Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

50 files changed, 508 insertions, 290 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 23120c00a88..90e28081712 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -22,6 +22,7 @@ menuconfig DRM
 config DRM_USB
 	tristate
 	depends on DRM
+	depends on USB_ARCH_HAS_HCD
 	select USB
 
 config DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c
index 66d4a28ad5a..0303935d10e 100644
--- a/drivers/gpu/drm/drm_edid_load.c
+++ b/drivers/gpu/drm/drm_edid_load.c
@@ -119,7 +119,7 @@ static int edid_load(struct drm_connector *connector, char *name,
 {
 	const struct firmware *fw;
 	struct platform_device *pdev;
-	u8 *fwdata = NULL, *edid;
+	u8 *fwdata = NULL, *edid, *new_edid;
 	int fwsize, expected;
 	int builtin = 0, err = 0;
 	int i, valid_extensions = 0;
@@ -195,12 +195,14 @@ static int edid_load(struct drm_connector *connector, char *name,
 		    "\"%s\" for connector \"%s\"\n", valid_extensions,
 		    edid[0x7e], name, connector_name);
 		edid[0x7e] = valid_extensions;
-		edid = krealloc(edid, (valid_extensions + 1) * EDID_LENGTH,
+		new_edid = krealloc(edid, (valid_extensions + 1) * EDID_LENGTH,
 		    GFP_KERNEL);
-		if (edid == NULL) {
+		if (new_edid == NULL) {
 			err = -ENOMEM;
+			kfree(edid);
 			goto relfw_out;
 		}
+		edid = new_edid;
 	}
 
