Adding upstream version 4.19.249.upstream/4.19.249

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

15 files changed, 6266 insertions, 0 deletions

diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig
new file mode 100644
index 000000000..3f6dfa989
--- /dev/null
+++ b/fs/fscache/Kconfig
@@ -0,0 +1,61 @@
+
+config FSCACHE
+	tristate "General filesystem local caching manager"
+	help
+	  This option enables a generic filesystem caching manager that can be
+	  used by various network and other filesystems to cache data locally.
+	  Different sorts of caches can be plugged in, depending on the
+	  resources available.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_STATS
+	bool "Gather statistical information on local caching"
+	depends on FSCACHE && PROC_FS
+	help
+	  This option causes statistical information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/stats
+
+	  The gathering of statistics adds a certain amount of overhead to
+	  execution as there are a quite a few stats gathered, and on a
+	  multi-CPU system these may be on cachelines that keep bouncing
+	  between CPUs.  On the other hand, the stats are very useful for
+	  debugging purposes.  Saying 'Y' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_HISTOGRAM
+	bool "Gather latency information on local caching"
+	depends on FSCACHE && PROC_FS
+	help
+	  This option causes latency information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/histogram
+
+	  The generation of this histogram adds a certain amount of overhead to
+	  execution as there are a number of points at which data is gathered,
+	  and on a multi-CPU system these may be on cachelines that keep
+	  bouncing between CPUs.  On the other hand, the histogram may be
+	  useful for debugging purposes.  Saying 'N' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_DEBUG
+	bool "Debug FS-Cache"
+	depends on FSCACHE
+	help
+	  This permits debugging to be dynamically enabled in the local caching
+	  management module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_OBJECT_LIST
+	bool "Maintain global object list for debugging purposes"
+	depends on FSCACHE && PROC_FS
+	help
+	  Maintain a global list of active fscache objects that can be
+	  retrieved through /proc/fs/fscache/objects for debugging purposes
diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile
new file mode 100644
index 000000000..79e08e05e
--- /dev/null
+++ b/fs/fscache/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for general filesystem caching code
+#
+
+fscache-y := \
+	cache.o \
+	cookie.o \
+	fsdef.o \
+	main.o \
+	netfs.o \
+	object.o \
+	operation.o \
+	page.o
+
+fscache-$(CONFIG_PROC_FS) += proc.o
+fscache-$(CONFIG_FSCACHE_STATS) += stats.o
+fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o
+fscache-$(CONFIG_FSCACHE_OBJECT_LIST) += object-list.o
+
+obj-$(CONFIG_FSCACHE) := fscache.o
diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
new file mode 100644
index 000000000..cdcb376ef
--- /dev/null
+++ b/fs/fscache/cache.c
@@ -0,0 +1,421 @@
+/* FS-Cache cache handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+LIST_HEAD(fscache_cache_list);
+DECLARE_RWSEM(fscache_addremove_sem);
+DECLARE_WAIT_QUEUE_HEAD(fscache_cache_cleared_wq);
+EXPORT_SYMBOL(fscache_cache_cleared_wq);
+
+static LIST_HEAD(fscache_cache_tag_list);
+
+/*
+ * look up a cache tag
+ */
+struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *name)
+{
+	struct fscache_cache_tag *tag, *xtag;
+
+	/* firstly check for the existence of the tag under read lock */
+	down_read(&fscache_addremove_sem);
+
+	list_for_each_entry(tag, &fscache_cache_tag_list, link) {
+		if (strcmp(tag->name, name) == 0) {
+			atomic_inc(&tag->usage);
+			up_read(&fscache_addremove_sem);
+			return tag;
+		}
+	}
+
+	up_read(&fscache_addremove_sem);
+
+	/* the tag does not exist - create a candidate */
+	xtag = kzalloc(sizeof(*xtag) + strlen(name) + 1, GFP_KERNEL);
+	if (!xtag)
+		/* return a dummy tag if out of memory */
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&xtag->usage, 1);
+	strcpy(xtag->name, name);
+
+	/* write lock, search again and add if still not present */
+	down_write(&fscache_addremove_sem);
+
+	list_for_each_entry(tag, &fscache_cache_tag_list, link) {
+		if (strcmp(tag->name, name) == 0) {
+			atomic_inc(&tag->usage);
+			up_write(&fscache_addremove_sem);
+			kfree(xtag);
+			return tag;
+		}
+	}
+
+	list_add_tail(&xtag->link, &fscache_cache_tag_list);
+	up_write(&fscache_addremove_sem);
+	return xtag;
+}
+
+/*
+ * release a reference to a cache tag
+ */
+void __fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+	if (tag != ERR_PTR(-ENOMEM)) {
+		down_write(&fscache_addremove_sem);
+
+		if (atomic_dec_and_test(&tag->usage))
+			list_del_init(&tag->link);
+		else
+			tag = NULL;
+
+		up_write(&fscache_addremove_sem);
+
+		kfree(tag);
+	}
+}
+
+/*
+ * select a cache in which to store an object
+ * - the cache addremove semaphore must be at least read-locked by the caller
+ * - the object will never be an index
+ */
+struct fscache_cache *fscache_select_cache_for_object(
+	struct fscache_cookie *cookie)
+{
+	struct fscache_cache_tag *tag;
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+
+	_enter("");
+
+	if (list_empty(&fscache_cache_list)) {
+		_leave(" = NULL [no cache]");
+		return NULL;
+	}
+
+	/* we check the parent to determine the cache to use */
+	spin_lock(&cookie->lock);
+
+	/* the first in the parent's backing list should be the preferred
+	 * cache */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		object = hlist_entry(cookie->backing_objects.first,
+				     struct fscache_object, cookie_link);
+
+		cache = object->cache;
+		if (fscache_object_is_dying(object) ||
+		    test_bit(FSCACHE_IOERROR, &cache->flags))
+			cache = NULL;
+
+		spin_unlock(&cookie->lock);
+		_leave(" = %p [parent]", cache);
+		return cache;
+	}
+
+	/* the parent is unbacked */
+	if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		/* cookie not an index and is unbacked */
+		spin_unlock(&cookie->lock);
+		_leave(" = NULL [cookie ub,ni]");
+		return NULL;
+	}
+
+	spin_unlock(&cookie->lock);
+
+	if (!cookie->def->select_cache)
+		goto no_preference;
+
+	/* ask the netfs for its preference */
+	tag = cookie->def->select_cache(cookie->parent->netfs_data,
+					cookie->netfs_data);
+	if (!tag)
+		goto no_preference;
+
+	if (tag == ERR_PTR(-ENOMEM)) {
+		_leave(" = NULL [nomem tag]");
+		return NULL;
+	}
+
+	if (!tag->cache) {
+		_leave(" = NULL [unbacked tag]");
+		return NULL;
+	}
+
+	if (test_bit(FSCACHE_IOERROR, &tag->cache->flags))
+		return NULL;
+
+	_leave(" = %p [specific]", tag->cache);
+	return tag->cache;
+
+no_preference:
+	/* netfs has no preference - just select first cache */
+	cache = list_entry(fscache_cache_list.next,
+			   struct fscache_cache, link);
+	_leave(" = %p [first]", cache);
+	return cache;
+}
+
+/**
+ * fscache_init_cache - Initialise a cache record
+ * @cache: The cache record to be initialised
+ * @ops: The cache operations to be installed in that record
+ * @idfmt: Format string to define identifier
+ * @...: sprintf-style arguments
+ *
+ * Initialise a record of a cache and fill in the name.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_init_cache(struct fscache_cache *cache,
+			const struct fscache_cache_ops *ops,
+			const char *idfmt,
+			...)
+{
+	va_list va;
+
+	memset(cache, 0, sizeof(*cache));
+
+	cache->ops = ops;
+
+	va_start(va, idfmt);
+	vsnprintf(cache->identifier, sizeof(cache->identifier), idfmt, va);
+	va_end(va);
+
+	INIT_WORK(&cache->op_gc, fscache_operation_gc);
+	INIT_LIST_HEAD(&cache->link);
+	INIT_LIST_HEAD(&cache->object_list);
+	INIT_LIST_HEAD(&cache->op_gc_list);
+	spin_lock_init(&cache->object_list_lock);
+	spin_lock_init(&cache->op_gc_list_lock);
+}
+EXPORT_SYMBOL(fscache_init_cache);
+
+/**
+ * fscache_add_cache - Declare a cache as being open for business
+ * @cache: The record describing the cache
+ * @ifsdef: The record of the cache object describing the top-level index
+ * @tagname: The tag describing this cache
+ *
+ * Add a cache to the system, making it available for netfs's to use.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+int fscache_add_cache(struct fscache_cache *cache,
+		      struct fscache_object *ifsdef,
+		      const char *tagname)
+{
+	struct fscache_cache_tag *tag;
+
+	ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index);
+	BUG_ON(!cache->ops);
+	BUG_ON(!ifsdef);
+
+	cache->flags = 0;
+	ifsdef->event_mask =
+		((1 << NR_FSCACHE_OBJECT_EVENTS) - 1) &
+		~(1 << FSCACHE_OBJECT_EV_CLEARED);
+	__set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &ifsdef->flags);
+
+	if (!tagname)
+		tagname = cache->identifier;
+
+	BUG_ON(!tagname[0]);
+
+	_enter("{%s.%s},,%s", cache->ops->name, cache->identifier, tagname);
+
+	/* we use the cache tag to uniquely identify caches */
+	tag = __fscache_lookup_cache_tag(tagname);
+	if (IS_ERR(tag))
+		goto nomem;
+
+	if (test_and_set_bit(FSCACHE_TAG_RESERVED, &tag->flags))
+		goto tag_in_use;
+
+	cache->kobj = kobject_create_and_add(tagname, fscache_root);
+	if (!cache->kobj)
+		goto error;
+
+	ifsdef->cache = cache;
+	cache->fsdef = ifsdef;
+
+	down_write(&fscache_addremove_sem);
+
+	tag->cache = cache;
+	cache->tag = tag;
+
+	/* add the cache to the list */
+	list_add(&cache->link, &fscache_cache_list);
+
+	/* add the cache's netfs definition index object to the cache's
+	 * list */
+	spin_lock(&cache->object_list_lock);
+	list_add_tail(&ifsdef->cache_link, &cache->object_list);
+	spin_unlock(&cache->object_list_lock);
+	fscache_objlist_add(ifsdef);
+
+	/* add the cache's netfs definition index object to the top level index
+	 * cookie as a known backing object */
+	spin_lock(&fscache_fsdef_index.lock);
+
+	hlist_add_head(&ifsdef->cookie_link,
+		       &fscache_fsdef_index.backing_objects);
+
+	atomic_inc(&fscache_fsdef_index.usage);
+
+	/* done */
+	spin_unlock(&fscache_fsdef_index.lock);
+	up_write(&fscache_addremove_sem);
+
+	pr_notice("Cache \"%s\" added (type %s)\n",
+		  cache->tag->name, cache->ops->name);
+	kobject_uevent(cache->kobj, KOBJ_ADD);
+
+	_leave(" = 0 [%s]", cache->identifier);
+	return 0;
+
+tag_in_use:
+	pr_err("Cache tag '%s' already in use\n", tagname);
+	__fscache_release_cache_tag(tag);
+	_leave(" = -EXIST");
+	return -EEXIST;
+
+error:
+	__fscache_release_cache_tag(tag);
+	_leave(" = -EINVAL");
+	return -EINVAL;
+
+nomem:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(fscache_add_cache);
+
+/**
+ * fscache_io_error - Note a cache I/O error
+ * @cache: The record describing the cache
+ *
+ * Note that an I/O error occurred in a cache and that it should no longer be
+ * used for anything.  This also reports the error into the kernel log.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_io_error(struct fscache_cache *cache)
+{
+	if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags))
+		pr_err("Cache '%s' stopped due to I/O error\n",
+		       cache->ops->name);
+}
+EXPORT_SYMBOL(fscache_io_error);
+
+/*
+ * request withdrawal of all the objects in a cache
+ * - all the objects being withdrawn are moved onto the supplied list
+ */
+static void fscache_withdraw_all_objects(struct fscache_cache *cache,
+					 struct list_head *dying_objects)
+{
+	struct fscache_object *object;
+
+	while (!list_empty(&cache->object_list)) {
+		spin_lock(&cache->object_list_lock);
+
+		if (!list_empty(&cache->object_list)) {
+			object = list_entry(cache->object_list.next,
+					    struct fscache_object, cache_link);
+			list_move_tail(&object->cache_link, dying_objects);
+
+			_debug("withdraw %p", object->cookie);
+
+			/* This must be done under object_list_lock to prevent
+			 * a race with fscache_drop_object().
+			 */
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
+		}
+
+		spin_unlock(&cache->object_list_lock);
+		cond_resched();
+	}
+}
+
+/**
+ * fscache_withdraw_cache - Withdraw a cache from the active service
+ * @cache: The record describing the cache
+ *
+ * Withdraw a cache from service, unbinding all its cache objects from the
+ * netfs cookies they're currently representing.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_withdraw_cache(struct fscache_cache *cache)
+{
+	LIST_HEAD(dying_objects);
+
+	_enter("");
+
+	pr_notice("Withdrawing cache \"%s\"\n",
+		  cache->tag->name);
+
+	/* make the cache unavailable for cookie acquisition */
+	if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags))
+		BUG();
+
+	down_write(&fscache_addremove_sem);
+	list_del_init(&cache->link);
+	cache->tag->cache = NULL;
+	up_write(&fscache_addremove_sem);
+
+	/* make sure all pages pinned by operations on behalf of the netfs are
+	 * written to disk */
+	fscache_stat(&fscache_n_cop_sync_cache);
+	cache->ops->sync_cache(cache);
+	fscache_stat_d(&fscache_n_cop_sync_cache);
+
+	/* dissociate all the netfs pages backed by this cache from the block
+	 * mappings in the cache */
+	fscache_stat(&fscache_n_cop_dissociate_pages);
+	cache->ops->dissociate_pages(cache);
+	fscache_stat_d(&fscache_n_cop_dissociate_pages);
+
+	/* we now have to destroy all the active objects pertaining to this
+	 * cache - which we do by passing them off to thread pool to be
+	 * disposed of */
+	_debug("destroy");
+
+	fscache_withdraw_all_objects(cache, &dying_objects);
+
+	/* wait for all extant objects to finish their outstanding operations
+	 * and go away */
+	_debug("wait for finish");
+	wait_event(fscache_cache_cleared_wq,
+		   atomic_read(&cache->object_count) == 0);
+	_debug("wait for clearance");
+	wait_event(fscache_cache_cleared_wq,
+		   list_empty(&cache->object_list));
+	_debug("cleared");
+	ASSERT(list_empty(&dying_objects));
+
+	kobject_put(cache->kobj);
+
+	clear_bit(FSCACHE_TAG_RESERVED, &cache->tag->flags);
+	fscache_release_cache_tag(cache->tag);
+	cache->tag = NULL;
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_withdraw_cache);
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
new file mode 100644
index 000000000..2ff05adfc
--- /dev/null
+++ b/fs/fscache/cookie.c
@@ -0,0 +1,952 @@
+/* netfs cookie management
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for more information on
+ * the netfs API.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+struct kmem_cache *fscache_cookie_jar;
+
+static atomic_t fscache_object_debug_id = ATOMIC_INIT(0);
+
+#define fscache_cookie_hash_shift 15
+static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift];
+
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie,
+					    loff_t object_size);
+static int fscache_alloc_object(struct fscache_cache *cache,
+				struct fscache_cookie *cookie);
+static int fscache_attach_object(struct fscache_cookie *cookie,
+				 struct fscache_object *object);
+
+static void fscache_print_cookie(struct fscache_cookie *cookie, char prefix)
+{
+	struct hlist_node *object;
+	const u8 *k;
+	unsigned loop;
+
+	pr_err("%c-cookie c=%p [p=%p fl=%lx nc=%u na=%u]\n",
+	       prefix, cookie, cookie->parent, cookie->flags,
+	       atomic_read(&cookie->n_children),
+	       atomic_read(&cookie->n_active));
+	pr_err("%c-cookie d=%p n=%p\n",
+	       prefix, cookie->def, cookie->netfs_data);
+
+	object = READ_ONCE(cookie->backing_objects.first);
+	if (object)
+		pr_err("%c-cookie o=%p\n",
+		       prefix, hlist_entry(object, struct fscache_object, cookie_link));
+
+	pr_err("%c-key=[%u] '", prefix, cookie->key_len);
+	k = (cookie->key_len <= sizeof(cookie->inline_key)) ?
+		cookie->inline_key : cookie->key;
+	for (loop = 0; loop < cookie->key_len; loop++)
+		pr_cont("%02x", k[loop]);
+	pr_cont("'\n");
+}
+
+void fscache_free_cookie(struct fscache_cookie *cookie)
+{
+	if (cookie) {
+		BUG_ON(!hlist_empty(&cookie->backing_objects));
+		if (cookie->aux_len > sizeof(cookie->inline_aux))
+			kfree(cookie->aux);
+		if (cookie->key_len > sizeof(cookie->inline_key))
+			kfree(cookie->key);
+		kmem_cache_free(fscache_cookie_jar, cookie);
+	}
+}
+
+/*
+ * Set the index key in a cookie.  The cookie struct has space for a 16-byte
+ * key plus length and hash, but if that's not big enough, it's instead a
+ * pointer to a buffer containing 3 bytes of hash, 1 byte of length and then
+ * the key data.
+ */
+static int fscache_set_key(struct fscache_cookie *cookie,
+			   const void *index_key, size_t index_key_len)
+{
+	u32 *buf;
+	int bufs;
+
+	bufs = DIV_ROUND_UP(index_key_len, sizeof(*buf));
+
+	if (index_key_len > sizeof(cookie->inline_key)) {
+		buf = kcalloc(bufs, sizeof(*buf), GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		cookie->key = buf;
+	} else {
+		buf = (u32 *)cookie->inline_key;
+	}
+
+	memcpy(buf, index_key, index_key_len);
+	cookie->key_hash = fscache_hash(0, buf, bufs);
+	return 0;
+}
+
+static long fscache_compare_cookie(const struct fscache_cookie *a,
+				   const struct fscache_cookie *b)
+{
+	const void *ka, *kb;
+
+	if (a->key_hash != b->key_hash)
+		return (long)a->key_hash - (long)b->key_hash;
+	if (a->parent != b->parent)
+		return (long)a->parent - (long)b->parent;
+	if (a->key_len != b->key_len)
+		return (long)a->key_len - (long)b->key_len;
+	if (a->type != b->type)
+		return (long)a->type - (long)b->type;
+
+	if (a->key_len <= sizeof(a->inline_key)) {
+		ka = &a->inline_key;
+		kb = &b->inline_key;
+	} else {
+		ka = a->key;
+		kb = b->key;
+	}
+	return memcmp(ka, kb, a->key_len);
+}
+
+/*
+ * Allocate a cookie.
+ */
+struct fscache_cookie *fscache_alloc_cookie(
+	struct fscache_cookie *parent,
+	const struct fscache_cookie_def *def,
+	const void *index_key, size_t index_key_len,
+	const void *aux_data, size_t aux_data_len,
+	void *netfs_data,
+	loff_t object_size)
+{
+	struct fscache_cookie *cookie;
+
+	/* allocate and initialise a cookie */
+	cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL);
+	if (!cookie)
+		return NULL;
+
+	cookie->key_len = index_key_len;
+	cookie->aux_len = aux_data_len;
+
+	if (fscache_set_key(cookie, index_key, index_key_len) < 0)
+		goto nomem;
+
+	if (cookie->aux_len <= sizeof(cookie->inline_aux)) {
+		memcpy(cookie->inline_aux, aux_data, cookie->aux_len);
+	} else {
+		cookie->aux = kmemdup(aux_data, cookie->aux_len, GFP_KERNEL);
+		if (!cookie->aux)
+			goto nomem;
+	}
+
+	atomic_set(&cookie->usage, 1);
+	atomic_set(&cookie->n_children, 0);
+
+	/* We keep the active count elevated until relinquishment to prevent an
+	 * attempt to wake up every time the object operations queue quiesces.
+	 */
+	atomic_set(&cookie->n_active, 1);
+
+	cookie->def		= def;
+	cookie->parent		= parent;
+	cookie->netfs_data	= netfs_data;
+	cookie->flags		= (1 << FSCACHE_COOKIE_NO_DATA_YET);
+	cookie->type		= def->type;
+	spin_lock_init(&cookie->lock);
+	spin_lock_init(&cookie->stores_lock);
+	INIT_HLIST_HEAD(&cookie->backing_objects);
+
+	/* radix tree insertion won't use the preallocation pool unless it's
+	 * told it may not wait */
+	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+	return cookie;
+
+nomem:
+	fscache_free_cookie(cookie);
+	return NULL;
+}
+
+/*
+ * Attempt to insert the new cookie into the hash.  If there's a collision, we
+ * return the old cookie if it's not in use and an error otherwise.
