Merge with /pub/scm/linux/kernel/git/torvalds/linux-2.6.git

Signed-off-by: Steve French <sfrench@us.ibm.com>

49 files changed, 948 insertions, 740 deletions

diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index eda449778fa5..c4d13bf904d2 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -1,7 +1,7 @@
 /*
  * V9FS FID Management
  *
- *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -40,7 +40,7 @@
  *
  */
 
-static int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry)
+int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry)
 {
 	struct list_head *fid_list = (struct list_head *)dentry->d_fsdata;
 	dprintk(DEBUG_9P, "fid %d (%p) dentry %s (%p)\n", fid->fid, fid,
@@ -57,7 +57,6 @@ static int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry)
 	}
 
 	fid->uid = current->uid;
-	fid->pid = current->pid;
 	list_add(&fid->list, fid_list);
 	return 0;
 }
@@ -68,14 +67,11 @@ static int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry)
  *
  */
 
-struct v9fs_fid *v9fs_fid_create(struct dentry *dentry,
-	struct v9fs_session_info *v9ses, int fid, int create)
+struct v9fs_fid *v9fs_fid_create(struct v9fs_session_info *v9ses, int fid)
 {
 	struct v9fs_fid *new;
 
-	dprintk(DEBUG_9P, "fid create dentry %p, fid %d, create %d\n",
-		dentry, fid, create);
-
+	dprintk(DEBUG_9P, "fid create fid %d\n", fid);
 	new = kmalloc(sizeof(struct v9fs_fid), GFP_KERNEL);
 	if (new == NULL) {
 		dprintk(DEBUG_ERROR, "Out of Memory\n");
@@ -85,19 +81,13 @@ struct v9fs_fid *v9fs_fid_create(struct dentry *dentry,
 	new->fid = fid;
 	new->v9ses = v9ses;
 	new->fidopen = 0;
-	new->fidcreate = create;
 	new->fidclunked = 0;
 	new->iounit = 0;
 	new->rdir_pos = 0;
 	new->rdir_fcall = NULL;
+	INIT_LIST_HEAD(&new->list);
 
-	if (v9fs_fid_insert(new, dentry) == 0)
-		return new;
-	else {
-		dprintk(DEBUG_ERROR, "Problems inserting to dentry\n");
-		kfree(new);
-		return NULL;
-	}
+	return new;
 }
 
 /**
@@ -113,140 +103,29 @@ void v9fs_fid_destroy(struct v9fs_fid *fid)
 }
 
 /**
- * v9fs_fid_walk_up - walks from the process current directory
- * 	up to the specified dentry.
- */
-static struct v9fs_fid *v9fs_fid_walk_up(struct dentry *dentry)
-{
-	int fidnum, cfidnum, err;
-	struct v9fs_fid *cfid;
-	struct dentry *cde;
-	struct v9fs_session_info *v9ses;
-
-	v9ses = v9fs_inode2v9ses(current->fs->pwd->d_inode);
-	cfid = v9fs_fid_lookup(current->fs->pwd);
-	if (cfid == NULL) {
-		dprintk(DEBUG_ERROR, "process cwd doesn't have a fid\n");
-		return ERR_PTR(-ENOENT);
-	}
-
-	cfidnum = cfid->fid;
-	cde = current->fs->pwd;
-	/* TODO: take advantage of multiwalk */
-
-	fidnum = v9fs_get_idpool(&v9ses->fidpool);
-	if (fidnum < 0) {
-		dprintk(DEBUG_ERROR, "could not get a new fid num\n");
-		err = -ENOENT;
-		goto clunk_fid;
-	}
-
-	while (cde != dentry) {
-		if (cde == cde->d_parent) {
-			dprintk(DEBUG_ERROR, "can't find dentry\n");
-			err = -ENOENT;
-			goto clunk_fid;
-		}
-
-		err = v9fs_t_walk(v9ses, cfidnum, fidnum, "..", NULL);
-		if (err < 0) {
-			dprintk(DEBUG_ERROR, "problem walking to parent\n");
-			goto clunk_fid;
-		}
-
-		cfidnum = fidnum;
-		cde = cde->d_parent;
-	}
-
-	return v9fs_fid_create(dentry, v9ses, fidnum, 0);
-
-clunk_fid:
-	v9fs_t_clunk(v9ses, fidnum);
-	return ERR_PTR(err);
-}
-
-/**
  * v9fs_fid_lookup - retrieve the right fid from a  particular dentry
  * @dentry: dentry to look for fid in
  * @type: intent of lookup (operation or traversal)
  *
- * search list of fids associated with a dentry for a fid with a matching
- * thread id or uid.  If that fails, look up the dentry's parents to see if you
- * can find a matching fid.
+ * find a fid in the dentry
+ *
+ * TODO: only match fids that have the same uid as current user
  *
  */
 
 struct v9fs_fid *v9fs_fid_lookup(struct dentry *dentry)
 {
 	struct list_head *fid_list = (struct list_head *)dentry->d_fsdata;
-	struct v9fs_fid *current_fid = NULL;
-	struct v9fs_fid *temp = NULL;
 	struct v9fs_fid *return_fid = NULL;
 
 	dprintk(DEBUG_9P, " dentry: %s (%p)\n", dentry->d_iname, dentry);
 
-	if (fid_list) {
-		list_for_each_entry_safe(current_fid, temp, fid_list, list) {
-			if (!current_fid->fidcreate) {
-				return_fid = current_fid;
-				break;
-			}
-		}
-
-		if (!return_fid)
-			return_fid = current_fid;
-	}
-
-	/* we are at the root but didn't match */
-	if ((!return_fid) && (dentry->d_parent == dentry)) {
-		/* TODO: clone attach with new uid */
-		return_fid = current_fid;
-	}
+	if (fid_list)
+		return_fid = list_entry(fid_list->next, struct v9fs_fid, list);
 
 	if (!return_fid) {
-		struct dentry *par = current->fs->pwd->d_parent;
-		int count = 1;
-		while (par != NULL) {
-			if (par == dentry)
-				break;
-			count++;
-			if (par == par->d_parent) {
-				dprintk(DEBUG_ERROR,
-					"got to root without finding dentry\n");
-				break;
-			}
-			par = par->d_parent;
-		}
-
-/* XXX - there may be some duplication we can get rid of */
-		if (par == dentry) {
-			return_fid = v9fs_fid_walk_up(dentry);
-			if (IS_ERR(return_fid))
-				return_fid = NULL;
-		}
+		dprintk(DEBUG_ERROR, "Couldn't find a fid in dentry\n");
 	}
 
 	return return_fid;
 }
-
-struct v9fs_fid *v9fs_fid_get_created(struct dentry *dentry)
-{
-	struct list_head *fid_list;
-	struct v9fs_fid *fid, *ftmp, *ret;
-
-	dprintk(DEBUG_9P, " dentry: %s (%p)\n", dentry->d_iname, dentry);
-	fid_list = (struct list_head *)dentry->d_fsdata;
-	ret = NULL;
-	if (fid_list) {
-		list_for_each_entry_safe(fid, ftmp, fid_list, list) {
-			if (fid->fidcreate && fid->pid == current->pid) {
-				list_del(&fid->list);
-				ret = fid;
-				break;
-			}
-		}
-	}
-
-	dprintk(DEBUG_9P, "return %p\n", ret);
-	return ret;
-}
diff --git a/fs/9p/fid.h b/fs/9p/fid.h
index 84c673a44c83..1fc2dd08d75a 100644
--- a/fs/9p/fid.h
+++ b/fs/9p/fid.h
@@ -33,7 +33,6 @@ struct v9fs_fid {
 
 	u32 fid;
 	unsigned char fidopen;	  /* set when fid is opened */
-	unsigned char fidcreate;  /* set when fid was just created */
 	unsigned char fidclunked; /* set when fid has already been clunked */
 
 	struct v9fs_qid qid;
@@ -45,7 +44,6 @@ struct v9fs_fid {
 	struct v9fs_fcall *rdir_fcall;
 
 	/* management stuff */
-	pid_t pid;		/* thread associated with this fid */
 	uid_t uid;		/* user associated with this fid */
 
 	/* private data */
@@ -56,5 +54,5 @@ struct v9fs_fid {
 struct v9fs_fid *v9fs_fid_lookup(struct dentry *dentry);
 struct v9fs_fid *v9fs_fid_get_created(struct dentry *);
 void v9fs_fid_destroy(struct v9fs_fid *fid);
-struct v9fs_fid *v9fs_fid_create(struct dentry *,
-	struct v9fs_session_info *v9ses, int fid, int create);
+struct v9fs_fid *v9fs_fid_create(struct v9fs_session_info *, int fid);
+int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry);
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index ef3386549140..61352491ba36 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -397,6 +397,7 @@ v9fs_session_init(struct v9fs_session_info *v9ses,
 	}
 
 	if (v9ses->afid != ~0) {
+		dprintk(DEBUG_ERROR, "afid not equal to ~0\n");
 		if (v9fs_t_clunk(v9ses, v9ses->afid))
 			dprintk(DEBUG_ERROR, "clunk failed\n");
 	}
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 69cf2905dc90..a759278acaae 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -51,3 +51,4 @@ int v9fs_dir_release(struct inode *inode, struct file *filp);
 int v9fs_file_open(struct inode *inode, struct file *file);
 void v9fs_inode2stat(struct inode *inode, struct v9fs_stat *stat);
 void v9fs_dentry_release(struct dentry *);
+int v9fs_uflags2omode(int uflags);
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 2dd806dac9f1..12c9cc926b71 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -43,47 +43,18 @@
 #include "fid.h"
 
 /**
- * v9fs_dentry_validate - VFS dcache hook to validate cache
- * @dentry:  dentry that is being validated
- * @nd: path data
+ * v9fs_dentry_delete - called when dentry refcount equals 0
+ * @dentry:  dentry in question
  *
- * dcache really shouldn't be used for 9P2000 as at all due to
- * potential attached semantics to directory traversal (walk).
- *
- * FUTURE: look into how to use dcache to allow multi-stage
- * walks in Plan 9 & potential for better dcache operation which
- * would remain valid for Plan 9 semantics.  Older versions
- * had validation via stat for those interested.  However, since
- * stat has the same approximate overhead as walk there really
- * is no difference.  The only improvement would be from a
- * time-decay cache like NFS has and that undermines the
- * synchronous nature of 9P2000.
+ * By returning 1 here we should remove cacheing of unused
+ * dentry components.
  *
  */
 
-static int v9fs_dentry_validate(struct dentry *dentry, struct nameidata *nd)
+int v9fs_dentry_delete(struct dentry *dentry)
 {
-	struct dentry *dc = current->fs->pwd;
-
-	dprintk(DEBUG_VFS, "dentry: %s (%p)\n", dentry->d_iname, dentry);
-	if (v9fs_fid_lookup(dentry)) {
-		dprintk(DEBUG_VFS, "VALID\n");
-		return 1;
-	}
-
-	while (dc != NULL) {
-		if (dc == dentry) {
-			dprintk(DEBUG_VFS, "VALID\n");
-			return 1;
-		}
-		if (dc == dc->d_parent)
-			break;
-
-		dc = dc->d_parent;
-	}
-
-	dprintk(DEBUG_VFS, "INVALID\n");
-	return 0;
+	dprintk(DEBUG_VFS, " dentry: %s (%p)\n", dentry->d_iname, dentry);
+	return 1;
 }
 
 /**
@@ -118,6 +89,6 @@ void v9fs_dentry_release(struct dentry *dentry)
 }
 
 struct dentry_operations v9fs_dentry_operations = {
-	.d_revalidate = v9fs_dentry_validate,
+	.d_delete = v9fs_dentry_delete,
 	.d_release = v9fs_dentry_release,
 };
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index c7e14d917215..de3a129698da 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -53,94 +53,70 @@
 int v9fs_file_open(struct inode *inode, struct file *file)
 {
 	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
-	struct v9fs_fid *v9fid, *fid;
+	struct v9fs_fid *vfid;
 	struct v9fs_fcall *fcall = NULL;
-	int open_mode = 0;
-	unsigned int iounit = 0;
-	int newfid = -1;
-	long result = -1;
+	int omode;
+	int fid = V9FS_NOFID;
+	int err;
 
 	dprintk(DEBUG_VFS, "inode: %p file: %p \n", inode, file);
 
-	v9fid = v9fs_fid_get_created(file->f_dentry);
-	if (!v9fid)
-		v9fid = v9fs_fid_lookup(file->f_dentry);
-
-	if (!v9fid) {
+	vfid = v9fs_fid_lookup(file->f_dentry);
+	if (!vfid) {
 		dprintk(DEBUG_ERROR, "Couldn't resolve fid from dentry\n");
 		return -EBADF;
 	}
 
-	if (!v9fid->fidcreate) {
-		fid = kmalloc(sizeof(struct v9fs_fid), GFP_KERNEL);
-		if (fid == NULL) {
-			dprintk(DEBUG_ERROR, "Out of Memory\n");
-			return -ENOMEM;
-		}
-
-		fid->fidopen = 0;
-		fid->fidcreate = 0;
-		fid->fidclunked = 0;
-		fid->iounit = 0;
-		fid->v9ses = v9ses;
-
-		newfid = v9fs_get_idpool(&v9ses->fidpool);
-		if (newfid < 0) {
+	fid = v9fs_get_idpool(&v9ses->fidpool);
+	if (fid < 0) {
 			eprintk(KERN_WARNING, "newfid fails!\n");
 			return -ENOSPC;
 		}
 
-		result =
-		    v9fs_t_walk(v9ses, v9fid->fid, newfid, NULL, NULL);
-
-		if (result < 0) {
-			v9fs_put_idpool(newfid, &v9ses->fidpool);
+	err = v9fs_t_walk(v9ses, vfid->fid, fid, NULL, NULL);
+	if (err < 0) {
 			dprintk(DEBUG_ERROR, "rewalk didn't work\n");
-			return -EBADF;
+		goto put_fid;
+	}
+
+	vfid = kmalloc(sizeof(struct v9fs_fid), GFP_KERNEL);
+	if (vfid == NULL) {
+		dprintk(DEBUG_ERROR, "out of memory\n");
+		goto clunk_fid;
 		}
 
-		fid->fid = newfid;
-		v9fid = fid;
 		/* TODO: do special things for O_EXCL, O_NOFOLLOW, O_SYNC */
 		/* translate open mode appropriately */
-		open_mode = file->f_flags & 0x3;
+	omode = v9fs_uflags2omode(file->f_flags);
+	err = v9fs_t_open(v9ses, fid, omode, &fcall);
+	if (err < 0) {
+		PRINT_FCALL_ERROR("open failed", fcall);
+		goto destroy_vfid;
+	}
 
