M7350v1_en_gpl

kernel/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

kernel/fs/fscache/Makefile

@@ -0,0 +1,20 @@
+#
+# 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

kernel/fs/fscache/cache.c

@@ -0,0 +1,420 @@
+/* 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 (object->state >= FSCACHE_OBJECT_DYING ||
+		    test_bit(FSCACHE_IOERROR, &cache->flags))
+			cache = NULL;
+
+		spin_unlock(&cookie->lock);
+		_leave(" = %p [parent]", cache);
+		return cache;
+	}
+
+	/* the parent is unbacked */
+	if (cookie->def->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;
+
+	BUG_ON(!cache->ops);
+	BUG_ON(!ifsdef);
+
+	cache->flags = 0;
+	ifsdef->event_mask = ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+	ifsdef->state = FSCACHE_OBJECT_ACTIVE;
+
+	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->cookie = &fscache_fsdef_index;
+	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);
+
+	printk(KERN_NOTICE "FS-Cache: 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:
+	printk(KERN_ERR "FS-Cache: 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)
+{
+	set_bit(FSCACHE_IOERROR, &cache->flags);
+
+	printk(KERN_ERR "FS-Cache: 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;
+
+	spin_lock(&cache->object_list_lock);
+
+	while (!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);
+
+		spin_lock(&object->lock);
+		spin_unlock(&cache->object_list_lock);
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_WITHDRAW);
+		spin_unlock(&object->lock);
+
+		cond_resched();
+		spin_lock(&cache->object_list_lock);
+	}
+
+	spin_unlock(&cache->object_list_lock);
+}
+
+/**
+ * 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("");
+
+	printk(KERN_NOTICE "FS-Cache: 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);

kernel/fs/fscache/cookie.c

@@ -0,0 +1,514 @@
+/* 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);
+
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie);
+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);
+
+/*
+ * initialise an cookie jar slab element prior to any use
+ */
+void fscache_cookie_init_once(void *_cookie)
+{
+	struct fscache_cookie *cookie = _cookie;
+
+	memset(cookie, 0, sizeof(*cookie));
+	spin_lock_init(&cookie->lock);
+	spin_lock_init(&cookie->stores_lock);
+	INIT_HLIST_HEAD(&cookie->backing_objects);
+}
+
+/*
+ * 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,
+	void *netfs_data)
+{
+	struct fscache_cookie *cookie;
+
+	BUG_ON(!def);
+
+	_enter("{%s},{%s},%p",
+	       parent ? (char *) parent->def->name : "<no-parent>",
+	       def->name, netfs_data);
+
+	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->get_key);
+	BUG_ON(!def->name[0]);
+
+	BUG_ON(def->type == FSCACHE_COOKIE_TYPE_INDEX &&
+	       parent->def->type != FSCACHE_COOKIE_TYPE_INDEX);
+
+	/* allocate and initialise a cookie */
+	cookie = kmem_cache_alloc(fscache_cookie_jar, GFP_KERNEL);
+	if (!cookie) {
+		fscache_stat(&fscache_n_acquires_oom);
+		_leave(" [ENOMEM]");
+		return NULL;
+	}
+
+	atomic_set(&cookie->usage, 1);
+	atomic_set(&cookie->n_children, 0);
+
+	atomic_inc(&parent->usage);
+	atomic_inc(&parent->n_children);
+
+	cookie->def		= def;
+	cookie->parent		= parent;
+	cookie->netfs_data	= netfs_data;
+	cookie->flags		= 0;
+
+	/* 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_WAIT);
+
+	switch (cookie->def->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;
+	}
+
+	/* 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->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		if (fscache_acquire_non_index_cookie(cookie) < 0) {
+			atomic_dec(&parent->n_children);
+			__fscache_cookie_put(cookie);
+			fscache_stat(&fscache_n_acquires_nobufs);
+			_leave(" = NULL");
+			return NULL;
+		}
+	}
+
+	fscache_stat(&fscache_n_acquires_ok);
+	_leave(" = %p", cookie);
+	return cookie;
+}
+EXPORT_SYMBOL(__fscache_acquire_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)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+	uint64_t i_size;
+	int ret;
+
+	_enter("");
+
+	cookie->flags = 1 << FSCACHE_COOKIE_UNAVAILABLE;
+
+	/* 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);
+
+	cookie->flags =
+		(1 << FSCACHE_COOKIE_LOOKING_UP) |
+		(1 << FSCACHE_COOKIE_CREATING) |
+		(1 << FSCACHE_COOKIE_NO_DATA_YET);
+
+	/* 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;
+	}
+
+	/* pass on how big the object we're caching is supposed to be */
+	cookie->def->get_attr(cookie->netfs_data, &i_size);
+
+	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, i_size);
+
+	/* initiate the process of looking up all the objects in the chain
+	 * (done by fscache_initialise_object()) */
+	fscache_enqueue_object(object);
+
+	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,
+			    fscache_wait_bit, 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;
+	struct hlist_node *_n;
+	int ret;
+
+	_enter("%p,%p{%s}", cache, cookie, cookie->def->name);
+
+	spin_lock(&cookie->lock);
+	hlist_for_each_entry(object, _n, &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;
+	}
+
+	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_stat_d(&fscache_n_cop_put_object);
+	}
+
+	_leave(" = 0");
+	return 0;
+
+object_already_extant:
+	ret = -ENOBUFS;
+	if (object->state >= FSCACHE_OBJECT_DYING) {
+		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_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;
+	struct hlist_node *_n;
+	int ret;
+
+	_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
+
+	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, _n, &cookie->backing_objects, cookie_link) {
+		if (p->cache == object->cache) {
+			if (p->state >= FSCACHE_OBJECT_DYING)
+				ret = -ENOBUFS;
+			goto cant_attach_object;
+		}
+	}
+
+	/* pin the parent object */
+	spin_lock_nested(&cookie->parent->lock, 1);
+	hlist_for_each_entry(p, _n, &cookie->parent->backing_objects,
+			     cookie_link) {
+		if (p->cache == object->cache) {
+			if (p->state >= FSCACHE_OBJECT_DYING) {
+				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 */
+	object->cookie = cookie;
+	atomic_inc(&cookie->usage);
+	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;
+}
+
+/*
+ * update the index entries backing a cookie
+ */
+void __fscache_update_cookie(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct hlist_node *_p;
+
+	fscache_stat(&fscache_n_updates);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_updates_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("{%s}", cookie->def->name);
+
+	BUG_ON(!cookie->def->get_aux);
+
+	spin_lock(&cookie->lock);
+
+	/* update the index entry on disk in each cache backing this cookie */
+	hlist_for_each_entry(object, _p,
+			     &cookie->backing_objects, cookie_link) {
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+	}
+
+	spin_unlock(&cookie->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_update_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, int retire)
+{
+	struct fscache_cache *cache;
+	struct fscache_object *object;
+	unsigned long event;
+
+	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",
+	       cookie, cookie->def->name, cookie->netfs_data, retire);
+
+	if (atomic_read(&cookie->n_children) != 0) {
+		printk(KERN_ERR "FS-Cache: Cookie '%s' still has children\n",
+		       cookie->def->name);
+		BUG();
+	}
+
+	/* wait for the cookie to finish being instantiated (or to fail) */
+	if (test_bit(FSCACHE_COOKIE_CREATING, &cookie->flags)) {
+		fscache_stat(&fscache_n_relinquishes_waitcrt);
+		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_CREATING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	}
+
+	event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE;
+
+	spin_lock(&cookie->lock);
+
+	/* break links with all the active objects */
+	while (!hlist_empty(&cookie->backing_objects)) {
+		object = hlist_entry(cookie->backing_objects.first,
+				     struct fscache_object,
+				     cookie_link);
+
+		_debug("RELEASE OBJ%x", object->debug_id);
+
+		/* detach each cache object from the object cookie */
+		spin_lock(&object->lock);
+		hlist_del_init(&object->cookie_link);
+
+		cache = object->cache;
+		object->cookie = NULL;
+		fscache_raise_event(object, event);
+		spin_unlock(&object->lock);
+
+		if (atomic_dec_and_test(&cookie->usage))
+			/* the cookie refcount shouldn't be reduced to 0 yet */
+			BUG();
+	}
+
+	/* detach pointers back to the netfs */
+	cookie->netfs_data	= NULL;
+	cookie->def		= NULL;
+
+	spin_unlock(&cookie->lock);
+
+	if (cookie->parent) {
+		ASSERTCMP(atomic_read(&cookie->parent->usage), >, 0);
+		ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0);
+		atomic_dec(&cookie->parent->n_children);
+	}
+
+	/* finally dispose of the cookie */
+	ASSERTCMP(atomic_read(&cookie->usage), >, 0);
+	fscache_cookie_put(cookie);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_relinquish_cookie);
+
+/*
+ * destroy a cookie
+ */
+void __fscache_cookie_put(struct fscache_cookie *cookie)
+{
+	struct fscache_cookie *parent;
+
+	_enter("%p", cookie);
+
+	for (;;) {
+		_debug("FREE COOKIE %p", cookie);
+		parent = cookie->parent;
+		BUG_ON(!hlist_empty(&cookie->backing_objects));
+		kmem_cache_free(fscache_cookie_jar, cookie);
+
+		if (!parent)
+			break;
+
+		cookie = parent;
+		BUG_ON(atomic_read(&cookie->usage) <= 0);
+		if (!atomic_dec_and_test(&cookie->usage))
+			break;
+	}
+
+	_leave("");
+}