+ */
+struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *candidate)
+{
+	struct fscache_cookie *cursor;
+	struct hlist_bl_head *h;
+	struct hlist_bl_node *p;
+	unsigned int bucket;
+
+	bucket = candidate->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1);
+	h = &fscache_cookie_hash[bucket];
+
+	hlist_bl_lock(h);
+	hlist_bl_for_each_entry(cursor, p, h, hash_link) {
+		if (fscache_compare_cookie(candidate, cursor) == 0)
+			goto collision;
+	}
+
+	__set_bit(FSCACHE_COOKIE_ACQUIRED, &candidate->flags);
+	fscache_cookie_get(candidate->parent, fscache_cookie_get_acquire_parent);
+	atomic_inc(&candidate->parent->n_children);
+	hlist_bl_add_head(&candidate->hash_link, h);
+	hlist_bl_unlock(h);
+	return candidate;
+
+collision:
+	if (test_and_set_bit(FSCACHE_COOKIE_ACQUIRED, &cursor->flags)) {
+		trace_fscache_cookie(cursor, fscache_cookie_collision,
+				     atomic_read(&cursor->usage));
+		pr_err("Duplicate cookie detected\n");
+		fscache_print_cookie(cursor, 'O');
+		fscache_print_cookie(candidate, 'N');
+		hlist_bl_unlock(h);
+		return NULL;
+	}
+
+	fscache_cookie_get(cursor, fscache_cookie_get_reacquire);
+	hlist_bl_unlock(h);
+	return cursor;
+}
+
+/*
+ * request a cookie to represent an object (index, datafile, xattr, etc)
+ * - parent specifies the parent object
+ *   - the top level index cookie for each netfs is stored in the fscache_netfs
+ *     struct upon registration
+ * - def points to the definition
+ * - the netfs_data will be passed to the functions pointed to in *def
+ * - all attached caches will be searched to see if they contain this object
+ * - index objects aren't stored on disk until there's a dependent file that
+ *   needs storing
+ * - other objects are stored in a selected cache immediately, and all the
+ *   indices forming the path to it are instantiated if necessary
+ * - we never let on to the netfs about errors
+ *   - we may set a negative cookie pointer, but that's okay
+ */
+struct fscache_cookie *__fscache_acquire_cookie(
+	struct fscache_cookie *parent,
+	const struct fscache_cookie_def *def,
+	const void *index_key, size_t index_key_len,
+	const void *aux_data, size_t aux_data_len,
+	void *netfs_data,
+	loff_t object_size,
+	bool enable)
+{
+	struct fscache_cookie *candidate, *cookie;
+
+	BUG_ON(!def);
+
+	_enter("{%s},{%s},%p,%u",
+	       parent ? (char *) parent->def->name : "<no-parent>",
+	       def->name, netfs_data, enable);
+
+	if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255)
+		return NULL;
+	if (!aux_data || !aux_data_len) {
+		aux_data = NULL;
+		aux_data_len = 0;
+	}
+
+	fscache_stat(&fscache_n_acquires);
+
+	/* if there's no parent cookie, then we don't create one here either */
+	if (!parent) {
+		fscache_stat(&fscache_n_acquires_null);
+		_leave(" [no parent]");
+		return NULL;
+	}
+
+	/* validate the definition */
+	BUG_ON(!def->name[0]);
+
+	BUG_ON(def->type == FSCACHE_COOKIE_TYPE_INDEX &&
+	       parent->type != FSCACHE_COOKIE_TYPE_INDEX);
+
+	candidate = fscache_alloc_cookie(parent, def,
+					 index_key, index_key_len,
+					 aux_data, aux_data_len,
+					 netfs_data, object_size);
+	if (!candidate) {
+		fscache_stat(&fscache_n_acquires_oom);
+		_leave(" [ENOMEM]");
+		return NULL;
+	}
+
+	cookie = fscache_hash_cookie(candidate);
+	if (!cookie) {
+		trace_fscache_cookie(candidate, fscache_cookie_discard, 1);
+		goto out;
+	}
+
+	if (cookie == candidate)
+		candidate = NULL;
+
+	switch (cookie->type) {
+	case FSCACHE_COOKIE_TYPE_INDEX:
+		fscache_stat(&fscache_n_cookie_index);
+		break;
+	case FSCACHE_COOKIE_TYPE_DATAFILE:
+		fscache_stat(&fscache_n_cookie_data);
+		break;
+	default:
+		fscache_stat(&fscache_n_cookie_special);
+		break;
+	}
+
+	trace_fscache_acquire(cookie);
+
+	if (enable) {
+		/* if the object is an index then we need do nothing more here
+		 * - we create indices on disk when we need them as an index
+		 * may exist in multiple caches */
+		if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) {
+			if (fscache_acquire_non_index_cookie(cookie, object_size) == 0) {
+				set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+			} else {
+				atomic_dec(&parent->n_children);
+				fscache_cookie_put(cookie,
+						   fscache_cookie_put_acquire_nobufs);
+				fscache_stat(&fscache_n_acquires_nobufs);
+				_leave(" = NULL");
+				return NULL;
+			}
+		} else {
+			set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+		}
+	}
+
+	fscache_stat(&fscache_n_acquires_ok);
+
+out:
+	fscache_free_cookie(candidate);
+	return cookie;
+}
+EXPORT_SYMBOL(__fscache_acquire_cookie);
+
+/*
+ * Enable a cookie to permit it to accept new operations.
+ */
+void __fscache_enable_cookie(struct fscache_cookie *cookie,
+			     const void *aux_data,
+			     loff_t object_size,
+			     bool (*can_enable)(void *data),
+			     void *data)
+{
+	_enter("%p", cookie);
+
+	trace_fscache_enable(cookie);
+
+	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
+			 TASK_UNINTERRUPTIBLE);
+
+	fscache_update_aux(cookie, aux_data);
+
+	if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
+		goto out_unlock;
+
+	if (can_enable && !can_enable(data)) {
+		/* The netfs decided it didn't want to enable after all */
+	} else if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		/* Wait for outstanding disablement to complete */
+		__fscache_wait_on_invalidate(cookie);
+
+		if (fscache_acquire_non_index_cookie(cookie, object_size) == 0)
+			set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+	} else {
+		set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+	}
+
+out_unlock:
+	clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags);
+	wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK);
+}
+EXPORT_SYMBOL(__fscache_enable_cookie);
+
+/*
+ * acquire a non-index cookie
+ * - this must make sure the index chain is instantiated and instantiate the
+ *   object representation too
+ */
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie,
+					    loff_t object_size)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+	int ret;
+
+	_enter("");
+
+	set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+
+	/* now we need to see whether the backing objects for this cookie yet
+	 * exist, if not there'll be nothing to search */
+	down_read(&fscache_addremove_sem);
+
+	if (list_empty(&fscache_cache_list)) {
+		up_read(&fscache_addremove_sem);
+		_leave(" = 0 [no caches]");
+		return 0;
+	}
+
+	/* select a cache in which to store the object */
+	cache = fscache_select_cache_for_object(cookie->parent);
+	if (!cache) {
+		up_read(&fscache_addremove_sem);
+		fscache_stat(&fscache_n_acquires_no_cache);
+		_leave(" = -ENOMEDIUM [no cache]");
+		return -ENOMEDIUM;
+	}
+
+	_debug("cache %s", cache->tag->name);
+
+	set_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+
+	/* ask the cache to allocate objects for this cookie and its parent
+	 * chain */
+	ret = fscache_alloc_object(cache, cookie);
+	if (ret < 0) {
+		up_read(&fscache_addremove_sem);
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	spin_lock(&cookie->lock);
+	if (hlist_empty(&cookie->backing_objects)) {
+		spin_unlock(&cookie->lock);
+		goto unavailable;
+	}
+
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	fscache_set_store_limit(object, object_size);
+
+	/* initiate the process of looking up all the objects in the chain
+	 * (done by fscache_initialise_object()) */
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_NEW_CHILD);
+
+	spin_unlock(&cookie->lock);
+
+	/* we may be required to wait for lookup to complete at this point */
+	if (!fscache_defer_lookup) {
+		_debug("non-deferred lookup %p", &cookie->flags);
+		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
+			    TASK_UNINTERRUPTIBLE);
+		_debug("complete");
+		if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags))
+			goto unavailable;
+	}
+
+	up_read(&fscache_addremove_sem);
+	_leave(" = 0 [deferred]");
+	return 0;
+
+unavailable:
+	up_read(&fscache_addremove_sem);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+
+/*
+ * recursively allocate cache object records for a cookie/cache combination
+ * - caller must be holding the addremove sem
+ */
+static int fscache_alloc_object(struct fscache_cache *cache,
+				struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%p{%s}", cache, cookie, cookie->def->name);
+
+	spin_lock(&cookie->lock);
+	hlist_for_each_entry(object, &cookie->backing_objects,
+			     cookie_link) {
+		if (object->cache == cache)
+			goto object_already_extant;
+	}
+	spin_unlock(&cookie->lock);
+
+	/* ask the cache to allocate an object (we may end up with duplicate
+	 * objects at this stage, but we sort that out later) */
+	fscache_stat(&fscache_n_cop_alloc_object);
+	object = cache->ops->alloc_object(cache, cookie);
+	fscache_stat_d(&fscache_n_cop_alloc_object);
+	if (IS_ERR(object)) {
+		fscache_stat(&fscache_n_object_no_alloc);
+		ret = PTR_ERR(object);
+		goto error;
+	}
+
+	ASSERTCMP(object->cookie, ==, cookie);
+	fscache_stat(&fscache_n_object_alloc);
+
+	object->debug_id = atomic_inc_return(&fscache_object_debug_id);
+
+	_debug("ALLOC OBJ%x: %s {%lx}",
+	       object->debug_id, cookie->def->name, object->events);
+
+	ret = fscache_alloc_object(cache, cookie->parent);
+	if (ret < 0)
+		goto error_put;
+
+	/* only attach if we managed to allocate all we needed, otherwise
+	 * discard the object we just allocated and instead use the one
+	 * attached to the cookie */
+	if (fscache_attach_object(cookie, object) < 0) {
+		fscache_stat(&fscache_n_cop_put_object);
+		cache->ops->put_object(object, fscache_obj_put_attach_fail);
+		fscache_stat_d(&fscache_n_cop_put_object);
+	}
+
+	_leave(" = 0");
+	return 0;
+
+object_already_extant:
+	ret = -ENOBUFS;
+	if (fscache_object_is_dying(object) ||
+	    fscache_cache_is_broken(object)) {
+		spin_unlock(&cookie->lock);
+		goto error;
+	}
+	spin_unlock(&cookie->lock);
+	_leave(" = 0 [found]");
+	return 0;
+
+error_put:
+	fscache_stat(&fscache_n_cop_put_object);
+	cache->ops->put_object(object, fscache_obj_put_alloc_fail);
+	fscache_stat_d(&fscache_n_cop_put_object);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * attach a cache object to a cookie
+ */
+static int fscache_attach_object(struct fscache_cookie *cookie,
+				 struct fscache_object *object)
+{
+	struct fscache_object *p;
+	struct fscache_cache *cache = object->cache;
+	int ret;
+
+	_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
+
+	ASSERTCMP(object->cookie, ==, cookie);
+
+	spin_lock(&cookie->lock);
+
+	/* there may be multiple initial creations of this object, but we only
+	 * want one */
+	ret = -EEXIST;
+	hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) {
+		if (p->cache == object->cache) {
+			if (fscache_object_is_dying(p))
+				ret = -ENOBUFS;
+			goto cant_attach_object;
+		}
+	}
+
+	/* pin the parent object */
+	spin_lock_nested(&cookie->parent->lock, 1);
+	hlist_for_each_entry(p, &cookie->parent->backing_objects,
+			     cookie_link) {
+		if (p->cache == object->cache) {
+			if (fscache_object_is_dying(p)) {
+				ret = -ENOBUFS;
+				spin_unlock(&cookie->parent->lock);
+				goto cant_attach_object;
+			}
+			object->parent = p;
+			spin_lock(&p->lock);
+			p->n_children++;
+			spin_unlock(&p->lock);
+			break;
+		}
+	}
+	spin_unlock(&cookie->parent->lock);
+
+	/* attach to the cache's object list */
+	if (list_empty(&object->cache_link)) {
+		spin_lock(&cache->object_list_lock);
+		list_add(&object->cache_link, &cache->object_list);
+		spin_unlock(&cache->object_list_lock);
+	}
+
+	/* Attach to the cookie.  The object already has a ref on it. */
+	hlist_add_head(&object->cookie_link, &cookie->backing_objects);
+
+	fscache_objlist_add(object);
+	ret = 0;
+
+cant_attach_object:
+	spin_unlock(&cookie->lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Invalidate an object.  Callable with spinlocks held.
+ */
+void __fscache_invalidate(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+
+	_enter("{%s}", cookie->def->name);
+
+	fscache_stat(&fscache_n_invalidates);
+
+	/* Only permit invalidation of data files.  Invalidating an index will
+	 * require the caller to release all its attachments to the tree rooted
+	 * there, and if it's doing that, it may as well just retire the
+	 * cookie.
+	 */
+	ASSERTCMP(cookie->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE);
+
+	/* If there's an object, we tell the object state machine to handle the
+	 * invalidation on our behalf, otherwise there's nothing to do.
+	 */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		spin_lock(&cookie->lock);
+
+		if (fscache_cookie_enabled(cookie) &&
+		    !hlist_empty(&cookie->backing_objects) &&
+		    !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING,
+				      &cookie->flags)) {
+			object = hlist_entry(cookie->backing_objects.first,
+					     struct fscache_object,
+					     cookie_link);
+			if (fscache_object_is_live(object))
+				fscache_raise_event(
+					object, FSCACHE_OBJECT_EV_INVALIDATE);
+		}
+
+		spin_unlock(&cookie->lock);
+	}
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_invalidate);
+
+/*
+ * Wait for object invalidation to complete.
+ */
+void __fscache_wait_on_invalidate(struct fscache_cookie *cookie)
+{
+	_enter("%p", cookie);
+
+	wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING,
+		    TASK_UNINTERRUPTIBLE);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_wait_on_invalidate);
+
+/*
+ * update the index entries backing a cookie
+ */
+void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data)
+{
+	struct fscache_object *object;
+
+	fscache_stat(&fscache_n_updates);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_updates_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("{%s}", cookie->def->name);
+
+	spin_lock(&cookie->lock);
+
+	fscache_update_aux(cookie, aux_data);
+
+	if (fscache_cookie_enabled(cookie)) {
+		/* update the index entry on disk in each cache backing this
+		 * cookie.
+		 */
+		hlist_for_each_entry(object,
+				     &cookie->backing_objects, cookie_link) {
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+		}
+	}
+
+	spin_unlock(&cookie->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_update_cookie);
+
+/*
+ * Disable a cookie to stop it from accepting new requests from the netfs.
+ */
+void __fscache_disable_cookie(struct fscache_cookie *cookie,
+			      const void *aux_data,
+			      bool invalidate)
+{
+	struct fscache_object *object;
+	bool awaken = false;
+
+	_enter("%p,%u", cookie, invalidate);
+
+	trace_fscache_disable(cookie);
+
+	ASSERTCMP(atomic_read(&cookie->n_active), >, 0);
+
+	if (atomic_read(&cookie->n_children) != 0) {
+		pr_err("Cookie '%s' still has children\n",
+		       cookie->def->name);
+		BUG();
+	}
+
+	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
+			 TASK_UNINTERRUPTIBLE);
+
+	fscache_update_aux(cookie, aux_data);
+
+	if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
+		goto out_unlock_enable;
+
+	/* If the cookie is being invalidated, wait for that to complete first
+	 * so that we can reuse the flag.
+	 */
+	__fscache_wait_on_invalidate(cookie);
+
+	/* Dispose of the backing objects */
+	set_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags);
+
+	spin_lock(&cookie->lock);
+	if (!hlist_empty(&cookie->backing_objects)) {
+		hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
+			if (invalidate)
+				set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+			clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
+		}
+	} else {
+		if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+			awaken = true;
+	}
+	spin_unlock(&cookie->lock);
+	if (awaken)
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+
+	/* Wait for cessation of activity requiring access to the netfs (when
+	 * n_active reaches 0).  This makes sure outstanding reads and writes
+	 * have completed.
+	 */
+	if (!atomic_dec_and_test(&cookie->n_active)) {
+		wait_var_event(&cookie->n_active,
+			       !atomic_read(&cookie->n_active));
+	}
+
+	/* Make sure any pending writes are cancelled. */
+	if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX)
+		fscache_invalidate_writes(cookie);
+
+	/* Reset the cookie state if it wasn't relinquished */
+	if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
+		atomic_inc(&cookie->n_active);
+		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+	}
+
+out_unlock_enable:
+	clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags);
+	wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK);
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_disable_cookie);
+
+/*
+ * release a cookie back to the cache
+ * - the object will be marked as recyclable on disk if retire is true
+ * - all dependents of this cookie must have already been unregistered
+ *   (indices/files/pages)
+ */
+void __fscache_relinquish_cookie(struct fscache_cookie *cookie,
+				 const void *aux_data,
+				 bool retire)
+{
+	fscache_stat(&fscache_n_relinquishes);
+	if (retire)
+		fscache_stat(&fscache_n_relinquishes_retire);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_relinquishes_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("%p{%s,%p,%d},%d",
+	       cookie, cookie->def->name, cookie->netfs_data,
+	       atomic_read(&cookie->n_active), retire);
+
+	trace_fscache_relinquish(cookie, retire);
+
+	/* No further netfs-accessing operations on this cookie permitted */
+	if (test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags))
+		BUG();
+
+	__fscache_disable_cookie(cookie, aux_data, retire);
+
+	/* Clear pointers back to the netfs */
+	cookie->netfs_data	= NULL;
+	cookie->def		= NULL;
+	BUG_ON(!radix_tree_empty(&cookie->stores));
+
+	if (cookie->parent) {
+		ASSERTCMP(atomic_read(&cookie->parent->usage), >, 0);
+		ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0);
+		atomic_dec(&cookie->parent->n_children);
+	}
+
+	/* Dispose of the netfs's link to the cookie */
+	ASSERTCMP(atomic_read(&cookie->usage), >, 0);
+	fscache_cookie_put(cookie, fscache_cookie_put_relinquish);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_relinquish_cookie);
+
+/*
+ * Remove a cookie from the hash table.
+ */
+static void fscache_unhash_cookie(struct fscache_cookie *cookie)
+{
+	struct hlist_bl_head *h;
+	unsigned int bucket;
+
+	bucket = cookie->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1);
+	h = &fscache_cookie_hash[bucket];
+
+	hlist_bl_lock(h);
+	hlist_bl_del(&cookie->hash_link);
+	hlist_bl_unlock(h);
+}
+
+/*
+ * Drop a reference to a cookie.
+ */
+void fscache_cookie_put(struct fscache_cookie *cookie,
+			enum fscache_cookie_trace where)
+{
+	struct fscache_cookie *parent;
+	int usage;
+
+	_enter("%p", cookie);
+
+	do {
+		usage = atomic_dec_return(&cookie->usage);
+		trace_fscache_cookie(cookie, where, usage);
+
+		if (usage > 0)
+			return;
+		BUG_ON(usage < 0);
+
+		parent = cookie->parent;
+		fscache_unhash_cookie(cookie);
+		fscache_free_cookie(cookie);
+
+		cookie = parent;
+		where = fscache_cookie_put_parent;
+	} while (cookie);
+
+	_leave("");
+}
+
+/*
+ * check the consistency between the netfs inode and the backing cache
+ *
+ * NOTE: it only serves no-index type
+ */
+int __fscache_check_consistency(struct fscache_cookie *cookie,
+				const void *aux_data)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+	bool wake_cookie = false;
+	int ret;
+
+	_enter("%p,", cookie);
+
+	ASSERTCMP(cookie->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	if (hlist_empty(&cookie->backing_objects))
+		return 0;
+
+	op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY);
+	if (!op)
+		return -ENOMEM;
+
+	fscache_operation_init(cookie, op, NULL, NULL, NULL);
+	op->flags = FSCACHE_OP_MYTHREAD |
+		(1 << FSCACHE_OP_WAITING) |
+		(1 << FSCACHE_OP_UNUSE_COOKIE);
+	trace_fscache_page_op(cookie, NULL, op, fscache_page_op_check_consistency);
+
+	spin_lock(&cookie->lock);
+
+	fscache_update_aux(cookie, aux_data);
+
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
+		goto inconsistent;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+	if (test_bit(FSCACHE_IOERROR, &object->cache->flags))
+		goto inconsistent;
+
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+
+	__fscache_use_cookie(cookie);
+	if (fscache_submit_op(object, op) < 0)
+		goto submit_failed;
+
+	/* the work queue now carries its own ref on the object */
+	spin_unlock(&cookie->lock);
+
+	ret = fscache_wait_for_operation_activation(object, op, NULL, NULL);
+	if (ret == 0) {
+		/* ask the cache to honour the operation */
+		ret = object->cache->ops->check_consistency(op);
+		fscache_op_complete(op, false);
+	} else if (ret == -ENOBUFS) {
+		ret = 0;
+	}
+
+	fscache_put_operation(op);
+	_leave(" = %d", ret);
+	return ret;
+
+submit_failed:
+	wake_cookie = __fscache_unuse_cookie(cookie);
+inconsistent:
+	spin_unlock(&cookie->lock);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
+	kfree(op);
+	_leave(" = -ESTALE");
+	return -ESTALE;
+}
+EXPORT_SYMBOL(__fscache_check_consistency);
diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c
new file mode 100644
index 000000000..aa46e48d8
--- /dev/null
+++ b/fs/fscache/fsdef.c
@@ -0,0 +1,101 @@
+/* Filesystem index definition
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include "internal.h"
+
+static
+enum fscache_checkaux fscache_fsdef_netfs_check_aux(void *cookie_netfs_data,
+						    const void *data,
+						    uint16_t datalen,
+						    loff_t object_size);
+
+/*
+ * The root index is owned by FS-Cache itself.
+ *
+ * When a netfs requests caching facilities, FS-Cache will, if one doesn't
+ * already exist, create an entry in the root index with the key being the name
+ * of the netfs ("AFS" for example), and the auxiliary data holding the index
+ * structure version supplied by the netfs:
+ *
+ *				     FSDEF
+ *				       |
+ *				 +-----------+
+ *				 |           |
+ *				NFS         AFS
+ *			       [v=1]       [v=1]
+ *
+ * If an entry with the appropriate name does already exist, the version is
+ * compared.  If the version is different, the entire subtree from that entry
+ * will be discarded and a new entry created.
+ *
+ * The new entry will be an index, and a cookie referring to it will be passed
+ * to the netfs.  This is then the root handle by which the netfs accesses the
+ * cache.  It can create whatever objects it likes in that index, including
+ * further indices.
+ */
+static struct fscache_cookie_def fscache_fsdef_index_def = {
+	.name		= ".FS-Cache",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+};
+
+struct fscache_cookie fscache_fsdef_index = {
+	.usage		= ATOMIC_INIT(1),
+	.n_active	= ATOMIC_INIT(1),
+	.lock		= __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock),
+	.backing_objects = HLIST_HEAD_INIT,
+	.def		= &fscache_fsdef_index_def,
+	.flags		= 1 << FSCACHE_COOKIE_ENABLED,
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+};
+EXPORT_SYMBOL(fscache_fsdef_index);
+
+/*
+ * Definition of an entry in the root index.  Each entry is an index, keyed to
+ * a specific netfs and only applicable to a particular version of the index
+ * structure used by that netfs.
