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: (31 commits)
  FS-Cache: Provide nop fscache_stat_d() if CONFIG_FSCACHE_STATS=n
  SLOW_WORK: Fix GFS2 to #include <linux/module.h> before using THIS_MODULE
  SLOW_WORK: Fix CIFS to pass THIS_MODULE to slow_work_register_user()
  CacheFiles: Don't log lookup/create failing with ENOBUFS
  CacheFiles: Catch an overly long wait for an old active object
  CacheFiles: Better showing of debugging information in active object problems
  CacheFiles: Mark parent directory locks as I_MUTEX_PARENT to keep lockdep happy
  CacheFiles: Handle truncate unlocking the page we're reading
  CacheFiles: Don't write a full page if there's only a partial page to cache
  FS-Cache: Actually requeue an object when requested
  FS-Cache: Start processing an object's operations on that object's death
  FS-Cache: Make sure FSCACHE_COOKIE_LOOKING_UP cleared on lookup failure
  FS-Cache: Add a retirement stat counter
  FS-Cache: Handle pages pending storage that get evicted under OOM conditions
  FS-Cache: Handle read request vs lookup, creation or other cache failure
  FS-Cache: Don't delete pending pages from the page-store tracking tree
  FS-Cache: Fix lock misorder in fscache_write_op()
  FS-Cache: The object-available state can't rely on the cookie to be available
  FS-Cache: Permit cache retrieval ops to be interrupted in the initial wait phase
  FS-Cache: Use radix tree preload correctly in tracking of pages to be stored
  ...

Documentation/filesystems/caching/fscache.txt

@@ -235,6 +235,7 @@ proc files.
 		neg=N	Number of negative lookups made
 		pos=N	Number of positive lookups made
 		crt=N	Number of objects created by lookup
+		tmo=N	Number of lookups timed out and requeued
 	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
@@ -250,8 +251,10 @@ proc files.
 		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
+		int=N	Number of alloc reqs aborted -ERESTARTSYS
 		ops=N	Number of alloc reqs submitted
 		owt=N	Number of alloc reqs waited for CPU time
+		abt=N	Number of alloc reqs aborted due to object death
 	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
@@ -261,6 +264,7 @@ proc files.
 		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
+		abt=N	Number of retr reqs aborted due to object death
 	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
@@ -268,12 +272,37 @@ proc files.
 		oom=N	Number of store reqs failed -ENOMEM
 		ops=N	Number of store reqs submitted
 		run=N	Number of store reqs granted CPU time
+		pgs=N	Number of pages given store req processing time
+		rxd=N	Number of store reqs deleted from tracking tree
+		olm=N	Number of store reqs over store limit
+	VmScan	nos=N	Number of release reqs against pages with no pending store
+		gon=N	Number of release reqs against pages stored by time lock granted
+		bsy=N	Number of release reqs ignored due to in-progress store
+		can=N	Number of page stores cancelled due to release req
 	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
+		can=N	Number of async ops cancelled
+		rej=N	Number of async ops rejected due to object lookup/create failure
 		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
+	CacheOp	alo=N	Number of in-progress alloc_object() cache ops
+		luo=N	Number of in-progress lookup_object() cache ops
+		luc=N	Number of in-progress lookup_complete() cache ops
+		gro=N	Number of in-progress grab_object() cache ops
+		upo=N	Number of in-progress update_object() cache ops
+		dro=N	Number of in-progress drop_object() cache ops
+		pto=N	Number of in-progress put_object() cache ops
+		syn=N	Number of in-progress sync_cache() cache ops
+		atc=N	Number of in-progress attr_changed() cache ops
+		rap=N	Number of in-progress read_or_alloc_page() cache ops
+		ras=N	Number of in-progress read_or_alloc_pages() cache ops
+		alp=N	Number of in-progress allocate_page() cache ops
+		als=N	Number of in-progress allocate_pages() cache ops
+		wrp=N	Number of in-progress write_page() cache ops
+		ucp=N	Number of in-progress uncache_page() cache ops
+		dsp=N	Number of in-progress dissociate_pages() cache ops
 
 
  (*) /proc/fs/fscache/histogram
@@ -299,6 +328,87 @@ proc files.
      jiffy range covered, and the SECS field the equivalent number of seconds.
 
 
+===========
+OBJECT LIST
+===========
+
+If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a
+list of all the objects currently allocated and allow them to be viewed
+through:
+
+	/proc/fs/fscache/objects
+
+This will look something like:
+
+	[root@andromeda ~]# head /proc/fs/fscache/objects
+	OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA       OBJECT_KEY, AUX_DATA
+	======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================
+	   17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
+	   1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
+
+where the first set of columns before the '|' describe the object:
+
+	COLUMN	DESCRIPTION
+	=======	===============================================================
+	OBJECT	Object debugging ID (appears as OBJ%x in some debug messages)
+	PARENT	Debugging ID of parent object
+	STAT	Object state
+	CHLDN	Number of child objects of this object
+	OPS	Number of outstanding operations on this object
+	OOP	Number of outstanding child object management operations
+	IPR
+	EX	Number of outstanding exclusive operations
+	READS	Number of outstanding read operations
+	EM	Object's event mask
+	EV	Events raised on this object
+	F	Object flags
+	S	Object slow-work work item flags
+
+and the second set of columns describe the object's cookie, if present:
+
+	COLUMN		DESCRIPTION
+	===============	=======================================================
+	NETFS_COOKIE_DEF Name of netfs cookie definition
+	TY		Cookie type (IX - index, DT - data, hex - special)
+	FL		Cookie flags
+	NETFS_DATA	Netfs private data stored in the cookie
+	OBJECT_KEY	Object key	} 1 column, with separating comma
+	AUX_DATA	Object aux data	} presence may be configured
+
+The data shown may be filtered by attaching the a key to an appropriate keyring
+before viewing the file.  Something like:
+
+		keyctl add user fscache:objlist <restrictions> @s
+
+where <restrictions> are a selection of the following letters:
+
+	K	Show hexdump of object key (don't show if not given)
+	A	Show hexdump of object aux data (don't show if not given)
+
+and the following paired letters:
+
+	C	Show objects that have a cookie
+	c	Show objects that don't have a cookie
+	B	Show objects that are busy
+	b	Show objects that aren't busy
+	W	Show objects that have pending writes
+	w	Show objects that don't have pending writes
+	R	Show objects that have outstanding reads
+	r	Show objects that don't have outstanding reads
+	S	Show objects that have slow work queued
+	s	Show objects that don't have slow work queued
+
+If neither side of a letter pair is given, then both are implied.  For example:
+
+	keyctl add user fscache:objlist KB @s
+
+shows objects that are busy, and lists their object keys, but does not dump
+their auxiliary data.  It also implies "CcWwRrSs", but as 'B' is given, 'b' is
+not implied.
+
+By default all objects and all fields will be shown.
+
+
 =========
 DEBUGGING
 =========

Documentation/filesystems/caching/netfs-api.txt

@@ -641,7 +641,7 @@ 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:
+invalidation functions must use:
 
 	bool fscache_check_page_write(struct fscache_cookie *cookie,
 				      struct page *page);
@@ -654,6 +654,25 @@ to see if a page is being written to the cache, and:
 to wait for it to finish if it is.
 
 
+When releasepage() is being implemented, a special FS-Cache function exists to
+manage the heuristics of coping with vmscan trying to eject pages, which may
+conflict with the cache trying to write pages to the cache (which may itself
+need to allocate memory):
+
+	bool fscache_maybe_release_page(struct fscache_cookie *cookie,
+					struct page *page,
+					gfp_t gfp);
+
+This takes the netfs cookie, and the page and gfp arguments as supplied to
+releasepage().  It will return false if the page cannot be released yet for
+some reason and if it returns true, the page has been uncached and can now be
+released.
+
+To make a page available for release, this function may wait for an outstanding
+storage request to complete, or it may attempt to cancel the storage request -
+in which case the page will not be stored in the cache this time.
+
+
 ==========================
 INDEX AND DATA FILE UPDATE
 ==========================

Documentation/slow-work.txt

@@ -41,6 +41,13 @@ 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.
 
+A further class of work item is available, based on the slow work item class:
+
+ (*) Delayed slow work items.
+
+These are slow work items that have a timer to defer queueing of the item for
+a while.
+
 
 THREAD-TO-CLASS ALLOCATION
 --------------------------
@@ -64,9 +71,11 @@ 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();
+	 int ret = slow_work_register_user(struct module *module);
 
-This will return 0 if successful, or a -ve error upon failure.
+This will return 0 if successful, or a -ve error upon failure.  The module
+pointer should be the module interested in using this facility (almost
+certainly THIS_MODULE).
 
 
 Slow work items may then be set up by:
@@ -91,6 +100,10 @@ Slow work items may then be set up by:
 
 	slow_work_init(&myitem, &myitem_ops);
 
+     or:
+
+	delayed_slow_work_init(&myitem, &myitem_ops);
+
      or:
 
 	vslow_work_init(&myitem, &myitem_ops);
@@ -102,15 +115,92 @@ 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.
+on the item, 0 otherwise, or (for delayed work):
+
+	int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay);
 
 
 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
+operation.  But as the reference counting is optional, means to cancel
+existing work items are also included:
+
+	cancel_slow_work(&myitem);
+	cancel_delayed_slow_work(&myitem);
+
+can be used to cancel pending work.  The above cancel function waits for
+existing work to have been executed (or prevent execution of them, depending
+on timing).
+
+
+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();
+	slow_work_unregister_user(struct module *module);
+
+The module pointer is used to wait for all outstanding work items for that
+module before completing the unregistration.  This prevents the put_ref() code
+from being taken away before it completes.  module should almost certainly be
+THIS_MODULE.
+
+
+================
+HELPER FUNCTIONS
+================
+
+The slow-work facility provides a function by which it can be determined
+whether or not an item is queued for later execution:
+
+	bool queued = slow_work_is_queued(struct slow_work *work);
+
+If it returns false, then the item is not on the queue (it may be executing
+with a requeue pending).  This can be used to work out whether an item on which
+another depends is on the queue, thus allowing a dependent item to be queued
+after it.
+
+If the above shows an item on which another depends not to be queued, then the
+owner of the dependent item might need to wait.  However, to avoid locking up
+the threads unnecessarily be sleeping in them, it can make sense under some
+circumstances to return the work item to the queue, thus deferring it until
+some other items have had a chance to make use of the yielded thread.
+
+To yield a thread and defer an item, the work function should simply enqueue
+the work item again and return.  However, this doesn't work if there's nothing
+actually on the queue, as the thread just vacated will jump straight back into
+the item's work function, thus busy waiting on a CPU.
+
+Instead, the item should use the thread to wait for the dependency to go away,
+but rather than using schedule() or schedule_timeout() to sleep, it should use
+the following function:
+
+	bool requeue = slow_work_sleep_till_thread_needed(
+			struct slow_work *work,
+			signed long *_timeout);
+
+This will add a second wait and then sleep, such that it will be woken up if
+either something appears on the queue that could usefully make use of the
+thread - and behind which this item can be queued, or if the event the caller
+set up to wait for happens.  True will be returned if something else appeared
+on the queue and this work function should perhaps return, of false if
+something else woke it up.  The timeout is as for schedule_timeout().
+
+For example:
+
+	wq = bit_waitqueue(&my_flags, MY_BIT);
+	init_wait(&wait);
+	requeue = false;
+	do {
+		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+		if (!test_bit(MY_BIT, &my_flags))
+			break;
+		requeue = slow_work_sleep_till_thread_needed(&my_work,
+							     &timeout);
+	} while (timeout > 0 && !requeue);
+	finish_wait(wq, &wait);
+	if (!test_bit(MY_BIT, &my_flags)
+		goto do_my_thing;
+	if (requeue)
+		return; // to slow_work
 
 
 ===============
@@ -118,7 +208,8 @@ ITEM OPERATIONS
 ===============
 
 Each work item requires a table of operations of type struct slow_work_ops.
-All members are required:
+Only ->execute() is required; the getting and putting of a reference and the
+describing of an item are all optional.
 
  (*) Get a reference on an item:
 
@@ -148,6 +239,16 @@ All members are required:
      This should perform the work required of the item.  It may sleep, it may
      perform disk I/O and it may wait for locks.
 
+ (*) View an item through /proc:
+
+	void (*desc)(struct slow_work *work, struct seq_file *m);
+
+     If supplied, this should print to 'm' a small string describing the work
+     the item is to do.  This should be no more than about 40 characters, and
+     shouldn't include a newline character.
+
+     See the 'Viewing executing and queued items' section below.
+
 
 ==================
 POOL CONFIGURATION
@@ -172,3 +273,50 @@ The slow-work thread pool has a number of configurables:
      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.
+
+
+==================================
+VIEWING EXECUTING AND QUEUED ITEMS
+==================================
+
+If CONFIG_SLOW_WORK_PROC is enabled, a proc file is made available:
+
+	/proc/slow_work_rq
+
+through which the list of work items being executed and the queues of items to
+be executed may be viewed.  The owner of a work item is given the chance to
+add some information of its own.
+
+The contents look something like the following:
+
+    THR PID   ITEM ADDR        FL MARK  DESC
+    === ===== ================ == ===== ==========
+      0  3005 ffff880023f52348  a 952ms FSC: OBJ17d3: LOOK
+      1  3006 ffff880024e33668  2 160ms FSC: OBJ17e5 OP60d3b: Write1/Store fl=2
+      2  3165 ffff8800296dd180  a 424ms FSC: OBJ17e4: LOOK
+      3  4089 ffff8800262c8d78  a 212ms FSC: OBJ17ea: CRTN
+      4  4090 ffff88002792bed8  2 388ms FSC: OBJ17e8 OP60d36: Write1/Store fl=2
+      5  4092 ffff88002a0ef308  2 388ms FSC: OBJ17e7 OP60d2e: Write1/Store fl=2
+      6  4094 ffff88002abaf4b8  2 132ms FSC: OBJ17e2 OP60d4e: Write1/Store fl=2
+      7  4095 ffff88002bb188e0  a 388ms FSC: OBJ17e9: CRTN
+    vsq     - ffff880023d99668  1 308ms FSC: OBJ17e0 OP60f91: Write1/EnQ fl=2
+    vsq     - ffff8800295d1740  1 212ms FSC: OBJ16be OP4d4b6: Write1/EnQ fl=2
+    vsq     - ffff880025ba3308  1 160ms FSC: OBJ179a OP58dec: Write1/EnQ fl=2
+    vsq     - ffff880024ec83e0  1 160ms FSC: OBJ17ae OP599f2: Write1/EnQ fl=2
+    vsq     - ffff880026618e00  1 160ms FSC: OBJ17e6 OP60d33: Write1/EnQ fl=2
+    vsq     - ffff880025a2a4b8  1 132ms FSC: OBJ16a2 OP4d583: Write1/EnQ fl=2
+    vsq     - ffff880023cbe6d8  9 212ms FSC: OBJ17eb: LOOK
+    vsq     - ffff880024d37590  9 212ms FSC: OBJ17ec: LOOK
+    vsq     - ffff880027746cb0  9 212ms FSC: OBJ17ed: LOOK
+    vsq     - ffff880024d37ae8  9 212ms FSC: OBJ17ee: LOOK
+    vsq     - ffff880024d37cb0  9 212ms FSC: OBJ17ef: LOOK
+    vsq     - ffff880025036550  9 212ms FSC: OBJ17f0: LOOK
+    vsq     - ffff8800250368e0  9 212ms FSC: OBJ17f1: LOOK
+    vsq     - ffff880025036aa8  9 212ms FSC: OBJ17f2: LOOK
+
+In the 'THR' column, executing items show the thread they're occupying and
+queued threads indicate which queue they're on.  'PID' shows the process ID of
+a slow-work thread that's executing something.  'FL' shows the work item flags.
+'MARK' indicates how long since an item was queued or began executing.  Lastly,
+the 'DESC' column permits the owner of an item to give some information.
+

fs/9p/cache.c

@@ -343,18 +343,7 @@ int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
 
 	BUG_ON(!vcookie->fscache);
 
-	if (PageFsCache(page)) {
+	return fscache_maybe_release_page(vnode->cache, page, gfp);
-		if (fscache_check_page_write(vcookie->fscache, page)) {
-			if (!(gfp & __GFP_WAIT))
-				return 0;
-			fscache_wait_on_page_write(vcookie->fscache, page);
-		}
-
-		fscache_uncache_page(vcookie->fscache, page);
-		ClearPageFsCache(page);
-	}
-
-	return 1;
 }
 
 void __v9fs_fscache_invalidate_page(struct page *page)
@@ -368,7 +357,6 @@ void __v9fs_fscache_invalidate_page(struct page *page)
 		fscache_wait_on_page_write(vcookie->fscache, page);
 		BUG_ON(!PageLocked(page));
 		fscache_uncache_page(vcookie->fscache, page);
-		ClearPageFsCache(page);
 	}
 }
 

fs/afs/file.c

@@ -315,7 +315,6 @@ static void afs_invalidatepage(struct page *page, unsigned long offset)
 			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
 
@@ -349,17 +348,9 @@ static int afs_releasepage(struct page *page, gfp_t 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_maybe_release_page(vnode->cache, page, gfp_flags)) {
-		if (fscache_check_page_write(vnode->cache, page)) {
+		_leave(" = F [cache busy]");
-			if (!(gfp_flags & __GFP_WAIT)) {
+		return 0;
-				_leave(" = F [cache busy]");
-				return 0;
-			}
-			fscache_wait_on_page_write(vnode->cache, page);
-		}
-
-		fscache_uncache_page(vnode->cache, page);
-		ClearPageFsCache(page);
 	}
 #endif
 

fs/cachefiles/interface.c

@@ -114,8 +114,9 @@ nomem_lookup_data:
 
