Re: [alsa-devel] [PATCH] ASoC: Intel: sof_rt5682: Ignore the speaker amp when there isn't one. - Pierre-Louis Bossart

From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
To: Sam McNally <sammc@chromium.org>, LKML <linux-kernel@vger.kernel.org>
Cc: Jaroslav Kysela <perex@perex.cz>,
	Liam Girdwood <liam.r.girdwood@linux.intel.com>,
	alsa-devel@alsa-project.org,
	Bard Liao <yung-chuan.liao@linux.intel.com>,
	Sathya Prakash M R <sathya.prakash.m.r@intel.com>,
	Mark Brown <broonie@kernel.org>,
	Cezary Rojewski <cezary.rojewski@intel.com>,
	Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>,
	Takashi Iwai <tiwai@suse.com>,
	Jairaj Arava <jairaj.arava@intel.com>,
	Xun Zhang <xun2.zhang@intel.com>,
	Jie Yang <yang.jie@linux.intel.com>,
	Kai Vehmanen <kai.vehmanen@linux.intel.com>,
	Sathyanarayana Nujella <sathyanarayana.nujella@intel.com>
Subject: Re: [alsa-devel] [PATCH] ASoC: Intel: sof_rt5682: Ignore the speaker amp when there isn't one.
Date: Thu, 2 Jan 2020 12:48:22 -0600	[thread overview]
Message-ID: <a7ab606a-1e35-29aa-ea60-7c31374eb7b4@linux.intel.com> (raw)
In-Reply-To: <20200102112558.1.Ib87c4a7fbb3fc818ea12198e291b87dc2d5bc8c2@changeid>

On 1/1/20 6:28 PM, Sam McNally wrote:
> Some members of the Google_Hatch family include a rt5682, but not a
> speaker amp. When a speaker amp is also present, it matches MX98357A
> as well, resulting in the quirk_data field in the snd_soc_acpi_mach
> being non-null. When only the rt5682 is present, quirk_data is left
> null.

Sorry, I don't get this last sentence.

There is a single entry for 10EC5682 in sound-acpi-intel-glk-match.c and 
quirk_data is assigned - thus can never be NULL.

I wonder if your Chrome kernel has an extra entry in 
snd_soc_acpi_intel_glk_machines[] ? What I am missing?

> 
> The sof_rt5682 driver's DMI data matching identifies that a speaker amp
> is present for all Google_Hatch family devices. Detect cases where there
> is no speaker amp by checking for a null quirk_data in the
> snd_soc_acpi_mach and remove the speaker amp bit in that case.
> 
> Signed-off-by: Sam McNally <sammc@chromium.org>
> ---
> 
>   sound/soc/intel/boards/sof_rt5682.c | 9 ++++++++-
>   1 file changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c
> index ad8a2b4bc709..8a13231dee15 100644
> --- a/sound/soc/intel/boards/sof_rt5682.c
> +++ b/sound/soc/intel/boards/sof_rt5682.c
> @@ -603,6 +603,14 @@ static int sof_audio_probe(struct platform_device *pdev)
>   
>   	dmi_check_system(sof_rt5682_quirk_table);
>   
> +	mach = (&pdev->dev)->platform_data;
> +
> +	/* A speaker amp might not be present when the quirk claims one is.
> +	 * Detect this via whether the machine driver match includes quirk_data.
> +	 */
> +	if ((sof_rt5682_quirk & SOF_SPEAKER_AMP_PRESENT) && !mach->quirk_data)
> +		sof_rt5682_quirk &= ~SOF_SPEAKER_AMP_PRESENT;
> +
>   	if (soc_intel_is_byt() || soc_intel_is_cht()) {
>   		is_legacy_cpu = 1;
>   		dmic_be_num = 0;
> @@ -663,7 +671,6 @@ static int sof_audio_probe(struct platform_device *pdev)
>   	INIT_LIST_HEAD(&ctx->hdmi_pcm_list);
>   
>   	sof_audio_card_rt5682.dev = &pdev->dev;
> -	mach = (&pdev->dev)->platform_data;
>   
>   	/* set platform name for each dailink */
>   	ret = snd_soc_fixup_dai_links_platform_name(&sof_audio_card_rt5682,
> 