On Oct 15, Jakub Kicinski wrote:
> On Mon, 14 Oct 2019 12:49:51 +0200, Lorenzo Bianconi wrote:
> > mvneta driver can run on not cache coherent devices so it is
> > necessary to sync DMA buffers before sending them to the device
> > in order to avoid memory corruptions. Running perf analysis we can
On Mon, 14 Oct 2019 12:49:51 +0200, Lorenzo Bianconi wrote:
> mvneta driver can run on not cache coherent devices so it is
> necessary to sync DMA buffers before sending them to the device
> in order to avoid memory corruptions. Running perf analysis we can
> see a performance cost associated with
mvneta driver can run on not cache coherent devices so it is
necessary to sync DMA buffers before sending them to the device
in order to avoid memory corruptions. Running perf analysis we can
see a performance cost associated with this DMA-sync (anyway it is
already there in the original driver cod
