1 files changed, 354 insertions, 344 deletions

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 8adb32a9387..b01fbfb51f4 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -1,40 +1,37 @@
-
+/*
+ * Copyright (C) Neil Brown 2002
+ * Copyright (C) Christoph Hellwig 2007
+ *
+ * This file contains the code mapping from inodes to NFS file handles,
+ * and for mapping back from file handles to dentries.
+ *
+ * For details on why we do all the strange and hairy things in here
+ * take a look at Documentation/filesystems/nfs/Exporting.
+ */
 #include <linux/exportfs.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/sched.h>
 
 #define dprintk(fmt, args...) do{}while(0)
 
 
-static int get_name(struct dentry *dentry, char *name,
-		struct dentry *child);
-
-
-static struct dentry *exportfs_get_dentry(struct super_block *sb, void *obj)
-{
-	struct dentry *result = ERR_PTR(-ESTALE);
+static int get_name(const struct path *path, char *name, struct dentry *child);
 
-	if (sb->s_export_op->get_dentry) {
-		result = sb->s_export_op->get_dentry(sb, obj);
-		if (!result)
-			result = ERR_PTR(-ESTALE);
-	}
 
-	return result;
-}
-
-static int exportfs_get_name(struct dentry *dir, char *name,
-		struct dentry *child)
+static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir,
+		char *name, struct dentry *child)
 {
-	struct export_operations *nop = dir->d_sb->s_export_op;
+	const struct export_operations *nop = dir->d_sb->s_export_op;
+	struct path path = {.mnt = mnt, .dentry = dir};
 
 	if (nop->get_name)
 		return nop->get_name(dir, name, child);
 	else
-		return get_name(dir, name, child);
+		return get_name(&path, name, child);
 }
 
 /*
@@ -46,297 +43,196 @@ find_acceptable_alias(struct dentry *result,
 		void *context)
 {
 	struct dentry *dentry, *toput = NULL;
+	struct inode *inode;
 
 	if (acceptable(context, result))
 		return result;
 
-	spin_lock(&dcache_lock);
-	list_for_each_entry(dentry, &result->d_inode->i_dentry, d_alias) {
-		dget_locked(dentry);
-		spin_unlock(&dcache_lock);
+	inode = result->d_inode;
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+		dget(dentry);
+		spin_unlock(&inode->i_lock);
 		if (toput)
 			dput(toput);
 		if (dentry != result && acceptable(context, dentry)) {
 			dput(result);
 			return dentry;
 		}
-		spin_lock(&dcache_lock);
+		spin_lock(&inode->i_lock);
 		toput = dentry;
 	}
-	spin_unlock(&dcache_lock);
+	spin_unlock(&inode->i_lock);
 
 	if (toput)
 		dput(toput);
 	return NULL;
 }
 
-/*
- * Find root of a disconnected subtree and return a reference to it.
- */
-static struct dentry *
-find_disconnected_root(struct dentry *dentry)
+static bool dentry_connected(struct dentry *dentry)
 {
 	dget(dentry);
-	spin_lock(&dentry->d_lock);
-	while (!IS_ROOT(dentry) &&
-	       (dentry->d_parent->d_flags & DCACHE_DISCONNECTED)) {
-		struct dentry *parent = dentry->d_parent;
-		dget(parent);
-		spin_unlock(&dentry->d_lock);
+	while (dentry->d_flags & DCACHE_DISCONNECTED) {
+		struct dentry *parent = dget_parent(dentry);
+
 		dput(dentry);
+		if (IS_ROOT(dentry)) {
+			dput(parent);
+			return false;
+		}
 		dentry = parent;
-		spin_lock(&dentry->d_lock);
 	}
-	spin_unlock(&dentry->d_lock);
-	return dentry;
+	dput(dentry);
+	return true;
 }
 
-
-/*
- * Make sure target_dir is fully connected to the dentry tree.
- *
- * It may already be, as the flag isn't always updated when connection happens.
- */
-static int
-reconnect_path(struct super_block *sb, struct dentry *target_dir)
+static void clear_disconnected(struct dentry *dentry)
 {
-	char nbuf[NAME_MAX+1];
-	int noprogress = 0;
-	int err = -ESTALE;
+	dget(dentry);
+	while (dentry->d_flags & DCACHE_DISCONNECTED) {
+		struct dentry *parent = dget_parent(dentry);
 
