All of lore.kernel.org
 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 5/5] drm/i915/gt: Disable arbitration on no-preempt requests
Date: Thu,  7 Jan 2021 22:17:24 +0000	[thread overview]
Message-ID: <20210107221724.10036-5-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20210107221724.10036-1-chris@chris-wilson.co.uk>

If a request is submitted and known to require no preemption, disable
arbitration around the batch which prevents the HW from handling a
preemption request during the payload.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 6 +++---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c       | 3 +++
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index cf9a6b4eb913..b91b32195dcf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2534,6 +2534,9 @@ static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch)
 {
 	int err;
 
+	if (intel_context_nopreempt(eb->context))
+		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags);
+
 	err = eb_move_to_gpu(eb);
 	if (err)
 		return err;
@@ -2574,9 +2577,6 @@ static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch)
 			return err;
 	}
 
-	if (intel_context_nopreempt(eb->context))
-		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 1972dd5dca00..2e36e0a9d8a6 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -427,6 +427,9 @@ int gen8_emit_bb_start(struct i915_request *rq,
 {
 	u32 *cs;
 
+	if (unlikely(i915_request_has_nopreempt(rq)))
+		return gen8_emit_bb_start_noarb(rq, offset, len, flags);
+
 	cs = intel_ring_begin(rq, 6);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
-- 
2.20.1

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

  parent reply	other threads:[~2021-01-07 22:17 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-07 22:17 [Intel-gfx] [PATCH 1/5] drm/i915/selftests: Skip unstable timing measurements Chris Wilson
2021-01-07 22:17 ` [Intel-gfx] [PATCH 2/5] drm/i915/gt: Restore ce->signal flush before releasing virtual engine Chris Wilson
2021-01-08 15:18   ` Andi Shyti
2021-01-08 15:24     ` Chris Wilson
2021-01-08 15:54       ` Andi Shyti
2021-01-07 22:17 ` [Intel-gfx] [PATCH 3/5] drm/i915/gt: Only retire on the last breadcrumb if the last request Chris Wilson
2021-01-08 15:55   ` Andi Shyti
2021-01-07 22:17 ` [Intel-gfx] [PATCH 4/5] drm/i915/gt: Only disable preemption on gen8 render engines Chris Wilson
2021-01-08 15:24   ` Andi Shyti
2021-01-07 22:17 ` Chris Wilson [this message]
2021-01-08 15:27   ` [Intel-gfx] [PATCH 5/5] drm/i915/gt: Disable arbitration on no-preempt requests Andi Shyti
2021-01-07 23:07 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [1/5] drm/i915/selftests: Skip unstable timing measurements Patchwork
2021-01-07 23:09 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-01-07 23:38 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2021-01-08  0:16 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [1/5] drm/i915/selftests: Skip unstable timing measurements (rev2) Patchwork
2021-01-08  0:18 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-01-08  0:45 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-01-08  2:59 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
2021-01-08 12:26 ` [Intel-gfx] [PATCH 1/5] drm/i915/selftests: Skip unstable timing measurements Andi Shyti
2021-01-08 13:26   ` Chris Wilson
2021-01-08 13:51     ` Andi Shyti
2021-01-08 13:54       ` Chris Wilson
2021-01-08 15:04         ` Andi Shyti
2021-01-08 13:28 ` [Intel-gfx] [PATCH] " Chris Wilson
2021-01-08 15:14   ` Chris Wilson
2021-01-08 15:25     ` Andi Shyti
2021-01-08 18:14 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with drm/i915/selftests: Skip unstable timing measurements (rev4) Patchwork
2021-01-08 18:16 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-01-08 18:45 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " 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=20210107221724.10036-5-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.