 /*
  * attempt to look up the nominated node in this cache
+ * - return -ETIMEDOUT to be scheduled again
  */
-static void cachefiles_lookup_object(struct fscache_object *_object)
+static int cachefiles_lookup_object(struct fscache_object *_object)
 {
 	struct cachefiles_lookup_data *lookup_data;
 	struct cachefiles_object *parent, *object;
@@ -145,13 +146,15 @@ static void cachefiles_lookup_object(struct fscache_object *_object)
 	    object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
 		cachefiles_attr_changed(&object->fscache);
 
-	if (ret < 0) {
+	if (ret < 0 && ret != -ETIMEDOUT) {
-		printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n",
+		if (ret != -ENOBUFS)
-		       ret);
+			printk(KERN_WARNING
+			       "CacheFiles: Lookup failed error %d\n", ret);
 		fscache_object_lookup_error(&object->fscache);
 	}
 
 	_leave(" [%d]", ret);
+	return ret;
 }
 
 /*
@@ -331,6 +334,7 @@ static void cachefiles_put_object(struct fscache_object *_object)
 		}
 
 		cache = object->fscache.cache;
+		fscache_object_destroy(&object->fscache);
 		kmem_cache_free(cachefiles_object_jar, object);
 		fscache_object_destroyed(cache);
 	}
@@ -403,12 +407,26 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 	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);
+
+	/* if there's an extension to a partial page at the end of the backing
+	 * file, we need to discard the partial page so that we pick up new
+	 * data after it */
+	if (oi_size & ~PAGE_MASK && ni_size > oi_size) {
+		_debug("discard tail %llx", oi_size);
+		newattrs.ia_valid = ATTR_SIZE;
+		newattrs.ia_size = oi_size & PAGE_MASK;
+		ret = notify_change(object->backer, &newattrs);
+		if (ret < 0)
+			goto truncate_failed;
+	}
+
+	newattrs.ia_valid = ATTR_SIZE;
+	newattrs.ia_size = ni_size;
 	ret = notify_change(object->backer, &newattrs);
+
+truncate_failed:
 	mutex_unlock(&object->backer->d_inode->i_mutex);
 	cachefiles_end_secure(cache, saved_cred);
 

fs/cachefiles/namei.c

@@ -21,17 +21,81 @@
 #include <linux/security.h>
 #include "internal.h"
 
-static int cachefiles_wait_bit(void *flags)
+#define CACHEFILES_KEYBUF_SIZE 512
+
+/*
+ * dump debugging info about an object
+ */
+static noinline
+void __cachefiles_printk_object(struct cachefiles_object *object,
+				const char *prefix,
+				u8 *keybuf)
 {
-	schedule();
+	struct fscache_cookie *cookie;
-	return 0;
+	unsigned keylen, loop;
+
+	printk(KERN_ERR "%sobject: OBJ%x\n",
+	       prefix, object->fscache.debug_id);
+	printk(KERN_ERR "%sobjstate=%s fl=%lx swfl=%lx ev=%lx[%lx]\n",
+	       prefix, fscache_object_states[object->fscache.state],
+	       object->fscache.flags, object->fscache.work.flags,
+	       object->fscache.events,
+	       object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK);
+	printk(KERN_ERR "%sops=%u inp=%u exc=%u\n",
+	       prefix, object->fscache.n_ops, object->fscache.n_in_progress,
+	       object->fscache.n_exclusive);
+	printk(KERN_ERR "%sparent=%p\n",
+	       prefix, object->fscache.parent);
+
+	spin_lock(&object->fscache.lock);
+	cookie = object->fscache.cookie;
+	if (cookie) {
+		printk(KERN_ERR "%scookie=%p [pr=%p nd=%p fl=%lx]\n",
+		       prefix,
+		       object->fscache.cookie,
+		       object->fscache.cookie->parent,
+		       object->fscache.cookie->netfs_data,
+		       object->fscache.cookie->flags);
+		if (keybuf)
+			keylen = cookie->def->get_key(cookie->netfs_data, keybuf,
+						      CACHEFILES_KEYBUF_SIZE);
+		else
+			keylen = 0;
+	} else {
+		printk(KERN_ERR "%scookie=NULL\n", prefix);
+		keylen = 0;
+	}
+	spin_unlock(&object->fscache.lock);
+
+	if (keylen) {
+		printk(KERN_ERR "%skey=[%u] '", prefix, keylen);
+		for (loop = 0; loop < keylen; loop++)
+			printk("%02x", keybuf[loop]);
+		printk("'\n");
+	}
+}
+
+/*
+ * dump debugging info about a pair of objects
+ */
+static noinline void cachefiles_printk_object(struct cachefiles_object *object,
+					      struct cachefiles_object *xobject)
+{
+	u8 *keybuf;
+
+	keybuf = kmalloc(CACHEFILES_KEYBUF_SIZE, GFP_NOIO);
+	if (object)
+		__cachefiles_printk_object(object, "", keybuf);
+	if (xobject)
+		__cachefiles_printk_object(xobject, "x", keybuf);
+	kfree(keybuf);
 }
 
 /*
  * record the fact that an object is now active
  */
-static void cachefiles_mark_object_active(struct cachefiles_cache *cache,
+static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
-					  struct cachefiles_object *object)
+					 struct cachefiles_object *object)
 {
 	struct cachefiles_object *xobject;
 	struct rb_node **_p, *_parent = NULL;
@@ -42,8 +106,11 @@ static void cachefiles_mark_object_active(struct cachefiles_cache *cache,
 try_again:
 	write_lock(&cache->active_lock);
 
-	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
+		printk(KERN_ERR "CacheFiles: Error: Object already active\n");
+		cachefiles_printk_object(object, NULL);
 		BUG();
+	}
 
 	dentry = object->dentry;
 	_p = &cache->active_nodes.rb_node;
@@ -66,8 +133,8 @@ try_again:
 	rb_insert_color(&object->active_node, &cache->active_nodes);
 
 	write_unlock(&cache->active_lock);
-	_leave("");
+	_leave(" = 0");
-	return;
+	return 0;
 
 	/* an old object from a previous incarnation is hogging the slot - we
 	 * need to wait for it to be destroyed */
@@ -76,44 +143,70 @@ wait_for_old_object:
 		printk(KERN_ERR "\n");
 		printk(KERN_ERR "CacheFiles: Error:"
 		       " Unexpected object collision\n");
-		printk(KERN_ERR "xobject: OBJ%x\n",
+		cachefiles_printk_object(object, xobject);
-		       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");
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
-	wait_on_bit(&xobject->flags, CACHEFILES_OBJECT_ACTIVE,
+		wait_queue_head_t *wq;
-		    cachefiles_wait_bit, TASK_UNINTERRUPTIBLE);
+
-	_debug("<<< waited");
+		signed long timeout = 60 * HZ;
+		wait_queue_t wait;
+		bool requeue;
+
+		/* if the object we're waiting for is queued for processing,
+		 * then just put ourselves on the queue behind it */
+		if (slow_work_is_queued(&xobject->fscache.work)) {
+			_debug("queue OBJ%x behind OBJ%x immediately",
+			       object->fscache.debug_id,
+			       xobject->fscache.debug_id);
+			goto requeue;
+		}
+
+		/* otherwise we sleep until either the object we're waiting for
+		 * is done, or the slow-work facility wants the thread back to
+		 * do other work */
+		wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE);
+		init_wait(&wait);
+		requeue = false;
+		do {
+			prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+			if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags))
+				break;
+			requeue = slow_work_sleep_till_thread_needed(
+				&object->fscache.work, &timeout);
+		} while (timeout > 0 && !requeue);
+		finish_wait(wq, &wait);
+
+		if (requeue &&
+		    test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
+			_debug("queue OBJ%x behind OBJ%x after wait",
+			       object->fscache.debug_id,
+			       xobject->fscache.debug_id);
+			goto requeue;
+		}
+
+		if (timeout <= 0) {
+			printk(KERN_ERR "\n");
+			printk(KERN_ERR "CacheFiles: Error: Overlong"
+			       " wait for old active object to go away\n");
+			cachefiles_printk_object(object, xobject);
+			goto requeue;
+		}
+	}
+
+	ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags));
 
 	cache->cache.ops->put_object(&xobject->fscache);
 	goto try_again;
+
+requeue:
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	cache->cache.ops->put_object(&xobject->fscache);
+	_leave(" = -ETIMEDOUT");
+	return -ETIMEDOUT;
 }
 
 /*
@@ -254,7 +347,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
 
 	dir = dget_parent(object->dentry);
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
 	ret = cachefiles_bury_object(cache, dir, object->dentry);
 
 	dput(dir);
@@ -307,7 +400,7 @@ lookup_again:
 	/* search the current directory for the element name */
 	_debug("lookup '%s'", name);
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
 
 	start = jiffies;
 	next = lookup_one_len(name, dir, nlen);
@@ -418,12 +511,15 @@ lookup_again:
 	}
 
 	/* note that we're now using this object */
-	cachefiles_mark_object_active(cache, object);
+	ret = cachefiles_mark_object_active(cache, object);
 
 	mutex_unlock(&dir->d_inode->i_mutex);
 	dput(dir);
 	dir = NULL;
 
+	if (ret == -ETIMEDOUT)
+		goto mark_active_timed_out;
+
 	_debug("=== OBTAINED_OBJECT ===");
 
 	if (object->new) {
@@ -467,6 +563,10 @@ create_error:
 		cachefiles_io_error(cache, "Create/mkdir failed");
 	goto error;
 
+mark_active_timed_out:
+	_debug("mark active timed out");
+	goto release_dentry;
+
 check_error:
 	_debug("check error %d", ret);
 	write_lock(&cache->active_lock);
@@ -474,7 +574,7 @@ check_error:
 	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
 	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
 	write_unlock(&cache->active_lock);
-
+release_dentry:
 	dput(object->dentry);
 	object->dentry = NULL;
 	goto error_out;
@@ -495,9 +595,6 @@ error:
 error_out2:
 	dput(dir);
 error_out:
-	if (ret == -ENOSPC)
-		ret = -ENOBUFS;
-
 	_leave(" = error %d", -ret);
 	return ret;
 }

fs/cachefiles/rdwr.c

@@ -40,8 +40,10 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
 
 	_debug("--- monitor %p %lx ---", page, page->flags);
 
-	if (!PageUptodate(page) && !PageError(page))
+	if (!PageUptodate(page) && !PageError(page)) {
-		dump_stack();
+		/* unlocked, not uptodate and not erronous? */
+		_debug("page probably truncated");
+	}
 
 	/* remove from the waitqueue */
 	list_del(&wait->task_list);
@@ -60,6 +62,84 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
 	return 0;
 }
 
+/*
+ * handle a probably truncated page
+ * - check to see if the page is still relevant and reissue the read if
+ *   possible
+ * - return -EIO on error, -ENODATA if the page is gone, -EINPROGRESS if we
+ *   must wait again and 0 if successful
+ */
+static int cachefiles_read_reissue(struct cachefiles_object *object,
+				   struct cachefiles_one_read *monitor)
+{
+	struct address_space *bmapping = object->backer->d_inode->i_mapping;
+	struct page *backpage = monitor->back_page, *backpage2;
+	int ret;
+
+	kenter("{ino=%lx},{%lx,%lx}",
+	       object->backer->d_inode->i_ino,
+	       backpage->index, backpage->flags);
+
+	/* skip if the page was truncated away completely */
+	if (backpage->mapping != bmapping) {
+		kleave(" = -ENODATA [mapping]");
+		return -ENODATA;
+	}
+
+	backpage2 = find_get_page(bmapping, backpage->index);
+	if (!backpage2) {
+		kleave(" = -ENODATA [gone]");
+		return -ENODATA;
+	}
+
+	if (backpage != backpage2) {
+		put_page(backpage2);
+		kleave(" = -ENODATA [different]");
+		return -ENODATA;
+	}
+
+	/* the page is still there and we already have a ref on it, so we don't
+	 * need a second */
+	put_page(backpage2);
+
+	INIT_LIST_HEAD(&monitor->op_link);
+	add_page_wait_queue(backpage, &monitor->monitor);
+
+	if (trylock_page(backpage)) {
+		ret = -EIO;
+		if (PageError(backpage))
+			goto unlock_discard;
+		ret = 0;
+		if (PageUptodate(backpage))
+			goto unlock_discard;
+
+		kdebug("reissue read");
+		ret = bmapping->a_ops->readpage(NULL, backpage);
+		if (ret < 0)
+			goto unlock_discard;
+	}
+
+	/* 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);
+	}
+
+	/* it'll reappear on the todo list */
+	kleave(" = -EINPROGRESS");
+	return -EINPROGRESS;
+
+unlock_discard:
+	unlock_page(backpage);
+	spin_lock_irq(&object->work_lock);
+	list_del(&monitor->op_link);
+	spin_unlock_irq(&object->work_lock);
+	kleave(" = %d", ret);
+	return ret;
+}
+
 /*
  * copy data from backing pages to netfs pages to complete a read operation
  * - driven by FS-Cache's thread pool
@@ -92,20 +172,26 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 
 		_debug("- copy {%lu}", monitor->back_page->index);
 
-		error = -EIO;
+	recheck:
 		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;
-		}
+		} else if (!PageError(monitor->back_page)) {
-
+			/* the page has probably been truncated */
-		if (error)
+			error = cachefiles_read_reissue(object, monitor);
+			if (error == -EINPROGRESS)
+				goto next;
+			goto recheck;
+		} else {
 			cachefiles_io_error_obj(
 				object,
 				"Readpage failed on backing file %lx",
 				(unsigned long) monitor->back_page->flags);
+			error = -EIO;
+		}
 
 		page_cache_release(monitor->back_page);
 
@@ -114,6 +200,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 		fscache_put_retrieval(op);
 		kfree(monitor);
 
+	next:
 		/* let the thread pool have some air occasionally */
 		max--;
 		if (max < 0 || need_resched()) {
@@ -333,7 +420,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
-	op->op.flags = FSCACHE_OP_FAST;
+	op->op.flags &= FSCACHE_OP_KEEP_FLAGS;
+	op->op.flags |= FSCACHE_OP_FAST;
 	op->op.processor = cachefiles_read_copier;
 
 	pagevec_init(&pagevec, 0);
@@ -639,7 +727,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 
 	pagevec_init(&pagevec, 0);
 
-	op->op.flags = FSCACHE_OP_FAST;
+	op->op.flags &= FSCACHE_OP_KEEP_FLAGS;
+	op->op.flags |= FSCACHE_OP_FAST;
 	op->op.processor = cachefiles_read_copier;
 
 	INIT_LIST_HEAD(&backpages);
@@ -801,7 +890,8 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	struct cachefiles_cache *cache;
 	mm_segment_t old_fs;
 	struct file *file;
-	loff_t pos;
+	loff_t pos, eof;
+	size_t len;
 	void *data;
 	int ret;
 
@@ -835,15 +925,29 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 		ret = -EIO;
 		if (file->f_op->write) {
 			pos = (loff_t) page->index << PAGE_SHIFT;
+
+			/* we mustn't write more data than we have, so we have
+			 * to beware of a partial page at EOF */
+			eof = object->fscache.store_limit_l;
+			len = PAGE_SIZE;
+			if (eof & ~PAGE_MASK) {
+				ASSERTCMP(pos, <, eof);
+				if (eof - pos < PAGE_SIZE) {
+					_debug("cut short %llx to %llx",
+					       pos, eof);
+					len = eof - pos;
+					ASSERTCMP(pos + len, ==, eof);
+				}
+			}
+
 			data = kmap(page);
 			old_fs = get_fs();
 			set_fs(KERNEL_DS);
 			ret = file->f_op->write(
-				file, (const void __user *) data, PAGE_SIZE,
+				file, (const void __user *) data, len, &pos);
-				&pos);
 			set_fs(old_fs);
 			kunmap(page);
-			if (ret != PAGE_SIZE)
+			if (ret != len)
 				ret = -EIO;
 		}
 		fput(file);

fs/cifs/cifsfs.c

@@ -1037,7 +1037,7 @@ init_cifs(void)
 	if (rc)
 		goto out_unregister_key_type;
 #endif
-	rc = slow_work_register_user();
+	rc = slow_work_register_user(THIS_MODULE);
 	if (rc)
 		goto out_unregister_resolver_key;
 

fs/fscache/Kconfig

@@ -54,3 +54,10 @@ config FSCACHE_DEBUG
 	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
 
 	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_OBJECT_LIST
+	bool "Maintain global object list for debugging purposes"
+	depends on FSCACHE && PROC_FS
+	help
+	  Maintain a global list of active fscache objects that can be
+	  retrieved through /proc/fs/fscache/objects for debugging purposes

fs/fscache/Makefile

@@ -15,5 +15,6 @@ fscache-y := \
 fscache-$(CONFIG_PROC_FS) += proc.o
 fscache-$(CONFIG_FSCACHE_STATS) += stats.o
 fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o
+fscache-$(CONFIG_FSCACHE_OBJECT_LIST) += object-list.o
 
 obj-$(CONFIG_FSCACHE) := fscache.o

fs/fscache/cache.c

@@ -263,6 +263,7 @@ int fscache_add_cache(struct fscache_cache *cache,
 	spin_lock(&cache->object_list_lock);
 	list_add_tail(&ifsdef->cache_link, &cache->object_list);
 	spin_unlock(&cache->object_list_lock);
+	fscache_objlist_add(ifsdef);
 
