Merge branch 'fscache' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs into for-linus

8 files changed, 470 insertions, 86 deletions

diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
index 6a3c48abd677..b52aed1dca97 100644
--- a/fs/fscache/cache.c
+++ b/fs/fscache/cache.c
@@ -314,10 +314,10 @@ EXPORT_SYMBOL(fscache_add_cache);
  */
 void fscache_io_error(struct fscache_cache *cache)
 {
-	set_bit(FSCACHE_IOERROR, &cache->flags);
-
-	printk(KERN_ERR "FS-Cache: Cache %s stopped due to I/O error\n",
-	       cache->ops->name);
+	if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags))
+		printk(KERN_ERR "FS-Cache:"
+		       " Cache '%s' stopped due to I/O error\n",
+		       cache->ops->name);
 }
 EXPORT_SYMBOL(fscache_io_error);
 
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 990535071a8a..8dcb114758e3 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -370,6 +370,66 @@ cant_attach_object:
 }
 
 /*
+ * Invalidate an object.  Callable with spinlocks held.
+ */
+void __fscache_invalidate(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+
+	_enter("{%s}", cookie->def->name);
+
+	fscache_stat(&fscache_n_invalidates);
+
+	/* Only permit invalidation of data files.  Invalidating an index will
+	 * require the caller to release all its attachments to the tree rooted
+	 * there, and if it's doing that, it may as well just retire the
+	 * cookie.
+	 */
+	ASSERTCMP(cookie->def->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE);
+
+	/* We will be updating the cookie too. */
+	BUG_ON(!cookie->def->get_aux);
+
+	/* If there's an object, we tell the object state machine to handle the
+	 * invalidation on our behalf, otherwise there's nothing to do.
+	 */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		spin_lock(&cookie->lock);
+
+		if (!hlist_empty(&cookie->backing_objects) &&
+		    !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING,
+				      &cookie->flags)) {
+			object = hlist_entry(cookie->backing_objects.first,
+					     struct fscache_object,
+					     cookie_link);
+			if (object->state < FSCACHE_OBJECT_DYING)
+				fscache_raise_event(
+					object, FSCACHE_OBJECT_EV_INVALIDATE);
+		}
+
+		spin_unlock(&cookie->lock);
+	}
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_invalidate);
+
+/*
+ * Wait for object invalidation to complete.
+ */
+void __fscache_wait_on_invalidate(struct fscache_cookie *cookie)
+{
+	_enter("%p", cookie);
+
+	wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING,
+		    fscache_wait_bit_interruptible,
+		    TASK_UNINTERRUPTIBLE);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_wait_on_invalidate);
+
+/*
  * update the index entries backing a cookie
  */
 void __fscache_update_cookie(struct fscache_cookie *cookie)
@@ -442,16 +502,34 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 
 	event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE;
 
+try_again:
 	spin_lock(&cookie->lock);
 
 	/* break links with all the active objects */
 	while (!hlist_empty(&cookie->backing_objects)) {
+		int n_reads;
 		object = hlist_entry(cookie->backing_objects.first,
 				     struct fscache_object,
 				     cookie_link);
 
 		_debug("RELEASE OBJ%x", object->debug_id);
 
+		set_bit(FSCACHE_COOKIE_WAITING_ON_READS, &cookie->flags);
+		n_reads = atomic_read(&object->n_reads);
+		if (n_reads) {
+			int n_ops = object->n_ops;
+			int n_in_progress = object->n_in_progress;
+			spin_unlock(&cookie->lock);
+			printk(KERN_ERR "FS-Cache:"
+			       " Cookie '%s' still has %d outstanding reads (%d,%d)\n",
+			       cookie->def->name,
+			       n_reads, n_ops, n_in_progress);
+			wait_on_bit(&cookie->flags, FSCACHE_COOKIE_WAITING_ON_READS,
+				    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			printk("Wait finished\n");
+			goto try_again;
+		}
+
 		/* detach each cache object from the object cookie */
 		spin_lock(&object->lock);
 		hlist_del_init(&object->cookie_link);
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index f6aad48d38a8..ee38fef4be51 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -121,12 +121,19 @@ 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 int fscache_cancel_op(struct fscache_operation *,
+			     void (*)(struct fscache_operation *));
+extern void fscache_cancel_all_ops(struct fscache_object *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
 extern void fscache_operation_gc(struct work_struct *);
 
