;
-}
-EXPORT_SYMBOL_GPL(rpcb_getport_sync);
-
 static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc)
 {
 	struct rpc_message msg = {

net/sunrpc/sched.c

@@ -908,7 +908,7 @@ static int rpciod_start(void)
 	 * Create the rpciod thread and wait for it to start.
 	 */
 	dprintk("RPC:       creating workqueue rpciod\n");
-	wq = create_workqueue("rpciod");
+	wq = alloc_workqueue("rpciod", WQ_RESCUER, 0);
 	rpciod_workqueue = wq;
 	return rpciod_workqueue != NULL;
 }

net/sunrpc/xdr.c

@@ -111,6 +111,23 @@ xdr_decode_string_inplace(__be32 *p, char **sp,
 }
 EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
 
+/**
+ * xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf
+ * @buf: XDR buffer where string resides
+ * @len: length of string, in bytes
+ *
+ */
+void
+xdr_terminate_string(struct xdr_buf *buf, const u32 len)
+{
+	char *kaddr;
+
+	kaddr = kmap_atomic(buf->pages[0], KM_USER0);
+	kaddr[buf->page_base + len] = '\0';
+	kunmap_atomic(kaddr, KM_USER0);
+}
+EXPORT_SYMBOL(xdr_terminate_string);
+
 void
 xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base,
 		 unsigned int len)
@@ -395,24 +412,29 @@ xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
 {
 	struct kvec *tail;
 	size_t copy;
-	char *p;
 	unsigned int pglen = buf->page_len;
+	unsigned int tailbuf_len;
 
 	tail = buf->tail;
 	BUG_ON (len > pglen);
 
+	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
+
 	/* Shift the tail first */
-	if (tail->iov_len != 0) {
-		p = (char *)tail->iov_base + len;
+	if (tailbuf_len != 0) {
+		unsigned int free_space = tailbuf_len - tail->iov_len;
+
+		if (len < free_space)
+			free_space = len;
+		tail->iov_len += free_space;
+
+		copy = len;
 		if (tail->iov_len > len) {
-			copy = tail->iov_len - len;
-			memmove(p, tail->iov_base, copy);
+			char *p = (char *)tail->iov_base + len;
+			memmove(p, tail->iov_base, tail->iov_len - len);
 		} else
-			buf->buflen -= len;
-		/* Copy from the inlined pages into the tail */
-		copy = len;
-		if (copy > tail->iov_len)
 			copy = tail->iov_len;
+		/* Copy from the inlined pages into the tail */
 		_copy_from_pages((char *)tail->iov_base,
 				buf->pages, buf->page_base + pglen - len,
 				copy);
@@ -550,6 +572,27 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 }
 EXPORT_SYMBOL_GPL(xdr_init_decode);
 
+/**
+ * xdr_inline_peek - Allow read-ahead in the XDR data stream
+ * @xdr: pointer to xdr_stream struct
+ * @nbytes: number of bytes of data to decode
+ *
+ * Check if the input buffer is long enough to enable us to decode
+ * 'nbytes' more bytes of data starting at the current position.
+ * If so return the current pointer without updating the current
+ * pointer position.
+ */
+__be32 * xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes)
+{
+	__be32 *p = xdr->p;
+	__be32 *q = p + XDR_QUADLEN(nbytes);
+
+	if (unlikely(q > xdr->end || q < p))
+		return NULL;
+	return p;
+}
+EXPORT_SYMBOL_GPL(xdr_inline_peek);
+
 /**
  * xdr_inline_decode - Retrieve non-page XDR data to decode
  * @xdr: pointer to xdr_stream struct