Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: (32 commits)
  [PATCH] ocfs2: zero_user_page conversion
  ocfs2: Support xfs style space reservation ioctls
  ocfs2: support for removing file regions
  ocfs2: update truncate handling of partial clusters
  ocfs2: btree support for removal of arbirtrary extents
  ocfs2: Support creation of unwritten extents
  ocfs2: support writing of unwritten extents
  ocfs2: small cleanup of ocfs2_write_begin_nolock()
  ocfs2: btree changes for unwritten extents
  ocfs2: abstract btree growing calls
  ocfs2: use all extent block suballocators
  ocfs2: plug truncate into cached dealloc routines
  ocfs2: simplify deallocation locking
  ocfs2: harden buffer check during mapping of page blocks
  ocfs2: shared writeable mmap
  ocfs2: factor out write aops into nolock variants
  ocfs2: rework ocfs2_buffered_write_cluster()
  ocfs2: take ip_alloc_sem during entire truncate
  ocfs2: Add "preferred slot" mount option
  [KJ PATCH] Replacing memset(<addr>,0,PAGE_SIZE) with clear_page() in fs/ocfs2/dlm/dlmrecovery.c
  ...

Documentation/filesystems/configfs/configfs.txt

@@ -238,6 +238,8 @@ config_item_type.
 		struct config_group *(*make_group)(struct config_group *group,
 						   const char *name);
 		int (*commit_item)(struct config_item *item);
+		void (*disconnect_notify)(struct config_group *group,
+					  struct config_item *item);
 		void (*drop_item)(struct config_group *group,
 				  struct config_item *item);
 	};
@@ -268,6 +270,16 @@ the item in other threads, the memory is safe.  It may take some time
 for the item to actually disappear from the subsystem's usage.  But it
 is gone from configfs.
 
+When drop_item() is called, the item's linkage has already been torn
+down.  It no longer has a reference on its parent and has no place in
+the item hierarchy.  If a client needs to do some cleanup before this
+teardown happens, the subsystem can implement the
+ct_group_ops->disconnect_notify() method.  The method is called after
+configfs has removed the item from the filesystem view but before the
+item is removed from its parent group.  Like drop_item(),
+disconnect_notify() is void and cannot fail.  Client subsystems should
+not drop any references here, as they still must do it in drop_item().
+
 A config_group cannot be removed while it still has child items.  This
 is implemented in the configfs rmdir(2) code.  ->drop_item() will not be
 called, as the item has not been dropped.  rmdir(2) will fail, as the
@@ -280,18 +292,18 @@ tells configfs to make the subsystem appear in the file tree.
 
 	struct configfs_subsystem {
 		struct config_group	su_group;
-		struct semaphore	su_sem;
+		struct mutex		su_mutex;
 	};
 
 	int configfs_register_subsystem(struct configfs_subsystem *subsys);
 	void configfs_unregister_subsystem(struct configfs_subsystem *subsys);
 
-	A subsystem consists of a toplevel config_group and a semaphore.
+	A subsystem consists of a toplevel config_group and a mutex.
 The group is where child config_items are created.  For a subsystem,
 this group is usually defined statically.  Before calling
 configfs_register_subsystem(), the subsystem must have initialized the
 group via the usual group _init() functions, and it must also have
-initialized the semaphore.
+initialized the mutex.
 	When the register call returns, the subsystem is live, and it
 will be visible via configfs.  At that point, mkdir(2) can be called and
 the subsystem must be ready for it.
@@ -303,7 +315,7 @@ subsystem/group and the simple_child item in configfs_example.c  It
 shows a trivial object displaying and storing an attribute, and a simple
 group creating and destroying these children.
 
-[Hierarchy Navigation and the Subsystem Semaphore]
+[Hierarchy Navigation and the Subsystem Mutex]
 
 There is an extra bonus that configfs provides.  The config_groups and
 config_items are arranged in a hierarchy due to the fact that they
@@ -314,19 +326,19 @@ and config_item->ci_parent structure members.
 
 A subsystem can navigate the cg_children list and the ci_parent pointer
 to see the tree created by the subsystem.  This can race with configfs'
-management of the hierarchy, so configfs uses the subsystem semaphore to
+management of the hierarchy, so configfs uses the subsystem mutex to
 protect modifications.  Whenever a subsystem wants to navigate the
 hierarchy, it must do so under the protection of the subsystem
-semaphore.
+mutex.
 
-A subsystem will be prevented from acquiring the semaphore while a newly
+A subsystem will be prevented from acquiring the mutex while a newly
 allocated item has not been linked into this hierarchy.   Similarly, it
-will not be able to acquire the semaphore while a dropping item has not
+will not be able to acquire the mutex while a dropping item has not
 yet been unlinked.  This means that an item's ci_parent pointer will
 never be NULL while the item is in configfs, and that an item will only
 be in its parent's cg_children list for the same duration.  This allows
 a subsystem to trust ci_parent and cg_children while they hold the
-semaphore.
+mutex.
 
 [Item Aggregation Via symlink(2)]
 
@@ -386,6 +398,33 @@ As a consequence of this, default_groups cannot be removed directly via
 rmdir(2).  They also are not considered when rmdir(2) on the parent
 group is checking for children.
 
