summaryrefslogtreecommitdiffstats
path: root/sound/isa
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-08-15 19:08:10 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-08-15 19:08:10 -0700
commit70b20dd7f897c6c14ab9e0d8400aed520ab5f09b (patch)
treef8c024c5b683cf612a1fe7784bc50b2af0d4eabd /sound/isa
parent71f3a82fab1b631ae9cb1feb677f498d4ca5007d (diff)
downloadlinux-70b20dd7f897c6c14ab9e0d8400aed520ab5f09b.tar.gz
linux-70b20dd7f897c6c14ab9e0d8400aed520ab5f09b.tar.bz2
linux-70b20dd7f897c6c14ab9e0d8400aed520ab5f09b.zip
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>
Diffstat (limited to 'sound/isa')
0 files changed, 0 insertions, 0 deletions