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;
@@ -292,7 +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->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 */
@@ -353,60 +346,56 @@ 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;
 	}
 
 	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;
 }
 
@@ -414,7 +403,6 @@ 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;
 }
@@ -517,21 +504,13 @@ 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 &
@@ -539,9 +518,6 @@ 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)
@@ -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,
+	gvt_dbg_sched("ring id %d workload lrca %x\n", rq->engine->id,
 		      workload->ctx_desc.lrca);
 
-	context_page_num = gvt->dev_priv->engine[ring_id]->context_size;
-
+	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);
 	}
 }
 

drivers/gpu/drm/i915/i915_gem_context.c

@@ -127,14 +127,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
 		struct intel_context *ce = &ctx->__engine[n];
 
-		if (!ce->state)
-			continue;
-
-		WARN_ON(ce->pin_count);
-		if (ce->ring)
-			intel_ring_free(ce->ring);
-
-		__i915_gem_object_release_unless_active(ce->state->obj);
+		if (ce->ops)
+			ce->ops->destroy(ce);
 	}
 
 	kfree(ctx->name);
@@ -266,6 +260,7 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 		    struct drm_i915_file_private *file_priv)
 {
 	struct i915_gem_context *ctx;
+	unsigned int n;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -283,6 +278,12 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->i915 = dev_priv;
 	ctx->sched.priority = I915_PRIORITY_NORMAL;
 
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
+
+		ce->gem_context = ctx;
+	}
+
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
 

drivers/gpu/drm/i915/i915_gem_context.h

@@ -45,6 +45,11 @@ struct intel_ring;
 
 #define DEFAULT_CONTEXT_HANDLE 0
 
+struct intel_context_ops {
+	void (*unpin)(struct intel_context *ce);
+	void (*destroy)(struct intel_context *ce);
+};
+
 /**
  * struct i915_gem_context - client state
  *
@@ -144,11 +149,14 @@ struct i915_gem_context {
 
 	/** engine: per-engine logical HW state */
 	struct intel_context {
+		struct i915_gem_context *gem_context;
 		struct i915_vma *state;
 		struct intel_ring *ring;
 		u32 *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
+
+		const struct intel_context_ops *ops;
 	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */
@@ -263,25 +271,22 @@ to_intel_context(struct i915_gem_context *ctx,
 	return &ctx->__engine[engine->id];
 }
 
-static inline struct intel_ring *
+static inline struct intel_context *
 intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 {
 	return engine->context_pin(engine, ctx);
 }
 
-static inline void __intel_context_pin(struct i915_gem_context *ctx,
-				       const struct intel_engine_cs *engine)
+static inline void __intel_context_pin(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-
 	GEM_BUG_ON(!ce->pin_count);
 	ce->pin_count++;
 }
 
-static inline void intel_context_unpin(struct i915_gem_context *ctx,
-				       struct intel_engine_cs *engine)
+static inline void intel_context_unpin(struct intel_context *ce)
 {
-	engine->context_unpin(engine, ctx);
+	GEM_BUG_ON(!ce->ops);
+	ce->ops->unpin(ce);
 }
 
 /* i915_gem_context.c */

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1485,8 +1485,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 			ee->ctx =
 				i915_error_object_create(i915,
-							 to_intel_context(ctx,
-									  engine)->state);
+							 request->hw_context->state);
 
 			error->simulated |=
 				i915_gem_context_no_error_capture(ctx);

drivers/gpu/drm/i915/i915_perf.c

@@ -1221,7 +1221,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id;
 	} else {
 		struct intel_engine_cs *engine = dev_priv->engine[RCS];
-		struct intel_ring *ring;
+		struct intel_context *ce;
 		int ret;
 
 		ret = i915_mutex_lock_interruptible(&dev_priv->drm);
@@ -1234,19 +1234,19 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		 *
 		 * NB: implied RCS engine...
 		 */
-		ring = intel_context_pin(stream->ctx, engine);
+		ce = intel_context_pin(stream->ctx, engine);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
-		if (IS_ERR(ring))
-			return PTR_ERR(ring);
+		if (IS_ERR(ce))
+			return PTR_ERR(ce);
 
+		dev_priv->perf.oa.pinned_ctx = ce;
 