+ */
+struct fscache_cookie_def fscache_fsdef_netfs_def = {
+	.name		= "FSDEF.netfs",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.check_aux	= fscache_fsdef_netfs_check_aux,
+};
+
+/*
+ * check that the index structure version number stored in the auxiliary data
+ * matches the one the netfs gave us
+ */
+static enum fscache_checkaux fscache_fsdef_netfs_check_aux(
+	void *cookie_netfs_data,
+	const void *data,
+	uint16_t datalen,
+	loff_t object_size)
+{
+	struct fscache_netfs *netfs = cookie_netfs_data;
+	uint32_t version;
+
+	_enter("{%s},,%hu", netfs->name, datalen);
+
+	if (datalen != sizeof(version)) {
+		_leave(" = OBSOLETE [dl=%d v=%zu]", datalen, sizeof(version));
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	memcpy(&version, data, sizeof(version));
+	if (version != netfs->version) {
+		_leave(" = OBSOLETE [ver=%x net=%x]", version, netfs->version);
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
+}
diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c
new file mode 100644
index 000000000..9a13e9e15
--- /dev/null
+++ b/fs/fscache/histogram.c
@@ -0,0 +1,91 @@
+/* FS-Cache latency histogram
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL THREAD
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+atomic_t fscache_obj_instantiate_histogram[HZ];
+atomic_t fscache_objs_histogram[HZ];
+atomic_t fscache_ops_histogram[HZ];
+atomic_t fscache_retrieval_delay_histogram[HZ];
+atomic_t fscache_retrieval_histogram[HZ];
+
+/*
+ * display the time-taken histogram
+ */
+static int fscache_histogram_show(struct seq_file *m, void *v)
+{
+	unsigned long index;
+	unsigned n[5], t;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "JIFS  SECS  OBJ INST  OP RUNS   OBJ RUNS  RETRV DLY RETRIEVLS\n");
+		return 0;
+	case 2:
+		seq_puts(m, "===== ===== ========= ========= ========= ========= =========\n");
+		return 0;
+	default:
+		index = (unsigned long) v - 3;
+		n[0] = atomic_read(&fscache_obj_instantiate_histogram[index]);
+		n[1] = atomic_read(&fscache_ops_histogram[index]);
+		n[2] = atomic_read(&fscache_objs_histogram[index]);
+		n[3] = atomic_read(&fscache_retrieval_delay_histogram[index]);
+		n[4] = atomic_read(&fscache_retrieval_histogram[index]);
+		if (!(n[0] | n[1] | n[2] | n[3] | n[4]))
+			return 0;
+
+		t = (index * 1000) / HZ;
+
+		seq_printf(m, "%4lu  0.%03u %9u %9u %9u %9u %9u\n",
+			   index, t, n[0], n[1], n[2], n[3], n[4]);
+		return 0;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *fscache_histogram_start(struct seq_file *m, loff_t *_pos)
+{
+	if ((unsigned long long)*_pos >= HZ + 2)
+		return NULL;
+	if (*_pos == 0)
+		*_pos = 1;
+	return (void *)(unsigned long) *_pos;
+}
+
+/*
+ * move to the next line
+ */
+static void *fscache_histogram_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (unsigned long long)*pos > HZ + 2 ?
+		NULL : (void *)(unsigned long) *pos;
+}
+
+/*
+ * clean up after reading
+ */
+static void fscache_histogram_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations fscache_histogram_ops = {
+	.start		= fscache_histogram_start,
+	.stop		= fscache_histogram_stop,
+	.next		= fscache_histogram_next,
+	.show		= fscache_histogram_show,
+};
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
new file mode 100644
index 000000000..cc87288a5
--- /dev/null
+++ b/fs/fscache/internal.h
@@ -0,0 +1,496 @@
+/* Internal definitions for FS-Cache
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/*
+ * Lock order, in the order in which multiple locks should be obtained:
+ * - fscache_addremove_sem
+ * - cookie->lock
+ * - cookie->parent->lock
+ * - cache->object_list_lock
+ * - object->lock
+ * - object->parent->lock
+ * - cookie->stores_lock
+ * - fscache_thread_lock
+ *
+ */
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) "FS-Cache: " fmt
+
+#include <linux/fscache-cache.h>
+#include <trace/events/fscache.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+
+#define FSCACHE_MIN_THREADS	4
+#define FSCACHE_MAX_THREADS	32
+
+/*
+ * cache.c
+ */
+extern struct list_head fscache_cache_list;
+extern struct rw_semaphore fscache_addremove_sem;
+
+extern struct fscache_cache *fscache_select_cache_for_object(
+	struct fscache_cookie *);
+
+/*
+ * cookie.c
+ */
+extern struct kmem_cache *fscache_cookie_jar;
+
+extern void fscache_free_cookie(struct fscache_cookie *);
+extern struct fscache_cookie *fscache_alloc_cookie(struct fscache_cookie *,
+						   const struct fscache_cookie_def *,
+						   const void *, size_t,
+						   const void *, size_t,
+						   void *, loff_t);
+extern struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *);
+extern void fscache_cookie_put(struct fscache_cookie *,
+			       enum fscache_cookie_trace);
+
+/*
+ * fsdef.c
+ */
+extern struct fscache_cookie fscache_fsdef_index;
+extern struct fscache_cookie_def fscache_fsdef_netfs_def;
+
+/*
+ * histogram.c
+ */
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+extern atomic_t fscache_obj_instantiate_histogram[HZ];
+extern atomic_t fscache_objs_histogram[HZ];
+extern atomic_t fscache_ops_histogram[HZ];
+extern atomic_t fscache_retrieval_delay_histogram[HZ];
+extern atomic_t fscache_retrieval_histogram[HZ];
+
+static inline void fscache_hist(atomic_t histogram[], unsigned long start_jif)
+{
+	unsigned long jif = jiffies - start_jif;
+	if (jif >= HZ)
+		jif = HZ - 1;
+	atomic_inc(&histogram[jif]);
+}
+
+extern const struct seq_operations fscache_histogram_ops;
+
+#else
+#define fscache_hist(hist, start_jif) do {} while (0)
+#endif
+
+/*
+ * main.c
+ */
+extern unsigned fscache_defer_lookup;
+extern unsigned fscache_defer_create;
+extern unsigned fscache_debug;
+extern struct kobject *fscache_root;
+extern struct workqueue_struct *fscache_object_wq;
+extern struct workqueue_struct *fscache_op_wq;
+DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
+
+extern unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n);
+
+static inline bool fscache_object_congested(void)
+{
+	return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq);
+}
+
+/*
+ * object.c
+ */
+extern void fscache_enqueue_object(struct fscache_object *);
+
+/*
+ * object-list.c
+ */
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+extern const struct file_operations fscache_objlist_fops;
+
+extern void fscache_objlist_add(struct fscache_object *);
+extern void fscache_objlist_remove(struct fscache_object *);
+#else
+#define fscache_objlist_add(object) do {} while(0)
+#define fscache_objlist_remove(object) do {} while(0)
+#endif
+
+/*
+ * operation.c
+ */
+extern int fscache_submit_exclusive_op(struct fscache_object *,
+				       struct fscache_operation *);
+extern int fscache_submit_op(struct fscache_object *,
+			     struct fscache_operation *);
+extern int fscache_cancel_op(struct fscache_operation *, bool);
+extern void fscache_cancel_all_ops(struct fscache_object *);
+extern void fscache_abort_object(struct fscache_object *);
+extern void fscache_start_operations(struct fscache_object *);
+extern void fscache_operation_gc(struct work_struct *);
+
+/*
+ * page.c
+ */
+extern int fscache_wait_for_deferred_lookup(struct fscache_cookie *);
+extern int fscache_wait_for_operation_activation(struct fscache_object *,
+						 struct fscache_operation *,
+						 atomic_t *,
+						 atomic_t *);
+extern void fscache_invalidate_writes(struct fscache_cookie *);
+
+/*
+ * proc.c
+ */
+#ifdef CONFIG_PROC_FS
+extern int __init fscache_proc_init(void);
+extern void fscache_proc_cleanup(void);
+#else
+#define fscache_proc_init()	(0)
+#define fscache_proc_cleanup()	do {} while (0)
+#endif
+
+/*
+ * stats.c
+ */
+#ifdef CONFIG_FSCACHE_STATS
+extern atomic_t fscache_n_ops_processed[FSCACHE_MAX_THREADS];
+extern atomic_t fscache_n_objs_processed[FSCACHE_MAX_THREADS];
+
+extern atomic_t fscache_n_op_pend;
+extern atomic_t fscache_n_op_run;
+extern atomic_t fscache_n_op_enqueue;
+extern atomic_t fscache_n_op_deferred_release;
+extern atomic_t fscache_n_op_initialised;
+extern atomic_t fscache_n_op_release;
+extern atomic_t fscache_n_op_gc;
+extern atomic_t fscache_n_op_cancelled;
+extern atomic_t fscache_n_op_rejected;
+
+extern atomic_t fscache_n_attr_changed;
+extern atomic_t fscache_n_attr_changed_ok;
+extern atomic_t fscache_n_attr_changed_nobufs;
+extern atomic_t fscache_n_attr_changed_nomem;
+extern atomic_t fscache_n_attr_changed_calls;
+
+extern atomic_t fscache_n_allocs;
+extern atomic_t fscache_n_allocs_ok;
+extern atomic_t fscache_n_allocs_wait;
+extern atomic_t fscache_n_allocs_nobufs;
+extern atomic_t fscache_n_allocs_intr;
+extern atomic_t fscache_n_allocs_object_dead;
+extern atomic_t fscache_n_alloc_ops;
+extern atomic_t fscache_n_alloc_op_waits;
+
+extern atomic_t fscache_n_retrievals;
+extern atomic_t fscache_n_retrievals_ok;
+extern atomic_t fscache_n_retrievals_wait;
+extern atomic_t fscache_n_retrievals_nodata;
+extern atomic_t fscache_n_retrievals_nobufs;
+extern atomic_t fscache_n_retrievals_intr;
+extern atomic_t fscache_n_retrievals_nomem;
+extern atomic_t fscache_n_retrievals_object_dead;
+extern atomic_t fscache_n_retrieval_ops;
+extern atomic_t fscache_n_retrieval_op_waits;
+
+extern atomic_t fscache_n_stores;
+extern atomic_t fscache_n_stores_ok;
+extern atomic_t fscache_n_stores_again;
+extern atomic_t fscache_n_stores_nobufs;
+extern atomic_t fscache_n_stores_oom;
+extern atomic_t fscache_n_store_ops;
+extern atomic_t fscache_n_store_calls;
+extern atomic_t fscache_n_store_pages;
+extern atomic_t fscache_n_store_radix_deletes;
+extern atomic_t fscache_n_store_pages_over_limit;
+
+extern atomic_t fscache_n_store_vmscan_not_storing;
+extern atomic_t fscache_n_store_vmscan_gone;
+extern atomic_t fscache_n_store_vmscan_busy;
+extern atomic_t fscache_n_store_vmscan_cancelled;
+extern atomic_t fscache_n_store_vmscan_wait;
+
+extern atomic_t fscache_n_marks;
+extern atomic_t fscache_n_uncaches;
+
+extern atomic_t fscache_n_acquires;
+extern atomic_t fscache_n_acquires_null;
+extern atomic_t fscache_n_acquires_no_cache;
+extern atomic_t fscache_n_acquires_ok;
+extern atomic_t fscache_n_acquires_nobufs;
+extern atomic_t fscache_n_acquires_oom;
+
+extern atomic_t fscache_n_invalidates;
+extern atomic_t fscache_n_invalidates_run;
+
+extern atomic_t fscache_n_updates;
+extern atomic_t fscache_n_updates_null;
+extern atomic_t fscache_n_updates_run;
+
+extern atomic_t fscache_n_relinquishes;
+extern atomic_t fscache_n_relinquishes_null;
+extern atomic_t fscache_n_relinquishes_waitcrt;
+extern atomic_t fscache_n_relinquishes_retire;
+
+extern atomic_t fscache_n_cookie_index;
+extern atomic_t fscache_n_cookie_data;
+extern atomic_t fscache_n_cookie_special;
+
+extern atomic_t fscache_n_object_alloc;
+extern atomic_t fscache_n_object_no_alloc;
+extern atomic_t fscache_n_object_lookups;
+extern atomic_t fscache_n_object_lookups_negative;
+extern atomic_t fscache_n_object_lookups_positive;
+extern atomic_t fscache_n_object_lookups_timed_out;
+extern atomic_t fscache_n_object_created;
+extern atomic_t fscache_n_object_avail;
+extern atomic_t fscache_n_object_dead;
+
+extern atomic_t fscache_n_checkaux_none;
+extern atomic_t fscache_n_checkaux_okay;
+extern atomic_t fscache_n_checkaux_update;
+extern atomic_t fscache_n_checkaux_obsolete;
+
+extern atomic_t fscache_n_cop_alloc_object;
+extern atomic_t fscache_n_cop_lookup_object;
+extern atomic_t fscache_n_cop_lookup_complete;
+extern atomic_t fscache_n_cop_grab_object;
+extern atomic_t fscache_n_cop_invalidate_object;
+extern atomic_t fscache_n_cop_update_object;
+extern atomic_t fscache_n_cop_drop_object;
+extern atomic_t fscache_n_cop_put_object;
+extern atomic_t fscache_n_cop_sync_cache;
+extern atomic_t fscache_n_cop_attr_changed;
+extern atomic_t fscache_n_cop_read_or_alloc_page;
+extern atomic_t fscache_n_cop_read_or_alloc_pages;
+extern atomic_t fscache_n_cop_allocate_page;
+extern atomic_t fscache_n_cop_allocate_pages;
+extern atomic_t fscache_n_cop_write_page;
+extern atomic_t fscache_n_cop_uncache_page;
+extern atomic_t fscache_n_cop_dissociate_pages;
+
+extern atomic_t fscache_n_cache_no_space_reject;
+extern atomic_t fscache_n_cache_stale_objects;
+extern atomic_t fscache_n_cache_retired_objects;
+extern atomic_t fscache_n_cache_culled_objects;
+
+static inline void fscache_stat(atomic_t *stat)
+{
+	atomic_inc(stat);
+}
+
+static inline void fscache_stat_d(atomic_t *stat)
+{
+	atomic_dec(stat);
+}
+
+#define __fscache_stat(stat) (stat)
+
+int fscache_stats_show(struct seq_file *m, void *v);
+#else
+
+#define __fscache_stat(stat) (NULL)
+#define fscache_stat(stat) do {} while (0)
+#define fscache_stat_d(stat) do {} while (0)
+#endif
+
+/*
+ * raise an event on an object
+ * - if the event is not masked for that object, then the object is
+ *   queued for attention by the thread pool.
+ */
+static inline void fscache_raise_event(struct fscache_object *object,
+				       unsigned event)
+{
+	BUG_ON(event >= NR_FSCACHE_OBJECT_EVENTS);
+#if 0
+	printk("*** fscache_raise_event(OBJ%d{%lx},%x)\n",
+	       object->debug_id, object->event_mask, (1 << event));
+#endif
+	if (!test_and_set_bit(event, &object->events) &&
+	    test_bit(event, &object->event_mask))
+		fscache_enqueue_object(object);
+}
+
+static inline void fscache_cookie_get(struct fscache_cookie *cookie,
+				      enum fscache_cookie_trace where)
+{
+	int usage = atomic_inc_return(&cookie->usage);
+
+	trace_fscache_cookie(cookie, where, usage);
+}
+
+/*
+ * get an extra reference to a netfs retrieval context
+ */
+static inline
+void *fscache_get_context(struct fscache_cookie *cookie, void *context)
+{
+	if (cookie->def->get_context)
+		cookie->def->get_context(cookie->netfs_data, context);
+	return context;
+}
+
+/*
+ * release a reference to a netfs retrieval context
+ */
+static inline
+void fscache_put_context(struct fscache_cookie *cookie, void *context)
+{
+	if (cookie->def->put_context)
+		cookie->def->put_context(cookie->netfs_data, context);
+}
+
+/*
+ * Update the auxiliary data on a cookie.
+ */
+static inline
+void fscache_update_aux(struct fscache_cookie *cookie, const void *aux_data)
+{
+	void *p;
+
+	if (!aux_data)
+		return;
+	if (cookie->aux_len <= sizeof(cookie->inline_aux))
+		p = cookie->inline_aux;
+	else
+		p = cookie->aux;
+
+	if (memcmp(p, aux_data, cookie->aux_len) != 0) {
+		memcpy(p, aux_data, cookie->aux_len);
+		set_bit(FSCACHE_COOKIE_AUX_UPDATED, &cookie->flags);
+	}
+}
+
+/*****************************************************************************/
+/*
+ * debug tracing
+ */
+#define dbgprintk(FMT, ...) \
+	printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+
+#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
+
+#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
+
+#ifdef __KDEBUG
+#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
+#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
+#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
+
+#elif defined(CONFIG_FSCACHE_DEBUG)
+#define _enter(FMT, ...)			\
+do {						\
+	if (__do_kdebug(ENTER))			\
+		kenter(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _leave(FMT, ...)			\
+do {						\
+	if (__do_kdebug(LEAVE))			\
+		kleave(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _debug(FMT, ...)			\
+do {						\
+	if (__do_kdebug(DEBUG))			\
+		kdebug(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#else
+#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
+#endif
+
+/*
+ * determine whether a particular optional debugging point should be logged
+ * - we need to go through three steps to persuade cpp to correctly join the
+ *   shorthand in FSCACHE_DEBUG_LEVEL with its prefix
+ */
+#define ____do_kdebug(LEVEL, POINT) \
+	unlikely((fscache_debug & \
+		  (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3))))
+#define ___do_kdebug(LEVEL, POINT) \
+	____do_kdebug(LEVEL, POINT)
+#define __do_kdebug(POINT) \
+	___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT)
+
+#define FSCACHE_DEBUG_CACHE	0
+#define FSCACHE_DEBUG_COOKIE	1
+#define FSCACHE_DEBUG_PAGE	2
+#define FSCACHE_DEBUG_OPERATION	3
+
+#define FSCACHE_POINT_ENTER	1
+#define FSCACHE_POINT_LEAVE	2
+#define FSCACHE_POINT_DEBUG	4
+
+#ifndef FSCACHE_DEBUG_LEVEL
+#define FSCACHE_DEBUG_LEVEL CACHE
+#endif
+
+/*
+ * assertions
+ */
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		pr_err("%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIF(C, X)							\
+do {									\
+	if (unlikely((C) && !(X))) {					\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		pr_err("\n");					\
+		pr_err("Assertion failed\n");	\
+		pr_err("%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#else
+
+#define ASSERT(X)			do {} while (0)
+#define ASSERTCMP(X, OP, Y)		do {} while (0)
+#define ASSERTIF(C, X)			do {} while (0)
+#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
+
+#endif /* assert or not */
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
new file mode 100644
index 000000000..aa49234e9
--- /dev/null
+++ b/fs/fscache/main.c
@@ -0,0 +1,235 @@
+/* General filesystem local caching manager
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#define CREATE_TRACE_POINTS
+#include "internal.h"
+
+MODULE_DESCRIPTION("FS Cache Manager");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+unsigned fscache_defer_lookup = 1;
+module_param_named(defer_lookup, fscache_defer_lookup, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_defer_lookup,
+		 "Defer cookie lookup to background thread");
+
+unsigned fscache_defer_create = 1;
+module_param_named(defer_create, fscache_defer_create, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_defer_create,
+		 "Defer cookie creation to background thread");
+
+unsigned fscache_debug;
+module_param_named(debug, fscache_debug, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_debug,
+		 "FS-Cache debugging mask");
+
+struct kobject *fscache_root;
+struct workqueue_struct *fscache_object_wq;
+struct workqueue_struct *fscache_op_wq;
+
+DEFINE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
+
+/* these values serve as lower bounds, will be adjusted in fscache_init() */
+static unsigned fscache_object_max_active = 4;
+static unsigned fscache_op_max_active = 2;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table_header *fscache_sysctl_header;
+
+static int fscache_max_active_sysctl(struct ctl_table *table, int write,
+				     void __user *buffer,
+				     size_t *lenp, loff_t *ppos)
+{
+	struct workqueue_struct **wqp = table->extra1;
+	unsigned int *datap = table->data;
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret == 0)
+		workqueue_set_max_active(*wqp, *datap);
+	return ret;
+}
+
+static struct ctl_table fscache_sysctls[] = {
+	{
+		.procname	= "object_max_active",
+		.data		= &fscache_object_max_active,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= fscache_max_active_sysctl,
+		.extra1		= &fscache_object_wq,
+	},
+	{
+		.procname	= "operation_max_active",
+		.data		= &fscache_op_max_active,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= fscache_max_active_sysctl,
+		.extra1		= &fscache_op_wq,
+	},
+	{}
+};
+
+static struct ctl_table fscache_sysctls_root[] = {
+	{
+		.procname	= "fscache",
+		.mode		= 0555,
+		.child		= fscache_sysctls,
+	},
+	{}
+};
+#endif
+
+/*
+ * Mixing scores (in bits) for (7,20):
+ * Input delta: 1-bit      2-bit
+ * 1 round:     330.3     9201.6
+ * 2 rounds:   1246.4    25475.4
+ * 3 rounds:   1907.1    31295.1
+ * 4 rounds:   2042.3    31718.6
+ * Perfect:    2048      31744
+ *            (32*64)   (32*31/2 * 64)
+ */
+#define HASH_MIX(x, y, a)	\
+	(	x ^= (a),	\
+	y ^= x,	x = rol32(x, 7),\
+	x += y,	y = rol32(y,20),\
+	y *= 9			)
+
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
+{
+	/* Use arch-optimized multiply if one exists */
+	return __hash_32(y ^ __hash_32(x));
+}
+
+/*
+ * Generate a hash.  This is derived from full_name_hash(), but we want to be
+ * sure it is arch independent and that it doesn't change as bits of the
+ * computed hash value might appear on disk.  The caller also guarantees that
+ * the hashed data will be a series of aligned 32-bit words.
