Merge tag 'v4.10-rc8' into drm-next

Linux 4.10-rc8

Backmerge Linus rc8 to fix some conflicts, but also
to avoid pulling it in via a fixes pull from someone.

13 files changed, 106 insertions, 80 deletions

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 7bb11a555b76..b9c8e2407682 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -481,7 +481,6 @@ struct parser_exec_state {
 	(s->vgpu->gvt->device_info.gmadr_bytes_in_cmd >> 2)
 
 static unsigned long bypass_scan_mask = 0;
-static bool bypass_batch_buffer_scan = true;
 
 /* ring ALL, type = 0 */
 static struct sub_op_bits sub_op_mi[] = {
@@ -1543,9 +1542,6 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s)
 {
 	struct intel_gvt *gvt = s->vgpu->gvt;
 
-	if (bypass_batch_buffer_scan)
-		return 0;
-
 	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) {
 		/* BDW decides privilege based on address space */
 		if (cmd_val(s, 0) & (1 << 8))
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 136c6e77561a..46eb9fd3c03f 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -364,58 +364,30 @@ static void free_workload(struct intel_vgpu_workload *workload)
 #define get_desc_from_elsp_dwords(ed, i) \
 	((struct execlist_ctx_descriptor_format *)&((ed)->data[i * 2]))
 
-
-#define BATCH_BUFFER_ADDR_MASK ((1UL << 32) - (1U << 2))
-#define BATCH_BUFFER_ADDR_HIGH_MASK ((1UL << 16) - (1U))
-static int set_gma_to_bb_cmd(struct intel_shadow_bb_entry *entry_obj,
-			     unsigned long add, int gmadr_bytes)
-{
-	if (WARN_ON(gmadr_bytes != 4 && gmadr_bytes != 8))
-		return -1;
-
-	*((u32 *)(entry_obj->bb_start_cmd_va + (1 << 2))) = add &
-		BATCH_BUFFER_ADDR_MASK;
-	if (gmadr_bytes == 8) {
-		*((u32 *)(entry_obj->bb_start_cmd_va + (2 << 2))) =
-			add & BATCH_BUFFER_ADDR_HIGH_MASK;
-	}
-
-	return 0;
-}
-
 static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 {
-	int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd;
+	const int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd;
+	struct intel_shadow_bb_entry *entry_obj;
 
 	/* pin the gem object to ggtt */
-	if (!list_empty(&workload->shadow_bb)) {
-		struct intel_shadow_bb_entry *entry_obj =
-			list_first_entry(&workload->shadow_bb,
-					 struct intel_shadow_bb_entry,
-					 list);
-		struct intel_shadow_bb_entry *temp;
+	list_for_each_entry(entry_obj, &workload->shadow_bb, list) {
+		struct i915_vma *vma;
 
-		list_for_each_entry_safe(entry_obj, temp, &workload->shadow_bb,
-				list) {
-			struct i915_vma *vma;
-
-			vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0,
-						       4, 0);
-			if (IS_ERR(vma)) {
-				gvt_err("Cannot pin\n");
-				return;
-			}
-
-			/* FIXME: we are not tracking our pinned VMA leaving it
-			 * up to the core to fix up the stray pin_count upon
-			 * free.
-			 */
-
-			/* update the relocate gma with shadow batch buffer*/
-			set_gma_to_bb_cmd(entry_obj,
-					  i915_ggtt_offset(vma),
-					  gmadr_bytes);
+		vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0);
+		if (IS_ERR(vma)) {
+			gvt_err("Cannot pin\n");
+			return;
 		}
+
+		/* FIXME: we are not tracking our pinned VMA leaving it
+		 * up to the core to fix up the stray pin_count upon
+		 * free.
+		 */
+
+		/* update the relocate gma with shadow batch buffer*/
+		entry_obj->bb_start_cmd_va[1] = i915_ggtt_offset(vma);
+		if (gmadr_bytes == 8)
+			entry_obj->bb_start_cmd_va[2] = 0;
 	}
 }
 
@@ -826,7 +798,7 @@ int intel_vgpu_init_execlist(struct intel_vgpu *vgpu)
 		INIT_LIST_HEAD(&vgpu->workload_q_head[i]);
 	}
 
-	vgpu->workloads = kmem_cache_create("gvt-g vgpu workload",
+	vgpu->workloads = kmem_cache_create("gvt-g_vgpu_workload",
 			sizeof(struct intel_vgpu_workload), 0,
 			SLAB_HWCACHE_ALIGN,
 			NULL);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 10c3a4b95a92..0f7f5d97f582 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -262,8 +262,8 @@ static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt,
 	return NULL;
 }
 