+[Dependant Subsystems]
+
+Sometimes other drivers depend on particular configfs items.  For
+example, ocfs2 mounts depend on a heartbeat region item.  If that
+region item is removed with rmdir(2), the ocfs2 mount must BUG or go
+readonly.  Not happy.
+
+configfs provides two additional API calls: configfs_depend_item() and
+configfs_undepend_item().  A client driver can call
+configfs_depend_item() on an existing item to tell configfs that it is
+depended on.  configfs will then return -EBUSY from rmdir(2) for that
+item.  When the item is no longer depended on, the client driver calls
+configfs_undepend_item() on it.
+
+These API cannot be called underneath any configfs callbacks, as
+they will conflict.  They can block and allocate.  A client driver
+probably shouldn't calling them of its own gumption.  Rather it should
+be providing an API that external subsystems call.
+
+How does this work?  Imagine the ocfs2 mount process.  When it mounts,
+it asks for a heartbeat region item.  This is done via a call into the
+heartbeat code.  Inside the heartbeat code, the region item is looked
+up.  Here, the heartbeat code calls configfs_depend_item().  If it
+succeeds, then heartbeat knows the region is safe to give to ocfs2.
+If it fails, it was being torn down anyway, and heartbeat can gracefully
+pass up an error.
+
 [Committable Items]
 
 NOTE: Committable items are currently unimplemented.

Documentation/filesystems/configfs/configfs_example.c

@@ -453,7 +453,7 @@ static int __init configfs_example_init(void)
 		subsys = example_subsys[i];
 
 		config_group_init(&subsys->su_group);
-		init_MUTEX(&subsys->su_sem);
+		mutex_init(&subsys->su_mutex);
 		ret = configfs_register_subsystem(subsys);
 		if (ret) {
 			printk(KERN_ERR "Error %d while registering subsystem %s\n",

fs/configfs/configfs_internal.h

@@ -29,6 +29,7 @@
 
 struct configfs_dirent {
 	atomic_t		s_count;
+	int			s_dependent_count;
 	struct list_head	s_sibling;
 	struct list_head	s_children;
 	struct list_head	s_links;

fs/configfs/dir.c

@@ -355,6 +355,10 @@ static int configfs_detach_prep(struct dentry *dentry)
 			/* Mark that we've taken i_mutex */
 			sd->s_type |= CONFIGFS_USET_DROPPING;
 
+			/*
+			 * Yup, recursive.  If there's a problem, blame
+			 * deep nesting of default_groups
+			 */
 			ret = configfs_detach_prep(sd->s_dentry);
 			if (!ret)
 				continue;
@@ -562,7 +566,7 @@ static int populate_groups(struct config_group *group)
 
 /*
  * All of link_obj/unlink_obj/link_group/unlink_group require that
- * subsys->su_sem is held.
+ * subsys->su_mutex is held.
  */
 
 static void unlink_obj(struct config_item *item)
@@ -713,6 +717,28 @@ static void configfs_detach_group(struct config_item *item)
 	configfs_detach_item(item);
 }
 
+/*
+ * After the item has been detached from the filesystem view, we are
+ * ready to tear it out of the hierarchy.  Notify the client before
+ * we do that so they can perform any cleanup that requires
+ * navigating the hierarchy.  A client does not need to provide this
+ * callback.  The subsystem semaphore MUST be held by the caller, and
+ * references must be valid for both items.  It also assumes the
+ * caller has validated ci_type.
+ */
+static void client_disconnect_notify(struct config_item *parent_item,
+				     struct config_item *item)
+{
+	struct config_item_type *type;
+
+	type = parent_item->ci_type;
+	BUG_ON(!type);
+
+	if (type->ct_group_ops && type->ct_group_ops->disconnect_notify)
+		type->ct_group_ops->disconnect_notify(to_config_group(parent_item),
+						      item);
+}
+
 /*
  * Drop the initial reference from make_item()/make_group()
  * This function assumes that reference is held on item
@@ -738,6 +764,239 @@ static void client_drop_item(struct config_item *parent_item,
 		config_item_put(item);
 }
 
