Merge tag 'drm-intel-fixes-2024-05-30' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-fixes

drm/i915 fixes for v6.10-rc2:
- Fix a race in audio component by registering it later
- Make DPT object unshrinkable to avoid shrinking when framebuffer has
  not shrunk
- Fix CCS id calculation to fix a perf regression
- Fix selftest caching mode
- Fix FIELD_PREP compiler warnings
- Fix indefinite wait for GT wakeref release
- Revert overeager multi-gt pm reference removal

Signed-off-by: Dave Airlie <[email protected]>
From: Jani Nikula <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

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

@@ -1252,17 +1252,6 @@ static const struct component_ops i915_audio_component_bind_ops = {
 static void i915_audio_component_init(struct drm_i915_private *i915)
 {
 	u32 aud_freq, aud_freq_init;
-	int ret;
-
-	ret = component_add_typed(i915->drm.dev,
-				  &i915_audio_component_bind_ops,
-				  I915_COMPONENT_AUDIO);
-	if (ret < 0) {
-		drm_err(&i915->drm,
-			"failed to add audio component (%d)\n", ret);
-		/* continue with reduced functionality */
-		return;
-	}
 
 	if (DISPLAY_VER(i915) >= 9) {
 		aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL);
@@ -1285,6 +1274,21 @@ static void i915_audio_component_init(struct drm_i915_private *i915)
 
 	/* init with current cdclk */
 	intel_audio_cdclk_change_post(i915);
+}
+
+static void i915_audio_component_register(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = component_add_typed(i915->drm.dev,
+				  &i915_audio_component_bind_ops,
+				  I915_COMPONENT_AUDIO);
+	if (ret < 0) {
+		drm_err(&i915->drm,
+			"failed to add audio component (%d)\n", ret);
+		/* continue with reduced functionality */
+		return;
+	}
 
 	i915->display.audio.component_registered = true;
 }
@@ -1317,6 +1321,12 @@ void intel_audio_init(struct drm_i915_private *i915)
 		i915_audio_component_init(i915);
 }
 
+void intel_audio_register(struct drm_i915_private *i915)
+{
+	if (!i915->display.audio.lpe.platdev)
+		i915_audio_component_register(i915);
+}
+
 /**
  * intel_audio_deinit() - deinitialize the audio driver
  * @i915: the i915 drm device private data

drivers/gpu/drm/i915/display/intel_audio.h

@@ -28,6 +28,7 @@ void intel_audio_codec_get_config(struct intel_encoder *encoder,
 void intel_audio_cdclk_change_pre(struct drm_i915_private *dev_priv);
 void intel_audio_cdclk_change_post(struct drm_i915_private *dev_priv);
 void intel_audio_init(struct drm_i915_private *dev_priv);
+void intel_audio_register(struct drm_i915_private *i915);
 void intel_audio_deinit(struct drm_i915_private *dev_priv);
 void intel_audio_sdp_split_update(const struct intel_crtc_state *crtc_state);
 

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

@@ -540,6 +540,8 @@ void intel_display_driver_register(struct drm_i915_private *i915)
 
 	intel_display_driver_enable_user_access(i915);
 
+	intel_audio_register(i915);
+
 	intel_display_debugfs_register(i915);
 
 	/*

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -255,6 +255,7 @@ struct i915_execbuffer {
 	struct intel_context *context; /* logical state for the request */
 	struct i915_gem_context *gem_context; /** caller's context */
 	intel_wakeref_t wakeref;
+	intel_wakeref_t wakeref_gt0;
 
 	/** our requests to build */
 	struct i915_request *requests[MAX_ENGINE_INSTANCE + 1];
@@ -2685,6 +2686,7 @@ static int
 eb_select_engine(struct i915_execbuffer *eb)
 {
 	struct intel_context *ce, *child;
+	struct intel_gt *gt;
 	unsigned int idx;
 	int err;
 
@@ -2708,10 +2710,17 @@ eb_select_engine(struct i915_execbuffer *eb)
 		}
 	}
 	eb->num_batches = ce->parallel.number_children + 1;
+	gt = ce->engine->gt;
 
 	for_each_child(ce, child)
 		intel_context_get(child);
 	eb->wakeref = intel_gt_pm_get(ce->engine->gt);
+	/*
+	 * Keep GT0 active on MTL so that i915_vma_parked() doesn't
+	 * free VMAs while execbuf ioctl is validating VMAs.
+	 */
+	if (gt->info.id)
+		eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915));
 
