5.15-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shengjiu Wang <shengjiu.wang@xxxxxxx>
commit 88e98af9f4b5b0d60c1fe7f7f2701b5467691e75 upstream.
When suspended, the DMA channel may enter PAUSE state if dmaengine_pause()
is supported by DMA.
At this state, dmaengine_synchronize() should not be called, otherwise
the DMA channel can't be resumed successfully.
Fixes: e8343410ddf0 ("ALSA: dmaengine: Synchronize dma channel after drop()")
Signed-off-by: Shengjiu Wang <shengjiu.wang@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://patch.msgid.link/1721198693-27636-1-git-send-email-shengjiu.wang@xxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
sound/core/pcm_dmaengine.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
--- a/sound/core/pcm_dmaengine.c
+++ b/sound/core/pcm_dmaengine.c
@@ -347,8 +347,12 @@ EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_open
int snd_dmaengine_pcm_sync_stop(struct snd_pcm_substream *substream)
{
struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream);
+ struct dma_tx_state state;
+ enum dma_status status;
- dmaengine_synchronize(prtd->dma_chan);
+ status = dmaengine_tx_status(prtd->dma_chan, prtd->cookie, &state);
+ if (status != DMA_PAUSED)
+ dmaengine_synchronize(prtd->dma_chan);
return 0;
}
