diff --git a/drivers/firewire/fw-card.c b/drivers/firewire/fw-card.c
index 0aeab3218bb6d6b8c503b2f2386133e611f4a5f7..3e9719948a8e7817658496929115fe52bda45473 100644
--- a/drivers/firewire/fw-card.c
+++ b/drivers/firewire/fw-card.c
@@ -510,9 +510,11 @@ fw_core_remove_card(struct fw_card *card)
 	/* Set up the dummy driver. */
 	card->driver = &dummy_driver;
 
-	fw_flush_transactions(card);
-
 	fw_destroy_nodes(card);
+	flush_scheduled_work();
+
+	fw_flush_transactions(card);
+	del_timer_sync(&card->flush_timer);
 
 	fw_card_put(card);
 }
diff --git a/drivers/firewire/fw-sbp2.c b/drivers/firewire/fw-sbp2.c
index ba816ef6def1b66b97a250a5b70a7d719fbee367..238730f75db197f857636ef224736d205cd2b571 100644
--- a/drivers/firewire/fw-sbp2.c
+++ b/drivers/firewire/fw-sbp2.c
@@ -159,6 +159,7 @@ struct sbp2_pointer {
 
 struct sbp2_orb {
 	struct fw_transaction t;
+	struct kref kref;
 	dma_addr_t request_bus;
 	int rcode;
 	struct sbp2_pointer pointer;
@@ -279,6 +280,14 @@ static const struct {
 	}
 };
 
+static void
+free_orb(struct kref *kref)
+{
+	struct sbp2_orb *orb = container_of(kref, struct sbp2_orb, kref);
+
+	kfree(orb);
+}
+
 static void
 sbp2_status_write(struct fw_card *card, struct fw_request *request,
 		  int tcode, int destination, int source,
@@ -312,8 +321,8 @@ sbp2_status_write(struct fw_card *card, struct fw_request *request,
 	spin_lock_irqsave(&card->lock, flags);
 	list_for_each_entry(orb, &sd->orb_list, link) {
 		if (STATUS_GET_ORB_HIGH(status) == 0 &&
-		    STATUS_GET_ORB_LOW(status) == orb->request_bus &&
-		    orb->rcode == RCODE_COMPLETE) {
+		    STATUS_GET_ORB_LOW(status) == orb->request_bus) {
+			orb->rcode = RCODE_COMPLETE;
 			list_del(&orb->link);
 			break;
 		}
@@ -325,6 +334,8 @@ sbp2_status_write(struct fw_card *card, struct fw_request *request,
 	else
 		fw_error("status write for unknown orb\n");
 
+	kref_put(&orb->kref, free_orb);
+
 	fw_send_response(card, request, RCODE_COMPLETE);
 }
 
@@ -335,13 +346,27 @@ complete_transaction(struct fw_card *card, int rcode,
 	struct sbp2_orb *orb = data;
 	unsigned long flags;
 
-	orb->rcode = rcode;
-	if (rcode != RCODE_COMPLETE) {
-		spin_lock_irqsave(&card->lock, flags);
+	/*
+	 * This is a little tricky.  We can get the status write for
+	 * the orb before we get this callback.  The status write
+	 * handler above will assume the orb pointer transaction was
+	 * successful and set the rcode to RCODE_COMPLETE for the orb.
+	 * So this callback only sets the rcode if it hasn't already
+	 * been set and only does the cleanup if the transaction
+	 * failed and we didn't already get a status write.
+	 */
+	spin_lock_irqsave(&card->lock, flags);
+
+	if (orb->rcode == -1)
+		orb->rcode = rcode;
+	if (orb->rcode != RCODE_COMPLETE) {
 		list_del(&orb->link);
-		spin_unlock_irqrestore(&card->lock, flags);
 		orb->callback(orb, NULL);
 	}
+
+	spin_unlock_irqrestore(&card->lock, flags);
+
+	kref_put(&orb->kref, free_orb);
 }
 
 static void
@@ -360,6 +385,10 @@ sbp2_send_orb(struct sbp2_orb *orb, struct fw_unit *unit,
 	list_add_tail(&orb->link, &sd->orb_list);
 	spin_unlock_irqrestore(&device->card->lock, flags);
 
