Merge tag 'drm-intel-next-2014-05-06' of git://anongit.freedesktop.org/drm-intel into drm-next

- ring init improvements (Chris)
- vebox2 support (Zhao Yakui)
- more prep work for runtime pm on Baytrail (Imre)
- eDram support for BDW (Ben)
- prep work for userptr support (Chris)
- first parts of the encoder->mode_set callback removal (Daniel)
- 64b reloc fixes (Ben)
- first part of atomic plane updates (Ville)

* tag 'drm-intel-next-2014-05-06' of git://anongit.freedesktop.org/drm-intel: (75 commits)
  drm/i915: Remove useless checks from primary enable/disable
  drm/i915: Merge LP1+ watermarks in safer way
  drm/i915: Make sure computed watermarks never overflow the registers
  drm/i915: Add pipe update trace points
  drm/i915: Perform primary enable/disable atomically with sprite updates
  drm/i915: Make sprite updates atomic
  drm/i915: Support 64b relocations
  drm/i915: Support 64b execbuf
  drm/i915/sdvo: Remove ->mode_set callback
  drm/i915/crt: Remove ->mode_set callback
  drm/i915/tv: Remove ->mode_set callback
  drm/i915/tv: Rip out pipe-disabling nonsense from ->mode_set
  drm/i915/tv: De-magic device check
  drm/i915/tv: extract set_color_conversion
  drm/i915/tv: extract set_tv_mode_timings
  drm/i915/dvo: Remove ->mode_set callback
  drm/i915: Make encoder->mode_set callbacks optional
  drm/i915: Make primary_enabled match the actual hardware state
  drm/i915: Move ring_begin to signal()
  drm/i915: Virtualize the ringbuffer signal func
  ...

26 files changed, 1472 insertions, 778 deletions

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 9bac0979a294..69d34e47d3bc 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -28,7 +28,7 @@
 #include "i915_drv.h"
 
 /**
- * DOC: i915 batch buffer command parser
+ * DOC: batch buffer command parser
  *
  * Motivation:
  * Certain OpenGL features (e.g. transform feedback, performance monitoring)
@@ -919,7 +919,7 @@ int i915_parse_cmds(struct intel_ring_buffer *ring,
 			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
 					 *cmd,
 					 length,
-					 (unsigned long)(batch_end - cmd));
+					 batch_end - cmd);
 			ret = -EINVAL;
 			break;
 		}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 1e83ae45041c..18b3565f431a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1239,9 +1239,13 @@ static int vlv_drpc_info(struct seq_file *m)
 	u32 rpmodectl1, rcctl1;
 	unsigned fw_rendercount = 0, fw_mediacount = 0;
 
+	intel_runtime_pm_get(dev_priv);
+
 	rpmodectl1 = I915_READ(GEN6_RP_CONTROL);
 	rcctl1 = I915_READ(GEN6_RC_CONTROL);
 
+	intel_runtime_pm_put(dev_priv);
+
 	seq_printf(m, "Video Turbo Mode: %s\n",
 		   yesno(rpmodectl1 & GEN6_RP_MEDIA_TURBO));
 	seq_printf(m, "Turbo enabled: %s\n",
@@ -1261,6 +1265,11 @@ static int vlv_drpc_info(struct seq_file *m)
 			(I915_READ(VLV_GTLC_PW_STATUS) &
 				VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down");
 