+ */
+unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n)
+{
+	unsigned int a, x = 0, y = salt;
+
+	for (; n; n--) {
+		a = *data++;
+		HASH_MIX(x, y, a);
+	}
+	return fold_hash(x, y);
+}
+
+/*
+ * initialise the fs caching module
+ */
+static int __init fscache_init(void)
+{
+	unsigned int nr_cpus = num_possible_cpus();
+	unsigned int cpu;
+	int ret;
+
+	fscache_object_max_active =
+		clamp_val(nr_cpus,
+			  fscache_object_max_active, WQ_UNBOUND_MAX_ACTIVE);
+
+	ret = -ENOMEM;
+	fscache_object_wq = alloc_workqueue("fscache_object", WQ_UNBOUND,
+					    fscache_object_max_active);
+	if (!fscache_object_wq)
+		goto error_object_wq;
+
+	fscache_op_max_active =
+		clamp_val(fscache_object_max_active / 2,
+			  fscache_op_max_active, WQ_UNBOUND_MAX_ACTIVE);
+
+	ret = -ENOMEM;
+	fscache_op_wq = alloc_workqueue("fscache_operation", WQ_UNBOUND,
+					fscache_op_max_active);
+	if (!fscache_op_wq)
+		goto error_op_wq;
+
+	for_each_possible_cpu(cpu)
+		init_waitqueue_head(&per_cpu(fscache_object_cong_wait, cpu));
+
+	ret = fscache_proc_init();
+	if (ret < 0)
+		goto error_proc;
+
+#ifdef CONFIG_SYSCTL
+	ret = -ENOMEM;
+	fscache_sysctl_header = register_sysctl_table(fscache_sysctls_root);
+	if (!fscache_sysctl_header)
+		goto error_sysctl;
+#endif
+
+	fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar",
+					       sizeof(struct fscache_cookie),
+					       0, 0, NULL);
+	if (!fscache_cookie_jar) {
+		pr_notice("Failed to allocate a cookie jar\n");
+		ret = -ENOMEM;
+		goto error_cookie_jar;
+	}
+
+	fscache_root = kobject_create_and_add("fscache", kernel_kobj);
+	if (!fscache_root)
+		goto error_kobj;
+
+	pr_notice("Loaded\n");
+	return 0;
+
+error_kobj:
+	kmem_cache_destroy(fscache_cookie_jar);
+error_cookie_jar:
+#ifdef CONFIG_SYSCTL
+	unregister_sysctl_table(fscache_sysctl_header);
+error_sysctl:
+#endif
+	fscache_proc_cleanup();
+error_proc:
+	destroy_workqueue(fscache_op_wq);
+error_op_wq:
+	destroy_workqueue(fscache_object_wq);
+error_object_wq:
+	return ret;
+}
+
+fs_initcall(fscache_init);
+
+/*
+ * clean up on module removal
+ */
+static void __exit fscache_exit(void)
+{
+	_enter("");
+
+	kobject_put(fscache_root);
+	kmem_cache_destroy(fscache_cookie_jar);
+#ifdef CONFIG_SYSCTL
+	unregister_sysctl_table(fscache_sysctl_header);
+#endif
+	fscache_proc_cleanup();
+	destroy_workqueue(fscache_op_wq);
+	destroy_workqueue(fscache_object_wq);
+	pr_notice("Unloaded\n");
+}
+
+module_exit(fscache_exit);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
new file mode 100644
index 000000000..c2f605483
--- /dev/null
+++ b/fs/fscache/netfs.c
@@ -0,0 +1,78 @@
+/* FS-Cache netfs (client) registration
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+/*
+ * register a network filesystem for caching
+ */
+int __fscache_register_netfs(struct fscache_netfs *netfs)
+{
+	struct fscache_cookie *candidate, *cookie;
+
+	_enter("{%s}", netfs->name);
+
+	/* allocate a cookie for the primary index */
+	candidate = fscache_alloc_cookie(&fscache_fsdef_index,
+					 &fscache_fsdef_netfs_def,
+					 netfs->name, strlen(netfs->name),
+					 &netfs->version, sizeof(netfs->version),
+					 netfs, 0);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	candidate->flags = 1 << FSCACHE_COOKIE_ENABLED;
+
+	/* check the netfs type is not already present */
+	cookie = fscache_hash_cookie(candidate);
+	if (!cookie)
+		goto already_registered;
+	if (cookie != candidate) {
+		trace_fscache_cookie(candidate, fscache_cookie_discard, 1);
+		fscache_free_cookie(candidate);
+	}
+
+	fscache_cookie_get(cookie->parent, fscache_cookie_get_register_netfs);
+	atomic_inc(&cookie->parent->n_children);
+
+	netfs->primary_index = cookie;
+
+	pr_notice("Netfs '%s' registered for caching\n", netfs->name);
+	trace_fscache_netfs(netfs);
+	_leave(" = 0");
+	return 0;
+
+already_registered:
+	fscache_cookie_put(candidate, fscache_cookie_put_dup_netfs);
+	_leave(" = -EEXIST");
+	return -EEXIST;
+}
+EXPORT_SYMBOL(__fscache_register_netfs);
+
+/*
+ * unregister a network filesystem from the cache
+ * - all cookies must have been released first
+ */
+void __fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+	_enter("{%s.%u}", netfs->name, netfs->version);
+
+	fscache_relinquish_cookie(netfs->primary_index, NULL, false);
+	pr_notice("Netfs '%s' unregistered from caching\n", netfs->name);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_unregister_netfs);
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
new file mode 100644
index 000000000..43e6e28c1
--- /dev/null
+++ b/fs/fscache/object-list.c
@@ -0,0 +1,417 @@
+/* Global fscache object list maintainer and viewer
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/key.h>
+#include <keys/user-type.h>
+#include "internal.h"
+
+static struct rb_root fscache_object_list;
+static DEFINE_RWLOCK(fscache_object_list_lock);
+
+struct fscache_objlist_data {
+	unsigned long	config;		/* display configuration */
+#define FSCACHE_OBJLIST_CONFIG_KEY	0x00000001	/* show object keys */
+#define FSCACHE_OBJLIST_CONFIG_AUX	0x00000002	/* show object auxdata */
+#define FSCACHE_OBJLIST_CONFIG_COOKIE	0x00000004	/* show objects with cookies */
+#define FSCACHE_OBJLIST_CONFIG_NOCOOKIE	0x00000008	/* show objects without cookies */
+#define FSCACHE_OBJLIST_CONFIG_BUSY	0x00000010	/* show busy objects */
+#define FSCACHE_OBJLIST_CONFIG_IDLE	0x00000020	/* show idle objects */
+#define FSCACHE_OBJLIST_CONFIG_PENDWR	0x00000040	/* show objects with pending writes */
+#define FSCACHE_OBJLIST_CONFIG_NOPENDWR	0x00000080	/* show objects without pending writes */
+#define FSCACHE_OBJLIST_CONFIG_READS	0x00000100	/* show objects with active reads */
+#define FSCACHE_OBJLIST_CONFIG_NOREADS	0x00000200	/* show objects without active reads */
+#define FSCACHE_OBJLIST_CONFIG_EVENTS	0x00000400	/* show objects with events */
+#define FSCACHE_OBJLIST_CONFIG_NOEVENTS	0x00000800	/* show objects without no events */
+#define FSCACHE_OBJLIST_CONFIG_WORK	0x00001000	/* show objects with work */
+#define FSCACHE_OBJLIST_CONFIG_NOWORK	0x00002000	/* show objects without work */
+};
+
+/*
+ * Add an object to the object list
+ * - we use the address of the fscache_object structure as the key into the
+ *   tree
+ */
+void fscache_objlist_add(struct fscache_object *obj)
+{
+	struct fscache_object *xobj;
+	struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL;
+
+	ASSERT(RB_EMPTY_NODE(&obj->objlist_link));
+
+	write_lock(&fscache_object_list_lock);
+
+	while (*p) {
+		parent = *p;
+		xobj = rb_entry(parent, struct fscache_object, objlist_link);
+
+		if (obj < xobj)
+			p = &(*p)->rb_left;
+		else if (obj > xobj)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&obj->objlist_link, parent, p);
+	rb_insert_color(&obj->objlist_link, &fscache_object_list);
+
+	write_unlock(&fscache_object_list_lock);
+}
+
+/*
+ * Remove an object from the object list.
+ */
+void fscache_objlist_remove(struct fscache_object *obj)
+{
+	if (RB_EMPTY_NODE(&obj->objlist_link))
+		return;
+
+	write_lock(&fscache_object_list_lock);
+
+	BUG_ON(RB_EMPTY_ROOT(&fscache_object_list));
+	rb_erase(&obj->objlist_link, &fscache_object_list);
+
+	write_unlock(&fscache_object_list_lock);
+}
+
+/*
+ * find the object in the tree on or after the specified index
+ */
+static struct fscache_object *fscache_objlist_lookup(loff_t *_pos)
+{
+	struct fscache_object *pobj, *obj = NULL, *minobj = NULL;
+	struct rb_node *p;
+	unsigned long pos;
+
+	if (*_pos >= (unsigned long) ERR_PTR(-ENOENT))
+		return NULL;
+	pos = *_pos;
+
+	/* banners (can't represent line 0 by pos 0 as that would involve
+	 * returning a NULL pointer) */
+	if (pos == 0)
+		return (struct fscache_object *)(long)++(*_pos);
+	if (pos < 3)
+		return (struct fscache_object *)pos;
+
+	pobj = (struct fscache_object *)pos;
+	p = fscache_object_list.rb_node;
+	while (p) {
+		obj = rb_entry(p, struct fscache_object, objlist_link);
+		if (pobj < obj) {
+			if (!minobj || minobj > obj)
+				minobj = obj;
+			p = p->rb_left;
+		} else if (pobj > obj) {
+			p = p->rb_right;
+		} else {
+			minobj = obj;
+			break;
+		}
+		obj = NULL;
+	}
+
+	if (!minobj)
+		*_pos = (unsigned long) ERR_PTR(-ENOENT);
+	else if (minobj != obj)
+		*_pos = (unsigned long) minobj;
+	return minobj;
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *fscache_objlist_start(struct seq_file *m, loff_t *_pos)
+	__acquires(&fscache_object_list_lock)
+{
+	read_lock(&fscache_object_list_lock);
+	return fscache_objlist_lookup(_pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *fscache_objlist_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	(*_pos)++;
+	return fscache_objlist_lookup(_pos);
+}
+
+/*
+ * clean up after reading
+ */
+static void fscache_objlist_stop(struct seq_file *m, void *v)
+	__releases(&fscache_object_list_lock)
+{
+	read_unlock(&fscache_object_list_lock);
+}
+
+/*
+ * display an object
+ */
+static int fscache_objlist_show(struct seq_file *m, void *v)
+{
+	struct fscache_objlist_data *data = m->private;
+	struct fscache_object *obj = v;
+	struct fscache_cookie *cookie;
+	unsigned long config = data->config;
+	char _type[3], *type;
+	u8 *p;
+
+	if ((unsigned long) v == 1) {
+		seq_puts(m, "OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS"
+			 " EM EV FL S"
+			 " | NETFS_COOKIE_DEF TY FL NETFS_DATA");
+		if (config & (FSCACHE_OBJLIST_CONFIG_KEY |
+			      FSCACHE_OBJLIST_CONFIG_AUX))
+			seq_puts(m, "       ");
+		if (config & FSCACHE_OBJLIST_CONFIG_KEY)
+			seq_puts(m, "OBJECT_KEY");
+		if ((config & (FSCACHE_OBJLIST_CONFIG_KEY |
+			       FSCACHE_OBJLIST_CONFIG_AUX)) ==
+		    (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX))
+			seq_puts(m, ", ");
+		if (config & FSCACHE_OBJLIST_CONFIG_AUX)
+			seq_puts(m, "AUX_DATA");
+		seq_puts(m, "\n");
+		return 0;
+	}
+
+	if ((unsigned long) v == 2) {
+		seq_puts(m, "======== ======== ==== ===== === === === == ====="
+			 " == == == ="
+			 " | ================ == == ================");
+		if (config & (FSCACHE_OBJLIST_CONFIG_KEY |
+			      FSCACHE_OBJLIST_CONFIG_AUX))
+			seq_puts(m, " ================");
+		seq_puts(m, "\n");
+		return 0;
+	}
+
+	/* filter out any unwanted objects */
+#define FILTER(criterion, _yes, _no)					\
+	do {								\
+		unsigned long yes = FSCACHE_OBJLIST_CONFIG_##_yes;	\
+		unsigned long no = FSCACHE_OBJLIST_CONFIG_##_no;	\
+		if (criterion) {					\
+			if (!(config & yes))				\
+				return 0;				\
+		} else {						\
+			if (!(config & no))				\
+				return 0;				\
+		}							\
+	} while(0)
+
+	cookie = obj->cookie;
+	if (~config) {
+		FILTER(cookie->def,
+		       COOKIE, NOCOOKIE);
+		FILTER(fscache_object_is_active(obj) ||
+		       obj->n_ops != 0 ||
+		       obj->n_obj_ops != 0 ||
+		       obj->flags ||
+		       !list_empty(&obj->dependents),
+		       BUSY, IDLE);
+		FILTER(test_bit(FSCACHE_OBJECT_PENDING_WRITE, &obj->flags),
+		       PENDWR, NOPENDWR);
+		FILTER(atomic_read(&obj->n_reads),
+		       READS, NOREADS);
+		FILTER(obj->events & obj->event_mask,
+		       EVENTS, NOEVENTS);
+		FILTER(work_busy(&obj->work), WORK, NOWORK);
+	}
+
+	seq_printf(m,
+		   "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %2lx %1x | ",
+		   obj->debug_id,
+		   obj->parent ? obj->parent->debug_id : -1,
+		   obj->state->short_name,
+		   obj->n_children,
+		   obj->n_ops,
+		   obj->n_obj_ops,
+		   obj->n_in_progress,
+		   obj->n_exclusive,
+		   atomic_read(&obj->n_reads),
+		   obj->event_mask,
+		   obj->events,
+		   obj->flags,
+		   work_busy(&obj->work));
+
+	if (fscache_use_cookie(obj)) {
+		uint16_t keylen = 0, auxlen = 0;
+
+		switch (cookie->type) {
+		case 0:
+			type = "IX";
+			break;
+		case 1:
+			type = "DT";
+			break;
+		default:
+			snprintf(_type, sizeof(_type), "%02u",
+				 cookie->type);
+			type = _type;
+			break;
+		}
+
+		seq_printf(m, "%-16s %s %2lx %16p",
+			   cookie->def->name,
+			   type,
+			   cookie->flags,
+			   cookie->netfs_data);
+
+		if (config & FSCACHE_OBJLIST_CONFIG_KEY)
+			keylen = cookie->key_len;
+
+		if (config & FSCACHE_OBJLIST_CONFIG_AUX)
+			auxlen = cookie->aux_len;
+
+		if (keylen > 0 || auxlen > 0) {
+			seq_puts(m, " ");
+			p = keylen <= sizeof(cookie->inline_key) ?
+				cookie->inline_key : cookie->key;
+			for (; keylen > 0; keylen--)
+				seq_printf(m, "%02x", *p++);
+			if (auxlen > 0) {
+				if (config & FSCACHE_OBJLIST_CONFIG_KEY)
+					seq_puts(m, ", ");
+				p = auxlen <= sizeof(cookie->inline_aux) ?
+					cookie->inline_aux : cookie->aux;
+				for (; auxlen > 0; auxlen--)
+					seq_printf(m, "%02x", *p++);
+			}
+		}
+
+		seq_puts(m, "\n");
+		fscache_unuse_cookie(obj);
+	} else {
+		seq_puts(m, "<no_netfs>\n");
+	}
+	return 0;
+}
+
+static const struct seq_operations fscache_objlist_ops = {
+	.start		= fscache_objlist_start,
+	.stop		= fscache_objlist_stop,
+	.next		= fscache_objlist_next,
+	.show		= fscache_objlist_show,
+};
+
+/*
+ * get the configuration for filtering the list
+ */
+static void fscache_objlist_config(struct fscache_objlist_data *data)
+{
+#ifdef CONFIG_KEYS
+	const struct user_key_payload *confkey;
+	unsigned long config;
+	struct key *key;
+	const char *buf;
+	int len;
+
+	key = request_key(&key_type_user, "fscache:objlist", NULL);
+	if (IS_ERR(key))
+		goto no_config;
+
+	config = 0;
+	rcu_read_lock();
+
+	confkey = user_key_payload_rcu(key);
+	if (!confkey) {
+		/* key was revoked */
+		rcu_read_unlock();
+		key_put(key);
+		goto no_config;
+	}
+
+	buf = confkey->data;
+
+	for (len = confkey->datalen - 1; len >= 0; len--) {
+		switch (buf[len]) {
+		case 'K': config |= FSCACHE_OBJLIST_CONFIG_KEY;		break;
+		case 'A': config |= FSCACHE_OBJLIST_CONFIG_AUX;		break;
+		case 'C': config |= FSCACHE_OBJLIST_CONFIG_COOKIE;	break;
+		case 'c': config |= FSCACHE_OBJLIST_CONFIG_NOCOOKIE;	break;
+		case 'B': config |= FSCACHE_OBJLIST_CONFIG_BUSY;	break;
+		case 'b': config |= FSCACHE_OBJLIST_CONFIG_IDLE;	break;
+		case 'W': config |= FSCACHE_OBJLIST_CONFIG_PENDWR;	break;
+		case 'w': config |= FSCACHE_OBJLIST_CONFIG_NOPENDWR;	break;
+		case 'R': config |= FSCACHE_OBJLIST_CONFIG_READS;	break;
+		case 'r': config |= FSCACHE_OBJLIST_CONFIG_NOREADS;	break;
+		case 'S': config |= FSCACHE_OBJLIST_CONFIG_WORK;	break;
+		case 's': config |= FSCACHE_OBJLIST_CONFIG_NOWORK;	break;
+		}
+	}
+
+	rcu_read_unlock();
+	key_put(key);
+
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK;
+
+	data->config = config;
+	return;
+
+no_config:
+#endif
+	data->config = ULONG_MAX;
+}
+
+/*
+ * open "/proc/fs/fscache/objects" to provide a list of active objects
+ * - can be configured by a user-defined key added to the caller's keyrings
+ */
+static int fscache_objlist_open(struct inode *inode, struct file *file)
+{
+	struct fscache_objlist_data *data;
+
+	data = __seq_open_private(file, &fscache_objlist_ops, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	/* get the configuration key */
+	fscache_objlist_config(data);
+
+	return 0;
+}
+
+/*
+ * clean up on close
+ */
+static int fscache_objlist_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+
+	kfree(m->private);
+	m->private = NULL;
+	return seq_release(inode, file);
+}
+
+const struct file_operations fscache_objlist_fops = {
+	.open		= fscache_objlist_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= fscache_objlist_release,
+};
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
new file mode 100644
index 000000000..6d9cb1719
--- /dev/null
+++ b/fs/fscache/object.c
@@ -0,0 +1,1137 @@
+/* FS-Cache object state machine handler
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/object.txt for a description of the
+ * object state machine and the in-kernel representations.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/prefetch.h>
+#include "internal.h"
+
+static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *, int);
+static const struct fscache_state *fscache_kill_dependents(struct fscache_object *, int);
+static const struct fscache_state *fscache_drop_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_initialise_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_invalidate_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *, int);
+static const struct fscache_state *fscache_kill_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_lookup_failure(struct fscache_object *, int);
+static const struct fscache_state *fscache_look_up_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
+static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
+static const struct fscache_state *fscache_update_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_dead(struct fscache_object *, int);
+
+#define __STATE_NAME(n) fscache_osm_##n
+#define STATE(n) (&__STATE_NAME(n))
+
+/*
+ * Define a work state.  Work states are execution states.  No event processing
+ * is performed by them.  The function attached to a work state returns a
+ * pointer indicating the next state to which the state machine should
+ * transition.  Returning NO_TRANSIT repeats the current state, but goes back
+ * to the scheduler first.
+ */
+#define WORK_STATE(n, sn, f) \
+	const struct fscache_state __STATE_NAME(n) = {			\
+		.name = #n,						\
+		.short_name = sn,					\
+		.work = f						\
+	}
+
+/*
+ * Returns from work states.
+ */
+#define transit_to(state) ({ prefetch(&STATE(state)->work); STATE(state); })
+
+#define NO_TRANSIT ((struct fscache_state *)NULL)
+
+/*
+ * Define a wait state.  Wait states are event processing states.  No execution
+ * is performed by them.  Wait states are just tables of "if event X occurs,
+ * clear it and transition to state Y".  The dispatcher returns to the
+ * scheduler if none of the events in which the wait state has an interest are
+ * currently pending.
+ */
+#define WAIT_STATE(n, sn, ...) \
+	const struct fscache_state __STATE_NAME(n) = {			\
+		.name = #n,						\
+		.short_name = sn,					\
+		.work = NULL,						\
+		.transitions = { __VA_ARGS__, { 0, NULL } }		\
+	}
+
+#define TRANSIT_TO(state, emask) \
+	{ .events = (emask), .transit_to = STATE(state) }
+
+/*
+ * The object state machine.
+ */
+static WORK_STATE(INIT_OBJECT,		"INIT", fscache_initialise_object);
+static WORK_STATE(PARENT_READY,		"PRDY", fscache_parent_ready);
+static WORK_STATE(ABORT_INIT,		"ABRT", fscache_abort_initialisation);
+static WORK_STATE(LOOK_UP_OBJECT,	"LOOK", fscache_look_up_object);
+static WORK_STATE(CREATE_OBJECT,	"CRTO", fscache_look_up_object);
+static WORK_STATE(OBJECT_AVAILABLE,	"AVBL", fscache_object_available);
+static WORK_STATE(JUMPSTART_DEPS,	"JUMP", fscache_jumpstart_dependents);
+
+static WORK_STATE(INVALIDATE_OBJECT,	"INVL", fscache_invalidate_object);
+static WORK_STATE(UPDATE_OBJECT,	"UPDT", fscache_update_object);
+
+static WORK_STATE(LOOKUP_FAILURE,	"LCFL", fscache_lookup_failure);
+static WORK_STATE(KILL_OBJECT,		"KILL", fscache_kill_object);
+static WORK_STATE(KILL_DEPENDENTS,	"KDEP", fscache_kill_dependents);
+static WORK_STATE(DROP_OBJECT,		"DROP", fscache_drop_object);
+static WORK_STATE(OBJECT_DEAD,		"DEAD", fscache_object_dead);
+
+static WAIT_STATE(WAIT_FOR_INIT,	"?INI",
+		  TRANSIT_TO(INIT_OBJECT,	1 << FSCACHE_OBJECT_EV_NEW_CHILD));
+
+static WAIT_STATE(WAIT_FOR_PARENT,	"?PRN",
+		  TRANSIT_TO(PARENT_READY,	1 << FSCACHE_OBJECT_EV_PARENT_READY));
+
+static WAIT_STATE(WAIT_FOR_CMD,		"?CMD",
+		  TRANSIT_TO(INVALIDATE_OBJECT,	1 << FSCACHE_OBJECT_EV_INVALIDATE),
+		  TRANSIT_TO(UPDATE_OBJECT,	1 << FSCACHE_OBJECT_EV_UPDATE),
+		  TRANSIT_TO(JUMPSTART_DEPS,	1 << FSCACHE_OBJECT_EV_NEW_CHILD));
+
+static WAIT_STATE(WAIT_FOR_CLEARANCE,	"?CLR",
+		  TRANSIT_TO(KILL_OBJECT,	1 << FSCACHE_OBJECT_EV_CLEARED));
+
+/*
+ * Out-of-band event transition tables.  These are for handling unexpected
+ * events, such as an I/O error.  If an OOB event occurs, the state machine
+ * clears and disables the event and forces a transition to the nominated work
+ * state (acurrently executing work states will complete first).
+ *
+ * In such a situation, object->state remembers the state the machine should
+ * have been in/gone to and returning NO_TRANSIT returns to that.