-static ssize_t available_instance_show(struct kobject *kobj, struct device *dev,
-		char *buf)
+static ssize_t available_instances_show(struct kobject *kobj,
+					struct device *dev, char *buf)
 {
 	struct intel_vgpu_type *type;
 	unsigned int num = 0;
@@ -301,12 +301,12 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev,
 				type->fence);
 }
 
-static MDEV_TYPE_ATTR_RO(available_instance);
+static MDEV_TYPE_ATTR_RO(available_instances);
 static MDEV_TYPE_ATTR_RO(device_api);
 static MDEV_TYPE_ATTR_RO(description);
 
 static struct attribute *type_attrs[] = {
-	&mdev_type_attr_available_instance.attr,
+	&mdev_type_attr_available_instances.attr,
 	&mdev_type_attr_device_api.attr,
 	&mdev_type_attr_description.attr,
 	NULL,
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 3b30c28bff51..2833dfa8c9ae 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -113,7 +113,7 @@ struct intel_shadow_bb_entry {
 	struct drm_i915_gem_object *obj;
 	void *va;
 	unsigned long len;
-	void *bb_start_cmd_va;
+	u32 *bb_start_cmd_va;
 };
 
 #define workload_q_head(vgpu, ring_id) \
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 1dfc0b204a72..f6017f2cfb86 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -213,7 +213,8 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 			} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_KBP;
 				DRM_DEBUG_KMS("Found KabyPoint PCH\n");
-				WARN_ON(!IS_KABYLAKE(dev_priv));
+				WARN_ON(!IS_SKYLAKE(dev_priv) &&
+					!IS_KABYLAKE(dev_priv));
 			} else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) ||
 				   (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) ||
 				   ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) &&
@@ -2377,7 +2378,7 @@ static int intel_runtime_suspend(struct device *kdev)
 
 	assert_forcewakes_inactive(dev_priv);
 
-	if (!IS_VALLEYVIEW(dev_priv) || !IS_CHERRYVIEW(dev_priv))
+	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		intel_hpd_poll_init(dev_priv);
 
 	DRM_DEBUG_KMS("Device suspended\n");
@@ -2426,6 +2427,7 @@ static int intel_runtime_resume(struct device *kdev)
 	 * we can do is to hope that things will still work (and disable RPM).
 	 */
 	i915_gem_init_swizzling(dev_priv);
+	i915_gem_restore_fences(dev_priv);
 
 	intel_runtime_pm_enable_interrupts(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 244628065f94..e44c598ecb82 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2242,6 +2242,11 @@ struct drm_i915_private {
 
 	struct i915_frontbuffer_tracking fb_tracking;
 
+	struct intel_atomic_helper {
+		struct llist_head free_list;
+		struct work_struct free_work;
+	} atomic_helper;
+
 	u16 orig_clock;
 
 	bool mchbar_need_disable;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a51b134038a0..88f3628b4e29 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2009,8 +2009,16 @@ void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
 
-		if (WARN_ON(reg->pin_count))
-			continue;
+		/* Ideally we want to assert that the fence register is not
+		 * live at this point (i.e. that no piece of code will be
+		 * trying to write through fence + GTT, as that both violates
+		 * our tracking of activity and associated locking/barriers,
+		 * but also is illegal given that the hw is powered down).
+		 *
+		 * Previously we used reg->pin_count as a "liveness" indicator.
+		 * That is not sufficient, and we need a more fine-grained
+		 * tool if we want to have a sanity check here.
+		 */
 
 		if (!reg->vma)
 			continue;
@@ -3513,7 +3521,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
 	/* Treat this as an end-of-frame, like intel_user_framebuffer_dirty() */
-	if (obj->cache_dirty) {
+	if (obj->cache_dirty || obj->base.write_domain == I915_GEM_DOMAIN_CPU) {
 		i915_gem_clflush_object(obj, true);
 		intel_fb_obj_flush(obj, false, ORIGIN_DIRTYFB);
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 57bec08e80c5..d02cfaefe1c8 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1180,14 +1180,14 @@ validate_exec_list(struct drm_device *dev,
 			if (exec[i].offset !=
 			    gen8_canonical_addr(exec[i].offset & PAGE_MASK))
 				return -EINVAL;
-
-			/* From drm_mm perspective address space is continuous,
-			 * so from this point we're always using non-canonical
-			 * form internally.
-			 */
-			exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
 		}
 
