Merge git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.6-fscache

* git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.6-fscache: (41 commits)
  NFS: Add mount options to enable local caching on NFS
  NFS: Display local caching state
  NFS: Store pages from an NFS inode into a local cache
  NFS: Read pages from FS-Cache into an NFS inode
  NFS: nfs_readpage_async() needs to be accessible as a fallback for local caching
  NFS: Add read context retention for FS-Cache to call back with
  NFS: FS-Cache page management
  NFS: Add some new I/O counters for FS-Cache doing things for NFS
  NFS: Invalidate FsCache page flags when cache removed
  NFS: Use local disk inode cache
  NFS: Define and create inode-level cache objects
  NFS: Define and create superblock-level objects
  NFS: Define and create server-level objects
  NFS: Register NFS for caching and retrieve the top-level index
  NFS: Permit local filesystem caching to be enabled for NFS
  NFS: Add FS-Cache option bit and debug bit
  NFS: Add comment banners to some NFS functions
  FS-Cache: Make kAFS use FS-Cache
  CacheFiles: A cache that backs onto a mounted filesystem
  CacheFiles: Export things for CacheFiles
  ...

Documentation/filesystems/caching/backend-api.txt

@@ -0,0 +1,658 @@
+			  ==========================
+			  FS-CACHE CACHE BACKEND API
+			  ==========================
+
+The FS-Cache system provides an API by which actual caches can be supplied to
+FS-Cache for it to then serve out to network filesystems and other interested
+parties.
+
+This API is declared in <linux/fscache-cache.h>.
+
+
+====================================
+INITIALISING AND REGISTERING A CACHE
+====================================
+
+To start off, a cache definition must be initialised and registered for each
+cache the backend wants to make available.  For instance, CacheFS does this in
+the fill_super() operation on mounting.
+
+The cache definition (struct fscache_cache) should be initialised by calling:
+
+	void fscache_init_cache(struct fscache_cache *cache,
+				struct fscache_cache_ops *ops,
+				const char *idfmt,
+				...);
+
+Where:
+
+ (*) "cache" is a pointer to the cache definition;
+
+ (*) "ops" is a pointer to the table of operations that the backend supports on
+     this cache; and
+
+ (*) "idfmt" is a format and printf-style arguments for constructing a label
+     for the cache.
+
+
+The cache should then be registered with FS-Cache by passing a pointer to the
+previously initialised cache definition to:
+
+	int fscache_add_cache(struct fscache_cache *cache,
+			      struct fscache_object *fsdef,
+			      const char *tagname);
+
+Two extra arguments should also be supplied:
+
+ (*) "fsdef" which should point to the object representation for the FS-Cache
+     master index in this cache.  Netfs primary index entries will be created
+     here.  FS-Cache keeps the caller's reference to the index object if
+     successful and will release it upon withdrawal of the cache.
+
+ (*) "tagname" which, if given, should be a text string naming this cache.  If
+     this is NULL, the identifier will be used instead.  For CacheFS, the
+     identifier is set to name the underlying block device and the tag can be
+     supplied by mount.
+
+This function may return -ENOMEM if it ran out of memory or -EEXIST if the tag
+is already in use.  0 will be returned on success.
+
+
+=====================
+UNREGISTERING A CACHE
+=====================
+
+A cache can be withdrawn from the system by calling this function with a
+pointer to the cache definition:
+
+	void fscache_withdraw_cache(struct fscache_cache *cache);
+
+In CacheFS's case, this is called by put_super().
+
+
+========
+SECURITY
+========
+
+The cache methods are executed one of two contexts:
+
+ (1) that of the userspace process that issued the netfs operation that caused
+     the cache method to be invoked, or
+
+ (2) that of one of the processes in the FS-Cache thread pool.
+
+In either case, this may not be an appropriate context in which to access the
+cache.
+
+The calling process's fsuid, fsgid and SELinux security identities may need to
+be masqueraded for the duration of the cache driver's access to the cache.
+This is left to the cache to handle; FS-Cache makes no effort in this regard.
+
+
+===================================
+CONTROL AND STATISTICS PRESENTATION
+===================================
+
+The cache may present data to the outside world through FS-Cache's interfaces
+in sysfs and procfs - the former for control and the latter for statistics.
+
+A sysfs directory called /sys/fs/fscache/<cachetag>/ is created if CONFIG_SYSFS
+is enabled.  This is accessible through the kobject struct fscache_cache::kobj
+and is for use by the cache as it sees fit.
+
+
+========================
+RELEVANT DATA STRUCTURES
+========================
+
+ (*) Index/Data file FS-Cache representation cookie:
+
+	struct fscache_cookie {
+		struct fscache_object_def	*def;
+		struct fscache_netfs		*netfs;
+		void				*netfs_data;
+		...
+	};
+
+     The fields that might be of use to the backend describe the object
+     definition, the netfs definition and the netfs's data for this cookie.
+     The object definition contain functions supplied by the netfs for loading
+     and matching index entries; these are required to provide some of the
+     cache operations.
+
+
+ (*) In-cache object representation:
+
+	struct fscache_object {
+		int				debug_id;
+		enum {
+			FSCACHE_OBJECT_RECYCLING,
+			...
+		}				state;
+		spinlock_t			lock
+		struct fscache_cache		*cache;
+		struct fscache_cookie		*cookie;
+		...
+	};
+
+     Structures of this type should be allocated by the cache backend and
+     passed to FS-Cache when requested by the appropriate cache operation.  In
+     the case of CacheFS, they're embedded in CacheFS's internal object
+     structures.
+
+     The debug_id is a simple integer that can be used in debugging messages
+     that refer to a particular object.  In such a case it should be printed
+     using "OBJ%x" to be consistent with FS-Cache.
+
+     Each object contains a pointer to the cookie that represents the object it
+     is backing.  An object should retired when put_object() is called if it is
+     in state FSCACHE_OBJECT_RECYCLING.  The fscache_object struct should be
+     initialised by calling fscache_object_init(object).
+
+
+ (*) FS-Cache operation record:
+
+	struct fscache_operation {
+		atomic_t		usage;
+		struct fscache_object	*object;
+		unsigned long		flags;
+	#define FSCACHE_OP_EXCLUSIVE
+		void (*processor)(struct fscache_operation *op);
+		void (*release)(struct fscache_operation *op);
+		...
+	};
+
+     FS-Cache has a pool of threads that it uses to give CPU time to the
+     various asynchronous operations that need to be done as part of driving
+     the cache.  These are represented by the above structure.  The processor
+     method is called to give the op CPU time, and the release method to get
+     rid of it when its usage count reaches 0.
+
+     An operation can be made exclusive upon an object by setting the
+     appropriate flag before enqueuing it with fscache_enqueue_operation().  If
+     an operation needs more processing time, it should be enqueued again.
+
+
+ (*) FS-Cache retrieval operation record:
+
+	struct fscache_retrieval {
+		struct fscache_operation op;
+		struct address_space	*mapping;
+		struct list_head	*to_do;
+		...
+	};
+
+     A structure of this type is allocated by FS-Cache to record retrieval and
+     allocation requests made by the netfs.  This struct is then passed to the
+     backend to do the operation.  The backend may get extra refs to it by
+     calling fscache_get_retrieval() and refs may be discarded by calling
+     fscache_put_retrieval().
+
+     A retrieval operation can be used by the backend to do retrieval work.  To
+     do this, the retrieval->op.processor method pointer should be set
+     appropriately by the backend and fscache_enqueue_retrieval() called to
+     submit it to the thread pool.  CacheFiles, for example, uses this to queue
+     page examination when it detects PG_lock being cleared.
+
+     The to_do field is an empty list available for the cache backend to use as
+     it sees fit.
+
+
+ (*) FS-Cache storage operation record:
+
+	struct fscache_storage {
+		struct fscache_operation op;
+		pgoff_t			store_limit;
+		...
+	};
+
+     A structure of this type is allocated by FS-Cache to record outstanding
+     writes to be made.  FS-Cache itself enqueues this operation and invokes
+     the write_page() method on the object at appropriate times to effect
+     storage.
+
+
+================
+CACHE OPERATIONS
+================
+
+The cache backend provides FS-Cache with a table of operations that can be
+performed on the denizens of the cache.  These are held in a structure of type:
+
+	struct fscache_cache_ops
+
+ (*) Name of cache provider [mandatory]:
+
+	const char *name
+
+     This isn't strictly an operation, but should be pointed at a string naming
+     the backend.
+
+
+ (*) Allocate a new object [mandatory]:
+
+	struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+					       struct fscache_cookie *cookie)
+
+     This method is used to allocate a cache object representation to back a
+     cookie in a particular cache.  fscache_object_init() should be called on
+     the object to initialise it prior to returning.
+
+     This function may also be used to parse the index key to be used for
+     multiple lookup calls to turn it into a more convenient form.  FS-Cache
+     will call the lookup_complete() method to allow the cache to release the
+     form once lookup is complete or aborted.
+
+
+ (*) Look up and create object [mandatory]:
+
+	void (*lookup_object)(struct fscache_object *object)
+
+     This method is used to look up an object, given that the object is already
+     allocated and attached to the cookie.  This should instantiate that object
+     in the cache if it can.
+
+     The method should call fscache_object_lookup_negative() as soon as
+     possible if it determines the object doesn't exist in the cache.  If the
+     object is found to exist and the netfs indicates that it is valid then
+     fscache_obtained_object() should be called once the object is in a
+     position to have data stored in it.  Similarly, fscache_obtained_object()
+     should also be called once a non-present object has been created.
+
+     If a lookup error occurs, fscache_object_lookup_error() should be called
+     to abort the lookup of that object.
+
+
+ (*) Release lookup data [mandatory]:
+
+	void (*lookup_complete)(struct fscache_object *object)
+
+     This method is called to ask the cache to release any resources it was
+     using to perform a lookup.
+
+
+ (*) Increment object refcount [mandatory]:
+
+	struct fscache_object *(*grab_object)(struct fscache_object *object)
+
+     This method is called to increment the reference count on an object.  It
+     may fail (for instance if the cache is being withdrawn) by returning NULL.
+     It should return the object pointer if successful.
+
+
+ (*) Lock/Unlock object [mandatory]:
+
+	void (*lock_object)(struct fscache_object *object)
+	void (*unlock_object)(struct fscache_object *object)
+
+     These methods are used to exclusively lock an object.  It must be possible
+     to schedule with the lock held, so a spinlock isn't sufficient.
+
+
+ (*) Pin/Unpin object [optional]:
+
+	int (*pin_object)(struct fscache_object *object)
+	void (*unpin_object)(struct fscache_object *object)
+
+     These methods are used to pin an object into the cache.  Once pinned an
+     object cannot be reclaimed to make space.  Return -ENOSPC if there's not
+     enough space in the cache to permit this.
+
+
+ (*) Update object [mandatory]:
+
+	int (*update_object)(struct fscache_object *object)
+
+     This is called to update the index entry for the specified object.  The
+     new information should be in object->cookie->netfs_data.  This can be
+     obtained by calling object->cookie->def->get_aux()/get_attr().
+
+
+ (*) Discard object [mandatory]:
+
+	void (*drop_object)(struct fscache_object *object)
+
+     This method is called to indicate that an object has been unbound from its
+     cookie, and that the cache should release the object's resources and
+     retire it if it's in state FSCACHE_OBJECT_RECYCLING.
+
+     This method should not attempt to release any references held by the
+     caller.  The caller will invoke the put_object() method as appropriate.
+
+
+ (*) Release object reference [mandatory]:
+
+	void (*put_object)(struct fscache_object *object)
+
+     This method is used to discard a reference to an object.  The object may
+     be freed when all the references to it are released.
+
+
+ (*) Synchronise a cache [mandatory]:
+
+	void (*sync)(struct fscache_cache *cache)
+
+     This is called to ask the backend to synchronise a cache with its backing
+     device.
+
+
+ (*) Dissociate a cache [mandatory]:
+
+	void (*dissociate_pages)(struct fscache_cache *cache)
+
+     This is called to ask a cache to perform any page dissociations as part of
+     cache withdrawal.
+
+
+ (*) Notification that the attributes on a netfs file changed [mandatory]:
+
+	int (*attr_changed)(struct fscache_object *object);
+
+     This is called to indicate to the cache that certain attributes on a netfs
+     file have changed (for example the maximum size a file may reach).  The
+     cache can read these from the netfs by calling the cookie's get_attr()
+     method.
+
+     The cache may use the file size information to reserve space on the cache.
+     It should also call fscache_set_store_limit() to indicate to FS-Cache the
+     highest byte it's willing to store for an object.
+
+     This method may return -ve if an error occurred or the cache object cannot
+     be expanded.  In such a case, the object will be withdrawn from service.
+
+     This operation is run asynchronously from FS-Cache's thread pool, and
+     storage and retrieval operations from the netfs are excluded during the
+     execution of this operation.
+
+
+ (*) Reserve cache space for an object's data [optional]:
+
+	int (*reserve_space)(struct fscache_object *object, loff_t size);
+
+     This is called to request that cache space be reserved to hold the data
+     for an object and the metadata used to track it.  Zero size should be
+     taken as request to cancel a reservation.
+
+     This should return 0 if successful, -ENOSPC if there isn't enough space
+     available, or -ENOMEM or -EIO on other errors.
+
+     The reservation may exceed the current size of the object, thus permitting
+     future expansion.  If the amount of space consumed by an object would
+     exceed the reservation, it's permitted to refuse requests to allocate
+     pages, but not required.  An object may be pruned down to its reservation
+     size if larger than that already.
+
+
+ (*) Request page be read from cache [mandatory]:
+
+	int (*read_or_alloc_page)(struct fscache_retrieval *op,
+				  struct page *page,
+				  gfp_t gfp)
+
+     This is called to attempt to read a netfs page from the cache, or to
+     reserve a backing block if not.  FS-Cache will have done as much checking
+     as it can before calling, but most of the work belongs to the backend.
+
+     If there's no page in the cache, then -ENODATA should be returned if the
+     backend managed to reserve a backing block; -ENOBUFS or -ENOMEM if it
+     didn't.
+
+     If there is suitable data in the cache, then a read operation should be
+     queued and 0 returned.  When the read finishes, fscache_end_io() should be
+     called.
+
+     The fscache_mark_pages_cached() should be called for the page if any cache
+     metadata is retained.  This will indicate to the netfs that the page needs
+     explicit uncaching.  This operation takes a pagevec, thus allowing several
+     pages to be marked at once.
+
+     The retrieval record pointed to by op should be retained for each page
+     queued and released when I/O on the page has been formally ended.
+     fscache_get/put_retrieval() are available for this purpose.
+
+     The retrieval record may be used to get CPU time via the FS-Cache thread
+     pool.  If this is desired, the op->op.processor should be set to point to
+     the appropriate processing routine, and fscache_enqueue_retrieval() should
+     be called at an appropriate point to request CPU time.  For instance, the
+     retrieval routine could be enqueued upon the completion of a disk read.
+     The to_do field in the retrieval record is provided to aid in this.
+
+     If an I/O error occurs, fscache_io_error() should be called and -ENOBUFS
+     returned if possible or fscache_end_io() called with a suitable error
+     code..
+
+
+ (*) Request pages be read from cache [mandatory]:
+
+	int (*read_or_alloc_pages)(struct fscache_retrieval *op,
+				   struct list_head *pages,
+				   unsigned *nr_pages,
+				   gfp_t gfp)
+
+     This is like the read_or_alloc_page() method, except it is handed a list
+     of pages instead of one page.  Any pages on which a read operation is
+     started must be added to the page cache for the specified mapping and also
+     to the LRU.  Such pages must also be removed from the pages list and
+     *nr_pages decremented per page.
+
+     If there was an error such as -ENOMEM, then that should be returned; else
+     if one or more pages couldn't be read or allocated, then -ENOBUFS should
+     be returned; else if one or more pages couldn't be read, then -ENODATA
+     should be returned.  If all the pages are dispatched then 0 should be
+     returned.
+
+
+ (*) Request page be allocated in the cache [mandatory]:
+
+	int (*allocate_page)(struct fscache_retrieval *op,
+			     struct page *page,
+			     gfp_t gfp)
+
+     This is like the read_or_alloc_page() method, except that it shouldn't
+     read from the cache, even if there's data there that could be retrieved.
+     It should, however, set up any internal metadata required such that
+     the write_page() method can write to the cache.
+
+     If there's no backing block available, then -ENOBUFS should be returned
+     (or -ENOMEM if there were other problems).  If a block is successfully
+     allocated, then the netfs page should be marked and 0 returned.
+
+
+ (*) Request pages be allocated in the cache [mandatory]:
+
+	int (*allocate_pages)(struct fscache_retrieval *op,
+			      struct list_head *pages,
+			      unsigned *nr_pages,
+			      gfp_t gfp)
+
+     This is an multiple page version of the allocate_page() method.  pages and
+     nr_pages should be treated as for the read_or_alloc_pages() method.
+
+
+ (*) Request page be written to cache [mandatory]:
+
+	int (*write_page)(struct fscache_storage *op,
+			  struct page *page);
+
+     This is called to write from a page on which there was a previously
+     successful read_or_alloc_page() call or similar.  FS-Cache filters out
+     pages that don't have mappings.
+
+     This method is called asynchronously from the FS-Cache thread pool.  It is
+     not required to actually store anything, provided -ENODATA is then
+     returned to the next read of this page.
+
+     If an error occurred, then a negative error code should be returned,
+     otherwise zero should be returned.  FS-Cache will take appropriate action
+     in response to an error, such as withdrawing this object.
+
+     If this method returns success then FS-Cache will inform the netfs
+     appropriately.
+
+
+ (*) Discard retained per-page metadata [mandatory]:
+
+	void (*uncache_page)(struct fscache_object *object, struct page *page)
+
+     This is called when a netfs page is being evicted from the pagecache.  The
+     cache backend should tear down any internal representation or tracking it
+     maintains for this page.
+
+
+==================
+FS-CACHE UTILITIES
+==================
+
+FS-Cache provides some utilities that a cache backend may make use of:
+
+ (*) Note occurrence of an I/O error in a cache:
+
+	void fscache_io_error(struct fscache_cache *cache)
+
+     This tells FS-Cache that an I/O error occurred in the cache.  After this
+     has been called, only resource dissociation operations (object and page
+     release) will be passed from the netfs to the cache backend for the
+     specified cache.
+
+     This does not actually withdraw the cache.  That must be done separately.
+
+
+ (*) Invoke the retrieval I/O completion function:
+
+	void fscache_end_io(struct fscache_retrieval *op, struct page *page,
+			    int error);
+
+     This is called to note the end of an attempt to retrieve a page.  The
+     error value should be 0 if successful and an error otherwise.
+
+
+ (*) Set highest store limit:
+
+	void fscache_set_store_limit(struct fscache_object *object,
+				     loff_t i_size);
+
+     This sets the limit FS-Cache imposes on the highest byte it's willing to
+     try and store for a netfs.  Any page over this limit is automatically
+     rejected by fscache_read_alloc_page() and co with -ENOBUFS.
+
+
+ (*) Mark pages as being cached:
+
+	void fscache_mark_pages_cached(struct fscache_retrieval *op,
+				       struct pagevec *pagevec);
+
+     This marks a set of pages as being cached.  After this has been called,
+     the netfs must call fscache_uncache_page() to unmark the pages.
+
+
+ (*) Perform coherency check on an object:
+
+	enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+						const void *data,
+						uint16_t datalen);
+
+     This asks the netfs to perform a coherency check on an object that has
+     just been looked up.  The cookie attached to the object will determine the
+     netfs to use.  data and datalen should specify where the auxiliary data
+     retrieved from the cache can be found.
+
+     One of three values will be returned:
+
+	(*) FSCACHE_CHECKAUX_OKAY
+
+	    The coherency data indicates the object is valid as is.
+
+	(*) FSCACHE_CHECKAUX_NEEDS_UPDATE
+
+	    The coherency data needs updating, but otherwise the object is
+	    valid.
+
+	(*) FSCACHE_CHECKAUX_OBSOLETE
+
+	    The coherency data indicates that the object is obsolete and should
+	    be discarded.
+
+
+ (*) Initialise a freshly allocated object:
+
+	void fscache_object_init(struct fscache_object *object);
+
+     This initialises all the fields in an object representation.
+
+
+ (*) Indicate the destruction of an object:
+
+	void fscache_object_destroyed(struct fscache_cache *cache);
+
+     This must be called to inform FS-Cache that an object that belonged to a
+     cache has been destroyed and deallocated.  This will allow continuation
+     of the cache withdrawal process when it is stopped pending destruction of
+     all the objects.
+
+
+ (*) Indicate negative lookup on an object:
+
+	void fscache_object_lookup_negative(struct fscache_object *object);
+
+     This is called to indicate to FS-Cache that a lookup process for an object
+     found a negative result.
+
+     This changes the state of an object to permit reads pending on lookup
+     completion to go off and start fetching data from the netfs server as it's
+     known at this point that there can't be any data in the cache.
+
+     This may be called multiple times on an object.  Only the first call is
+     significant - all subsequent calls are ignored.
+
+
+ (*) Indicate an object has been obtained:
+
+	void fscache_obtained_object(struct fscache_object *object);
+
+     This is called to indicate to FS-Cache that a lookup process for an object
+     produced a positive result, or that an object was created.  This should
+     only be called once for any particular object.
+
+     This changes the state of an object to indicate:
+
+	(1) if no call to fscache_object_lookup_negative() has been made on
+	    this object, that there may be data available, and that reads can
+	    now go and look for it; and
+
+        (2) that writes may now proceed against this object.
+
+
+ (*) Indicate that object lookup failed:
+
+	void fscache_object_lookup_error(struct fscache_object *object);
+
+     This marks an object as having encountered a fatal error (usually EIO)
+     and causes it to move into a state whereby it will be withdrawn as soon
+     as possible.
+
+
+ (*) Get and release references on a retrieval record:
+
+	void fscache_get_retrieval(struct fscache_retrieval *op);
+	void fscache_put_retrieval(struct fscache_retrieval *op);
+
+     These two functions are used to retain a retrieval record whilst doing
+     asynchronous data retrieval and block allocation.
+
+
+ (*) Enqueue a retrieval record for processing.
+
+	void fscache_enqueue_retrieval(struct fscache_retrieval *op);
+
+     This enqueues a retrieval record for processing by the FS-Cache thread
+     pool.  One of the threads in the pool will invoke the retrieval record's
+     op->op.processor callback function.  This function may be called from
+     within the callback function.
+
+
+ (*) List of object state names:
+
+	const char *fscache_object_states[];
+
+     For debugging purposes, this may be used to turn the state that an object
+     is in into a text string for display purposes.

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.

Documentation/filesystems/caching/fscache.txt

@@ -0,0 +1,333 @@
+			  ==========================
+			  General Filesystem Caching
+			  ==========================
+
+========
+OVERVIEW
+========
+
+This facility is a general purpose cache for network filesystems, though it
+could be used for caching other things such as ISO9660 filesystems too.
+
+FS-Cache mediates between cache backends (such as CacheFS) and network
+filesystems:
+
+	+---------+
+	|         |                        +--------------+
+	|   NFS   |--+                     |              |
+	|         |  |                 +-->|   CacheFS    |
+	+---------+  |   +----------+  |   |  /dev/hda5   |
+	             |   |          |  |   +--------------+
+	+---------+  +-->|          |  |
+	|         |      |          |--+
+	|   AFS   |----->| FS-Cache |
+	|         |      |          |--+
+	+---------+  +-->|          |  |
+	             |   |          |  |   +--------------+
+	+---------+  |   +----------+  |   |              |
+	|         |  |                 +-->|  CacheFiles  |
+	|  ISOFS  |--+                     |  /var/cache  |
+	|         |                        +--------------+
+	+---------+
+
+Or to look at it another way, FS-Cache is a module that provides a caching
+facility to a network filesystem such that the cache is transparent to the
+user:
+
+	+---------+
+	|         |
+	| Server  |
+	|         |
+	+---------+
+	     |                  NETWORK
+	~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+	     |
+	     |           +----------+
+	     V           |          |
+	+---------+      |          |
+	|         |      |          |
+	|   NFS   |----->| FS-Cache |
+	|         |      |          |--+
+	+---------+      |          |  |   +--------------+   +--------------+
+	     |           |          |  |   |              |   |              |
+	     V           +----------+  +-->|  CacheFiles  |-->|  Ext3        |
+	+---------+                        |  /var/cache  |   |  /dev/sda6   |
+	|         |                        +--------------+   +--------------+
+	|   VFS   |                                ^                     ^
+	|         |                                |                     |
+	+---------+                                +--------------+      |
+	     |                  KERNEL SPACE                      |      |
+	~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~|~~~~~~|~~~~
+	     |                  USER SPACE                        |      |
+	     V                                                    |      |
+	+---------+                                           +--------------+
+	|         |                                           |              |
+	| Process |                                           | cachefilesd  |
+	|         |                                           |              |
+	+---------+                                           +--------------+
+
+
+FS-Cache does not follow the idea of completely loading every netfs file
+opened in its entirety into a cache before permitting it to be accessed and
+then serving the pages out of that cache rather than the netfs inode because:
+
+ (1) It must be practical to operate without a cache.
+
+ (2) The size of any accessible file must not be limited to the size of the
+     cache.
+
+ (3) The combined size of all opened files (this includes mapped libraries)
+     must not be limited to the size of the cache.
+
+ (4) The user should not be forced to download an entire file just to do a
+     one-off access of a small portion of it (such as might be done with the
+     "file" program).
+
+It instead serves the cache out in PAGE_SIZE chunks as and when requested by
+the netfs('s) using it.
+
+
+FS-Cache provides the following facilities:
+
+ (1) More than one cache can be used at once.  Caches can be selected
+     explicitly by use of tags.
+
+ (2) Caches can be added / removed at any time.
+
+ (3) The netfs is provided with an interface that allows either party to
+     withdraw caching facilities from a file (required for (2)).
+
+ (4) The interface to the netfs returns as few errors as possible, preferring
+     rather to let the netfs remain oblivious.
+
+ (5) Cookies are used to represent indices, files and other objects to the
+     netfs.  The simplest cookie is just a NULL pointer - indicating nothing
+     cached there.
+
+ (6) The netfs is allowed to propose - dynamically - any index hierarchy it
+     desires, though it must be aware that the index search function is
+     recursive, stack space is limited, and indices can only be children of
+     indices.
+
+ (7) Data I/O is done direct to and from the netfs's pages.  The netfs
+     indicates that page A is at index B of the data-file represented by cookie
+     C, and that it should be read or written.  The cache backend may or may
+     not start I/O on that page, but if it does, a netfs callback will be
+     invoked to indicate completion.  The I/O may be either synchronous or
+     asynchronous.
+
+ (8) Cookies can be "retired" upon release.  At this point FS-Cache will mark
+     them as obsolete and the index hierarchy rooted at that point will get
+     recycled.
+
+ (9) The netfs provides a "match" function for index searches.  In addition to
+     saying whether a match was made or not, this can also specify that an
+     entry should be updated or deleted.
+
+(10) As much as possible is done asynchronously.
+
+
+FS-Cache maintains a virtual indexing tree in which all indices, files, objects
+and pages are kept.  Bits of this tree may actually reside in one or more
+caches.
+
+                                           FSDEF
+                                             |
+                        +------------------------------------+
+                        |                                    |
+                       NFS                                  AFS
+                        |                                    |
+           +--------------------------+                +-----------+
+           |                          |                |           |
+        homedir                     mirror          afs.org   redhat.com
+           |                          |                            |
+     +------------+           +---------------+              +----------+
+     |            |           |               |              |          |
+   00001        00002       00007           00125        vol00001   vol00002
+     |            |           |               |                         |
+ +---+---+     +-----+      +---+      +------+------+            +-----+----+
+ |   |   |     |     |      |   |      |      |      |            |     |    |
+PG0 PG1 PG2   PG0  XATTR   PG0 PG1   DIRENT DIRENT DIRENT        R/W   R/O  Bak
+                     |                                            |
+                    PG0                                       +-------+
+                                                              |       |
+                                                            00001   00003
+                                                              |
+                                                          +---+---+
+                                                          |   |   |
+                                                         PG0 PG1 PG2
+
+In the example above, you can see two netfs's being backed: NFS and AFS.  These
+have different index hierarchies:
+
+ (*) The NFS primary index contains per-server indices.  Each server index is
+     indexed by NFS file handles to get data file objects.  Each data file
+     objects can have an array of pages, but may also have further child
+     objects, such as extended attributes and directory entries.  Extended
+     attribute objects themselves have page-array contents.
+
+ (*) The AFS primary index contains per-cell indices.  Each cell index contains
+     per-logical-volume indices.  Each of volume index contains up to three
+     indices for the read-write, read-only and backup mirrors of those volumes.
+     Each of these contains vnode data file objects, each of which contains an
+     array of pages.
+
+The very top index is the FS-Cache master index in which individual netfs's
+have entries.
+
+Any index object may reside in more than one cache, provided it only has index
+children.  Any index with non-index object children will be assumed to only
+reside in one cache.
+
+
+The netfs API to FS-Cache can be found in:
+
+	Documentation/filesystems/caching/netfs-api.txt
+
+The cache backend API to FS-Cache can be found in:
+
+	Documentation/filesystems/caching/backend-api.txt
+
+A description of the internal representations and object state machine can be
+found in:
+
+	Documentation/filesystems/caching/object.txt
+
+
+=======================
+STATISTICAL INFORMATION
+=======================
+
+If FS-Cache is compiled with the following options enabled:
+
+	CONFIG_FSCACHE_STATS=y
+	CONFIG_FSCACHE_HISTOGRAM=y
+
+then it will gather certain statistics and display them through a number of
+proc files.
+
+ (*) /proc/fs/fscache/stats
+
+     This shows counts of a number of events that can happen in FS-Cache:
+
+	CLASS	EVENT	MEANING
+	=======	=======	=======================================================
+	Cookies	idx=N	Number of index cookies allocated
+		dat=N	Number of data storage cookies allocated
+		spc=N	Number of special cookies allocated
+	Objects	alc=N	Number of objects allocated
+		nal=N	Number of object allocation failures
+		avl=N	Number of objects that reached the available state
+		ded=N	Number of objects that reached the dead state
+	ChkAux	non=N	Number of objects that didn't have a coherency check
+		ok=N	Number of objects that passed a coherency check
+		upd=N	Number of objects that needed a coherency data update
+		obs=N	Number of objects that were declared obsolete
+	Pages	mrk=N	Number of pages marked as being cached
+		unc=N	Number of uncache page requests seen
+	Acquire	n=N	Number of acquire cookie requests seen
+		nul=N	Number of acq reqs given a NULL parent
+		noc=N	Number of acq reqs rejected due to no cache available
+		ok=N	Number of acq reqs succeeded
+		nbf=N	Number of acq reqs rejected due to error
+		oom=N	Number of acq reqs failed on ENOMEM
+	Lookups	n=N	Number of lookup calls made on cache backends
+		neg=N	Number of negative lookups made
+		pos=N	Number of positive lookups made
+		crt=N	Number of objects created by lookup
+	Updates	n=N	Number of update cookie requests seen
+		nul=N	Number of upd reqs given a NULL parent
+		run=N	Number of upd reqs granted CPU time
+	Relinqs	n=N	Number of relinquish cookie requests seen
+		nul=N	Number of rlq reqs given a NULL parent
+		wcr=N	Number of rlq reqs waited on completion of creation
+	AttrChg	n=N	Number of attribute changed requests seen
+		ok=N	Number of attr changed requests queued
+		nbf=N	Number of attr changed rejected -ENOBUFS
+		oom=N	Number of attr changed failed -ENOMEM
+		run=N	Number of attr changed ops given CPU time
+	Allocs	n=N	Number of allocation requests seen
+		ok=N	Number of successful alloc reqs
+		wt=N	Number of alloc reqs that waited on lookup completion
+		nbf=N	Number of alloc reqs rejected -ENOBUFS
+		ops=N	Number of alloc reqs submitted
+		owt=N	Number of alloc reqs waited for CPU time
+	Retrvls	n=N	Number of retrieval (read) requests seen
+		ok=N	Number of successful retr reqs
+		wt=N	Number of retr reqs that waited on lookup completion
+		nod=N	Number of retr reqs returned -ENODATA
+		nbf=N	Number of retr reqs rejected -ENOBUFS
+		int=N	Number of retr reqs aborted -ERESTARTSYS
+		oom=N	Number of retr reqs failed -ENOMEM
+		ops=N	Number of retr reqs submitted
+		owt=N	Number of retr reqs waited for CPU time
+	Stores	n=N	Number of storage (write) requests seen
+		ok=N	Number of successful store reqs
+		agn=N	Number of store reqs on a page already pending storage
+		nbf=N	Number of store reqs rejected -ENOBUFS
+		oom=N	Number of store reqs failed -ENOMEM
+		ops=N	Number of store reqs submitted
+		run=N	Number of store reqs granted CPU time
+	Ops	pend=N	Number of times async ops added to pending queues
+		run=N	Number of times async ops given CPU time
+		enq=N	Number of times async ops queued for processing
+		dfr=N	Number of async ops queued for deferred release
+		rel=N	Number of async ops released
+		gc=N	Number of deferred-release async ops garbage collected
+
+
+ (*) /proc/fs/fscache/histogram
+
+	cat /proc/fs/fscache/histogram
+	JIFS  SECS  OBJ INST  OP RUNS   OBJ RUNS  RETRV DLY RETRIEVLS
+	===== ===== ========= ========= ========= ========= =========
+
+     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
+	=======		=======================================================
+	OBJ INST	Length of time to instantiate an object
+	OP RUNS		Length of time a call to process an operation took
+	OBJ RUNS	Length of time a call to process an object event took
+	RETRV DLY	Time between an requesting a read and lookup completing
+	RETRIEVLS	Time between beginning and end of a retrieval
+
+     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_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime
+debugging enabled by adjusting the value in:
+
+	/sys/module/fscache/parameters/debug
+
+This is a bitmask of debugging streams to enable:
+
+	BIT	VALUE	STREAM				POINT
+	=======	=======	===============================	=======================
+	0	1	Cache management		Function entry trace
+	1	2					Function exit trace
+	2	4					General
+	3	8	Cookie management		Function entry trace
+	4	16					Function exit trace
+	5	32					General
+	6	64	Page handling			Function entry trace
+	7	128					Function exit trace
+	8	256					General
+	9	512	Operation management		Function entry trace
+	10	1024					Function exit trace
+	11	2048					General
+
+The appropriate set of values should be OR'd together and the result written to
+the control file.  For example:
+
+	echo $((1|8|64)) >/sys/module/fscache/parameters/debug
+
+will turn on all function entry debugging.

