16 files changed, 4866 insertions, 0 deletions

diff --git a/Documentation/filesystems/caching/cachefiles.txt b/Documentation/filesystems/caching/cachefiles.txt
new file mode 100644
index 000000000000..c78a49b7bba6
--- /dev/null
+++ b/Documentation/filesystems/caching/cachefiles.txt
@@ -0,0 +1,501 @@
+	       ===============================================
+	       CacheFiles: CACHE ON ALREADY MOUNTED FILESYSTEM
+	       ===============================================
+
+Contents:
+
+ (*) Overview.
+
+ (*) Requirements.
+
+ (*) Configuration.
+
+ (*) Starting the cache.
+
+ (*) Things to avoid.
+
+ (*) Cache culling.
+
+ (*) Cache structure.
+
+ (*) Security model and SELinux.
+
+ (*) A note on security.
+
+ (*) Statistical information.
+
+ (*) Debugging.
+
+
+========
+OVERVIEW
+========
+
+CacheFiles is a caching backend that's meant to use as a cache a directory on
+an already mounted filesystem of a local type (such as Ext3).
+
+CacheFiles uses a userspace daemon to do some of the cache management - such as
+reaping stale nodes and culling.  This is called cachefilesd and lives in
+/sbin.
+
+The filesystem and data integrity of the cache are only as good as those of the
+filesystem providing the backing services.  Note that CacheFiles does not
+attempt to journal anything since the journalling interfaces of the various
+filesystems are very specific in nature.
+
+CacheFiles creates a misc character device - "/dev/cachefiles" - that is used
+to communication with the daemon.  Only one thing may have this open at once,
+and whilst it is open, a cache is at least partially in existence.  The daemon
+opens this and sends commands down it to control the cache.
+
+CacheFiles is currently limited to a single cache.
+
+CacheFiles attempts to maintain at least a certain percentage of free space on
+the filesystem, shrinking the cache by culling the objects it contains to make
+space if necessary - see the "Cache Culling" section.  This means it can be
+placed on the same medium as a live set of data, and will expand to make use of
+spare space and automatically contract when the set of data requires more
+space.
+
+
+============
+REQUIREMENTS
+============
+
+The use of CacheFiles and its daemon requires the following features to be
+available in the system and in the cache filesystem:
+
+	- dnotify.
+
+	- extended attributes (xattrs).
+
+	- openat() and friends.
+
+	- bmap() support on files in the filesystem (FIBMAP ioctl).
+
+	- The use of bmap() to detect a partial page at the end of the file.
+
+It is strongly recommended that the "dir_index" option is enabled on Ext3
+filesystems being used as a cache.
+
+
+=============
+CONFIGURATION
+=============
+
+The cache is configured by a script in /etc/cachefilesd.conf.  These commands
+set up cache ready for use.  The following script commands are available:
+
+ (*) brun <N>%
+ (*) bcull <N>%
+ (*) bstop <N>%
+ (*) frun <N>%
+ (*) fcull <N>%
+ (*) fstop <N>%
+
+	Configure the culling limits.  Optional.  See the section on culling
+	The defaults are 7% (run), 5% (cull) and 1% (stop) respectively.
+
+	The commands beginning with a 'b' are file space (block) limits, those
+	beginning with an 'f' are file count limits.
+
+ (*) dir <path>
+
+	Specify the directory containing the root of the cache.  Mandatory.
+
+ (*) tag <name>
+
+	Specify a tag to FS-Cache to use in distinguishing multiple caches.
+	Optional.  The default is "CacheFiles".
+
+ (*) debug <mask>
+
+	Specify a numeric bitmask to control debugging in the kernel module.
+	Optional.  The default is zero (all off).  The following values can be
+	OR'd into the mask to collect various information:
+
+		1	Turn on trace of function entry (_enter() macros)
+		2	Turn on trace of function exit (_leave() macros)
+		4	Turn on trace of internal debug points (_debug())
+
+	This mask can also be set through sysfs, eg:
+
+		echo 5 >/sys/modules/cachefiles/parameters/debug
+
+
+==================
+STARTING THE CACHE
+==================
+
+The cache is started by running the daemon.  The daemon opens the cache device,
+configures the cache and tells it to begin caching.  At that point the cache
+binds to fscache and the cache becomes live.
+
+The daemon is run as follows:
+
+	/sbin/cachefilesd [-d]* [-s] [-n] [-f <configfile>]
+
+The flags are:
+
+ (*) -d
+
+	Increase the debugging level.  This can be specified multiple times and
+	is cumulative with itself.
+
+ (*) -s
+
+	Send messages to stderr instead of syslog.
+
+ (*) -n
+
+	Don't daemonise and go into background.
+
+ (*) -f <configfile>
+
+	Use an alternative configuration file rather than the default one.
+
+
+===============
+THINGS TO AVOID
+===============
+
+Do not mount other things within the cache as this will cause problems.  The
+kernel module contains its own very cut-down path walking facility that ignores
+mountpoints, but the daemon can't avoid them.
+
+Do not create, rename or unlink files and directories in the cache whilst the
+cache is active, as this may cause the state to become uncertain.
+
+Renaming files in the cache might make objects appear to be other objects (the
+filename is part of the lookup key).
+
+Do not change or remove the extended attributes attached to cache files by the
+cache as this will cause the cache state management to get confused.
+
+Do not create files or directories in the cache, lest the cache get confused or
+serve incorrect data.
+
+Do not chmod files in the cache.  The module creates things with minimal
+permissions to prevent random users being able to access them directly.
+
+
+=============
+CACHE CULLING
+=============
+
+The cache may need culling occasionally to make space.  This involves
+discarding objects from the cache that have been used less recently than
+anything else.  Culling is based on the access time of data objects.  Empty
+directories are culled if not in use.
+
+Cache culling is done on the basis of the percentage of blocks and the
+percentage of files available in the underlying filesystem.  There are six
+"limits":
+
+ (*) brun
+ (*) frun
+
+     If the amount of free space and the number of available files in the cache
+     rises above both these limits, then culling is turned off.
+
+ (*) bcull
+ (*) fcull
+
+     If the amount of available space or the number of available files in the
+     cache falls below either of these limits, then culling is started.
+
+ (*) bstop
+ (*) fstop
+
+     If the amount of available space or the number of available files in the
+     cache falls below either of these limits, then no further allocation of
+     disk space or files is permitted until culling has raised things above
+     these limits again.
+
+These must be configured thusly:
+
+	0 <= bstop < bcull < brun < 100
+	0 <= fstop < fcull < frun < 100
+
+Note that these are percentages of available space and available files, and do
+_not_ appear as 100 minus the percentage displayed by the "df" program.
+
+The userspace daemon scans the cache to build up a table of cullable objects.
+These are then culled in least recently used order.  A new scan of the cache is
+started as soon as space is made in the table.  Objects will be skipped if
+their atimes have changed or if the kernel module says it is still using them.
+
+
+===============
+CACHE STRUCTURE
+===============
+
+The CacheFiles module will create two directories in the directory it was
+given:
+
+ (*) cache/
+
+ (*) graveyard/
+
+The active cache objects all reside in the first directory.  The CacheFiles
+kernel module moves any retired or culled objects that it can't simply unlink
+to the graveyard from which the daemon will actually delete them.
+
+The daemon uses dnotify to monitor the graveyard directory, and will delete
+anything that appears therein.
+
+
+The module represents index objects as directories with the filename "I..." or
+"J...".  Note that the "cache/" directory is itself a special index.
+
+Data objects are represented as files if they have no children, or directories
+if they do.  Their filenames all begin "D..." or "E...".  If represented as a
+directory, data objects will have a file in the directory called "data" that
+actually holds the data.
+
+Special objects are similar to data objects, except their filenames begin
+"S..." or "T...".
+
+
+If an object has children, then it will be represented as a directory.
+Immediately in the representative directory are a collection of directories
+named for hash values of the child object keys with an '@' prepended.  Into
+this directory, if possible, will be placed the representations of the child
+objects:
+
+	INDEX     INDEX      INDEX                             DATA FILES
+	========= ========== ================================= ================
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...DB1ry
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...N22ry
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...FP1ry
+
+
+If the key is so long that it exceeds NAME_MAX with the decorations added on to
+it, then it will be cut into pieces, the first few of which will be used to
+make a nest of directories, and the last one of which will be the objects
+inside the last directory.  The names of the intermediate directories will have
+'+' prepended:
+
+	J1223/@23/+xy...z/+kl...m/Epqr
+
+
+Note that keys are raw data, and not only may they exceed NAME_MAX in size,
+they may also contain things like '/' and NUL characters, and so they may not
+be suitable for turning directly into a filename.
+
+To handle this, CacheFiles will use a suitably printable filename directly and
+"base-64" encode ones that aren't directly suitable.  The two versions of
+object filenames indicate the encoding:
+
+	OBJECT TYPE	PRINTABLE	ENCODED
+	===============	===============	===============
+	Index		"I..."		"J..."
+	Data		"D..."		"E..."
+	Special		"S..."		"T..."
+
+Intermediate directories are always "@" or "+" as appropriate.
+
+
+Each object in the cache has an extended attribute label that holds the object
+type ID (required to distinguish special objects) and the auxiliary data from
+the netfs.  The latter is used to detect stale objects in the cache and update
+or retire them.
+
+
+Note that CacheFiles will erase from the cache any file it doesn't recognise or
+any file of an incorrect type (such as a FIFO file or a device file).
+
+
+==========================
+SECURITY MODEL AND SELINUX
+==========================
+
+CacheFiles is implemented to deal properly with the LSM security features of
+the Linux kernel and the SELinux facility.
+
+One of the problems that CacheFiles faces is that it is generally acting on
+behalf of a process, and running in that process's context, and that includes a
+security context that is not appropriate for accessing the cache - either
+because the files in the cache are inaccessible to that process, or because if
+the process creates a file in the cache, that file may be inaccessible to other
+processes.
+
+The way CacheFiles works is to temporarily change the security context (fsuid,
+fsgid and actor security label) that the process acts as - without changing the
+security context of the process when it the target of an operation performed by
+some other process (so signalling and suchlike still work correctly).
+
+
+When the CacheFiles module is asked to bind to its cache, it:
+
+ (1) Finds the security label attached to the root cache directory and uses
+     that as the security label with which it will create files.  By default,
+     this is:
+
+	cachefiles_var_t
+
+ (2) Finds the security label of the process which issued the bind request
+     (presumed to be the cachefilesd daemon), which by default will be:
+
+	cachefilesd_t
+
+     and asks LSM to supply a security ID as which it should act given the
+     daemon's label.  By default, this will be:
+
+	cachefiles_kernel_t
+
+     SELinux transitions the daemon's security ID to the module's security ID
+     based on a rule of this form in the policy.
+
+	type_transition <daemon's-ID> kernel_t : process <module's-ID>;
+
+     For instance:
+
+	type_transition cachefilesd_t kernel_t : process cachefiles_kernel_t;
+
+
+The module's security ID gives it permission to create, move and remove files
+and directories in the cache, to find and access directories and files in the
+cache, to set and access extended attributes on cache objects, and to read and
+write files in the cache.
+
+The daemon's security ID gives it only a very restricted set of permissions: it
+may scan directories, stat files and erase files and directories.  It may
+not read or write files in the cache, and so it is precluded from accessing the
+data cached therein; nor is it permitted to create new files in the cache.
+
+
+There are policy source files available in:
+
+	http://people.redhat.com/~dhowells/fscache/cachefilesd-0.8.tar.bz2
+
+and later versions.  In that tarball, see the files:
+
+	cachefilesd.te
+	cachefilesd.fc
+	cachefilesd.if
+
+They are built and installed directly by the RPM.
+
+If a non-RPM based system is being used, then copy the above files to their own
+directory and run:
+
+	make -f /usr/share/selinux/devel/Makefile
+	semodule -i cachefilesd.pp
+
+You will need checkpolicy and selinux-policy-devel installed prior to the
+build.
+
+
+By default, the cache is located in /var/fscache, but if it is desirable that
+it should be elsewhere, than either the above policy files must be altered, or
+an auxiliary policy must be installed to label the alternate location of the
+cache.
+
+For instructions on how to add an auxiliary policy to enable the cache to be
+located elsewhere when SELinux is in enforcing mode, please see:
+
+	/usr/share/doc/cachefilesd-*/move-cache.txt
+
+When the cachefilesd rpm is installed; alternatively, the document can be found
+in the sources.
+
+
+==================
+A NOTE ON SECURITY
+==================
+
+CacheFiles makes use of the split security in the task_struct.  It allocates
+its own task_security structure, and redirects current->act_as to point to it
+when it acts on behalf of another process, in that process's context.
+
+The reason it does this is that it calls vfs_mkdir() and suchlike rather than
+bypassing security and calling inode ops directly.  Therefore the VFS and LSM
+may deny the CacheFiles access to the cache data because under some
+circumstances the caching code is running in the security context of whatever
+process issued the original syscall on the netfs.
+
+Furthermore, should CacheFiles create a file or directory, the security
+parameters with that object is created (UID, GID, security label) would be
+derived from that process that issued the system call, thus potentially
+preventing other processes from accessing the cache - including CacheFiles's
+cache management daemon (cachefilesd).
+
+What is required is to temporarily override the security of the process that
+issued the system call.  We can't, however, just do an in-place change of the
+security data as that affects the process as an object, not just as a subject.
+This means it may lose signals or ptrace events for example, and affects what
+the process looks like in /proc.
+
+So CacheFiles makes use of a logical split in the security between the
+objective security (task->sec) and the subjective security (task->act_as).  The
+objective security holds the intrinsic security properties of a process and is
+never overridden.  This is what appears in /proc, and is what is used when a
+process is the target of an operation by some other process (SIGKILL for
+example).
+
+The subjective security holds the active security properties of a process, and
+may be overridden.  This is not seen externally, and is used whan a process
+acts upon another object, for example SIGKILLing another process or opening a
+file.
+
+LSM hooks exist that allow SELinux (or Smack or whatever) to reject a request
+for CacheFiles to run in a context of a specific security label, or to create
+files and directories with another security label.
+
+
+=======================
+STATISTICAL INFORMATION
+=======================
+
+If FS-Cache is compiled with the following option enabled:
+
+	CONFIG_CACHEFILES_HISTOGRAM=y
+
+then it will gather certain statistics and display them through a proc file.
+
+ (*) /proc/fs/cachefiles/histogram
+
+	cat /proc/fs/cachefiles/histogram
+	JIFS  SECS  LOOKUPS   MKDIRS    CREATES
+	===== ===== ========= ========= =========
+
+     This shows the breakdown of the number of times each amount of time
+     between 0 jiffies and HZ-1 jiffies a variety of tasks took to run.  The
+     columns are as follows:
+
+	COLUMN		TIME MEASUREMENT
+	=======		=======================================================
+	LOOKUPS		Length of time to perform a lookup on the backing fs
+	MKDIRS		Length of time to perform a mkdir on the backing fs
+	CREATES		Length of time to perform a create on the backing fs
+
+     Each row shows the number of events that took a particular range of times.
+     Each step is 1 jiffy in size.  The JIFS column indicates the particular
+     jiffy range covered, and the SECS field the equivalent number of seconds.
+
+
+=========
+DEBUGGING
+=========
+
+If CONFIG_CACHEFILES_DEBUG is enabled, the CacheFiles facility can have runtime
+debugging enabled by adjusting the value in:
+
+	/sys/module/cachefiles/parameters/debug
+
+This is a bitmask of debugging streams to enable:
+
+	BIT	VALUE	STREAM				POINT
+	=======	=======	===============================	=======================
+	0	1	General				Function entry trace
+	1	2					Function exit trace
+	2	4					General
+
+The appropriate set of values should be OR'd together and the result written to
+the control file.  For example:
+
+	echo $((1|4|8)) >/sys/module/cachefiles/parameters/debug
+
+will turn on all function entry debugging.
diff --git a/fs/Kconfig b/fs/Kconfig
index 3942df6ad04f..c0022b1d5877 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -69,6 +69,7 @@ config GENERIC_ACL
 menu "Caches"
 
 source "fs/fscache/Kconfig"
+source "fs/cachefiles/Kconfig"
 
 endmenu
 
diff --git a/fs/Makefile b/fs/Makefile
index ff5a10d898c6..055d5237b109 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -117,6 +117,7 @@ obj-$(CONFIG_AFS_FS)		+= afs/
 obj-$(CONFIG_BEFS_FS)		+= befs/
 obj-$(CONFIG_HOSTFS)		+= hostfs/
 obj-$(CONFIG_HPPFS)		+= hppfs/
+obj-$(CONFIG_CACHEFILES)	+= cachefiles/
 obj-$(CONFIG_DEBUG_FS)		+= debugfs/
 obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_BTRFS_FS)		+= btrfs/
diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig
new file mode 100644
index 000000000000..80e9c6167f0b
--- /dev/null
+++ b/fs/cachefiles/Kconfig
@@ -0,0 +1,39 @@
+
+config CACHEFILES
+	tristate "Filesystem caching on files"
+	depends on FSCACHE && BLOCK
+	help
+	  This permits use of a mounted filesystem as a cache for other
+	  filesystems - primarily networking filesystems - thus allowing fast
+	  local disk to enhance the speed of slower devices.