 	/* add the cache's netfs definition index object to the top level index
 	 * cookie as a known backing object */
@@ -380,11 +381,15 @@ void fscache_withdraw_cache(struct fscache_cache *cache)
 
 	/* make sure all pages pinned by operations on behalf of the netfs are
 	 * written to disk */
+	fscache_stat(&fscache_n_cop_sync_cache);
 	cache->ops->sync_cache(cache);
+	fscache_stat_d(&fscache_n_cop_sync_cache);
 
 	/* dissociate all the netfs pages backed by this cache from the block
 	 * mappings in the cache */
+	fscache_stat(&fscache_n_cop_dissociate_pages);
 	cache->ops->dissociate_pages(cache);
+	fscache_stat_d(&fscache_n_cop_dissociate_pages);
 
 	/* we now have to destroy all the active objects pertaining to this
 	 * cache - which we do by passing them off to thread pool to be

fs/fscache/cookie.c

@@ -36,6 +36,7 @@ void fscache_cookie_init_once(void *_cookie)
 
 	memset(cookie, 0, sizeof(*cookie));
 	spin_lock_init(&cookie->lock);
+	spin_lock_init(&cookie->stores_lock);
 	INIT_HLIST_HEAD(&cookie->backing_objects);
 }
 
@@ -102,7 +103,9 @@ struct fscache_cookie *__fscache_acquire_cookie(
 	cookie->netfs_data	= netfs_data;
 	cookie->flags		= 0;
 
-	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS);
+	/* radix tree insertion won't use the preallocation pool unless it's
+	 * told it may not wait */
+	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT);
 
 	switch (cookie->def->type) {
 	case FSCACHE_COOKIE_TYPE_INDEX:
@@ -249,7 +252,9 @@ static int fscache_alloc_object(struct fscache_cache *cache,
 
 	/* ask the cache to allocate an object (we may end up with duplicate
 	 * objects at this stage, but we sort that out later) */
+	fscache_stat(&fscache_n_cop_alloc_object);
 	object = cache->ops->alloc_object(cache, cookie);
+	fscache_stat_d(&fscache_n_cop_alloc_object);
 	if (IS_ERR(object)) {
 		fscache_stat(&fscache_n_object_no_alloc);
 		ret = PTR_ERR(object);
@@ -270,8 +275,11 @@ static int fscache_alloc_object(struct fscache_cache *cache,
 	/* 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)
+	if (fscache_attach_object(cookie, object) < 0) {
+		fscache_stat(&fscache_n_cop_put_object);
 		cache->ops->put_object(object);
+		fscache_stat_d(&fscache_n_cop_put_object);
+	}
 
 	_leave(" = 0");
 	return 0;
@@ -287,7 +295,9 @@ object_already_extant:
 	return 0;
 
 error_put:
+	fscache_stat(&fscache_n_cop_put_object);
 	cache->ops->put_object(object);
+	fscache_stat_d(&fscache_n_cop_put_object);
 error:
 	_leave(" = %d", ret);
 	return ret;
@@ -349,6 +359,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
 	object->cookie = cookie;
 	atomic_inc(&cookie->usage);
 	hlist_add_head(&object->cookie_link, &cookie->backing_objects);
+
+	fscache_objlist_add(object);
 	ret = 0;
 
 cant_attach_object:
@@ -403,6 +415,8 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 	unsigned long event;
 
 	fscache_stat(&fscache_n_relinquishes);
+	if (retire)
+		fscache_stat(&fscache_n_relinquishes_retire);
 
 	if (!cookie) {
 		fscache_stat(&fscache_n_relinquishes_null);
@@ -428,12 +442,8 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 
 	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,
@@ -456,6 +466,10 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 			BUG();
 	}
 
+	/* detach pointers back to the netfs */
+	cookie->netfs_data	= NULL;
+	cookie->def		= NULL;
+
 	spin_unlock(&cookie->lock);
 
 	if (cookie->parent) {

fs/fscache/internal.h

@@ -17,6 +17,7 @@
  * - cache->object_list_lock
  * - object->lock
  * - object->parent->lock
+ * - cookie->stores_lock
  * - fscache_thread_lock
  *
  */
@@ -88,10 +89,23 @@ extern int fscache_wait_bit_interruptible(void *);
 /*
  * object.c
  */
+extern const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5];
+
 extern void fscache_withdrawing_object(struct fscache_cache *,
 				       struct fscache_object *);
 extern void fscache_enqueue_object(struct fscache_object *);
 
+/*
+ * object-list.c
+ */
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+extern const struct file_operations fscache_objlist_fops;
+
+extern void fscache_objlist_add(struct fscache_object *);
+#else
+#define fscache_objlist_add(object) do {} while(0)
+#endif
+
 /*
  * operation.c
  */
@@ -99,6 +113,7 @@ extern int fscache_submit_exclusive_op(struct fscache_object *,
 				       struct fscache_operation *);
 extern int fscache_submit_op(struct fscache_object *,
 			     struct fscache_operation *);
+extern int fscache_cancel_op(struct fscache_operation *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
 extern void fscache_operation_gc(struct work_struct *);
@@ -127,6 +142,8 @@ extern atomic_t fscache_n_op_enqueue;
 extern atomic_t fscache_n_op_deferred_release;
 extern atomic_t fscache_n_op_release;
 extern atomic_t fscache_n_op_gc;
+extern atomic_t fscache_n_op_cancelled;
+extern atomic_t fscache_n_op_rejected;
 
 extern atomic_t fscache_n_attr_changed;
 extern atomic_t fscache_n_attr_changed_ok;
@@ -138,6 +155,8 @@ extern atomic_t fscache_n_allocs;
 extern atomic_t fscache_n_allocs_ok;
 extern atomic_t fscache_n_allocs_wait;
 extern atomic_t fscache_n_allocs_nobufs;
+extern atomic_t fscache_n_allocs_intr;
+extern atomic_t fscache_n_allocs_object_dead;
 extern atomic_t fscache_n_alloc_ops;
 extern atomic_t fscache_n_alloc_op_waits;
 
@@ -148,6 +167,7 @@ extern atomic_t fscache_n_retrievals_nodata;
 extern atomic_t fscache_n_retrievals_nobufs;
 extern atomic_t fscache_n_retrievals_intr;
 extern atomic_t fscache_n_retrievals_nomem;
+extern atomic_t fscache_n_retrievals_object_dead;
 extern atomic_t fscache_n_retrieval_ops;
 extern atomic_t fscache_n_retrieval_op_waits;
 
@@ -158,6 +178,14 @@ extern atomic_t fscache_n_stores_nobufs;
 extern atomic_t fscache_n_stores_oom;
 extern atomic_t fscache_n_store_ops;
 extern atomic_t fscache_n_store_calls;
+extern atomic_t fscache_n_store_pages;
+extern atomic_t fscache_n_store_radix_deletes;
+extern atomic_t fscache_n_store_pages_over_limit;
+
+extern atomic_t fscache_n_store_vmscan_not_storing;
+extern atomic_t fscache_n_store_vmscan_gone;
+extern atomic_t fscache_n_store_vmscan_busy;
+extern atomic_t fscache_n_store_vmscan_cancelled;
 
 extern atomic_t fscache_n_marks;
 extern atomic_t fscache_n_uncaches;
@@ -176,6 +204,7 @@ extern atomic_t fscache_n_updates_run;
 extern atomic_t fscache_n_relinquishes;
 extern atomic_t fscache_n_relinquishes_null;
 extern atomic_t fscache_n_relinquishes_waitcrt;
+extern atomic_t fscache_n_relinquishes_retire;
 
 extern atomic_t fscache_n_cookie_index;
 extern atomic_t fscache_n_cookie_data;
@@ -186,6 +215,7 @@ extern atomic_t fscache_n_object_no_alloc;
 extern atomic_t fscache_n_object_lookups;
 extern atomic_t fscache_n_object_lookups_negative;
 extern atomic_t fscache_n_object_lookups_positive;
+extern atomic_t fscache_n_object_lookups_timed_out;
 extern atomic_t fscache_n_object_created;
 extern atomic_t fscache_n_object_avail;
 extern atomic_t fscache_n_object_dead;
@@ -195,15 +225,41 @@ extern atomic_t fscache_n_checkaux_okay;
 extern atomic_t fscache_n_checkaux_update;
 extern atomic_t fscache_n_checkaux_obsolete;
 
+extern atomic_t fscache_n_cop_alloc_object;
+extern atomic_t fscache_n_cop_lookup_object;
+extern atomic_t fscache_n_cop_lookup_complete;
+extern atomic_t fscache_n_cop_grab_object;
+extern atomic_t fscache_n_cop_update_object;
+extern atomic_t fscache_n_cop_drop_object;
+extern atomic_t fscache_n_cop_put_object;
+extern atomic_t fscache_n_cop_sync_cache;
+extern atomic_t fscache_n_cop_attr_changed;
+extern atomic_t fscache_n_cop_read_or_alloc_page;
+extern atomic_t fscache_n_cop_read_or_alloc_pages;
+extern atomic_t fscache_n_cop_allocate_page;
+extern atomic_t fscache_n_cop_allocate_pages;
+extern atomic_t fscache_n_cop_write_page;
+extern atomic_t fscache_n_cop_uncache_page;
+extern atomic_t fscache_n_cop_dissociate_pages;
+
 static inline void fscache_stat(atomic_t *stat)
 {
 	atomic_inc(stat);
 }
 
+static inline void fscache_stat_d(atomic_t *stat)
+{
+	atomic_dec(stat);
+}
+
+#define __fscache_stat(stat) (stat)
+
 extern const struct file_operations fscache_stats_fops;
 #else
 
+#define __fscache_stat(stat) (NULL)
 #define fscache_stat(stat) do {} while (0)
+#define fscache_stat_d(stat) do {} while (0)
 #endif
 
 /*

fs/fscache/main.c

@@ -48,7 +48,7 @@ static int __init fscache_init(void)
 {
 	int ret;
 
-	ret = slow_work_register_user();
+	ret = slow_work_register_user(THIS_MODULE);
 	if (ret < 0)
 		goto error_slow_work;
 
@@ -80,7 +80,7 @@ error_kobj:
 error_cookie_jar:
 	fscache_proc_cleanup();
 error_proc:
-	slow_work_unregister_user();
+	slow_work_unregister_user(THIS_MODULE);
 error_slow_work:
 	return ret;
 }
@@ -97,7 +97,7 @@ static void __exit fscache_exit(void)
 	kobject_put(fscache_root);
 	kmem_cache_destroy(fscache_cookie_jar);
 	fscache_proc_cleanup();
-	slow_work_unregister_user();
+	slow_work_unregister_user(THIS_MODULE);
 	printk(KERN_NOTICE "FS-Cache: Unloaded\n");
 }
 