Documentation/filesystems/caching/netfs-api.txt

@@ -0,0 +1,778 @@
+			===============================
+			FS-CACHE NETWORK FILESYSTEM API
+			===============================
+
+There's an API by which a network filesystem can make use of the FS-Cache
+facilities.  This is based around a number of principles:
+
+ (1) Caches can store a number of different object types.  There are two main
+     object types: indices and files.  The first is a special type used by
+     FS-Cache to make finding objects faster and to make retiring of groups of
+     objects easier.
+
+ (2) Every index, file or other object is represented by a cookie.  This cookie
+     may or may not have anything associated with it, but the netfs doesn't
+     need to care.
+
+ (3) Barring the top-level index (one entry per cached netfs), the index
+     hierarchy for each netfs is structured according the whim of the netfs.
+
+This API is declared in <linux/fscache.h>.
+
+This document contains the following sections:
+
+	 (1) Network filesystem definition
+	 (2) Index definition
+	 (3) Object definition
+	 (4) Network filesystem (un)registration
+	 (5) Cache tag lookup
+	 (6) Index registration
+	 (7) Data file registration
+	 (8) Miscellaneous object registration
+	 (9) Setting the data file size
+	(10) Page alloc/read/write
+	(11) Page uncaching
+	(12) Index and data file update
+	(13) Miscellaneous cookie operations
+	(14) Cookie unregistration
+	(15) Index and data file invalidation
+	(16) FS-Cache specific page flags.
+
+
+=============================
+NETWORK FILESYSTEM DEFINITION
+=============================
+
+FS-Cache needs a description of the network filesystem.  This is specified
+using a record of the following structure:
+
+	struct fscache_netfs {
+		uint32_t			version;
+		const char			*name;
+		struct fscache_cookie		*primary_index;
+		...
+	};
+
+This first two fields should be filled in before registration, and the third
+will be filled in by the registration function; any other fields should just be
+ignored and are for internal use only.
+
+The fields are:
+
+ (1) The name of the netfs (used as the key in the toplevel index).
+
+ (2) The version of the netfs (if the name matches but the version doesn't, the
+     entire in-cache hierarchy for this netfs will be scrapped and begun
+     afresh).
+
+ (3) The cookie representing the primary index will be allocated according to
+     another parameter passed into the registration function.
+
+For example, kAFS (linux/fs/afs/) uses the following definitions to describe
+itself:
+
+	struct fscache_netfs afs_cache_netfs = {
+		.version	= 0,
+		.name		= "afs",
+	};
+
+
+================
+INDEX DEFINITION
+================
+
+Indices are used for two purposes:
+
+ (1) To aid the finding of a file based on a series of keys (such as AFS's
+     "cell", "volume ID", "vnode ID").
+
+ (2) To make it easier to discard a subset of all the files cached based around
+     a particular key - for instance to mirror the removal of an AFS volume.
+
+However, since it's unlikely that any two netfs's are going to want to define
+their index hierarchies in quite the same way, FS-Cache tries to impose as few
+restraints as possible on how an index is structured and where it is placed in
+the tree.  The netfs can even mix indices and data files at the same level, but
+it's not recommended.
+
+Each index entry consists of a key of indeterminate length plus some auxilliary
+data, also of indeterminate length.
+
+There are some limits on indices:
+
+ (1) Any index containing non-index objects should be restricted to a single
+     cache.  Any such objects created within an index will be created in the
+     first cache only.  The cache in which an index is created can be
+     controlled by cache tags (see below).
+
+ (2) The entry data must be atomically journallable, so it is limited to about
+     400 bytes at present.  At least 400 bytes will be available.
+
+ (3) The depth of the index tree should be judged with care as the search
+     function is recursive.  Too many layers will run the kernel out of stack.
+
+
+=================
+OBJECT DEFINITION
+=================
+
+To define an object, a structure of the following type should be filled out:
+
+	struct fscache_cookie_def
+	{
+		uint8_t name[16];
+		uint8_t type;
+
+		struct fscache_cache_tag *(*select_cache)(
+			const void *parent_netfs_data,
+			const void *cookie_netfs_data);
+
+		uint16_t (*get_key)(const void *cookie_netfs_data,
+				    void *buffer,
+				    uint16_t bufmax);
+
+		void (*get_attr)(const void *cookie_netfs_data,
+				 uint64_t *size);
+
+		uint16_t (*get_aux)(const void *cookie_netfs_data,
+				    void *buffer,
+				    uint16_t bufmax);
+
+		enum fscache_checkaux (*check_aux)(void *cookie_netfs_data,
+						   const void *data,
+						   uint16_t datalen);
+
+		void (*get_context)(void *cookie_netfs_data, void *context);
+
+		void (*put_context)(void *cookie_netfs_data, void *context);
+
+		void (*mark_pages_cached)(void *cookie_netfs_data,
+					  struct address_space *mapping,
+					  struct pagevec *cached_pvec);
+
+		void (*now_uncached)(void *cookie_netfs_data);
+	};
+
+This has the following fields:
+
+ (1) The type of the object [mandatory].
+
+     This is one of the following values:
+
+	(*) FSCACHE_COOKIE_TYPE_INDEX
+
+	    This defines an index, which is a special FS-Cache type.
+
+	(*) FSCACHE_COOKIE_TYPE_DATAFILE
+
+	    This defines an ordinary data file.
+
+	(*) Any other value between 2 and 255
+
+	    This defines an extraordinary object such as an XATTR.
+
+ (2) The name of the object type (NUL terminated unless all 16 chars are used)
+     [optional].
+
+ (3) A function to select the cache in which to store an index [optional].
+
+     This function is invoked when an index needs to be instantiated in a cache
+     during the instantiation of a non-index object.  Only the immediate index
+     parent for the non-index object will be queried.  Any indices above that
+     in the hierarchy may be stored in multiple caches.  This function does not
+     need to be supplied for any non-index object or any index that will only
+     have index children.
+
+     If this function is not supplied or if it returns NULL then the first
+     cache in the parent's list will be chosed, or failing that, the first
+     cache in the master list.
+
+ (4) A function to retrieve an object's key from the netfs [mandatory].
+
+     This function will be called with the netfs data that was passed to the
+     cookie acquisition function and the maximum length of key data that it may
+     provide.  It should write the required key data into the given buffer and
+     return the quantity it wrote.
+
+ (5) A function to retrieve attribute data from the netfs [optional].
+
+     This function will be called with the netfs data that was passed to the
+     cookie acquisition function.  It should return the size of the file if
+     this is a data file.  The size may be used to govern how much cache must
+     be reserved for this file in the cache.
+
+     If the function is absent, a file size of 0 is assumed.
+
+ (6) A function to retrieve auxilliary data from the netfs [optional].
+
+     This function will be called with the netfs data that was passed to the
+     cookie acquisition function and the maximum length of auxilliary data that
+     it may provide.  It should write the auxilliary data into the given buffer
+     and return the quantity it wrote.
+
+     If this function is absent, the auxilliary data length will be set to 0.
+
+     The length of the auxilliary data buffer may be dependent on the key
+     length.  A netfs mustn't rely on being able to provide more than 400 bytes
+     for both.
+
+ (7) A function to check the auxilliary data [optional].
+
+     This function will be called to check that a match found in the cache for
+     this object is valid.  For instance with AFS it could check the auxilliary
+     data against the data version number returned by the server to determine
+     whether the index entry in a cache is still valid.
+
+     If this function is absent, it will be assumed that matching objects in a
+     cache are always valid.
+
+     If present, the function should return one of the following values:
+
+	(*) FSCACHE_CHECKAUX_OKAY		- the entry is okay as is
+	(*) FSCACHE_CHECKAUX_NEEDS_UPDATE	- the entry requires update
+	(*) FSCACHE_CHECKAUX_OBSOLETE		- the entry should be deleted
+
+     This function can also be used to extract data from the auxilliary data in
+     the cache and copy it into the netfs's structures.
+
+ (8) A pair of functions to manage contexts for the completion callback
+     [optional].
+
+     The cache read/write functions are passed a context which is then passed
+     to the I/O completion callback function.  To ensure this context remains
+     valid until after the I/O completion is called, two functions may be
+     provided: one to get an extra reference on the context, and one to drop a
+     reference to it.
+
+     If the context is not used or is a type of object that won't go out of
+     scope, then these functions are not required.  These functions are not
+     required for indices as indices may not contain data.  These functions may
+     be called in interrupt context and so may not sleep.
+
+ (9) A function to mark a page as retaining cache metadata [optional].
+
+     This is called by the cache to indicate that it is retaining in-memory
+     information for this page and that the netfs should uncache the page when
+     it has finished.  This does not indicate whether there's data on the disk
+     or not.  Note that several pages at once may be presented for marking.
+
+     The PG_fscache bit is set on the pages before this function would be
+     called, so the function need not be provided if this is sufficient.
+
+     This function is not required for indices as they're not permitted data.
+
+(10) A function to unmark all the pages retaining cache metadata [mandatory].
+
+     This is called by FS-Cache to indicate that a backing store is being
+     unbound from a cookie and that all the marks on the pages should be
+     cleared to prevent confusion.  Note that the cache will have torn down all
+     its tracking information so that the pages don't need to be explicitly
+     uncached.
+
+     This function is not required for indices as they're not permitted data.
+
+
+===================================
+NETWORK FILESYSTEM (UN)REGISTRATION
+===================================
+
+The first step is to declare the network filesystem to the cache.  This also
+involves specifying the layout of the primary index (for AFS, this would be the
+"cell" level).
+
+The registration function is:
+
+	int fscache_register_netfs(struct fscache_netfs *netfs);
+
+It just takes a pointer to the netfs definition.  It returns 0 or an error as
+appropriate.
+
+For kAFS, registration is done as follows:
+
+	ret = fscache_register_netfs(&afs_cache_netfs);
+
+The last step is, of course, unregistration:
+
+	void fscache_unregister_netfs(struct fscache_netfs *netfs);
+
+
+================
+CACHE TAG LOOKUP
+================
+
+FS-Cache permits the use of more than one cache.  To permit particular index
+subtrees to be bound to particular caches, the second step is to look up cache
+representation tags.  This step is optional; it can be left entirely up to
+FS-Cache as to which cache should be used.  The problem with doing that is that
+FS-Cache will always pick the first cache that was registered.
+
+To get the representation for a named tag:
+
+	struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name);
+
+This takes a text string as the name and returns a representation of a tag.  It
+will never return an error.  It may return a dummy tag, however, if it runs out
+of memory; this will inhibit caching with this tag.
+
+Any representation so obtained must be released by passing it to this function:
+
+	void fscache_release_cache_tag(struct fscache_cache_tag *tag);
+
+The tag will be retrieved by FS-Cache when it calls the object definition
+operation select_cache().
+
+
+==================
+INDEX REGISTRATION
+==================
+
+The third step is to inform FS-Cache about part of an index hierarchy that can
+be used to locate files.  This is done by requesting a cookie for each index in
+the path to the file:
+
+	struct fscache_cookie *
+	fscache_acquire_cookie(struct fscache_cookie *parent,
+			       const struct fscache_object_def *def,
+			       void *netfs_data);
+
+This function creates an index entry in the index represented by parent,
+filling in the index entry by calling the operations pointed to by def.
+
+Note that this function never returns an error - all errors are handled
+internally.  It may, however, return NULL to indicate no cookie.  It is quite
+acceptable to pass this token back to this function as the parent to another
+acquisition (or even to the relinquish cookie, read page and write page
+functions - see below).
+
+Note also that no indices are actually created in a cache until a non-index
+object needs to be created somewhere down the hierarchy.  Furthermore, an index
+may be created in several different caches independently at different times.
+This is all handled transparently, and the netfs doesn't see any of it.
+
+For example, with AFS, a cell would be added to the primary index.  This index
+entry would have a dependent inode containing a volume location index for the
+volume mappings within this cell:
+
+	cell->cache =
+		fscache_acquire_cookie(afs_cache_netfs.primary_index,
+				       &afs_cell_cache_index_def,
+				       cell);
+
+Then when a volume location was accessed, it would be entered into the cell's
+index and an inode would be allocated that acts as a volume type and hash chain
+combination:
+
+	vlocation->cache =
+		fscache_acquire_cookie(cell->cache,
+				       &afs_vlocation_cache_index_def,
+				       vlocation);
+
+And then a particular flavour of volume (R/O for example) could be added to
+that index, creating another index for vnodes (AFS inode equivalents):
+
+	volume->cache =
+		fscache_acquire_cookie(vlocation->cache,
+				       &afs_volume_cache_index_def,
+				       volume);
+
+
+======================
+DATA FILE REGISTRATION
+======================
+
+The fourth step is to request a data file be created in the cache.  This is
+identical to index cookie acquisition.  The only difference is that the type in
+the object definition should be something other than index type.
+
+	vnode->cache =
+		fscache_acquire_cookie(volume->cache,
+				       &afs_vnode_cache_object_def,
+				       vnode);
+
+
+=================================
+MISCELLANEOUS OBJECT REGISTRATION
+=================================
+
+An optional step is to request an object of miscellaneous type be created in
+the cache.  This is almost identical to index cookie acquisition.  The only
+difference is that the type in the object definition should be something other
+than index type.  Whilst the parent object could be an index, it's more likely
+it would be some other type of object such as a data file.
+
+	xattr->cache =
+		fscache_acquire_cookie(vnode->cache,
+				       &afs_xattr_cache_object_def,
+				       xattr);
+
+Miscellaneous objects might be used to store extended attributes or directory
+entries for example.
+
+
+==========================
+SETTING THE DATA FILE SIZE
+==========================
+
+The fifth step is to set the physical attributes of the file, such as its size.
+This doesn't automatically reserve any space in the cache, but permits the
+cache to adjust its metadata for data tracking appropriately:
+
+	int fscache_attr_changed(struct fscache_cookie *cookie);
+
+The cache will return -ENOBUFS if there is no backing cache or if there is no
+space to allocate any extra metadata required in the cache.  The attributes
+will be accessed with the get_attr() cookie definition operation.
+
+Note that attempts to read or write data pages in the cache over this size may
+be rebuffed with -ENOBUFS.
+
+This operation schedules an attribute adjustment to happen asynchronously at
+some point in the future, and as such, it may happen after the function returns
+to the caller.  The attribute adjustment excludes read and write operations.
+
+
+=====================
+PAGE READ/ALLOC/WRITE
+=====================
+
+And the sixth step is to store and retrieve pages in the cache.  There are
+three functions that are used to do this.
+
+Note:
+
+ (1) A page should not be re-read or re-allocated without uncaching it first.
+
+ (2) A read or allocated page must be uncached when the netfs page is released
+     from the pagecache.
+
+ (3) A page should only be written to the cache if previous read or allocated.
+
+This permits the cache to maintain its page tracking in proper order.
+
+
+PAGE READ
+---------
+
+Firstly, the netfs should ask FS-Cache to examine the caches and read the
+contents cached for a particular page of a particular file if present, or else
+allocate space to store the contents if not:
+
+	typedef
+	void (*fscache_rw_complete_t)(struct page *page,
+				      void *context,
+				      int error);
+
+	int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+				       struct page *page,
+				       fscache_rw_complete_t end_io_func,
+				       void *context,
+				       gfp_t gfp);
+
+The cookie argument must specify a cookie for an object that isn't an index,
+the page specified will have the data loaded into it (and is also used to
+specify the page number), and the gfp argument is used to control how any
+memory allocations made are satisfied.
+
+If the cookie indicates the inode is not cached:
+
+ (1) The function will return -ENOBUFS.
+
+Else if there's a copy of the page resident in the cache:
+
+ (1) The mark_pages_cached() cookie operation will be called on that page.
+
+ (2) The function will submit a request to read the data from the cache's
+     backing device directly into the page specified.
+
+ (3) The function will return 0.
+
+ (4) When the read is complete, end_io_func() will be invoked with:
+
+     (*) The netfs data supplied when the cookie was created.
+
+     (*) The page descriptor.
+
+     (*) The context argument passed to the above function.  This will be
+         maintained with the get_context/put_context functions mentioned above.
+
+     (*) An argument that's 0 on success or negative for an error code.
+
+     If an error occurs, it should be assumed that the page contains no usable
+     data.
+
+     end_io_func() will be called in process context if the read is results in
+     an error, but it might be called in interrupt context if the read is
+     successful.
+
+Otherwise, if there's not a copy available in cache, but the cache may be able
+to store the page:
+
+ (1) The mark_pages_cached() cookie operation will be called on that page.
+
+ (2) A block may be reserved in the cache and attached to the object at the
+     appropriate place.
+
+ (3) The function will return -ENODATA.
+
+This function may also return -ENOMEM or -EINTR, in which case it won't have
+read any data from the cache.
+
+
+PAGE ALLOCATE
+-------------
+
+Alternatively, if there's not expected to be any data in the cache for a page
+because the file has been extended, a block can simply be allocated instead:
+
+	int fscache_alloc_page(struct fscache_cookie *cookie,
+			       struct page *page,
+			       gfp_t gfp);
+
+This is similar to the fscache_read_or_alloc_page() function, except that it
+never reads from the cache.  It will return 0 if a block has been allocated,
+rather than -ENODATA as the other would.  One or the other must be performed
+before writing to the cache.
+
+The mark_pages_cached() cookie operation will be called on the page if
+successful.
+
+
+PAGE WRITE
+----------
+
+Secondly, if the netfs changes the contents of the page (either due to an
+initial download or if a user performs a write), then the page should be
+written back to the cache:
+
+	int fscache_write_page(struct fscache_cookie *cookie,
+			       struct page *page,
+			       gfp_t gfp);
+
+The cookie argument must specify a data file cookie, the page specified should
+contain the data to be written (and is also used to specify the page number),
+and the gfp argument is used to control how any memory allocations made are
+satisfied.
+
+The page must have first been read or allocated successfully and must not have
+been uncached before writing is performed.
+
+If the cookie indicates the inode is not cached then:
+
+ (1) The function will return -ENOBUFS.
+
+Else if space can be allocated in the cache to hold this page:
+
+ (1) PG_fscache_write will be set on the page.
+
+ (2) The function will submit a request to write the data to cache's backing
+     device directly from the page specified.
+
+ (3) The function will return 0.
+
+ (4) When the write is complete PG_fscache_write is cleared on the page and
+     anyone waiting for that bit will be woken up.
+
+Else if there's no space available in the cache, -ENOBUFS will be returned.  It
+is also possible for the PG_fscache_write bit to be cleared when no write took
+place if unforeseen circumstances arose (such as a disk error).
+
+Writing takes place asynchronously.
+
+
+MULTIPLE PAGE READ
+------------------
+
+A facility is provided to read several pages at once, as requested by the
+readpages() address space operation:
+
+	int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+					struct address_space *mapping,
+					struct list_head *pages,
+					int *nr_pages,
+					fscache_rw_complete_t end_io_func,
+					void *context,
+					gfp_t gfp);
+
+This works in a similar way to fscache_read_or_alloc_page(), except:
+
+ (1) Any page it can retrieve data for is removed from pages and nr_pages and
+     dispatched for reading to the disk.  Reads of adjacent pages on disk may
+     be merged for greater efficiency.
+
+ (2) The mark_pages_cached() cookie operation will be called on several pages
+     at once if they're being read or allocated.
+
+ (3) If there was an general error, then that error will be returned.
+
+     Else if some pages couldn't be allocated or read, then -ENOBUFS will be
+     returned.
+
+     Else if some pages couldn't be read but were allocated, then -ENODATA will
+     be returned.
+
+     Otherwise, if all pages had reads dispatched, then 0 will be returned, the
+     list will be empty and *nr_pages will be 0.
+
+ (4) end_io_func will be called once for each page being read as the reads
+     complete.  It will be called in process context if error != 0, but it may
+     be called in interrupt context if there is no error.
+
+Note that a return of -ENODATA, -ENOBUFS or any other error does not preclude
+some of the pages being read and some being allocated.  Those pages will have
+been marked appropriately and will need uncaching.
+
+
+==============
+PAGE UNCACHING
+==============
+
+To uncache a page, this function should be called:
+
+	void fscache_uncache_page(struct fscache_cookie *cookie,
+				  struct page *page);
+
+This function permits the cache to release any in-memory representation it
+might be holding for this netfs page.  This function must be called once for
+each page on which the read or write page functions above have been called to
+make sure the cache's in-memory tracking information gets torn down.
+
+Note that pages can't be explicitly deleted from the a data file.  The whole
+data file must be retired (see the relinquish cookie function below).
+
+Furthermore, note that this does not cancel the asynchronous read or write
+operation started by the read/alloc and write functions, so the page
+invalidation and release functions must use:
+
+	bool fscache_check_page_write(struct fscache_cookie *cookie,
+				      struct page *page);
+
+to see if a page is being written to the cache, and:
+
+	void fscache_wait_on_page_write(struct fscache_cookie *cookie,
+					struct page *page);
+
+to wait for it to finish if it is.
+
+
+==========================
+INDEX AND DATA FILE UPDATE
+==========================
+
+To request an update of the index data for an index or other object, the
+following function should be called:
+
+	void fscache_update_cookie(struct fscache_cookie *cookie);
+
+This function will refer back to the netfs_data pointer stored in the cookie by
+the acquisition function to obtain the data to write into each revised index
+entry.  The update method in the parent index definition will be called to
+transfer the data.
+
+Note that partial updates may happen automatically at other times, such as when
+data blocks are added to a data file object.
+
+
+===============================
+MISCELLANEOUS COOKIE OPERATIONS
+===============================
+
+There are a number of operations that can be used to control cookies:
+
+ (*) Cookie pinning:
+
+	int fscache_pin_cookie(struct fscache_cookie *cookie);
+	void fscache_unpin_cookie(struct fscache_cookie *cookie);
+
+     These operations permit data cookies to be pinned into the cache and to
+     have the pinning removed.  They are not permitted on index cookies.
+
+     The pinning function will return 0 if successful, -ENOBUFS in the cookie
+     isn't backed by a cache, -EOPNOTSUPP if the cache doesn't support pinning,
+     -ENOSPC if there isn't enough space to honour the operation, -ENOMEM or
+     -EIO if there's any other problem.
+
+ (*) Data space reservation:
+
+	int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size);
+
+     This permits a netfs to request cache space be reserved to store up to the
+     given amount of a file.  It is permitted to ask for more than the current
+     size of the file to allow for future file expansion.
+
+     If size is given as zero then the reservation will be cancelled.
+
+     The function will return 0 if successful, -ENOBUFS in the cookie isn't
+     backed by a cache, -EOPNOTSUPP if the cache doesn't support reservations,
+     -ENOSPC if there isn't enough space to honour the operation, -ENOMEM or
+     -EIO if there's any other problem.
+
+     Note that this doesn't pin an object in a cache; it can still be culled to
+     make space if it's not in use.
+
+
+=====================
+COOKIE UNREGISTRATION
+=====================
+
+To get rid of a cookie, this function should be called.
+
+	void fscache_relinquish_cookie(struct fscache_cookie *cookie,
+				       int retire);
+
+If retire is non-zero, then the object will be marked for recycling, and all
+copies of it will be removed from all active caches in which it is present.
+Not only that but all child objects will also be retired.
+
+If retire is zero, then the object may be available again when next the
+acquisition function is called.  Retirement here will overrule the pinning on a
+cookie.
+
+One very important note - relinquish must NOT be called for a cookie unless all
+the cookies for "child" indices, objects and pages have been relinquished
+first.
+
+
+================================
+INDEX AND DATA FILE INVALIDATION
+================================
+
+There is no direct way to invalidate an index subtree or a data file.  To do
+this, the caller should relinquish and retire the cookie they have, and then
+acquire a new one.
+
+
+===========================
+FS-CACHE SPECIFIC PAGE FLAG
+===========================
+
+FS-Cache makes use of a page flag, PG_private_2, for its own purpose.  This is
+given the alternative name PG_fscache.
+
+PG_fscache is used to indicate that the page is known by the cache, and that
+the cache must be informed if the page is going to go away.  It's an indication
+to the netfs that the cache has an interest in this page, where an interest may
+be a pointer to it, resources allocated or reserved for it, or I/O in progress
+upon it.
+
+The netfs can use this information in methods such as releasepage() to
+determine whether it needs to uncache a page or update it.
+
+Furthermore, if this bit is set, releasepage() and invalidatepage() operations
+will be called on a page to get rid of it, even if PG_private is not set.  This
+allows caching to attempted on a page before read_cache_pages() to be called
+after fscache_read_or_alloc_pages() as the former will try and release pages it
+was given under certain circumstances.
+
+This bit does not overlap with such as PG_private.  This means that FS-Cache
+can be used with a filesystem that uses the block buffering code.
+
+There are a number of operations defined on this flag:
+
+	int PageFsCache(struct page *page);
+	void SetPageFsCache(struct page *page)
+	void ClearPageFsCache(struct page *page)
+	int TestSetPageFsCache(struct page *page)
+	int TestClearPageFsCache(struct page *page)
+
+These functions are bit test, bit set, bit clear, bit test and set and bit
+test and clear operations on PG_fscache.

Documentation/filesystems/caching/object.txt

@@ -0,0 +1,313 @@
+	     ====================================================
+	     IN-KERNEL CACHE OBJECT REPRESENTATION AND MANAGEMENT
+	     ====================================================
+
+By: David Howells <dhowells@redhat.com>
+
+Contents:
+
+ (*) Representation
+
+ (*) Object management state machine.
+
+     - Provision of cpu time.
+     - Locking simplification.
+
+ (*) The set of states.
+
+ (*) The set of events.
+
+
+==============
+REPRESENTATION
+==============
+
+FS-Cache maintains an in-kernel representation of each object that a netfs is
+currently interested in.  Such objects are represented by the fscache_cookie
+struct and are referred to as cookies.
+
+FS-Cache also maintains a separate in-kernel representation of the objects that
+a cache backend is currently actively caching.  Such objects are represented by
+the fscache_object struct.  The cache backends allocate these upon request, and
+are expected to embed them in their own representations.  These are referred to
+as objects.
+
+There is a 1:N relationship between cookies and objects.  A cookie may be
+represented by multiple objects - an index may exist in more than one cache -
+or even by no objects (it may not be cached).
+
+Furthermore, both cookies and objects are hierarchical.  The two hierarchies
+correspond, but the cookies tree is a superset of the union of the object trees
+of multiple caches:
+
+	    NETFS INDEX TREE               :      CACHE 1     :      CACHE 2
+	                                   :                  :
+	                                   :   +-----------+  :
+	                          +----------->|  IObject  |  :
+	      +-----------+       |        :   +-----------+  :
+	      |  ICookie  |-------+        :         |        :
+	      +-----------+       |        :         |        :   +-----------+
+	            |             +------------------------------>|  IObject  |
+	            |                      :         |        :   +-----------+
+	            |                      :         V        :         |
+	            |                      :   +-----------+  :         |
+	            V             +----------->|  IObject  |  :         |
+	      +-----------+       |        :   +-----------+  :         |
+	      |  ICookie  |-------+        :         |        :         V
+	      +-----------+       |        :         |        :   +-----------+
+	            |             +------------------------------>|  IObject  |
+	      +-----+-----+                :         |        :   +-----------+
+	      |           |                :         |        :         |
+	      V           |                :         V        :         |
+	+-----------+     |                :   +-----------+  :         |
+	|  ICookie  |------------------------->|  IObject  |  :         |
+	+-----------+     |                :   +-----------+  :         |
+	      |           V                :         |        :         V
+	      |     +-----------+          :         |        :   +-----------+
+	      |     |  ICookie  |-------------------------------->|  IObject  |
+	      |     +-----------+          :         |        :   +-----------+
+	      V           |                :         V        :         |
+	+-----------+     |                :   +-----------+  :         |
+	|  DCookie  |------------------------->|  DObject  |  :         |
+	+-----------+     |                :   +-----------+  :         |
+	                  |                :                  :         |
+	          +-------+-------+        :                  :         |
+	          |               |        :                  :         |
+	          V               V        :                  :         V
+	    +-----------+   +-----------+  :                  :   +-----------+
+	    |  DCookie  |   |  DCookie  |------------------------>|  DObject  |
+	    +-----------+   +-----------+  :                  :   +-----------+
+	                                   :                  :
+
+In the above illustration, ICookie and IObject represent indices and DCookie
+and DObject represent data storage objects.  Indices may have representation in
+multiple caches, but currently, non-index objects may not.  Objects of any type
+may also be entirely unrepresented.
+
+As far as the netfs API goes, the netfs is only actually permitted to see
+pointers to the cookies.  The cookies themselves and any objects attached to
+those cookies are hidden from it.
+
+
+===============================
+OBJECT MANAGEMENT STATE MACHINE
+===============================
+
+Within FS-Cache, each active object is managed by its own individual state
+machine.  The state for an object is kept in the fscache_object struct, in
+object->state.  A cookie may point to a set of objects that are in different
+states.
+
+Each state has an action associated with it that is invoked when the machine
+wakes up in that state.  There are four logical sets of states:
+
+ (1) Preparation: states that wait for the parent objects to become ready.  The
+     representations are hierarchical, and it is expected that an object must
+     be created or accessed with respect to its parent object.
+
+ (2) Initialisation: states that perform lookups in the cache and validate
+     what's found and that create on disk any missing metadata.
+
+ (3) Normal running: states that allow netfs operations on objects to proceed
+     and that update the state of objects.
+
+ (4) Termination: states that detach objects from their netfs cookies, that
+     delete objects from disk, that handle disk and system errors and that free
+     up in-memory resources.
+
+
+In most cases, transitioning between states is in response to signalled events.
+When a state has finished processing, it will usually set the mask of events in
+which it is interested (object->event_mask) and relinquish the worker thread.
+Then when an event is raised (by calling fscache_raise_event()), if the event
+is not masked, the object will be queued for processing (by calling
+fscache_enqueue_object()).
+
+
+PROVISION OF CPU TIME
+---------------------
+
+The work to be done by the various states is given CPU time by the threads of
+the slow work facility (see Documentation/slow-work.txt).  This is used in
+preference to the workqueue facility because:
+
+ (1) Threads may be completely occupied for very long periods of time by a
+     particular work item.  These state actions may be doing sequences of
+     synchronous, journalled disk accesses (lookup, mkdir, create, setxattr,
+     getxattr, truncate, unlink, rmdir, rename).
+
+ (2) Threads may do little actual work, but may rather spend a lot of time
+     sleeping on I/O.  This means that single-threaded and 1-per-CPU-threaded
+     workqueues don't necessarily have the right numbers of threads.
+
+
+LOCKING SIMPLIFICATION
+----------------------
+
+Because only one worker thread may be operating on any particular object's
+state machine at once, this simplifies the locking, particularly with respect
+to disconnecting the netfs's representation of a cache object (fscache_cookie)
+from the cache backend's representation (fscache_object) - which may be
+requested from either end.
+
+
+=================
+THE SET OF STATES
+=================
+
+The object state machine has a set of states that it can be in.  There are
+preparation states in which the object sets itself up and waits for its parent
+object to transit to a state that allows access to its children:
+
+ (1) State FSCACHE_OBJECT_INIT.
+
+     Initialise the object and wait for the parent object to become active.  In
+     the cache, it is expected that it will not be possible to look an object
+     up from the parent object, until that parent object itself has been looked
+     up.
+
+There are initialisation states in which the object sets itself up and accesses
+disk for the object metadata:
+
+ (2) State FSCACHE_OBJECT_LOOKING_UP.
+
+     Look up the object on disk, using the parent as a starting point.
+     FS-Cache expects the cache backend to probe the cache to see whether this
+     object is represented there, and if it is, to see if it's valid (coherency
+     management).
+
+     The cache should call fscache_object_lookup_negative() to indicate lookup
+     failure for whatever reason, and should call fscache_obtained_object() to
+     indicate success.
+
+     At the completion of lookup, FS-Cache will let the netfs go ahead with
+     read operations, no matter whether the file is yet cached.  If not yet
+     cached, read operations will be immediately rejected with ENODATA until
+     the first known page is uncached - as to that point there can be no data
+     to be read out of the cache for that file that isn't currently also held
+     in the pagecache.
+
+ (3) State FSCACHE_OBJECT_CREATING.
+
+     Create an object on disk, using the parent as a starting point.  This
+     happens if the lookup failed to find the object, or if the object's
+     coherency data indicated what's on disk is out of date.  In this state,
+     FS-Cache expects the cache to create
+
+     The cache should call fscache_obtained_object() if creation completes
+     successfully, fscache_object_lookup_negative() otherwise.
+
+     At the completion of creation, FS-Cache will start processing write
+     operations the netfs has queued for an object.  If creation failed, the
+     write ops will be transparently discarded, and nothing recorded in the
+     cache.
+
+There are some normal running states in which the object spends its time
+servicing netfs requests:
+
+ (4) State FSCACHE_OBJECT_AVAILABLE.
+
+     A transient state in which pending operations are started, child objects
+     are permitted to advance from FSCACHE_OBJECT_INIT state, and temporary
+     lookup data is freed.
+
+ (5) State FSCACHE_OBJECT_ACTIVE.
+
+     The normal running state.  In this state, requests the netfs makes will be
+     passed on to the cache.
+
+ (6) State FSCACHE_OBJECT_UPDATING.
+
+     The state machine comes here to update the object in the cache from the
+     netfs's records.  This involves updating the auxiliary data that is used
+     to maintain coherency.
+
+And there are terminal states in which an object cleans itself up, deallocates
+memory and potentially deletes stuff from disk:
+
+ (7) State FSCACHE_OBJECT_LC_DYING.
+
+     The object comes here if it is dying because of a lookup or creation
+     error.  This would be due to a disk error or system error of some sort.
+     Temporary data is cleaned up, and the parent is released.
+
+ (8) State FSCACHE_OBJECT_DYING.
+
+     The object comes here if it is dying due to an error, because its parent
+     cookie has been relinquished by the netfs or because the cache is being
+     withdrawn.
+
+     Any child objects waiting on this one are given CPU time so that they too
+     can destroy themselves.  This object waits for all its children to go away
+     before advancing to the next state.
+
+ (9) State FSCACHE_OBJECT_ABORT_INIT.
+
+     The object comes to this state if it was waiting on its parent in
+     FSCACHE_OBJECT_INIT, but its parent died.  The object will destroy itself
+     so that the parent may proceed from the FSCACHE_OBJECT_DYING state.
+
+(10) State FSCACHE_OBJECT_RELEASING.
+(11) State FSCACHE_OBJECT_RECYCLING.
+
+     The object comes to one of these two states when dying once it is rid of
+     all its children, if it is dying because the netfs relinquished its
+     cookie.  In the first state, the cached data is expected to persist, and
+     in the second it will be deleted.
+
+(12) State FSCACHE_OBJECT_WITHDRAWING.
+
+     The object transits to this state if the cache decides it wants to
+     withdraw the object from service, perhaps to make space, but also due to
+     error or just because the whole cache is being withdrawn.
+
+(13) State FSCACHE_OBJECT_DEAD.
+
+     The object transits to this state when the in-memory object record is
+     ready to be deleted.  The object processor shouldn't ever see an object in
+     this state.
+
+
+THE SET OF EVENTS
+-----------------
+
+There are a number of events that can be raised to an object state machine:
+
+ (*) FSCACHE_OBJECT_EV_UPDATE
+
+     The netfs requested that an object be updated.  The state machine will ask
+     the cache backend to update the object, and the cache backend will ask the
+     netfs for details of the change through its cookie definition ops.
+
+ (*) FSCACHE_OBJECT_EV_CLEARED
+
+     This is signalled in two circumstances:
+
+     (a) when an object's last child object is dropped and
+
+     (b) when the last operation outstanding on an object is completed.
+
+     This is used to proceed from the dying state.
+
+ (*) FSCACHE_OBJECT_EV_ERROR
+
+     This is signalled when an I/O error occurs during the processing of some
+     object.
+
+ (*) FSCACHE_OBJECT_EV_RELEASE
+ (*) FSCACHE_OBJECT_EV_RETIRE
+
+     These are signalled when the netfs relinquishes a cookie it was using.
+     The event selected depends on whether the netfs asks for the backing
+     object to be retired (deleted) or retained.
+
+ (*) FSCACHE_OBJECT_EV_WITHDRAW
+
+     This is signalled when the cache backend wants to withdraw an object.
+     This means that the object will have to be detached from the netfs's
+     cookie.
+
+Because the withdrawing releasing/retiring events are all handled by the object
+state machine, it doesn't matter if there's a collision with both ends trying
+to sever the connection at the same time.  The state machine can just pick
+which one it wants to honour, and that effects the other.

Documentation/filesystems/caching/operations.txt

@@ -0,0 +1,213 @@
+		       ================================
+		       ASYNCHRONOUS OPERATIONS HANDLING
+		       ================================
+
+By: David Howells <dhowells@redhat.com>
+
+Contents:
+
+ (*) Overview.
+
+ (*) Operation record initialisation.
+
+ (*) Parameters.
+
+ (*) Procedure.
+
+ (*) Asynchronous callback.
+
+
+========
+OVERVIEW
+========
+
+FS-Cache has an asynchronous operations handling facility that it uses for its
+data storage and retrieval routines.  Its operations are represented by
+fscache_operation structs, though these are usually embedded into some other
+structure.
+
+This facility is available to and expected to be be used by the cache backends,
+and FS-Cache will create operations and pass them off to the appropriate cache
+backend for completion.
+
+To make use of this facility, <linux/fscache-cache.h> should be #included.
+
+
+===============================
+OPERATION RECORD INITIALISATION
+===============================
+
+An operation is recorded in an fscache_operation struct:
+
+	struct fscache_operation {
+		union {
+			struct work_struct fast_work;
+			struct slow_work slow_work;
+		};
+		unsigned long		flags;
+		fscache_operation_processor_t processor;
+		...
+	};
+
+Someone wanting to issue an operation should allocate something with this
+struct embedded in it.  They should initialise it by calling:
+
+	void fscache_operation_init(struct fscache_operation *op,
+				    fscache_operation_release_t release);
+
+with the operation to be initialised and the release function to use.
+
+The op->flags parameter should be set to indicate the CPU time provision and
+the exclusivity (see the Parameters section).
+
+The op->fast_work, op->slow_work and op->processor flags should be set as
+appropriate for the CPU time provision (see the Parameters section).
+
+FSCACHE_OP_WAITING may be set in op->flags prior to each submission of the
+operation and waited for afterwards.
+
+
+==========
+PARAMETERS
+==========
+
+There are a number of parameters that can be set in the operation record's flag
+parameter.  There are three options for the provision of CPU time in these
+operations:
+
+ (1) The operation may be done synchronously (FSCACHE_OP_MYTHREAD).  A thread
+     may decide it wants to handle an operation itself without deferring it to
+     another thread.
+
+     This is, for example, used in read operations for calling readpages() on
+     the backing filesystem in CacheFiles.  Although readpages() does an
+     asynchronous data fetch, the determination of whether pages exist is done
+     synchronously - and the netfs does not proceed until this has been
+     determined.
+
+     If this option is to be used, FSCACHE_OP_WAITING must be set in op->flags
+     before submitting the operation, and the operating thread must wait for it
+     to be cleared before proceeding:
+
+		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+
+
+ (2) The operation may be fast asynchronous (FSCACHE_OP_FAST), in which case it
+     will be given to keventd to process.  Such an operation is not permitted
+     to sleep on I/O.
+
+     This is, for example, used by CacheFiles to copy data from a backing fs
+     page to a netfs page after the backing fs has read the page in.
+
+     If this option is used, op->fast_work and op->processor must be
+     initialised before submitting the operation:
+
+		INIT_WORK(&op->fast_work, do_some_work);
+
+
+ (3) The operation may be slow asynchronous (FSCACHE_OP_SLOW), in which case it
+     will be given to the slow work facility to process.  Such an operation is
+     permitted to sleep on I/O.
+
+     This is, for example, used by FS-Cache to handle background writes of
+     pages that have just been fetched from a remote server.
+
+     If this option is used, op->slow_work and op->processor must be
+     initialised before submitting the operation:
+
+		fscache_operation_init_slow(op, processor)
+
+
+Furthermore, operations may be one of two types:
+
+ (1) Exclusive (FSCACHE_OP_EXCLUSIVE).  Operations of this type may not run in
+     conjunction with any other operation on the object being operated upon.
+
+     An example of this is the attribute change operation, in which the file
+     being written to may need truncation.
+
+ (2) Shareable.  Operations of this type may be running simultaneously.  It's
+     up to the operation implementation to prevent interference between other
+     operations running at the same time.
+
+
+=========
+PROCEDURE
+=========
+
+Operations are used through the following procedure:
+
+ (1) The submitting thread must allocate the operation and initialise it
+     itself.  Normally this would be part of a more specific structure with the
+     generic op embedded within.
+
+ (2) The submitting thread must then submit the operation for processing using
+     one of the following two functions:
+
+	int fscache_submit_op(struct fscache_object *object,
+			      struct fscache_operation *op);
+
+	int fscache_submit_exclusive_op(struct fscache_object *object,
+					struct fscache_operation *op);
+
+     The first function should be used to submit non-exclusive ops and the
+     second to submit exclusive ones.  The caller must still set the
+     FSCACHE_OP_EXCLUSIVE flag.
+
+     If successful, both functions will assign the operation to the specified
+     object and return 0.  -ENOBUFS will be returned if the object specified is
+     permanently unavailable.
+
+     The operation manager will defer operations on an object that is still
+     undergoing lookup or creation.  The operation will also be deferred if an
+     operation of conflicting exclusivity is in progress on the object.
+
+     If the operation is asynchronous, the manager will retain a reference to
+     it, so the caller should put their reference to it by passing it to:
+
+	void fscache_put_operation(struct fscache_operation *op);
+
+ (3) If the submitting thread wants to do the work itself, and has marked the
+     operation with FSCACHE_OP_MYTHREAD, then it should monitor
+     FSCACHE_OP_WAITING as described above and check the state of the object if
+     necessary (the object might have died whilst the thread was waiting).
+
+     When it has finished doing its processing, it should call
+     fscache_put_operation() on it.
+
+ (4) The operation holds an effective lock upon the object, preventing other
+     exclusive ops conflicting until it is released.  The operation can be
+     enqueued for further immediate asynchronous processing by adjusting the
+     CPU time provisioning option if necessary, eg:
+
+	op->flags &= ~FSCACHE_OP_TYPE;
+	op->flags |= ~FSCACHE_OP_FAST;
+
+     and calling:
+
+	void fscache_enqueue_operation(struct fscache_operation *op)
+
+     This can be used to allow other things to have use of the worker thread
+     pools.
+
+
+=====================
+ASYNCHRONOUS CALLBACK
+=====================
+
+When used in asynchronous mode, the worker thread pool will invoke the
+processor method with a pointer to the operation.  This should then get at the
+container struct by using container_of():
+
+	static void fscache_write_op(struct fscache_operation *_op)
+	{
+		struct fscache_storage *op =
+			container_of(_op, struct fscache_storage, op);
+	...
+	}
+
+The caller holds a reference on the operation, and will invoke
+fscache_put_operation() when the processor function returns.  The processor
+function is at liberty to call fscache_enqueue_operation() or to take extra
+references.

Documentation/slow-work.txt

@@ -0,0 +1,174 @@
+		     ====================================
+		     SLOW WORK ITEM EXECUTION THREAD POOL
+		     ====================================
+
+By: David Howells <dhowells@redhat.com>
+
+The slow work item execution thread pool is a pool of threads for performing
+things that take a relatively long time, such as making mkdir calls.
+Typically, when processing something, these items will spend a lot of time
+blocking a thread on I/O, thus making that thread unavailable for doing other
+work.
+
+The standard workqueue model is unsuitable for this class of work item as that
+limits the owner to a single thread or a single thread per CPU.  For some
+tasks, however, more threads - or fewer - are required.
+
+There is just one pool per system.  It contains no threads unless something
+wants to use it - and that something must register its interest first.  When
+the pool is active, the number of threads it contains is dynamic, varying
+between a maximum and minimum setting, depending on the load.
+
+
+====================
+CLASSES OF WORK ITEM
+====================
+
+This pool support two classes of work items:
+
+ (*) Slow work items.
+
+ (*) Very slow work items.
+
+The former are expected to finish much quicker than the latter.
+
+An operation of the very slow class may do a batch combination of several
+lookups, mkdirs, and a create for instance.
+
+An operation of the ordinarily slow class may, for example, write stuff or
+expand files, provided the time taken to do so isn't too long.
+
+Operations of both types may sleep during execution, thus tying up the thread
+loaned to it.
+
+
+THREAD-TO-CLASS ALLOCATION
+--------------------------
+
+Not all the threads in the pool are available to work on very slow work items.
+The number will be between one and one fewer than the number of active threads.
+This is configurable (see the "Pool Configuration" section).
+
+All the threads are available to work on ordinarily slow work items, but a
+percentage of the threads will prefer to work on very slow work items.
+
+The configuration ensures that at least one thread will be available to work on
+very slow work items, and at least one thread will be available that won't work
+on very slow work items at all.
+
+
+=====================
+USING SLOW WORK ITEMS
+=====================
+
+Firstly, a module or subsystem wanting to make use of slow work items must
+register its interest:
+
+	 int ret = slow_work_register_user();
+
+This will return 0 if successful, or a -ve error upon failure.
+
+
+Slow work items may then be set up by:
+
+ (1) Declaring a slow_work struct type variable:
+
+	#include <linux/slow-work.h>
+
+	struct slow_work myitem;
+
+ (2) Declaring the operations to be used for this item:
+
+	struct slow_work_ops myitem_ops = {
+		.get_ref = myitem_get_ref,
+		.put_ref = myitem_put_ref,
+		.execute = myitem_execute,
+	};
+
+     [*] For a description of the ops, see section "Item Operations".
+
+ (3) Initialising the item:
+
+	slow_work_init(&myitem, &myitem_ops);
+
+     or:
+
+	vslow_work_init(&myitem, &myitem_ops);
+
+     depending on its class.
+
+A suitably set up work item can then be enqueued for processing:
+
+	int ret = slow_work_enqueue(&myitem);
+
+This will return a -ve error if the thread pool is unable to gain a reference
+on the item, 0 otherwise.
+
+
+The items are reference counted, so there ought to be no need for a flush
+operation.  When all a module's slow work items have been processed, and the
+module has no further interest in the facility, it should unregister its
+interest:
+
+	slow_work_unregister_user();
+
+
+===============
+ITEM OPERATIONS
+===============
+
+Each work item requires a table of operations of type struct slow_work_ops.
+All members are required:
+
+ (*) Get a reference on an item:
+
+	int (*get_ref)(struct slow_work *work);
+
+     This allows the thread pool to attempt to pin an item by getting a
+     reference on it.  This function should return 0 if the reference was
+     granted, or a -ve error otherwise.  If an error is returned,
+     slow_work_enqueue() will fail.
+
+     The reference is held whilst the item is queued and whilst it is being
+     executed.  The item may then be requeued with the same reference held, or
+     the reference will be released.
+
+ (*) Release a reference on an item:
+
+	void (*put_ref)(struct slow_work *work);
+
+     This allows the thread pool to unpin an item by releasing the reference on
+     it.  The thread pool will not touch the item again once this has been
+     called.
+
+ (*) Execute an item:
+
+	void (*execute)(struct slow_work *work);
+
+     This should perform the work required of the item.  It may sleep, it may
+     perform disk I/O and it may wait for locks.
+
+
+==================
+POOL CONFIGURATION
+==================
+
+The slow-work thread pool has a number of configurables:
+
+ (*) /proc/sys/kernel/slow-work/min-threads
+
+     The minimum number of threads that should be in the pool whilst it is in
+     use.  This may be anywhere between 2 and max-threads.
+
+ (*) /proc/sys/kernel/slow-work/max-threads
+
+     The maximum number of threads that should in the pool.  This may be
+     anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater.
+
+ (*) /proc/sys/kernel/slow-work/vslow-percentage
+
+     The percentage of active threads in the pool that may be used to execute
+     very slow work items.  This may be between 1 and 99.  The resultant number
+     is bounded to between 1 and one fewer than the number of active threads.
+     This ensures there is always at least one thread that can process very
+     slow work items, and always at least one thread that won't.

fs/Kconfig

@@ -66,6 +66,13 @@ config GENERIC_ACL
 	bool
 	select FS_POSIX_ACL
 
+menu "Caches"
+
+source "fs/fscache/Kconfig"
+source "fs/cachefiles/Kconfig"
+
+endmenu
+
 if BLOCK
 menu "CD-ROM/DVD Filesystems"
 

fs/Makefile

@@ -63,6 +63,7 @@ obj-$(CONFIG_PROFILING)		+= dcookies.o
 obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
+obj-$(CONFIG_FSCACHE)		+= fscache/
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
 obj-$(CONFIG_EXT2_FS)		+= ext2/
@@ -116,6 +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/

fs/afs/Kconfig

@@ -19,3 +19,11 @@ config AFS_DEBUG
 	  See <file:Documentation/filesystems/afs.txt> for more information.
 