+#ifdef DEBUG
+static void configfs_dump_one(struct configfs_dirent *sd, int level)
+{
+	printk(KERN_INFO "%*s\"%s\":\n", level, " ", configfs_get_name(sd));
+
+#define type_print(_type) if (sd->s_type & _type) printk(KERN_INFO "%*s %s\n", level, " ", #_type);
+	type_print(CONFIGFS_ROOT);
+	type_print(CONFIGFS_DIR);
+	type_print(CONFIGFS_ITEM_ATTR);
+	type_print(CONFIGFS_ITEM_LINK);
+	type_print(CONFIGFS_USET_DIR);
+	type_print(CONFIGFS_USET_DEFAULT);
+	type_print(CONFIGFS_USET_DROPPING);
+#undef type_print
+}
+
+static int configfs_dump(struct configfs_dirent *sd, int level)
+{
+	struct configfs_dirent *child_sd;
+	int ret = 0;
+
+	configfs_dump_one(sd, level);
+
+	if (!(sd->s_type & (CONFIGFS_DIR|CONFIGFS_ROOT)))
+		return 0;
+
+	list_for_each_entry(child_sd, &sd->s_children, s_sibling) {
+		ret = configfs_dump(child_sd, level + 2);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+#endif
+
+
+/*
+ * configfs_depend_item() and configfs_undepend_item()
+ *
+ * WARNING: Do not call these from a configfs callback!
+ *
+ * This describes these functions and their helpers.
+ *
+ * Allow another kernel system to depend on a config_item.  If this
+ * happens, the item cannot go away until the dependant can live without
+ * it.  The idea is to give client modules as simple an interface as
+ * possible.  When a system asks them to depend on an item, they just
+ * call configfs_depend_item().  If the item is live and the client
+ * driver is in good shape, we'll happily do the work for them.
+ *
+ * Why is the locking complex?  Because configfs uses the VFS to handle
+ * all locking, but this function is called outside the normal
+ * VFS->configfs path.  So it must take VFS locks to prevent the
+ * VFS->configfs stuff (configfs_mkdir(), configfs_rmdir(), etc).  This is
+ * why you can't call these functions underneath configfs callbacks.
+ *
+ * Note, btw, that this can be called at *any* time, even when a configfs
+ * subsystem isn't registered, or when configfs is loading or unloading.
+ * Just like configfs_register_subsystem().  So we take the same
+ * precautions.  We pin the filesystem.  We lock each i_mutex _in_order_
+ * on our way down the tree.  If we can find the target item in the
+ * configfs tree, it must be part of the subsystem tree as well, so we
+ * do not need the subsystem semaphore.  Holding the i_mutex chain locks
+ * out mkdir() and rmdir(), who might be racing us.
+ */
+
+/*
+ * configfs_depend_prep()
+ *
+ * Only subdirectories count here.  Files (CONFIGFS_NOT_PINNED) are
+ * attributes.  This is similar but not the same to configfs_detach_prep().
+ * Note that configfs_detach_prep() expects the parent to be locked when it
+ * is called, but we lock the parent *inside* configfs_depend_prep().  We
+ * do that so we can unlock it if we find nothing.
+ *
+ * Here we do a depth-first search of the dentry hierarchy looking for
+ * our object.  We take i_mutex on each step of the way down.  IT IS
+ * ESSENTIAL THAT i_mutex LOCKING IS ORDERED.  If we come back up a branch,
+ * we'll drop the i_mutex.
+ *
+ * If the target is not found, -ENOENT is bubbled up and we have released
+ * all locks.  If the target was found, the locks will be cleared by
+ * configfs_depend_rollback().
+ *
+ * This adds a requirement that all config_items be unique!
+ *
+ * This is recursive because the locking traversal is tricky.  There isn't
+ * much on the stack, though, so folks that need this function - be careful
+ * about your stack!  Patches will be accepted to make it iterative.
+ */
+static int configfs_depend_prep(struct dentry *origin,
+				struct config_item *target)
+{
+	struct configfs_dirent *child_sd, *sd = origin->d_fsdata;
+	int ret = 0;
+
+	BUG_ON(!origin || !sd);
+
+	/* Lock this guy on the way down */
+	mutex_lock(&sd->s_dentry->d_inode->i_mutex);
+	if (sd->s_element == target)  /* Boo-yah */
+		goto out;
+
+	list_for_each_entry(child_sd, &sd->s_children, s_sibling) {
+		if (child_sd->s_type & CONFIGFS_DIR) {
+			ret = configfs_depend_prep(child_sd->s_dentry,
+						   target);
+			if (!ret)
+				goto out;  /* Child path boo-yah */
+		}
+	}
+
+	/* We looped all our children and didn't find target */
+	mutex_unlock(&sd->s_dentry->d_inode->i_mutex);
+	ret = -ENOENT;
+
+out:
+	return ret;
+}
+
+/*
+ * This is ONLY called if configfs_depend_prep() did its job.  So we can
+ * trust the entire path from item back up to origin.
+ *
+ * We walk backwards from item, unlocking each i_mutex.  We finish by
+ * unlocking origin.
+ */
+static void configfs_depend_rollback(struct dentry *origin,
+				     struct config_item *item)
+{
+	struct dentry *dentry = item->ci_dentry;
+
+	while (dentry != origin) {
+		mutex_unlock(&dentry->d_inode->i_mutex);
+		dentry = dentry->d_parent;
+	}
+
+	mutex_unlock(&origin->d_inode->i_mutex);
+}
+
+int configfs_depend_item(struct configfs_subsystem *subsys,
+			 struct config_item *target)
+{
+	int ret;
+	struct configfs_dirent *p, *root_sd, *subsys_sd = NULL;
+	struct config_item *s_item = &subsys->su_group.cg_item;
+
+	/*
+	 * Pin the configfs filesystem.  This means we can safely access
+	 * the root of the configfs filesystem.
+	 */
+	ret = configfs_pin_fs();
+	if (ret)
+		return ret;
+
+	/*
+	 * Next, lock the root directory.  We're going to check that the
+	 * subsystem is really registered, and so we need to lock out
+	 * configfs_[un]register_subsystem().
+	 */
+	mutex_lock(&configfs_sb->s_root->d_inode->i_mutex);
+
+	root_sd = configfs_sb->s_root->d_fsdata;
+
+	list_for_each_entry(p, &root_sd->s_children, s_sibling) {
+		if (p->s_type & CONFIGFS_DIR) {
+			if (p->s_element == s_item) {
+				subsys_sd = p;
+				break;
+			}
+		}
+	}
+
+	if (!subsys_sd) {
+		ret = -ENOENT;
+		goto out_unlock_fs;
+	}
+
+	/* Ok, now we can trust subsys/s_item */
+
+	/* Scan the tree, locking i_mutex recursively, return 0 if found */
+	ret = configfs_depend_prep(subsys_sd->s_dentry, target);
+	if (ret)
+		goto out_unlock_fs;
+
+	/* We hold all i_mutexes from the subsystem down to the target */
+	p = target->ci_dentry->d_fsdata;
+	p->s_dependent_count += 1;
+
+	configfs_depend_rollback(subsys_sd->s_dentry, target);
+
+out_unlock_fs:
+	mutex_unlock(&configfs_sb->s_root->d_inode->i_mutex);
+
+	/*
+	 * If we succeeded, the fs is pinned via other methods.  If not,
+	 * we're done with it anyway.  So release_fs() is always right.
+	 */
+	configfs_release_fs();
+
+	return ret;
+}
+EXPORT_SYMBOL(configfs_depend_item);
+
+/*
+ * Release the dependent linkage.  This is much simpler than
+ * configfs_depend_item() because we know that that the client driver is
+ * pinned, thus the subsystem is pinned, and therefore configfs is pinned.
+ */
+void configfs_undepend_item(struct configfs_subsystem *subsys,
+			    struct config_item *target)
+{
+	struct configfs_dirent *sd;
+
+	/*
+	 * Since we can trust everything is pinned, we just need i_mutex
+	 * on the item.
+	 */
+	mutex_lock(&target->ci_dentry->d_inode->i_mutex);
+
+	sd = target->ci_dentry->d_fsdata;
+	BUG_ON(sd->s_dependent_count < 1);
+
+	sd->s_dependent_count -= 1;
+
+	/*
+	 * After this unlock, we cannot trust the item to stay alive!
+	 * DO NOT REFERENCE item after this unlock.
+	 */
+	mutex_unlock(&target->ci_dentry->d_inode->i_mutex);
+}
+EXPORT_SYMBOL(configfs_undepend_item);
 
