diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 9e6f76fec52789..c6fcb5b86a450d 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -259,7 +259,7 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 		/* adjust pm to dpms changes BEFORE enabling crtcs */
 		radeon_pm_compute_clocks(rdev);
 		/* disable crtc pair power gating before programming */
-		if (ASIC_IS_DCE6(rdev))
+		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set)
 			atombios_powergate_crtc(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_ENABLE);
 		if (ASIC_IS_DCE3(rdev) && !ASIC_IS_DCE6(rdev))
@@ -279,7 +279,7 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 		atombios_enable_crtc(crtc, ATOM_DISABLE);
 		radeon_crtc->enabled = false;
 		/* power gating is per-pair */
-		if (ASIC_IS_DCE6(rdev)) {
+		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set) {
 			struct drm_crtc *other_crtc;
 			struct radeon_crtc *other_radeon_crtc;
 			list_for_each_entry(other_crtc, &rdev->ddev->mode_config.crtc_list, head) {
@@ -1531,12 +1531,12 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				 * crtc virtual pixel clock.
 				 */
 				if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) {
-					if (ASIC_IS_DCE5(rdev))
-						return ATOM_DCPLL;
+					if (rdev->clock.dp_extclk)
+						return ATOM_PPLL_INVALID;
 					else if (ASIC_IS_DCE6(rdev))
 						return ATOM_PPLL0;
-					else if (rdev->clock.dp_extclk)
-						return ATOM_PPLL_INVALID;
+					else if (ASIC_IS_DCE5(rdev))
+						return ATOM_DCPLL;
 				}
 			}
 		}
@@ -1635,18 +1635,28 @@ static bool atombios_crtc_mode_fixup(struct drm_crtc *crtc,
 static void atombios_crtc_prepare(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
 
+	radeon_crtc->in_mode_set = true;
 	/* pick pll */
 	radeon_crtc->pll_id = radeon_atom_pick_pll(crtc);
 
+	/* disable crtc pair power gating before programming */
+	if (ASIC_IS_DCE6(rdev))
+		atombios_powergate_crtc(crtc, ATOM_DISABLE);
+
 	atombios_lock_crtc(crtc, ATOM_ENABLE);
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
 
 static void atombios_crtc_commit(struct drm_crtc *crtc)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
 	atombios_lock_crtc(crtc, ATOM_DISABLE);
+	radeon_crtc->in_mode_set = false;
 }
 
 static void atombios_crtc_disable(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index e585a3b947eb7c..e93b80a6d4e969 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1229,24 +1229,8 @@ void evergreen_agp_enable(struct radeon_device *rdev)
 
 void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save)
 {
-	save->vga_control[0] = RREG32(D1VGA_CONTROL);
-	save->vga_control[1] = RREG32(D2VGA_CONTROL);
 	save->vga_render_control = RREG32(VGA_RENDER_CONTROL);
 	save->vga_hdp_control = RREG32(VGA_HDP_CONTROL);
-	save->crtc_control[0] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET);
-	save->crtc_control[1] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET);
-	if (rdev->num_crtc >= 4) {
-		save->vga_control[2] = RREG32(EVERGREEN_D3VGA_CONTROL);
-		save->vga_control[3] = RREG32(EVERGREEN_D4VGA_CONTROL);
-		save->crtc_control[2] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET);
-		save->crtc_control[3] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET);
-	}
-	if (rdev->num_crtc >= 6) {
-		save->vga_control[4] = RREG32(EVERGREEN_D5VGA_CONTROL);
-		save->vga_control[5] = RREG32(EVERGREEN_D6VGA_CONTROL);
-		save->crtc_control[4] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET);
-		save->crtc_control[5] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET);
-	}
 
 	/* Stop all video */
 	WREG32(VGA_RENDER_CONTROL, 0);
@@ -1357,47 +1341,6 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s
 	/* Unlock host access */
 	WREG32(VGA_HDP_CONTROL, save->vga_hdp_control);
 	mdelay(1);
-	/* Restore video state */
-	WREG32(D1VGA_CONTROL, save->vga_control[0]);
-	WREG32(D2VGA_CONTROL, save->vga_control[1]);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_D3VGA_CONTROL, save->vga_control[2]);
-		WREG32(EVERGREEN_D4VGA_CONTROL, save->vga_control[3]);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_D5VGA_CONTROL, save->vga_control[4]);
-		WREG32(EVERGREEN_D6VGA_CONTROL, save->vga_control[5]);
-	}
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 1);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 1);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 1);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 1);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 1);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 1);
-	}
-	WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, save->crtc_control[0]);
-	WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, save->crtc_control[1]);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, save->crtc_control[2]);
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, save->crtc_control[3]);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, save->crtc_control[4]);
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, save->crtc_control[5]);
-	}
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
-	}
 	WREG32(VGA_RENDER_CONTROL, save->vga_render_control);
 }
 
