diff --git a/drivers/firewire/fw-card.c b/drivers/firewire/fw-card.c
index 1332b66ae0b395fd485c9ec9671db33e1289f72a..da873d795aad94bccf9e88a58a4b9bde9821daf1 100644
--- a/drivers/firewire/fw-card.c
+++ b/drivers/firewire/fw-card.c
@@ -16,12 +16,15 @@
  * Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  */
 
-#include <linux/module.h>
-#include <linux/errno.h>
+#include <linux/completion.h>
+#include <linux/crc-itu-t.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/kref.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/crc-itu-t.h>
+
 #include "fw-transaction.h"
 #include "fw-topology.h"
 #include "fw-device.h"
@@ -396,7 +399,6 @@ fw_card_initialize(struct fw_card *card, const struct fw_card_driver *driver,
 {
 	static atomic_t index = ATOMIC_INIT(-1);
 
-	atomic_set(&card->device_count, 0);
 	card->index = atomic_inc_return(&index);
 	card->driver = driver;
 	card->device = device;
@@ -405,6 +407,8 @@ fw_card_initialize(struct fw_card *card, const struct fw_card_driver *driver,
 	card->color = 0;
 	card->broadcast_channel = BROADCAST_CHANNEL_INITIAL;
 
+	kref_init(&card->kref);
+	init_completion(&card->done);
 	INIT_LIST_HEAD(&card->transaction_list);
 	spin_lock_init(&card->lock);
 	setup_timer(&card->flush_timer,
@@ -506,6 +510,14 @@ static struct fw_card_driver dummy_driver = {
 	.enable_phys_dma = dummy_enable_phys_dma,
 };
 
+void
+fw_card_release(struct kref *kref)
+{
+	struct fw_card *card = container_of(kref, struct fw_card, kref);
+
+	complete(&card->done);
+}
+
 void
 fw_core_remove_card(struct fw_card *card)
 {
@@ -521,12 +533,10 @@ fw_core_remove_card(struct fw_card *card)
 	card->driver = &dummy_driver;
 
 	fw_destroy_nodes(card);
-	/*
-	 * Wait for all device workqueue jobs to finish.  Otherwise the
-	 * firewire-core module could be unloaded before the jobs ran.
-	 */
-	while (atomic_read(&card->device_count) > 0)
-		msleep(100);
+
+	/* Wait for all users, especially device workqueue jobs, to finish. */
+	fw_card_put(card);
+	wait_for_completion(&card->done);
 
 	cancel_delayed_work_sync(&card->work);
 	fw_flush_transactions(card);
diff --git a/drivers/firewire/fw-device.c b/drivers/firewire/fw-device.c
index d9c8daf7ae7d798b29a728464e1365c2fbe10b22..0855fb5568e806cf92546e466b73a702e9f55de6 100644
--- a/drivers/firewire/fw-device.c
+++ b/drivers/firewire/fw-device.c
@@ -168,7 +168,7 @@ static void fw_device_release(struct device *dev)
 	fw_node_put(device->node);
 	kfree(device->config_rom);
 	kfree(device);
-	atomic_dec(&card->device_count);
+	fw_card_put(card);
 }
 
 int fw_device_enable_phys_dma(struct fw_device *device)
@@ -946,8 +946,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		 */
 		device_initialize(&device->device);
 		atomic_set(&device->state, FW_DEVICE_INITIALIZING);
-		atomic_inc(&card->device_count);
-		device->card = card;
+		device->card = fw_card_get(card);
 		device->node = fw_node_get(node);
 		device->node_id = node->node_id;
 		device->generation = card->generation;
diff --git a/drivers/firewire/fw-transaction.h b/drivers/firewire/fw-transaction.h
index 219094e38542817d8cd31c701530c365b5007d8b..2ae1b0d6cb7bdfaa6929ccc06a00d63501acebcf 100644
--- a/drivers/firewire/fw-transaction.h
+++ b/drivers/firewire/fw-transaction.h
@@ -19,14 +19,15 @@
 #ifndef __fw_transaction_h
 #define __fw_transaction_h
 
+#include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/firewire-constants.h>
+#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/spinlock_types.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
-#include <asm/atomic.h>
 
 #define TCODE_IS_READ_REQUEST(tcode)	(((tcode) & ~1) == 4)
 #define TCODE_IS_BLOCK_PACKET(tcode)	(((tcode) &  1) != 0)
@@ -219,7 +220,8 @@ extern struct bus_type fw_bus_type;
 struct fw_card {
 	const struct fw_card_driver *driver;
 	struct device *device;
-	atomic_t device_count;
+	struct kref kref;
+	struct completion done;
 
 	int node_id;
 	int generation;
@@ -260,6 +262,20 @@ struct fw_card {
 	int bm_generation;
 };
 
+static inline struct fw_card *fw_card_get(struct fw_card *card)
+{
+	kref_get(&card->kref);
+
+	return card;
+}
+
+void fw_card_release(struct kref *kref);
+
+static inline void fw_card_put(struct fw_card *card)
+{
+	kref_put(&card->kref, fw_card_release);
+}
+
 /*
  * The iso packet format allows for an immediate header/payload part
  * stored in 'header' immediately after the packet info plus an