From: Ben Widawsky <ben@bwidawsk.net>
To: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 01/10] drm/i915: No LLC_MLC for HSW.
Date: Thu, 25 Oct 2012 18:03:43 -0700 [thread overview]
Message-ID: <20121025180343.0000670e@unknown> (raw)
In-Reply-To: <20121025134722.31e78bca@jbarnes-desktop>
On Thu, 25 Oct 2012 13:47:22 -0700
Jesse Barnes <jbarnes@virtuousgeek.org> wrote:
> On Mon, 22 Oct 2012 18:34:06 -0700
> Ben Widawsky <ben@bwidawsk.net> wrote:
>
> > The mid-level cache or as it's more commonly referred to now as L3,
> > is not setup this way on HSW.
> >
> > Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> > ---
> > drivers/gpu/drm/i915/i915_gem_gtt.c | 10 +++++++---
> > 1 file changed, 7 insertions(+), 3 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c
> > b/drivers/gpu/drm/i915/i915_gem_gtt.c index 47e427e..5751ad2 100644
> > --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> > +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> > @@ -218,7 +218,11 @@ void i915_ppgtt_bind_object(struct
> > i915_hw_ppgtt *ppgtt,
> > switch (cache_level) {
> > case I915_CACHE_LLC_MLC:
> > - pte_flags |= GEN6_PTE_CACHE_LLC_MLC;
> > + /* Haswell doesn't set L3 this way */
> > + if (IS_HASWELL(obj->base.dev))
> > + pte_flags |= GEN6_PTE_CACHE_LLC;
> > + else
> > + pte_flags |= GEN6_PTE_CACHE_LLC_MLC;
> > break;
> > case I915_CACHE_LLC:
> > pte_flags |= GEN6_PTE_CACHE_LLC;
> > @@ -253,12 +257,12 @@ static unsigned int
> > cache_level_to_agp_type(struct drm_device *dev, {
> > switch (cache_level) {
> > case I915_CACHE_LLC_MLC:
> > - if (INTEL_INFO(dev)->gen >= 6)
> > - return AGP_USER_CACHED_MEMORY_LLC_MLC;
> > /* Older chipsets do not have this extra level of
> > CPU
> > * cacheing, so fallthrough and request the PTE
> > simply
> > * as cached.
> > */
> > + if (INTEL_INFO(dev)->gen >= 6 && !IS_HASWELL(dev))
> > + return AGP_USER_CACHED_MEMORY_LLC_MLC;
> > case I915_CACHE_LLC:
> > return AGP_USER_CACHED_MEMORY;
> > default:
>
> We might want a .has_mlc or something here at some point, but that
> doesn't have to happen here.
>
> Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
>
To be clear, HSW has MLC, (and I'd vote we converge on calling calling
it GPU L3 or something since docs don't seem to use the term MLC
anymore) it just doesn't get set in the PTE anymore.
next prev parent reply other threads:[~2012-10-26 1:04 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-23 1:34 [PATCH 00/10] Kill AGP dependencies for Gen6+ Ben Widawsky
2012-10-23 1:34 ` [PATCH 01/10] drm/i915: No LLC_MLC for HSW Ben Widawsky
2012-10-23 10:15 ` Mika Kuoppala
2012-10-25 20:47 ` Jesse Barnes
2012-10-26 1:03 ` Ben Widawsky [this message]
2012-10-23 1:34 ` [PATCH 02/10] drm/i915: Add dev to ppgtt Ben Widawsky
2012-10-25 20:48 ` Jesse Barnes
2012-10-23 1:34 ` [PATCH 03/10] drm/i915: introduce gtt_pte_t Ben Widawsky
2012-10-25 20:49 ` Jesse Barnes
2012-10-23 1:34 ` [PATCH 04/10] drm/i915: Extract PPGTT pte encoding Ben Widawsky
2012-10-25 20:50 ` Jesse Barnes
2012-10-23 1:34 ` [PATCH 05/10] drm/i915: move more pte encoding to pte encode Ben Widawsky
2012-10-25 20:51 ` Jesse Barnes
2012-10-31 10:52 ` Daniel Vetter
2012-10-23 1:34 ` [PATCH 06/10] drm/i915: Stop using AGP layer for GEN6+ Ben Widawsky
2012-10-23 9:59 ` Chris Wilson
2012-10-23 14:57 ` Ben Widawsky
2012-10-23 14:58 ` Daniel Vetter
2012-10-23 19:57 ` Ben Widawsky
2012-10-23 20:03 ` Daniel Vetter
2012-10-23 20:27 ` Ben Widawsky
2012-10-25 20:55 ` Jesse Barnes
2012-10-25 20:54 ` Jesse Barnes
[not found] ` <878vaxwk61.fsf@gaia.fi.intel.com>
2012-10-24 17:56 ` Ben Widawsky
2012-10-26 20:54 ` [PATCH 06/10 v2] " Ben Widawsky
2012-10-29 2:08 ` [PATCH 6/9 v3] " Ben Widawsky
2012-10-31 9:57 ` Daniel Vetter
2012-10-31 15:51 ` Ben Widawsky
2012-10-31 10:37 ` [PATCH 06/10 v2] " Chris Wilson
2012-10-23 1:34 ` [PATCH 07/10] drm/i915: Calculate correct stolen size for GEN7+ Ben Widawsky
2012-10-25 21:06 ` Jesse Barnes
2012-10-25 22:15 ` Ben Widawsky
2012-10-25 22:39 ` Jesse Barnes
2012-10-23 1:34 ` [PATCH 08/10] drm/i915: Kill off now unused gen6+ AGP code Ben Widawsky
2012-10-25 21:07 ` Jesse Barnes
2012-10-23 1:34 ` [PATCH 09/10] drm/i915: flush system agent TLBs on SNB Ben Widawsky
2012-10-23 14:17 ` Jesse Barnes
2012-10-23 14:28 ` Daniel Vetter
2012-10-23 14:35 ` Jesse Barnes
2012-10-23 14:42 ` Ben Widawsky
2012-10-25 21:07 ` Jesse Barnes
2012-10-26 20:55 ` [PATCH 09/10 v2] " Ben Widawsky
2012-10-23 1:34 ` [PATCH 10/10] drm/i915: Kill off actually requiring AGP Ben Widawsky
2012-10-23 2:03 ` Ben Widawsky
2012-10-25 21:09 ` Jesse Barnes
2012-10-25 22:15 ` Ben Widawsky
2012-10-25 22:39 ` Jesse Barnes
2012-10-25 22:47 ` Daniel Vetter
2012-10-26 20:52 ` Ben Widawsky
2012-10-26 20:58 ` [PATCH 00/10] Kill AGP dependencies for Gen6+ Ben Widawsky
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20121025180343.0000670e@unknown \
--to=ben@bwidawsk.net \
--cc=intel-gfx@lists.freedesktop.org \
--cc=jbarnes@virtuousgeek.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox