提交 d4ba7854 编写于 作者: W Wolfram Sang 提交者: Mark Brown

ASoC: imx-ssi: use dma_writecombine consistently

If the channel is allocated as writecombine, then mmaping it should also
use writecombine. Also, add a proper device for the call. Ported from a
similar fix for mach-mxs.
Signed-off-by: NWolfram Sang <w.sang@pengutronix.de>
Acked-by: NSascha Hauer <s.hauer@pengutronix.de>
Acked-by: NLiam Girdwood <lrg@ti.com>
Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
上级 18a4eef3
...@@ -357,8 +357,8 @@ int snd_imx_pcm_mmap(struct snd_pcm_substream *substream, ...@@ -357,8 +357,8 @@ int snd_imx_pcm_mmap(struct snd_pcm_substream *substream,
struct snd_pcm_runtime *runtime = substream->runtime; struct snd_pcm_runtime *runtime = substream->runtime;
int ret; int ret;
ret = dma_mmap_coherent(NULL, vma, runtime->dma_area, ret = dma_mmap_writecombine(substream->pcm->card->dev, vma,
runtime->dma_addr, runtime->dma_bytes); runtime->dma_area, runtime->dma_addr, runtime->dma_bytes);
pr_debug("%s: ret: %d %p 0x%08x 0x%08x\n", __func__, ret, pr_debug("%s: ret: %d %p 0x%08x 0x%08x\n", __func__, ret,
runtime->dma_area, runtime->dma_area,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册