 		/*
 		 * Explicitly track the ID (instead of calling
 		 * i915_ggtt_offset() on the fly) considering the difference
 		 * with gen8+ and execlists
 		 */
-		dev_priv->perf.oa.specific_ctx_id =
-			i915_ggtt_offset(to_intel_context(stream->ctx, engine)->state);
+		dev_priv->perf.oa.specific_ctx_id = i915_ggtt_offset(ce->state);
 	}
 
 	return 0;
@@ -1262,17 +1262,14 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_context *ce;
 
-	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 	dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-	} else {
-		struct intel_engine_cs *engine = dev_priv->engine[RCS];
 
+	ce = fetch_and_zero(&dev_priv->perf.oa.pinned_ctx);
+	if (ce) {
 		mutex_lock(&dev_priv->drm.struct_mutex);
-
-		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-		intel_context_unpin(stream->ctx, engine);
-
+		intel_context_unpin(ce);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 }

drivers/gpu/drm/i915/i915_request.c

@@ -383,8 +383,8 @@ static void __retire_engine_request(struct intel_engine_cs *engine,
 	 * the subsequent request.
 	 */
 	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context, engine);
-	engine->last_retired_context = rq->gem_context;
+		intel_context_unpin(engine->last_retired_context);
+	engine->last_retired_context = rq->hw_context;
 }
 
 static void __retire_engine_upto(struct intel_engine_cs *engine,
@@ -456,7 +456,7 @@ static void i915_request_retire(struct i915_request *request)
 
 	/* Retirement decays the ban score as it is a sign of ctx progress */
 	atomic_dec_if_positive(&request->gem_context->ban_score);
-	intel_context_unpin(request->gem_context, request->engine);
+	intel_context_unpin(request->hw_context);
 
 	__retire_engine_upto(request->engine, request);
 
@@ -657,7 +657,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 {
 	struct drm_i915_private *i915 = engine->i915;
 	struct i915_request *rq;
-	struct intel_ring *ring;
+	struct intel_context *ce;
 	int ret;
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
@@ -681,22 +681,21 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 * GGTT space, so do this first before we reserve a seqno for
 	 * ourselves.
 	 */
-	ring = intel_context_pin(ctx, engine);
-	if (IS_ERR(ring))
-		return ERR_CAST(ring);
-	GEM_BUG_ON(!ring);
+	ce = intel_context_pin(ctx, engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
 
 	ret = reserve_gt(i915);
 	if (ret)
 		goto err_unpin;
 
-	ret = intel_ring_wait_for_space(ring, MIN_SPACE_FOR_ADD_REQUEST);
+	ret = intel_ring_wait_for_space(ce->ring, MIN_SPACE_FOR_ADD_REQUEST);
 	if (ret)
 		goto err_unreserve;
 
 	/* Move our oldest request to the slab-cache (if not in use!) */
-	rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link);
-	if (!list_is_last(&rq->ring_link, &ring->request_list) &&
+	rq = list_first_entry(&ce->ring->request_list, typeof(*rq), ring_link);
+	if (!list_is_last(&rq->ring_link, &ce->ring->request_list) &&
 	    i915_request_completed(rq))
 		i915_request_retire(rq);
 
@@ -761,8 +760,9 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	rq->i915 = i915;
 	rq->engine = engine;
 	rq->gem_context = ctx;
-	rq->ring = ring;
-	rq->timeline = ring->timeline;
+	rq->hw_context = ce;
+	rq->ring = ce->ring;
+	rq->timeline = ce->ring->timeline;
 	GEM_BUG_ON(rq->timeline == &engine->timeline);
 
 	spin_lock_init(&rq->lock);
@@ -814,14 +814,14 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		goto err_unwind;
 
 	/* Keep a second pin for the dual retirement along engine and ring */
-	__intel_context_pin(rq->gem_context, engine);
+	__intel_context_pin(ce);
 
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno);
 	return rq;
 
 err_unwind:
-	rq->ring->emit = rq->head;
+	ce->ring->emit = rq->head;
 
 	/* Make sure we didn't add ourselves to external state before freeing */
 	GEM_BUG_ON(!list_empty(&rq->active_list));
@@ -832,7 +832,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 err_unreserve:
 	unreserve_gt(i915);
 err_unpin:
-	intel_context_unpin(ctx, engine);
+	intel_context_unpin(ce);
 	return ERR_PTR(ret);
 }
 