 	  If unsure, say N.
+
+config AFS_FSCACHE
+	bool "Provide AFS client caching support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on AFS_FS=m && FSCACHE || AFS_FS=y && FSCACHE=y
+	help
+	  Say Y here if you want AFS data to be cached locally on disk through
+	  the generic filesystem cache manager

fs/afs/Makefile

@@ -2,7 +2,10 @@
 # Makefile for Red Hat Linux AFS client.
 #
 
+afs-cache-$(CONFIG_AFS_FSCACHE) := cache.o
+
 kafs-objs := \
+	$(afs-cache-y) \
 	callback.o \
 	cell.o \
 	cmservice.o \

fs/afs/cache.c

@@ -1,6 +1,6 @@
 /* AFS caching stuff
  *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -9,248 +9,395 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_cell_cache_match(void *target,
-						const void *entry);
-static void afs_cell_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_cache_cell_index_def = {
-	.name			= "cell_ix",
-	.data_size		= sizeof(struct afs_cache_cell),
-	.keys[0]		= { CACHEFS_INDEX_KEYS_ASCIIZ, 64 },
-	.match			= afs_cell_cache_match,
-	.update			= afs_cell_cache_update,
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include "internal.h"
+
+static uint16_t afs_cell_cache_get_key(const void *cookie_netfs_data,
+				       void *buffer, uint16_t buflen);
+static uint16_t afs_cell_cache_get_aux(const void *cookie_netfs_data,
+				       void *buffer, uint16_t buflen);
+static enum fscache_checkaux afs_cell_cache_check_aux(void *cookie_netfs_data,
+						      const void *buffer,
+						      uint16_t buflen);
+
+static uint16_t afs_vlocation_cache_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t buflen);
+static uint16_t afs_vlocation_cache_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t buflen);
+static enum fscache_checkaux afs_vlocation_cache_check_aux(
+	void *cookie_netfs_data, const void *buffer, uint16_t buflen);
+
+static uint16_t afs_volume_cache_get_key(const void *cookie_netfs_data,
+					 void *buffer, uint16_t buflen);
+
+static uint16_t afs_vnode_cache_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t buflen);
+static void afs_vnode_cache_get_attr(const void *cookie_netfs_data,
+				     uint64_t *size);
+static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
+					void *buffer, uint16_t buflen);
+static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
+						       const void *buffer,
+						       uint16_t buflen);
+static void afs_vnode_cache_now_uncached(void *cookie_netfs_data);
+
+struct fscache_netfs afs_cache_netfs = {
+	.name			= "afs",
+	.version		= 0,
+};
+
+struct fscache_cookie_def afs_cell_cache_index_def = {
+	.name		= "AFS.cell",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= afs_cell_cache_get_key,
+	.get_aux	= afs_cell_cache_get_aux,
+	.check_aux	= afs_cell_cache_check_aux,
+};
+
+struct fscache_cookie_def afs_vlocation_cache_index_def = {
+	.name			= "AFS.vldb",
+	.type			= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key		= afs_vlocation_cache_get_key,
+	.get_aux		= afs_vlocation_cache_get_aux,
+	.check_aux		= afs_vlocation_cache_check_aux,
+};
+
+struct fscache_cookie_def afs_volume_cache_index_def = {
+	.name		= "AFS.volume",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= afs_volume_cache_get_key,
+};
+
+struct fscache_cookie_def afs_vnode_cache_index_def = {
+	.name			= "AFS.vnode",
+	.type			= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key		= afs_vnode_cache_get_key,
+	.get_attr		= afs_vnode_cache_get_attr,
+	.get_aux		= afs_vnode_cache_get_aux,
+	.check_aux		= afs_vnode_cache_check_aux,
+	.now_uncached		= afs_vnode_cache_now_uncached,
 };
-#endif
 
 /*
- * match a cell record obtained from the cache
+ * set the key for the index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_cell_cache_match(void *target,
-						const void *entry)
+static uint16_t afs_cell_cache_get_key(const void *cookie_netfs_data,
+				       void *buffer, uint16_t bufmax)
 {
-	const struct afs_cache_cell *ccell = entry;
-	struct afs_cell *cell = target;
+	const struct afs_cell *cell = cookie_netfs_data;
+	uint16_t klen;
 
-	_enter("{%s},{%s}", ccell->name, cell->name);
+	_enter("%p,%p,%u", cell, buffer, bufmax);
 
-	if (strncmp(ccell->name, cell->name, sizeof(ccell->name)) == 0) {
-		_leave(" = SUCCESS");
-		return CACHEFS_MATCH_SUCCESS;
-	}
+	klen = strlen(cell->name);
+	if (klen > bufmax)
+		return 0;
 
-	_leave(" = FAILED");
-	return CACHEFS_MATCH_FAILED;
+	memcpy(buffer, cell->name, klen);
+	return klen;
 }
-#endif
 
 /*
- * update a cell record in the cache
+ * provide new auxilliary cache data
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_cell_cache_update(void *source, void *entry)
+static uint16_t afs_cell_cache_get_aux(const void *cookie_netfs_data,
+				       void *buffer, uint16_t bufmax)
 {
-	struct afs_cache_cell *ccell = entry;
-	struct afs_cell *cell = source;
+	const struct afs_cell *cell = cookie_netfs_data;
+	uint16_t dlen;
 
-	_enter("%p,%p", source, entry);
+	_enter("%p,%p,%u", cell, buffer, bufmax);
 
-	strncpy(ccell->name, cell->name, sizeof(ccell->name));
+	dlen = cell->vl_naddrs * sizeof(cell->vl_addrs[0]);
+	dlen = min(dlen, bufmax);
+	dlen &= ~(sizeof(cell->vl_addrs[0]) - 1);
 
-	memcpy(ccell->vl_servers,
-	       cell->vl_addrs,
-	       min(sizeof(ccell->vl_servers), sizeof(cell->vl_addrs)));
+	memcpy(buffer, cell->vl_addrs, dlen);
+	return dlen;
+}
 
+/*
+ * check that the auxilliary data indicates that the entry is still valid
+ */
+static enum fscache_checkaux afs_cell_cache_check_aux(void *cookie_netfs_data,
+						      const void *buffer,
+						      uint16_t buflen)
+{
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
 }
-#endif
-
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vlocation_cache_match(void *target,
-						     const void *entry);
-static void afs_vlocation_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_vlocation_cache_index_def = {
-	.name		= "vldb",
-	.data_size	= sizeof(struct afs_cache_vlocation),
-	.keys[0]	= { CACHEFS_INDEX_KEYS_ASCIIZ, 64 },
-	.match		= afs_vlocation_cache_match,
-	.update		= afs_vlocation_cache_update,
-};
-#endif
 
+/*****************************************************************************/
 /*
- * match a VLDB record stored in the cache
- * - may also load target from entry
+ * set the key for the index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vlocation_cache_match(void *target,
-						     const void *entry)
+static uint16_t afs_vlocation_cache_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
 {
-	const struct afs_cache_vlocation *vldb = entry;
-	struct afs_vlocation *vlocation = target;
+	const struct afs_vlocation *vlocation = cookie_netfs_data;
+	uint16_t klen;
+
+	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, bufmax);
+
+	klen = strnlen(vlocation->vldb.name, sizeof(vlocation->vldb.name));
+	if (klen > bufmax)
+		return 0;
 
-	_enter("{%s},{%s}", vlocation->vldb.name, vldb->name);
+	memcpy(buffer, vlocation->vldb.name, klen);
 
-	if (strncmp(vlocation->vldb.name, vldb->name, sizeof(vldb->name)) == 0
-	    ) {
-		if (!vlocation->valid ||
-		    vlocation->vldb.rtime == vldb->rtime
+	_leave(" = %u", klen);
+	return klen;
+}
+
+/*
+ * provide new auxilliary cache data
+ */
+static uint16_t afs_vlocation_cache_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct afs_vlocation *vlocation = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, bufmax);
+
+	dlen = sizeof(struct afs_cache_vlocation);
+	dlen -= offsetof(struct afs_cache_vlocation, nservers);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, (uint8_t *)&vlocation->vldb.nservers, dlen);
+
+	_leave(" = %u", dlen);
+	return dlen;
+}
+
+/*
+ * check that the auxilliary data indicates that the entry is still valid
+ */
+static
+enum fscache_checkaux afs_vlocation_cache_check_aux(void *cookie_netfs_data,
+						    const void *buffer,
+						    uint16_t buflen)
+{
+	const struct afs_cache_vlocation *cvldb;
+	struct afs_vlocation *vlocation = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, buflen);
+
+	/* check the size of the data is what we're expecting */
+	dlen = sizeof(struct afs_cache_vlocation);
+	dlen -= offsetof(struct afs_cache_vlocation, nservers);
+	if (dlen != buflen)
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	cvldb = container_of(buffer, struct afs_cache_vlocation, nservers);
+
+	/* if what's on disk is more valid than what's in memory, then use the
+	 * VL record from the cache */
+	if (!vlocation->valid || vlocation->vldb.rtime == cvldb->rtime) {
+		memcpy((uint8_t *)&vlocation->vldb.nservers, buffer, dlen);
+		vlocation->valid = 1;
+		_leave(" = SUCCESS [c->m]");
+		return FSCACHE_CHECKAUX_OKAY;
+	}
+
+	/* need to update the cache if the cached info differs */
+	if (memcmp(&vlocation->vldb, buffer, dlen) != 0) {
+		/* delete if the volume IDs for this name differ */
+		if (memcmp(&vlocation->vldb.vid, &cvldb->vid,
+			   sizeof(cvldb->vid)) != 0
 		    ) {
-			vlocation->vldb = *vldb;
-			vlocation->valid = 1;
-			_leave(" = SUCCESS [c->m]");
-			return CACHEFS_MATCH_SUCCESS;
-		} else if (memcmp(&vlocation->vldb, vldb, sizeof(*vldb)) != 0) {
-			/* delete if VIDs for this name differ */
-			if (memcmp(&vlocation->vldb.vid,
-				   &vldb->vid,
-				   sizeof(vldb->vid)) != 0) {
-				_leave(" = DELETE");
-				return CACHEFS_MATCH_SUCCESS_DELETE;
-			}
-
-			_leave(" = UPDATE");
-			return CACHEFS_MATCH_SUCCESS_UPDATE;
-		} else {
-			_leave(" = SUCCESS");
-			return CACHEFS_MATCH_SUCCESS;
+			_leave(" = OBSOLETE");
+			return FSCACHE_CHECKAUX_OBSOLETE;
 		}
+
+		_leave(" = UPDATE");
+		return FSCACHE_CHECKAUX_NEEDS_UPDATE;
 	}
 
-	_leave(" = FAILED");
-	return CACHEFS_MATCH_FAILED;
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
 }
-#endif
 
+/*****************************************************************************/
 /*
- * update a VLDB record stored in the cache
+ * set the key for the volume index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_vlocation_cache_update(void *source, void *entry)
+static uint16_t afs_volume_cache_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
 {
-	struct afs_cache_vlocation *vldb = entry;
-	struct afs_vlocation *vlocation = source;
+	const struct afs_volume *volume = cookie_netfs_data;
+	uint16_t klen;
+
+	_enter("{%u},%p,%u", volume->type, buffer, bufmax);
+
+	klen = sizeof(volume->type);
+	if (klen > bufmax)
+		return 0;
 
-	_enter("");
+	memcpy(buffer, &volume->type, sizeof(volume->type));
+
+	_leave(" = %u", klen);
+	return klen;
 
-	*vldb = vlocation->vldb;
 }
-#endif
-
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_volume_cache_match(void *target,
-						  const void *entry);
-static void afs_volume_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_volume_cache_index_def = {
-	.name		= "volume",
-	.data_size	= sizeof(struct afs_cache_vhash),
-	.keys[0]	= { CACHEFS_INDEX_KEYS_BIN, 1 },
-	.keys[1]	= { CACHEFS_INDEX_KEYS_BIN, 1 },
-	.match		= afs_volume_cache_match,
-	.update		= afs_volume_cache_update,
-};
-#endif
 
+/*****************************************************************************/
 /*
- * match a volume hash record stored in the cache
+ * set the key for the index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_volume_cache_match(void *target,
-						  const void *entry)
+static uint16_t afs_vnode_cache_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
 {
-	const struct afs_cache_vhash *vhash = entry;
-	struct afs_volume *volume = target;
+	const struct afs_vnode *vnode = cookie_netfs_data;
+	uint16_t klen;
 
-	_enter("{%u},{%u}", volume->type, vhash->vtype);
+	_enter("{%x,%x,%llx},%p,%u",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
+	       buffer, bufmax);
 
-	if (volume->type == vhash->vtype) {
-		_leave(" = SUCCESS");
-		return CACHEFS_MATCH_SUCCESS;
-	}
+	klen = sizeof(vnode->fid.vnode);
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, &vnode->fid.vnode, sizeof(vnode->fid.vnode));
 
-	_leave(" = FAILED");
-	return CACHEFS_MATCH_FAILED;
+	_leave(" = %u", klen);
+	return klen;
 }
-#endif
 
 /*
- * update a volume hash record stored in the cache
+ * provide updated file attributes
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_volume_cache_update(void *source, void *entry)
+static void afs_vnode_cache_get_attr(const void *cookie_netfs_data,
+				     uint64_t *size)
 {
-	struct afs_cache_vhash *vhash = entry;
-	struct afs_volume *volume = source;
+	const struct afs_vnode *vnode = cookie_netfs_data;
 
-	_enter("");
+	_enter("{%x,%x,%llx},",
+	       vnode->fid.vnode, vnode->fid.unique,
+	       vnode->status.data_version);
 
-	vhash->vtype = volume->type;
+	*size = vnode->status.size;
 }
-#endif
-
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vnode_cache_match(void *target,
-						 const void *entry);
-static void afs_vnode_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_vnode_cache_index_def = {
-	.name		= "vnode",
-	.data_size	= sizeof(struct afs_cache_vnode),
-	.keys[0]	= { CACHEFS_INDEX_KEYS_BIN, 4 },
-	.match		= afs_vnode_cache_match,
-	.update		= afs_vnode_cache_update,
-};
-#endif
 
 /*
- * match a vnode record stored in the cache
+ * provide new auxilliary cache data
+ */
+static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
+{
+	const struct afs_vnode *vnode = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%x,%x,%Lx},%p,%u",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
+	       buffer, bufmax);
+
+	dlen = sizeof(vnode->fid.unique) + sizeof(vnode->status.data_version);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, &vnode->fid.unique, sizeof(vnode->fid.unique));
+	buffer += sizeof(vnode->fid.unique);
+	memcpy(buffer, &vnode->status.data_version,
+	       sizeof(vnode->status.data_version));
+
+	_leave(" = %u", dlen);
+	return dlen;
+}
+
+/*
+ * check that the auxilliary data indicates that the entry is still valid
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vnode_cache_match(void *target,
-						 const void *entry)
+static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
+						       const void *buffer,
+						       uint16_t buflen)
 {
-	const struct afs_cache_vnode *cvnode = entry;
-	struct afs_vnode *vnode = target;
-
-	_enter("{%x,%x,%Lx},{%x,%x,%Lx}",
-	       vnode->fid.vnode,
-	       vnode->fid.unique,
-	       vnode->status.version,
-	       cvnode->vnode_id,
-	       cvnode->vnode_unique,
-	       cvnode->data_version);
-
-	if (vnode->fid.vnode != cvnode->vnode_id) {
-		_leave(" = FAILED");
-		return CACHEFS_MATCH_FAILED;
+	struct afs_vnode *vnode = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%x,%x,%llx},%p,%u",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
+	       buffer, buflen);
+
+	/* check the size of the data is what we're expecting */
+	dlen = sizeof(vnode->fid.unique) + sizeof(vnode->status.data_version);
+	if (dlen != buflen) {
+		_leave(" = OBSOLETE [len %hx != %hx]", dlen, buflen);
+		return FSCACHE_CHECKAUX_OBSOLETE;
 	}
 
-	if (vnode->fid.unique != cvnode->vnode_unique ||
-	    vnode->status.version != cvnode->data_version) {
-		_leave(" = DELETE");
-		return CACHEFS_MATCH_SUCCESS_DELETE;
+	if (memcmp(buffer,
+		   &vnode->fid.unique,
+		   sizeof(vnode->fid.unique)
+		   ) != 0) {
+		unsigned unique;
+
+		memcpy(&unique, buffer, sizeof(unique));
+
+		_leave(" = OBSOLETE [uniq %x != %x]",
+		       unique, vnode->fid.unique);
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	if (memcmp(buffer + sizeof(vnode->fid.unique),
+		   &vnode->status.data_version,
+		   sizeof(vnode->status.data_version)
+		   ) != 0) {
+		afs_dataversion_t version;
+
+		memcpy(&version, buffer + sizeof(vnode->fid.unique),
+		       sizeof(version));
+
+		_leave(" = OBSOLETE [vers %llx != %llx]",
+		       version, vnode->status.data_version);
+		return FSCACHE_CHECKAUX_OBSOLETE;
 	}
 
 	_leave(" = SUCCESS");
-	return CACHEFS_MATCH_SUCCESS;
+	return FSCACHE_CHECKAUX_OKAY;
 }
-#endif
 
 /*
- * update a vnode record stored in the cache
+ * indication the cookie is no longer uncached
+ * - this function is called when the backing store currently caching a cookie
+ *   is removed
+ * - the netfs should use this to clean up any markers indicating cached pages
+ * - this is mandatory for any object that may have data
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_vnode_cache_update(void *source, void *entry)
+static void afs_vnode_cache_now_uncached(void *cookie_netfs_data)
 {
-	struct afs_cache_vnode *cvnode = entry;
-	struct afs_vnode *vnode = source;
+	struct afs_vnode *vnode = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	_enter("{%x,%x,%Lx}",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version);
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	for (;;) {
+		/* grab a bunch of pages to clean */
+		nr_pages = pagevec_lookup(&pvec, vnode->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
 
-	_enter("");
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
 
-	cvnode->vnode_id	= vnode->fid.vnode;
-	cvnode->vnode_unique	= vnode->fid.unique;
-	cvnode->data_version	= vnode->status.version;
+	_leave("");
 }
-#endif

fs/afs/cache.h

@@ -1,6 +1,6 @@
 /* AFS local cache management interface
  *
- * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -9,15 +9,4 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#ifndef AFS_CACHE_H
-#define AFS_CACHE_H
-
-#undef AFS_CACHING_SUPPORT
-
-#include <linux/mm.h>
-#ifdef AFS_CACHING_SUPPORT
-#include <linux/cachefs.h>
-#endif
-#include "types.h"
-
-#endif /* AFS_CACHE_H */
+#include <linux/fscache.h>

fs/afs/cell.c

@@ -147,12 +147,11 @@ struct afs_cell *afs_cell_create(const char *name, char *vllist)
 	if (ret < 0)
 		goto error;
 
-#ifdef AFS_CACHING_SUPPORT
-	/* put it up for caching */
-	cachefs_acquire_cookie(afs_cache_netfs.primary_index,
-			       &afs_vlocation_cache_index_def,
-			       cell,
-			       &cell->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	/* put it up for caching (this never returns an error) */
+	cell->cache = fscache_acquire_cookie(afs_cache_netfs.primary_index,
+					     &afs_cell_cache_index_def,
+					     cell);
 #endif
 
 	/* add to the cell lists */
@@ -362,10 +361,9 @@ static void afs_cell_destroy(struct afs_cell *cell)
 	list_del_init(&cell->proc_link);
 	up_write(&afs_proc_cells_sem);
 
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(cell->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(cell->cache, 0);
 #endif
-
 	key_put(cell->anonymous_key);
 	kfree(cell);
 

fs/afs/file.c

@@ -23,6 +23,9 @@ static void afs_invalidatepage(struct page *page, unsigned long offset);
 static int afs_releasepage(struct page *page, gfp_t gfp_flags);
 static int afs_launder_page(struct page *page);
 
+static int afs_readpages(struct file *filp, struct address_space *mapping,
+			 struct list_head *pages, unsigned nr_pages);
+
 const struct file_operations afs_file_operations = {
 	.open		= afs_open,
 	.release	= afs_release,
@@ -46,6 +49,7 @@ const struct inode_operations afs_file_inode_operations = {
 
 const struct address_space_operations afs_fs_aops = {
 	.readpage	= afs_readpage,
+	.readpages	= afs_readpages,
 	.set_page_dirty	= afs_set_page_dirty,
 	.launder_page	= afs_launder_page,
 	.releasepage	= afs_releasepage,
@@ -101,37 +105,18 @@ int afs_release(struct inode *inode, struct file *file)
 /*
  * deal with notification that a page was read from the cache
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_readpage_read_complete(void *cookie_data,
-				       struct page *page,
-				       void *data,
-				       int error)
+static void afs_file_readpage_read_complete(struct page *page,
+					    void *data,
+					    int error)
 {
-	_enter("%p,%p,%p,%d", cookie_data, page, data, error);
+	_enter("%p,%p,%d", page, data, error);
 
-	if (error)
-		SetPageError(page);
-	else
+	/* if the read completes with an error, we just unlock the page and let
+	 * the VM reissue the readpage */
+	if (!error)
 		SetPageUptodate(page);
 	unlock_page(page);
-
 }
-#endif
-
-/*
- * deal with notification that a page was written to the cache
- */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_readpage_write_complete(void *cookie_data,
-					struct page *page,
-					void *data,
-					int error)
-{
-	_enter("%p,%p,%p,%d", cookie_data, page, data, error);
-
-	unlock_page(page);
-}
-#endif
 
 /*
  * AFS read page from file, directory or symlink
@@ -161,9 +146,9 @@ static int afs_readpage(struct file *file, struct page *page)
 	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
 		goto error;
 
-#ifdef AFS_CACHING_SUPPORT
 	/* is it cached? */
-	ret = cachefs_read_or_alloc_page(vnode->cache,
+#ifdef CONFIG_AFS_FSCACHE
+	ret = fscache_read_or_alloc_page(vnode->cache,
 					 page,
 					 afs_file_readpage_read_complete,
 					 NULL,
@@ -171,20 +156,21 @@ static int afs_readpage(struct file *file, struct page *page)
 #else
 	ret = -ENOBUFS;
 #endif
-
 	switch (ret) {
-		/* read BIO submitted and wb-journal entry found */
-	case 1:
-		BUG(); // TODO - handle wb-journal match
-
 		/* read BIO submitted (page in cache) */
 	case 0:
 		break;
 
-		/* no page available in cache */
-	case -ENOBUFS:
+		/* page not yet cached */
 	case -ENODATA:
+		_debug("cache said ENODATA");
+		goto go_on;
+
+		/* page will not be cached */
+	case -ENOBUFS:
+		_debug("cache said ENOBUFS");
 	default:
+	go_on:
 		offset = page->index << PAGE_CACHE_SHIFT;
 		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
 
@@ -198,27 +184,25 @@ static int afs_readpage(struct file *file, struct page *page)
 				set_bit(AFS_VNODE_DELETED, &vnode->flags);
 				ret = -ESTALE;
 			}
-#ifdef AFS_CACHING_SUPPORT
-			cachefs_uncache_page(vnode->cache, page);
+
+#ifdef CONFIG_AFS_FSCACHE
+			fscache_uncache_page(vnode->cache, page);
 #endif
+			BUG_ON(PageFsCache(page));
 			goto error;
 		}
 
 		SetPageUptodate(page);
 
-#ifdef AFS_CACHING_SUPPORT
-		if (cachefs_write_page(vnode->cache,
-				       page,
-				       afs_file_readpage_write_complete,
-				       NULL,
-				       GFP_KERNEL) != 0
-		    ) {
-			cachefs_uncache_page(vnode->cache, page);
-			unlock_page(page);
+		/* send the page to the cache */
+#ifdef CONFIG_AFS_FSCACHE
+		if (PageFsCache(page) &&
+		    fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
+			fscache_uncache_page(vnode->cache, page);
+			BUG_ON(PageFsCache(page));
 		}
-#else
-		unlock_page(page);
 #endif
+		unlock_page(page);
 	}
 
 	_leave(" = 0");
@@ -232,34 +216,59 @@ error:
 }
 
 /*
- * invalidate part or all of a page
+ * read a set of pages
  */
-static void afs_invalidatepage(struct page *page, unsigned long offset)
+static int afs_readpages(struct file *file, struct address_space *mapping,
+			 struct list_head *pages, unsigned nr_pages)
 {
-	int ret = 1;
+	struct afs_vnode *vnode;
+	int ret = 0;
 
-	_enter("{%lu},%lu", page->index, offset);
+	_enter(",{%lu},,%d", mapping->host->i_ino, nr_pages);
 
-	BUG_ON(!PageLocked(page));
+	vnode = AFS_FS_I(mapping->host);
+	if (vnode->flags & AFS_VNODE_DELETED) {
+		_leave(" = -ESTALE");
+		return -ESTALE;
+	}
 
-	if (PagePrivate(page)) {
-		/* We release buffers only if the entire page is being
-		 * invalidated.
-		 * The get_block cached value has been unconditionally
-		 * invalidated, so real IO is not possible anymore.
-		 */
-		if (offset == 0) {
-			BUG_ON(!PageLocked(page));
-
-			ret = 0;
-			if (!PageWriteback(page))
-				ret = page->mapping->a_ops->releasepage(page,
-									0);
-			/* possibly should BUG_ON(!ret); - neilb */
-		}
+	/* attempt to read as many of the pages as possible */
+#ifdef CONFIG_AFS_FSCACHE
+	ret = fscache_read_or_alloc_pages(vnode->cache,
+					  mapping,
+					  pages,
+					  &nr_pages,
+					  afs_file_readpage_read_complete,
+					  NULL,
+					  mapping_gfp_mask(mapping));
+#else
+	ret = -ENOBUFS;
+#endif
+
+	switch (ret) {
+		/* all pages are being read from the cache */
+	case 0:
+		BUG_ON(!list_empty(pages));
+		BUG_ON(nr_pages != 0);
+		_leave(" = 0 [reading all]");
+		return 0;
+
+		/* there were pages that couldn't be read from the cache */
+	case -ENODATA:
+	case -ENOBUFS:
+		break;
+
+		/* other error */
+	default:
+		_leave(" = %d", ret);
+		return ret;
 	}
 
-	_leave(" = %d", ret);
+	/* load the missing pages from the network */
+	ret = read_cache_pages(mapping, pages, (void *) afs_readpage, file);
+
+	_leave(" = %d [netting]", ret);
+	return ret;
 }
 
 /*
@@ -273,25 +282,82 @@ static int afs_launder_page(struct page *page)
 }
 
 /*
- * release a page and cleanup its private data
+ * invalidate part or all of a page
+ * - release a page and clean up its private data if offset is 0 (indicating
+ *   the entire page)
+ */
+static void afs_invalidatepage(struct page *page, unsigned long offset)
+{
+	struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
+
+	_enter("{%lu},%lu", page->index, offset);
+
+	BUG_ON(!PageLocked(page));
+
+	/* we clean up only if the entire page is being invalidated */
+	if (offset == 0) {
+#ifdef CONFIG_AFS_FSCACHE
+		if (PageFsCache(page)) {
+			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+			fscache_wait_on_page_write(vnode->cache, page);
+			fscache_uncache_page(vnode->cache, page);
+			ClearPageFsCache(page);
+		}
+#endif
+
+		if (PagePrivate(page)) {
+			if (wb && !PageWriteback(page)) {
+				set_page_private(page, 0);
+				afs_put_writeback(wb);
+			}
+
+			if (!page_private(page))
+				ClearPagePrivate(page);
+		}
+	}
+
+	_leave("");
+}
+
+/*
+ * release a page and clean up its private state if it's not busy
+ * - return true if the page can now be released, false if not
  */
 static int afs_releasepage(struct page *page, gfp_t gfp_flags)
 {
+	struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
 	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
-	struct afs_writeback *wb;
 
 	_enter("{{%x:%u}[%lu],%lx},%x",
 	       vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
 	       gfp_flags);
 
+	/* deny if page is being written to the cache and the caller hasn't
+	 * elected to wait */
+#ifdef CONFIG_AFS_FSCACHE
+	if (PageFsCache(page)) {
+		if (fscache_check_page_write(vnode->cache, page)) {
+			if (!(gfp_flags & __GFP_WAIT)) {
+				_leave(" = F [cache busy]");
+				return 0;
+			}
+			fscache_wait_on_page_write(vnode->cache, page);
+		}
+
+		fscache_uncache_page(vnode->cache, page);
+		ClearPageFsCache(page);
+	}
+#endif
+
 	if (PagePrivate(page)) {
-		wb = (struct afs_writeback *) page_private(page);
-		ASSERT(wb != NULL);
-		set_page_private(page, 0);
+		if (wb) {
+			set_page_private(page, 0);
+			afs_put_writeback(wb);
+		}
 		ClearPagePrivate(page);
-		afs_put_writeback(wb);
 	}
 
-	_leave(" = 0");
-	return 0;
+	/* indicate that the page can be released */
+	_leave(" = T");
+	return 1;
 }

fs/afs/inode.c

@@ -61,6 +61,11 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 		return -EBADMSG;
 	}
 
+#ifdef CONFIG_AFS_FSCACHE
+	if (vnode->status.size != inode->i_size)
+		fscache_attr_changed(vnode->cache);
+#endif
+
 	inode->i_nlink		= vnode->status.nlink;
 	inode->i_uid		= vnode->status.owner;
 	inode->i_gid		= 0;
@@ -149,15 +154,6 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 		return inode;
 	}
 
-#ifdef AFS_CACHING_SUPPORT
-	/* set up caching before reading the status, as fetch-status reads the
-	 * first page of symlinks to see if they're really mntpts */
-	cachefs_acquire_cookie(vnode->volume->cache,
-			       NULL,
-			       vnode,
-			       &vnode->cache);
-#endif
-
 	if (!status) {
 		/* it's a remotely extant inode */
 		set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
@@ -183,6 +179,15 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 		}
 	}
 
+	/* set up caching before mapping the status, as map-status reads the
+	 * first page of symlinks to see if they're really mountpoints */
+	inode->i_size = vnode->status.size;
+#ifdef CONFIG_AFS_FSCACHE
+	vnode->cache = fscache_acquire_cookie(vnode->volume->cache,
+					      &afs_vnode_cache_index_def,
+					      vnode);
+#endif
+
 	ret = afs_inode_map_status(vnode, key);
 	if (ret < 0)
 		goto bad_inode;
@@ -196,6 +201,10 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 
 	/* failure */
 bad_inode:
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(vnode->cache, 0);
+	vnode->cache = NULL;
+#endif
 	iget_failed(inode);
 	_leave(" = %d [bad]", ret);
 	return ERR_PTR(ret);
@@ -340,8 +349,8 @@ void afs_clear_inode(struct inode *inode)
 	ASSERT(list_empty(&vnode->writebacks));
 	ASSERT(!vnode->cb_promised);
 
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(vnode->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(vnode->cache, 0);
 	vnode->cache = NULL;
 #endif
 

fs/afs/internal.h

@@ -21,6 +21,7 @@
 
 #include "afs.h"
 #include "afs_vl.h"
+#include "cache.h"
 
 #define AFS_CELL_MAX_ADDRS 15
 
@@ -193,8 +194,8 @@ struct afs_cell {
 	struct key		*anonymous_key;	/* anonymous user key for this cell */
 	struct list_head	proc_link;	/* /proc cell list link */
 	struct proc_dir_entry	*proc_dir;	/* /proc dir for this cell */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 
 	/* server record management */
@@ -249,8 +250,8 @@ struct afs_vlocation {
 	struct list_head	grave;		/* link in master graveyard list */
 	struct list_head	update;		/* link in master update list */
 	struct afs_cell		*cell;		/* cell to which volume belongs */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 	struct afs_cache_vlocation vldb;	/* volume information DB record */
 	struct afs_volume	*vols[3];	/* volume access record pointer (index by type) */
@@ -302,8 +303,8 @@ struct afs_volume {
 	atomic_t		usage;
 	struct afs_cell		*cell;		/* cell to which belongs (unrefd ptr) */
 	struct afs_vlocation	*vlocation;	/* volume location */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 	afs_volid_t		vid;		/* volume ID */
 	afs_voltype_t		type;		/* type of volume */
@@ -333,8 +334,8 @@ struct afs_vnode {
 	struct afs_server	*server;	/* server currently supplying this file */
 	struct afs_fid		fid;		/* the file identifier for this inode */
 	struct afs_file_status	status;		/* AFS status info for this file */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 	struct afs_permits	*permits;	/* cache of permits so far obtained */
 	struct mutex		permits_lock;	/* lock for altering permits list */
@@ -427,6 +428,22 @@ struct afs_uuid {
 };
 
 /*****************************************************************************/
+/*
+ * cache.c
+ */
+#ifdef CONFIG_AFS_FSCACHE
+extern struct fscache_netfs afs_cache_netfs;
+extern struct fscache_cookie_def afs_cell_cache_index_def;
+extern struct fscache_cookie_def afs_vlocation_cache_index_def;
+extern struct fscache_cookie_def afs_volume_cache_index_def;
+extern struct fscache_cookie_def afs_vnode_cache_index_def;
+#else
+#define afs_cell_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#define afs_vlocation_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#define afs_volume_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#define afs_vnode_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#endif
+
 /*
  * callback.c
  */
@@ -446,9 +463,6 @@ extern void afs_callback_update_kill(void);
  */
 extern struct rw_semaphore afs_proc_cells_sem;
 extern struct list_head afs_proc_cells;
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_cache_cell_index_def;
-#endif
 
 #define afs_get_cell(C) do { atomic_inc(&(C)->usage); } while(0)
 extern int afs_cell_init(char *);
@@ -554,9 +568,6 @@ extern void afs_clear_inode(struct inode *);
  * main.c
  */
 extern struct afs_uuid afs_uuid;
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_netfs afs_cache_netfs;
-#endif
 
 /*
  * misc.c
@@ -637,10 +648,6 @@ extern int afs_get_MAC_address(u8 *, size_t);
 /*
  * vlclient.c
  */
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_vlocation_cache_index_def;
-#endif
-
 extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *,
 				    const char *, struct afs_cache_vlocation *,
 				    const struct afs_wait_mode *);
@@ -664,12 +671,6 @@ extern void afs_vlocation_purge(void);
 /*
  * vnode.c
  */
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_vnode_cache_index_def;
-#endif
-
-extern struct afs_timer_ops afs_vnode_cb_timed_out_ops;
-
 static inline struct afs_vnode *AFS_FS_I(struct inode *inode)
 {
 	return container_of(inode, struct afs_vnode, vfs_inode);
@@ -711,10 +712,6 @@ extern int afs_vnode_release_lock(struct afs_vnode *, struct key *);
 /*
  * volume.c
  */
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_volume_cache_index_def;
-#endif
-
 #define afs_get_volume(V) do { atomic_inc(&(V)->usage); } while(0)
 
 extern void afs_put_volume(struct afs_volume *);

fs/afs/main.c

@@ -1,6 +1,6 @@
 /* AFS client file system
  *
- * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2002,5 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -29,18 +29,6 @@ static char *rootcell;
 module_param(rootcell, charp, 0);
 MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list");
 
-#ifdef AFS_CACHING_SUPPORT
-static struct cachefs_netfs_operations afs_cache_ops = {
-	.get_page_cookie	= afs_cache_get_page_cookie,
-};
-
-struct cachefs_netfs afs_cache_netfs = {
-	.name			= "afs",
-	.version		= 0,
-	.ops			= &afs_cache_ops,
-};
-#endif
-
 struct afs_uuid afs_uuid;
 
 /*
@@ -104,10 +92,9 @@ static int __init afs_init(void)
 	if (ret < 0)
 		return ret;
 
-#ifdef AFS_CACHING_SUPPORT
+#ifdef CONFIG_AFS_FSCACHE
 	/* we want to be able to cache */
-	ret = cachefs_register_netfs(&afs_cache_netfs,
-				     &afs_cache_cell_index_def);
+	ret = fscache_register_netfs(&afs_cache_netfs);
 	if (ret < 0)
 		goto error_cache;
 #endif
@@ -142,8 +129,8 @@ error_fs:
 error_open_socket:
 error_vl_update_init:
 error_cell_init:
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_unregister_netfs(&afs_cache_netfs);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_unregister_netfs(&afs_cache_netfs);
 error_cache:
 #endif
 	afs_callback_update_kill();
@@ -175,8 +162,8 @@ static void __exit afs_exit(void)
 	afs_vlocation_purge();
 	flush_scheduled_work();
 	afs_cell_purge();
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_unregister_netfs(&afs_cache_netfs);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_unregister_netfs(&afs_cache_netfs);
 #endif
 	afs_proc_cleanup();
 	rcu_barrier();

fs/afs/mntpt.c

@@ -173,9 +173,9 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 	if (PageError(page))
 		goto error;
 
-	buf = kmap(page);
+	buf = kmap_atomic(page, KM_USER0);
 	memcpy(devname, buf, size);
-	kunmap(page);
+	kunmap_atomic(buf, KM_USER0);
 	page_cache_release(page);
 	page = NULL;
 

fs/afs/vlocation.c

@@ -281,9 +281,8 @@ static void afs_vlocation_apply_update(struct afs_vlocation *vl,
 
 	vl->vldb = *vldb;
 
-#ifdef AFS_CACHING_SUPPORT
-	/* update volume entry in local cache */
-	cachefs_update_cookie(vl->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_update_cookie(vl->cache);
 #endif
 }
 
@@ -304,11 +303,9 @@ static int afs_vlocation_fill_in_record(struct afs_vlocation *vl,
 	memset(&vldb, 0, sizeof(vldb));
 
 	/* see if we have an in-cache copy (will set vl->valid if there is) */
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_acquire_cookie(cell->cache,
-			       &afs_volume_cache_index_def,
-			       vlocation,
-			       &vl->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	vl->cache = fscache_acquire_cookie(vl->cell->cache,
+					   &afs_vlocation_cache_index_def, vl);
 #endif
 
 	if (vl->valid) {
@@ -420,6 +417,11 @@ fill_in_record:
 	spin_unlock(&vl->lock);
 	wake_up(&vl->waitq);
 
+	/* update volume entry in local cache */
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_update_cookie(vl->cache);
+#endif
+
 	/* schedule for regular updates */
 	afs_vlocation_queue_for_updates(vl);
 	goto success;
@@ -465,7 +467,7 @@ found_in_memory:
 	spin_unlock(&vl->lock);
 
 success:
-	_leave(" = %p",vl);
+	_leave(" = %p", vl);
 	return vl;
 
 error_abandon:
@@ -523,10 +525,9 @@ static void afs_vlocation_destroy(struct afs_vlocation *vl)
 {
 	_enter("%p", vl);
 
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(vl->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(vl->cache, 0);
 #endif
-
 	afs_put_cell(vl->cell);
 	kfree(vl);
 }

fs/afs/volume.c

@@ -124,13 +124,11 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	}
 
 	/* attach the cache and volume location */
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_acquire_cookie(vlocation->cache,
-			       &afs_vnode_cache_index_def,
-			       volume,
-			       &volume->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	volume->cache = fscache_acquire_cookie(vlocation->cache,
+					       &afs_volume_cache_index_def,
+					       volume);
 #endif
-
 	afs_get_vlocation(vlocation);
 	volume->vlocation = vlocation;
 
@@ -194,8 +192,8 @@ void afs_put_volume(struct afs_volume *volume)
 	up_write(&vlocation->cell->vl_sem);
 
 	/* finish cleaning up the volume */
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(volume->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(volume->cache, 0);
 #endif
 	afs_put_vlocation(vlocation);
 

fs/afs/write.c

@@ -780,3 +780,24 @@ int afs_fsync(struct file *file, struct dentry *dentry, int datasync)
 	_leave(" = %d", ret);
 	return ret;
 }
+
+/*
+ * notification that a previously read-only page is about to become writable
+ * - if it returns an error, the caller will deliver a bus error signal
+ */
+int afs_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+{
+	struct afs_vnode *vnode = AFS_FS_I(vma->vm_file->f_mapping->host);
+
+	_enter("{{%x:%u}},{%lx}",
+	       vnode->fid.vid, vnode->fid.vnode, page->index);
+
+	/* wait for the page to be written to the cache before we allow it to
+	 * be modified */
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_wait_on_page_write(vnode->cache, page);
+#endif
+
+	_leave(" = 0");
+	return 0;
+}

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.