+	seq_printf(m, "Render RC6 residency since boot: %u\n",
+		   I915_READ(VLV_GT_RENDER_RC6));
+	seq_printf(m, "Media RC6 residency since boot: %u\n",
+		   I915_READ(VLV_GT_MEDIA_RC6));
+
 	spin_lock_irq(&dev_priv->uncore.lock);
 	fw_rendercount = dev_priv->uncore.fw_rendercount;
 	fw_mediacount = dev_priv->uncore.fw_mediacount;
@@ -1689,6 +1698,9 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	}
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
+		if (ctx->obj == NULL)
+			continue;
+
 		seq_puts(m, "HW context ");
 		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
@@ -1898,53 +1910,6 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int i915_dpio_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
-
-	if (!IS_VALLEYVIEW(dev)) {
-		seq_puts(m, "unsupported\n");
-		return 0;
-	}
-
-	ret = mutex_lock_interruptible(&dev_priv->dpio_lock);
-	if (ret)
-		return ret;
-
-	seq_printf(m, "DPIO_CTL: 0x%08x\n", I915_READ(DPIO_CTL));
-
-	seq_printf(m, "DPIO PLL DW3 CH0 : 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(0)));
-	seq_printf(m, "DPIO PLL DW3 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(1)));
-
-	seq_printf(m, "DPIO PLL DW5 CH0: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(0)));
-	seq_printf(m, "DPIO PLL DW5 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(1)));
-
-	seq_printf(m, "DPIO PLL DW7 CH0: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(0)));
-	seq_printf(m, "DPIO PLL DW7 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(1)));
-
-	seq_printf(m, "DPIO PLL DW10 CH0: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(0)));
-	seq_printf(m, "DPIO PLL DW10 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(1)));
-
-	seq_printf(m, "DPIO_FASTCLK_DISABLE: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_CMN_DW0));
-
-	mutex_unlock(&dev_priv->dpio_lock);
-
-	return 0;
-}
-
 static int i915_llc(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -3299,9 +3264,15 @@ static int
 i915_wedged_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	intel_runtime_pm_get(dev_priv);
 
 	i915_handle_error(dev, val,
 			  "Manually setting wedged to %llu", val);
+
+	intel_runtime_pm_put(dev_priv);
+
 	return 0;
 }
 
@@ -3803,7 +3774,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0},
 	{"i915_swizzle_info", i915_swizzle_info, 0},
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
-	{"i915_dpio", i915_dpio_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
 	{"i915_sink_crc_eDP1", i915_sink_crc, 0},
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 58f2c467d68e..d02c8de4bd6c 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1340,7 +1340,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	ret = i915_gem_init(dev);
 	if (ret)
-		goto cleanup_power;
+		goto cleanup_irq;
 
 	INIT_WORK(&dev_priv->console_resume_work, intel_console_resume);
 
@@ -1349,10 +1349,8 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	/* Always safe in the mode setting case. */
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
 	dev->vblank_disable_allowed = true;
-	if (INTEL_INFO(dev)->num_pipes == 0) {
-		intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
+	if (INTEL_INFO(dev)->num_pipes == 0)
 		return 0;
-	}
 
 	ret = intel_fbdev_init(dev);
 	if (ret)
@@ -1387,8 +1385,7 @@ cleanup_gem:
 	mutex_unlock(&dev->struct_mutex);
 	WARN_ON(dev_priv->mm.aliasing_ppgtt);
 	drm_mm_takedown(&dev_priv->gtt.base.mm);
-cleanup_power:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
+cleanup_irq:
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
 	i915_gem_cleanup_stolen(dev);
@@ -1573,6 +1570,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	spin_lock_init(&dev_priv->backlight_lock);
 	spin_lock_init(&dev_priv->uncore.lock);
 	spin_lock_init(&dev_priv->mm.object_stat_lock);
+	dev_priv->ring_index = 0;
 	mutex_init(&dev_priv->dpio_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
@@ -1930,6 +1928,8 @@ void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
+	if (file_priv && file_priv->bsd_ring)
+		file_priv->bsd_ring = NULL;
 	kfree(file_priv);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 254b3236200b..208e185c16a9 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -279,6 +279,26 @@ static const struct intel_device_info intel_broadwell_m_info = {
 	GEN_DEFAULT_PIPEOFFSETS,
 };
 
+static const struct intel_device_info intel_broadwell_gt3d_info = {
+	.gen = 8, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+};
+
+static const struct intel_device_info intel_broadwell_gt3m_info = {
+	.gen = 8, .is_mobile = 1, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+};
+
 /*
  * Make sure any device matches here are from most specific to most
  * general.  For example, since the Quanta match is based on the subsystem
@@ -311,8 +331,10 @@ static const struct intel_device_info intel_broadwell_m_info = {
 	INTEL_HSW_M_IDS(&intel_haswell_m_info), \
 	INTEL_VLV_M_IDS(&intel_valleyview_m_info),	\
 	INTEL_VLV_D_IDS(&intel_valleyview_d_info),	\
-	INTEL_BDW_M_IDS(&intel_broadwell_m_info),	\
-	INTEL_BDW_D_IDS(&intel_broadwell_d_info)
+	INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info),	\
+	INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info),	\
+	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),	\
+	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info)
 
 static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_PCI_IDS,
@@ -551,7 +573,6 @@ static int i915_drm_thaw_early(struct drm_device *dev)
 static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int error = 0;
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET) &&
 	    restore_gtt_mappings) {
@@ -569,8 +590,10 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		drm_mode_config_reset(dev);
 
 		mutex_lock(&dev->struct_mutex);
-
-		error = i915_gem_init_hw(dev);
+		if (i915_gem_init_hw(dev)) {
+			DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
+			atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
+		}
 		mutex_unlock(&dev->struct_mutex);
 