@@ -1018,8 +1018,8 @@ i915_request_await_object(struct i915_request *to,
 void __i915_request_add(struct i915_request *request, bool flush_caches)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct intel_ring *ring = request->ring;
 	struct i915_timeline *timeline = request->timeline;
+	struct intel_ring *ring = request->ring;
 	struct i915_request *prev;
 	u32 *cs;
 	int err;

drivers/gpu/drm/i915/i915_request.h

@@ -95,6 +95,7 @@ struct i915_request {
 	 */
 	struct i915_gem_context *gem_context;
 	struct intel_engine_cs *engine;
+	struct intel_context *hw_context;
 	struct intel_ring *ring;
 	struct i915_timeline *timeline;
 	struct intel_signal_node signaling;

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -645,6 +645,12 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 	return 0;
 }
 
+static void __intel_context_unpin(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine)
+{
+	intel_context_unpin(to_intel_context(ctx, engine));
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -658,7 +664,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
  */
 int intel_engine_init_common(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_context *ce;
 	int ret;
 
 	engine->set_default_submission(engine);
@@ -670,18 +677,18 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * be available. To avoid this we always pin the default
 	 * context.
 	 */
-	ring = intel_context_pin(engine->i915->kernel_context, engine);
-	if (IS_ERR(ring))
-		return PTR_ERR(ring);
+	ce = intel_context_pin(i915->kernel_context, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
 	/*
 	 * Similarly the preempt context must always be available so that
 	 * we can interrupt the engine at any time.
 	 */
-	if (engine->i915->preempt_context) {
-		ring = intel_context_pin(engine->i915->preempt_context, engine);
-		if (IS_ERR(ring)) {
-			ret = PTR_ERR(ring);
+	if (i915->preempt_context) {
+		ce = intel_context_pin(i915->preempt_context, engine);
+		if (IS_ERR(ce)) {
+			ret = PTR_ERR(ce);
 			goto err_unpin_kernel;
 		}
 	}
@@ -690,7 +697,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	if (ret)
 		goto err_unpin_preempt;
 
-	if (HWS_NEEDS_PHYSICAL(engine->i915))
+	if (HWS_NEEDS_PHYSICAL(i915))
 		ret = init_phys_status_page(engine);
 	else
 		ret = init_status_page(engine);
@@ -702,10 +709,11 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(engine);
 err_unpin_preempt:
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+
 err_unpin_kernel:
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 	return ret;
 }
 
@@ -718,6 +726,8 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	intel_engine_cleanup_scratch(engine);
 
 	if (HWS_NEEDS_PHYSICAL(engine->i915))
@@ -732,9 +742,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		i915_gem_object_put(engine->default_state);
 
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 
 	i915_timeline_fini(&engine->timeline);
 }
@@ -1007,8 +1017,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
  */
 bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 {
-	const struct i915_gem_context * const kernel_context =
-		engine->i915->kernel_context;
+	const struct intel_context *kernel_context =
+		to_intel_context(engine->i915->kernel_context, engine);
 	struct i915_request *rq;
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
@@ -1020,7 +1030,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 */
 	rq = __i915_gem_active_peek(&engine->timeline.last_request);
 	if (rq)
-		return rq->gem_context == kernel_context;
+		return rq->hw_context == kernel_context;
 	else
 		return engine->last_retired_context == kernel_context;
 }
@@ -1107,16 +1117,16 @@ void intel_engines_unpark(struct drm_i915_private *i915)
  */
 void intel_engine_lost_context(struct intel_engine_cs *engine)
 {
-	struct i915_gem_context *ctx;
+	struct intel_context *ce;
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
 
 	engine->legacy_active_context = NULL;
 	engine->legacy_active_ppgtt = NULL;
 
-	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);
 }
 
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)

drivers/gpu/drm/i915/intel_guc_submission.c

@@ -513,9 +513,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_guc_client *client = guc->execbuf_client;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc =
-		lower_32_bits(intel_lr_context_descriptor(rq->gem_context,
-							  engine));
+	u32 ctx_desc = lower_32_bits(rq->hw_context->lrc_desc);
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
 	spin_lock(&client->wq_lock);
@@ -553,8 +551,8 @@ static void inject_preempt_context(struct work_struct *work)
 					     preempt_work[engine->id]);
 	struct intel_guc_client *client = guc->preempt_client;
 	struct guc_stage_desc *stage_desc = __get_stage_desc(client);
-	u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(client->owner,
-								 engine));
+	u32 ctx_desc = lower_32_bits(to_intel_context(client->owner,
+						      engine)->lrc_desc);
 	u32 data[7];
 