kernel/fs/fscache/fsdef.c

@@ -0,0 +1,144 @@
+/* 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 uint16_t fscache_fsdef_netfs_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax);
+
+static uint16_t fscache_fsdef_netfs_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax);
+
+static
+enum fscache_checkaux fscache_fsdef_netfs_check_aux(void *cookie_netfs_data,
+						    const void *data,
+						    uint16_t datalen);
+
+/*
+ * 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),
+	.lock		= __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock),
+	.backing_objects = HLIST_HEAD_INIT,
+	.def		= &fscache_fsdef_index_def,
+};
+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,
+	.get_key	= fscache_fsdef_netfs_get_key,
+	.get_aux	= fscache_fsdef_netfs_get_aux,
+	.check_aux	= fscache_fsdef_netfs_check_aux,
+};
+
+/*
+ * get the key data for an FSDEF index record - this is the name of the netfs
+ * for which this entry is created
+ */
+static uint16_t fscache_fsdef_netfs_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct fscache_netfs *netfs = cookie_netfs_data;
+	unsigned klen;
+
+	_enter("{%s.%u},", netfs->name, netfs->version);
+
+	klen = strlen(netfs->name);
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, netfs->name, klen);
+	return klen;
+}
+
+/*
+ * get the auxiliary data for an FSDEF index record - this is the index
+ * structure version number of the netfs for which this version is created
+ */
+static uint16_t fscache_fsdef_netfs_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct fscache_netfs *netfs = cookie_netfs_data;
+	unsigned dlen;
+
+	_enter("{%s.%u},", netfs->name, netfs->version);
+
+	dlen = sizeof(uint32_t);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, &netfs->version, dlen);
+	return dlen;
+}
+
+/*
+ * 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)
+{
+	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;
+}

kernel/fs/fscache/histogram.c

@@ -0,0 +1,109 @@
+/* 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)
+{
+}
+
+static const struct seq_operations fscache_histogram_ops = {
+	.start		= fscache_histogram_start,
+	.stop		= fscache_histogram_stop,
+	.next		= fscache_histogram_next,
+	.show		= fscache_histogram_show,
+};
+
+/*
+ * open "/proc/fs/fscache/histogram" to provide latency data
+ */
+static int fscache_histogram_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fscache_histogram_ops);
+}
+
+const struct file_operations fscache_histogram_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_histogram_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};

kernel/fs/fscache/internal.h

@@ -0,0 +1,438 @@
+/* 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
+ *
+ */
+
+#include <linux/fscache-cache.h>
+#include <linux/sched.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_cookie_init_once(void *);
+extern void __fscache_cookie_put(struct fscache_cookie *);
+
+/*
+ * 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 file_operations fscache_histogram_fops;
+
+#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);
+
+static inline bool fscache_object_congested(void)
+{
+	return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq);
+}
+
+extern int fscache_wait_bit(void *);
+extern int fscache_wait_bit_interruptible(void *);
+
+/*
+ * object.c
+ */
+extern const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5];
+
+extern void fscache_withdrawing_object(struct fscache_cache *,
+				       struct fscache_object *);
+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 *);
+#else
+#define fscache_objlist_add(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 *);
+extern void fscache_abort_object(struct fscache_object *);
+extern void fscache_start_operations(struct fscache_object *);
+extern void fscache_operation_gc(struct work_struct *);
+
+/*
+ * 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_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_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_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_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;
+
+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)
+
+extern const struct file_operations fscache_stats_fops;
+#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)
+{
+	if (!test_and_set_bit(event, &object->events) &&
+	    test_bit(event, &object->event_mask))
+		fscache_enqueue_object(object);
+}
+
+/*
+ * drop a reference to a cookie
+ */
+static inline void fscache_cookie_put(struct fscache_cookie *cookie)
+{
+	BUG_ON(atomic_read(&cookie->usage) <= 0);
+	if (atomic_dec_and_test(&cookie->usage))
+		__fscache_cookie_put(cookie);
+}
+
+/*
+ * 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);
+}
+
+/*****************************************************************************/
+/*
+ * 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))) {						\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		printk(KERN_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))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		printk(KERN_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 */