 		/* We need working interrupts for modeset enabling ... */
@@ -613,7 +636,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
 	intel_runtime_pm_put(dev_priv);
-	return error;
+	return 0;
 }
 
 static int i915_drm_thaw(struct drm_device *dev)
@@ -758,11 +781,8 @@ int i915_reset(struct drm_device *dev)
 		 * reset and the re-install of drm irq. Skip for ironlake per
 		 * previous concerns that it doesn't respond well to some forms
 		 * of re-init after reset. */
-		if (INTEL_INFO(dev)->gen > 5) {
-			mutex_lock(&dev->struct_mutex);
-			intel_enable_gt_powersave(dev);
-			mutex_unlock(&dev->struct_mutex);
-		}
+		if (INTEL_INFO(dev)->gen > 5)
+			intel_reset_gt_powersave(dev);
 
 		intel_hpd_init(dev);
 	} else {
@@ -896,13 +916,6 @@ static int i915_pm_poweroff(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
-static void snb_runtime_suspend(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-
-	intel_runtime_pm_disable_interrupts(dev);
-}
-
 static void hsw_runtime_suspend(struct drm_i915_private *dev_priv)
 {
 	hsw_enable_pc8(dev_priv);
@@ -912,12 +925,7 @@ static void snb_runtime_resume(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
 
-	intel_runtime_pm_restore_interrupts(dev);
 	intel_init_pch_refclk(dev);
-	i915_gem_init_swizzling(dev);
-	mutex_lock(&dev_priv->rps.hw_lock);
-	gen6_update_ring_freq(dev);
-	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 static void hsw_runtime_resume(struct drm_i915_private *dev_priv)
@@ -925,19 +933,67 @@ static void hsw_runtime_resume(struct drm_i915_private *dev_priv)
 	hsw_disable_pc8(dev_priv);
 }
 
+int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on)
+{
+	u32 val;
+	int err;
+
+	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
+	WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on);
+
+#define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT)
+	/* Wait for a previous force-off to settle */
+	if (force_on) {
+		err = wait_for(!COND, 20);
+		if (err) {
+			DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n",
+				  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
+			return err;
+		}
+	}
+
+	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
+	val &= ~VLV_GFX_CLK_FORCE_ON_BIT;
+	if (force_on)
+		val |= VLV_GFX_CLK_FORCE_ON_BIT;
+	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, val);
+
+	if (!force_on)
+		return 0;
+
+	err = wait_for(COND, 20);
+	if (err)
+		DRM_ERROR("timeout waiting for GFX clock force-on (%08x)\n",
+			  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
+
+	return err;
+#undef COND
+}
+
 static int intel_runtime_suspend(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev))))
+		return -ENODEV;
+
 	WARN_ON(!HAS_RUNTIME_PM(dev));
 	assert_force_wake_inactive(dev_priv);
 
 	DRM_DEBUG_KMS("Suspending device\n");
 
+	/*
+	 * rps.work can't be rearmed here, since we get here only after making
+	 * sure the GPU is idle and the RPS freq is set to the minimum. See
+	 * intel_mark_idle().
+	 */
+	cancel_work_sync(&dev_priv->rps.work);
+	intel_runtime_pm_disable_interrupts(dev);
+
 	if (IS_GEN6(dev))
-		snb_runtime_suspend(dev_priv);
+		;
 	else if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hsw_runtime_suspend(dev_priv);
 	else
@@ -981,6 +1037,12 @@ static int intel_runtime_resume(struct device *device)
 	else
 		WARN_ON(1);
 
