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 20/20] drm/i915/selftests: Always flush before unpining after writing
Date: Mon, 11 May 2020 08:57:22 +0100	[thread overview]
Message-ID: <20200511075722.13483-20-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200511075722.13483-1-chris@chris-wilson.co.uk>

Be consistent, and even when we know we had used a WC, flush the mapped
object after writing into it. The flush understands the mapping type and
will only flush the WCB if I915_MAP_WC.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_object_blt.c          | 8 ++++++--
 drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c | 2 ++
 drivers/gpu/drm/i915/gt/selftest_ring_submission.c      | 2 ++
 drivers/gpu/drm/i915/gt/selftest_rps.c                  | 2 ++
 drivers/gpu/drm/i915/selftests/i915_request.c           | 9 +++++++--
 5 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
index 2fc7737ef5f4..f457d7130491 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
@@ -78,10 +78,12 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 	} while (rem);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(ce->vm->gt);
 
+	i915_gem_object_flush_map(pool->obj);
 	i915_gem_object_unpin_map(pool->obj);
 
+	intel_gt_chipset_flush(ce->vm->gt);
+
 	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
@@ -289,10 +291,12 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	} while (rem);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(ce->vm->gt);
 
+	i915_gem_object_flush_map(pool->obj);
 	i915_gem_object_unpin_map(pool->obj);
 
+	intel_gt_chipset_flush(ce->vm->gt);
+
 	batch = i915_vma_instance(pool->obj, ce->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 3f6079e1dfb6..87d7d8aa080f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -158,6 +158,8 @@ static int wc_set(struct context *ctx, unsigned long offset, u32 v)
 		return PTR_ERR(map);
 
 	map[offset / sizeof(*map)] = v;
+
+	__i915_gem_object_flush_map(ctx->obj, offset, sizeof(*map));
 	i915_gem_object_unpin_map(ctx->obj);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
index 9995faadd7e8..3350e7c995bc 100644
--- a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c
@@ -54,6 +54,8 @@ static struct i915_vma *create_wally(struct intel_engine_cs *engine)
 	*cs++ = STACK_MAGIC;
 
 	*cs++ = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
 	vma->private = intel_context_create(engine); /* dummy residuals */
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index bfa1a15564f7..6275d69aa9cc 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -727,6 +727,7 @@ int live_rps_frequency_cs(void *arg)
 
 err_vma:
 		*cancel = MI_BATCH_BUFFER_END;
+		i915_gem_object_flush_map(vma->obj);
 		i915_gem_object_unpin_map(vma->obj);
 		i915_vma_unpin(vma);
 		i915_vma_put(vma);
@@ -868,6 +869,7 @@ int live_rps_frequency_srm(void *arg)
 
 err_vma:
 		*cancel = MI_BATCH_BUFFER_END;
+		i915_gem_object_flush_map(vma->obj);
 		i915_gem_object_unpin_map(vma->obj);
 		i915_vma_unpin(vma);
 		i915_vma_put(vma);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index ffdfcb3805b5..6014e8dfcbb1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -816,10 +816,12 @@ static int recursive_batch_resolve(struct i915_vma *batch)
 		return PTR_ERR(cmd);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(batch->vm->gt);
 
+	__i915_gem_object_flush_map(batch->obj, 0, sizeof(*cmd));
 	i915_gem_object_unpin_map(batch->obj);
 
+	intel_gt_chipset_flush(batch->vm->gt);
+
 	return 0;
 }
 
@@ -1060,9 +1062,12 @@ static int live_sequential_engines(void *arg)
 					      I915_MAP_WC);
 		if (!IS_ERR(cmd)) {
 			*cmd = MI_BATCH_BUFFER_END;
-			intel_gt_chipset_flush(engine->gt);
 
+			__i915_gem_object_flush_map(request[idx]->batch->obj,
+						    0, sizeof(*cmd));
 			i915_gem_object_unpin_map(request[idx]->batch->obj);
+
+			intel_gt_chipset_flush(engine->gt);
 		}
 
 		i915_vma_put(request[idx]->batch);
-- 
2.20.1

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

  parent reply	other threads:[~2020-05-11  7:58 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-11  7:57 [Intel-gfx] [PATCH 01/20] drm/i915/gt: Mark up the racy read of execlists->context_tag Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 02/20] drm/i915/gt: Couple up old virtual breadcrumb on new sibling Chris Wilson
2020-05-12  8:41   ` Tvrtko Ursulin
2020-05-12  8:49     ` Chris Wilson
2020-05-12 10:12       ` Tvrtko Ursulin
2020-05-12 10:28         ` Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 03/20] dma-buf: Use atomic_fetch_add() for the context id Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 04/20] drm/i915: Mark the addition of the initial-breadcrumb in the request Chris Wilson
2020-05-11 11:21   ` Mika Kuoppala
2020-05-11 11:30     ` Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 05/20] drm/i915: Tidy awaiting on dma-fences Chris Wilson
2020-05-11 11:30   ` Mika Kuoppala
2020-05-11  7:57 ` [Intel-gfx] [PATCH 06/20] dma-buf: Proxy fence, an unsignaled fence placeholder Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 07/20] drm/syncobj: Allow use of dma-fence-proxy Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 08/20] drm/i915/gem: Teach execbuf how to wait on future syncobj Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 09/20] drm/i915/gem: Allow combining submit-fences with syncobj Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 10/20] drm/i915/gt: Declare when we enabled timeslicing Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 11/20] drm/i915/gem: Remove redundant exec_fence Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 12/20] drm/i915: Drop no-semaphore boosting Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 13/20] drm/i915: Move saturated workload detection back to the context Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 14/20] drm/i915: Remove the saturation backoff for HW semaphores Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 15/20] drm/i915/gt: Use built-in active intel_context reference Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 16/20] drm/i915: Drop I915_RESET_TIMEOUT and friends Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 17/20] drm/i915: Drop I915_IDLE_ENGINES_TIMEOUT Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 18/20] drm/i915/selftests: Always call the provided engine->emit_init_breadcrumb Chris Wilson
2020-05-11  7:57 ` [Intel-gfx] [PATCH 19/20] drm/i915: Emit await(batch) before MI_BB_START Chris Wilson
2020-05-11  7:57 ` Chris Wilson [this message]
2020-05-11  8:05 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/20] drm/i915/gt: Mark up the racy read of execlists->context_tag Patchwork
2020-05-11  8:32 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2020-05-11  9:07 ` [Intel-gfx] [PATCH 01/20] " Mika Kuoppala

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=20200511075722.13483-20-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.