@@ -1986,10 +1929,18 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	if (rdev->flags & RADEON_IS_IGP)
 		rdev->config.evergreen.tile_config |= 1 << 4;
 	else {
-		if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-			rdev->config.evergreen.tile_config |= 1 << 4;
-		else
+		switch ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) {
+		case 0: /* four banks */
 			rdev->config.evergreen.tile_config |= 0 << 4;
+			break;
+		case 1: /* eight banks */
+			rdev->config.evergreen.tile_config |= 1 << 4;
+			break;
+		case 2: /* sixteen banks */
+		default:
+			rdev->config.evergreen.tile_config |= 2 << 4;
+			break;
+		}
 	}
 	rdev->config.evergreen.tile_config |= 0 << 8;
 	rdev->config.evergreen.tile_config |=
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index f2e5c545c973d2..e44a62a07fe396 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -788,6 +788,13 @@ static int evergreen_cs_track_validate_texture(struct radeon_cs_parser *p,
 	case V_030000_SQ_TEX_DIM_1D_ARRAY:
 	case V_030000_SQ_TEX_DIM_2D_ARRAY:
 		depth = 1;
+		break;
+	case V_030000_SQ_TEX_DIM_2D_MSAA:
+	case V_030000_SQ_TEX_DIM_2D_ARRAY_MSAA:
+		surf.nsamples = 1 << llevel;
+		llevel = 0;
+		depth = 1;
+		break;
 	case V_030000_SQ_TEX_DIM_3D:
 		break;
 	default:
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 9945d86d900153..853800e8582f97 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -574,10 +574,18 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 	if (rdev->flags & RADEON_IS_IGP)
 		rdev->config.cayman.tile_config |= 1 << 4;
 	else {
-		if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-			rdev->config.cayman.tile_config |= 1 << 4;
-		else
+		switch ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) {
+		case 0: /* four banks */
 			rdev->config.cayman.tile_config |= 0 << 4;
+			break;
+		case 1: /* eight banks */
+			rdev->config.cayman.tile_config |= 1 << 4;
+			break;
+		case 2: /* sixteen banks */
+		default:
+			rdev->config.cayman.tile_config |= 2 << 4;
+			break;
+		}
 	}
 	rdev->config.cayman.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 637280f541a384..d79c639ae739cf 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3789,3 +3789,23 @@ static void r600_pcie_gen2_enable(struct radeon_device *rdev)
 		WREG32_PCIE_P(PCIE_LC_LINK_WIDTH_CNTL, link_width_cntl);
 	}
 }
+
+/**
+ * r600_get_gpu_clock - return GPU clock counter snapshot
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Fetches a GPU clock counter snapshot (R6xx-cayman).
+ * Returns the 64 bit clock counter snapshot.
+ */
+uint64_t r600_get_gpu_clock(struct radeon_device *rdev)
+{
+	uint64_t clock;
+
+	mutex_lock(&rdev->gpu_clock_mutex);
+	WREG32(RLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+	clock = (uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_LSB) |
+	        ((uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	mutex_unlock(&rdev->gpu_clock_mutex);
+	return clock;
+}
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 1119e31e5c2f73..3dab49cb1d4a64 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -1559,13 +1559,14 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 					      u32 tiling_flags)
 {
 	struct r600_cs_track *track = p->track;
-	u32 nfaces, llevel, blevel, w0, h0, d0;
-	u32 word0, word1, l0_size, mipmap_size, word2, word3;
+	u32 dim, nfaces, llevel, blevel, w0, h0, d0;
+	u32 word0, word1, l0_size, mipmap_size, word2, word3, word4, word5;
 	u32 height_align, pitch, pitch_align, depth_align;
-	u32 array, barray, larray;
+	u32 barray, larray;
 	u64 base_align;
 	struct array_mode_checker array_check;
 	u32 format;
+	bool is_array;
 
 	/* on legacy kernel we don't perform advanced check */
 	if (p->rdev == NULL)
@@ -1583,12 +1584,28 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 			word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
 	}
 	word1 = radeon_get_ib_value(p, idx + 1);
+	word2 = radeon_get_ib_value(p, idx + 2) << 8;
+	word3 = radeon_get_ib_value(p, idx + 3) << 8;
+	word4 = radeon_get_ib_value(p, idx + 4);
+	word5 = radeon_get_ib_value(p, idx + 5);
+	dim = G_038000_DIM(word0);
 	w0 = G_038000_TEX_WIDTH(word0) + 1;
+	pitch = (G_038000_PITCH(word0) + 1) * 8;
 	h0 = G_038004_TEX_HEIGHT(word1) + 1;
 	d0 = G_038004_TEX_DEPTH(word1);
+	format = G_038004_DATA_FORMAT(word1);
+	blevel = G_038010_BASE_LEVEL(word4);
+	llevel = G_038014_LAST_LEVEL(word5);
+	/* pitch in texels */
+	array_check.array_mode = G_038000_TILE_MODE(word0);
+	array_check.group_size = track->group_size;
+	array_check.nbanks = track->nbanks;
+	array_check.npipes = track->npipes;
+	array_check.nsamples = 1;
+	array_check.blocksize = r600_fmt_get_blocksize(format);
 	nfaces = 1;
-	array = 0;
-	switch (G_038000_DIM(word0)) {
+	is_array = false;
+	switch (dim) {
 	case V_038000_SQ_TEX_DIM_1D:
 	case V_038000_SQ_TEX_DIM_2D:
 	case V_038000_SQ_TEX_DIM_3D:
@@ -1601,29 +1618,25 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		break;
 	case V_038000_SQ_TEX_DIM_1D_ARRAY:
 	case V_038000_SQ_TEX_DIM_2D_ARRAY:
-		array = 1;
+		is_array = true;
 		break;
-	case V_038000_SQ_TEX_DIM_2D_MSAA:
 	case V_038000_SQ_TEX_DIM_2D_ARRAY_MSAA:
+		is_array = true;
+		/* fall through */
+	case V_038000_SQ_TEX_DIM_2D_MSAA:
+		array_check.nsamples = 1 << llevel;
+		llevel = 0;
+		break;
 	default:
 		dev_warn(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0));
 		return -EINVAL;
 	}
-	format = G_038004_DATA_FORMAT(word1);
 	if (!r600_fmt_is_valid_texture(format, p->family)) {
 		dev_warn(p->dev, "%s:%d texture invalid format %d\n",
 			 __func__, __LINE__, format);
 		return -EINVAL;
 	}
 