+	i915_gem_init_swizzling(dev);
+	gen6_update_ring_freq(dev);
+
+	intel_runtime_pm_restore_interrupts(dev);
+	intel_reset_gt_powersave(dev);
+
 	DRM_DEBUG_KMS("Device resumed\n");
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7d6acb401fd9..3fc2e3d71136 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -325,7 +325,6 @@ struct drm_i915_error_state {
 	u32 gab_ctl;
 	u32 gfx_mode;
 	u32 extra_instdone[I915_NUM_INSTDONE_REG];
-	u32 pipestat[I915_MAX_PIPES];
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
@@ -929,6 +928,7 @@ struct i915_power_domains {
 	 * time are on. They are kept on until after the first modeset.
 	 */
 	bool init_power_on;
+	bool initializing;
 	int power_well_count;
 
 	struct mutex lock;
@@ -1473,6 +1473,8 @@ struct drm_i915_private {
 	struct i915_dri1_state dri1;
 	/* Old ums support infrastructure, same warning applies. */
 	struct i915_ums_state ums;
+	/* the indicator for dispatch video commands on two BSD rings */
+	int ring_index;
 };
 
 static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
@@ -1680,6 +1682,7 @@ struct drm_i915_file_private {
 
 	struct i915_hw_context *private_default_ctx;
 	atomic_t rps_wait_boost;
+	struct  intel_ring_buffer *bsd_ring;
 };
 
 /*
@@ -1834,11 +1837,14 @@ struct drm_i915_cmd_table {
 #define BSD_RING		(1<<VCS)
 #define BLT_RING		(1<<BCS)
 #define VEBOX_RING		(1<<VECS)
-#define HAS_BSD(dev)            (INTEL_INFO(dev)->ring_mask & BSD_RING)
-#define HAS_BLT(dev)            (INTEL_INFO(dev)->ring_mask & BLT_RING)
-#define HAS_VEBOX(dev)            (INTEL_INFO(dev)->ring_mask & VEBOX_RING)
-#define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
-#define HAS_WT(dev)            (IS_HASWELL(dev) && to_i915(dev)->ellc_size)
+#define BSD2_RING		(1<<VCS2)
+#define HAS_BSD(dev)		(INTEL_INFO(dev)->ring_mask & BSD_RING)
+#define HAS_BSD2(dev)		(INTEL_INFO(dev)->ring_mask & BSD2_RING)
+#define HAS_BLT(dev)		(INTEL_INFO(dev)->ring_mask & BLT_RING)
+#define HAS_VEBOX(dev)		(INTEL_INFO(dev)->ring_mask & VEBOX_RING)
+#define HAS_LLC(dev)		(INTEL_INFO(dev)->has_llc)
+#define HAS_WT(dev)		((IS_HASWELL(dev) || IS_BROADWELL(dev)) && \
+				 to_i915(dev)->ellc_size)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
@@ -1969,6 +1975,7 @@ extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
 extern unsigned long i915_mch_val(struct drm_i915_private *dev_priv);
 extern unsigned long i915_gfx_val(struct drm_i915_private *dev_priv);
 extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
+int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 
 extern void intel_console_resume(struct work_struct *work);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5c8b86196c84..e1fa919017e2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -43,6 +43,9 @@ static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *o
 static __must_check int
 i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
 			       bool readonly);
+static void
+i915_gem_object_retire(struct drm_i915_gem_object *obj);
+
 static int i915_gem_phys_pwrite(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				struct drm_i915_gem_pwrite *args,
@@ -352,6 +355,8 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
 		ret = i915_gem_object_wait_rendering(obj, true);
 		if (ret)
 			return ret;
+
+		i915_gem_object_retire(obj);
 	}
 
 	ret = i915_gem_object_get_pages(obj);
@@ -767,6 +772,8 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 		ret = i915_gem_object_wait_rendering(obj, false);
 		if (ret)
 			return ret;
+
+		i915_gem_object_retire(obj);
 	}
 	/* Same trick applies to invalidate partially written cachelines read
 	 * before writing. */
@@ -1154,7 +1161,8 @@ static int
 i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj,
 				     struct intel_ring_buffer *ring)
 {
-	i915_gem_retire_requests_ring(ring);
+	if (!obj->active)
+		return 0;
 
 	/* Manually manage the write flush as we may have not yet
 	 * retired the buffer.
@@ -1164,7 +1172,6 @@ i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj,
 	 * we know we have passed the last write.
 	 */
 	obj->last_write_seqno = 0;
-	obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
 
 	return 0;
 }
@@ -1785,58 +1792,58 @@ static unsigned long
 __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 		  bool purgeable_only)
 {
-	struct list_head still_bound_list;
-	struct drm_i915_gem_object *obj, *next;
+	struct list_head still_in_list;
+	struct drm_i915_gem_object *obj;
 	unsigned long count = 0;
 
-	list_for_each_entry_safe(obj, next,
-				 &dev_priv->mm.unbound_list,
-				 global_list) {
-		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
-		    i915_gem_object_put_pages(obj) == 0) {
-			count += obj->base.size >> PAGE_SHIFT;
-			if (count >= target)
-				return count;
-		}
-	}
-
 	/*
-	 * As we may completely rewrite the bound list whilst unbinding
+	 * As we may completely rewrite the (un)bound list whilst unbinding
 	 * (due to retiring requests) we have to strictly process only
 	 * one element of the list at the time, and recheck the list
 	 * on every iteration.
+	 *
+	 * In particular, we must hold a reference whilst removing the
+	 * object as we may end up waiting for and/or retiring the objects.
+	 * This might release the final reference (held by the active list)
+	 * and result in the object being freed from under us. This is
+	 * similar to the precautions the eviction code must take whilst
+	 * removing objects.
+	 *
+	 * Also note that although these lists do not hold a reference to
+	 * the object we can safely grab one here: The final object
+	 * unreferencing and the bound_list are both protected by the
+	 * dev->struct_mutex and so we won't ever be able to observe an
+	 * object on the bound_list with a reference count equals 0.
 	 */
-	INIT_LIST_HEAD(&still_bound_list);
+	INIT_LIST_HEAD(&still_in_list);
+	while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
+		obj = list_first_entry(&dev_priv->mm.unbound_list,
+				       typeof(*obj), global_list);
+		list_move_tail(&obj->global_list, &still_in_list);
+
+		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+			continue;
+
+		drm_gem_object_reference(&obj->base);
+
+		if (i915_gem_object_put_pages(obj) == 0)
+			count += obj->base.size >> PAGE_SHIFT;
+
+		drm_gem_object_unreference(&obj->base);
+	}
+	list_splice(&still_in_list, &dev_priv->mm.unbound_list);
+
+	INIT_LIST_HEAD(&still_in_list);
 	while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
 		struct i915_vma *vma, *v;
 
 		obj = list_first_entry(&dev_priv->mm.bound_list,
 				       typeof(*obj), global_list);
-		list_move_tail(&obj->global_list, &still_bound_list);
+		list_move_tail(&obj->global_list, &still_in_list);
 
 		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
 			continue;
 
-		/*
-		 * Hold a reference whilst we unbind this object, as we may
-		 * end up waiting for and retiring requests. This might
-		 * release the final reference (held by the active list)
-		 * and result in the object being freed from under us.
-		 * in this object being freed.
-		 *
-		 * Note 1: Shrinking the bound list is special since only active
-		 * (and hence bound objects) can contain such limbo objects, so
-		 * we don't need special tricks for shrinking the unbound list.
-		 * The only other place where we have to be careful with active
-		 * objects suddenly disappearing due to retiring requests is the
-		 * eviction code.
-		 *
-		 * Note 2: Even though the bound list doesn't hold a reference
-		 * to the object we can safely grab one here: The final object
-		 * unreferencing and the bound_list are both protected by the
-		 * dev->struct_mutex and so we won't ever be able to observe an
-		 * object on the bound_list with a reference count equals 0.
-		 */
 		drm_gem_object_reference(&obj->base);
 
 		list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
@@ -1848,7 +1855,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 
 		drm_gem_object_unreference(&obj->base);
 	}
-	list_splice(&still_bound_list, &dev_priv->mm.bound_list);
+	list_splice(&still_in_list, &dev_priv->mm.bound_list);
 
 	return count;
 }
@@ -1862,17 +1869,8 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
 static unsigned long
 i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_gem_object *obj, *next;
-	long freed = 0;
-
 	i915_gem_evict_everything(dev_priv->dev);
-
-	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
-				 global_list) {
-		if (i915_gem_object_put_pages(obj) == 0)
-			freed += obj->base.size >> PAGE_SHIFT;
-	}
-	return freed;
+	return __i915_gem_shrink(dev_priv, LONG_MAX, false);
 }
 
 static int
@@ -2089,6 +2087,19 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 	WARN_ON(i915_verify_lists(dev));
 }
 