 static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
@@ -783,7 +1042,7 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
 	snprintf(name, dentry->d_name.len + 1, "%s", dentry->d_name.name);
 
-	down(&subsys->su_sem);
+	mutex_lock(&subsys->su_mutex);
 	group = NULL;
 	item = NULL;
 	if (type->ct_group_ops->make_group) {
@@ -797,7 +1056,7 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 		if (item)
 			link_obj(parent_item, item);
 	}
-	up(&subsys->su_sem);
+	mutex_unlock(&subsys->su_mutex);
 
 	kfree(name);
 	if (!item) {
@@ -841,13 +1100,16 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 out_unlink:
 	if (ret) {
 		/* Tear down everything we built up */
-		down(&subsys->su_sem);
+		mutex_lock(&subsys->su_mutex);
+
+		client_disconnect_notify(parent_item, item);
 		if (group)
 			unlink_group(group);
 		else
 			unlink_obj(item);
 		client_drop_item(parent_item, item);
-		up(&subsys->su_sem);
+
+		mutex_unlock(&subsys->su_mutex);
 
 		if (module_got)
 			module_put(owner);
@@ -881,6 +1143,13 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (sd->s_type & CONFIGFS_USET_DEFAULT)
 		return -EPERM;
 
+	/*
+	 * Here's where we check for dependents.  We're protected by
+	 * i_mutex.
+	 */
+	if (sd->s_dependent_count)
+		return -EBUSY;
+
 	/* Get a working ref until we have the child */
 	parent_item = configfs_get_config_item(dentry->d_parent);
 	subsys = to_config_group(parent_item)->cg_subsys;
@@ -910,17 +1179,19 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (sd->s_type & CONFIGFS_USET_DIR) {
 		configfs_detach_group(item);
 
-		down(&subsys->su_sem);
+		mutex_lock(&subsys->su_mutex);
+		client_disconnect_notify(parent_item, item);
 		unlink_group(to_config_group(item));
 	} else {
 		configfs_detach_item(item);
 
-		down(&subsys->su_sem);
+		mutex_lock(&subsys->su_mutex);
+		client_disconnect_notify(parent_item, item);
 		unlink_obj(item);
 	}
 
 	client_drop_item(parent_item, item);
-	up(&subsys->su_sem);
+	mutex_unlock(&subsys->su_mutex);
 
 	/* Drop our reference from above */
 	config_item_put(item);

fs/configfs/file.c

@@ -27,19 +27,26 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
-#include <asm/semaphore.h>
 
 #include <linux/configfs.h>
 #include "configfs_internal.h"
 
