Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Jim Cromie <jim.cromie@gmail.com>
To:     Maarten Lankhorst <maarten.lankhorst@linux.intel.com>,
        Maxime Ripard <mripard@kernel.org>,
        Thomas Zimmermann <tzimmermann@suse.de>,
        David Airlie <airlied@linux.ie>,
        Daniel Vetter <daniel@ffwll.ch>,
        Zhenyu Wang <zhenyuw@linux.intel.com>,
        Zhi Wang <zhi.a.wang@intel.com>,
        Jani Nikula <jani.nikula@linux.intel.com>,
        Joonas Lahtinen <joonas.lahtinen@linux.intel.com>,
        Rodrigo Vivi <rodrigo.vivi@intel.com>,
        dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
        intel-gvt-dev@lists.freedesktop.org,
        intel-gfx@lists.freedesktop.org
Cc:     jbaron@akamai.com, Jim Cromie <jim.cromie@gmail.com>
Subject: [RFC PATCH v2 0/4] Allow using dyndbg to replace drm_debug_enabled
Date:   Sat, 10 Jul 2021 23:49:58 -0600
Message-Id: <20210711055003.528167-1-jim.cromie@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

drm_debug_enabled() is called a lot to do unlikely bit-tests to
control debug printing; this is a good job for dynamic-debug, IFF it
is built with JUMP_LABEL.
 
Enable the use of dynamic-debug to avoid drm_debug_enabled()
overheads, opt in with CONFIG_DRM_USE_DYNAMIC_DEBUG=y.

I have this patchset running bare-metal on an i915 laptop & an amdgpu
desktop (both as loadable modules).

I booted the amdgpu box with:

BOOT_IMAGE=(hd2,gpt2)/vmlinuz-5.13.0-dd7-13692-g8def25788f56 \
     root=UUID=mumble ro \
     rootflags=subvol=root00 rhgb \
     dynamic_debug.verbose=3 main.dyndbg=+p \
     amdgpu.debug=1 amdgpu.test=1 \
     "amdgpu.dyndbg=format ^[ +p"

That last line activates ~1700 callsites with a format like '[DML' etc
at boot, causing ~76k prdbgs in 409 seconds, before I turned them off
with:

  echo module amdgpu -p > /proc/dynamic_debug/control

[root@gandalf jimc]# journalctl -b-0 | grep -P '\[(DML|VBLANK|SURFACE|BIOS|BANDWIDTH)' | wc
  68708  578503 5054437
[root@gandalf jimc]# journalctl -b-0 | grep -P '\[(DML|VBLANK|SURFACE|BIOS|BANDWIDTH|\w+)' | wc
  76298  661176 6028087

IOW, things appear to hold up under some stress.

this is on top of master @ v5.13-13688-gde5540965853

v1 is here:
https://lore.kernel.org/lkml/20201204035318.332419-1-jim.cromie@gmail.com/

Jim Cromie (4):
  drm_print.h: rewrap __DRM_DEFINE_DBG_RATELIMITED macro
  drm: fixup comment spelling
  drm: RFC add choice to use dynamic debug in drm-debug
  i915: map gvt pr_debug categories to bits in parameters/debug_gvt

 drivers/gpu/drm/Kconfig            |  13 ++++
 drivers/gpu/drm/drm_print.c        |  75 +++++++++++++++++-
 drivers/gpu/drm/i915/gvt/Makefile  |   4 +
 drivers/gpu/drm/i915/i915_params.c |  76 ++++++++++++++++++
 include/drm/drm_print.h            | 119 ++++++++++++++++++++---------
 5 files changed, 249 insertions(+), 38 deletions(-)

-- 
2.31.1