-	/*
-	 * It is possible that a confused file system might not let us complete
-	 * the path to the root.  For example, if get_parent returns a directory
-	 * in which we cannot find a name for the child.  While this implies a
-	 * very sick filesystem we don't want it to cause knfsd to spin.  Hence
-	 * the noprogress counter.  If we go through the loop 10 times (2 is
-	 * probably enough) without getting anywhere, we just give up
-	 */
-	while (target_dir->d_flags & DCACHE_DISCONNECTED && noprogress++ < 10) {
-		struct dentry *pd = find_disconnected_root(target_dir);
-
-		if (!IS_ROOT(pd)) {
-			/* must have found a connected parent - great */
-			spin_lock(&pd->d_lock);
-			pd->d_flags &= ~DCACHE_DISCONNECTED;
-			spin_unlock(&pd->d_lock);
-			noprogress = 0;
-		} else if (pd == sb->s_root) {
-			printk(KERN_ERR "export: Eeek filesystem root is not connected, impossible\n");
-			spin_lock(&pd->d_lock);
-			pd->d_flags &= ~DCACHE_DISCONNECTED;
-			spin_unlock(&pd->d_lock);
-			noprogress = 0;
-		} else {
-			/*
-			 * We have hit the top of a disconnected path, try to
-			 * find parent and connect.
-			 *
-			 * Racing with some other process renaming a directory
-			 * isn't much of a problem here.  If someone renames
-			 * the directory, it will end up properly connected,
-			 * which is what we want
-			 *
-			 * Getting the parent can't be supported generically,
-			 * the locking is too icky.
-			 *
-			 * Instead we just return EACCES.  If server reboots
-			 * or inodes get flushed, you lose
-			 */
-			struct dentry *ppd = ERR_PTR(-EACCES);
-			struct dentry *npd;
-
-			mutex_lock(&pd->d_inode->i_mutex);
-			if (sb->s_export_op->get_parent)
-				ppd = sb->s_export_op->get_parent(pd);
-			mutex_unlock(&pd->d_inode->i_mutex);
-
-			if (IS_ERR(ppd)) {
-				err = PTR_ERR(ppd);
-				dprintk("%s: get_parent of %ld failed, err %d\n",
-					__FUNCTION__, pd->d_inode->i_ino, err);
-				dput(pd);
-				break;
-			}
+		WARN_ON_ONCE(IS_ROOT(dentry));
 
-			dprintk("%s: find name of %lu in %lu\n", __FUNCTION__,
-				pd->d_inode->i_ino, ppd->d_inode->i_ino);
-			err = exportfs_get_name(ppd, nbuf, pd);
-			if (err) {
-				dput(ppd);
-				dput(pd);
-				if (err == -ENOENT)
-					/* some race between get_parent and
-					 * get_name?  just try again
-					 */
-					continue;
-				break;
-			}
-			dprintk("%s: found name: %s\n", __FUNCTION__, nbuf);
-			mutex_lock(&ppd->d_inode->i_mutex);
-			npd = lookup_one_len(nbuf, ppd, strlen(nbuf));
-			mutex_unlock(&ppd->d_inode->i_mutex);
-			if (IS_ERR(npd)) {
-				err = PTR_ERR(npd);
-				dprintk("%s: lookup failed: %d\n",
-					__FUNCTION__, err);
-				dput(ppd);
-				dput(pd);
-				break;
-			}
-			/* we didn't really want npd, we really wanted
-			 * a side-effect of the lookup.
-			 * hopefully, npd == pd, though it isn't really
-			 * a problem if it isn't
-			 */
-			if (npd == pd)
-				noprogress = 0;
-			else
-				printk("%s: npd != pd\n", __FUNCTION__);
-			dput(npd);
-			dput(ppd);
-			if (IS_ROOT(pd)) {
-				/* something went wrong, we have to give up */
-				dput(pd);
-				break;
-			}
-		}
-		dput(pd);
-	}
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_DISCONNECTED;
+		spin_unlock(&dentry->d_lock);
 
-	if (target_dir->d_flags & DCACHE_DISCONNECTED) {
-		/* something went wrong - oh-well */
-		if (!err)
-			err = -ESTALE;
-		return err;
+		dput(dentry);
+		dentry = parent;
 	}
-
-	return 0;
+	dput(dentry);
 }
 
-/**
- * find_exported_dentry - helper routine to implement export_operations->decode_fh
- * @sb:		The &super_block identifying the filesystem
- * @obj:	An opaque identifier of the object to be found - passed to
- *		get_inode
- * @parent:	An optional opqaue identifier of the parent of the object.
- * @acceptable:	A function used to test possible &dentries to see if they are
- *		acceptable
- * @context:	A parameter to @acceptable so that it knows on what basis to
- *		judge.
+/*
+ * Reconnect a directory dentry with its parent.
  *
- * find_exported_dentry is the central helper routine to enable file systems
- * to provide the decode_fh() export_operation.  It's main task is to take
- * an &inode, find or create an appropriate &dentry structure, and possibly
- * splice this into the dcache in the correct place.
+ * This can return a dentry, or NULL, or an error.
  *
- * The decode_fh() operation provided by the filesystem should call
- * find_exported_dentry() with the same parameters that it received except
- * that instead of the file handle fragment, pointers to opaque identifiers
- * for the object and optionally its parent are passed.  The default decode_fh
- * routine passes one pointer to the start of the filehandle fragment, and
- * one 8 bytes into the fragment.  It is expected that most filesystems will
- * take this approach, though the offset to the parent identifier may well be
- * different.
+ * In the first case the returned dentry is the parent of the given
+ * dentry, and may itself need to be reconnected to its parent.
  *
- * find_exported_dentry() will call get_dentry to get an dentry pointer from
- * the file system.  If any &dentry in the d_alias list is acceptable, it will
- * be returned.  Otherwise find_exported_dentry() will attempt to splice a new
- * &dentry into the dcache using get_name() and get_parent() to find the
- * appropriate place.
+ * In the NULL case, a concurrent VFS operation has either renamed or
+ * removed this directory.  The concurrent operation has reconnected our
+ * dentry, so we no longer need to.
  */
-
-struct dentry *
-find_exported_dentry(struct super_block *sb, void *obj, void *parent,
-		     int (*acceptable)(void *context, struct dentry *de),
-		     void *context)
+static struct dentry *reconnect_one(struct vfsmount *mnt,
+		struct dentry *dentry, char *nbuf)
 {
-	struct dentry *result, *alias;
-	int err = -ESTALE;
+	struct dentry *parent;
+	struct dentry *tmp;
+	int err;
+
+	parent = ERR_PTR(-EACCES);
+	mutex_lock(&dentry->d_inode->i_mutex);
+	if (mnt->mnt_sb->s_export_op->get_parent)
+		parent = mnt->mnt_sb->s_export_op->get_parent(dentry);
+	mutex_unlock(&dentry->d_inode->i_mutex);
+
+	if (IS_ERR(parent)) {
+		dprintk("%s: get_parent of %ld failed, err %d\n",
+			__func__, dentry->d_inode->i_ino, PTR_ERR(parent));
+		return parent;
+	}
 
+	dprintk("%s: find name of %lu in %lu\n", __func__,
+		dentry->d_inode->i_ino, parent->d_inode->i_ino);
+	err = exportfs_get_name(mnt, parent, nbuf, dentry);
+	if (err == -ENOENT)
+		goto out_reconnected;
+	if (err)
+		goto out_err;
+	dprintk("%s: found name: %s\n", __func__, nbuf);
+	mutex_lock(&parent->d_inode->i_mutex);
+	tmp = lookup_one_len(nbuf, parent, strlen(nbuf));
+	mutex_unlock(&parent->d_inode->i_mutex);
+	if (IS_ERR(tmp)) {
+		dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
+		goto out_err;
+	}
+	if (tmp != dentry) {
+		dput(tmp);
+		goto out_reconnected;
+	}
+	dput(tmp);
+	if (IS_ROOT(dentry)) {
+		err = -ESTALE;
+		goto out_err;
+	}
+	return parent;
+
+out_err:
+	dput(parent);
+	return ERR_PTR(err);
+out_reconnected:
+	dput(parent);
 	/*
-	 * Attempt to find the inode.
+	 * Someone must have renamed our entry into another parent, in
+	 * which case it has been reconnected by the rename.
+	 *
+	 * Or someone removed it entirely, in which case filehandle
+	 * lookup will succeed but the directory is now IS_DEAD and
+	 * subsequent operations on it will fail.
+	 *
+	 * Alternatively, maybe there was no race at all, and the
+	 * filesystem is just corrupt and gave us a parent that doesn't
+	 * actually contain any entry pointing to this inode.  So,
+	 * double check that this worked and return -ESTALE if not:
 	 */
-	result = exportfs_get_dentry(sb, obj);
-	if (IS_ERR(result))
-		return result;
-
-	if (S_ISDIR(result->d_inode->i_mode)) {
-		if (!(result->d_flags & DCACHE_DISCONNECTED)) {
-			if (acceptable(context, result))
-				return result;
-			err = -EACCES;
-			goto err_result;
-		}
-
-		err = reconnect_path(sb, result);
-		if (err)
-			goto err_result;
-	} else {
-		struct dentry *target_dir, *nresult;
-		char nbuf[NAME_MAX+1];
+	if (!dentry_connected(dentry))
+		return ERR_PTR(-ESTALE);
+	return NULL;
+}
 
-		alias = find_acceptable_alias(result, acceptable, context);
-		if (alias)
-			return alias;
+/*
+ * Make sure target_dir is fully connected to the dentry tree.
+ *
+ * On successful return, DCACHE_DISCONNECTED will be cleared on
+ * target_dir, and target_dir->d_parent->...->d_parent will reach the
+ * root of the filesystem.
+ *
+ * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected.
+ * But the converse is not true: target_dir may have DCACHE_DISCONNECTED
+ * set but already be connected.  In that case we'll verify the
+ * connection to root and then clear the flag.
+ *
+ * Note that target_dir could be removed by a concurrent operation.  In
+ * that case reconnect_path may still succeed with target_dir fully
+ * connected, but further operations using the filehandle will fail when
+ * necessary (due to S_DEAD being set on the directory).
+ */
+static int
+reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf)
+{
+	struct dentry *dentry, *parent;
 
-		if (parent == NULL)
-			goto err_result;
+	dentry = dget(target_dir);
 
-		target_dir = exportfs_get_dentry(sb,parent);
-		if (IS_ERR(target_dir)) {
-			err = PTR_ERR(target_dir);
-			goto err_result;
-		}
+	while (dentry->d_flags & DCACHE_DISCONNECTED) {
+		BUG_ON(dentry == mnt->mnt_sb->s_root);
 
-		err = reconnect_path(sb, target_dir);
-		if (err) {
-			dput(target_dir);
-			goto err_result;
-		}
+		if (IS_ROOT(dentry))
+			parent = reconnect_one(mnt, dentry, nbuf);
+		else
+			parent = dget_parent(dentry);
 
-		/*
-		 * As we weren't after a directory, have one more step to go.
-		 */
-		err = exportfs_get_name(target_dir, nbuf, result);
-		if (!err) {
-			mutex_lock(&target_dir->d_inode->i_mutex);
-			nresult = lookup_one_len(nbuf, target_dir,
-						 strlen(nbuf));
-			mutex_unlock(&target_dir->d_inode->i_mutex);
-			if (!IS_ERR(nresult)) {
-				if (nresult->d_inode) {
-					dput(result);
-					result = nresult;
-				} else
-					dput(nresult);
-			}
-		}
-		dput(target_dir);
+		if (!parent)
+			break;
+		dput(dentry);
+		if (IS_ERR(parent))
+			return PTR_ERR(parent);
+		dentry = parent;
 	}
-
-	alias = find_acceptable_alias(result, acceptable, context);
-	if (alias)
-		return alias;
-
-	/* drat - I just cannot find anything acceptable */
-	dput(result);
-	/* It might be justifiable to return ESTALE here,
-	 * but the filehandle at-least looks reasonable good
-	 * and it may just be a permission problem, so returning
-	 * -EACCESS is safer
-	 */
-	return ERR_PTR(-EACCES);
-
- err_result:
-	dput(result);
-	return ERR_PTR(err);
+	dput(dentry);
+	clear_disconnected(target_dir);
+	return 0;
 }
 