 /*
+ * page.c
+ */
+extern void fscache_invalidate_writes(struct fscache_cookie *);
+
+/*
  * proc.c
  */
 #ifdef CONFIG_PROC_FS
@@ -194,6 +201,7 @@ extern atomic_t fscache_n_store_vmscan_not_storing;
 extern atomic_t fscache_n_store_vmscan_gone;
 extern atomic_t fscache_n_store_vmscan_busy;
 extern atomic_t fscache_n_store_vmscan_cancelled;
+extern atomic_t fscache_n_store_vmscan_wait;
 
 extern atomic_t fscache_n_marks;
 extern atomic_t fscache_n_uncaches;
@@ -205,6 +213,9 @@ extern atomic_t fscache_n_acquires_ok;
 extern atomic_t fscache_n_acquires_nobufs;
 extern atomic_t fscache_n_acquires_oom;
 
+extern atomic_t fscache_n_invalidates;
+extern atomic_t fscache_n_invalidates_run;
+
 extern atomic_t fscache_n_updates;
 extern atomic_t fscache_n_updates_null;
 extern atomic_t fscache_n_updates_run;
@@ -237,6 +248,7 @@ extern atomic_t fscache_n_cop_alloc_object;
 extern atomic_t fscache_n_cop_lookup_object;
 extern atomic_t fscache_n_cop_lookup_complete;
 extern atomic_t fscache_n_cop_grab_object;
+extern atomic_t fscache_n_cop_invalidate_object;
 extern atomic_t fscache_n_cop_update_object;
 extern atomic_t fscache_n_cop_drop_object;
 extern atomic_t fscache_n_cop_put_object;
@@ -278,6 +290,7 @@ extern const struct file_operations fscache_stats_fops;
 static inline void fscache_raise_event(struct fscache_object *object,
 				       unsigned event)
 {
+	BUG_ON(event >= NR_FSCACHE_OBJECT_EVENTS);
 	if (!test_and_set_bit(event, &object->events) &&
 	    test_bit(event, &object->event_mask))
 		fscache_enqueue_object(object);
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index ebe29c581380..f27c89d17885 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -245,7 +245,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v)
 		   obj->n_in_progress,
 		   obj->n_exclusive,
 		   atomic_read(&obj->n_reads),
-		   obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK,
+		   obj->event_mask,
 		   obj->events,
 		   obj->flags,
 		   work_busy(&obj->work));
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index b6b897c550ac..50d41c180211 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -14,6 +14,7 @@
 
 #define FSCACHE_DEBUG_LEVEL COOKIE
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
@@ -22,6 +23,7 @@ const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
 	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
 	[FSCACHE_OBJECT_AVAILABLE]	= "OBJECT_AVAILABLE",
 	[FSCACHE_OBJECT_ACTIVE]		= "OBJECT_ACTIVE",
+	[FSCACHE_OBJECT_INVALIDATING]	= "OBJECT_INVALIDATING",
 	[FSCACHE_OBJECT_UPDATING]	= "OBJECT_UPDATING",
 	[FSCACHE_OBJECT_DYING]		= "OBJECT_DYING",
 	[FSCACHE_OBJECT_LC_DYING]	= "OBJECT_LC_DYING",
@@ -39,6 +41,7 @@ const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = {
 	[FSCACHE_OBJECT_CREATING]	= "CRTN",
 	[FSCACHE_OBJECT_AVAILABLE]	= "AVBL",
 	[FSCACHE_OBJECT_ACTIVE]		= "ACTV",
+	[FSCACHE_OBJECT_INVALIDATING]	= "INVL",
 	[FSCACHE_OBJECT_UPDATING]	= "UPDT",
 	[FSCACHE_OBJECT_DYING]		= "DYNG",
 	[FSCACHE_OBJECT_LC_DYING]	= "LCDY",
@@ -54,6 +57,7 @@ static void fscache_put_object(struct fscache_object *);
 static void fscache_initialise_object(struct fscache_object *);
 static void fscache_lookup_object(struct fscache_object *);
 static void fscache_object_available(struct fscache_object *);
+static void fscache_invalidate_object(struct fscache_object *);
 static void fscache_release_object(struct fscache_object *);
 static void fscache_withdraw_object(struct fscache_object *);
 static void fscache_enqueue_dependents(struct fscache_object *);
@@ -79,6 +83,15 @@ static inline void fscache_done_parent_op(struct fscache_object *object)
 }
 