kernel/fs/fscache/main.c

@@ -0,0 +1,218 @@
+/* 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>
+#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;
+}
+
+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,
+	},
+	{}
+};
+
+ctl_table fscache_sysctls_root[] = {
+	{
+		.procname	= "fscache",
+		.mode		= 0555,
+		.child		= fscache_sysctls,
+	},
+	{}
+};
+#endif
+
+/*
+ * 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,
+					       fscache_cookie_init_once);
+	if (!fscache_cookie_jar) {
+		printk(KERN_NOTICE
+		       "FS-Cache: 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;
+
+	printk(KERN_NOTICE "FS-Cache: 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);
+	printk(KERN_NOTICE "FS-Cache: Unloaded\n");
+}
+
+module_exit(fscache_exit);
+
+/*
+ * wait_on_bit() sleep function for uninterruptible waiting
+ */
+int fscache_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+EXPORT_SYMBOL(fscache_wait_bit);
+
+/*
+ * wait_on_bit() sleep function for interruptible waiting
+ */
+int fscache_wait_bit_interruptible(void *flags)
+{
+	schedule();
+	return signal_pending(current);
+}
+EXPORT_SYMBOL(fscache_wait_bit_interruptible);

kernel/fs/fscache/netfs.c

@@ -0,0 +1,103 @@
+/* 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"
+
+static LIST_HEAD(fscache_netfs_list);
+
+/*
+ * register a network filesystem for caching
+ */
+int __fscache_register_netfs(struct fscache_netfs *netfs)
+{
+	struct fscache_netfs *ptr;
+	int ret;
+
+	_enter("{%s}", netfs->name);
+
+	INIT_LIST_HEAD(&netfs->link);
+
+	/* allocate a cookie for the primary index */
+	netfs->primary_index =
+		kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL);
+
+	if (!netfs->primary_index) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	/* initialise the primary index cookie */
+	atomic_set(&netfs->primary_index->usage, 1);
+	atomic_set(&netfs->primary_index->n_children, 0);
+
+	netfs->primary_index->def		= &fscache_fsdef_netfs_def;
+	netfs->primary_index->parent		= &fscache_fsdef_index;
+	netfs->primary_index->netfs_data	= netfs;
+
+	atomic_inc(&netfs->primary_index->parent->usage);
+	atomic_inc(&netfs->primary_index->parent->n_children);
+
+	spin_lock_init(&netfs->primary_index->lock);
+	INIT_HLIST_HEAD(&netfs->primary_index->backing_objects);
+
+	/* check the netfs type is not already present */
+	down_write(&fscache_addremove_sem);
+
+	ret = -EEXIST;
+	list_for_each_entry(ptr, &fscache_netfs_list, link) {
+		if (strcmp(ptr->name, netfs->name) == 0)
+			goto already_registered;
+	}
+
+	list_add(&netfs->link, &fscache_netfs_list);
+	ret = 0;
+
+	printk(KERN_NOTICE "FS-Cache: Netfs '%s' registered for caching\n",
+	       netfs->name);
+
+already_registered:
+	up_write(&fscache_addremove_sem);
+
+	if (ret < 0) {
+		netfs->primary_index->parent = NULL;
+		__fscache_cookie_put(netfs->primary_index);
+		netfs->primary_index = NULL;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+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);
+
+	down_write(&fscache_addremove_sem);
+
+	list_del(&netfs->link);
+	fscache_relinquish_cookie(netfs->primary_index, 0);
+
+	up_write(&fscache_addremove_sem);
+
+	printk(KERN_NOTICE "FS-Cache: Netfs '%s' unregistered from caching\n",
+	       netfs->name);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_unregister_netfs);

kernel/fs/fscache/object-list.c

@@ -0,0 +1,432 @@
+/* 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 */
+
+	u8		buf[512];	/* key and aux data buffer */
+};
+
+/*
+ * 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;
+
+	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);
+}
+
+/**
+ * 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 *obj)
+{
+	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);
+}
+EXPORT_SYMBOL(fscache_object_destroy);
+
+/*
+ * 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;
+	unsigned long config = data->config;
+	uint16_t keylen, auxlen;
+	char _type[3], *type;
+	bool no_cookie;
+	u8 *buf = data->buf, *p;
+
+	if ((unsigned long) v == 1) {
+		seq_puts(m, "OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS"
+			 " EM EV F 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)
+
+	if (~config) {
+		FILTER(obj->cookie,
+		       COOKIE, NOCOOKIE);
+		FILTER(obj->state != FSCACHE_OBJECT_ACTIVE ||
+		       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 %1lx %1x | ",
+		   obj->debug_id,
+		   obj->parent ? obj->parent->debug_id : -1,
+		   fscache_object_states_short[obj->state],
+		   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 & FSCACHE_OBJECT_EVENTS_MASK,
+		   obj->events,
+		   obj->flags,
+		   work_busy(&obj->work));
+
+	no_cookie = true;
+	keylen = auxlen = 0;
+	if (obj->cookie) {
+		spin_lock(&obj->lock);
+		if (obj->cookie) {
+			switch (obj->cookie->def->type) {
+			case 0:
+				type = "IX";
+				break;
+			case 1:
+				type = "DT";
+				break;
+			default:
+				sprintf(_type, "%02u",
+					obj->cookie->def->type);
+				type = _type;
+				break;
+			}
+
+			seq_printf(m, "%-16s %s %2lx %16p",
+				   obj->cookie->def->name,
+				   type,
+				   obj->cookie->flags,
+				   obj->cookie->netfs_data);
+
+			if (obj->cookie->def->get_key &&
+			    config & FSCACHE_OBJLIST_CONFIG_KEY)
+				keylen = obj->cookie->def->get_key(
+					obj->cookie->netfs_data,
+					buf, 400);
+
+			if (obj->cookie->def->get_aux &&
+			    config & FSCACHE_OBJLIST_CONFIG_AUX)
+				auxlen = obj->cookie->def->get_aux(
+					obj->cookie->netfs_data,
+					buf + keylen, 512 - keylen);
+
+			no_cookie = false;
+		}
+		spin_unlock(&obj->lock);
+
+		if (!no_cookie && (keylen > 0 || auxlen > 0)) {
+			seq_printf(m, " ");
+			for (p = buf; keylen > 0; keylen--)
+				seq_printf(m, "%02x", *p++);
+			if (auxlen > 0) {
+				if (config & FSCACHE_OBJLIST_CONFIG_KEY)
+					seq_printf(m, ", ");
+				for (; auxlen > 0; auxlen--)
+					seq_printf(m, "%02x", *p++);
+			}
+		}
+	}
+
+	if (no_cookie)
+		seq_printf(m, "<no_cookie>\n");
+	else
+		seq_printf(m, "\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
+	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 = key->payload.data;
+	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;
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &fscache_objlist_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+
+	/* buffer for key extraction */
+	data = kmalloc(sizeof(struct fscache_objlist_data), GFP_KERNEL);
+	if (!data) {
+		seq_release(inode, file);
+		return -ENOMEM;
+	}
+
+	/* get the configuration key */
+	fscache_objlist_config(data);
+
+	m->private = 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 = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_objlist_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= fscache_objlist_release,
+};