+
+	  See Documentation/filesystems/caching/cachefiles.txt for more
+	  information.
+
+config CACHEFILES_DEBUG
+	bool "Debug CacheFiles"
+	depends on CACHEFILES
+	help
+	  This permits debugging to be dynamically enabled in the filesystem
+	  caching on files module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/cachefiles/parameter/debug or
+	  by including a debugging specifier in /etc/cachefilesd.conf.
+
+config CACHEFILES_HISTOGRAM
+	bool "Gather latency information on CacheFiles"
+	depends on CACHEFILES && PROC_FS
+	help
+
+	  This option causes latency information to be gathered on CacheFiles
+	  operation and exported through file:
+
+		/proc/fs/cachefiles/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/cachefiles.txt for more
+	  information.
diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile
new file mode 100644
index 000000000000..32cbab0ffce3
--- /dev/null
+++ b/fs/cachefiles/Makefile
@@ -0,0 +1,18 @@
+#
+# Makefile for caching in a mounted filesystem
+#
+
+cachefiles-y := \
+	bind.o \
+	daemon.o \
+	interface.o \
+	key.o \
+	main.o \
+	namei.o \
+	rdwr.o \
+	security.o \
+	xattr.o
+
+cachefiles-$(CONFIG_CACHEFILES_HISTOGRAM) += proc.o
+
+obj-$(CONFIG_CACHEFILES) := cachefiles.o
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
new file mode 100644
index 000000000000..3797e0077b35
--- /dev/null
+++ b/fs/cachefiles/bind.c
@@ -0,0 +1,286 @@
+/* Bind and unbind a cache from the filesystem backing it
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/ctype.h>
+#include "internal.h"
+
+static int cachefiles_daemon_add_cache(struct cachefiles_cache *caches);
+
+/*
+ * bind a directory as a cache
+ */
+int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
+{
+	_enter("{%u,%u,%u,%u,%u,%u},%s",
+	       cache->frun_percent,
+	       cache->fcull_percent,
+	       cache->fstop_percent,
+	       cache->brun_percent,
+	       cache->bcull_percent,
+	       cache->bstop_percent,
+	       args);
+
+	/* start by checking things over */
+	ASSERT(cache->fstop_percent >= 0 &&
+	       cache->fstop_percent < cache->fcull_percent &&
+	       cache->fcull_percent < cache->frun_percent &&
+	       cache->frun_percent  < 100);
+
+	ASSERT(cache->bstop_percent >= 0 &&
+	       cache->bstop_percent < cache->bcull_percent &&
+	       cache->bcull_percent < cache->brun_percent &&
+	       cache->brun_percent  < 100);
+
+	if (*args) {
+		kerror("'bind' command doesn't take an argument");
+		return -EINVAL;
+	}
+
+	if (!cache->rootdirname) {
+		kerror("No cache directory specified");
+		return -EINVAL;
+	}
+
+	/* don't permit already bound caches to be re-bound */
+	if (test_bit(CACHEFILES_READY, &cache->flags)) {
+		kerror("Cache already bound");
+		return -EBUSY;
+	}
+
+	/* make sure we have copies of the tag and dirname strings */
+	if (!cache->tag) {
+		/* the tag string is released by the fops->release()
+		 * function, so we don't release it on error here */
+		cache->tag = kstrdup("CacheFiles", GFP_KERNEL);
+		if (!cache->tag)
+			return -ENOMEM;
+	}
+
+	/* add the cache */
+	return cachefiles_daemon_add_cache(cache);
+}
+
+/*
+ * add a cache
+ */
+static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
+{
+	struct cachefiles_object *fsdef;
+	struct nameidata nd;
+	struct kstatfs stats;
+	struct dentry *graveyard, *cachedir, *root;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("");
+
+	/* we want to work under the module's security ID */
+	ret = cachefiles_get_security_ID(cache);
+	if (ret < 0)
+		return ret;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+
+	/* allocate the root index object */
+	ret = -ENOMEM;
+
+	fsdef = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL);
+	if (!fsdef)
+		goto error_root_object;
+
+	ASSERTCMP(fsdef->backer, ==, NULL);
+
+	atomic_set(&fsdef->usage, 1);
+	fsdef->type = FSCACHE_COOKIE_TYPE_INDEX;
+
+	_debug("- fsdef %p", fsdef);
+
+	/* look up the directory at the root of the cache */
+	memset(&nd, 0, sizeof(nd));
+
+	ret = path_lookup(cache->rootdirname, LOOKUP_DIRECTORY, &nd);
+	if (ret < 0)
+		goto error_open_root;
+
+	cache->mnt = mntget(nd.path.mnt);
+	root = dget(nd.path.dentry);
+	path_put(&nd.path);
+
+	/* check parameters */
+	ret = -EOPNOTSUPP;
+	if (!root->d_inode ||
+	    !root->d_inode->i_op ||
+	    !root->d_inode->i_op->lookup ||
+	    !root->d_inode->i_op->mkdir ||
+	    !root->d_inode->i_op->setxattr ||
+	    !root->d_inode->i_op->getxattr ||
+	    !root->d_sb ||
+	    !root->d_sb->s_op ||
+	    !root->d_sb->s_op->statfs ||
+	    !root->d_sb->s_op->sync_fs)
+		goto error_unsupported;
+
+	ret = -EROFS;
+	if (root->d_sb->s_flags & MS_RDONLY)
+		goto error_unsupported;
+
+	/* determine the security of the on-disk cache as this governs
+	 * security ID of files we create */
+	ret = cachefiles_determine_cache_security(cache, root, &saved_cred);
+	if (ret < 0)
+		goto error_unsupported;
+
+	/* get the cache size and blocksize */
+	ret = vfs_statfs(root, &stats);
+	if (ret < 0)
+		goto error_unsupported;
+
+	ret = -ERANGE;
+	if (stats.f_bsize <= 0)
+		goto error_unsupported;
+
+	ret = -EOPNOTSUPP;
+	if (stats.f_bsize > PAGE_SIZE)
+		goto error_unsupported;
+
+	cache->bsize = stats.f_bsize;
+	cache->bshift = 0;
+	if (stats.f_bsize < PAGE_SIZE)
+		cache->bshift = PAGE_SHIFT - ilog2(stats.f_bsize);
+
+	_debug("blksize %u (shift %u)",
+	       cache->bsize, cache->bshift);
+
+	_debug("size %llu, avail %llu",
+	       (unsigned long long) stats.f_blocks,
+	       (unsigned long long) stats.f_bavail);
+
+	/* set up caching limits */
+	do_div(stats.f_files, 100);
+	cache->fstop = stats.f_files * cache->fstop_percent;
+	cache->fcull = stats.f_files * cache->fcull_percent;
+	cache->frun  = stats.f_files * cache->frun_percent;
+
+	_debug("limits {%llu,%llu,%llu} files",
+	       (unsigned long long) cache->frun,
+	       (unsigned long long) cache->fcull,
+	       (unsigned long long) cache->fstop);
+
+	stats.f_blocks >>= cache->bshift;
+	do_div(stats.f_blocks, 100);
+	cache->bstop = stats.f_blocks * cache->bstop_percent;
+	cache->bcull = stats.f_blocks * cache->bcull_percent;
+	cache->brun  = stats.f_blocks * cache->brun_percent;
+
+	_debug("limits {%llu,%llu,%llu} blocks",
+	       (unsigned long long) cache->brun,
+	       (unsigned long long) cache->bcull,
+	       (unsigned long long) cache->bstop);
+
+	/* get the cache directory and check its type */
+	cachedir = cachefiles_get_directory(cache, root, "cache");
+	if (IS_ERR(cachedir)) {
+		ret = PTR_ERR(cachedir);
+		goto error_unsupported;
+	}
+
+	fsdef->dentry = cachedir;
+	fsdef->fscache.cookie = NULL;
+
+	ret = cachefiles_check_object_type(fsdef);
+	if (ret < 0)
+		goto error_unsupported;
+
+	/* get the graveyard directory */
+	graveyard = cachefiles_get_directory(cache, root, "graveyard");
+	if (IS_ERR(graveyard)) {
+		ret = PTR_ERR(graveyard);
+		goto error_unsupported;
+	}
+
+	cache->graveyard = graveyard;
+
+	/* publish the cache */
+	fscache_init_cache(&cache->cache,
+			   &cachefiles_cache_ops,
+			   "%s",
+			   fsdef->dentry->d_sb->s_id);
+
+	fscache_object_init(&fsdef->fscache, NULL, &cache->cache);
+
+	ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag);
+	if (ret < 0)
+		goto error_add_cache;
+
+	/* done */
+	set_bit(CACHEFILES_READY, &cache->flags);
+	dput(root);
+
+	printk(KERN_INFO "CacheFiles:"
+	       " File cache on %s registered\n",
+	       cache->cache.identifier);
+
+	/* check how much space the cache has */
+	cachefiles_has_space(cache, 0, 0);
+	cachefiles_end_secure(cache, saved_cred);
+	return 0;
+
+error_add_cache:
+	dput(cache->graveyard);
+	cache->graveyard = NULL;
+error_unsupported:
+	mntput(cache->mnt);
+	cache->mnt = NULL;
+	dput(fsdef->dentry);
+	fsdef->dentry = NULL;
+	dput(root);
+error_open_root:
+	kmem_cache_free(cachefiles_object_jar, fsdef);
+error_root_object:
+	cachefiles_end_secure(cache, saved_cred);
+	kerror("Failed to register: %d", ret);
+	return ret;
+}
+
+/*
+ * unbind a cache on fd release
+ */
+void cachefiles_daemon_unbind(struct cachefiles_cache *cache)
+{
+	_enter("");
+
+	if (test_bit(CACHEFILES_READY, &cache->flags)) {
+		printk(KERN_INFO "CacheFiles:"
+		       " File cache on %s unregistering\n",
+		       cache->cache.identifier);
+
+		fscache_withdraw_cache(&cache->cache);
+	}
+
+	dput(cache->graveyard);
+	mntput(cache->mnt);
+
+	kfree(cache->rootdirname);
+	kfree(cache->secctx);
+	kfree(cache->tag);
+
+	_leave("");
+}
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
new file mode 100644
index 000000000000..4618516dd994
--- /dev/null
+++ b/fs/cachefiles/daemon.c
@@ -0,0 +1,755 @@
+/* Daemon 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/ctype.h>
+#include <linux/fs_struct.h>
+#include "internal.h"
+
+static int cachefiles_daemon_open(struct inode *, struct file *);
+static int cachefiles_daemon_release(struct inode *, struct file *);
+static ssize_t cachefiles_daemon_read(struct file *, char __user *, size_t,
+				      loff_t *);
+static ssize_t cachefiles_daemon_write(struct file *, const char __user *,
+				       size_t, loff_t *);
+static unsigned int cachefiles_daemon_poll(struct file *,
+					   struct poll_table_struct *);
+static int cachefiles_daemon_frun(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_fcull(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_fstop(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_brun(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_bcull(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_bstop(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_cull(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_debug(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_dir(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_inuse(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_secctx(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_tag(struct cachefiles_cache *, char *);
+
+static unsigned long cachefiles_open;
+
+const struct file_operations cachefiles_daemon_fops = {
+	.owner		= THIS_MODULE,
+	.open		= cachefiles_daemon_open,
+	.release	= cachefiles_daemon_release,
+	.read		= cachefiles_daemon_read,
+	.write		= cachefiles_daemon_write,
+	.poll		= cachefiles_daemon_poll,
+};
+
+struct cachefiles_daemon_cmd {
+	char name[8];
+	int (*handler)(struct cachefiles_cache *cache, char *args);
+};
+
+static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = {
+	{ "bind",	cachefiles_daemon_bind		},
+	{ "brun",	cachefiles_daemon_brun		},
+	{ "bcull",	cachefiles_daemon_bcull		},
+	{ "bstop",	cachefiles_daemon_bstop		},
+	{ "cull",	cachefiles_daemon_cull		},
+	{ "debug",	cachefiles_daemon_debug		},
+	{ "dir",	cachefiles_daemon_dir		},
+	{ "frun",	cachefiles_daemon_frun		},
+	{ "fcull",	cachefiles_daemon_fcull		},
+	{ "fstop",	cachefiles_daemon_fstop		},
+	{ "inuse",	cachefiles_daemon_inuse		},
+	{ "secctx",	cachefiles_daemon_secctx	},
+	{ "tag",	cachefiles_daemon_tag		},
+	{ "",		NULL				}
+};
+
+
+/*
+ * do various checks
+ */
+static int cachefiles_daemon_open(struct inode *inode, struct file *file)
+{
+	struct cachefiles_cache *cache;
+
+	_enter("");
+
+	/* only the superuser may do this */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* the cachefiles device may only be open once at a time */
+	if (xchg(&cachefiles_open, 1) == 1)
+		return -EBUSY;
+
+	/* allocate a cache record */
+	cache = kzalloc(sizeof(struct cachefiles_cache), GFP_KERNEL);
+	if (!cache) {
+		cachefiles_open = 0;
+		return -ENOMEM;
+	}
+
+	mutex_init(&cache->daemon_mutex);
+	cache->active_nodes = RB_ROOT;
+	rwlock_init(&cache->active_lock);
+	init_waitqueue_head(&cache->daemon_pollwq);
+
+	/* set default caching limits
+	 * - limit at 1% free space and/or free files
+	 * - cull below 5% free space and/or free files
+	 * - cease culling above 7% free space and/or free files
+	 */
+	cache->frun_percent = 7;
+	cache->fcull_percent = 5;
+	cache->fstop_percent = 1;
+	cache->brun_percent = 7;
+	cache->bcull_percent = 5;
+	cache->bstop_percent = 1;
+
+	file->private_data = cache;
+	cache->cachefilesd = file;
+	return 0;
+}
+
+/*
+ * release a cache
+ */
+static int cachefiles_daemon_release(struct inode *inode, struct file *file)
+{
+	struct cachefiles_cache *cache = file->private_data;
+
+	_enter("");
+
+	ASSERT(cache);
+
+	set_bit(CACHEFILES_DEAD, &cache->flags);
+
+	cachefiles_daemon_unbind(cache);
+
+	ASSERT(!cache->active_nodes.rb_node);
+
+	/* clean up the control file interface */
+	cache->cachefilesd = NULL;
+	file->private_data = NULL;
+	cachefiles_open = 0;
+
+	kfree(cache);
+
+	_leave("");
+	return 0;
+}
+
+/*
+ * read the cache state
+ */
+static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
+				      size_t buflen, loff_t *pos)
+{
+	struct cachefiles_cache *cache = file->private_data;
+	char buffer[256];
+	int n;
+
+	//_enter(",,%zu,", buflen);
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags))
+		return 0;
+
+	/* check how much space the cache has */
+	cachefiles_has_space(cache, 0, 0);
+
+	/* summarise */
+	clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
+
+	n = snprintf(buffer, sizeof(buffer),
+		     "cull=%c"
+		     " frun=%llx"
+		     " fcull=%llx"
+		     " fstop=%llx"
+		     " brun=%llx"
+		     " bcull=%llx"
+		     " bstop=%llx",
+		     test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0',
+		     (unsigned long long) cache->frun,
+		     (unsigned long long) cache->fcull,
+		     (unsigned long long) cache->fstop,
+		     (unsigned long long) cache->brun,
+		     (unsigned long long) cache->bcull,
+		     (unsigned long long) cache->bstop
+		     );
+
+	if (n > buflen)
+		return -EMSGSIZE;
+
+	if (copy_to_user(_buffer, buffer, n) != 0)
+		return -EFAULT;
+
+	return n;
+}
+
+/*
+ * command the cache
+ */
+static ssize_t cachefiles_daemon_write(struct file *file,
+				       const char __user *_data,
+				       size_t datalen,
+				       loff_t *pos)
+{
+	const struct cachefiles_daemon_cmd *cmd;
+	struct cachefiles_cache *cache = file->private_data;
+	ssize_t ret;
+	char *data, *args, *cp;
+
+	//_enter(",,%zu,", datalen);
+
+	ASSERT(cache);
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags))
+		return -EIO;
+
+	if (datalen < 0 || datalen > PAGE_SIZE - 1)
+		return -EOPNOTSUPP;
+
+	/* drag the command string into the kernel so we can parse it */
+	data = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = -EFAULT;
+	if (copy_from_user(data, _data, datalen) != 0)
+		goto error;
+
+	data[datalen] = '\0';
+
+	ret = -EINVAL;
+	if (memchr(data, '\0', datalen))
+		goto error;
+
+	/* strip any newline */
+	cp = memchr(data, '\n', datalen);
+	if (cp) {
+		if (cp == data)
+			goto error;
+
+		*cp = '\0';
+	}
+
+	/* parse the command */
+	ret = -EOPNOTSUPP;
+
+	for (args = data; *args; args++)
+		if (isspace(*args))
+			break;
+	if (*args) {
+		if (args == data)
+			goto error;
+		*args = '\0';
+		for (args++; isspace(*args); args++)
+			continue;
+	}
+
+	/* run the appropriate command handler */
+	for (cmd = cachefiles_daemon_cmds; cmd->name[0]; cmd++)
+		if (strcmp(cmd->name, data) == 0)
+			goto found_command;
+
+error:
+	kfree(data);
+	//_leave(" = %zd", ret);
+	return ret;
+