-		if (file->f_flags & O_EXCL)
-			open_mode |= V9FS_OEXCL;
+	file->private_data = vfid;
+	vfid->fid = fid;
+	vfid->fidopen = 1;
+	vfid->fidclunked = 0;
+	vfid->iounit = fcall->params.ropen.iounit;
+	vfid->rdir_pos = 0;
+	vfid->rdir_fcall = NULL;
+	vfid->filp = file;
+	kfree(fcall);
 
-		if (v9ses->extended) {
-			if (file->f_flags & O_TRUNC)
-				open_mode |= V9FS_OTRUNC;
+	return 0;
 
-			if (file->f_flags & O_APPEND)
-				open_mode |= V9FS_OAPPEND;
-		}
+destroy_vfid:
+	v9fs_fid_destroy(vfid);
 
-		result = v9fs_t_open(v9ses, newfid, open_mode, &fcall);
-		if (result < 0) {
-			PRINT_FCALL_ERROR("open failed", fcall);
-			kfree(fcall);
-			return result;
-		}
+clunk_fid:
+	v9fs_t_clunk(v9ses, fid);
 
-		iounit = fcall->params.ropen.iounit;
+put_fid:
+	v9fs_put_idpool(fid, &v9ses->fidpool);
 		kfree(fcall);
-	} else {
-		/* create case */
-		newfid = v9fid->fid;
-		iounit = v9fid->iounit;
-		v9fid->fidcreate = 0;
-	}
-
-	file->private_data = v9fid;
-
-	v9fid->rdir_pos = 0;
-	v9fid->rdir_fcall = NULL;
-	v9fid->fidopen = 1;
-	v9fid->filp = file;
-	v9fid->iounit = iounit;
 
-	return 0;
+	return err;
 }
 
 /**
@@ -289,9 +265,7 @@ v9fs_file_write(struct file *filp, const char __user * data,
 		total += result;
 	} while (count);
 
-	if(inode->i_mapping->nrpages)
 		invalidate_inode_pages2(inode->i_mapping);
-
 	return total;
 }
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 63e5b0398e8b..dce729d42869 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -125,6 +125,38 @@ static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode)
 	return res;
 }
 
+int v9fs_uflags2omode(int uflags)
+{
+	int ret;
+
+	ret = 0;
+	switch (uflags&3) {
+	default:
+	case O_RDONLY:
+		ret = V9FS_OREAD;
+		break;
+
+	case O_WRONLY:
+		ret = V9FS_OWRITE;
+		break;
+
+	case O_RDWR:
+		ret = V9FS_ORDWR;
+		break;
+	}
+
+	if (uflags & O_EXCL)
+		ret |= V9FS_OEXCL;
+
+	if (uflags & O_TRUNC)
+		ret |= V9FS_OTRUNC;
+
+	if (uflags & O_APPEND)
+		ret |= V9FS_OAPPEND;
+
+	return ret;
+}
+
 /**
  * v9fs_blank_wstat - helper function to setup a 9P stat structure
  * @v9ses: 9P session info (for determining extended mode)
@@ -163,7 +195,7 @@ v9fs_blank_wstat(struct v9fs_wstat *wstat)
 
 struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 {
-	struct inode *inode = NULL;
+	struct inode *inode;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
 
 	dprintk(DEBUG_VFS, "super block: %p mode: %o\n", sb, mode);
@@ -222,171 +254,135 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 	return inode;
 }
 
-/**
- * v9fs_create - helper function to create files and directories
- * @dir: directory inode file is being created in
- * @file_dentry: dentry file is being created in
- * @perm: permissions file is being created with
- * @open_mode: resulting open mode for file
- *
- */
-
 static int
-v9fs_create(struct inode *dir,
-	    struct dentry *file_dentry,
-	    unsigned int perm, unsigned int open_mode)
+v9fs_create(struct v9fs_session_info *v9ses, u32 pfid, char *name,
+	u32 perm, u8 mode, u32 *fidp, struct v9fs_qid *qid, u32 *iounit)
 {
-	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
-	struct super_block *sb = dir->i_sb;
-	struct v9fs_fid *dirfid =
-	    v9fs_fid_lookup(file_dentry->d_parent);
-	struct v9fs_fid *fid = NULL;
-	struct inode *file_inode = NULL;
-	struct v9fs_fcall *fcall = NULL;
-	struct v9fs_qid qid;
-	int dirfidnum = -1;
-	long newfid = -1;
-	int result = 0;
-	unsigned int iounit = 0;
-	int wfidno = -1;
+	u32 fid;
 	int err;
+	struct v9fs_fcall *fcall;
 
-	perm = unixmode2p9mode(v9ses, perm);
-
-	dprintk(DEBUG_VFS, "dir: %p dentry: %p perm: %o mode: %o\n", dir,
-		file_dentry, perm, open_mode);
-
-	if (!dirfid)
-		return -EBADF;
-
-	dirfidnum = dirfid->fid;
-	if (dirfidnum < 0) {
-		dprintk(DEBUG_ERROR, "No fid for the directory #%lu\n",
-			dir->i_ino);
-		return -EBADF;
-	}
-
-	if (file_dentry->d_inode) {
-		dprintk(DEBUG_ERROR,
-			"Odd. There is an inode for dir %lu, name :%s:\n",
-			dir->i_ino, file_dentry->d_name.name);
-		return -EEXIST;
-	}
-
-	newfid = v9fs_get_idpool(&v9ses->fidpool);
-	if (newfid < 0) {
+	fid = v9fs_get_idpool(&v9ses->fidpool);
+	if (fid < 0) {
 		eprintk(KERN_WARNING, "no free fids available\n");
-		return -ENOSPC;
+		err = -ENOSPC;
+		goto error;
 	}
 
-	result = v9fs_t_walk(v9ses, dirfidnum, newfid, NULL, &fcall);
-	if (result < 0) {
+	err = v9fs_t_walk(v9ses, pfid, fid, NULL, &fcall);
+	if (err < 0) {
 		PRINT_FCALL_ERROR("clone error", fcall);
-		v9fs_put_idpool(newfid, &v9ses->fidpool);
-		newfid = -1;
-		goto CleanUpFid;
+		goto error;
 	}
-
 	kfree(fcall);
-	fcall = NULL;
 
-	result = v9fs_t_create(v9ses, newfid, (char *)file_dentry->d_name.name,
-			       perm, open_mode, &fcall);
-	if (result < 0) {
+	err = v9fs_t_create(v9ses, fid, name, perm, mode, &fcall);
+	if (err < 0) {
 		PRINT_FCALL_ERROR("create fails", fcall);
-		goto CleanUpFid;
+		goto error;
 	}
 
-	iounit = fcall->params.rcreate.iounit;
-	qid = fcall->params.rcreate.qid;
+	if (iounit)
+		*iounit = fcall->params.rcreate.iounit;
+
+	if (qid)
+		*qid = fcall->params.rcreate.qid;
+
+	if (fidp)
+		*fidp = fid;
+
 	kfree(fcall);
-	fcall = NULL;
+	return 0;
 
-	if (!(perm&V9FS_DMDIR)) {
-		fid = v9fs_fid_create(file_dentry, v9ses, newfid, 1);
-		dprintk(DEBUG_VFS, "fid %p %d\n", fid, fid->fidcreate);
-		if (!fid) {
-			result = -ENOMEM;
-			goto CleanUpFid;
-		}
+error:
+	if (fid >= 0)
+		v9fs_put_idpool(fid, &v9ses->fidpool);
 
-		fid->qid = qid;
-		fid->iounit = iounit;
-	} else {
-		err = v9fs_t_clunk(v9ses, newfid);
-		newfid = -1;
-		if (err < 0)
-			dprintk(DEBUG_ERROR, "clunk for mkdir failed: %d\n", err);
-	}
+	kfree(fcall);
+	return err;
+}
+
+static struct v9fs_fid*
+v9fs_clone_walk(struct v9fs_session_info *v9ses, u32 fid, struct dentry *dentry)
+{
+	int err;
+	u32 nfid;
+	struct v9fs_fid *ret;
+	struct v9fs_fcall *fcall;
 
-	/* walk to the newly created file and put the fid in the dentry */
-	wfidno = v9fs_get_idpool(&v9ses->fidpool);
-	if (wfidno < 0) {
+	nfid = v9fs_get_idpool(&v9ses->fidpool);
+	if (nfid < 0) {
 		eprintk(KERN_WARNING, "no free fids available\n");
-		return -ENOSPC;
+		err = -ENOSPC;
+		goto error;
 	}
 
-	result = v9fs_t_walk(v9ses, dirfidnum, wfidno,
-		(char *) file_dentry->d_name.name, &fcall);
-	if (result < 0) {
-		PRINT_FCALL_ERROR("clone error", fcall);
-		v9fs_put_idpool(wfidno, &v9ses->fidpool);
-		wfidno = -1;
-		goto CleanUpFid;
+	err = v9fs_t_walk(v9ses, fid, nfid, (char *) dentry->d_name.name,
+		&fcall);
+
+	if (err < 0) {
+		PRINT_FCALL_ERROR("walk error", fcall);
+		v9fs_put_idpool(nfid, &v9ses->fidpool);
+		goto error;
 	}
+
 	kfree(fcall);
 	fcall = NULL;
+	ret = v9fs_fid_create(v9ses, nfid);
+	if (!ret) {
+		err = -ENOMEM;
+		goto clunk_fid;
+	}
 
-	if (!v9fs_fid_create(file_dentry, v9ses, wfidno, 0)) {
-		v9fs_put_idpool(wfidno, &v9ses->fidpool);
-
-		goto CleanUpFid;
+	err = v9fs_fid_insert(ret, dentry);
+	if (err < 0) {
+		v9fs_fid_destroy(ret);
+		goto clunk_fid;
 	}
 
-	if ((perm & V9FS_DMSYMLINK) || (perm & V9FS_DMLINK) ||
-	    (perm & V9FS_DMNAMEDPIPE) || (perm & V9FS_DMSOCKET) ||
-	    (perm & V9FS_DMDEVICE))
-		return 0;
+	return ret;
 
-	result = v9fs_t_stat(v9ses, wfidno, &fcall);
-	if (result < 0) {
-		PRINT_FCALL_ERROR("stat error", fcall);
-		goto CleanUpFid;
-	}
+clunk_fid:
+	v9fs_t_clunk(v9ses, nfid);
+
+error:
+	kfree(fcall);
+	return ERR_PTR(err);
+}
 
+struct inode *
+v9fs_inode_from_fid(struct v9fs_session_info *v9ses, u32 fid,
+	struct super_block *sb)
+{
+	int err, umode;
+	struct inode *ret;
+	struct v9fs_fcall *fcall;
 
-	file_inode = v9fs_get_inode(sb,
-		p9mode2unixmode(v9ses, fcall->params.rstat.stat.mode));
+	ret = NULL;
+	err = v9fs_t_stat(v9ses, fid, &fcall);
+	if (err) {
+		PRINT_FCALL_ERROR("stat error", fcall);
+		goto error;
+	}
 
-	if ((!file_inode) || IS_ERR(file_inode)) {
-		dprintk(DEBUG_ERROR, "create inode failed\n");
-		result = -EBADF;
-		goto CleanUpFid;
+	umode = p9mode2unixmode(v9ses, fcall->params.rstat.stat.mode);
+	ret = v9fs_get_inode(sb, umode);
+	if (IS_ERR(ret)) {
+		err = PTR_ERR(ret);
+		ret = NULL;
+		goto error;
 	}
 
-	v9fs_stat2inode(&fcall->params.rstat.stat, file_inode, sb);
+	v9fs_stat2inode(&fcall->params.rstat.stat, ret, sb);
 	kfree(fcall);
-	fcall = NULL;
-	file_dentry->d_op = &v9fs_dentry_operations;
-	d_instantiate(file_dentry, file_inode);
-
-	return 0;
+	return ret;
 
-      CleanUpFid:
+error:
 	kfree(fcall);
-	fcall = NULL;
+	if (ret)
+		iput(ret);
 
-	if (newfid >= 0) {
- 		err = v9fs_t_clunk(v9ses, newfid);
- 		if (err < 0)
- 			dprintk(DEBUG_ERROR, "clunk failed: %d\n", err);
-	}
-	if (wfidno >= 0) {
- 		err = v9fs_t_clunk(v9ses, wfidno);
- 		if (err < 0)
- 			dprintk(DEBUG_ERROR, "clunk failed: %d\n", err);
-	}
-	return result;
+	return ERR_PTR(err);
 }
 
 /**
@@ -440,20 +436,97 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir)
 	return result;
 }
 
+static int
+v9fs_open_created(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+
 /**
  * v9fs_vfs_create - VFS hook to create files
  * @inode: directory inode that is being deleted
  * @dentry:  dentry that is being deleted
- * @perm: create permissions
+ * @mode: create permissions
  * @nd: path information
  *
  */
 
 static int
-v9fs_vfs_create(struct inode *inode, struct dentry *dentry, int perm,
+v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode,
 		struct nameidata *nd)
 {
-	return v9fs_create(inode, dentry, perm, O_RDWR);
+	int err;
+	u32 fid, perm, iounit;
+	int flags;
+	struct v9fs_session_info *v9ses;
+	struct v9fs_fid *dfid, *vfid, *ffid;
+	struct inode *inode;
+	struct v9fs_qid qid;
+	struct file *filp;
+
+	inode = NULL;
+	vfid = NULL;
+	v9ses = v9fs_inode2v9ses(dir);
+	dfid = v9fs_fid_lookup(dentry->d_parent);
+	perm = unixmode2p9mode(v9ses, mode);
+
+	if (nd && nd->flags & LOOKUP_OPEN)
+		flags = nd->intent.open.flags - 1;
+	else
+		flags = O_RDWR;
+
+	err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name,
+		perm, v9fs_uflags2omode(flags), &fid, &qid, &iounit);
+
+	if (err)
+		goto error;
+
+	vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry);
+	if (IS_ERR(vfid)) {
+		err = PTR_ERR(vfid);
+		vfid = NULL;
+		goto error;
+	}
+
+	inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		inode = NULL;
+		goto error;
+	}
+
+	dentry->d_op = &v9fs_dentry_operations;
+	d_instantiate(dentry, inode);
+
+	if (nd && nd->flags & LOOKUP_OPEN) {
+		ffid = v9fs_fid_create(v9ses, fid);
+		if (!ffid)
+			return -ENOMEM;
+
+		filp = lookup_instantiate_filp(nd, dentry, v9fs_open_created);
+		if (IS_ERR(filp)) {
+			v9fs_fid_destroy(ffid);
+			return PTR_ERR(filp);
+		}
+
+		ffid->rdir_pos = 0;
+		ffid->rdir_fcall = NULL;
+		ffid->fidopen = 1;
+		ffid->iounit = iounit;
+		ffid->filp = filp;
+		filp->private_data = ffid;
+	}
+
+	return 0;
+
+error:
+	if (vfid)
+		v9fs_fid_destroy(vfid);
+
+	if (inode)
+		iput(inode);
+
+	return err;
 }
 
