Merge tag 'drm-intel-next-fixes-2022-10-13' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

- Fix revocation of non-persistent contexts (Tvrtko Ursulin)
- Handle migration for dpt (Matthew Auld)
- Fix display problems after resume (Thomas Hellström)
- Allow control over the flags when migrating (Matthew Auld)
- Consider DG2_RC_CCS_CC when migrating buffers (Matthew Auld)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Y0gK9QmCmktLLzqp@tursulin-desk

drivers/gpu/drm/i915/display/intel_fb_pin.c

@@ -26,10 +26,17 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb,
 	struct drm_device *dev = fb->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct i915_gem_ww_ctx ww;
 	struct i915_vma *vma;
 	u32 alignment;
 	int ret;
 
+	/*
+	 * We are not syncing against the binding (and potential migrations)
+	 * below, so this vm must never be async.
+	 */
+	GEM_WARN_ON(vm->bind_async_flags);
+
 	if (WARN_ON(!i915_gem_object_is_framebuffer(obj)))
 		return ERR_PTR(-EINVAL);
 
@@ -37,29 +44,48 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb,
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
-	ret = i915_gem_object_lock_interruptible(obj, NULL);
-	if (!ret) {
-		ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
-		i915_gem_object_unlock(obj);
-	}
-	if (ret) {
-		vma = ERR_PTR(ret);
-		goto err;
-	}
+	for_i915_gem_ww(&ww, ret, true) {
+		ret = i915_gem_object_lock(obj, &ww);
+		if (ret)
+			continue;
 
-	vma = i915_vma_instance(obj, vm, view);
-	if (IS_ERR(vma))
-		goto err;
+		if (HAS_LMEM(dev_priv)) {
+			unsigned int flags = obj->flags;
 
-	if (i915_vma_misplaced(vma, 0, alignment, 0)) {
-		ret = i915_vma_unbind_unlocked(vma);
-		if (ret) {
-			vma = ERR_PTR(ret);
-			goto err;
+			/*
+			 * For this type of buffer we need to able to read from the CPU
+			 * the clear color value found in the buffer, hence we need to
+			 * ensure it is always in the mappable part of lmem, if this is
+			 * a small-bar device.
+			 */
+			if (intel_fb_rc_ccs_cc_plane(fb) >= 0)
+				flags &= ~I915_BO_ALLOC_GPU_ONLY;
+			ret = __i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0,
+							flags);
+			if (ret)
+				continue;
 		}
-	}
 
-	ret = i915_vma_pin(vma, 0, alignment, PIN_GLOBAL);
+		ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
+		if (ret)
+			continue;
+
+		vma = i915_vma_instance(obj, vm, view);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			continue;
+		}
+
+		if (i915_vma_misplaced(vma, 0, alignment, 0)) {
+			ret = i915_vma_unbind(vma);
+			if (ret)
+				continue;
+		}
+
+		ret = i915_vma_pin_ww(vma, &ww, 0, alignment, PIN_GLOBAL);
+		if (ret)
+			continue;
+	}
 	if (ret) {
 		vma = ERR_PTR(ret);
 		goto err;

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1383,14 +1383,8 @@ kill_engines(struct i915_gem_engines *engines, bool exit, bool persistent)
 	 */
 	for_each_gem_engine(ce, engines, it) {
 		struct intel_engine_cs *engine;
-		bool skip = false;
 
-		if (exit)
-			skip = intel_context_set_exiting(ce);
-		else if (!persistent)
-			skip = intel_context_exit_nonpersistent(ce, NULL);
-
-		if (skip)
+		if ((exit || !persistent) && intel_context_revoke(ce))
 			continue; /* Already marked. */
 
