Skip to contentSkip to conversation

ALSA: ASoC: fix NULL pointer dereference in soc_suspend()

PATCH In review Daniel Mack 2 participants 2 messages Jun 3, 2009 – Jun 4, 2009

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 ALSA: ASoC: fix NULL pointer dereference in soc_suspend()

In case the initalization of an soc_device failed, there is no codec associated with it. soc_suspend() will still dereference the pointer and cause an Ooops when entering the sleep mode.

This happens on our board with a multi-target kernel image when booted on a machine without audio circuits.

This patch makes the code bail out very early in this special case.

---
 sound/soc/soc-core.c |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)
sound/soc/soc-core.c +6 -0
index 1cd149b..4545a15 100644
@@ -632,6 +632,12 @@ static int soc_suspend(struct platform_device *pdev, pm_message_t state)
 	struct snd_soc_codec *codec = card->codec;
 	int i;
 
+	/* If the initialization of this soc device failed, there is no codec
+	 * associated with it. Just bail out in this case.
+	 */
+	if (!codec)
+		return 0;
+
 	/* Due to the resume being scheduled into a workqueue we could
 	* suspend before that's finished - wait for it to complete.
 	 */
Signature · 1 line
1.6.3.1
#1 lore raw
Quoted 8 lines · Daniel Mack

In case the initalization of an soc_device failed, there is no codec associated with it. soc_suspend() will still dereference the pointer and cause an Ooops when entering the sleep mode.

This happens on our board with a multi-target kernel image when booted on a machine without audio circuits.

This patch makes the code bail out very early in this special case.

A better fix would be to stop the device registering at all if the initialsation fails but that's a bit more involved and in the meantime this makes the situation better. Probably best to wait for the real fix until multiple cards are supported.

Thanks, I've applied this.