 /**
@@ -464,9 +537,57 @@ v9fs_vfs_create(struct inode *inode, struct dentry *dentry, int perm,
  *
  */
 
-static int v9fs_vfs_mkdir(struct inode *inode, struct dentry *dentry, int mode)
+static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-	return v9fs_create(inode, dentry, mode | S_IFDIR, O_RDONLY);
+	int err;
+	u32 fid, perm;
+	struct v9fs_session_info *v9ses;
+	struct v9fs_fid *dfid, *vfid;
+	struct inode *inode;
+
+	inode = NULL;
+	vfid = NULL;
+	v9ses = v9fs_inode2v9ses(dir);
+	dfid = v9fs_fid_lookup(dentry->d_parent);
+	perm = unixmode2p9mode(v9ses, mode | S_IFDIR);
+
+	err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name,
+		perm, V9FS_OREAD, &fid, NULL, NULL);
+
+	if (err) {
+		dprintk(DEBUG_ERROR, "create error %d\n", err);
+		goto error;
+	}
+
+	err = v9fs_t_clunk(v9ses, fid);
+	if (err) {
+		dprintk(DEBUG_ERROR, "clunk error %d\n", err);
+		goto error;
+	}
+
+	vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry);
+	if (IS_ERR(vfid)) {
+		err = PTR_ERR(vfid);
+		vfid = NULL;
+		goto error;
+	}
+
+	inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		inode = NULL;
+		goto error;
+	}
+
+	dentry->d_op = &v9fs_dentry_operations;
+	d_instantiate(dentry, inode);
+	return 0;
+
+error:
+	if (vfid)
+		v9fs_fid_destroy(vfid);
+
+	return err;
 }
 
 /**
@@ -516,9 +637,8 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(-ENOSPC);
 	}
 
-	result =
-	    v9fs_t_walk(v9ses, dirfidnum, newfid, (char *)dentry->d_name.name,
-			NULL);
+	result = v9fs_t_walk(v9ses, dirfidnum, newfid,
+		(char *)dentry->d_name.name, NULL);
 	if (result < 0) {
 		v9fs_put_idpool(newfid, &v9ses->fidpool);
 		if (result == -ENOENT) {
@@ -551,13 +671,17 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 	inode->i_ino = v9fs_qid2ino(&fcall->params.rstat.stat.qid);
 
-	fid = v9fs_fid_create(dentry, v9ses, newfid, 0);
+	fid = v9fs_fid_create(v9ses, newfid);
 	if (fid == NULL) {
 		dprintk(DEBUG_ERROR, "couldn't insert\n");
 		result = -ENOMEM;
 		goto FreeFcall;
 	}
 
+	result = v9fs_fid_insert(fid, dentry);
+	if (result < 0)
+		goto FreeFcall;
+
 	fid->qid = fcall->params.rstat.stat.qid;
 
 	dentry->d_op = &v9fs_dentry_operations;
@@ -886,8 +1010,8 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	}
 
 	/* copy extension buffer into buffer */
-	if (fcall->params.rstat.stat.extension.len+1 < buflen)
-		buflen = fcall->params.rstat.stat.extension.len + 1;
+	if (fcall->params.rstat.stat.extension.len < buflen)
+		buflen = fcall->params.rstat.stat.extension.len;
 
 	memcpy(buffer, fcall->params.rstat.stat.extension.str, buflen - 1);
 	buffer[buflen-1] = 0;
@@ -951,7 +1075,7 @@ static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (!link)
 		link = ERR_PTR(-ENOMEM);
 	else {
-		len = v9fs_readlink(dentry, link, PATH_MAX);
+		len = v9fs_readlink(dentry, link, strlen(link));
 
 		if (len < 0) {
 			__putname(link);
@@ -983,53 +1107,75 @@ static void v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void
 static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry,
 	int mode, const char *extension)
 {
-	int err, retval;
+	int err;
+	u32 fid, perm;
 	struct v9fs_session_info *v9ses;
+	struct v9fs_fid *dfid, *vfid;
+	struct inode *inode;
 	struct v9fs_fcall *fcall;
-	struct v9fs_fid *fid;
 	struct v9fs_wstat wstat;
 
-	v9ses = v9fs_inode2v9ses(dir);
-	retval = -EPERM;
 	fcall = NULL;
+	inode = NULL;
+	vfid = NULL;
+	v9ses = v9fs_inode2v9ses(dir);
+	dfid = v9fs_fid_lookup(dentry->d_parent);
+	perm = unixmode2p9mode(v9ses, mode);
 
 	if (!v9ses->extended) {
 		dprintk(DEBUG_ERROR, "not extended\n");
-		goto free_mem;
+		return -EPERM;
 	}
 
-	/* issue a create */
-	retval = v9fs_create(dir, dentry, mode, 0);
-	if (retval != 0)
-		goto free_mem;
+	err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name,
+		perm, V9FS_OREAD, &fid, NULL, NULL);
 
-	fid = v9fs_fid_get_created(dentry);
-	if (!fid) {
-		dprintk(DEBUG_ERROR, "couldn't resolve fid from dentry\n");
-		goto free_mem;
+	if (err)
+		goto error;
+
+	err = v9fs_t_clunk(v9ses, fid);
+	if (err)
+		goto error;
+
+	vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry);
+	if (IS_ERR(vfid)) {
+		err = PTR_ERR(vfid);
+		vfid = NULL;
+		goto error;
+	}
+
+	inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		inode = NULL;
+		goto error;
 	}
 
 	/* issue a Twstat */
 	v9fs_blank_wstat(&wstat);
 	wstat.muid = v9ses->name;
 	wstat.extension = (char *) extension;
-	retval = v9fs_t_wstat(v9ses, fid->fid, &wstat, &fcall);
-	if (retval < 0) {
-		PRINT_FCALL_ERROR("wstat error", fcall);
-		goto free_mem;
-	}
-
-	err = v9fs_t_clunk(v9ses, fid->fid);
+	err = v9fs_t_wstat(v9ses, vfid->fid, &wstat, &fcall);
 	if (err < 0) {
-		dprintk(DEBUG_ERROR, "clunk failed: %d\n", err);
-		goto free_mem;
+		PRINT_FCALL_ERROR("wstat error", fcall);
+		goto error;
 	}
 
-	d_drop(dentry);		/* FID - will this also clunk? */
+	kfree(fcall);
+	dentry->d_op = &v9fs_dentry_operations;
+	d_instantiate(dentry, inode);
+	return 0;
 
-free_mem:
+error:
 	kfree(fcall);
-	return retval;
+	if (vfid)
+		v9fs_fid_destroy(vfid);
+
+	if (inode)
+		iput(inode);
+
+	return err;
+
 }
 
 /**
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 2c4fa75be025..cdf787ee08de 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -146,7 +146,6 @@ static struct super_block *v9fs_get_sb(struct file_system_type
 	inode->i_gid = gid;
 
 	root = d_alloc_root(inode);
-
 	if (!root) {
 		retval = -ENOMEM;
 		goto put_back_sb;
@@ -157,16 +156,22 @@ static struct super_block *v9fs_get_sb(struct file_system_type
 	stat_result = v9fs_t_stat(v9ses, newfid, &fcall);
 	if (stat_result < 0) {
 		dprintk(DEBUG_ERROR, "stat error\n");
+		kfree(fcall);
 		v9fs_t_clunk(v9ses, newfid);
-		v9fs_put_idpool(newfid, &v9ses->fidpool);
 	} else {
 		/* Setup the Root Inode */
-		root_fid = v9fs_fid_create(root, v9ses, newfid, 0);
+		root_fid = v9fs_fid_create(v9ses, newfid);
 		if (root_fid == NULL) {
 			retval = -ENOMEM;
 			goto put_back_sb;
 		}
 
+		retval = v9fs_fid_insert(root_fid, root);
+		if (retval < 0) {
+			kfree(fcall);
+			goto put_back_sb;
+		}
+
 		root_fid->qid = fcall->params.rstat.stat.qid;
 		root->d_inode->i_ino =
 		    v9fs_qid2ino(&fcall->params.rstat.stat.qid);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 1b117a441298..c2eac2a50bd2 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -938,6 +938,11 @@ static int load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 		kfree(elf_interpreter);
 	} else {
 		elf_entry = loc->elf_ex.e_entry;
+		if (BAD_ADDR(elf_entry)) {
+			send_sig(SIGSEGV, current, 0);
+			retval = -ENOEXEC; /* Nobody gets to see this, but.. */
+			goto out_free_dentry;
+		}
 	}
 
 	kfree(elf_phdata);
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 057e60217fc5..537ac70edfe5 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -2531,18 +2531,9 @@ static int rtc_ioctl(unsigned fd, unsigned cmd, unsigned long arg)
 		val32 = kval;
 		return put_user(val32, (unsigned int __user *)arg);
 	case RTC_IRQP_SET32:
+		return sys_ioctl(fd, RTC_IRQP_SET, arg); 
 	case RTC_EPOCH_SET32:
-		ret = get_user(val32, (unsigned int __user *)arg);
-		if (ret)
-			return ret;
-		kval = val32;
-
-		set_fs(KERNEL_DS);
-		ret = sys_ioctl(fd, (cmd == RTC_IRQP_SET32) ?
-				RTC_IRQP_SET : RTC_EPOCH_SET,
-				(unsigned long)&kval);
-		set_fs(oldfs);
-		return ret;
+		return sys_ioctl(fd, RTC_EPOCH_SET, arg);
 	default:
 		/* unreached */
 		return -ENOIOCTLCMD;
diff --git a/fs/exec.c b/fs/exec.c
index 0e1c95074d42..0b515ac53134 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -885,6 +885,12 @@ int flush_old_exec(struct linux_binprm * bprm)
 	current->flags &= ~PF_RANDOMIZE;
 	flush_thread();
 
+	/* Set the new mm task size. We have to do that late because it may
+	 * depend on TIF_32BIT which is only updated in flush_thread() on
+	 * some architectures like powerpc
+	 */
+	current->mm->task_size = TASK_SIZE;
+
 	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || 
 	    file_permission(bprm->file, MAY_READ) ||
 	    (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 21fd59c7bc24..c72a8a97935c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -111,6 +111,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 
 		/* Doesn't hurt to "reset" the validity timeout */
 		fuse_invalidate_entry_cache(entry);
+
+		/* For negative dentries, always do a fresh lookup */
 		if (!inode)
 			return 0;
 
@@ -122,6 +124,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 		fuse_lookup_init(req, entry->d_parent->d_inode, entry, &outarg);
 		request_send(fc, req);
 		err = req->out.h.error;
+		/* Zero nodeid is same as -ENOENT */
+		if (!err && !outarg.nodeid)
+			err = -ENOENT;
 		if (!err) {
 			struct fuse_inode *fi = get_fuse_inode(inode);
 			if (outarg.nodeid != get_node_id(inode)) {
@@ -190,8 +195,9 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	fuse_lookup_init(req, dir, entry, &outarg);
 	request_send(fc, req);
 	err = req->out.h.error;
-	if (!err && ((outarg.nodeid && invalid_nodeid(outarg.nodeid)) ||
-		     !valid_mode(outarg.attr.mode)))
+	/* Zero nodeid is same as -ENOENT, but with valid timeout */
+	if (!err && outarg.nodeid &&
+	    (invalid_nodeid(outarg.nodeid) || !valid_mode(outarg.attr.mode)))
 		err = -EIO;
 	if (!err && outarg.nodeid) {
 		inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
diff --git a/fs/namei.c b/fs/namei.c
index e28de846c591..557dcf395ca1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2224,13 +2224,17 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
  * and other special files.  --ADM
  */
 asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
-			   int newdfd, const char __user *newname)
+			   int newdfd, const char __user *newname,
+			   int flags)
 {
 	struct dentry *new_dentry;
 	struct nameidata nd, old_nd;
 	int error;
 	char * to;
 
+	if (flags != 0)
+		return -EINVAL;
+
 	to = getname(newname);
 	if (IS_ERR(to))
 		return PTR_ERR(to);
@@ -2263,7 +2267,7 @@ exit:
 
 asmlinkage long sys_link(const char __user *oldname, const char __user *newname)
 {
-	return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname);
+	return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 /*
diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog
index 02f44094bda9..9d8ffa89e2c2 100644
--- a/fs/ntfs/ChangeLog
+++ b/fs/ntfs/ChangeLog
@@ -1,9 +1,9 @@
 ToDo/Notes:
 	- Find and fix bugs.
 	- The only places in the kernel where a file is resized are
-	  ntfs_file_write*() and ntfs_truncate() for both of which i_sem is
+	  ntfs_file_write*() and ntfs_truncate() for both of which i_mutex is
 	  held.  Just have to be careful in read-/writepage and other helpers
-	  not running under i_sem that we play nice...  Also need to be careful
+	  not running under i_mutex that we play nice.  Also need to be careful
 	  with initialized_size extension in ntfs_file_write*() and writepage.
 	  UPDATE: The only things that need to be checked are the compressed
 	  write and the other attribute resize/write cases like index
@@ -19,6 +19,24 @@ ToDo/Notes:
 	- Enable the code for setting the NT4 compatibility flag when we start
 	  making NTFS 1.2 specific modifications.
 
+2.1.26 - Minor bug fixes and updates.
+
+	- Fix a potential overflow in file.c where a cast to s64 was missing in
+	  a left shift of a page index.
+	- The struct inode has had its i_sem semaphore changed to a mutex named
+	  i_mutex.
+	- We have struct kmem_cache now so use it instead of the typedef
+	  kmem_cache_t.  (Pekka Enberg)
+	- Implement support for sector sizes above 512 bytes (up to the maximum
+	  supported by NTFS which is 4096 bytes).
+	- Do more detailed reporting of why we cannot mount read-write by
+	  special casing the VOLUME_MODIFIED_BY_CHKDSK flag.
+	- Miscellaneous updates to layout.h.
+	- Cope with attribute list attribute having invalid flags.  Windows
+	  copes with this and even chkdsk does not detect or fix this so we
+	  have to cope with it, too.  Thanks to Pawel Kot for reporting the
+	  problem.
+
 2.1.25 - (Almost) fully implement write(2) and truncate(2).
 