-	/* pitch in texels */
-	pitch = (G_038000_PITCH(word0) + 1) * 8;
-	array_check.array_mode = G_038000_TILE_MODE(word0);
-	array_check.group_size = track->group_size;
-	array_check.nbanks = track->nbanks;
-	array_check.npipes = track->npipes;
-	array_check.nsamples = 1;
-	array_check.blocksize = r600_fmt_get_blocksize(format);
 	if (r600_get_array_mode_alignment(&array_check,
 					  &pitch_align, &height_align, &depth_align, &base_align)) {
 		dev_warn(p->dev, "%s:%d tex array mode (%d) invalid\n",
@@ -1649,20 +1662,13 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		return -EINVAL;
 	}
 
-	word2 = radeon_get_ib_value(p, idx + 2) << 8;
-	word3 = radeon_get_ib_value(p, idx + 3) << 8;
-
-	word0 = radeon_get_ib_value(p, idx + 4);
-	word1 = radeon_get_ib_value(p, idx + 5);
-	blevel = G_038010_BASE_LEVEL(word0);
-	llevel = G_038014_LAST_LEVEL(word1);
 	if (blevel > llevel) {
 		dev_warn(p->dev, "texture blevel %d > llevel %d\n",
 			 blevel, llevel);
 	}
-	if (array == 1) {
-		barray = G_038014_BASE_ARRAY(word1);
-		larray = G_038014_LAST_ARRAY(word1);
+	if (is_array) {
+		barray = G_038014_BASE_ARRAY(word5);
+		larray = G_038014_LAST_ARRAY(word5);
 
 		nfaces = larray - barray + 1;
 	}
@@ -1679,7 +1685,6 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		return -EINVAL;
 	}
 	/* using get ib will give us the offset into the mipmap bo */
-	word3 = radeon_get_ib_value(p, idx + 3) << 8;
 	if ((mipmap_size + word3) > radeon_bo_size(mipmap)) {
 		/*dev_warn(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n",
 		  w0, h0, format, blevel, nlevels, word3, mipmap_size, radeon_bo_size(texture));*/
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 4b116ae75fc2ce..fd328f4c3ea82a 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -602,6 +602,9 @@
 #define RLC_HB_WPTR                                       0x3f1c
 #define RLC_HB_WPTR_LSB_ADDR                              0x3f14
 #define RLC_HB_WPTR_MSB_ADDR                              0x3f18
+#define RLC_GPU_CLOCK_COUNT_LSB				  0x3f38
+#define RLC_GPU_CLOCK_COUNT_MSB				  0x3f3c
+#define RLC_CAPTURE_GPU_CLOCK_COUNT			  0x3f40
 #define RLC_MC_CNTL                                       0x3f44
 #define RLC_UCODE_CNTL                                    0x3f48
 #define RLC_UCODE_ADDR                                    0x3f2c
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 5431af29240836..99304194a65c80 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -300,6 +300,7 @@ struct radeon_bo_va {
 	uint64_t			soffset;
 	uint64_t			eoffset;
 	uint32_t			flags;
+	struct radeon_fence		*fence;
 	bool				valid;
 };
 
@@ -1533,6 +1534,7 @@ struct radeon_device {
 	unsigned 		debugfs_count;
 	/* virtual memory */
 	struct radeon_vm_manager	vm_manager;
+	struct mutex			gpu_clock_mutex;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -1733,11 +1735,11 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_pm_finish(rdev) (rdev)->asic->pm.finish((rdev))
 #define radeon_pm_init_profile(rdev) (rdev)->asic->pm.init_profile((rdev))
 #define radeon_pm_get_dynpm_state(rdev) (rdev)->asic->pm.get_dynpm_state((rdev))
-#define radeon_pre_page_flip(rdev, crtc) rdev->asic->pflip.pre_page_flip((rdev), (crtc))
-#define radeon_page_flip(rdev, crtc, base) rdev->asic->pflip.page_flip((rdev), (crtc), (base))
-#define radeon_post_page_flip(rdev, crtc) rdev->asic->pflip.post_page_flip((rdev), (crtc))
-#define radeon_wait_for_vblank(rdev, crtc) rdev->asic->display.wait_for_vblank((rdev), (crtc))
-#define radeon_mc_wait_for_idle(rdev) rdev->asic->mc_wait_for_idle((rdev))
+#define radeon_pre_page_flip(rdev, crtc) (rdev)->asic->pflip.pre_page_flip((rdev), (crtc))
+#define radeon_page_flip(rdev, crtc, base) (rdev)->asic->pflip.page_flip((rdev), (crtc), (base))
+#define radeon_post_page_flip(rdev, crtc) (rdev)->asic->pflip.post_page_flip((rdev), (crtc))
+#define radeon_wait_for_vblank(rdev, crtc) (rdev)->asic->display.wait_for_vblank((rdev), (crtc))
+#define radeon_mc_wait_for_idle(rdev) (rdev)->asic->mc_wait_for_idle((rdev))
 
