Subject: Re: bus_dmamap_sync() in ti(4) or the lack thereof
To: Tobias Nygren <firstname.lastname@example.org>
From: Matt Thomas <email@example.com>
Date: 02/27/2007 13:55:11
Tobias Nygren wrote:
> ti(4) doesn't work right on sparc64. With DIAGNOSTIC i get tons
> of "iommu_dvmamap_load: map still in use".
> I took a glance at the ti(4) code and noticed the absence of any
> preread/postread dma syncs, despite the fact that the driver relies
> heavily on reuse of dma maps. This can't be right, can it?
> The fact that the driver appears to reload maps without unloading
> them first might be caused by something else, though.
It depends on whether it was running on a system with cache coherence or not.
ti works fine on alpha, for instance, since it's cache coherent.