 /*
+ * Notify netfs of invalidation completion.
+ */
+static inline void fscache_invalidation_complete(struct fscache_cookie *cookie)
+{
+	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+}
+
+/*
  * process events that have been sent to an object's state machine
  * - initiates parent lookup
  * - does object lookup
@@ -90,6 +103,7 @@ static void fscache_object_state_machine(struct fscache_object *object)
 {
 	enum fscache_object_state new_state;
 	struct fscache_cookie *cookie;
+	int event;
 
 	ASSERT(object != NULL);
 
@@ -101,7 +115,8 @@ static void fscache_object_state_machine(struct fscache_object *object)
 		/* wait for the parent object to become ready */
 	case FSCACHE_OBJECT_INIT:
 		object->event_mask =
-			ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+			FSCACHE_OBJECT_EVENTS_MASK &
+			~(1 << FSCACHE_OBJECT_EV_CLEARED);
 		fscache_initialise_object(object);
 		goto done;
 
@@ -125,6 +140,16 @@ static void fscache_object_state_machine(struct fscache_object *object)
 	case FSCACHE_OBJECT_ACTIVE:
 		goto active_transit;
 
+		/* Invalidate an object on disk */
+	case FSCACHE_OBJECT_INVALIDATING:
+		clear_bit(FSCACHE_OBJECT_EV_INVALIDATE, &object->events);
+		fscache_stat(&fscache_n_invalidates_run);
+		fscache_stat(&fscache_n_cop_invalidate_object);
+		fscache_invalidate_object(object);
+		fscache_stat_d(&fscache_n_cop_invalidate_object);
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+		goto active_transit;
+
 		/* update the object metadata on disk */
 	case FSCACHE_OBJECT_UPDATING:
 		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
@@ -251,13 +276,17 @@ static void fscache_object_state_machine(struct fscache_object *object)
 
 	/* determine the transition from a lookup state */
 lookup_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 	case FSCACHE_OBJECT_EV_RETIRE:
 	case FSCACHE_OBJECT_EV_RELEASE:
 	case FSCACHE_OBJECT_EV_ERROR:
 		new_state = FSCACHE_OBJECT_LC_DYING;
 		goto change_state;
+	case FSCACHE_OBJECT_EV_INVALIDATE:
+		new_state = FSCACHE_OBJECT_INVALIDATING;
+		goto change_state;
 	case FSCACHE_OBJECT_EV_REQUEUE:
 		goto done;
 	case -1:
@@ -268,13 +297,17 @@ lookup_transit:
 
 	/* determine the transition from an active state */
 active_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 	case FSCACHE_OBJECT_EV_RETIRE:
 	case FSCACHE_OBJECT_EV_RELEASE:
 	case FSCACHE_OBJECT_EV_ERROR:
 		new_state = FSCACHE_OBJECT_DYING;
 		goto change_state;
+	case FSCACHE_OBJECT_EV_INVALIDATE:
+		new_state = FSCACHE_OBJECT_INVALIDATING;
+		goto change_state;
 	case FSCACHE_OBJECT_EV_UPDATE:
 		new_state = FSCACHE_OBJECT_UPDATING;
 		goto change_state;
@@ -287,7 +320,8 @@ active_transit:
 
 	/* determine the transition from a terminal state */
 terminal_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 		new_state = FSCACHE_OBJECT_WITHDRAWING;
 		goto change_state;
@@ -320,8 +354,8 @@ done:
 
