Re: [PATCH 00/17] dmaengine: dw-edma: Support dynamic LL appends

[Koichiro Den]

On Tue, Jun 16, 2026 at 11:13:39AM +0200, Niklas Cassel wrote:
> Hello Koichiro,
> 
> On Tue, Jun 16, 2026 at 12:40:54AM +0900, Koichiro Den wrote:
> > Hi,
> > 
> > This series is a reworked version of Frank's earlier RFT series:
> > 
> >   https://lore.kernel.org/dmaengine/20260109-edma_dymatic-v1-0-9a98c9c98536@xxxxxxx/
> > 
> > After discussing the HDMA test results with Frank, I am sending this as a
> > standalone series that keeps the main dynamic-append direction, while adding the
> > fixes and HDMA handling needed to make it work reliably on both eDMA and HDMA.
> > 
> > Several patches are kept from, or based on, Frank's RFT series; the individual
> > patches carry the corresponding attribution.
> > 
> > The series has been tested on both eDMA and HDMA systems. Both completed the fio
> > test set reliably; performance results are shown below.
> 
> Great work! The performance increase is significant :)
> 
> In Frank's earlier RFT series, the change
> "dmaengine: dw-edma: Dynamically append requests while running"
> broke the pci_endpoint_test selftest:
> https://lore.kernel.org/dmaengine/aXNQcowVEMaE1xr5@ryzen/
> 
> I can see that you have included a modified version of this change in
> this series. Does the pci_endpoint_test selftest pass with your series?

Yes, I verified that the pci_endpoint_test READ_TEST and WRITE_TEST cases pass
on both eDMA and HDMA platforms, with this series applied. Perhaps I should have
mentioned that in the cover letter. I'll do so in the next revision after
retesting.

Best regards,
Koichiro

> 
> 
> Kind regards,
> Niklas