 	connector->display_info.raw_edid = edid;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ed22612bc84..a24ffbe97c0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -346,11 +346,40 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */
 	INTEL_VGA_DEVICE(0x0402, &intel_haswell_d_info), /* GT1 desktop */
 	INTEL_VGA_DEVICE(0x0412, &intel_haswell_d_info), /* GT2 desktop */
+	INTEL_VGA_DEVICE(0x0422, &intel_haswell_d_info), /* GT2 desktop */
 	INTEL_VGA_DEVICE(0x040a, &intel_haswell_d_info), /* GT1 server */
 	INTEL_VGA_DEVICE(0x041a, &intel_haswell_d_info), /* GT2 server */
+	INTEL_VGA_DEVICE(0x042a, &intel_haswell_d_info), /* GT2 server */
 	INTEL_VGA_DEVICE(0x0406, &intel_haswell_m_info), /* GT1 mobile */
 	INTEL_VGA_DEVICE(0x0416, &intel_haswell_m_info), /* GT2 mobile */
-	INTEL_VGA_DEVICE(0x0c16, &intel_haswell_d_info), /* SDV */
+	INTEL_VGA_DEVICE(0x0426, &intel_haswell_m_info), /* GT2 mobile */
+	INTEL_VGA_DEVICE(0x0C02, &intel_haswell_d_info), /* SDV GT1 desktop */
+	INTEL_VGA_DEVICE(0x0C12, &intel_haswell_d_info), /* SDV GT2 desktop */
+	INTEL_VGA_DEVICE(0x0C22, &intel_haswell_d_info), /* SDV GT2 desktop */
+	INTEL_VGA_DEVICE(0x0C0A, &intel_haswell_d_info), /* SDV GT1 server */
+	INTEL_VGA_DEVICE(0x0C1A, &intel_haswell_d_info), /* SDV GT2 server */
+	INTEL_VGA_DEVICE(0x0C2A, &intel_haswell_d_info), /* SDV GT2 server */
+	INTEL_VGA_DEVICE(0x0C06, &intel_haswell_m_info), /* SDV GT1 mobile */
+	INTEL_VGA_DEVICE(0x0C16, &intel_haswell_m_info), /* SDV GT2 mobile */
+	INTEL_VGA_DEVICE(0x0C26, &intel_haswell_m_info), /* SDV GT2 mobile */
+	INTEL_VGA_DEVICE(0x0A02, &intel_haswell_d_info), /* ULT GT1 desktop */
+	INTEL_VGA_DEVICE(0x0A12, &intel_haswell_d_info), /* ULT GT2 desktop */
+	INTEL_VGA_DEVICE(0x0A22, &intel_haswell_d_info), /* ULT GT2 desktop */
+	INTEL_VGA_DEVICE(0x0A0A, &intel_haswell_d_info), /* ULT GT1 server */
+	INTEL_VGA_DEVICE(0x0A1A, &intel_haswell_d_info), /* ULT GT2 server */
+	INTEL_VGA_DEVICE(0x0A2A, &intel_haswell_d_info), /* ULT GT2 server */
+	INTEL_VGA_DEVICE(0x0A06, &intel_haswell_m_info), /* ULT GT1 mobile */
+	INTEL_VGA_DEVICE(0x0A16, &intel_haswell_m_info), /* ULT GT2 mobile */
+	INTEL_VGA_DEVICE(0x0A26, &intel_haswell_m_info), /* ULT GT2 mobile */
+	INTEL_VGA_DEVICE(0x0D12, &intel_haswell_d_info), /* CRW GT1 desktop */
+	INTEL_VGA_DEVICE(0x0D22, &intel_haswell_d_info), /* CRW GT2 desktop */
+	INTEL_VGA_DEVICE(0x0D32, &intel_haswell_d_info), /* CRW GT2 desktop */
+	INTEL_VGA_DEVICE(0x0D1A, &intel_haswell_d_info), /* CRW GT1 server */
+	INTEL_VGA_DEVICE(0x0D2A, &intel_haswell_d_info), /* CRW GT2 server */
+	INTEL_VGA_DEVICE(0x0D3A, &intel_haswell_d_info), /* CRW GT2 server */
+	INTEL_VGA_DEVICE(0x0D16, &intel_haswell_m_info), /* CRW GT1 mobile */
+	INTEL_VGA_DEVICE(0x0D26, &intel_haswell_m_info), /* CRW GT2 mobile */
+	INTEL_VGA_DEVICE(0x0D36, &intel_haswell_m_info), /* CRW GT2 mobile */
 	INTEL_VGA_DEVICE(0x0f30, &intel_valleyview_m_info),
 	INTEL_VGA_DEVICE(0x0157, &intel_valleyview_m_info),
 	INTEL_VGA_DEVICE(0x0155, &intel_valleyview_d_info),
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index da8b01fb1bf..a9d58d72bb4 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -451,7 +451,6 @@ int i915_switch_context(struct intel_ring_buffer *ring,
 	struct drm_i915_file_private *file_priv = NULL;
 	struct i915_hw_context *to;
 	struct drm_i915_gem_object *from_obj = ring->last_context_obj;
-	int ret;
 
 	if (dev_priv->hw_contexts_disabled)
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 5af631e788c..ff2819ea081 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -291,6 +291,16 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	target_i915_obj = to_intel_bo(target_obj);
 	target_offset = target_i915_obj->gtt_offset;
 
+	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
+	 * pipe_control writes because the gpu doesn't properly redirect them
+	 * through the ppgtt for non_secure batchbuffers. */
+	if (unlikely(IS_GEN6(dev) &&
+	    reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
+	    !target_i915_obj->has_global_gtt_mapping)) {
+		i915_gem_gtt_bind_object(target_i915_obj,
+					 target_i915_obj->cache_level);
+	}
+
 	/* The target buffer should have appeared before us in the
 	 * exec_object list, so it should have a GTT space bound by now.
 	 */
@@ -399,16 +409,6 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		io_mapping_unmap_atomic(reloc_page);
 	}
 