+static void
+i915_gem_object_retire(struct drm_i915_gem_object *obj)
+{
+	struct intel_ring_buffer *ring = obj->ring;
+
+	if (ring == NULL)
+		return;
+
+	if (i915_seqno_passed(ring->get_seqno(ring, true),
+			      obj->last_read_seqno))
+		i915_gem_object_move_to_inactive(obj);
+}
+
 static int
 i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 {
@@ -2108,8 +2119,8 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 	for_each_ring(ring, dev_priv, i) {
 		intel_ring_init_seqno(ring, seqno);
 
-		for (j = 0; j < ARRAY_SIZE(ring->sync_seqno); j++)
-			ring->sync_seqno[j] = 0;
+		for (j = 0; j < ARRAY_SIZE(ring->semaphore.sync_seqno); j++)
+			ring->semaphore.sync_seqno[j] = 0;
 	}
 
 	return 0;
@@ -2384,6 +2395,11 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 
 		i915_gem_free_request(request);
 	}
+
+	/* These may not have been flush before the reset, do so now */
+	kfree(ring->preallocated_lazy_request);
+	ring->preallocated_lazy_request = NULL;
+	ring->outstanding_lazy_seqno = 0;
 }
 
 void i915_gem_restore_fences(struct drm_device *dev)
@@ -2424,8 +2440,6 @@ void i915_gem_reset(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i)
 		i915_gem_reset_ring_cleanup(dev_priv, ring);
 
-	i915_gem_cleanup_ringbuffer(dev);
-
 	i915_gem_context_reset(dev);
 
 	i915_gem_restore_fences(dev);
@@ -2678,7 +2692,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
 	idx = intel_ring_sync_index(from, to);
 
 	seqno = obj->last_read_seqno;
-	if (seqno <= from->sync_seqno[idx])
+	if (seqno <= from->semaphore.sync_seqno[idx])
 		return 0;
 
 	ret = i915_gem_check_olr(obj->ring, seqno);
@@ -2686,13 +2700,13 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
 		return ret;
 
 	trace_i915_gem_ring_sync_to(from, to, seqno);
-	ret = to->sync_to(to, from, seqno);
+	ret = to->semaphore.sync_to(to, from, seqno);
 	if (!ret)
 		/* We use last_read_seqno because sync_to()
 		 * might have just caused seqno wrap under
 		 * the radar.
 		 */
-		from->sync_seqno[idx] = obj->last_read_seqno;
+		from->semaphore.sync_seqno[idx] = obj->last_read_seqno;
 
 	return ret;
 }
@@ -3426,6 +3440,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
+	i915_gem_object_retire(obj);
 	i915_gem_object_flush_cpu_write_domain(obj, false);
 
 	/* Serialise direct access to this object with the barriers for
@@ -3524,6 +3539,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		 * in obj->write_domain and have been skipping the clflushes.
 		 * Just set it to the CPU cache for now.
 		 */
+		i915_gem_object_retire(obj);
 		WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);
 
 		old_read_domains = obj->base.read_domains;
@@ -3746,6 +3762,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
+	i915_gem_object_retire(obj);
 	i915_gem_object_flush_gtt_write_domain(obj);
 
 	old_write_domain = obj->base.write_domain;
@@ -4233,6 +4250,17 @@ void i915_gem_vma_destroy(struct i915_vma *vma)
 	kfree(vma);
 }
 
+static void
+i915_gem_stop_ringbuffers(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring;
+	int i;
+
+	for_each_ring(ring, dev_priv, i)
+		intel_stop_ring_buffer(ring);
+}
+
 int
 i915_gem_suspend(struct drm_device *dev)
 {
@@ -4254,7 +4282,7 @@ i915_gem_suspend(struct drm_device *dev)
 		i915_gem_evict_everything(dev);
 
 	i915_kernel_lost_context(dev);
-	i915_gem_cleanup_ringbuffer(dev);
+	i915_gem_stop_ringbuffers(dev);
 
 	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
 	 * We need to replace this with a semaphore, or something.
@@ -4374,13 +4402,20 @@ static int i915_gem_init_rings(struct drm_device *dev)
 			goto cleanup_blt_ring;
 	}
 