kernel/fs/fscache/object.c

@@ -0,0 +1,892 @@
+/* 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 "internal.h"
+
+const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
+	[FSCACHE_OBJECT_INIT]		= "OBJECT_INIT",
+	[FSCACHE_OBJECT_LOOKING_UP]	= "OBJECT_LOOKING_UP",
+	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
+	[FSCACHE_OBJECT_AVAILABLE]	= "OBJECT_AVAILABLE",
+	[FSCACHE_OBJECT_ACTIVE]		= "OBJECT_ACTIVE",
+	[FSCACHE_OBJECT_UPDATING]	= "OBJECT_UPDATING",
+	[FSCACHE_OBJECT_DYING]		= "OBJECT_DYING",
+	[FSCACHE_OBJECT_LC_DYING]	= "OBJECT_LC_DYING",
+	[FSCACHE_OBJECT_ABORT_INIT]	= "OBJECT_ABORT_INIT",
+	[FSCACHE_OBJECT_RELEASING]	= "OBJECT_RELEASING",
+	[FSCACHE_OBJECT_RECYCLING]	= "OBJECT_RECYCLING",
+	[FSCACHE_OBJECT_WITHDRAWING]	= "OBJECT_WITHDRAWING",
+	[FSCACHE_OBJECT_DEAD]		= "OBJECT_DEAD",
+};
+EXPORT_SYMBOL(fscache_object_states);
+
+const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = {
+	[FSCACHE_OBJECT_INIT]		= "INIT",
+	[FSCACHE_OBJECT_LOOKING_UP]	= "LOOK",
+	[FSCACHE_OBJECT_CREATING]	= "CRTN",
+	[FSCACHE_OBJECT_AVAILABLE]	= "AVBL",
+	[FSCACHE_OBJECT_ACTIVE]		= "ACTV",
+	[FSCACHE_OBJECT_UPDATING]	= "UPDT",
+	[FSCACHE_OBJECT_DYING]		= "DYNG",
+	[FSCACHE_OBJECT_LC_DYING]	= "LCDY",
+	[FSCACHE_OBJECT_ABORT_INIT]	= "ABTI",
+	[FSCACHE_OBJECT_RELEASING]	= "RELS",
+	[FSCACHE_OBJECT_RECYCLING]	= "RCYC",
+	[FSCACHE_OBJECT_WITHDRAWING]	= "WTHD",
+	[FSCACHE_OBJECT_DEAD]		= "DEAD",
+};
+
+static int  fscache_get_object(struct fscache_object *);
+static void fscache_put_object(struct fscache_object *);
+static void fscache_initialise_object(struct fscache_object *);
+static void fscache_lookup_object(struct fscache_object *);
+static void fscache_object_available(struct fscache_object *);
+static void fscache_release_object(struct fscache_object *);
+static void fscache_withdraw_object(struct fscache_object *);
+static void fscache_enqueue_dependents(struct fscache_object *);
+static void fscache_dequeue_object(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_ops--;
+	parent->n_obj_ops--;
+	if (parent->n_ops == 0)
+		fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+	spin_unlock(&parent->lock);
+}
+
+/*
+ * process events that have been sent to an object's state machine
+ * - initiates parent lookup
+ * - does object lookup
+ * - does object creation
+ * - does object recycling and retirement
+ * - does object withdrawal
+ */
+static void fscache_object_state_machine(struct fscache_object *object)
+{
+	enum fscache_object_state new_state;
+	struct fscache_cookie *cookie;
+
+	ASSERT(object != NULL);
+
+	_enter("{OBJ%x,%s,%lx}",
+	       object->debug_id, fscache_object_states[object->state],
+	       object->events);
+
+	switch (object->state) {
+		/* wait for the parent object to become ready */
+	case FSCACHE_OBJECT_INIT:
+		object->event_mask =
+			ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+		fscache_initialise_object(object);
+		goto done;
+
+		/* look up the object metadata on disk */
+	case FSCACHE_OBJECT_LOOKING_UP:
+		fscache_lookup_object(object);
+		goto lookup_transit;
+
+		/* create the object metadata on disk */
+	case FSCACHE_OBJECT_CREATING:
+		fscache_lookup_object(object);
+		goto lookup_transit;
+
+		/* handle an object becoming available; start pending
+		 * operations and queue dependent operations for processing */
+	case FSCACHE_OBJECT_AVAILABLE:
+		fscache_object_available(object);
+		goto active_transit;
+
+		/* normal running state */
+	case FSCACHE_OBJECT_ACTIVE:
+		goto active_transit;
+
+		/* update the object metadata on disk */
+	case FSCACHE_OBJECT_UPDATING:
+		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
+		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);
+		goto active_transit;
+
+		/* handle an object dying during lookup or creation */
+	case FSCACHE_OBJECT_LC_DYING:
+		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+		fscache_stat(&fscache_n_cop_lookup_complete);
+		object->cache->ops->lookup_complete(object);
+		fscache_stat_d(&fscache_n_cop_lookup_complete);
+
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DYING;
+		cookie = object->cookie;
+		if (cookie) {
+			if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP,
+					       &cookie->flags))
+				wake_up_bit(&cookie->flags,
+					    FSCACHE_COOKIE_LOOKING_UP);
+			if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+					       &cookie->flags))
+				wake_up_bit(&cookie->flags,
+					    FSCACHE_COOKIE_CREATING);
+		}
+		spin_unlock(&object->lock);
+
+		fscache_done_parent_op(object);
+
+		/* wait for completion of all active operations on this object
+		 * and the death of all child objects of this object */
+	case FSCACHE_OBJECT_DYING:
+	dying:
+		clear_bit(FSCACHE_OBJECT_EV_CLEARED, &object->events);
+		spin_lock(&object->lock);
+		_debug("dying OBJ%x {%d,%d}",
+		       object->debug_id, object->n_ops, object->n_children);
+		if (object->n_ops == 0 && object->n_children == 0) {
+			object->event_mask &=
+				~(1 << FSCACHE_OBJECT_EV_CLEARED);
+			object->event_mask |=
+				(1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+				(1 << FSCACHE_OBJECT_EV_RETIRE) |
+				(1 << FSCACHE_OBJECT_EV_RELEASE) |
+				(1 << FSCACHE_OBJECT_EV_ERROR);
+		} else {
+			object->event_mask &=
+				~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+				  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+				  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+				  (1 << FSCACHE_OBJECT_EV_ERROR));
+			object->event_mask |=
+				1 << FSCACHE_OBJECT_EV_CLEARED;
+		}
+		spin_unlock(&object->lock);
+		fscache_enqueue_dependents(object);
+		fscache_start_operations(object);
+		goto terminal_transit;
+
+		/* handle an abort during initialisation */
+	case FSCACHE_OBJECT_ABORT_INIT:
+		_debug("handle abort init %lx", object->events);
+		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+
+		spin_lock(&object->lock);
+		fscache_dequeue_object(object);
+
+		object->state = FSCACHE_OBJECT_DYING;
+		if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+				       &object->cookie->flags))
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_CREATING);
+		spin_unlock(&object->lock);
+		goto dying;
+
+		/* handle the netfs releasing an object and possibly marking it
+		 * obsolete too */
+	case FSCACHE_OBJECT_RELEASING:
+	case FSCACHE_OBJECT_RECYCLING:
+		object->event_mask &=
+			~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+			  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			  (1 << FSCACHE_OBJECT_EV_ERROR));
+		fscache_release_object(object);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DEAD;
+		spin_unlock(&object->lock);
+		fscache_stat(&fscache_n_object_dead);
+		goto terminal_transit;
+
