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,