+	if (HAS_BSD2(dev)) {
+		ret = intel_init_bsd2_ring_buffer(dev);
+		if (ret)
+			goto cleanup_vebox_ring;
+	}
 
 	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
 	if (ret)
-		goto cleanup_vebox_ring;
+		goto cleanup_bsd2_ring;
 
 	return 0;
 
+cleanup_bsd2_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[VCS2]);
 cleanup_vebox_ring:
 	intel_cleanup_ring_buffer(&dev_priv->ring[VECS]);
 cleanup_blt_ring:
@@ -4438,15 +4473,11 @@ i915_gem_init_hw(struct drm_device *dev)
 	 * the do_switch), but before enabling PPGTT. So don't move this.
 	 */
 	ret = i915_gem_context_enable(dev_priv);
-	if (ret) {
+	if (ret && ret != -EIO) {
 		DRM_ERROR("Context enable failed %d\n", ret);
-		goto err_out;
+		i915_gem_cleanup_ringbuffer(dev);
 	}
 
-	return 0;
-
-err_out:
-	i915_gem_cleanup_ringbuffer(dev);
 	return ret;
 }
 
@@ -4459,8 +4490,9 @@ int i915_gem_init(struct drm_device *dev)
 
 	if (IS_VALLEYVIEW(dev)) {
 		/* VLVA0 (potential hack), BIOS isn't actually waking us */
-		I915_WRITE(VLV_GTLC_WAKE_CTRL, 1);
-		if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) & 1) == 1, 10))
+		I915_WRITE(VLV_GTLC_WAKE_CTRL, VLV_GTLC_ALLOWWAKEREQ);
+		if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) &
+			      VLV_GTLC_ALLOWWAKEACK), 10))
 			DRM_DEBUG_DRIVER("allow wake ack timed out\n");
 	}
 
@@ -4473,18 +4505,21 @@ int i915_gem_init(struct drm_device *dev)
 	}
 
 	ret = i915_gem_init_hw(dev);
-	mutex_unlock(&dev->struct_mutex);
-	if (ret) {
-		WARN_ON(dev_priv->mm.aliasing_ppgtt);
-		i915_gem_context_fini(dev);
-		drm_mm_takedown(&dev_priv->gtt.base.mm);
-		return ret;
+	if (ret == -EIO) {
+		/* Allow ring initialisation to fail by marking the GPU as
+		 * wedged. But we only want to do this where the GPU is angry,
+		 * for all other failure, such as an allocation failure, bail.
+		 */
+		DRM_ERROR("Failed to initialize GPU, declaring it wedged\n");
+		atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
+		ret = 0;
 	}
+	mutex_unlock(&dev->struct_mutex);
 
 	/* Allow hardware batchbuffers unless told otherwise, but not for KMS. */
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		dev_priv->dri1.allow_batchbuffer = 1;
-	return 0;
+	return ret;
 }
 
 void
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0ec8621eb4f8..47fe8ecef135 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -262,10 +262,12 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 
 static int
 relocate_entry_cpu(struct drm_i915_gem_object *obj,
-		   struct drm_i915_gem_relocation_entry *reloc)
+		   struct drm_i915_gem_relocation_entry *reloc,
+		   uint64_t target_offset)
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
+	uint64_t delta = reloc->delta + target_offset;
 	char *vaddr;
 	int ret;
 
@@ -275,7 +277,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 
 	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
 				reloc->offset >> PAGE_SHIFT));
-	*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+	*(uint32_t *)(vaddr + page_offset) = lower_32_bits(delta);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		page_offset = offset_in_page(page_offset + sizeof(uint32_t));
@@ -286,7 +288,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 			    (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
 		}
 
-		*(uint32_t *)(vaddr + page_offset) = 0;
+		*(uint32_t *)(vaddr + page_offset) = upper_32_bits(delta);
 	}
 
 	kunmap_atomic(vaddr);
@@ -296,10 +298,12 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 
 static int
 relocate_entry_gtt(struct drm_i915_gem_object *obj,
-		   struct drm_i915_gem_relocation_entry *reloc)
+		   struct drm_i915_gem_relocation_entry *reloc,
+		   uint64_t target_offset)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint64_t delta = reloc->delta + target_offset;
 	uint32_t __iomem *reloc_entry;
 	void __iomem *reloc_page;
 	int ret;
@@ -318,7 +322,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 			reloc->offset & PAGE_MASK);
 	reloc_entry = (uint32_t __iomem *)
 		(reloc_page + offset_in_page(reloc->offset));
-	iowrite32(reloc->delta, reloc_entry);
+	iowrite32(lower_32_bits(delta), reloc_entry);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		reloc_entry += 1;
@@ -331,7 +335,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 			reloc_entry = reloc_page;
 		}
 