+/*
+ * A simple attribute can only be 4096 characters.  Why 4k?  Because the
+ * original code limited it to PAGE_SIZE.  That's a bad idea, though,
+ * because an attribute of 16k on ia64 won't work on x86.  So we limit to
+ * 4k, our minimum common page size.
+ */
+#define SIMPLE_ATTR_SIZE 4096
 
 struct configfs_buffer {
 	size_t			count;
 	loff_t			pos;
 	char			* page;
 	struct configfs_item_operations	* ops;
-	struct semaphore	sem;
+	struct mutex		mutex;
 	int			needs_read_fill;
 };
 
@@ -69,7 +76,7 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf
 
 	count = ops->show_attribute(item,attr,buffer->page);
 	buffer->needs_read_fill = 0;
-	BUG_ON(count > (ssize_t)PAGE_SIZE);
+	BUG_ON(count > (ssize_t)SIMPLE_ATTR_SIZE);
 	if (count >= 0)
 		buffer->count = count;
 	else
@@ -102,7 +109,7 @@ configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *pp
 	struct configfs_buffer * buffer = file->private_data;
 	ssize_t retval = 0;
 
-	down(&buffer->sem);
+	mutex_lock(&buffer->mutex);
 	if (buffer->needs_read_fill) {
 		if ((retval = fill_read_buffer(file->f_path.dentry,buffer)))
 			goto out;
@@ -112,7 +119,7 @@ configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *pp
 	retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
 					 buffer->count);
 out:
-	up(&buffer->sem);
+	mutex_unlock(&buffer->mutex);
 	return retval;
 }
 
@@ -137,8 +144,8 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size
 	if (!buffer->page)
 		return -ENOMEM;
 
-	if (count >= PAGE_SIZE)
-		count = PAGE_SIZE - 1;
+	if (count >= SIMPLE_ATTR_SIZE)
+		count = SIMPLE_ATTR_SIZE - 1;
 	error = copy_from_user(buffer->page,buf,count);
 	buffer->needs_read_fill = 1;
 	/* if buf is assumed to contain a string, terminate it by \0,
@@ -193,13 +200,13 @@ configfs_write_file(struct file *file, const char __user *buf, size_t count, lof
 	struct configfs_buffer * buffer = file->private_data;
 	ssize_t len;
 
-	down(&buffer->sem);
+	mutex_lock(&buffer->mutex);
 	len = fill_write_buffer(buffer, buf, count);
 	if (len > 0)
 		len = flush_write_buffer(file->f_path.dentry, buffer, count);
 	if (len > 0)
 		*ppos += len;
-	up(&buffer->sem);
+	mutex_unlock(&buffer->mutex);
 	return len;
 }
 
@@ -253,7 +260,7 @@ static int check_perm(struct inode * inode, struct file * file)
 		error = -ENOMEM;
 		goto Enomem;
 	}
-	init_MUTEX(&buffer->sem);
+	mutex_init(&buffer->mutex);
 	buffer->needs_read_fill = 1;
 	buffer->ops = ops;
 	file->private_data = buffer;
@@ -292,6 +299,7 @@ static int configfs_release(struct inode * inode, struct file * filp)
 	if (buffer) {
 		if (buffer->page)
 			free_page((unsigned long)buffer->page);
+		mutex_destroy(&buffer->mutex);
 		kfree(buffer);
 	}
 	return 0;

fs/configfs/item.c

@@ -62,7 +62,6 @@ void config_item_init(struct config_item * item)
  *	dynamically allocated string that @item->ci_name points to.
  *	Otherwise, use the static @item->ci_namebuf array.
  */
-
 int config_item_set_name(struct config_item * item, const char * fmt, ...)
 {
 	int error = 0;
@@ -139,12 +138,7 @@ struct config_item * config_item_get(struct config_item * item)
 	return item;
 }
 
-/**
- *	config_item_cleanup - free config_item resources.
- *	@item:	item.
- */
-
-void config_item_cleanup(struct config_item * item)
+static void config_item_cleanup(struct config_item * item)
 {
 	struct config_item_type * t = item->ci_type;
 	struct config_group * s = item->ci_group;
@@ -179,35 +173,31 @@ void config_item_put(struct config_item * item)
 		kref_put(&item->ci_kref, config_item_release);
 }
 
-
 /**
  *	config_group_init - initialize a group for use
  *	@k:	group
  */
-
 void config_group_init(struct config_group *group)
 {
 	config_item_init(&group->cg_item);
 	INIT_LIST_HEAD(&group->cg_children);
 }
 
-
 /**
- *	config_group_find_obj - search for item in group.
+ *	config_group_find_item - search for item in group.
  *	@group:	group we're looking in.
  *	@name:	item's name.
  *
- *	Lock group via @group->cg_subsys, and iterate over @group->cg_list,
- *	looking for a matching config_item. If matching item is found
- *	take a reference and return the item.
+ *	Iterate over @group->cg_list, looking for a matching config_item.
+ *	If matching item is found take a reference and return the item.
+ *	Caller must have locked group via @group->cg_subsys->su_mtx.
  */
-
-struct config_item * config_group_find_obj(struct config_group * group, const char * name)
+struct config_item *config_group_find_item(struct config_group *group,
+					   const char *name)
 {
 	struct list_head * entry;
 	struct config_item * ret = NULL;
 