 /* Common functions */
 /* AGP */
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index f4af243104387b..18c38d14c8cd88 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -255,13 +255,10 @@ extern int rs690_mc_wait_for_idle(struct radeon_device *rdev);
  * rv515
  */
 struct rv515_mc_save {
-	u32 d1vga_control;
-	u32 d2vga_control;
 	u32 vga_render_control;
 	u32 vga_hdp_control;
-	u32 d1crtc_control;
-	u32 d2crtc_control;
 };
+
 int rv515_init(struct radeon_device *rdev);
 void rv515_fini(struct radeon_device *rdev);
 uint32_t rv515_mc_rreg(struct radeon_device *rdev, uint32_t reg);
@@ -371,6 +368,7 @@ void r600_kms_blit_copy(struct radeon_device *rdev,
 			unsigned num_gpu_pages,
 			struct radeon_sa_bo *vb);
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
+uint64_t r600_get_gpu_clock(struct radeon_device *rdev);
 
 /*
  * rv770,rv730,rv710,rv740
@@ -389,11 +387,10 @@ void r700_cp_fini(struct radeon_device *rdev);
  * evergreen
  */
 struct evergreen_mc_save {
-	u32 vga_control[6];
 	u32 vga_render_control;
 	u32 vga_hdp_control;
-	u32 crtc_control[6];
 };
+
 void evergreen_pcie_gart_tlb_flush(struct radeon_device *rdev);
 int evergreen_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
@@ -472,5 +469,6 @@ int si_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id);
 void si_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
 void si_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm);
 int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
+uint64_t si_get_gpu_clock(struct radeon_device *rdev);
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index b1e3820df36397..f9c21f9d16bc47 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1263,6 +1263,8 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 union igp_info {
 	struct _ATOM_INTEGRATED_SYSTEM_INFO info;
 	struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7;
 };
 
 bool radeon_atombios_sideport_present(struct radeon_device *rdev)
@@ -1390,27 +1392,50 @@ static void radeon_atombios_get_igp_ss_overrides(struct radeon_device *rdev,
 	struct radeon_mode_info *mode_info = &rdev->mode_info;
 	int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo);
 	u16 data_offset, size;
-	struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 *igp_info;
+	union igp_info *igp_info;
 	u8 frev, crev;
 	u16 percentage = 0, rate = 0;
 
 	/* get any igp specific overrides */
 	if (atom_parse_data_header(mode_info->atom_context, index, &size,
 				   &frev, &crev, &data_offset)) {
-		igp_info = (struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 *)
+		igp_info = (union igp_info *)
 			(mode_info->atom_context->bios + data_offset);
-		switch (id) {
-		case ASIC_INTERNAL_SS_ON_TMDS:
-			percentage = le16_to_cpu(igp_info->usDVISSPercentage);
-			rate = le16_to_cpu(igp_info->usDVISSpreadRateIn10Hz);
+		switch (crev) {
+		case 6:
+			switch (id) {
+			case ASIC_INTERNAL_SS_ON_TMDS:
+				percentage = le16_to_cpu(igp_info->info_6.usDVISSPercentage);
+				rate = le16_to_cpu(igp_info->info_6.usDVISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_HDMI:
+				percentage = le16_to_cpu(igp_info->info_6.usHDMISSPercentage);
+				rate = le16_to_cpu(igp_info->info_6.usHDMISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_LVDS:
+				percentage = le16_to_cpu(igp_info->info_6.usLvdsSSPercentage);
+				rate = le16_to_cpu(igp_info->info_6.usLvdsSSpreadRateIn10Hz);
+				break;
+			}
 			break;
-		case ASIC_INTERNAL_SS_ON_HDMI:
-			percentage = le16_to_cpu(igp_info->usHDMISSPercentage);
-			rate = le16_to_cpu(igp_info->usHDMISSpreadRateIn10Hz);
+		case 7:
+			switch (id) {
+			case ASIC_INTERNAL_SS_ON_TMDS:
+				percentage = le16_to_cpu(igp_info->info_7.usDVISSPercentage);
+				rate = le16_to_cpu(igp_info->info_7.usDVISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_HDMI:
+				percentage = le16_to_cpu(igp_info->info_7.usHDMISSPercentage);
+				rate = le16_to_cpu(igp_info->info_7.usHDMISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_LVDS:
+				percentage = le16_to_cpu(igp_info->info_7.usLvdsSSPercentage);
+				rate = le16_to_cpu(igp_info->info_7.usLvdsSSpreadRateIn10Hz);
+				break;
+			}
 			break;
-		case ASIC_INTERNAL_SS_ON_LVDS:
-			percentage = le16_to_cpu(igp_info->usLvdsSSPercentage);
-			rate = le16_to_cpu(igp_info->usLvdsSSpreadRateIn10Hz);
+		default:
+			DRM_ERROR("Unsupported IGP table: %d %d\n", frev, crev);
 			break;
 		}
 		if (percentage)
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 576f4f6919f28d..f75247d42ffdca 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -719,6 +719,34 @@ static struct radeon_i2c_bus_rec combios_setup_i2c_bus(struct radeon_device *rde
 	return i2c;
 }
 