-	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
-	 * pipe_control writes because the gpu doesn't properly redirect them
-	 * through the ppgtt for non_secure batchbuffers. */
-	if (unlikely(IS_GEN6(dev) &&
-	    reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
-	    !target_i915_obj->has_global_gtt_mapping)) {
-		i915_gem_gtt_bind_object(target_i915_obj,
-					 target_i915_obj->cache_level);
-	}
-
 	/* and update the user's relocation entry */
 	reloc->presumed_offset = target_offset;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9fd25a43553..ee9b68f6bc3 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -361,7 +361,8 @@ int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->mm.gtt->needs_dmar)
+	/* don't map imported dma buf objects */
+	if (dev_priv->mm.gtt->needs_dmar && !obj->sg_table)
 		return intel_gtt_map_memory(obj->pages,
 					    obj->base.size >> PAGE_SHIFT,
 					    &obj->sg_list,
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 2f5388af8df..7631807a278 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -32,6 +32,7 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
+#ifdef CONFIG_PM
 static u32 calc_residency(struct drm_device *dev, const u32 reg)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -224,3 +225,14 @@ void i915_teardown_sysfs(struct drm_device *dev)
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
 }
+#else
+void i915_setup_sysfs(struct drm_device *dev)
+{
+	return;
+}
+
+void i915_teardown_sysfs(struct drm_device *dev)
+{
+	return;
+}
+#endif /* CONFIG_PM */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f6159765f1e..a69a3d0d3ac 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -869,6 +869,7 @@ intel_vlv_find_best_pll(const intel_limit_t *limit, struct drm_crtc *crtc,
 	unsigned long bestppm, ppm, absppm;
 	int dotclk, flag;
 
+	flag = 0;
 	dotclk = target * 1000;
 	bestppm = 1000000;
 	ppm = absppm = 0;
@@ -3753,17 +3754,6 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			continue;
 		}
 
-		if (intel_encoder->type == INTEL_OUTPUT_EDP) {
-			/* Use VBT settings if we have an eDP panel */
-			unsigned int edp_bpc = dev_priv->edp.bpp / 3;
-
-			if (edp_bpc < display_bpc) {
-				DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
-				display_bpc = edp_bpc;
-			}
-			continue;
-		}
-
 		/* Not one of the known troublemakers, check the EDID */
 		list_for_each_entry(connector, &dev->mode_config.connector_list,
 				    head) {
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 0a56b9ab0f5..a6c426afaa7 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1174,10 +1174,14 @@ static void ironlake_edp_panel_off(struct intel_dp *intel_dp)
 	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
 
 	pp = ironlake_get_pp_control(dev_priv);
-	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	/* We need to switch off panel power _and_ force vdd, for otherwise some
+	 * panels get very unhappy and cease to work. */
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
 
+	intel_dp->want_panel_vdd = false;
+
 	ironlake_wait_panel_off(intel_dp);
 }
 
@@ -1287,11 +1291,9 @@ static void intel_dp_prepare(struct drm_encoder *encoder)
 	 * ensure that we have vdd while we switch off the panel. */
 	ironlake_edp_panel_vdd_on(intel_dp);
 	ironlake_edp_backlight_off(intel_dp);
-	ironlake_edp_panel_off(intel_dp);
-
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+	ironlake_edp_panel_off(intel_dp);
 	intel_dp_link_down(intel_dp);
-	ironlake_edp_panel_vdd_off(intel_dp, false);
 }
 
 static void intel_dp_commit(struct drm_encoder *encoder)
@@ -1326,11 +1328,9 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 		/* Switching the panel off requires vdd. */
 		ironlake_edp_panel_vdd_on(intel_dp);
 		ironlake_edp_backlight_off(intel_dp);
-		ironlake_edp_panel_off(intel_dp);
-
 		intel_dp_sink_dpms(intel_dp, mode);
+		ironlake_edp_panel_off(intel_dp);
 		intel_dp_link_down(intel_dp);
-		ironlake_edp_panel_vdd_off(intel_dp, false);
 
 		if (is_cpu_edp(intel_dp))
 			ironlake_edp_pll_off(encoder);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 84353559441..132ab511b90 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -46,15 +46,16 @@
 })
 
 #define wait_for_atomic_us(COND, US) ({ \
-	int i, ret__ = -ETIMEDOUT;	\
-	for (i = 0; i < (US); i++) {	\
-		if ((COND)) {		\
-			ret__ = 0;	\
-			break;		\
-		}			\
-		udelay(1);		\
-	}				\
-	ret__;				\
+	unsigned long timeout__ = jiffies + usecs_to_jiffies(US);	\
+	int ret__ = 0;							\
+	while (!(COND)) {						\
+		if (time_after(jiffies, timeout__)) {			\
+			ret__ = -ETIMEDOUT;				\
+			break;						\
+		}							\
+		cpu_relax();						\
+	}								\
+	ret__;								\
 })
 