+found_command:
+	mutex_lock(&cache->daemon_mutex);
+
+	ret = -EIO;
+	if (!test_bit(CACHEFILES_DEAD, &cache->flags))
+		ret = cmd->handler(cache, args);
+
+	mutex_unlock(&cache->daemon_mutex);
+
+	if (ret == 0)
+		ret = datalen;
+	goto error;
+}
+
+/*
+ * poll for culling state
+ * - use POLLOUT to indicate culling state
+ */
+static unsigned int cachefiles_daemon_poll(struct file *file,
+					   struct poll_table_struct *poll)
+{
+	struct cachefiles_cache *cache = file->private_data;
+	unsigned int mask;
+
+	poll_wait(file, &cache->daemon_pollwq, poll);
+	mask = 0;
+
+	if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
+		mask |= POLLIN;
+
+	if (test_bit(CACHEFILES_CULLING, &cache->flags))
+		mask |= POLLOUT;
+
+	return mask;
+}
+
+/*
+ * give a range error for cache space constraints
+ * - can be tail-called
+ */
+static int cachefiles_daemon_range_error(struct cachefiles_cache *cache,
+					 char *args)
+{
+	kerror("Free space limits must be in range"
+	       " 0%%<=stop<cull<run<100%%");
+
+	return -EINVAL;
+}
+
+/*
+ * set the percentage of files at which to stop culling
+ * - command: "frun <N>%"
+ */
+static int cachefiles_daemon_frun(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long frun;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	frun = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (frun <= cache->fcull_percent || frun >= 100)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->frun_percent = frun;
+	return 0;
+}
+
+/*
+ * set the percentage of files at which to start culling
+ * - command: "fcull <N>%"
+ */
+static int cachefiles_daemon_fcull(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long fcull;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	fcull = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (fcull <= cache->fstop_percent || fcull >= cache->frun_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->fcull_percent = fcull;
+	return 0;
+}
+
+/*
+ * set the percentage of files at which to stop allocating
+ * - command: "fstop <N>%"
+ */
+static int cachefiles_daemon_fstop(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long fstop;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	fstop = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (fstop < 0 || fstop >= cache->fcull_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->fstop_percent = fstop;
+	return 0;
+}
+
+/*
+ * set the percentage of blocks at which to stop culling
+ * - command: "brun <N>%"
+ */
+static int cachefiles_daemon_brun(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long brun;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	brun = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (brun <= cache->bcull_percent || brun >= 100)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->brun_percent = brun;
+	return 0;
+}
+
+/*
+ * set the percentage of blocks at which to start culling
+ * - command: "bcull <N>%"
+ */
+static int cachefiles_daemon_bcull(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long bcull;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	bcull = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (bcull <= cache->bstop_percent || bcull >= cache->brun_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->bcull_percent = bcull;
+	return 0;
+}
+
+/*
+ * set the percentage of blocks at which to stop allocating
+ * - command: "bstop <N>%"
+ */
+static int cachefiles_daemon_bstop(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long bstop;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	bstop = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (bstop < 0 || bstop >= cache->bcull_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->bstop_percent = bstop;
+	return 0;
+}
+
+/*
+ * set the cache directory
+ * - command: "dir <name>"
+ */
+static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args)
+{
+	char *dir;
+
+	_enter(",%s", args);
+
+	if (!*args) {
+		kerror("Empty directory specified");
+		return -EINVAL;
+	}
+
+	if (cache->rootdirname) {
+		kerror("Second cache directory specified");
+		return -EEXIST;
+	}
+
+	dir = kstrdup(args, GFP_KERNEL);
+	if (!dir)
+		return -ENOMEM;
+
+	cache->rootdirname = dir;
+	return 0;
+}
+
+/*
+ * set the cache security context
+ * - command: "secctx <ctx>"
+ */
+static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args)
+{
+	char *secctx;
+
+	_enter(",%s", args);
+
+	if (!*args) {
+		kerror("Empty security context specified");
+		return -EINVAL;
+	}
+
+	if (cache->secctx) {
+		kerror("Second security context specified");
+		return -EINVAL;
+	}
+
+	secctx = kstrdup(args, GFP_KERNEL);
+	if (!secctx)
+		return -ENOMEM;
+
+	cache->secctx = secctx;
+	return 0;
+}
+
+/*
+ * set the cache tag
+ * - command: "tag <name>"
+ */
+static int cachefiles_daemon_tag(struct cachefiles_cache *cache, char *args)
+{
+	char *tag;
+
+	_enter(",%s", args);
+
+	if (!*args) {
+		kerror("Empty tag specified");
+		return -EINVAL;
+	}
+
+	if (cache->tag)
+		return -EEXIST;
+
+	tag = kstrdup(args, GFP_KERNEL);
+	if (!tag)
+		return -ENOMEM;
+
+	cache->tag = tag;
+	return 0;
+}
+
+/*
+ * request a node in the cache be culled from the current working directory
+ * - command: "cull <name>"
+ */
+static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
+{
+	struct fs_struct *fs;
+	struct dentry *dir;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter(",%s", args);
+
+	if (strchr(args, '/'))
+		goto inval;
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags)) {
+		kerror("cull applied to unready cache");
+		return -EIO;
+	}
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		kerror("cull applied to dead cache");
+		return -EIO;
+	}
+
+	/* extract the directory dentry from the cwd */
+	fs = current->fs;
+	read_lock(&fs->lock);
+	dir = dget(fs->pwd.dentry);
+	read_unlock(&fs->lock);
+
+	if (!S_ISDIR(dir->d_inode->i_mode))
+		goto notdir;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_cull(cache, dir, args);
+	cachefiles_end_secure(cache, saved_cred);
+
+	dput(dir);
+	_leave(" = %d", ret);
+	return ret;
+
+notdir:
+	dput(dir);
+	kerror("cull command requires dirfd to be a directory");
+	return -ENOTDIR;
+
+inval:
+	kerror("cull command requires dirfd and filename");
+	return -EINVAL;
+}
+
+/*
+ * set debugging mode
+ * - command: "debug <mask>"
+ */
+static int cachefiles_daemon_debug(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long mask;
+
+	_enter(",%s", args);
+
+	mask = simple_strtoul(args, &args, 0);
+	if (args[0] != '\0')
+		goto inval;
+
+	cachefiles_debug = mask;
+	_leave(" = 0");
+	return 0;
+
+inval:
+	kerror("debug command requires mask");
+	return -EINVAL;
+}
+
+/*
+ * find out whether an object in the current working directory is in use or not
+ * - command: "inuse <name>"
+ */
+static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
+{
+	struct fs_struct *fs;
+	struct dentry *dir;
+	const struct cred *saved_cred;
+	int ret;
+
+	//_enter(",%s", args);
+
+	if (strchr(args, '/'))
+		goto inval;
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags)) {
+		kerror("inuse applied to unready cache");
+		return -EIO;
+	}
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		kerror("inuse applied to dead cache");
+		return -EIO;
+	}
+
+	/* extract the directory dentry from the cwd */
+	fs = current->fs;
+	read_lock(&fs->lock);
+	dir = dget(fs->pwd.dentry);
+	read_unlock(&fs->lock);
+
+	if (!S_ISDIR(dir->d_inode->i_mode))
+		goto notdir;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_check_in_use(cache, dir, args);
+	cachefiles_end_secure(cache, saved_cred);
+
+	dput(dir);
+	//_leave(" = %d", ret);
+	return ret;
+
+notdir:
+	dput(dir);
+	kerror("inuse command requires dirfd to be a directory");
+	return -ENOTDIR;
+
+inval:
+	kerror("inuse command requires dirfd and filename");
+	return -EINVAL;
+}
+
+/*
+ * see if we have space for a number of pages and/or a number of files in the
+ * cache
+ */
+int cachefiles_has_space(struct cachefiles_cache *cache,
+			 unsigned fnr, unsigned bnr)
+{
+	struct kstatfs stats;
+	int ret;
+
+	//_enter("{%llu,%llu,%llu,%llu,%llu,%llu},%u,%u",
+	//       (unsigned long long) cache->frun,
+	//       (unsigned long long) cache->fcull,
+	//       (unsigned long long) cache->fstop,
+	//       (unsigned long long) cache->brun,
+	//       (unsigned long long) cache->bcull,
+	//       (unsigned long long) cache->bstop,
+	//       fnr, bnr);
+
+	/* find out how many pages of blockdev are available */
+	memset(&stats, 0, sizeof(stats));
+
+	ret = vfs_statfs(cache->mnt->mnt_root, &stats);
+	if (ret < 0) {
+		if (ret == -EIO)
+			cachefiles_io_error(cache, "statfs failed");
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	stats.f_bavail >>= cache->bshift;
+
+	//_debug("avail %llu,%llu",
+	//       (unsigned long long) stats.f_ffree,
+	//       (unsigned long long) stats.f_bavail);
+
+	/* see if there is sufficient space */
+	if (stats.f_ffree > fnr)
+		stats.f_ffree -= fnr;
+	else
+		stats.f_ffree = 0;
+
+	if (stats.f_bavail > bnr)
+		stats.f_bavail -= bnr;
+	else
+		stats.f_bavail = 0;
+
+	ret = -ENOBUFS;
+	if (stats.f_ffree < cache->fstop ||
+	    stats.f_bavail < cache->bstop)
+		goto begin_cull;
+
+	ret = 0;
+	if (stats.f_ffree < cache->fcull ||
+	    stats.f_bavail < cache->bcull)
+		goto begin_cull;
+
+	if (test_bit(CACHEFILES_CULLING, &cache->flags) &&
+	    stats.f_ffree >= cache->frun &&
+	    stats.f_bavail >= cache->brun &&
+	    test_and_clear_bit(CACHEFILES_CULLING, &cache->flags)
+	    ) {
+		_debug("cease culling");
+		cachefiles_state_changed(cache);
+	}
+
+	//_leave(" = 0");
+	return 0;
+
+begin_cull:
+	if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) {
+		_debug("### CULL CACHE ###");
+		cachefiles_state_changed(cache);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
new file mode 100644
index 000000000000..1e962348d111
--- /dev/null
+++ b/fs/cachefiles/interface.c
@@ -0,0 +1,449 @@
+/* FS-Cache interface to CacheFiles
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/mount.h>
+#include <linux/buffer_head.h>
+#include "internal.h"
+
+#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
+
+struct cachefiles_lookup_data {
+	struct cachefiles_xattr	*auxdata;	/* auxiliary data */
+	char			*key;		/* key path */
+};
+
+static int cachefiles_attr_changed(struct fscache_object *_object);
+
+/*
+ * allocate an object record for a cookie lookup and prepare the lookup data
+ */
+static struct fscache_object *cachefiles_alloc_object(
+	struct fscache_cache *_cache,
+	struct fscache_cookie *cookie)
+{
+	struct cachefiles_lookup_data *lookup_data;
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct cachefiles_xattr *auxdata;
+	unsigned keylen, auxlen;
+	void *buffer;
+	char *key;
+
+	cache = container_of(_cache, struct cachefiles_cache, cache);
+
+	_enter("{%s},%p,", cache->cache.identifier, cookie);
+
+	lookup_data = kmalloc(sizeof(*lookup_data), GFP_KERNEL);
+	if (!lookup_data)
+		goto nomem_lookup_data;
+
+	/* create a new object record and a temporary leaf image */
+	object = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL);
+	if (!object)
+		goto nomem_object;
+
+	ASSERTCMP(object->backer, ==, NULL);
+
+	BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
+	atomic_set(&object->usage, 1);
+
+	fscache_object_init(&object->fscache, cookie, &cache->cache);
+
+	object->type = cookie->def->type;
+
+	/* get hold of the raw key
+	 * - stick the length on the front and leave space on the back for the
+	 *   encoder
+	 */
+	buffer = kmalloc((2 + 512) + 3, GFP_KERNEL);
+	if (!buffer)
+		goto nomem_buffer;
+
+	keylen = cookie->def->get_key(cookie->netfs_data, buffer + 2, 512);
+	ASSERTCMP(keylen, <, 512);
+
+	*(uint16_t *)buffer = keylen;
+	((char *)buffer)[keylen + 2] = 0;
+	((char *)buffer)[keylen + 3] = 0;
+	((char *)buffer)[keylen + 4] = 0;
+
+	/* turn the raw key into something that can work with as a filename */
+	key = cachefiles_cook_key(buffer, keylen + 2, object->type);
+	if (!key)
+		goto nomem_key;
+
+	/* get hold of the auxiliary data and prepend the object type */
+	auxdata = buffer;
+	auxlen = 0;
+	if (cookie->def->get_aux) {
+		auxlen = cookie->def->get_aux(cookie->netfs_data,
+					      auxdata->data, 511);
+		ASSERTCMP(auxlen, <, 511);
+	}
+
+	auxdata->len = auxlen + 1;
+	auxdata->type = cookie->def->type;
+
+	lookup_data->auxdata = auxdata;
+	lookup_data->key = key;
+	object->lookup_data = lookup_data;
+
+	_leave(" = %p [%p]", &object->fscache, lookup_data);
+	return &object->fscache;
+
+nomem_key:
+	kfree(buffer);
+nomem_buffer:
+	BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
+	kmem_cache_free(cachefiles_object_jar, object);
+	fscache_object_destroyed(&cache->cache);
+nomem_object:
+	kfree(lookup_data);
+nomem_lookup_data:
+	_leave(" = -ENOMEM");
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * attempt to look up the nominated node in this cache
+ */
+static void cachefiles_lookup_object(struct fscache_object *_object)
+{
+	struct cachefiles_lookup_data *lookup_data;
+	struct cachefiles_object *parent, *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("{OBJ%x}", _object->debug_id);
+
+	cache = container_of(_object->cache, struct cachefiles_cache, cache);
+	parent = container_of(_object->parent,
+			      struct cachefiles_object, fscache);
+	object = container_of(_object, struct cachefiles_object, fscache);
+	lookup_data = object->lookup_data;
+
+	ASSERTCMP(lookup_data, !=, NULL);
+
+	/* look up the key, creating any missing bits */
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_walk_to_object(parent, object,
+					lookup_data->key,
+					lookup_data->auxdata);
+	cachefiles_end_secure(cache, saved_cred);
+
+	/* polish off by setting the attributes of non-index files */
+	if (ret == 0 &&
+	    object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+		cachefiles_attr_changed(&object->fscache);
+
+	if (ret < 0) {
+		printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n",
+		       ret);
+		fscache_object_lookup_error(&object->fscache);
+	}
+
+	_leave(" [%d]", ret);
+}
+
+/*
+ * indication of lookup completion
+ */
+static void cachefiles_lookup_complete(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%p}", object->fscache.debug_id, object->lookup_data);
+
+	if (object->lookup_data) {
+		kfree(object->lookup_data->key);
+		kfree(object->lookup_data->auxdata);
+		kfree(object->lookup_data);
+		object->lookup_data = NULL;
+	}
+}
+
+/*
+ * increment the usage count on an inode object (may fail if unmounting)
+ */
+static
+struct fscache_object *cachefiles_grab_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object =
+		container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%d}", _object->debug_id, atomic_read(&object->usage));
+
+#ifdef CACHEFILES_DEBUG_SLAB
+	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
+#endif
+
+	atomic_inc(&object->usage);
+	return &object->fscache;
+}
+
+/*
+ * update the auxilliary data for an object object on disk
+ */
+static void cachefiles_update_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_xattr *auxdata;
+	struct cachefiles_cache *cache;
+	struct fscache_cookie *cookie;
