forked from luck/tmp_suning_uos_patched
ALSA: update dell-wmi mic-mute registration to new world order
Commitc647f806b8
("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:c647f806b8
"ALSA: hda - Allow multiple ADCs for mic mute LED controls" Cc: Takashi Iwai <tiwai@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
71f3a82fab
commit
70b20dd7f8
|
@ -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)) {
|
||||
|
|
Loading…
Reference in New Issue
Block a user