+		/* handle the parent cache of this object being withdrawn from
+		 * active service */
+	case FSCACHE_OBJECT_WITHDRAWING:
+		object->event_mask &=
+			~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+			  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			  (1 << FSCACHE_OBJECT_EV_ERROR));
+		fscache_withdraw_object(object);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DEAD;
+		spin_unlock(&object->lock);
+		fscache_stat(&fscache_n_object_dead);
+		goto terminal_transit;
+
+		/* complain about the object being woken up once it is
+		 * deceased */
+	case FSCACHE_OBJECT_DEAD:
+		printk(KERN_ERR "FS-Cache:"
+		       " Unexpected event in dead state %lx\n",
+		       object->events & object->event_mask);
+		BUG();
+
+	default:
+		printk(KERN_ERR "FS-Cache: Unknown object state %u\n",
+		       object->state);
+		BUG();
+	}
+
+	/* determine the transition from a lookup state */
+lookup_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+	case FSCACHE_OBJECT_EV_RETIRE:
+	case FSCACHE_OBJECT_EV_RELEASE:
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_LC_DYING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_REQUEUE:
+		goto done;
+	case -1:
+		goto done; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+	/* determine the transition from an active state */
+active_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+	case FSCACHE_OBJECT_EV_RETIRE:
+	case FSCACHE_OBJECT_EV_RELEASE:
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_DYING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_UPDATE:
+		new_state = FSCACHE_OBJECT_UPDATING;
+		goto change_state;
+	case -1:
+		new_state = FSCACHE_OBJECT_ACTIVE;
+		goto change_state; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+	/* determine the transition from a terminal state */
+terminal_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+		new_state = FSCACHE_OBJECT_WITHDRAWING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_RETIRE:
+		new_state = FSCACHE_OBJECT_RECYCLING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_RELEASE:
+		new_state = FSCACHE_OBJECT_RELEASING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_WITHDRAWING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_CLEARED:
+		new_state = FSCACHE_OBJECT_DYING;
+		goto change_state;
+	case -1:
+		goto done; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+change_state:
+	spin_lock(&object->lock);
+	object->state = new_state;
+	spin_unlock(&object->lock);
+
+done:
+	_leave(" [->%s]", fscache_object_states[object->state]);
+	return;
+
+unsupported_event:
+	printk(KERN_ERR "FS-Cache:"
+	       " Unsupported event %lx [mask %lx] in state %s\n",
+	       object->events, object->event_mask,
+	       fscache_object_states[object->state]);
+	BUG();
+}
+
+/*
+ * execute an object
+ */
+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_state_machine(object);
+	fscache_hist(fscache_objs_histogram, start);
+	if (object->events & object->event_mask)
+		fscache_enqueue_object(object);
+	clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	fscache_put_object(object);
+}
+EXPORT_SYMBOL(fscache_object_work_func);
+
+/*
+ * 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
+ * - an object's cookie is pinned until we clear FSCACHE_COOKIE_CREATING on the
+ *   leaf-most cookies of the object and all its children
+ */
+static void fscache_initialise_object(struct fscache_object *object)
+{
+	struct fscache_object *parent;
+
+	_enter("");
+	ASSERT(object->cookie != NULL);
+	ASSERT(object->cookie->parent != NULL);
+
+	if (object->events & ((1 << FSCACHE_OBJECT_EV_ERROR) |
+			      (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			      (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			      (1 << FSCACHE_OBJECT_EV_WITHDRAW))) {
+		_debug("abort init %lx", object->events);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_ABORT_INIT;
+		spin_unlock(&object->lock);
+		return;
+	}
+
+	spin_lock(&object->cookie->lock);
+	spin_lock_nested(&object->cookie->parent->lock, 1);
+
+	parent = object->parent;
+	if (!parent) {
+		_debug("no parent");
+		set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+	} else {
+		spin_lock(&object->lock);
+		spin_lock_nested(&parent->lock, 1);
+		_debug("parent %s", fscache_object_states[parent->state]);
+
+		if (parent->state >= FSCACHE_OBJECT_DYING) {
+			_debug("bad parent");
+			set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+		} else if (parent->state < FSCACHE_OBJECT_AVAILABLE) {
+			_debug("wait");
+
+			/* we may get woken up in this state by child objects
+			 * binding on to us, so we need to make sure we don't
+			 * add ourself to the list multiple times */
+			if (list_empty(&object->dep_link)) {
+				fscache_stat(&fscache_n_cop_grab_object);
+				object->cache->ops->grab_object(object);
+				fscache_stat_d(&fscache_n_cop_grab_object);
+				list_add(&object->dep_link,
+					 &parent->dependents);
+
+				/* fscache_acquire_non_index_cookie() uses this
+				 * to wake the chain up */
+				if (parent->state == FSCACHE_OBJECT_INIT)
+					fscache_enqueue_object(parent);
+			}
+		} else {
+			_debug("go");
+			parent->n_ops++;
+			parent->n_obj_ops++;
+			object->lookup_jif = jiffies;
+			object->state = FSCACHE_OBJECT_LOOKING_UP;
+			set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+		}
+
+		spin_unlock(&parent->lock);
+		spin_unlock(&object->lock);
+	}
+
+	spin_unlock(&object->cookie->parent->lock);
+	spin_unlock(&object->cookie->lock);
+	_leave("");
+}
+
+/*
+ * 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
+ * - an object's cookie is pinned until we clear FSCACHE_COOKIE_CREATING on the
+ *   leaf-most cookies of the object and all its children
+ */
+static void fscache_lookup_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_object *parent;
+	int ret;
+
+	_enter("");
+
+	parent = object->parent;
+	ASSERT(parent != NULL);
+	ASSERTCMP(parent->n_ops, >, 0);
+	ASSERTCMP(parent->n_obj_ops, >, 0);
+
+	/* make sure the parent is still available */
+	ASSERTCMP(parent->state, >=, FSCACHE_OBJECT_AVAILABLE);
+
+	if (parent->state >= FSCACHE_OBJECT_DYING ||
+	    test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+		_debug("unavailable");
+		set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+		_leave("");
+		return;
+	}
+
+	_debug("LOOKUP \"%s/%s\" in \"%s\"",
+	       parent->cookie->def->name, 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);
+
+	if (test_bit(FSCACHE_OBJECT_EV_ERROR, &object->events))
+		set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+
+	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);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	}
+
+	_leave("");
+}
+
+/**
+ * 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, fscache_object_states[object->state]);
