summaryrefslogtreecommitdiffstats
path: root/sound/pci
diff options
context:
space:
mode:
authorTakashi Iwai <tiwai@suse.de>2013-04-17 18:16:05 +0200
committerTakashi Iwai <tiwai@suse.de>2013-04-17 18:20:42 +0200
commit594813ffa741b4bcdeff85ca09d734117ac93371 (patch)
tree057a919c7c7273e144828d7a967d10f87aa68823 /sound/pci
parent83f26ad2c909083fa638d2df1b1a25bcbf2d1be2 (diff)
ALSA: hda - Don't call vmaster hook when bus->shutdown is set
The flag bus->shutdown implies that the control elements might have been already destroyed. When a codec is resumed at this state and tries to call vmaster hook (e.g. in snd_hda_gen_init()), it would refer to a non-existing object, resulting in Oops in the end. This patch just adds a check of the flag in the caller side for avoiding such a crash. Though, the best would be to clear hook->sw_kctl by the destructor of the corresponding ctl element, but vmaster uses its own private_free, it can't be done easily. So let it be for a while. Signed-off-by: Takashi Iwai <tiwai@suse.de>
Diffstat (limited to 'sound/pci')
-rw-r--r--sound/pci/hda/hda_codec.c5
1 files changed, 5 insertions, 0 deletions
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index e37b7388e8a..3603cbe2d40 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2784,6 +2784,11 @@ void snd_hda_sync_vmaster_hook(struct hda_vmaster_mute_hook *hook)
{
if (!hook->hook || !hook->codec)
return;
+ /* don't call vmaster hook in the destructor since it might have
+ * been already destroyed
+ */
+ if (hook->codec->bus->shutdown)
+ return;
switch (hook->mute_mode) {
case HDA_VMUTE_FOLLOW_MASTER:
snd_ctl_sync_vmaster_hook(hook->sw_kctl);