On Tue, Mar 29, 2016 at 01:55:02PM +0200, Daniel Vetter wrote:
> *Blonk* or whatever the sound for suddenly realization is. Totally forgot
> that we're reuseding set_domain(GTT) for wc mmaps because this it's a nice
> trick.
>
> Otoh, is that trick the reason why wc mmaps aren't coherent enough? O
On Fri, Mar 25, 2016 at 02:05:42PM +, Zanoni, Paulo R wrote:
> Em Qui, 2016-03-24 às 21:20 +, ch...@chris-wilson.co.uk escreveu:
> > On Thu, Mar 24, 2016 at 09:03:59PM +, ch...@chris-wilson.co.uk
> > wrote:
> > >
> > > On Thu, Mar 24, 2016 at 08:53:21PM +, Zanoni, Paulo R wrote:
>
On Fri, Mar 25, 2016 at 02:05:42PM +, Zanoni, Paulo R wrote:
> What if I have both a WC mmap and a GTT mmap, and I'm actually using
> the GTT mmap now? My set_domain call will be treated as WC mmap usage,
> while in fact it should be treated as GTT usage. Is there a way to
> differentiate betwe
Em Qui, 2016-03-24 às 21:20 +, ch...@chris-wilson.co.uk escreveu:
> On Thu, Mar 24, 2016 at 09:03:59PM +, ch...@chris-wilson.co.uk
> wrote:
> >
> > On Thu, Mar 24, 2016 at 08:53:21PM +, Zanoni, Paulo R wrote:
> > >
> > > Em Qui, 2016-03-24 às 19:31 +, Chris Wilson escreveu:
> > >
On Thu, Mar 24, 2016 at 09:21:49PM +, Zanoni, Paulo R wrote:
> Em Qui, 2016-03-24 às 21:03 +, ch...@chris-wilson.co.uk escreveu:
> > On Thu, Mar 24, 2016 at 08:53:21PM +, Zanoni, Paulo R wrote:
> > >
> > > Em Qui, 2016-03-24 às 19:31 +, Chris Wilson escreveu:
> > > >
> > > > On Th
Em Qui, 2016-03-24 às 21:03 +, ch...@chris-wilson.co.uk escreveu:
> On Thu, Mar 24, 2016 at 08:53:21PM +, Zanoni, Paulo R wrote:
> >
> > Em Qui, 2016-03-24 às 19:31 +, Chris Wilson escreveu:
> > >
> > > On Thu, Mar 24, 2016 at 04:16:11PM -0300, Paulo Zanoni wrote:
> > > >
> > > >
>
On Thu, Mar 24, 2016 at 09:03:59PM +, ch...@chris-wilson.co.uk wrote:
> On Thu, Mar 24, 2016 at 08:53:21PM +, Zanoni, Paulo R wrote:
> > Em Qui, 2016-03-24 às 19:31 +, Chris Wilson escreveu:
> > > On Thu, Mar 24, 2016 at 04:16:11PM -0300, Paulo Zanoni wrote:
> > > >
> > > > FBC and the
On Thu, Mar 24, 2016 at 08:53:21PM +, Zanoni, Paulo R wrote:
> Em Qui, 2016-03-24 às 19:31 +, Chris Wilson escreveu:
> > On Thu, Mar 24, 2016 at 04:16:11PM -0300, Paulo Zanoni wrote:
> > >
> > > FBC and the frontbuffer tracking infrastructure were designed
> > > assuming
> > > that user sp
Em Qui, 2016-03-24 às 19:31 +, Chris Wilson escreveu:
> On Thu, Mar 24, 2016 at 04:16:11PM -0300, Paulo Zanoni wrote:
> >
> > FBC and the frontbuffer tracking infrastructure were designed
> > assuming
> > that user space applications would follow a specific set of rules
> > regarding frontbuff
On Thu, Mar 24, 2016 at 04:16:11PM -0300, Paulo Zanoni wrote:
> FBC and the frontbuffer tracking infrastructure were designed assuming
> that user space applications would follow a specific set of rules
> regarding frontbuffer management and mmapping. I recently discovered
> that current user space