+
+	spin_lock(&object->lock);
+	if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
+		fscache_stat(&fscache_n_object_lookups_negative);
+
+		/* transit here to allow write requests to begin stacking up
+		 * and read requests to begin returning ENODATA */
+		object->state = FSCACHE_OBJECT_CREATING;
+		spin_unlock(&object->lock);
+
+		set_bit(FSCACHE_COOKIE_PENDING_FILL, &cookie->flags);
+		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+		_debug("wake up lookup %p", &cookie->flags);
+		smp_mb__before_clear_bit();
+		clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	} else {
+		ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
+		spin_unlock(&object->lock);
+	}
+
+	_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, fscache_object_states[object->state]);
+
+	/* if we were still looking up, then we must have a positive lookup
+	 * result, in which case there may be data available */
+	spin_lock(&object->lock);
+	if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
+		fscache_stat(&fscache_n_object_lookups_positive);
+
+		clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+		object->state = FSCACHE_OBJECT_AVAILABLE;
+		spin_unlock(&object->lock);
+
+		smp_mb__before_clear_bit();
+		clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	} else {
+		ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
+		fscache_stat(&fscache_n_object_created);
+
+		object->state = FSCACHE_OBJECT_AVAILABLE;
+		spin_unlock(&object->lock);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+		smp_wmb();
+	}
+
+	if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_CREATING);
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_obtained_object);
+
+/*
+ * handle an object that has just become available
+ */
+static void fscache_object_available(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	if (object->cookie &&
+	    test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags))
+		wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING);
+
+	fscache_done_parent_op(object);
+	if (object->n_in_progress == 0) {
+		if (object->n_ops > 0) {
+			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
+			ASSERTIF(object->n_ops > object->n_obj_ops,
+				 !list_empty(&object->pending_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_enqueue_dependents(object);
+
+	fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif);
+	fscache_stat(&fscache_n_object_avail);
+
+	_leave("");
+}
+
+/*
+ * drop an object's attachments
+ */
+static void fscache_drop_object(struct fscache_object *object)
+{
+	struct fscache_object *parent = object->parent;
+	struct fscache_cache *cache = object->cache;
+
+	_enter("{OBJ%x,%d}", object->debug_id, object->n_children);
+
+	ASSERTCMP(object->cookie, ==, NULL);
+	ASSERT(hlist_unhashed(&object->cookie_link));
+
+	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);
+
+	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);
+
+	_leave("");
+}
+
+/*
+ * release or recycle an object that the netfs has discarded
+ */
+static void fscache_release_object(struct fscache_object *object)
+{
+	_enter("");
+
+	fscache_drop_object(object);
+}
+
+/*
+ * withdraw an object from active service
+ */
+static void fscache_withdraw_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie;
+	bool detached;
+
+	_enter("");
+
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+	if (cookie) {
+		/* need to get the cookie lock before the object lock, starting
+		 * from the object pointer */
+		atomic_inc(&cookie->usage);
+		spin_unlock(&object->lock);
+
+		detached = false;
+		spin_lock(&cookie->lock);
+		spin_lock(&object->lock);
+
+		if (object->cookie == cookie) {
+			hlist_del_init(&object->cookie_link);
+			object->cookie = NULL;
+			detached = true;
+		}
+		spin_unlock(&cookie->lock);
+		fscache_cookie_put(cookie);
+		if (detached)
+			fscache_cookie_put(cookie);
+	}
+
+	spin_unlock(&object->lock);
+
+	fscache_drop_object(object);
+}
+
+/*
+ * withdraw an object from active service at the behest of the cache
+ * - need break the links to a cached object cookie
+ * - called under two situations:
+ *   (1) recycler decides to reclaim an in-use object
+ *   (2) a cache is unmounted
+ * - have to take care as the cookie can be being relinquished by the netfs
+ *   simultaneously
+ * - the object is pinned by the caller holding a refcount on it
+ */
+void fscache_withdrawing_object(struct fscache_cache *cache,
+				struct fscache_object *object)
+{
+	bool enqueue = false;
+
+	_enter(",OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+	if (object->state < FSCACHE_OBJECT_WITHDRAWING) {
+		object->state = FSCACHE_OBJECT_WITHDRAWING;
+		enqueue = true;
+	}
+	spin_unlock(&object->lock);
+
+	if (enqueue)
+		fscache_enqueue_object(object);
+
+	_leave("");
+}
+
+/*
+ * get a ref on an object
+ */
+static int fscache_get_object(struct fscache_object *object)
+{
+	int ret;
+
+	fscache_stat(&fscache_n_cop_grab_object);
+	ret = object->cache->ops->grab_object(object) ? 0 : -EAGAIN;
+	fscache_stat_d(&fscache_n_cop_grab_object);
+	return ret;
+}
+
+/*
+ * discard a ref on a work item
+ */
+static void fscache_put_object(struct fscache_object *object)
+{
+	fscache_stat(&fscache_n_cop_put_object);
+	object->cache->ops->put_object(object);
+	fscache_stat_d(&fscache_n_cop_put_object);
+}
+
+/*
+ * 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) >= 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);
+
+		put_cpu_var(fscache_object_cong_wait);
+	}
+}
+
+/**
+ * fscache_object_sleep_till_congested - Sleep until object wq is congested
+ * @timoutp: 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 = &__get_cpu_var(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
+ * - the caller must hold the object's lock
+ * - this may cause an already locked object to wind up being processed again
+ */
+static void fscache_enqueue_dependents(struct fscache_object *object)
+{
+	struct fscache_object *dep;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (list_empty(&object->dependents))
+		return;
+
+	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);
+
+
+		/* sort onto appropriate lists */
+		fscache_enqueue_object(dep);
+		fscache_put_object(dep);
+
+		if (!list_empty(&object->dependents))
+			cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+}
+
+/*
+ * remove an object from whatever queue it's waiting on
+ * - the caller must hold object->lock
+ */
+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
+ */
+enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+					const void *data, uint16_t datalen)
+{
+	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);
+	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);

