On 11/17/2012 12:31 PM, Russell King - ARM Linux wrote: > On Fri, Oct 19, 2012 at 02:45:55PM +0200, Péter Ujfalusi wrote: >> Hi, >> >> On 10/19/2012 01:33 AM, Russell King - ARM Linux wrote: >>> I'm merely pointing out here that we need their feedback here before >>> deciding if there's anything further that needs to happen. >> >> Thanks Russell, I'll take a look at the implication of the prefetch for audio. > > Péter, any news? Sorry, I was carried away with other things... I did some testing with and without the dma prefetch for audio (on BeagleBoard with mplayer: -ao alsa/pulse). When we have prefetch enabled we tend to resume after pause from a slightly off place than when the prefetch is disabled. I also remember that in n9 we have had some issue with the DMA prefetch. So I would for sure enable the prefetch for non cyclic DMA. For the cyclic I would not enable it for now. I need to dig a bit deeper in DMA/McBSP to have better view on the issue. I have one comment to the patch itself as well. -- Péter -- To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html