+		/* From drm_mm perspective address space is continuous,
+		 * so from this point we're always using non-canonical
+		 * form internally.
+		 */
+		exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
+
 		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
 			return -EINVAL;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_internal.c b/drivers/gpu/drm/i915/i915_gem_internal.c
index 628699a91106..933019e1b206 100644
--- a/drivers/gpu/drm/i915/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/i915_gem_internal.c
@@ -54,8 +54,16 @@ i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 
 	max_order = MAX_ORDER;
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) /* minimum max swiotlb size is IO_TLB_SEGSIZE */
-		max_order = min(max_order, ilog2(IO_TLB_SEGPAGES));
+	if (swiotlb_nr_tbl()) {
+		unsigned int max_segment;
+
+		max_segment = swiotlb_max_segment();
+		if (max_segment) {
+			max_segment = max_t(unsigned int, max_segment,
+					    PAGE_SIZE) >> PAGE_SHIFT;
+			max_order = min(max_order, ilog2(max_segment));
+		}
+	}
 #endif
 
 	gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 385e29af8baa..2bf5aca6e37c 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -499,6 +499,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev);
 	struct edid *edid;
 	struct i2c_adapter *i2c;
+	bool ret = false;
 
 	BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
 
@@ -515,17 +516,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		 */
 		if (!is_digital) {
 			DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
-			return true;
+			ret = true;
+		} else {
+			DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 		}
-
-		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 	} else {
 		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n");
 	}
 
 	kfree(edid);
 
-	return false;
+	return ret;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b3e773c9f872..01341670738f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2578,8 +2578,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			 * We only keep the x/y offsets, so push all of the
 			 * gtt offset into the x/y offsets.
 			 */
-			_intel_adjust_tile_offset(&x, &y, tile_size,
-						  tile_width, tile_height, pitch_tiles,
+			_intel_adjust_tile_offset(&x, &y,
+						  tile_width, tile_height,
+						  tile_size, pitch_tiles,
 						  gtt_offset_rotated * tile_size, 0);
 
 			gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height;
@@ -4252,10 +4253,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 	drm_crtc_vblank_put(&intel_crtc->base);
 
 	wake_up_all(&dev_priv->pending_flip_queue);
-	queue_work(dev_priv->wq, &work->unpin_work);
-
 	trace_i915_flip_complete(intel_crtc->plane,
 				 work->pending_flip_obj);
+
+	queue_work(dev_priv->wq, &work->unpin_work);
 }
 
 static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
@@ -6881,6 +6882,12 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
 	}
 
 	state = drm_atomic_state_alloc(crtc->dev);
+	if (!state) {
+		DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory",
+			      crtc->base.id, crtc->name);
+		return;
+	}
+
 	state->acquire_ctx = crtc->dev->mode_config.acquire_ctx;
 
 	/* Everything's already locked, -EDEADLK can't happen. */
@@ -14562,8 +14569,14 @@ intel_atomic_commit_ready(struct i915_sw_fence *fence,
 		break;
 
 	case FENCE_FREE:
-		drm_atomic_state_put(&state->base);
-		break;
+		{
+			struct intel_atomic_helper *helper =
+				&to_i915(state->base.dev)->atomic_helper;
+
+			if (llist_add(&state->freed, &helper->free_list))
+				schedule_work(&helper->free_work);
+			break;
+		}
 	}
 
 	return NOTIFY_DONE;
@@ -16586,6 +16599,18 @@ fail:
 	drm_modeset_acquire_fini(&ctx);
 }
 
+static void intel_atomic_helper_free_state(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), atomic_helper.free_work);
+	struct intel_atomic_state *state, *next;
+	struct llist_node *freed;
+
+	freed = llist_del_all(&dev_priv->atomic_helper.free_list);
+	llist_for_each_entry_safe(state, next, freed, freed)
+		drm_atomic_state_put(&state->base);
+}
+
 int intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16605,6 +16630,9 @@ int intel_modeset_init(struct drm_device *dev)
 
 	dev->mode_config.funcs = &intel_mode_funcs;
 
+	INIT_WORK(&dev_priv->atomic_helper.free_work,
+		  intel_atomic_helper_free_state);
+
 	intel_init_quirks(dev);
 
 	intel_init_pm(dev_priv);
@@ -17262,6 +17290,9 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	flush_work(&dev_priv->atomic_helper.free_work);
+	WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
+
 	intel_disable_gt_powersave(dev_priv);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index c92a2558beb4..e59e43a9f3a6 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1855,7 +1855,8 @@ bxt_get_dpll(struct intel_crtc *crtc,
 		return NULL;
 
 	if ((encoder->type == INTEL_OUTPUT_DP ||
-	     encoder->type == INTEL_OUTPUT_EDP) &&
+	     encoder->type == INTEL_OUTPUT_EDP ||
+	     encoder->type == INTEL_OUTPUT_DP_MST) &&
 	    !bxt_ddi_dp_set_dpll_hw_state(clock, &dpll_hw_state))
 		return NULL;
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a60f442f2686..40fed65a791d 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -371,6 +371,8 @@ struct intel_atomic_state {
 	struct skl_wm_values wm_results;
 
 	struct i915_sw_fence commit_ready;
+
+	struct llist_node freed;
 };
 
 struct intel_plane_state {