fs/fscache/object-list.c

@@ -0,0 +1,432 @@
+/* Global fscache object list maintainer and viewer
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/key.h>
+#include <keys/user-type.h>
+#include "internal.h"
+
+static struct rb_root fscache_object_list;
+static DEFINE_RWLOCK(fscache_object_list_lock);
+
+struct fscache_objlist_data {
+	unsigned long	config;		/* display configuration */
+#define FSCACHE_OBJLIST_CONFIG_KEY	0x00000001	/* show object keys */
+#define FSCACHE_OBJLIST_CONFIG_AUX	0x00000002	/* show object auxdata */
+#define FSCACHE_OBJLIST_CONFIG_COOKIE	0x00000004	/* show objects with cookies */
+#define FSCACHE_OBJLIST_CONFIG_NOCOOKIE	0x00000008	/* show objects without cookies */
+#define FSCACHE_OBJLIST_CONFIG_BUSY	0x00000010	/* show busy objects */
+#define FSCACHE_OBJLIST_CONFIG_IDLE	0x00000020	/* show idle objects */
+#define FSCACHE_OBJLIST_CONFIG_PENDWR	0x00000040	/* show objects with pending writes */
+#define FSCACHE_OBJLIST_CONFIG_NOPENDWR	0x00000080	/* show objects without pending writes */
+#define FSCACHE_OBJLIST_CONFIG_READS	0x00000100	/* show objects with active reads */
+#define FSCACHE_OBJLIST_CONFIG_NOREADS	0x00000200	/* show objects without active reads */
+#define FSCACHE_OBJLIST_CONFIG_EVENTS	0x00000400	/* show objects with events */
+#define FSCACHE_OBJLIST_CONFIG_NOEVENTS	0x00000800	/* show objects without no events */
+#define FSCACHE_OBJLIST_CONFIG_WORK	0x00001000	/* show objects with slow work */
+#define FSCACHE_OBJLIST_CONFIG_NOWORK	0x00002000	/* show objects without slow work */
+
+	u8		buf[512];	/* key and aux data buffer */
+};
+
+/*
+ * Add an object to the object list
+ * - we use the address of the fscache_object structure as the key into the
+ *   tree
+ */
+void fscache_objlist_add(struct fscache_object *obj)
+{
+	struct fscache_object *xobj;
+	struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL;
+
+	write_lock(&fscache_object_list_lock);
+
+	while (*p) {
+		parent = *p;
+		xobj = rb_entry(parent, struct fscache_object, objlist_link);
+
+		if (obj < xobj)
+			p = &(*p)->rb_left;
+		else if (obj > xobj)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&obj->objlist_link, parent, p);
+	rb_insert_color(&obj->objlist_link, &fscache_object_list);
+
+	write_unlock(&fscache_object_list_lock);
+}
+
+/**
+ * fscache_object_destroy - Note that a cache object is about to be destroyed
+ * @object: The object to be destroyed
+ *
+ * Note the imminent destruction and deallocation of a cache object record.
+ */
+void fscache_object_destroy(struct fscache_object *obj)
+{
+	write_lock(&fscache_object_list_lock);
+
+	BUG_ON(RB_EMPTY_ROOT(&fscache_object_list));
+	rb_erase(&obj->objlist_link, &fscache_object_list);
+
+	write_unlock(&fscache_object_list_lock);
+}
+EXPORT_SYMBOL(fscache_object_destroy);
+
+/*
+ * find the object in the tree on or after the specified index
+ */
+static struct fscache_object *fscache_objlist_lookup(loff_t *_pos)
+{
+	struct fscache_object *pobj, *obj, *minobj = NULL;
+	struct rb_node *p;
+	unsigned long pos;
+
+	if (*_pos >= (unsigned long) ERR_PTR(-ENOENT))
+		return NULL;
+	pos = *_pos;
+
+	/* banners (can't represent line 0 by pos 0 as that would involve
+	 * returning a NULL pointer) */
+	if (pos == 0)
+		return (struct fscache_object *) ++(*_pos);
+	if (pos < 3)
+		return (struct fscache_object *)pos;
+
+	pobj = (struct fscache_object *)pos;
+	p = fscache_object_list.rb_node;
+	while (p) {
+		obj = rb_entry(p, struct fscache_object, objlist_link);
+		if (pobj < obj) {
+			if (!minobj || minobj > obj)
+				minobj = obj;
+			p = p->rb_left;
+		} else if (pobj > obj) {
+			p = p->rb_right;
+		} else {
+			minobj = obj;
+			break;
+		}
+		obj = NULL;
+	}
+
+	if (!minobj)
+		*_pos = (unsigned long) ERR_PTR(-ENOENT);
+	else if (minobj != obj)
+		*_pos = (unsigned long) minobj;
+	return minobj;
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *fscache_objlist_start(struct seq_file *m, loff_t *_pos)
+	__acquires(&fscache_object_list_lock)
+{
+	read_lock(&fscache_object_list_lock);
+	return fscache_objlist_lookup(_pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *fscache_objlist_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	(*_pos)++;
+	return fscache_objlist_lookup(_pos);
+}
+
+/*
+ * clean up after reading
+ */
+static void fscache_objlist_stop(struct seq_file *m, void *v)
+	__releases(&fscache_object_list_lock)
+{
+	read_unlock(&fscache_object_list_lock);
+}
+
+/*
+ * display an object
+ */
+static int fscache_objlist_show(struct seq_file *m, void *v)
+{
+	struct fscache_objlist_data *data = m->private;
+	struct fscache_object *obj = v;
+	unsigned long config = data->config;
+	uint16_t keylen, auxlen;
+	char _type[3], *type;
+	bool no_cookie;
+	u8 *buf = data->buf, *p;
+
+	if ((unsigned long) v == 1) {
+		seq_puts(m, "OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS"
+			 " EM EV F S"
+			 " | NETFS_COOKIE_DEF TY FL NETFS_DATA");
+		if (config & (FSCACHE_OBJLIST_CONFIG_KEY |
+			      FSCACHE_OBJLIST_CONFIG_AUX))
+			seq_puts(m, "       ");
+		if (config & FSCACHE_OBJLIST_CONFIG_KEY)
+			seq_puts(m, "OBJECT_KEY");
+		if ((config & (FSCACHE_OBJLIST_CONFIG_KEY |
+			       FSCACHE_OBJLIST_CONFIG_AUX)) ==
+		    (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX))
+			seq_puts(m, ", ");
+		if (config & FSCACHE_OBJLIST_CONFIG_AUX)
+			seq_puts(m, "AUX_DATA");
+		seq_puts(m, "\n");
+		return 0;
+	}
+
+	if ((unsigned long) v == 2) {
+		seq_puts(m, "======== ======== ==== ===== === === === == ====="
+			 " == == = ="
+			 " | ================ == == ================");
+		if (config & (FSCACHE_OBJLIST_CONFIG_KEY |
+			      FSCACHE_OBJLIST_CONFIG_AUX))
+			seq_puts(m, " ================");
+		seq_puts(m, "\n");
+		return 0;
+	}
+
+	/* filter out any unwanted objects */
+#define FILTER(criterion, _yes, _no)					\
+	do {								\
+		unsigned long yes = FSCACHE_OBJLIST_CONFIG_##_yes;	\
+		unsigned long no = FSCACHE_OBJLIST_CONFIG_##_no;	\
+		if (criterion) {					\
+			if (!(config & yes))				\
+				return 0;				\
+		} else {						\
+			if (!(config & no))				\
+				return 0;				\
+		}							\
+	} while(0)
+
+	if (~config) {
+		FILTER(obj->cookie,
+		       COOKIE, NOCOOKIE);
+		FILTER(obj->state != FSCACHE_OBJECT_ACTIVE ||
+		       obj->n_ops != 0 ||
+		       obj->n_obj_ops != 0 ||
+		       obj->flags ||
+		       !list_empty(&obj->dependents),
+		       BUSY, IDLE);
+		FILTER(test_bit(FSCACHE_OBJECT_PENDING_WRITE, &obj->flags),
+		       PENDWR, NOPENDWR);
+		FILTER(atomic_read(&obj->n_reads),
+		       READS, NOREADS);
+		FILTER(obj->events & obj->event_mask,
+		       EVENTS, NOEVENTS);
+		FILTER(obj->work.flags & ~(1UL << SLOW_WORK_VERY_SLOW),
+		       WORK, NOWORK);
+	}
+
+	seq_printf(m,
+		   "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1lx | ",
+		   obj->debug_id,
+		   obj->parent ? obj->parent->debug_id : -1,
+		   fscache_object_states_short[obj->state],
+		   obj->n_children,
+		   obj->n_ops,
+		   obj->n_obj_ops,
+		   obj->n_in_progress,
+		   obj->n_exclusive,
+		   atomic_read(&obj->n_reads),
+		   obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK,
+		   obj->events,
+		   obj->flags,
+		   obj->work.flags);
+
+	no_cookie = true;
+	keylen = auxlen = 0;
+	if (obj->cookie) {
+		spin_lock(&obj->lock);
+		if (obj->cookie) {
+			switch (obj->cookie->def->type) {
+			case 0:
+				type = "IX";
+				break;
+			case 1:
+				type = "DT";
+				break;
+			default:
+				sprintf(_type, "%02u",
+					obj->cookie->def->type);
+				type = _type;
+				break;
+			}
+
+			seq_printf(m, "%-16s %s %2lx %16p",
+				   obj->cookie->def->name,
+				   type,
+				   obj->cookie->flags,
+				   obj->cookie->netfs_data);
+
+			if (obj->cookie->def->get_key &&
+			    config & FSCACHE_OBJLIST_CONFIG_KEY)
+				keylen = obj->cookie->def->get_key(
+					obj->cookie->netfs_data,
+					buf, 400);
+
+			if (obj->cookie->def->get_aux &&
+			    config & FSCACHE_OBJLIST_CONFIG_AUX)
+				auxlen = obj->cookie->def->get_aux(
+					obj->cookie->netfs_data,
+					buf + keylen, 512 - keylen);
+
+			no_cookie = false;
+		}
+		spin_unlock(&obj->lock);
+
+		if (!no_cookie && (keylen > 0 || auxlen > 0)) {
+			seq_printf(m, " ");
+			for (p = buf; keylen > 0; keylen--)
+				seq_printf(m, "%02x", *p++);
+			if (auxlen > 0) {
+				if (config & FSCACHE_OBJLIST_CONFIG_KEY)
+					seq_printf(m, ", ");
+				for (; auxlen > 0; auxlen--)
+					seq_printf(m, "%02x", *p++);
+			}
+		}
+	}
+
+	if (no_cookie)
+		seq_printf(m, "<no_cookie>\n");
+	else
+		seq_printf(m, "\n");
+	return 0;
+}
+
+static const struct seq_operations fscache_objlist_ops = {
+	.start		= fscache_objlist_start,
+	.stop		= fscache_objlist_stop,
+	.next		= fscache_objlist_next,
+	.show		= fscache_objlist_show,
+};
+
+/*
+ * get the configuration for filtering the list
+ */
+static void fscache_objlist_config(struct fscache_objlist_data *data)
+{
+#ifdef CONFIG_KEYS
+	struct user_key_payload *confkey;
+	unsigned long config;
+	struct key *key;
+	const char *buf;
+	int len;
+
+	key = request_key(&key_type_user, "fscache:objlist", NULL);
+	if (IS_ERR(key))
+		goto no_config;
+
+	config = 0;
+	rcu_read_lock();
+
+	confkey = key->payload.data;
+	buf = confkey->data;
+
+	for (len = confkey->datalen - 1; len >= 0; len--) {
+		switch (buf[len]) {
+		case 'K': config |= FSCACHE_OBJLIST_CONFIG_KEY;		break;
+		case 'A': config |= FSCACHE_OBJLIST_CONFIG_AUX;		break;
+		case 'C': config |= FSCACHE_OBJLIST_CONFIG_COOKIE;	break;
+		case 'c': config |= FSCACHE_OBJLIST_CONFIG_NOCOOKIE;	break;
+		case 'B': config |= FSCACHE_OBJLIST_CONFIG_BUSY;	break;
+		case 'b': config |= FSCACHE_OBJLIST_CONFIG_IDLE;	break;
+		case 'W': config |= FSCACHE_OBJLIST_CONFIG_PENDWR;	break;
+		case 'w': config |= FSCACHE_OBJLIST_CONFIG_NOPENDWR;	break;
+		case 'R': config |= FSCACHE_OBJLIST_CONFIG_READS;	break;
+		case 'r': config |= FSCACHE_OBJLIST_CONFIG_NOREADS;	break;
+		case 'S': config |= FSCACHE_OBJLIST_CONFIG_WORK;	break;
+		case 's': config |= FSCACHE_OBJLIST_CONFIG_NOWORK;	break;
+		}
+	}
+
+	rcu_read_unlock();
+	key_put(key);
+
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS;
+	if (!(config & (FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK)))
+	    config   |= FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK;
+
+	data->config = config;
+	return;
+
+no_config:
+#endif
+	data->config = ULONG_MAX;
+}
+
+/*
+ * open "/proc/fs/fscache/objects" to provide a list of active objects
+ * - can be configured by a user-defined key added to the caller's keyrings
+ */
+static int fscache_objlist_open(struct inode *inode, struct file *file)
+{
+	struct fscache_objlist_data *data;
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &fscache_objlist_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+
+	/* buffer for key extraction */
+	data = kmalloc(sizeof(struct fscache_objlist_data), GFP_KERNEL);
+	if (!data) {
+		seq_release(inode, file);
+		return -ENOMEM;
+	}
+
+	/* get the configuration key */
+	fscache_objlist_config(data);
+
+	m->private = data;
+	return 0;
+}
+
+/*
+ * clean up on close
+ */
+static int fscache_objlist_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+
+	kfree(m->private);
+	m->private = NULL;
+	return seq_release(inode, file);
+}
+
+const struct file_operations fscache_objlist_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_objlist_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= fscache_objlist_release,
+};

fs/fscache/object.c

@@ -14,9 +14,10 @@
 
 #define FSCACHE_DEBUG_LEVEL COOKIE
 #include <linux/module.h>
+#include <linux/seq_file.h>
 #include "internal.h"
 
-const char *fscache_object_states[] = {
+const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
 	[FSCACHE_OBJECT_INIT]		= "OBJECT_INIT",
 	[FSCACHE_OBJECT_LOOKING_UP]	= "OBJECT_LOOKING_UP",
 	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
@@ -33,9 +34,28 @@ const char *fscache_object_states[] = {
 };
 EXPORT_SYMBOL(fscache_object_states);
 
+const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = {
+	[FSCACHE_OBJECT_INIT]		= "INIT",
+	[FSCACHE_OBJECT_LOOKING_UP]	= "LOOK",
+	[FSCACHE_OBJECT_CREATING]	= "CRTN",
+	[FSCACHE_OBJECT_AVAILABLE]	= "AVBL",
+	[FSCACHE_OBJECT_ACTIVE]		= "ACTV",
+	[FSCACHE_OBJECT_UPDATING]	= "UPDT",
+	[FSCACHE_OBJECT_DYING]		= "DYNG",
+	[FSCACHE_OBJECT_LC_DYING]	= "LCDY",
+	[FSCACHE_OBJECT_ABORT_INIT]	= "ABTI",
+	[FSCACHE_OBJECT_RELEASING]	= "RELS",
+	[FSCACHE_OBJECT_RECYCLING]	= "RCYC",
+	[FSCACHE_OBJECT_WITHDRAWING]	= "WTHD",
+	[FSCACHE_OBJECT_DEAD]		= "DEAD",
+};
+
 static 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 *);
+#ifdef CONFIG_SLOW_WORK_PROC
+static void fscache_object_slow_work_desc(struct slow_work *, struct seq_file *);
+#endif
 static void fscache_initialise_object(struct fscache_object *);
 static void fscache_lookup_object(struct fscache_object *);
 static void fscache_object_available(struct fscache_object *);
@@ -45,9 +65,13 @@ 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 = {
+	.owner		= THIS_MODULE,
 	.get_ref	= fscache_object_slow_work_get_ref,
 	.put_ref	= fscache_object_slow_work_put_ref,
 	.execute	= fscache_object_slow_work_execute,
+#ifdef CONFIG_SLOW_WORK_PROC
+	.desc		= fscache_object_slow_work_desc,
+#endif
 };
 EXPORT_SYMBOL(fscache_object_slow_work_ops);
 
@@ -81,6 +105,7 @@ static inline void fscache_done_parent_op(struct fscache_object *object)
 static void fscache_object_state_machine(struct fscache_object *object)
 {
 	enum fscache_object_state new_state;
+	struct fscache_cookie *cookie;
 
 	ASSERT(object != NULL);
 
@@ -120,20 +145,31 @@ static void fscache_object_state_machine(struct fscache_object *object)
 	case FSCACHE_OBJECT_UPDATING:
 		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
 		fscache_stat(&fscache_n_updates_run);
+		fscache_stat(&fscache_n_cop_update_object);
 		object->cache->ops->update_object(object);
+		fscache_stat_d(&fscache_n_cop_update_object);
 		goto active_transit;
 
 		/* handle an object dying during lookup or creation */
 	case FSCACHE_OBJECT_LC_DYING:
 		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+		fscache_stat(&fscache_n_cop_lookup_complete);
 		object->cache->ops->lookup_complete(object);
+		fscache_stat_d(&fscache_n_cop_lookup_complete);
 
 		spin_lock(&object->lock);
 		object->state = FSCACHE_OBJECT_DYING;
-		if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+		cookie = object->cookie;
-				       &object->cookie->flags))
+		if (cookie) {
-			wake_up_bit(&object->cookie->flags,
+			if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP,
-				    FSCACHE_COOKIE_CREATING);
+					       &cookie->flags))
+				wake_up_bit(&cookie->flags,
+					    FSCACHE_COOKIE_LOOKING_UP);
+			if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+					       &cookie->flags))
+				wake_up_bit(&cookie->flags,
+					    FSCACHE_COOKIE_CREATING);
+		}
 		spin_unlock(&object->lock);
 
 		fscache_done_parent_op(object);
@@ -165,6 +201,7 @@ static void fscache_object_state_machine(struct fscache_object *object)
 		}
 		spin_unlock(&object->lock);
 		fscache_enqueue_dependents(object);
+		fscache_start_operations(object);
 		goto terminal_transit;
 
 		/* handle an abort during initialisation */
@@ -316,15 +353,30 @@ static void fscache_object_slow_work_execute(struct slow_work *work)
 
 	_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);
+	clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
 }
 
+/*
+ * describe an object for slow-work debugging
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+static void fscache_object_slow_work_desc(struct slow_work *work,
+					  struct seq_file *m)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+
+	seq_printf(m, "FSC: OBJ%x: %s",
+		   object->debug_id,
+		   fscache_object_states_short[object->state]);
+}
+#endif
+
 /*
  * initialise an object
  * - check the specified object's parent to see if we can make use of it
@@ -376,7 +428,9 @@ static void fscache_initialise_object(struct fscache_object *object)
 			 * binding on to us, so we need to make sure we don't
 			 * add ourself to the list multiple times */
 			if (list_empty(&object->dep_link)) {
+				fscache_stat(&fscache_n_cop_grab_object);
 				object->cache->ops->grab_object(object);
+				fscache_stat_d(&fscache_n_cop_grab_object);
 				list_add(&object->dep_link,
 					 &parent->dependents);
 
@@ -414,6 +468,7 @@ static void fscache_lookup_object(struct fscache_object *object)
 {
 	struct fscache_cookie *cookie = object->cookie;
 	struct fscache_object *parent;
+	int ret;
 
 	_enter("");
 
@@ -438,11 +493,20 @@ static void fscache_lookup_object(struct fscache_object *object)
 	       object->cache->tag->name);
 
 	fscache_stat(&fscache_n_object_lookups);
-	object->cache->ops->lookup_object(object);
+	fscache_stat(&fscache_n_cop_lookup_object);
+	ret = object->cache->ops->lookup_object(object);
+	fscache_stat_d(&fscache_n_cop_lookup_object);
 
 	if (test_bit(FSCACHE_OBJECT_EV_ERROR, &object->events))
 		set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
 
+	if (ret == -ETIMEDOUT) {
+		/* probably stuck behind another object, so move this one to
+		 * the back of the queue */
+		fscache_stat(&fscache_n_object_lookups_timed_out);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	}
+
 	_leave("");
 }
 
@@ -546,7 +610,8 @@ static void fscache_object_available(struct fscache_object *object)
 
 	spin_lock(&object->lock);
 
-	if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags))
+	if (object->cookie &&
+	    test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags))
 		wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING);
 
 	fscache_done_parent_op(object);
@@ -562,7 +627,9 @@ static void fscache_object_available(struct fscache_object *object)
 	}
 	spin_unlock(&object->lock);
 
+	fscache_stat(&fscache_n_cop_lookup_complete);
 	object->cache->ops->lookup_complete(object);
+	fscache_stat_d(&fscache_n_cop_lookup_complete);
 	fscache_enqueue_dependents(object);
 
 	fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif);
@@ -581,11 +648,16 @@ static void fscache_drop_object(struct fscache_object *object)
 
 	_enter("{OBJ%x,%d}", object->debug_id, object->n_children);
 
+	ASSERTCMP(object->cookie, ==, NULL);
+	ASSERT(hlist_unhashed(&object->cookie_link));
+
 	spin_lock(&cache->object_list_lock);
 	list_del_init(&object->cache_link);
 	spin_unlock(&cache->object_list_lock);
 
+	fscache_stat(&fscache_n_cop_drop_object);
 	cache->ops->drop_object(object);
+	fscache_stat_d(&fscache_n_cop_drop_object);
 
 	if (parent) {
 		_debug("release parent OBJ%x {%d}",
@@ -600,7 +672,9 @@ static void fscache_drop_object(struct fscache_object *object)
 	}
 
 	/* this just shifts the object release to the slow work processor */
+	fscache_stat(&fscache_n_cop_put_object);
 	object->cache->ops->put_object(object);
+	fscache_stat_d(&fscache_n_cop_put_object);
 
 	_leave("");
 }
@@ -690,8 +764,12 @@ static int fscache_object_slow_work_get_ref(struct slow_work *work)
 {
 	struct fscache_object *object =
 		container_of(work, struct fscache_object, work);
+	int ret;
 
-	return object->cache->ops->grab_object(object) ? 0 : -EAGAIN;
+	fscache_stat(&fscache_n_cop_grab_object);
+	ret = object->cache->ops->grab_object(object) ? 0 : -EAGAIN;
+	fscache_stat_d(&fscache_n_cop_grab_object);
+	return ret;
 }
 
 /*
@@ -702,7 +780,9 @@ 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);
+	fscache_stat(&fscache_n_cop_put_object);
+	object->cache->ops->put_object(object);
+	fscache_stat_d(&fscache_n_cop_put_object);
 }
 
 /*
@@ -739,7 +819,9 @@ static void fscache_enqueue_dependents(struct fscache_object *object)
 
 		/* sort onto appropriate lists */
 		fscache_enqueue_object(dep);
+		fscache_stat(&fscache_n_cop_put_object);
 		dep->cache->ops->put_object(dep);
+		fscache_stat_d(&fscache_n_cop_put_object);
 
 		if (!list_empty(&object->dependents))
 			cond_resched_lock(&object->lock);

fs/fscache/operation.c

@@ -13,6 +13,7 @@
 
 #define FSCACHE_DEBUG_LEVEL OPERATION
 #include <linux/module.h>
+#include <linux/seq_file.h>
 #include "internal.h"
 
 atomic_t fscache_op_debug_id;
@@ -31,32 +32,33 @@ 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));
 
