All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Vetter <daniel.vetter@ffwll.ch>
To: DRI Development <dri-devel@lists.freedesktop.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
	Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
	Daniel Vetter <daniel.vetter@intel.com>,
	Mika Kuoppala <mika.kuoppala@intel.com>
Subject: [PATCH 3/9] drm/i915: Avoid the gpu reset vs. modeset deadlock
Date: Wed, 19 Jul 2017 14:54:56 +0200	[thread overview]
Message-ID: <20170719125502.25696-4-daniel.vetter@ffwll.ch> (raw)
In-Reply-To: <20170719125502.25696-1-daniel.vetter@ffwll.ch>

... using the biggest hammer we have. This is essentially a weaponized
version of the timeout-based wedging Chris added in

commit 36703e79a982c8ce5a8e43833291f2719e92d0d1
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Thu Jun 22 11:56:25 2017 +0100

    drm/i915: Break modeset deadlocks on reset

Because defense-in-depth is good it's good to still have both. Also
note that with the locking change we can now restrict this a lot (old
gpus and special testing only), so this doesn't kill the TDR benefits
on at least anything remotely modern.

And futuremore with a few tricks it should be possible to make a much
more educated guess about whether an atomic commit is stuck waiting on
the gpu (atomic_t counting the pending i915_sw_fence used by the
atomic modeset code should do it), so we can improve this.

But for now just start with something that is guaranteed to recover
faster, for much better CI througput.

This defacto reverts TDR on these platforms, but there's not really a
single commit to specify as the sole offender.

Fixes: 4680816be336 ("drm/i915: Wait first for submission, before waiting for request completion")
Fixes: 221fe7994554 ("drm/i915: Perform a direct reset of the GPU from the waiter")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 97777ffa1566..010a1f3e000c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3471,6 +3471,11 @@ void intel_prepare_reset(struct drm_i915_private *dev_priv)
 	    !gpu_reset_clobbers_display(dev_priv))
 		return;
 
+	/* We have a modeset vs reset deadlock, defensively unbreak it.
+	 *
+	 * FIXME: We can do a _lot_ better, this is just a first iteration.*/
+	i915_gem_set_wedged(dev_priv);
+
 	/*
 	 * Need mode_config.mutex so that we don't
 	 * trample ongoing ->detect() and whatnot.
-- 
2.13.2

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

  parent reply	other threads:[~2017-07-19 12:54 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-19 12:54 [PATCH 0/9] gpu reset vs modeset fix, plus page_flip removal Daniel Vetter
2017-07-19 12:54 ` [PATCH 1/9] drm/i915: Nuke legacy flip queueing code Daniel Vetter
2017-07-19 12:54 ` [PATCH 2/9] drm/i915: Unbreak gpu reset vs. modeset locking Daniel Vetter
2017-07-19 12:54 ` Daniel Vetter [this message]
2017-07-19 13:32   ` [PATCH 3/9] drm/i915: Avoid the gpu reset vs. modeset deadlock Chris Wilson
2017-07-19 13:44     ` Daniel Vetter
2017-07-19 18:44       ` Daniel Vetter
2017-07-19 12:54 ` [PATCH 4/9] drm/i915: Push i915_sw_fence_wait into the nonblocking atomic commit Daniel Vetter
2017-07-19 13:04   ` Chris Wilson
2017-07-19 13:14     ` Daniel Vetter
2017-07-19 12:54 ` [PATCH 5/9] drm/i915: More surgically unbreak the modeset vs reset deadlock Daniel Vetter
2017-07-19 13:42   ` Chris Wilson
2017-07-19 14:05     ` Daniel Vetter
2017-07-19 14:11       ` Daniel Vetter
2017-07-19 12:54 ` [PATCH 6/9] drm/i915: Rip out legacy page_flip completion/irq handling Daniel Vetter
2017-07-19 12:55 ` [PATCH 7/9] drm/i915: adjust has_pending_fb_unpin to atomic Daniel Vetter
2017-07-19 13:06   ` Chris Wilson
2017-07-19 13:15     ` Daniel Vetter
2017-07-19 14:08       ` [Intel-gfx] " Chris Wilson
2017-07-19 12:55 ` [PATCH 8/9] drm/i915: Remove intel_flip_work infrastructure Daniel Vetter
2017-07-19 13:07   ` Chris Wilson
2017-07-19 13:24     ` [Intel-gfx] " Daniel Vetter
2017-07-19 14:16       ` Chris Wilson
2017-07-19 12:55 ` [PATCH 9/9] drm/i915: Drop unpin stall in atomic_prepare_commit Daniel Vetter
2017-07-19 13:09   ` Chris Wilson
2017-07-19 13:20     ` Daniel Vetter
2017-07-19 14:01   ` Maarten Lankhorst
2017-07-20  8:46     ` Daniel Vetter
2017-07-19 14:15 ` ✓ Fi.CI.BAT: success for gpu reset vs modeset fix, plus page_flip removal Patchwork
2017-07-19 14:46   ` Chris Wilson

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=20170719125502.25696-4-daniel.vetter@ffwll.ch \
    --to=daniel.vetter@ffwll.ch \
    --cc=daniel.vetter@intel.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=mika.kuoppala@intel.com \
    /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.