 #define wait_for(COND, MS) _wait_for(COND, MS, 1)
@@ -380,7 +381,6 @@ extern void intel_pch_panel_fitting(struct drm_device *dev,
 				    const struct drm_display_mode *mode,
 				    struct drm_display_mode *adjusted_mode);
 extern u32 intel_panel_get_max_backlight(struct drm_device *dev);
-extern u32 intel_panel_get_backlight(struct drm_device *dev);
 extern void intel_panel_set_backlight(struct drm_device *dev, u32 level);
 extern int intel_panel_setup_backlight(struct drm_device *dev);
 extern void intel_panel_enable_backlight(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 1991a4408cf..b9755f6378d 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -486,9 +486,6 @@ int intel_setup_gmbus(struct drm_device *dev)
 		bus->dev_priv = dev_priv;
 
 		bus->adapter.algo = &gmbus_algorithm;
-		ret = i2c_add_adapter(&bus->adapter);
-		if (ret)
-			goto err;
 
 		/* By default use a conservative clock rate */
 		bus->reg0 = port | GMBUS_RATE_100KHZ;
@@ -498,6 +495,10 @@ int intel_setup_gmbus(struct drm_device *dev)
 			bus->force_bit = true;
 
 		intel_gpio_setup(bus, port);
+
+		ret = i2c_add_adapter(&bus->adapter);
+		if (ret)
+			goto err;
 	}
 
 	intel_i2c_reset(dev_priv->dev);
@@ -540,9 +541,6 @@ void intel_teardown_gmbus(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	if (dev_priv->gmbus == NULL)
-		return;
-
 	for (i = 0; i < GMBUS_NUM_PORTS; i++) {
 		struct intel_gmbus *bus = &dev_priv->gmbus[i];
 		i2c_del_adapter(&bus->adapter);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 10c7d39034e..3df4f5fa892 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -213,7 +213,7 @@ static u32 intel_panel_compute_brightness(struct drm_device *dev, u32 val)
 	return val;
 }
 
-u32 intel_panel_get_backlight(struct drm_device *dev)
+static u32 intel_panel_get_backlight(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val;
@@ -311,9 +311,6 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 	if (dev_priv->backlight_level == 0)
 		dev_priv->backlight_level = intel_panel_get_max_backlight(dev);
 
-	dev_priv->backlight_enabled = true;
-	intel_panel_actually_set_backlight(dev, dev_priv->backlight_level);
-
 	if (INTEL_INFO(dev)->gen >= 4) {
 		uint32_t reg, tmp;
 
@@ -326,7 +323,7 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 		 * we don't track the backlight dpms state, hence check whether
 		 * we have to do anything first. */
 		if (tmp & BLM_PWM_ENABLE)
-			return;
+			goto set_level;
 
 		if (dev_priv->num_pipe == 3)
 			tmp &= ~BLM_PIPE_SELECT_IVB;
@@ -347,6 +344,14 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 			I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
 		}
 	}
+
+set_level:
+	/* Call below after setting BLC_PWM_CPU_CTL2 and BLC_PWM_PCH_CTL1.
+	 * BLC_PWM_CPU_CTL may be cleared to zero automatically when these
+	 * registers are set.
+	 */
+	dev_priv->backlight_enabled = true;
+	intel_panel_actually_set_backlight(dev, dev_priv->backlight_level);
 }
 
 static void intel_panel_init_backlight(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 94aabcaa3a6..58c07cdafb7 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3963,6 +3963,7 @@ static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Force wake wait timed out\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE, 1);
+	POSTING_READ(FORCEWAKE);
 
 	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1), 500))
 		DRM_ERROR("Force wake wait timed out\n");
@@ -3983,6 +3984,7 @@ static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Force wake wait timed out\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(1));
+	POSTING_READ(FORCEWAKE_MT);
 