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

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("");
+}

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;
+}

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,
+};

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

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;
+}

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);

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;
+}

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);
+}

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);
+}

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;
+}

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;
+}

fs/fscache/Kconfig

@@ -0,0 +1,56 @@
+
+config FSCACHE
+	tristate "General filesystem local caching manager"
+	depends on EXPERIMENTAL
+	select SLOW_WORK
+	help
+	  This option enables a generic filesystem caching manager that can be
+	  used by various network and other filesystems to cache data locally.
+	  Different sorts of caches can be plugged in, depending on the
+	  resources available.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_STATS
+	bool "Gather statistical information on local caching"
+	depends on FSCACHE && PROC_FS
+	help
+	  This option causes statistical information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/stats
+
+	  The gathering of statistics adds a certain amount of overhead to
+	  execution as there are a quite a few stats gathered, and on a
+	  multi-CPU system these may be on cachelines that keep bouncing
+	  between CPUs.  On the other hand, the stats are very useful for
+	  debugging purposes.  Saying 'Y' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_HISTOGRAM
+	bool "Gather latency information on local caching"
+	depends on FSCACHE && PROC_FS
+	help
+	  This option causes latency information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/histogram
+
+	  The generation of this histogram adds a certain amount of overhead to
+	  execution as there are a number of points at which data is gathered,
+	  and on a multi-CPU system these may be on cachelines that keep
+	  bouncing between CPUs.  On the other hand, the histogram may be
+	  useful for debugging purposes.  Saying 'N' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_DEBUG
+	bool "Debug FS-Cache"
+	depends on FSCACHE
+	help
+	  This permits debugging to be dynamically enabled in the local caching
+	  management module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.

fs/fscache/Makefile

@@ -0,0 +1,19 @@
+#
+# Makefile for general filesystem caching code
+#
+
+fscache-y := \
+	cache.o \
+	cookie.o \
+	fsdef.o \
+	main.o \
+	netfs.o \
+	object.o \
+	operation.o \
+	page.o
+
+fscache-$(CONFIG_PROC_FS) += proc.o
+fscache-$(CONFIG_FSCACHE_STATS) += stats.o
+fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o
+
+obj-$(CONFIG_FSCACHE) := fscache.o

fs/fscache/cache.c

@@ -0,0 +1,415 @@
+/* FS-Cache cache handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+LIST_HEAD(fscache_cache_list);
+DECLARE_RWSEM(fscache_addremove_sem);
+DECLARE_WAIT_QUEUE_HEAD(fscache_cache_cleared_wq);
+EXPORT_SYMBOL(fscache_cache_cleared_wq);
+
+static LIST_HEAD(fscache_cache_tag_list);
+
+/*
+ * look up a cache tag
+ */
+struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *name)
+{
+	struct fscache_cache_tag *tag, *xtag;
+
+	/* firstly check for the existence of the tag under read lock */
+	down_read(&fscache_addremove_sem);
+
+	list_for_each_entry(tag, &fscache_cache_tag_list, link) {
+		if (strcmp(tag->name, name) == 0) {
+			atomic_inc(&tag->usage);
+			up_read(&fscache_addremove_sem);
+			return tag;
+		}
+	}
+
+	up_read(&fscache_addremove_sem);
+
+	/* the tag does not exist - create a candidate */
+	xtag = kzalloc(sizeof(*xtag) + strlen(name) + 1, GFP_KERNEL);
+	if (!xtag)
+		/* return a dummy tag if out of memory */
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&xtag->usage, 1);
+	strcpy(xtag->name, name);
+
+	/* write lock, search again and add if still not present */
+	down_write(&fscache_addremove_sem);
+
+	list_for_each_entry(tag, &fscache_cache_tag_list, link) {
+		if (strcmp(tag->name, name) == 0) {
+			atomic_inc(&tag->usage);
+			up_write(&fscache_addremove_sem);
+			kfree(xtag);
+			return tag;
+		}
+	}
+
+	list_add_tail(&xtag->link, &fscache_cache_tag_list);
+	up_write(&fscache_addremove_sem);
+	return xtag;
+}
+
+/*
+ * release a reference to a cache tag
+ */
+void __fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+	if (tag != ERR_PTR(-ENOMEM)) {
+		down_write(&fscache_addremove_sem);
+
+		if (atomic_dec_and_test(&tag->usage))
+			list_del_init(&tag->link);
+		else
+			tag = NULL;
+
+		up_write(&fscache_addremove_sem);
+
+		kfree(tag);
+	}
+}
+
+/*
+ * select a cache in which to store an object
+ * - the cache addremove semaphore must be at least read-locked by the caller
+ * - the object will never be an index
+ */
+struct fscache_cache *fscache_select_cache_for_object(
+	struct fscache_cookie *cookie)
+{
+	struct fscache_cache_tag *tag;
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+
+	_enter("");
+
+	if (list_empty(&fscache_cache_list)) {
+		_leave(" = NULL [no cache]");
+		return NULL;
+	}
+
+	/* we check the parent to determine the cache to use */
+	spin_lock(&cookie->lock);
+
+	/* the first in the parent's backing list should be the preferred
+	 * cache */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		object = hlist_entry(cookie->backing_objects.first,
+				     struct fscache_object, cookie_link);
+
+		cache = object->cache;
+		if (object->state >= FSCACHE_OBJECT_DYING ||
+		    test_bit(FSCACHE_IOERROR, &cache->flags))
+			cache = NULL;
+
+		spin_unlock(&cookie->lock);
+		_leave(" = %p [parent]", cache);
+		return cache;
+	}
+
+	/* the parent is unbacked */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		/* cookie not an index and is unbacked */
+		spin_unlock(&cookie->lock);
+		_leave(" = NULL [cookie ub,ni]");
+		return NULL;
+	}
+
+	spin_unlock(&cookie->lock);
+
+	if (!cookie->def->select_cache)
+		goto no_preference;
+
+	/* ask the netfs for its preference */
+	tag = cookie->def->select_cache(cookie->parent->netfs_data,
+					cookie->netfs_data);
+	if (!tag)
+		goto no_preference;
+
+	if (tag == ERR_PTR(-ENOMEM)) {
+		_leave(" = NULL [nomem tag]");
+		return NULL;
+	}
+
+	if (!tag->cache) {
+		_leave(" = NULL [unbacked tag]");
+		return NULL;
+	}
+
+	if (test_bit(FSCACHE_IOERROR, &tag->cache->flags))
+		return NULL;
+
+	_leave(" = %p [specific]", tag->cache);
+	return tag->cache;
+
+no_preference:
+	/* netfs has no preference - just select first cache */
+	cache = list_entry(fscache_cache_list.next,
+			   struct fscache_cache, link);
+	_leave(" = %p [first]", cache);
+	return cache;
+}
+
+/**
+ * fscache_init_cache - Initialise a cache record
+ * @cache: The cache record to be initialised
+ * @ops: The cache operations to be installed in that record
+ * @idfmt: Format string to define identifier
+ * @...: sprintf-style arguments
+ *
+ * Initialise a record of a cache and fill in the name.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_init_cache(struct fscache_cache *cache,
+			const struct fscache_cache_ops *ops,
+			const char *idfmt,
+			...)
+{
+	va_list va;
+
+	memset(cache, 0, sizeof(*cache));
+
+	cache->ops = ops;
+
+	va_start(va, idfmt);
+	vsnprintf(cache->identifier, sizeof(cache->identifier), idfmt, va);
+	va_end(va);
+
+	INIT_WORK(&cache->op_gc, fscache_operation_gc);
+	INIT_LIST_HEAD(&cache->link);
+	INIT_LIST_HEAD(&cache->object_list);
+	INIT_LIST_HEAD(&cache->op_gc_list);
+	spin_lock_init(&cache->object_list_lock);
+	spin_lock_init(&cache->op_gc_list_lock);
+}
+EXPORT_SYMBOL(fscache_init_cache);
+
+/**
+ * fscache_add_cache - Declare a cache as being open for business
+ * @cache: The record describing the cache
+ * @ifsdef: The record of the cache object describing the top-level index
+ * @tagname: The tag describing this cache
+ *
+ * Add a cache to the system, making it available for netfs's to use.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+int fscache_add_cache(struct fscache_cache *cache,
+		      struct fscache_object *ifsdef,
+		      const char *tagname)
+{
+	struct fscache_cache_tag *tag;
+
+	BUG_ON(!cache->ops);
+	BUG_ON(!ifsdef);
+
+	cache->flags = 0;
+	ifsdef->event_mask = ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+	ifsdef->state = FSCACHE_OBJECT_ACTIVE;
+
+	if (!tagname)
+		tagname = cache->identifier;
+
+	BUG_ON(!tagname[0]);
+
+	_enter("{%s.%s},,%s", cache->ops->name, cache->identifier, tagname);
+
+	/* we use the cache tag to uniquely identify caches */
+	tag = __fscache_lookup_cache_tag(tagname);
+	if (IS_ERR(tag))
+		goto nomem;
+
+	if (test_and_set_bit(FSCACHE_TAG_RESERVED, &tag->flags))
+		goto tag_in_use;
+
+	cache->kobj = kobject_create_and_add(tagname, fscache_root);
+	if (!cache->kobj)
+		goto error;
+
+	ifsdef->cookie = &fscache_fsdef_index;
+	ifsdef->cache = cache;
+	cache->fsdef = ifsdef;
+
+	down_write(&fscache_addremove_sem);
+
+	tag->cache = cache;
+	cache->tag = tag;
+
+	/* add the cache to the list */
+	list_add(&cache->link, &fscache_cache_list);
+
+	/* add the cache's netfs definition index object to the cache's
+	 * list */
+	spin_lock(&cache->object_list_lock);
+	list_add_tail(&ifsdef->cache_link, &cache->object_list);
+	spin_unlock(&cache->object_list_lock);
+
+	/* add the cache's netfs definition index object to the top level index
+	 * cookie as a known backing object */
+	spin_lock(&fscache_fsdef_index.lock);
+
+	hlist_add_head(&ifsdef->cookie_link,
+		       &fscache_fsdef_index.backing_objects);
+
+	atomic_inc(&fscache_fsdef_index.usage);
+
+	/* done */
+	spin_unlock(&fscache_fsdef_index.lock);
+	up_write(&fscache_addremove_sem);
+
+	printk(KERN_NOTICE "FS-Cache: Cache \"%s\" added (type %s)\n",
+	       cache->tag->name, cache->ops->name);
+	kobject_uevent(cache->kobj, KOBJ_ADD);
+
+	_leave(" = 0 [%s]", cache->identifier);
+	return 0;
+
+tag_in_use:
+	printk(KERN_ERR "FS-Cache: Cache tag '%s' already in use\n", tagname);
+	__fscache_release_cache_tag(tag);
+	_leave(" = -EXIST");
+	return -EEXIST;
+
+error:
+	__fscache_release_cache_tag(tag);
+	_leave(" = -EINVAL");
+	return -EINVAL;
+
+nomem:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(fscache_add_cache);
+
+/**
+ * fscache_io_error - Note a cache I/O error
+ * @cache: The record describing the cache
+ *
+ * Note that an I/O error occurred in a cache and that it should no longer be
+ * used for anything.  This also reports the error into the kernel log.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_io_error(struct fscache_cache *cache)
+{
+	set_bit(FSCACHE_IOERROR, &cache->flags);
+
+	printk(KERN_ERR "FS-Cache: Cache %s stopped due to I/O error\n",
+	       cache->ops->name);
+}
+EXPORT_SYMBOL(fscache_io_error);
+
+/*
+ * request withdrawal of all the objects in a cache
+ * - all the objects being withdrawn are moved onto the supplied list
+ */
+static void fscache_withdraw_all_objects(struct fscache_cache *cache,
+					 struct list_head *dying_objects)
+{
+	struct fscache_object *object;
+
+	spin_lock(&cache->object_list_lock);
+
+	while (!list_empty(&cache->object_list)) {
+		object = list_entry(cache->object_list.next,
+				    struct fscache_object, cache_link);
+		list_move_tail(&object->cache_link, dying_objects);
+
+		_debug("withdraw %p", object->cookie);
+
+		spin_lock(&object->lock);
+		spin_unlock(&cache->object_list_lock);
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_WITHDRAW);
+		spin_unlock(&object->lock);
+
+		cond_resched();
+		spin_lock(&cache->object_list_lock);
+	}
+
+	spin_unlock(&cache->object_list_lock);
+}
+
+/**
+ * fscache_withdraw_cache - Withdraw a cache from the active service
+ * @cache: The record describing the cache
+ *
+ * Withdraw a cache from service, unbinding all its cache objects from the
+ * netfs cookies they're currently representing.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_withdraw_cache(struct fscache_cache *cache)
+{
+	LIST_HEAD(dying_objects);
+
+	_enter("");
+
+	printk(KERN_NOTICE "FS-Cache: Withdrawing cache \"%s\"\n",
+	       cache->tag->name);
+
+	/* make the cache unavailable for cookie acquisition */
+	if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags))
+		BUG();
+
+	down_write(&fscache_addremove_sem);
+	list_del_init(&cache->link);
+	cache->tag->cache = NULL;
+	up_write(&fscache_addremove_sem);
+
+	/* make sure all pages pinned by operations on behalf of the netfs are
+	 * written to disk */
+	cache->ops->sync_cache(cache);
+
+	/* dissociate all the netfs pages backed by this cache from the block
+	 * mappings in the cache */
+	cache->ops->dissociate_pages(cache);
+
+	/* we now have to destroy all the active objects pertaining to this
+	 * cache - which we do by passing them off to thread pool to be
+	 * disposed of */
+	_debug("destroy");
+
+	fscache_withdraw_all_objects(cache, &dying_objects);
+
+	/* wait for all extant objects to finish their outstanding operations
+	 * and go away */
+	_debug("wait for finish");
+	wait_event(fscache_cache_cleared_wq,
+		   atomic_read(&cache->object_count) == 0);
+	_debug("wait for clearance");
+	wait_event(fscache_cache_cleared_wq,
+		   list_empty(&cache->object_list));
+	_debug("cleared");
+	ASSERT(list_empty(&dying_objects));
+
+	kobject_put(cache->kobj);
+
+	clear_bit(FSCACHE_TAG_RESERVED, &cache->tag->flags);
+	fscache_release_cache_tag(cache->tag);
+	cache->tag = NULL;
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_withdraw_cache);

fs/fscache/cookie.c

@@ -0,0 +1,500 @@
+/* netfs cookie management
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for more information on
+ * the netfs API.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+struct kmem_cache *fscache_cookie_jar;
+
+static atomic_t fscache_object_debug_id = ATOMIC_INIT(0);
+
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie);
+static int fscache_alloc_object(struct fscache_cache *cache,
+				struct fscache_cookie *cookie);
+static int fscache_attach_object(struct fscache_cookie *cookie,
+				 struct fscache_object *object);
+
+/*
+ * initialise an cookie jar slab element prior to any use
+ */
+void fscache_cookie_init_once(void *_cookie)
+{
+	struct fscache_cookie *cookie = _cookie;
+
+	memset(cookie, 0, sizeof(*cookie));
+	spin_lock_init(&cookie->lock);
+	INIT_HLIST_HEAD(&cookie->backing_objects);
+}
+
+/*
+ * request a cookie to represent an object (index, datafile, xattr, etc)
+ * - parent specifies the parent object
+ *   - the top level index cookie for each netfs is stored in the fscache_netfs
+ *     struct upon registration
+ * - def points to the definition
+ * - the netfs_data will be passed to the functions pointed to in *def
+ * - all attached caches will be searched to see if they contain this object
+ * - index objects aren't stored on disk until there's a dependent file that
+ *   needs storing
+ * - other objects are stored in a selected cache immediately, and all the
+ *   indices forming the path to it are instantiated if necessary
+ * - we never let on to the netfs about errors
+ *   - we may set a negative cookie pointer, but that's okay
+ */
+struct fscache_cookie *__fscache_acquire_cookie(
+	struct fscache_cookie *parent,
+	const struct fscache_cookie_def *def,
+	void *netfs_data)
+{
+	struct fscache_cookie *cookie;
+
+	BUG_ON(!def);
+
+	_enter("{%s},{%s},%p",
+	       parent ? (char *) parent->def->name : "<no-parent>",
+	       def->name, netfs_data);
+
+	fscache_stat(&fscache_n_acquires);
+
+	/* if there's no parent cookie, then we don't create one here either */
+	if (!parent) {
+		fscache_stat(&fscache_n_acquires_null);
+		_leave(" [no parent]");
+		return NULL;
+	}
+
+	/* validate the definition */
+	BUG_ON(!def->get_key);
+	BUG_ON(!def->name[0]);
+
+	BUG_ON(def->type == FSCACHE_COOKIE_TYPE_INDEX &&
+	       parent->def->type != FSCACHE_COOKIE_TYPE_INDEX);
+
+	/* allocate and initialise a cookie */
+	cookie = kmem_cache_alloc(fscache_cookie_jar, GFP_KERNEL);
+	if (!cookie) {
+		fscache_stat(&fscache_n_acquires_oom);
+		_leave(" [ENOMEM]");
+		return NULL;
+	}
+
+	atomic_set(&cookie->usage, 1);
+	atomic_set(&cookie->n_children, 0);
+
+	atomic_inc(&parent->usage);
+	atomic_inc(&parent->n_children);
+
+	cookie->def		= def;
+	cookie->parent		= parent;
+	cookie->netfs_data	= netfs_data;
+	cookie->flags		= 0;
+
+	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS);
+
+	switch (cookie->def->type) {
+	case FSCACHE_COOKIE_TYPE_INDEX:
+		fscache_stat(&fscache_n_cookie_index);
+		break;
+	case FSCACHE_COOKIE_TYPE_DATAFILE:
+		fscache_stat(&fscache_n_cookie_data);
+		break;
+	default:
+		fscache_stat(&fscache_n_cookie_special);
+		break;
+	}
+
+	/* if the object is an index then we need do nothing more here - we
+	 * create indices on disk when we need them as an index may exist in
+	 * multiple caches */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		if (fscache_acquire_non_index_cookie(cookie) < 0) {
+			atomic_dec(&parent->n_children);
+			__fscache_cookie_put(cookie);
+			fscache_stat(&fscache_n_acquires_nobufs);
+			_leave(" = NULL");
+			return NULL;
+		}
+	}
+
+	fscache_stat(&fscache_n_acquires_ok);
+	_leave(" = %p", cookie);
+	return cookie;
+}
+EXPORT_SYMBOL(__fscache_acquire_cookie);
+
+/*
+ * acquire a non-index cookie
+ * - this must make sure the index chain is instantiated and instantiate the
+ *   object representation too
+ */
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+	uint64_t i_size;
+	int ret;
+
+	_enter("");
+
+	cookie->flags = 1 << FSCACHE_COOKIE_UNAVAILABLE;
+
+	/* now we need to see whether the backing objects for this cookie yet
+	 * exist, if not there'll be nothing to search */
+	down_read(&fscache_addremove_sem);
+
+	if (list_empty(&fscache_cache_list)) {
+		up_read(&fscache_addremove_sem);
+		_leave(" = 0 [no caches]");
+		return 0;
+	}
+
+	/* select a cache in which to store the object */
+	cache = fscache_select_cache_for_object(cookie->parent);
+	if (!cache) {
+		up_read(&fscache_addremove_sem);
+		fscache_stat(&fscache_n_acquires_no_cache);
+		_leave(" = -ENOMEDIUM [no cache]");
+		return -ENOMEDIUM;
+	}
+
+	_debug("cache %s", cache->tag->name);
+
+	cookie->flags =
+		(1 << FSCACHE_COOKIE_LOOKING_UP) |
+		(1 << FSCACHE_COOKIE_CREATING) |
+		(1 << FSCACHE_COOKIE_NO_DATA_YET);
+
+	/* ask the cache to allocate objects for this cookie and its parent
+	 * chain */
+	ret = fscache_alloc_object(cache, cookie);
+	if (ret < 0) {
+		up_read(&fscache_addremove_sem);
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	/* pass on how big the object we're caching is supposed to be */
+	cookie->def->get_attr(cookie->netfs_data, &i_size);
+
+	spin_lock(&cookie->lock);
+	if (hlist_empty(&cookie->backing_objects)) {
+		spin_unlock(&cookie->lock);
+		goto unavailable;
+	}
+
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	fscache_set_store_limit(object, i_size);
+
+	/* initiate the process of looking up all the objects in the chain
+	 * (done by fscache_initialise_object()) */
+	fscache_enqueue_object(object);
+
+	spin_unlock(&cookie->lock);
+
+	/* we may be required to wait for lookup to complete at this point */
+	if (!fscache_defer_lookup) {
+		_debug("non-deferred lookup %p", &cookie->flags);
+		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("complete");
+		if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags))
+			goto unavailable;
+	}
+
+	up_read(&fscache_addremove_sem);
+	_leave(" = 0 [deferred]");
+	return 0;
+
+unavailable:
+	up_read(&fscache_addremove_sem);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+
+/*
+ * recursively allocate cache object records for a cookie/cache combination
+ * - caller must be holding the addremove sem
+ */
+static int fscache_alloc_object(struct fscache_cache *cache,
+				struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct hlist_node *_n;
+	int ret;
+
+	_enter("%p,%p{%s}", cache, cookie, cookie->def->name);
+
+	spin_lock(&cookie->lock);
+	hlist_for_each_entry(object, _n, &cookie->backing_objects,
+			     cookie_link) {
+		if (object->cache == cache)
+			goto object_already_extant;
+	}
+	spin_unlock(&cookie->lock);
+
+	/* ask the cache to allocate an object (we may end up with duplicate
+	 * objects at this stage, but we sort that out later) */
+	object = cache->ops->alloc_object(cache, cookie);
+	if (IS_ERR(object)) {
+		fscache_stat(&fscache_n_object_no_alloc);
+		ret = PTR_ERR(object);
+		goto error;
+	}
+
+	fscache_stat(&fscache_n_object_alloc);
+
+	object->debug_id = atomic_inc_return(&fscache_object_debug_id);
+
+	_debug("ALLOC OBJ%x: %s {%lx}",
+	       object->debug_id, cookie->def->name, object->events);
+
+	ret = fscache_alloc_object(cache, cookie->parent);
+	if (ret < 0)
+		goto error_put;
+
+	/* only attach if we managed to allocate all we needed, otherwise
+	 * discard the object we just allocated and instead use the one
+	 * attached to the cookie */
+	if (fscache_attach_object(cookie, object) < 0)
+		cache->ops->put_object(object);
+
+	_leave(" = 0");
+	return 0;
+
+object_already_extant:
+	ret = -ENOBUFS;
+	if (object->state >= FSCACHE_OBJECT_DYING) {
+		spin_unlock(&cookie->lock);
+		goto error;
+	}
+	spin_unlock(&cookie->lock);
+	_leave(" = 0 [found]");
+	return 0;
+
+error_put:
+	cache->ops->put_object(object);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * attach a cache object to a cookie
+ */
+static int fscache_attach_object(struct fscache_cookie *cookie,
+				 struct fscache_object *object)
+{
+	struct fscache_object *p;
+	struct fscache_cache *cache = object->cache;
+	struct hlist_node *_n;
+	int ret;
+
+	_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
+
+	spin_lock(&cookie->lock);
+
+	/* there may be multiple initial creations of this object, but we only
+	 * want one */
+	ret = -EEXIST;
+	hlist_for_each_entry(p, _n, &cookie->backing_objects, cookie_link) {
+		if (p->cache == object->cache) {
+			if (p->state >= FSCACHE_OBJECT_DYING)
+				ret = -ENOBUFS;
+			goto cant_attach_object;
+		}
+	}
+
+	/* pin the parent object */
+	spin_lock_nested(&cookie->parent->lock, 1);
+	hlist_for_each_entry(p, _n, &cookie->parent->backing_objects,
+			     cookie_link) {
+		if (p->cache == object->cache) {
+			if (p->state >= FSCACHE_OBJECT_DYING) {
+				ret = -ENOBUFS;
+				spin_unlock(&cookie->parent->lock);
+				goto cant_attach_object;
+			}
+			object->parent = p;
+			spin_lock(&p->lock);
+			p->n_children++;
+			spin_unlock(&p->lock);
+			break;
+		}
+	}
+	spin_unlock(&cookie->parent->lock);
+
+	/* attach to the cache's object list */
+	if (list_empty(&object->cache_link)) {
+		spin_lock(&cache->object_list_lock);
+		list_add(&object->cache_link, &cache->object_list);
+		spin_unlock(&cache->object_list_lock);
+	}
+
+	/* attach to the cookie */
+	object->cookie = cookie;
+	atomic_inc(&cookie->usage);
+	hlist_add_head(&object->cookie_link, &cookie->backing_objects);
+	ret = 0;
+
+cant_attach_object:
+	spin_unlock(&cookie->lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * update the index entries backing a cookie
+ */
+void __fscache_update_cookie(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct hlist_node *_p;
+
+	fscache_stat(&fscache_n_updates);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_updates_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("{%s}", cookie->def->name);
+
+	BUG_ON(!cookie->def->get_aux);
+
+	spin_lock(&cookie->lock);
+
+	/* update the index entry on disk in each cache backing this cookie */
+	hlist_for_each_entry(object, _p,
+			     &cookie->backing_objects, cookie_link) {
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+	}
+
+	spin_unlock(&cookie->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_update_cookie);
+
+/*
+ * release a cookie back to the cache
+ * - the object will be marked as recyclable on disk if retire is true
+ * - all dependents of this cookie must have already been unregistered
+ *   (indices/files/pages)
+ */
+void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+{
+	struct fscache_cache *cache;
+	struct fscache_object *object;
+	unsigned long event;
+
+	fscache_stat(&fscache_n_relinquishes);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_relinquishes_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("%p{%s,%p},%d",
+	       cookie, cookie->def->name, cookie->netfs_data, retire);
+
+	if (atomic_read(&cookie->n_children) != 0) {
+		printk(KERN_ERR "FS-Cache: Cookie '%s' still has children\n",
+		       cookie->def->name);
+		BUG();
+	}
+
+	/* wait for the cookie to finish being instantiated (or to fail) */
+	if (test_bit(FSCACHE_COOKIE_CREATING, &cookie->flags)) {
+		fscache_stat(&fscache_n_relinquishes_waitcrt);
+		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_CREATING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	}
+
+	event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE;
+
+	/* detach pointers back to the netfs */
+	spin_lock(&cookie->lock);
+
+	cookie->netfs_data	= NULL;
+	cookie->def		= NULL;
+
+	/* break links with all the active objects */
+	while (!hlist_empty(&cookie->backing_objects)) {
+		object = hlist_entry(cookie->backing_objects.first,
+				     struct fscache_object,
+				     cookie_link);
+
+		_debug("RELEASE OBJ%x", object->debug_id);
+
+		/* detach each cache object from the object cookie */
+		spin_lock(&object->lock);
+		hlist_del_init(&object->cookie_link);
+
+		cache = object->cache;
+		object->cookie = NULL;
+		fscache_raise_event(object, event);
+		spin_unlock(&object->lock);
+
+		if (atomic_dec_and_test(&cookie->usage))
+			/* the cookie refcount shouldn't be reduced to 0 yet */
+			BUG();
+	}
+
+	spin_unlock(&cookie->lock);
+
+	if (cookie->parent) {
+		ASSERTCMP(atomic_read(&cookie->parent->usage), >, 0);
+		ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0);
+		atomic_dec(&cookie->parent->n_children);
+	}
+
+	/* finally dispose of the cookie */
+	ASSERTCMP(atomic_read(&cookie->usage), >, 0);
+	fscache_cookie_put(cookie);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_relinquish_cookie);
+
+/*
+ * destroy a cookie
+ */
+void __fscache_cookie_put(struct fscache_cookie *cookie)
+{
+	struct fscache_cookie *parent;
+
+	_enter("%p", cookie);
+
+	for (;;) {
+		_debug("FREE COOKIE %p", cookie);
+		parent = cookie->parent;
+		BUG_ON(!hlist_empty(&cookie->backing_objects));
+		kmem_cache_free(fscache_cookie_jar, cookie);
+
+		if (!parent)
+			break;
+
+		cookie = parent;
+		BUG_ON(atomic_read(&cookie->usage) <= 0);
+		if (!atomic_dec_and_test(&cookie->usage))
+			break;
+	}
+
+	_leave("");
+}

fs/fscache/fsdef.c

@@ -0,0 +1,144 @@
+/* Filesystem index definition
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include "internal.h"
+
+static uint16_t fscache_fsdef_netfs_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax);
+
+static uint16_t fscache_fsdef_netfs_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax);
+
+static
+enum fscache_checkaux fscache_fsdef_netfs_check_aux(void *cookie_netfs_data,
+						    const void *data,
+						    uint16_t datalen);
+
+/*
+ * The root index is owned by FS-Cache itself.
+ *
+ * When a netfs requests caching facilities, FS-Cache will, if one doesn't
+ * already exist, create an entry in the root index with the key being the name
+ * of the netfs ("AFS" for example), and the auxiliary data holding the index
+ * structure version supplied by the netfs:
+ *
+ *				     FSDEF
+ *				       |
+ *				 +-----------+
+ *				 |           |
+ *				NFS         AFS
+ *			       [v=1]       [v=1]
+ *
+ * If an entry with the appropriate name does already exist, the version is
+ * compared.  If the version is different, the entire subtree from that entry
+ * will be discarded and a new entry created.
+ *
+ * The new entry will be an index, and a cookie referring to it will be passed
+ * to the netfs.  This is then the root handle by which the netfs accesses the
+ * cache.  It can create whatever objects it likes in that index, including
+ * further indices.
+ */
+static struct fscache_cookie_def fscache_fsdef_index_def = {
+	.name		= ".FS-Cache",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+};
+
+struct fscache_cookie fscache_fsdef_index = {
+	.usage		= ATOMIC_INIT(1),
+	.lock		= __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock),
+	.backing_objects = HLIST_HEAD_INIT,
+	.def		= &fscache_fsdef_index_def,
+};
+EXPORT_SYMBOL(fscache_fsdef_index);
+
+/*
+ * Definition of an entry in the root index.  Each entry is an index, keyed to
+ * a specific netfs and only applicable to a particular version of the index
+ * structure used by that netfs.
+ */
+struct fscache_cookie_def fscache_fsdef_netfs_def = {
+	.name		= "FSDEF.netfs",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= fscache_fsdef_netfs_get_key,
+	.get_aux	= fscache_fsdef_netfs_get_aux,
+	.check_aux	= fscache_fsdef_netfs_check_aux,
+};
+
+/*
+ * get the key data for an FSDEF index record - this is the name of the netfs
+ * for which this entry is created
+ */
+static uint16_t fscache_fsdef_netfs_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct fscache_netfs *netfs = cookie_netfs_data;
+	unsigned klen;
+
+	_enter("{%s.%u},", netfs->name, netfs->version);
+
+	klen = strlen(netfs->name);
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, netfs->name, klen);
+	return klen;
+}
+
+/*
+ * get the auxiliary data for an FSDEF index record - this is the index
+ * structure version number of the netfs for which this version is created
+ */
+static uint16_t fscache_fsdef_netfs_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct fscache_netfs *netfs = cookie_netfs_data;
+	unsigned dlen;
+
+	_enter("{%s.%u},", netfs->name, netfs->version);
+
+	dlen = sizeof(uint32_t);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, &netfs->version, dlen);
+	return dlen;
+}
+
+/*
+ * check that the index structure version number stored in the auxiliary data
+ * matches the one the netfs gave us
+ */
+static enum fscache_checkaux fscache_fsdef_netfs_check_aux(
+	void *cookie_netfs_data,
+	const void *data,
+	uint16_t datalen)
+{
+	struct fscache_netfs *netfs = cookie_netfs_data;
+	uint32_t version;
+
+	_enter("{%s},,%hu", netfs->name, datalen);
+
+	if (datalen != sizeof(version)) {
+		_leave(" = OBSOLETE [dl=%d v=%zu]", datalen, sizeof(version));
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	memcpy(&version, data, sizeof(version));
+	if (version != netfs->version) {
+		_leave(" = OBSOLETE [ver=%x net=%x]", version, netfs->version);
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
+}

fs/fscache/histogram.c

@@ -0,0 +1,109 @@
+/* FS-Cache latency histogram
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL THREAD
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+atomic_t fscache_obj_instantiate_histogram[HZ];
+atomic_t fscache_objs_histogram[HZ];
+atomic_t fscache_ops_histogram[HZ];
+atomic_t fscache_retrieval_delay_histogram[HZ];
+atomic_t fscache_retrieval_histogram[HZ];
+
+/*
+ * display the time-taken histogram
+ */
+static int fscache_histogram_show(struct seq_file *m, void *v)
+{
+	unsigned long index;
+	unsigned n[5], t;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "JIFS  SECS  OBJ INST  OP RUNS   OBJ RUNS "
+			 " RETRV DLY RETRIEVLS\n");
+		return 0;
+	case 2:
+		seq_puts(m, "===== ===== ========= ========= ========="
+			 " ========= =========\n");
+		return 0;
+	default:
+		index = (unsigned long) v - 3;
+		n[0] = atomic_read(&fscache_obj_instantiate_histogram[index]);
+		n[1] = atomic_read(&fscache_ops_histogram[index]);
+		n[2] = atomic_read(&fscache_objs_histogram[index]);
+		n[3] = atomic_read(&fscache_retrieval_delay_histogram[index]);
+		n[4] = atomic_read(&fscache_retrieval_histogram[index]);
+		if (!(n[0] | n[1] | n[2] | n[3] | n[4]))
+			return 0;
+
+		t = (index * 1000) / HZ;
+
+		seq_printf(m, "%4lu  0.%03u %9u %9u %9u %9u %9u\n",
+			   index, t, n[0], n[1], n[2], n[3], n[4]);
+		return 0;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *fscache_histogram_start(struct seq_file *m, loff_t *_pos)
+{
+	if ((unsigned long long)*_pos >= HZ + 2)
+		return NULL;
+	if (*_pos == 0)
+		*_pos = 1;
+	return (void *)(unsigned long) *_pos;
+}
+
+/*
+ * move to the next line
+ */
+static void *fscache_histogram_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (unsigned long long)*pos > HZ + 2 ?
+		NULL : (void *)(unsigned long) *pos;
+}
+
+/*
+ * clean up after reading
+ */
+static void fscache_histogram_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations fscache_histogram_ops = {
+	.start		= fscache_histogram_start,
+	.stop		= fscache_histogram_stop,
+	.next		= fscache_histogram_next,
+	.show		= fscache_histogram_show,
+};
+
+/*
+ * open "/proc/fs/fscache/histogram" to provide latency data
+ */
+static int fscache_histogram_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fscache_histogram_ops);
+}
+
+const struct file_operations fscache_histogram_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_histogram_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};

fs/fscache/internal.h

@@ -0,0 +1,380 @@
+/* Internal definitions for FS-Cache
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/*
+ * Lock order, in the order in which multiple locks should be obtained:
+ * - fscache_addremove_sem
+ * - cookie->lock
+ * - cookie->parent->lock
+ * - cache->object_list_lock
+ * - object->lock
+ * - object->parent->lock
+ * - fscache_thread_lock
+ *
+ */
+
+#include <linux/fscache-cache.h>
+#include <linux/sched.h>
+
+#define FSCACHE_MIN_THREADS	4
+#define FSCACHE_MAX_THREADS	32
+
+/*
+ * fsc-cache.c
+ */
+extern struct list_head fscache_cache_list;
+extern struct rw_semaphore fscache_addremove_sem;
+
+extern struct fscache_cache *fscache_select_cache_for_object(
+	struct fscache_cookie *);
+
+/*
+ * fsc-cookie.c
+ */
+extern struct kmem_cache *fscache_cookie_jar;
+
+extern void fscache_cookie_init_once(void *);
+extern void __fscache_cookie_put(struct fscache_cookie *);
+
+/*
+ * fsc-fsdef.c
+ */
+extern struct fscache_cookie fscache_fsdef_index;
+extern struct fscache_cookie_def fscache_fsdef_netfs_def;
+
+/*
+ * fsc-histogram.c
+ */
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+extern atomic_t fscache_obj_instantiate_histogram[HZ];
+extern atomic_t fscache_objs_histogram[HZ];
+extern atomic_t fscache_ops_histogram[HZ];
+extern atomic_t fscache_retrieval_delay_histogram[HZ];
+extern atomic_t fscache_retrieval_histogram[HZ];
+
+static inline void fscache_hist(atomic_t histogram[], unsigned long start_jif)
+{
+	unsigned long jif = jiffies - start_jif;
+	if (jif >= HZ)
+		jif = HZ - 1;
+	atomic_inc(&histogram[jif]);
+}
+
+extern const struct file_operations fscache_histogram_fops;
+
+#else
+#define fscache_hist(hist, start_jif) do {} while (0)
+#endif
+
+/*
+ * fsc-main.c
+ */
+extern unsigned fscache_defer_lookup;
+extern unsigned fscache_defer_create;
+extern unsigned fscache_debug;
+extern struct kobject *fscache_root;
+
+extern int fscache_wait_bit(void *);
+extern int fscache_wait_bit_interruptible(void *);
+
+/*
+ * fsc-object.c
+ */
+extern void fscache_withdrawing_object(struct fscache_cache *,
+				       struct fscache_object *);
+extern void fscache_enqueue_object(struct fscache_object *);
+
+/*
+ * fsc-operation.c
+ */
+extern int fscache_submit_exclusive_op(struct fscache_object *,
+				       struct fscache_operation *);
+extern int fscache_submit_op(struct fscache_object *,
+			     struct fscache_operation *);
+extern void fscache_abort_object(struct fscache_object *);
+extern void fscache_start_operations(struct fscache_object *);
+extern void fscache_operation_gc(struct work_struct *);
+
+/*
+ * fsc-proc.c
+ */
+#ifdef CONFIG_PROC_FS
+extern int __init fscache_proc_init(void);
+extern void fscache_proc_cleanup(void);
+#else
+#define fscache_proc_init()	(0)
+#define fscache_proc_cleanup()	do {} while (0)
+#endif
+
+/*
+ * fsc-stats.c
+ */
+#ifdef CONFIG_FSCACHE_STATS
+extern atomic_t fscache_n_ops_processed[FSCACHE_MAX_THREADS];
+extern atomic_t fscache_n_objs_processed[FSCACHE_MAX_THREADS];
+
+extern atomic_t fscache_n_op_pend;
+extern atomic_t fscache_n_op_run;
+extern atomic_t fscache_n_op_enqueue;
+extern atomic_t fscache_n_op_deferred_release;
+extern atomic_t fscache_n_op_release;
+extern atomic_t fscache_n_op_gc;
+
+extern atomic_t fscache_n_attr_changed;
+extern atomic_t fscache_n_attr_changed_ok;
+extern atomic_t fscache_n_attr_changed_nobufs;
+extern atomic_t fscache_n_attr_changed_nomem;
+extern atomic_t fscache_n_attr_changed_calls;
+
+extern atomic_t fscache_n_allocs;
+extern atomic_t fscache_n_allocs_ok;
+extern atomic_t fscache_n_allocs_wait;
+extern atomic_t fscache_n_allocs_nobufs;
+extern atomic_t fscache_n_alloc_ops;
+extern atomic_t fscache_n_alloc_op_waits;
+
+extern atomic_t fscache_n_retrievals;
+extern atomic_t fscache_n_retrievals_ok;
+extern atomic_t fscache_n_retrievals_wait;
+extern atomic_t fscache_n_retrievals_nodata;
+extern atomic_t fscache_n_retrievals_nobufs;
+extern atomic_t fscache_n_retrievals_intr;
+extern atomic_t fscache_n_retrievals_nomem;
+extern atomic_t fscache_n_retrieval_ops;
+extern atomic_t fscache_n_retrieval_op_waits;
+
+extern atomic_t fscache_n_stores;
+extern atomic_t fscache_n_stores_ok;
+extern atomic_t fscache_n_stores_again;
+extern atomic_t fscache_n_stores_nobufs;
+extern atomic_t fscache_n_stores_oom;
+extern atomic_t fscache_n_store_ops;
+extern atomic_t fscache_n_store_calls;
+
+extern atomic_t fscache_n_marks;
+extern atomic_t fscache_n_uncaches;
+
+extern atomic_t fscache_n_acquires;
+extern atomic_t fscache_n_acquires_null;
+extern atomic_t fscache_n_acquires_no_cache;
+extern atomic_t fscache_n_acquires_ok;
+extern atomic_t fscache_n_acquires_nobufs;
+extern atomic_t fscache_n_acquires_oom;
+
+extern atomic_t fscache_n_updates;
+extern atomic_t fscache_n_updates_null;
+extern atomic_t fscache_n_updates_run;
+
+extern atomic_t fscache_n_relinquishes;
+extern atomic_t fscache_n_relinquishes_null;
+extern atomic_t fscache_n_relinquishes_waitcrt;
+
+extern atomic_t fscache_n_cookie_index;
+extern atomic_t fscache_n_cookie_data;
+extern atomic_t fscache_n_cookie_special;
+
+extern atomic_t fscache_n_object_alloc;
+extern atomic_t fscache_n_object_no_alloc;
+extern atomic_t fscache_n_object_lookups;
+extern atomic_t fscache_n_object_lookups_negative;
+extern atomic_t fscache_n_object_lookups_positive;
+extern atomic_t fscache_n_object_created;
+extern atomic_t fscache_n_object_avail;
+extern atomic_t fscache_n_object_dead;
+
+extern atomic_t fscache_n_checkaux_none;
+extern atomic_t fscache_n_checkaux_okay;
+extern atomic_t fscache_n_checkaux_update;
+extern atomic_t fscache_n_checkaux_obsolete;
+
+static inline void fscache_stat(atomic_t *stat)
+{
+	atomic_inc(stat);
+}
+
+extern const struct file_operations fscache_stats_fops;
+#else
+
+#define fscache_stat(stat) do {} while (0)
+#endif
+
+/*
+ * raise an event on an object
+ * - if the event is not masked for that object, then the object is
+ *   queued for attention by the thread pool.
+ */
+static inline void fscache_raise_event(struct fscache_object *object,
+				       unsigned event)
+{
+	if (!test_and_set_bit(event, &object->events) &&
+	    test_bit(event, &object->event_mask))
+		fscache_enqueue_object(object);
+}
+
+/*
+ * drop a reference to a cookie
+ */
+static inline void fscache_cookie_put(struct fscache_cookie *cookie)
+{
+	BUG_ON(atomic_read(&cookie->usage) <= 0);
+	if (atomic_dec_and_test(&cookie->usage))
+		__fscache_cookie_put(cookie);
+}
+
+/*
+ * get an extra reference to a netfs retrieval context
+ */
+static inline
+void *fscache_get_context(struct fscache_cookie *cookie, void *context)
+{
+	if (cookie->def->get_context)
+		cookie->def->get_context(cookie->netfs_data, context);
+	return context;
+}
+
+/*
+ * release a reference to a netfs retrieval context
+ */
+static inline
+void fscache_put_context(struct fscache_cookie *cookie, void *context)
+{
+	if (cookie->def->put_context)
+		cookie->def->put_context(cookie->netfs_data, context);
+}
+
+/*****************************************************************************/
+/*
+ * debug tracing
+ */
+#define dbgprintk(FMT, ...) \
+	printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+
+/* make sure we maintain the format strings, even when debugging is disabled */
+static inline __attribute__((format(printf, 1, 2)))
+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__)
+
+#define kjournal(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+
+#ifdef __KDEBUG
+#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
+#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
+#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
+
+#elif defined(CONFIG_FSCACHE_DEBUG)
+#define _enter(FMT, ...)			\
+do {						\
+	if (__do_kdebug(ENTER))			\
+		kenter(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _leave(FMT, ...)			\
+do {						\
+	if (__do_kdebug(LEAVE))			\
+		kleave(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _debug(FMT, ...)			\
+do {						\
+	if (__do_kdebug(DEBUG))			\
+		kdebug(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#else
+#define _enter(FMT, ...) _dbprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) _dbprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#endif
+
+/*
+ * determine whether a particular optional debugging point should be logged
+ * - we need to go through three steps to persuade cpp to correctly join the
+ *   shorthand in FSCACHE_DEBUG_LEVEL with its prefix
+ */
+#define ____do_kdebug(LEVEL, POINT) \
+	unlikely((fscache_debug & \
+		  (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3))))
+#define ___do_kdebug(LEVEL, POINT) \
+	____do_kdebug(LEVEL, POINT)
+#define __do_kdebug(POINT) \
+	___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT)
+
+#define FSCACHE_DEBUG_CACHE	0
+#define FSCACHE_DEBUG_COOKIE	1
+#define FSCACHE_DEBUG_PAGE	2
+#define FSCACHE_DEBUG_OPERATION	3
+
+#define FSCACHE_POINT_ENTER	1
+#define FSCACHE_POINT_LEAVE	2
+#define FSCACHE_POINT_DEBUG	4
+
+#ifndef FSCACHE_DEBUG_LEVEL
+#define FSCACHE_DEBUG_LEVEL CACHE
+#endif
+
+/*
+ * assertions
+ */
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		printk(KERN_ERR "%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIF(C, X)							\
+do {									\
+	if (unlikely((C) && !(X))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		printk(KERN_ERR "%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#else
+
+#define ASSERT(X)			do {} while (0)
+#define ASSERTCMP(X, OP, Y)		do {} while (0)
+#define ASSERTIF(C, X)			do {} while (0)
+#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
+
+#endif /* assert or not */

fs/fscache/main.c

@@ -0,0 +1,124 @@
+/* General filesystem local caching manager
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+MODULE_DESCRIPTION("FS Cache Manager");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+unsigned fscache_defer_lookup = 1;
+module_param_named(defer_lookup, fscache_defer_lookup, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_defer_lookup,
+		 "Defer cookie lookup to background thread");
+
+unsigned fscache_defer_create = 1;
+module_param_named(defer_create, fscache_defer_create, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_defer_create,
+		 "Defer cookie creation to background thread");
+
+unsigned fscache_debug;
+module_param_named(debug, fscache_debug, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_debug,
+		 "FS-Cache debugging mask");
+
+struct kobject *fscache_root;
+
+/*
+ * initialise the fs caching module
+ */
+static int __init fscache_init(void)
+{
+	int ret;
+
+	ret = slow_work_register_user();
+	if (ret < 0)
+		goto error_slow_work;
+
+	ret = fscache_proc_init();
+	if (ret < 0)
+		goto error_proc;
+
+	fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar",
+					       sizeof(struct fscache_cookie),
+					       0,
+					       0,
+					       fscache_cookie_init_once);
+	if (!fscache_cookie_jar) {
+		printk(KERN_NOTICE
+		       "FS-Cache: Failed to allocate a cookie jar\n");
+		ret = -ENOMEM;
+		goto error_cookie_jar;
+	}
+
+	fscache_root = kobject_create_and_add("fscache", kernel_kobj);
+	if (!fscache_root)
+		goto error_kobj;
+
+	printk(KERN_NOTICE "FS-Cache: Loaded\n");
+	return 0;
+
+error_kobj:
+	kmem_cache_destroy(fscache_cookie_jar);
+error_cookie_jar:
+	fscache_proc_cleanup();
+error_proc:
+	slow_work_unregister_user();
+error_slow_work:
+	return ret;
+}
+
+fs_initcall(fscache_init);
+
+/*
+ * clean up on module removal
+ */
+static void __exit fscache_exit(void)
+{
+	_enter("");
+
+	kobject_put(fscache_root);
+	kmem_cache_destroy(fscache_cookie_jar);
+	fscache_proc_cleanup();
+	slow_work_unregister_user();
+	printk(KERN_NOTICE "FS-Cache: Unloaded\n");
+}
+
+module_exit(fscache_exit);
+
+/*
+ * wait_on_bit() sleep function for uninterruptible waiting
+ */
+int fscache_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+EXPORT_SYMBOL(fscache_wait_bit);
+
+/*
+ * wait_on_bit() sleep function for interruptible waiting
+ */
+int fscache_wait_bit_interruptible(void *flags)
+{
+	schedule();
+	return signal_pending(current);
+}
+EXPORT_SYMBOL(fscache_wait_bit_interruptible);

