From: Ben Widawsky <benjamin.widawsky@intel.com>
To: Damien Lespiau <damien.lespiau@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
Ben Widawsky <ben@bwidawsk.net>,
Intel GFX <intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 1/5] drm/i915/hsw: Set correct Haswell PTE encodings.
Date: Mon, 15 Jul 2013 09:54:35 -0700 [thread overview]
Message-ID: <20130715165434.GA30017@intel.com> (raw)
In-Reply-To: <20130715142300.GB1064@strange.amr.corp.intel.com>
On Mon, Jul 15, 2013 at 03:23:00PM +0100, Damien Lespiau wrote:
> On Thu, Jul 04, 2013 at 11:02:03AM -0700, Ben Widawsky wrote:
> > +/* Cacheability Control is a 4-bit value. The low three bits are stored in *
> > + * bits 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
> > + */
> > +#define HSW_CACHEABILITY_CONTROL(bits) ((((bits) & 0x7) << 1) | \
> > + (((bits) & 0x8) << (11 - 3)))
> > +#define HSW_WB_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x3)
>
> One small note, an age of '0' means "old" as in it's likely to be
> evicted before buffers aged 3, 2 or 1. We don't use any other age yet,
> so it doesn't matter for now, but might in the future.
>
> --
> Damien
>
FWIW, I have no intention of using any ages in the kernel. We can pick 3
equally well. Maybe in a way off future if or when we decide to have the
kernel try to track which cacheability to use for objects, we'll care.
Daniel, would you mind adding a comment on merge? Damien is correct 3 is
youngest, 0 is oldest.
--
Ben Widawsky, Intel Open Source Technology Center
next prev parent reply other threads:[~2013-07-15 16:54 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-04 18:02 [PATCH 1/5] drm/i915/hsw: Set correct Haswell PTE encodings Ben Widawsky
2013-07-04 18:02 ` [PATCH 2/5] drm/i915: Define some of the eLLC magic Ben Widawsky
2013-07-13 0:02 ` Rodrigo Vivi
2013-07-14 20:36 ` Ben Widawsky
2013-07-04 18:02 ` [PATCH 3/5] drm/i915: store eLLC size Ben Widawsky
2013-07-04 18:42 ` [PATCH 3.5/5] drm/i915: Do eLLC detection earlier Ben Widawsky
2013-07-13 0:04 ` Rodrigo Vivi
2013-07-13 9:39 ` Daniel Vetter
2013-07-14 20:37 ` Ben Widawsky
2013-07-16 6:02 ` [PATCH 3/5] drm/i915: store eLLC size Daniel Vetter
2013-07-04 18:02 ` [PATCH 4/5] drm/i915: Use eLLC/LLC by default when available Ben Widawsky
2013-07-04 18:17 ` Daniel Vetter
2013-07-04 18:40 ` Ben Widawsky
2013-07-13 0:08 ` Rodrigo Vivi
2013-07-04 18:02 ` [PATCH 5/5] drm/i915: debugfs entries for [e]LLC Ben Widawsky
2013-07-04 18:14 ` Daniel Vetter
2013-07-04 18:40 ` Ben Widawsky
2013-07-04 18:43 ` Daniel Vetter
2013-07-04 18:46 ` Ben Widawsky
2013-07-09 18:35 ` Chad Versace
2013-07-09 20:16 ` Ben Widawsky
2013-07-04 18:47 ` [PATCH 6/6] drm/i915: Add a param for eLLC size Ben Widawsky
2013-07-16 6:10 ` Daniel Vetter
2013-07-13 0:11 ` [PATCH 5/5] drm/i915: debugfs entries for [e]LLC Rodrigo Vivi
2013-07-13 0:00 ` [PATCH 1/5] drm/i915/hsw: Set correct Haswell PTE encodings Rodrigo Vivi
2013-07-14 20:34 ` Ben Widawsky
2013-07-15 14:16 ` Damien Lespiau
2013-07-15 14:23 ` Damien Lespiau
2013-07-15 16:54 ` Ben Widawsky [this message]
2013-07-16 6:00 ` Daniel Vetter
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=20130715165434.GA30017@intel.com \
--to=benjamin.widawsky@intel.com \
--cc=ben@bwidawsk.net \
--cc=damien.lespiau@intel.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox