From: Ben Widawsky <ben@bwidawsk.net>
To: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Intel Graphics Development <intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 4/7] drm/i915: properly set ppgtt cacheability on snb
Date: Tue, 10 Apr 2012 15:11:07 -0700 [thread overview]
Message-ID: <20120410221107.GD21080@bolo_yeung.jf.intel.com> (raw)
In-Reply-To: <1333185723-5047-5-git-send-email-daniel.vetter@ffwll.ch>
On Sat, Mar 31, 2012 at 11:22:00AM +0200, Daniel Vetter wrote:
> For some reason snb has 2 fields to set ppgtt cacheability. This one
> here does not exist on gen7.
>
> This might explain why ppgtt wasn't a win on snb like on ivb - not
> enough pte caching.
So, is it a win now?
>
> Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 3 +++
> drivers/gpu/drm/i915/i915_reg.h | 4 ++++
> 2 files changed, 7 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 5dc5f42..cab70ef 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -3766,6 +3766,9 @@ void i915_gem_init_ppgtt(struct drm_device *dev)
> if (INTEL_INFO(dev)->gen == 6) {
> uint32_t ecochk, gab_ctl, ecobits;
>
> + ecobits = I915_READ(GAC_ECO_BITS);
> + I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
> +
> gab_ctl = I915_READ(GAB_CTL);
> I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);
>
Is this a bad rebase? This doesn't apply to whatever I am using.
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index e72c251..5457980 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -125,6 +125,10 @@
> #define ECOCHK_PPGTT_CACHE64B (0x3<<3)
> #define ECOCHK_PPGTT_CACHE4B (0x0<<3)
>
> +#define GAC_ECO_BITS 0x14090
> +#define ECOBITS_PPGTT_CACHE64B (3<<8)
> +#define ECOBITS_PPGTT_CACHE4B (0<<8)
> +
> #define GAB_CTL 0x24000
> #define GAB_CTL_CONT_AFTER_PAGEFAULT (1<<8)
>
According to bspec, but 13 must be set to a 1 also.
next prev parent reply other threads:[~2012-04-10 22:11 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-31 9:21 [PATCH 0/7] A set of SNB workarounds Daniel Vetter
2012-03-31 9:21 ` [PATCH 1/7] drm/i915: implement ColorBlt w/a Daniel Vetter
2012-03-31 10:54 ` Chris Wilson
2012-03-31 13:15 ` Chris Wilson
2012-04-10 9:08 ` Michael Groh
2012-04-10 9:54 ` Paul Menzel
2012-04-10 22:24 ` Ben Widawsky
2012-04-11 10:18 ` Daniel Vetter
2012-03-31 9:21 ` [PATCH 2/7] drm/i915: implement a media hang w/a Daniel Vetter
2012-04-10 21:30 ` Ben Widawsky
2012-04-10 21:34 ` Ben Widawsky
2012-04-10 21:36 ` Ben Widawsky
2012-03-31 9:21 ` [PATCH 3/7] drm/i915: set w/a bit for snb pagefaults Daniel Vetter
2012-04-10 21:46 ` Ben Widawsky
2012-03-31 9:22 ` [PATCH 4/7] drm/i915: properly set ppgtt cacheability on snb Daniel Vetter
2012-04-10 22:11 ` Ben Widawsky [this message]
2012-04-10 22:27 ` Daniel Vetter
2012-04-10 22:35 ` Ben Widawsky
2012-03-31 9:22 ` [PATCH 5/7] drm/i915: implement w/a for incorrect guarband clipping Daniel Vetter
2012-04-10 22:13 ` Ben Widawsky
2012-04-10 22:20 ` Daniel Vetter
2012-03-31 9:22 ` [PATCH 6/7] drm/i915: implement async flush w/a Daniel Vetter
2012-03-31 10:52 ` Chris Wilson
2012-04-10 9:53 ` Paul Menzel
2012-04-10 22:22 ` Ben Widawsky
2012-03-31 9:22 ` [PATCH 7/7] drm/i915: set stc evict disable lra evict w/a Daniel Vetter
2012-04-10 22:31 ` 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=20120410221107.GD21080@bolo_yeung.jf.intel.com \
--to=ben@bwidawsk.net \
--cc=daniel.vetter@ffwll.ch \
--cc=intel-gfx@lists.freedesktop.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.