+ */
+static const struct fscache_transition fscache_osm_init_oob[] = {
+	   TRANSIT_TO(ABORT_INIT,
+		      (1 << FSCACHE_OBJECT_EV_ERROR) |
+		      (1 << FSCACHE_OBJECT_EV_KILL)),
+	   { 0, NULL }
+};
+
+static const struct fscache_transition fscache_osm_lookup_oob[] = {
+	   TRANSIT_TO(LOOKUP_FAILURE,
+		      (1 << FSCACHE_OBJECT_EV_ERROR) |
+		      (1 << FSCACHE_OBJECT_EV_KILL)),
+	   { 0, NULL }
+};
+
+static const struct fscache_transition fscache_osm_run_oob[] = {
+	   TRANSIT_TO(KILL_OBJECT,
+		      (1 << FSCACHE_OBJECT_EV_ERROR) |
+		      (1 << FSCACHE_OBJECT_EV_KILL)),
+	   { 0, NULL }
+};
+
+static int  fscache_get_object(struct fscache_object *,
+			       enum fscache_obj_ref_trace);
+static void fscache_put_object(struct fscache_object *,
+			       enum fscache_obj_ref_trace);
+static bool fscache_enqueue_dependents(struct fscache_object *, int);
+static void fscache_dequeue_object(struct fscache_object *);
+static void fscache_update_aux_data(struct fscache_object *);
+
+/*
+ * we need to notify the parent when an op completes that we had outstanding
+ * upon it
+ */
+static inline void fscache_done_parent_op(struct fscache_object *object)
+{
+	struct fscache_object *parent = object->parent;
+
+	_enter("OBJ%x {OBJ%x,%x}",
+	       object->debug_id, parent->debug_id, parent->n_ops);
+
+	spin_lock_nested(&parent->lock, 1);
+	parent->n_obj_ops--;
+	parent->n_ops--;
+	if (parent->n_ops == 0)
+		fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+	spin_unlock(&parent->lock);
+}
+
+/*
+ * Object state machine dispatcher.
+ */
+static void fscache_object_sm_dispatcher(struct fscache_object *object)
+{
+	const struct fscache_transition *t;
+	const struct fscache_state *state, *new_state;
+	unsigned long events, event_mask;
+	bool oob;
+	int event = -1;
+
+	ASSERT(object != NULL);
+
+	_enter("{OBJ%x,%s,%lx}",
+	       object->debug_id, object->state->name, object->events);
+
+	event_mask = object->event_mask;
+restart:
+	object->event_mask = 0; /* Mask normal event handling */
+	state = object->state;
+restart_masked:
+	events = object->events;
+
+	/* Handle any out-of-band events (typically an error) */
+	if (events & object->oob_event_mask) {
+		_debug("{OBJ%x} oob %lx",
+		       object->debug_id, events & object->oob_event_mask);
+		oob = true;
+		for (t = object->oob_table; t->events; t++) {
+			if (events & t->events) {
+				state = t->transit_to;
+				ASSERT(state->work != NULL);
+				event = fls(events & t->events) - 1;
+				__clear_bit(event, &object->oob_event_mask);
+				clear_bit(event, &object->events);
+				goto execute_work_state;
+			}
+		}
+	}
+	oob = false;
+
+	/* Wait states are just transition tables */
+	if (!state->work) {
+		if (events & event_mask) {
+			for (t = state->transitions; t->events; t++) {
+				if (events & t->events) {
+					new_state = t->transit_to;
+					event = fls(events & t->events) - 1;
+					trace_fscache_osm(object, state,
+							  true, false, event);
+					clear_bit(event, &object->events);
+					_debug("{OBJ%x} ev %d: %s -> %s",
+					       object->debug_id, event,
+					       state->name, new_state->name);
+					object->state = state = new_state;
+					goto execute_work_state;
+				}
+			}
+
+			/* The event mask didn't include all the tabled bits */
+			BUG();
+		}
+		/* Randomly woke up */
+		goto unmask_events;
+	}
+
+execute_work_state:
+	_debug("{OBJ%x} exec %s", object->debug_id, state->name);
+
+	trace_fscache_osm(object, state, false, oob, event);
+	new_state = state->work(object, event);
+	event = -1;
+	if (new_state == NO_TRANSIT) {
+		_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
+		if (unlikely(state == STATE(OBJECT_DEAD))) {
+			_leave(" [dead]");
+			return;
+		}
+		fscache_enqueue_object(object);
+		event_mask = object->oob_event_mask;
+		goto unmask_events;
+	}
+
+	_debug("{OBJ%x} %s -> %s",
+	       object->debug_id, state->name, new_state->name);
+	object->state = state = new_state;
+
+	if (state->work) {
+		if (unlikely(state == STATE(OBJECT_DEAD))) {
+			_leave(" [dead]");
+			return;
+		}
+		goto restart_masked;
+	}
+
+	/* Transited to wait state */
+	event_mask = object->oob_event_mask;
+	for (t = state->transitions; t->events; t++)
+		event_mask |= t->events;
+
+unmask_events:
+	object->event_mask = event_mask;
+	smp_mb();
+	events = object->events;
+	if (events & event_mask)
+		goto restart;
+	_leave(" [msk %lx]", event_mask);
+}
+
+/*
+ * execute an object
+ */
+static void fscache_object_work_func(struct work_struct *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+	unsigned long start;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	start = jiffies;
+	fscache_object_sm_dispatcher(object);
+	fscache_hist(fscache_objs_histogram, start);
+	fscache_put_object(object, fscache_obj_put_work);
+}
+
+/**
+ * fscache_object_init - Initialise a cache object description
+ * @object: Object description
+ * @cookie: Cookie object will be attached to
+ * @cache: Cache in which backing object will be found
+ *
+ * Initialise a cache object description to its basic values.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_object_init(struct fscache_object *object,
+			 struct fscache_cookie *cookie,
+			 struct fscache_cache *cache)
+{
+	const struct fscache_transition *t;
+
+	atomic_inc(&cache->object_count);
+
+	object->state = STATE(WAIT_FOR_INIT);
+	object->oob_table = fscache_osm_init_oob;
+	object->flags = 1 << FSCACHE_OBJECT_IS_LIVE;
+	spin_lock_init(&object->lock);
+	INIT_LIST_HEAD(&object->cache_link);
+	INIT_HLIST_NODE(&object->cookie_link);
+	INIT_WORK(&object->work, fscache_object_work_func);
+	INIT_LIST_HEAD(&object->dependents);
+	INIT_LIST_HEAD(&object->dep_link);
+	INIT_LIST_HEAD(&object->pending_ops);
+	object->n_children = 0;
+	object->n_ops = object->n_in_progress = object->n_exclusive = 0;
+	object->events = 0;
+	object->store_limit = 0;
+	object->store_limit_l = 0;
+	object->cache = cache;
+	object->cookie = cookie;
+	fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
+	object->parent = NULL;
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	RB_CLEAR_NODE(&object->objlist_link);
+#endif
+
+	object->oob_event_mask = 0;
+	for (t = object->oob_table; t->events; t++)
+		object->oob_event_mask |= t->events;
+	object->event_mask = object->oob_event_mask;
+	for (t = object->state->transitions; t->events; t++)
+		object->event_mask |= t->events;
+}
+EXPORT_SYMBOL(fscache_object_init);
+
+/*
+ * Mark the object as no longer being live, making sure that we synchronise
+ * against op submission.
+ */
+static inline void fscache_mark_object_dead(struct fscache_object *object)
+{
+	spin_lock(&object->lock);
+	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	spin_unlock(&object->lock);
+}
+
+/*
+ * Abort object initialisation before we start it.
+ */
+static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *object,
+								int event)
+{
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	object->oob_event_mask = 0;
+	fscache_dequeue_object(object);
+	return transit_to(KILL_OBJECT);
+}
+
+/*
+ * initialise an object
+ * - check the specified object's parent to see if we can make use of it
+ *   immediately to do a creation
+ * - we may need to start the process of creating a parent and we need to wait
+ *   for the parent's lookup and creation to complete if it's not there yet
+ */
+static const struct fscache_state *fscache_initialise_object(struct fscache_object *object,
+							     int event)
+{
+	struct fscache_object *parent;
+	bool success;
+
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	ASSERT(list_empty(&object->dep_link));
+
+	parent = object->parent;
+	if (!parent) {
+		_leave(" [no parent]");
+		return transit_to(DROP_OBJECT);
+	}
+
+	_debug("parent: %s of:%lx", parent->state->name, parent->flags);
+
+	if (fscache_object_is_dying(parent)) {
+		_leave(" [bad parent]");
+		return transit_to(DROP_OBJECT);
+	}
+
+	if (fscache_object_is_available(parent)) {
+		_leave(" [ready]");
+		return transit_to(PARENT_READY);
+	}
+
+	_debug("wait");
+
+	spin_lock(&parent->lock);
+	fscache_stat(&fscache_n_cop_grab_object);
+	success = false;
+	if (fscache_object_is_live(parent) &&
+	    object->cache->ops->grab_object(object, fscache_obj_get_add_to_deps)) {
+		list_add(&object->dep_link, &parent->dependents);
+		success = true;
+	}
+	fscache_stat_d(&fscache_n_cop_grab_object);
+	spin_unlock(&parent->lock);
+	if (!success) {
+		_leave(" [grab failed]");
+		return transit_to(DROP_OBJECT);
+	}
+
+	/* fscache_acquire_non_index_cookie() uses this
+	 * to wake the chain up */
+	fscache_raise_event(parent, FSCACHE_OBJECT_EV_NEW_CHILD);
+	_leave(" [wait]");
+	return transit_to(WAIT_FOR_PARENT);
+}
+
+/*
+ * Once the parent object is ready, we should kick off our lookup op.
+ */
+static const struct fscache_state *fscache_parent_ready(struct fscache_object *object,
+							int event)
+{
+	struct fscache_object *parent = object->parent;
+
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	ASSERT(parent != NULL);
+
+	spin_lock(&parent->lock);
+	parent->n_ops++;
+	parent->n_obj_ops++;
+	object->lookup_jif = jiffies;
+	spin_unlock(&parent->lock);
+
+	_leave("");
+	return transit_to(LOOK_UP_OBJECT);
+}
+
+/*
+ * look an object up in the cache from which it was allocated
+ * - we hold an "access lock" on the parent object, so the parent object cannot
+ *   be withdrawn by either party till we've finished
+ */
+static const struct fscache_state *fscache_look_up_object(struct fscache_object *object,
+							  int event)
+{
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_object *parent = object->parent;
+	int ret;
+
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	object->oob_table = fscache_osm_lookup_oob;
+
+	ASSERT(parent != NULL);
+	ASSERTCMP(parent->n_ops, >, 0);
+	ASSERTCMP(parent->n_obj_ops, >, 0);
+
+	/* make sure the parent is still available */
+	ASSERT(fscache_object_is_available(parent));
+
+	if (fscache_object_is_dying(parent) ||
+	    test_bit(FSCACHE_IOERROR, &object->cache->flags) ||
+	    !fscache_use_cookie(object)) {
+		_leave(" [unavailable]");
+		return transit_to(LOOKUP_FAILURE);
+	}
+
+	_debug("LOOKUP \"%s\" in \"%s\"",
+	       cookie->def->name, object->cache->tag->name);
+
+	fscache_stat(&fscache_n_object_lookups);
+	fscache_stat(&fscache_n_cop_lookup_object);
+	ret = object->cache->ops->lookup_object(object);
+	fscache_stat_d(&fscache_n_cop_lookup_object);
+
+	fscache_unuse_cookie(object);
+
+	if (ret == -ETIMEDOUT) {
+		/* probably stuck behind another object, so move this one to
+		 * the back of the queue */
+		fscache_stat(&fscache_n_object_lookups_timed_out);
+		_leave(" [timeout]");
+		return NO_TRANSIT;
+	}
+
+	if (ret < 0) {
+		_leave(" [error]");
+		return transit_to(LOOKUP_FAILURE);
+	}
+
+	_leave(" [ok]");
+	return transit_to(OBJECT_AVAILABLE);
+}
+
+/**
+ * fscache_object_lookup_negative - Note negative cookie lookup
+ * @object: Object pointing to cookie to mark
+ *
+ * Note negative lookup, permitting those waiting to read data from an already
+ * existing backing object to continue as there's no data for them to read.
+ */
+void fscache_object_lookup_negative(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x,%s}", object->debug_id, object->state->name);
+
+	if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
+		fscache_stat(&fscache_n_object_lookups_negative);
+
+		/* Allow write requests to begin stacking up and read requests to begin
+		 * returning ENODATA.
+		 */
+		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+		clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+
+		_debug("wake up lookup %p", &cookie->flags);
+		clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+	}
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_object_lookup_negative);
+
+/**
+ * fscache_obtained_object - Note successful object lookup or creation
+ * @object: Object pointing to cookie to mark
+ *
+ * Note successful lookup and/or creation, permitting those waiting to write
+ * data to a backing object to continue.
+ *
+ * Note that after calling this, an object's cookie may be relinquished by the
+ * netfs, and so must be accessed with object lock held.
+ */
+void fscache_obtained_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x,%s}", object->debug_id, object->state->name);
+
+	/* if we were still looking up, then we must have a positive lookup
+	 * result, in which case there may be data available */
+	if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
+		fscache_stat(&fscache_n_object_lookups_positive);
+
+		/* We do (presumably) have data */
+		clear_bit_unlock(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+		clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+
+		/* Allow write requests to begin stacking up and read requests
+		 * to begin shovelling data.
+		 */
+		clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+	} else {
+		fscache_stat(&fscache_n_object_created);
+	}
+
+	set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags);
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_obtained_object);
+
+/*
+ * handle an object that has just become available
+ */
+static const struct fscache_state *fscache_object_available(struct fscache_object *object,
+							    int event)
+{
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	object->oob_table = fscache_osm_run_oob;
+
+	spin_lock(&object->lock);
+
+	fscache_done_parent_op(object);
+	if (object->n_in_progress == 0) {
+		if (object->n_ops > 0) {
+			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
+			fscache_start_operations(object);
+		} else {
+			ASSERT(list_empty(&object->pending_ops));
+		}
+	}
+	spin_unlock(&object->lock);
+
+	fscache_stat(&fscache_n_cop_lookup_complete);
+	object->cache->ops->lookup_complete(object);
+	fscache_stat_d(&fscache_n_cop_lookup_complete);
+
+	fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif);
+	fscache_stat(&fscache_n_object_avail);
+
+	_leave("");
+	return transit_to(JUMPSTART_DEPS);
+}
+
+/*
+ * Wake up this object's dependent objects now that we've become available.
+ */
+static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *object,
+								int event)
+{
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_PARENT_READY))
+		return NO_TRANSIT; /* Not finished; requeue */
+	return transit_to(WAIT_FOR_CMD);
+}
+
+/*
+ * Handle lookup or creation failute.
+ */
+static const struct fscache_state *fscache_lookup_failure(struct fscache_object *object,
+							  int event)
+{
+	struct fscache_cookie *cookie;
+
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	object->oob_event_mask = 0;
+
+	fscache_stat(&fscache_n_cop_lookup_complete);
+	object->cache->ops->lookup_complete(object);
+	fscache_stat_d(&fscache_n_cop_lookup_complete);
+
+	set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags);
+
+	cookie = object->cookie;
+	set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+
+	fscache_done_parent_op(object);
+	return transit_to(KILL_OBJECT);
+}
+
+/*
+ * Wait for completion of all active operations on this object and the death of
+ * all child objects of this object.
+ */
+static const struct fscache_state *fscache_kill_object(struct fscache_object *object,
+						       int event)
+{
+	_enter("{OBJ%x,%d,%d},%d",
+	       object->debug_id, object->n_ops, object->n_children, event);
+
+	fscache_mark_object_dead(object);
+	object->oob_event_mask = 0;
+
+	if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+		/* Reject any new read/write ops and abort any that are pending. */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		fscache_cancel_all_ops(object);
+	}
+
+	if (list_empty(&object->dependents) &&
+	    object->n_ops == 0 &&
+	    object->n_children == 0)
+		return transit_to(DROP_OBJECT);
+
+	if (object->n_in_progress == 0) {
+		spin_lock(&object->lock);
+		if (object->n_ops > 0 && object->n_in_progress == 0)
+			fscache_start_operations(object);
+		spin_unlock(&object->lock);
+	}
+
+	if (!list_empty(&object->dependents))
+		return transit_to(KILL_DEPENDENTS);
+
+	return transit_to(WAIT_FOR_CLEARANCE);
+}
+
+/*
+ * Kill dependent objects.
+ */
+static const struct fscache_state *fscache_kill_dependents(struct fscache_object *object,
+							   int event)
+{
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_KILL))
+		return NO_TRANSIT; /* Not finished */
+	return transit_to(WAIT_FOR_CLEARANCE);
+}
+
+/*
+ * Drop an object's attachments
+ */
+static const struct fscache_state *fscache_drop_object(struct fscache_object *object,
+						       int event)
+{
+	struct fscache_object *parent = object->parent;
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_cache *cache = object->cache;
+	bool awaken = false;
+
+	_enter("{OBJ%x,%d},%d", object->debug_id, object->n_children, event);
+
+	ASSERT(cookie != NULL);
+	ASSERT(!hlist_unhashed(&object->cookie_link));
+
+	if (test_bit(FSCACHE_COOKIE_AUX_UPDATED, &cookie->flags)) {
+		_debug("final update");
+		fscache_update_aux_data(object);
+	}
+
+	/* Make sure the cookie no longer points here and that the netfs isn't
+	 * waiting for us.
+	 */
+	spin_lock(&cookie->lock);
+	hlist_del_init(&object->cookie_link);
+	if (hlist_empty(&cookie->backing_objects) &&
+	    test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+		awaken = true;
+	spin_unlock(&cookie->lock);
+
+	if (awaken)
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+
+
+	/* Prevent a race with our last child, which has to signal EV_CLEARED
+	 * before dropping our spinlock.
+	 */
+	spin_lock(&object->lock);
+	spin_unlock(&object->lock);
+
+	/* Discard from the cache's collection of objects */
+	spin_lock(&cache->object_list_lock);
+	list_del_init(&object->cache_link);
+	spin_unlock(&cache->object_list_lock);
+
+	fscache_stat(&fscache_n_cop_drop_object);
+	cache->ops->drop_object(object);
+	fscache_stat_d(&fscache_n_cop_drop_object);
+
+	/* The parent object wants to know when all it dependents have gone */
+	if (parent) {
+		_debug("release parent OBJ%x {%d}",
+		       parent->debug_id, parent->n_children);
+
+		spin_lock(&parent->lock);
+		parent->n_children--;
+		if (parent->n_children == 0)
+			fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+		spin_unlock(&parent->lock);
+		object->parent = NULL;
+	}
+
+	/* this just shifts the object release to the work processor */
+	fscache_put_object(object, fscache_obj_put_drop_obj);
+	fscache_stat(&fscache_n_object_dead);
+
+	_leave("");
+	return transit_to(OBJECT_DEAD);
+}
+
+/*
+ * get a ref on an object
+ */
+static int fscache_get_object(struct fscache_object *object,
+			      enum fscache_obj_ref_trace why)
+{
+	int ret;
+
+	fscache_stat(&fscache_n_cop_grab_object);
+	ret = object->cache->ops->grab_object(object, why) ? 0 : -EAGAIN;
+	fscache_stat_d(&fscache_n_cop_grab_object);
+	return ret;
+}
+
+/*
+ * Discard a ref on an object
+ */
+static void fscache_put_object(struct fscache_object *object,
+			       enum fscache_obj_ref_trace why)
+{
+	fscache_stat(&fscache_n_cop_put_object);
+	object->cache->ops->put_object(object, why);
+	fscache_stat_d(&fscache_n_cop_put_object);
+}
+
+/**
+ * fscache_object_destroy - Note that a cache object is about to be destroyed
+ * @object: The object to be destroyed
+ *
+ * Note the imminent destruction and deallocation of a cache object record.
+ */
+void fscache_object_destroy(struct fscache_object *object)
+{
+	fscache_objlist_remove(object);
+
+	/* We can get rid of the cookie now */
+	fscache_cookie_put(object->cookie, fscache_cookie_put_object);
+	object->cookie = NULL;
+}
+EXPORT_SYMBOL(fscache_object_destroy);
+
+/*
+ * enqueue an object for metadata-type processing
+ */
+void fscache_enqueue_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (fscache_get_object(object, fscache_obj_get_queue) >= 0) {
+		wait_queue_head_t *cong_wq =
+			&get_cpu_var(fscache_object_cong_wait);
+
+		if (queue_work(fscache_object_wq, &object->work)) {
+			if (fscache_object_congested())
+				wake_up(cong_wq);
+		} else
+			fscache_put_object(object, fscache_obj_put_queue);
+
+		put_cpu_var(fscache_object_cong_wait);
+	}
+}
+
+/**
+ * fscache_object_sleep_till_congested - Sleep until object wq is congested
+ * @timeoutp: Scheduler sleep timeout
+ *
+ * Allow an object handler to sleep until the object workqueue is congested.
+ *
+ * The caller must set up a wake up event before calling this and must have set
+ * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
+ * condition before calling this function as no test is made here.
+ *
+ * %true is returned if the object wq is congested, %false otherwise.
+ */
+bool fscache_object_sleep_till_congested(signed long *timeoutp)
+{
+	wait_queue_head_t *cong_wq = this_cpu_ptr(&fscache_object_cong_wait);
+	DEFINE_WAIT(wait);
+
+	if (fscache_object_congested())
+		return true;
+
+	add_wait_queue_exclusive(cong_wq, &wait);
+	if (!fscache_object_congested())
+		*timeoutp = schedule_timeout(*timeoutp);
+	finish_wait(cong_wq, &wait);
+
+	return fscache_object_congested();
+}
+EXPORT_SYMBOL_GPL(fscache_object_sleep_till_congested);
+
+/*
+ * Enqueue the dependents of an object for metadata-type processing.
+ *
+ * If we don't manage to finish the list before the scheduler wants to run
+ * again then return false immediately.  We return true if the list was
+ * cleared.
+ */
+static bool fscache_enqueue_dependents(struct fscache_object *object, int event)
+{
+	struct fscache_object *dep;
+	bool ret = true;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (list_empty(&object->dependents))
+		return true;
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->dependents)) {
+		dep = list_entry(object->dependents.next,
+				 struct fscache_object, dep_link);
+		list_del_init(&dep->dep_link);
+
+		fscache_raise_event(dep, event);
+		fscache_put_object(dep, fscache_obj_put_enq_dep);
+
+		if (!list_empty(&object->dependents) && need_resched()) {
+			ret = false;
+			break;
+		}
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * remove an object from whatever queue it's waiting on
+ */
+static void fscache_dequeue_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (!list_empty(&object->dep_link)) {
+		spin_lock(&object->parent->lock);
+		list_del_init(&object->dep_link);
+		spin_unlock(&object->parent->lock);
+	}
+
+	_leave("");
+}
+
+/**
+ * fscache_check_aux - Ask the netfs whether an object on disk is still valid
+ * @object: The object to ask about
+ * @data: The auxiliary data for the object
+ * @datalen: The size of the auxiliary data
+ *
+ * This function consults the netfs about the coherency state of an object.