+	fscache_set_op_state(op, "EnQ");
+
+	ASSERT(list_empty(&op->pend_link));
 	ASSERT(op->processor != NULL);
 	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
-	if (list_empty(&op->pend_link)) {
+	fscache_stat(&fscache_n_op_enqueue);
-		switch (op->flags & FSCACHE_OP_TYPE) {
+	switch (op->flags & FSCACHE_OP_TYPE) {
-		case FSCACHE_OP_FAST:
+	case FSCACHE_OP_FAST:
-			_debug("queue fast");
+		_debug("queue fast");
-			atomic_inc(&op->usage);
+		atomic_inc(&op->usage);
-			if (!schedule_work(&op->fast_work))
+		if (!schedule_work(&op->fast_work))
-				fscache_put_operation(op);
+			fscache_put_operation(op);
-			break;
+		break;
-		case FSCACHE_OP_SLOW:
+	case FSCACHE_OP_SLOW:
-			_debug("queue slow");
+		_debug("queue slow");
-			slow_work_enqueue(&op->slow_work);
+		slow_work_enqueue(&op->slow_work);
-			break;
+		break;
-		case FSCACHE_OP_MYTHREAD:
+	case FSCACHE_OP_MYTHREAD:
-			_debug("queue for caller's attention");
+		_debug("queue for caller's attention");
-			break;
+		break;
-		default:
+	default:
-			printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
+		printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
-			       op->flags);
+		       op->flags);
-			BUG();
+		BUG();
-			break;
+		break;
-		}
-		fscache_stat(&fscache_n_op_enqueue);
 	}
 }
 EXPORT_SYMBOL(fscache_enqueue_operation);
@@ -67,6 +69,8 @@ EXPORT_SYMBOL(fscache_enqueue_operation);
 static void fscache_run_op(struct fscache_object *object,
 			   struct fscache_operation *op)
 {
+	fscache_set_op_state(op, "Run");
+
 	object->n_in_progress++;
 	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
 		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
@@ -87,9 +91,12 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 
 	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
 
+	fscache_set_op_state(op, "SubmitX");
+
 	spin_lock(&object->lock);
 	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
 	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+	ASSERT(list_empty(&op->pend_link));
 
 	ret = -ENOBUFS;
 	if (fscache_object_is_active(object)) {
@@ -190,9 +197,12 @@ int fscache_submit_op(struct fscache_object *object,
 
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
+	fscache_set_op_state(op, "Submit");
+
 	spin_lock(&object->lock);
 	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
 	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+	ASSERT(list_empty(&op->pend_link));
 
 	ostate = object->state;
 	smp_rmb();
@@ -222,6 +232,11 @@ int fscache_submit_op(struct fscache_object *object,
 		list_add_tail(&op->pend_link, &object->pending_ops);
 		fscache_stat(&fscache_n_op_pend);
 		ret = 0;
+	} else if (object->state == FSCACHE_OBJECT_DYING ||
+		   object->state == FSCACHE_OBJECT_LC_DYING ||
+		   object->state == FSCACHE_OBJECT_WITHDRAWING) {
+		fscache_stat(&fscache_n_op_rejected);
+		ret = -ENOBUFS;
 	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
 		fscache_report_unexpected_submission(object, op, ostate);
 		ASSERT(!fscache_object_is_active(object));
@@ -264,12 +279,7 @@ void fscache_start_operations(struct fscache_object *object)
 			stop = true;
 		}
 		list_del_init(&op->pend_link);
-		object->n_in_progress++;
+		fscache_run_op(object, op);
-
-		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);
@@ -281,6 +291,36 @@ void fscache_start_operations(struct fscache_object *object)
 	       object->n_in_progress, object->debug_id);
 }
 
+/*
+ * cancel an operation that's pending on an object
+ */
+int fscache_cancel_op(struct fscache_operation *op)
+{
+	struct fscache_object *object = op->object;
+	int ret;
+
+	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
+
+	spin_lock(&object->lock);
+
+	ret = -EBUSY;
+	if (!list_empty(&op->pend_link)) {
+		fscache_stat(&fscache_n_op_cancelled);
+		list_del_init(&op->pend_link);
+		object->n_ops--;
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		fscache_put_operation(op);
+		ret = 0;
+	}
+
+	spin_unlock(&object->lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
 /*
  * release an operation
  * - queues pending ops if this is the last in-progress op
@@ -298,6 +338,8 @@ void fscache_put_operation(struct fscache_operation *op)
 	if (!atomic_dec_and_test(&op->usage))
 		return;
 
+	fscache_set_op_state(op, "Put");
+
 	_debug("PUT OP");
 	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
 		BUG();
@@ -311,6 +353,9 @@ void fscache_put_operation(struct fscache_operation *op)
 
 	object = op->object;
 
+	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
+		atomic_dec(&object->n_reads);
+
 	/* now... we may get called with the object spinlock held, so we
 	 * complete the cleanup here only if we can immediately acquire the
 	 * lock, and defer it otherwise */
@@ -452,8 +497,27 @@ static void fscache_op_execute(struct slow_work *work)
 	_leave("");
 }
 
+/*
+ * describe an operation for slow-work debugging
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+static void fscache_op_desc(struct slow_work *work, struct seq_file *m)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+
+	seq_printf(m, "FSC: OBJ%x OP%x: %s/%s fl=%lx",
+		   op->object->debug_id, op->debug_id,
+		   op->name, op->state, op->flags);
+}
+#endif
+
 const struct slow_work_ops fscache_op_slow_work_ops = {
+	.owner		= THIS_MODULE,
 	.get_ref	= fscache_op_get_ref,
 	.put_ref	= fscache_op_put_ref,
 	.execute	= fscache_op_execute,
+#ifdef CONFIG_SLOW_WORK_PROC
+	.desc		= fscache_op_desc,
+#endif
 };

fs/fscache/page.c

@@ -43,18 +43,102 @@ void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *pa
 EXPORT_SYMBOL(__fscache_wait_on_page_write);
 
 /*
- * note that a page has finished being written to the cache
+ * decide whether a page can be released, possibly by cancelling a store to it
+ * - we're allowed to sleep if __GFP_WAIT is flagged
  */
-static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *page)
+bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
+				  struct page *page,
+				  gfp_t gfp)
 {
 	struct page *xpage;
+	void *val;
+
+	_enter("%p,%p,%x", cookie, page, gfp);
+
+	rcu_read_lock();
+	val = radix_tree_lookup(&cookie->stores, page->index);
+	if (!val) {
+		rcu_read_unlock();
+		fscache_stat(&fscache_n_store_vmscan_not_storing);
+		__fscache_uncache_page(cookie, page);
+		return true;
+	}
+
+	/* see if the page is actually undergoing storage - if so we can't get
+	 * rid of it till the cache has finished with it */
+	if (radix_tree_tag_get(&cookie->stores, page->index,
+			       FSCACHE_COOKIE_STORING_TAG)) {
+		rcu_read_unlock();
+		goto page_busy;
+	}
+
+	/* the page is pending storage, so we attempt to cancel the store and
+	 * discard the store request so that the page can be reclaimed */
+	spin_lock(&cookie->stores_lock);
+	rcu_read_unlock();
+
+	if (radix_tree_tag_get(&cookie->stores, page->index,
+			       FSCACHE_COOKIE_STORING_TAG)) {
+		/* the page started to undergo storage whilst we were looking,
+		 * so now we can only wait or return */
+		spin_unlock(&cookie->stores_lock);
+		goto page_busy;
+	}
 
-	spin_lock(&cookie->lock);
 	xpage = radix_tree_delete(&cookie->stores, page->index);
-	spin_unlock(&cookie->lock);
+	spin_unlock(&cookie->stores_lock);
-	ASSERT(xpage != NULL);
+
+	if (xpage) {
+		fscache_stat(&fscache_n_store_vmscan_cancelled);
+		fscache_stat(&fscache_n_store_radix_deletes);
+		ASSERTCMP(xpage, ==, page);
+	} else {
+		fscache_stat(&fscache_n_store_vmscan_gone);
+	}
 
 	wake_up_bit(&cookie->flags, 0);
+	if (xpage)
+		page_cache_release(xpage);
+	__fscache_uncache_page(cookie, page);
+	return true;
+
+page_busy:
+	/* we might want to wait here, but that could deadlock the allocator as
+	 * the slow-work threads writing to the cache may all end up sleeping
+	 * on memory allocation */
+	fscache_stat(&fscache_n_store_vmscan_busy);
+	return false;
+}
+EXPORT_SYMBOL(__fscache_maybe_release_page);
+
+/*
+ * note that a page has finished being written to the cache
+ */
+static void fscache_end_page_write(struct fscache_object *object,
+				   struct page *page)
+{
+	struct fscache_cookie *cookie;
+	struct page *xpage = NULL;
+
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+	if (cookie) {
+		/* delete the page from the tree if it is now no longer
+		 * pending */
+		spin_lock(&cookie->stores_lock);
+		radix_tree_tag_clear(&cookie->stores, page->index,
+				     FSCACHE_COOKIE_STORING_TAG);
+		if (!radix_tree_tag_get(&cookie->stores, page->index,
+					FSCACHE_COOKIE_PENDING_TAG)) {
+			fscache_stat(&fscache_n_store_radix_deletes);
+			xpage = radix_tree_delete(&cookie->stores, page->index);
+		}
+		spin_unlock(&cookie->stores_lock);
+		wake_up_bit(&cookie->flags, 0);
+	}
+	spin_unlock(&object->lock);
+	if (xpage)
+		page_cache_release(xpage);
 }
 
 /*
@@ -63,14 +147,21 @@ static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *p
 static void fscache_attr_changed_op(struct fscache_operation *op)
 {
 	struct fscache_object *object = op->object;
+	int ret;
 
 	_enter("{OBJ%x OP%x}", object->debug_id, op->debug_id);
 
 	fscache_stat(&fscache_n_attr_changed_calls);
 
-	if (fscache_object_is_active(object) &&
+	if (fscache_object_is_active(object)) {
-	    object->cache->ops->attr_changed(object) < 0)
+		fscache_set_op_state(op, "CallFS");
-		fscache_abort_object(object);
+		fscache_stat(&fscache_n_cop_attr_changed);
+		ret = object->cache->ops->attr_changed(object);
+		fscache_stat_d(&fscache_n_cop_attr_changed);
+		fscache_set_op_state(op, "Done");
+		if (ret < 0)
+			fscache_abort_object(object);
+	}
 
 	_leave("");
 }
@@ -99,6 +190,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 	fscache_operation_init(op, NULL);
 	fscache_operation_init_slow(op, fscache_attr_changed_op);
 	op->flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_EXCLUSIVE);
+	fscache_set_op_name(op, "Attr");
 
 	spin_lock(&cookie->lock);
 
@@ -184,6 +276,7 @@ static struct fscache_retrieval *fscache_alloc_retrieval(
 	op->start_time	= jiffies;
 	INIT_WORK(&op->op.fast_work, fscache_retrieval_work);
 	INIT_LIST_HEAD(&op->to_do);
+	fscache_set_op_name(&op->op, "Retr");
 	return op;
 }
 
@@ -220,6 +313,43 @@ static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
 	return 0;
 }
 
+/*
+ * wait for an object to become active (or dead)
+ */
+static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
+						 struct fscache_retrieval *op,
+						 atomic_t *stat_op_waits,
+						 atomic_t *stat_object_dead)
+{
+	int ret;
+
+	if (!test_bit(FSCACHE_OP_WAITING, &op->op.flags))
+		goto check_if_dead;
+
+	_debug(">>> WT");
+	fscache_stat(stat_op_waits);
+	if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			fscache_wait_bit_interruptible,
+			TASK_INTERRUPTIBLE) < 0) {
+		ret = fscache_cancel_op(&op->op);
+		if (ret == 0)
+			return -ERESTARTSYS;
+
+		/* it's been removed from the pending queue by another party,
+		 * so we should get to run shortly */
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	}
+	_debug("<<< GO");
+
+check_if_dead:
+	if (unlikely(fscache_object_is_dead(object))) {
+		fscache_stat(stat_object_dead);
+		return -ENOBUFS;
+	}
+	return 0;
+}
+
 /*
  * read a page from the cache or allocate a block in which to store it
  * - we return:
@@ -257,6 +387,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
 	}
+	fscache_set_op_name(&op->op, "RetrRA1");
 
 	spin_lock(&cookie->lock);
 
@@ -267,6 +398,9 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 
 	ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP);
 
+	atomic_inc(&object->n_reads);
+	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+
 	if (fscache_submit_op(object, &op->op) < 0)
 		goto nobufs_unlock;
 	spin_unlock(&cookie->lock);
@@ -279,23 +413,27 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 
 	/* 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)) {
+	ret = fscache_wait_for_retrieval_activation(
-		_debug(">>> WT");
+		object, op,
-		fscache_stat(&fscache_n_retrieval_op_waits);
+		__fscache_stat(&fscache_n_retrieval_op_waits),
-		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+		__fscache_stat(&fscache_n_retrievals_object_dead));
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	if (ret < 0)
-		_debug("<<< GO");
+		goto error;
-	}
 
 	/* ask the cache to honour the operation */
 	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) {
+		fscache_stat(&fscache_n_cop_allocate_page);
 		ret = object->cache->ops->allocate_page(op, page, gfp);
+		fscache_stat_d(&fscache_n_cop_allocate_page);
 		if (ret == 0)
 			ret = -ENODATA;
 	} else {
+		fscache_stat(&fscache_n_cop_read_or_alloc_page);
 		ret = object->cache->ops->read_or_alloc_page(op, page, gfp);
+		fscache_stat_d(&fscache_n_cop_read_or_alloc_page);
 	}
 
+error:
 	if (ret == -ENOMEM)
 		fscache_stat(&fscache_n_retrievals_nomem);
 	else if (ret == -ERESTARTSYS)
@@ -347,7 +485,6 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 				  void *context,
 				  gfp_t gfp)
 {
-	fscache_pages_retrieval_func_t func;
 	struct fscache_retrieval *op;
 	struct fscache_object *object;
 	int ret;
@@ -369,6 +506,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	op = fscache_alloc_retrieval(mapping, end_io_func, context);
 	if (!op)
 		return -ENOMEM;
+	fscache_set_op_name(&op->op, "RetrRAN");
 
 	spin_lock(&cookie->lock);
 
@@ -377,6 +515,9 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
 
+	atomic_inc(&object->n_reads);
+	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+
 	if (fscache_submit_op(object, &op->op) < 0)
 		goto nobufs_unlock;
 	spin_unlock(&cookie->lock);
@@ -389,21 +530,27 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 
 	/* 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)) {
+	ret = fscache_wait_for_retrieval_activation(
-		_debug(">>> WT");
+		object, op,
-		fscache_stat(&fscache_n_retrieval_op_waits);
+		__fscache_stat(&fscache_n_retrieval_op_waits),
-		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+		__fscache_stat(&fscache_n_retrievals_object_dead));
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	if (ret < 0)
-		_debug("<<< GO");
+		goto error;
-	}
 
 	/* ask the cache to honour the operation */
-	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags))
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) {
-		func = object->cache->ops->allocate_pages;
+		fscache_stat(&fscache_n_cop_allocate_pages);
-	else
+		ret = object->cache->ops->allocate_pages(
-		func = object->cache->ops->read_or_alloc_pages;
+			op, pages, nr_pages, gfp);
-	ret = func(op, pages, nr_pages, gfp);
+		fscache_stat_d(&fscache_n_cop_allocate_pages);
+	} else {
+		fscache_stat(&fscache_n_cop_read_or_alloc_pages);
+		ret = object->cache->ops->read_or_alloc_pages(
+			op, pages, nr_pages, gfp);
+		fscache_stat_d(&fscache_n_cop_read_or_alloc_pages);
+	}
 
+error:
 	if (ret == -ENOMEM)
 		fscache_stat(&fscache_n_retrievals_nomem);
 	else if (ret == -ERESTARTSYS)
@@ -461,6 +608,7 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
 	if (!op)
 		return -ENOMEM;
+	fscache_set_op_name(&op->op, "RetrAL1");
 
 	spin_lock(&cookie->lock);
 
@@ -475,18 +623,22 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_alloc_ops);
 
-	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+	ret = fscache_wait_for_retrieval_activation(
-		_debug(">>> WT");
+		object, op,
-		fscache_stat(&fscache_n_alloc_op_waits);
+		__fscache_stat(&fscache_n_alloc_op_waits),
-		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+		__fscache_stat(&fscache_n_allocs_object_dead));
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	if (ret < 0)
-		_debug("<<< GO");
+		goto error;
-	}
 
 	/* ask the cache to honour the operation */
+	fscache_stat(&fscache_n_cop_allocate_page);
 	ret = object->cache->ops->allocate_page(op, page, gfp);
+	fscache_stat_d(&fscache_n_cop_allocate_page);
 
-	if (ret < 0)
+error:
+	if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_allocs_intr);
+	else if (ret < 0)
 		fscache_stat(&fscache_n_allocs_nobufs);
 	else
 		fscache_stat(&fscache_n_allocs_ok);
@@ -521,7 +673,7 @@ 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 fscache_cookie *cookie;
 	struct page *page;
 	unsigned n;
 	void *results[1];
@@ -529,16 +681,19 @@ static void fscache_write_op(struct fscache_operation *_op)
 
 	_enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage));
 
-	spin_lock(&cookie->lock);
+	fscache_set_op_state(&op->op, "GetPage");
-	spin_lock(&object->lock);
 
-	if (!fscache_object_is_active(object)) {
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+
+	if (!fscache_object_is_active(object) || !cookie) {
 		spin_unlock(&object->lock);
-		spin_unlock(&cookie->lock);
 		_leave("");
 		return;
 	}
 