fs/fscache/netfs.c

@@ -0,0 +1,103 @@
+/* FS-Cache netfs (client) registration
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+static LIST_HEAD(fscache_netfs_list);
+
+/*
+ * register a network filesystem for caching
+ */
+int __fscache_register_netfs(struct fscache_netfs *netfs)
+{
+	struct fscache_netfs *ptr;
+	int ret;
+
+	_enter("{%s}", netfs->name);
+
+	INIT_LIST_HEAD(&netfs->link);
+
+	/* allocate a cookie for the primary index */
+	netfs->primary_index =
+		kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL);
+
+	if (!netfs->primary_index) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	/* initialise the primary index cookie */
+	atomic_set(&netfs->primary_index->usage, 1);
+	atomic_set(&netfs->primary_index->n_children, 0);
+
+	netfs->primary_index->def		= &fscache_fsdef_netfs_def;
+	netfs->primary_index->parent		= &fscache_fsdef_index;
+	netfs->primary_index->netfs_data	= netfs;
+
+	atomic_inc(&netfs->primary_index->parent->usage);
+	atomic_inc(&netfs->primary_index->parent->n_children);
+
+	spin_lock_init(&netfs->primary_index->lock);
+	INIT_HLIST_HEAD(&netfs->primary_index->backing_objects);
+
+	/* check the netfs type is not already present */
+	down_write(&fscache_addremove_sem);
+
+	ret = -EEXIST;
+	list_for_each_entry(ptr, &fscache_netfs_list, link) {
+		if (strcmp(ptr->name, netfs->name) == 0)
+			goto already_registered;
+	}
+
+	list_add(&netfs->link, &fscache_netfs_list);
+	ret = 0;
+
+	printk(KERN_NOTICE "FS-Cache: Netfs '%s' registered for caching\n",
+	       netfs->name);
+
+already_registered:
+	up_write(&fscache_addremove_sem);
+
+	if (ret < 0) {
+		netfs->primary_index->parent = NULL;
+		__fscache_cookie_put(netfs->primary_index);
+		netfs->primary_index = NULL;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(__fscache_register_netfs);
+
+/*
+ * unregister a network filesystem from the cache
+ * - all cookies must have been released first
+ */
+void __fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+	_enter("{%s.%u}", netfs->name, netfs->version);
+
+	down_write(&fscache_addremove_sem);
+
+	list_del(&netfs->link);
+	fscache_relinquish_cookie(netfs->primary_index, 0);
+
+	up_write(&fscache_addremove_sem);
+
+	printk(KERN_NOTICE "FS-Cache: Netfs '%s' unregistered from caching\n",
+	       netfs->name);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_unregister_netfs);

fs/fscache/object.c

@@ -0,0 +1,810 @@
+/* FS-Cache object state machine handler
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/object.txt for a description of the
+ * object state machine and the in-kernel representations.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include "internal.h"
+
+const char *fscache_object_states[] = {
+	[FSCACHE_OBJECT_INIT]		= "OBJECT_INIT",
+	[FSCACHE_OBJECT_LOOKING_UP]	= "OBJECT_LOOKING_UP",
+	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
+	[FSCACHE_OBJECT_AVAILABLE]	= "OBJECT_AVAILABLE",
+	[FSCACHE_OBJECT_ACTIVE]		= "OBJECT_ACTIVE",
+	[FSCACHE_OBJECT_UPDATING]	= "OBJECT_UPDATING",
+	[FSCACHE_OBJECT_DYING]		= "OBJECT_DYING",
+	[FSCACHE_OBJECT_LC_DYING]	= "OBJECT_LC_DYING",
+	[FSCACHE_OBJECT_ABORT_INIT]	= "OBJECT_ABORT_INIT",
+	[FSCACHE_OBJECT_RELEASING]	= "OBJECT_RELEASING",
+	[FSCACHE_OBJECT_RECYCLING]	= "OBJECT_RECYCLING",
+	[FSCACHE_OBJECT_WITHDRAWING]	= "OBJECT_WITHDRAWING",
+	[FSCACHE_OBJECT_DEAD]		= "OBJECT_DEAD",
+};
+EXPORT_SYMBOL(fscache_object_states);
+
+static void fscache_object_slow_work_put_ref(struct slow_work *);
+static int  fscache_object_slow_work_get_ref(struct slow_work *);
+static void fscache_object_slow_work_execute(struct slow_work *);
+static void fscache_initialise_object(struct fscache_object *);
+static void fscache_lookup_object(struct fscache_object *);
+static void fscache_object_available(struct fscache_object *);
+static void fscache_release_object(struct fscache_object *);
+static void fscache_withdraw_object(struct fscache_object *);
+static void fscache_enqueue_dependents(struct fscache_object *);
+static void fscache_dequeue_object(struct fscache_object *);
+
+const struct slow_work_ops fscache_object_slow_work_ops = {
+	.get_ref	= fscache_object_slow_work_get_ref,
+	.put_ref	= fscache_object_slow_work_put_ref,
+	.execute	= fscache_object_slow_work_execute,
+};
+EXPORT_SYMBOL(fscache_object_slow_work_ops);
+
+/*
+ * we need to notify the parent when an op completes that we had outstanding
+ * upon it
+ */
+static inline void fscache_done_parent_op(struct fscache_object *object)
+{
+	struct fscache_object *parent = object->parent;
+
+	_enter("OBJ%x {OBJ%x,%x}",
+	       object->debug_id, parent->debug_id, parent->n_ops);
+
+	spin_lock_nested(&parent->lock, 1);
+	parent->n_ops--;
+	parent->n_obj_ops--;
+	if (parent->n_ops == 0)
+		fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+	spin_unlock(&parent->lock);
+}
+
+/*
+ * process events that have been sent to an object's state machine
+ * - initiates parent lookup
+ * - does object lookup
+ * - does object creation
+ * - does object recycling and retirement
+ * - does object withdrawal
+ */
+static void fscache_object_state_machine(struct fscache_object *object)
+{
+	enum fscache_object_state new_state;
+
+	ASSERT(object != NULL);
+
+	_enter("{OBJ%x,%s,%lx}",
+	       object->debug_id, fscache_object_states[object->state],
+	       object->events);
+
+	switch (object->state) {
+		/* wait for the parent object to become ready */
+	case FSCACHE_OBJECT_INIT:
+		object->event_mask =
+			ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+		fscache_initialise_object(object);
+		goto done;
+
+		/* look up the object metadata on disk */
+	case FSCACHE_OBJECT_LOOKING_UP:
+		fscache_lookup_object(object);
+		goto lookup_transit;
+
+		/* create the object metadata on disk */
+	case FSCACHE_OBJECT_CREATING:
+		fscache_lookup_object(object);
+		goto lookup_transit;
+
+		/* handle an object becoming available; start pending
+		 * operations and queue dependent operations for processing */
+	case FSCACHE_OBJECT_AVAILABLE:
+		fscache_object_available(object);
+		goto active_transit;
+
+		/* normal running state */
+	case FSCACHE_OBJECT_ACTIVE:
+		goto active_transit;
+
+		/* update the object metadata on disk */
+	case FSCACHE_OBJECT_UPDATING:
+		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
+		fscache_stat(&fscache_n_updates_run);
+		object->cache->ops->update_object(object);
+		goto active_transit;
+
+		/* handle an object dying during lookup or creation */
+	case FSCACHE_OBJECT_LC_DYING:
+		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+		object->cache->ops->lookup_complete(object);
+
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DYING;
+		if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+				       &object->cookie->flags))
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_CREATING);
+		spin_unlock(&object->lock);
+
+		fscache_done_parent_op(object);
+
+		/* wait for completion of all active operations on this object
+		 * and the death of all child objects of this object */
+	case FSCACHE_OBJECT_DYING:
+	dying:
+		clear_bit(FSCACHE_OBJECT_EV_CLEARED, &object->events);
+		spin_lock(&object->lock);
+		_debug("dying OBJ%x {%d,%d}",
+		       object->debug_id, object->n_ops, object->n_children);
+		if (object->n_ops == 0 && object->n_children == 0) {
+			object->event_mask &=
+				~(1 << FSCACHE_OBJECT_EV_CLEARED);
+			object->event_mask |=
+				(1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+				(1 << FSCACHE_OBJECT_EV_RETIRE) |
+				(1 << FSCACHE_OBJECT_EV_RELEASE) |
+				(1 << FSCACHE_OBJECT_EV_ERROR);
+		} else {
+			object->event_mask &=
+				~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+				  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+				  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+				  (1 << FSCACHE_OBJECT_EV_ERROR));
+			object->event_mask |=
+				1 << FSCACHE_OBJECT_EV_CLEARED;
+		}
+		spin_unlock(&object->lock);
+		fscache_enqueue_dependents(object);
+		goto terminal_transit;
+
+		/* handle an abort during initialisation */
+	case FSCACHE_OBJECT_ABORT_INIT:
+		_debug("handle abort init %lx", object->events);
+		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+
+		spin_lock(&object->lock);
+		fscache_dequeue_object(object);
+
+		object->state = FSCACHE_OBJECT_DYING;
+		if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+				       &object->cookie->flags))
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_CREATING);
+		spin_unlock(&object->lock);
+		goto dying;
+
+		/* handle the netfs releasing an object and possibly marking it
+		 * obsolete too */
+	case FSCACHE_OBJECT_RELEASING:
+	case FSCACHE_OBJECT_RECYCLING:
+		object->event_mask &=
+			~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+			  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			  (1 << FSCACHE_OBJECT_EV_ERROR));
+		fscache_release_object(object);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DEAD;
+		spin_unlock(&object->lock);
+		fscache_stat(&fscache_n_object_dead);
+		goto terminal_transit;
+
+		/* handle the parent cache of this object being withdrawn from
+		 * active service */
+	case FSCACHE_OBJECT_WITHDRAWING:
+		object->event_mask &=
+			~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+			  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			  (1 << FSCACHE_OBJECT_EV_ERROR));
+		fscache_withdraw_object(object);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DEAD;
+		spin_unlock(&object->lock);
+		fscache_stat(&fscache_n_object_dead);
+		goto terminal_transit;
+
+		/* complain about the object being woken up once it is
+		 * deceased */
+	case FSCACHE_OBJECT_DEAD:
+		printk(KERN_ERR "FS-Cache:"
+		       " Unexpected event in dead state %lx\n",
+		       object->events & object->event_mask);
+		BUG();
+
+	default:
+		printk(KERN_ERR "FS-Cache: Unknown object state %u\n",
+		       object->state);
+		BUG();
+	}
+
+	/* determine the transition from a lookup state */
+lookup_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+	case FSCACHE_OBJECT_EV_RETIRE:
+	case FSCACHE_OBJECT_EV_RELEASE:
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_LC_DYING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_REQUEUE:
+		goto done;
+	case -1:
+		goto done; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+	/* determine the transition from an active state */
+active_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+	case FSCACHE_OBJECT_EV_RETIRE:
+	case FSCACHE_OBJECT_EV_RELEASE:
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_DYING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_UPDATE:
+		new_state = FSCACHE_OBJECT_UPDATING;
+		goto change_state;
+	case -1:
+		new_state = FSCACHE_OBJECT_ACTIVE;
+		goto change_state; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+	/* determine the transition from a terminal state */
+terminal_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+		new_state = FSCACHE_OBJECT_WITHDRAWING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_RETIRE:
+		new_state = FSCACHE_OBJECT_RECYCLING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_RELEASE:
+		new_state = FSCACHE_OBJECT_RELEASING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_WITHDRAWING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_CLEARED:
+		new_state = FSCACHE_OBJECT_DYING;
+		goto change_state;
+	case -1:
+		goto done; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+change_state:
+	spin_lock(&object->lock);
+	object->state = new_state;
+	spin_unlock(&object->lock);
+
+done:
+	_leave(" [->%s]", fscache_object_states[object->state]);
+	return;
+
+unsupported_event:
+	printk(KERN_ERR "FS-Cache:"
+	       " Unsupported event %lx [mask %lx] in state %s\n",
+	       object->events, object->event_mask,
+	       fscache_object_states[object->state]);
+	BUG();
+}
+
+/*
+ * execute an object
+ */
+static void fscache_object_slow_work_execute(struct slow_work *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+	unsigned long start;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+
+	start = jiffies;
+	fscache_object_state_machine(object);
+	fscache_hist(fscache_objs_histogram, start);
+	if (object->events & object->event_mask)
+		fscache_enqueue_object(object);
+}
+
+/*
+ * initialise an object
+ * - check the specified object's parent to see if we can make use of it
+ *   immediately to do a creation
+ * - we may need to start the process of creating a parent and we need to wait
+ *   for the parent's lookup and creation to complete if it's not there yet
+ * - an object's cookie is pinned until we clear FSCACHE_COOKIE_CREATING on the
+ *   leaf-most cookies of the object and all its children
+ */
+static void fscache_initialise_object(struct fscache_object *object)
+{
+	struct fscache_object *parent;
+
+	_enter("");
+	ASSERT(object->cookie != NULL);
+	ASSERT(object->cookie->parent != NULL);
+	ASSERT(list_empty(&object->work.link));
+
+	if (object->events & ((1 << FSCACHE_OBJECT_EV_ERROR) |
+			      (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			      (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			      (1 << FSCACHE_OBJECT_EV_WITHDRAW))) {
+		_debug("abort init %lx", object->events);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_ABORT_INIT;
+		spin_unlock(&object->lock);
+		return;
+	}
+
+	spin_lock(&object->cookie->lock);
+	spin_lock_nested(&object->cookie->parent->lock, 1);
+
+	parent = object->parent;
+	if (!parent) {
+		_debug("no parent");
+		set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+	} else {
+		spin_lock(&object->lock);
+		spin_lock_nested(&parent->lock, 1);
+		_debug("parent %s", fscache_object_states[parent->state]);
+
+		if (parent->state >= FSCACHE_OBJECT_DYING) {
+			_debug("bad parent");
+			set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+		} else if (parent->state < FSCACHE_OBJECT_AVAILABLE) {
+			_debug("wait");
+
+			/* we may get woken up in this state by child objects
+			 * binding on to us, so we need to make sure we don't
+			 * add ourself to the list multiple times */
+			if (list_empty(&object->dep_link)) {
+				object->cache->ops->grab_object(object);
+				list_add(&object->dep_link,
+					 &parent->dependents);
+
+				/* fscache_acquire_non_index_cookie() uses this
+				 * to wake the chain up */
+				if (parent->state == FSCACHE_OBJECT_INIT)
+					fscache_enqueue_object(parent);
+			}
+		} else {
+			_debug("go");
+			parent->n_ops++;
+			parent->n_obj_ops++;
+			object->lookup_jif = jiffies;
+			object->state = FSCACHE_OBJECT_LOOKING_UP;
+			set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+		}
+
+		spin_unlock(&parent->lock);
+		spin_unlock(&object->lock);
+	}
+
+	spin_unlock(&object->cookie->parent->lock);
+	spin_unlock(&object->cookie->lock);
+	_leave("");
+}
+
+/*
+ * look an object up in the cache from which it was allocated
+ * - we hold an "access lock" on the parent object, so the parent object cannot
+ *   be withdrawn by either party till we've finished
+ * - an object's cookie is pinned until we clear FSCACHE_COOKIE_CREATING on the
+ *   leaf-most cookies of the object and all its children
+ */
+static void fscache_lookup_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_object *parent;
+
+	_enter("");
+
+	parent = object->parent;
+	ASSERT(parent != NULL);
+	ASSERTCMP(parent->n_ops, >, 0);
+	ASSERTCMP(parent->n_obj_ops, >, 0);
+
+	/* make sure the parent is still available */
+	ASSERTCMP(parent->state, >=, FSCACHE_OBJECT_AVAILABLE);
+
+	if (parent->state >= FSCACHE_OBJECT_DYING ||
+	    test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+		_debug("unavailable");
+		set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+		_leave("");
+		return;
+	}
+
+	_debug("LOOKUP \"%s/%s\" in \"%s\"",
+	       parent->cookie->def->name, cookie->def->name,
+	       object->cache->tag->name);
+
+	fscache_stat(&fscache_n_object_lookups);
+	object->cache->ops->lookup_object(object);
+
+	if (test_bit(FSCACHE_OBJECT_EV_ERROR, &object->events))
+		set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+
+	_leave("");
+}
+
+/**
+ * fscache_object_lookup_negative - Note negative cookie lookup
+ * @object: Object pointing to cookie to mark
+ *
+ * Note negative lookup, permitting those waiting to read data from an already
+ * existing backing object to continue as there's no data for them to read.
+ */
+void fscache_object_lookup_negative(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x,%s}",
+	       object->debug_id, fscache_object_states[object->state]);
+
+	spin_lock(&object->lock);
+	if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
+		fscache_stat(&fscache_n_object_lookups_negative);
+
+		/* transit here to allow write requests to begin stacking up
+		 * and read requests to begin returning ENODATA */
+		object->state = FSCACHE_OBJECT_CREATING;
+		spin_unlock(&object->lock);
+
+		set_bit(FSCACHE_COOKIE_PENDING_FILL, &cookie->flags);
+		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+		_debug("wake up lookup %p", &cookie->flags);
+		smp_mb__before_clear_bit();
+		clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	} else {
+		ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
+		spin_unlock(&object->lock);
+	}
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_object_lookup_negative);
+
+/**
+ * fscache_obtained_object - Note successful object lookup or creation
+ * @object: Object pointing to cookie to mark
+ *
+ * Note successful lookup and/or creation, permitting those waiting to write
+ * data to a backing object to continue.
+ *
+ * Note that after calling this, an object's cookie may be relinquished by the
+ * netfs, and so must be accessed with object lock held.
+ */
+void fscache_obtained_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x,%s}",
+	       object->debug_id, fscache_object_states[object->state]);
+
+	/* if we were still looking up, then we must have a positive lookup
+	 * result, in which case there may be data available */
+	spin_lock(&object->lock);
+	if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
+		fscache_stat(&fscache_n_object_lookups_positive);
+
+		clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+		object->state = FSCACHE_OBJECT_AVAILABLE;
+		spin_unlock(&object->lock);
+
+		smp_mb__before_clear_bit();
+		clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	} else {
+		ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
+		fscache_stat(&fscache_n_object_created);
+
+		object->state = FSCACHE_OBJECT_AVAILABLE;
+		spin_unlock(&object->lock);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+		smp_wmb();
+	}
+
+	if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_CREATING);
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_obtained_object);
+
+/*
+ * handle an object that has just become available
+ */
+static void fscache_object_available(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags))
+		wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING);
+
+	fscache_done_parent_op(object);
+	if (object->n_in_progress == 0) {
+		if (object->n_ops > 0) {
+			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
+			ASSERTIF(object->n_ops > object->n_obj_ops,
+				 !list_empty(&object->pending_ops));
+			fscache_start_operations(object);
+		} else {
+			ASSERT(list_empty(&object->pending_ops));
+		}
+	}
+	spin_unlock(&object->lock);
+
+	object->cache->ops->lookup_complete(object);
+	fscache_enqueue_dependents(object);
+
+	fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif);
+	fscache_stat(&fscache_n_object_avail);
+
+	_leave("");
+}
+
+/*
+ * drop an object's attachments
+ */
+static void fscache_drop_object(struct fscache_object *object)
+{
+	struct fscache_object *parent = object->parent;
+	struct fscache_cache *cache = object->cache;
+
+	_enter("{OBJ%x,%d}", object->debug_id, object->n_children);
+
+	spin_lock(&cache->object_list_lock);
+	list_del_init(&object->cache_link);
+	spin_unlock(&cache->object_list_lock);
+
+	cache->ops->drop_object(object);
+
+	if (parent) {
+		_debug("release parent OBJ%x {%d}",
+		       parent->debug_id, parent->n_children);
+
+		spin_lock(&parent->lock);
+		parent->n_children--;
+		if (parent->n_children == 0)
+			fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+		spin_unlock(&parent->lock);
+		object->parent = NULL;
+	}
+
+	/* this just shifts the object release to the slow work processor */
+	object->cache->ops->put_object(object);
+
+	_leave("");
+}
+
+/*
+ * release or recycle an object that the netfs has discarded
+ */
+static void fscache_release_object(struct fscache_object *object)
+{
+	_enter("");
+
+	fscache_drop_object(object);
+}
+
+/*
+ * withdraw an object from active service
+ */
+static void fscache_withdraw_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie;
+	bool detached;
+
+	_enter("");
+
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+	if (cookie) {
+		/* need to get the cookie lock before the object lock, starting
+		 * from the object pointer */
+		atomic_inc(&cookie->usage);
+		spin_unlock(&object->lock);
+
+		detached = false;
+		spin_lock(&cookie->lock);
+		spin_lock(&object->lock);
+
+		if (object->cookie == cookie) {
+			hlist_del_init(&object->cookie_link);
+			object->cookie = NULL;
+			detached = true;
+		}
+		spin_unlock(&cookie->lock);
+		fscache_cookie_put(cookie);
+		if (detached)
+			fscache_cookie_put(cookie);
+	}
+
+	spin_unlock(&object->lock);
+
+	fscache_drop_object(object);
+}
+
+/*
+ * withdraw an object from active service at the behest of the cache
+ * - need break the links to a cached object cookie
+ * - called under two situations:
+ *   (1) recycler decides to reclaim an in-use object
+ *   (2) a cache is unmounted
+ * - have to take care as the cookie can be being relinquished by the netfs
+ *   simultaneously
+ * - the object is pinned by the caller holding a refcount on it
+ */
+void fscache_withdrawing_object(struct fscache_cache *cache,
+				struct fscache_object *object)
+{
+	bool enqueue = false;
+
+	_enter(",OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+	if (object->state < FSCACHE_OBJECT_WITHDRAWING) {
+		object->state = FSCACHE_OBJECT_WITHDRAWING;
+		enqueue = true;
+	}
+	spin_unlock(&object->lock);
+
+	if (enqueue)
+		fscache_enqueue_object(object);
+
+	_leave("");
+}
+
+/*
+ * allow the slow work item processor to get a ref on an object
+ */
+static int fscache_object_slow_work_get_ref(struct slow_work *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+
+	return object->cache->ops->grab_object(object) ? 0 : -EAGAIN;
+}
+
+/*
+ * allow the slow work item processor to discard a ref on a work item
+ */
+static void fscache_object_slow_work_put_ref(struct slow_work *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+
+	return object->cache->ops->put_object(object);
+}
+
+/*
+ * enqueue an object for metadata-type processing
+ */
+void fscache_enqueue_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	slow_work_enqueue(&object->work);
+}
+
+/*
+ * enqueue the dependents of an object for metadata-type processing
+ * - the caller must hold the object's lock
+ * - this may cause an already locked object to wind up being processed again
+ */
+static void fscache_enqueue_dependents(struct fscache_object *object)
+{
+	struct fscache_object *dep;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (list_empty(&object->dependents))
+		return;
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->dependents)) {
+		dep = list_entry(object->dependents.next,
+				 struct fscache_object, dep_link);
+		list_del_init(&dep->dep_link);
+
+
+		/* sort onto appropriate lists */
+		fscache_enqueue_object(dep);
+		dep->cache->ops->put_object(dep);
+
+		if (!list_empty(&object->dependents))
+			cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+}
+
+/*
+ * remove an object from whatever queue it's waiting on
+ * - the caller must hold object->lock
+ */
+void fscache_dequeue_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (!list_empty(&object->dep_link)) {
+		spin_lock(&object->parent->lock);
+		list_del_init(&object->dep_link);
+		spin_unlock(&object->parent->lock);
+	}
+
+	_leave("");
+}
+
+/**
+ * fscache_check_aux - Ask the netfs whether an object on disk is still valid
+ * @object: The object to ask about
+ * @data: The auxiliary data for the object
+ * @datalen: The size of the auxiliary data
+ *
+ * This function consults the netfs about the coherency state of an object
+ */
+enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+					const void *data, uint16_t datalen)
+{
+	enum fscache_checkaux result;
+
+	if (!object->cookie->def->check_aux) {
+		fscache_stat(&fscache_n_checkaux_none);
+		return FSCACHE_CHECKAUX_OKAY;
+	}
+
+	result = object->cookie->def->check_aux(object->cookie->netfs_data,
+						data, datalen);
+	switch (result) {
+		/* entry okay as is */
+	case FSCACHE_CHECKAUX_OKAY:
+		fscache_stat(&fscache_n_checkaux_okay);
+		break;
+
+		/* entry requires update */
+	case FSCACHE_CHECKAUX_NEEDS_UPDATE:
+		fscache_stat(&fscache_n_checkaux_update);
+		break;
+
+		/* entry requires deletion */
+	case FSCACHE_CHECKAUX_OBSOLETE:
+		fscache_stat(&fscache_n_checkaux_obsolete);
+		break;
+
+	default:
+		BUG();
+	}
+
+	return result;
+}
+EXPORT_SYMBOL(fscache_check_aux);

fs/fscache/operation.c

@@ -0,0 +1,459 @@
+/* FS-Cache worker operation management routines
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/operations.txt
+ */
+
+#define FSCACHE_DEBUG_LEVEL OPERATION
+#include <linux/module.h>
+#include "internal.h"
+
+atomic_t fscache_op_debug_id;
+EXPORT_SYMBOL(fscache_op_debug_id);
+
+/**
+ * fscache_enqueue_operation - Enqueue an operation for processing
+ * @op: The operation to enqueue
+ *
+ * Enqueue an operation for processing by the FS-Cache thread pool.
+ *
+ * This will get its own ref on the object.
+ */
+void fscache_enqueue_operation(struct fscache_operation *op)
+{
+	_enter("{OBJ%x OP%x,%u}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERT(op->processor != NULL);
+	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	if (list_empty(&op->pend_link)) {
+		switch (op->flags & FSCACHE_OP_TYPE) {
+		case FSCACHE_OP_FAST:
+			_debug("queue fast");
+			atomic_inc(&op->usage);
+			if (!schedule_work(&op->fast_work))
+				fscache_put_operation(op);
+			break;
+		case FSCACHE_OP_SLOW:
+			_debug("queue slow");
+			slow_work_enqueue(&op->slow_work);
+			break;
+		case FSCACHE_OP_MYTHREAD:
+			_debug("queue for caller's attention");
+			break;
+		default:
+			printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
+			       op->flags);
+			BUG();
+			break;
+		}
+		fscache_stat(&fscache_n_op_enqueue);
+	}
+}
+EXPORT_SYMBOL(fscache_enqueue_operation);
+
+/*
+ * start an op running
+ */
+static void fscache_run_op(struct fscache_object *object,
+			   struct fscache_operation *op)
+{
+	object->n_in_progress++;
+	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+	if (op->processor)
+		fscache_enqueue_operation(op);
+	fscache_stat(&fscache_n_op_run);
+}
+
+/*
+ * submit an exclusive operation for an object
+ * - other ops are excluded from running simultaneously with this one
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_exclusive_op(struct fscache_object *object,
+				struct fscache_operation *op)
+{
+	int ret;
+
+	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+
+	ret = -ENOBUFS;
+	if (fscache_object_is_active(object)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+
+		if (object->n_ops > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_in_progress, ==, 0);
+			fscache_run_op(object, op);
+		}
+
+		/* need to issue a new write op after this */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		ret = 0;
+	} else if (object->state == FSCACHE_OBJECT_CREATING) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else {
+		/* not allowed to submit ops in any other state */
+		BUG();
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * report an unexpected submission
+ */
+static void fscache_report_unexpected_submission(struct fscache_object *object,
+						 struct fscache_operation *op,
+						 unsigned long ostate)
+{
+	static bool once_only;
+	struct fscache_operation *p;
+	unsigned n;
+
+	if (once_only)
+		return;
+	once_only = true;
+
+	kdebug("unexpected submission OP%x [OBJ%x %s]",
+	       op->debug_id, object->debug_id,
+	       fscache_object_states[object->state]);
+	kdebug("objstate=%s [%s]",
+	       fscache_object_states[object->state],
+	       fscache_object_states[ostate]);
+	kdebug("objflags=%lx", object->flags);
+	kdebug("objevent=%lx [%lx]", object->events, object->event_mask);
+	kdebug("ops=%u inp=%u exc=%u",
+	       object->n_ops, object->n_in_progress, object->n_exclusive);
+
+	if (!list_empty(&object->pending_ops)) {
+		n = 0;
+		list_for_each_entry(p, &object->pending_ops, pend_link) {
+			ASSERTCMP(p->object, ==, object);
+			kdebug("%p %p", op->processor, op->release);
+			n++;
+		}
+
+		kdebug("n=%u", n);
+	}
+
+	dump_stack();
+}
+
+/*
+ * submit an operation for an object
+ * - objects may be submitted only in the following states:
+ *   - during object creation (write ops may be submitted)
+ *   - whilst the object is active
+ *   - after an I/O error incurred in one of the two above states (op rejected)
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_op(struct fscache_object *object,
+		      struct fscache_operation *op)
+{
+	unsigned long ostate;
+	int ret;
+
+	_enter("{OBJ%x OP%x},{%u}",
+	       object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+
+	ostate = object->state;
+	smp_rmb();
+
+	if (fscache_object_is_active(object)) {
+		op->object = object;
+		object->n_ops++;
+
+		if (object->n_exclusive > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_exclusive, ==, 0);
+			fscache_run_op(object, op);
+		}
+		ret = 0;
+	} else if (object->state == FSCACHE_OBJECT_CREATING) {
+		op->object = object;
+		object->n_ops++;
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+		fscache_report_unexpected_submission(object, op, ostate);
+		ASSERT(!fscache_object_is_active(object));
+		ret = -ENOBUFS;
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * queue an object for withdrawal on error, aborting all following asynchronous
+ * operations
+ */
+void fscache_abort_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+}
+
+/*
+ * jump start the operation processing on an object
+ * - caller must hold object->lock
+ */
+void fscache_start_operations(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+	bool stop = false;
+
+	while (!list_empty(&object->pending_ops) && !stop) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+			if (object->n_in_progress > 0)
+				break;
+			stop = true;
+		}
+		list_del_init(&op->pend_link);
+		object->n_in_progress++;
+
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		if (op->processor)
+			fscache_enqueue_operation(op);
+
+		/* the pending queue was holding a ref on the object */
+		fscache_put_operation(op);
+	}
+
+	ASSERTCMP(object->n_in_progress, <=, object->n_ops);
+
+	_debug("woke %d ops on OBJ%x",
+	       object->n_in_progress, object->debug_id);
+}
+
+/*
+ * release an operation
+ * - queues pending ops if this is the last in-progress op
+ */
+void fscache_put_operation(struct fscache_operation *op)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+
+	_enter("{OBJ%x OP%x,%d}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	if (!atomic_dec_and_test(&op->usage))
+		return;
+
+	_debug("PUT OP");
+	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
+		BUG();
+
+	fscache_stat(&fscache_n_op_release);
+
+	if (op->release) {
+		op->release(op);
+		op->release = NULL;
+	}
+
+	object = op->object;
+
+	/* now... we may get called with the object spinlock held, so we
+	 * complete the cleanup here only if we can immediately acquire the
+	 * lock, and defer it otherwise */
+	if (!spin_trylock(&object->lock)) {
+		_debug("defer put");
+		fscache_stat(&fscache_n_op_deferred_release);
+
+		cache = object->cache;
+		spin_lock(&cache->op_gc_list_lock);
+		list_add_tail(&op->pend_link, &cache->op_gc_list);
+		spin_unlock(&cache->op_gc_list_lock);
+		schedule_work(&cache->op_gc);
+		_leave(" [defer]");
+		return;
+	}
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+		ASSERTCMP(object->n_exclusive, >, 0);
+		object->n_exclusive--;
+	}
+
+	ASSERTCMP(object->n_in_progress, >, 0);
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	ASSERTCMP(object->n_ops, >, 0);
+	object->n_ops--;
+	if (object->n_ops == 0)
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+	spin_unlock(&object->lock);
+
+	kfree(op);
+	_leave(" [done]");
+}
+EXPORT_SYMBOL(fscache_put_operation);
+
+/*
+ * garbage collect operations that have had their release deferred
+ */
+void fscache_operation_gc(struct work_struct *work)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+	struct fscache_cache *cache =
+		container_of(work, struct fscache_cache, op_gc);
+	int count = 0;
+
+	_enter("");
+
+	do {
+		spin_lock(&cache->op_gc_list_lock);
+		if (list_empty(&cache->op_gc_list)) {
+			spin_unlock(&cache->op_gc_list_lock);
+			break;
+		}
+
+		op = list_entry(cache->op_gc_list.next,
+				struct fscache_operation, pend_link);
+		list_del(&op->pend_link);
+		spin_unlock(&cache->op_gc_list_lock);
+
+		object = op->object;
+
+		_debug("GC DEFERRED REL OBJ%x OP%x",
+		       object->debug_id, op->debug_id);
+		fscache_stat(&fscache_n_op_gc);
+
+		ASSERTCMP(atomic_read(&op->usage), ==, 0);
+
+		spin_lock(&object->lock);
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+			ASSERTCMP(object->n_exclusive, >, 0);
+			object->n_exclusive--;
+		}
+
+		ASSERTCMP(object->n_in_progress, >, 0);
+		object->n_in_progress--;
+		if (object->n_in_progress == 0)
+			fscache_start_operations(object);
+
+		ASSERTCMP(object->n_ops, >, 0);
+		object->n_ops--;
+		if (object->n_ops == 0)
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+		spin_unlock(&object->lock);
+
+	} while (count++ < 20);
+
+	if (!list_empty(&cache->op_gc_list))
+		schedule_work(&cache->op_gc);
+
+	_leave("");
+}
+
+/*
+ * allow the slow work item processor to get a ref on an operation
+ */
+static int fscache_op_get_ref(struct slow_work *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+
+	atomic_inc(&op->usage);
+	return 0;
+}
+
+/*
+ * allow the slow work item processor to discard a ref on an operation
+ */
+static void fscache_op_put_ref(struct slow_work *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+
+	fscache_put_operation(op);
+}
+
+/*
+ * execute an operation using the slow thread pool to provide processing context
+ * - the caller holds a ref to this object, so we don't need to hold one
+ */
+static void fscache_op_execute(struct slow_work *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+	unsigned long start;
+
+	_enter("{OBJ%x OP%x,%d}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERT(op->processor != NULL);
+	start = jiffies;
+	op->processor(op);
+	fscache_hist(fscache_ops_histogram, start);
+
+	_leave("");
+}
+
+const struct slow_work_ops fscache_op_slow_work_ops = {
+	.get_ref	= fscache_op_get_ref,
+	.put_ref	= fscache_op_put_ref,
+	.execute	= fscache_op_execute,
+};