kernel/fs/fscache/operation.c

@@ -0,0 +1,463 @@
+/* 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);
+
+/**
+ * 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)
+{
+	_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);
+	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	fscache_stat(&fscache_n_op_enqueue);
+	switch (op->flags & FSCACHE_OP_TYPE) {
+	case FSCACHE_OP_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:
+		_debug("queue for caller's attention");
+		break;
+	default:
+		printk(KERN_ERR "FS-Cache: 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)
+{
+	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);
+	fscache_stat(&fscache_n_op_run);
+}
+
+/*
+ * 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)
+{
+	int ret;
+
+	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
+
+	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));
+
+	ret = -ENOBUFS;
+	if (fscache_object_is_active(object)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+
+		if (object->n_ops > 1) {
+			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 (object->state == FSCACHE_OBJECT_CREATING) {
+		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 {
+		/* not allowed to submit ops in any other state */
+		BUG();
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * report an unexpected submission
+ */
+static void fscache_report_unexpected_submission(struct fscache_object *object,
+						 struct fscache_operation *op,
+						 unsigned long 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,
+	       fscache_object_states[object->state]);
+	kdebug("objstate=%s [%s]",
+	       fscache_object_states[object->state],
+	       fscache_object_states[ostate]);
+	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 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)
+{
+	unsigned long ostate;
+	int ret;
+
+	_enter("{OBJ%x OP%x},{%u}",
+	       object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	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();
+
+	if (fscache_object_is_active(object)) {
+		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 (object->state == FSCACHE_OBJECT_CREATING) {
+		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 (object->state == FSCACHE_OBJECT_DYING ||
+		   object->state == FSCACHE_OBJECT_LC_DYING ||
+		   object->state == FSCACHE_OBJECT_WITHDRAWING) {
+		fscache_stat(&fscache_n_op_rejected);
+		ret = -ENOBUFS;
+	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+		fscache_report_unexpected_submission(object, op, ostate);
+		ASSERT(!fscache_object_is_active(object));
+		ret = -ENOBUFS;
+	} else {
+		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
+ * - 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)
+{
+	struct fscache_object *object = op->object;
+	int ret;
+
+	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
+
+	spin_lock(&object->lock);
+
+	ret = -EBUSY;
+	if (!list_empty(&op->pend_link)) {
+		fscache_stat(&fscache_n_op_cancelled);
+		list_del_init(&op->pend_link);
+		object->n_ops--;
+		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);
+		ret = 0;
+	}
+
+	spin_unlock(&object->lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * 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->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	if (!atomic_dec_and_test(&op->usage))
+		return;
+
+	_debug("PUT OP");
+	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
+		BUG();
+
+	fscache_stat(&fscache_n_op_release);
+
+	if (op->release) {
+		op->release(op);
+		op->release = NULL;
+	}
+
+	object = op->object;
+
+	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
+		atomic_dec(&object->n_reads);
+
+	/* 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;
+	}
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+		ASSERTCMP(object->n_exclusive, >, 0);
+		object->n_exclusive--;
+	}
+
+	ASSERTCMP(object->n_in_progress, >, 0);
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	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;
+
+		_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);
+
+		spin_lock(&object->lock);
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+			ASSERTCMP(object->n_exclusive, >, 0);
+			object->n_exclusive--;
+		}
+
+		ASSERTCMP(object->n_in_progress, >, 0);
+		object->n_in_progress--;
+		if (object->n_in_progress == 0)
+			fscache_start_operations(object);
+
+		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);
+
+	} 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));
+
+	ASSERT(op->processor != NULL);
+	start = jiffies;
+	op->processor(op);
+	fscache_hist(fscache_ops_histogram, start);
+	fscache_put_operation(op);
+
+	_leave("");
+}