 	/*
@@ -726,7 +724,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 		struct i915_request *rq, *rn;
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
-			if (last && rq->gem_context != last->gem_context) {
+			if (last && rq->hw_context != last->hw_context) {
 				if (port == last_port) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);

drivers/gpu/drm/i915/intel_lrc.c

@@ -164,7 +164,8 @@
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
-					    struct intel_engine_cs *engine);
+					    struct intel_engine_cs *engine,
+					    struct intel_context *ce);
 static void execlists_init_reg_state(u32 *reg_state,
 				     struct i915_gem_context *ctx,
 				     struct intel_engine_cs *engine,
@@ -189,12 +190,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 		!i915_request_completed(last));
 }
 
-/**
- * intel_lr_context_descriptor_update() - calculate & cache the descriptor
- * 					  descriptor for a pinned context
- * @ctx: Context to work on
- * @engine: Engine the descriptor will be used with
- *
+/*
  * The context descriptor encodes various attributes of a context,
  * including its GTT address and some flags. Because it's fairly
  * expensive to calculate, we'll just do it once and cache the result,
@@ -222,9 +218,9 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
  */
 static void
 intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
-				   struct intel_engine_cs *engine)
+				   struct intel_engine_cs *engine,
+				   struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc;
 
 	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH)));
@@ -418,8 +414,7 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce =
-		to_intel_context(rq->gem_context, rq->engine);
+	struct intel_context *ce = rq->hw_context;
 	struct i915_hw_ppgtt *ppgtt =
 		rq->gem_context->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
 	u32 *reg_state = ce->lrc_reg_state;
@@ -496,14 +491,14 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 	execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK);
 }
 
-static bool ctx_single_port_submission(const struct i915_gem_context *ctx)
+static bool ctx_single_port_submission(const struct intel_context *ce)
 {
 	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
-		i915_gem_context_force_single_submission(ctx));
+		i915_gem_context_force_single_submission(ce->gem_context));
 }
 
-static bool can_merge_ctx(const struct i915_gem_context *prev,
-			  const struct i915_gem_context *next)
+static bool can_merge_ctx(const struct intel_context *prev,
+			  const struct intel_context *next)
 {
 	if (prev != next)
 		return false;
@@ -680,8 +675,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 			 * second request, and so we never need to tell the
 			 * hardware about the first.
 			 */
-			if (last && !can_merge_ctx(rq->gem_context,
-						   last->gem_context)) {
+			if (last &&
+			    !can_merge_ctx(rq->hw_context, last->hw_context)) {
 				/*
 				 * If we are on the second port and cannot
 				 * combine this request with the last, then we
@@ -700,14 +695,14 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->gem_context) ||
-				    ctx_single_port_submission(rq->gem_context)) {
+				if (ctx_single_port_submission(last->hw_context) ||
+				    ctx_single_port_submission(rq->hw_context)) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
 					goto done;
 				}
 
-				GEM_BUG_ON(last->gem_context == rq->gem_context);
+				GEM_BUG_ON(last->hw_context == rq->hw_context);
 
 				if (submit)
 					port_assign(port, last);
@@ -1339,6 +1334,37 @@ static void execlists_schedule(struct i915_request *request,
 	spin_unlock_irq(&engine->timeline.lock);
 }
 
+static void execlists_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(!ce->state);
+	GEM_BUG_ON(ce->pin_count);
+
+	intel_ring_free(ce->ring);
+	__i915_gem_object_release_unless_active(ce->state->obj);
+}
+
+static void __execlists_context_unpin(struct intel_context *ce)
+{
+	intel_ring_unpin(ce->ring);
+
+	ce->state->obj->pin_global--;
+	i915_gem_object_unpin_map(ce->state->obj);
+	i915_vma_unpin(ce->state);
+
+	i915_gem_context_put(ce->gem_context);
+}
+
+static void execlists_context_unpin(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->gem_context->i915->drm.struct_mutex);
+	GEM_BUG_ON(ce->pin_count == 0);
+
+	if (--ce->pin_count)
+		return;
+
+	__execlists_context_unpin(ce);
+}
+
 static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 {
 	unsigned int flags;
@@ -1362,21 +1388,15 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	return i915_vma_pin(vma, 0, GEN8_LR_CONTEXT_ALIGN, flags);
 }
 