 	- Change ntfs_map_runlist_nolock(), ntfs_attr_find_vcn_nolock() and
@@ -373,7 +391,7 @@ ToDo/Notes:
 	  single one of them had an mst error.  (Thanks to Ken MacFerrin for
 	  the bug report.)
 	- Fix error handling in fs/ntfs/quota.c::ntfs_mark_quotas_out_of_date()
-	  where we failed to release i_sem on the $Quota/$Q attribute inode.
+	  where we failed to release i_mutex on the $Quota/$Q attribute inode.
 	- Fix bug in handling of bad inodes in fs/ntfs/namei.c::ntfs_lookup().
 	- Add mapping of unmapped buffers to all remaining code paths, i.e.
 	  fs/ntfs/aops.c::ntfs_write_mst_block(), mft.c::ntfs_sync_mft_mirror(),
@@ -874,7 +892,7 @@ ToDo/Notes:
 	  clusters. (Philipp Thomas)
 	- attrib.c::load_attribute_list(): Fix bug when initialized_size is a
 	  multiple of the block_size but not the cluster size. (Szabolcs
-	  Szakacsits <szaka@sienet.hu>)
+	  Szakacsits)
 
 2.1.2 - Important bug fixes aleviating the hangs in statfs.
 
@@ -884,7 +902,7 @@ ToDo/Notes:
 
 	- Add handling for initialized_size != data_size in compressed files.
 	- Reduce function local stack usage from 0x3d4 bytes to just noise in
-	  fs/ntfs/upcase.c. (Randy Dunlap <rdunlap@xenotime.net>)
+	  fs/ntfs/upcase.c. (Randy Dunlap)
 	- Remove compiler warnings for newer gcc.
 	- Pages are no longer kmapped by mm/filemap.c::generic_file_write()
 	  around calls to ->{prepare,commit}_write.  Adapt NTFS appropriately
@@ -1201,11 +1219,11 @@ ToDo/Notes:
 	  the kernel. We probably want a kernel generic init_address_space()
 	  function...
 	- Drop BKL from ntfs_readdir() after consultation with Al Viro. The
-	  only caller of ->readdir() is vfs_readdir() which holds i_sem during
-	  the call, and i_sem is sufficient protection against changes in the
-	  directory inode (including ->i_size).
+	  only caller of ->readdir() is vfs_readdir() which holds i_mutex
+	  during the call, and i_mutex is sufficient protection against changes
+	  in the directory inode (including ->i_size).
 	- Use generic_file_llseek() for directories (as opposed to
-	  default_llseek()) as this downs i_sem instead of the BKL which is
+	  default_llseek()) as this downs i_mutex instead of the BKL which is
 	  what we now need for exclusion against ->f_pos changes considering we
 	  no longer take the BKL in ntfs_readdir().
 
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index d0d45d1c853a..d95fac7fdeb6 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -6,7 +6,7 @@ ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
 	     index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
 	     unistr.o upcase.o
 
-EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.25\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.26\"
 
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 1c0a4315876a..7e361da770b3 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -2,7 +2,7 @@
  * aops.c - NTFS kernel address space operations and page cache handling.
  *	    Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -200,8 +200,8 @@ static int ntfs_read_block(struct page *page)
 	/* $MFT/$DATA must have its complete runlist in memory at all times. */
 	BUG_ON(!ni->runlist.rl && !ni->mft_no && !NInoAttr(ni));
 
-	blocksize_bits = VFS_I(ni)->i_blkbits;
-	blocksize = 1 << blocksize_bits;
+	blocksize = vol->sb->s_blocksize;
+	blocksize_bits = vol->sb->s_blocksize_bits;
 
 	if (!page_has_buffers(page)) {
 		create_empty_buffers(page, blocksize, 0);
@@ -569,10 +569,8 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc)
 
 	BUG_ON(!NInoNonResident(ni));
 	BUG_ON(NInoMstProtected(ni));
-
-	blocksize_bits = vi->i_blkbits;
-	blocksize = 1 << blocksize_bits;
-
+	blocksize = vol->sb->s_blocksize;
+	blocksize_bits = vol->sb->s_blocksize_bits;
 	if (!page_has_buffers(page)) {
 		BUG_ON(!PageUptodate(page));
 		create_empty_buffers(page, blocksize,
@@ -949,8 +947,8 @@ static int ntfs_write_mst_block(struct page *page,
 	 */
 	BUG_ON(!(is_mft || S_ISDIR(vi->i_mode) ||
 			(NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
-	bh_size_bits = vi->i_blkbits;
-	bh_size = 1 << bh_size_bits;
+	bh_size = vol->sb->s_blocksize;
+	bh_size_bits = vol->sb->s_blocksize_bits;
 	max_bhs = PAGE_CACHE_SIZE / bh_size;
 	BUG_ON(!max_bhs);
 	BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
@@ -1596,7 +1594,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 
 	BUG_ON(!PageUptodate(page));
 	end = ofs + ni->itype.index.block_size;
-	bh_size = 1 << VFS_I(ni)->i_blkbits;
+	bh_size = VFS_I(ni)->i_sb->s_blocksize;
 	spin_lock(&mapping->private_lock);
 	if (unlikely(!page_has_buffers(page))) {
 		spin_unlock(&mapping->private_lock);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index fb413d3d8618..5027d3d1b3fe 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
 /*
  * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -248,7 +248,7 @@ do_non_resident_extend:
 		 * enough to make ntfs_writepage() work.
 		 */
 		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = (index + 1) << PAGE_CACHE_SHIFT;
+		ni->initialized_size = (s64)(index + 1) << PAGE_CACHE_SHIFT;
 		if (ni->initialized_size > new_init_size)
 			ni->initialized_size = new_init_size;
 		write_unlock_irqrestore(&ni->size_lock, flags);
@@ -529,8 +529,8 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
 			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
 			vi->i_ino, ni->type, pages[0]->index, nr_pages,
 			(long long)pos, bytes);
-	blocksize_bits = vi->i_blkbits;
-	blocksize = 1 << blocksize_bits;
+	blocksize = vol->sb->s_blocksize;
+	blocksize_bits = vol->sb->s_blocksize_bits;
 	u = 0;
 	do {
 		struct page *page = pages[u];
@@ -1525,7 +1525,7 @@ static inline int ntfs_commit_pages_after_non_resident_write(
 
 	vi = pages[0]->mapping->host;
 	ni = NTFS_I(vi);
-	blocksize = 1 << vi->i_blkbits;
+	blocksize = vi->i_sb->s_blocksize;
 	end = pos + bytes;
 	u = 0;
 	do {
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index ea1bd3feea1b..55263b7de9c0 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -677,13 +677,28 @@ static int ntfs_read_locked_inode(struct inode *vi)
 		ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino);
 		NInoSetAttrList(ni);
 		a = ctx->attr;
-		if (a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_SPARSE) {
+		if (a->flags & ATTR_COMPRESSION_MASK) {
 			ntfs_error(vi->i_sb, "Attribute list attribute is "
-					"compressed/encrypted/sparse.");
+					"compressed.");
 			goto unm_err_out;
 		}
+		if (a->flags & ATTR_IS_ENCRYPTED ||
+				a->flags & ATTR_IS_SPARSE) {
+			if (a->non_resident) {
+				ntfs_error(vi->i_sb, "Non-resident attribute "
+						"list attribute is encrypted/"
+						"sparse.");
+				goto unm_err_out;
+			}
+			ntfs_warning(vi->i_sb, "Resident attribute list "
+					"attribute in inode 0x%lx is marked "
+					"encrypted/sparse which is not true.  "
+					"However, Windows allows this and "
+					"chkdsk does not detect or correct it "
+					"so we will just ignore the invalid "
+					"flags and pretend they are not set.",
+					vi->i_ino);
+		}
 		/* Now allocate memory for the attribute list. */
 		ni->attr_list_size = (u32)ntfs_attr_size(a);
 		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
@@ -1809,19 +1824,33 @@ int ntfs_read_inode_mount(struct inode *vi)
 	} else /* if (!err) */ {
 		ATTR_LIST_ENTRY *al_entry, *next_al_entry;
 		u8 *al_end;
+		static const char *es = "  Not allowed.  $MFT is corrupt.  "
+				"You should run chkdsk.";
 
 		ntfs_debug("Attribute list attribute found in $MFT.");
 		NInoSetAttrList(ni);
 		a = ctx->attr;
-		if (a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_SPARSE) {
+		if (a->flags & ATTR_COMPRESSION_MASK) {
 			ntfs_error(sb, "Attribute list attribute is "
-					"compressed/encrypted/sparse. Not "
-					"allowed. $MFT is corrupt. You should "
-					"run chkdsk.");
+					"compressed.%s", es);
 			goto put_err_out;
 		}
+		if (a->flags & ATTR_IS_ENCRYPTED ||
+				a->flags & ATTR_IS_SPARSE) {
+			if (a->non_resident) {
+				ntfs_error(sb, "Non-resident attribute list "
+						"attribute is encrypted/"
+						"sparse.%s", es);
+				goto put_err_out;
+			}
+			ntfs_warning(sb, "Resident attribute list attribute "
+					"in $MFT system file is marked "
+					"encrypted/sparse which is not true.  "
+					"However, Windows allows this and "
+					"chkdsk does not detect or correct it "
+					"so we will just ignore the invalid "
+					"flags and pretend they are not set.");
+		}
 		/* Now allocate memory for the attribute list. */
 		ni->attr_list_size = (u32)ntfs_attr_size(a);
 		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index f5678d5d7919..bb408d4dcbb0 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -838,15 +838,19 @@ enum {
 	   F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
 	   F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
 	   is used to to obtain all flags that are valid for setting. */
-
 	/*
-	 * The following flags are only present in the FILE_NAME attribute (in
+	 * The following flag is only present in the FILE_NAME attribute (in
 	 * the field file_attributes).
 	 */
 	FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT	= const_cpu_to_le32(0x10000000),
 	/* Note, this is a copy of the corresponding bit from the mft record,
 	   telling us whether this is a directory or not, i.e. whether it has
 	   an index root attribute or not. */
+	/*
+	 * The following flag is present both in the STANDARD_INFORMATION
+	 * attribute and in the FILE_NAME attribute (in the field
+	 * file_attributes).
+	 */
 	FILE_ATTR_DUP_VIEW_INDEX_PRESENT	= const_cpu_to_le32(0x20000000),
 	/* Note, this is a copy of the corresponding bit from the mft record,
 	   telling us whether this file has a view index present (eg. object id
@@ -1071,9 +1075,15 @@ typedef struct {
 					   modified. */
 /* 20*/	sle64 last_access_time;		/* Time this mft record was last
 					   accessed. */
-/* 28*/	sle64 allocated_size;		/* Byte size of allocated space for the
-					   data attribute. NOTE: Is a multiple
-					   of the cluster size. */
+/* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
+					   for the data attribute.  So for
+					   normal $DATA, this is the
+					   allocated_size from the unnamed
+					   $DATA attribute and for compressed
+					   and/or sparse $DATA, this is the
+					   compressed_size from the unnamed
+					   $DATA attribute.  NOTE: This is a
+					   multiple of the cluster size. */
 /* 30*/	sle64 data_size;		/* Byte size of actual data in data
 					   attribute. */
 /* 38*/	FILE_ATTR_FLAGS file_attributes;	/* Flags describing the file. */
@@ -1904,12 +1914,13 @@ enum {
 	VOLUME_DELETE_USN_UNDERWAY	= const_cpu_to_le16(0x0010),
 	VOLUME_REPAIR_OBJECT_ID		= const_cpu_to_le16(0x0020),
 
+	VOLUME_CHKDSK_UNDERWAY		= const_cpu_to_le16(0x4000),
 	VOLUME_MODIFIED_BY_CHKDSK	= const_cpu_to_le16(0x8000),
 
-	VOLUME_FLAGS_MASK		= const_cpu_to_le16(0x803f),
+	VOLUME_FLAGS_MASK		= const_cpu_to_le16(0xc03f),
 
 	/* To make our life easier when checking if we must mount read-only. */
-	VOLUME_MUST_MOUNT_RO_MASK	= const_cpu_to_le16(0x8027),
+	VOLUME_MUST_MOUNT_RO_MASK	= const_cpu_to_le16(0xc027),
 } __attribute__ ((__packed__));
 
 typedef le16 VOLUME_FLAGS;
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 0c65cbb8c5cf..6499aafc2258 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -1,7 +1,7 @@
 /**
  * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -473,7 +473,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
 	runlist_element *rl;
 	unsigned int block_start, block_end, m_start, m_end, page_ofs;
 	int i_bhs, nr_bhs, err = 0;
-	unsigned char blocksize_bits = vol->mftmirr_ino->i_blkbits;
+	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
 
 	ntfs_debug("Entering for inode 0x%lx.", mft_no);
 	BUG_ON(!max_bhs);
@@ -672,8 +672,8 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
 {
 	ntfs_volume *vol = ni->vol;
 	struct page *page = ni->page;
-	unsigned char blocksize_bits = vol->mft_ino->i_blkbits;
-	unsigned int blocksize = 1 << blocksize_bits;
+	unsigned int blocksize = vol->sb->s_blocksize;
+	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
 	int max_bhs = vol->mft_record_size / blocksize;
 	struct buffer_head *bhs[max_bhs];
 	struct buffer_head *bh, *head;
diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h
index 446b5014115c..653d2a5c4899 100644
--- a/fs/ntfs/ntfs.h
+++ b/fs/ntfs/ntfs.h
@@ -50,11 +50,11 @@ typedef enum {
 /* Global variables. */
 
 /* Slab caches (from super.c). */
-extern kmem_cache_t *ntfs_name_cache;
-extern kmem_cache_t *ntfs_inode_cache;
-extern kmem_cache_t *ntfs_big_inode_cache;
-extern kmem_cache_t *ntfs_attr_ctx_cache;
-extern kmem_cache_t *ntfs_index_ctx_cache;
+extern struct kmem_cache *ntfs_name_cache;
+extern struct kmem_cache *ntfs_inode_cache;
+extern struct kmem_cache *ntfs_big_inode_cache;
+extern struct kmem_cache *ntfs_attr_ctx_cache;
+extern struct kmem_cache *ntfs_index_ctx_cache;
 
 /* The various operations structs defined throughout the driver files. */
 extern struct address_space_operations ntfs_aops;
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index c3a3f1a8310b..368a8ec10668 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -1,7 +1,7 @@
 /*
  * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  * Copyright (c) 2001,2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -22,6 +22,7 @@
 
 #include <linux/stddef.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>	/* For bdev_hardsect_size(). */
@@ -471,9 +472,16 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 			ntfs_error(sb, "Volume is dirty and read-only%s", es);
 			return -EROFS;
 		}
+		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
+			ntfs_error(sb, "Volume has been modified by chkdsk "
+					"and is read-only%s", es);
+			return -EROFS;
+		}
 		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-			ntfs_error(sb, "Volume has unsupported flags set and "
-					"is read-only%s", es);
+			ntfs_error(sb, "Volume has unsupported flags set "
+					"(0x%x) and is read-only%s",
+					(unsigned)le16_to_cpu(vol->vol_flags),
+					es);
 			return -EROFS;
 		}
 		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
@@ -641,7 +649,7 @@ static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
 {
 	const char *read_err_str = "Unable to read %s boot sector.";
 	struct buffer_head *bh_primary, *bh_backup;
-	long nr_blocks = NTFS_SB(sb)->nr_blocks;
+	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
 
