accel/habanalabs: poll for device status update following WFE cmd

Currently, we rely on COMMS protocol's ack to verify that WFE command
has been acknowledged by the FW. However, this does not guarantee that
the device status has been updated.
Although unlikely, this could trigger a race since the driver expects
the device to be halted at that stage, but it might not be.
Therefore, we increase WFE's robustness by polling on the status
register that will be updated once the device is actually halted.

Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

Author: KobyElbaz

drivers/accel/habanalabs/common/firmware_if.c

@@ -1368,21 +1368,39 @@ void hl_fw_ask_hard_reset_without_linux(struct hl_device *hdev)
 
 void hl_fw_ask_halt_machine_without_linux(struct hl_device *hdev)
 {
-	struct static_fw_load_mgr *static_loader =
-			&hdev->fw_loader.static_loader;
+	struct fw_load_mgr *fw_loader = &hdev->fw_loader;
+	u32 status, cpu_boot_status_reg, cpu_timeout;
+	struct static_fw_load_mgr *static_loader;
+	struct pre_fw_load_props *pre_fw_load;
 	int rc;
 
 	if (hdev->device_cpu_is_halted)
 		return;
 
 	/* Stop device CPU to make sure nothing bad happens */
 	if (hdev->asic_prop.dynamic_fw_load) {
+		pre_fw_load = &fw_loader->pre_fw_load;
+		cpu_timeout = fw_loader->cpu_timeout;
+		cpu_boot_status_reg = pre_fw_load->cpu_boot_status_reg;
+
 		rc = hl_fw_dynamic_send_protocol_cmd(hdev, &hdev->fw_loader,
-				COMMS_GOTO_WFE, 0, false,
-				hdev->fw_loader.cpu_timeout);
-		if (rc)
+				COMMS_GOTO_WFE, 0, false, cpu_timeout);
+		if (rc) {
 			dev_err(hdev->dev, "Failed sending COMMS_GOTO_WFE\n");
+		} else {
+			rc = hl_poll_timeout(
+				hdev,
+				cpu_boot_status_reg,
+				status,
+				status == CPU_BOOT_STATUS_IN_WFE,
+				hdev->fw_poll_interval_usec,
+				cpu_timeout);
+			if (rc)
+				dev_err(hdev->dev, "Current status=%u. Timed-out updating to WFE\n",
+						status);
+		}
 	} else {
+		static_loader = &hdev->fw_loader.static_loader;
 		WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_GOTO_WFE);
 		msleep(static_loader->cpu_reset_wait_msec);