+static struct radeon_i2c_bus_rec radeon_combios_get_i2c_info_from_table(struct radeon_device *rdev)
+{
+	struct drm_device *dev = rdev->ddev;
+	struct radeon_i2c_bus_rec i2c;
+	u16 offset;
+	u8 id, blocks, clk, data;
+	int i;
+
+	i2c.valid = false;
+
+	offset = combios_get_table_offset(dev, COMBIOS_I2C_INFO_TABLE);
+	if (offset) {
+		blocks = RBIOS8(offset + 2);
+		for (i = 0; i < blocks; i++) {
+			id = RBIOS8(offset + 3 + (i * 5) + 0);
+			if (id == 136) {
+				clk = RBIOS8(offset + 3 + (i * 5) + 3);
+				data = RBIOS8(offset + 3 + (i * 5) + 4);
+				/* gpiopad */
+				i2c = combios_setup_i2c_bus(rdev, DDC_MONID,
+							    (1 << clk), (1 << data));
+				break;
+			}
+		}
+	}
+	return i2c;
+}
+
 void radeon_combios_i2c_init(struct radeon_device *rdev)
 {
 	struct drm_device *dev = rdev->ddev;
@@ -755,30 +783,14 @@ void radeon_combios_i2c_init(struct radeon_device *rdev)
 	} else if (rdev->family == CHIP_RS300 ||
 		   rdev->family == CHIP_RS400 ||
 		   rdev->family == CHIP_RS480) {
-		u16 offset;
-		u8 id, blocks, clk, data;
-		int i;
-
 		/* 0x68 */
 		i2c = combios_setup_i2c_bus(rdev, DDC_CRT2, 0, 0);
 		rdev->i2c_bus[3] = radeon_i2c_create(dev, &i2c, "MONID");
 
-		offset = combios_get_table_offset(dev, COMBIOS_I2C_INFO_TABLE);
-		if (offset) {
-			blocks = RBIOS8(offset + 2);
-			for (i = 0; i < blocks; i++) {
-				id = RBIOS8(offset + 3 + (i * 5) + 0);
-				if (id == 136) {
-					clk = RBIOS8(offset + 3 + (i * 5) + 3);
-					data = RBIOS8(offset + 3 + (i * 5) + 4);
-					/* gpiopad */
-					i2c = combios_setup_i2c_bus(rdev, DDC_MONID,
-								    (1 << clk), (1 << data));
-					rdev->i2c_bus[4] = radeon_i2c_create(dev, &i2c, "GPIOPAD_MASK");
-					break;
-				}
-			}
-		}
+		/* gpiopad */
+		i2c = radeon_combios_get_i2c_info_from_table(rdev);
+		if (i2c.valid)
+			rdev->i2c_bus[4] = radeon_i2c_create(dev, &i2c, "GPIOPAD_MASK");
 	} else if ((rdev->family == CHIP_R200) ||
 		   (rdev->family >= CHIP_R300)) {
 		/* 0x68 */
@@ -2321,7 +2333,10 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev)
 			connector = (tmp >> 12) & 0xf;
 
 			ddc_type = (tmp >> 8) & 0xf;
-			ddc_i2c = combios_setup_i2c_bus(rdev, ddc_type, 0, 0);
+			if (ddc_type == 5)
+				ddc_i2c = radeon_combios_get_i2c_info_from_table(rdev);
+			else
+				ddc_i2c = combios_setup_i2c_bus(rdev, ddc_type, 0, 0);
 
 			switch (connector) {
 			case CONNECTOR_PROPRIETARY_LEGACY:
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 8a4c49ef0cc4e4..b4a0db24f4ddc4 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -278,6 +278,30 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 	return 0;
 }
 
+static void radeon_bo_vm_fence_va(struct radeon_cs_parser *parser,
+				  struct radeon_fence *fence)
+{
+	struct radeon_fpriv *fpriv = parser->filp->driver_priv;
+	struct radeon_vm *vm = &fpriv->vm;
+	struct radeon_bo_list *lobj;
+
+	if (parser->chunk_ib_idx == -1) {
+		return;
+	}
+	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0) {
+		return;
+	}
+
+	list_for_each_entry(lobj, &parser->validated, tv.head) {
+		struct radeon_bo_va *bo_va;
+		struct radeon_bo *rbo = lobj->bo;
+
+		bo_va = radeon_bo_va(rbo, vm);
+		radeon_fence_unref(&bo_va->fence);
+		bo_va->fence = radeon_fence_ref(fence);
+	}
+}
+
 /**
  * cs_parser_fini() - clean parser states
  * @parser:	parser structure holding parsing context.
@@ -290,11 +314,14 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 {
 	unsigned i;
 
