intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH v2] drm/i915: Check for awaits on still currently executing requests
Date: Fri, 29 May 2020 11:09:27 +0100	[thread overview]
Message-ID: <20200529100927.2193-1-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200529085809.23691-2-chris@chris-wilson.co.uk>

With the advent of preempt-to-busy, a request may still be on the GPU as
we unwind. And in the case of a unpreemptible [due to HW] request, that
request will remain indefinitely on the GPU even though we have
returned it back to our submission queue, and cleared the active bit.

We only run the execution callbacks on transferring the request from our
submission queue to the execution queue, but if this is a bonded request
that the HW is waiting for, we will not submit it (as we wait for a
fresh execution) even though it is still being executed.

As we know that there are always preemption points between requests, we
know that only the currently executing request may be still active even
though we have cleared the flag.

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Testcase: igt/gem_exec_balancer/bonded-dual
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_request.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index e5aba6824e26..dfc143f81168 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -363,6 +363,16 @@ static void __llist_add(struct llist_node *node, struct llist_head *head)
 	head->first = node;
 }
 
+static bool __request_in_flight(struct i915_request *signal)
+{
+	bool result = false;
+
+	if (intel_context_inflight(signal->context))
+		result = signal == execlists_active(&signal->engine->execlists);
+
+	return result;
+}
+
 static int
 __await_execution(struct i915_request *rq,
 		  struct i915_request *signal,
@@ -393,7 +403,7 @@ __await_execution(struct i915_request *rq,
 	}
 
 	spin_lock_irq(&signal->lock);
-	if (i915_request_is_active(signal)) {
+	if (i915_request_is_active(signal) || __request_in_flight(signal)) {
 		if (hook) {
 			hook(rq, &signal->fence);
 			i915_request_put(signal);
-- 
2.20.1

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

  reply	other threads:[~2020-05-29 10:10 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-29  8:58 [Intel-gfx] [PATCH 1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() Chris Wilson
2020-05-29  8:58 ` [Intel-gfx] [PATCH 2/2] drm/i915: Once executed, always executed Chris Wilson
2020-05-29 10:09   ` Chris Wilson [this message]
2020-05-29 10:17   ` [Intel-gfx] [PATCH v3] drm/i915: Check for awaits on still currently executing requests Chris Wilson
2020-05-29 12:28   ` [Intel-gfx] [PATCH v4] " Chris Wilson
2020-05-29 14:03     ` Chris Wilson
2020-05-29 14:39     ` [Intel-gfx] [PATCH v2] " Chris Wilson
2020-05-29 16:01       ` Tvrtko Ursulin
2020-05-29  9:28 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() Patchwork
2020-05-29 10:31 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2020-05-29 10:44 ` [Intel-gfx] ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() (rev2) Patchwork
2020-05-29 11:33 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() (rev3) Patchwork
2020-05-29 12:54 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
2020-05-29 13:18 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() (rev4) Patchwork
2020-05-29 13:57 ` [Intel-gfx] [PATCH 1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() Tvrtko Ursulin
2020-05-29 14:44 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() (rev4) Patchwork
2020-05-29 15:24 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() (rev5) Patchwork
2020-05-29 17:42 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2020-05-29 17:46 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Add a few asserts around handling of i915_request_is_active() (rev6) Patchwork
2020-05-29 20:07 ` [Intel-gfx] ✓ Fi.CI.IGT: " 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=20200529100927.2193-1-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).