-static struct intel_ring *
-execlists_context_pin(struct intel_engine_cs *engine,
-		      struct i915_gem_context *ctx)
+static struct intel_context *
+__execlists_context_pin(struct intel_engine_cs *engine,
+			struct i915_gem_context *ctx,
+			struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	void *vaddr;
 	int ret;
 
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-
-	if (likely(ce->pin_count++))
-		goto out;
-	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
-
-	ret = execlists_context_deferred_alloc(ctx, engine);
+	ret = execlists_context_deferred_alloc(ctx, engine, ce);
 	if (ret)
 		goto err;
 	GEM_BUG_ON(!ce->state);
@@ -1395,7 +1415,7 @@ execlists_context_pin(struct intel_engine_cs *engine,
 	if (ret)
 		goto unpin_map;
 
-	intel_lr_context_descriptor_update(ctx, engine);
+	intel_lr_context_descriptor_update(ctx, engine, ce);
 
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
@@ -1404,8 +1424,7 @@ execlists_context_pin(struct intel_engine_cs *engine,
 
 	ce->state->obj->pin_global++;
 	i915_gem_context_get(ctx);
-out:
-	return ce->ring;
+	return ce;
 
 unpin_map:
 	i915_gem_object_unpin_map(ce->state->obj);
@@ -1416,33 +1435,33 @@ execlists_context_pin(struct intel_engine_cs *engine,
 	return ERR_PTR(ret);
 }
 
-static void execlists_context_unpin(struct intel_engine_cs *engine,
+static const struct intel_context_ops execlists_context_ops = {
+	.unpin = execlists_context_unpin,
+	.destroy = execlists_context_destroy,
+};
+
+static struct intel_context *
+execlists_context_pin(struct intel_engine_cs *engine,
 		      struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
 
-	if (--ce->pin_count)
-		return;
+	if (likely(ce->pin_count++))
+		return ce;
+	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	intel_ring_unpin(ce->ring);
+	ce->ops = &execlists_context_ops;
 
-	ce->state->obj->pin_global--;
-	i915_gem_object_unpin_map(ce->state->obj);
-	i915_vma_unpin(ce->state);
-
-	i915_gem_context_put(ctx);
+	return __execlists_context_pin(engine, ctx, ce);
 }
 
 static int execlists_request_alloc(struct i915_request *request)
 {
-	struct intel_context *ce =
-		to_intel_context(request->gem_context, request->engine);
 	int ret;
 
-	GEM_BUG_ON(!ce->pin_count);
+	GEM_BUG_ON(!request->hw_context->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -1956,7 +1975,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
-	regs = to_intel_context(request->gem_context, engine)->lrc_reg_state;
+	regs = request->hw_context->lrc_reg_state;
 	if (engine->default_state) {
 		void *defaults;
 
@@ -2327,8 +2346,6 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->reset.finish = execlists_reset_finish;
 
 	engine->context_pin = execlists_context_pin;
-	engine->context_unpin = execlists_context_unpin;
-
 	engine->request_alloc = execlists_request_alloc;
 
 	engine->emit_flush = gen8_emit_flush;
@@ -2563,7 +2580,7 @@ static void execlists_init_reg_state(u32 *regs,
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: dev_priv->mm.aliasing_ppgtt;
 	u32 base = engine->mmio_base;
-	bool rcs = engine->id == RCS;
+	bool rcs = engine->class == RENDER_CLASS;
 
 	/* A context is actually a big batch buffer with several
 	 * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The
@@ -2710,10 +2727,10 @@ populate_lr_context(struct i915_gem_context *ctx,
 }
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
-					    struct intel_engine_cs *engine)
+					    struct intel_engine_cs *engine,
+					    struct intel_context *ce)
 {
 	struct drm_i915_gem_object *ctx_obj;
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	struct i915_vma *vma;
 	uint32_t context_size;
 	struct intel_ring *ring;

drivers/gpu/drm/i915/intel_lrc.h

@@ -104,11 +104,4 @@ struct i915_gem_context;
 
 void intel_lr_context_resume(struct drm_i915_private *dev_priv);
 
-static inline uint64_t
-intel_lr_context_descriptor(struct i915_gem_context *ctx,
-			    struct intel_engine_cs *engine)
-{
-	return to_intel_context(ctx, engine)->lrc_desc;
-}
-
 #endif /* _INTEL_LRC_H_ */