-	if (!error)
+	if (!error) {
+		/* fence all bo va before ttm_eu_fence_buffer_objects so bo are still reserved */
+		radeon_bo_vm_fence_va(parser, parser->ib.fence);
 		ttm_eu_fence_buffer_objects(&parser->validated,
 					    parser->ib.fence);
-	else
+	} else {
 		ttm_eu_backoff_reservation(&parser->validated);
+	}
 
 	if (parser->relocs != NULL) {
 		for (i = 0; i < parser->nrelocs; i++) {
@@ -388,7 +415,6 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 
 	if (parser->chunk_ib_idx == -1)
 		return 0;
-
 	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 711e95ad39bfd6..8794744cdf1a58 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -67,7 +67,8 @@ static void radeon_hide_cursor(struct drm_crtc *crtc)
 
 	if (ASIC_IS_DCE4(rdev)) {
 		WREG32(RADEON_MM_INDEX, EVERGREEN_CUR_CONTROL + radeon_crtc->crtc_offset);
-		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT));
+		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT) |
+		       EVERGREEN_CURSOR_URGENT_CONTROL(EVERGREEN_CURSOR_URGENT_1_2));
 	} else if (ASIC_IS_AVIVO(rdev)) {
 		WREG32(RADEON_MM_INDEX, AVIVO_D1CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, (AVIVO_D1CURSOR_MODE_24BPP << AVIVO_D1CURSOR_MODE_SHIFT));
@@ -94,7 +95,8 @@ static void radeon_show_cursor(struct drm_crtc *crtc)
 	if (ASIC_IS_DCE4(rdev)) {
 		WREG32(RADEON_MM_INDEX, EVERGREEN_CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_EN |
-		       EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT));
+		       EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT) |
+		       EVERGREEN_CURSOR_URGENT_CONTROL(EVERGREEN_CURSOR_URGENT_1_2));
 	} else if (ASIC_IS_AVIVO(rdev)) {
 		WREG32(RADEON_MM_INDEX, AVIVO_D1CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, AVIVO_D1CURSOR_EN |
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 742af8244e898e..d2e243867ac6f3 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1009,6 +1009,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	atomic_set(&rdev->ih.lock, 0);
 	mutex_init(&rdev->gem.mutex);
 	mutex_init(&rdev->pm.mutex);
+	mutex_init(&rdev->gpu_clock_mutex);
 	init_rwsem(&rdev->pm.mclk_lock);
 	init_rwsem(&rdev->exclusive_lock);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 4b736ecb0aa535..d7269f48d37cc7 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -60,9 +60,11 @@
  *   2.16.0 - fix evergreen 2D tiled surface calculation
  *   2.17.0 - add STRMOUT_BASE_UPDATE for r7xx
  *   2.18.0 - r600-eg: allow "invalid" DB formats
+ *   2.19.0 - r600-eg: MSAA textures
+ *   2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	18
+#define KMS_DRIVER_MINOR	20
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index b3720054614db5..bb3b7fe05ccdfe 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -814,7 +814,7 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 		return -EINVAL;
 	}
 
-	if (bo_va->valid)
+	if (bo_va->valid && mem)
 		return 0;
 
 	ngpu_pages = radeon_bo_ngpu_pages(bo);
@@ -859,11 +859,27 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev,
 		     struct radeon_bo *bo)
 {
 	struct radeon_bo_va *bo_va;
+	int r;
 
 	bo_va = radeon_bo_va(bo, vm);
 	if (bo_va == NULL)
 		return 0;
 
+	/* wait for va use to end */
+	while (bo_va->fence) {
+		r = radeon_fence_wait(bo_va->fence, false);
+		if (r) {
+			DRM_ERROR("error while waiting for fence: %d\n", r);
+		}
+		if (r == -EDEADLK) {
+			r = radeon_gpu_reset(rdev);
+			if (!r)
+				continue;
+		}
+		break;
+	}
+	radeon_fence_unref(&bo_va->fence);
+
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
 	radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
@@ -934,7 +950,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 }
 
 /**
- * radeon_vm_init - tear down a vm instance
+ * radeon_vm_fini - tear down a vm instance
  *
  * @rdev: radeon_device pointer
  * @vm: requested vm
@@ -952,12 +968,15 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 	radeon_vm_unbind_locked(rdev, vm);
 	mutex_unlock(&rdev->vm_manager.lock);
 
