Re: [Nouveau] [PATCH] nouveau/hmm: fix migrate zero page to GPU

[Ben Skeggs]

On Thu, 21 May 2020 at 07:05, Ralph Campbell <rcampbell@xxxxxxxxxx> wrote:
>
>
> On 5/20/20 12:20 PM, Jason Gunthorpe wrote:
> > On Wed, May 20, 2020 at 11:36:52AM -0700, Ralph Campbell wrote:
> >> When calling OpenCL clEnqueueSVMMigrateMem() on a region of memory that
> >> is backed by pte_none() or zero pages, migrate_vma_setup() will fill the
> >> source PFN array with an entry indicating the source page is zero.
> >> Use this to optimize migration to device private memory by allocating
> >> GPU memory and zero filling it instead of failing to migrate the page.
> >>
> >> Signed-off-by: Ralph Campbell <rcampbell@xxxxxxxxxx>
> >>
> >> This patch applies cleanly to Jason's Gunthorpe's hmm tree plus two
> >> patches I posted earlier. The first is queued in Ben Skegg's nouveau
> >> tree and the second is still pending review/not queued.
> >> [1] ("nouveau/hmm: map pages after migration")
> >> https://lore.kernel.org/linux-mm/20200304001339.8248-5-rcampbell@xxxxxxxxxx/
> >> [2] ("nouveau/hmm: fix nouveau_dmem_chunk allocations")
> >> https://lore.kernel.org/lkml/20200421231107.30958-1-rcampbell@xxxxxxxxxx/
> >
> > It would be best if it goes through Ben's tree if it doesn't have
> > conflicts with the hunks I have in the hmm tree.. Is it the case?
> >
> > Jason
>
> I think there might be some merge conflicts even though it is semantically
> independent of the other changes. I guess since we are at 5.7-rc6 and not
> far from the merge window, I can rebase after 5.8-rc1 and resend.
> I posted this mostly to get some review and as a "heads up" of the issue.
Both look alright to me, and apply cleanly on top of my tree already,
so I've got them locally.

Ben.

> _______________________________________________
> Nouveau mailing list
> Nouveau@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/nouveau