+ * The caller must be holding a ref on cookie->n_active (held by
+ * fscache_look_up_object() on behalf of the cache backend during object lookup
+ * and creation).
+ */
+enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+					const void *data, uint16_t datalen,
+					loff_t object_size)
+{
+	enum fscache_checkaux result;
+
+	if (!object->cookie->def->check_aux) {
+		fscache_stat(&fscache_n_checkaux_none);
+		return FSCACHE_CHECKAUX_OKAY;
+	}
+
+	result = object->cookie->def->check_aux(object->cookie->netfs_data,
+						data, datalen, object_size);
+	switch (result) {
+		/* entry okay as is */
+	case FSCACHE_CHECKAUX_OKAY:
+		fscache_stat(&fscache_n_checkaux_okay);
+		break;
+
+		/* entry requires update */
+	case FSCACHE_CHECKAUX_NEEDS_UPDATE:
+		fscache_stat(&fscache_n_checkaux_update);
+		break;
+
+		/* entry requires deletion */
+	case FSCACHE_CHECKAUX_OBSOLETE:
+		fscache_stat(&fscache_n_checkaux_obsolete);
+		break;
+
+	default:
+		BUG();
+	}
+
+	return result;
+}
+EXPORT_SYMBOL(fscache_check_aux);
+
+/*
+ * Asynchronously invalidate an object.
+ */
+static const struct fscache_state *_fscache_invalidate_object(struct fscache_object *object,
+							      int event)
+{
+	struct fscache_operation *op;
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	/* We're going to need the cookie.  If the cookie is not available then
+	 * retire the object instead.
+	 */
+	if (!fscache_use_cookie(object)) {
+		ASSERT(radix_tree_empty(&object->cookie->stores));
+		set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+		_leave(" [no cookie]");
+		return transit_to(KILL_OBJECT);
+	}
+
+	/* Reject any new read/write ops and abort any that are pending. */
+	fscache_invalidate_writes(cookie);
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	fscache_cancel_all_ops(object);
+
+	/* Now we have to wait for in-progress reads and writes */
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		goto nomem;
+
+	fscache_operation_init(cookie, op, object->cache->ops->invalidate_object,
+			       NULL, NULL);
+	op->flags = FSCACHE_OP_ASYNC |
+		(1 << FSCACHE_OP_EXCLUSIVE) |
+		(1 << FSCACHE_OP_UNUSE_COOKIE);
+	trace_fscache_page_op(cookie, NULL, op, fscache_page_op_invalidate);
+
+	spin_lock(&cookie->lock);
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto submit_op_failed;
+	spin_unlock(&cookie->lock);
+	fscache_put_operation(op);
+
+	/* Once we've completed the invalidation, we know there will be no data
+	 * stored in the cache and thus we can reinstate the data-check-skip
+	 * optimisation.
+	 */
+	set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* We can allow read and write requests to come in once again.  They'll
+	 * queue up behind our exclusive invalidation operation.
+	 */
+	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+	_leave(" [ok]");
+	return transit_to(UPDATE_OBJECT);
+
+nomem:
+	fscache_mark_object_dead(object);
+	fscache_unuse_cookie(object);
+	_leave(" [ENOMEM]");
+	return transit_to(KILL_OBJECT);
+
+submit_op_failed:
+	fscache_mark_object_dead(object);
+	spin_unlock(&cookie->lock);
+	fscache_unuse_cookie(object);
+	kfree(op);
+	_leave(" [EIO]");
+	return transit_to(KILL_OBJECT);
+}
+
+static const struct fscache_state *fscache_invalidate_object(struct fscache_object *object,
+							     int event)
+{
+	const struct fscache_state *s;
+
+	fscache_stat(&fscache_n_invalidates_run);
+	fscache_stat(&fscache_n_cop_invalidate_object);
+	s = _fscache_invalidate_object(object, event);
+	fscache_stat_d(&fscache_n_cop_invalidate_object);
+	return s;
+}
+
+/*
+ * Update auxiliary data.
+ */
+static void fscache_update_aux_data(struct fscache_object *object)
+{
+	fscache_stat(&fscache_n_updates_run);
+	fscache_stat(&fscache_n_cop_update_object);
+	object->cache->ops->update_object(object);
+	fscache_stat_d(&fscache_n_cop_update_object);
+}
+
+/*
+ * Asynchronously update an object.
+ */
+static const struct fscache_state *fscache_update_object(struct fscache_object *object,
+							 int event)
+{
+	_enter("{OBJ%x},%d", object->debug_id, event);
+
+	fscache_update_aux_data(object);
+
+	_leave("");
+	return transit_to(WAIT_FOR_CMD);
+}
+
+/**
+ * fscache_object_retrying_stale - Note retrying stale object
+ * @object: The object that will be retried
+ *
+ * Note that an object lookup found an on-disk object that was adjudged to be
+ * stale and has been deleted.  The lookup will be retried.
+ */
+void fscache_object_retrying_stale(struct fscache_object *object)
+{
+	fscache_stat(&fscache_n_cache_no_space_reject);
+}
+EXPORT_SYMBOL(fscache_object_retrying_stale);
+
+/**
+ * fscache_object_mark_killed - Note that an object was killed
+ * @object: The object that was culled
+ * @why: The reason the object was killed.
+ *
+ * Note that an object was killed.  Returns true if the object was
+ * already marked killed, false if it wasn't.
+ */
+void fscache_object_mark_killed(struct fscache_object *object,
+				enum fscache_why_object_killed why)
+{
+	if (test_and_set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags)) {
+		pr_err("Error: Object already killed by cache [%s]\n",
+		       object->cache->identifier);
+		return;
+	}
+
+	switch (why) {
+	case FSCACHE_OBJECT_NO_SPACE:
+		fscache_stat(&fscache_n_cache_no_space_reject);
+		break;
+	case FSCACHE_OBJECT_IS_STALE:
+		fscache_stat(&fscache_n_cache_stale_objects);
+		break;
+	case FSCACHE_OBJECT_WAS_RETIRED:
+		fscache_stat(&fscache_n_cache_retired_objects);
+		break;
+	case FSCACHE_OBJECT_WAS_CULLED:
+		fscache_stat(&fscache_n_cache_culled_objects);
+		break;
+	}
+}
+EXPORT_SYMBOL(fscache_object_mark_killed);
+
+/*
+ * The object is dead.  We can get here if an object gets queued by an event
+ * that would lead to its death (such as EV_KILL) when the dispatcher is
+ * already running (and so can be requeued) but hasn't yet cleared the event
+ * mask.
+ */
+static const struct fscache_state *fscache_object_dead(struct fscache_object *object,
+						       int event)
+{
+	if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD,
+			      &object->flags))
+		return NO_TRANSIT;
+
+	WARN(true, "FS-Cache object redispatched after death");
+	return NO_TRANSIT;
+}
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
new file mode 100644
index 000000000..8d2657903
--- /dev/null
+++ b/fs/fscache/operation.c
@@ -0,0 +1,637 @@
+/* FS-Cache worker operation management routines
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/operations.txt
+ */
+
+#define FSCACHE_DEBUG_LEVEL OPERATION
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+atomic_t fscache_op_debug_id;
+EXPORT_SYMBOL(fscache_op_debug_id);
+
+static void fscache_operation_dummy_cancel(struct fscache_operation *op)
+{
+}
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation.  The caller must still set flags,
+ * object and processor if needed.
+ */
+void fscache_operation_init(struct fscache_cookie *cookie,
+			    struct fscache_operation *op,
+			    fscache_operation_processor_t processor,
+			    fscache_operation_cancel_t cancel,
+			    fscache_operation_release_t release)
+{
+	INIT_WORK(&op->work, fscache_op_work_func);
+	atomic_set(&op->usage, 1);
+	op->state = FSCACHE_OP_ST_INITIALISED;
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+	op->processor = processor;
+	op->cancel = cancel ?: fscache_operation_dummy_cancel;
+	op->release = release;
+	INIT_LIST_HEAD(&op->pend_link);
+	fscache_stat(&fscache_n_op_initialised);
+	trace_fscache_op(cookie, op, fscache_op_init);
+}
+EXPORT_SYMBOL(fscache_operation_init);
+
+/**
+ * fscache_enqueue_operation - Enqueue an operation for processing
+ * @op: The operation to enqueue
+ *
+ * Enqueue an operation for processing by the FS-Cache thread pool.
+ *
+ * This will get its own ref on the object.
+ */
+void fscache_enqueue_operation(struct fscache_operation *op)
+{
+	struct fscache_cookie *cookie = op->object->cookie;
+	
+	_enter("{OBJ%x OP%x,%u}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERT(list_empty(&op->pend_link));
+	ASSERT(op->processor != NULL);
+	ASSERT(fscache_object_is_available(op->object));
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS,
+		    op->state, ==,  FSCACHE_OP_ST_CANCELLED);
+
+	fscache_stat(&fscache_n_op_enqueue);
+	switch (op->flags & FSCACHE_OP_TYPE) {
+	case FSCACHE_OP_ASYNC:
+		trace_fscache_op(cookie, op, fscache_op_enqueue_async);
+		_debug("queue async");
+		atomic_inc(&op->usage);
+		if (!queue_work(fscache_op_wq, &op->work))
+			fscache_put_operation(op);
+		break;
+	case FSCACHE_OP_MYTHREAD:
+		trace_fscache_op(cookie, op, fscache_op_enqueue_mythread);
+		_debug("queue for caller's attention");
+		break;
+	default:
+		pr_err("Unexpected op type %lx", op->flags);
+		BUG();
+		break;
+	}
+}
+EXPORT_SYMBOL(fscache_enqueue_operation);
+
+/*
+ * start an op running
+ */
+static void fscache_run_op(struct fscache_object *object,
+			   struct fscache_operation *op)
+{
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+
+	op->state = FSCACHE_OP_ST_IN_PROGRESS;
+	object->n_in_progress++;
+	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+	if (op->processor)
+		fscache_enqueue_operation(op);
+	else
+		trace_fscache_op(object->cookie, op, fscache_op_run);
+	fscache_stat(&fscache_n_op_run);
+}
+
+/*
+ * report an unexpected submission
+ */
+static void fscache_report_unexpected_submission(struct fscache_object *object,
+						 struct fscache_operation *op,
+						 const struct fscache_state *ostate)
+{
+	static bool once_only;
+	struct fscache_operation *p;
+	unsigned n;
+
+	if (once_only)
+		return;
+	once_only = true;
+
+	kdebug("unexpected submission OP%x [OBJ%x %s]",
+	       op->debug_id, object->debug_id, object->state->name);
+	kdebug("objstate=%s [%s]", object->state->name, ostate->name);
+	kdebug("objflags=%lx", object->flags);
+	kdebug("objevent=%lx [%lx]", object->events, object->event_mask);
+	kdebug("ops=%u inp=%u exc=%u",
+	       object->n_ops, object->n_in_progress, object->n_exclusive);
+
+	if (!list_empty(&object->pending_ops)) {
+		n = 0;
+		list_for_each_entry(p, &object->pending_ops, pend_link) {
+			ASSERTCMP(p->object, ==, object);
+			kdebug("%p %p", op->processor, op->release);
+			n++;
+		}
+
+		kdebug("n=%u", n);
+	}
+
+	dump_stack();
+}
+
+/*
+ * submit an exclusive operation for an object
+ * - other ops are excluded from running simultaneously with this one
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_exclusive_op(struct fscache_object *object,
+				struct fscache_operation *op)
+{
+	const struct fscache_state *ostate;
+	unsigned long flags;
+	int ret;
+
+	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
+
+	trace_fscache_op(object->cookie, op, fscache_op_submit_ex);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+	ASSERT(list_empty(&op->pend_link));
+
+	ostate = object->state;
+	smp_rmb();
+
+	op->state = FSCACHE_OP_ST_PENDING;
+	flags = READ_ONCE(object->flags);
+	if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) {
+		fscache_stat(&fscache_n_op_rejected);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else if (unlikely(fscache_cache_is_broken(object))) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -EIO;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+
+		if (object->n_in_progress > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_in_progress, ==, 0);
+			fscache_run_op(object, op);
+		}
+
+		/* need to issue a new write op after this */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else {
+		fscache_report_unexpected_submission(object, op, ostate);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * submit an operation for an object
+ * - objects may be submitted only in the following states:
+ *   - during object creation (write ops may be submitted)
+ *   - whilst the object is active
+ *   - after an I/O error incurred in one of the two above states (op rejected)
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_op(struct fscache_object *object,
+		      struct fscache_operation *op)
+{
+	const struct fscache_state *ostate;
+	unsigned long flags;
+	int ret;
+
+	_enter("{OBJ%x OP%x},{%u}",
+	       object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	trace_fscache_op(object->cookie, op, fscache_op_submit);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+	ASSERT(list_empty(&op->pend_link));
+
+	ostate = object->state;
+	smp_rmb();
+
+	op->state = FSCACHE_OP_ST_PENDING;
+	flags = READ_ONCE(object->flags);
+	if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) {
+		fscache_stat(&fscache_n_op_rejected);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else if (unlikely(fscache_cache_is_broken(object))) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -EIO;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) {
+		op->object = object;
+		object->n_ops++;
+
+		if (object->n_exclusive > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_exclusive, ==, 0);
+			fscache_run_op(object, op);
+		}
+		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) {
+		op->object = object;
+		object->n_ops++;
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else {
+		fscache_report_unexpected_submission(object, op, ostate);
+		ASSERT(!fscache_object_is_active(object));
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * queue an object for withdrawal on error, aborting all following asynchronous
+ * operations
+ */
+void fscache_abort_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+}
+
+/*
+ * Jump start the operation processing on an object.  The caller must hold
+ * object->lock.
+ */
+void fscache_start_operations(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+	bool stop = false;
+
+	while (!list_empty(&object->pending_ops) && !stop) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+			if (object->n_in_progress > 0)
+				break;
+			stop = true;
+		}
+		list_del_init(&op->pend_link);
+		fscache_run_op(object, op);
+
+		/* the pending queue was holding a ref on the object */
+		fscache_put_operation(op);
+	}
+
+	ASSERTCMP(object->n_in_progress, <=, object->n_ops);
+
+	_debug("woke %d ops on OBJ%x",
+	       object->n_in_progress, object->debug_id);
+}
+
+/*
+ * cancel an operation that's pending on an object
+ */
+int fscache_cancel_op(struct fscache_operation *op,
+		      bool cancel_in_progress_op)
+{
+	struct fscache_object *object = op->object;
+	bool put = false;
+	int ret;
+
+	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
+
+	trace_fscache_op(object->cookie, op, fscache_op_cancel);
+
+	ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING);
+	ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	spin_lock(&object->lock);
+
+	ret = -EBUSY;
+	if (op->state == FSCACHE_OP_ST_PENDING) {
+		ASSERT(!list_empty(&op->pend_link));
+		list_del_init(&op->pend_link);
+		put = true;
+
+		fscache_stat(&fscache_n_op_cancelled);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		ret = 0;
+	} else if (op->state == FSCACHE_OP_ST_IN_PROGRESS && cancel_in_progress_op) {
+		ASSERTCMP(object->n_in_progress, >, 0);
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		object->n_in_progress--;
+		if (object->n_in_progress == 0)
+			fscache_start_operations(object);
+
+		fscache_stat(&fscache_n_op_cancelled);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		ret = 0;
+	}
+
+	if (put)
+		fscache_put_operation(op);
+	spin_unlock(&object->lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Cancel all pending operations on an object
+ */
+void fscache_cancel_all_ops(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+
+	_enter("OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->pending_ops)) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+		fscache_stat(&fscache_n_op_cancelled);
+		list_del_init(&op->pend_link);
+
+		trace_fscache_op(object->cookie, op, fscache_op_cancel_all);
+
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		fscache_put_operation(op);
+		cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+
+/*
+ * Record the completion or cancellation of an in-progress operation.
+ */
+void fscache_op_complete(struct fscache_operation *op, bool cancelled)
+{
+	struct fscache_object *object = op->object;
+
+	_enter("OBJ%x", object->debug_id);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+	ASSERTCMP(object->n_in_progress, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_exclusive, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_in_progress, ==, 1);
+
+	spin_lock(&object->lock);
+
+	if (!cancelled) {
+		trace_fscache_op(object->cookie, op, fscache_op_completed);
+		op->state = FSCACHE_OP_ST_COMPLETE;
+	} else {
+		op->cancel(op);
+		trace_fscache_op(object->cookie, op, fscache_op_cancelled);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+	}
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+		object->n_exclusive--;
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_op_complete);
+
+/*
+ * release an operation
+ * - queues pending ops if this is the last in-progress op
+ */
+void fscache_put_operation(struct fscache_operation *op)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+
+	_enter("{OBJ%x OP%x,%d}",
+	       op->object ? op->object->debug_id : 0,
+	       op->debug_id, atomic_read(&op->usage));
+
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	if (!atomic_dec_and_test(&op->usage))
+		return;
+
+	trace_fscache_op(op->object ? op->object->cookie : NULL, op, fscache_op_put);
+
+	_debug("PUT OP");
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_INITIALISED &&
+		    op->state != FSCACHE_OP_ST_COMPLETE,
+		    op->state, ==, FSCACHE_OP_ST_CANCELLED);
+
+	fscache_stat(&fscache_n_op_release);
+
+	if (op->release) {
+		op->release(op);
+		op->release = NULL;
+	}
+	op->state = FSCACHE_OP_ST_DEAD;
+
+	object = op->object;
+	if (likely(object)) {
+		if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
+			atomic_dec(&object->n_reads);
+		if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags))
+			fscache_unuse_cookie(object);
+
+		/* now... we may get called with the object spinlock held, so we
+		 * complete the cleanup here only if we can immediately acquire the
+		 * lock, and defer it otherwise */
+		if (!spin_trylock(&object->lock)) {
+			_debug("defer put");
+			fscache_stat(&fscache_n_op_deferred_release);
+
+			cache = object->cache;
+			spin_lock(&cache->op_gc_list_lock);
+			list_add_tail(&op->pend_link, &cache->op_gc_list);
+			spin_unlock(&cache->op_gc_list_lock);
+			schedule_work(&cache->op_gc);
+			_leave(" [defer]");
+			return;
+		}
+
+		ASSERTCMP(object->n_ops, >, 0);
+		object->n_ops--;
+		if (object->n_ops == 0)
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+		spin_unlock(&object->lock);
+	}
+
+	kfree(op);
+	_leave(" [done]");
+}
+EXPORT_SYMBOL(fscache_put_operation);
+
+/*
+ * garbage collect operations that have had their release deferred
+ */
+void fscache_operation_gc(struct work_struct *work)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+	struct fscache_cache *cache =
+		container_of(work, struct fscache_cache, op_gc);
+	int count = 0;
+
+	_enter("");
+
+	do {
+		spin_lock(&cache->op_gc_list_lock);
+		if (list_empty(&cache->op_gc_list)) {
+			spin_unlock(&cache->op_gc_list_lock);
+			break;
+		}
+
+		op = list_entry(cache->op_gc_list.next,
+				struct fscache_operation, pend_link);
+		list_del(&op->pend_link);
+		spin_unlock(&cache->op_gc_list_lock);
+
+		object = op->object;
+		trace_fscache_op(object->cookie, op, fscache_op_gc);
+
+		spin_lock(&object->lock);
+
+		_debug("GC DEFERRED REL OBJ%x OP%x",
+		       object->debug_id, op->debug_id);
+		fscache_stat(&fscache_n_op_gc);
+
+		ASSERTCMP(atomic_read(&op->usage), ==, 0);
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD);
+
+		ASSERTCMP(object->n_ops, >, 0);
+		object->n_ops--;
+		if (object->n_ops == 0)
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+		spin_unlock(&object->lock);
+		kfree(op);
+
+	} while (count++ < 20);
+
+	if (!list_empty(&cache->op_gc_list))
+		schedule_work(&cache->op_gc);
+
+	_leave("");
+}
+
+/*
+ * execute an operation using fs_op_wq to provide processing context -
+ * the caller holds a ref to this object, so we don't need to hold one
+ */
+void fscache_op_work_func(struct work_struct *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, work);
+	unsigned long start;
+
+	_enter("{OBJ%x OP%x,%d}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	trace_fscache_op(op->object->cookie, op, fscache_op_work);
+
+	ASSERT(op->processor != NULL);
+	start = jiffies;
+	op->processor(op);
+	fscache_hist(fscache_ops_histogram, start);
+	fscache_put_operation(op);
+
+	_leave("");
+}
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
new file mode 100644
index 000000000..111349f67
--- /dev/null
+++ b/fs/fscache/page.c
@@ -0,0 +1,1252 @@
+/* Cache page management and data I/O routines
+ *
+ * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL PAGE
+#include <linux/module.h>
+#include <linux/fscache-cache.h>
+#include <linux/buffer_head.h>
+#include <linux/pagevec.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+/*
+ * check to see if a page is being written to the cache
+ */
+bool __fscache_check_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	void *val;
+
+	rcu_read_lock();
+	val = radix_tree_lookup(&cookie->stores, page->index);
+	rcu_read_unlock();
+	trace_fscache_check_page(cookie, page, val, 0);
+
+	return val != NULL;
+}
+EXPORT_SYMBOL(__fscache_check_page_write);
+
+/*
+ * wait for a page to finish being written to the cache
+ */
+void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0);
+
+	trace_fscache_page(cookie, page, fscache_page_write_wait);
+
+	wait_event(*wq, !__fscache_check_page_write(cookie, page));
+}
+EXPORT_SYMBOL(__fscache_wait_on_page_write);
+
+/*
+ * wait for a page to finish being written to the cache. Put a timeout here
+ * since we might be called recursively via parent fs.