 	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
 		err = intel_context_alloc_state(ce);
@@ -2750,6 +2759,9 @@ eb_select_engine(struct i915_execbuffer *eb)
 	return err;
 
 err:
+	if (gt->info.id)
+		intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0);
+
 	intel_gt_pm_put(ce->engine->gt, eb->wakeref);
 	for_each_child(ce, child)
 		intel_context_put(child);
@@ -2763,6 +2775,12 @@ eb_put_engine(struct i915_execbuffer *eb)
 	struct intel_context *child;
 
 	i915_vm_put(eb->context->vm);
+	/*
+	 * This works in conjunction with eb_select_engine() to prevent
+	 * i915_vma_parked() from interfering while execbuf validates vmas.
+	 */
+	if (eb->gt->info.id)
+		intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0);
 	intel_gt_pm_put(eb->context->engine->gt, eb->wakeref);
 	for_each_child(eb->context, child)
 		intel_context_put(child);

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

@@ -284,7 +284,9 @@ bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj);
 static inline bool
 i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj)
 {
-	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE);
+	/* TODO: make DPT shrinkable when it has no bound vmas */
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE) &&
+		!obj->is_dpt;
 }
 
 static inline bool

drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c

@@ -196,7 +196,7 @@ static int verify_access(struct drm_i915_private *i915,
 	if (err)
 		goto out_file;
 
-	mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, true);
+	mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, false);
 	vaddr = i915_gem_object_pin_map_unlocked(native_obj, mode);
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);

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

@@ -263,8 +263,13 @@ static void signal_irq_work(struct irq_work *work)
 		i915_request_put(rq);
 	}
 
+	/* Lazy irq enabling after HW submission */
 	if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers))
 		intel_breadcrumbs_arm_irq(b);
+
+	/* And confirm that we still want irqs enabled before we yield */
+	if (READ_ONCE(b->irq_armed) && !atomic_read(&b->active))
+		intel_breadcrumbs_disarm_irq(b);
 }
 
 struct intel_breadcrumbs *
@@ -315,13 +320,7 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
 		return;
 
 	/* Kick the work once more to drain the signalers, and disarm the irq */
-	irq_work_sync(&b->irq_work);
-	while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) {
-		local_irq_disable();
-		signal_irq_work(&b->irq_work);
-		local_irq_enable();
-		cond_resched();
-	}
+	irq_work_queue(&b->irq_work);
 }
 
 void intel_breadcrumbs_free(struct kref *kref)
@@ -404,7 +403,7 @@ static void insert_breadcrumb(struct i915_request *rq)
 	 * the request as it may have completed and raised the interrupt as
 	 * we were attaching it into the lists.
 	 */
-	if (!b->irq_armed || __i915_request_is_complete(rq))
+	if (!READ_ONCE(b->irq_armed) || __i915_request_is_complete(rq))
 		irq_work_queue(&b->irq_work);
 }
 

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

@@ -885,6 +885,12 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 	if (IS_DG2(gt->i915)) {
 		u8 first_ccs = __ffs(CCS_MASK(gt));
 
+		/*
+		 * Store the number of active cslices before
+		 * changing the CCS engine configuration
+		 */
+		gt->ccs.cslices = CCS_MASK(gt);
+
 		/* Mask off all the CCS engine */
 		info->engine_mask &= ~GENMASK(CCS3, CCS0);
 		/* Put back in the first CCS engine */

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

@@ -19,7 +19,7 @@ unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt)
 
 	/* Build the value for the fixed CCS load balancing */
 	for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
-		if (CCS_MASK(gt) & BIT(cslice))
+		if (gt->ccs.cslices & BIT(cslice))
 			/*
 			 * If available, assign the cslice
 			 * to the first available engine...

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

@@ -207,6 +207,14 @@ struct intel_gt {
 					    [MAX_ENGINE_INSTANCE + 1];
 	enum intel_submission_method submission_method;
 
+	struct {
+		/*
+		 * Mask of the non fused CCS slices
+		 * to be used for the load balancing
+		 */
+		intel_engine_mask_t cslices;
+	} ccs;
+
 	/*
 	 * Default address space (either GGTT or ppGTT depending on arch).
 	 *