kernel/fs/fscache/page.c

@@ -0,0 +1,996 @@
+/* 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();
+
+	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);
+
+	wait_event(*wq, !__fscache_check_page_write(cookie, page));
+}
+EXPORT_SYMBOL(__fscache_wait_on_page_write);
+
+/*
+ * decide whether a page can be released, possibly by cancelling a store to it
+ * - we're allowed to sleep if __GFP_WAIT 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);
+
+	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);
+	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);
+	if (xpage)
+		page_cache_release(xpage);
+	__fscache_uncache_page(cookie, page);
+	return true;
+
+page_busy:
+	/* we might want to wait here, but that could deadlock the allocator as
+	 * the work threads writing to the cache may all end up sleeping
+	 * on memory allocation */
+	fscache_stat(&fscache_n_store_vmscan_busy);
+	return false;
+}
+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;
+
+	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);
+		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);
+		}
+		spin_unlock(&cookie->stores_lock);
+		wake_up_bit(&cookie->flags, 0);
+	}
+	spin_unlock(&object->lock);
+	if (xpage)
+		page_cache_release(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);
+	}
+
+	_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;
+
+	_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(op, fscache_attr_changed_op, NULL);
+	op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE);
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto nobufs;
+	spin_unlock(&cookie->lock);
+	fscache_stat(&fscache_n_attr_changed_ok);
+	fscache_put_operation(op);
+	_leave(" = 0");
+	return 0;
+
+nobufs:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	fscache_stat(&fscache_n_attr_changed_nobufs);
+	_leave(" = %d", -ENOBUFS);
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_attr_changed);
+
+/*
+ * 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);
+
+	fscache_hist(fscache_retrieval_histogram, op->start_time);
+	if (op->context)
+		fscache_put_context(op->op.object->cookie, op->context);
+
+	_leave("");
+}
+
+/*
+ * allocate a retrieval op
+ */
+static struct fscache_retrieval *fscache_alloc_retrieval(
+	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(&op->op, NULL, fscache_release_retrieval_op);
+	op->op.flags	= FSCACHE_OP_MYTHREAD | (1 << FSCACHE_OP_WAITING);
+	op->mapping	= mapping;
+	op->end_io_func	= end_io_func;
+	op->context	= context;
+	op->start_time	= jiffies;
+	INIT_LIST_HEAD(&op->to_do);
+	return op;
+}
+
+/*
+ * wait for a deferred lookup to complete
+ */
+static 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,
+			fscache_wait_bit_interruptible,
+			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)
+ */
+static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
+						 struct fscache_retrieval *op,
+						 atomic_t *stat_op_waits,
+						 atomic_t *stat_object_dead)
+{
+	int ret;
+
+	if (!test_bit(FSCACHE_OP_WAITING, &op->op.flags))
+		goto check_if_dead;
+
+	_debug(">>> WT");
+	fscache_stat(stat_op_waits);
+	if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			fscache_wait_bit_interruptible,
+			TASK_INTERRUPTIBLE) < 0) {
+		ret = fscache_cancel_op(&op->op);
+		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->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	}
+	_debug("<<< GO");
+
+check_if_dead:
+	if (unlikely(fscache_object_is_dead(object))) {
+		fscache_stat(stat_object_dead);
+		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;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	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(page->mapping, end_io_func, context);
+	if (!op) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP);
+
+	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;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure */
+	fscache_get_context(object->cookie, op->context);
+
+	/* 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_retrieval_activation(
+		object, 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:
+	spin_unlock(&cookie->lock);
+	kfree(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;
+	int ret;
+
+	_enter("%p,,%d,,,", cookie, *nr_pages);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	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(mapping, end_io_func, context);
+	if (!op)
+		return -ENOMEM;
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	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;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure */
+	fscache_get_context(object->cookie, op->context);
+
+	/* 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_retrieval_activation(
+		object, 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:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+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;
+	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 (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
+	if (!op)
+		return -ENOMEM;
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_alloc_ops);
+
+	ret = fscache_wait_for_retrieval_activation(
+		object, 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:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_allocs_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_alloc_page);
+
+/*
+ * 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));
+
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+
+	if (!fscache_object_is_active(object) || !cookie) {
+		spin_unlock(&object->lock);
+		_leave("");
+		return;
+	}
+
+	spin_lock(&cookie->stores_lock);
+
+	fscache_stat(&fscache_n_store_calls);
+
+	/* find a page to store */
+	page = NULL;
+	n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, 1,
+				       FSCACHE_COOKIE_PENDING_TAG);
+	if (n != 1)
+		goto superseded;
+	page = results[0];
+	_debug("gang %d [%lx]", n, page->index);
+	if (page->index > op->store_limit) {
+		fscache_stat(&fscache_n_store_pages_over_limit);
+		goto superseded;
+	}
+
+	radix_tree_tag_set(&cookie->stores, page->index,
+			   FSCACHE_COOKIE_STORING_TAG);
+	radix_tree_tag_clear(&cookie->stores, page->index,
+			     FSCACHE_COOKIE_PENDING_TAG);
+
+	spin_unlock(&cookie->stores_lock);
+	spin_unlock(&object->lock);
+
+	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);
+	fscache_end_page_write(object, page);
+	if (ret < 0) {
+		fscache_abort_object(object);
+	} else {
+		fscache_enqueue_operation(&op->op);
+	}
+
+	_leave("");
+	return;
+
+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);
+	_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 (set FSCACHE_COOKIE_PENDING_FILL and queue deferred
+ *	    fill op)
+ *
+ *	(b) writes deferred till post-creation (mark page for writing and
+ *	    return immediately)
+ *
+ *  (2) negative lookup, object created, initial fill being made from netfs
+ *      (FSCACHE_COOKIE_INITIAL_FILL is set)
+ *
+ *	(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,
+			 gfp_t gfp)
+{
+	struct fscache_storage *op;
+	struct fscache_object *object;
+	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);
+
+	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (!op)
+		goto nomem;
+
+	fscache_operation_init(&op->op, fscache_write_op,
+			       fscache_release_write_op);
+	op->op.flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_WAITING);
+
+	ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
+	if (ret < 0)
+		goto nomem_free;
+
+	ret = -ENOBUFS;
+	spin_lock(&cookie->lock);
+
+	if (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;
+
+	/* add the page to the pending-storage radix tree on the backing
+	 * object */
+	spin_lock(&object->lock);
+	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;
+	}
+
+	radix_tree_tag_set(&cookie->stores, page->index,
+			   FSCACHE_COOKIE_PENDING_TAG);
+	page_cache_get(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;
+
+	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();
+	kfree(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);
+	spin_unlock(&cookie->stores_lock);
+	page_cache_release(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();
+	kfree(op);
+	fscache_stat(&fscache_n_stores_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+
+nomem_free:
+	kfree(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;
+
+	/* 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_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)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+	unsigned long loop;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_add(pagevec->nr, &fscache_n_marks);
+#endif
+
+	for (loop = 0; loop < pagevec->nr; loop++) {
+		struct page *page = pagevec->pages[loop];
+
+		_debug("- mark %p{%lx}", page, page->index);
+		if (TestSetPageFsCache(page)) {
+			static bool once_only;
+			if (!once_only) {
+				once_only = true;
+				printk(KERN_WARNING "FS-Cache:"
+				       " Cookie type %s marked page %lx"
+				       " multiple times\n",
+				       cookie->def->name, page->index);
+			}
+		}
+	}
+
+	if (cookie->def->mark_pages_cached)
+		cookie->def->mark_pages_cached(cookie->netfs_data,
+					       op->mapping, pagevec);
+	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, 0);
+	next = 0;
+	do {
+		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+			break;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			next = page->index;
+			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);

kernel/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("fs/fscache/stats", S_IFREG | 0444, NULL,
+			 &fscache_stats_fops))
+		goto error_stats;
+#endif
+
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	if (!proc_create("fs/fscache/histogram", S_IFREG | 0444, NULL,
+			 &fscache_histogram_fops))
+		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);
+}

kernel/fs/fscache/stats.c

@@ -0,0 +1,280 @@
+/* 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_requeue;
+atomic_t fscache_n_op_deferred_release;
+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_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_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_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;
+
+/*
+ * display the general statistics
+ */
+static 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, "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\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));
+
+	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    : dfr=%u rel=%u gc=%u\n",
+		   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: upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+		   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));
+	return 0;
+}
+
+/*
+ * open "/proc/fs/fscache/stats" allowing provision of a statistical summary
+ */
+static int fscache_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, fscache_stats_show, NULL);
+}
+
+const struct file_operations fscache_stats_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};