+ */
+static
+bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0);
+
+	return wait_event_timeout(*wq, !__fscache_check_page_write(cookie, page),
+				  HZ);
+}
+
+/*
+ * decide whether a page can be released, possibly by cancelling a store to it
+ * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged
+ */
+bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
+				  struct page *page,
+				  gfp_t gfp)
+{
+	struct page *xpage;
+	void *val;
+
+	_enter("%p,%p,%x", cookie, page, gfp);
+
+	trace_fscache_page(cookie, page, fscache_page_maybe_release);
+
+try_again:
+	rcu_read_lock();
+	val = radix_tree_lookup(&cookie->stores, page->index);
+	if (!val) {
+		rcu_read_unlock();
+		fscache_stat(&fscache_n_store_vmscan_not_storing);
+		__fscache_uncache_page(cookie, page);
+		return true;
+	}
+
+	/* see if the page is actually undergoing storage - if so we can't get
+	 * rid of it till the cache has finished with it */
+	if (radix_tree_tag_get(&cookie->stores, page->index,
+			       FSCACHE_COOKIE_STORING_TAG)) {
+		rcu_read_unlock();
+		goto page_busy;
+	}
+
+	/* the page is pending storage, so we attempt to cancel the store and
+	 * discard the store request so that the page can be reclaimed */
+	spin_lock(&cookie->stores_lock);
+	rcu_read_unlock();
+
+	if (radix_tree_tag_get(&cookie->stores, page->index,
+			       FSCACHE_COOKIE_STORING_TAG)) {
+		/* the page started to undergo storage whilst we were looking,
+		 * so now we can only wait or return */
+		spin_unlock(&cookie->stores_lock);
+		goto page_busy;
+	}
+
+	xpage = radix_tree_delete(&cookie->stores, page->index);
+	trace_fscache_page(cookie, page, fscache_page_radix_delete);
+	spin_unlock(&cookie->stores_lock);
+
+	if (xpage) {
+		fscache_stat(&fscache_n_store_vmscan_cancelled);
+		fscache_stat(&fscache_n_store_radix_deletes);
+		ASSERTCMP(xpage, ==, page);
+	} else {
+		fscache_stat(&fscache_n_store_vmscan_gone);
+	}
+
+	wake_up_bit(&cookie->flags, 0);
+	trace_fscache_wake_cookie(cookie);
+	if (xpage)
+		put_page(xpage);
+	__fscache_uncache_page(cookie, page);
+	return true;
+
+page_busy:
+	/* We will wait here if we're allowed to, but that could deadlock the
+	 * allocator as the work threads writing to the cache may all end up
+	 * sleeping on memory allocation, so we may need to impose a timeout
+	 * too. */
+	if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) {
+		fscache_stat(&fscache_n_store_vmscan_busy);
+		return false;
+	}
+
+	fscache_stat(&fscache_n_store_vmscan_wait);
+	if (!release_page_wait_timeout(cookie, page))
+		_debug("fscache writeout timeout page: %p{%lx}",
+			page, page->index);
+
+	gfp &= ~__GFP_DIRECT_RECLAIM;
+	goto try_again;
+}
+EXPORT_SYMBOL(__fscache_maybe_release_page);
+
+/*
+ * note that a page has finished being written to the cache
+ */
+static void fscache_end_page_write(struct fscache_object *object,
+				   struct page *page)
+{
+	struct fscache_cookie *cookie;
+	struct page *xpage = NULL, *val;
+
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+	if (cookie) {
+		/* delete the page from the tree if it is now no longer
+		 * pending */
+		spin_lock(&cookie->stores_lock);
+		radix_tree_tag_clear(&cookie->stores, page->index,
+				     FSCACHE_COOKIE_STORING_TAG);
+		trace_fscache_page(cookie, page, fscache_page_radix_clear_store);
+		if (!radix_tree_tag_get(&cookie->stores, page->index,
+					FSCACHE_COOKIE_PENDING_TAG)) {
+			fscache_stat(&fscache_n_store_radix_deletes);
+			xpage = radix_tree_delete(&cookie->stores, page->index);
+			trace_fscache_page(cookie, page, fscache_page_radix_delete);
+			trace_fscache_page(cookie, page, fscache_page_write_end);
+
+			val = radix_tree_lookup(&cookie->stores, page->index);
+			trace_fscache_check_page(cookie, page, val, 1);
+		} else {
+			trace_fscache_page(cookie, page, fscache_page_write_end_pend);
+		}
+		spin_unlock(&cookie->stores_lock);
+		wake_up_bit(&cookie->flags, 0);
+		trace_fscache_wake_cookie(cookie);
+	} else {
+		trace_fscache_page(cookie, page, fscache_page_write_end_noc);
+	}
+	spin_unlock(&object->lock);
+	if (xpage)
+		put_page(xpage);
+}
+
+/*
+ * actually apply the changed attributes to a cache object
+ */
+static void fscache_attr_changed_op(struct fscache_operation *op)
+{
+	struct fscache_object *object = op->object;
+	int ret;
+
+	_enter("{OBJ%x OP%x}", object->debug_id, op->debug_id);
+
+	fscache_stat(&fscache_n_attr_changed_calls);
+
+	if (fscache_object_is_active(object)) {
+		fscache_stat(&fscache_n_cop_attr_changed);
+		ret = object->cache->ops->attr_changed(object);
+		fscache_stat_d(&fscache_n_cop_attr_changed);
+		if (ret < 0)
+			fscache_abort_object(object);
+		fscache_op_complete(op, ret < 0);
+	} else {
+		fscache_op_complete(op, true);
+	}
+
+	_leave("");
+}
+
+/*
+ * notification that the attributes on an object have changed
+ */
+int __fscache_attr_changed(struct fscache_cookie *cookie)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+	bool wake_cookie = false;
+
+	_enter("%p", cookie);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+
+	fscache_stat(&fscache_n_attr_changed);
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op) {
+		fscache_stat(&fscache_n_attr_changed_nomem);
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	fscache_operation_init(cookie, op, fscache_attr_changed_op, NULL, NULL);
+	trace_fscache_page_op(cookie, NULL, op, fscache_page_op_attr_changed);
+	op->flags = FSCACHE_OP_ASYNC |
+		(1 << FSCACHE_OP_EXCLUSIVE) |
+		(1 << FSCACHE_OP_UNUSE_COOKIE);
+
+	spin_lock(&cookie->lock);
+
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	__fscache_use_cookie(cookie);
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto nobufs_dec;
+	spin_unlock(&cookie->lock);
+	fscache_stat(&fscache_n_attr_changed_ok);
+	fscache_put_operation(op);
+	_leave(" = 0");
+	return 0;
+
+nobufs_dec:
+	wake_cookie = __fscache_unuse_cookie(cookie);
+nobufs:
+	spin_unlock(&cookie->lock);
+	fscache_put_operation(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
+	fscache_stat(&fscache_n_attr_changed_nobufs);
+	_leave(" = %d", -ENOBUFS);
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_attr_changed);
+
+/*
+ * Handle cancellation of a pending retrieval op
+ */
+static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	atomic_set(&op->n_pages, 0);
+}
+
+/*
+ * release a retrieval op reference
+ */
+static void fscache_release_retrieval_op(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	_enter("{OP%x}", op->op.debug_id);
+
+	ASSERTIFCMP(op->op.state != FSCACHE_OP_ST_INITIALISED,
+		    atomic_read(&op->n_pages), ==, 0);
+
+	fscache_hist(fscache_retrieval_histogram, op->start_time);
+	if (op->context)
+		fscache_put_context(op->cookie, op->context);
+
+	_leave("");
+}
+
+/*
+ * allocate a retrieval op
+ */
+static struct fscache_retrieval *fscache_alloc_retrieval(
+	struct fscache_cookie *cookie,
+	struct address_space *mapping,
+	fscache_rw_complete_t end_io_func,
+	void *context)
+{
+	struct fscache_retrieval *op;
+
+	/* allocate a retrieval operation and attempt to submit it */
+	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (!op) {
+		fscache_stat(&fscache_n_retrievals_nomem);
+		return NULL;
+	}
+
+	fscache_operation_init(cookie, &op->op, NULL,
+			       fscache_do_cancel_retrieval,
+			       fscache_release_retrieval_op);
+	op->op.flags	= FSCACHE_OP_MYTHREAD |
+		(1UL << FSCACHE_OP_WAITING) |
+		(1UL << FSCACHE_OP_UNUSE_COOKIE);
+	op->cookie	= cookie;
+	op->mapping	= mapping;
+	op->end_io_func	= end_io_func;
+	op->context	= context;
+	op->start_time	= jiffies;
+	INIT_LIST_HEAD(&op->to_do);
+
+	/* Pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure.
+	 */
+	if (context)
+		fscache_get_context(op->cookie, context);
+	return op;
+}
+
+/*
+ * wait for a deferred lookup to complete
+ */
+int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
+{
+	unsigned long jif;
+
+	_enter("");
+
+	if (!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) {
+		_leave(" = 0 [imm]");
+		return 0;
+	}
+
+	fscache_stat(&fscache_n_retrievals_wait);
+
+	jif = jiffies;
+	if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
+			TASK_INTERRUPTIBLE) != 0) {
+		fscache_stat(&fscache_n_retrievals_intr);
+		_leave(" = -ERESTARTSYS");
+		return -ERESTARTSYS;
+	}
+
+	ASSERT(!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags));
+
+	smp_rmb();
+	fscache_hist(fscache_retrieval_delay_histogram, jif);
+	_leave(" = 0 [dly]");
+	return 0;
+}
+
+/*
+ * wait for an object to become active (or dead)
+ */
+int fscache_wait_for_operation_activation(struct fscache_object *object,
+					  struct fscache_operation *op,
+					  atomic_t *stat_op_waits,
+					  atomic_t *stat_object_dead)
+{
+	int ret;
+
+	if (!test_bit(FSCACHE_OP_WAITING, &op->flags))
+		goto check_if_dead;
+
+	_debug(">>> WT");
+	if (stat_op_waits)
+		fscache_stat(stat_op_waits);
+	if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
+			TASK_INTERRUPTIBLE) != 0) {
+		trace_fscache_op(object->cookie, op, fscache_op_signal);
+		ret = fscache_cancel_op(op, false);
+		if (ret == 0)
+			return -ERESTARTSYS;
+
+		/* it's been removed from the pending queue by another party,
+		 * so we should get to run shortly */
+		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
+			    TASK_UNINTERRUPTIBLE);
+	}
+	_debug("<<< GO");
+
+check_if_dead:
+	if (op->state == FSCACHE_OP_ST_CANCELLED) {
+		if (stat_object_dead)
+			fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [cancelled]");
+		return -ENOBUFS;
+	}
+	if (unlikely(fscache_object_is_dying(object) ||
+		     fscache_cache_is_broken(object))) {
+		enum fscache_operation_state state = op->state;
+		trace_fscache_op(object->cookie, op, fscache_op_signal);
+		fscache_cancel_op(op, true);
+		if (stat_object_dead)
+			fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [obj dead %d]", state);
+		return -ENOBUFS;
+	}
+	return 0;
+}
+
+/*
+ * read a page from the cache or allocate a block in which to store it
+ * - we return:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ERESTARTSYS - interrupted
+ *   -ENOBUFS	- no backing object available in which to cache the block
+ *   -ENODATA	- no data available in the backing object for this block
+ *   0		- dispatched a read - it'll call end_io_func() when finished
+ */
+int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+				 struct page *page,
+				 fscache_rw_complete_t end_io_func,
+				 void *context,
+				 gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	bool wake_cookie = false;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(cookie, page->mapping,
+				     end_io_func, context);
+	if (!op) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+	atomic_set(&op->n_pages, 1);
+	trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_retr_one);
+
+	spin_lock(&cookie->lock);
+
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	ASSERT(test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags));
+
+	__fscache_use_cookie(cookie);
+	atomic_inc(&object->n_reads);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock_dec;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* we wait for the operation to become active, and then process it
+	 * *here*, in this thread, and not in the thread pool */
+	ret = fscache_wait_for_operation_activation(
+		object, &op->op,
+		__fscache_stat(&fscache_n_retrieval_op_waits),
+		__fscache_stat(&fscache_n_retrievals_object_dead));
+	if (ret < 0)
+		goto error;
+
+	/* ask the cache to honour the operation */
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) {
+		fscache_stat(&fscache_n_cop_allocate_page);
+		ret = object->cache->ops->allocate_page(op, page, gfp);
+		fscache_stat_d(&fscache_n_cop_allocate_page);
+		if (ret == 0)
+			ret = -ENODATA;
+	} else {
+		fscache_stat(&fscache_n_cop_read_or_alloc_page);
+		ret = object->cache->ops->read_or_alloc_page(op, page, gfp);
+		fscache_stat_d(&fscache_n_cop_read_or_alloc_page);
+	}
+
+error:
+	if (ret == -ENOMEM)
+		fscache_stat(&fscache_n_retrievals_nomem);
+	else if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_retrievals_intr);
+	else if (ret == -ENODATA)
+		fscache_stat(&fscache_n_retrievals_nodata);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_retrievals_nobufs);
+	else
+		fscache_stat(&fscache_n_retrievals_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
+	wake_cookie = __fscache_unuse_cookie(cookie);
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
+	fscache_put_retrieval(op);
+nobufs:
+	fscache_stat(&fscache_n_retrievals_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_read_or_alloc_page);
+
+/*
+ * read a list of page from the cache or allocate a block in which to store
+ * them
+ * - we return:
+ *   -ENOMEM	- out of memory, some pages may be being read
+ *   -ERESTARTSYS - interrupted, some pages may be being read
+ *   -ENOBUFS	- no backing object or space available in which to cache any
+ *                pages not being read
+ *   -ENODATA	- no data available in the backing object for some or all of
+ *                the pages
+ *   0		- dispatched a read on all pages
+ *
+ * end_io_func() will be called for each page read from the cache as it is
+ * finishes being read
+ *
+ * any pages for which a read is dispatched will be removed from pages and
+ * nr_pages
+ */
+int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages,
+				  fscache_rw_complete_t end_io_func,
+				  void *context,
+				  gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	bool wake_cookie = false;
+	int ret;
+
+	_enter("%p,,%d,,,", cookie, *nr_pages);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(*nr_pages, >, 0);
+	ASSERT(!list_empty(pages));
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(cookie, mapping, end_io_func, context);
+	if (!op)
+		return -ENOMEM;
+	atomic_set(&op->n_pages, *nr_pages);
+	trace_fscache_page_op(cookie, NULL, &op->op, fscache_page_op_retr_multi);
+
+	spin_lock(&cookie->lock);
+
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	__fscache_use_cookie(cookie);
+	atomic_inc(&object->n_reads);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock_dec;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* we wait for the operation to become active, and then process it
+	 * *here*, in this thread, and not in the thread pool */
+	ret = fscache_wait_for_operation_activation(
+		object, &op->op,
+		__fscache_stat(&fscache_n_retrieval_op_waits),
+		__fscache_stat(&fscache_n_retrievals_object_dead));
+	if (ret < 0)
+		goto error;
+
+	/* ask the cache to honour the operation */
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) {
+		fscache_stat(&fscache_n_cop_allocate_pages);
+		ret = object->cache->ops->allocate_pages(
+			op, pages, nr_pages, gfp);
+		fscache_stat_d(&fscache_n_cop_allocate_pages);
+	} else {
+		fscache_stat(&fscache_n_cop_read_or_alloc_pages);
+		ret = object->cache->ops->read_or_alloc_pages(
+			op, pages, nr_pages, gfp);
+		fscache_stat_d(&fscache_n_cop_read_or_alloc_pages);
+	}
+
+error:
+	if (ret == -ENOMEM)
+		fscache_stat(&fscache_n_retrievals_nomem);
+	else if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_retrievals_intr);
+	else if (ret == -ENODATA)
+		fscache_stat(&fscache_n_retrievals_nodata);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_retrievals_nobufs);
+	else
+		fscache_stat(&fscache_n_retrievals_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
+	wake_cookie = __fscache_unuse_cookie(cookie);
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	fscache_put_retrieval(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
+nobufs:
+	fscache_stat(&fscache_n_retrievals_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_read_or_alloc_pages);
+
+/*
+ * allocate a block in the cache on which to store a page
+ * - we return:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ERESTARTSYS - interrupted
+ *   -ENOBUFS	- no backing object available in which to cache the block
+ *   0		- block allocated
+ */
+int __fscache_alloc_page(struct fscache_cookie *cookie,
+			 struct page *page,
+			 gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	bool wake_cookie = false;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_allocs);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(cookie, page->mapping, NULL, NULL);
+	if (!op)
+		return -ENOMEM;
+	atomic_set(&op->n_pages, 1);
+	trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_alloc_one);
+
+	spin_lock(&cookie->lock);
+
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	__fscache_use_cookie(cookie);
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock_dec;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_alloc_ops);
+
+	ret = fscache_wait_for_operation_activation(
+		object, &op->op,
+		__fscache_stat(&fscache_n_alloc_op_waits),
+		__fscache_stat(&fscache_n_allocs_object_dead));
+	if (ret < 0)
+		goto error;
+
+	/* ask the cache to honour the operation */
+	fscache_stat(&fscache_n_cop_allocate_page);
+	ret = object->cache->ops->allocate_page(op, page, gfp);
+	fscache_stat_d(&fscache_n_cop_allocate_page);
+
+error:
+	if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_allocs_intr);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_allocs_nobufs);
+	else
+		fscache_stat(&fscache_n_allocs_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock_dec:
+	wake_cookie = __fscache_unuse_cookie(cookie);
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	fscache_put_retrieval(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
+nobufs:
+	fscache_stat(&fscache_n_allocs_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_alloc_page);
+
+/*
+ * Unmark pages allocate in the readahead code path (via:
+ * fscache_readpages_or_alloc) after delegating to the base filesystem
+ */
+void __fscache_readpages_cancel(struct fscache_cookie *cookie,
+				struct list_head *pages)
+{
+	struct page *page;
+
+	list_for_each_entry(page, pages, lru) {
+		if (PageFsCache(page))
+			__fscache_uncache_page(cookie, page);
+	}
+}
+EXPORT_SYMBOL(__fscache_readpages_cancel);
+
+/*
+ * release a write op reference
+ */
+static void fscache_release_write_op(struct fscache_operation *_op)
+{
+	_enter("{OP%x}", _op->debug_id);
+}
+
+/*
+ * perform the background storage of a page into the cache
+ */
+static void fscache_write_op(struct fscache_operation *_op)
+{
+	struct fscache_storage *op =
+		container_of(_op, struct fscache_storage, op);
+	struct fscache_object *object = op->op.object;
+	struct fscache_cookie *cookie;
+	struct page *page;
+	unsigned n;
+	void *results[1];
+	int ret;
+
+	_enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage));
+
+again:
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+
+	if (!fscache_object_is_active(object)) {
+		/* If we get here, then the on-disk cache object likely no
+		 * longer exists, so we should just cancel this write
+		 * operation.
+		 */
+		spin_unlock(&object->lock);
+		fscache_op_complete(&op->op, true);
+		_leave(" [inactive]");
+		return;
+	}
+
+	if (!cookie) {
+		/* If we get here, then the cookie belonging to the object was
+		 * detached, probably by the cookie being withdrawn due to
+		 * memory pressure, which means that the pages we might write
+		 * to the cache from no longer exist - therefore, we can just
+		 * cancel this write operation.