 unsupported_event:
 	printk(KERN_ERR "FS-Cache:"
-	       " Unsupported event %lx [mask %lx] in state %s\n",
-	       object->events, object->event_mask,
+	       " Unsupported event %d [%lx/%lx] in state %s\n",
+	       event, object->events, object->event_mask,
 	       fscache_object_states[object->state]);
 	BUG();
 }
@@ -587,8 +621,6 @@ static void fscache_object_available(struct fscache_object *object)
 	if (object->n_in_progress == 0) {
 		if (object->n_ops > 0) {
 			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
-			ASSERTIF(object->n_ops > object->n_obj_ops,
-				 !list_empty(&object->pending_ops));
 			fscache_start_operations(object);
 		} else {
 			ASSERT(list_empty(&object->pending_ops));
@@ -681,6 +713,7 @@ static void fscache_withdraw_object(struct fscache_object *object)
 		if (object->cookie == cookie) {
 			hlist_del_init(&object->cookie_link);
 			object->cookie = NULL;
+			fscache_invalidation_complete(cookie);
 			detached = true;
 		}
 		spin_unlock(&cookie->lock);
@@ -890,3 +923,55 @@ enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
 	return result;
 }
 EXPORT_SYMBOL(fscache_check_aux);
+
+/*
+ * Asynchronously invalidate an object.
+ */
+static void fscache_invalidate_object(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	/* Reject any new read/write ops and abort any that are pending. */
+	fscache_invalidate_writes(cookie);
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	fscache_cancel_all_ops(object);
+
+	/* Now we have to wait for in-progress reads and writes */
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op) {
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+		_leave(" [ENOMEM]");
+		return;
+	}
+
+	fscache_operation_init(op, object->cache->ops->invalidate_object, NULL);
+	op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE);
+
+	spin_lock(&cookie->lock);
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto submit_op_failed;
+	spin_unlock(&cookie->lock);
+	fscache_put_operation(op);
+
+	/* Once we've completed the invalidation, we know there will be no data
+	 * stored in the cache and thus we can reinstate the data-check-skip
+	 * optimisation.
+	 */
+	set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* We can allow read and write requests to come in once again.  They'll
+	 * queue up behind our exclusive invalidation operation.
+	 */
+	fscache_invalidation_complete(cookie);
+	_leave("");
+	return;
+
+submit_op_failed:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+	_leave(" [EIO]");
+}
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 30afdfa7aec7..762a9ec4ffa4 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -37,6 +37,7 @@ void fscache_enqueue_operation(struct fscache_operation *op)
 	ASSERT(op->processor != NULL);
 	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
 
 	fscache_stat(&fscache_n_op_enqueue);
 	switch (op->flags & FSCACHE_OP_TYPE) {
@@ -64,6 +65,9 @@ EXPORT_SYMBOL(fscache_enqueue_operation);
 static void fscache_run_op(struct fscache_object *object,
 			   struct fscache_operation *op)
 {
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+
+	op->state = FSCACHE_OP_ST_IN_PROGRESS;
 	object->n_in_progress++;
 	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
 		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
@@ -84,18 +88,21 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 
 	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
 
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
 	spin_lock(&object->lock);
 	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
 	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
 	ASSERT(list_empty(&op->pend_link));
 
-	ret = -ENOBUFS;
+	op->state = FSCACHE_OP_ST_PENDING;
 	if (fscache_object_is_active(object)) {
 		op->object = object;
 		object->n_ops++;
 		object->n_exclusive++;	/* reads and writes must wait */
 
-		if (object->n_ops > 1) {
+		if (object->n_in_progress > 0) {
 			atomic_inc(&op->usage);
 			list_add_tail(&op->pend_link, &object->pending_ops);
 			fscache_stat(&fscache_n_op_pend);
@@ -121,8 +128,11 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		fscache_stat(&fscache_n_op_pend);
 		ret = 0;
 	} else {
-		/* not allowed to submit ops in any other state */
-		BUG();
+		/* If we're in any other state, there must have been an I/O
+		 * error of some nature.
+		 */
+		ASSERT(test_bit(FSCACHE_IOERROR, &object->cache->flags));
+		ret = -EIO;
 	}
 
 	spin_unlock(&object->lock);
@@ -186,6 +196,7 @@ int fscache_submit_op(struct fscache_object *object,
 	_enter("{OBJ%x OP%x},{%u}",
 	       object->debug_id, op->debug_id, atomic_read(&op->usage));
 
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
 	spin_lock(&object->lock);
@@ -196,6 +207,7 @@ int fscache_submit_op(struct fscache_object *object,
 	ostate = object->state;
 	smp_rmb();
 