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -571,8 +571,7 @@ static void reset_ring(struct intel_engine_cs *engine,
 	 */
 	if (request) {
 		struct drm_i915_private *dev_priv = request->i915;
-		struct intel_context *ce =
-			to_intel_context(request->gem_context, engine);
+		struct intel_context *ce = request->hw_context;
 		struct i915_hw_ppgtt *ppgtt;
 
 		if (ce->state) {
@@ -1186,7 +1185,31 @@ intel_ring_free(struct intel_ring *ring)
 	kfree(ring);
 }
 
-static int context_pin(struct intel_context *ce)
+static void intel_ring_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->pin_count);
+
+	if (ce->state)
+		__i915_gem_object_release_unless_active(ce->state->obj);
+}
+
+static void intel_ring_context_unpin(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->gem_context->i915->drm.struct_mutex);
+	GEM_BUG_ON(ce->pin_count == 0);
+
+	if (--ce->pin_count)
+		return;
+
+	if (ce->state) {
+		ce->state->obj->pin_global--;
+		i915_vma_unpin(ce->state);
+	}
+
+	i915_gem_context_put(ce->gem_context);
+}
+
+static int __context_pin(struct intel_context *ce)
 {
 	struct i915_vma *vma = ce->state;
 	int ret;
@@ -1275,25 +1298,19 @@ alloc_context_vma(struct intel_engine_cs *engine)
 	return ERR_PTR(err);
 }
 
-static struct intel_ring *
-intel_ring_context_pin(struct intel_engine_cs *engine,
-		       struct i915_gem_context *ctx)
+static struct intel_context *
+__ring_context_pin(struct intel_engine_cs *engine,
+		   struct i915_gem_context *ctx,
+		   struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-	int ret;
-
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-
-	if (likely(ce->pin_count++))
-		goto out;
-	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
+	int err;
 
 	if (!ce->state && engine->context_size) {
 		struct i915_vma *vma;
 
 		vma = alloc_context_vma(engine);
 		if (IS_ERR(vma)) {
-			ret = PTR_ERR(vma);
+			err = PTR_ERR(vma);
 			goto err;
 		}
 
@@ -1301,8 +1318,8 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 	}
 
 	if (ce->state) {
-		ret = context_pin(ce);
-		if (ret)
+		err = __context_pin(ce);
+		if (err)
 			goto err;
 
 		ce->state->obj->pin_global++;
@@ -1310,32 +1327,37 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 
 	i915_gem_context_get(ctx);
 
-out:
 	/* One ringbuffer to rule them all */
-	return engine->buffer;
+	GEM_BUG_ON(!engine->buffer);
+	ce->ring = engine->buffer;
+
+	return ce;
 
 err:
 	ce->pin_count = 0;
-	return ERR_PTR(ret);
+	return ERR_PTR(err);
 }
 
-static void intel_ring_context_unpin(struct intel_engine_cs *engine,
+static const struct intel_context_ops ring_context_ops = {
+	.unpin = intel_ring_context_unpin,
+	.destroy = intel_ring_context_destroy,
+};
+
+static struct intel_context *
+intel_ring_context_pin(struct intel_engine_cs *engine,
 		       struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
 
-	if (--ce->pin_count)
-		return;
+	if (likely(ce->pin_count++))
+		return ce;
+	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	if (ce->state) {
-		ce->state->obj->pin_global--;
-		i915_vma_unpin(ce->state);
-	}
+	ce->ops = &ring_context_ops;
 
-	i915_gem_context_put(ctx);
+	return __ring_context_pin(engine, ctx, ce);
 }
 
 static int intel_init_ring_buffer(struct intel_engine_cs *engine)
@@ -1346,10 +1368,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 
 	intel_engine_setup_common(engine);
 
-	err = intel_engine_init_common(engine);
-	if (err)
-		goto err;
-
 	timeline = i915_timeline_create(engine->i915, engine->name);
 	if (IS_ERR(timeline)) {
 		err = PTR_ERR(timeline);
@@ -1371,8 +1389,14 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->buffer);
 	engine->buffer = ring;
 
+	err = intel_engine_init_common(engine);
+	if (err)
+		goto err_unpin;
+
 	return 0;
 
+err_unpin:
+	intel_ring_unpin(ring);
 err_ring:
 	intel_ring_free(ring);
 err:
@@ -1458,7 +1482,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(to_intel_context(rq->gem_context, engine)->state) | flags;
+	*cs++ = i915_ggtt_offset(rq->hw_context->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1549,7 +1573,7 @@ static int switch_context(struct i915_request *rq)
 		hw_flags = MI_FORCE_RESTORE;
 	}
 
