redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

ALSA: update dell-wmi mic-mute registration to new world order 

Commit c647f806b8 ("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>
hifive-unleashed-5.1
Linus Torvalds 2018-08-15 19:08:10 -07:00
parent 71f3a82fab
commit 70b20dd7f8
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
sound/pci/hda/dell_wmi_helper.c
View File

@ -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)) {