+	op->state = FSCACHE_OP_ST_PENDING;
 	if (fscache_object_is_active(object)) {
 		op->object = object;
 		object->n_ops++;
@@ -225,12 +237,15 @@ int fscache_submit_op(struct fscache_object *object,
 		   object->state == FSCACHE_OBJECT_LC_DYING ||
 		   object->state == FSCACHE_OBJECT_WITHDRAWING) {
 		fscache_stat(&fscache_n_op_rejected);
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
 		fscache_report_unexpected_submission(object, op, ostate);
 		ASSERT(!fscache_object_is_active(object));
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else {
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	}
 
@@ -283,20 +298,28 @@ void fscache_start_operations(struct fscache_object *object)
 /*
  * cancel an operation that's pending on an object
  */
-int fscache_cancel_op(struct fscache_operation *op)
+int fscache_cancel_op(struct fscache_operation *op,
+		      void (*do_cancel)(struct fscache_operation *))
 {
 	struct fscache_object *object = op->object;
 	int ret;
 
 	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
 
+	ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING);
+	ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
 	spin_lock(&object->lock);
 
 	ret = -EBUSY;
-	if (!list_empty(&op->pend_link)) {
+	if (op->state == FSCACHE_OP_ST_PENDING) {
+		ASSERT(!list_empty(&op->pend_link));
 		fscache_stat(&fscache_n_op_cancelled);
 		list_del_init(&op->pend_link);
-		object->n_ops--;
+		if (do_cancel)
+			do_cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 			object->n_exclusive--;
 		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
@@ -311,6 +334,70 @@ int fscache_cancel_op(struct fscache_operation *op)
 }
 
 /*
+ * Cancel all pending operations on an object
+ */
+void fscache_cancel_all_ops(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+
+	_enter("OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->pending_ops)) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+		fscache_stat(&fscache_n_op_cancelled);
+		list_del_init(&op->pend_link);
+
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		fscache_put_operation(op);
+		cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+
+/*
+ * Record the completion or cancellation of an in-progress operation.
+ */
+void fscache_op_complete(struct fscache_operation *op, bool cancelled)
+{
+	struct fscache_object *object = op->object;
+
+	_enter("OBJ%x", object->debug_id);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+	ASSERTCMP(object->n_in_progress, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_exclusive, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_in_progress, ==, 1);
+
+	spin_lock(&object->lock);
+
+	op->state = cancelled ?
+		FSCACHE_OP_ST_CANCELLED : FSCACHE_OP_ST_COMPLETE;
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+		object->n_exclusive--;
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_op_complete);
+
+/*
  * release an operation
  * - queues pending ops if this is the last in-progress op
  */
@@ -328,8 +415,9 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 
 	_debug("PUT OP");
-	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
-		BUG();
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_COMPLETE,
+		    op->state, ==, FSCACHE_OP_ST_CANCELLED);
+	op->state = FSCACHE_OP_ST_DEAD;
 
 	fscache_stat(&fscache_n_op_release);
 
@@ -340,8 +428,14 @@ 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);
+	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) {
+		if (atomic_dec_and_test(&object->n_reads)) {
+			clear_bit(FSCACHE_COOKIE_WAITING_ON_READS,
+				  &object->cookie->flags);
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_WAITING_ON_READS);
+		}
+	}
 
 	/* now... we may get called with the object spinlock held, so we
 	 * complete the cleanup here only if we can immediately acquire the
@@ -359,16 +453,6 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 	}
 
-	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
-		ASSERTCMP(object->n_exclusive, >, 0);
-		object->n_exclusive--;
-	}
-
-	ASSERTCMP(object->n_in_progress, >, 0);
-	object->n_in_progress--;
-	if (object->n_in_progress == 0)
-		fscache_start_operations(object);
-
 	ASSERTCMP(object->n_ops, >, 0);
 	object->n_ops--;
 	if (object->n_ops == 0)
@@ -407,23 +491,14 @@ void fscache_operation_gc(struct work_struct *work)
 		spin_unlock(&cache->op_gc_list_lock);
 
 		object = op->object;
+		spin_lock(&object->lock);
 
 		_debug("GC DEFERRED REL OBJ%x OP%x",
 		       object->debug_id, op->debug_id);
 		fscache_stat(&fscache_n_op_gc);
 