 	/* Try to read primary boot sector. */
 	if ((bh_primary = sb_bread(sb, 0))) {
@@ -688,13 +696,18 @@ hotfix_primary_boot_sector:
 		/*
 		 * If we managed to read sector zero and the volume is not
 		 * read-only, copy the found, valid backup boot sector to the
-		 * primary boot sector.
+		 * primary boot sector.  Note we only copy the actual boot
+		 * sector structure, not the actual whole device sector as that
+		 * may be bigger and would potentially damage the $Boot system
+		 * file (FIXME: Would be nice to know if the backup boot sector
+		 * on a large sector device contains the whole boot loader or
+		 * just the first 512 bytes).
 		 */
 		if (!(sb->s_flags & MS_RDONLY)) {
 			ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
 					"boot sector from backup copy.");
 			memcpy(bh_primary->b_data, bh_backup->b_data,
-					sb->s_blocksize);
+					NTFS_BLOCK_SIZE);
 			mark_buffer_dirty(bh_primary);
 			sync_dirty_buffer(bh_primary);
 			if (buffer_uptodate(bh_primary)) {
@@ -733,9 +746,13 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 			vol->sector_size);
 	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
 			vol->sector_size_bits);
-	if (vol->sector_size != vol->sb->s_blocksize)
-		ntfs_warning(vol->sb, "The boot sector indicates a sector size "
-				"different from the device sector size.");
+	if (vol->sector_size < vol->sb->s_blocksize) {
+		ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
+				"device block size (%lu).  This is not "
+				"supported.  Sorry.", vol->sector_size,
+				vol->sb->s_blocksize);
+		return FALSE;
+	}
 	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
 	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
 	ntfs_debug("sectors_per_cluster_bits = 0x%x",
@@ -748,16 +765,11 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
 			vol->cluster_size);
 	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
-	ntfs_debug("vol->cluster_size_bits = %i (0x%x)",
-			vol->cluster_size_bits, vol->cluster_size_bits);
-	if (vol->sector_size > vol->cluster_size) {
-		ntfs_error(vol->sb, "Sector sizes above the cluster size are "
-				"not supported.  Sorry.");
-		return FALSE;
-	}
-	if (vol->sb->s_blocksize > vol->cluster_size) {
-		ntfs_error(vol->sb, "Cluster sizes smaller than the device "
-				"sector size are not supported.  Sorry.");
+	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
+	if (vol->cluster_size < vol->sector_size) {
+		ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
+				"sector size (%i).  This is not supported.  "
+				"Sorry.", vol->cluster_size, vol->sector_size);
 		return FALSE;
 	}
 	clusters_per_mft_record = b->clusters_per_mft_record;
@@ -786,11 +798,18 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	 * we store $MFT/$DATA, the table of mft records in the page cache.
 	 */
 	if (vol->mft_record_size > PAGE_CACHE_SIZE) {
-		ntfs_error(vol->sb, "Mft record size %i (0x%x) exceeds the "
-				"page cache size on your system %lu (0x%lx).  "
+		ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
+				"PAGE_CACHE_SIZE on your system (%lu).  "
 				"This is not supported.  Sorry.",
-				vol->mft_record_size, vol->mft_record_size,
-				PAGE_CACHE_SIZE, PAGE_CACHE_SIZE);
+				vol->mft_record_size, PAGE_CACHE_SIZE);
+		return FALSE;
+	}
+	/* We cannot support mft record sizes below the sector size. */
+	if (vol->mft_record_size < vol->sector_size) {
+		ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
+				"sector size (%i).  This is not supported.  "
+				"Sorry.", vol->mft_record_size,
+				vol->sector_size);
 		return FALSE;
 	}
 	clusters_per_index_record = b->clusters_per_index_record;
@@ -816,6 +835,14 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
 			vol->index_record_size_bits,
 			vol->index_record_size_bits);
+	/* We cannot support index record sizes below the sector size. */
+	if (vol->index_record_size < vol->sector_size) {
+		ntfs_error(vol->sb, "Index record size (%i) is smaller than "
+				"the sector size (%i).  This is not "
+				"supported.  Sorry.", vol->index_record_size,
+				vol->sector_size);
+		return FALSE;
+	}
 	/*
 	 * Get the size of the volume in clusters and check for 64-bit-ness.
 	 * Windows currently only uses 32 bits to save the clusters so we do
@@ -845,15 +872,18 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	}
 	ll = sle64_to_cpu(b->mft_lcn);
 	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFT LCN is beyond end of volume.  Weird.");
+		ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
+				"volume.  Weird.", (unsigned long long)ll,
+				(unsigned long long)ll);
 		return FALSE;
 	}
 	vol->mft_lcn = ll;
 	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
 	ll = sle64_to_cpu(b->mftmirr_lcn);
 	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFTMirr LCN is beyond end of volume.  "
-				"Weird.");
+		ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
+				"of volume.  Weird.", (unsigned long long)ll,
+				(unsigned long long)ll);
 		return FALSE;
 	}
 	vol->mftmirr_lcn = ll;
@@ -1822,11 +1852,24 @@ get_ctx_vol_failed:
 	/* Make sure that no unsupported volume flags are set. */
 	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
 		static const char *es1a = "Volume is dirty";
-		static const char *es1b = "Volume has unsupported flags set";
-		static const char *es2 = ".  Run chkdsk and mount in Windows.";
-		const char *es1;
-		
-		es1 = vol->vol_flags & VOLUME_IS_DIRTY ? es1a : es1b;
+		static const char *es1b = "Volume has been modified by chkdsk";
+		static const char *es1c = "Volume has unsupported flags set";
+		static const char *es2a = ".  Run chkdsk and mount in Windows.";
+		static const char *es2b = ".  Mount in Windows.";
+		const char *es1, *es2;
+
+		es2 = es2a;
+		if (vol->vol_flags & VOLUME_IS_DIRTY)
+			es1 = es1a;
+		else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
+			es1 = es1b;
+			es2 = es2b;
+		} else {
+			es1 = es1c;
+			ntfs_warning(sb, "Unsupported volume flags 0x%x "
+					"encountered.",
+					(unsigned)le16_to_cpu(vol->vol_flags));
+		}
 		/* If a read-write mount, convert it to a read-only mount. */
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
@@ -2685,7 +2728,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	ntfs_volume *vol;
 	struct buffer_head *bh;
 	struct inode *tmp_ino;
-	int result;
+	int blocksize, result;
 
 	ntfs_debug("Entering.");
 #ifndef NTFS_RW
@@ -2724,60 +2767,85 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	if (!parse_options(vol, (char*)opt))
 		goto err_out_now;
 
+	/* We support sector sizes up to the PAGE_CACHE_SIZE. */
+	if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
+		if (!silent)
+			ntfs_error(sb, "Device has unsupported sector size "
+					"(%i).  The maximum supported sector "
+					"size on this architecture is %lu "
+					"bytes.",
+					bdev_hardsect_size(sb->s_bdev),
+					PAGE_CACHE_SIZE);
+		goto err_out_now;
+	}
 	/*
-	 * TODO: Fail safety check. In the future we should really be able to
-	 * cope with this being the case, but for now just bail out.
+	 * Setup the device access block size to NTFS_BLOCK_SIZE or the hard
+	 * sector size, whichever is bigger.
 	 */
-	if (bdev_hardsect_size(sb->s_bdev) > NTFS_BLOCK_SIZE) {
+	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
+	if (blocksize < NTFS_BLOCK_SIZE) {
 		if (!silent)
-			ntfs_error(sb, "Device has unsupported hardsect_size.");
+			ntfs_error(sb, "Unable to set device block size.");
 		goto err_out_now;
 	}
-
-	/* Setup the device access block size to NTFS_BLOCK_SIZE. */
-	if (sb_set_blocksize(sb, NTFS_BLOCK_SIZE) != NTFS_BLOCK_SIZE) {
+	BUG_ON(blocksize != sb->s_blocksize);
+	ntfs_debug("Set device block size to %i bytes (block size bits %i).",
+			blocksize, sb->s_blocksize_bits);
+	/* Determine the size of the device in units of block_size bytes. */
+	if (!i_size_read(sb->s_bdev->bd_inode)) {
 		if (!silent)
-			ntfs_error(sb, "Unable to set block size.");
+			ntfs_error(sb, "Unable to determine device size.");
 		goto err_out_now;
 	}
-
-	/* Get the size of the device in units of NTFS_BLOCK_SIZE bytes. */
 	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
-			NTFS_BLOCK_SIZE_BITS;
-
+			sb->s_blocksize_bits;
 	/* Read the boot sector and return unlocked buffer head to it. */
 	if (!(bh = read_ntfs_boot_sector(sb, silent))) {
 		if (!silent)
 			ntfs_error(sb, "Not an NTFS volume.");
 		goto err_out_now;
 	}
-
 	/*
-	 * Extract the data from the boot sector and setup the ntfs super block
+	 * Extract the data from the boot sector and setup the ntfs volume
 	 * using it.
 	 */
 	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
-
-	/* Initialize the cluster and mft allocators. */
-	ntfs_setup_allocators(vol);
-
 	brelse(bh);
-
 	if (!result) {
 		if (!silent)
 			ntfs_error(sb, "Unsupported NTFS filesystem.");
 		goto err_out_now;
 	}
-
 	/*
-	 * TODO: When we start coping with sector sizes different from
-	 * NTFS_BLOCK_SIZE, we now probably need to set the blocksize of the
-	 * device (probably to NTFS_BLOCK_SIZE).
+	 * If the boot sector indicates a sector size bigger than the current
+	 * device block size, switch the device block size to the sector size.
+	 * TODO: It may be possible to support this case even when the set
+	 * below fails, we would just be breaking up the i/o for each sector
+	 * into multiple blocks for i/o purposes but otherwise it should just
+	 * work.  However it is safer to leave disabled until someone hits this
+	 * error message and then we can get them to try it without the setting
+	 * so we know for sure that it works.
 	 */
-
+	if (vol->sector_size > blocksize) {
+		blocksize = sb_set_blocksize(sb, vol->sector_size);
+		if (blocksize != vol->sector_size) {
+			if (!silent)
+				ntfs_error(sb, "Unable to set device block "
+						"size to sector size (%i).",
+						vol->sector_size);
+			goto err_out_now;
+		}
+		BUG_ON(blocksize != sb->s_blocksize);
+		vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
+				sb->s_blocksize_bits;
+		ntfs_debug("Changed device block size to %i bytes (block size "
+				"bits %i) to match volume sector size.",
+				blocksize, sb->s_blocksize_bits);
+	}
+	/* Initialize the cluster and mft allocators. */
+	ntfs_setup_allocators(vol);
 	/* Setup remaining fields in the super block. */
 	sb->s_magic = NTFS_SB_MAGIC;
-
 	/*
 	 * Ntfs allows 63 bits for the file size, i.e. correct would be:
 	 *	sb->s_maxbytes = ~0ULL >> 1;
@@ -2787,9 +2855,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	 * without overflowing the index or to 2^63 - 1, whichever is smaller.
 	 */
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
-
+	/* Ntfs measures time in 100ns intervals. */
 	sb->s_time_gran = 100;
-
 	/*
 	 * Now load the metadata required for the page cache and our address
 	 * space operations to function. We do this by setting up a specialised
@@ -2987,14 +3054,14 @@ err_out_now:
  * strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
  * (255) Unicode characters + a terminating NULL Unicode character.
  */
-kmem_cache_t *ntfs_name_cache;
+struct kmem_cache *ntfs_name_cache;
 
 /* Slab caches for efficient allocation/deallocation of inodes. */
-kmem_cache_t *ntfs_inode_cache;
-kmem_cache_t *ntfs_big_inode_cache;
+struct kmem_cache *ntfs_inode_cache;
+struct kmem_cache *ntfs_big_inode_cache;
 
 /* Init once constructor for the inode slab cache. */
-static void ntfs_big_inode_init_once(void *foo, kmem_cache_t *cachep,
+static void ntfs_big_inode_init_once(void *foo, struct kmem_cache *cachep,
 		unsigned long flags)
 {
 	ntfs_inode *ni = (ntfs_inode *)foo;
@@ -3008,8 +3075,8 @@ static void ntfs_big_inode_init_once(void *foo, kmem_cache_t *cachep,
  * Slab caches to optimize allocations and deallocations of attribute search
  * contexts and index contexts, respectively.
  */
-kmem_cache_t *ntfs_attr_ctx_cache;
-kmem_cache_t *ntfs_index_ctx_cache;
+struct kmem_cache *ntfs_attr_ctx_cache;
+struct kmem_cache *ntfs_index_ctx_cache;
 
 /* Driver wide semaphore. */
 DECLARE_MUTEX(ntfs_lock);
diff --git a/fs/ntfs/upcase.c b/fs/ntfs/upcase.c
index 879cdf1d5bd3..9101807dc81a 100644
--- a/fs/ntfs/upcase.c
+++ b/fs/ntfs/upcase.c
@@ -3,10 +3,7 @@
  *	      Part of the Linux-NTFS project.
  *
  * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
- * Copyright (c) 2001-2004 Anton Altaparmakov
- *
- * Modified for mkntfs inclusion 9 June 2001 by Anton Altaparmakov.
- * Modified for kernel inclusion 10 September 2001 by Anton Altparmakov.
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -75,12 +72,13 @@ ntfschar *generate_default_upcase(void)
 	if (!uc)
 		return uc;
 	memset(uc, 0, default_upcase_len * sizeof(ntfschar));
+	/* Generate the little endian Unicode upcase table used by ntfs. */
 	for (i = 0; i < default_upcase_len; i++)
 		uc[i] = cpu_to_le16(i);
 	for (r = 0; uc_run_table[r][0]; r++)
 		for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
-			uc[i] = cpu_to_le16((le16_to_cpu(uc[i]) +
-					uc_run_table[r][2]));
+			uc[i] = cpu_to_le16(le16_to_cpu(uc[i]) +
+					uc_run_table[r][2]);
 	for (r = 0; uc_dup_table[r][0]; r++)
 		for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
 			uc[i + 1] = cpu_to_le16(le16_to_cpu(uc[i + 1]) - 1);
diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h
index 375cd20a9f61..406ab55dfb32 100644
--- a/fs/ntfs/volume.h
+++ b/fs/ntfs/volume.h
@@ -2,7 +2,7 @@
  * volume.h - Defines for volume structures in NTFS Linux kernel driver. Part
  *	      of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -41,10 +41,8 @@ typedef struct {
 	 * structure has stabilized... (AIA)
 	 */
 	/* Device specifics. */
-	struct super_block *sb;		/* Pointer back to the super_block,
-					   so we don't have to get the offset
-					   every time. */
-	LCN nr_blocks;			/* Number of NTFS_BLOCK_SIZE bytes
+	struct super_block *sb;		/* Pointer back to the super_block. */
+	LCN nr_blocks;			/* Number of sb->s_blocksize bytes
 					   sized blocks on the device. */
 	/* Configuration provided by user at mount time. */
 	unsigned long flags;		/* Miscellaneous flags, see below. */
@@ -141,8 +139,8 @@ typedef enum {
 	NV_ShowSystemFiles,	/* 1: Return system files in ntfs_readdir(). */
 	NV_CaseSensitive,	/* 1: Treat file names as case sensitive and
 				      create filenames in the POSIX namespace.
-				      Otherwise be case insensitive and create
-				      file names in WIN32 namespace. */
+				      Otherwise be case insensitive but still
+				      create file names in POSIX namespace. */
 	NV_LogFileEmpty,	/* 1: $LogFile journal is empty. */
 	NV_QuotaOutOfDate,	/* 1: $Quota is out of date. */
 	NV_UsnJrnlStamped,	/* 1: $UsnJrnl has been stamped. */
@@ -153,7 +151,7 @@ typedef enum {
  * Macro tricks to expand the NVolFoo(), NVolSetFoo(), and NVolClearFoo()
  * functions.
  */
-#define NVOL_FNS(flag)					\
+#define DEFINE_NVOL_BIT_OPS(flag)					\
 static inline int NVol##flag(ntfs_volume *vol)		\
 {							\
 	return test_bit(NV_##flag, &(vol)->flags);	\
@@ -168,12 +166,12 @@ static inline void NVolClear##flag(ntfs_volume *vol)	\
 }
 