+	const struct cred *saved_cred;
+	unsigned auxlen;
+
+	_enter("{OBJ%x}", _object->debug_id);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache, struct cachefiles_cache,
+			     cache);
+	cookie = object->fscache.cookie;
+
+	if (!cookie->def->get_aux) {
+		_leave(" [no aux]");
+		return;
+	}
+
+	auxdata = kmalloc(2 + 512 + 3, GFP_KERNEL);
+	if (!auxdata) {
+		_leave(" [nomem]");
+		return;
+	}
+
+	auxlen = cookie->def->get_aux(cookie->netfs_data, auxdata->data, 511);
+	ASSERTCMP(auxlen, <, 511);
+
+	auxdata->len = auxlen + 1;
+	auxdata->type = cookie->def->type;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	cachefiles_update_object_xattr(object, auxdata);
+	cachefiles_end_secure(cache, saved_cred);
+	kfree(auxdata);
+	_leave("");
+}
+
+/*
+ * discard the resources pinned by an object and effect retirement if
+ * requested
+ */
+static void cachefiles_drop_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+
+	ASSERT(_object);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%d}",
+	       object->fscache.debug_id, atomic_read(&object->usage));
+
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+#ifdef CACHEFILES_DEBUG_SLAB
+	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
+#endif
+
+	/* delete retired objects */
+	if (object->fscache.state == FSCACHE_OBJECT_RECYCLING &&
+	    _object != cache->cache.fsdef
+	    ) {
+		_debug("- retire object OBJ%x", object->fscache.debug_id);
+		cachefiles_begin_secure(cache, &saved_cred);
+		cachefiles_delete_object(cache, object);
+		cachefiles_end_secure(cache, saved_cred);
+	}
+
+	/* close the filesystem stuff attached to the object */
+	if (object->backer != object->dentry)
+		dput(object->backer);
+	object->backer = NULL;
+
+	/* note that the object is now inactive */
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
+		write_lock(&cache->active_lock);
+		if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
+					&object->flags))
+			BUG();
+		rb_erase(&object->active_node, &cache->active_nodes);
+		wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+		write_unlock(&cache->active_lock);
+	}
+
+	dput(object->dentry);
+	object->dentry = NULL;
+
+	_leave("");
+}
+
+/*
+ * dispose of a reference to an object
+ */
+static void cachefiles_put_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct fscache_cache *cache;
+
+	ASSERT(_object);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%d}",
+	       object->fscache.debug_id, atomic_read(&object->usage));
+
+#ifdef CACHEFILES_DEBUG_SLAB
+	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
+#endif
+
+	ASSERTIFCMP(object->fscache.parent,
+		    object->fscache.parent->n_children, >, 0);
+
+	if (atomic_dec_and_test(&object->usage)) {
+		_debug("- kill object OBJ%x", object->fscache.debug_id);
+
+		ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
+		ASSERTCMP(object->fscache.parent, ==, NULL);
+		ASSERTCMP(object->backer, ==, NULL);
+		ASSERTCMP(object->dentry, ==, NULL);
+		ASSERTCMP(object->fscache.n_ops, ==, 0);
+		ASSERTCMP(object->fscache.n_children, ==, 0);
+
+		if (object->lookup_data) {
+			kfree(object->lookup_data->key);
+			kfree(object->lookup_data->auxdata);
+			kfree(object->lookup_data);
+			object->lookup_data = NULL;
+		}
+
+		cache = object->fscache.cache;
+		kmem_cache_free(cachefiles_object_jar, object);
+		fscache_object_destroyed(cache);
+	}
+
+	_leave("");
+}
+
+/*
+ * sync a cache
+ */
+static void cachefiles_sync_cache(struct fscache_cache *_cache)
+{
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("%p", _cache);
+
+	cache = container_of(_cache, struct cachefiles_cache, cache);
+
+	/* make sure all pages pinned by operations on behalf of the netfs are
+	 * written to disc */
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = fsync_super(cache->mnt->mnt_sb);
+	cachefiles_end_secure(cache, saved_cred);
+
+	if (ret == -EIO)
+		cachefiles_io_error(cache,
+				    "Attempt to sync backing fs superblock"
+				    " returned error %d",
+				    ret);
+}
+
+/*
+ * notification the attributes on an object have changed
+ * - called with reads/writes excluded by FS-Cache
+ */
+static int cachefiles_attr_changed(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	struct iattr newattrs;
+	uint64_t ni_size;
+	loff_t oi_size;
+	int ret;
+
+	_object->cookie->def->get_attr(_object->cookie->netfs_data, &ni_size);
+
+	_enter("{OBJ%x},[%llu]",
+	       _object->debug_id, (unsigned long long) ni_size);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	if (ni_size == object->i_size)
+		return 0;
+
+	if (!object->backer)
+		return -ENOBUFS;
+
+	ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+
+	fscache_set_store_limit(&object->fscache, ni_size);
+
+	oi_size = i_size_read(object->backer->d_inode);
+	if (oi_size == ni_size)
+		return 0;
+
+	newattrs.ia_size = ni_size;
+	newattrs.ia_valid = ATTR_SIZE;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	mutex_lock(&object->backer->d_inode->i_mutex);
+	ret = notify_change(object->backer, &newattrs);
+	mutex_unlock(&object->backer->d_inode->i_mutex);
+	cachefiles_end_secure(cache, saved_cred);
+
+	if (ret == -EIO) {
+		fscache_set_store_limit(&object->fscache, 0);
+		cachefiles_io_error_obj(object, "Size set failed");
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * dissociate a cache from all the pages it was backing
+ */
+static void cachefiles_dissociate_pages(struct fscache_cache *cache)
+{
+	_enter("");
+}
+
+const struct fscache_cache_ops cachefiles_cache_ops = {
+	.name			= "cachefiles",
+	.alloc_object		= cachefiles_alloc_object,
+	.lookup_object		= cachefiles_lookup_object,
+	.lookup_complete	= cachefiles_lookup_complete,
+	.grab_object		= cachefiles_grab_object,
+	.update_object		= cachefiles_update_object,
+	.drop_object		= cachefiles_drop_object,
+	.put_object		= cachefiles_put_object,
+	.sync_cache		= cachefiles_sync_cache,
+	.attr_changed		= cachefiles_attr_changed,
+	.read_or_alloc_page	= cachefiles_read_or_alloc_page,
+	.read_or_alloc_pages	= cachefiles_read_or_alloc_pages,
+	.allocate_page		= cachefiles_allocate_page,
+	.allocate_pages		= cachefiles_allocate_pages,
+	.write_page		= cachefiles_write_page,
+	.uncache_page		= cachefiles_uncache_page,
+	.dissociate_pages	= cachefiles_dissociate_pages,
+};
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
new file mode 100644
index 000000000000..19218e1463d6
--- /dev/null
+++ b/fs/cachefiles/internal.h
@@ -0,0 +1,360 @@
+/* General netfs cache on cache files internal defs
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/fscache-cache.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <linux/security.h>
+
+struct cachefiles_cache;
+struct cachefiles_object;
+
+extern unsigned cachefiles_debug;
+#define CACHEFILES_DEBUG_KENTER	1
+#define CACHEFILES_DEBUG_KLEAVE	2
+#define CACHEFILES_DEBUG_KDEBUG	4
+
+/*
+ * node records
+ */
+struct cachefiles_object {
+	struct fscache_object		fscache;	/* fscache handle */
+	struct cachefiles_lookup_data	*lookup_data;	/* cached lookup data */
+	struct dentry			*dentry;	/* the file/dir representing this object */
+	struct dentry			*backer;	/* backing file */
+	loff_t				i_size;		/* object size */
+	unsigned long			flags;
+#define CACHEFILES_OBJECT_ACTIVE	0		/* T if marked active */
+	atomic_t			usage;		/* object usage count */
+	uint8_t				type;		/* object type */
+	uint8_t				new;		/* T if object new */
+	spinlock_t			work_lock;
+	struct rb_node			active_node;	/* link in active tree (dentry is key) */
+};
+
+extern struct kmem_cache *cachefiles_object_jar;
+
+/*
+ * Cache files cache definition
+ */
+struct cachefiles_cache {
+	struct fscache_cache		cache;		/* FS-Cache record */
+	struct vfsmount			*mnt;		/* mountpoint holding the cache */
+	struct dentry			*graveyard;	/* directory into which dead objects go */
+	struct file			*cachefilesd;	/* manager daemon handle */
+	const struct cred		*cache_cred;	/* security override for accessing cache */
+	struct mutex			daemon_mutex;	/* command serialisation mutex */
+	wait_queue_head_t		daemon_pollwq;	/* poll waitqueue for daemon */
+	struct rb_root			active_nodes;	/* active nodes (can't be culled) */
+	rwlock_t			active_lock;	/* lock for active_nodes */
+	atomic_t			gravecounter;	/* graveyard uniquifier */
+	unsigned			frun_percent;	/* when to stop culling (% files) */
+	unsigned			fcull_percent;	/* when to start culling (% files) */
+	unsigned			fstop_percent;	/* when to stop allocating (% files) */
+	unsigned			brun_percent;	/* when to stop culling (% blocks) */
+	unsigned			bcull_percent;	/* when to start culling (% blocks) */
+	unsigned			bstop_percent;	/* when to stop allocating (% blocks) */
+	unsigned			bsize;		/* cache's block size */
+	unsigned			bshift;		/* min(ilog2(PAGE_SIZE / bsize), 0) */
+	uint64_t			frun;		/* when to stop culling */
+	uint64_t			fcull;		/* when to start culling */
+	uint64_t			fstop;		/* when to stop allocating */
+	sector_t			brun;		/* when to stop culling */
+	sector_t			bcull;		/* when to start culling */
+	sector_t			bstop;		/* when to stop allocating */
+	unsigned long			flags;
+#define CACHEFILES_READY		0	/* T if cache prepared */
+#define CACHEFILES_DEAD			1	/* T if cache dead */
+#define CACHEFILES_CULLING		2	/* T if cull engaged */
+#define CACHEFILES_STATE_CHANGED	3	/* T if state changed (poll trigger) */
+	char				*rootdirname;	/* name of cache root directory */
+	char				*secctx;	/* LSM security context */
+	char				*tag;		/* cache binding tag */
+};
+
+/*
+ * backing file read tracking
+ */
+struct cachefiles_one_read {
+	wait_queue_t			monitor;	/* link into monitored waitqueue */
+	struct page			*back_page;	/* backing file page we're waiting for */
+	struct page			*netfs_page;	/* netfs page we're going to fill */
+	struct fscache_retrieval	*op;		/* retrieval op covering this */
+	struct list_head		op_link;	/* link in op's todo list */
+};
+
+/*
+ * backing file write tracking
+ */
+struct cachefiles_one_write {
+	struct page			*netfs_page;	/* netfs page to copy */
+	struct cachefiles_object	*object;
+	struct list_head		obj_link;	/* link in object's lists */
+	fscache_rw_complete_t		end_io_func;
+	void				*context;
+};
+
+/*
+ * auxiliary data xattr buffer
+ */
+struct cachefiles_xattr {
+	uint16_t			len;
+	uint8_t				type;
+	uint8_t				data[];
+};
+
+/*
+ * note change of state for daemon
+ */
+static inline void cachefiles_state_changed(struct cachefiles_cache *cache)
+{
+	set_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
+	wake_up_all(&cache->daemon_pollwq);
+}
+
+/*
+ * cf-bind.c
+ */
+extern int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args);
+extern void cachefiles_daemon_unbind(struct cachefiles_cache *cache);
+
+/*
+ * cf-daemon.c
+ */
+extern const struct file_operations cachefiles_daemon_fops;
+
+extern int cachefiles_has_space(struct cachefiles_cache *cache,
+				unsigned fnr, unsigned bnr);
+
+/*
+ * cf-interface.c
+ */
+extern const struct fscache_cache_ops cachefiles_cache_ops;
+
+/*
+ * cf-key.c
+ */
+extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type);
+
+/*
+ * cf-namei.c
+ */
+extern int cachefiles_delete_object(struct cachefiles_cache *cache,
+				    struct cachefiles_object *object);
+extern int cachefiles_walk_to_object(struct cachefiles_object *parent,
+				     struct cachefiles_object *object,
+				     const char *key,
+				     struct cachefiles_xattr *auxdata);
+extern struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
+					       struct dentry *dir,
+					       const char *name);
+
+extern int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
+			   char *filename);
+
+extern int cachefiles_check_in_use(struct cachefiles_cache *cache,
+				   struct dentry *dir, char *filename);
+
+/*
+ * cf-proc.c
+ */
+#ifdef CONFIG_CACHEFILES_HISTOGRAM
+extern atomic_t cachefiles_lookup_histogram[HZ];
+extern atomic_t cachefiles_mkdir_histogram[HZ];
+extern atomic_t cachefiles_create_histogram[HZ];
+
+extern int __init cachefiles_proc_init(void);
+extern void cachefiles_proc_cleanup(void);
+static inline
+void cachefiles_hist(atomic_t histogram[], unsigned long start_jif)
+{
+	unsigned long jif = jiffies - start_jif;
+	if (jif >= HZ)
+		jif = HZ - 1;
+	atomic_inc(&histogram[jif]);
+}
+
+#else
+#define cachefiles_proc_init()		(0)
+#define cachefiles_proc_cleanup()	do {} while (0)
+#define cachefiles_hist(hist, start_jif) do {} while (0)
+#endif
+
+/*
+ * cf-rdwr.c
+ */
+extern int cachefiles_read_or_alloc_page(struct fscache_retrieval *,
+					 struct page *, gfp_t);
+extern int cachefiles_read_or_alloc_pages(struct fscache_retrieval *,
+					  struct list_head *, unsigned *,
+					  gfp_t);
+extern int cachefiles_allocate_page(struct fscache_retrieval *, struct page *,
+				    gfp_t);
+extern int cachefiles_allocate_pages(struct fscache_retrieval *,
+				     struct list_head *, unsigned *, gfp_t);
+extern int cachefiles_write_page(struct fscache_storage *, struct page *);
+extern void cachefiles_uncache_page(struct fscache_object *, struct page *);
+
+/*
+ * cf-security.c
+ */
+extern int cachefiles_get_security_ID(struct cachefiles_cache *cache);
+extern int cachefiles_determine_cache_security(struct cachefiles_cache *cache,
+					       struct dentry *root,
+					       const struct cred **_saved_cred);
+
+static inline void cachefiles_begin_secure(struct cachefiles_cache *cache,
+					   const struct cred **_saved_cred)
+{
+	*_saved_cred = override_creds(cache->cache_cred);
+}
+
+static inline void cachefiles_end_secure(struct cachefiles_cache *cache,
+					 const struct cred *saved_cred)
+{
+	revert_creds(saved_cred);
+}
+
+/*
+ * cf-xattr.c
+ */
+extern int cachefiles_check_object_type(struct cachefiles_object *object);
+extern int cachefiles_set_object_xattr(struct cachefiles_object *object,
+				       struct cachefiles_xattr *auxdata);
+extern int cachefiles_update_object_xattr(struct cachefiles_object *object,
+					  struct cachefiles_xattr *auxdata);
+extern int cachefiles_check_object_xattr(struct cachefiles_object *object,
+					 struct cachefiles_xattr *auxdata);
+extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
+					  struct dentry *dentry);
+
+
+/*
+ * error handling
+ */
+#define kerror(FMT, ...) printk(KERN_ERR "CacheFiles: "FMT"\n", ##__VA_ARGS__)
+
+#define cachefiles_io_error(___cache, FMT, ...)		\
+do {							\
+	kerror("I/O Error: " FMT, ##__VA_ARGS__);	\
+	fscache_io_error(&(___cache)->cache);		\
+	set_bit(CACHEFILES_DEAD, &(___cache)->flags);	\
+} while (0)
+
+#define cachefiles_io_error_obj(object, FMT, ...)			\
+do {									\
+	struct cachefiles_cache *___cache;				\
+									\
+	___cache = container_of((object)->fscache.cache,		\
+				struct cachefiles_cache, cache);	\
+	cachefiles_io_error(___cache, FMT, ##__VA_ARGS__);		\
+} while (0)
+
+
+/*
+ * debug tracing
+ */
+#define dbgprintk(FMT, ...) \
+	printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+
+/* make sure we maintain the format strings, even when debugging is disabled */
+static inline void _dbprintk(const char *fmt, ...)
+	__attribute__((format(printf, 1, 2)));
+static inline void _dbprintk(const char *fmt, ...)
