diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 055d5e7fbf12..2318b4c7a8f8 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -986,6 +986,15 @@ static int i915_pm_freeze(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
+static int i915_pm_freeze_late(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+
+	return intel_suspend_complete(dev_priv);
+}
+
 static int i915_pm_thaw_early(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1570,6 +1579,7 @@ static const struct dev_pm_ops i915_pm_ops = {
 	.resume_early = i915_pm_resume_early,
 	.resume = i915_pm_resume,
 	.freeze = i915_pm_freeze,
+	.freeze_late = i915_pm_freeze_late,
 	.thaw_early = i915_pm_thaw_early,
 	.thaw = i915_pm_thaw,
 	.poweroff = i915_pm_poweroff,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index b672b843fd5e..728938f02341 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1902,6 +1902,22 @@ static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
 	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
 	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
 
+	if (!USES_PPGTT(dev_priv->dev))
+		/* Spec: "For GGTT, there is NO pat_sel[2:0] from the entry,
+		 * so RTL will always use the value corresponding to
+		 * pat_sel = 000".
+		 * So let's disable cache for GGTT to avoid screen corruptions.
+		 * MOCS still can be used though.
+		 * - System agent ggtt writes (i.e. cpu gtt mmaps) already work
+		 * before this patch, i.e. the same uncached + snooping access
+		 * like on gen6/7 seems to be in effect.
+		 * - So this just fixes blitter/render access. Again it looks
+		 * like it's not just uncached access, but uncached + snooping.
+		 * So we can still hold onto all our assumptions wrt cpu
+		 * clflushing on LLC machines.
+		 */
+		pat = GEN8_PPAT(0, GEN8_PPAT_UC);
+
 	/* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
 	 * write would work. */
 	I915_WRITE(GEN8_PRIVATE_PAT, pat);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 0e018cb49147..41b3be217493 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1098,12 +1098,25 @@ static u32 get_backlight_min_vbt(struct intel_connector *connector)
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_panel *panel = &connector->panel;
+	int min;
 
 	WARN_ON(panel->backlight.max == 0);
 
+	/*
+	 * XXX: If the vbt value is 255, it makes min equal to max, which leads
+	 * to problems. There are such machines out there. Either our
+	 * interpretation is wrong or the vbt has bogus data. Or both. Safeguard
+	 * against this by letting the minimum be at most (arbitrarily chosen)
+	 * 25% of the max.
+	 */
+	min = clamp_t(int, dev_priv->vbt.backlight.min_brightness, 0, 64);
+	if (min != dev_priv->vbt.backlight.min_brightness) {
+		DRM_DEBUG_KMS("clamping VBT min backlight %d/255 to %d/255\n",
+			      dev_priv->vbt.backlight.min_brightness, min);
+	}
+
 	/* vbt value is a coefficient in range [0..255] */
-	return scale(dev_priv->vbt.backlight.min_brightness, 0, 255,
-		     0, panel->backlight.max);
+	return scale(min, 0, 255, 0, panel->backlight.max);
 }
 
 static int bdw_setup_backlight(struct intel_connector *connector)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 377afa504d2b..89c01fa6dd8e 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -4313,8 +4313,8 @@ static int cik_cp_gfx_start(struct radeon_device *rdev)
 	/* init the CE partitions.  CE only used for gfx on CIK */
 	radeon_ring_write(ring, PACKET3(PACKET3_SET_BASE, 2));
 	radeon_ring_write(ring, PACKET3_BASE_INDEX(CE_PARTITION_BASE));
-	radeon_ring_write(ring, 0xc000);
-	radeon_ring_write(ring, 0xc000);
+	radeon_ring_write(ring, 0x8000);
+	radeon_ring_write(ring, 0x8000);
 
 	/* setup clear context state */
 	radeon_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0));
@@ -9447,6 +9447,9 @@ void dce8_bandwidth_update(struct radeon_device *rdev)
 	u32 num_heads = 0, lb_size;
 	int i;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	for (i = 0; i < rdev->num_crtc; i++) {
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 4e8432d07f15..d748963af08b 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -667,17 +667,20 @@ int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	struct radeon_ib ib;
 	unsigned i;
+	unsigned index;
 	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
 	u32 tmp = 0;
+	u64 gpu_addr;
 
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
 
 	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
+	rdev->wb.wb[index/4] = cpu_to_le32(tmp);
 
 	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
 	if (r) {
@@ -686,8 +689,8 @@ int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	}
 
 	ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
-	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
-	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr);
+	ib.ptr[1] = lower_32_bits(gpu_addr);
+	ib.ptr[2] = upper_32_bits(gpu_addr);
 	ib.ptr[3] = 1;
 	ib.ptr[4] = 0xDEADBEEF;
 	ib.length_dw = 5;
@@ -704,7 +707,7 @@ int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 		return r;
 	}
 	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index f37d39d2bbbc..85995b4e3338 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2345,6 +2345,9 @@ void evergreen_bandwidth_update(struct radeon_device *rdev)
 	u32 num_heads = 0, lb_size;
 	int i;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	for (i = 0; i < rdev->num_crtc; i++) {
@@ -2552,6 +2555,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
 					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
 					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 10f8be0ee173..b53b31a7b76f 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3207,6 +3207,9 @@ void r100_bandwidth_update(struct radeon_device *rdev)
 	uint32_t pixel_bytes1 = 0;
 	uint32_t pixel_bytes2 = 0;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled) {
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
index aabc343b9a8f..cf0df45d455e 100644
--- a/drivers/gpu/drm/radeon/r600_dma.c
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -338,17 +338,17 @@ int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	struct radeon_ib ib;
 	unsigned i;
+	unsigned index;
 	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
 	u32 tmp = 0;
+	u64 gpu_addr;
 
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
 
-	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
+	gpu_addr = rdev->wb.gpu_addr + index;
 
 	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
 	if (r) {
@@ -357,8 +357,8 @@ int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	}
 
 	ib.ptr[0] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1);
-	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
-	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff;
+	ib.ptr[1] = lower_32_bits(gpu_addr);
+	ib.ptr[2] = upper_32_bits(gpu_addr) & 0xff;
 	ib.ptr[3] = 0xDEADBEEF;
 	ib.length_dw = 4;
 
@@ -374,7 +374,7 @@ int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 		return r;
 	}
 	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 5f6db4629aaa..9acb1c3c005b 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -879,6 +879,9 @@ void rs600_bandwidth_update(struct radeon_device *rdev)
 	u32 d1mode_priority_a_cnt, d2mode_priority_a_cnt;
 	/* FIXME: implement full support */
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled)
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3462b64369bf..0a2d36e81108 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -579,6 +579,9 @@ void rs690_bandwidth_update(struct radeon_device *rdev)
 	u32 d1mode_priority_a_cnt, d1mode_priority_b_cnt;
 	u32 d2mode_priority_a_cnt, d2mode_priority_b_cnt;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled)
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 8a477bf1fdb3..c55d653aaf5f 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -1277,6 +1277,9 @@ void rv515_bandwidth_update(struct radeon_device *rdev)
 	struct drm_display_mode *mode0 = NULL;
 	struct drm_display_mode *mode1 = NULL;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index eeea5b6a1775..7d5083dc4acb 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2384,6 +2384,9 @@ void dce6_bandwidth_update(struct radeon_device *rdev)
 	u32 num_heads = 0, lb_size;
 	int i;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	for (i = 0; i < rdev->num_crtc; i++) {