All of lore.kernel.org
 help / color / mirror / Atom feed
From: kai.chen@intel.com
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 0/2] Disable and remove decoupled MMIO feature
Date: Tue, 23 May 2017 14:58:10 -0700	[thread overview]
Message-ID: <20170523215812.18328-1-kai.chen@intel.com> (raw)

From: Kai Chen <kai.chen@intel.com>

In theory, decoupled mmio should require less cycles for single read/write 
operation by avoiding frequent software forcewake. However, it turns out 
this design not to be true on HW reality and not to provide any decoupling 
benefit. It also introduces problems which cause failures in intel-gpu-tools
tests (gem), and also cause driver code and debugging more complex.

The patch set is organized as follows:
 - Patch 1 is to disable decoupled MMIO. This patch can also be backported
   to other shipped kernel as a quick fix.
 - Patch 2 is to totally remove implemented decoupled MMIO code on top of
   Patch 1.

Kai Chen (2):
  drm/i915: Disable decoupled MMIO
  drm/i915: Remove decoupled MMIO code

 drivers/gpu/drm/i915/i915_drv.h     |   3 -
 drivers/gpu/drm/i915/i915_pci.c     |   1 -
 drivers/gpu/drm/i915/i915_reg.h     |   7 --
 drivers/gpu/drm/i915/intel_uncore.c | 126 ------------------------------------
 4 files changed, 137 deletions(-)

-- 
2.9.3

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

             reply	other threads:[~2017-05-23 21:57 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-23 21:58 kai.chen [this message]
2017-05-23 21:58 ` [PATCH 1/2] drm/i915: Disable decoupled MMIO kai.chen
2017-05-24  9:06   ` Tvrtko Ursulin
2017-05-23 21:58 ` [PATCH 2/2] drm/i915: Remove decoupled MMIO code kai.chen
2017-05-24  9:08   ` Tvrtko Ursulin
2017-05-30  7:05     ` Jani Nikula
2017-05-23 22:12 ` ✓ Fi.CI.BAT: success for Disable and remove decoupled MMIO feature Patchwork
2017-05-24  5:33   ` Saarinen, Jani
2017-05-24  8:54 ` Patchwork

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=20170523215812.18328-1-kai.chen@intel.com \
    --to=kai.chen@intel.com \
    --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.