+	/* Take a ref for the orb list and for the transaction callback. */
+	kref_get(&orb->kref);
+	kref_get(&orb->kref);
+
 	fw_send_request(device->card, &orb->t, TCODE_WRITE_BLOCK_REQUEST,
 			node_id, generation, device->max_speed, offset,
 			&orb->pointer, sizeof(orb->pointer),
@@ -416,6 +445,7 @@ sbp2_send_management_orb(struct fw_unit *unit, int node_id, int generation,
 	if (orb == NULL)
 		return -ENOMEM;
 
+	kref_init(&orb->base.kref);
 	orb->response_bus =
 		dma_map_single(device->card->device, &orb->response,
 			       sizeof(orb->response), DMA_FROM_DEVICE);
@@ -490,7 +520,7 @@ sbp2_send_management_orb(struct fw_unit *unit, int node_id, int generation,
 	if (response)
 		fw_memcpy_from_be32(response,
 				    orb->response, sizeof(orb->response));
-	kfree(orb);
+	kref_put(&orb->base.kref, free_orb);
 
 	return retval;
 }
@@ -886,7 +916,6 @@ complete_command_orb(struct sbp2_orb *base_orb, struct sbp2_status *status)
 
 	orb->cmd->result = result;
 	orb->done(orb->cmd);
-	kfree(orb);
 }
 
 static int sbp2_command_orb_map_scatterlist(struct sbp2_command_orb *orb)
@@ -1005,6 +1034,7 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done)
 
 	/* Initialize rcode to something not RCODE_COMPLETE. */
 	orb->base.rcode = -1;
+	kref_init(&orb->base.kref);
 
 	orb->unit = unit;
 	orb->done = done;
@@ -1051,10 +1081,11 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done)
 	sbp2_send_orb(&orb->base, unit, sd->node_id, sd->generation,
 		      sd->command_block_agent_address + SBP2_ORB_POINTER);
 
+	kref_put(&orb->base.kref, free_orb);
 	return 0;
 
  fail_mapping:
-	kfree(orb);
+	kref_put(&orb->base.kref, free_orb);
  fail_alloc:
 	return SCSI_MLQUEUE_HOST_BUSY;
 }
diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c
index 47dbe8f17e8210cabe7b87254b7ba1ac329a1c9d..a81ba8fca0db168314a2ce21aee0cecb0fd4f567 100644
--- a/drivers/ieee1394/sbp2.c
+++ b/drivers/ieee1394/sbp2.c
@@ -513,9 +513,9 @@ static int sbp2util_create_command_orb_pool(struct sbp2_lu *lu)
 	return 0;
 }
 
-static void sbp2util_remove_command_orb_pool(struct sbp2_lu *lu)
+static void sbp2util_remove_command_orb_pool(struct sbp2_lu *lu,
+					     struct hpsb_host *host)
 {
-	struct hpsb_host *host = lu->hi->host;
 	struct list_head *lh, *next;
 	struct sbp2_command_info *cmd;
 	unsigned long flags;
@@ -922,15 +922,16 @@ static void sbp2_remove_device(struct sbp2_lu *lu)
 
 	if (!lu)
 		return;
-
 	hi = lu->hi;
+	if (!hi)
+		goto no_hi;
 
 	if (lu->shost) {
 		scsi_remove_host(lu->shost);
 		scsi_host_put(lu->shost);
 	}
 	flush_scheduled_work();
-	sbp2util_remove_command_orb_pool(lu);
+	sbp2util_remove_command_orb_pool(lu, hi->host);
 
 	list_del(&lu->lu_list);
 
@@ -971,9 +972,8 @@ static void sbp2_remove_device(struct sbp2_lu *lu)
 
 	lu->ud->device.driver_data = NULL;
 
-	if (hi)
-		module_put(hi->host->driver->owner);
-
+	module_put(hi->host->driver->owner);
+no_hi:
 	kfree(lu);
 }