As the request now may implicitly invoke a context-switch, we should
follow that with a GPU TLB invalidation. Also even before using GGTT, we
should invalidate the TLBs for any updates (as well as the ppgtt
invalidates that are unconditionally applied by execbuf). Since we
almost always require the TLB invalidate, do it unconditionally on
request allocation and so we can remove it from all other paths.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 7 +------
drivers/gpu/drm/i915/i915_gem_render_state.c | 4 ----
drivers/gpu/drm/i915/i915_gem_request.c | 5 +++++
drivers/gpu/drm/i915/selftests/huge_pages.c | 4 ----
drivers/gpu/drm/i915/selftests/i915_gem_context.c | 4 ----
drivers/gpu/drm/i915/selftests/i915_gem_request.c | 10 ----------
drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 6 ------
7 files changed, 6 insertions(+), 34 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index af49da64ff3a..28e647042908 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1111,10 +1111,6 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
if (err)
goto err_request;
- err = eb->engine->emit_flush(rq, EMIT_INVALIDATE);
- if (err)
- goto err_request;
-
err = eb->engine->emit_bb_start(rq,
batch->node.start, PAGE_SIZE,
cache->gen > 5 ? 0 : I915_DISPATCH_SECURE);
@@ -1814,8 +1810,7 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
/* Unconditionally flush any chipset caches (for streaming writes). */
i915_gem_chipset_flush(eb->i915);
- /* Unconditionally invalidate GPU caches and TLBs. */
- return eb->engine->emit_flush(eb->request, EMIT_INVALIDATE);
+ return true;
}
static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index c2723a06fbb4..f7fc0df251ac 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -208,10 +208,6 @@ int i915_gem_render_state_emit(struct drm_i915_gem_request *rq)
if (err)
goto err_unpin;
- err = engine->emit_flush(rq, EMIT_INVALIDATE);
- if (err)
- goto err_unpin;
-
err = engine->emit_bb_start(rq,
so.batch_offset, so.batch_size,
I915_DISPATCH_SECURE);
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 445495f9893c..2c68a2bbe244 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -718,6 +718,11 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
if (ret)
goto err_ctx;
+ /* Unconditionally invalidate GPU caches and TLBs. */
+ ret = engine->emit_flush(req, EMIT_INVALIDATE);
+ if (ret)
+ goto err_ctx;
+
/* Check that we didn't interrupt ourselves with a new request */
GEM_BUG_ON(req->timeline->seqno != req->fence.seqno);
return req;
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index eb142bd4c9e1..8e6ad64aba91 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -989,10 +989,6 @@ static int gpu_write(struct i915_vma *vma,
i915_vma_unpin(batch);
i915_vma_close(batch);
- err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
- if (err)
- goto err_request;
-
err = rq->engine->emit_bb_start(rq,
batch->node.start, batch->node.size,
flags);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 664d1b4f8c69..09340b3c1156 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -158,10 +158,6 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
goto err_batch;
}
- err = engine->emit_flush(rq, EMIT_INVALIDATE);
- if (err)
- goto err_request;
-
flags = 0;
if (INTEL_GEN(vm->i915) <= 5)
flags |= I915_DISPATCH_SECURE;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_request.c b/drivers/gpu/drm/i915/selftests/i915_gem_request.c
index e3871db78beb..647bf2bbd799 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_request.c
@@ -459,10 +459,6 @@ empty_request(struct intel_engine_cs *engine,
if (IS_ERR(request))
return request;
- err = engine->emit_flush(request, EMIT_INVALIDATE);
- if (err)
- goto out_request;
-
err = engine->emit_bb_start(request,
batch->node.start,
batch->node.size,
@@ -671,9 +667,6 @@ static int live_all_engines(void *arg)
goto out_request;
}
- err = engine->emit_flush(request[id], EMIT_INVALIDATE);
- GEM_BUG_ON(err);
-
err = engine->emit_bb_start(request[id],
batch->node.start,
batch->node.size,
@@ -790,9 +783,6 @@ static int live_sequential_engines(void *arg)
}
}
- err = engine->emit_flush(request[id], EMIT_INVALIDATE);
- GEM_BUG_ON(err);
-
err = engine->emit_bb_start(request[id],
batch->node.start,
batch->node.size,
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index cafe39e2e0f7..f91e8c3e4ad8 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -114,10 +114,6 @@ static int emit_recurse_batch(struct hang *h,
if (err)
goto unpin_vma;
- err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
- if (err)
- goto unpin_hws;
-
i915_vma_move_to_active(vma, rq, 0);
if (!i915_gem_object_has_active_reference(vma->obj)) {
i915_gem_object_get(vma->obj);
@@ -169,8 +165,6 @@ static int emit_recurse_batch(struct hang *h,
err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
-unpin_hws:
- i915_vma_unpin(hws);
unpin_vma:
i915_vma_unpin(vma);
return err;
--
2.15.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