+	spin_lock(&cookie->stores_lock);
+
 	fscache_stat(&fscache_n_store_calls);
 
 	/* find a page to store */
@@ -549,23 +704,35 @@ static void fscache_write_op(struct fscache_operation *_op)
 		goto superseded;
 	page = results[0];
 	_debug("gang %d [%lx]", n, page->index);
-	if (page->index > op->store_limit)
+	if (page->index > op->store_limit) {
+		fscache_stat(&fscache_n_store_pages_over_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) {
+		radix_tree_tag_set(&cookie->stores, page->index,
+				   FSCACHE_COOKIE_STORING_TAG);
+		radix_tree_tag_clear(&cookie->stores, page->index,
+				     FSCACHE_COOKIE_PENDING_TAG);
+	}
+
+	spin_unlock(&cookie->stores_lock);
+	spin_unlock(&object->lock);
+
+	if (page) {
+		fscache_set_op_state(&op->op, "Store");
+		fscache_stat(&fscache_n_store_pages);
+		fscache_stat(&fscache_n_cop_write_page);
 		ret = object->cache->ops->write_page(op, page);
-		fscache_end_page_write(cookie, page);
+		fscache_stat_d(&fscache_n_cop_write_page);
-		page_cache_release(page);
+		fscache_set_op_state(&op->op, "EndWrite");
-		if (ret < 0)
+		fscache_end_page_write(object, page);
+		if (ret < 0) {
+			fscache_set_op_state(&op->op, "Abort");
 			fscache_abort_object(object);
-		else
+		} else {
 			fscache_enqueue_operation(&op->op);
+		}
 	}
 
 	_leave("");
@@ -575,9 +742,9 @@ superseded:
 	/* this writer is going away and there aren't any more things to
 	 * write */
 	_debug("cease");
+	spin_unlock(&cookie->stores_lock);
 	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 	spin_unlock(&object->lock);
-	spin_unlock(&cookie->lock);
 	_leave("");
 }
 
@@ -634,6 +801,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 	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);
+	fscache_set_op_name(&op->op, "Write1");
 
 	ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
 	if (ret < 0)
@@ -652,6 +820,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 	/* add the page to the pending-storage radix tree on the backing
 	 * object */
 	spin_lock(&object->lock);
+	spin_lock(&cookie->stores_lock);
 
 	_debug("store limit %llx", (unsigned long long) object->store_limit);
 
@@ -672,6 +841,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 	if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags))
 		goto already_pending;
 
+	spin_unlock(&cookie->stores_lock);
 	spin_unlock(&object->lock);
 
 	op->op.debug_id	= atomic_inc_return(&fscache_op_debug_id);
@@ -693,6 +863,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 already_queued:
 	fscache_stat(&fscache_n_stores_again);
 already_pending:
+	spin_unlock(&cookie->stores_lock);
 	spin_unlock(&object->lock);
 	spin_unlock(&cookie->lock);
 	radix_tree_preload_end();
@@ -702,7 +873,9 @@ already_pending:
 	return 0;
 
 submit_failed:
+	spin_lock(&cookie->stores_lock);
 	radix_tree_delete(&cookie->stores, page->index);
+	spin_unlock(&cookie->stores_lock);
 	page_cache_release(page);
 	ret = -ENOBUFS;
 	goto nobufs;
@@ -763,7 +936,9 @@ void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page)
 	if (TestClearPageFsCache(page) &&
 	    object->cache->ops->uncache_page) {
 		/* the cache backend releases the cookie lock */
+		fscache_stat(&fscache_n_cop_uncache_page);
 		object->cache->ops->uncache_page(object, page);
+		fscache_stat_d(&fscache_n_cop_uncache_page);
 		goto done;
 	}
 

fs/fscache/proc.c

@@ -37,10 +37,20 @@ int __init fscache_proc_init(void)
 		goto error_histogram;
 #endif
 
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL,
+			 &fscache_objlist_fops))
+		goto error_objects;
+#endif
+
 	_leave(" = 0");
 	return 0;
 
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+error_objects:
+#endif
 #ifdef CONFIG_FSCACHE_HISTOGRAM
+	remove_proc_entry("fs/fscache/histogram", NULL);
 error_histogram:
 #endif
 #ifdef CONFIG_FSCACHE_STATS
@@ -58,6 +68,9 @@ error_dir:
  */
 void fscache_proc_cleanup(void)
 {
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	remove_proc_entry("fs/fscache/objects", NULL);
+#endif
 #ifdef CONFIG_FSCACHE_HISTOGRAM
 	remove_proc_entry("fs/fscache/histogram", NULL);
 #endif

fs/fscache/stats.c

@@ -25,6 +25,8 @@ atomic_t fscache_n_op_requeue;
 atomic_t fscache_n_op_deferred_release;
 atomic_t fscache_n_op_release;
 atomic_t fscache_n_op_gc;
+atomic_t fscache_n_op_cancelled;
+atomic_t fscache_n_op_rejected;
 
 atomic_t fscache_n_attr_changed;
 atomic_t fscache_n_attr_changed_ok;
@@ -36,6 +38,8 @@ atomic_t fscache_n_allocs;
 atomic_t fscache_n_allocs_ok;
 atomic_t fscache_n_allocs_wait;
 atomic_t fscache_n_allocs_nobufs;
+atomic_t fscache_n_allocs_intr;
+atomic_t fscache_n_allocs_object_dead;
 atomic_t fscache_n_alloc_ops;
 atomic_t fscache_n_alloc_op_waits;
 
@@ -46,6 +50,7 @@ atomic_t fscache_n_retrievals_nodata;
 atomic_t fscache_n_retrievals_nobufs;
 atomic_t fscache_n_retrievals_intr;
 atomic_t fscache_n_retrievals_nomem;
+atomic_t fscache_n_retrievals_object_dead;
 atomic_t fscache_n_retrieval_ops;
 atomic_t fscache_n_retrieval_op_waits;
 
@@ -56,6 +61,14 @@ atomic_t fscache_n_stores_nobufs;
 atomic_t fscache_n_stores_oom;
 atomic_t fscache_n_store_ops;
 atomic_t fscache_n_store_calls;
+atomic_t fscache_n_store_pages;
+atomic_t fscache_n_store_radix_deletes;
+atomic_t fscache_n_store_pages_over_limit;
+
+atomic_t fscache_n_store_vmscan_not_storing;
+atomic_t fscache_n_store_vmscan_gone;
+atomic_t fscache_n_store_vmscan_busy;
+atomic_t fscache_n_store_vmscan_cancelled;
 
 atomic_t fscache_n_marks;
 atomic_t fscache_n_uncaches;
@@ -74,6 +87,7 @@ atomic_t fscache_n_updates_run;
 atomic_t fscache_n_relinquishes;
 atomic_t fscache_n_relinquishes_null;
 atomic_t fscache_n_relinquishes_waitcrt;
+atomic_t fscache_n_relinquishes_retire;
 
 atomic_t fscache_n_cookie_index;
 atomic_t fscache_n_cookie_data;
@@ -84,6 +98,7 @@ atomic_t fscache_n_object_no_alloc;
 atomic_t fscache_n_object_lookups;
 atomic_t fscache_n_object_lookups_negative;
 atomic_t fscache_n_object_lookups_positive;
+atomic_t fscache_n_object_lookups_timed_out;
 atomic_t fscache_n_object_created;
 atomic_t fscache_n_object_avail;
 atomic_t fscache_n_object_dead;
@@ -93,6 +108,23 @@ atomic_t fscache_n_checkaux_okay;
 atomic_t fscache_n_checkaux_update;
 atomic_t fscache_n_checkaux_obsolete;
 
+atomic_t fscache_n_cop_alloc_object;
+atomic_t fscache_n_cop_lookup_object;
+atomic_t fscache_n_cop_lookup_complete;
+atomic_t fscache_n_cop_grab_object;
+atomic_t fscache_n_cop_update_object;
+atomic_t fscache_n_cop_drop_object;
+atomic_t fscache_n_cop_put_object;
+atomic_t fscache_n_cop_sync_cache;
+atomic_t fscache_n_cop_attr_changed;
+atomic_t fscache_n_cop_read_or_alloc_page;
+atomic_t fscache_n_cop_read_or_alloc_pages;
+atomic_t fscache_n_cop_allocate_page;
+atomic_t fscache_n_cop_allocate_pages;
+atomic_t fscache_n_cop_write_page;
+atomic_t fscache_n_cop_uncache_page;
+atomic_t fscache_n_cop_dissociate_pages;
+
 /*
  * display the general statistics
  */
@@ -129,10 +161,11 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   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",
+	seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u tmo=%u\n",
 		   atomic_read(&fscache_n_object_lookups),
 		   atomic_read(&fscache_n_object_lookups_negative),
 		   atomic_read(&fscache_n_object_lookups_positive),
+		   atomic_read(&fscache_n_object_lookups_timed_out),
 		   atomic_read(&fscache_n_object_created));
 
 	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
@@ -140,10 +173,11 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_updates_null),
 		   atomic_read(&fscache_n_updates_run));
 
-	seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u\n",
+	seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u rtr=%u\n",
 		   atomic_read(&fscache_n_relinquishes),
 		   atomic_read(&fscache_n_relinquishes_null),
-		   atomic_read(&fscache_n_relinquishes_waitcrt));
+		   atomic_read(&fscache_n_relinquishes_waitcrt),
+		   atomic_read(&fscache_n_relinquishes_retire));
 
 	seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n",
 		   atomic_read(&fscache_n_attr_changed),
@@ -152,14 +186,16 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   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",
+	seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n",
 		   atomic_read(&fscache_n_allocs),
 		   atomic_read(&fscache_n_allocs_ok),
 		   atomic_read(&fscache_n_allocs_wait),
-		   atomic_read(&fscache_n_allocs_nobufs));
+		   atomic_read(&fscache_n_allocs_nobufs),
-	seq_printf(m, "Allocs : ops=%u owt=%u\n",
+		   atomic_read(&fscache_n_allocs_intr));
+	seq_printf(m, "Allocs : ops=%u owt=%u abt=%u\n",
 		   atomic_read(&fscache_n_alloc_ops),
-		   atomic_read(&fscache_n_alloc_op_waits));
+		   atomic_read(&fscache_n_alloc_op_waits),
+		   atomic_read(&fscache_n_allocs_object_dead));
 
 	seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u"
 		   " int=%u oom=%u\n",
@@ -170,9 +206,10 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   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",
+	seq_printf(m, "Retrvls: ops=%u owt=%u abt=%u\n",
 		   atomic_read(&fscache_n_retrieval_ops),
-		   atomic_read(&fscache_n_retrieval_op_waits));
+		   atomic_read(&fscache_n_retrieval_op_waits),
+		   atomic_read(&fscache_n_retrievals_object_dead));
 
 	seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n",
 		   atomic_read(&fscache_n_stores),
@@ -180,18 +217,49 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   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",
+	seq_printf(m, "Stores : ops=%u run=%u pgs=%u rxd=%u olm=%u\n",
 		   atomic_read(&fscache_n_store_ops),
-		   atomic_read(&fscache_n_store_calls));
+		   atomic_read(&fscache_n_store_calls),
+		   atomic_read(&fscache_n_store_pages),
+		   atomic_read(&fscache_n_store_radix_deletes),
+		   atomic_read(&fscache_n_store_pages_over_limit));
 
-	seq_printf(m, "Ops    : pend=%u run=%u enq=%u\n",
+	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n",
+		   atomic_read(&fscache_n_store_vmscan_not_storing),
+		   atomic_read(&fscache_n_store_vmscan_gone),
+		   atomic_read(&fscache_n_store_vmscan_busy),
+		   atomic_read(&fscache_n_store_vmscan_cancelled));
+
+	seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u rej=%u\n",
 		   atomic_read(&fscache_n_op_pend),
 		   atomic_read(&fscache_n_op_run),
-		   atomic_read(&fscache_n_op_enqueue));
+		   atomic_read(&fscache_n_op_enqueue),
+		   atomic_read(&fscache_n_op_cancelled),
+		   atomic_read(&fscache_n_op_rejected));
 	seq_printf(m, "Ops    : dfr=%u rel=%u gc=%u\n",
 		   atomic_read(&fscache_n_op_deferred_release),
 		   atomic_read(&fscache_n_op_release),
 		   atomic_read(&fscache_n_op_gc));
+
+	seq_printf(m, "CacheOp: alo=%d luo=%d luc=%d gro=%d\n",
+		   atomic_read(&fscache_n_cop_alloc_object),
+		   atomic_read(&fscache_n_cop_lookup_object),
+		   atomic_read(&fscache_n_cop_lookup_complete),
+		   atomic_read(&fscache_n_cop_grab_object));
+	seq_printf(m, "CacheOp: upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+		   atomic_read(&fscache_n_cop_update_object),
+		   atomic_read(&fscache_n_cop_drop_object),
+		   atomic_read(&fscache_n_cop_put_object),
+		   atomic_read(&fscache_n_cop_attr_changed),
+		   atomic_read(&fscache_n_cop_sync_cache));
+	seq_printf(m, "CacheOp: rap=%d ras=%d alp=%d als=%d wrp=%d ucp=%d dsp=%d\n",
+		   atomic_read(&fscache_n_cop_read_or_alloc_page),
+		   atomic_read(&fscache_n_cop_read_or_alloc_pages),
+		   atomic_read(&fscache_n_cop_allocate_page),
+		   atomic_read(&fscache_n_cop_allocate_pages),
+		   atomic_read(&fscache_n_cop_write_page),
+		   atomic_read(&fscache_n_cop_uncache_page),
+		   atomic_read(&fscache_n_cop_dissociate_pages));
 	return 0;
 }
 

fs/gfs2/main.c

@@ -114,7 +114,7 @@ static int __init init_gfs2_fs(void)
 	if (error)
 		goto fail_unregister;
 
-	error = slow_work_register_user();
+	error = slow_work_register_user(THIS_MODULE);
 	if (error)
 		goto fail_slow;
 
@@ -163,7 +163,7 @@ static void __exit exit_gfs2_fs(void)
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
-	slow_work_unregister_user();
+	slow_work_unregister_user(THIS_MODULE);
 
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);

fs/gfs2/recovery.c

@@ -7,6 +7,7 @@
  * of the GNU General Public License version 2.
  */
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -593,6 +594,7 @@ fail:
 }
 
 struct slow_work_ops gfs2_recover_ops = {
+	.owner	 = THIS_MODULE,
 	.get_ref = gfs2_recover_get_ref,
 	.put_ref = gfs2_recover_put_ref,
 	.execute = gfs2_recover_work,

fs/nfs/fscache.c

@@ -359,17 +359,13 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 
 	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);
+		if (!fscache_maybe_release_page(cookie, page, gfp))
+			return 0;
+
 		nfs_add_fscache_stats(page->mapping->host,
 				      NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
 	}

include/linux/fscache-cache.h

@@ -91,6 +91,8 @@ struct fscache_operation {
 #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 */
+#define FSCACHE_OP_DEC_READ_CNT	7	/* decrement object->n_reads on destruction */
+#define FSCACHE_OP_KEEP_FLAGS	0xc0	/* flags to keep when repurposing an op */
 
 	atomic_t		usage;
 	unsigned		debug_id;	/* debugging ID */
@@ -102,6 +104,16 @@ struct fscache_operation {
 
 	/* operation releaser */
 	fscache_operation_release_t release;
+
+#ifdef CONFIG_SLOW_WORK_PROC
+	const char *name;		/* operation name */
+	const char *state;		/* operation state */
+#define fscache_set_op_name(OP, N)	do { (OP)->name  = (N); } while(0)
+#define fscache_set_op_state(OP, S)	do { (OP)->state = (S); } while(0)
+#else
+#define fscache_set_op_name(OP, N)	do { } while(0)
+#define fscache_set_op_state(OP, S)	do { } while(0)
+#endif
 };
 
 extern atomic_t fscache_op_debug_id;
@@ -125,6 +137,7 @@ static inline void fscache_operation_init(struct fscache_operation *op,
 	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
 	op->release = release;
 	INIT_LIST_HEAD(&op->pend_link);
+	fscache_set_op_state(op, "Init");
 }
 
 /**
@@ -221,8 +234,10 @@ struct fscache_cache_ops {
 	struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
 					       struct fscache_cookie *cookie);
 
-	/* look up the object for a cookie */
+	/* look up the object for a cookie
-	void (*lookup_object)(struct fscache_object *object);
+	 * - return -ETIMEDOUT to be requeued
+	 */
+	int (*lookup_object)(struct fscache_object *object);
 