 /* Emit the ntfs volume bitops functions. */
-NVOL_FNS(Errors)
-NVOL_FNS(ShowSystemFiles)
-NVOL_FNS(CaseSensitive)
-NVOL_FNS(LogFileEmpty)
-NVOL_FNS(QuotaOutOfDate)
-NVOL_FNS(UsnJrnlStamped)
-NVOL_FNS(SparseEnabled)
+DEFINE_NVOL_BIT_OPS(Errors)
+DEFINE_NVOL_BIT_OPS(ShowSystemFiles)
+DEFINE_NVOL_BIT_OPS(CaseSensitive)
+DEFINE_NVOL_BIT_OPS(LogFileEmpty)
+DEFINE_NVOL_BIT_OPS(QuotaOutOfDate)
+DEFINE_NVOL_BIT_OPS(UsnJrnlStamped)
+DEFINE_NVOL_BIT_OPS(SparseEnabled)
 
 #endif /* _LINUX_NTFS_VOLUME_H */
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index fd741cea5705..636593bf4d17 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -74,6 +74,7 @@ struct mlog_attribute {
 #define define_mask(_name) {			\
 	.attr = {				\
 		.name = #_name,			\
+		.owner = THIS_MODULE,		\
 		.mode = S_IRUGO | S_IWUSR,	\
 	},					\
 	.mask = ML_##_name,			\
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index e8c56a3d9c64..2cadc3009c83 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -256,7 +256,7 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 	}								\
 } while (0)
 
-#if (BITS_PER_LONG == 32) || defined(CONFIG_X86_64)
+#if (BITS_PER_LONG == 32) || defined(CONFIG_X86_64) || (defined(CONFIG_UML_X86) && defined(CONFIG_64BIT))
 #define MLFi64 "lld"
 #define MLFu64 "llu"
 #define MLFx64 "llx"
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index cf7828f23361..e1fceb8aa32d 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -756,7 +756,7 @@ static int __init init_o2nm(void)
 	if (!ocfs2_table_header) {
 		printk(KERN_ERR "nodemanager: unable to register sysctl\n");
 		ret = -ENOMEM; /* or something. */
-		goto out;
+		goto out_o2net;
 	}
 
 	ret = o2net_register_hb_callbacks();
@@ -780,6 +780,8 @@ out_callbacks:
 	o2net_unregister_hb_callbacks();
 out_sysctl:
 	unregister_sysctl_table(ocfs2_table_header);
+out_o2net:
+	o2net_exit();
 out:
 	return ret;
 }
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index d22d4cf08db1..0f60cc0d3985 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1318,7 +1318,7 @@ static void o2net_start_connect(void *arg)
 {
 	struct o2net_node *nn = arg;
 	struct o2net_sock_container *sc = NULL;
-	struct o2nm_node *node = NULL;
+	struct o2nm_node *node = NULL, *mynode = NULL;
 	struct socket *sock = NULL;
 	struct sockaddr_in myaddr = {0, }, remoteaddr = {0, };
 	int ret = 0;
@@ -1334,6 +1334,12 @@ static void o2net_start_connect(void *arg)
 		goto out;
 	}
 
+	mynode = o2nm_get_node_by_num(o2nm_this_node());
+	if (mynode == NULL) {
+		ret = 0;
+		goto out;
+	}
+
 	spin_lock(&nn->nn_lock);
 	/* see if we already have one pending or have given up */
 	if (nn->nn_sc || nn->nn_persistent_error)
@@ -1361,12 +1367,14 @@ static void o2net_start_connect(void *arg)
 	sock->sk->sk_allocation = GFP_ATOMIC;
 
 	myaddr.sin_family = AF_INET;
+	myaddr.sin_addr.s_addr = (__force u32)mynode->nd_ipv4_address;
 	myaddr.sin_port = (__force u16)htons(0); /* any port */
 
 	ret = sock->ops->bind(sock, (struct sockaddr *)&myaddr,
 			      sizeof(myaddr));
 	if (ret) {
-		mlog(0, "bind failed: %d\n", ret);
+		mlog(ML_ERROR, "bind failed with %d at address %u.%u.%u.%u\n",
+		     ret, NIPQUAD(mynode->nd_ipv4_address));
 		goto out;
 	}
 
@@ -1407,6 +1415,8 @@ out:
 		sc_put(sc);
 	if (node)
 		o2nm_node_put(node);
+	if (mynode)
+		o2nm_node_put(mynode);
 
 	return;
 }
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index a6f4585501c8..616ff2b8434a 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -85,13 +85,10 @@ enum {
 	O2NET_DRIVER_READY,
 };
 
-int o2net_init_tcp_sock(struct inode *inode);
 int o2net_send_message(u32 msg_type, u32 key, void *data, u32 len,
 		       u8 target_node, int *status);
 int o2net_send_message_vec(u32 msg_type, u32 key, struct kvec *vec,
 			   size_t veclen, u8 target_node, int *status);
-int o2net_broadcast_message(u32 msg_type, u32 key, void *data, u32 len,
-			    struct inode *group);
 
 int o2net_register_handler(u32 msg_type, u32 key, u32 max_len,
 			   o2net_msg_handler_func *func, void *data,
@@ -107,7 +104,5 @@ void o2net_disconnect_node(struct o2nm_node *node);
 
 int o2net_init(void);
 void o2net_exit(void);
-int o2net_proc_init(struct proc_dir_entry *parent);
-void o2net_proc_exit(struct proc_dir_entry *parent);
 
 #endif /* O2CLUSTER_TCP_H */
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 23ceaa7127b4..9c772583744a 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -37,9 +37,7 @@
 #define DLM_THREAD_SHUFFLE_INTERVAL    5     // flush everything every 5 passes
 #define DLM_THREAD_MS                  200   // flush at least every 200 ms
 
-#define DLM_HASH_BITS     7
-#define DLM_HASH_SIZE     (1 << DLM_HASH_BITS)
-#define DLM_HASH_MASK     (DLM_HASH_SIZE - 1)
+#define DLM_HASH_BUCKETS     (PAGE_SIZE / sizeof(struct hlist_head))
 
 enum dlm_ast_type {
 	DLM_AST = 0,
@@ -87,7 +85,7 @@ enum dlm_ctxt_state {
 struct dlm_ctxt
 {
 	struct list_head list;
-	struct list_head *resources;
+	struct hlist_head *lockres_hash;
 	struct list_head dirty_list;
 	struct list_head purge_list;
 	struct list_head pending_asts;
@@ -217,7 +215,7 @@ struct dlm_lock_resource
 {
 	/* WARNING: Please see the comment in dlm_init_lockres before
 	 * adding fields here. */
-	struct list_head list;
+	struct hlist_node hash_node;
 	struct kref      refs;
 
 	/* please keep these next 3 in this order
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index f339fe27975a..54f61b76ab51 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -117,8 +117,8 @@ EXPORT_SYMBOL_GPL(dlm_print_one_lock);
 void dlm_dump_lock_resources(struct dlm_ctxt *dlm)
 {
 	struct dlm_lock_resource *res;
-	struct list_head *iter;
-	struct list_head *bucket;
+	struct hlist_node *iter;
+	struct hlist_head *bucket;
 	int i;
 
 	mlog(ML_NOTICE, "struct dlm_ctxt: %s, node=%u, key=%u\n",
@@ -129,12 +129,10 @@ void dlm_dump_lock_resources(struct dlm_ctxt *dlm)
 	}
 
 	spin_lock(&dlm->spinlock);
-	for (i=0; i<DLM_HASH_SIZE; i++) {
-		bucket = &(dlm->resources[i]);
-		list_for_each(iter, bucket) {
-			res = list_entry(iter, struct dlm_lock_resource, list);
+	for (i=0; i<DLM_HASH_BUCKETS; i++) {
+		bucket = &(dlm->lockres_hash[i]);
+		hlist_for_each_entry(res, iter, bucket, hash_node)
 			dlm_print_one_lock_resource(res);
-		}
 	}
 	spin_unlock(&dlm->spinlock);
 }
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6ee30837389c..8f3a9e3106fd 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -77,26 +77,26 @@ static void dlm_unregister_domain_handlers(struct dlm_ctxt *dlm);
 
 void __dlm_unhash_lockres(struct dlm_lock_resource *lockres)
 {
-	list_del_init(&lockres->list);
+	hlist_del_init(&lockres->hash_node);
 	dlm_lockres_put(lockres);
 }
 
 void __dlm_insert_lockres(struct dlm_ctxt *dlm,
 		       struct dlm_lock_resource *res)
 {
-	struct list_head *bucket;
+	struct hlist_head *bucket;
 	struct qstr *q;
 
 	assert_spin_locked(&dlm->spinlock);
 
 	q = &res->lockname;
 	q->hash = full_name_hash(q->name, q->len);
-	bucket = &(dlm->resources[q->hash & DLM_HASH_MASK]);
+	bucket = &(dlm->lockres_hash[q->hash % DLM_HASH_BUCKETS]);
 
 	/* get a reference for our hashtable */
 	dlm_lockres_get(res);
 
-	list_add_tail(&res->list, bucket);
+	hlist_add_head(&res->hash_node, bucket);
 }
 
 struct dlm_lock_resource * __dlm_lookup_lockres(struct dlm_ctxt *dlm,
@@ -104,9 +104,9 @@ struct dlm_lock_resource * __dlm_lookup_lockres(struct dlm_ctxt *dlm,
 					 unsigned int len)
 {
 	unsigned int hash;
-	struct list_head *iter;
+	struct hlist_node *iter;
 	struct dlm_lock_resource *tmpres=NULL;
-	struct list_head *bucket;
+	struct hlist_head *bucket;
 
 	mlog_entry("%.*s\n", len, name);
 
@@ -114,11 +114,11 @@ struct dlm_lock_resource * __dlm_lookup_lockres(struct dlm_ctxt *dlm,
 
 	hash = full_name_hash(name, len);
 
-	bucket = &(dlm->resources[hash & DLM_HASH_MASK]);
+	bucket = &(dlm->lockres_hash[hash % DLM_HASH_BUCKETS]);
 
 	/* check for pre-existing lock */
-	list_for_each(iter, bucket) {
-		tmpres = list_entry(iter, struct dlm_lock_resource, list);
+	hlist_for_each(iter, bucket) {
+		tmpres = hlist_entry(iter, struct dlm_lock_resource, hash_node);
 		if (tmpres->lockname.len == len &&
 		    memcmp(tmpres->lockname.name, name, len) == 0) {
 			dlm_lockres_get(tmpres);
@@ -193,8 +193,8 @@ static int dlm_wait_on_domain_helper(const char *domain)
 
 static void dlm_free_ctxt_mem(struct dlm_ctxt *dlm)
 {
-	if (dlm->resources)
-		free_page((unsigned long) dlm->resources);
+	if (dlm->lockres_hash)
+		free_page((unsigned long) dlm->lockres_hash);
 
 	if (dlm->name)
 		kfree(dlm->name);
@@ -303,10 +303,10 @@ static void dlm_migrate_all_locks(struct dlm_ctxt *dlm)
 	mlog(0, "Migrating locks from domain %s\n", dlm->name);
 restart:
 	spin_lock(&dlm->spinlock);
-	for (i=0; i<DLM_HASH_SIZE; i++) {
-		while (!list_empty(&dlm->resources[i])) {
-			res = list_entry(dlm->resources[i].next,
-				     struct dlm_lock_resource, list);
+	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
+		while (!hlist_empty(&dlm->lockres_hash[i])) {
+			res = hlist_entry(dlm->lockres_hash[i].first,
+					  struct dlm_lock_resource, hash_node);
 			/* need reference when manually grabbing lockres */
 			dlm_lockres_get(res);
 			/* this should unhash the lockres
@@ -1191,18 +1191,17 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 		goto leave;
 	}
 
-	dlm->resources = (struct list_head *) __get_free_page(GFP_KERNEL);
-	if (!dlm->resources) {
+	dlm->lockres_hash = (struct hlist_head *) __get_free_page(GFP_KERNEL);
+	if (!dlm->lockres_hash) {
 		mlog_errno(-ENOMEM);
 		kfree(dlm->name);
 		kfree(dlm);
 		dlm = NULL;
 		goto leave;
 	}
-	memset(dlm->resources, 0, PAGE_SIZE);
 
-	for (i=0; i<DLM_HASH_SIZE; i++)
-		INIT_LIST_HEAD(&dlm->resources[i]);
+	for (i=0; i<DLM_HASH_BUCKETS; i++)
+		INIT_HLIST_HEAD(&dlm->lockres_hash[i]);
 
 	strcpy(dlm->name, domain);
 	dlm->key = key;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 2e2e95e69499..847dd3cc4cf5 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -564,7 +564,7 @@ static void dlm_lockres_release(struct kref *kref)
 