+		 */
+		spin_unlock(&object->lock);
+		fscache_op_complete(&op->op, true);
+		_leave(" [cancel] op{f=%lx s=%u} obj{s=%s f=%lx}",
+		       _op->flags, _op->state, object->state->short_name,
+		       object->flags);
+		return;
+	}
+
+	spin_lock(&cookie->stores_lock);
+
+	fscache_stat(&fscache_n_store_calls);
+
+	/* find a page to store */
+	results[0] = NULL;
+	page = NULL;
+	n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, 1,
+				       FSCACHE_COOKIE_PENDING_TAG);
+	trace_fscache_gang_lookup(cookie, &op->op, results, n, op->store_limit);
+	if (n != 1)
+		goto superseded;
+	page = results[0];
+	_debug("gang %d [%lx]", n, page->index);
+
+	radix_tree_tag_set(&cookie->stores, page->index,
+			   FSCACHE_COOKIE_STORING_TAG);
+	radix_tree_tag_clear(&cookie->stores, page->index,
+			     FSCACHE_COOKIE_PENDING_TAG);
+	trace_fscache_page(cookie, page, fscache_page_radix_pend2store);
+
+	spin_unlock(&cookie->stores_lock);
+	spin_unlock(&object->lock);
+
+	if (page->index >= op->store_limit)
+		goto discard_page;
+
+	fscache_stat(&fscache_n_store_pages);
+	fscache_stat(&fscache_n_cop_write_page);
+	ret = object->cache->ops->write_page(op, page);
+	fscache_stat_d(&fscache_n_cop_write_page);
+	trace_fscache_wrote_page(cookie, page, &op->op, ret);
+	fscache_end_page_write(object, page);
+	if (ret < 0) {
+		fscache_abort_object(object);
+		fscache_op_complete(&op->op, true);
+	} else {
+		fscache_enqueue_operation(&op->op);
+	}
+
+	_leave("");
+	return;
+
+discard_page:
+	fscache_stat(&fscache_n_store_pages_over_limit);
+	trace_fscache_wrote_page(cookie, page, &op->op, -ENOBUFS);
+	fscache_end_page_write(object, page);
+	goto again;
+
+superseded:
+	/* this writer is going away and there aren't any more things to
+	 * write */
+	_debug("cease");
+	spin_unlock(&cookie->stores_lock);
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	spin_unlock(&object->lock);
+	fscache_op_complete(&op->op, false);
+	_leave("");
+}
+
+/*
+ * Clear the pages pending writing for invalidation
+ */
+void fscache_invalidate_writes(struct fscache_cookie *cookie)
+{
+	struct page *page;
+	void *results[16];
+	int n, i;
+
+	_enter("");
+
+	for (;;) {
+		spin_lock(&cookie->stores_lock);
+		n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0,
+					       ARRAY_SIZE(results),
+					       FSCACHE_COOKIE_PENDING_TAG);
+		if (n == 0) {
+			spin_unlock(&cookie->stores_lock);
+			break;
+		}
+
+		for (i = n - 1; i >= 0; i--) {
+			page = results[i];
+			radix_tree_delete(&cookie->stores, page->index);
+			trace_fscache_page(cookie, page, fscache_page_radix_delete);
+			trace_fscache_page(cookie, page, fscache_page_inval);
+		}
+
+		spin_unlock(&cookie->stores_lock);
+
+		for (i = n - 1; i >= 0; i--)
+			put_page(results[i]);
+	}
+
+	wake_up_bit(&cookie->flags, 0);
+	trace_fscache_wake_cookie(cookie);
+
+	_leave("");
+}
+
+/*
+ * request a page be stored in the cache
+ * - returns:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ENOBUFS	- no backing object available in which to cache the page
+ *   0		- dispatched a write - it'll call end_io_func() when finished
+ *
+ * if the cookie still has a backing object at this point, that object can be
+ * in one of a few states with respect to storage processing:
+ *
+ *  (1) negative lookup, object not yet created (FSCACHE_COOKIE_CREATING is
+ *      set)
+ *
+ *	(a) no writes yet
+ *
+ *	(b) writes deferred till post-creation (mark page for writing and
+ *	    return immediately)
+ *
+ *  (2) negative lookup, object created, initial fill being made from netfs
+ *
+ *	(a) fill point not yet reached this page (mark page for writing and
+ *          return)
+ *
+ *	(b) fill point passed this page (queue op to store this page)
+ *
+ *  (3) object extant (queue op to store this page)
+ *
+ * any other state is invalid
+ */
+int __fscache_write_page(struct fscache_cookie *cookie,
+			 struct page *page,
+			 loff_t object_size,
+			 gfp_t gfp)
+{
+	struct fscache_storage *op;
+	struct fscache_object *object;
+	bool wake_cookie = false;
+	int ret;
+
+	_enter("%p,%x,", cookie, (u32) page->flags);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERT(PageFsCache(page));
+
+	fscache_stat(&fscache_n_stores);
+
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
+	op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY);
+	if (!op)
+		goto nomem;
+
+	fscache_operation_init(cookie, &op->op, fscache_write_op, NULL,
+			       fscache_release_write_op);
+	op->op.flags = FSCACHE_OP_ASYNC |
+		(1 << FSCACHE_OP_WAITING) |
+		(1 << FSCACHE_OP_UNUSE_COOKIE);
+
+	ret = radix_tree_maybe_preload(gfp & ~__GFP_HIGHMEM);
+	if (ret < 0)
+		goto nomem_free;
+
+	trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_write_one);
+
+	ret = -ENOBUFS;
+	spin_lock(&cookie->lock);
+
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+	if (test_bit(FSCACHE_IOERROR, &object->cache->flags))
+		goto nobufs;
+
+	trace_fscache_page(cookie, page, fscache_page_write);
+
+	/* add the page to the pending-storage radix tree on the backing
+	 * object */
+	spin_lock(&object->lock);
+
+	if (object->store_limit_l != object_size)
+		fscache_set_store_limit(object, object_size);
+
+	spin_lock(&cookie->stores_lock);
+
+	_debug("store limit %llx", (unsigned long long) object->store_limit);
+
+	ret = radix_tree_insert(&cookie->stores, page->index, page);
+	if (ret < 0) {
+		if (ret == -EEXIST)
+			goto already_queued;
+		_debug("insert failed %d", ret);
+		goto nobufs_unlock_obj;
+	}
+
+	trace_fscache_page(cookie, page, fscache_page_radix_insert);
+	radix_tree_tag_set(&cookie->stores, page->index,
+			   FSCACHE_COOKIE_PENDING_TAG);
+	trace_fscache_page(cookie, page, fscache_page_radix_set_pend);
+	get_page(page);
+
+	/* we only want one writer at a time, but we do need to queue new
+	 * writers after exclusive ops */
+	if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags))
+		goto already_pending;
+
+	spin_unlock(&cookie->stores_lock);
+	spin_unlock(&object->lock);
+
+	op->op.debug_id	= atomic_inc_return(&fscache_op_debug_id);
+	op->store_limit = object->store_limit;
+
+	__fscache_use_cookie(cookie);
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto submit_failed;
+
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	fscache_stat(&fscache_n_store_ops);
+	fscache_stat(&fscache_n_stores_ok);
+
+	/* the work queue now carries its own ref on the object */
+	fscache_put_operation(&op->op);
+	_leave(" = 0");
+	return 0;
+
+already_queued:
+	fscache_stat(&fscache_n_stores_again);
+already_pending:
+	spin_unlock(&cookie->stores_lock);
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	fscache_put_operation(&op->op);
+	fscache_stat(&fscache_n_stores_ok);
+	_leave(" = 0");
+	return 0;
+
+submit_failed:
+	spin_lock(&cookie->stores_lock);
+	radix_tree_delete(&cookie->stores, page->index);
+	trace_fscache_page(cookie, page, fscache_page_radix_delete);
+	spin_unlock(&cookie->stores_lock);
+	wake_cookie = __fscache_unuse_cookie(cookie);
+	put_page(page);
+	ret = -ENOBUFS;
+	goto nobufs;
+
+nobufs_unlock_obj:
+	spin_unlock(&cookie->stores_lock);
+	spin_unlock(&object->lock);
+nobufs:
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	fscache_put_operation(&op->op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
+	fscache_stat(&fscache_n_stores_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+
+nomem_free:
+	fscache_put_operation(&op->op);
+nomem:
+	fscache_stat(&fscache_n_stores_oom);
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(__fscache_write_page);
+
+/*
+ * remove a page from the cache
+ */
+void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page)
+{
+	struct fscache_object *object;
+
+	_enter(",%p", page);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	fscache_stat(&fscache_n_uncaches);
+
+	/* cache withdrawal may beat us to it */
+	if (!PageFsCache(page))
+		goto done;
+
+	trace_fscache_page(cookie, page, fscache_page_uncache);
+
+	/* get the object */
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects)) {
+		ClearPageFsCache(page);
+		goto done_unlock;
+	}
+
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	/* there might now be stuff on disk we could read */
+	clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* only invoke the cache backend if we managed to mark the page
+	 * uncached here; this deals with synchronisation vs withdrawal */
+	if (TestClearPageFsCache(page) &&
+	    object->cache->ops->uncache_page) {
+		/* the cache backend releases the cookie lock */
+		fscache_stat(&fscache_n_cop_uncache_page);
+		object->cache->ops->uncache_page(object, page);
+		fscache_stat_d(&fscache_n_cop_uncache_page);
+		goto done;
+	}
+
+done_unlock:
+	spin_unlock(&cookie->lock);
+done:
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_uncache_page);
+
+/**
+ * fscache_mark_page_cached - Mark a page as being cached
+ * @op: The retrieval op pages are being marked for
+ * @page: The page to be marked
+ *
+ * Mark a netfs page as being cached.  After this is called, the netfs
+ * must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_inc(&fscache_n_marks);
+#endif
+
+	trace_fscache_page(cookie, page, fscache_page_cached);
+
+	_debug("- mark %p{%lx}", page, page->index);
+	if (TestSetPageFsCache(page)) {
+		static bool once_only;
+		if (!once_only) {
+			once_only = true;
+			pr_warn("Cookie type %s marked page %lx multiple times\n",
+				cookie->def->name, page->index);
+		}
+	}
+
+	if (cookie->def->mark_page_cached)
+		cookie->def->mark_page_cached(cookie->netfs_data,
+					      op->mapping, page);
+}
+EXPORT_SYMBOL(fscache_mark_page_cached);
+
+/**
+ * fscache_mark_pages_cached - Mark pages as being cached
+ * @op: The retrieval op pages are being marked for
+ * @pagevec: The pages to be marked
+ *
+ * Mark a bunch of netfs pages as being cached.  After this is called,
+ * the netfs must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_pages_cached(struct fscache_retrieval *op,
+			       struct pagevec *pagevec)
+{
+	unsigned long loop;
+
+	for (loop = 0; loop < pagevec->nr; loop++)
+		fscache_mark_page_cached(op, pagevec->pages[loop]);
+
+	pagevec_reinit(pagevec);
+}
+EXPORT_SYMBOL(fscache_mark_pages_cached);
+
+/*
+ * Uncache all the pages in an inode that are marked PG_fscache, assuming them
+ * to be associated with the given cookie.
+ */
+void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
+				       struct inode *inode)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct pagevec pvec;
+	pgoff_t next;
+	int i;
+
+	_enter("%p,%p", cookie, inode);
+
+	if (!mapping || mapping->nrpages == 0) {
+		_leave(" [no pages]");
+		return;
+	}
+
+	pagevec_init(&pvec);
+	next = 0;
+	do {
+		if (!pagevec_lookup(&pvec, mapping, &next))
+			break;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			if (PageFsCache(page)) {
+				__fscache_wait_on_page_write(cookie, page);
+				__fscache_uncache_page(cookie, page);
+			}
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	} while (next);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_uncache_all_inode_pages);
diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c
new file mode 100644
index 000000000..49a8c9041
--- /dev/null
+++ b/fs/fscache/proc.c
@@ -0,0 +1,81 @@
+/* FS-Cache statistics viewing interface
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL OPERATION
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * initialise the /proc/fs/fscache/ directory
+ */
+int __init fscache_proc_init(void)
+{
+	_enter("");
+
+	if (!proc_mkdir("fs/fscache", NULL))
+		goto error_dir;
+
+#ifdef CONFIG_FSCACHE_STATS
+	if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL,
+			fscache_stats_show))
+		goto error_stats;
+#endif
+
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	if (!proc_create_seq("fs/fscache/histogram", S_IFREG | 0444, NULL,
+			 &fscache_histogram_ops))
+		goto error_histogram;
+#endif
+
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL,
+			 &fscache_objlist_fops))
+		goto error_objects;
+#endif
+
+	_leave(" = 0");
+	return 0;
+
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+error_objects:
+#endif
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	remove_proc_entry("fs/fscache/histogram", NULL);
+error_histogram:
+#endif
+#ifdef CONFIG_FSCACHE_STATS
+	remove_proc_entry("fs/fscache/stats", NULL);
+error_stats:
+#endif
+	remove_proc_entry("fs/fscache", NULL);
+error_dir:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/fscache/ directory
+ */
+void fscache_proc_cleanup(void)
+{
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	remove_proc_entry("fs/fscache/objects", NULL);
+#endif
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	remove_proc_entry("fs/fscache/histogram", NULL);
+#endif
+#ifdef CONFIG_FSCACHE_STATS
+	remove_proc_entry("fs/fscache/stats", NULL);
+#endif
+	remove_proc_entry("fs/fscache", NULL);
+}
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
new file mode 100644
index 000000000..00564a1df
--- /dev/null
+++ b/fs/fscache/stats.c
@@ -0,0 +1,286 @@
+/* FS-Cache statistics
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL THREAD
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * operation counters
+ */
+atomic_t fscache_n_op_pend;
+atomic_t fscache_n_op_run;
+atomic_t fscache_n_op_enqueue;
+atomic_t fscache_n_op_deferred_release;
+atomic_t fscache_n_op_initialised;
+atomic_t fscache_n_op_release;
+atomic_t fscache_n_op_gc;
+atomic_t fscache_n_op_cancelled;
+atomic_t fscache_n_op_rejected;
+
+atomic_t fscache_n_attr_changed;
+atomic_t fscache_n_attr_changed_ok;
+atomic_t fscache_n_attr_changed_nobufs;
+atomic_t fscache_n_attr_changed_nomem;
+atomic_t fscache_n_attr_changed_calls;
+
+atomic_t fscache_n_allocs;
+atomic_t fscache_n_allocs_ok;
+atomic_t fscache_n_allocs_wait;
+atomic_t fscache_n_allocs_nobufs;
+atomic_t fscache_n_allocs_intr;
+atomic_t fscache_n_allocs_object_dead;
+atomic_t fscache_n_alloc_ops;
+atomic_t fscache_n_alloc_op_waits;
+
+atomic_t fscache_n_retrievals;
+atomic_t fscache_n_retrievals_ok;
+atomic_t fscache_n_retrievals_wait;
+atomic_t fscache_n_retrievals_nodata;
+atomic_t fscache_n_retrievals_nobufs;
+atomic_t fscache_n_retrievals_intr;
+atomic_t fscache_n_retrievals_nomem;
+atomic_t fscache_n_retrievals_object_dead;
+atomic_t fscache_n_retrieval_ops;
+atomic_t fscache_n_retrieval_op_waits;
+
+atomic_t fscache_n_stores;
+atomic_t fscache_n_stores_ok;
+atomic_t fscache_n_stores_again;
+atomic_t fscache_n_stores_nobufs;
+atomic_t fscache_n_stores_oom;
+atomic_t fscache_n_store_ops;
+atomic_t fscache_n_store_calls;
+atomic_t fscache_n_store_pages;
+atomic_t fscache_n_store_radix_deletes;
+atomic_t fscache_n_store_pages_over_limit;
+
+atomic_t fscache_n_store_vmscan_not_storing;
+atomic_t fscache_n_store_vmscan_gone;
+atomic_t fscache_n_store_vmscan_busy;
+atomic_t fscache_n_store_vmscan_cancelled;
+atomic_t fscache_n_store_vmscan_wait;
+
+atomic_t fscache_n_marks;
+atomic_t fscache_n_uncaches;
+
+atomic_t fscache_n_acquires;
+atomic_t fscache_n_acquires_null;
+atomic_t fscache_n_acquires_no_cache;
+atomic_t fscache_n_acquires_ok;
+atomic_t fscache_n_acquires_nobufs;
+atomic_t fscache_n_acquires_oom;
+
+atomic_t fscache_n_invalidates;
+atomic_t fscache_n_invalidates_run;
+
+atomic_t fscache_n_updates;
+atomic_t fscache_n_updates_null;
+atomic_t fscache_n_updates_run;
+
+atomic_t fscache_n_relinquishes;
+atomic_t fscache_n_relinquishes_null;
+atomic_t fscache_n_relinquishes_waitcrt;
+atomic_t fscache_n_relinquishes_retire;
+
+atomic_t fscache_n_cookie_index;
+atomic_t fscache_n_cookie_data;
+atomic_t fscache_n_cookie_special;
+
+atomic_t fscache_n_object_alloc;
+atomic_t fscache_n_object_no_alloc;
+atomic_t fscache_n_object_lookups;
+atomic_t fscache_n_object_lookups_negative;
+atomic_t fscache_n_object_lookups_positive;
+atomic_t fscache_n_object_lookups_timed_out;
+atomic_t fscache_n_object_created;
+atomic_t fscache_n_object_avail;
+atomic_t fscache_n_object_dead;
+
+atomic_t fscache_n_checkaux_none;
+atomic_t fscache_n_checkaux_okay;
+atomic_t fscache_n_checkaux_update;
+atomic_t fscache_n_checkaux_obsolete;
+
+atomic_t fscache_n_cop_alloc_object;
+atomic_t fscache_n_cop_lookup_object;
+atomic_t fscache_n_cop_lookup_complete;
+atomic_t fscache_n_cop_grab_object;
+atomic_t fscache_n_cop_invalidate_object;
+atomic_t fscache_n_cop_update_object;
+atomic_t fscache_n_cop_drop_object;
+atomic_t fscache_n_cop_put_object;
+atomic_t fscache_n_cop_sync_cache;
+atomic_t fscache_n_cop_attr_changed;
+atomic_t fscache_n_cop_read_or_alloc_page;
+atomic_t fscache_n_cop_read_or_alloc_pages;
+atomic_t fscache_n_cop_allocate_page;
+atomic_t fscache_n_cop_allocate_pages;
+atomic_t fscache_n_cop_write_page;
+atomic_t fscache_n_cop_uncache_page;
+atomic_t fscache_n_cop_dissociate_pages;
+
+atomic_t fscache_n_cache_no_space_reject;
+atomic_t fscache_n_cache_stale_objects;
+atomic_t fscache_n_cache_retired_objects;
+atomic_t fscache_n_cache_culled_objects;
+
+/*
+ * display the general statistics
+ */
+int fscache_stats_show(struct seq_file *m, void *v)
+{
+	seq_puts(m, "FS-Cache statistics\n");
+
+	seq_printf(m, "Cookies: idx=%u dat=%u spc=%u\n",
+		   atomic_read(&fscache_n_cookie_index),
+		   atomic_read(&fscache_n_cookie_data),
+		   atomic_read(&fscache_n_cookie_special));
+
+	seq_printf(m, "Objects: alc=%u nal=%u avl=%u ded=%u\n",
+		   atomic_read(&fscache_n_object_alloc),
+		   atomic_read(&fscache_n_object_no_alloc),
+		   atomic_read(&fscache_n_object_avail),
+		   atomic_read(&fscache_n_object_dead));
+	seq_printf(m, "ChkAux : non=%u ok=%u upd=%u obs=%u\n",
+		   atomic_read(&fscache_n_checkaux_none),
+		   atomic_read(&fscache_n_checkaux_okay),
+		   atomic_read(&fscache_n_checkaux_update),
+		   atomic_read(&fscache_n_checkaux_obsolete));
+
+	seq_printf(m, "Pages  : mrk=%u unc=%u\n",
+		   atomic_read(&fscache_n_marks),
+		   atomic_read(&fscache_n_uncaches));
+
+	seq_printf(m, "Acquire: n=%u nul=%u noc=%u ok=%u nbf=%u"
+		   " oom=%u\n",
+		   atomic_read(&fscache_n_acquires),
+		   atomic_read(&fscache_n_acquires_null),
+		   atomic_read(&fscache_n_acquires_no_cache),
+		   atomic_read(&fscache_n_acquires_ok),
+		   atomic_read(&fscache_n_acquires_nobufs),
+		   atomic_read(&fscache_n_acquires_oom));
+
+	seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u tmo=%u\n",
+		   atomic_read(&fscache_n_object_lookups),
+		   atomic_read(&fscache_n_object_lookups_negative),
+		   atomic_read(&fscache_n_object_lookups_positive),
+		   atomic_read(&fscache_n_object_created),
+		   atomic_read(&fscache_n_object_lookups_timed_out));
+
+	seq_printf(m, "Invals : n=%u run=%u\n",
+		   atomic_read(&fscache_n_invalidates),
+		   atomic_read(&fscache_n_invalidates_run));
+
+	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
+		   atomic_read(&fscache_n_updates),
+		   atomic_read(&fscache_n_updates_null),
+		   atomic_read(&fscache_n_updates_run));
+
+	seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u rtr=%u\n",
+		   atomic_read(&fscache_n_relinquishes),
+		   atomic_read(&fscache_n_relinquishes_null),
+		   atomic_read(&fscache_n_relinquishes_waitcrt),
+		   atomic_read(&fscache_n_relinquishes_retire));
+
+	seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n",
+		   atomic_read(&fscache_n_attr_changed),
+		   atomic_read(&fscache_n_attr_changed_ok),
+		   atomic_read(&fscache_n_attr_changed_nobufs),
+		   atomic_read(&fscache_n_attr_changed_nomem),
+		   atomic_read(&fscache_n_attr_changed_calls));
+
+	seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n",
+		   atomic_read(&fscache_n_allocs),
+		   atomic_read(&fscache_n_allocs_ok),
+		   atomic_read(&fscache_n_allocs_wait),
+		   atomic_read(&fscache_n_allocs_nobufs),
+		   atomic_read(&fscache_n_allocs_intr));
+	seq_printf(m, "Allocs : ops=%u owt=%u abt=%u\n",
+		   atomic_read(&fscache_n_alloc_ops),
+		   atomic_read(&fscache_n_alloc_op_waits),
+		   atomic_read(&fscache_n_allocs_object_dead));
+
+	seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u"
+		   " int=%u oom=%u\n",
+		   atomic_read(&fscache_n_retrievals),
+		   atomic_read(&fscache_n_retrievals_ok),
+		   atomic_read(&fscache_n_retrievals_wait),
+		   atomic_read(&fscache_n_retrievals_nodata),
+		   atomic_read(&fscache_n_retrievals_nobufs),
+		   atomic_read(&fscache_n_retrievals_intr),
+		   atomic_read(&fscache_n_retrievals_nomem));
+	seq_printf(m, "Retrvls: ops=%u owt=%u abt=%u\n",
+		   atomic_read(&fscache_n_retrieval_ops),
+		   atomic_read(&fscache_n_retrieval_op_waits),
+		   atomic_read(&fscache_n_retrievals_object_dead));
+
+	seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n",
+		   atomic_read(&fscache_n_stores),
+		   atomic_read(&fscache_n_stores_ok),
+		   atomic_read(&fscache_n_stores_again),
+		   atomic_read(&fscache_n_stores_nobufs),
+		   atomic_read(&fscache_n_stores_oom));
+	seq_printf(m, "Stores : ops=%u run=%u pgs=%u rxd=%u olm=%u\n",
+		   atomic_read(&fscache_n_store_ops),
+		   atomic_read(&fscache_n_store_calls),
+		   atomic_read(&fscache_n_store_pages),
+		   atomic_read(&fscache_n_store_radix_deletes),
+		   atomic_read(&fscache_n_store_pages_over_limit));
+
+	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u wt=%u\n",
+		   atomic_read(&fscache_n_store_vmscan_not_storing),
+		   atomic_read(&fscache_n_store_vmscan_gone),
+		   atomic_read(&fscache_n_store_vmscan_busy),
+		   atomic_read(&fscache_n_store_vmscan_cancelled),
+		   atomic_read(&fscache_n_store_vmscan_wait));
+
+	seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u rej=%u\n",
+		   atomic_read(&fscache_n_op_pend),
+		   atomic_read(&fscache_n_op_run),
+		   atomic_read(&fscache_n_op_enqueue),
+		   atomic_read(&fscache_n_op_cancelled),
+		   atomic_read(&fscache_n_op_rejected));
+	seq_printf(m, "Ops    : ini=%u dfr=%u rel=%u gc=%u\n",
+		   atomic_read(&fscache_n_op_initialised),
+		   atomic_read(&fscache_n_op_deferred_release),
+		   atomic_read(&fscache_n_op_release),
+		   atomic_read(&fscache_n_op_gc));
+
+	seq_printf(m, "CacheOp: alo=%d luo=%d luc=%d gro=%d\n",
+		   atomic_read(&fscache_n_cop_alloc_object),
+		   atomic_read(&fscache_n_cop_lookup_object),
+		   atomic_read(&fscache_n_cop_lookup_complete),
+		   atomic_read(&fscache_n_cop_grab_object));
+	seq_printf(m, "CacheOp: inv=%d upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+		   atomic_read(&fscache_n_cop_invalidate_object),
+		   atomic_read(&fscache_n_cop_update_object),
+		   atomic_read(&fscache_n_cop_drop_object),
+		   atomic_read(&fscache_n_cop_put_object),
+		   atomic_read(&fscache_n_cop_attr_changed),
+		   atomic_read(&fscache_n_cop_sync_cache));
+	seq_printf(m, "CacheOp: rap=%d ras=%d alp=%d als=%d wrp=%d ucp=%d dsp=%d\n",
+		   atomic_read(&fscache_n_cop_read_or_alloc_page),
+		   atomic_read(&fscache_n_cop_read_or_alloc_pages),
+		   atomic_read(&fscache_n_cop_allocate_page),
+		   atomic_read(&fscache_n_cop_allocate_pages),
+		   atomic_read(&fscache_n_cop_write_page),
+		   atomic_read(&fscache_n_cop_uncache_page),
+		   atomic_read(&fscache_n_cop_dissociate_pages));
+	seq_printf(m, "CacheEv: nsp=%d stl=%d rtr=%d cul=%d\n",
+		   atomic_read(&fscache_n_cache_no_space_reject),
+		   atomic_read(&fscache_n_cache_stale_objects),
+		   atomic_read(&fscache_n_cache_retired_objects),
+		   atomic_read(&fscache_n_cache_culled_objects));
+	return 0;
+}