 	/* finished looking up */
 	void (*lookup_complete)(struct fscache_object *object);
@@ -297,12 +312,14 @@ 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;
+	spinlock_t			stores_lock;	/* lock on page store tree */
 	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 */
+#define FSCACHE_COOKIE_STORING_TAG	1		/* pages tag: writing to cache */
 
 	unsigned long			flags;
 #define FSCACHE_COOKIE_LOOKING_UP	0	/* T if non-index cookie being looked up still */
@@ -337,6 +354,7 @@ struct fscache_object {
 		FSCACHE_OBJECT_RECYCLING,	/* retiring object */
 		FSCACHE_OBJECT_WITHDRAWING,	/* withdrawing object */
 		FSCACHE_OBJECT_DEAD,		/* object is now dead */
+		FSCACHE_OBJECT__NSTATES
 	} state;
 
 	int			debug_id;	/* debugging ID */
@@ -345,6 +363,7 @@ struct fscache_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 */
+	atomic_t		n_reads;	/* number of read ops in progress */
 	spinlock_t		lock;		/* state and operations lock */
 
 	unsigned long		lookup_jif;	/* time at which lookup started */
@@ -358,6 +377,7 @@ struct fscache_object {
 #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 */
+#define FSCACHE_OBJECT_EVENTS_MASK	0x7f	/* mask of all events*/
 
 	unsigned long		flags;
 #define FSCACHE_OBJECT_LOCK		0	/* T if object is busy being processed */
@@ -373,7 +393,11 @@ struct fscache_object {
 	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 */
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+	struct rb_node		objlist_link;	/* link in global object list */
+#endif
 	pgoff_t			store_limit;	/* current storage limit */
+	loff_t			store_limit_l;	/* current storage limit */
 };
 
 extern const char *fscache_object_states[];
@@ -383,6 +407,10 @@ extern const char *fscache_object_states[];
 	 (obj)->state >= FSCACHE_OBJECT_AVAILABLE &&	      \
 	 (obj)->state < FSCACHE_OBJECT_DYING)
 
+#define fscache_object_is_dead(obj)				\
+	(test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) &&	\
+	 (obj)->state >= FSCACHE_OBJECT_DYING)
+
 extern const struct slow_work_ops fscache_object_slow_work_ops;
 
 /**
@@ -414,6 +442,7 @@ void fscache_object_init(struct fscache_object *object,
 	object->events = object->event_mask = 0;
 	object->flags = 0;
 	object->store_limit = 0;
+	object->store_limit_l = 0;
 	object->cache = cache;
 	object->cookie = cookie;
 	object->parent = NULL;
@@ -422,6 +451,12 @@ void fscache_object_init(struct fscache_object *object,
 extern void fscache_object_lookup_negative(struct fscache_object *object);
 extern void fscache_obtained_object(struct fscache_object *object);
 
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+extern void fscache_object_destroy(struct fscache_object *object);
+#else
+#define fscache_object_destroy(object) do {} while(0)
+#endif
+
 /**
  * fscache_object_destroyed - Note destruction of an object in a cache
  * @cache: The cache from which the object came
@@ -460,6 +495,7 @@ static inline void fscache_object_lookup_error(struct fscache_object *object)
 static inline
 void fscache_set_store_limit(struct fscache_object *object, loff_t i_size)
 {
+	object->store_limit_l = i_size;
 	object->store_limit = i_size >> PAGE_SHIFT;
 	if (i_size & ~PAGE_MASK)
 		object->store_limit++;

include/linux/fscache.h

@@ -202,6 +202,8 @@ 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 *);
+extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *,
+					 gfp_t);
 
 /**
  * fscache_register_netfs - Register a filesystem as desiring caching services
@@ -615,4 +617,29 @@ void fscache_wait_on_page_write(struct fscache_cookie *cookie,
 		__fscache_wait_on_page_write(cookie, page);
 }
 
+/**
+ * fscache_maybe_release_page - Consider releasing a page, cancelling a store
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ * @gfp: The gfp flags passed to releasepage()
+ *
+ * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's
+ * releasepage() call.  A storage request on the page may cancelled if it is
+ * not currently being processed.
+ *
+ * The function returns true if the page no longer has a storage request on it,
+ * and false if a storage request is left in place.  If true is returned, the
+ * page will have been passed to fscache_uncache_page().  If false is returned
+ * the page cannot be freed yet.
+ */
+static inline
+bool fscache_maybe_release_page(struct fscache_cookie *cookie,
+				struct page *page,
+				gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie) && PageFsCache(page))
+		return __fscache_maybe_release_page(cookie, page, gfp);
+	return false;
+}
+
 #endif /* _LINUX_FSCACHE_H */

include/linux/slow-work.h

@@ -17,13 +17,20 @@
 #ifdef CONFIG_SLOW_WORK
 
 #include <linux/sysctl.h>
+#include <linux/timer.h>
 
 struct slow_work;
+#ifdef CONFIG_SLOW_WORK_PROC
+struct seq_file;
+#endif
 
 /*
  * The operations used to support slow work items
  */
 struct slow_work_ops {
+	/* owner */
+	struct module *owner;
+
 	/* get a ref on a work item
 	 * - return 0 if successful, -ve if not
 	 */
@@ -34,6 +41,11 @@ struct slow_work_ops {
 
 	/* execute a work item */
 	void (*execute)(struct slow_work *work);
+
+#ifdef CONFIG_SLOW_WORK_PROC
+	/* describe a work item for /proc */
+	void (*desc)(struct slow_work *work, struct seq_file *m);
+#endif
 };
 
 /*
@@ -42,13 +54,24 @@ struct slow_work_ops {
  *   queued
  */
 struct slow_work {
+	struct module		*owner;	/* the owning module */
 	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 */
+#define SLOW_WORK_CANCELLING	4	/* item is being cancelled, don't enqueue */
+#define SLOW_WORK_DELAYED	5	/* item is struct delayed_slow_work with active timer */
 	const struct slow_work_ops *ops; /* operations table for this item */
 	struct list_head	link;	/* link in queue */
+#ifdef CONFIG_SLOW_WORK_PROC
+	struct timespec		mark;	/* jiffies at which queued or exec begun */
+#endif
+};
+
+struct delayed_slow_work {
+	struct slow_work	work;
+	struct timer_list	timer;
 };
 
 /**
@@ -66,6 +89,20 @@ static inline void slow_work_init(struct slow_work *work,
 	INIT_LIST_HEAD(&work->link);
 }
 
+/**
+ * slow_work_init - Initialise a delayed slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a delayed slow work item.
+ */
+static inline void delayed_slow_work_init(struct delayed_slow_work *dwork,
+					  const struct slow_work_ops *ops)
+{
+	init_timer(&dwork->timer);
+	slow_work_init(&dwork->work, ops);
+}
+
 /**
  * vslow_work_init - Initialise a very slow work item
  * @work: The work item to initialise
@@ -83,9 +120,40 @@ static inline void vslow_work_init(struct slow_work *work,
 	INIT_LIST_HEAD(&work->link);
 }
 
+/**
+ * slow_work_is_queued - Determine if a slow work item is on the work queue
+ * work: The work item to test
+ *
+ * Determine if the specified slow-work item is on the work queue.  This
+ * returns true if it is actually on the queue.
+ *
+ * If the item is executing and has been marked for requeue when execution
+ * finishes, then false will be returned.
+ *
+ * Anyone wishing to wait for completion of execution can wait on the
+ * SLOW_WORK_EXECUTING bit.
+ */
+static inline bool slow_work_is_queued(struct slow_work *work)
+{
+	unsigned long flags = work->flags;
+	return flags & SLOW_WORK_PENDING && !(flags & SLOW_WORK_EXECUTING);
+}
+
 extern int slow_work_enqueue(struct slow_work *work);
-extern int slow_work_register_user(void);
+extern void slow_work_cancel(struct slow_work *work);
-extern void slow_work_unregister_user(void);
+extern int slow_work_register_user(struct module *owner);
+extern void slow_work_unregister_user(struct module *owner);
+
+extern int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
+				     unsigned long delay);
+
+static inline void delayed_slow_work_cancel(struct delayed_slow_work *dwork)
+{
+	slow_work_cancel(&dwork->work);
+}
+
+extern bool slow_work_sleep_till_thread_needed(struct slow_work *work,
+					       signed long *_timeout);
 
 #ifdef CONFIG_SYSCTL
 extern ctl_table slow_work_sysctls[];

init/Kconfig

@@ -1098,6 +1098,16 @@ config SLOW_WORK
 
 	  See Documentation/slow-work.txt.
 
+config SLOW_WORK_PROC
+	bool "Slow work debugging through /proc"
+	default n
+	depends on SLOW_WORK && PROC_FS
+	help
+	  Display the contents of the slow work run queue through /proc,
+	  including items currently executing.
+
+	  See Documentation/slow-work.txt.
+
 endmenu		# General setup
 
 config HAVE_GENERIC_DMA_COHERENT

kernel/Makefile

@@ -94,6 +94,7 @@ obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_SLOW_WORK_PROC) += slow-work-proc.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)

kernel/slow-work-proc.c

@@ -0,0 +1,227 @@
+/* Slow work debugging
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/seq_file.h>
+#include "slow-work.h"
+
+#define ITERATOR_SHIFT		(BITS_PER_LONG - 4)
+#define ITERATOR_SELECTOR	(0xfUL << ITERATOR_SHIFT)
+#define ITERATOR_COUNTER	(~ITERATOR_SELECTOR)
+
+void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m)
+{
+	seq_puts(m, "Slow-work: New thread");
+}
+
+/*
+ * Render the time mark field on a work item into a 5-char time with units plus
+ * a space
+ */
+static void slow_work_print_mark(struct seq_file *m, struct slow_work *work)
+{
+	struct timespec now, diff;
+
+	now = CURRENT_TIME;
+	diff = timespec_sub(now, work->mark);
+
+	if (diff.tv_sec < 0)
+		seq_puts(m, "  -ve ");
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000)
+		seq_printf(m, "%3luns ", diff.tv_nsec);
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000)
+		seq_printf(m, "%3luus ", diff.tv_nsec / 1000);
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000)
+		seq_printf(m, "%3lums ", diff.tv_nsec / 1000000);
+	else if (diff.tv_sec <= 1)
+		seq_puts(m, "   1s ");
+	else if (diff.tv_sec < 60)
+		seq_printf(m, "%4lus ", diff.tv_sec);
+	else if (diff.tv_sec < 60 * 60)
+		seq_printf(m, "%4lum ", diff.tv_sec / 60);
+	else if (diff.tv_sec < 60 * 60 * 24)
+		seq_printf(m, "%4luh ", diff.tv_sec / 3600);
+	else
+		seq_puts(m, "exces ");
+}
+
+/*
+ * Describe a slow work item for /proc
+ */
+static int slow_work_runqueue_show(struct seq_file *m, void *v)
+{
+	struct slow_work *work;
+	struct list_head *p = v;
+	unsigned long id;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "THR PID   ITEM ADDR        FL MARK  DESC\n");
+		return 0;
+	case 2:
+		seq_puts(m, "=== ===== ================ == ===== ==========\n");
+		return 0;
+
+	case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1:
+		id = (unsigned long) v - 3;
+
+		read_lock(&slow_work_execs_lock);
+		work = slow_work_execs[id];
+		if (work) {
+			smp_read_barrier_depends();
+
+			seq_printf(m, "%3lu %5d %16p %2lx ",
+				   id, slow_work_pids[id], work, work->flags);
+			slow_work_print_mark(m, work);
+
+			if (work->ops->desc)
+				work->ops->desc(work, m);
+			seq_putc(m, '\n');
+		}
+		read_unlock(&slow_work_execs_lock);
+		return 0;
+
+	default:
+		work = list_entry(p, struct slow_work, link);
+		seq_printf(m, "%3s     - %16p %2lx ",
+			   work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq",
+			   work, work->flags);
+		slow_work_print_mark(m, work);
+
+		if (work->ops->desc)
+			work->ops->desc(work, m);
+		seq_putc(m, '\n');
+		return 0;
+	}
+}
+
+/*
+ * map the iterator to a work item
+ */
+static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *p;
+	unsigned long count, id;
+
+	switch (*_pos >> ITERATOR_SHIFT) {
+	case 0x0:
+		if (*_pos == 0)
+			*_pos = 1;
+		if (*_pos < 3)
+			return (void *)(unsigned long) *_pos;
+		if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT)
+			for (id = *_pos - 3;
+			     id < SLOW_WORK_THREAD_LIMIT;
+			     id++, (*_pos)++)
+				if (slow_work_execs[id])
+					return (void *)(unsigned long) *_pos;
+		*_pos = 0x1UL << ITERATOR_SHIFT;
+
+	case 0x1:
+		count = *_pos & ITERATOR_COUNTER;
+		list_for_each(p, &slow_work_queue) {
+			if (count == 0)
+				return p;
+			count--;
+		}
+		*_pos = 0x2UL << ITERATOR_SHIFT;
+
+	case 0x2:
+		count = *_pos & ITERATOR_COUNTER;
+		list_for_each(p, &vslow_work_queue) {
+			if (count == 0)
+				return p;
+			count--;
+		}
+		*_pos = 0x3UL << ITERATOR_SHIFT;
+
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos)
+{
+	spin_lock_irq(&slow_work_queue_lock);
+	return slow_work_runqueue_index(m, _pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	struct list_head *p = v;
+	unsigned long selector = *_pos >> ITERATOR_SHIFT;
+
+	(*_pos)++;
+	switch (selector) {
+	case 0x0:
+		return slow_work_runqueue_index(m, _pos);
+
+	case 0x1:
+		if (*_pos >> ITERATOR_SHIFT == 0x1) {
+			p = p->next;
+			if (p != &slow_work_queue)
+				return p;
+		}
+		*_pos = 0x2UL << ITERATOR_SHIFT;
+		p = &vslow_work_queue;
+
+	case 0x2:
+		if (*_pos >> ITERATOR_SHIFT == 0x2) {
+			p = p->next;
+			if (p != &vslow_work_queue)
+				return p;
+		}
+		*_pos = 0x3UL << ITERATOR_SHIFT;
+
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * clean up after reading
+ */
+static void slow_work_runqueue_stop(struct seq_file *m, void *v)
+{
+	spin_unlock_irq(&slow_work_queue_lock);
+}
+
+static const struct seq_operations slow_work_runqueue_ops = {
+	.start		= slow_work_runqueue_start,
+	.stop		= slow_work_runqueue_stop,
+	.next		= slow_work_runqueue_next,
+	.show		= slow_work_runqueue_show,
+};
+
+/*
+ * open "/proc/slow_work_rq" to list queue contents
+ */
+static int slow_work_runqueue_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slow_work_runqueue_ops);
+}
+
+const struct file_operations slow_work_runqueue_fops = {
+	.owner		= THIS_MODULE,
+	.open		= slow_work_runqueue_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};

kernel/slow-work.c

@@ -16,11 +16,8 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/wait.h>
-
+#include <linux/proc_fs.h>
-#define SLOW_WORK_CULL_TIMEOUT (5 * HZ)	/* cull threads 5s after running out of
+#include "slow-work.h"
-					 * 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);
@@ -46,7 +43,7 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process
 
 #ifdef CONFIG_SYSCTL
 static const int slow_work_min_min_threads = 2;
-static int slow_work_max_max_threads = 255;
+static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT;
 static const int slow_work_min_vslow = 1;
 static const int slow_work_max_vslow = 99;
 
@@ -97,6 +94,32 @@ 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 */
 
+/*
+ * slow work ID allocation (use slow_work_queue_lock)
+ */
+static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+
+/*
+ * Unregistration tracking to prevent put_ref() from disappearing during module
+ * unload
+ */
+#ifdef CONFIG_MODULES
+static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT];
+static struct module *slow_work_unreg_module;
+static struct slow_work *slow_work_unreg_work_item;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq);
+static DEFINE_MUTEX(slow_work_unreg_sync_lock);
+#endif
+
+/*
+ * Data for tracking currently executing items for indication through /proc
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT];
+pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT];
+DEFINE_RWLOCK(slow_work_execs_lock);
+#endif
+
 /*
  * 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
@@ -105,9 +128,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */
  * 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);
+LIST_HEAD(slow_work_queue);
-static LIST_HEAD(vslow_work_queue);
+LIST_HEAD(vslow_work_queue);
-static DEFINE_SPINLOCK(slow_work_queue_lock);
+DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The following are two wait queues that get pinged when a work item is placed
+ * on an empty queue.  These allow work items that are hogging a thread by
+ * sleeping in a way that could be deferred to yield their thread and enqueue
+ * themselves.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation);
+static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation);
 
 /*
  * The thread controls.  A variable used to signal to the threads that they
@@ -126,6 +158,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited);
 static int slow_work_user_count;
 static DEFINE_MUTEX(slow_work_user_lock);
 
+static inline int slow_work_get_ref(struct slow_work *work)
+{
+	if (work->ops->get_ref)
+		return work->ops->get_ref(work);
+
+	return 0;
+}
+
+static inline void slow_work_put_ref(struct slow_work *work)
+{
+	if (work->ops->put_ref)
+		work->ops->put_ref(work);
+}
+
 /*
  * Calculate the maximum number of active threads in the pool that are
  * permitted to process very slow work items.
@@ -149,8 +195,11 @@ static unsigned slow_work_calc_vsmax(void)
  * 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)
+static noinline bool slow_work_execute(int id)
 {
+#ifdef CONFIG_MODULES
+	struct module *module;
+#endif
 	struct slow_work *work = NULL;
 	unsigned vsmax;
 	bool very_slow;
@@ -186,6 +235,16 @@ static bool slow_work_execute(void)
 	} else {
 		very_slow = false; /* avoid the compiler warning */
 	}
+
+#ifdef CONFIG_MODULES
+	if (work)
+		slow_work_thread_processing[id] = work->owner;
+#endif
+	if (work) {
+		slow_work_mark_time(work);
+		slow_work_begin_exec(id, work);
+	}
+
 	spin_unlock_irq(&slow_work_queue_lock);
 
 	if (!work)
@@ -194,12 +253,19 @@ static bool slow_work_execute(void)
 	if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
 		BUG();
 
-	work->ops->execute(work);
+	/* don't execute if the work is in the process of being cancelled */
+	if (!test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		work->ops->execute(work);
 
 	if (very_slow)
 		atomic_dec(&vslow_work_executing_count);
 	clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
 