 	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1), 500))
 		DRM_ERROR("Force wake wait timed out\n");
@@ -4018,14 +4020,14 @@ void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
 static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	/* The below doubles as a POSTING_READ */
+	POSTING_READ(FORCEWAKE);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
 static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(1));
-	/* The below doubles as a POSTING_READ */
+	POSTING_READ(FORCEWAKE_MT);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index bf0195a96d5..e2a73b38abe 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -227,31 +227,36 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 	 * number of bits based on the write domains has little performance
 	 * impact.
 	 */
-	flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
-	flags |= PIPE_CONTROL_TLB_INVALIDATE;
-	flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
-	flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
-	/*
-	 * Ensure that any following seqno writes only happen when the render
-	 * cache is indeed flushed (but only if the caller actually wants that).
-	 */
-	if (flush_domains)
+	if (flush_domains) {
+		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+		/*
+		 * Ensure that any following seqno writes only happen
+		 * when the render cache is indeed flushed.
+		 */
 		flags |= PIPE_CONTROL_CS_STALL;
+	}
+	if (invalidate_domains) {
+		flags |= PIPE_CONTROL_TLB_INVALIDATE;
+		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		/*
+		 * TLB invalidate requires a post-sync write.
+		 */
+		flags |= PIPE_CONTROL_QW_WRITE;
+	}
 
-	ret = intel_ring_begin(ring, 6);
+	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
+	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
 	intel_ring_emit(ring, flags);
 	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
-	intel_ring_emit(ring, 0); /* lower dword */
-	intel_ring_emit(ring, 0); /* uppwer dword */
-	intel_ring_emit(ring, MI_NOOP);
+	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
 	return 0;
@@ -289,8 +294,6 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	I915_WRITE_HEAD(ring, 0);
 	ring->write_tail(ring, 0);
 
-	/* Initialize the ring. */
-	I915_WRITE_START(ring, obj->gtt_offset);
 	head = I915_READ_HEAD(ring) & HEAD_ADDR;
 
 	/* G45 ring initialization fails to reset head to zero */
@@ -316,6 +319,11 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		}
 	}
 
+	/* Initialize the ring. This must happen _after_ we've cleared the ring
+	 * registers with the above sequence (the readback of the HEAD registers
+	 * also enforces ordering), otherwise the hw might lose the new ring
+	 * register values. */
+	I915_WRITE_START(ring, obj->gtt_offset);
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 26a6a4d0d07..d172e987313 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -444,13 +444,16 @@ static bool intel_sdvo_write_cmd(struct intel_sdvo *intel_sdvo, u8 cmd,
 	struct i2c_msg *msgs;
 	int i, ret = true;
 
+        /* Would be simpler to allocate both in one go ? */        
 	buf = (u8 *)kzalloc(args_len * 2 + 2, GFP_KERNEL);
 	if (!buf)
 		return false;
 
 	msgs = kcalloc(args_len + 3, sizeof(*msgs), GFP_KERNEL);
-	if (!msgs)
+	if (!msgs) {
+	        kfree(buf);
 		return false;
+        }
 
 	intel_sdvo_debug_write(intel_sdvo, cmd, args, args_len);
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index a4d7c500c97..b69642d5d85 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -468,10 +468,11 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 {
 	unsigned int vcomax, vcomin, pllreffreq;
 	unsigned int delta, tmpdelta;
-	unsigned int testr, testn, testm, testo;
+	int testr, testn, testm, testo;
 	unsigned int p, m, n;
-	unsigned int computed;
+	unsigned int computed, vco;
 	int tmp;
+	const unsigned int m_div_val[] = { 1, 2, 4, 8 };
 
 	m = n = p = 0;
 	vcomax = 1488000;
@@ -490,12 +491,13 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 				if (delta == 0)
 					break;
 				for (testo = 5; testo < 33; testo++) {
-					computed = pllreffreq * (testn + 1) /
+					vco = pllreffreq * (testn + 1) /
 						(testr + 1);
-					if (computed < vcomin)
+					if (vco < vcomin)
 						continue;
-					if (computed > vcomax)
+					if (vco > vcomax)
 						continue;
+					computed = vco / (m_div_val[testm] * (testo + 1));
 					if (computed > clock)
 						tmpdelta = computed - clock;
 					else
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index fc841e87b34..26ebffebe71 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -211,11 +211,6 @@ static int nouveau_dsm_power_state(enum vga_switcheroo_client_id id,
 	return nouveau_dsm_set_discrete_state(nouveau_dsm_priv.dhandle, state);
 }
 