 		/*

drivers/gpu/drm/i915/gem/i915_gem_object.c

@@ -652,6 +652,41 @@ bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj,
 int i915_gem_object_migrate(struct drm_i915_gem_object *obj,
 			    struct i915_gem_ww_ctx *ww,
 			    enum intel_region_id id)
+{
+	return __i915_gem_object_migrate(obj, ww, id, obj->flags);
+}
+
+/**
+ * __i915_gem_object_migrate - Migrate an object to the desired region id, with
+ * control of the extra flags
+ * @obj: The object to migrate.
+ * @ww: An optional struct i915_gem_ww_ctx. If NULL, the backend may
+ * not be successful in evicting other objects to make room for this object.
+ * @id: The region id to migrate to.
+ * @flags: The object flags. Normally just obj->flags.
+ *
+ * Attempt to migrate the object to the desired memory region. The
+ * object backend must support migration and the object may not be
+ * pinned, (explicitly pinned pages or pinned vmas). The object must
+ * be locked.
+ * On successful completion, the object will have pages pointing to
+ * memory in the new region, but an async migration task may not have
+ * completed yet, and to accomplish that, i915_gem_object_wait_migration()
+ * must be called.
+ *
+ * Note: the @ww parameter is not used yet, but included to make sure
+ * callers put some effort into obtaining a valid ww ctx if one is
+ * available.
+ *
+ * Return: 0 on success. Negative error code on failure. In particular may
+ * return -ENXIO on lack of region space, -EDEADLK for deadlock avoidance
+ * if @ww is set, -EINTR or -ERESTARTSYS if signal pending, and
+ * -EBUSY if the object is pinned.
+ */
+int __i915_gem_object_migrate(struct drm_i915_gem_object *obj,
+			      struct i915_gem_ww_ctx *ww,
+			      enum intel_region_id id,
+			      unsigned int flags)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct intel_memory_region *mr;
@@ -672,7 +707,7 @@ int i915_gem_object_migrate(struct drm_i915_gem_object *obj,
 		return 0;
 	}
 
-	return obj->ops->migrate(obj, mr);
+	return obj->ops->migrate(obj, mr, flags);
 }
 
 /**

drivers/gpu/drm/i915/gem/i915_gem_object.h

@@ -608,6 +608,10 @@ bool i915_gem_object_migratable(struct drm_i915_gem_object *obj);
 int i915_gem_object_migrate(struct drm_i915_gem_object *obj,
 			    struct i915_gem_ww_ctx *ww,
 			    enum intel_region_id id);
+int __i915_gem_object_migrate(struct drm_i915_gem_object *obj,
+			      struct i915_gem_ww_ctx *ww,
+			      enum intel_region_id id,
+			      unsigned int flags);
 
 bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj,
 				 enum intel_region_id id);

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

@@ -107,7 +107,8 @@ struct drm_i915_gem_object_ops {
 	 * pinning or for as long as the object lock is held.
 	 */
 	int (*migrate)(struct drm_i915_gem_object *obj,
-		       struct intel_memory_region *mr);
+		       struct intel_memory_region *mr,
+		       unsigned int flags);
 
 	void (*release)(struct drm_i915_gem_object *obj);
 

drivers/gpu/drm/i915/gem/i915_gem_ttm.c

@@ -848,9 +848,10 @@ static int __i915_ttm_migrate(struct drm_i915_gem_object *obj,
 }
 
 static int i915_ttm_migrate(struct drm_i915_gem_object *obj,
-			    struct intel_memory_region *mr)
+			    struct intel_memory_region *mr,
+			    unsigned int flags)
 {
-	return __i915_ttm_migrate(obj, mr, obj->flags);
+	return __i915_ttm_migrate(obj, mr, flags);
 }
 
 static void i915_ttm_put_pages(struct drm_i915_gem_object *obj,

drivers/gpu/drm/i915/gt/intel_context.c

@@ -614,13 +614,12 @@ bool intel_context_ban(struct intel_context *ce, struct i915_request *rq)
 	return ret;
 }
 
-bool intel_context_exit_nonpersistent(struct intel_context *ce,
-				      struct i915_request *rq)
+bool intel_context_revoke(struct intel_context *ce)
 {
 	bool ret = intel_context_set_exiting(ce);
 
 	if (ce->ops->revoke)
-		ce->ops->revoke(ce, rq, ce->engine->props.preempt_timeout_ms);
+		ce->ops->revoke(ce, NULL, ce->engine->props.preempt_timeout_ms);
 
 	return ret;
 }

drivers/gpu/drm/i915/gt/intel_context.h

@@ -329,8 +329,7 @@ static inline bool intel_context_set_exiting(struct intel_context *ce)
 	return test_and_set_bit(CONTEXT_EXITING, &ce->flags);
 }
 