-        /* XXX LOCKING! */
 	list_for_each(entry,&group->cg_children) {
 		struct config_item * item = to_item(entry);
 		if (config_item_name(item) &&
@@ -219,9 +209,8 @@ struct config_item * config_group_find_obj(struct config_group * group, const ch
 	return ret;
 }
 
-
 EXPORT_SYMBOL(config_item_init);
 EXPORT_SYMBOL(config_group_init);
 EXPORT_SYMBOL(config_item_get);
 EXPORT_SYMBOL(config_item_put);
-EXPORT_SYMBOL(config_group_find_obj);
+EXPORT_SYMBOL(config_group_find_item);

fs/dlm/config.c

@@ -133,14 +133,6 @@ static ssize_t cluster_set(struct cluster *cl, unsigned int *cl_field,
 	return len;
 }
 
-#define __CONFIGFS_ATTR(_name,_mode,_read,_write) {                           \
-	.attr   = { .ca_name = __stringify(_name),                            \
-		    .ca_mode = _mode,                                         \
-		    .ca_owner = THIS_MODULE },                                \
-	.show   = _read,                                                      \
-	.store  = _write,                                                     \
-}
-
 #define CLUSTER_ATTR(name, check_zero)                                        \
 static ssize_t name##_write(struct cluster *cl, const char *buf, size_t len)  \
 {                                                                             \
@@ -615,7 +607,7 @@ static struct clusters clusters_root = {
 int dlm_config_init(void)
 {
 	config_group_init(&clusters_root.subsys.su_group);
-	init_MUTEX(&clusters_root.subsys.su_sem);
+	mutex_init(&clusters_root.subsys.su_mutex);
 	return configfs_register_subsystem(&clusters_root.subsys);
 }
 
@@ -759,9 +751,9 @@ static struct space *get_space(char *name)
 	if (!space_list)
 		return NULL;
 
-	down(&space_list->cg_subsys->su_sem);
-	i = config_group_find_obj(space_list, name);
-	up(&space_list->cg_subsys->su_sem);
+	mutex_lock(&space_list->cg_subsys->su_mutex);
+	i = config_group_find_item(space_list, name);
+	mutex_unlock(&space_list->cg_subsys->su_mutex);
 
 	return to_space(i);
 }
@@ -780,7 +772,7 @@ static struct comm *get_comm(int nodeid, struct sockaddr_storage *addr)
 	if (!comm_list)
 		return NULL;
 
-	down(&clusters_root.subsys.su_sem);
+	mutex_lock(&clusters_root.subsys.su_mutex);
 
 	list_for_each_entry(i, &comm_list->cg_children, ci_entry) {
 		cm = to_comm(i);
@@ -800,7 +792,7 @@ static struct comm *get_comm(int nodeid, struct sockaddr_storage *addr)
 			break;
 		}
 	}
-	up(&clusters_root.subsys.su_sem);
+	mutex_unlock(&clusters_root.subsys.su_mutex);
 
 	if (!found)
 		cm = NULL;

fs/ocfs2/alloc.h

@@ -34,7 +34,17 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
 			u32 cpos,
 			u64 start_blk,
 			u32 new_clusters,
+			u8 flags,
 			struct ocfs2_alloc_context *meta_ac);
+struct ocfs2_cached_dealloc_ctxt;
+int ocfs2_mark_extent_written(struct inode *inode, struct buffer_head *di_bh,
+			      handle_t *handle, u32 cpos, u32 len, u32 phys,
+			      struct ocfs2_alloc_context *meta_ac,
+			      struct ocfs2_cached_dealloc_ctxt *dealloc);
+int ocfs2_remove_extent(struct inode *inode, struct buffer_head *di_bh,
+			u32 cpos, u32 len, handle_t *handle,
+			struct ocfs2_alloc_context *meta_ac,
+			struct ocfs2_cached_dealloc_ctxt *dealloc);
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
 			   struct inode *inode,
 			   struct ocfs2_dinode *fe);
@@ -62,17 +72,41 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb,
 				      struct ocfs2_dinode **tl_copy);
 int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
 					 struct ocfs2_dinode *tl_copy);
+int ocfs2_truncate_log_needs_flush(struct ocfs2_super *osb);
+int ocfs2_truncate_log_append(struct ocfs2_super *osb,
+			      handle_t *handle,
+			      u64 start_blk,
+			      unsigned int num_clusters);
+int __ocfs2_flush_truncate_log(struct ocfs2_super *osb);
+
+/*
+ * Process local structure which describes the block unlinks done
+ * during an operation. This is populated via
+ * ocfs2_cache_block_dealloc().
+ *
+ * ocfs2_run_deallocs() should be called after the potentially
+ * de-allocating routines. No journal handles should be open, and most
+ * locks should have been dropped.
+ */
+struct ocfs2_cached_dealloc_ctxt {
+	struct ocfs2_per_slot_free_list		*c_first_suballocator;
+};
+static inline void ocfs2_init_dealloc_ctxt(struct ocfs2_cached_dealloc_ctxt *c)
+{
+	c->c_first_suballocator = NULL;
+}
+int ocfs2_run_deallocs(struct ocfs2_super *osb,
+		       struct ocfs2_cached_dealloc_ctxt *ctxt);
 
 struct ocfs2_truncate_context {
-	struct inode *tc_ext_alloc_inode;
-	struct buffer_head *tc_ext_alloc_bh;
+	struct ocfs2_cached_dealloc_ctxt tc_dealloc;
 	int tc_ext_alloc_locked; /* is it cluster locked? */
 	/* these get destroyed once it's passed to ocfs2_commit_truncate. */
 	struct buffer_head *tc_last_eb_bh;
 };
 
