All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 10/10] drm/i915: Detect if we missed kicking the execlists tasklet
Date: Mon, 14 May 2018 10:37:10 +0100	[thread overview]
Message-ID: <20180514093710.7730-11-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20180514093710.7730-1-chris@chris-wilson.co.uk>

If inside hangcheck we see that the engine has paused, but there is an
execlists interrupt still pending, we know that the tasklet did not
fire. Dump the GEM trace along with the current engine state, and kick
the tasklet to recovery without having to go through a GPU reset.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_hangcheck.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index d47e346bd49e..4b0745d94ab8 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -267,6 +267,21 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd)
 		}
 	}
 
+	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) {
+		if (GEM_SHOW_DEBUG()) {
+			struct drm_printer p = drm_debug_printer("hangcheck");
+
+			GEM_TRACE_DUMP();
+			intel_engine_dump(engine, &p,
+					  "%s CS stuck\n", engine->name);
+		}
+
+		if (i915_tasklet_try(&engine->execlists.tasklet))
+			return ENGINE_WAIT_KICK;
+
+		return ENGINE_WAIT;
+	}
+
 	return ENGINE_DEAD;
 }
 
-- 
2.17.0

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

  parent reply	other threads:[~2018-05-14  9:37 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-14  9:37 Direct execlists submission Chris Wilson
2018-05-14  9:37 ` [PATCH 01/10] drm/i915: Mark up nested spinlocks Chris Wilson
2018-05-14 10:06   ` Tvrtko Ursulin
2018-05-14  9:37 ` [PATCH 02/10] drm/i915: Remove tasklet flush before disable Chris Wilson
2018-05-14  9:37 ` [PATCH 03/10] drm/i915: Wrap tasklet_struct for abuse Chris Wilson
2018-05-14  9:37 ` [PATCH 04/10] drm/i915: Only sync tasklets once for recursive reset preparation Chris Wilson
2018-05-14  9:37 ` [PATCH 05/10] drm/i915/execlists: Direct submit onto idle engines Chris Wilson
2018-05-14  9:37 ` [PATCH 06/10] drm/i915/execlists: Direct submission from irq handler Chris Wilson
2018-05-14  9:37 ` [PATCH 07/10] drm/i915: Rearrange gen8_cs_irq_handler Chris Wilson
2018-05-14  9:37 ` [PATCH 08/10] drm/i915: Remove USES_GUC_SUBMISSION() pointer chasing from gen8_cs_irq_handler Chris Wilson
2018-05-14 10:27   ` Tvrtko Ursulin
2018-05-14 11:45     ` Chris Wilson
2018-05-14  9:37 ` [PATCH 09/10] drm/i915: Speed up idle detection by kicking the tasklets Chris Wilson
2018-05-14  9:37 ` Chris Wilson [this message]
2018-05-14  9:42 ` ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/10] drm/i915: Mark up nested spinlocks Patchwork
2018-05-14  9:45 ` ✗ Fi.CI.SPARSE: " Patchwork
2018-05-14  9:59 ` ✓ Fi.CI.BAT: success " Patchwork
2018-05-14 10:11 ` Direct execlists submission Tvrtko Ursulin
2018-05-14 10:25   ` Chris Wilson
2018-05-14 14:54     ` Chris Wilson
2018-05-14 12:45 ` ✓ Fi.CI.IGT: success for series starting with [01/10] drm/i915: Mark up nested spinlocks 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=20180514093710.7730-11-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --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.