 	/* By the time we're ready to blow this guy away, we shouldn't
 	 * be on any lists. */
-	BUG_ON(!list_empty(&res->list));
+	BUG_ON(!hlist_unhashed(&res->hash_node));
 	BUG_ON(!list_empty(&res->granted));
 	BUG_ON(!list_empty(&res->converting));
 	BUG_ON(!list_empty(&res->blocked));
@@ -605,7 +605,7 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 
 	init_waitqueue_head(&res->wq);
 	spin_lock_init(&res->spinlock);
-	INIT_LIST_HEAD(&res->list);
+	INIT_HLIST_NODE(&res->hash_node);
 	INIT_LIST_HEAD(&res->granted);
 	INIT_LIST_HEAD(&res->converting);
 	INIT_LIST_HEAD(&res->blocked);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index ed76bda1a534..1e232000f3f7 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1693,7 +1693,10 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 					      u8 dead_node, u8 new_master)
 {
 	int i;
-	struct list_head *iter, *iter2, *bucket;
+	struct list_head *iter, *iter2;
+	struct hlist_node *hash_iter;
+	struct hlist_head *bucket;
+
 	struct dlm_lock_resource *res;
 
 	mlog_entry_void();
@@ -1717,10 +1720,9 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 	 * for now we need to run the whole hash, clear
 	 * the RECOVERING state and set the owner
 	 * if necessary */
-	for (i=0; i<DLM_HASH_SIZE; i++) {
-		bucket = &(dlm->resources[i]);
-		list_for_each(iter, bucket) {
-			res = list_entry (iter, struct dlm_lock_resource, list);
+	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
+		bucket = &(dlm->lockres_hash[i]);
+		hlist_for_each_entry(res, hash_iter, bucket, hash_node) {
 			if (res->state & DLM_LOCK_RES_RECOVERING) {
 				if (res->owner == dead_node) {
 					mlog(0, "(this=%u) res %.*s owner=%u "
@@ -1852,10 +1854,10 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 
 static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 {
-	struct list_head *iter;
+	struct hlist_node *iter;
 	struct dlm_lock_resource *res;
 	int i;
-	struct list_head *bucket;
+	struct hlist_head *bucket;
 	struct dlm_lock *lock;
 
 
@@ -1876,10 +1878,9 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 	 *    can be kicked again to see if any ASTs or BASTs
 	 *    need to be fired as a result.
 	 */
-	for (i=0; i<DLM_HASH_SIZE; i++) {
-		bucket = &(dlm->resources[i]);
-		list_for_each(iter, bucket) {
-			res = list_entry (iter, struct dlm_lock_resource, list);
+	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
+		bucket = &(dlm->lockres_hash[i]);
+		hlist_for_each_entry(res, iter, bucket, hash_node) {
  			/* always prune any $RECOVERY entries for dead nodes,
  			 * otherwise hangs can occur during later recovery */
 			if (dlm_is_recovery_lock(res->lockname.name,
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index b6ba292e9544..e6f207eebab4 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -181,6 +181,12 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode,
 			ret = -EBADR;
 			if (rec_end > OCFS2_I(inode)->ip_clusters) {
 				mlog_errno(ret);
+				ocfs2_error(inode->i_sb,
+					    "Extent %d at e_blkno %"MLFu64" of inode %"MLFu64" goes past ip_clusters of %u\n",
+					    i,
+					    le64_to_cpu(rec->e_blkno),
+					    OCFS2_I(inode)->ip_blkno,
+					    OCFS2_I(inode)->ip_clusters);
 				goto out_free;
 			}
 
@@ -226,6 +232,12 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode,
 			ret = -EBADR;
 			if (blkno) {
 				mlog_errno(ret);
+				ocfs2_error(inode->i_sb,
+					    "Multiple extents for (cpos = %u, clusters = %u) on inode %"MLFu64"; e_blkno %"MLFu64" and rec %d at e_blkno %"MLFu64"\n",
+					    cpos, clusters,
+					    OCFS2_I(inode)->ip_blkno,
+					    blkno, i,
+					    le64_to_cpu(rec->e_blkno));
 				goto out_free;
 			}
 
@@ -238,6 +250,10 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode,
 		 */
 		ret = -EBADR;
 		if (!blkno) {
+			ocfs2_error(inode->i_sb,
+				    "No record found for (cpos = %u, clusters = %u) on inode %"MLFu64"\n",
+				    cpos, clusters,
+				    OCFS2_I(inode)->ip_blkno);
 			mlog_errno(ret);
 			goto out_free;
 		}
@@ -266,6 +282,20 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode,
 
 	for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) {
 		rec = &el->l_recs[i];
+
+		if ((le32_to_cpu(rec->e_cpos) + le32_to_cpu(rec->e_clusters)) >
+		    OCFS2_I(inode)->ip_clusters) {
+			ret = -EBADR;
+			mlog_errno(ret);
+			ocfs2_error(inode->i_sb,
+				    "Extent %d at e_blkno %"MLFu64" of inode %"MLFu64" goes past ip_clusters of %u\n",
+				    i,
+				    le64_to_cpu(rec->e_blkno),
+				    OCFS2_I(inode)->ip_blkno,
+				    OCFS2_I(inode)->ip_clusters);
+			return ret;
+		}
+
 		ret = ocfs2_extent_map_insert(inode, rec,
 					      le16_to_cpu(el->l_tree_depth));
 		if (ret) {
@@ -526,6 +556,10 @@ static int ocfs2_extent_map_insert(struct inode *inode,
 		    OCFS2_I(inode)->ip_map.em_clusters) {
 			ret = -EBADR;
 			mlog_errno(ret);
+			ocfs2_error(inode->i_sb,
+				    "Zero e_clusters on non-tail extent record at e_blkno %"MLFu64" on inode %"MLFu64"\n",
+				    le64_to_cpu(rec->e_blkno),
+				    OCFS2_I(inode)->ip_blkno);
 			return ret;
 		}
 
@@ -588,12 +622,12 @@ static int ocfs2_extent_map_insert(struct inode *inode,
  * Existing record in the extent map:
  *
  *	cpos = 10, len = 10
- * 	|---------|
+ *	|---------|
  *
  * New Record:
  *
  *	cpos = 10, len = 20
- * 	|------------------|
+ *	|------------------|
  *
  * The passed record is the new on-disk record.  The new_clusters value
  * is how many clusters were added to the file.  If the append is a
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 1715bc90e705..8a4048b55fdc 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -933,9 +933,6 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	struct file *filp = iocb->ki_filp;
 	struct inode *inode = filp->f_dentry->d_inode;
 	loff_t newsize, saved_pos;
-#ifdef OCFS2_ORACORE_WORKAROUNDS
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-#endif
 
 	mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf,
 		   (unsigned int)count,
@@ -951,14 +948,6 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		return -EIO;
 	}
 
-#ifdef OCFS2_ORACORE_WORKAROUNDS
-	/* ugh, work around some applications which open everything O_DIRECT +
-	 * O_APPEND and really don't mean to use O_DIRECT. */
-	if (osb->s_mount_opt & OCFS2_MOUNT_COMPAT_OCFS &&
-	    (filp->f_flags & O_APPEND) && (filp->f_flags & O_DIRECT)) 
-		filp->f_flags &= ~O_DIRECT;
-#endif
-
 	mutex_lock(&inode->i_mutex);
 	/* to match setattr's i_mutex -> i_alloc_sem -> rw_lock ordering */
 	if (filp->f_flags & O_DIRECT) {
@@ -1079,27 +1068,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	/* communicate with ocfs2_dio_end_io */
 	ocfs2_iocb_set_rw_locked(iocb);
 
-#ifdef OCFS2_ORACORE_WORKAROUNDS
-	if (osb->s_mount_opt & OCFS2_MOUNT_COMPAT_OCFS &&
-	    filp->f_flags & O_DIRECT) {
-		unsigned int saved_flags = filp->f_flags;
-		int sector_size = 1 << osb->s_sectsize_bits;
-
-		if ((saved_pos & (sector_size - 1)) ||
-		    (count & (sector_size - 1)) ||
-		    ((unsigned long)buf & (sector_size - 1))) {
-			filp->f_flags |= O_SYNC;
-			filp->f_flags &= ~O_DIRECT;
-		}
-
-		ret = generic_file_aio_write_nolock(iocb, &local_iov, 1,
-						    &iocb->ki_pos);
-
-		filp->f_flags = saved_flags;
-	} else
-#endif
-		ret = generic_file_aio_write_nolock(iocb, &local_iov, 1,
-						    &iocb->ki_pos);
+	ret = generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
 
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
@@ -1140,9 +1109,6 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	int ret = 0, rw_level = -1, have_alloc_sem = 0;
 	struct file *filp = iocb->ki_filp;
 	struct inode *inode = filp->f_dentry->d_inode;
-#ifdef OCFS2_ORACORE_WORKAROUNDS
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-#endif
 
 	mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf,
 		   (unsigned int)count,
@@ -1155,21 +1121,6 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 		goto bail;
 	}
 
-#ifdef OCFS2_ORACORE_WORKAROUNDS
-	if (osb->s_mount_opt & OCFS2_MOUNT_COMPAT_OCFS) {
-		if (filp->f_flags & O_DIRECT) {
-			int sector_size = 1 << osb->s_sectsize_bits;
-
-			if ((pos & (sector_size - 1)) ||
-			    (count & (sector_size - 1)) ||
-			    ((unsigned long)buf & (sector_size - 1)) ||
-			    (i_size_read(inode) & (sector_size -1))) {
-				filp->f_flags &= ~O_DIRECT;
-			}
-		}
-	}
-#endif
-
 	/* 
 	 * buffered reads protect themselves in ->readpage().  O_DIRECT reads
 	 * need locks to protect pending reads from racing with truncate.
diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c
index 0bbd22f46c80..cbfd45a97a63 100644
--- a/fs/ocfs2/heartbeat.c
+++ b/fs/ocfs2/heartbeat.c
@@ -67,6 +67,7 @@ void ocfs2_init_node_maps(struct ocfs2_super *osb)
 	ocfs2_node_map_init(&osb->mounted_map);
 	ocfs2_node_map_init(&osb->recovery_map);
 	ocfs2_node_map_init(&osb->umount_map);
+	ocfs2_node_map_init(&osb->osb_recovering_orphan_dirs);
 }
 
 static void ocfs2_do_node_down(int node_num,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 8122489c5762..315472a5c192 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -41,6 +41,7 @@
 #include "dlmglue.h"
 #include "extent_map.h"
 #include "file.h"
+#include "heartbeat.h"
 #include "inode.h"
 #include "journal.h"
 #include "namei.h"
@@ -544,6 +545,42 @@ bail:
 	return status;
 }
 
+/* 
+ * Serialize with orphan dir recovery. If the process doing
+ * recovery on this orphan dir does an iget() with the dir
+ * i_mutex held, we'll deadlock here. Instead we detect this
+ * and exit early - recovery will wipe this inode for us.
+ */
+static int ocfs2_check_orphan_recovery_state(struct ocfs2_super *osb,
+					     int slot)
+{
+	int ret = 0;
+
+	spin_lock(&osb->osb_lock);
+	if (ocfs2_node_map_test_bit(osb, &osb->osb_recovering_orphan_dirs, slot)) {
+		mlog(0, "Recovery is happening on orphan dir %d, will skip "
+		     "this inode\n", slot);
+		ret = -EDEADLK;
+		goto out;
+	}
+	/* This signals to the orphan recovery process that it should
+	 * wait for us to handle the wipe. */
+	osb->osb_orphan_wipes[slot]++;
+out:
+	spin_unlock(&osb->osb_lock);
+	return ret;
+}
+
+static void ocfs2_signal_wipe_completion(struct ocfs2_super *osb,
+					 int slot)
+{
+	spin_lock(&osb->osb_lock);
+	osb->osb_orphan_wipes[slot]--;
+	spin_unlock(&osb->osb_lock);
+
+	wake_up(&osb->osb_wipe_event);
+}
+
 static int ocfs2_wipe_inode(struct inode *inode,
 			    struct buffer_head *di_bh)
 {
@@ -555,6 +592,11 @@ static int ocfs2_wipe_inode(struct inode *inode,
 	/* We've already voted on this so it should be readonly - no
 	 * spinlock needed. */
 	orphaned_slot = OCFS2_I(inode)->ip_orphaned_slot;
+
+	status = ocfs2_check_orphan_recovery_state(osb, orphaned_slot);
+	if (status)
+		return status;
+
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
 						       ORPHAN_DIR_SYSTEM_INODE,
 						       orphaned_slot);
@@ -597,6 +639,7 @@ bail_unlock_dir:
 	brelse(orphan_dir_bh);
 bail:
 	iput(orphan_dir_inode);
+	ocfs2_signal_wipe_completion(osb, orphaned_slot);
 
 	return status;
 }
@@ -822,7 +865,8 @@ void ocfs2_delete_inode(struct inode *inode)
 
 	status = ocfs2_wipe_inode(inode, di_bh);
 	if (status < 0) {
-		mlog_errno(status);
+		if (status != -EDEADLK)
+			mlog_errno(status);
 		goto bail_unlock_inode;
 	}
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index d329c9df90ae..4be801f4559b 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1408,21 +1408,17 @@ bail:
 	return status;
 }
 
-static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+static int ocfs2_queue_orphans(struct ocfs2_super *osb,
+			       int slot,
+			       struct inode **head)
 {
-	int status = 0;
-	int have_disk_lock = 0;
-	struct inode *inode = NULL;
-	struct inode *iter;
+	int status;
 	struct inode *orphan_dir_inode = NULL;
+	struct inode *iter;
 	unsigned long offset, blk, local;
 	struct buffer_head *bh = NULL;
 	struct ocfs2_dir_entry *de;
 	struct super_block *sb = osb->sb;
-	struct ocfs2_inode_info *oi;
-
-	mlog(0, "Recover inodes from orphan dir in slot %d\n", slot);
 
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
 						       ORPHAN_DIR_SYSTEM_INODE,
@@ -1430,17 +1426,15 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 	if  (!orphan_dir_inode) {
 		status = -ENOENT;
 		mlog_errno(status);
-		goto out;
-	}
+		return status;
+	}	
 
 	mutex_lock(&orphan_dir_inode->i_mutex);
 	status = ocfs2_meta_lock(orphan_dir_inode, NULL, NULL, 0);
 	if (status < 0) {
-		mutex_unlock(&orphan_dir_inode->i_mutex);
 		mlog_errno(status);
 		goto out;
 	}
-	have_disk_lock = 1;
 
 	offset = 0;
 	iter = NULL;
@@ -1451,11 +1445,10 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		if (!bh)
 			status = -EINVAL;
 		if (status < 0) {
-			mutex_unlock(&orphan_dir_inode->i_mutex);
 			if (bh)
 				brelse(bh);
 			mlog_errno(status);
-			goto out;
+			goto out_unlock;
 		}
 
 		local = 0;
@@ -1465,11 +1458,10 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 
 			if (!ocfs2_check_dir_entry(orphan_dir_inode,
 						  de, bh, local)) {
-				mutex_unlock(&orphan_dir_inode->i_mutex);
 				status = -EINVAL;
 				mlog_errno(status);
 				brelse(bh);
-				goto out;
+				goto out_unlock;
 			}
 
 			local += le16_to_cpu(de->rec_len);
@@ -1504,18 +1496,95 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 
 			mlog(0, "queue orphan %"MLFu64"\n",
 			     OCFS2_I(iter)->ip_blkno);
-			OCFS2_I(iter)->ip_next_orphan = inode;
-			inode = iter;
+			/* No locking is required for the next_orphan
+			 * queue as there is only ever a single
+			 * process doing orphan recovery. */
+			OCFS2_I(iter)->ip_next_orphan = *head;
+			*head = iter;
 		}
 		brelse(bh);
 	}
-	mutex_unlock(&orphan_dir_inode->i_mutex);
 