FBC and the frontbuffer tracking infrastructure were designed assuming
that user space applications would follow a specific set of rules
regarding frontbuffer management and mmapping. I recently discovered
that current user space is not exactly following these rules: my
investigation led me to the
On Wed, 2016-03-23 at 09:53 +0100, Daniel Vetter wrote:
> On Tue, Mar 22, 2016 at 09:48:00PM +, Zanoni, Paulo R wrote:
> > Em Ter, 2016-03-22 às 12:29 +0100, Daniel Vetter escreveu:
> > > On Mon, Mar 21, 2016 at 04:26:57PM -0300, Paulo Zanoni wrote:
> > > >
> > > > FBC and the frontbuffer trac
On Tue, Mar 22, 2016 at 09:48:00PM +, Zanoni, Paulo R wrote:
> Em Ter, 2016-03-22 às 12:29 +0100, Daniel Vetter escreveu:
> > On Mon, Mar 21, 2016 at 04:26:57PM -0300, Paulo Zanoni wrote:
> > >
> > > FBC and the frontbuffer tracking infrastructure were designed
> > > assuming
> > > that user s
Em Ter, 2016-03-22 às 12:29 +0100, Daniel Vetter escreveu:
> On Mon, Mar 21, 2016 at 04:26:57PM -0300, Paulo Zanoni wrote:
> >
> > FBC and the frontbuffer tracking infrastructure were designed
> > assuming
> > that user space applications would follow a specific set of rules
> > regarding frontbuf
On Tue, 22 Mar 2016, Daniel Vetter wrote:
> [ text/plain ]
> On Tue, Mar 22, 2016 at 12:28:20PM +0200, Jani Nikula wrote:
>> On Mon, 21 Mar 2016, Paulo Zanoni wrote:
>> > +enum fb_mmap_wa_flags {
>> > + FB_MMAP_WA_CPU =1 << 0,
>> > + FB_MMAP_WA_GTT =1 << 1,
>> > + FB_MMAP_WA_DI
On Mon, Mar 21, 2016 at 04:26:57PM -0300, Paulo Zanoni wrote:
> FBC and the frontbuffer tracking infrastructure were designed assuming
> that user space applications would follow a specific set of rules
> regarding frontbuffer management and mmapping. I recently discovered
> that current user space
On Tue, Mar 22, 2016 at 12:28:20PM +0200, Jani Nikula wrote:
> On Mon, 21 Mar 2016, Paulo Zanoni wrote:
> > +enum fb_mmap_wa_flags {
> > + FB_MMAP_WA_CPU =1 << 0,
> > + FB_MMAP_WA_GTT =1 << 1,
> > + FB_MMAP_WA_DISABLE =1 << 2,
> > + FB_MMAP_WA_FLAG_COUNT = 3,
> > +};
>
On Mon, 21 Mar 2016, Paulo Zanoni wrote:
> +enum fb_mmap_wa_flags {
> + FB_MMAP_WA_CPU =1 << 0,
> + FB_MMAP_WA_GTT =1 << 1,
> + FB_MMAP_WA_DISABLE =1 << 2,
> + FB_MMAP_WA_FLAG_COUNT = 3,
> +};
Drive-by review, adding bit flags as enums doesn't feel like what en
Hi Paulo,
[auto build test WARNING on drm-intel/for-linux-next]
[also build test WARNING on next-20160321]
[cannot apply to v4.5]
[if your patch is applied to the wrong git tree, please drop us a note to help
improving the system]
url:
https://github.com/0day-ci/linux/commits/Paulo-Zanoni/En
FBC and the frontbuffer tracking infrastructure were designed assuming
that user space applications would follow a specific set of rules
regarding frontbuffer management and mmapping. I recently discovered
that current user space is not exactly following these rules: my
investigation led me to the
20 matches
Mail list logo