+{
+}
+
+#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__)
+
+
+#if defined(__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_CACHEFILES_DEBUG)
+#define _enter(FMT, ...)				\
+do {							\
+	if (cachefiles_debug & CACHEFILES_DEBUG_KENTER)	\
+		kenter(FMT, ##__VA_ARGS__);		\
+} while (0)
+
+#define _leave(FMT, ...)				\
+do {							\
+	if (cachefiles_debug & CACHEFILES_DEBUG_KLEAVE)	\
+		kleave(FMT, ##__VA_ARGS__);		\
+} while (0)
+
+#define _debug(FMT, ...)				\
+do {							\
+	if (cachefiles_debug & CACHEFILES_DEBUG_KDEBUG)	\
+		kdebug(FMT, ##__VA_ARGS__);		\
+} while (0)
+
+#else
+#define _enter(FMT, ...) _dbprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) _dbprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#endif
+
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "CacheFiles: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "CacheFiles: 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 "CacheFiles: 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 "CacheFiles: 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
diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c
new file mode 100644
index 000000000000..81b8b2b3a674
--- /dev/null
+++ b/fs/cachefiles/key.c
@@ -0,0 +1,159 @@
+/* Key to pathname encoder
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/slab.h>
+#include "internal.h"
+
+static const char cachefiles_charmap[64] =
+	"0123456789"			/* 0 - 9 */
+	"abcdefghijklmnopqrstuvwxyz"	/* 10 - 35 */
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZ"	/* 36 - 61 */
+	"_-"				/* 62 - 63 */
+	;
+
+static const char cachefiles_filecharmap[256] = {
+	/* we skip space and tab and control chars */
+	[33 ... 46] = 1,		/* '!' -> '.' */
+	/* we skip '/' as it's significant to pathwalk */
+	[48 ... 127] = 1,		/* '0' -> '~' */
+};
+
+/*
+ * turn the raw key into something cooked
+ * - the raw key should include the length in the two bytes at the front
+ * - the key may be up to 514 bytes in length (including the length word)
+ *   - "base64" encode the strange keys, mapping 3 bytes of raw to four of
+ *     cooked
+ *   - need to cut the cooked key into 252 char lengths (189 raw bytes)
+ */
+char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type)
+{
+	unsigned char csum, ch;
+	unsigned int acc;
+	char *key;
+	int loop, len, max, seg, mark, print;
+
+	_enter(",%d", keylen);
+
+	BUG_ON(keylen < 2 || keylen > 514);
+
+	csum = raw[0] + raw[1];
+	print = 1;
+	for (loop = 2; loop < keylen; loop++) {
+		ch = raw[loop];
+		csum += ch;
+		print &= cachefiles_filecharmap[ch];
+	}
+
+	if (print) {
+		/* if the path is usable ASCII, then we render it directly */
+		max = keylen - 2;
+		max += 2;	/* two base64'd length chars on the front */
+		max += 5;	/* @checksum/M */
+		max += 3 * 2;	/* maximum number of segment dividers (".../M")
+				 * is ((514 + 251) / 252) = 3
+				 */
+		max += 1;	/* NUL on end */
+	} else {
+		/* calculate the maximum length of the cooked key */
+		keylen = (keylen + 2) / 3;
+
+		max = keylen * 4;
+		max += 5;	/* @checksum/M */
+		max += 3 * 2;	/* maximum number of segment dividers (".../M")
+				 * is ((514 + 188) / 189) = 3
+				 */
+		max += 1;	/* NUL on end */
+	}
+
+	max += 1;	/* 2nd NUL on end */
+
+	_debug("max: %d", max);
+
+	key = kmalloc(max, GFP_KERNEL);
+	if (!key)
+		return NULL;
+
+	len = 0;
+
+	/* build the cooked key */
+	sprintf(key, "@%02x%c+", (unsigned) csum, 0);
+	len = 5;
+	mark = len - 1;
+
+	if (print) {
+		acc = *(uint16_t *) raw;
+		raw += 2;
+
+		key[len + 1] = cachefiles_charmap[acc & 63];
+		acc >>= 6;
+		key[len] = cachefiles_charmap[acc & 63];
+		len += 2;
+
+		seg = 250;
+		for (loop = keylen; loop > 0; loop--) {
+			if (seg <= 0) {
+				key[len++] = '\0';
+				mark = len;
+				key[len++] = '+';
+				seg = 252;
+			}
+
+			key[len++] = *raw++;
+			ASSERT(len < max);
+		}
+
+		switch (type) {
+		case FSCACHE_COOKIE_TYPE_INDEX:		type = 'I';	break;
+		case FSCACHE_COOKIE_TYPE_DATAFILE:	type = 'D';	break;
+		default:				type = 'S';	break;
+		}
+	} else {
+		seg = 252;
+		for (loop = keylen; loop > 0; loop--) {
+			if (seg <= 0) {
+				key[len++] = '\0';
+				mark = len;
+				key[len++] = '+';
+				seg = 252;
+			}
+
+			acc = *raw++;
+			acc |= *raw++ << 8;
+			acc |= *raw++ << 16;
+
+			_debug("acc: %06x", acc);
+
+			key[len++] = cachefiles_charmap[acc & 63];
+			acc >>= 6;
+			key[len++] = cachefiles_charmap[acc & 63];
+			acc >>= 6;
+			key[len++] = cachefiles_charmap[acc & 63];
+			acc >>= 6;
+			key[len++] = cachefiles_charmap[acc & 63];
+
+			ASSERT(len < max);
+		}
+
+		switch (type) {
+		case FSCACHE_COOKIE_TYPE_INDEX:		type = 'J';	break;
+		case FSCACHE_COOKIE_TYPE_DATAFILE:	type = 'E';	break;
+		default:				type = 'T';	break;
+		}
+	}
+
+	key[mark] = type;
+	key[len++] = 0;
+	key[len] = 0;
+
+	_leave(" = %p %d", key, len);
+	return key;
+}
diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c
new file mode 100644
index 000000000000..4bfa8cf43bf5
--- /dev/null
+++ b/fs/cachefiles/main.c
@@ -0,0 +1,106 @@
+/* Network filesystem caching backend to use cache files on a premounted
+ * filesystem
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/sysctl.h>
+#include <linux/miscdevice.h>
+#include "internal.h"
+
+unsigned cachefiles_debug;
+module_param_named(debug, cachefiles_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(cachefiles_debug, "CacheFiles debugging mask");
+
+MODULE_DESCRIPTION("Mounted-filesystem based cache");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+struct kmem_cache *cachefiles_object_jar;
+
+static struct miscdevice cachefiles_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "cachefiles",
+	.fops	= &cachefiles_daemon_fops,
+};
+
+static void cachefiles_object_init_once(void *_object)
+{
+	struct cachefiles_object *object = _object;
+
+	memset(object, 0, sizeof(*object));
+	spin_lock_init(&object->work_lock);
+}
+
+/*
+ * initialise the fs caching module
+ */
+static int __init cachefiles_init(void)
+{
+	int ret;
+
+	ret = misc_register(&cachefiles_dev);
+	if (ret < 0)
+		goto error_dev;
+
+	/* create an object jar */
+	ret = -ENOMEM;
+	cachefiles_object_jar =
+		kmem_cache_create("cachefiles_object_jar",
+				  sizeof(struct cachefiles_object),
+				  0,
+				  SLAB_HWCACHE_ALIGN,
+				  cachefiles_object_init_once);
+	if (!cachefiles_object_jar) {
+		printk(KERN_NOTICE
+		       "CacheFiles: Failed to allocate an object jar\n");
+		goto error_object_jar;
+	}
+
+	ret = cachefiles_proc_init();
+	if (ret < 0)
+		goto error_proc;
+
+	printk(KERN_INFO "CacheFiles: Loaded\n");
+	return 0;
+
+error_proc:
+	kmem_cache_destroy(cachefiles_object_jar);
+error_object_jar:
+	misc_deregister(&cachefiles_dev);
+error_dev:
+	kerror("failed to register: %d", ret);
+	return ret;
+}
+
+fs_initcall(cachefiles_init);
+
+/*
+ * clean up on module removal
+ */
+static void __exit cachefiles_exit(void)
+{
+	printk(KERN_INFO "CacheFiles: Unloading\n");
+
+	cachefiles_proc_cleanup();
+	kmem_cache_destroy(cachefiles_object_jar);
+	misc_deregister(&cachefiles_dev);
+}
+
+module_exit(cachefiles_exit);
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
new file mode 100644
index 000000000000..4ce818ae39ea
--- /dev/null
+++ b/fs/cachefiles/namei.c
@@ -0,0 +1,771 @@
+/* CacheFiles path walking and related routines
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/quotaops.h>
+#include <linux/xattr.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+#include "internal.h"
+
+static int cachefiles_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+
+/*
+ * record the fact that an object is now active
+ */
+static void cachefiles_mark_object_active(struct cachefiles_cache *cache,
+					  struct cachefiles_object *object)
+{
+	struct cachefiles_object *xobject;
+	struct rb_node **_p, *_parent = NULL;
+	struct dentry *dentry;
+
+	_enter(",%p", object);
+
+try_again:
+	write_lock(&cache->active_lock);
+
+	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+		BUG();
+
+	dentry = object->dentry;
+	_p = &cache->active_nodes.rb_node;
+	while (*_p) {
+		_parent = *_p;
+		xobject = rb_entry(_parent,
+				   struct cachefiles_object, active_node);
+
+		ASSERT(xobject != object);
+
+		if (xobject->dentry > dentry)
+			_p = &(*_p)->rb_left;
+		else if (xobject->dentry < dentry)
+			_p = &(*_p)->rb_right;
+		else
+			goto wait_for_old_object;
+	}
+
+	rb_link_node(&object->active_node, _parent, _p);
+	rb_insert_color(&object->active_node, &cache->active_nodes);
+
+	write_unlock(&cache->active_lock);
+	_leave("");
+	return;
+
+	/* an old object from a previous incarnation is hogging the slot - we
+	 * need to wait for it to be destroyed */
+wait_for_old_object:
+	if (xobject->fscache.state < FSCACHE_OBJECT_DYING) {
+		printk(KERN_ERR "\n");
+		printk(KERN_ERR "CacheFiles: Error:"
+		       " Unexpected object collision\n");
+		printk(KERN_ERR "xobject: OBJ%x\n",
+		       xobject->fscache.debug_id);
+		printk(KERN_ERR "xobjstate=%s\n",
+		       fscache_object_states[xobject->fscache.state]);
+		printk(KERN_ERR "xobjflags=%lx\n", xobject->fscache.flags);
+		printk(KERN_ERR "xobjevent=%lx [%lx]\n",
+		       xobject->fscache.events, xobject->fscache.event_mask);
+		printk(KERN_ERR "xops=%u inp=%u exc=%u\n",
+		       xobject->fscache.n_ops, xobject->fscache.n_in_progress,
+		       xobject->fscache.n_exclusive);
+		printk(KERN_ERR "xcookie=%p [pr=%p nd=%p fl=%lx]\n",
+		       xobject->fscache.cookie,
+		       xobject->fscache.cookie->parent,
+		       xobject->fscache.cookie->netfs_data,
+		       xobject->fscache.cookie->flags);
+		printk(KERN_ERR "xparent=%p\n",
+		       xobject->fscache.parent);
+		printk(KERN_ERR "object: OBJ%x\n",
+		       object->fscache.debug_id);
+		printk(KERN_ERR "cookie=%p [pr=%p nd=%p fl=%lx]\n",
+		       object->fscache.cookie,
+		       object->fscache.cookie->parent,
+		       object->fscache.cookie->netfs_data,
+		       object->fscache.cookie->flags);
+		printk(KERN_ERR "parent=%p\n",
+		       object->fscache.parent);
+		BUG();
+	}
+	atomic_inc(&xobject->usage);
+	write_unlock(&cache->active_lock);
+
+	_debug(">>> wait");
+	wait_on_bit(&xobject->flags, CACHEFILES_OBJECT_ACTIVE,
+		    cachefiles_wait_bit, TASK_UNINTERRUPTIBLE);
+	_debug("<<< waited");
+
+	cache->cache.ops->put_object(&xobject->fscache);
+	goto try_again;
+}
+
+/*
+ * delete an object representation from the cache
+ * - file backed objects are unlinked
+ * - directory backed objects are stuffed into the graveyard for userspace to
+ *   delete
+ * - unlocks the directory mutex
+ */
+static int cachefiles_bury_object(struct cachefiles_cache *cache,
+				  struct dentry *dir,
+				  struct dentry *rep)
+{
+	struct dentry *grave, *trap;
+	char nbuffer[8 + 8 + 1];
+	int ret;
+
+	_enter(",'%*.*s','%*.*s'",
+	       dir->d_name.len, dir->d_name.len, dir->d_name.name,
+	       rep->d_name.len, rep->d_name.len, rep->d_name.name);
+
+	/* non-directories can just be unlinked */
+	if (!S_ISDIR(rep->d_inode->i_mode)) {
+		_debug("unlink stale object");
+		ret = vfs_unlink(dir->d_inode, rep);
+
+		mutex_unlock(&dir->d_inode->i_mutex);
+
+		if (ret == -EIO)
+			cachefiles_io_error(cache, "Unlink failed");
+
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	/* directories have to be moved to the graveyard */
+	_debug("move stale object to graveyard");
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+try_again:
+	/* first step is to make up a grave dentry in the graveyard */
+	sprintf(nbuffer, "%08x%08x",
+		(uint32_t) get_seconds(),
+		(uint32_t) atomic_inc_return(&cache->gravecounter));
+
+	/* do the multiway lock magic */
+	trap = lock_rename(cache->graveyard, dir);
+
+	/* do some checks before getting the grave dentry */
+	if (rep->d_parent != dir) {
+		/* the entry was probably culled when we dropped the parent dir
+		 * lock */
+		unlock_rename(cache->graveyard, dir);
+		_leave(" = 0 [culled?]");
+		return 0;
+	}
+
+	if (!S_ISDIR(cache->graveyard->d_inode->i_mode)) {
+		unlock_rename(cache->graveyard, dir);
+		cachefiles_io_error(cache, "Graveyard no longer a directory");
+		return -EIO;
+	}
+
+	if (trap == rep) {
+		unlock_rename(cache->graveyard, dir);
+		cachefiles_io_error(cache, "May not make directory loop");
+		return -EIO;
+	}
+
+	if (d_mountpoint(rep)) {
+		unlock_rename(cache->graveyard, dir);
+		cachefiles_io_error(cache, "Mountpoint in cache");
+		return -EIO;
+	}
+
+	grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer));
+	if (IS_ERR(grave)) {
+		unlock_rename(cache->graveyard, dir);
+
+		if (PTR_ERR(grave) == -ENOMEM) {
+			_leave(" = -ENOMEM");
+			return -ENOMEM;
+		}
+
+		cachefiles_io_error(cache, "Lookup error %ld",
+				    PTR_ERR(grave));
+		return -EIO;
+	}
+
+	if (grave->d_inode) {
+		unlock_rename(cache->graveyard, dir);
+		dput(grave);
+		grave = NULL;
+		cond_resched();
+		goto try_again;
+	}
+
+	if (d_mountpoint(grave)) {
+		unlock_rename(cache->graveyard, dir);
+		dput(grave);
+		cachefiles_io_error(cache, "Mountpoint in graveyard");
+		return -EIO;
+	}
+
+	/* target should not be an ancestor of source */
+	if (trap == grave) {
+		unlock_rename(cache->graveyard, dir);
+		dput(grave);
+		cachefiles_io_error(cache, "May not make directory loop");
+		return -EIO;
+	}
+
+	/* attempt the rename */
+	ret = vfs_rename(dir->d_inode, rep, cache->graveyard->d_inode, grave);
+	if (ret != 0 && ret != -ENOMEM)
+		cachefiles_io_error(cache, "Rename failed with error %d", ret);
+
+	unlock_rename(cache->graveyard, dir);
+	dput(grave);
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * delete an object representation from the cache
+ */
+int cachefiles_delete_object(struct cachefiles_cache *cache,
+			     struct cachefiles_object *object)
+{
+	struct dentry *dir;
+	int ret;
+
+	_enter(",{%p}", object->dentry);
+
+	ASSERT(object->dentry);
+	ASSERT(object->dentry->d_inode);
+	ASSERT(object->dentry->d_parent);
+
+	dir = dget_parent(object->dentry);
+
+	mutex_lock(&dir->d_inode->i_mutex);
+	ret = cachefiles_bury_object(cache, dir, object->dentry);
+
+	dput(dir);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * walk from the parent object to the child object through the backing
+ * filesystem, creating directories as we go
+ */
+int cachefiles_walk_to_object(struct cachefiles_object *parent,
+			      struct cachefiles_object *object,
+			      const char *key,
+			      struct cachefiles_xattr *auxdata)
+{
+	struct cachefiles_cache *cache;
+	struct dentry *dir, *next = NULL;
+	unsigned long start;
+	const char *name;
+	int ret, nlen;
+
+	_enter("{%p},,%s,", parent->dentry, key);
+
+	cache = container_of(parent->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	ASSERT(parent->dentry);
+	ASSERT(parent->dentry->d_inode);
+
+	if (!(S_ISDIR(parent->dentry->d_inode->i_mode))) {
+		// TODO: convert file to dir
+		_leave("looking up in none directory");
+		return -ENOBUFS;
+	}
+
+	dir = dget(parent->dentry);
+
+advance:
+	/* attempt to transit the first directory component */
+	name = key;
+	nlen = strlen(key);
+
+	/* key ends in a double NUL */
+	key = key + nlen + 1;
+	if (!*key)