+out_unlock:
 	ocfs2_meta_unlock(orphan_dir_inode, 0);
-	have_disk_lock = 0;
-
+out:
+	mutex_unlock(&orphan_dir_inode->i_mutex);
 	iput(orphan_dir_inode);
-	orphan_dir_inode = NULL;
+	return status;
+}
+
+static int ocfs2_orphan_recovery_can_continue(struct ocfs2_super *osb,
+					      int slot)
+{
+	int ret;
+
+	spin_lock(&osb->osb_lock);
+	ret = !osb->osb_orphan_wipes[slot];
+	spin_unlock(&osb->osb_lock);
+	return ret;
+}
+
+static void ocfs2_mark_recovering_orphan_dir(struct ocfs2_super *osb,
+					     int slot)
+{
+	spin_lock(&osb->osb_lock);
+	/* Mark ourselves such that new processes in delete_inode()
+	 * know to quit early. */
+	ocfs2_node_map_set_bit(osb, &osb->osb_recovering_orphan_dirs, slot);
+	while (osb->osb_orphan_wipes[slot]) {
+		/* If any processes are already in the middle of an
+		 * orphan wipe on this dir, then we need to wait for
+		 * them. */
+		spin_unlock(&osb->osb_lock);
+		wait_event_interruptible(osb->osb_wipe_event,
+					 ocfs2_orphan_recovery_can_continue(osb, slot));
+		spin_lock(&osb->osb_lock);
+	}
+	spin_unlock(&osb->osb_lock);
+}
+
+static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
+					      int slot)
+{
+	ocfs2_node_map_clear_bit(osb, &osb->osb_recovering_orphan_dirs, slot);
+}
+
+/*
+ * Orphan recovery. Each mounted node has it's own orphan dir which we
+ * must run during recovery. Our strategy here is to build a list of
+ * the inodes in the orphan dir and iget/iput them. The VFS does
+ * (most) of the rest of the work.
+ *
+ * Orphan recovery can happen at any time, not just mount so we have a
+ * couple of extra considerations.
+ *
+ * - We grab as many inodes as we can under the orphan dir lock -
+ *   doing iget() outside the orphan dir risks getting a reference on
+ *   an invalid inode.
+ * - We must be sure not to deadlock with other processes on the
+ *   system wanting to run delete_inode(). This can happen when they go
+ *   to lock the orphan dir and the orphan recovery process attempts to
+ *   iget() inside the orphan dir lock. This can be avoided by
+ *   advertising our state to ocfs2_delete_inode().
+ */
+static int ocfs2_recover_orphans(struct ocfs2_super *osb,
+				 int slot)
+{
+	int ret = 0;
+	struct inode *inode = NULL;
+	struct inode *iter;
+	struct ocfs2_inode_info *oi;
+
+	mlog(0, "Recover inodes from orphan dir in slot %d\n", slot);
+
+	ocfs2_mark_recovering_orphan_dir(osb, slot);
+	ret = ocfs2_queue_orphans(osb, slot, &inode);
+	ocfs2_clear_recovering_orphan_dir(osb, slot);
+
+	/* Error here should be noted, but we want to continue with as
+	 * many queued inodes as we've got. */
+	if (ret)
+		mlog_errno(ret);
 
 	while (inode) {
 		oi = OCFS2_I(inode);
@@ -1541,14 +1610,7 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		inode = iter;
 	}
 
-out:
-	if (have_disk_lock)
-		ocfs2_meta_unlock(orphan_dir_inode, 0);
-
-	if (orphan_dir_inode)
-		iput(orphan_dir_inode);
-
-	return status;
+	return ret;
 }
 
 static int ocfs2_wait_on_mount(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 8d8e4779df92..e89de9b6e491 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -174,9 +174,6 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_NOINTR  = 1 << 2,   /* Don't catch signals */
 	OCFS2_MOUNT_ERRORS_PANIC = 1 << 3, /* Panic on errors */
 	OCFS2_MOUNT_DATA_WRITEBACK = 1 << 4, /* No data ordering */
-#ifdef OCFS2_ORACORE_WORKAROUNDS
-	OCFS2_MOUNT_COMPAT_OCFS = 1 << 30, /* ocfs1 compatibility mode */
-#endif
 };
 
 #define OCFS2_OSB_SOFT_RO	0x0001
@@ -290,6 +287,10 @@ struct ocfs2_super
 	struct inode			*osb_tl_inode;
 	struct buffer_head		*osb_tl_bh;
 	struct work_struct		osb_truncate_log_wq;
+
+	struct ocfs2_node_map		osb_recovering_orphan_dirs;
+	unsigned int			*osb_orphan_wipes;
+	wait_queue_head_t		osb_wipe_event;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index dfb8a5bedfc8..c5b1ac547c15 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -138,7 +138,6 @@
 
 /* Journal limits (in bytes) */
 #define OCFS2_MIN_JOURNAL_SIZE		(4 * 1024 * 1024)
-#define OCFS2_MAX_JOURNAL_SIZE		(500 * 1024 * 1024)
 
 struct ocfs2_system_inode_info {
 	char	*si_name;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 046824b6b625..8dd3aafec499 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1325,6 +1325,16 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	}
 	mlog(ML_NOTICE, "max_slots for this device: %u\n", osb->max_slots);
 
+	init_waitqueue_head(&osb->osb_wipe_event);
+	osb->osb_orphan_wipes = kcalloc(osb->max_slots,
+					sizeof(*osb->osb_orphan_wipes),
+					GFP_KERNEL);
+	if (!osb->osb_orphan_wipes) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto bail;
+	}
+
 	osb->s_feature_compat =
 		le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_compat);
 	osb->s_feature_ro_compat =
@@ -1638,6 +1648,7 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 	if (osb->slot_info)
 		ocfs2_free_slot_info(osb->slot_info);
 
+	kfree(osb->osb_orphan_wipes);
 	/* FIXME
 	 * This belongs in journal shutdown, but because we have to
 	 * allocate osb->journal at the start of ocfs2_initalize_osb(),
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index c66bd5e4c05c..cde5d48994ae 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -27,6 +27,7 @@
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/smp_lock.h>
@@ -104,6 +105,7 @@ ramfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 		d_instantiate(dentry, inode);
 		dget(dentry);	/* Extra count - pin the dentry in core */
 		error = 0;
+		dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	}
 	return error;
 }
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index f3473176c83a..be12879bb179 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -1464,13 +1464,11 @@ static ssize_t reiserfs_file_write(struct file *file,	/* the file we are going t
 		   partially overwritten pages, if needed. And lock the pages,
 		   so that nobody else can access these until we are done.
 		   We get number of actual blocks needed as a result. */
-		blocks_to_allocate =
-		    reiserfs_prepare_file_region_for_write(inode, pos,
-							   num_pages,
-							   write_bytes,
-							   prepared_pages);
-		if (blocks_to_allocate < 0) {
-			res = blocks_to_allocate;
+		res = reiserfs_prepare_file_region_for_write(inode, pos,
+							     num_pages,
+							     write_bytes,
+							     prepared_pages);
+		if (res < 0) {
 			reiserfs_release_claimed_blocks(inode->i_sb,
 							num_pages <<
 							(PAGE_CACHE_SHIFT -
@@ -1478,6 +1476,8 @@ static ssize_t reiserfs_file_write(struct file *file,	/* the file we are going t
 			break;
 		}
 
+		blocks_to_allocate = res;
+
 		/* First we correct our estimate of how many blocks we need */
 		reiserfs_release_claimed_blocks(inode->i_sb,
 						(num_pages <<
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index b33d67bba2fd..d60f6238c66a 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -627,11 +627,6 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	reiserfs_write_lock(inode->i_sb);
 	version = get_inode_item_key_version(inode);
 
-	if (block < 0) {
-		reiserfs_write_unlock(inode->i_sb);
-		return -EIO;
-	}
-
 	if (!file_capable(inode, block)) {
 		reiserfs_write_unlock(inode->i_sb);
 		return -EFBIG;
@@ -934,12 +929,13 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 				     //pos_in_item * inode->i_sb->s_blocksize,
 				     TYPE_INDIRECT, 3);	// key type is unimportant
 
+			RFALSE(cpu_key_k_offset(&tmp_key) > cpu_key_k_offset(&key),
+			       "green-805: invalid offset");
 			blocks_needed =
 			    1 +
 			    ((cpu_key_k_offset(&key) -
 			      cpu_key_k_offset(&tmp_key)) >> inode->i_sb->
 			     s_blocksize_bits);
-			RFALSE(blocks_needed < 0, "green-805: invalid offset");
 
 			if (blocks_needed == 1) {
 				un = &unf_single;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index b7a179560ab4..5a9d2722fa0a 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2319,8 +2319,7 @@ static int journal_read(struct super_block *p_s_sb)
 		return 1;
 	}
 	jh = (struct reiserfs_journal_header *)(journal->j_header_bh->b_data);
-	if (le32_to_cpu(jh->j_first_unflushed_offset) >= 0 &&
-	    le32_to_cpu(jh->j_first_unflushed_offset) <
+	if (le32_to_cpu(jh->j_first_unflushed_offset) <
 	    SB_ONDISK_JOURNAL_SIZE(p_s_sb)
 	    && le32_to_cpu(jh->j_last_flush_trans_id) > 0) {
 		oldest_start =
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 8f2beec526cf..74d8be87f983 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -540,7 +540,7 @@ xfs_probe_cluster(
 
 	/* First sum forwards in this page */
 	do {
-		if (mapped != buffer_mapped(bh))
+		if (!buffer_uptodate(bh) || (mapped != buffer_mapped(bh)))
 			return total;
 		total += bh->b_size;
 	} while ((bh = bh->b_this_page) != head);
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 53a00fb217fa..7c0e39dc6189 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -68,6 +68,9 @@ kmem_zone_t	*qm_dqzone;
 kmem_zone_t	*qm_dqtrxzone;
 STATIC kmem_shaker_t	xfs_qm_shaker;
 
+STATIC cred_t	xfs_zerocr;
+STATIC xfs_inode_t	xfs_zeroino;
+
 STATIC void	xfs_qm_list_init(xfs_dqlist_t *, char *, int);
 STATIC void	xfs_qm_list_destroy(xfs_dqlist_t *);
 
@@ -1393,8 +1396,6 @@ xfs_qm_qino_alloc(
 	xfs_trans_t	*tp;
 	int		error;
 	unsigned long	s;
-	cred_t		zerocr;
-	xfs_inode_t	zeroino;
 	int		committed;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QINOCREATE);
@@ -1406,11 +1407,9 @@ xfs_qm_qino_alloc(
 		xfs_trans_cancel(tp, 0);
 		return error;
 	}
-	memset(&zerocr, 0, sizeof(zerocr));
-	memset(&zeroino, 0, sizeof(zeroino));
 
-	if ((error = xfs_dir_ialloc(&tp, &zeroino, S_IFREG, 1, 0,
-				   &zerocr, 0, 1, ip, &committed))) {
+	if ((error = xfs_dir_ialloc(&tp, &xfs_zeroino, S_IFREG, 1, 0,
+				   &xfs_zerocr, 0, 1, ip, &committed))) {
 		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
 				 XFS_TRANS_ABORT);
 		return error;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 06fc061c50fc..5b413946b1c5 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -130,7 +130,8 @@ xfs_growfs_rt_alloc(
 		/*
 		 * Lock the inode.
 		 */
-		if ((error = xfs_trans_iget(mp, tp, ino, 0, XFS_ILOCK_EXCL, &ip)))
+		if ((error = xfs_trans_iget(mp, tp, ino, 0,
+						XFS_ILOCK_EXCL, &ip)))
 			goto error_exit;
 		XFS_BMAP_INIT(&flist, &firstblock);
 		/*
@@ -170,8 +171,8 @@ xfs_growfs_rt_alloc(
 			/*
 			 * Lock the bitmap inode.
 			 */
-			if ((error = xfs_trans_iget(mp, tp, ino, 0, XFS_ILOCK_EXCL,
-					&ip)))
+			if ((error = xfs_trans_iget(mp, tp, ino, 0,
+							XFS_ILOCK_EXCL, &ip)))
 				goto error_exit;
 			/*
 			 * Get a buffer for the block.
@@ -2023,8 +2024,8 @@ xfs_growfs_rt(
 		/*
 		 * Lock out other callers by grabbing the bitmap inode lock.
 		 */
-		if ((error = xfs_trans_iget(mp, tp, 0, mp->m_sb.sb_rbmino,
-				XFS_ILOCK_EXCL, &ip)))
+		if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
+						XFS_ILOCK_EXCL, &ip)))
 			goto error_exit;
 		ASSERT(ip == mp->m_rbmip);
 		/*
@@ -2037,8 +2038,8 @@ xfs_growfs_rt(
 		/*
 		 * Get the summary inode into the transaction.
 		 */
-		if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rsumino,
-				0, XFS_ILOCK_EXCL, &ip)))
+		if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rsumino, 0,
+						XFS_ILOCK_EXCL, &ip)))
 			goto error_exit;
 		ASSERT(ip == mp->m_rsumip);
 		/*
@@ -2158,10 +2159,9 @@ xfs_rtallocate_extent(
 	/*
 	 * Lock out other callers by grabbing the bitmap inode lock.
 	 */
-	error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0, XFS_ILOCK_EXCL, &ip);
-	if (error) {
+	if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
+					XFS_ILOCK_EXCL, &ip)))
 		return error;
-	}
 	sumbp = NULL;
 	/*
 	 * Allocate by size, or near another block, or exactly at some block.
@@ -2221,10 +2221,9 @@ xfs_rtfree_extent(
 	/*
 	 * Synchronize by locking the bitmap inode.
 	 */
-	error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0, XFS_ILOCK_EXCL, &ip);
-	if (error) {
+	if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
+					XFS_ILOCK_EXCL, &ip)))
 		return error;
-	}
 #if defined(__KERNEL__) && defined(DEBUG)
 	/*
 	 * Check to see that this whole range is currently allocated.
@@ -2365,8 +2364,8 @@ xfs_rtpick_extent(
 	__uint64_t	seq;		/* sequence number of file creation */
 	__uint64_t	*seqp;		/* pointer to seqno in inode */
 
-	error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0, XFS_ILOCK_EXCL, &ip);
-	if (error)
+	if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
+					XFS_ILOCK_EXCL, &ip)))
 		return error;
 	ASSERT(ip == mp->m_rbmip);
 	seqp = (__uint64_t *)&ip->i_d.di_atime;