fs/fscache/page.c

@@ -0,0 +1,816 @@
+/* Cache page management and data I/O routines
+ *
+ * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL PAGE
+#include <linux/module.h>
+#include <linux/fscache-cache.h>
+#include <linux/buffer_head.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/*
+ * check to see if a page is being written to the cache
+ */
+bool __fscache_check_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	void *val;
+
+	rcu_read_lock();
+	val = radix_tree_lookup(&cookie->stores, page->index);
+	rcu_read_unlock();
+
+	return val != NULL;
+}
+EXPORT_SYMBOL(__fscache_check_page_write);
+
+/*
+ * wait for a page to finish being written to the cache
+ */
+void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0);
+
+	wait_event(*wq, !__fscache_check_page_write(cookie, page));
+}
+EXPORT_SYMBOL(__fscache_wait_on_page_write);
+
+/*
+ * note that a page has finished being written to the cache
+ */
+static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	struct page *xpage;
+
+	spin_lock(&cookie->lock);
+	xpage = radix_tree_delete(&cookie->stores, page->index);
+	spin_unlock(&cookie->lock);
+	ASSERT(xpage != NULL);
+
+	wake_up_bit(&cookie->flags, 0);
+}
+
+/*
+ * actually apply the changed attributes to a cache object
+ */
+static void fscache_attr_changed_op(struct fscache_operation *op)
+{
+	struct fscache_object *object = op->object;
+
+	_enter("{OBJ%x OP%x}", object->debug_id, op->debug_id);
+
+	fscache_stat(&fscache_n_attr_changed_calls);
+
+	if (fscache_object_is_active(object) &&
+	    object->cache->ops->attr_changed(object) < 0)
+		fscache_abort_object(object);
+
+	_leave("");
+}
+
+/*
+ * notification that the attributes on an object have changed
+ */
+int __fscache_attr_changed(struct fscache_cookie *cookie)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+
+	_enter("%p", cookie);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+
+	fscache_stat(&fscache_n_attr_changed);
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op) {
+		fscache_stat(&fscache_n_attr_changed_nomem);
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	fscache_operation_init(op, NULL);
+	fscache_operation_init_slow(op, fscache_attr_changed_op);
+	op->flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_EXCLUSIVE);
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto nobufs;
+	spin_unlock(&cookie->lock);
+	fscache_stat(&fscache_n_attr_changed_ok);
+	fscache_put_operation(op);
+	_leave(" = 0");
+	return 0;
+
+nobufs:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	fscache_stat(&fscache_n_attr_changed_nobufs);
+	_leave(" = %d", -ENOBUFS);
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_attr_changed);
+
+/*
+ * handle secondary execution given to a retrieval op on behalf of the
+ * cache
+ */
+static void fscache_retrieval_work(struct work_struct *work)
+{
+	struct fscache_retrieval *op =
+		container_of(work, struct fscache_retrieval, op.fast_work);
+	unsigned long start;
+
+	_enter("{OP%x}", op->op.debug_id);
+
+	start = jiffies;
+	op->op.processor(&op->op);
+	fscache_hist(fscache_ops_histogram, start);
+	fscache_put_operation(&op->op);
+}
+
+/*
+ * release a retrieval op reference
+ */
+static void fscache_release_retrieval_op(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	_enter("{OP%x}", op->op.debug_id);
+
+	fscache_hist(fscache_retrieval_histogram, op->start_time);
+	if (op->context)
+		fscache_put_context(op->op.object->cookie, op->context);
+
+	_leave("");
+}
+
+/*
+ * allocate a retrieval op
+ */
+static struct fscache_retrieval *fscache_alloc_retrieval(
+	struct address_space *mapping,
+	fscache_rw_complete_t end_io_func,
+	void *context)
+{
+	struct fscache_retrieval *op;
+
+	/* allocate a retrieval operation and attempt to submit it */
+	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (!op) {
+		fscache_stat(&fscache_n_retrievals_nomem);
+		return NULL;
+	}
+
+	fscache_operation_init(&op->op, fscache_release_retrieval_op);
+	op->op.flags	= FSCACHE_OP_MYTHREAD | (1 << FSCACHE_OP_WAITING);
+	op->mapping	= mapping;
+	op->end_io_func	= end_io_func;
+	op->context	= context;
+	op->start_time	= jiffies;
+	INIT_WORK(&op->op.fast_work, fscache_retrieval_work);
+	INIT_LIST_HEAD(&op->to_do);
+	return op;
+}
+
+/*
+ * wait for a deferred lookup to complete
+ */
+static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
+{
+	unsigned long jif;
+
+	_enter("");
+
+	if (!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) {
+		_leave(" = 0 [imm]");
+		return 0;
+	}
+
+	fscache_stat(&fscache_n_retrievals_wait);
+
+	jif = jiffies;
+	if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
+			fscache_wait_bit_interruptible,
+			TASK_INTERRUPTIBLE) != 0) {
+		fscache_stat(&fscache_n_retrievals_intr);
+		_leave(" = -ERESTARTSYS");
+		return -ERESTARTSYS;
+	}
+
+	ASSERT(!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags));
+
+	smp_rmb();
+	fscache_hist(fscache_retrieval_delay_histogram, jif);
+	_leave(" = 0 [dly]");
+	return 0;
+}
+
+/*
+ * read a page from the cache or allocate a block in which to store it
+ * - we return:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ERESTARTSYS - interrupted
+ *   -ENOBUFS	- no backing object available in which to cache the block
+ *   -ENODATA	- no data available in the backing object for this block
+ *   0		- dispatched a read - it'll call end_io_func() when finished
+ */
+int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+				 struct page *page,
+				 fscache_rw_complete_t end_io_func,
+				 void *context,
+				 gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(page->mapping, end_io_func, context);
+	if (!op) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure */
+	fscache_get_context(object->cookie, op->context);
+
+	/* we wait for the operation to become active, and then process it
+	 * *here*, in this thread, and not in the thread pool */
+	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+		_debug(">>> WT");
+		fscache_stat(&fscache_n_retrieval_op_waits);
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("<<< GO");
+	}
+
+	/* ask the cache to honour the operation */
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) {
+		ret = object->cache->ops->allocate_page(op, page, gfp);
+		if (ret == 0)
+			ret = -ENODATA;
+	} else {
+		ret = object->cache->ops->read_or_alloc_page(op, page, gfp);
+	}
+
+	if (ret == -ENOMEM)
+		fscache_stat(&fscache_n_retrievals_nomem);
+	else if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_retrievals_intr);
+	else if (ret == -ENODATA)
+		fscache_stat(&fscache_n_retrievals_nodata);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_retrievals_nobufs);
+	else
+		fscache_stat(&fscache_n_retrievals_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_retrievals_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_read_or_alloc_page);
+
+/*
+ * read a list of page from the cache or allocate a block in which to store
+ * them
+ * - we return:
+ *   -ENOMEM	- out of memory, some pages may be being read
+ *   -ERESTARTSYS - interrupted, some pages may be being read
+ *   -ENOBUFS	- no backing object or space available in which to cache any
+ *                pages not being read
+ *   -ENODATA	- no data available in the backing object for some or all of
+ *                the pages
+ *   0		- dispatched a read on all pages
+ *
+ * end_io_func() will be called for each page read from the cache as it is
+ * finishes being read
+ *
+ * any pages for which a read is dispatched will be removed from pages and
+ * nr_pages
+ */
+int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages,
+				  fscache_rw_complete_t end_io_func,
+				  void *context,
+				  gfp_t gfp)
+{
+	fscache_pages_retrieval_func_t func;
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,,%d,,,", cookie, *nr_pages);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(*nr_pages, >, 0);
+	ASSERT(!list_empty(pages));
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(mapping, end_io_func, context);
+	if (!op)
+		return -ENOMEM;
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure */
+	fscache_get_context(object->cookie, op->context);
+
+	/* we wait for the operation to become active, and then process it
+	 * *here*, in this thread, and not in the thread pool */
+	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+		_debug(">>> WT");
+		fscache_stat(&fscache_n_retrieval_op_waits);
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("<<< GO");
+	}
+
+	/* ask the cache to honour the operation */
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags))
+		func = object->cache->ops->allocate_pages;
+	else
+		func = object->cache->ops->read_or_alloc_pages;
+	ret = func(op, pages, nr_pages, gfp);
+
+	if (ret == -ENOMEM)
+		fscache_stat(&fscache_n_retrievals_nomem);
+	else if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_retrievals_intr);
+	else if (ret == -ENODATA)
+		fscache_stat(&fscache_n_retrievals_nodata);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_retrievals_nobufs);
+	else
+		fscache_stat(&fscache_n_retrievals_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_retrievals_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_read_or_alloc_pages);
+
+/*
+ * allocate a block in the cache on which to store a page
+ * - we return:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ERESTARTSYS - interrupted
+ *   -ENOBUFS	- no backing object available in which to cache the block
+ *   0		- block allocated
+ */
+int __fscache_alloc_page(struct fscache_cookie *cookie,
+			 struct page *page,
+			 gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_allocs);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
+	if (!op)
+		return -ENOMEM;
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_alloc_ops);
+
+	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+		_debug(">>> WT");
+		fscache_stat(&fscache_n_alloc_op_waits);
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("<<< GO");
+	}
+
+	/* ask the cache to honour the operation */
+	ret = object->cache->ops->allocate_page(op, page, gfp);
+
+	if (ret < 0)
+		fscache_stat(&fscache_n_allocs_nobufs);
+	else
+		fscache_stat(&fscache_n_allocs_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_allocs_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_alloc_page);
+
+/*
+ * release a write op reference
+ */
+static void fscache_release_write_op(struct fscache_operation *_op)
+{
+	_enter("{OP%x}", _op->debug_id);
+}
+
+/*
+ * perform the background storage of a page into the cache
+ */
+static void fscache_write_op(struct fscache_operation *_op)
+{
+	struct fscache_storage *op =
+		container_of(_op, struct fscache_storage, op);
+	struct fscache_object *object = op->op.object;
+	struct fscache_cookie *cookie = object->cookie;
+	struct page *page;
+	unsigned n;
+	void *results[1];
+	int ret;
+
+	_enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage));
+
+	spin_lock(&cookie->lock);
+	spin_lock(&object->lock);
+
+	if (!fscache_object_is_active(object)) {
+		spin_unlock(&object->lock);
+		spin_unlock(&cookie->lock);
+		_leave("");
+		return;
+	}
+
+	fscache_stat(&fscache_n_store_calls);
+
+	/* find a page to store */
+	page = NULL;
+	n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, 1,
+				       FSCACHE_COOKIE_PENDING_TAG);
+	if (n != 1)
+		goto superseded;
+	page = results[0];
+	_debug("gang %d [%lx]", n, page->index);
+	if (page->index > op->store_limit)
+		goto superseded;
+
+	radix_tree_tag_clear(&cookie->stores, page->index,
+			     FSCACHE_COOKIE_PENDING_TAG);
+
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+
+	if (page) {
+		ret = object->cache->ops->write_page(op, page);
+		fscache_end_page_write(cookie, page);
+		page_cache_release(page);
+		if (ret < 0)
+			fscache_abort_object(object);
+		else
+			fscache_enqueue_operation(&op->op);
+	}
+
+	_leave("");
+	return;
+
+superseded:
+	/* this writer is going away and there aren't any more things to
+	 * write */
+	_debug("cease");
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+	_leave("");
+}
+
+/*
+ * request a page be stored in the cache
+ * - returns:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ENOBUFS	- no backing object available in which to cache the page
+ *   0		- dispatched a write - it'll call end_io_func() when finished
+ *
+ * if the cookie still has a backing object at this point, that object can be
+ * in one of a few states with respect to storage processing:
+ *
+ *  (1) negative lookup, object not yet created (FSCACHE_COOKIE_CREATING is
+ *      set)
+ *
+ *	(a) no writes yet (set FSCACHE_COOKIE_PENDING_FILL and queue deferred
+ *	    fill op)
+ *
+ *	(b) writes deferred till post-creation (mark page for writing and
+ *	    return immediately)
+ *
+ *  (2) negative lookup, object created, initial fill being made from netfs
+ *      (FSCACHE_COOKIE_INITIAL_FILL is set)
+ *
+ *	(a) fill point not yet reached this page (mark page for writing and
+ *          return)
+ *
+ *	(b) fill point passed this page (queue op to store this page)
+ *
+ *  (3) object extant (queue op to store this page)
+ *
+ * any other state is invalid
+ */
+int __fscache_write_page(struct fscache_cookie *cookie,
+			 struct page *page,
+			 gfp_t gfp)
+{
+	struct fscache_storage *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%x,", cookie, (u32) page->flags);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERT(PageFsCache(page));
+
+	fscache_stat(&fscache_n_stores);
+
+	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (!op)
+		goto nomem;
+
+	fscache_operation_init(&op->op, fscache_release_write_op);
+	fscache_operation_init_slow(&op->op, fscache_write_op);
+	op->op.flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_WAITING);
+
+	ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
+	if (ret < 0)
+		goto nomem_free;
+
+	ret = -ENOBUFS;
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+	if (test_bit(FSCACHE_IOERROR, &object->cache->flags))
+		goto nobufs;
+
+	/* add the page to the pending-storage radix tree on the backing
+	 * object */
+	spin_lock(&object->lock);
+
+	_debug("store limit %llx", (unsigned long long) object->store_limit);
+
+	ret = radix_tree_insert(&cookie->stores, page->index, page);
+	if (ret < 0) {
+		if (ret == -EEXIST)
+			goto already_queued;
+		_debug("insert failed %d", ret);
+		goto nobufs_unlock_obj;
+	}
+
+	radix_tree_tag_set(&cookie->stores, page->index,
+			   FSCACHE_COOKIE_PENDING_TAG);
+	page_cache_get(page);
+
+	/* we only want one writer at a time, but we do need to queue new
+	 * writers after exclusive ops */
+	if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags))
+		goto already_pending;
+
+	spin_unlock(&object->lock);
+
+	op->op.debug_id	= atomic_inc_return(&fscache_op_debug_id);
+	op->store_limit = object->store_limit;
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto submit_failed;
+
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	fscache_stat(&fscache_n_store_ops);
+	fscache_stat(&fscache_n_stores_ok);
+
+	/* the slow work queue now carries its own ref on the object */
+	fscache_put_operation(&op->op);
+	_leave(" = 0");
+	return 0;
+
+already_queued:
+	fscache_stat(&fscache_n_stores_again);
+already_pending:
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	kfree(op);
+	fscache_stat(&fscache_n_stores_ok);
+	_leave(" = 0");
+	return 0;
+
+submit_failed:
+	radix_tree_delete(&cookie->stores, page->index);
+	page_cache_release(page);
+	ret = -ENOBUFS;
+	goto nobufs;
+
+nobufs_unlock_obj:
+	spin_unlock(&object->lock);
+nobufs:
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	kfree(op);
+	fscache_stat(&fscache_n_stores_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+
+nomem_free:
+	kfree(op);
+nomem:
+	fscache_stat(&fscache_n_stores_oom);
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(__fscache_write_page);
+
+/*
+ * remove a page from the cache
+ */
+void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page)
+{
+	struct fscache_object *object;
+
+	_enter(",%p", page);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	fscache_stat(&fscache_n_uncaches);
+
+	/* cache withdrawal may beat us to it */
+	if (!PageFsCache(page))
+		goto done;
+
+	/* get the object */
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects)) {
+		ClearPageFsCache(page);
+		goto done_unlock;
+	}
+
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	/* there might now be stuff on disk we could read */
+	clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* only invoke the cache backend if we managed to mark the page
+	 * uncached here; this deals with synchronisation vs withdrawal */
+	if (TestClearPageFsCache(page) &&
+	    object->cache->ops->uncache_page) {
+		/* the cache backend releases the cookie lock */
+		object->cache->ops->uncache_page(object, page);
+		goto done;
+	}
+
+done_unlock:
+	spin_unlock(&cookie->lock);
+done:
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_uncache_page);
+
+/**
+ * fscache_mark_pages_cached - Mark pages as being cached
+ * @op: The retrieval op pages are being marked for
+ * @pagevec: The pages to be marked
+ *
+ * Mark a bunch of netfs pages as being cached.  After this is called,
+ * the netfs must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_pages_cached(struct fscache_retrieval *op,
+			       struct pagevec *pagevec)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+	unsigned long loop;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_add(pagevec->nr, &fscache_n_marks);
+#endif
+
+	for (loop = 0; loop < pagevec->nr; loop++) {
+		struct page *page = pagevec->pages[loop];
+
+		_debug("- mark %p{%lx}", page, page->index);
+		if (TestSetPageFsCache(page)) {
+			static bool once_only;
+			if (!once_only) {
+				once_only = true;
+				printk(KERN_WARNING "FS-Cache:"
+				       " Cookie type %s marked page %lx"
+				       " multiple times\n",
+				       cookie->def->name, page->index);
+			}
+		}
+	}
+
+	if (cookie->def->mark_pages_cached)
+		cookie->def->mark_pages_cached(cookie->netfs_data,
+					       op->mapping, pagevec);
+	pagevec_reinit(pagevec);
+}
+EXPORT_SYMBOL(fscache_mark_pages_cached);

fs/fscache/proc.c

@@ -0,0 +1,68 @@
+/* FS-Cache statistics viewing interface
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL OPERATION
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * initialise the /proc/fs/fscache/ directory
+ */
+int __init fscache_proc_init(void)
+{
+	_enter("");
+
+	if (!proc_mkdir("fs/fscache", NULL))
+		goto error_dir;
+
+#ifdef CONFIG_FSCACHE_STATS
+	if (!proc_create("fs/fscache/stats", S_IFREG | 0444, NULL,
+			 &fscache_stats_fops))
+		goto error_stats;
+#endif
+
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	if (!proc_create("fs/fscache/histogram", S_IFREG | 0444, NULL,
+			 &fscache_histogram_fops))
+		goto error_histogram;
+#endif
+
+	_leave(" = 0");
+	return 0;
+
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+error_histogram:
+#endif
+#ifdef CONFIG_FSCACHE_STATS
+	remove_proc_entry("fs/fscache/stats", NULL);
+error_stats:
+#endif
+	remove_proc_entry("fs/fscache", NULL);
+error_dir:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/fscache/ directory
+ */
+void fscache_proc_cleanup(void)
+{
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	remove_proc_entry("fs/fscache/histogram", NULL);
+#endif
+#ifdef CONFIG_FSCACHE_STATS
+	remove_proc_entry("fs/fscache/stats", NULL);
+#endif
+	remove_proc_entry("fs/fscache", NULL);
+}

fs/fscache/stats.c

@@ -0,0 +1,212 @@
+/* FS-Cache statistics
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL THREAD
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * operation counters
+ */
+atomic_t fscache_n_op_pend;
+atomic_t fscache_n_op_run;
+atomic_t fscache_n_op_enqueue;
+atomic_t fscache_n_op_requeue;
+atomic_t fscache_n_op_deferred_release;
+atomic_t fscache_n_op_release;
+atomic_t fscache_n_op_gc;
+
+atomic_t fscache_n_attr_changed;
+atomic_t fscache_n_attr_changed_ok;
+atomic_t fscache_n_attr_changed_nobufs;
+atomic_t fscache_n_attr_changed_nomem;
+atomic_t fscache_n_attr_changed_calls;
+
+atomic_t fscache_n_allocs;
+atomic_t fscache_n_allocs_ok;
+atomic_t fscache_n_allocs_wait;
+atomic_t fscache_n_allocs_nobufs;
+atomic_t fscache_n_alloc_ops;
+atomic_t fscache_n_alloc_op_waits;
+
+atomic_t fscache_n_retrievals;
+atomic_t fscache_n_retrievals_ok;
+atomic_t fscache_n_retrievals_wait;
+atomic_t fscache_n_retrievals_nodata;
+atomic_t fscache_n_retrievals_nobufs;
+atomic_t fscache_n_retrievals_intr;
+atomic_t fscache_n_retrievals_nomem;
+atomic_t fscache_n_retrieval_ops;
+atomic_t fscache_n_retrieval_op_waits;
+
+atomic_t fscache_n_stores;
+atomic_t fscache_n_stores_ok;
+atomic_t fscache_n_stores_again;
+atomic_t fscache_n_stores_nobufs;
+atomic_t fscache_n_stores_oom;
+atomic_t fscache_n_store_ops;
+atomic_t fscache_n_store_calls;
+
+atomic_t fscache_n_marks;
+atomic_t fscache_n_uncaches;
+
+atomic_t fscache_n_acquires;
+atomic_t fscache_n_acquires_null;
+atomic_t fscache_n_acquires_no_cache;
+atomic_t fscache_n_acquires_ok;
+atomic_t fscache_n_acquires_nobufs;
+atomic_t fscache_n_acquires_oom;
+
+atomic_t fscache_n_updates;
+atomic_t fscache_n_updates_null;
+atomic_t fscache_n_updates_run;
+
+atomic_t fscache_n_relinquishes;
+atomic_t fscache_n_relinquishes_null;
+atomic_t fscache_n_relinquishes_waitcrt;
+
+atomic_t fscache_n_cookie_index;
+atomic_t fscache_n_cookie_data;
+atomic_t fscache_n_cookie_special;
+
+atomic_t fscache_n_object_alloc;
+atomic_t fscache_n_object_no_alloc;
+atomic_t fscache_n_object_lookups;
+atomic_t fscache_n_object_lookups_negative;
+atomic_t fscache_n_object_lookups_positive;
+atomic_t fscache_n_object_created;
+atomic_t fscache_n_object_avail;
+atomic_t fscache_n_object_dead;
+
+atomic_t fscache_n_checkaux_none;
+atomic_t fscache_n_checkaux_okay;
+atomic_t fscache_n_checkaux_update;
+atomic_t fscache_n_checkaux_obsolete;
+
+/*
+ * display the general statistics
+ */
+static int fscache_stats_show(struct seq_file *m, void *v)
+{
+	seq_puts(m, "FS-Cache statistics\n");
+
+	seq_printf(m, "Cookies: idx=%u dat=%u spc=%u\n",
+		   atomic_read(&fscache_n_cookie_index),
+		   atomic_read(&fscache_n_cookie_data),
+		   atomic_read(&fscache_n_cookie_special));
+
+	seq_printf(m, "Objects: alc=%u nal=%u avl=%u ded=%u\n",
+		   atomic_read(&fscache_n_object_alloc),
+		   atomic_read(&fscache_n_object_no_alloc),
+		   atomic_read(&fscache_n_object_avail),
+		   atomic_read(&fscache_n_object_dead));
+	seq_printf(m, "ChkAux : non=%u ok=%u upd=%u obs=%u\n",
+		   atomic_read(&fscache_n_checkaux_none),
+		   atomic_read(&fscache_n_checkaux_okay),
+		   atomic_read(&fscache_n_checkaux_update),
+		   atomic_read(&fscache_n_checkaux_obsolete));
+
+	seq_printf(m, "Pages  : mrk=%u unc=%u\n",
+		   atomic_read(&fscache_n_marks),
+		   atomic_read(&fscache_n_uncaches));
+
+	seq_printf(m, "Acquire: n=%u nul=%u noc=%u ok=%u nbf=%u"
+		   " oom=%u\n",
+		   atomic_read(&fscache_n_acquires),
+		   atomic_read(&fscache_n_acquires_null),
+		   atomic_read(&fscache_n_acquires_no_cache),
+		   atomic_read(&fscache_n_acquires_ok),
+		   atomic_read(&fscache_n_acquires_nobufs),
+		   atomic_read(&fscache_n_acquires_oom));
+
+	seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u\n",
+		   atomic_read(&fscache_n_object_lookups),
+		   atomic_read(&fscache_n_object_lookups_negative),
+		   atomic_read(&fscache_n_object_lookups_positive),
+		   atomic_read(&fscache_n_object_created));
+
+	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
+		   atomic_read(&fscache_n_updates),
+		   atomic_read(&fscache_n_updates_null),
+		   atomic_read(&fscache_n_updates_run));
+
+	seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u\n",
+		   atomic_read(&fscache_n_relinquishes),
+		   atomic_read(&fscache_n_relinquishes_null),
+		   atomic_read(&fscache_n_relinquishes_waitcrt));
+
+	seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n",
+		   atomic_read(&fscache_n_attr_changed),
+		   atomic_read(&fscache_n_attr_changed_ok),
+		   atomic_read(&fscache_n_attr_changed_nobufs),
+		   atomic_read(&fscache_n_attr_changed_nomem),
+		   atomic_read(&fscache_n_attr_changed_calls));
+
+	seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u\n",
+		   atomic_read(&fscache_n_allocs),
+		   atomic_read(&fscache_n_allocs_ok),
+		   atomic_read(&fscache_n_allocs_wait),
+		   atomic_read(&fscache_n_allocs_nobufs));
+	seq_printf(m, "Allocs : ops=%u owt=%u\n",
+		   atomic_read(&fscache_n_alloc_ops),
+		   atomic_read(&fscache_n_alloc_op_waits));
+
+	seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u"
+		   " int=%u oom=%u\n",
+		   atomic_read(&fscache_n_retrievals),
+		   atomic_read(&fscache_n_retrievals_ok),
+		   atomic_read(&fscache_n_retrievals_wait),
+		   atomic_read(&fscache_n_retrievals_nodata),
+		   atomic_read(&fscache_n_retrievals_nobufs),
+		   atomic_read(&fscache_n_retrievals_intr),
+		   atomic_read(&fscache_n_retrievals_nomem));
+	seq_printf(m, "Retrvls: ops=%u owt=%u\n",
+		   atomic_read(&fscache_n_retrieval_ops),
+		   atomic_read(&fscache_n_retrieval_op_waits));
+
+	seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n",
+		   atomic_read(&fscache_n_stores),
+		   atomic_read(&fscache_n_stores_ok),
+		   atomic_read(&fscache_n_stores_again),
+		   atomic_read(&fscache_n_stores_nobufs),
+		   atomic_read(&fscache_n_stores_oom));
+	seq_printf(m, "Stores : ops=%u run=%u\n",
+		   atomic_read(&fscache_n_store_ops),
+		   atomic_read(&fscache_n_store_calls));
+
+	seq_printf(m, "Ops    : pend=%u run=%u enq=%u\n",
+		   atomic_read(&fscache_n_op_pend),
+		   atomic_read(&fscache_n_op_run),
+		   atomic_read(&fscache_n_op_enqueue));
+	seq_printf(m, "Ops    : dfr=%u rel=%u gc=%u\n",
+		   atomic_read(&fscache_n_op_deferred_release),
+		   atomic_read(&fscache_n_op_release),
+		   atomic_read(&fscache_n_op_gc));
+	return 0;
+}
+
+/*
+ * open "/proc/fs/fscache/stats" allowing provision of a statistical summary
+ */
+static int fscache_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, fscache_stats_show, NULL);
+}
+
+const struct file_operations fscache_stats_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};

fs/nfs/Kconfig

@@ -84,3 +84,11 @@ config ROOT_NFS
 	  <file:Documentation/filesystems/nfsroot.txt>.
 
 	  Most people say N here.
+
+config NFS_FSCACHE
+	bool "Provide NFS client caching support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
+	help
+	  Say Y here if you want NFS data to be cached locally on disc through
+	  the general filesystem cache manager

fs/nfs/Makefile

@@ -15,3 +15,4 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   callback.o callback_xdr.o callback_proc.o \
 			   nfs4namespace.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o

fs/nfs/client.c

@@ -45,6 +45,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -154,6 +155,8 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
 
+	nfs_fscache_get_client_cookie(clp);
+
 	return clp;
 
 error_3:
@@ -187,6 +190,8 @@ static void nfs_free_client(struct nfs_client *clp)
 
 	nfs4_shutdown_client(clp);
 
+	nfs_fscache_release_client_cookie(clp);
+
 	/* -EIO all pending I/O */
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
@@ -760,6 +765,7 @@ static int nfs_init_server(struct nfs_server *server,
 
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
+	server->options = data->options;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1148,6 +1154,7 @@ static int nfs4_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
 	server->caps |= NFS_CAP_ATOMIC_OPEN;
+	server->options = data->options;
 
 	/* Get a client record */
 	error = nfs4_set_client(server,
@@ -1559,7 +1566,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 
 	/* display header on line 1 */
 	if (v == &nfs_volume_list) {
-		seq_puts(m, "NV SERVER   PORT DEV     FSID\n");
+		seq_puts(m, "NV SERVER   PORT DEV     FSID              FSC\n");
 		return 0;
 	}
 	/* display one transport per line on subsequent lines */
@@ -1573,12 +1580,13 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 		 (unsigned long long) server->fsid.major,
 		 (unsigned long long) server->fsid.minor);
 
-	seq_printf(m, "v%u %s %s %-7s %-17s\n",
+	seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
 		   dev,
-		   fsid);
+		   fsid,
+		   nfs_server_fscache_state(server));
 
 	return 0;
 }

fs/nfs/file.c

@@ -35,6 +35,7 @@
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
@@ -409,6 +410,13 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	return copied;
 }
 
+/*
+ * Partially or wholly invalidate a page
+ * - Release the private state associated with a page if undergoing complete
+ *   page invalidation
+ * - Called if either PG_private or PG_fscache is set on the page
+ * - Caller holds page lock
+ */
 static void nfs_invalidate_page(struct page *page, unsigned long offset)
 {
 	dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %lu)\n", page, offset);
@@ -417,23 +425,43 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 		return;
 	/* Cancel any unstarted writes on this page */
 	nfs_wb_page_cancel(page->mapping->host, page);
+
+	nfs_fscache_invalidate_page(page, page->mapping->host);
 }
 
+/*
+ * Attempt to release the private state associated with a page
+ * - Called if either PG_private or PG_fscache is set on the page
+ * - Caller holds page lock
+ * - Return true (may release page) or false (may not)
+ */
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
 	/* If PagePrivate() is set, then the page is not freeable */
-	return 0;
+	if (PagePrivate(page))
+		return 0;
+	return nfs_fscache_release_page(page, gfp);
 }
 
+/*
+ * Attempt to clear the private state associated with a page when an error
+ * occurs that requires the cached contents of an inode to be written back or
+ * destroyed
+ * - Called if either PG_private or fscache is set on the page
+ * - Caller holds page lock
+ * - Return 0 if successful, -error otherwise
+ */
 static int nfs_launder_page(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
+	struct nfs_inode *nfsi = NFS_I(inode);
 
 	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
 		inode->i_ino, (long long)page_offset(page));
 
+	nfs_fscache_wait_on_page_write(nfsi, page);
 	return nfs_wb_page(inode, page);
 }
 
@@ -451,6 +479,11 @@ const struct address_space_operations nfs_file_aops = {
 	.launder_page = nfs_launder_page,
 };
 
+/*
+ * Notification that a PTE pointing to an NFS page is about to be made
+ * writable, implying that someone is about to modify the page through a
+ * shared-writable mapping
+ */
 static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -465,6 +498,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		filp->f_mapping->host->i_ino,
 		(long long)page_offset(page));
 
+	/* make sure the cache has finished storing the page */
+	nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
+
 	lock_page(page);
 	mapping = page->mapping;
 	if (mapping != dentry->d_inode->i_mapping)

fs/nfs/fscache-index.c

@@ -0,0 +1,337 @@
+/* NFS FS-Cache index structure definition
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/in6.h>
+
+#include "internal.h"
+#include "fscache.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FSCACHE
+
+/*
+ * Define the NFS filesystem for FS-Cache.  Upon registration FS-Cache sticks
+ * the cookie for the top-level index object for NFS into here.  The top-level
+ * index can than have other cache objects inserted into it.
+ */
+struct fscache_netfs nfs_fscache_netfs = {
+	.name		= "nfs",
+	.version	= 0,
+};
+
+/*
+ * Register NFS for caching
+ */
+int nfs_fscache_register(void)
+{
+	return fscache_register_netfs(&nfs_fscache_netfs);
+}
+
+/*
+ * Unregister NFS for caching
+ */
+void nfs_fscache_unregister(void)
+{
+	fscache_unregister_netfs(&nfs_fscache_netfs);
+}
+
+/*
+ * Layout of the key for an NFS server cache object.
+ */
+struct nfs_server_key {
+	uint16_t	nfsversion;		/* NFS protocol version */
+	uint16_t	family;			/* address family */
+	uint16_t	port;			/* IP port */
+	union {
+		struct in_addr	ipv4_addr;	/* IPv4 address */
+		struct in6_addr ipv6_addr;	/* IPv6 address */
+	} addr[0];
+};
+
+/*
+ * Generate a key to describe a server in the main NFS index
+ * - We return the length of the key, or 0 if we can't generate one
+ */
+static uint16_t nfs_server_get_key(const void *cookie_netfs_data,
+				   void *buffer, uint16_t bufmax)
+{
+	const struct nfs_client *clp = cookie_netfs_data;
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr;
+	const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr;
+	struct nfs_server_key *key = buffer;
+	uint16_t len = sizeof(struct nfs_server_key);
+
+	key->nfsversion = clp->rpc_ops->version;
+	key->family = clp->cl_addr.ss_family;
+
+	memset(key, 0, len);
+
+	switch (clp->cl_addr.ss_family) {
+	case AF_INET:
+		key->port = sin->sin_port;
+		key->addr[0].ipv4_addr = sin->sin_addr;
+		len += sizeof(key->addr[0].ipv4_addr);
+		break;
+
+	case AF_INET6:
+		key->port = sin6->sin6_port;
+		key->addr[0].ipv6_addr = sin6->sin6_addr;
+		len += sizeof(key->addr[0].ipv6_addr);
+		break;
+
+	default:
+		printk(KERN_WARNING "NFS: Unknown network family '%d'\n",
+		       clp->cl_addr.ss_family);
+		len = 0;
+		break;
+	}
+
+	return len;
+}
+
+/*
+ * Define the server object for FS-Cache.  This is used to describe a server
+ * object to fscache_acquire_cookie().  It is keyed by the NFS protocol and
+ * server address parameters.
+ */
+const struct fscache_cookie_def nfs_fscache_server_index_def = {
+	.name		= "NFS.server",
+	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= nfs_server_get_key,
+};
+
+/*
+ * Generate a key to describe a superblock key in the main NFS index
+ */
+static uint16_t nfs_super_get_key(const void *cookie_netfs_data,
+				  void *buffer, uint16_t bufmax)
+{
+	const struct nfs_fscache_key *key;
+	const struct nfs_server *nfss = cookie_netfs_data;
+	uint16_t len;
+
+	key = nfss->fscache_key;
+	len = sizeof(key->key) + key->key.uniq_len;
+	if (len > bufmax) {
+		len = 0;
+	} else {
+		memcpy(buffer, &key->key, sizeof(key->key));
+		memcpy(buffer + sizeof(key->key),
+		       key->key.uniquifier, key->key.uniq_len);
+	}
+
+	return len;
+}
+
+/*
+ * Define the superblock object for FS-Cache.  This is used to describe a
+ * superblock object to fscache_acquire_cookie().  It is keyed by all the NFS
+ * parameters that might cause a separate superblock.
+ */
+const struct fscache_cookie_def nfs_fscache_super_index_def = {
+	.name		= "NFS.super",
+	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= nfs_super_get_key,
+};
+
+/*
+ * Definition of the auxiliary data attached to NFS inode storage objects
+ * within the cache.
+ *
+ * The contents of this struct are recorded in the on-disk local cache in the
+ * auxiliary data attached to the data storage object backing an inode.  This
+ * permits coherency to be managed when a new inode binds to an already extant
+ * cache object.
+ */
+struct nfs_fscache_inode_auxdata {
+	struct timespec	mtime;
+	struct timespec	ctime;
+	loff_t		size;
+	u64		change_attr;
+};
+
+/*
+ * Generate a key to describe an NFS inode in an NFS server's index
+ */
+static uint16_t nfs_fscache_inode_get_key(const void *cookie_netfs_data,
+					  void *buffer, uint16_t bufmax)
+{
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+	uint16_t nsize;
+
+	/* use the inode's NFS filehandle as the key */
+	nsize = nfsi->fh.size;
+	memcpy(buffer, nfsi->fh.data, nsize);
+	return nsize;
+}
+
+/*
+ * Get certain file attributes from the netfs data
+ * - This function can be absent for an index
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static void nfs_fscache_inode_get_attr(const void *cookie_netfs_data,
+				       uint64_t *size)
+{
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+
+	*size = nfsi->vfs_inode.i_size;
+}
+
+/*
+ * Get the auxiliary data from netfs data
+ * - This function can be absent if the index carries no state data
+ * - Should store the auxiliary data in the buffer
+ * - Should return the amount of amount stored
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data,
+					  void *buffer, uint16_t bufmax)
+{
+	struct nfs_fscache_inode_auxdata auxdata;
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+
+	memset(&auxdata, 0, sizeof(auxdata));
+	auxdata.size = nfsi->vfs_inode.i_size;
+	auxdata.mtime = nfsi->vfs_inode.i_mtime;
+	auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata.change_attr = nfsi->change_attr;
+
+	if (bufmax > sizeof(auxdata))
+		bufmax = sizeof(auxdata);
+
+	memcpy(buffer, &auxdata, bufmax);
+	return bufmax;
+}
+
+/*
+ * Consult the netfs about the state of an object
+ * - This function can be absent if the index carries no state data
+ * - The netfs data from the cookie being used as the target is
+ *   presented, as is the auxiliary data
+ */
+static
+enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
+						  const void *data,
+						  uint16_t datalen)
+{
+	struct nfs_fscache_inode_auxdata auxdata;
+	struct nfs_inode *nfsi = cookie_netfs_data;
+
+	if (datalen != sizeof(auxdata))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	memset(&auxdata, 0, sizeof(auxdata));
+	auxdata.size = nfsi->vfs_inode.i_size;
+	auxdata.mtime = nfsi->vfs_inode.i_mtime;
+	auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata.change_attr = nfsi->change_attr;
+
+	if (memcmp(data, &auxdata, datalen) != 0)
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+/*
+ * Indication from FS-Cache that the cookie is no longer cached
+ * - This function is called when the backing store currently caching a cookie
+ *   is removed
+ * - The netfs should use this to clean up any markers indicating cached pages
+ * - This is mandatory for any object that may have data
+ */
+static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data)
+{
+	struct nfs_inode *nfsi = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi);
+
+	for (;;) {
+		/* grab a bunch of pages to unmark */
+		nr_pages = pagevec_lookup(&pvec,
+					  nfsi->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+/*
+ * Get an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ *   context.
+ * - The read context is passed back to NFS in the event that a data read on the
+ *   cache fails with EIO - in which case the server must be contacted to
+ *   retrieve the data, which requires the read context for security.
+ */
+static void nfs_fh_get_context(void *cookie_netfs_data, void *context)
+{
+	get_nfs_open_context(context);
+}
+
+/*
+ * Release an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ *   context.
+ */
+static void nfs_fh_put_context(void *cookie_netfs_data, void *context)
+{
+	if (context)
+		put_nfs_open_context(context);
+}
+
+/*
+ * Define the inode object for FS-Cache.  This is used to describe an inode
+ * object to fscache_acquire_cookie().  It is keyed by the NFS file handle for
+ * an inode.
+ *
+ * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime
+ * held in the cache auxiliary data for the data storage object with those in
+ * the inode struct in memory.
+ */
+const struct fscache_cookie_def nfs_fscache_inode_object_def = {
+	.name		= "NFS.fh",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= nfs_fscache_inode_get_key,
+	.get_attr	= nfs_fscache_inode_get_attr,
+	.get_aux	= nfs_fscache_inode_get_aux,
+	.check_aux	= nfs_fscache_inode_check_aux,
+	.now_uncached	= nfs_fscache_inode_now_uncached,
+	.get_context	= nfs_fh_get_context,
+	.put_context	= nfs_fh_put_context,
+};

fs/nfs/fscache.c

@@ -0,0 +1,523 @@
+/* NFS filesystem cache interface
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/in6.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+#include "iostat.h"
+#include "fscache.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FSCACHE
+
+static struct rb_root nfs_fscache_keys = RB_ROOT;
+static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
+
+/*
+ * Get the per-client index cookie for an NFS client if the appropriate mount
+ * flag was set
+ * - We always try and get an index cookie for the client, but get filehandle
+ *   cookies on a per-superblock basis, depending on the mount flags
+ */
+void nfs_fscache_get_client_cookie(struct nfs_client *clp)
+{
+	/* create a cache index for looking up filehandles */
+	clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
+					      &nfs_fscache_server_index_def,
+					      clp);
+	dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
+		 clp, clp->fscache);
+}
+
+/*
+ * Dispose of a per-client cookie
+ */
+void nfs_fscache_release_client_cookie(struct nfs_client *clp)
+{
+	dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n",
+		 clp, clp->fscache);
+
+	fscache_relinquish_cookie(clp->fscache, 0);
+	clp->fscache = NULL;
+}
+
+/*
+ * Get the cache cookie for an NFS superblock.  We have to handle
+ * uniquification here because the cache doesn't do it for us.
+ */
+void nfs_fscache_get_super_cookie(struct super_block *sb,
+				  struct nfs_parsed_mount_data *data)
+{
+	struct nfs_fscache_key *key, *xkey;
+	struct nfs_server *nfss = NFS_SB(sb);
+	struct rb_node **p, *parent;
+	const char *uniq = data->fscache_uniq ?: "";
+	int diff, ulen;
+
+	ulen = strlen(uniq);
+	key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
+	if (!key)
+		return;
+
+	key->nfs_client = nfss->nfs_client;
+	key->key.super.s_flags = sb->s_flags & NFS_MS_MASK;
+	key->key.nfs_server.flags = nfss->flags;
+	key->key.nfs_server.rsize = nfss->rsize;
+	key->key.nfs_server.wsize = nfss->wsize;
+	key->key.nfs_server.acregmin = nfss->acregmin;
+	key->key.nfs_server.acregmax = nfss->acregmax;
+	key->key.nfs_server.acdirmin = nfss->acdirmin;
+	key->key.nfs_server.acdirmax = nfss->acdirmax;
+	key->key.nfs_server.fsid = nfss->fsid;
+	key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor;
+
+	key->key.uniq_len = ulen;
+	memcpy(key->key.uniquifier, uniq, ulen);
+
+	spin_lock(&nfs_fscache_keys_lock);
+	p = &nfs_fscache_keys.rb_node;
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		xkey = rb_entry(parent, struct nfs_fscache_key, node);
+
+		if (key->nfs_client < xkey->nfs_client)
+			goto go_left;
+		if (key->nfs_client > xkey->nfs_client)
+			goto go_right;
+
+		diff = memcmp(&key->key, &xkey->key, sizeof(key->key));
+		if (diff < 0)
+			goto go_left;
+		if (diff > 0)
+			goto go_right;
+
+		if (key->key.uniq_len == 0)
+			goto non_unique;
+		diff = memcmp(key->key.uniquifier,
+			      xkey->key.uniquifier,
+			      key->key.uniq_len);
+		if (diff < 0)
+			goto go_left;
+		if (diff > 0)
+			goto go_right;
+		goto non_unique;
+
+	go_left:
+		p = &(*p)->rb_left;
+		continue;
+	go_right:
+		p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&key->node, parent, p);
+	rb_insert_color(&key->node, &nfs_fscache_keys);
+	spin_unlock(&nfs_fscache_keys_lock);
+	nfss->fscache_key = key;
+
+	/* create a cache index for looking up filehandles */
+	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
+					       &nfs_fscache_super_index_def,
+					       nfss);
+	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
+		 nfss, nfss->fscache);
+	return;
+
+non_unique:
+	spin_unlock(&nfs_fscache_keys_lock);
+	kfree(key);
+	nfss->fscache_key = NULL;
+	nfss->fscache = NULL;
+	printk(KERN_WARNING "NFS:"
+	       " Cache request denied due to non-unique superblock keys\n");
+}
+
+/*
+ * release a per-superblock cookie
+ */
+void nfs_fscache_release_super_cookie(struct super_block *sb)
+{
+	struct nfs_server *nfss = NFS_SB(sb);
+
+	dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n",
+		 nfss, nfss->fscache);
+
+	fscache_relinquish_cookie(nfss->fscache, 0);
+	nfss->fscache = NULL;
+
+	if (nfss->fscache_key) {
+		spin_lock(&nfs_fscache_keys_lock);
+		rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys);
+		spin_unlock(&nfs_fscache_keys_lock);
+		kfree(nfss->fscache_key);
+		nfss->fscache_key = NULL;
+	}
+}
+
+/*
+ * Initialise the per-inode cache cookie pointer for an NFS inode.
+ */
+void nfs_fscache_init_inode_cookie(struct inode *inode)
+{
+	NFS_I(inode)->fscache = NULL;
+	if (S_ISREG(inode->i_mode))
+		set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
+/*
+ * Get the per-inode cache cookie for an NFS inode.
+ */
+static void nfs_fscache_enable_inode_cookie(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (nfsi->fscache || !NFS_FSCACHE(inode))
+		return;
+
+	if ((NFS_SB(sb)->options & NFS_OPTION_FSCACHE)) {
+		nfsi->fscache = fscache_acquire_cookie(
+			NFS_SB(sb)->fscache,
+			&nfs_fscache_inode_object_def,
+			nfsi);
+
+		dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
+			 sb, nfsi, nfsi->fscache);
+	}
+}
+
+/*
+ * Release a per-inode cookie.
+ */
+void nfs_fscache_release_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n",
+		 nfsi, nfsi->fscache);
+
+	fscache_relinquish_cookie(nfsi->fscache, 0);
+	nfsi->fscache = NULL;
+}
+
+/*
+ * Retire a per-inode cookie, destroying the data attached to it.
+ */
+void nfs_fscache_zap_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	dfprintk(FSCACHE, "NFS: zapping cookie (0x%p/0x%p)\n",
+		 nfsi, nfsi->fscache);
+
+	fscache_relinquish_cookie(nfsi->fscache, 1);
+	nfsi->fscache = NULL;
+}
+
+/*
+ * Turn off the cache with regard to a per-inode cookie if opened for writing,
+ * invalidating all the pages in the page cache relating to the associated
+ * inode to clear the per-page caching.
+ */
+static void nfs_fscache_disable_inode_cookie(struct inode *inode)
+{
+	clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+
+	if (NFS_I(inode)->fscache) {
+		dfprintk(FSCACHE,
+			 "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));
+
+		/* Need to invalidate any mapped pages that were read in before
+		 * turning off the cache.
+		 */
+		if (inode->i_mapping && inode->i_mapping->nrpages)
+			invalidate_inode_pages2(inode->i_mapping);
+
+		nfs_fscache_zap_inode_cookie(inode);
+	}
+}
+
+/*
+ * wait_on_bit() sleep function for uninterruptible waiting
+ */
+static int nfs_fscache_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+
+/*
+ * Lock against someone else trying to also acquire or relinquish a cookie
+ */
+static inline void nfs_fscache_inode_lock(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	while (test_and_set_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags))
+		wait_on_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK,
+			    nfs_fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * Unlock cookie management lock
+ */
+static inline void nfs_fscache_inode_unlock(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	smp_mb__before_clear_bit();
+	clear_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK);
+}
+
+/*
+ * Decide if we should enable or disable local caching for this inode.
+ * - For now, with NFS, only regular files that are open read-only will be able
+ *   to use the cache.
+ * - May be invoked multiple times in parallel by parallel nfs_open() functions.
+ */
+void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
+{
+	if (NFS_FSCACHE(inode)) {
+		nfs_fscache_inode_lock(inode);
+		if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+			nfs_fscache_disable_inode_cookie(inode);
+		else
+			nfs_fscache_enable_inode_cookie(inode);
+		nfs_fscache_inode_unlock(inode);
+	}
+}
+
+/*
+ * Replace a per-inode cookie due to revalidation detecting a file having
+ * changed on the server.
+ */
+void nfs_fscache_reset_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct nfs_server *nfss = NFS_SERVER(inode);
+	struct fscache_cookie *old = nfsi->fscache;
+
+	nfs_fscache_inode_lock(inode);
+	if (nfsi->fscache) {
+		/* retire the current fscache cache and get a new one */
+		fscache_relinquish_cookie(nfsi->fscache, 1);
+
+		nfsi->fscache = fscache_acquire_cookie(
+			nfss->nfs_client->fscache,
+			&nfs_fscache_inode_object_def,
+			nfsi);
+
+		dfprintk(FSCACHE,
+			 "NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
+			 nfss, nfsi, old, nfsi->fscache);
+	}
+	nfs_fscache_inode_unlock(inode);
+}
+
+/*
+ * Release the caching state associated with a page, if the page isn't busy
+ * interacting with the cache.
+ * - Returns true (can release page) or false (page busy).
+ */
+int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	struct nfs_inode *nfsi = NFS_I(page->mapping->host);
+	struct fscache_cookie *cookie = nfsi->fscache;
+
+	BUG_ON(!cookie);
+
+	if (fscache_check_page_write(cookie, page)) {
+		if (!(gfp & __GFP_WAIT))
+			return 0;
+		fscache_wait_on_page_write(cookie, page);
+	}
+
+	if (PageFsCache(page)) {
+		dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
+			 cookie, page, nfsi);
+
+		fscache_uncache_page(cookie, page);
+		nfs_add_fscache_stats(page->mapping->host,
+				      NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+	}
+
+	return 1;
+}
+
+/*
+ * Release the caching state associated with a page if undergoing complete page
+ * invalidation.
+ */
+void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct fscache_cookie *cookie = nfsi->fscache;
+
+	BUG_ON(!cookie);
+
+	dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
+		 cookie, page, nfsi);
+
+	fscache_wait_on_page_write(cookie, page);
+
+	BUG_ON(!PageLocked(page));
+	fscache_uncache_page(cookie, page);
+	nfs_add_fscache_stats(page->mapping->host,
+			      NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+}
+
+/*
+ * Handle completion of a page being read from the cache.
+ * - Called in process (keventd) context.
+ */
+static void nfs_readpage_from_fscache_complete(struct page *page,
+					       void *context,
+					       int error)
+{
+	dfprintk(FSCACHE,
+		 "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
+		 page, context, error);
+
+	/* if the read completes with an error, we just unlock the page and let
+	 * the VM reissue the readpage */
+	if (!error) {
+		SetPageUptodate(page);
+		unlock_page(page);
+	} else {
+		error = nfs_readpage_async(context, page->mapping->host, page);
+		if (error)
+			unlock_page(page);
+	}
+}
+
+/*
+ * Retrieve a page from fscache
+ */
+int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+				struct inode *inode, struct page *page)
+{
+	int ret;
+
+	dfprintk(FSCACHE,
+		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
+		 NFS_I(inode)->fscache, page, page->index, page->flags, inode);
+
+	ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
+					 page,
+					 nfs_readpage_from_fscache_complete,
+					 ctx,
+					 GFP_KERNEL);
+
+	switch (ret) {
+	case 0: /* read BIO submitted (page in fscache) */
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache: BIO submitted\n");
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1);
+		return ret;
+
+	case -ENOBUFS: /* inode not in cache */
+	case -ENODATA: /* page not in cache */
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache %d\n", ret);
+		return 1;
+
+	default:
+		dfprintk(FSCACHE, "NFS:    readpage_from_fscache %d\n", ret);
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
+	}
+	return ret;
+}
+
+/*
+ * Retrieve a set of pages from fscache
+ */
+int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+				 struct inode *inode,
+				 struct address_space *mapping,
+				 struct list_head *pages,
+				 unsigned *nr_pages)
+{
+	int ret, npages = *nr_pages;
+
+	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
+		 NFS_I(inode)->fscache, npages, inode);
+
+	ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
+					  mapping, pages, nr_pages,
+					  nfs_readpage_from_fscache_complete,
+					  ctx,
+					  mapping_gfp_mask(mapping));
+	if (*nr_pages < npages)
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
+				      npages);
+	if (*nr_pages > 0)
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
+				      *nr_pages);
+
+	switch (ret) {
+	case 0: /* read submitted to the cache for all pages */
+		BUG_ON(!list_empty(pages));
+		BUG_ON(*nr_pages != 0);
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: submitted\n");
+
+		return ret;
+
+	case -ENOBUFS: /* some pages aren't cached and can't be */
+	case -ENODATA: /* some pages aren't cached */
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
+		return 1;
+
+	default:
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: ret  %d\n", ret);
+	}
+
+	return ret;
+}
+
+/*
+ * Store a newly fetched page in fscache
+ * - PG_fscache must be set on the page
+ */
+void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
+{
+	int ret;
+
+	dfprintk(FSCACHE,
+		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
+		 NFS_I(inode)->fscache, page, page->index, page->flags, sync);
+
+	ret = fscache_write_page(NFS_I(inode)->fscache, page, GFP_KERNEL);
+	dfprintk(FSCACHE,
+		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
+		 page, page->index, page->flags, ret);
+
+	if (ret != 0) {
+		fscache_uncache_page(NFS_I(inode)->fscache, page);
+		nfs_add_fscache_stats(inode,
+				      NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1);
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+	} else {
+		nfs_add_fscache_stats(inode,
+				      NFSIOS_FSCACHE_PAGES_WRITTEN_OK, 1);
+	}
+}