+		key = NULL;
+
+lookup_again:
+	/* search the current directory for the element name */
+	_debug("lookup '%s'", name);
+
+	mutex_lock(&dir->d_inode->i_mutex);
+
+	start = jiffies;
+	next = lookup_one_len(name, dir, nlen);
+	cachefiles_hist(cachefiles_lookup_histogram, start);
+	if (IS_ERR(next))
+		goto lookup_error;
+
+	_debug("next -> %p %s", next, next->d_inode ? "positive" : "negative");
+
+	if (!key)
+		object->new = !next->d_inode;
+
+	/* if this element of the path doesn't exist, then the lookup phase
+	 * failed, and we can release any readers in the certain knowledge that
+	 * there's nothing for them to actually read */
+	if (!next->d_inode)
+		fscache_object_lookup_negative(&object->fscache);
+
+	/* we need to create the object if it's negative */
+	if (key || object->type == FSCACHE_COOKIE_TYPE_INDEX) {
+		/* index objects and intervening tree levels must be subdirs */
+		if (!next->d_inode) {
+			ret = cachefiles_has_space(cache, 1, 0);
+			if (ret < 0)
+				goto create_error;
+
+			start = jiffies;
+			ret = vfs_mkdir(dir->d_inode, next, 0);
+			cachefiles_hist(cachefiles_mkdir_histogram, start);
+			if (ret < 0)
+				goto create_error;
+
+			ASSERT(next->d_inode);
+
+			_debug("mkdir -> %p{%p{ino=%lu}}",
+			       next, next->d_inode, next->d_inode->i_ino);
+
+		} else if (!S_ISDIR(next->d_inode->i_mode)) {
+			kerror("inode %lu is not a directory",
+			       next->d_inode->i_ino);
+			ret = -ENOBUFS;
+			goto error;
+		}
+
+	} else {
+		/* non-index objects start out life as files */
+		if (!next->d_inode) {
+			ret = cachefiles_has_space(cache, 1, 0);
+			if (ret < 0)
+				goto create_error;
+
+			start = jiffies;
+			ret = vfs_create(dir->d_inode, next, S_IFREG, NULL);
+			cachefiles_hist(cachefiles_create_histogram, start);
+			if (ret < 0)
+				goto create_error;
+
+			ASSERT(next->d_inode);
+
+			_debug("create -> %p{%p{ino=%lu}}",
+			       next, next->d_inode, next->d_inode->i_ino);
+
+		} else if (!S_ISDIR(next->d_inode->i_mode) &&
+			   !S_ISREG(next->d_inode->i_mode)
+			   ) {
+			kerror("inode %lu is not a file or directory",
+			       next->d_inode->i_ino);
+			ret = -ENOBUFS;
+			goto error;
+		}
+	}
+
+	/* process the next component */
+	if (key) {
+		_debug("advance");
+		mutex_unlock(&dir->d_inode->i_mutex);
+		dput(dir);
+		dir = next;
+		next = NULL;
+		goto advance;
+	}
+
+	/* we've found the object we were looking for */
+	object->dentry = next;
+
+	/* if we've found that the terminal object exists, then we need to
+	 * check its attributes and delete it if it's out of date */
+	if (!object->new) {
+		_debug("validate '%*.*s'",
+		       next->d_name.len, next->d_name.len, next->d_name.name);
+
+		ret = cachefiles_check_object_xattr(object, auxdata);
+		if (ret == -ESTALE) {
+			/* delete the object (the deleter drops the directory
+			 * mutex) */
+			object->dentry = NULL;
+
+			ret = cachefiles_bury_object(cache, dir, next);
+			dput(next);
+			next = NULL;
+
+			if (ret < 0)
+				goto delete_error;
+
+			_debug("redo lookup");
+			goto lookup_again;
+		}
+	}
+
+	/* note that we're now using this object */
+	cachefiles_mark_object_active(cache, object);
+
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(dir);
+	dir = NULL;
+
+	_debug("=== OBTAINED_OBJECT ===");
+
+	if (object->new) {
+		/* attach data to a newly constructed terminal object */
+		ret = cachefiles_set_object_xattr(object, auxdata);
+		if (ret < 0)
+			goto check_error;
+	} else {
+		/* always update the atime on an object we've just looked up
+		 * (this is used to keep track of culling, and atimes are only
+		 * updated by read, write and readdir but not lookup or
+		 * open) */
+		touch_atime(cache->mnt, next);
+	}
+
+	/* open a file interface onto a data file */
+	if (object->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		if (S_ISREG(object->dentry->d_inode->i_mode)) {
+			const struct address_space_operations *aops;
+
+			ret = -EPERM;
+			aops = object->dentry->d_inode->i_mapping->a_ops;
+			if (!aops->bmap)
+				goto check_error;
+
+			object->backer = object->dentry;
+		} else {
+			BUG(); // TODO: open file in data-class subdir
+		}
+	}
+
+	object->new = 0;
+	fscache_obtained_object(&object->fscache);
+
+	_leave(" = 0 [%lu]", object->dentry->d_inode->i_ino);
+	return 0;
+
+create_error:
+	_debug("create error %d", ret);
+	if (ret == -EIO)
+		cachefiles_io_error(cache, "Create/mkdir failed");
+	goto error;
+
+check_error:
+	_debug("check error %d", ret);
+	write_lock(&cache->active_lock);
+	rb_erase(&object->active_node, &cache->active_nodes);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+	write_unlock(&cache->active_lock);
+
+	dput(object->dentry);
+	object->dentry = NULL;
+	goto error_out;
+
+delete_error:
+	_debug("delete error %d", ret);
+	goto error_out2;
+
+lookup_error:
+	_debug("lookup error %ld", PTR_ERR(next));
+	ret = PTR_ERR(next);
+	if (ret == -EIO)
+		cachefiles_io_error(cache, "Lookup failed");
+	next = NULL;
+error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(next);
+error_out2:
+	dput(dir);
+error_out:
+	if (ret == -ENOSPC)
+		ret = -ENOBUFS;
+
+	_leave(" = error %d", -ret);
+	return ret;
+}
+
+/*
+ * get a subdirectory
+ */
+struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
+					struct dentry *dir,
+					const char *dirname)
+{
+	struct dentry *subdir;
+	unsigned long start;
+	int ret;
+
+	_enter(",,%s", dirname);
+
+	/* search the current directory for the element name */
+	mutex_lock(&dir->d_inode->i_mutex);
+
+	start = jiffies;
+	subdir = lookup_one_len(dirname, dir, strlen(dirname));
+	cachefiles_hist(cachefiles_lookup_histogram, start);
+	if (IS_ERR(subdir)) {
+		if (PTR_ERR(subdir) == -ENOMEM)
+			goto nomem_d_alloc;
+		goto lookup_error;
+	}
+
+	_debug("subdir -> %p %s",
+	       subdir, subdir->d_inode ? "positive" : "negative");
+
+	/* we need to create the subdir if it doesn't exist yet */
+	if (!subdir->d_inode) {
+		ret = cachefiles_has_space(cache, 1, 0);
+		if (ret < 0)
+			goto mkdir_error;
+
+		_debug("attempt mkdir");
+
+		ret = vfs_mkdir(dir->d_inode, subdir, 0700);
+		if (ret < 0)
+			goto mkdir_error;
+
+		ASSERT(subdir->d_inode);
+
+		_debug("mkdir -> %p{%p{ino=%lu}}",
+		       subdir,
+		       subdir->d_inode,
+		       subdir->d_inode->i_ino);
+	}
+
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+	/* we need to make sure the subdir is a directory */
+	ASSERT(subdir->d_inode);
+
+	if (!S_ISDIR(subdir->d_inode->i_mode)) {
+		kerror("%s is not a directory", dirname);
+		ret = -EIO;
+		goto check_error;
+	}
+
+	ret = -EPERM;
+	if (!subdir->d_inode->i_op ||
+	    !subdir->d_inode->i_op->setxattr ||
+	    !subdir->d_inode->i_op->getxattr ||
+	    !subdir->d_inode->i_op->lookup ||
+	    !subdir->d_inode->i_op->mkdir ||
+	    !subdir->d_inode->i_op->create ||
+	    !subdir->d_inode->i_op->rename ||
+	    !subdir->d_inode->i_op->rmdir ||
+	    !subdir->d_inode->i_op->unlink)
+		goto check_error;
+
+	_leave(" = [%lu]", subdir->d_inode->i_ino);
+	return subdir;
+
+check_error:
+	dput(subdir);
+	_leave(" = %d [check]", ret);
+	return ERR_PTR(ret);
+
+mkdir_error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(subdir);
+	kerror("mkdir %s failed with error %d", dirname, ret);
+	return ERR_PTR(ret);
+
+lookup_error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	ret = PTR_ERR(subdir);
+	kerror("Lookup %s failed with error %d", dirname, ret);
+	return ERR_PTR(ret);
+
+nomem_d_alloc:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	_leave(" = -ENOMEM");
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * find out if an object is in use or not
+ * - if finds object and it's not in use:
+ *   - returns a pointer to the object and a reference on it
+ *   - returns with the directory locked
+ */
+static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
+					      struct dentry *dir,
+					      char *filename)
+{
+	struct cachefiles_object *object;
+	struct rb_node *_n;
+	struct dentry *victim;
+	unsigned long start;
+	int ret;
+
+	//_enter(",%*.*s/,%s",
+	//       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+
+	/* look up the victim */
+	mutex_lock_nested(&dir->d_inode->i_mutex, 1);
+
+	start = jiffies;
+	victim = lookup_one_len(filename, dir, strlen(filename));
+	cachefiles_hist(cachefiles_lookup_histogram, start);
+	if (IS_ERR(victim))
+		goto lookup_error;
+
+	//_debug("victim -> %p %s",
+	//       victim, victim->d_inode ? "positive" : "negative");
+
+	/* if the object is no longer there then we probably retired the object
+	 * at the netfs's request whilst the cull was in progress
+	 */
+	if (!victim->d_inode) {
+		mutex_unlock(&dir->d_inode->i_mutex);
+		dput(victim);
+		_leave(" = -ENOENT [absent]");
+		return ERR_PTR(-ENOENT);
+	}
+
+	/* check to see if we're using this object */
+	read_lock(&cache->active_lock);
+
+	_n = cache->active_nodes.rb_node;
+
+	while (_n) {
+		object = rb_entry(_n, struct cachefiles_object, active_node);
+
+		if (object->dentry > victim)
+			_n = _n->rb_left;
+		else if (object->dentry < victim)
+			_n = _n->rb_right;
+		else
+			goto object_in_use;
+	}
+
+	read_unlock(&cache->active_lock);
+
+	//_leave(" = %p", victim);
+	return victim;
+
+object_in_use:
+	read_unlock(&cache->active_lock);
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(victim);
+	//_leave(" = -EBUSY [in use]");
+	return ERR_PTR(-EBUSY);
+
+lookup_error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	ret = PTR_ERR(victim);
+	if (ret == -ENOENT) {
+		/* file or dir now absent - probably retired by netfs */
+		_leave(" = -ESTALE [absent]");
+		return ERR_PTR(-ESTALE);
+	}
+
+	if (ret == -EIO) {
+		cachefiles_io_error(cache, "Lookup failed");
+	} else if (ret != -ENOMEM) {
+		kerror("Internal error: %d", ret);
+		ret = -EIO;
+	}
+
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * cull an object if it's not in use
+ * - called only by cache manager daemon
+ */
+int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
+		    char *filename)
+{
+	struct dentry *victim;
+	int ret;
+
+	_enter(",%*.*s/,%s",
+	       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+
+	victim = cachefiles_check_active(cache, dir, filename);
+	if (IS_ERR(victim))
+		return PTR_ERR(victim);
+
+	_debug("victim -> %p %s",
+	       victim, victim->d_inode ? "positive" : "negative");
+
+	/* okay... the victim is not being used so we can cull it
+	 * - start by marking it as stale
+	 */
+	_debug("victim is cullable");
+
+	ret = cachefiles_remove_object_xattr(cache, victim);
+	if (ret < 0)
+		goto error_unlock;
+
+	/*  actually remove the victim (drops the dir mutex) */
+	_debug("bury");
+
+	ret = cachefiles_bury_object(cache, dir, victim);
+	if (ret < 0)
+		goto error;
+
+	dput(victim);
+	_leave(" = 0");
+	return 0;
+
+error_unlock:
+	mutex_unlock(&dir->d_inode->i_mutex);
+error:
+	dput(victim);
+	if (ret == -ENOENT) {
+		/* file or dir now absent - probably retired by netfs */
+		_leave(" = -ESTALE [absent]");
+		return -ESTALE;
+	}
+
+	if (ret != -ENOMEM) {
+		kerror("Internal error: %d", ret);
+		ret = -EIO;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * find out if an object is in use or not
+ * - called only by cache manager daemon
+ * - returns -EBUSY or 0 to indicate whether an object is in use or not
+ */
+int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
+			    char *filename)
+{
+	struct dentry *victim;
+
+	//_enter(",%*.*s/,%s",
+	//       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+
+	victim = cachefiles_check_active(cache, dir, filename);
+	if (IS_ERR(victim))
+		return PTR_ERR(victim);
+
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(victim);
+	//_leave(" = 0");
+	return 0;
+}
diff --git a/fs/cachefiles/proc.c b/fs/cachefiles/proc.c
new file mode 100644
index 000000000000..eccd33941199
--- /dev/null
+++ b/fs/cachefiles/proc.c
@@ -0,0 +1,134 @@
+/* CacheFiles 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+atomic_t cachefiles_lookup_histogram[HZ];
+atomic_t cachefiles_mkdir_histogram[HZ];
+atomic_t cachefiles_create_histogram[HZ];
+
+/*
+ * display the latency histogram
+ */
+static int cachefiles_histogram_show(struct seq_file *m, void *v)
+{
+	unsigned long index;
+	unsigned x, y, z, t;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "JIFS  SECS  LOOKUPS   MKDIRS    CREATES\n");
+		return 0;
+	case 2:
+		seq_puts(m, "===== ===== ========= ========= =========\n");
+		return 0;
+	default:
+		index = (unsigned long) v - 3;
+		x = atomic_read(&cachefiles_lookup_histogram[index]);
+		y = atomic_read(&cachefiles_mkdir_histogram[index]);
+		z = atomic_read(&cachefiles_create_histogram[index]);
+		if (x == 0 && y == 0 && z == 0)
+			return 0;
+
+		t = (index * 1000) / HZ;
+
+		seq_printf(m, "%4lu  0.%03u %9u %9u %9u\n", index, t, x, y, z);
+		return 0;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *cachefiles_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 *cachefiles_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 cachefiles_histogram_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations cachefiles_histogram_ops = {
+	.start		= cachefiles_histogram_start,
+	.stop		= cachefiles_histogram_stop,
+	.next		= cachefiles_histogram_next,
+	.show		= cachefiles_histogram_show,
+};
+
+/*
+ * open "/proc/fs/cachefiles/XXX" which provide statistics summaries
+ */
+static int cachefiles_histogram_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &cachefiles_histogram_ops);
+}
+
+static const struct file_operations cachefiles_histogram_fops = {
+	.owner		= THIS_MODULE,
+	.open		= cachefiles_histogram_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * initialise the /proc/fs/cachefiles/ directory
+ */
+int __init cachefiles_proc_init(void)
+{
+	_enter("");
+
+	if (!proc_mkdir("fs/cachefiles", NULL))
+		goto error_dir;
+
+	if (!proc_create("fs/cachefiles/histogram", S_IFREG | 0444, NULL,
+			 &cachefiles_histogram_fops))
+		goto error_histogram;
+
+	_leave(" = 0");
+	return 0;
+
+error_histogram:
+	remove_proc_entry("fs/cachefiles", NULL);
+error_dir:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/cachefiles/ directory
+ */
+void cachefiles_proc_cleanup(void)
+{
+	remove_proc_entry("fs/cachefiles/histogram", NULL);
+	remove_proc_entry("fs/cachefiles", NULL);
+}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
new file mode 100644
index 000000000000..a69787e7dd96
--- /dev/null
+++ b/fs/cachefiles/rdwr.c
@@ -0,0 +1,879 @@
+/* Storage object read/write
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/mount.h>
+#include <linux/file.h>
+#include "internal.h"
+
+/*
+ * detect wake up events generated by the unlocking of pages in which we're
+ * interested
+ * - we use this to detect read completion of backing pages
+ * - the caller holds the waitqueue lock
+ */
+static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
+				  int sync, void *_key)
+{
+	struct cachefiles_one_read *monitor =
+		container_of(wait, struct cachefiles_one_read, monitor);
+	struct cachefiles_object *object;
+	struct wait_bit_key *key = _key;
