From: Takashi Iwai Date: Fri, 27 Nov 2015 13:23:00 +0000 (+0100) Subject: ALSA: hda - Skip ELD notification during system suspend X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=8ae743e82f0b86f3b860c27fc2c8f574cf959fd0;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git ALSA: hda - Skip ELD notification during system suspend The recent addition of ELD notifier for Intel HDMI/DP codec may lead the bad codec connection found as kernel messages like below: Suspending console(s) (use no_console_suspend to debug) hdmi_present_sense: snd_hda_codec_hdmi hdaudioC0D2: HDMI status: Codec=2 Pin=6 Presence_Detect=1 ELD_Valid=1 snd_hda_intel 0000:00:1f.3: spurious response 0x0:0x2, last cmd=0x206f2e08 snd_hda_intel 0000:00:1f.3: spurious response 0x0:0x2, last cmd=0x206f2e08 .... snd_hda_codec_hdmi hdaudioC0D2: HDMI: ELD buf size is 0, force 128 snd_hda_intel 0000:00:1f.3: azx_get_response timeout, switching to polling mode: last cmd=0x206f2f00 snd_hda_intel 0000:00:1f.3: No response from codec, disabling MSI: last cmd=0x206f2f00 snd_hda_intel 0000:00:1f.3: azx_get_response timeout, switching to single_cmd mode: last cmd=0x206f2f00 azx_single_wait_for_response: 42 callbacks suppressed This seems appearing when the sound driver went to suspend before i915 driver. Then i915 driver disables HDMI/DP audio bit and calls the registered notifier, and the HDA codec tries to handle it as a hot(un)plug. But since the driver is already in the suspended state, it fails miserably. As this is a sort of spurious wakeup, it can be ignored safely, as long as it's delivered during the system suspend. OTOH, if a notification comes during the runtime suspend, the situation is different: we need to wake up. But during the system suspend, such a notification can't be the reason for a wakeup. This patch addresses it by a simple check of the current sound card status. The skipped notification doesn't matter because the HDA driver will check the plugged status forcibly at the resume in return. Then, why the card status, not a runtime PM status or else? The HDA controller driver is supposed to set the card status to D3 at the system suspend but not at the runtime suspend. So we can see it as a flag that is set only for the system suspend. Admittedly, it's a bit ugly, but it should work well for now. Reported-and-tested-by: "Zhang, Xiong Y" Fixes: 25adc137c546 ('ALSA: hda - Wake the codec up on pin/ELD notify events') Cc: # v4.3+ Signed-off-by: Takashi Iwai --- diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index bdb6f226d006..4b6fb668c91c 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2352,6 +2352,12 @@ static void intel_pin_eld_notify(void *audio_ptr, int port) struct hda_codec *codec = audio_ptr; int pin_nid = port + 0x04; + /* skip notification during system suspend (but not in runtime PM); + * the state will be updated at resume + */ + if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0) + return; + check_presence_and_report(codec, pin_nid); }