Merge tag 'drm-intel-fixes-2017-07-27' of git://anongit.freedesktop.org/git/drm-intel into drm-fixes

i915 fixes for -rc3

Bit more than usual since we missed -rc2. 4x cc: stable, 2 gvt
patches, but all fairly minor stuff. Last minute rebase was to add a
few missing cc: stable, I did prep the pull this morning already and
made sure CI approves.

* tag 'drm-intel-fixes-2017-07-27' of git://anongit.freedesktop.org/git/drm-intel:
  drm/i915: Fix bad comparison in skl_compute_plane_wm.
  drm/i915: Force CPU synchronisation even if userspace requests ASYNC
  drm/i915: Only skip updating execobject.offset after error
  drm/i915: Only mark the execobject as pinned on success
  drm/i915: Remove assertion from raw __i915_vma_unpin()
  drm/i915/cnl: Fix loadgen select programming on ddi vswing sequence
  drm/i915: Fix scaler init during CRTC HW state readout
  drm/i915/selftests: Fix an error handling path in 'mock_gem_device()'
  drm/i915: Unbreak gpu reset vs. modeset locking
  drm/i915: Fix cursor updates on some platforms
  drm/i915: Fix user ptr check size in eb_relocate_vma()
  drm/i915/gvt: Extend KBL platform support in GVT-g
  drm/i915/gvt: Fix the vblank timer close issue after shutdown VMs in reverse

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

@@ -323,27 +323,27 @@ void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt)
 {
 	struct intel_gvt_irq *irq = &gvt->irq;
 	struct intel_vgpu *vgpu;
-	bool have_enabled_pipe = false;
 	int pipe, id;
 
 	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
 		return;
 
-	hrtimer_cancel(&irq->vblank_timer.timer);
-
 	for_each_active_vgpu(gvt, vgpu, id) {
 		for (pipe = 0; pipe < I915_MAX_PIPES; pipe++) {
-			have_enabled_pipe =
+			if (pipe_is_enabled(vgpu, pipe))
-				pipe_is_enabled(vgpu, pipe);
+				goto out;
-			if (have_enabled_pipe)
-				break;
 		}
 	}
 
-	if (have_enabled_pipe)
+	/* all the pipes are disabled */
-		hrtimer_start(&irq->vblank_timer.timer,
+	hrtimer_cancel(&irq->vblank_timer.timer);
-			ktime_add_ns(ktime_get(), irq->vblank_timer.period),
+	return;
-			HRTIMER_MODE_ABS);
+
+out:
+	hrtimer_start(&irq->vblank_timer.timer,
+		ktime_add_ns(ktime_get(), irq->vblank_timer.period),
+		HRTIMER_MODE_ABS);
+
 }
 
 static void emulate_vblank_on_pipe(struct intel_vgpu *vgpu, int pipe)

drivers/gpu/drm/i915/i915_gem_clflush.c

@@ -114,7 +114,7 @@ i915_clflush_notify(struct i915_sw_fence *fence,
 	return NOTIFY_DONE;
 }
 
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 			     unsigned int flags)
 {
 	struct clflush *clflush;
@@ -128,7 +128,7 @@ void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	 */
 	if (!i915_gem_object_has_struct_page(obj)) {
 		obj->cache_dirty = false;
-		return;
+		return false;
 	}
 
 	/* If the GPU is snooping the contents of the CPU cache,
@@ -140,7 +140,7 @@ void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	 * tracking.
 	 */
 	if (!(flags & I915_CLFLUSH_FORCE) && obj->cache_coherent)
-		return;
+		return false;
 
 	trace_i915_gem_object_clflush(obj);
 
@@ -179,4 +179,5 @@ void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 	}
 
 	obj->cache_dirty = false;
+	return true;
 }

drivers/gpu/drm/i915/i915_gem_clflush.h

@@ -28,7 +28,7 @@
 struct drm_i915_private;
 struct drm_i915_gem_object;
 