+	struct page *page = wait->private;
+
+	ASSERT(key);
+
+	_enter("{%lu},%u,%d,{%p,%u}",
+	       monitor->netfs_page->index, mode, sync,
+	       key->flags, key->bit_nr);
+
+	if (key->flags != &page->flags ||
+	    key->bit_nr != PG_locked)
+		return 0;
+
+	_debug("--- monitor %p %lx ---", page, page->flags);
+
+	if (!PageUptodate(page) && !PageError(page))
+		dump_stack();
+
+	/* remove from the waitqueue */
+	list_del(&wait->task_list);
+
+	/* move onto the action list and queue for FS-Cache thread pool */
+	ASSERT(monitor->op);
+
+	object = container_of(monitor->op->op.object,
+			      struct cachefiles_object, fscache);
+
+	spin_lock(&object->work_lock);
+	list_add_tail(&monitor->op_link, &monitor->op->to_do);
+	spin_unlock(&object->work_lock);
+
+	fscache_enqueue_retrieval(monitor->op);
+	return 0;
+}
+
+/*
+ * copy data from backing pages to netfs pages to complete a read operation
+ * - driven by FS-Cache's thread pool
+ */
+static void cachefiles_read_copier(struct fscache_operation *_op)
+{
+	struct cachefiles_one_read *monitor;
+	struct cachefiles_object *object;
+	struct fscache_retrieval *op;
+	struct pagevec pagevec;
+	int error, max;
+
+	op = container_of(_op, struct fscache_retrieval, op);
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+
+	_enter("{ino=%lu}", object->backer->d_inode->i_ino);
+
+	pagevec_init(&pagevec, 0);
+
+	max = 8;
+	spin_lock_irq(&object->work_lock);
+
+	while (!list_empty(&op->to_do)) {
+		monitor = list_entry(op->to_do.next,
+				     struct cachefiles_one_read, op_link);
+		list_del(&monitor->op_link);
+
+		spin_unlock_irq(&object->work_lock);
+
+		_debug("- copy {%lu}", monitor->back_page->index);
+
+		error = -EIO;
+		if (PageUptodate(monitor->back_page)) {
+			copy_highpage(monitor->netfs_page, monitor->back_page);
+
+			pagevec_add(&pagevec, monitor->netfs_page);
+			fscache_mark_pages_cached(monitor->op, &pagevec);
+			error = 0;
+		}
+
+		if (error)
+			cachefiles_io_error_obj(
+				object,
+				"Readpage failed on backing file %lx",
+				(unsigned long) monitor->back_page->flags);
+
+		page_cache_release(monitor->back_page);
+
+		fscache_end_io(op, monitor->netfs_page, error);
+		page_cache_release(monitor->netfs_page);
+		fscache_put_retrieval(op);
+		kfree(monitor);
+
+		/* let the thread pool have some air occasionally */
+		max--;
+		if (max < 0 || need_resched()) {
+			if (!list_empty(&op->to_do))
+				fscache_enqueue_retrieval(op);
+			_leave(" [maxed out]");
+			return;
+		}
+
+		spin_lock_irq(&object->work_lock);
+	}
+
+	spin_unlock_irq(&object->work_lock);
+	_leave("");
+}
+
+/*
+ * read the corresponding page to the given set from the backing file
+ * - an uncertain page is simply discarded, to be tried again another time
+ */
+static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
+					    struct fscache_retrieval *op,
+					    struct page *netpage,
+					    struct pagevec *pagevec)
+{
+	struct cachefiles_one_read *monitor;
+	struct address_space *bmapping;
+	struct page *newpage, *backpage;
+	int ret;
+
+	_enter("");
+
+	pagevec_reinit(pagevec);
+
+	_debug("read back %p{%lu,%d}",
+	       netpage, netpage->index, page_count(netpage));
+
+	monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+	if (!monitor)
+		goto nomem;
+
+	monitor->netfs_page = netpage;
+	monitor->op = fscache_get_retrieval(op);
+
+	init_waitqueue_func_entry(&monitor->monitor, cachefiles_read_waiter);
+
+	/* attempt to get hold of the backing page */
+	bmapping = object->backer->d_inode->i_mapping;
+	newpage = NULL;
+
+	for (;;) {
+		backpage = find_get_page(bmapping, netpage->index);
+		if (backpage)
+			goto backing_page_already_present;
+
+		if (!newpage) {
+			newpage = page_cache_alloc_cold(bmapping);
+			if (!newpage)
+				goto nomem_monitor;
+		}
+
+		ret = add_to_page_cache(newpage, bmapping,
+					netpage->index, GFP_KERNEL);
+		if (ret == 0)
+			goto installed_new_backing_page;
+		if (ret != -EEXIST)
+			goto nomem_page;
+	}
+
+	/* we've installed a new backing page, so now we need to add it
+	 * to the LRU list and start it reading */
+installed_new_backing_page:
+	_debug("- new %p", newpage);
+
+	backpage = newpage;
+	newpage = NULL;
+
+	page_cache_get(backpage);
+	pagevec_add(pagevec, backpage);
+	__pagevec_lru_add_file(pagevec);
+
+read_backing_page:
+	ret = bmapping->a_ops->readpage(NULL, backpage);
+	if (ret < 0)
+		goto read_error;
+
+	/* set the monitor to transfer the data across */
+monitor_backing_page:
+	_debug("- monitor add");
+
+	/* install the monitor */
+	page_cache_get(monitor->netfs_page);
+	page_cache_get(backpage);
+	monitor->back_page = backpage;
+	monitor->monitor.private = backpage;
+	add_page_wait_queue(backpage, &monitor->monitor);
+	monitor = NULL;
+
+	/* but the page may have been read before the monitor was installed, so
+	 * the monitor may miss the event - so we have to ensure that we do get
+	 * one in such a case */
+	if (trylock_page(backpage)) {
+		_debug("jumpstart %p {%lx}", backpage, backpage->flags);
+		unlock_page(backpage);
+	}
+	goto success;
+
+	/* if the backing page is already present, it can be in one of
+	 * three states: read in progress, read failed or read okay */
+backing_page_already_present:
+	_debug("- present");
+
+	if (newpage) {
+		page_cache_release(newpage);
+		newpage = NULL;
+	}
+
+	if (PageError(backpage))
+		goto io_error;
+
+	if (PageUptodate(backpage))
+		goto backing_page_already_uptodate;
+
+	if (!trylock_page(backpage))
+		goto monitor_backing_page;
+	_debug("read %p {%lx}", backpage, backpage->flags);
+	goto read_backing_page;
+
+	/* the backing page is already up to date, attach the netfs
+	 * page to the pagecache and LRU and copy the data across */
+backing_page_already_uptodate:
+	_debug("- uptodate");
+
+	pagevec_add(pagevec, netpage);
+	fscache_mark_pages_cached(op, pagevec);
+
+	copy_highpage(netpage, backpage);
+	fscache_end_io(op, netpage, 0);
+
+success:
+	_debug("success");
+	ret = 0;
+
+out:
+	if (backpage)
+		page_cache_release(backpage);
+	if (monitor) {
+		fscache_put_retrieval(monitor->op);
+		kfree(monitor);
+	}
+	_leave(" = %d", ret);
+	return ret;
+
+read_error:
+	_debug("read error %d", ret);
+	if (ret == -ENOMEM)
+		goto out;
+io_error:
+	cachefiles_io_error_obj(object, "Page read error on backing file");
+	ret = -ENOBUFS;
+	goto out;
+
+nomem_page:
+	page_cache_release(newpage);
+nomem_monitor:
+	fscache_put_retrieval(monitor->op);
+	kfree(monitor);
+nomem:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * read a page from the cache or allocate a block in which to store it
+ * - cache withdrawal is prevented by the caller
+ * - returns -EINTR if interrupted
+ * - returns -ENOMEM if ran out of memory
+ * - returns -ENOBUFS if no buffers can be made available
+ * - returns -ENOBUFS if page is beyond EOF
+ * - if the page is backed by a block in the cache:
+ *   - a read will be started which will call the callback on completion
+ *   - 0 will be returned
+ * - else if the page is unbacked:
+ *   - the metadata will be retained
+ *   - -ENODATA will be returned
+ */
+int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
+				  struct page *page,
+				  gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct pagevec pagevec;
+	struct inode *inode;
+	sector_t block0, block;
+	unsigned shift;
+	int ret;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("{%p},{%lx},,,", object, page->index);
+
+	if (!object->backer)
+		return -ENOBUFS;
+
+	inode = object->backer->d_inode;
+	ASSERT(S_ISREG(inode->i_mode));
+	ASSERT(inode->i_mapping->a_ops->bmap);
+	ASSERT(inode->i_mapping->a_ops->readpages);
+
+	/* calculate the shift required to use bmap */
+	if (inode->i_sb->s_blocksize > PAGE_SIZE)
+		return -ENOBUFS;
+
+	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
+
+	op->op.flags = FSCACHE_OP_FAST;
+	op->op.processor = cachefiles_read_copier;
+
+	pagevec_init(&pagevec, 0);
+
+	/* we assume the absence or presence of the first block is a good
+	 * enough indication for the page as a whole
+	 * - TODO: don't use bmap() for this as it is _not_ actually good
+	 *   enough for this as it doesn't indicate errors, but it's all we've
+	 *   got for the moment
+	 */
+	block0 = page->index;
+	block0 <<= shift;
+
+	block = inode->i_mapping->a_ops->bmap(inode->i_mapping, block0);
+	_debug("%llx -> %llx",
+	       (unsigned long long) block0,
+	       (unsigned long long) block);
+
+	if (block) {
+		/* submit the apparently valid page to the backing fs to be
+		 * read from disk */
+		ret = cachefiles_read_backing_file_one(object, op, page,
+						       &pagevec);
+	} else if (cachefiles_has_space(cache, 0, 1) == 0) {
+		/* there's space in the cache we can use */
+		pagevec_add(&pagevec, page);
+		fscache_mark_pages_cached(op, &pagevec);
+		ret = -ENODATA;
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * read the corresponding pages to the given set from the backing file
+ * - any uncertain pages are simply discarded, to be tried again another time
+ */
+static int cachefiles_read_backing_file(struct cachefiles_object *object,
+					struct fscache_retrieval *op,
+					struct list_head *list,
+					struct pagevec *mark_pvec)
+{
+	struct cachefiles_one_read *monitor = NULL;
+	struct address_space *bmapping = object->backer->d_inode->i_mapping;
+	struct pagevec lru_pvec;
+	struct page *newpage = NULL, *netpage, *_n, *backpage = NULL;
+	int ret = 0;
+
+	_enter("");
+
+	pagevec_init(&lru_pvec, 0);
+
+	list_for_each_entry_safe(netpage, _n, list, lru) {
+		list_del(&netpage->lru);
+
+		_debug("read back %p{%lu,%d}",
+		       netpage, netpage->index, page_count(netpage));
+
+		if (!monitor) {
+			monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+			if (!monitor)
+				goto nomem;
+
+			monitor->op = fscache_get_retrieval(op);
+			init_waitqueue_func_entry(&monitor->monitor,
+						  cachefiles_read_waiter);
+		}
+
+		for (;;) {
+			backpage = find_get_page(bmapping, netpage->index);
+			if (backpage)
+				goto backing_page_already_present;
+
+			if (!newpage) {
+				newpage = page_cache_alloc_cold(bmapping);
+				if (!newpage)
+					goto nomem;
+			}
+
+			ret = add_to_page_cache(newpage, bmapping,
+						netpage->index, GFP_KERNEL);
+			if (ret == 0)
+				goto installed_new_backing_page;
+			if (ret != -EEXIST)
+				goto nomem;
+		}
+
+		/* we've installed a new backing page, so now we need to add it
+		 * to the LRU list and start it reading */
+	installed_new_backing_page:
+		_debug("- new %p", newpage);
+
+		backpage = newpage;
+		newpage = NULL;
+
+		page_cache_get(backpage);
+		if (!pagevec_add(&lru_pvec, backpage))
+			__pagevec_lru_add_file(&lru_pvec);
+
+	reread_backing_page:
+		ret = bmapping->a_ops->readpage(NULL, backpage);
+		if (ret < 0)
+			goto read_error;
+
+		/* add the netfs page to the pagecache and LRU, and set the
+		 * monitor to transfer the data across */
+	monitor_backing_page:
+		_debug("- monitor add");
+
+		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
+					GFP_KERNEL);
+		if (ret < 0) {
+			if (ret == -EEXIST) {
+				page_cache_release(netpage);
+				continue;
+			}
+			goto nomem;
+		}
+
+		page_cache_get(netpage);
+		if (!pagevec_add(&lru_pvec, netpage))
+			__pagevec_lru_add_file(&lru_pvec);
+
+		/* install a monitor */
+		page_cache_get(netpage);
+		monitor->netfs_page = netpage;
+
+		page_cache_get(backpage);
+		monitor->back_page = backpage;
+		monitor->monitor.private = backpage;
+		add_page_wait_queue(backpage, &monitor->monitor);
+		monitor = NULL;
+
+		/* but the page may have been read before the monitor was
+		 * installed, so the monitor may miss the event - so we have to
+		 * ensure that we do get one in such a case */
+		if (trylock_page(backpage)) {
+			_debug("2unlock %p {%lx}", backpage, backpage->flags);
+			unlock_page(backpage);
+		}
+
+		page_cache_release(backpage);
+		backpage = NULL;
+
+		page_cache_release(netpage);
+		netpage = NULL;
+		continue;
+
+		/* if the backing page is already present, it can be in one of
+		 * three states: read in progress, read failed or read okay */
+	backing_page_already_present:
+		_debug("- present %p", backpage);
+
+		if (PageError(backpage))
+			goto io_error;
+
+		if (PageUptodate(backpage))
+			goto backing_page_already_uptodate;
+
+		_debug("- not ready %p{%lx}", backpage, backpage->flags);
+
+		if (!trylock_page(backpage))
+			goto monitor_backing_page;
+
+		if (PageError(backpage)) {
+			_debug("error %lx", backpage->flags);
+			unlock_page(backpage);
+			goto io_error;
+		}
+
+		if (PageUptodate(backpage))
+			goto backing_page_already_uptodate_unlock;
+
+		/* we've locked a page that's neither up to date nor erroneous,
+		 * so we need to attempt to read it again */
+		goto reread_backing_page;
+
+		/* the backing page is already up to date, attach the netfs
+		 * page to the pagecache and LRU and copy the data across */
+	backing_page_already_uptodate_unlock:
+		_debug("uptodate %lx", backpage->flags);
+		unlock_page(backpage);
+	backing_page_already_uptodate:
+		_debug("- uptodate");
+
+		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
+					GFP_KERNEL);
+		if (ret < 0) {
+			if (ret == -EEXIST) {
+				page_cache_release(netpage);
+				continue;
+			}
+			goto nomem;
+		}
+
+		copy_highpage(netpage, backpage);
+
+		page_cache_release(backpage);
+		backpage = NULL;
+
+		if (!pagevec_add(mark_pvec, netpage))
+			fscache_mark_pages_cached(op, mark_pvec);
+
+		page_cache_get(netpage);
+		if (!pagevec_add(&lru_pvec, netpage))
+			__pagevec_lru_add_file(&lru_pvec);
+
+		fscache_end_io(op, netpage, 0);
+		page_cache_release(netpage);
+		netpage = NULL;
+		continue;
+	}
+
+	netpage = NULL;
+
+	_debug("out");
+
+out:
+	/* tidy up */
+	pagevec_lru_add_file(&lru_pvec);
+
+	if (newpage)
+		page_cache_release(newpage);
+	if (netpage)
+		page_cache_release(netpage);
+	if (backpage)
+		page_cache_release(backpage);
+	if (monitor) {
+		fscache_put_retrieval(op);
+		kfree(monitor);
+	}
+
+	list_for_each_entry_safe(netpage, _n, list, lru) {
+		list_del(&netpage->lru);
+		page_cache_release(netpage);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+
+nomem:
+	_debug("nomem");
+	ret = -ENOMEM;
+	goto out;
+
+read_error:
+	_debug("read error %d", ret);
+	if (ret == -ENOMEM)
+		goto out;
+io_error:
+	cachefiles_io_error_obj(object, "Page read error on backing file");
+	ret = -ENOBUFS;
+	goto out;
+}
+
+/*
+ * read a list of pages from the cache or allocate blocks in which to store
+ * them
+ */
+int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
+				   struct list_head *pages,
+				   unsigned *nr_pages,
+				   gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct list_head backpages;
+	struct pagevec pagevec;
+	struct inode *inode;
+	struct page *page, *_n;
+	unsigned shift, nrbackpages;
+	int ret, ret2, space;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("{OBJ%x,%d},,%d,,",
+	       object->fscache.debug_id, atomic_read(&op->op.usage),
+	       *nr_pages);
+
+	if (!object->backer)
+		return -ENOBUFS;
+
+	space = 1;
+	if (cachefiles_has_space(cache, 0, *nr_pages) < 0)
