From 70b20dd7f897c6c14ab9e0d8400aed520ab5f09b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 15 Aug 2018 19:08:10 -0700 Subject: ALSA: update dell-wmi mic-mute registration to new world order Commit c647f806b8c2 ("ALSA: hda - Allow multiple ADCs for mic mute LED controls") changed the return value of the snd_hda_gen_add_micmute_led() without actually updating the callers. Admittedly, almost no callers actually cared about the return value. But one call site very much did: the Dell wmi code. It would see the registration return zero, which _used_ to mean "failed" but now means "success", and clear the dell_micmute_led_set_func pointer. End result: the successful registration would end up calling the Dell code that thought it had all failed, and call through a NULL pointer. To make matters worse, it ends up being a tail-call, and with the retpoline sequence you don't even see the caller (dell_micmute_update()) in the stack trace, so the error ended up way less obvious than it should have been. Fixes: c647f806b8c2 "ALSA: hda - Allow multiple ADCs for mic mute LED controls" Cc: Takashi Iwai Signed-off-by: Linus Torvalds --- sound/pci/hda/dell_wmi_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c index 8a7dbd1a7fbf..bbd6c87a4ed6 100644 --- a/sound/pci/hda/dell_wmi_helper.c +++ b/sound/pci/hda/dell_wmi_helper.c @@ -30,7 +30,7 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec, removefunc = (dell_micmute_led_set_func(false) < 0) || (snd_hda_gen_add_micmute_led(codec, - dell_micmute_update) <= 0); + dell_micmute_update) < 0); } if (dell_micmute_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) { -- cgit v1.2.3