Merge tag 'drm-intel-next-2018-06-06' into gvt-next

Backmerge for recent request->hw_context change and
new vGPU huge page capability definition.

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

1 files changed, 61 insertions, 117 deletions

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 847f295e6755..cf5a22cb6e06 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -54,11 +54,8 @@ static void set_context_pdp_root_pointer(
 
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 {
-	struct intel_vgpu *vgpu = workload->vgpu;
-	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+		workload->req->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -128,9 +125,8 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
 	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+		workload->req->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *dst;
@@ -205,7 +201,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 
 static inline bool is_gvt_request(struct i915_request *req)
 {
-	return i915_gem_context_force_single_submission(req->ctx);
+	return i915_gem_context_force_single_submission(req->gem_context);
 }
 
 static void save_ring_hw_state(struct intel_vgpu *vgpu, int ring_id)
@@ -280,10 +276,8 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
-		struct intel_engine_cs *engine)
+static void shadow_context_descriptor_update(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc = 0;
 
 	desc = ce->lrc_desc;
@@ -292,7 +286,7 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 	 * like GEN8_CTX_* cached in desc_template
 	 */
 	desc &= U64_MAX << 12;
-	desc |= ctx->desc_template & ((1ULL << 12) - 1);
+	desc |= ce->gem_context->desc_template & ((1ULL << 12) - 1);
 
 	ce->lrc_desc = desc;
 }
@@ -300,12 +294,11 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
+	struct i915_request *req = workload->req;
 	void *shadow_ring_buffer_va;
 	u32 *cs;
-	struct i915_request *req = workload->req;
 
-	if (IS_KABYLAKE(req->i915) &&
-	    is_inhibit_context(req->ctx, req->engine->id))
+	if (IS_KABYLAKE(req->i915) && is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/* allocate shadow ring buffer */
@@ -353,92 +346,67 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-	int ring_id = workload->ring_id;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	struct intel_ring *ring;
+	struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id];
+	struct intel_context *ce;
+	struct i915_request *rq;
 	int ret;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	if (workload->shadowed)
+	if (workload->req)
 		return 0;
 
+	/* pin shadow context by gvt even the shadow context will be pinned
+	 * when i915 alloc request. That is because gvt will update the guest
+	 * context from shadow context when workload is completed, and at that
+	 * moment, i915 may already unpined the shadow context to make the
+	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
+	 * the guest context, gvt can unpin the shadow_ctx safely.
+	 */
+	ce = intel_context_pin(shadow_ctx, engine);
+	if (IS_ERR(ce)) {
+		gvt_vgpu_err("fail to pin shadow context\n");
+		return PTR_ERR(ce);
+	}
+
 	shadow_ctx->desc_template &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT);
 	shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode <<
 				    GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
-	if (!test_and_set_bit(ring_id, s->shadow_ctx_desc_updated))
-		shadow_context_descriptor_update(shadow_ctx,
-					dev_priv->engine[ring_id]);
+	if (!test_and_set_bit(workload->ring_id, s->shadow_ctx_desc_updated))
+		shadow_context_descriptor_update(ce);
 
 	ret = intel_gvt_scan_and_shadow_ringbuffer(workload);
 	if (ret)
-		goto err_scan;
+		goto err_unpin;
 
 	if ((workload->ring_id == RCS) &&
 	    (workload->wa_ctx.indirect_ctx.size != 0)) {
 		ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
 		if (ret)
-			goto err_scan;
+			goto err_shadow;
 	}
 
-	/* pin shadow context by gvt even the shadow context will be pinned
-	 * when i915 alloc request. That is because gvt will update the guest
-	 * context from shadow context when workload is completed, and at that
-	 * moment, i915 may already unpined the shadow context to make the
-	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
-	 * the guest context, gvt can unpin the shadow_ctx safely.
-	 */
-	ring = intel_context_pin(shadow_ctx, engine);
-	if (IS_ERR(ring)) {
-		ret = PTR_ERR(ring);
-		gvt_vgpu_err("fail to pin shadow context\n");
+	rq = i915_request_alloc(engine, shadow_ctx);
+	if (IS_ERR(rq)) {
+		gvt_vgpu_err("fail to allocate gem request\n");
+		ret = PTR_ERR(rq);
 		goto err_shadow;
 	}
+	workload->req = i915_request_get(rq);
 
 	ret = populate_shadow_context(workload);
 	if (ret)
-		goto err_unpin;
-	workload->shadowed = true;
-	return 0;
+		goto err_req;
 
-err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
+	return 0;
+err_req:
+	rq = fetch_and_zero(&workload->req);
+	i915_request_put(rq);
 err_shadow:
 	release_shadow_wa_ctx(&workload->wa_ctx);
-err_scan:
-	return ret;
-}
-
-static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
-{
-	int ring_id = workload->ring_id;
-	struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	struct i915_request *rq;
-	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	int ret;
-
-	rq = i915_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
-	if (IS_ERR(rq)) {
-		gvt_vgpu_err("fail to allocate gem request\n");
-		ret = PTR_ERR(rq);
-		goto err_unpin;
-	}
-
-	gvt_dbg_sched("ring id %d get i915 gem request %p\n", ring_id, rq);
-
-	workload->req = i915_request_get(rq);
-	ret = copy_workload_to_ring_buffer(workload);
-	if (ret)
-		goto err_unpin;
-	return 0;
-
 err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
-	release_shadow_wa_ctx(&workload->wa_ctx);
+	intel_context_unpin(ce);
 	return ret;
 }
 