fs/nfs/fscache.h

@@ -0,0 +1,220 @@
+/* NFS filesystem cache interface definitions
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _NFS_FSCACHE_H
+#define _NFS_FSCACHE_H
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/fscache.h>
+
+#ifdef CONFIG_NFS_FSCACHE
+
+/*
+ * set of NFS FS-Cache objects that form a superblock key
+ */
+struct nfs_fscache_key {
+	struct rb_node		node;
+	struct nfs_client	*nfs_client;	/* the server */
+
+	/* the elements of the unique key - as used by nfs_compare_super() and
+	 * nfs_compare_mount_options() to distinguish superblocks */
+	struct {
+		struct {
+			unsigned long	s_flags;	/* various flags
+							 * (& NFS_MS_MASK) */
+		} super;
+
+		struct {
+			struct nfs_fsid fsid;
+			int		flags;
+			unsigned int	rsize;		/* read size */
+			unsigned int	wsize;		/* write size */
+			unsigned int	acregmin;	/* attr cache timeouts */
+			unsigned int	acregmax;
+			unsigned int	acdirmin;
+			unsigned int	acdirmax;
+		} nfs_server;
+
+		struct {
+			rpc_authflavor_t au_flavor;
+		} rpc_auth;
+
+		/* uniquifier - can be used if nfs_server.flags includes
+		 * NFS_MOUNT_UNSHARED  */
+		u8 uniq_len;
+		char uniquifier[0];
+	} key;
+};
+
+/*
+ * fscache-index.c
+ */
+extern struct fscache_netfs nfs_fscache_netfs;
+extern const struct fscache_cookie_def nfs_fscache_server_index_def;
+extern const struct fscache_cookie_def nfs_fscache_super_index_def;
+extern const struct fscache_cookie_def nfs_fscache_inode_object_def;
+
+extern int nfs_fscache_register(void);
+extern void nfs_fscache_unregister(void);
+
+/*
+ * fscache.c
+ */
+extern void nfs_fscache_get_client_cookie(struct nfs_client *);
+extern void nfs_fscache_release_client_cookie(struct nfs_client *);
+
+extern void nfs_fscache_get_super_cookie(struct super_block *,
+					 struct nfs_parsed_mount_data *);
+extern void nfs_fscache_release_super_cookie(struct super_block *);
+
+extern void nfs_fscache_init_inode_cookie(struct inode *);
+extern void nfs_fscache_release_inode_cookie(struct inode *);
+extern void nfs_fscache_zap_inode_cookie(struct inode *);
+extern void nfs_fscache_set_inode_cookie(struct inode *, struct file *);
+extern void nfs_fscache_reset_inode_cookie(struct inode *);
+
+extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
+extern int nfs_fscache_release_page(struct page *, gfp_t);
+
+extern int __nfs_readpage_from_fscache(struct nfs_open_context *,
+				       struct inode *, struct page *);
+extern int __nfs_readpages_from_fscache(struct nfs_open_context *,
+					struct inode *, struct address_space *,
+					struct list_head *, unsigned *);
+extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int);
+
+/*
+ * wait for a page to complete writing to the cache
+ */
+static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
+						  struct page *page)
+{
+	if (PageFsCache(page))
+		fscache_wait_on_page_write(nfsi->fscache, page);
+}
+
+/*
+ * release the caching state associated with a page if undergoing complete page
+ * invalidation
+ */
+static inline void nfs_fscache_invalidate_page(struct page *page,
+					       struct inode *inode)
+{
+	if (PageFsCache(page))
+		__nfs_fscache_invalidate_page(page, inode);
+}
+
+/*
+ * Retrieve a page from an inode data storage object.
+ */
+static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+					    struct inode *inode,
+					    struct page *page)
+{
+	if (NFS_I(inode)->fscache)
+		return __nfs_readpage_from_fscache(ctx, inode, page);
+	return -ENOBUFS;
+}
+
+/*
+ * Retrieve a set of pages from an inode data storage object.
+ */
+static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+					     struct inode *inode,
+					     struct address_space *mapping,
+					     struct list_head *pages,
+					     unsigned *nr_pages)
+{
+	if (NFS_I(inode)->fscache)
+		return __nfs_readpages_from_fscache(ctx, inode, mapping, pages,
+						    nr_pages);
+	return -ENOBUFS;
+}
+
+/*
+ * Store a page newly fetched from the server in an inode data storage object
+ * in the cache.
+ */
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+					   struct page *page,
+					   int sync)
+{
+	if (PageFsCache(page))
+		__nfs_readpage_to_fscache(inode, page, sync);
+}
+
+/*
+ * indicate the client caching state as readable text
+ */
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+	if (server->fscache && (server->options & NFS_OPTION_FSCACHE))
+		return "yes";
+	return "no ";
+}
+
+
+#else /* CONFIG_NFS_FSCACHE */
+static inline int nfs_fscache_register(void) { return 0; }
+static inline void nfs_fscache_unregister(void) {}
+
+static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {}
+static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
+
+static inline void nfs_fscache_get_super_cookie(
+	struct super_block *sb,
+	struct nfs_parsed_mount_data *data)
+{
+}
+static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
+
+static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_release_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_zap_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_set_inode_cookie(struct inode *inode,
+						struct file *filp) {}
+static inline void nfs_fscache_reset_inode_cookie(struct inode *inode) {}
+
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	return 1; /* True: may release page */
+}
+static inline void nfs_fscache_invalidate_page(struct page *page,
+					       struct inode *inode) {}
+static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
+						  struct page *page) {}
+
+static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+					    struct inode *inode,
+					    struct page *page)
+{
+	return -ENOBUFS;
+}
+static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+					     struct inode *inode,
+					     struct address_space *mapping,
+					     struct list_head *pages,
+					     unsigned *nr_pages)
+{
+	return -ENOBUFS;
+}
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+					   struct page *page, int sync) {}
+
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+	return "no ";
+}
+
+#endif /* CONFIG_NFS_FSCACHE */
+#endif /* _NFS_FSCACHE_H */

fs/nfs/inode.c

@@ -46,6 +46,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -121,6 +122,7 @@ void nfs_clear_inode(struct inode *inode)
 	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
 	nfs_zap_acl_cache(inode);
 	nfs_access_zap_cache(inode);
+	nfs_fscache_release_inode_cookie(inode);
 }
 
 /**
@@ -355,6 +357,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		nfsi->attrtimeo_timestamp = now;
 		nfsi->access_cache = RB_ROOT;
 
+		nfs_fscache_init_inode_cookie(inode);
+
 		unlock_new_inode(inode);
 	} else
 		nfs_refresh_inode(inode, fattr);
@@ -686,6 +690,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 	ctx->mode = filp->f_mode;
 	nfs_file_set_open_context(filp, ctx);
 	put_nfs_open_context(ctx);
+	nfs_fscache_set_inode_cookie(inode, filp);
 	return 0;
 }
 
@@ -786,6 +791,7 @@ static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_spa
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 	spin_unlock(&inode->i_lock);
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
+	nfs_fscache_reset_inode_cookie(inode);
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
 			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 	return 0;
@@ -1030,6 +1036,7 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 	spin_lock(&inode->i_lock);
 	status = nfs_refresh_inode_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
+
 	return status;
 }
 
@@ -1436,6 +1443,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_fscache_register();
+	if (err < 0)
+		goto out7;
+
 	err = nfsiod_start();
 	if (err)
 		goto out6;
@@ -1488,6 +1499,8 @@ out4:
 out5:
 	nfsiod_stop();
 out6:
+	nfs_fscache_unregister();
+out7:
 	return err;
 }
 
@@ -1498,6 +1511,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_readpagecache();
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
+	nfs_fscache_unregister();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister("nfs");
 #endif

fs/nfs/internal.h

@@ -5,6 +5,8 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 
+#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
+
 struct nfs_string;
 
 /* Maximum number of readahead requests
@@ -37,10 +39,12 @@ struct nfs_parsed_mount_data {
 	int			acregmin, acregmax,
 				acdirmin, acdirmax;
 	int			namlen;
+	unsigned int		options;
 	unsigned int		bsize;
 	unsigned int		auth_flavor_len;
 	rpc_authflavor_t	auth_flavors[1];
 	char			*client_address;
+	char			*fscache_uniq;
 
 	struct {
 		struct sockaddr_storage	address;

fs/nfs/iostat.h

@@ -16,6 +16,9 @@
 
 struct nfs_iostats {
 	unsigned long long	bytes[__NFSIOS_BYTESMAX];
+#ifdef CONFIG_NFS_FSCACHE
+	unsigned long long	fscache[__NFSIOS_FSCACHEMAX];
+#endif
 	unsigned long		events[__NFSIOS_COUNTSMAX];
 } ____cacheline_aligned;
 
@@ -57,6 +60,21 @@ static inline void nfs_add_stats(const struct inode *inode,
 	nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
 }
 
+#ifdef CONFIG_NFS_FSCACHE
+static inline void nfs_add_fscache_stats(struct inode *inode,
+					 enum nfs_stat_fscachecounters stat,
+					 unsigned long addend)
+{
+	struct nfs_iostats *iostats;
+	int cpu;
+
+	cpu = get_cpu();
+	iostats = per_cpu_ptr(NFS_SERVER(inode)->io_stats, cpu);
+	iostats->fscache[stat] += addend;
+	put_cpu_no_resched();
+}
+#endif
+
 static inline struct nfs_iostats *nfs_alloc_iostats(void)
 {
 	return alloc_percpu(struct nfs_iostats);

fs/nfs/read.c

@@ -24,6 +24,7 @@
 
 #include "internal.h"
 #include "iostat.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -111,8 +112,8 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
 	}
 }
 
-static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
-		struct page *page)
+int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
+		       struct page *page)
 {
 	LIST_HEAD(one_request);
 	struct nfs_page	*new;
@@ -139,6 +140,11 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 
 static void nfs_readpage_release(struct nfs_page *req)
 {
+	struct inode *d_inode = req->wb_context->path.dentry->d_inode;
+
+	if (PageUptodate(req->wb_page))
+		nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+
 	unlock_page(req->wb_page);
 
 	dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",
@@ -510,8 +516,15 @@ int nfs_readpage(struct file *file, struct page *page)
 	} else
 		ctx = get_nfs_open_context(nfs_file_open_context(file));
 
+	if (!IS_SYNC(inode)) {
+		error = nfs_readpage_from_fscache(ctx, inode, page);
+		if (error == 0)
+			goto out;
+	}
+
 	error = nfs_readpage_async(ctx, inode, page);
 
+out:
 	put_nfs_open_context(ctx);
 	return error;
 out_unlock:
@@ -584,6 +597,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			return -EBADF;
 	} else
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(filp));
+
+	/* attempt to read as many of the pages as possible from the cache
+	 * - this returns -ENOBUFS immediately if the cookie is negative
+	 */
+	ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
+					 pages, &nr_pages);
+	if (ret == 0)
+		goto read_complete; /* all pages were read */
+
 	if (rsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
 	else
@@ -594,6 +616,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	nfs_pageio_complete(&pgio);
 	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
+read_complete:
 	put_nfs_open_context(desc.ctx);
 out:
 	return ret;

fs/nfs/super.c

@@ -60,6 +60,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -76,6 +77,7 @@ enum {
 	Opt_rdirplus, Opt_nordirplus,
 	Opt_sharecache, Opt_nosharecache,
 	Opt_resvport, Opt_noresvport,
+	Opt_fscache, Opt_nofscache,
 
 	/* Mount options that take integer arguments */
 	Opt_port,
@@ -93,6 +95,7 @@ enum {
 	Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
 	Opt_addr, Opt_mountaddr, Opt_clientaddr,
 	Opt_lookupcache,
+	Opt_fscache_uniq,
 
 	/* Special mount options */
 	Opt_userspace, Opt_deprecated, Opt_sloppy,
@@ -132,6 +135,9 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_nosharecache, "nosharecache" },
 	{ Opt_resvport, "resvport" },
 	{ Opt_noresvport, "noresvport" },
+	{ Opt_fscache, "fsc" },
+	{ Opt_fscache_uniq, "fsc=%s" },
+	{ Opt_nofscache, "nofsc" },
 
 	{ Opt_port, "port=%u" },
 	{ Opt_rsize, "rsize=%u" },
@@ -563,6 +569,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	if (clp->rpc_ops->version == 4)
 		seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
 #endif
+	if (nfss->options & NFS_OPTION_FSCACHE)
+		seq_printf(m, ",fsc");
 }
 
 /*
@@ -641,6 +649,10 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 			totals.events[i] += stats->events[i];
 		for (i = 0; i < __NFSIOS_BYTESMAX; i++)
 			totals.bytes[i] += stats->bytes[i];
+#ifdef CONFIG_NFS_FSCACHE
+		for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
+			totals.fscache[i] += stats->fscache[i];
+#endif
 
 		preempt_enable();
 	}
@@ -651,6 +663,13 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 	seq_printf(m, "\n\tbytes:\t");
 	for (i = 0; i < __NFSIOS_BYTESMAX; i++)
 		seq_printf(m, "%Lu ", totals.bytes[i]);
+#ifdef CONFIG_NFS_FSCACHE
+	if (nfss->options & NFS_OPTION_FSCACHE) {
+		seq_printf(m, "\n\tfsc:\t");
+		for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
+			seq_printf(m, "%Lu ", totals.bytes[i]);
+	}
+#endif
 	seq_printf(m, "\n");
 
 	rpc_print_iostats(m, nfss->client);
@@ -1044,6 +1063,24 @@ static int nfs_parse_mount_options(char *raw,
 		case Opt_noresvport:
 			mnt->flags |= NFS_MOUNT_NORESVPORT;
 			break;
+		case Opt_fscache:
+			mnt->options |= NFS_OPTION_FSCACHE;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = NULL;
+			break;
+		case Opt_nofscache:
+			mnt->options &= ~NFS_OPTION_FSCACHE;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = NULL;
+			break;
+		case Opt_fscache_uniq:
+			string = match_strdup(args);
+			if (!string)
+				goto out_nomem;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = string;
+			mnt->options |= NFS_OPTION_FSCACHE;
+			break;
 
 		/*
 		 * options that take numeric values
@@ -1870,8 +1907,6 @@ static void nfs_clone_super(struct super_block *sb,
  	nfs_initialise_sb(sb);
 }
 
-#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
-
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
 {
 	const struct nfs_server *a = s->s_fs_info;
@@ -2036,6 +2071,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 	if (!s->s_root) {
 		/* initial superblock/root creation */
 		nfs_fill_super(s, data);
+		nfs_fscache_get_super_cookie(s, data);
 	}
 
 	mntroot = nfs_get_root(s, mntfh);
@@ -2056,6 +2092,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 out:
 	kfree(data->nfs_server.hostname);
 	kfree(data->mount_server.hostname);
+	kfree(data->fscache_uniq);
 	security_free_mnt_opts(&data->lsm_opts);
 out_free_fh:
 	kfree(mntfh);
@@ -2083,6 +2120,7 @@ static void nfs_kill_super(struct super_block *s)
 
 	bdi_unregister(&server->backing_dev_info);
 	kill_anon_super(s);
+	nfs_fscache_release_super_cookie(s);
 	nfs_free_server(server);
 }
 
@@ -2390,6 +2428,7 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 	if (!s->s_root) {
 		/* initial superblock/root creation */
 		nfs4_fill_super(s);
+		nfs_fscache_get_super_cookie(s, data);
 	}
 
 	mntroot = nfs4_get_root(s, mntfh);
@@ -2411,6 +2450,7 @@ out:
 	kfree(data->client_address);
 	kfree(data->nfs_server.export_path);
 	kfree(data->nfs_server.hostname);
+	kfree(data->fscache_uniq);
 	security_free_mnt_opts(&data->lsm_opts);
 out_free_fh:
 	kfree(mntfh);
@@ -2437,6 +2477,7 @@ static void nfs4_kill_super(struct super_block *sb)
 	kill_anon_super(sb);
 
 	nfs4_renewd_prepare_shutdown(server);
+	nfs_fscache_release_super_cookie(sb);
 	nfs_free_server(server);
 }
 

fs/splice.c

@@ -59,7 +59,8 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
 		 */
 		wait_on_page_writeback(page);
 
-		if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+		if (page_has_private(page) &&
+		    !try_to_release_page(page, GFP_KERNEL))
 			goto out_unlock;
 
 		/*

fs/super.c

@@ -287,6 +287,7 @@ int fsync_super(struct super_block *sb)
 	__fsync_super(sb);
 	return sync_blockdev(sb->s_bdev);
 }
+EXPORT_SYMBOL_GPL(fsync_super);
 
 /**
  *	generic_shutdown_super	-	common helper for ->kill_sb()

include/linux/fscache-cache.h

@@ -0,0 +1,505 @@
+/* General filesystem caching backing cache interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ *	Documentation/filesystems/caching/backend-api.txt
+ *
+ * for a description of the cache backend interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_CACHE_H
+#define _LINUX_FSCACHE_CACHE_H
+
+#include <linux/fscache.h>
+#include <linux/sched.h>
+#include <linux/slow-work.h>
+
+#define NR_MAXCACHES BITS_PER_LONG
+
+struct fscache_cache;
+struct fscache_cache_ops;
+struct fscache_object;
+struct fscache_operation;
+
+/*
+ * cache tag definition
+ */
+struct fscache_cache_tag {
+	struct list_head	link;
+	struct fscache_cache	*cache;		/* cache referred to by this tag */
+	unsigned long		flags;
+#define FSCACHE_TAG_RESERVED	0		/* T if tag is reserved for a cache */
+	atomic_t		usage;
+	char			name[0];	/* tag name */
+};
+
+/*
+ * cache definition
+ */
+struct fscache_cache {
+	const struct fscache_cache_ops *ops;
+	struct fscache_cache_tag *tag;		/* tag representing this cache */
+	struct kobject		*kobj;		/* system representation of this cache */
+	struct list_head	link;		/* link in list of caches */
+	size_t			max_index_size;	/* maximum size of index data */
+	char			identifier[36];	/* cache label */
+
+	/* node management */
+	struct work_struct	op_gc;		/* operation garbage collector */
+	struct list_head	object_list;	/* list of data/index objects */
+	struct list_head	op_gc_list;	/* list of ops to be deleted */
+	spinlock_t		object_list_lock;
+	spinlock_t		op_gc_list_lock;
+	atomic_t		object_count;	/* no. of live objects in this cache */
+	struct fscache_object	*fsdef;		/* object for the fsdef index */
+	unsigned long		flags;
+#define FSCACHE_IOERROR		0	/* cache stopped on I/O error */
+#define FSCACHE_CACHE_WITHDRAWN	1	/* cache has been withdrawn */
+};
+
+extern wait_queue_head_t fscache_cache_cleared_wq;
+
+/*
+ * operation to be applied to a cache object
+ * - retrieval initiation operations are done in the context of the process
+ *   that issued them, and not in an async thread pool
+ */
+typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
+typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
+
+struct fscache_operation {
+	union {
+		struct work_struct fast_work;	/* record for fast ops */
+		struct slow_work slow_work;	/* record for (very) slow ops */
+	};
+	struct list_head	pend_link;	/* link in object->pending_ops */
+	struct fscache_object	*object;	/* object to be operated upon */
+
+	unsigned long		flags;
+#define FSCACHE_OP_TYPE		0x000f	/* operation type */
+#define FSCACHE_OP_FAST		0x0001	/* - fast op, processor may not sleep for disk */
+#define FSCACHE_OP_SLOW		0x0002	/* - (very) slow op, processor may sleep for disk */
+#define FSCACHE_OP_MYTHREAD	0x0003	/* - processing is done be issuing thread, not pool */
+#define FSCACHE_OP_WAITING	4	/* cleared when op is woken */
+#define FSCACHE_OP_EXCLUSIVE	5	/* exclusive op, other ops must wait */
+#define FSCACHE_OP_DEAD		6	/* op is now dead */
+
+	atomic_t		usage;
+	unsigned		debug_id;	/* debugging ID */
+
+	/* operation processor callback
+	 * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform
+	 *   the op in a non-pool thread */
+	fscache_operation_processor_t processor;
+
+	/* operation releaser */
+	fscache_operation_release_t release;
+};
+
+extern atomic_t fscache_op_debug_id;
+extern const struct slow_work_ops fscache_op_slow_work_ops;
+
+extern void fscache_enqueue_operation(struct fscache_operation *);
+extern void fscache_put_operation(struct fscache_operation *);
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation.  The caller must still set flags,
+ * object, either fast_work or slow_work if necessary, and processor if needed.
+ */
+static inline void fscache_operation_init(struct fscache_operation *op,
+					  fscache_operation_release_t release)
+{
+	atomic_set(&op->usage, 1);
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+	op->release = release;
+	INIT_LIST_HEAD(&op->pend_link);
+}
+
+/**
+ * fscache_operation_init_slow - Do additional initialisation of a slow op
+ * @op: The operation to initialise
+ * @processor: The processor function to assign
+ *
+ * Do additional initialisation of an operation as required for slow work.
+ */
+static inline
+void fscache_operation_init_slow(struct fscache_operation *op,
+				 fscache_operation_processor_t processor)
+{
+	op->processor = processor;
+	slow_work_init(&op->slow_work, &fscache_op_slow_work_ops);
+}
+
+/*
+ * data read operation
+ */
+struct fscache_retrieval {
+	struct fscache_operation op;
+	struct address_space	*mapping;	/* netfs pages */
+	fscache_rw_complete_t	end_io_func;	/* function to call on I/O completion */
+	void			*context;	/* netfs read context (pinned) */
+	struct list_head	to_do;		/* list of things to be done by the backend */
+	unsigned long		start_time;	/* time at which retrieval started */
+};
+
+typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op,
+					     struct page *page,
+					     gfp_t gfp);
+
+typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op,
+					      struct list_head *pages,
+					      unsigned *nr_pages,
+					      gfp_t gfp);
+
+/**
+ * fscache_get_retrieval - Get an extra reference on a retrieval operation
+ * @op: The retrieval operation to get a reference on
+ *
+ * Get an extra reference on a retrieval operation.
+ */
+static inline
+struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op)
+{
+	atomic_inc(&op->op.usage);
+	return op;
+}
+
+/**
+ * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing
+ * @op: The retrieval operation affected
+ *
+ * Enqueue a retrieval operation for processing by the FS-Cache thread pool.
+ */
+static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op)
+{
+	fscache_enqueue_operation(&op->op);
+}
+
+/**
+ * fscache_put_retrieval - Drop a reference to a retrieval operation
+ * @op: The retrieval operation affected
+ *
+ * Drop a reference to a retrieval operation.
+ */
+static inline void fscache_put_retrieval(struct fscache_retrieval *op)
+{
+	fscache_put_operation(&op->op);
+}
+
+/*
+ * cached page storage work item
+ * - used to do three things:
+ *   - batch writes to the cache
+ *   - do cache writes asynchronously
+ *   - defer writes until cache object lookup completion
+ */
+struct fscache_storage {
+	struct fscache_operation op;
+	pgoff_t			store_limit;	/* don't write more than this */
+};
+
+/*
+ * cache operations
+ */
+struct fscache_cache_ops {
+	/* name of cache provider */
+	const char *name;
+
+	/* allocate an object record for a cookie */
+	struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+					       struct fscache_cookie *cookie);
+
+	/* look up the object for a cookie */
+	void (*lookup_object)(struct fscache_object *object);
+
+	/* finished looking up */
+	void (*lookup_complete)(struct fscache_object *object);
+
+	/* increment the usage count on this object (may fail if unmounting) */
+	struct fscache_object *(*grab_object)(struct fscache_object *object);
+
+	/* pin an object in the cache */
+	int (*pin_object)(struct fscache_object *object);
+
+	/* unpin an object in the cache */
+	void (*unpin_object)(struct fscache_object *object);
+
+	/* store the updated auxilliary data on an object */
+	void (*update_object)(struct fscache_object *object);
+
+	/* discard the resources pinned by an object and effect retirement if
+	 * necessary */
+	void (*drop_object)(struct fscache_object *object);
+
+	/* dispose of a reference to an object */
+	void (*put_object)(struct fscache_object *object);
+
+	/* sync a cache */
+	void (*sync_cache)(struct fscache_cache *cache);
+
+	/* notification that the attributes of a non-index object (such as
+	 * i_size) have changed */
+	int (*attr_changed)(struct fscache_object *object);
+
+	/* reserve space for an object's data and associated metadata */
+	int (*reserve_space)(struct fscache_object *object, loff_t i_size);
+
+	/* request a backing block for a page be read or allocated in the
+	 * cache */
+	fscache_page_retrieval_func_t read_or_alloc_page;
+
+	/* request backing blocks for a list of pages be read or allocated in
+	 * the cache */
+	fscache_pages_retrieval_func_t read_or_alloc_pages;
+
+	/* request a backing block for a page be allocated in the cache so that
+	 * it can be written directly */
+	fscache_page_retrieval_func_t allocate_page;
+
+	/* request backing blocks for pages be allocated in the cache so that
+	 * they can be written directly */
+	fscache_pages_retrieval_func_t allocate_pages;
+
+	/* write a page to its backing block in the cache */
+	int (*write_page)(struct fscache_storage *op, struct page *page);
+
+	/* detach backing block from a page (optional)
+	 * - must release the cookie lock before returning
+	 * - may sleep
+	 */
+	void (*uncache_page)(struct fscache_object *object,
+			     struct page *page);
+
+	/* dissociate a cache from all the pages it was backing */
+	void (*dissociate_pages)(struct fscache_cache *cache);
+};
+
+/*
+ * data file or index object cookie
+ * - a file will only appear in one cache
+ * - a request to cache a file may or may not be honoured, subject to
+ *   constraints such as disk space
+ * - indices are created on disk just-in-time
+ */
+struct fscache_cookie {
+	atomic_t			usage;		/* number of users of this cookie */
+	atomic_t			n_children;	/* number of children of this cookie */
+	spinlock_t			lock;
+	struct hlist_head		backing_objects; /* object(s) backing this file/index */
+	const struct fscache_cookie_def	*def;		/* definition */
+	struct fscache_cookie		*parent;	/* parent of this entry */
+	void				*netfs_data;	/* back pointer to netfs */
+	struct radix_tree_root		stores;		/* pages to be stored on this cookie */
+#define FSCACHE_COOKIE_PENDING_TAG	0		/* pages tag: pending write to cache */
+
+	unsigned long			flags;
+#define FSCACHE_COOKIE_LOOKING_UP	0	/* T if non-index cookie being looked up still */
+#define FSCACHE_COOKIE_CREATING		1	/* T if non-index object being created still */
+#define FSCACHE_COOKIE_NO_DATA_YET	2	/* T if new object with no cached data yet */
+#define FSCACHE_COOKIE_PENDING_FILL	3	/* T if pending initial fill on object */
+#define FSCACHE_COOKIE_FILLING		4	/* T if filling object incrementally */
+#define FSCACHE_COOKIE_UNAVAILABLE	5	/* T if cookie is unavailable (error, etc) */
+};
+
+extern struct fscache_cookie fscache_fsdef_index;
+
+/*
+ * on-disk cache file or index handle
+ */
+struct fscache_object {
+	enum fscache_object_state {
+		FSCACHE_OBJECT_INIT,		/* object in initial unbound state */
+		FSCACHE_OBJECT_LOOKING_UP,	/* looking up object */
+		FSCACHE_OBJECT_CREATING,	/* creating object */
+
+		/* active states */
+		FSCACHE_OBJECT_AVAILABLE,	/* cleaning up object after creation */
+		FSCACHE_OBJECT_ACTIVE,		/* object is usable */
+		FSCACHE_OBJECT_UPDATING,	/* object is updating */
+
+		/* terminal states */
+		FSCACHE_OBJECT_DYING,		/* object waiting for accessors to finish */
+		FSCACHE_OBJECT_LC_DYING,	/* object cleaning up after lookup/create */
+		FSCACHE_OBJECT_ABORT_INIT,	/* abort the init state */
+		FSCACHE_OBJECT_RELEASING,	/* releasing object */
+		FSCACHE_OBJECT_RECYCLING,	/* retiring object */
+		FSCACHE_OBJECT_WITHDRAWING,	/* withdrawing object */
+		FSCACHE_OBJECT_DEAD,		/* object is now dead */
+	} state;
+
+	int			debug_id;	/* debugging ID */
+	int			n_children;	/* number of child objects */
+	int			n_ops;		/* number of ops outstanding on object */
+	int			n_obj_ops;	/* number of object ops outstanding on object */
+	int			n_in_progress;	/* number of ops in progress */
+	int			n_exclusive;	/* number of exclusive ops queued */
+	spinlock_t		lock;		/* state and operations lock */
+
+	unsigned long		lookup_jif;	/* time at which lookup started */
+	unsigned long		event_mask;	/* events this object is interested in */
+	unsigned long		events;		/* events to be processed by this object
+						 * (order is important - using fls) */
+#define FSCACHE_OBJECT_EV_REQUEUE	0	/* T if object should be requeued */
+#define FSCACHE_OBJECT_EV_UPDATE	1	/* T if object should be updated */
+#define FSCACHE_OBJECT_EV_CLEARED	2	/* T if accessors all gone */
+#define FSCACHE_OBJECT_EV_ERROR		3	/* T if fatal error occurred during processing */
+#define FSCACHE_OBJECT_EV_RELEASE	4	/* T if netfs requested object release */
+#define FSCACHE_OBJECT_EV_RETIRE	5	/* T if netfs requested object retirement */
+#define FSCACHE_OBJECT_EV_WITHDRAW	6	/* T if cache requested object withdrawal */
+
+	unsigned long		flags;
+#define FSCACHE_OBJECT_LOCK		0	/* T if object is busy being processed */
+#define FSCACHE_OBJECT_PENDING_WRITE	1	/* T if object has pending write */
+#define FSCACHE_OBJECT_WAITING		2	/* T if object is waiting on its parent */
+
+	struct list_head	cache_link;	/* link in cache->object_list */
+	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
+	struct fscache_cache	*cache;		/* cache that supplied this object */
+	struct fscache_cookie	*cookie;	/* netfs's file/index object */
+	struct fscache_object	*parent;	/* parent object */
+	struct slow_work	work;		/* attention scheduling record */
+	struct list_head	dependents;	/* FIFO of dependent objects */
+	struct list_head	dep_link;	/* link in parent's dependents list */
+	struct list_head	pending_ops;	/* unstarted operations on this object */
+	pgoff_t			store_limit;	/* current storage limit */
+};
+
+extern const char *fscache_object_states[];
+
+#define fscache_object_is_active(obj)			      \
+	(!test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) &&  \
+	 (obj)->state >= FSCACHE_OBJECT_AVAILABLE &&	      \
+	 (obj)->state < FSCACHE_OBJECT_DYING)
+
+extern const struct slow_work_ops fscache_object_slow_work_ops;
+
+/**
+ * fscache_object_init - Initialise a cache object description
+ * @object: Object description
+ *
+ * Initialise a cache object description to its basic values.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_object_init(struct fscache_object *object,
+			 struct fscache_cookie *cookie,
+			 struct fscache_cache *cache)
+{
+	atomic_inc(&cache->object_count);
+
+	object->state = FSCACHE_OBJECT_INIT;
+	spin_lock_init(&object->lock);
+	INIT_LIST_HEAD(&object->cache_link);
+	INIT_HLIST_NODE(&object->cookie_link);
+	vslow_work_init(&object->work, &fscache_object_slow_work_ops);
+	INIT_LIST_HEAD(&object->dependents);
+	INIT_LIST_HEAD(&object->dep_link);
+	INIT_LIST_HEAD(&object->pending_ops);
+	object->n_children = 0;
+	object->n_ops = object->n_in_progress = object->n_exclusive = 0;
+	object->events = object->event_mask = 0;
+	object->flags = 0;
+	object->store_limit = 0;
+	object->cache = cache;
+	object->cookie = cookie;
+	object->parent = NULL;
+}
+
+extern void fscache_object_lookup_negative(struct fscache_object *object);
+extern void fscache_obtained_object(struct fscache_object *object);
+
+/**
+ * fscache_object_destroyed - Note destruction of an object in a cache
+ * @cache: The cache from which the object came
+ *
+ * Note the destruction and deallocation of an object record in a cache.
+ */
+static inline void fscache_object_destroyed(struct fscache_cache *cache)
+{
+	if (atomic_dec_and_test(&cache->object_count))
+		wake_up_all(&fscache_cache_cleared_wq);
+}
+
+/**
+ * fscache_object_lookup_error - Note an object encountered an error
+ * @object: The object on which the error was encountered
+ *
+ * Note that an object encountered a fatal error (usually an I/O error) and
+ * that it should be withdrawn as soon as possible.
+ */
+static inline void fscache_object_lookup_error(struct fscache_object *object)
+{
+	set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events);
+}
+
+/**
+ * fscache_set_store_limit - Set the maximum size to be stored in an object
+ * @object: The object to set the maximum on
+ * @i_size: The limit to set in bytes
+ *
+ * Set the maximum size an object is permitted to reach, implying the highest
+ * byte that may be written.  Intended to be called by the attr_changed() op.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_set_store_limit(struct fscache_object *object, loff_t i_size)
+{
+	object->store_limit = i_size >> PAGE_SHIFT;
+	if (i_size & ~PAGE_MASK)
+		object->store_limit++;
+}
+
+/**
+ * fscache_end_io - End a retrieval operation on a page
+ * @op: The FS-Cache operation covering the retrieval
+ * @page: The page that was to be fetched
+ * @error: The error code (0 if successful)
+ *
+ * Note the end of an operation to retrieve a page, as covered by a particular
+ * operation record.
+ */
+static inline void fscache_end_io(struct fscache_retrieval *op,
+				  struct page *page, int error)
+{
+	op->end_io_func(page, op->context, error);
+}
+
+/*
+ * out-of-line cache backend functions
+ */
+extern void fscache_init_cache(struct fscache_cache *cache,
+			       const struct fscache_cache_ops *ops,
+			       const char *idfmt,
+			       ...) __attribute__ ((format (printf, 3, 4)));
+
+extern int fscache_add_cache(struct fscache_cache *cache,
+			     struct fscache_object *fsdef,
+			     const char *tagname);
+extern void fscache_withdraw_cache(struct fscache_cache *cache);
+
+extern void fscache_io_error(struct fscache_cache *cache);
+
+extern void fscache_mark_pages_cached(struct fscache_retrieval *op,
+				      struct pagevec *pagevec);
+
+extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+					       const void *data,
+					       uint16_t datalen);
+
+#endif /* _LINUX_FSCACHE_CACHE_H */

