diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-15 19:08:10 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-15 19:08:10 -0700 |
| commit | 70b20dd7f897c6c14ab9e0d8400aed520ab5f09b (patch) | |
| tree | f8c024c5b683cf612a1fe7784bc50b2af0d4eabd | |
| parent | 71f3a82fab1b631ae9cb1feb677f498d4ca5007d (diff) | |
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 <tiwai@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| -rw-r--r-- | sound/pci/hda/dell_wmi_helper.c | 2 |
1 files changed, 1 insertions, 1 deletions
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)) { |