-static int nouveau_dsm_init(void)
-{
-	return 0;
-}
-
 static int nouveau_dsm_get_client_id(struct pci_dev *pdev)
 {
 	/* easy option one - intel vendor ID means Integrated */
@@ -232,7 +227,6 @@ static int nouveau_dsm_get_client_id(struct pci_dev *pdev)
 static struct vga_switcheroo_handler nouveau_dsm_handler = {
 	.switchto = nouveau_dsm_switchto,
 	.power_state = nouveau_dsm_power_state,
-	.init = nouveau_dsm_init,
 	.get_client_id = nouveau_dsm_get_client_id,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c
index 77e564667b5..240cf962c99 100644
--- a/drivers/gpu/drm/nouveau/nouveau_i2c.c
+++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c
@@ -229,7 +229,7 @@ nouveau_i2c_init(struct drm_device *dev)
 			}
 			break;
 		case 6: /* NV50- DP AUX */
-			port->drive = entry[0];
+			port->drive = entry[0] & 0x0f;
 			port->sense = port->drive;
 			port->adapter.algo = &nouveau_dp_i2c_algo;
 			break;
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index 1cdfd6e757c..1866dbb4997 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -731,7 +731,6 @@ nouveau_card_init(struct drm_device *dev)
 			case 0xa3:
 			case 0xa5:
 			case 0xa8:
-			case 0xaf:
 				nva3_copy_create(dev);
 				break;
 			}
diff --git a/drivers/gpu/drm/nouveau/nv84_fifo.c b/drivers/gpu/drm/nouveau/nv84_fifo.c
index cc82d799fc3..c564c5e4c30 100644
--- a/drivers/gpu/drm/nouveau/nv84_fifo.c
+++ b/drivers/gpu/drm/nouveau/nv84_fifo.c
@@ -117,17 +117,22 @@ nv84_fifo_context_del(struct nouveau_channel *chan, int engine)
 	struct drm_device *dev = chan->dev;
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	unsigned long flags;
+	u32 save;
 
 	/* remove channel from playlist, will context switch if active */
 	spin_lock_irqsave(&dev_priv->context_switch_lock, flags);
 	nv_mask(dev, 0x002600 + (chan->id * 4), 0x80000000, 0x00000000);
 	nv50_fifo_playlist_update(dev);
 
+	save = nv_mask(dev, 0x002520, 0x0000003f, 0x15);
+
 	/* tell any engines on this channel to unload their contexts */
 	nv_wr32(dev, 0x0032fc, chan->ramin->vinst >> 12);
 	if (!nv_wait_ne(dev, 0x0032fc, 0xffffffff, 0xffffffff))
 		NV_INFO(dev, "PFIFO: channel %d unload timeout\n", chan->id);
 
+	nv_wr32(dev, 0x002520, save);
+
 	nv_wr32(dev, 0x002600 + (chan->id * 4), 0x00000000);
 	spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags);
 
@@ -184,10 +189,13 @@ nv84_fifo_fini(struct drm_device *dev, int engine, bool suspend)
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nv84_fifo_priv *priv = nv_engine(dev, engine);
 	int i;
+	u32 save;
 
 	/* set playlist length to zero, fifo will unload context */
 	nv_wr32(dev, 0x0032ec, 0);
 
+	save = nv_mask(dev, 0x002520, 0x0000003f, 0x15);
+
 	/* tell all connected engines to unload their contexts */
 	for (i = 0; i < priv->base.channels; i++) {
 		struct nouveau_channel *chan = dev_priv->channels.ptr[i];
@@ -199,6 +207,7 @@ nv84_fifo_fini(struct drm_device *dev, int engine, bool suspend)
 		}
 	}
 