-	/* remove all bo */
+	/* remove all bo at this point non are busy any more because unbind
+	 * waited for the last vm fence to signal
+	 */
 	r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 	if (!r) {
 		bo_va = radeon_bo_va(rdev->ring_tmp_bo.bo, vm);
 		list_del_init(&bo_va->bo_list);
 		list_del_init(&bo_va->vm_list);
+		radeon_fence_unref(&bo_va->fence);
 		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		kfree(bo_va);
 	}
@@ -969,6 +988,7 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 		r = radeon_bo_reserve(bo_va->bo, false);
 		if (!r) {
 			list_del_init(&bo_va->bo_list);
+			radeon_fence_unref(&bo_va->fence);
 			radeon_bo_unreserve(bo_va->bo);
 			kfree(bo_va);
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 84d045245739eb..1b57b0058ad642 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -134,25 +134,16 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 	struct radeon_device *rdev = rbo->rdev;
 	struct radeon_fpriv *fpriv = file_priv->driver_priv;
 	struct radeon_vm *vm = &fpriv->vm;
-	struct radeon_bo_va *bo_va, *tmp;
 
 	if (rdev->family < CHIP_CAYMAN) {
 		return;
 	}
 
 	if (radeon_bo_reserve(rbo, false)) {
+		dev_err(rdev->dev, "leaking bo va because we fail to reserve bo\n");
 		return;
 	}
-	list_for_each_entry_safe(bo_va, tmp, &rbo->va, bo_list) {
-		if (bo_va->vm == vm) {
-			/* remove from this vm address space */
-			mutex_lock(&vm->mutex);
-			list_del(&bo_va->vm_list);
-			mutex_unlock(&vm->mutex);
-			list_del(&bo_va->bo_list);
-			kfree(bo_va);
-		}
-	}
+	radeon_vm_bo_rmv(rdev, vm, rbo);
 	radeon_bo_unreserve(rbo);
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 1d73f16b5d97d4..414b4acf69479a 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -29,6 +29,7 @@
 #include "drm_sarea.h"
 #include "radeon.h"
 #include "radeon_drm.h"
+#include "radeon_asic.h"
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
@@ -167,17 +168,39 @@ static void radeon_set_filp_rights(struct drm_device *dev,
 int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_radeon_info *info;
+	struct drm_radeon_info *info = data;
 	struct radeon_mode_info *minfo = &rdev->mode_info;
-	uint32_t *value_ptr;
-	uint32_t value;
+	uint32_t value, *value_ptr;
+	uint64_t value64, *value_ptr64;
 	struct drm_crtc *crtc;
 	int i, found;
 
-	info = data;
+	/* TIMESTAMP is a 64-bit value, needs special handling. */
+	if (info->request == RADEON_INFO_TIMESTAMP) {
+		if (rdev->family >= CHIP_R600) {
+			value_ptr64 = (uint64_t*)((unsigned long)info->value);
+			if (rdev->family >= CHIP_TAHITI) {
+				value64 = si_get_gpu_clock(rdev);
+			} else {
+				value64 = r600_get_gpu_clock(rdev);
+			}
+
+			if (DRM_COPY_TO_USER(value_ptr64, &value64, sizeof(value64))) {
+				DRM_ERROR("copy_to_user %s:%u\n", __func__, __LINE__);
+				return -EFAULT;
+			}
+			return 0;
+		} else {
+			DRM_DEBUG_KMS("timestamp is r6xx+ only!\n");
+			return -EINVAL;
+		}
+	}
+
 	value_ptr = (uint32_t *)((unsigned long)info->value);
-	if (DRM_COPY_FROM_USER(&value, value_ptr, sizeof(value)))
+	if (DRM_COPY_FROM_USER(&value, value_ptr, sizeof(value))) {
+		DRM_ERROR("copy_from_user %s:%u\n", __func__, __LINE__);
 		return -EFAULT;
+	}
 
 	switch (info->request) {
 	case RADEON_INFO_DEVICE_ID:
@@ -337,7 +360,7 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		return -EINVAL;
 	}
 	if (DRM_COPY_TO_USER(value_ptr, &value, sizeof(uint32_t))) {
-		DRM_ERROR("copy_to_user\n");
+		DRM_ERROR("copy_to_user %s:%u\n", __func__, __LINE__);
 		return -EFAULT;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index d5fd615897ec75..94b4a1c12893ba 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -1025,9 +1025,11 @@ static int radeon_crtc_mode_set(struct drm_crtc *crtc,
 
 static void radeon_crtc_prepare(struct drm_crtc *crtc)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_crtc *crtci;
 
+	radeon_crtc->in_mode_set = true;
 	/*
 	* The hardware wedges sometimes if you reconfigure one CRTC
 	* whilst another is running (see fdo bug #24611).
@@ -1038,6 +1040,7 @@ static void radeon_crtc_prepare(struct drm_crtc *crtc)
 
 static void radeon_crtc_commit(struct drm_crtc *crtc)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_crtc *crtci;
 