 		ASSERTCMP(atomic_read(&op->usage), ==, 0);
-
-		spin_lock(&object->lock);
-		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
-			ASSERTCMP(object->n_exclusive, >, 0);
-			object->n_exclusive--;
-		}
-
-		ASSERTCMP(object->n_in_progress, >, 0);
-		object->n_in_progress--;
-		if (object->n_in_progress == 0)
-			fscache_start_operations(object);
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD);
 
 		ASSERTCMP(object->n_ops, >, 0);
 		object->n_ops--;
@@ -431,6 +506,7 @@ void fscache_operation_gc(struct work_struct *work)
 			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
 
 		spin_unlock(&object->lock);
+		kfree(op);
 
 	} while (count++ < 20);
 
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3f7a59bfa7ad..ff000e52072d 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -56,6 +56,7 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
 
 	_enter("%p,%p,%x", cookie, page, gfp);
 
+try_again:
 	rcu_read_lock();
 	val = radix_tree_lookup(&cookie->stores, page->index);
 	if (!val) {
@@ -104,11 +105,19 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
 	return true;
 
 page_busy:
-	/* we might want to wait here, but that could deadlock the allocator as
-	 * the work threads writing to the cache may all end up sleeping
-	 * on memory allocation */
-	fscache_stat(&fscache_n_store_vmscan_busy);
-	return false;
+	/* We will wait here if we're allowed to, but that could deadlock the
+	 * allocator as the work threads writing to the cache may all end up
+	 * sleeping on memory allocation, so we may need to impose a timeout
+	 * too. */
+	if (!(gfp & __GFP_WAIT)) {
+		fscache_stat(&fscache_n_store_vmscan_busy);
+		return false;
+	}
+
+	fscache_stat(&fscache_n_store_vmscan_wait);
+	__fscache_wait_on_page_write(cookie, page);
+	gfp &= ~__GFP_WAIT;
+	goto try_again;
 }
 EXPORT_SYMBOL(__fscache_maybe_release_page);
 
@@ -162,6 +171,7 @@ static void fscache_attr_changed_op(struct fscache_operation *op)
 			fscache_abort_object(object);
 	}
 
+	fscache_op_complete(op, true);
 	_leave("");
 }
 
@@ -223,6 +233,8 @@ static void fscache_release_retrieval_op(struct fscache_operation *_op)
 
 	_enter("{OP%x}", op->op.debug_id);
 
+	ASSERTCMP(op->n_pages, ==, 0);
+
 	fscache_hist(fscache_retrieval_histogram, op->start_time);
 	if (op->context)
 		fscache_put_context(op->op.object->cookie, op->context);
@@ -291,6 +303,17 @@ static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
 }
 
 /*
+ * Handle cancellation of a pending retrieval op
+ */
+static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	op->n_pages = 0;
+}
+
+/*
  * wait for an object to become active (or dead)
  */
 static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
@@ -307,8 +330,8 @@ static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
 	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);
+			TASK_INTERRUPTIBLE) != 0) {
+		ret = fscache_cancel_op(&op->op, fscache_do_cancel_retrieval);
 		if (ret == 0)
 			return -ERESTARTSYS;
 
@@ -320,7 +343,14 @@ static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
 	_debug("<<< GO");
 
 check_if_dead:
+	if (op->op.state == FSCACHE_OP_ST_CANCELLED) {
+		fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [cancelled]");
+		return -ENOBUFS;
+	}
 	if (unlikely(fscache_object_is_dead(object))) {
+		pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->op.state);
+		fscache_cancel_op(&op->op, fscache_do_cancel_retrieval);
 		fscache_stat(stat_object_dead);
 		return -ENOBUFS;
 	}
@@ -353,6 +383,11 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 	if (hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(page, !=, NULL);
 
@@ -364,6 +399,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
 	}
+	op->n_pages = 1;
 
 	spin_lock(&cookie->lock);
 
@@ -375,10 +411,10 @@ 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);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_retrieval_ops);
@@ -425,6 +461,8 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	kfree(op);
@@ -472,6 +510,11 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	if (hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(*nr_pages, >, 0);
 	ASSERT(!list_empty(pages));
@@ -482,6 +525,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	op = fscache_alloc_retrieval(mapping, end_io_func, context);
 	if (!op)
 		return -ENOMEM;
+	op->n_pages = *nr_pages;
 
 	spin_lock(&cookie->lock);
 
@@ -491,10 +535,10 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 			     struct fscache_object, cookie_link);
 
 	atomic_inc(&object->n_reads);
-	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_retrieval_ops);
@@ -541,6 +585,8 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	kfree(op);
@@ -577,12 +623,18 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(page, !=, NULL);
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	if (fscache_wait_for_deferred_lookup(cookie) < 0)
 		return -ERESTARTSYS;
 
 	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
 	if (!op)
 		return -ENOMEM;
+	op->n_pages = 1;
 
 	spin_lock(&cookie->lock);
 
@@ -658,9 +710,27 @@ static void fscache_write_op(struct fscache_operation *_op)
 	spin_lock(&object->lock);
 	cookie = object->cookie;
 
-	if (!fscache_object_is_active(object) || !cookie) {
+	if (!fscache_object_is_active(object)) {
+		/* If we get here, then the on-disk cache object likely longer
+		 * exists, so we should just cancel this write operation.
+		 */
+		spin_unlock(&object->lock);
+		fscache_op_complete(&op->op, false);
+		_leave(" [inactive]");
+		return;
+	}
+
+	if (!cookie) {
+		/* If we get here, then the cookie belonging to the object was
+		 * detached, probably by the cookie being withdrawn due to
+		 * memory pressure, which means that the pages we might write
+		 * to the cache from no longer exist - therefore, we can just
+		 * cancel this write operation.
+		 */
 		spin_unlock(&object->lock);
-		_leave("");
+		fscache_op_complete(&op->op, false);
+		_leave(" [cancel] op{f=%lx s=%u} obj{s=%u f=%lx}",
+		       _op->flags, _op->state, object->state, object->flags);
 		return;
 	}
 
@@ -696,6 +766,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 	fscache_end_page_write(object, page);
 	if (ret < 0) {
 		fscache_abort_object(object);
+		fscache_op_complete(&op->op, true);
 	} else {
 		fscache_enqueue_operation(&op->op);
 	}
@@ -710,6 +781,38 @@ superseded:
 	spin_unlock(&cookie->stores_lock);
 	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 	spin_unlock(&object->lock);
+	fscache_op_complete(&op->op, true);
+	_leave("");
+}
+
+/*
+ * Clear the pages pending writing for invalidation
+ */
+void fscache_invalidate_writes(struct fscache_cookie *cookie)
+{
+	struct page *page;
+	void *results[16];
+	int n, i;
+
+	_enter("");
+
+	while (spin_lock(&cookie->stores_lock),
+	       n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0,
+					      ARRAY_SIZE(results),
+					      FSCACHE_COOKIE_PENDING_TAG),
+	       n > 0) {
+		for (i = n - 1; i >= 0; i--) {
+			page = results[i];
+			radix_tree_delete(&cookie->stores, page->index);
+		}
+
+		spin_unlock(&cookie->stores_lock);
+
+		for (i = n - 1; i >= 0; i--)
+			page_cache_release(results[i]);
+	}
+
+	spin_unlock(&cookie->stores_lock);
 	_leave("");
 }
 
@@ -759,7 +862,12 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_stores);
 
-	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
+	op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY);
 	if (!op)
 		goto nomem;
 
@@ -915,6 +1023,40 @@ done:
 EXPORT_SYMBOL(__fscache_uncache_page);
 
 /**
+ * fscache_mark_page_cached - Mark a page as being cached
+ * @op: The retrieval op pages are being marked for
+ * @page: The page to be marked
+ *
+ * Mark a netfs page as being cached.  After this is called, the netfs
+ * must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_inc(&fscache_n_marks);
+#endif
+
+	_debug("- mark %p{%lx}", page, page->index);
+	if (TestSetPageFsCache(page)) {
+		static bool once_only;
+		if (!once_only) {
+			once_only = true;
+			printk(KERN_WARNING "FS-Cache:"
+			       " Cookie type %s marked page %lx"
+			       " multiple times\n",
+			       cookie->def->name, page->index);
+		}
+	}
+
+	if (cookie->def->mark_page_cached)
+		cookie->def->mark_page_cached(cookie->netfs_data,
+					      op->mapping, page);
+}
+EXPORT_SYMBOL(fscache_mark_page_cached);
+
+/**
  * fscache_mark_pages_cached - Mark pages as being cached
  * @op: The retrieval op pages are being marked for
  * @pagevec: The pages to be marked
@@ -925,32 +1067,11 @@ EXPORT_SYMBOL(__fscache_uncache_page);
 void fscache_mark_pages_cached(struct fscache_retrieval *op,
 			       struct pagevec *pagevec)
 {
-	struct fscache_cookie *cookie = op->op.object->cookie;
 	unsigned long loop;
 