 struct getdents_callback {
+	struct dir_context ctx;
 	char *name;		/* name that was found. It already points to a
 				   buffer NAME_MAX+1 is size */
-	unsigned long ino;	/* the inum we are looking for */
+	u64 ino;		/* the inum we are looking for */
 	int found;		/* inode matched? */
 	int sequence;		/* sequence counter */
 };
@@ -352,7 +248,7 @@ static int filldir_one(void * __buf, const char * name, int len,
 	int result = 0;
 
 	buf->sequence++;
-	if (buf->ino == ino) {
+	if (buf->ino == ino && len <= NAME_MAX) {
 		memcpy(buf->name, name, len);
 		buf->name[len] = '\0';
 		buf->found = 1;
@@ -363,20 +259,28 @@ static int filldir_one(void * __buf, const char * name, int len,
 
 /**
  * get_name - default export_operations->get_name function
- * @dentry: the directory in which to find a name
+ * @path:   the directory in which to find a name
  * @name:   a pointer to a %NAME_MAX+1 char buffer to store the name
  * @child:  the dentry for the child directory.
  *
  * calls readdir on the parent until it finds an entry with
  * the same inode number as the child, and returns that.
  */
-static int get_name(struct dentry *dentry, char *name,
-			struct dentry *child)
+static int get_name(const struct path *path, char *name, struct dentry *child)
 {
-	struct inode *dir = dentry->d_inode;
+	const struct cred *cred = current_cred();
+	struct inode *dir = path->dentry->d_inode;
 	int error;
 	struct file *file;
-	struct getdents_callback buffer;
+	struct kstat stat;
+	struct path child_path = {
+		.mnt = path->mnt,
+		.dentry = child,
+	};
+	struct getdents_callback buffer = {
+		.ctx.actor = filldir_one,
+		.name = name,
+	};
 
 	error = -ENOTDIR;
 	if (!dir || !S_ISDIR(dir->i_mode))
@@ -385,32 +289,40 @@ static int get_name(struct dentry *dentry, char *name,
 	if (!dir->i_fop)
 		goto out;
 	/*
+	 * inode->i_ino is unsigned long, kstat->ino is u64, so the
+	 * former would be insufficient on 32-bit hosts when the
+	 * filesystem supports 64-bit inode numbers.  So we need to
+	 * actually call ->getattr, not just read i_ino:
+	 */
+	error = vfs_getattr_nosec(&child_path, &stat);
+	if (error)
+		return error;
+	buffer.ino = stat.ino;
+	/*
 	 * Open the directory ...
 	 */
-	file = dentry_open(dget(dentry), NULL, O_RDONLY);
+	file = dentry_open(path, O_RDONLY, cred);
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out;
 
 	error = -EINVAL;
-	if (!file->f_op->readdir)
+	if (!file->f_op->iterate)
 		goto out_close;
 
-	buffer.name = name;
-	buffer.ino = child->d_inode->i_ino;
-	buffer.found = 0;
 	buffer.sequence = 0;
 	while (1) {
 		int old_seq = buffer.sequence;
 
-		error = vfs_readdir(file, filldir_one, &buffer);
+		error = iterate_dir(file, &buffer.ctx);
+		if (buffer.found) {
+			error = 0;
+			break;
+		}
 
 		if (error < 0)
 			break;
 
-		error = 0;
-		if (buffer.found)
-			break;
 		error = -ENOENT;
 		if (old_seq == buffer.sequence)
 			break;
@@ -424,110 +336,208 @@ out:
 
 /**
  * export_encode_fh - default export_operations->encode_fh function
- * @dentry:  the dentry to encode
- * @fh:      where to store the file handle fragment
+ * @inode:   the object to encode
+ * @fid:     where to store the file handle fragment
  * @max_len: maximum length to store there
- * @connectable: whether to store parent information
+ * @parent:  parent directory inode, if wanted
  *
  * This default encode_fh function assumes that the 32 inode number
  * is suitable for locating an inode, and that the generation number
  * can be used to check that it is still valid.  It places them in the
  * filehandle fragment where export_decode_fh expects to find them.
  */
-static int export_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len,
-		   int connectable)
+static int export_encode_fh(struct inode *inode, struct fid *fid,
+		int *max_len, struct inode *parent)
 {
-	struct inode * inode = dentry->d_inode;
 	int len = *max_len;
-	int type = 1;
-	
-	if (len < 2 || (connectable && len < 4))
-		return 255;
+	int type = FILEID_INO32_GEN;
+
+	if (parent && (len < 4)) {
+		*max_len = 4;
+		return FILEID_INVALID;
+	} else if (len < 2) {
+		*max_len = 2;
+		return FILEID_INVALID;
+	}
 
