ASOC: SOF: Intel: hda-loader: only wait for HDaudio IOC for IPC4 devices

Multiple users report a regression bisected to commit d5263db
("ASoC: SOF: Intel: don't ignore IOC interrupts for non-audio
transfers"). The firmware version is the likely suspect, as these
users relies on SOF 2.0 while Intel only tested with the 2.2 release.

Rather than completely disable the wait_for_completion(), which can
help us gather timing information on the different stages of the boot
process, the simplest course of action is to just disable it for older
IPC versions which are no longer under active development.

Closes: thesofproject#5072
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218961
Fixes: d5263db ("ASoC: SOF: Intel: don't ignore IOC interrupts for non-audio transfers")
Tested-by: Mike Krinkin <krinkin.m.u@gmail.com>
Tested-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>

sound/soc/sof/intel/hda-loader.c

@@ -310,15 +310,19 @@ int hda_cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *hext_stream
 		return ret;
 	}
 
-	/* Wait for completion of transfer */
-	time_left = wait_for_completion_timeout(&hda_stream->ioc,
-						msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS));
-
-	if (!time_left) {
-		dev_err(sdev->dev, "Code loader DMA did not complete\n");
-		return -ETIMEDOUT;
+	if (sdev->pdata->ipc_type == SOF_IPC_TYPE_4) {
+		/* Wait for completion of transfer */
+		time_left = wait_for_completion_timeout(&hda_stream->ioc,
+							msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS));
+
+		if (!time_left) {
+			dev_err(sdev->dev, "Code loader DMA did not complete\n");
+			return -ETIMEDOUT;
+		}
+		dev_dbg(sdev->dev, "Code loader DMA done\n");
 	}
-	dev_dbg(sdev->dev, "Code loader DMA done, waiting for FW_ENTERED status\n");
+
+	dev_dbg(sdev->dev, "waiting for FW_ENTERED status\n");
 
 	status = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
 					chip->rom_status_reg, reg,