-#ifdef CONFIG_FSCACHE_STATS
-	atomic_add(pagevec->nr, &fscache_n_marks);
-#endif
-
-	for (loop = 0; loop < pagevec->nr; loop++) {
-		struct page *page = pagevec->pages[loop];
-
-		_debug("- mark %p{%lx}", page, page->index);
-		if (TestSetPageFsCache(page)) {
-			static bool once_only;
-			if (!once_only) {
-				once_only = true;
-				printk(KERN_WARNING "FS-Cache:"
-				       " Cookie type %s marked page %lx"
-				       " multiple times\n",
-				       cookie->def->name, page->index);
-			}
-		}
-	}
+	for (loop = 0; loop < pagevec->nr; loop++)
+		fscache_mark_page_cached(op, pagevec->pages[loop]);
 
-	if (cookie->def->mark_pages_cached)
-		cookie->def->mark_pages_cached(cookie->netfs_data,
-					       op->mapping, pagevec);
 	pagevec_reinit(pagevec);
 }
 EXPORT_SYMBOL(fscache_mark_pages_cached);
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190d537f..8179e8bc4a3d 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -69,6 +69,7 @@ atomic_t fscache_n_store_vmscan_not_storing;
 atomic_t fscache_n_store_vmscan_gone;
 atomic_t fscache_n_store_vmscan_busy;
 atomic_t fscache_n_store_vmscan_cancelled;
+atomic_t fscache_n_store_vmscan_wait;
 
 atomic_t fscache_n_marks;
 atomic_t fscache_n_uncaches;
@@ -80,6 +81,9 @@ atomic_t fscache_n_acquires_ok;
 atomic_t fscache_n_acquires_nobufs;
 atomic_t fscache_n_acquires_oom;
 
+atomic_t fscache_n_invalidates;
+atomic_t fscache_n_invalidates_run;
+
 atomic_t fscache_n_updates;
 atomic_t fscache_n_updates_null;
 atomic_t fscache_n_updates_run;
@@ -112,6 +116,7 @@ atomic_t fscache_n_cop_alloc_object;
 atomic_t fscache_n_cop_lookup_object;
 atomic_t fscache_n_cop_lookup_complete;
 atomic_t fscache_n_cop_grab_object;
+atomic_t fscache_n_cop_invalidate_object;
 atomic_t fscache_n_cop_update_object;
 atomic_t fscache_n_cop_drop_object;
 atomic_t fscache_n_cop_put_object;
@@ -168,6 +173,10 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_object_created),
 		   atomic_read(&fscache_n_object_lookups_timed_out));
 
+	seq_printf(m, "Invals : n=%u run=%u\n",
+		   atomic_read(&fscache_n_invalidates),
+		   atomic_read(&fscache_n_invalidates_run));
+
 	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
 		   atomic_read(&fscache_n_updates),
 		   atomic_read(&fscache_n_updates_null),
@@ -224,11 +233,12 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_store_radix_deletes),
 		   atomic_read(&fscache_n_store_pages_over_limit));
 
-	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n",
+	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u wt=%u\n",
 		   atomic_read(&fscache_n_store_vmscan_not_storing),
 		   atomic_read(&fscache_n_store_vmscan_gone),
 		   atomic_read(&fscache_n_store_vmscan_busy),
-		   atomic_read(&fscache_n_store_vmscan_cancelled));
+		   atomic_read(&fscache_n_store_vmscan_cancelled),
+		   atomic_read(&fscache_n_store_vmscan_wait));
 
 	seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u rej=%u\n",
 		   atomic_read(&fscache_n_op_pend),
@@ -246,7 +256,8 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   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",
+	seq_printf(m, "CacheOp: inv=%d upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+		   atomic_read(&fscache_n_cop_invalidate_object),
 		   atomic_read(&fscache_n_cop_update_object),
 		   atomic_read(&fscache_n_cop_drop_object),
 		   atomic_read(&fscache_n_cop_put_object),