+	nv_wr32(dev, 0x002520, save);
 	nv_wr32(dev, 0x002140, 0);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvc0_pm.c b/drivers/gpu/drm/nouveau/nvc0_pm.c
index 7c95c44e288..4e712b10ebd 100644
--- a/drivers/gpu/drm/nouveau/nvc0_pm.c
+++ b/drivers/gpu/drm/nouveau/nvc0_pm.c
@@ -557,7 +557,7 @@ prog_mem(struct drm_device *dev, struct nvc0_pm_state *info)
 	nouveau_mem_exec(&exec, info->perflvl);
 
 	if (dev_priv->chipset < 0xd0)
-		nv_wr32(dev, 0x611200, 0x00003300);
+		nv_wr32(dev, 0x611200, 0x00003330);
 	else
 		nv_wr32(dev, 0x62c000, 0x03030300);
 }
diff --git a/drivers/gpu/drm/nouveau/nvd0_display.c b/drivers/gpu/drm/nouveau/nvd0_display.c
index d0d60e1e7f9..dac525b2994 100644
--- a/drivers/gpu/drm/nouveau/nvd0_display.c
+++ b/drivers/gpu/drm/nouveau/nvd0_display.c
@@ -790,7 +790,7 @@ nvd0_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 	int ch = EVO_CURS(nv_crtc->index);
 
-	evo_piow(crtc->dev, ch, 0x0084, (y << 16) | x);
+	evo_piow(crtc->dev, ch, 0x0084, (y << 16) | (x & 0xffff));
 	evo_piow(crtc->dev, ch, 0x0080, 0x00000000);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nve0_fifo.c b/drivers/gpu/drm/nouveau/nve0_fifo.c
index 1855ecbd843..e98d144e6eb 100644
--- a/drivers/gpu/drm/nouveau/nve0_fifo.c
+++ b/drivers/gpu/drm/nouveau/nve0_fifo.c
@@ -294,6 +294,25 @@ nve0_fifo_isr_vm_fault(struct drm_device *dev, int unit)
 	printk(" on channel 0x%010llx\n", (u64)inst << 12);
 }
 
+static int
+nve0_fifo_page_flip(struct drm_device *dev, u32 chid)
+{
+	struct nve0_fifo_priv *priv = nv_engine(dev, NVOBJ_ENGINE_FIFO);
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct nouveau_channel *chan = NULL;
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	spin_lock_irqsave(&dev_priv->channels.lock, flags);
+	if (likely(chid >= 0 && chid < priv->base.channels)) {
+		chan = dev_priv->channels.ptr[chid];
+		if (likely(chan))
+			ret = nouveau_finish_page_flip(chan, NULL);
+	}
+	spin_unlock_irqrestore(&dev_priv->channels.lock, flags);
+	return ret;
+}
+
 static void
 nve0_fifo_isr_subfifo_intr(struct drm_device *dev, int unit)
 {
@@ -303,11 +322,21 @@ nve0_fifo_isr_subfifo_intr(struct drm_device *dev, int unit)
 	u32 chid = nv_rd32(dev, 0x040120 + (unit * 0x2000)) & 0x7f;
 	u32 subc = (addr & 0x00070000);
 	u32 mthd = (addr & 0x00003ffc);
+	u32 show = stat;
+
+	if (stat & 0x00200000) {
+		if (mthd == 0x0054) {
+			if (!nve0_fifo_page_flip(dev, chid))
+				show &= ~0x00200000;
+		}
+	}
 
-	NV_INFO(dev, "PSUBFIFO %d:", unit);
-	nouveau_bitfield_print(nve0_fifo_subfifo_intr, stat);
-	NV_INFO(dev, "PSUBFIFO %d: ch %d subc %d mthd 0x%04x data 0x%08x\n",
-		unit, chid, subc, mthd, data);
+	if (show) {
+		NV_INFO(dev, "PFIFO%d:", unit);
+		nouveau_bitfield_print(nve0_fifo_subfifo_intr, show);
+		NV_INFO(dev, "PFIFO%d: ch %d subc %d mthd 0x%04x data 0x%08x\n",
+			unit, chid, subc, mthd, data);
+	}
 