 	len = 2;
-	fh[0] = inode->i_ino;
-	fh[1] = inode->i_generation;
-	if (connectable && !S_ISDIR(inode->i_mode)) {
-		struct inode *parent;
-
-		spin_lock(&dentry->d_lock);
-		parent = dentry->d_parent->d_inode;
-		fh[2] = parent->i_ino;
-		fh[3] = parent->i_generation;
-		spin_unlock(&dentry->d_lock);
+	fid->i32.ino = inode->i_ino;
+	fid->i32.gen = inode->i_generation;
+	if (parent) {
+		fid->i32.parent_ino = parent->i_ino;
+		fid->i32.parent_gen = parent->i_generation;
 		len = 4;
-		type = 2;
+		type = FILEID_INO32_GEN_PARENT;
 	}
 	*max_len = len;
 	return type;
 }
 
-
-/**
- * export_decode_fh - default export_operations->decode_fh function
- * @sb:  The superblock
- * @fh:  pointer to the file handle fragment
- * @fh_len: length of file handle fragment
- * @acceptable: function for testing acceptability of dentrys
- * @context:   context for @acceptable
- *
- * This is the default decode_fh() function.
- * a fileid_type of 1 indicates that the filehandlefragment
- * just contains an object identifier understood by  get_dentry.
- * a fileid_type of 2 says that there is also a directory
- * identifier 8 bytes in to the filehandlefragement.
- */
-static struct dentry *export_decode_fh(struct super_block *sb, __u32 *fh, int fh_len,
-			      int fileid_type,
-			 int (*acceptable)(void *context, struct dentry *de),
-			 void *context)
+int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
+			     int *max_len, struct inode *parent)
 {
-	__u32 parent[2];
-	parent[0] = parent[1] = 0;
-	if (fh_len < 2 || fileid_type > 2)
-		return NULL;
-	if (fileid_type == 2) {
-		if (fh_len > 2) parent[0] = fh[2];
-		if (fh_len > 3) parent[1] = fh[3];
-	}
-	return find_exported_dentry(sb, fh, parent,
-				   acceptable, context);
+	const struct export_operations *nop = inode->i_sb->s_export_op;
+
+	if (nop && nop->encode_fh)
+		return nop->encode_fh(inode, fid->raw, max_len, parent);
+
+	return export_encode_fh(inode, fid, max_len, parent);
 }
+EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh);
 
-int exportfs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len,
+int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
 		int connectable)
 {
- 	struct export_operations *nop = dentry->d_sb->s_export_op;
 	int error;
+	struct dentry *p = NULL;
+	struct inode *inode = dentry->d_inode, *parent = NULL;
 
-	if (nop->encode_fh)
-		error = nop->encode_fh(dentry, fh, max_len, connectable);
-	else
-		error = export_encode_fh(dentry, fh, max_len, connectable);
+	if (connectable && !S_ISDIR(inode->i_mode)) {
+		p = dget_parent(dentry);
+		/*
+		 * note that while p might've ceased to be our parent already,
+		 * it's still pinned by and still positive.
+		 */
+		parent = p->d_inode;
+	}
+
+	error = exportfs_encode_inode_fh(inode, fid, max_len, parent);
+	dput(p);
 
 	return error;
 }
 EXPORT_SYMBOL_GPL(exportfs_encode_fh);
 
