From: Takashi Iwai Date: Wed, 23 Oct 2013 23:20:24 +0000 (+0200) Subject: ALSA: hda - Fix unbalanced runtime PM refcount after S3/S4 X-Git-Url: http://git.mmlx.us/?a=commitdiff_plain;h=c9e32ffdbe042276914daac9cdc737b8896eace6;p=linux-edison.git ALSA: hda - Fix unbalanced runtime PM refcount after S3/S4 commit e6bbe666673ab044a3d39ddb74e4d9a401cf1d6f upstream. When a machine goes to S3/S4 after power-save is enabled, the runtime PM refcount might be incorrectly decreased because the power-down triggered soon after resume assumes that the controller was already powered up, and issues the pm_notify down. This patch fixes the incorrect pm_notify call simply by checking the current value properly. Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 55108b5fb29..31461ba32d3 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -4789,8 +4789,8 @@ static void hda_power_work(struct work_struct *work) spin_unlock(&codec->power_lock); state = hda_call_codec_suspend(codec, true); - codec->pm_down_notified = 0; - if (!bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) { + if (!codec->pm_down_notified && + !bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) { codec->pm_down_notified = 1; hda_call_pm_notify(bus, false); }