drm/i915: Store a pointer to intel_context in i915_request

To ease the frequent and ugly pointer dance of
&request->gem_context->engine[request->engine->id] during request
submission, store that pointer as request->hw_context. One major
advantage that we will exploit later is that this decouples the logical
context state from the engine itself.

v2: Set mock_context->ops so we don't crash and burn in selftests.
    Cleanups from Tvrtko.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-3-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gvt/mmio_context.c

@@ -446,9 +446,9 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 
 #define CTX_CONTEXT_CONTROL_VAL	0x03
 
-bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id)
+bool is_inhibit_context(struct intel_context *ce)
 {
-	u32 *reg_state = ctx->__engine[ring_id].lrc_reg_state;
+	const u32 *reg_state = ce->lrc_reg_state;
 	u32 inhibit_mask =
 		_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
@@ -501,7 +501,7 @@ static void switch_mmio(struct intel_vgpu *pre,
 			 * itself.
 			 */
 			if (mmio->in_context &&
-			    !is_inhibit_context(s->shadow_ctx, ring_id))
+			    !is_inhibit_context(&s->shadow_ctx->__engine[ring_id]))
 				continue;
 
 			if (mmio->mask)

drivers/gpu/drm/i915/gvt/mmio_context.h

@@ -49,7 +49,7 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre,
 
 void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt);
 
-bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id);
+bool is_inhibit_context(struct intel_context *ce);
 
 int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu,
 				       struct i915_request *req);

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;
@@ -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;
@@ -292,20 +286,19 @@ 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;
 }
 
 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->gem_context, 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 */
@@ -353,68 +346,63 @@ 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;
 	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;
-	}
-
-	/* 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");
-		goto err_shadow;
+			goto err_shadow;
 	}
 
 	ret = populate_shadow_context(workload);
 	if (ret)
-		goto err_unpin;
-	workload->shadowed = true;
+		goto err_shadow;
+
 	return 0;
 
-err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
 err_shadow:
 	release_shadow_wa_ctx(&workload->wa_ctx);
-err_scan:
+err_unpin:
+	intel_context_unpin(ce);
 	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;
@@ -437,7 +425,6 @@ static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
 	return 0;
 
 err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
 	release_shadow_wa_ctx(&workload->wa_ctx);
 	return ret;
 }
@@ -517,31 +504,20 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 	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 &
 		(~PER_CTX_ADDR_MASK)) | wa_ctx->per_ctx.shadow_gma;
 	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)
@@ -670,12 +646,9 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 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);
@@ -687,10 +660,6 @@ 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)
@@ -765,27 +734,23 @@ static struct intel_vgpu_workload *pick_next_workload(
 
 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;
@@ -858,6 +823,7 @@ 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;
 	int event;
 
 	mutex_lock(&gvt->lock);
@@ -866,11 +832,8 @@ 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 =
-			workload->vgpu->gvt->dev_priv;
-		struct intel_engine_cs *engine =
-			dev_priv->engine[workload->ring_id];
+	rq = fetch_and_zero(&workload->req);
+	if (rq) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
@@ -886,8 +849,6 @@ 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);
@@ -896,10 +857,13 @@ 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(rq);
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -1270,7 +1234,6 @@ alloc_workload(struct intel_vgpu *vgpu)
 	atomic_set(&workload->shadow_ctx_active, 0);
 
 	workload->status = -EINPROGRESS;
-	workload->shadowed = false;
 	workload->vgpu = vgpu;
 
 	return workload;

drivers/gpu/drm/i915/gvt/scheduler.h

@@ -83,7 +83,6 @@ struct intel_vgpu_workload {
 	struct i915_request *req;
 	/* if this workload has been dispatched to i915? */
 	bool dispatched;
-	bool shadowed;
 	int status;
 
 	struct intel_vgpu_mm *shadow_mm;

drivers/gpu/drm/i915/i915_drv.h

@@ -1950,6 +1950,7 @@ struct drm_i915_private {
 			 */
 			struct i915_perf_stream *exclusive_stream;
 
+			struct intel_context *pinned_ctx;
 			u32 specific_ctx_id;
 
 			struct hrtimer poll_check_timer;

drivers/gpu/drm/i915/i915_gem.c

@@ -3181,14 +3181,14 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 	i915_retire_requests(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		struct i915_gem_context *ctx;
+		struct intel_context *ce;
 
 		i915_gem_reset_engine(engine,
 				      engine->hangcheck.active_request,
 				      stalled_mask & ENGINE_MASK(id));
-		ctx = fetch_and_zero(&engine->last_retired_context);
-		if (ctx)
-			intel_context_unpin(ctx, engine);
+		ce = fetch_and_zero(&engine->last_retired_context);
+		if (ce)
+			intel_context_unpin(ce);
 
 		/*
 		 * Ostensibily, we always want a context loaded for powersaving,
@@ -4897,13 +4897,13 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *kernel_context = i915->kernel_context;
+	struct i915_gem_context *kctx = i915->kernel_context;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
 	for_each_engine(engine, i915, id) {
 		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
-		GEM_BUG_ON(engine->last_retired_context != kernel_context);
+		GEM_BUG_ON(engine->last_retired_context->gem_context != kctx);
 	}
 }