@@ -517,21 +485,13 @@ err:
 	return ret;
 }
 
-static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
+static void update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
-	struct intel_vgpu_workload *workload = container_of(wa_ctx,
-					struct intel_vgpu_workload,
-					wa_ctx);
-	int ring_id = workload->ring_id;
-	struct intel_vgpu_submission *s = &workload->vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
-	struct execlist_ring_context *shadow_ring_context;
-	struct page *page;
-
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	shadow_ring_context = kmap_atomic(page);
+	struct intel_vgpu_workload *workload =
+		container_of(wa_ctx, struct intel_vgpu_workload, wa_ctx);
+	struct i915_request *rq = workload->req;
+	struct execlist_ring_context *shadow_ring_context =
+		(struct execlist_ring_context *)rq->hw_context->lrc_reg_state;
 
 	shadow_ring_context->bb_per_ctx_ptr.val =
 		(shadow_ring_context->bb_per_ctx_ptr.val &
@@ -539,9 +499,6 @@ static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	shadow_ring_context->rcs_indirect_ctx.val =
 		(shadow_ring_context->rcs_indirect_ctx.val &
 		(~INDIRECT_CTX_ADDR_MASK)) | wa_ctx->indirect_ctx.shadow_gma;
-
-	kunmap_atomic(shadow_ring_context);
-	return 0;
 }
 
 static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
@@ -633,7 +590,7 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 		goto err_unpin_mm;
 	}
 
-	ret = intel_gvt_generate_request(workload);
+	ret = copy_workload_to_ring_buffer(workload);
 	if (ret) {
 		gvt_vgpu_err("fail to generate request\n");
 		goto err_unpin_mm;
@@ -670,12 +627,9 @@ err_unpin_mm:
 static int dispatch_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int ring_id = workload->ring_id;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	int ret = 0;
+	int ret;
 
 	gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n",
 		ring_id, workload);
@@ -688,10 +642,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 		goto out;
 
 	ret = prepare_workload(workload);
-	if (ret) {
-		intel_context_unpin(shadow_ctx, engine);
-		goto out;
-	}
 
 out:
 	if (ret)
@@ -767,27 +717,23 @@ out:
 
 static void update_guest_context(struct intel_vgpu_workload *workload)
 {
+	struct i915_request *rq = workload->req;
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	int ring_id = workload->ring_id;
-	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+	struct drm_i915_gem_object *ctx_obj = rq->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *src;
 	unsigned long context_gpa, context_page_num;
 	int i;
 
-	gvt_dbg_sched("ring id %d workload lrca %x\n", ring_id,
-			workload->ctx_desc.lrca);
-
-	context_page_num = gvt->dev_priv->engine[ring_id]->context_size;
+	gvt_dbg_sched("ring id %d workload lrca %x\n", rq->engine->id,
+		      workload->ctx_desc.lrca);
 
+	context_page_num = rq->engine->context_size;
 	context_page_num = context_page_num >> PAGE_SHIFT;
 
-	if (IS_BROADWELL(gvt->dev_priv) && ring_id == RCS)
+	if (IS_BROADWELL(gvt->dev_priv) && rq->engine->id == RCS)
 		context_page_num = 19;
 
 	i = 2;
@@ -860,6 +806,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		scheduler->current_workload[ring_id];
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct i915_request *rq = workload->req;
 	int event;
 
 	mutex_lock(&vgpu->vgpu_lock);
@@ -869,10 +816,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	 * switch to make sure request is completed.
 	 * For the workload w/o request, directly complete the workload.
 	 */
-	if (workload->req) {
-		struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-		struct intel_engine_cs *engine =
-			dev_priv->engine[workload->ring_id];
+	if (rq) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
@@ -888,8 +832,6 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 				workload->status = 0;
 		}
 
-		i915_request_put(fetch_and_zero(&workload->req));
-
 		if (!workload->status && !(vgpu->resetting_eng &
 					   ENGINE_MASK(ring_id))) {
 			update_guest_context(workload);
@@ -898,10 +840,13 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 					 INTEL_GVT_EVENT_MAX)
 				intel_vgpu_trigger_virtual_event(vgpu, event);
 		}
-		mutex_lock(&dev_priv->drm.struct_mutex);
+
 		/* unpin shadow ctx as the shadow_ctx update is done */
-		intel_context_unpin(s->shadow_ctx, engine);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
+		mutex_lock(&rq->i915->drm.struct_mutex);
+		intel_context_unpin(rq->hw_context);
+		mutex_unlock(&rq->i915->drm.struct_mutex);
+
+		i915_request_put(fetch_and_zero(&workload->req));
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -1271,7 +1216,6 @@ alloc_workload(struct intel_vgpu *vgpu)
 	atomic_set(&workload->shadow_ctx_active, 0);
 
 	workload->status = -EINPROGRESS;
-	workload->shadowed = false;
 	workload->vgpu = vgpu;
 
 	return workload;