Error out MRPC execution when no more GAS access

It was observed that after a firmware hard reset, the MRPC execution
will hang indefinitely. This is because after the reset, the host will
get all 1s for any BAR read, in which case the driver won't get a valid
MRPC status.

Add a read check to GAS access when a MRPC command execution don't
response timely, error out if the check fails.

Author: kelvin-cao

switchtec.c

@@ -52,6 +52,7 @@ enum mrpc_state {
 	MRPC_QUEUED,
 	MRPC_RUNNING,
 	MRPC_DONE,
+	MRPC_IO_ERROR,
 };
 
 struct switchtec_user {
@@ -72,6 +73,13 @@ struct switchtec_user {
 	int event_cnt;
 };
 
+static int check_access(struct switchtec_dev *stdev)
+{
+	u32 device = ioread32(&stdev->mmio_sys_info->device_id);
+
+	return stdev->pdev->device == device;
+}
+
 static struct switchtec_user *stuser_create(struct switchtec_dev *stdev)
 {
 	struct switchtec_user *stuser;
@@ -119,6 +127,7 @@ static void stuser_set_state(struct switchtec_user *stuser,
 		[MRPC_QUEUED] = "QUEUED",
 		[MRPC_RUNNING] = "RUNNING",
 		[MRPC_DONE] = "DONE",
+		[MRPC_IO_ERROR] = "IO_ERROR",
 	};
 
 	stuser->state = state;
@@ -186,6 +195,20 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
 	return 0;
 }
 
+static void mrpc_cleanup_cmd(struct switchtec_dev *stdev)
+{
+	/* requires the mrpc_mutex to already be held when called */
+	struct switchtec_user *stuser = list_entry(stdev->mrpc_queue.next,
+						   struct switchtec_user, list);
+
+	complete_all(&stuser->comp);
+	list_del_init(&stuser->list);
+	stuser_put(stuser);
+	stdev->mrpc_busy = 0;
+
+	mrpc_cmd_submit(stdev);
+}
+
 static void mrpc_complete_cmd(struct switchtec_dev *stdev)
 {
 	/* requires the mrpc_mutex to already be held when called */
@@ -226,12 +249,7 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev)
 		memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data,
 			      stuser->read_len);
 out:
-	complete_all(&stuser->comp);
-	list_del_init(&stuser->list);
-	stuser_put(stuser);
-	stdev->mrpc_busy = 0;
-
-	mrpc_cmd_submit(stdev);
+	mrpc_cleanup_cmd(stdev);
 }
 
 static void mrpc_event_work(struct work_struct *work)
@@ -248,6 +266,23 @@ static void mrpc_event_work(struct work_struct *work)
 	mutex_unlock(&stdev->mrpc_mutex);
 }
 
+static void mrpc_error_complete_cmd(struct switchtec_dev *stdev)
+{
+	/* requires the mrpc_mutex to already be held when called */
+
+	struct switchtec_user *stuser;
+
+	if (list_empty(&stdev->mrpc_queue))
+		return;
+
+	stuser = list_entry(stdev->mrpc_queue.next,
+			    struct switchtec_user, list);
+
+	stuser_set_state(stuser, MRPC_IO_ERROR);
+
+	mrpc_cleanup_cmd(stdev);
+}
+
 static void mrpc_timeout_work(struct work_struct *work)
 {
 	struct switchtec_dev *stdev;
@@ -259,6 +294,11 @@ static void mrpc_timeout_work(struct work_struct *work)
 
 	mutex_lock(&stdev->mrpc_mutex);
 
+	if (!check_access(stdev)) {
+		mrpc_error_complete_cmd(stdev);
+		goto out;
+	}
+
 	if (stdev->dma_mrpc)
 		status = stdev->dma_mrpc->status;
 	else
@@ -544,6 +584,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data,
 	if (rc)
 		return rc;
 
+	if (stuser->state == MRPC_IO_ERROR) {
+		mutex_unlock(&stdev->mrpc_mutex);
+		return -EIO;
+	}
+
 	if (stuser->state != MRPC_DONE) {
 		mutex_unlock(&stdev->mrpc_mutex);
 		return -EBADE;