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 			     unsigned int flags);
 #define I915_CLFLUSH_FORCE BIT(0)
 #define I915_CLFLUSH_SYNC BIT(1)

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -560,9 +560,6 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 		eb->args->flags |= __EXEC_HAS_RELOC;
 	}
 
-	entry->flags |= __EXEC_OBJECT_HAS_PIN;
-	GEM_BUG_ON(eb_vma_misplaced(entry, vma));
-
 	if (unlikely(entry->flags & EXEC_OBJECT_NEEDS_FENCE)) {
 		err = i915_vma_get_fence(vma);
 		if (unlikely(err)) {
@@ -574,6 +571,9 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb,
 			entry->flags |= __EXEC_OBJECT_HAS_FENCE;
 	}
 
+	entry->flags |= __EXEC_OBJECT_HAS_PIN;
+	GEM_BUG_ON(eb_vma_misplaced(entry, vma));
+
 	return 0;
 }
 
@@ -1458,7 +1458,7 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct i915_vma *vma)
 	 * to read. However, if the array is not writable the user loses
 	 * the updated relocation values.
 	 */
-	if (unlikely(!access_ok(VERIFY_READ, urelocs, remain*sizeof(urelocs))))
+	if (unlikely(!access_ok(VERIFY_READ, urelocs, remain*sizeof(*urelocs))))
 		return -EFAULT;
 
 	do {
@@ -1775,7 +1775,7 @@ out:
 		}
 	}
 
-	return err ?: have_copy;
+	return err;
 }
 
 static int eb_relocate(struct i915_execbuffer *eb)
@@ -1825,7 +1825,7 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 	int err;
 
 	for (i = 0; i < count; i++) {
-		const struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
+		struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
 		struct i915_vma *vma = exec_to_vma(entry);
 		struct drm_i915_gem_object *obj = vma->obj;
 
@@ -1841,12 +1841,14 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 			eb->request->capture_list = capture;
 		}
 
+		if (unlikely(obj->cache_dirty && !obj->cache_coherent)) {
+			if (i915_gem_clflush_object(obj, 0))
+				entry->flags &= ~EXEC_OBJECT_ASYNC;
+		}
+
 		if (entry->flags & EXEC_OBJECT_ASYNC)
 			goto skip_flushes;
 
-		if (unlikely(obj->cache_dirty && !obj->cache_coherent))
-			i915_gem_clflush_object(obj, 0);
-
 		err = i915_gem_request_await_object
 			(eb->request, obj, entry->flags & EXEC_OBJECT_WRITE);
 		if (err)
@@ -2209,7 +2211,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		goto err_unlock;
 
 	err = eb_relocate(&eb);
-	if (err)
+	if (err) {
 		/*
 		 * If the user expects the execobject.offset and
 		 * reloc.presumed_offset to be an exact match,
@@ -2218,8 +2220,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		 * relocation.
 		 */
 		args->flags &= ~__EXEC_HAS_RELOC;
-	if (err < 0)
 		goto err_vma;
+	}
 
 	if (unlikely(eb.batch->exec_entry->flags & EXEC_OBJECT_WRITE)) {
 		DRM_DEBUG("Attempting to use self-modifying batch buffer\n");

drivers/gpu/drm/i915/i915_vma.h

@@ -284,12 +284,12 @@ static inline void __i915_vma_pin(struct i915_vma *vma)
 
 static inline void __i915_vma_unpin(struct i915_vma *vma)
 {
-	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 	vma->flags--;
 }
 
 static inline void i915_vma_unpin(struct i915_vma *vma)
 {
+	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	__i915_vma_unpin(vma);
 }

drivers/gpu/drm/i915/intel_ddi.c

@@ -1896,8 +1896,8 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder, u32 level)
 		val = I915_READ(CNL_PORT_TX_DW4_LN(port, ln));
 		val &= ~LOADGEN_SELECT;
 