+	/* wake up anyone waiting for this work to be complete */
+	wake_up_bit(&work->flags, SLOW_WORK_EXECUTING);
+
+	slow_work_end_exec(id, work);
+
 	/* 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
@@ -219,7 +285,18 @@ static bool slow_work_execute(void)
 		spin_unlock_irq(&slow_work_queue_lock);
 	}
 
-	work->ops->put_ref(work);
+	/* sort out the race between module unloading and put_ref() */
+	slow_work_put_ref(work);
+
+#ifdef CONFIG_MODULES
+	module = slow_work_thread_processing[id];
+	slow_work_thread_processing[id] = NULL;
+	smp_mb();
+	if (slow_work_unreg_work_item == work ||
+	    slow_work_unreg_module == module)
+		wake_up_all(&slow_work_unreg_wq);
+#endif
+
 	return true;
 
 auto_requeue:
@@ -227,14 +304,60 @@ auto_requeue:
 	 * - we transfer our ref on the item back to the appropriate queue
 	 * - don't wake another thread up as we're awake already
 	 */
+	slow_work_mark_time(work);
 	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);
+	slow_work_thread_processing[id] = NULL;
 	return true;
 }
 
+/**
+ * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work
+ * work: The work item under execution that wants to sleep
+ * _timeout: Scheduler sleep timeout
+ *
+ * Allow a requeueable work item to sleep on a slow-work processor thread until
+ * that thread is needed to do some other work or the sleep is interrupted by
+ * some other event.
+ *
+ * The caller must set up a wake up event before calling this and must have set
+ * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
+ * condition before calling this function as no test is made here.
+ *
+ * False is returned if there is nothing on the queue; true is returned if the
+ * work item should be requeued
+ */
+bool slow_work_sleep_till_thread_needed(struct slow_work *work,
+					signed long *_timeout)
+{
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
+
+	DEFINE_WAIT(wait);
+
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+		wfo_wq = &vslow_work_queue_waits_for_occupation;
+		queue = &vslow_work_queue;
+	} else {
+		wfo_wq = &slow_work_queue_waits_for_occupation;
+		queue = &slow_work_queue;
+	}
+
+	if (!list_empty(queue))
+		return true;
+
+	add_wait_queue_exclusive(wfo_wq, &wait);
+	if (list_empty(queue))
+		*_timeout = schedule_timeout(*_timeout);
+	finish_wait(wfo_wq, &wait);
+
+	return !list_empty(queue);
+}
+EXPORT_SYMBOL(slow_work_sleep_till_thread_needed);
+
 /**
  * slow_work_enqueue - Schedule a slow work item for processing
  * @work: The work item to queue
@@ -260,16 +383,22 @@ auto_requeue:
  * 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.
+ * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is
+ * attempted queued)
  */
 int slow_work_enqueue(struct slow_work *work)
 {
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
 	unsigned long flags;
+	int ret;
+
+	if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		return -ECANCELED;
 
 	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
@@ -280,8 +409,19 @@ int slow_work_enqueue(struct slow_work *work)
 	 * maintaining our promise
 	 */
 	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+			wfo_wq = &vslow_work_queue_waits_for_occupation;
+			queue = &vslow_work_queue;
+		} else {
+			wfo_wq = &slow_work_queue_waits_for_occupation;
+			queue = &slow_work_queue;
+		}
+
 		spin_lock_irqsave(&slow_work_queue_lock, flags);
 
+		if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags)))
+			goto cancelled;
+
 		/* we promise that we will not attempt to execute the work
 		 * function in more than one thread simultaneously
 		 *
@@ -299,25 +439,221 @@ int slow_work_enqueue(struct slow_work *work)
 		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
 			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
 		} else {
-			if (work->ops->get_ref(work) < 0)
+			ret = slow_work_get_ref(work);
-				goto cant_get_ref;
+			if (ret < 0)
-			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+				goto failed;
-				list_add_tail(&work->link, &vslow_work_queue);
+			slow_work_mark_time(work);
-			else
+			list_add_tail(&work->link, queue);
-				list_add_tail(&work->link, &slow_work_queue);
 			wake_up(&slow_work_thread_wq);
+
+			/* if someone who could be requeued is sleeping on a
+			 * thread, then ask them to yield their thread */
+			if (work->link.prev == queue)
+				wake_up(wfo_wq);
 		}
 
 		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
 	}
 	return 0;
 
-cant_get_ref:
+cancelled:
+	ret = -ECANCELED;
+failed:
 	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
-	return -EAGAIN;
+	return ret;
 }
 EXPORT_SYMBOL(slow_work_enqueue);
 
+static int slow_work_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+/**
+ * slow_work_cancel - Cancel a slow work item
+ * @work: The work item to cancel
+ *
+ * This function will cancel a previously enqueued work item. If we cannot
+ * cancel the work item, it is guarenteed to have run when this function
+ * returns.
+ */
+void slow_work_cancel(struct slow_work *work)
+{
+	bool wait = true, put = false;
+
+	set_bit(SLOW_WORK_CANCELLING, &work->flags);
+	smp_mb();
+
+	/* if the work item is a delayed work item with an active timer, we
+	 * need to wait for the timer to finish _before_ getting the spinlock,
+	 * lest we deadlock against the timer routine
+	 *
+	 * the timer routine will leave DELAYED set if it notices the
+	 * CANCELLING flag in time
+	 */
+	if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+		struct delayed_slow_work *dwork =
+			container_of(work, struct delayed_slow_work, work);
+		del_timer_sync(&dwork->timer);
+	}
+
+	spin_lock_irq(&slow_work_queue_lock);
+
+	if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+		/* the timer routine aborted or never happened, so we are left
+		 * holding the timer's reference on the item and should just
+		 * drop the pending flag and wait for any ongoing execution to
+		 * finish */
+		struct delayed_slow_work *dwork =
+			container_of(work, struct delayed_slow_work, work);
+
+		BUG_ON(timer_pending(&dwork->timer));
+		BUG_ON(!list_empty(&work->link));
+
+		clear_bit(SLOW_WORK_DELAYED, &work->flags);
+		put = true;
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+	} else if (test_bit(SLOW_WORK_PENDING, &work->flags) &&
+		   !list_empty(&work->link)) {
+		/* the link in the pending queue holds a reference on the item
+		 * that we will need to release */
+		list_del_init(&work->link);
+		wait = false;
+		put = true;
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+	} else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) {
+		/* the executor is holding our only reference on the item, so
+		 * we merely need to wait for it to finish executing */
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+	}
+
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	/* the EXECUTING flag is set by the executor whilst the spinlock is set
+	 * and before the item is dequeued - so assuming the above doesn't
+	 * actually dequeue it, simply waiting for the EXECUTING flag to be
+	 * released here should be sufficient */
+	if (wait)
+		wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait,
+			    TASK_UNINTERRUPTIBLE);
+
+	clear_bit(SLOW_WORK_CANCELLING, &work->flags);
+	if (put)
+		slow_work_put_ref(work);
+}
+EXPORT_SYMBOL(slow_work_cancel);
+
+/*
+ * Handle expiry of the delay timer, indicating that a delayed slow work item
+ * should now be queued if not cancelled
+ */
+static void delayed_slow_work_timer(unsigned long data)
+{
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
+	struct slow_work *work = (struct slow_work *) data;
+	unsigned long flags;
+	bool queued = false, put = false, first = false;
+
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+		wfo_wq = &vslow_work_queue_waits_for_occupation;
+		queue = &vslow_work_queue;
+	} else {
+		wfo_wq = &slow_work_queue_waits_for_occupation;
+		queue = &slow_work_queue;
+	}
+
+	spin_lock_irqsave(&slow_work_queue_lock, flags);
+	if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) {
+		clear_bit(SLOW_WORK_DELAYED, &work->flags);
+
+		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+			/* we discard the reference the timer was holding in
+			 * favour of the one the executor holds */
+			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+			put = true;
+		} else {
+			slow_work_mark_time(work);
+			list_add_tail(&work->link, queue);
+			queued = true;
+			if (work->link.prev == queue)
+				first = true;
+		}
+	}
+
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	if (put)
+		slow_work_put_ref(work);
+	if (first)
+		wake_up(wfo_wq);
+	if (queued)
+		wake_up(&slow_work_thread_wq);
+}
+
+/**
+ * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing
+ * @dwork: The delayed work item to queue
+ * @delay: When to start executing the work, in jiffies from now
+ *
+ * This is similar to slow_work_enqueue(), but it adds a delay before the work
+ * is actually queued for processing.
+ *
+ * The item can have delayed processing requested on it whilst it is being
+ * executed.  The delay will begin immediately, and if it expires before the
+ * item finishes executing, the item will be placed back on the queue when it
+ * has done executing.
+ */
+int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
+			      unsigned long delay)
+{
+	struct slow_work *work = &dwork->work;
+	unsigned long flags;
+	int ret;
+
+	if (delay == 0)
+		return slow_work_enqueue(&dwork->work);
+
+	BUG_ON(slow_work_user_count <= 0);
+	BUG_ON(!work);
+	BUG_ON(!work->ops);
+
+	if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		return -ECANCELED;
+
+	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+		if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+			goto cancelled;
+
+		/* the timer holds a reference whilst it is pending */
+		ret = work->ops->get_ref(work);
+		if (ret < 0)
+			goto cant_get_ref;
+
+		if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags))
+			BUG();
+		dwork->timer.expires = jiffies + delay;
+		dwork->timer.data = (unsigned long) work;
+		dwork->timer.function = delayed_slow_work_timer;
+		add_timer(&dwork->timer);
+
+		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	}
+
+	return 0;
+
+cancelled:
+	ret = -ECANCELED;
+cant_get_ref:
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(delayed_slow_work_enqueue);
+
 /*
  * Schedule a cull of the thread pool at some time in the near future
  */
@@ -368,13 +704,23 @@ static inline bool slow_work_available(int vsmax)
  */
 static int slow_work_thread(void *_data)
 {
-	int vsmax;
+	int vsmax, id;
 
 	DEFINE_WAIT(wait);
 
 	set_freezable();
 	set_user_nice(current, -5);
 
+	/* allocate ourselves an ID */
+	spin_lock_irq(&slow_work_queue_lock);
+	id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+	BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT);
+	__set_bit(id, slow_work_ids);
+	slow_work_set_thread_pid(id, current->pid);
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	sprintf(current->comm, "kslowd%03u", id);
+
 	for (;;) {
 		vsmax = vslow_work_proportion;
 		vsmax *= atomic_read(&slow_work_thread_count);
@@ -395,7 +741,7 @@ static int slow_work_thread(void *_data)
 		vsmax *= atomic_read(&slow_work_thread_count);
 		vsmax /= 100;
 
-		if (slow_work_available(vsmax) && slow_work_execute()) {
+		if (slow_work_available(vsmax) && slow_work_execute(id)) {
 			cond_resched();
 			if (list_empty(&slow_work_queue) &&
 			    list_empty(&vslow_work_queue) &&
@@ -412,6 +758,11 @@ static int slow_work_thread(void *_data)
 			break;
 	}
 
+	spin_lock_irq(&slow_work_queue_lock);
+	slow_work_set_thread_pid(id, 0);
+	__clear_bit(id, slow_work_ids);
+	spin_unlock_irq(&slow_work_queue_lock);
+
 	if (atomic_dec_and_test(&slow_work_thread_count))
 		complete_and_exit(&slow_work_last_thread_exited, 0);
 	return 0;
@@ -426,21 +777,6 @@ static void slow_work_cull_timeout(unsigned long data)
 	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
  */
@@ -475,9 +811,11 @@ static void slow_work_new_thread_execute(struct slow_work *work)
 }
 
 static const struct slow_work_ops slow_work_new_thread_ops = {
-	.get_ref	= slow_work_new_thread_get_ref,
+	.owner		= THIS_MODULE,
-	.put_ref	= slow_work_new_thread_put_ref,
 	.execute	= slow_work_new_thread_execute,
+#ifdef CONFIG_SLOW_WORK_PROC
+	.desc		= slow_work_new_thread_desc,
+#endif
 };
 
 /*
@@ -546,12 +884,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
 
 /**
  * slow_work_register_user - Register a user of the facility
+ * @module: The module about to make use 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)
+int slow_work_register_user(struct module *module)
 {
 	struct task_struct *p;
 	int loop;
@@ -598,14 +937,79 @@ error:
 }
 EXPORT_SYMBOL(slow_work_register_user);
 
+/*
+ * wait for all outstanding items from the calling module to complete
+ * - note that more items may be queued whilst we're waiting
+ */
+static void slow_work_wait_for_items(struct module *module)
+{
+	DECLARE_WAITQUEUE(myself, current);
+	struct slow_work *work;
+	int loop;
+
+	mutex_lock(&slow_work_unreg_sync_lock);
+	add_wait_queue(&slow_work_unreg_wq, &myself);
+
+	for (;;) {
+		spin_lock_irq(&slow_work_queue_lock);
+
+		/* first of all, we wait for the last queued item in each list
+		 * to be processed */
+		list_for_each_entry_reverse(work, &vslow_work_queue, link) {
+			if (work->owner == module) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				slow_work_unreg_work_item = work;
+				goto do_wait;
+			}
+		}
+		list_for_each_entry_reverse(work, &slow_work_queue, link) {
+			if (work->owner == module) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				slow_work_unreg_work_item = work;
+				goto do_wait;
+			}
+		}
+
+		/* then we wait for the items being processed to finish */
+		slow_work_unreg_module = module;
+		smp_mb();
+		for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) {
+			if (slow_work_thread_processing[loop] == module)
+				goto do_wait;
+		}
+		spin_unlock_irq(&slow_work_queue_lock);
+		break; /* okay, we're done */
+
+	do_wait:
+		spin_unlock_irq(&slow_work_queue_lock);
+		schedule();
+		slow_work_unreg_work_item = NULL;
+		slow_work_unreg_module = NULL;
+	}
+
+	remove_wait_queue(&slow_work_unreg_wq, &myself);
+	mutex_unlock(&slow_work_unreg_sync_lock);
+}
+
 /**
  * slow_work_unregister_user - Unregister a user of the facility
+ * @module: The module whose items should be cleared
  *
  * Unregister a user of the facility, killing all the threads if this was the
  * last one.
+ *
+ * This waits for all the work items belonging to the nominated module to go
+ * away before proceeding.
  */
-void slow_work_unregister_user(void)
+void slow_work_unregister_user(struct module *module)
 {
+	/* first of all, wait for all outstanding items from the calling module
+	 * to complete */
+	if (module)
+		slow_work_wait_for_items(module);
+
+	/* then we can actually go about shutting down the facility if need
+	 * be */
 	mutex_lock(&slow_work_user_lock);
 
 	BUG_ON(slow_work_user_count <= 0);
@@ -638,6 +1042,10 @@ static int __init init_slow_work(void)
 #ifdef CONFIG_SYSCTL
 	if (slow_work_max_max_threads < nr_cpus * 2)
 		slow_work_max_max_threads = nr_cpus * 2;
+#endif
+#ifdef CONFIG_SLOW_WORK_PROC
+	proc_create("slow_work_rq", S_IFREG | 0400, NULL,
+		    &slow_work_runqueue_fops);
 #endif
 	return 0;
 }

kernel/slow-work.h

@@ -0,0 +1,72 @@
+/* Slow work private definitions
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define 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 */
+
+#define SLOW_WORK_THREAD_LIMIT	255	/* abs maximum number of slow-work threads */
+
+/*
+ * slow-work.c
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+extern struct slow_work *slow_work_execs[];
+extern pid_t slow_work_pids[];
+extern rwlock_t slow_work_execs_lock;
+#endif
+
+extern struct list_head slow_work_queue;
+extern struct list_head vslow_work_queue;
+extern spinlock_t slow_work_queue_lock;
+
+/*
+ * slow-work-proc.c
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+extern const struct file_operations slow_work_runqueue_fops;
+
+extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *);
+#endif
+
+/*
+ * Helper functions
+ */
+static inline void slow_work_set_thread_pid(int id, pid_t pid)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	slow_work_pids[id] = pid;
+#endif
+}
+
+static inline void slow_work_mark_time(struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	work->mark = CURRENT_TIME;
+#endif
+}
+
+static inline void slow_work_begin_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	slow_work_execs[id] = work;
+#endif
+}
+
+static inline void slow_work_end_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	write_lock(&slow_work_execs_lock);
+	slow_work_execs[id] = NULL;
+	write_unlock(&slow_work_execs_lock);
+#endif
+}

lib/radix-tree.c

@@ -200,6 +200,9 @@ radix_tree_node_free(struct radix_tree_node *node)
  * ensure that the addition of a single element in the tree cannot fail.  On
  * success, return zero, with preemption disabled.  On error, return -ENOMEM
  * with preemption not disabled.
+ *
+ * To make use of this facility, the radix tree must be initialised without
+ * __GFP_WAIT being passed to INIT_RADIX_TREE().
  */
 int radix_tree_preload(gfp_t gfp_mask)
 {
@@ -543,7 +546,6 @@ out:
 }
 EXPORT_SYMBOL(radix_tree_tag_clear);
 
-#ifndef __KERNEL__	/* Only the test harness uses this at present */
 /**
  * radix_tree_tag_get - get a tag on a radix tree node
  * @root:		radix tree root
@@ -606,7 +608,6 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 	}
 }
 EXPORT_SYMBOL(radix_tree_tag_get);
-#endif
 
 /**
  *	radix_tree_next_hole    -    find the next hole (not-present entry)