On Thu, Jul 26, 2018 at 05:28:53PM +0800, Christian König wrote:
> Am 26.07.2018 um 11:14 schrieb Huang Rui:
> > From: Bas Nieuwenhuizen <basni at chromium.org>
> >
> > Every set_pages_array_wb call resulted in cross-core
> > interrupts and TLB flushes. Merge more of them for
> > less overhead.
> >
> > This reduces the time needed to free a 1.6 GiB GTT WC
> > buffer as part of Vulkan CTS from ~2 sec to < 0.25 sec.
> > (Allocation still takes more than 2 sec though)
> >
> > Signed-off-by: Bas Nieuwenhuizen <basni at chromium.org>
> > Signed-off-by: Huang Rui <ray.huang at amd.com>
> > ---
> > drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 30 +++++++++++++++++++++++-------
> > 1 file changed, 23 insertions(+), 7 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
> > index 3f14c1c..27fb543 100644
> > --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
> > +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
> > @@ -301,6 +301,25 @@ static int set_pages_array_uc(struct page **pages, int addrinarray)
> > #endif
> > return 0;
> > }
> > +
> > +static int ttm_set_page_range_wb(struct page *p, unsigned long numpages)
> > +{
> > +#if IS_ENABLED(CONFIG_AGP)
> > + unsigned long i;
> > +
> > + for (i = 0; i < numpages; i++)
> > + unmap_page_from_agp(p + i);
> > +#endif
> > + return 0;
> > +}
> > +
> > +#else /* for !CONFIG_X86 */
> > +
> > +static int ttm_set_page_range_wb(struct page *p, unsigned long numpages)
> > +{
> > + return set_memory_wb((unsigned long)page_address(p), numpages);
> > +}
>
> Please use set_pages_wb() here instead of set_memory_wb(), this way it
> should also work on 32bit systems.
>
Actually, I fix it in patch 5 ("drm/ttm: use set_pages_wb instead of
set_memory_wb"). So should I sequeeze it int this patch? There is SMTP
network issue in SRDC, other patches are timeout...
[Net::SMTP] Timeout at /usr/lib/git-core/git-send-email line 1393.
Let me resend them into dri-devel as well.
Thanks,
Ray
