The ELD notification can be received asynchronously from the graphics side, and this may happen just at the moment the sound driver is processing the suspend or the resume, and it would confuse the whole procedure. Since the ELD and connection states are updated in anyway at the end of the resume, we can skip it when received during PM process.
Signed-off-by: Takashi Iwai tiwai@suse.de --- sound/pci/hda/patch_hdmi.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 4dc21ecf7230..75815acb77db 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2450,6 +2450,9 @@ static void intel_pin_eld_notify(void *audio_ptr, int port) */ if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0) return; + /* ditto during suspend/resume process itself */ + if (atomic_read(&(codec)->core.in_pm)) + return;
/* execute ELD update in a work for avoiding a deadlock */ per_pin = get_pin(spec, pin_idx);