[PATCH v3 1/2] drm/i915/gvt: optimization of context shadowing

[Yan Zhao]

Software is not expected to populate engine context except when using
restore inhibit bit or golden state to initialize it for the first time.

Therefore, if a newly submitted guest context is the same as the last
shadowed one, no need to populate its engine context from guest again.

Currently using lrca + ring_context_gpa to identify whether two guest
contexts are the same.

The reason of why context id is not included as an identifier is that
i915 recently changed the code and context id is only unique for a
context when OA is enabled. And when OA is on, context id is generated
based on lrca. Therefore, in that case, if two contexts are of the same
lrca, they have identical context ids as well.

This patch also works with old guest kernel like 4.20.

v3: updated commit message to describe engine context and context id
clearly (Kevin Tian)
v2: rebased to 5.6.0-rc4+
Signed-off-by: Yan Zhao <yan.y.zhao at intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.h       |  4 ++++
 drivers/gpu/drm/i915/gvt/scheduler.c | 25 ++++++++++++++++++++-----
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 58c2c7932e3f..e2d7ffd84457 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -163,6 +163,10 @@ struct intel_vgpu_submission {
 	const struct intel_vgpu_submission_ops *ops;
 	int virtual_submission_interface;
 	bool active;
+	struct {
+		u32 lrca;
+		u64 ring_context_gpa;
+	} last_ctx[I915_NUM_ENGINES];
 };
 
 struct intel_vgpu {
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 1c95bf8cbed0..a66050a3d65a 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -134,7 +134,10 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	struct page *page;
 	void *dst;
 	unsigned long context_gpa, context_page_num;
+	struct intel_vgpu_submission *s = &vgpu->submission;
 	int i;
+	bool skip = false;
+	int ring_id = workload->engine->id;
 
 	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
 	shadow_ring_context = kmap(page);
@@ -171,12 +174,22 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	sr_oa_regs(workload, (u32 *)shadow_ring_context, false);
 	kunmap(page);
 
-	if (IS_RESTORE_INHIBIT(shadow_ring_context->ctx_ctrl.val))
-		return 0;
+	gvt_dbg_sched("ring %s workload lrca %x, ctx_id %x, ctx gpa %llx",
+			workload->engine->name, workload->ctx_desc.lrca,
+			workload->ctx_desc.context_id,
+			workload->ring_context_gpa);
 
-	gvt_dbg_sched("ring %s workload lrca %x",
-		      workload->engine->name,
-		      workload->ctx_desc.lrca);
+	if ((s->last_ctx[ring_id].lrca ==
+				workload->ctx_desc.lrca) &&
+			(s->last_ctx[ring_id].ring_context_gpa ==
+				workload->ring_context_gpa))
+		skip = true;
+
+	s->last_ctx[ring_id].lrca = workload->ctx_desc.lrca;
+	s->last_ctx[ring_id].ring_context_gpa = workload->ring_context_gpa;
+
+	if (IS_RESTORE_INHIBIT(shadow_ring_context->ctx_ctrl.val) || skip)
+		return 0;
 
 	context_page_num = workload->engine->context_size;
 	context_page_num = context_page_num >> PAGE_SHIFT;
@@ -1260,6 +1273,8 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	atomic_set(&s->running_workload_num, 0);
 	bitmap_zero(s->tlb_handle_pending, I915_NUM_ENGINES);
 
+	memset(s->last_ctx, 0, sizeof(s->last_ctx));
+
 	i915_vm_put(&ppgtt->vm);
 	return 0;
 
-- 
2.17.1