-int ocfs2_zero_tail_for_truncate(struct inode *inode, handle_t *handle,
-				 u64 new_i_size);
+int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
+				  u64 range_start, u64 range_end);
 int ocfs2_prepare_truncate(struct ocfs2_super *osb,
 			   struct inode *inode,
 			   struct buffer_head *fe_bh,
@@ -84,6 +118,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 
 int ocfs2_find_leaf(struct inode *inode, struct ocfs2_extent_list *root_el,
 		    u32 cpos, struct buffer_head **leaf_bh);
+int ocfs2_search_extent_list(struct ocfs2_extent_list *el, u32 v_cluster);
 
 /*
  * Helper function to look at the # of clusters in an extent record.

fs/ocfs2/aops.h

@@ -42,57 +42,22 @@ int walk_page_buffers(	handle_t *handle,
 			int (*fn)(	handle_t *handle,
 					struct buffer_head *bh));
 
-struct ocfs2_write_ctxt;
-typedef int (ocfs2_page_writer)(struct inode *, struct ocfs2_write_ctxt *,
-				u64 *, unsigned int *, unsigned int *);
+int ocfs2_write_begin(struct file *file, struct address_space *mapping,
+		      loff_t pos, unsigned len, unsigned flags,
+		      struct page **pagep, void **fsdata);
 
-ssize_t ocfs2_buffered_write_cluster(struct file *file, loff_t pos,
-				     size_t count, ocfs2_page_writer *actor,
-				     void *priv);
+int ocfs2_write_end(struct file *file, struct address_space *mapping,
+		    loff_t pos, unsigned len, unsigned copied,
+		    struct page *page, void *fsdata);
 
-struct ocfs2_write_ctxt {
-	size_t				w_count;
-	loff_t				w_pos;
-	u32				w_cpos;
-	unsigned int			w_finished_copy;
+int ocfs2_write_end_nolock(struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied,
+			   struct page *page, void *fsdata);
 
-	/* This is true if page_size > cluster_size */
-	unsigned int			w_large_pages;
-
-	/* Filler callback and private data */
-	ocfs2_page_writer		*w_write_data_page;
-	void				*w_private;
-
-	/* Only valid for the filler callback */
-	struct page			*w_this_page;
-	unsigned int			w_this_page_new;
-};
-
-struct ocfs2_buffered_write_priv {
-	char				*b_src_buf;
-	const struct iovec		*b_cur_iov; /* Current iovec */
-	size_t				b_cur_off; /* Offset in the
-						    * current iovec */
-};
-int ocfs2_map_and_write_user_data(struct inode *inode,
-				  struct ocfs2_write_ctxt *wc,
-				  u64 *p_blkno,
-				  unsigned int *ret_from,
-				  unsigned int *ret_to);
-
-struct ocfs2_splice_write_priv {
-	struct splice_desc		*s_sd;
-	struct pipe_buffer		*s_buf;
-	struct pipe_inode_info		*s_pipe;
-	/* Neither offset value is ever larger than one page */
-	unsigned int			s_offset;
-	unsigned int			s_buf_offset;
-};
-int ocfs2_map_and_write_splice_data(struct inode *inode,
-				    struct ocfs2_write_ctxt *wc,
-				    u64 *p_blkno,
-				    unsigned int *ret_from,
-				    unsigned int *ret_to);
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, unsigned flags,
+			     struct page **pagep, void **fsdata,
+			     struct buffer_head *di_bh, struct page *mmap_page);
 
 /* all ocfs2_dio_end_io()'s fault */
 #define ocfs2_iocb_is_rw_locked(iocb) \

fs/ocfs2/cluster/heartbeat.c

@@ -1335,6 +1335,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	ret = wait_event_interruptible(o2hb_steady_queue,
 				atomic_read(&reg->hr_steady_iterations) == 0);
 	if (ret) {
+		/* We got interrupted (hello ptrace!).  Clean up */
 		spin_lock(&o2hb_live_lock);
 		hb_task = reg->hr_task;
 		reg->hr_task = NULL;
@@ -1345,7 +1346,16 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		goto out;
 	}
 
+	/* Ok, we were woken.  Make sure it wasn't by drop_item() */
+	spin_lock(&o2hb_live_lock);
+	hb_task = reg->hr_task;
+	spin_unlock(&o2hb_live_lock);
+
+	if (hb_task)
 		ret = count;
+	else
+		ret = -EIO;
+
 out:
 	if (filp)
 		fput(filp);
@@ -1523,6 +1533,15 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
 	if (hb_task)
 		kthread_stop(hb_task);
 