@@ -1048,6 +1051,7 @@ static void radeon_crtc_commit(struct drm_crtc *crtc)
 		if (crtci->enabled)
 			radeon_crtc_dpms(crtci, DRM_MODE_DPMS_ON);
 	}
+	radeon_crtc->in_mode_set = false;
 }
 
 static const struct drm_crtc_helper_funcs legacy_helper_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index f380d59c576342..d56978949f3492 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -275,6 +275,7 @@ struct radeon_crtc {
 	u16 lut_r[256], lut_g[256], lut_b[256];
 	bool enabled;
 	bool can_tile;
+	bool in_mode_set;
 	uint32_t crtc_offset;
 	struct drm_gem_object *cursor_bo;
 	uint64_t cursor_addr;
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 1f1a4c803c1dd2..1cb014b571ab93 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -52,11 +52,7 @@ void radeon_bo_clear_va(struct radeon_bo *bo)
 
 	list_for_each_entry_safe(bo_va, tmp, &bo->va, bo_list) {
 		/* remove from all vm address space */
-		mutex_lock(&bo_va->vm->mutex);
-		list_del(&bo_va->vm_list);
-		mutex_unlock(&bo_va->vm->mutex);
-		list_del(&bo_va->bo_list);
-		kfree(bo_va);
+		radeon_vm_bo_rmv(bo->rdev, bo_va->vm, bo);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index a12fbcc8ccb683..aa8ef491ef3c17 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -281,12 +281,8 @@ int rv515_debugfs_ga_info_init(struct radeon_device *rdev)
 
 void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save)
 {
-	save->d1vga_control = RREG32(R_000330_D1VGA_CONTROL);
-	save->d2vga_control = RREG32(R_000338_D2VGA_CONTROL);
 	save->vga_render_control = RREG32(R_000300_VGA_RENDER_CONTROL);
 	save->vga_hdp_control = RREG32(R_000328_VGA_HDP_CONTROL);
-	save->d1crtc_control = RREG32(R_006080_D1CRTC_CONTROL);
-	save->d2crtc_control = RREG32(R_006880_D2CRTC_CONTROL);
 
 	/* Stop all video */
 	WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0);
@@ -311,15 +307,6 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
 	/* Unlock host access */
 	WREG32(R_000328_VGA_HDP_CONTROL, save->vga_hdp_control);
 	mdelay(1);
-	/* Restore video state */
-	WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control);
-	WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control);
-	WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1);
-	WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 1);
-	WREG32(R_006080_D1CRTC_CONTROL, save->d1crtc_control);
-	WREG32(R_006880_D2CRTC_CONTROL, save->d2crtc_control);
-	WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0);
-	WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0);
 	WREG32(R_000300_VGA_RENDER_CONTROL, save->vga_render_control);
 }
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index c053f8193771a1..0139e227e3c724 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1639,11 +1639,19 @@ static void si_gpu_init(struct radeon_device *rdev)
 		/* XXX what about 12? */
 		rdev->config.si.tile_config |= (3 << 0);
 		break;
-	}
-	if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-		rdev->config.si.tile_config |= 1 << 4;
-	else
+	}	
+	switch ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) {
+	case 0: /* four banks */
 		rdev->config.si.tile_config |= 0 << 4;
+		break;
+	case 1: /* eight banks */
+		rdev->config.si.tile_config |= 1 << 4;
+		break;
+	case 2: /* sixteen banks */
+	default:
+		rdev->config.si.tile_config |= 2 << 4;
+		break;
+	}
 	rdev->config.si.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
 	rdev->config.si.tile_config |=
@@ -3960,3 +3968,22 @@ void si_fini(struct radeon_device *rdev)
 	rdev->bios = NULL;
 }
 
+/**
+ * si_get_gpu_clock - return GPU clock counter snapshot
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Fetches a GPU clock counter snapshot (SI).
+ * Returns the 64 bit clock counter snapshot.
+ */
+uint64_t si_get_gpu_clock(struct radeon_device *rdev)
+{
+	uint64_t clock;
+
+	mutex_lock(&rdev->gpu_clock_mutex);
+	WREG32(RLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+	clock = (uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_LSB) |
+	        ((uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	mutex_unlock(&rdev->gpu_clock_mutex);
+	return clock;
+}
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 7869089e876195..ef4815c27b1c67 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -698,6 +698,9 @@
 #define RLC_UCODE_ADDR                                    0xC32C
 #define RLC_UCODE_DATA                                    0xC330
 
+#define RLC_GPU_CLOCK_COUNT_LSB                           0xC338
+#define RLC_GPU_CLOCK_COUNT_MSB                           0xC33C
+#define RLC_CAPTURE_GPU_CLOCK_COUNT                       0xC340
 #define RLC_MC_CNTL                                       0xC344
 #define RLC_UCODE_CNTL                                    0xC348
 
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 7ff5c99b163893..c78bb997e2c608 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -213,9 +213,12 @@
 	{0x1002, 0x6800, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6801, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6802, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6806, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6810, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6816, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6817, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6818, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6819, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6820, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h
index 58056865b8e960..dc3a8cd7db8a07 100644
--- a/include/drm/radeon_drm.h
+++ b/include/drm/radeon_drm.h
@@ -964,6 +964,8 @@ struct drm_radeon_cs {
 #define RADEON_INFO_IB_VM_MAX_SIZE	0x0f
 /* max pipes - needed for compute shaders */
 #define RADEON_INFO_MAX_PIPES		0x10
+/* timestamp for GL_ARB_timer_query (OpenGL), returns the current GPU clock */
+#define RADEON_INFO_TIMESTAMP		0x11
 
 struct drm_radeon_info {
 	uint32_t		request;