-struct dentry *exportfs_decode_fh(struct vfsmount *mnt, __u32 *fh, int fh_len,
-		int fileid_type, int (*acceptable)(void *, struct dentry *),
-		void *context)
+struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
+		int fh_len, int fileid_type,
+		int (*acceptable)(void *, struct dentry *), void *context)
 {
-	struct export_operations *nop = mnt->mnt_sb->s_export_op;
-	struct dentry *result;
+	const struct export_operations *nop = mnt->mnt_sb->s_export_op;
+	struct dentry *result, *alias;
+	char nbuf[NAME_MAX+1];
+	int err;
+
+	/*
+	 * Try to get any dentry for the given file handle from the filesystem.
+	 */
+	if (!nop || !nop->fh_to_dentry)
+		return ERR_PTR(-ESTALE);
+	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
+	if (!result)
+		result = ERR_PTR(-ESTALE);
+	if (IS_ERR(result))
+		return result;
+
+	if (S_ISDIR(result->d_inode->i_mode)) {
+		/*
+		 * This request is for a directory.
+		 *
+		 * On the positive side there is only one dentry for each
+		 * directory inode.  On the negative side this implies that we
+		 * to ensure our dentry is connected all the way up to the
+		 * filesystem root.
+		 */
+		if (result->d_flags & DCACHE_DISCONNECTED) {
+			err = reconnect_path(mnt, result, nbuf);
+			if (err)
+				goto err_result;
+		}
+
+		if (!acceptable(context, result)) {
+			err = -EACCES;
+			goto err_result;
+		}
 
-	if (nop->decode_fh) {
-		result = nop->decode_fh(mnt->mnt_sb, fh, fh_len, fileid_type,
-			acceptable, context);
+		return result;
 	} else {
-		result = export_decode_fh(mnt->mnt_sb, fh, fh_len, fileid_type,
-			acceptable, context);
+		/*
+		 * It's not a directory.  Life is a little more complicated.
+		 */
+		struct dentry *target_dir, *nresult;
+
+		/*
+		 * See if either the dentry we just got from the filesystem
+		 * or any alias for it is acceptable.  This is always true
+		 * if this filesystem is exported without the subtreecheck
+		 * option.  If the filesystem is exported with the subtree
+		 * check option there's a fair chance we need to look at
+		 * the parent directory in the file handle and make sure
+		 * it's connected to the filesystem root.
+		 */
+		alias = find_acceptable_alias(result, acceptable, context);
+		if (alias)
+			return alias;
+
+		/*
+		 * Try to extract a dentry for the parent directory from the
+		 * file handle.  If this fails we'll have to give up.
+		 */
+		err = -ESTALE;
+		if (!nop->fh_to_parent)
+			goto err_result;
+
+		target_dir = nop->fh_to_parent(mnt->mnt_sb, fid,
+				fh_len, fileid_type);
+		if (!target_dir)
+			goto err_result;
+		err = PTR_ERR(target_dir);
+		if (IS_ERR(target_dir))
+			goto err_result;
+
+		/*
+		 * And as usual we need to make sure the parent directory is
+		 * connected to the filesystem root.  The VFS really doesn't
+		 * like disconnected directories..
+		 */
+		err = reconnect_path(mnt, target_dir, nbuf);
+		if (err) {
+			dput(target_dir);
+			goto err_result;
+		}
+
+		/*
+		 * Now that we've got both a well-connected parent and a
+		 * dentry for the inode we're after, make sure that our
+		 * inode is actually connected to the parent.
+		 */
+		err = exportfs_get_name(mnt, target_dir, nbuf, result);
+		if (!err) {
+			mutex_lock(&target_dir->d_inode->i_mutex);
+			nresult = lookup_one_len(nbuf, target_dir,
+						 strlen(nbuf));
+			mutex_unlock(&target_dir->d_inode->i_mutex);
+			if (!IS_ERR(nresult)) {
+				if (nresult->d_inode) {
+					dput(result);
+					result = nresult;
+				} else
+					dput(nresult);
+			}
+		}
+
+		/*
+		 * At this point we are done with the parent, but it's pinned
+		 * by the child dentry anyway.
+		 */
+		dput(target_dir);
+
+		/*
+		 * And finally make sure the dentry is actually acceptable
+		 * to NFSD.
+		 */
+		alias = find_acceptable_alias(result, acceptable, context);
+		if (!alias) {
+			err = -EACCES;
+			goto err_result;
+		}
+
+		return alias;
 	}
 
-	return result;
+ err_result:
+	dput(result);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(exportfs_decode_fh);
 
-EXPORT_SYMBOL(find_exported_dentry);
-
 MODULE_LICENSE("GPL");