+	/*
+	 * If we're racing a dev_write(), we need to wake them.  They will
+	 * check reg->hr_task
+	 */
+	if (atomic_read(&reg->hr_steady_iterations) != 0) {
+		atomic_set(&reg->hr_steady_iterations, 0);
+		wake_up(&o2hb_steady_queue);
+	}
+
 	config_item_put(item);
 }
 
@@ -1665,7 +1684,67 @@ void o2hb_setup_callback(struct o2hb_callback_func *hc,
 }
 EXPORT_SYMBOL_GPL(o2hb_setup_callback);
 
-int o2hb_register_callback(struct o2hb_callback_func *hc)
+static struct o2hb_region *o2hb_find_region(const char *region_uuid)
+{
+	struct o2hb_region *p, *reg = NULL;
+
+	assert_spin_locked(&o2hb_live_lock);
+
+	list_for_each_entry(p, &o2hb_all_regions, hr_all_item) {
+		if (!strcmp(region_uuid, config_item_name(&p->hr_item))) {
+			reg = p;
+			break;
+		}
+	}
+
+	return reg;
+}
+
+static int o2hb_region_get(const char *region_uuid)
+{
+	int ret = 0;
+	struct o2hb_region *reg;
+
+	spin_lock(&o2hb_live_lock);
+
+	reg = o2hb_find_region(region_uuid);
+	if (!reg)
+		ret = -ENOENT;
+	spin_unlock(&o2hb_live_lock);
+
+	if (ret)
+		goto out;
+
+	ret = o2nm_depend_this_node();
+	if (ret)
+		goto out;
+
+	ret = o2nm_depend_item(&reg->hr_item);
+	if (ret)
+		o2nm_undepend_this_node();
+
+out:
+	return ret;
+}
+
+static void o2hb_region_put(const char *region_uuid)
+{
+	struct o2hb_region *reg;
+
+	spin_lock(&o2hb_live_lock);
+
+	reg = o2hb_find_region(region_uuid);
+
+	spin_unlock(&o2hb_live_lock);
+
+	if (reg) {
+		o2nm_undepend_item(&reg->hr_item);
+		o2nm_undepend_this_node();
+	}
+}
+
+int o2hb_register_callback(const char *region_uuid,
+			   struct o2hb_callback_func *hc)
 {
 	struct o2hb_callback_func *tmp;
 	struct list_head *iter;
@@ -1681,6 +1760,12 @@ int o2hb_register_callback(struct o2hb_callback_func *hc)
 		goto out;
 	}
 
+	if (region_uuid) {
+		ret = o2hb_region_get(region_uuid);
+		if (ret)
+			goto out;
+	}
+
 	down_write(&o2hb_callback_sem);
 
 	list_for_each(iter, &hbcall->list) {
@@ -1702,16 +1787,21 @@ int o2hb_register_callback(struct o2hb_callback_func *hc)
 }
 EXPORT_SYMBOL_GPL(o2hb_register_callback);
 
-void o2hb_unregister_callback(struct o2hb_callback_func *hc)
+void o2hb_unregister_callback(const char *region_uuid,
+			      struct o2hb_callback_func *hc)
 {
 	BUG_ON(hc->hc_magic != O2HB_CB_MAGIC);
 
 	mlog(ML_HEARTBEAT, "on behalf of %p for funcs %p\n",
 	     __builtin_return_address(0), hc);
 
+	/* XXX Can this happen _with_ a region reference? */
 	if (list_empty(&hc->hc_item))
 		return;
 
+	if (region_uuid)
+		o2hb_region_put(region_uuid);
+
 	down_write(&o2hb_callback_sem);
 
 	list_del_init(&hc->hc_item);

fs/ocfs2/cluster/heartbeat.h

@@ -69,8 +69,10 @@ void o2hb_setup_callback(struct o2hb_callback_func *hc,
 			 o2hb_cb_func *func,
 			 void *data,
 			 int priority);
-int o2hb_register_callback(struct o2hb_callback_func *hc);
-void o2hb_unregister_callback(struct o2hb_callback_func *hc);
+int o2hb_register_callback(const char *region_uuid,
+			   struct o2hb_callback_func *hc);
+void o2hb_unregister_callback(const char *region_uuid,
+			      struct o2hb_callback_func *hc);
 void o2hb_fill_node_map(unsigned long *map,
 			unsigned bytes);
 void o2hb_init(void);

fs/ocfs2/cluster/nodemanager.h

@@ -77,4 +77,9 @@ struct o2nm_node *o2nm_get_node_by_ip(__be32 addr);
 void o2nm_node_get(struct o2nm_node *node);
 void o2nm_node_put(struct o2nm_node *node);
 
+int o2nm_depend_item(struct config_item *item);
+void o2nm_undepend_item(struct config_item *item);
+int o2nm_depend_this_node(void);
+void o2nm_undepend_this_node(void);
+
 #endif /* O2CLUSTER_NODEMANAGER_H */