Re: [PATCH RFC 2/2] dmaengine: fsl-edma: Support dynamic scatter/gather chaining
From: Benoît Monin
Date: Wed May 06 2026 - 10:03:43 EST
On Tuesday, 5 May 2026 at 17:07:48 CEST, Frank Li wrote:
> > > how do you test it? and how much preformance improved?
> > I did my tests by doing SPI transfers with the LPSPI controllers, doing DMA
> > transactions with different number of buffers and different buffer sizes.
> > Without chaining, interruptions on the SPI bus occur between each DMA
> > transaction. With chaining, the activity on the SPI bus is continuous as
> > long as DMA transactions are issued before the end of the current
> > transaction.
>
> Does SPI support issue new transfers without wait for previous transfer
> complete, or SPI transfer already support async queue?
>
This is done with a local version of fsl-lpspi driver adding a simple
offload support by borrowing the DMA channels allocated to the SPI
controller. I can then issue multiple DMA transactions with the dma_buf API
of the IIO subsystem and trigger SG chaining.
Best regards,
--
Benoît Monin, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com