-		if (((rate < 600000) && (width == 4) && (ln >= 1))  ||
+		if ((rate <= 600000 && width == 4 && ln >= 1)  ||
-		    ((rate < 600000) && (width < 4) && ((ln == 1) || (ln == 2)))) {
+		    (rate <= 600000 && width < 4 && (ln == 1 || ln == 2))) {
 			val |= LOADGEN_SELECT;
 		}
 		I915_WRITE(CNL_PORT_TX_DW4_LN(port, ln), val);

drivers/gpu/drm/i915/intel_display.c

@@ -3427,26 +3427,6 @@ static void intel_complete_page_flips(struct drm_i915_private *dev_priv)
 		intel_finish_page_flip_cs(dev_priv, crtc->pipe);
 }
 
-static void intel_update_primary_planes(struct drm_device *dev)
-{
-	struct drm_crtc *crtc;
-
-	for_each_crtc(dev, crtc) {
-		struct intel_plane *plane = to_intel_plane(crtc->primary);
-		struct intel_plane_state *plane_state =
-			to_intel_plane_state(plane->base.state);
-
-		if (plane_state->base.visible) {
-			trace_intel_update_plane(&plane->base,
-						 to_intel_crtc(crtc));
-
-			plane->update_plane(plane,
-					    to_intel_crtc_state(crtc->state),
-					    plane_state);
-		}
-	}
-}
-
 static int
 __intel_display_resume(struct drm_device *dev,
 		       struct drm_atomic_state *state,
@@ -3499,6 +3479,12 @@ void intel_prepare_reset(struct drm_i915_private *dev_priv)
 	struct drm_atomic_state *state;
 	int ret;
 
+
+	/* reset doesn't touch the display */
+	if (!i915.force_reset_modeset_test &&
+	    !gpu_reset_clobbers_display(dev_priv))
+		return;
+
 	/*
 	 * Need mode_config.mutex so that we don't
 	 * trample ongoing ->detect() and whatnot.
@@ -3512,12 +3498,6 @@ void intel_prepare_reset(struct drm_i915_private *dev_priv)
 
 		drm_modeset_backoff(ctx);
 	}
-
-	/* reset doesn't touch the display, but flips might get nuked anyway, */
-	if (!i915.force_reset_modeset_test &&
-	    !gpu_reset_clobbers_display(dev_priv))
-		return;
-
 	/*
 	 * Disabling the crtcs gracefully seems nicer. Also the
 	 * g33 docs say we should at least disable all the planes.
@@ -3547,6 +3527,14 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 	struct drm_atomic_state *state = dev_priv->modeset_restore_state;
 	int ret;
 
+	/* reset doesn't touch the display */
+	if (!i915.force_reset_modeset_test &&
+	    !gpu_reset_clobbers_display(dev_priv))
+		return;
+
+	if (!state)
+		goto unlock;
+
 	/*
 	 * Flips in the rings will be nuked by the reset,
 	 * so complete all pending flips so that user space
@@ -3558,22 +3546,10 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 
 	/* reset doesn't touch the display */
 	if (!gpu_reset_clobbers_display(dev_priv)) {
-		if (!state) {
+		/* for testing only restore the display */
-			/*
+		ret = __intel_display_resume(dev, state, ctx);
-			 * Flips in the rings have been nuked by the reset,
-			 * so update the base address of all primary
-			 * planes to the the last fb to make sure we're
-			 * showing the correct fb after a reset.
-			 *
-			 * FIXME: Atomic will make this obsolete since we won't schedule
-			 * CS-based flips (which might get lost in gpu resets) any more.
-			 */
-			intel_update_primary_planes(dev);
-		} else {
-			ret = __intel_display_resume(dev, state, ctx);
 			if (ret)
 				DRM_ERROR("Restoring old state failed with %i\n", ret);
-		}
 	} else {
 		/*
 		 * The display has been reset as well,
@@ -3597,8 +3573,8 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 		intel_hpd_init(dev_priv);
 	}
 
