diff options
| author | Linus Torvalds <[email protected]> | 2018-08-16 02:08:10 +0000 |
|---|---|---|
| committer | Linus Torvalds <[email protected]> | 2018-08-16 02:08:10 +0000 |
| commit | 70b20dd7f897c6c14ab9e0d8400aed520ab5f09b (patch) | |
| tree | f8c024c5b683cf612a1fe7784bc50b2af0d4eabd /tools/perf/scripts/python/call-graph-from-sql.py | |
| parent | Merge tag 'media/v4.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mc... (diff) | |
| download | kernel-70b20dd7f897c6c14ab9e0d8400aed520ab5f09b.tar.gz kernel-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 <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Diffstat (limited to 'tools/perf/scripts/python/call-graph-from-sql.py')
0 files changed, 0 insertions, 0 deletions