-bool intel_context_exit_nonpersistent(struct intel_context *ce,
-				      struct i915_request *rq);
+bool intel_context_revoke(struct intel_context *ce);
 
 static inline bool
 intel_context_force_single_submission(const struct intel_context *ce)

drivers/gpu/drm/i915/gt/intel_ggtt.c

@@ -1275,10 +1275,16 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
 			atomic_read(&vma->flags) & I915_VMA_BIND_MASK;
 
 		GEM_BUG_ON(!was_bound);
-		if (!retained_ptes)
+		if (!retained_ptes) {
+			/*
+			 * Clear the bound flags of the vma resource to allow
+			 * ptes to be repopulated.
+			 */
+			vma->resource->bound_flags = 0;
 			vma->ops->bind_vma(vm, NULL, vma->resource,
 					   obj ? obj->cache_level : 0,
 					   was_bound);
+		}
 		if (obj) { /* only used during resume => exclusive access */
 			write_domain_objs |= fetch_and_zero(&obj->write_domain);
 			obj->read_domains |= I915_GEM_DOMAIN_GTT;

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

@@ -684,7 +684,7 @@ static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 	 * Corner case where requests were sitting in the priority list or a
 	 * request resubmitted after the context was banned.
 	 */
-	if (unlikely(intel_context_is_banned(ce))) {
+	if (unlikely(!intel_context_is_schedulable(ce))) {
 		i915_request_put(i915_request_mark_eio(rq));
 		intel_engine_signal_breadcrumbs(ce->engine);
 		return 0;
@@ -870,15 +870,15 @@ static int guc_wq_item_append(struct intel_guc *guc,
 			      struct i915_request *rq)
 {
 	struct intel_context *ce = request_to_scheduling_context(rq);
-	int ret = 0;
+	int ret;
 
-	if (likely(!intel_context_is_banned(ce))) {
-		ret = __guc_wq_item_append(rq);
+	if (unlikely(!intel_context_is_schedulable(ce)))
+		return 0;
 
-		if (unlikely(ret == -EBUSY)) {
-			guc->stalled_request = rq;
-			guc->submission_stall_reason = STALL_MOVE_LRC_TAIL;
-		}
+	ret = __guc_wq_item_append(rq);
+	if (unlikely(ret == -EBUSY)) {
+		guc->stalled_request = rq;
+		guc->submission_stall_reason = STALL_MOVE_LRC_TAIL;
 	}
 
 	return ret;
@@ -897,7 +897,7 @@ static bool multi_lrc_submit(struct i915_request *rq)
 	 * submitting all the requests generated in parallel.
 	 */
 	return test_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, &rq->fence.flags) ||
-		intel_context_is_banned(ce);
+	       !intel_context_is_schedulable(ce);
 }
 
 static int guc_dequeue_one_context(struct intel_guc *guc)
@@ -966,7 +966,7 @@ register_context:
 		struct intel_context *ce = request_to_scheduling_context(last);
 
 		if (unlikely(!ctx_id_mapped(guc, ce->guc_id.id) &&
-			     !intel_context_is_banned(ce))) {
+			     intel_context_is_schedulable(ce))) {
 			ret = try_context_registration(ce, false);
 			if (unlikely(ret == -EPIPE)) {
 				goto deadlk;
@@ -1576,7 +1576,7 @@ static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub)
 {
 	struct intel_engine_cs *engine = __context_to_physical_engine(ce);
 
-	if (intel_context_is_banned(ce))
+	if (!intel_context_is_schedulable(ce))
 		return;
 
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
@@ -4424,12 +4424,12 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 {
 	trace_intel_context_reset(ce);
 
-	if (likely(!intel_context_is_banned(ce))) {
+	if (likely(intel_context_is_schedulable(ce))) {
 		capture_error_state(guc, ce);
 		guc_context_replay(ce);
 	} else {
 		drm_info(&guc_to_gt(guc)->i915->drm,
-			 "Ignoring context reset notification of banned context 0x%04X on %s",
+			 "Ignoring context reset notification of exiting context 0x%04X on %s",
 			 ce->guc_id.id, ce->engine->name);
 	}
 }