-	if (state)
+	drm_atomic_state_put(state);
-		drm_atomic_state_put(state);
+unlock:
 	drm_modeset_drop_locks(ctx);
 	drm_modeset_acquire_fini(ctx);
 	mutex_unlock(&dev->mode_config.mutex);
@@ -9117,6 +9093,13 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	u64 power_domain_mask;
 	bool active;
 
+	if (INTEL_GEN(dev_priv) >= 9) {
+		intel_crtc_init_scalers(crtc, pipe_config);
+
+		pipe_config->scaler_state.scaler_id = -1;
+		pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX);
+	}
+
 	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
@@ -9145,13 +9128,6 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	pipe_config->gamma_mode =
 		I915_READ(GAMMA_MODE(crtc->pipe)) & GAMMA_MODE_MODE_MASK;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		intel_crtc_init_scalers(crtc, pipe_config);
-
-		pipe_config->scaler_state.scaler_id = -1;
-		pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX);
-	}
-
 	power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
 	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
 		power_domain_mask |= BIT_ULL(power_domain);
@@ -9540,7 +9516,16 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 	 * On some platforms writing CURCNTR first will also
 	 * cause CURPOS to be armed by the CURBASE write.
 	 * Without the CURCNTR write the CURPOS write would
-	 * arm itself.
+	 * arm itself. Thus we always start the full update
+	 * with a CURCNTR write.
+	 *
+	 * On other platforms CURPOS always requires the
+	 * CURBASE write to arm the update. Additonally
+	 * a write to any of the cursor register will cancel
+	 * an already armed cursor update. Thus leaving out
+	 * the CURBASE write after CURPOS could lead to a
+	 * cursor that doesn't appear to move, or even change
+	 * shape. Thus we always write CURBASE.
 	 *
 	 * CURCNTR and CUR_FBC_CTL are always
 	 * armed by the CURBASE write only.
@@ -9559,6 +9544,7 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 		plane->cursor.cntl = cntl;
 	} else {
 		I915_WRITE_FW(CURPOS(pipe), pos);
+		I915_WRITE_FW(CURBASE(pipe), base);
 	}
 
 	POSTING_READ_FW(CURBASE(pipe));

drivers/gpu/drm/i915/intel_gvt.c

@@ -45,7 +45,7 @@ static bool is_supported_device(struct drm_i915_private *dev_priv)
 		return true;
 	if (IS_SKYLAKE(dev_priv))
 		return true;
-	if (IS_KABYLAKE(dev_priv) && INTEL_DEVID(dev_priv) == 0x591D)
+	if (IS_KABYLAKE(dev_priv))
 		return true;
 	return false;
 }

drivers/gpu/drm/i915/intel_pm.c

@@ -4463,8 +4463,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		if ((cpp * cstate->base.adjusted_mode.crtc_htotal / 512 < 1) &&
 		    (plane_bytes_per_line / 512 < 1))
 			selected_result = method2;
-		else if ((ddb_allocation && ddb_allocation /
+		else if (ddb_allocation >=
-			fixed_16_16_to_u32_round_up(plane_blocks_per_line)) >= 1)
+			 fixed_16_16_to_u32_round_up(plane_blocks_per_line))
 			selected_result = min_fixed_16_16(method1, method2);
 		else if (latency >= linetime_us)
 			selected_result = min_fixed_16_16(method1, method2);

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

@@ -206,7 +206,7 @@ struct drm_i915_private *mock_gem_device(void)
 	mkwrite_device_info(i915)->ring_mask = BIT(0);
 	i915->engine[RCS] = mock_engine(i915, "mock");
 	if (!i915->engine[RCS])
-		goto err_dependencies;
+		goto err_priorities;
 
 	i915->kernel_context = mock_context(i915, NULL);
 	if (!i915->kernel_context)