+		space = 0;
+
+	inode = object->backer->d_inode;
+	ASSERT(S_ISREG(inode->i_mode));
+	ASSERT(inode->i_mapping->a_ops->bmap);
+	ASSERT(inode->i_mapping->a_ops->readpages);
+
+	/* calculate the shift required to use bmap */
+	if (inode->i_sb->s_blocksize > PAGE_SIZE)
+		return -ENOBUFS;
+
+	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
+
+	pagevec_init(&pagevec, 0);
+
+	op->op.flags = FSCACHE_OP_FAST;
+	op->op.processor = cachefiles_read_copier;
+
+	INIT_LIST_HEAD(&backpages);
+	nrbackpages = 0;
+
+	ret = space ? -ENODATA : -ENOBUFS;
+	list_for_each_entry_safe(page, _n, pages, lru) {
+		sector_t block0, block;
+
+		/* we assume the absence or presence of the first block is a
+		 * good enough indication for the page as a whole
+		 * - TODO: don't use bmap() for this as it is _not_ actually
+		 *   good enough for this as it doesn't indicate errors, but
+		 *   it's all we've got for the moment
+		 */
+		block0 = page->index;
+		block0 <<= shift;
+
+		block = inode->i_mapping->a_ops->bmap(inode->i_mapping,
+						      block0);
+		_debug("%llx -> %llx",
+		       (unsigned long long) block0,
+		       (unsigned long long) block);
+
+		if (block) {
+			/* we have data - add it to the list to give to the
+			 * backing fs */
+			list_move(&page->lru, &backpages);
+			(*nr_pages)--;
+			nrbackpages++;
+		} else if (space && pagevec_add(&pagevec, page) == 0) {
+			fscache_mark_pages_cached(op, &pagevec);
+			ret = -ENODATA;
+		}
+	}
+
+	if (pagevec_count(&pagevec) > 0)
+		fscache_mark_pages_cached(op, &pagevec);
+
+	if (list_empty(pages))
+		ret = 0;
+
+	/* submit the apparently valid pages to the backing fs to be read from
+	 * disk */
+	if (nrbackpages > 0) {
+		ret2 = cachefiles_read_backing_file(object, op, &backpages,
+						    &pagevec);
+		if (ret2 == -ENOMEM || ret2 == -EINTR)
+			ret = ret2;
+	}
+
+	if (pagevec_count(&pagevec) > 0)
+		fscache_mark_pages_cached(op, &pagevec);
+
+	_leave(" = %d [nr=%u%s]",
+	       ret, *nr_pages, list_empty(pages) ? " empty" : "");
+	return ret;
+}
+
+/*
+ * allocate a block in the cache in which to store a page
+ * - cache withdrawal is prevented by the caller
+ * - returns -EINTR if interrupted
+ * - returns -ENOMEM if ran out of memory
+ * - returns -ENOBUFS if no buffers can be made available
+ * - returns -ENOBUFS if page is beyond EOF
+ * - otherwise:
+ *   - the metadata will be retained
+ *   - 0 will be returned
+ */
+int cachefiles_allocate_page(struct fscache_retrieval *op,
+			     struct page *page,
+			     gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct pagevec pagevec;
+	int ret;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("%p,{%lx},", object, page->index);
+
+	ret = cachefiles_has_space(cache, 0, 1);
+	if (ret == 0) {
+		pagevec_init(&pagevec, 0);
+		pagevec_add(&pagevec, page);
+		fscache_mark_pages_cached(op, &pagevec);
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * allocate blocks in the cache in which to store a set of pages
+ * - cache withdrawal is prevented by the caller
+ * - returns -EINTR if interrupted
+ * - returns -ENOMEM if ran out of memory
+ * - returns -ENOBUFS if some buffers couldn't be made available
+ * - returns -ENOBUFS if some pages are beyond EOF
+ * - otherwise:
+ *   - -ENODATA will be returned
+ * - metadata will be retained for any page marked
+ */
+int cachefiles_allocate_pages(struct fscache_retrieval *op,
+			      struct list_head *pages,
+			      unsigned *nr_pages,
+			      gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct pagevec pagevec;
+	struct page *page;
+	int ret;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("%p,,,%d,", object, *nr_pages);
+
+	ret = cachefiles_has_space(cache, 0, *nr_pages);
+	if (ret == 0) {
+		pagevec_init(&pagevec, 0);
+
+		list_for_each_entry(page, pages, lru) {
+			if (pagevec_add(&pagevec, page) == 0)
+				fscache_mark_pages_cached(op, &pagevec);
+		}
+
+		if (pagevec_count(&pagevec) > 0)
+			fscache_mark_pages_cached(op, &pagevec);
+		ret = -ENODATA;
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * request a page be stored in the cache
+ * - cache withdrawal is prevented by the caller
+ * - this request may be ignored if there's no cache block available, in which
+ *   case -ENOBUFS will be returned
+ * - if the op is in progress, 0 will be returned
+ */
+int cachefiles_write_page(struct fscache_storage *op, struct page *page)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	mm_segment_t old_fs;
+	struct file *file;
+	loff_t pos;
+	void *data;
+	int ret;
+
+	ASSERT(op != NULL);
+	ASSERT(page != NULL);
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+
+	_enter("%p,%p{%lx},,,", object, page, page->index);
+
+	if (!object->backer) {
+		_leave(" = -ENOBUFS");
+		return -ENOBUFS;
+	}
+
+	ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	/* write the page to the backing filesystem and let it store it in its
+	 * own time */
+	dget(object->backer);
+	mntget(cache->mnt);
+	file = dentry_open(object->backer, cache->mnt, O_RDWR,
+			   cache->cache_cred);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+	} else {
+		ret = -EIO;
+		if (file->f_op->write) {
+			pos = (loff_t) page->index << PAGE_SHIFT;
+			data = kmap(page);
+			old_fs = get_fs();
+			set_fs(KERNEL_DS);
+			ret = file->f_op->write(
+				file, (const void __user *) data, PAGE_SIZE,
+				&pos);
+			set_fs(old_fs);
+			kunmap(page);
+			if (ret != PAGE_SIZE)
+				ret = -EIO;
+		}
+		fput(file);
+	}
+
+	if (ret < 0) {
+		if (ret == -EIO)
+			cachefiles_io_error_obj(
+				object, "Write page to backing file failed");
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * detach a backing block from a page
+ * - cache withdrawal is prevented by the caller
+ */
+void cachefiles_uncache_page(struct fscache_object *_object, struct page *page)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("%p,{%lu}", object, page->index);
+
+	spin_unlock(&object->fscache.cookie->lock);
+}
diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c
new file mode 100644
index 000000000000..b5808cdb2232
--- /dev/null
+++ b/fs/cachefiles/security.c
@@ -0,0 +1,116 @@
+/* CacheFiles security management
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/fs.h>
+#include <linux/cred.h>
+#include "internal.h"
+
+/*
+ * determine the security context within which we access the cache from within
+ * the kernel
+ */
+int cachefiles_get_security_ID(struct cachefiles_cache *cache)
+{
+	struct cred *new;
+	int ret;
+
+	_enter("{%s}", cache->secctx);
+
+	new = prepare_kernel_cred(current);
+	if (!new) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	if (cache->secctx) {
+		ret = set_security_override_from_ctx(new, cache->secctx);
+		if (ret < 0) {
+			put_cred(new);
+			printk(KERN_ERR "CacheFiles:"
+			       " Security denies permission to nominate"
+			       " security context: error %d\n",
+			       ret);
+			goto error;
+		}
+	}
+
+	cache->cache_cred = new;
+	ret = 0;
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * see if mkdir and create can be performed in the root directory
+ */
+static int cachefiles_check_cache_dir(struct cachefiles_cache *cache,
+				      struct dentry *root)
+{
+	int ret;
+
+	ret = security_inode_mkdir(root->d_inode, root, 0);
+	if (ret < 0) {
+		printk(KERN_ERR "CacheFiles:"
+		       " Security denies permission to make dirs: error %d",
+		       ret);
+		return ret;
+	}
+
+	ret = security_inode_create(root->d_inode, root, 0);
+	if (ret < 0)
+		printk(KERN_ERR "CacheFiles:"
+		       " Security denies permission to create files: error %d",
+		       ret);
+
+	return ret;
+}
+
+/*
+ * check the security details of the on-disk cache
+ * - must be called with security override in force
+ */
+int cachefiles_determine_cache_security(struct cachefiles_cache *cache,
+					struct dentry *root,
+					const struct cred **_saved_cred)
+{
+	struct cred *new;
+	int ret;
+
+	_enter("");
+
+	/* duplicate the cache creds for COW (the override is currently in
+	 * force, so we can use prepare_creds() to do this) */
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	cachefiles_end_secure(cache, *_saved_cred);
+
+	/* use the cache root dir's security context as the basis with
+	 * which create files */
+	ret = set_create_files_as(new, root->d_inode);
+	if (ret < 0) {
+		_leave(" = %d [cfa]", ret);
+		return ret;
+	}
+
+	put_cred(cache->cache_cred);
+	cache->cache_cred = new;
+
+	cachefiles_begin_secure(cache, _saved_cred);
+	ret = cachefiles_check_cache_dir(cache, root);
+
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
new file mode 100644
index 000000000000..f3e7a0bf068b
--- /dev/null
+++ b/fs/cachefiles/xattr.c
@@ -0,0 +1,291 @@
+/* CacheFiles extended attribute management
+ *
+ * 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/quotaops.h>
+#include <linux/xattr.h>
+#include "internal.h"
+
+static const char cachefiles_xattr_cache[] =
+	XATTR_USER_PREFIX "CacheFiles.cache";
+
+/*
+ * check the type label on an object
+ * - done using xattrs
+ */
+int cachefiles_check_object_type(struct cachefiles_object *object)
+{
+	struct dentry *dentry = object->dentry;
+	char type[3], xtype[3];
+	int ret;
+
+	ASSERT(dentry);
+	ASSERT(dentry->d_inode);
+
+	if (!object->fscache.cookie)
+		strcpy(type, "C3");
+	else
+		snprintf(type, 3, "%02x", object->fscache.cookie->def->type);
+
+	_enter("%p{%s}", object, type);
+
+	/* attempt to install a type label directly */
+	ret = vfs_setxattr(dentry, cachefiles_xattr_cache, type, 2,
+			   XATTR_CREATE);
+	if (ret == 0) {
+		_debug("SET"); /* we succeeded */
+		goto error;
+	}
+
+	if (ret != -EEXIST) {
+		kerror("Can't set xattr on %*.*s [%lu] (err %d)",
+		       dentry->d_name.len, dentry->d_name.len,
+		       dentry->d_name.name, dentry->d_inode->i_ino,
+		       -ret);
+		goto error;
+	}
+
+	/* read the current type label */
+	ret = vfs_getxattr(dentry, cachefiles_xattr_cache, xtype, 3);
+	if (ret < 0) {
+		if (ret == -ERANGE)
+			goto bad_type_length;
+
+		kerror("Can't read xattr on %*.*s [%lu] (err %d)",
+		       dentry->d_name.len, dentry->d_name.len,
+		       dentry->d_name.name, dentry->d_inode->i_ino,
+		       -ret);
+		goto error;
+	}
+
+	/* check the type is what we're expecting */
+	if (ret != 2)
+		goto bad_type_length;
+
+	if (xtype[0] != type[0] || xtype[1] != type[1])
+		goto bad_type;
+
+	ret = 0;
+
+error:
+	_leave(" = %d", ret);
+	return ret;
+
+bad_type_length:
+	kerror("Cache object %lu type xattr length incorrect",
+	       dentry->d_inode->i_ino);
+	ret = -EIO;
+	goto error;
+
+bad_type:
+	xtype[2] = 0;
+	kerror("Cache object %*.*s [%lu] type %s not %s",
+	       dentry->d_name.len, dentry->d_name.len,
+	       dentry->d_name.name, dentry->d_inode->i_ino,
+	       xtype, type);
+	ret = -EIO;
+	goto error;
+}
+
+/*
+ * set the state xattr on a cache file
+ */
+int cachefiles_set_object_xattr(struct cachefiles_object *object,
+				struct cachefiles_xattr *auxdata)
+{
+	struct dentry *dentry = object->dentry;
+	int ret;
+
+	ASSERT(object->fscache.cookie);
+	ASSERT(dentry);
+
+	_enter("%p,#%d", object, auxdata->len);
+
+	/* attempt to install the cache metadata directly */
+	_debug("SET %s #%u", object->fscache.cookie->def->name, auxdata->len);
+
+	ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
+			   &auxdata->type, auxdata->len,
+			   XATTR_CREATE);
+	if (ret < 0 && ret != -ENOMEM)
+		cachefiles_io_error_obj(
+			object,
+			"Failed to set xattr with error %d", ret);
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * update the state xattr on a cache file
+ */
+int cachefiles_update_object_xattr(struct cachefiles_object *object,
+				   struct cachefiles_xattr *auxdata)
+{
+	struct dentry *dentry = object->dentry;
+	int ret;
+
+	ASSERT(object->fscache.cookie);
+	ASSERT(dentry);
+
+	_enter("%p,#%d", object, auxdata->len);
+
+	/* attempt to install the cache metadata directly */
+	_debug("SET %s #%u", object->fscache.cookie->def->name, auxdata->len);
+
+	ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
+			   &auxdata->type, auxdata->len,
+			   XATTR_REPLACE);
+	if (ret < 0 && ret != -ENOMEM)
+		cachefiles_io_error_obj(
+			object,
+			"Failed to update xattr with error %d", ret);
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * check the state xattr on a cache file
+ * - return -ESTALE if the object should be deleted
+ */
+int cachefiles_check_object_xattr(struct cachefiles_object *object,
+				  struct cachefiles_xattr *auxdata)
+{
+	struct cachefiles_xattr *auxbuf;
+	struct dentry *dentry = object->dentry;
+	int ret;
+
+	_enter("%p,#%d", object, auxdata->len);
+
+	ASSERT(dentry);
+	ASSERT(dentry->d_inode);
+
+	auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
+	if (!auxbuf) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	/* read the current type label */
+	ret = vfs_getxattr(dentry, cachefiles_xattr_cache,
+			   &auxbuf->type, 512 + 1);
+	if (ret < 0) {
+		if (ret == -ENODATA)
+			goto stale; /* no attribute - power went off
+				     * mid-cull? */
+
+		if (ret == -ERANGE)
+			goto bad_type_length;
+
+		cachefiles_io_error_obj(object,
+					"Can't read xattr on %lu (err %d)",
+					dentry->d_inode->i_ino, -ret);
+		goto error;
+	}
+
+	/* check the on-disk object */
+	if (ret < 1)
+		goto bad_type_length;
+
+	if (auxbuf->type != auxdata->type)
+		goto stale;
+
+	auxbuf->len = ret;
+
+	/* consult the netfs */
+	if (object->fscache.cookie->def->check_aux) {
+		enum fscache_checkaux result;
+		unsigned int dlen;
+
+		dlen = auxbuf->len - 1;
+
+		_debug("checkaux %s #%u",
+		       object->fscache.cookie->def->name, dlen);
+
+		result = fscache_check_aux(&object->fscache,
+					   &auxbuf->data, dlen);
+
+		switch (result) {
+			/* entry okay as is */
+		case FSCACHE_CHECKAUX_OKAY:
+			goto okay;
+
+			/* entry requires update */
+		case FSCACHE_CHECKAUX_NEEDS_UPDATE:
+			break;
+
+			/* entry requires deletion */
+		case FSCACHE_CHECKAUX_OBSOLETE:
+			goto stale;
+
+		default:
+			BUG();
+		}
+
+		/* update the current label */
+		ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
+				   &auxdata->type, auxdata->len,
+				   XATTR_REPLACE);
+		if (ret < 0) {
+			cachefiles_io_error_obj(object,
+						"Can't update xattr on %lu"
+						" (error %d)",
+						dentry->d_inode->i_ino, -ret);
+			goto error;
+		}
+	}
+
+okay:
+	ret = 0;
+
+error:
+	kfree(auxbuf);
+	_leave(" = %d", ret);
+	return ret;
+
+bad_type_length:
+	kerror("Cache object %lu xattr length incorrect",
+	       dentry->d_inode->i_ino);
+	ret = -EIO;
+	goto error;
+
+stale:
+	ret = -ESTALE;
+	goto error;
+}
+
+/*
+ * remove the object's xattr to mark it stale
+ */
+int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
+				   struct dentry *dentry)
+{
+	int ret;
+
+	ret = vfs_removexattr(dentry, cachefiles_xattr_cache);
+	if (ret < 0) {
+		if (ret == -ENOENT || ret == -ENODATA)
+			ret = 0;
+		else if (ret != -ENOMEM)
+			cachefiles_io_error(cache,
+					    "Can't remove xattr from %lu"
+					    " (error %d)",
+					    dentry->d_inode->i_ino, -ret);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}