-	if (to_intel_context(to_ctx, engine)->state &&
+	if (rq->hw_context->state &&
 	    (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) {
 		GEM_BUG_ON(engine->id != RCS);
 
@@ -1597,7 +1621,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!to_intel_context(request->gem_context, request->engine)->pin_count);
+	GEM_BUG_ON(!request->hw_context->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -2028,8 +2052,6 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,
 	engine->reset.finish = reset_finish;
 
 	engine->context_pin = intel_ring_context_pin;
-	engine->context_unpin = intel_ring_context_unpin;
-
 	engine->request_alloc = ring_request_alloc;
 
 	engine->emit_breadcrumb = i9xx_emit_breadcrumb;

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -436,10 +436,9 @@ struct intel_engine_cs {
 
 	void		(*set_default_submission)(struct intel_engine_cs *engine);
 
-	struct intel_ring *(*context_pin)(struct intel_engine_cs *engine,
-					  struct i915_gem_context *ctx);
-	void		(*context_unpin)(struct intel_engine_cs *engine,
+	struct intel_context *(*context_pin)(struct intel_engine_cs *engine,
 					     struct i915_gem_context *ctx);
+
 	int		(*request_alloc)(struct i915_request *rq);
 	int		(*init_context)(struct i915_request *rq);
 
@@ -555,7 +554,7 @@ struct intel_engine_cs {
 	 * to the kernel context and trash it as the save may not happen
 	 * before the hardware is powered down.
 	 */
-	struct i915_gem_context *last_retired_context;
+	struct intel_context *last_retired_context;
 
 	/* We track the current MI_SET_CONTEXT in order to eliminate
 	 * redudant context switches. This presumes that requests are not

drivers/gpu/drm/i915/selftests/mock_context.c

@@ -30,6 +30,7 @@ mock_context(struct drm_i915_private *i915,
 	     const char *name)
 {
 	struct i915_gem_context *ctx;
+	unsigned int n;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -43,6 +44,12 @@ mock_context(struct drm_i915_private *i915,
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
 
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
+
+		ce->gem_context = ctx;
+	}
+
 	ret = ida_simple_get(&i915->contexts.hw_ida,
 			     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
 	if (ret < 0)

drivers/gpu/drm/i915/selftests/mock_engine.c

@@ -72,25 +72,37 @@ static void hw_delay_complete(struct timer_list *t)
 	spin_unlock(&engine->hw_lock);
 }
 
-static struct intel_ring *
-mock_context_pin(struct intel_engine_cs *engine,
-		 struct i915_gem_context *ctx)
+static void mock_context_unpin(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
+	if (--ce->pin_count)
+		return;
 
-	if (!ce->pin_count++)
-		i915_gem_context_get(ctx);
+	i915_gem_context_put(ce->gem_context);
+}
 
-	return engine->buffer;
+static void mock_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->pin_count);
 }
 
-static void mock_context_unpin(struct intel_engine_cs *engine,
+static const struct intel_context_ops mock_context_ops = {
+	.unpin = mock_context_unpin,
+	.destroy = mock_context_destroy,
+};
+
+static struct intel_context *
+mock_context_pin(struct intel_engine_cs *engine,
 		 struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
-	if (!--ce->pin_count)
-		i915_gem_context_put(ctx);
+	if (!ce->pin_count++) {
+		i915_gem_context_get(ctx);
+		ce->ring = engine->buffer;
+		ce->ops = &mock_context_ops;
+	}
+
+	return ce;
 }
 
 static int mock_request_alloc(struct i915_request *request)
@@ -185,7 +197,6 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.status_page.page_addr = (void *)(engine + 1);
 
 	engine->base.context_pin = mock_context_pin;
-	engine->base.context_unpin = mock_context_unpin;
 	engine->base.request_alloc = mock_request_alloc;
 	engine->base.emit_flush = mock_emit_flush;
 	engine->base.emit_breadcrumb = mock_emit_breadcrumb;
@@ -238,11 +249,13 @@ void mock_engine_free(struct intel_engine_cs *engine)
 {
 	struct mock_engine *mock =
 		container_of(engine, typeof(*mock), base);
+	struct intel_context *ce;
 
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
-	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context, engine);
+	ce = fetch_and_zero(&engine->last_retired_context);
+	if (ce)
+		intel_context_unpin(ce);
 
 	mock_ring_free(engine->buffer);