include/linux/fscache.h

@@ -0,0 +1,618 @@
+/* General filesystem caching interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ *	Documentation/filesystems/caching/netfs-api.txt
+ *
+ * for a description of the network filesystem interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_H
+#define _LINUX_FSCACHE_H
+
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+
+#if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE)
+#define fscache_available() (1)
+#define fscache_cookie_valid(cookie) (cookie)
+#else
+#define fscache_available() (0)
+#define fscache_cookie_valid(cookie) (0)
+#endif
+
+
+/*
+ * overload PG_private_2 to give us PG_fscache - this is used to indicate that
+ * a page is currently backed by a local disk cache
+ */
+#define PageFsCache(page)		PagePrivate2((page))
+#define SetPageFsCache(page)		SetPagePrivate2((page))
+#define ClearPageFsCache(page)		ClearPagePrivate2((page))
+#define TestSetPageFsCache(page)	TestSetPagePrivate2((page))
+#define TestClearPageFsCache(page)	TestClearPagePrivate2((page))
+
+/* pattern used to fill dead space in an index entry */
+#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79
+
+struct pagevec;
+struct fscache_cache_tag;
+struct fscache_cookie;
+struct fscache_netfs;
+
+typedef void (*fscache_rw_complete_t)(struct page *page,
+				      void *context,
+				      int error);
+
+/* result of index entry consultation */
+enum fscache_checkaux {
+	FSCACHE_CHECKAUX_OKAY,		/* entry okay as is */
+	FSCACHE_CHECKAUX_NEEDS_UPDATE,	/* entry requires update */
+	FSCACHE_CHECKAUX_OBSOLETE,	/* entry requires deletion */
+};
+
+/*
+ * fscache cookie definition
+ */
+struct fscache_cookie_def {
+	/* name of cookie type */
+	char name[16];
+
+	/* cookie type */
+	uint8_t type;
+#define FSCACHE_COOKIE_TYPE_INDEX	0
+#define FSCACHE_COOKIE_TYPE_DATAFILE	1
+
+	/* select the cache into which to insert an entry in this index
+	 * - optional
+	 * - should return a cache identifier or NULL to cause the cache to be
+	 *   inherited from the parent if possible or the first cache picked
+	 *   for a non-index file if not
+	 */
+	struct fscache_cache_tag *(*select_cache)(
+		const void *parent_netfs_data,
+		const void *cookie_netfs_data);
+
+	/* get an index key
+	 * - should store the key data in the buffer
+	 * - should return the amount of amount stored
+	 * - not permitted to return an error
+	 * - the netfs data from the cookie being used as the source is
+	 *   presented
+	 */
+	uint16_t (*get_key)(const void *cookie_netfs_data,
+			    void *buffer,
+			    uint16_t bufmax);
+
+	/* get certain file attributes from the netfs data
+	 * - this function can be absent for an index
+	 * - not permitted to return an error
+	 * - the netfs data from the cookie being used as the source is
+	 *   presented
+	 */
+	void (*get_attr)(const void *cookie_netfs_data, uint64_t *size);
+
+	/* get the auxilliary data from netfs data
+	 * - this function can be absent if the index carries no state data
+	 * - should store the auxilliary data in the buffer
+	 * - should return the amount of amount stored
+	 * - not permitted to return an error
+	 * - the netfs data from the cookie being used as the source is
+	 *   presented
+	 */
+	uint16_t (*get_aux)(const void *cookie_netfs_data,
+			    void *buffer,
+			    uint16_t bufmax);
+
+	/* consult the netfs about the state of an object
+	 * - this function can be absent if the index carries no state data
+	 * - the netfs data from the cookie being used as the target is
+	 *   presented, as is the auxilliary data
+	 */
+	enum fscache_checkaux (*check_aux)(void *cookie_netfs_data,
+					   const void *data,
+					   uint16_t datalen);
+
+	/* get an extra reference on a read context
+	 * - this function can be absent if the completion function doesn't
+	 *   require a context
+	 */
+	void (*get_context)(void *cookie_netfs_data, void *context);
+
+	/* release an extra reference on a read context
+	 * - this function can be absent if the completion function doesn't
+	 *   require a context
+	 */
+	void (*put_context)(void *cookie_netfs_data, void *context);
+
+	/* indicate pages that now have cache metadata retained
+	 * - this function should mark the specified pages as now being cached
+	 * - the pages will have been marked with PG_fscache before this is
+	 *   called, so this is optional
+	 */
+	void (*mark_pages_cached)(void *cookie_netfs_data,
+				  struct address_space *mapping,
+				  struct pagevec *cached_pvec);
+
+	/* indicate the cookie is no longer cached
+	 * - this function is called when the backing store currently caching
+	 *   a cookie is removed
+	 * - the netfs should use this to clean up any markers indicating
+	 *   cached pages
+	 * - this is mandatory for any object that may have data
+	 */
+	void (*now_uncached)(void *cookie_netfs_data);
+};
+
+/*
+ * fscache cached network filesystem type
+ * - name, version and ops must be filled in before registration
+ * - all other fields will be set during registration
+ */
+struct fscache_netfs {
+	uint32_t			version;	/* indexing version */
+	const char			*name;		/* filesystem name */
+	struct fscache_cookie		*primary_index;
+	struct list_head		link;		/* internal link */
+};
+
+/*
+ * slow-path functions for when there is actually caching available, and the
+ * netfs does actually have a valid token
+ * - these are not to be called directly
+ * - these are undefined symbols when FS-Cache is not configured and the
+ *   optimiser takes care of not using them
+ */
+extern int __fscache_register_netfs(struct fscache_netfs *);
+extern void __fscache_unregister_netfs(struct fscache_netfs *);
+extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *);
+extern void __fscache_release_cache_tag(struct fscache_cache_tag *);
+
+extern struct fscache_cookie *__fscache_acquire_cookie(
+	struct fscache_cookie *,
+	const struct fscache_cookie_def *,
+	void *);
+extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
+extern void __fscache_update_cookie(struct fscache_cookie *);
+extern int __fscache_attr_changed(struct fscache_cookie *);
+extern int __fscache_read_or_alloc_page(struct fscache_cookie *,
+					struct page *,
+					fscache_rw_complete_t,
+					void *,
+					gfp_t);
+extern int __fscache_read_or_alloc_pages(struct fscache_cookie *,
+					 struct address_space *,
+					 struct list_head *,
+					 unsigned *,
+					 fscache_rw_complete_t,
+					 void *,
+					 gfp_t);
+extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t);
+extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t);
+extern void __fscache_uncache_page(struct fscache_cookie *, struct page *);
+extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *);
+extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *);
+
+/**
+ * fscache_register_netfs - Register a filesystem as desiring caching services
+ * @netfs: The description of the filesystem
+ *
+ * Register a filesystem as desiring caching services if they're available.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_register_netfs(struct fscache_netfs *netfs)
+{
+	if (fscache_available())
+		return __fscache_register_netfs(netfs);
+	else
+		return 0;
+}
+
+/**
+ * fscache_unregister_netfs - Indicate that a filesystem no longer desires
+ * caching services
+ * @netfs: The description of the filesystem
+ *
+ * Indicate that a filesystem no longer desires caching services for the
+ * moment.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+	if (fscache_available())
+		__fscache_unregister_netfs(netfs);
+}
+
+/**
+ * fscache_lookup_cache_tag - Look up a cache tag
+ * @name: The name of the tag to search for
+ *
+ * Acquire a specific cache referral tag that can be used to select a specific
+ * cache in which to cache an index.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name)
+{
+	if (fscache_available())
+		return __fscache_lookup_cache_tag(name);
+	else
+		return NULL;
+}
+
+/**
+ * fscache_release_cache_tag - Release a cache tag
+ * @tag: The tag to release
+ *
+ * Release a reference to a cache referral tag previously looked up.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+	if (fscache_available())
+		__fscache_release_cache_tag(tag);
+}
+
+/**
+ * fscache_acquire_cookie - Acquire a cookie to represent a cache object
+ * @parent: The cookie that's to be the parent of this one
+ * @def: A description of the cache object, including callback operations
+ * @netfs_data: An arbitrary piece of data to be kept in the cookie to
+ * represent the cache object to the netfs
+ *
+ * This function is used to inform FS-Cache about part of an index hierarchy
+ * that can be used to locate files.  This is done by requesting a cookie for
+ * each index in the path to the file.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cookie *fscache_acquire_cookie(
+	struct fscache_cookie *parent,
+	const struct fscache_cookie_def *def,
+	void *netfs_data)
+{
+	if (fscache_cookie_valid(parent))
+		return __fscache_acquire_cookie(parent, def, netfs_data);
+	else
+		return NULL;
+}
+
+/**
+ * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding
+ * it
+ * @cookie: The cookie being returned
+ * @retire: True if the cache object the cookie represents is to be discarded
+ *
+ * This function returns a cookie to the cache, forcibly discarding the
+ * associated cache object if retire is set to true.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_relinquish_cookie(cookie, retire);
+}
+
+/**
+ * fscache_update_cookie - Request that a cache object be updated
+ * @cookie: The cookie representing the cache object
+ *
+ * Request an update of the index data for the cache object associated with the
+ * cookie.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_update_cookie(struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_update_cookie(cookie);
+}
+
+/**
+ * fscache_pin_cookie - Pin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be pinned in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_pin_cookie(struct fscache_cookie *cookie)
+{
+	return -ENOBUFS;
+}
+
+/**
+ * fscache_pin_cookie - Unpin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be unpinned from the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unpin_cookie(struct fscache_cookie *cookie)
+{
+}
+
+/**
+ * fscache_attr_changed - Notify cache that an object's attributes changed
+ * @cookie: The cookie representing the cache object
+ *
+ * Send a notification to the cache indicating that an object's attributes have
+ * changed.  This includes the data size.  These attributes will be obtained
+ * through the get_attr() cookie definition op.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_attr_changed(struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_attr_changed(cookie);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_reserve_space - Reserve data space for a cached object
+ * @cookie: The cookie representing the cache object
+ * @i_size: The amount of space to be reserved
+ *
+ * Reserve an amount of space in the cache for the cache object attached to a
+ * cookie so that a write to that object within the space can always be
+ * honoured.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size)
+{
+	return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_page - Read a page from the cache or allocate a block
+ * in which to store it
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to fill if possible
+ * @end_io_func: The callback to invoke when and if the page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a page from the cache, or if that's not possible make a potential
+ * one-block reservation in the cache into which the page may be stored once
+ * fetched from the server.
+ *
+ * If the page is not backed by the cache object, or if it there's some reason
+ * it can't be, -ENOBUFS will be returned and nothing more will be done for
+ * that page.
+ *
+ * Else, if that page is backed by the cache, a read will be initiated directly
+ * to the netfs's page and 0 will be returned by this function.  The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure.  Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if the page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+			       struct page *page,
+			       fscache_rw_complete_t end_io_func,
+			       void *context,
+			       gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_read_or_alloc_page(cookie, page, end_io_func,
+						    context, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate
+ * blocks in which to store them
+ * @cookie: The cookie representing the cache object
+ * @mapping: The netfs inode mapping to which the pages will be attached
+ * @pages: A list of potential netfs pages to be filled
+ * @end_io_func: The callback to invoke when and if each page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a set of pages from the cache, or if that's not possible, attempt to
+ * make a potential one-block reservation for each page in the cache into which
+ * that page may be stored once fetched from the server.
+ *
+ * If some pages are not backed by the cache object, or if it there's some
+ * reason they can't be, -ENOBUFS will be returned and nothing more will be
+ * done for that pages.
+ *
+ * Else, if some of the pages are backed by the cache, a read will be initiated
+ * directly to the netfs's page and 0 will be returned by this function.  The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure.  Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if a page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in
+ * regard to different pages, the return values are prioritised in that order.
+ * Any pages submitted for reading are removed from the pages list.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+				struct address_space *mapping,
+				struct list_head *pages,
+				unsigned *nr_pages,
+				fscache_rw_complete_t end_io_func,
+				void *context,
+				gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_read_or_alloc_pages(cookie, mapping, pages,
+						     nr_pages, end_io_func,
+						     context, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_alloc_page - Allocate a block in which to store a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to allocate a page for
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request Allocation a block in the cache in which to store a netfs page
+ * without retrieving any contents from the cache.
+ *
+ * If the page is not backed by a file then -ENOBUFS will be returned and
+ * nothing more will be done, and no reservation will be made.
+ *
+ * Else, a block will be allocated if one wasn't already, and 0 will be
+ * returned
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_alloc_page(struct fscache_cookie *cookie,
+		       struct page *page,
+		       gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_alloc_page(cookie, page, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_write_page - Request storage of a page in the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to store
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request the contents of the netfs page be written into the cache.  This
+ * request may be ignored if no cache block is currently allocated, in which
+ * case it will return -ENOBUFS.
+ *
+ * If a cache block was already allocated, a write will be initiated and 0 will
+ * be returned.  The PG_fscache_write page bit is set immediately and will then
+ * be cleared at the completion of the write to indicate the success or failure
+ * of the operation.  Note that the completion may happen before the return.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_write_page(struct fscache_cookie *cookie,
+		       struct page *page,
+		       gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_write_page(cookie, page, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_uncache_page - Indicate that caching is no longer required on a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that was being cached.
+ *
+ * Tell the cache that we no longer want a page to be cached and that it should
+ * remove any knowledge of the netfs page it may have.
+ *
+ * Note that this cannot cancel any outstanding I/O operations between this
+ * page and the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_uncache_page(struct fscache_cookie *cookie,
+			  struct page *page)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_uncache_page(cookie, page);
+}
+
+/**
+ * fscache_check_page_write - Ask if a page is being writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache if a page is being written to the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+bool fscache_check_page_write(struct fscache_cookie *cookie,
+			      struct page *page)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_check_page_write(cookie, page);
+	return false;
+}
+
+/**
+ * fscache_wait_on_page_write - Wait for a page to complete writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache to wake us up when a page is no longer being written to the
+ * cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_wait_on_page_write(struct fscache_cookie *cookie,
+				struct page *page)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_wait_on_page_write(cookie, page);
+}
+
+#endif /* _LINUX_FSCACHE_H */

include/linux/nfs_fs.h

@@ -185,6 +185,9 @@ struct nfs_inode {
 	fmode_t			 delegation_state;
 	struct rw_semaphore	rwsem;
 #endif /* CONFIG_NFS_V4*/
+#ifdef CONFIG_NFS_FSCACHE
+	struct fscache_cookie	*fscache;
+#endif
 	struct inode		vfs_inode;
 };
 
@@ -207,6 +210,8 @@ struct nfs_inode {
 #define NFS_INO_ACL_LRU_SET	(2)		/* Inode is on the LRU list */
 #define NFS_INO_MOUNTPOINT	(3)		/* inode is remote mountpoint */
 #define NFS_INO_FLUSHING	(4)		/* inode is flushing out data */
+#define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
+#define NFS_INO_FSCACHE_LOCK	(6)		/* FS-Cache cookie management lock */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
@@ -260,6 +265,11 @@ static inline int NFS_STALE(const struct inode *inode)
 	return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 }
 
+static inline int NFS_FSCACHE(const struct inode *inode)
+{
+	return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
 static inline __u64 NFS_FILEID(const struct inode *inode)
 {
 	return NFS_I(inode)->fileid;
@@ -506,6 +516,8 @@ extern int  nfs_readpages(struct file *, struct address_space *,
 		struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
 extern void nfs_readdata_release(void *data);
+extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
+			       struct page *);
 
 /*
  * Allocate nfs_read_data structures
@@ -583,6 +595,7 @@ extern void * nfs_root_data(void);
 #define NFSDBG_CALLBACK		0x0100
 #define NFSDBG_CLIENT		0x0200
 #define NFSDBG_MOUNT		0x0400
+#define NFSDBG_FSCACHE		0x0800
 #define NFSDBG_ALL		0xFFFF
 
 #ifdef __KERNEL__

include/linux/nfs_fs_sb.h

@@ -64,6 +64,10 @@ struct nfs_client {
 	char			cl_ipaddr[48];
 	unsigned char		cl_id_uniquifier;
 #endif
+
+#ifdef CONFIG_NFS_FSCACHE
+	struct fscache_cookie	*fscache;	/* client index cache cookie */
+#endif
 };
 
 /*
@@ -96,12 +100,19 @@ struct nfs_server {
 	unsigned int		acdirmin;
 	unsigned int		acdirmax;
 	unsigned int		namelen;
+	unsigned int		options;	/* extra options enabled by mount */
+#define NFS_OPTION_FSCACHE	0x00000001	/* - local caching enabled */
 
 	struct nfs_fsid		fsid;
 	__u64			maxfilesize;	/* maximum file size */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	dev_t			s_dev;		/* superblock dev numbers */
 
+#ifdef CONFIG_NFS_FSCACHE
+	struct nfs_fscache_key	*fscache_key;	/* unique key for superblock */
+	struct fscache_cookie	*fscache;	/* superblock cookie */
+#endif
+
 #ifdef CONFIG_NFS_V4
 	u32			attr_bitmask[2];/* V4 bitmask representing the set
 						   of attributes supported on this

include/linux/nfs_iostat.h

@@ -116,4 +116,16 @@ enum nfs_stat_eventcounters {
 	__NFSIOS_COUNTSMAX,
 };
 
+/*
+ * NFS local caching servicing counters
+ */
+enum nfs_stat_fscachecounters {
+	NFSIOS_FSCACHE_PAGES_READ_OK,
+	NFSIOS_FSCACHE_PAGES_READ_FAIL,
+	NFSIOS_FSCACHE_PAGES_WRITTEN_OK,
+	NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL,
+	NFSIOS_FSCACHE_PAGES_UNCACHED,
+	__NFSIOS_FSCACHEMAX,
+};
+
 #endif	/* _LINUX_NFS_IOSTAT */

include/linux/page-flags.h

@@ -82,6 +82,7 @@ enum pageflags {
 	PG_arch_1,
 	PG_reserved,
 	PG_private,		/* If pagecache, has fs-private data */
+	PG_private_2,		/* If pagecache, has fs aux data */
 	PG_writeback,		/* Page is under writeback */
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
 	PG_head,		/* A head page */
@@ -108,6 +109,12 @@ enum pageflags {
 	/* Filesystems */
 	PG_checked = PG_owner_priv_1,
 
+	/* Two page bits are conscripted by FS-Cache to maintain local caching
+	 * state.  These bits are set on pages belonging to the netfs's inodes
+	 * when those inodes are being locally cached.
+	 */
+	PG_fscache = PG_private_2,	/* page backed by cache */
+
 	/* XEN */
 	PG_pinned = PG_owner_priv_1,
 	PG_savepinned = PG_dirty,
@@ -182,7 +189,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 
 struct page;	/* forward declaration */
 
-TESTPAGEFLAG(Locked, locked)
+TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked)
 PAGEFLAG(Error, error)
 PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
@@ -194,8 +201,6 @@ PAGEFLAG(Checked, checked)		/* Used by some filesystems */
 PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
 PAGEFLAG(SavePinned, savepinned);			/* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
-	__SETPAGEFLAG(Private, private)
 PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 
 __PAGEFLAG(SlobPage, slob_page)
@@ -204,6 +209,16 @@ __PAGEFLAG(SlobFree, slob_free)
 __PAGEFLAG(SlubFrozen, slub_frozen)
 __PAGEFLAG(SlubDebug, slub_debug)
 
+/*
+ * Private page markings that may be used by the filesystem that owns the page
+ * for its own purposes.
+ * - PG_private and PG_private_2 cause releasepage() and co to be invoked
+ */
+PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
+	__CLEARPAGEFLAG(Private, private)
+PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
+PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
@@ -384,9 +399,10 @@ static inline void __ClearPageTail(struct page *page)
  * these flags set.  It they are, there is a problem.
  */
 #define PAGE_FLAGS_CHECK_AT_FREE \
-	(1 << PG_lru   | 1 << PG_private   | 1 << PG_locked | \
-	 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \
-	 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active | \
+	(1 << PG_lru	 | 1 << PG_locked    | \
+	 1 << PG_private | 1 << PG_private_2 | \
+	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
+	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
 	 __PG_UNEVICTABLE | __PG_MLOCKED)
 
 /*
@@ -397,4 +413,16 @@ static inline void __ClearPageTail(struct page *page)
 #define PAGE_FLAGS_CHECK_AT_PREP	((1 << NR_PAGEFLAGS) - 1)
 
 #endif /* !__GENERATING_BOUNDS_H */
+
+/**
+ * page_has_private - Determine if page has private stuff
+ * @page: The page to be checked
+ *
+ * Determine if a page has private stuff, indicating that release routines
+ * should be invoked upon it.
+ */
+#define page_has_private(page)			\
+	((page)->flags & ((1 << PG_private) |	\
+			  (1 << PG_private_2)))
+
 #endif	/* PAGE_FLAGS_H */

include/linux/pagemap.h

@@ -383,6 +383,11 @@ static inline void wait_on_page_writeback(struct page *page)
 
 extern void end_page_writeback(struct page *page);
 
+/*
+ * Add an arbitrary waiter to a page's wait queue
+ */
+extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+
 /*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *

include/linux/slow-work.h

@@ -0,0 +1,95 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#ifndef _LINUX_SLOW_WORK_H
+#define _LINUX_SLOW_WORK_H
+
+#ifdef CONFIG_SLOW_WORK
+
+#include <linux/sysctl.h>
+
+struct slow_work;
+
+/*
+ * The operations used to support slow work items
+ */
+struct slow_work_ops {
+	/* get a ref on a work item
+	 * - return 0 if successful, -ve if not
+	 */
+	int (*get_ref)(struct slow_work *work);
+
+	/* discard a ref to a work item */
+	void (*put_ref)(struct slow_work *work);
+
+	/* execute a work item */
+	void (*execute)(struct slow_work *work);
+};
+
+/*
+ * A slow work item
+ * - A reference is held on the parent object by the thread pool when it is
+ *   queued
+ */
+struct slow_work {
+	unsigned long		flags;
+#define SLOW_WORK_PENDING	0	/* item pending (further) execution */
+#define SLOW_WORK_EXECUTING	1	/* item currently executing */
+#define SLOW_WORK_ENQ_DEFERRED	2	/* item enqueue deferred */
+#define SLOW_WORK_VERY_SLOW	3	/* item is very slow */
+	const struct slow_work_ops *ops; /* operations table for this item */
+	struct list_head	link;	/* link in queue */
+};
+
+/**
+ * slow_work_init - Initialise a slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a slow work item.
+ */
+static inline void slow_work_init(struct slow_work *work,
+				  const struct slow_work_ops *ops)
+{
+	work->flags = 0;
+	work->ops = ops;
+	INIT_LIST_HEAD(&work->link);
+}
+
+/**
+ * slow_work_init - Initialise a very slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a very slow work item.  This item will be restricted such that
+ * only a certain number of the pool threads will be able to execute items of
+ * this type.
+ */
+static inline void vslow_work_init(struct slow_work *work,
+				   const struct slow_work_ops *ops)
+{
+	work->flags = 1 << SLOW_WORK_VERY_SLOW;
+	work->ops = ops;
+	INIT_LIST_HEAD(&work->link);
+}
+
+extern int slow_work_enqueue(struct slow_work *work);
+extern int slow_work_register_user(void);
+extern void slow_work_unregister_user(void);
+
+#ifdef CONFIG_SYSCTL
+extern ctl_table slow_work_sysctls[];
+#endif
+
+#endif /* CONFIG_SLOW_WORK */
+#endif /* _LINUX_SLOW_WORK_H */

init/Kconfig

@@ -1014,6 +1014,18 @@ config MARKERS
 
 source "arch/Kconfig"
 
+config SLOW_WORK
+	default n
+	bool "Enable slow work thread pool"
+	help
+	  The slow work thread pool provides a number of dynamically allocated
+	  threads that can be used by the kernel to perform operations that
+	  take a relatively long time.
+
+	  An example of this would be CacheFiles doing a path lookup followed
+	  by a series of mkdirs and a create call, all of which have to touch
+	  disk.
+
 endmenu		# General setup
 
 config HAVE_GENERIC_DMA_COHERENT

kernel/Makefile

@@ -93,6 +93,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
+obj-$(CONFIG_SLOW_WORK) += slow-work.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/slow-work.c

@@ -0,0 +1,640 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/wait.h>
+
+#define SLOW_WORK_CULL_TIMEOUT (5 * HZ)	/* cull threads 5s after running out of
+					 * things to do */
+#define SLOW_WORK_OOM_TIMEOUT (5 * HZ)	/* can't start new threads for 5s after
+					 * OOM */
+
+static void slow_work_cull_timeout(unsigned long);
+static void slow_work_oom_timeout(unsigned long);
+
+#ifdef CONFIG_SYSCTL
+static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *,
+					void __user *, size_t *, loff_t *);
+
+static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+					void __user *, size_t *, loff_t *);
+#endif
+
+/*
+ * The pool of threads has at least min threads in it as long as someone is
+ * using the facility, and may have as many as max.
+ *
+ * A portion of the pool may be processing very slow operations.
+ */
+static unsigned slow_work_min_threads = 2;
+static unsigned slow_work_max_threads = 4;
+static unsigned vslow_work_proportion = 50; /* % of threads that may process
+					     * very slow work */
+
+#ifdef CONFIG_SYSCTL
+static const int slow_work_min_min_threads = 2;
+static int slow_work_max_max_threads = 255;
+static const int slow_work_min_vslow = 1;
+static const int slow_work_max_vslow = 99;
+
+ctl_table slow_work_sysctls[] = {
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "min-threads",
+		.data		= &slow_work_min_threads,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= slow_work_min_threads_sysctl,
+		.extra1		= (void *) &slow_work_min_min_threads,
+		.extra2		= &slow_work_max_threads,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "max-threads",
+		.data		= &slow_work_max_threads,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= slow_work_max_threads_sysctl,
+		.extra1		= &slow_work_min_threads,
+		.extra2		= (void *) &slow_work_max_max_threads,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "vslow-percentage",
+		.data		= &vslow_work_proportion,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= (void *) &slow_work_min_vslow,
+		.extra2		= (void *) &slow_work_max_vslow,
+	},
+	{ .ctl_name = 0 }
+};
+#endif
+
+/*
+ * The active state of the thread pool
+ */
+static atomic_t slow_work_thread_count;
+static atomic_t vslow_work_executing_count;
+
+static bool slow_work_may_not_start_new_thread;
+static bool slow_work_cull; /* cull a thread due to lack of activity */
+static DEFINE_TIMER(slow_work_cull_timer, slow_work_cull_timeout, 0, 0);
+static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
+static struct slow_work slow_work_new_thread; /* new thread starter */
+
+/*
+ * The queues of work items and the lock governing access to them.  These are
+ * shared between all the CPUs.  It doesn't make sense to have per-CPU queues
+ * as the number of threads bears no relation to the number of CPUs.
+ *
+ * There are two queues of work items: one for slow work items, and one for
+ * very slow work items.
+ */
+static LIST_HEAD(slow_work_queue);
+static LIST_HEAD(vslow_work_queue);
+static DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The thread controls.  A variable used to signal to the threads that they
+ * should exit when the queue is empty, a waitqueue used by the threads to wait
+ * for signals, and a completion set by the last thread to exit.
+ */
+static bool slow_work_threads_should_exit;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_thread_wq);
+static DECLARE_COMPLETION(slow_work_last_thread_exited);
+
+/*
+ * The number of users of the thread pool and its lock.  Whilst this is zero we
+ * have no threads hanging around, and when this reaches zero, we wait for all
+ * active or queued work items to complete and kill all the threads we do have.
+ */
+static int slow_work_user_count;
+static DEFINE_MUTEX(slow_work_user_lock);
+
+/*
+ * Calculate the maximum number of active threads in the pool that are
+ * permitted to process very slow work items.
+ *
+ * The answer is rounded up to at least 1, but may not equal or exceed the
+ * maximum number of the threads in the pool.  This means we always have at
+ * least one thread that can process slow work items, and we always have at
+ * least one thread that won't get tied up doing so.
+ */
+static unsigned slow_work_calc_vsmax(void)
+{
+	unsigned vsmax;
+
+	vsmax = atomic_read(&slow_work_thread_count) * vslow_work_proportion;
+	vsmax /= 100;
+	vsmax = max(vsmax, 1U);
+	return min(vsmax, slow_work_max_threads - 1);
+}
+
+/*
+ * Attempt to execute stuff queued on a slow thread.  Return true if we managed
+ * it, false if there was nothing to do.
+ */
+static bool slow_work_execute(void)
+{
+	struct slow_work *work = NULL;
+	unsigned vsmax;
+	bool very_slow;
+
+	vsmax = slow_work_calc_vsmax();
+
+	/* see if we can schedule a new thread to be started if we're not
+	 * keeping up with the work */
+	if (!waitqueue_active(&slow_work_thread_wq) &&
+	    (!list_empty(&slow_work_queue) || !list_empty(&vslow_work_queue)) &&
+	    atomic_read(&slow_work_thread_count) < slow_work_max_threads &&
+	    !slow_work_may_not_start_new_thread)
+		slow_work_enqueue(&slow_work_new_thread);
+
+	/* find something to execute */
+	spin_lock_irq(&slow_work_queue_lock);
+	if (!list_empty(&vslow_work_queue) &&
+	    atomic_read(&vslow_work_executing_count) < vsmax) {
+		work = list_entry(vslow_work_queue.next,
+				  struct slow_work, link);
+		if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags))
+			BUG();
+		list_del_init(&work->link);
+		atomic_inc(&vslow_work_executing_count);
+		very_slow = true;
+	} else if (!list_empty(&slow_work_queue)) {
+		work = list_entry(slow_work_queue.next,
+				  struct slow_work, link);
+		if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags))
+			BUG();
+		list_del_init(&work->link);
+		very_slow = false;
+	} else {
+		very_slow = false; /* avoid the compiler warning */
+	}
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	if (!work)
+		return false;
+
+	if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
+		BUG();
+
+	work->ops->execute(work);
+
+	if (very_slow)
+		atomic_dec(&vslow_work_executing_count);
+	clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
+
+	/* if someone tried to enqueue the item whilst we were executing it,
+	 * then it'll be left unenqueued to avoid multiple threads trying to
+	 * execute it simultaneously
+	 *
+	 * there is, however, a race between us testing the pending flag and
+	 * getting the spinlock, and between the enqueuer setting the pending
+	 * flag and getting the spinlock, so we use a deferral bit to tell us
+	 * if the enqueuer got there first
+	 */
+	if (test_bit(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irq(&slow_work_queue_lock);
+
+		if (!test_bit(SLOW_WORK_EXECUTING, &work->flags) &&
+		    test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags))
+			goto auto_requeue;
+
+		spin_unlock_irq(&slow_work_queue_lock);
+	}
+
+	work->ops->put_ref(work);
+	return true;
+
+auto_requeue:
+	/* we must complete the enqueue operation
+	 * - we transfer our ref on the item back to the appropriate queue
+	 * - don't wake another thread up as we're awake already
+	 */
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+		list_add_tail(&work->link, &vslow_work_queue);
+	else
+		list_add_tail(&work->link, &slow_work_queue);
+	spin_unlock_irq(&slow_work_queue_lock);
+	return true;
+}
+
+/**
+ * slow_work_enqueue - Schedule a slow work item for processing
+ * @work: The work item to queue
+ *
+ * Schedule a slow work item for processing.  If the item is already undergoing
+ * execution, this guarantees not to re-enter the execution routine until the
+ * first execution finishes.
+ *
+ * The item is pinned by this function as it retains a reference to it, managed
+ * through the item operations.  The item is unpinned once it has been
+ * executed.
+ *
+ * An item may hog the thread that is running it for a relatively large amount
+ * of time, sufficient, for example, to perform several lookup, mkdir, create
+ * and setxattr operations.  It may sleep on I/O and may sleep to obtain locks.
+ *
+ * Conversely, if a number of items are awaiting processing, it may take some
+ * time before any given item is given attention.  The number of threads in the
+ * pool may be increased to deal with demand, but only up to a limit.
+ *
+ * If SLOW_WORK_VERY_SLOW is set on the work item, then it will be placed in
+ * the very slow queue, from which only a portion of the threads will be
+ * allowed to pick items to execute.  This ensures that very slow items won't
+ * overly block ones that are just ordinarily slow.
+ *
+ * Returns 0 if successful, -EAGAIN if not.
+ */
+int slow_work_enqueue(struct slow_work *work)
+{
+	unsigned long flags;
+
+	BUG_ON(slow_work_user_count <= 0);
+	BUG_ON(!work);
+	BUG_ON(!work->ops);
+	BUG_ON(!work->ops->get_ref);
+
+	/* when honouring an enqueue request, we only promise that we will run
+	 * the work function in the future; we do not promise to run it once
+	 * per enqueue request
+	 *
+	 * we use the PENDING bit to merge together repeat requests without
+	 * having to disable IRQs and take the spinlock, whilst still
+	 * maintaining our promise
+	 */
+	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+		/* we promise that we will not attempt to execute the work
+		 * function in more than one thread simultaneously
+		 *
+		 * this, however, leaves us with a problem if we're asked to
+		 * enqueue the work whilst someone is executing the work
+		 * function as simply queueing the work immediately means that
+		 * another thread may try executing it whilst it is already
+		 * under execution
+		 *
+		 * to deal with this, we set the ENQ_DEFERRED bit instead of
+		 * enqueueing, and the thread currently executing the work
+		 * function will enqueue the work item when the work function
+		 * returns and it has cleared the EXECUTING bit
+		 */
+		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+		} else {
+			if (work->ops->get_ref(work) < 0)
+				goto cant_get_ref;
+			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+				list_add_tail(&work->link, &vslow_work_queue);
+			else
+				list_add_tail(&work->link, &slow_work_queue);
+			wake_up(&slow_work_thread_wq);
+		}
+
+		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	}
+	return 0;
+
+cant_get_ref:
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return -EAGAIN;
+}
+EXPORT_SYMBOL(slow_work_enqueue);
+
+/*
+ * Worker thread culling algorithm
+ */
+static bool slow_work_cull_thread(void)
+{
+	unsigned long flags;
+	bool do_cull = false;
+
+	spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+	if (slow_work_cull) {
+		slow_work_cull = false;
+
+		if (list_empty(&slow_work_queue) &&
+		    list_empty(&vslow_work_queue) &&
+		    atomic_read(&slow_work_thread_count) >
+		    slow_work_min_threads) {
+			mod_timer(&slow_work_cull_timer,
+				  jiffies + SLOW_WORK_CULL_TIMEOUT);
+			do_cull = true;
+		}
+	}
+
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return do_cull;
+}
+
+/*
+ * Determine if there is slow work available for dispatch
+ */
+static inline bool slow_work_available(int vsmax)
+{
+	return !list_empty(&slow_work_queue) ||
+		(!list_empty(&vslow_work_queue) &&
+		 atomic_read(&vslow_work_executing_count) < vsmax);
+}
+
+/*
+ * Worker thread dispatcher
+ */
+static int slow_work_thread(void *_data)
+{
+	int vsmax;
+
+	DEFINE_WAIT(wait);
+
+	set_freezable();
+	set_user_nice(current, -5);
+
+	for (;;) {
+		vsmax = vslow_work_proportion;
+		vsmax *= atomic_read(&slow_work_thread_count);
+		vsmax /= 100;
+
+		prepare_to_wait(&slow_work_thread_wq, &wait,
+				TASK_INTERRUPTIBLE);
+		if (!freezing(current) &&
+		    !slow_work_threads_should_exit &&
+		    !slow_work_available(vsmax) &&
+		    !slow_work_cull)
+			schedule();
+		finish_wait(&slow_work_thread_wq, &wait);
+
+		try_to_freeze();
+
+		vsmax = vslow_work_proportion;
+		vsmax *= atomic_read(&slow_work_thread_count);
+		vsmax /= 100;
+
+		if (slow_work_available(vsmax) && slow_work_execute()) {
+			cond_resched();
+			if (list_empty(&slow_work_queue) &&
+			    list_empty(&vslow_work_queue) &&
+			    atomic_read(&slow_work_thread_count) >
+			    slow_work_min_threads)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+			continue;
+		}
+
+		if (slow_work_threads_should_exit)
+			break;
+
+		if (slow_work_cull && slow_work_cull_thread())
+			break;
+	}
+
+	if (atomic_dec_and_test(&slow_work_thread_count))
+		complete_and_exit(&slow_work_last_thread_exited, 0);
+	return 0;
+}
+
+/*
+ * Handle thread cull timer expiration
+ */
+static void slow_work_cull_timeout(unsigned long data)
+{
+	slow_work_cull = true;
+	wake_up(&slow_work_thread_wq);
+}
+
+/*
+ * Get a reference on slow work thread starter
+ */
+static int slow_work_new_thread_get_ref(struct slow_work *work)
+{
+	return 0;
+}
+
+/*
+ * Drop a reference on slow work thread starter
+ */
+static void slow_work_new_thread_put_ref(struct slow_work *work)
+{
+}
+
+/*
+ * Start a new slow work thread
+ */
+static void slow_work_new_thread_execute(struct slow_work *work)
+{
+	struct task_struct *p;
+
+	if (slow_work_threads_should_exit)
+		return;
+
+	if (atomic_read(&slow_work_thread_count) >= slow_work_max_threads)
+		return;
+
+	if (!mutex_trylock(&slow_work_user_lock))
+		return;
+
+	slow_work_may_not_start_new_thread = true;
+	atomic_inc(&slow_work_thread_count);
+	p = kthread_run(slow_work_thread, NULL, "kslowd");
+	if (IS_ERR(p)) {
+		printk(KERN_DEBUG "Slow work thread pool: OOM\n");
+		if (atomic_dec_and_test(&slow_work_thread_count))
+			BUG(); /* we're running on a slow work thread... */
+		mod_timer(&slow_work_oom_timer,
+			  jiffies + SLOW_WORK_OOM_TIMEOUT);
+	} else {
+		/* ratelimit the starting of new threads */
+		mod_timer(&slow_work_oom_timer, jiffies + 1);
+	}
+
+	mutex_unlock(&slow_work_user_lock);
+}
+
+static const struct slow_work_ops slow_work_new_thread_ops = {
+	.get_ref	= slow_work_new_thread_get_ref,
+	.put_ref	= slow_work_new_thread_put_ref,
+	.execute	= slow_work_new_thread_execute,
+};
+
+/*
+ * post-OOM new thread start suppression expiration
+ */
+static void slow_work_oom_timeout(unsigned long data)
+{
+	slow_work_may_not_start_new_thread = false;
+}
+
+#ifdef CONFIG_SYSCTL
+/*
+ * Handle adjustment of the minimum number of threads
+ */
+static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
+					struct file *filp, void __user *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int n;
+
+	if (ret == 0) {
+		mutex_lock(&slow_work_user_lock);
+		if (slow_work_user_count > 0) {
+			/* see if we need to start or stop threads */
+			n = atomic_read(&slow_work_thread_count) -
+				slow_work_min_threads;
+
+			if (n < 0 && !slow_work_may_not_start_new_thread)
+				slow_work_enqueue(&slow_work_new_thread);
+			else if (n > 0)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+		}
+		mutex_unlock(&slow_work_user_lock);
+	}
+
+	return ret;
+}
+
+/*
+ * Handle adjustment of the maximum number of threads
+ */
+static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
+					struct file *filp, void __user *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int n;
+
+	if (ret == 0) {
+		mutex_lock(&slow_work_user_lock);
+		if (slow_work_user_count > 0) {
+			/* see if we need to stop threads */
+			n = slow_work_max_threads -
+				atomic_read(&slow_work_thread_count);
+
+			if (n < 0)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+		}
+		mutex_unlock(&slow_work_user_lock);
+	}
+
+	return ret;
+}
+#endif /* CONFIG_SYSCTL */
+
+/**
+ * slow_work_register_user - Register a user of the facility
+ *
+ * Register a user of the facility, starting up the initial threads if there
+ * aren't any other users at this point.  This will return 0 if successful, or
+ * an error if not.
+ */
+int slow_work_register_user(void)
+{
+	struct task_struct *p;
+	int loop;
+
+	mutex_lock(&slow_work_user_lock);
+
+	if (slow_work_user_count == 0) {
+		printk(KERN_NOTICE "Slow work thread pool: Starting up\n");
+		init_completion(&slow_work_last_thread_exited);
+
+		slow_work_threads_should_exit = false;
+		slow_work_init(&slow_work_new_thread,
+			       &slow_work_new_thread_ops);
+		slow_work_may_not_start_new_thread = false;
+		slow_work_cull = false;
+
+		/* start the minimum number of threads */
+		for (loop = 0; loop < slow_work_min_threads; loop++) {
+			atomic_inc(&slow_work_thread_count);
+			p = kthread_run(slow_work_thread, NULL, "kslowd");
+			if (IS_ERR(p))
+				goto error;
+		}
+		printk(KERN_NOTICE "Slow work thread pool: Ready\n");
+	}
+
+	slow_work_user_count++;
+	mutex_unlock(&slow_work_user_lock);
+	return 0;
+
+error:
+	if (atomic_dec_and_test(&slow_work_thread_count))
+		complete(&slow_work_last_thread_exited);
+	if (loop > 0) {
+		printk(KERN_ERR "Slow work thread pool:"
+		       " Aborting startup on ENOMEM\n");
+		slow_work_threads_should_exit = true;
+		wake_up_all(&slow_work_thread_wq);
+		wait_for_completion(&slow_work_last_thread_exited);
+		printk(KERN_ERR "Slow work thread pool: Aborted\n");
+	}
+	mutex_unlock(&slow_work_user_lock);
+	return PTR_ERR(p);
+}
+EXPORT_SYMBOL(slow_work_register_user);
+
+/**
+ * slow_work_unregister_user - Unregister a user of the facility
+ *
+ * Unregister a user of the facility, killing all the threads if this was the
+ * last one.
+ */
+void slow_work_unregister_user(void)
+{
+	mutex_lock(&slow_work_user_lock);
+
+	BUG_ON(slow_work_user_count <= 0);
+
+	slow_work_user_count--;
+	if (slow_work_user_count == 0) {
+		printk(KERN_NOTICE "Slow work thread pool: Shutting down\n");
+		slow_work_threads_should_exit = true;
+		wake_up_all(&slow_work_thread_wq);
+		wait_for_completion(&slow_work_last_thread_exited);
+		printk(KERN_NOTICE "Slow work thread pool:"
+		       " Shut down complete\n");
+	}
+
+	del_timer_sync(&slow_work_cull_timer);
+
+	mutex_unlock(&slow_work_user_lock);
+}
+EXPORT_SYMBOL(slow_work_unregister_user);
+
+/*
+ * Initialise the slow work facility
+ */
+static int __init init_slow_work(void)
+{
+	unsigned nr_cpus = num_possible_cpus();
+
+	if (slow_work_max_threads < nr_cpus)
+		slow_work_max_threads = nr_cpus;
+#ifdef CONFIG_SYSCTL
+	if (slow_work_max_max_threads < nr_cpus * 2)
+		slow_work_max_max_threads = nr_cpus * 2;
+#endif
+	return 0;
+}
+
+subsys_initcall(init_slow_work);

kernel/sysctl.c

@@ -48,6 +48,7 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
+#include <linux/slow-work.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -897,6 +898,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &scan_unevictable_handler,
 	},
 #endif
+#ifdef CONFIG_SLOW_WORK
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "slow-work",
+		.mode		= 0555,
+		.child		= slow_work_sysctls,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt

mm/filemap.c

@@ -564,6 +564,24 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 
+/**
+ * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
+ * @page - Page defining the wait queue of interest
+ * @waiter - Waiter to add to the queue
+ *
+ * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ */
+void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, waiter);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_page_wait_queue);
+
 /**
  * unlock_page - unlock a locked page
  * @page: the page
@@ -2463,6 +2481,9 @@ EXPORT_SYMBOL(generic_file_aio_write);
  * (presumably at page->private).  If the release was successful, return `1'.
  * Otherwise return zero.
  *
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS).
  *

mm/migrate.c

@@ -250,7 +250,7 @@ out:
  * The number of remaining references must be:
  * 1 for anonymous pages without a mapping
  * 2 for pages with a mapping
- * 3 for pages with a mapping and PagePrivate set.
+ * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page)
@@ -270,7 +270,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
  					page_index(page));
 
-	expected_count = 2 + !!PagePrivate(page);
+	expected_count = 2 + !!page_has_private(page);
 	if (page_count(page) != expected_count ||
 			(struct page *)radix_tree_deref_slot(pslot) != page) {
 		spin_unlock_irq(&mapping->tree_lock);
@@ -386,7 +386,7 @@ EXPORT_SYMBOL(fail_migrate_page);
 
 /*
  * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
+ * pages that do not use PagePrivate/PagePrivate2.
  *
  * Pages are locked upon entry and exit.
  */
@@ -522,7 +522,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (PagePrivate(page) &&
+	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
@@ -655,7 +655,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	 * free the metadata, so the page can be freed.
 	 */
 	if (!page->mapping) {
-		if (!PageAnon(page) && PagePrivate(page)) {
+		if (!PageAnon(page) && page_has_private(page)) {
 			/*
 			 * Go direct to try_to_free_buffers() here because
 			 * a) that's what try_to_release_page() would do anyway

mm/readahead.c

@@ -31,6 +31,42 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 
 #define list_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+/*
+ * see if a page needs releasing upon read_cache_pages() failure
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ *   before calling, such as the NFS fs marking pages that are cached locally
+ *   on disk, thus we need to give the fs a chance to clean up in the event of
+ *   an error
+ */
+static void read_cache_pages_invalidate_page(struct address_space *mapping,
+					     struct page *page)
+{
+	if (page_has_private(page)) {
+		if (!trylock_page(page))
+			BUG();
+		page->mapping = mapping;
+		do_invalidatepage(page, 0);
+		page->mapping = NULL;
+		unlock_page(page);
+	}
+	page_cache_release(page);
+}
+
+/*
+ * release a list of pages, invalidating them first if need be
+ */
+static void read_cache_pages_invalidate_pages(struct address_space *mapping,
+					      struct list_head *pages)
+{
+	struct page *victim;
+
+	while (!list_empty(pages)) {
+		victim = list_to_page(pages);
+		list_del(&victim->lru);
+		read_cache_pages_invalidate_page(mapping, victim);
+	}
+}
+
 /**
  * read_cache_pages - populate an address space with some pages & start reads against them
  * @mapping: the address_space
@@ -52,14 +88,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
-			page_cache_release(page);
+			read_cache_pages_invalidate_page(mapping, page);
 			continue;
 		}
 		page_cache_release(page);
 
 		ret = filler(data, page);
 		if (unlikely(ret)) {
-			put_pages_list(pages);
+			read_cache_pages_invalidate_pages(mapping, pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);

mm/swap.c

@@ -448,8 +448,8 @@ void pagevec_strip(struct pagevec *pvec)
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 
-		if (PagePrivate(page) && trylock_page(page)) {
-			if (PagePrivate(page))
+		if (page_has_private(page) && trylock_page(page)) {
+			if (page_has_private(page))
 				try_to_release_page(page, 0);
 			unlock_page(page);
 		}

mm/truncate.c

@@ -50,7 +50,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
 	zero_user_segment(page, partial, PAGE_CACHE_SIZE);
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, partial);
 }
 
@@ -99,7 +99,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return;
 
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, 0);
 
 	cancel_dirty_page(page, PAGE_CACHE_SIZE);
@@ -126,7 +126,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, 0))
+	if (page_has_private(page) && !try_to_release_page(page, 0))
 		return 0;
 
 	clear_page_mlock(page);
@@ -348,7 +348,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -356,7 +356,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 		goto failed;
 
 	clear_page_mlock(page);
-	BUG_ON(PagePrivate(page));
+	BUG_ON(page_has_private(page));
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	page_cache_release(page);	/* pagecache ref */

mm/vmscan.c

@@ -283,7 +283,7 @@ static inline int page_mapping_inuse(struct page *page)
 
 static inline int is_page_cache_freeable(struct page *page)
 {
-	return page_count(page) - !!PagePrivate(page) == 2;
+	return page_count(page) - !!page_has_private(page) == 2;
 }
 
 static int may_write_to_queue(struct backing_dev_info *bdi)
@@ -367,7 +367,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 		 * Some data journaling orphaned pages can have
 		 * page->mapping == NULL while being dirty with clean buffers.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (try_to_free_buffers(page)) {
 				ClearPageDirty(page);
 				printk("%s: orphaned page\n", __func__);
@@ -727,7 +727,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * process address space (page_count == 1) it can be freed.
 		 * Otherwise, leave the page on the LRU so it is swappable.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (!try_to_release_page(page, sc->gfp_mask))
 				goto activate_locked;
 			if (!mapping && page_count(page) == 1) {

security/security.c

@@ -445,6 +445,7 @@ int security_inode_create(struct inode *dir, struct dentry *dentry, int mode)
 		return 0;
 	return security_ops->inode_create(dir, dentry, mode);
 }
+EXPORT_SYMBOL_GPL(security_inode_create);
 
 int security_inode_link(struct dentry *old_dentry, struct inode *dir,
 			 struct dentry *new_dentry)
@@ -475,6 +476,7 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 		return 0;
 	return security_ops->inode_mkdir(dir, dentry, mode);
 }
+EXPORT_SYMBOL_GPL(security_inode_mkdir);
 
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry)
 {