5.15-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shengjiu Wang shengjiu.wang@nxp.com
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@nxp.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/1721198693-27636-1-git-send-email-shengjiu.wang@nxp... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- 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; }