 	nv_wr32(dev, 0x0400c0 + (unit * 0x2000), 0x80600008);
 	nv_wr32(dev, 0x040108 + (unit * 0x2000), stat);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 9e6f76fec52..c6fcb5b86a4 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 e585a3b947e..e93b80a6d4e 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 c16554122cc..e44a62a07fe 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:
@@ -961,13 +968,15 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 
 	if (track->db_dirty) {
 		/* Check stencil buffer */
-		if (G_028800_STENCIL_ENABLE(track->db_depth_control)) {
+		if (G_028044_FORMAT(track->db_s_info) != V_028044_STENCIL_INVALID &&
+		    G_028800_STENCIL_ENABLE(track->db_depth_control)) {
 			r = evergreen_cs_track_validate_stencil(p);
 			if (r)
 				return r;
 		}
 		/* Check depth buffer */
-		if (G_028800_Z_ENABLE(track->db_depth_control)) {
+		if (G_028040_FORMAT(track->db_z_info) != V_028040_Z_INVALID &&
+		    G_028800_Z_ENABLE(track->db_depth_control)) {
 			r = evergreen_cs_track_validate_depth(p);
 			if (r)
 				return r;
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index d3bd098e4e1..79347855d9b 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -1277,6 +1277,8 @@
 #define   S_028044_FORMAT(x)                           (((x) & 0x1) << 0)
 #define   G_028044_FORMAT(x)                           (((x) >> 0) & 0x1)
 #define   C_028044_FORMAT                              0xFFFFFFFE
+#define	    V_028044_STENCIL_INVALID			0
+#define	    V_028044_STENCIL_8				1
 #define   G_028044_TILE_SPLIT(x)                       (((x) >> 8) & 0x7)
 #define DB_Z_READ_BASE					0x28048
 #define DB_STENCIL_READ_BASE				0x2804c
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 9945d86d900..853800e8582 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 637280f541a..d79c639ae73 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 ca87f7afaf2..3dab49cb1d4 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -764,8 +764,10 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 	}
 
 	/* Check depth buffer */
-	if (track->db_dirty && (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
-		G_028800_Z_ENABLE(track->db_depth_control))) {
+	if (track->db_dirty &&
+	    G_028010_FORMAT(track->db_depth_info) != V_028010_DEPTH_INVALID &&
+	    (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
+	     G_028800_Z_ENABLE(track->db_depth_control))) {
 		r = r600_cs_track_validate_db(p);
 		if (r)
 			return r;
@@ -1557,13 +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)
@@ -1581,12 +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:
@@ -1599,29 +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",
@@ -1647,20 +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;
 	}
@@ -1677,7 +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 4b116ae75fc..fd328f4c3ea 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 5431af29240..99304194a65 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 f4af2431043..18c38d14c8c 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 b1e3820df36..f9c21f9d16b 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 576f4f6919f..f75247d42ff 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 8a4c49ef0cc..b4a0db24f4d 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 711e95ad39b..8794744cdf1 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 742af8244e8..d2e243867ac 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 dcea6f01ae4..d7269f48d37 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -59,9 +59,12 @@
  *   2.15.0 - add max_pipes query
  *   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	17
+#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 b3720054614..bb3b7fe05cc 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 84d04524573..1b57b0058ad 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 1d73f16b5d9..414b4acf694 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 d5fd615897e..94b4a1c1289 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 f380d59c576..d56978949f3 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 1f1a4c803c1..1cb014b571a 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 a12fbcc8ccb..aa8ef491ef3 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 c053f819377..0139e227e3c 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 7869089e876..ef4815c27b1 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/drivers/gpu/drm/udl/Kconfig b/drivers/gpu/drm/udl/Kconfig
index 0b5e096d39a..56e0bf31d42 100644
--- a/drivers/gpu/drm/udl/Kconfig
+++ b/drivers/gpu/drm/udl/Kconfig
@@ -1,6 +1,7 @@
 config DRM_UDL
 	tristate "DisplayLink"
 	depends on DRM && EXPERIMENTAL
+	depends on USB_ARCH_HAS_HCD
 	select DRM_USB
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 7bd65bdd15a..291ecc14558 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -308,7 +308,7 @@ struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev,
 	/* need to attach */
 	attach = dma_buf_attach(dma_buf, dev->dev);
 	if (IS_ERR(attach))
-		return ERR_PTR(PTR_ERR(attach));
+		return ERR_CAST(attach);
 
 	sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
 	if (IS_ERR(sg)) {