-		iowrite32(0, reloc_entry);
+		iowrite32(upper_32_bits(delta), reloc_entry);
 	}
 
 	io_mapping_unmap_atomic(reloc_page);
@@ -348,7 +352,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	struct drm_gem_object *target_obj;
 	struct drm_i915_gem_object *target_i915_obj;
 	struct i915_vma *target_vma;
-	uint32_t target_offset;
+	uint64_t target_offset;
 	int ret;
 
 	/* we've already hold a reference to all valid objects */
@@ -426,11 +430,10 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	if (obj->active && in_atomic())
 		return -EFAULT;
 
-	reloc->delta += target_offset;
 	if (use_cpu_reloc(obj))
-		ret = relocate_entry_cpu(obj, reloc);
+		ret = relocate_entry_cpu(obj, reloc, target_offset);
 	else
-		ret = relocate_entry_gtt(obj, reloc);
+		ret = relocate_entry_gtt(obj, reloc, target_offset);
 
 	if (ret)
 		return ret;
@@ -955,6 +958,9 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 			if (i915_gem_obj_ggtt_bound(obj) &&
 			    i915_gem_obj_to_ggtt(obj)->pin_count)
 				intel_mark_fb_busy(obj, ring);
+
+			/* update for the implicit flush after a batch */
+			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
 		}
 
 		trace_i915_gem_object_change_domain(obj, old_read, old_write);
@@ -981,8 +987,10 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret, i;
 
-	if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS])
-		return 0;
+	if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS]) {
+		DRM_DEBUG("sol reset is gen7/rcs only\n");
+		return -EINVAL;
+	}
 
 	ret = intel_ring_begin(ring, 4 * 3);
 	if (ret)
@@ -999,6 +1007,37 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 	return 0;
 }
 
+/**
+ * Find one BSD ring to dispatch the corresponding BSD command.
+ * The Ring ID is returned.
+ */
+static int gen8_dispatch_bsd_ring(struct drm_device *dev,
+				  struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_file_private *file_priv = file->driver_priv;
+
+	/* Check whether the file_priv is using one ring */
+	if (file_priv->bsd_ring)
+		return file_priv->bsd_ring->id;
+	else {
+		/* If no, use the ping-pong mechanism to select one ring */
+		int ring_id;
+
+		mutex_lock(&dev->struct_mutex);
+		if (dev_priv->ring_index == 0) {
+			ring_id = VCS;
+			dev_priv->ring_index = 1;
+		} else {
+			ring_id = VCS2;
+			dev_priv->ring_index = 0;
+		}
+		file_priv->bsd_ring = &dev_priv->ring[ring_id];
+		mutex_unlock(&dev->struct_mutex);
+		return ring_id;
+	}
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_file *file,
@@ -1013,7 +1052,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct i915_hw_context *ctx;
 	struct i915_address_space *vm;
 	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
-	u32 exec_start = args->batch_start_offset, exec_len;
+	u64 exec_start = args->batch_start_offset, exec_len;
 	u32 mask, flags;
 	int ret, mode, i;
 	bool need_relocs;
@@ -1035,7 +1074,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		flags |= I915_DISPATCH_PINNED;
 
-	if ((args->flags & I915_EXEC_RING_MASK) > I915_NUM_RINGS) {
+	if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) {
 		DRM_DEBUG("execbuf with unknown ring: %d\n",
 			  (int)(args->flags & I915_EXEC_RING_MASK));
 		return -EINVAL;
@@ -1043,7 +1082,14 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_DEFAULT)
 		ring = &dev_priv->ring[RCS];
-	else
+	else if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_BSD) {
+		if (HAS_BSD2(dev)) {
+			int ring_id;
+			ring_id = gen8_dispatch_bsd_ring(dev, file);
+			ring = &dev_priv->ring[ring_id];
+		} else
+			ring = &dev_priv->ring[VCS];
+	} else
 		ring = &dev_priv->ring[(args->flags & I915_EXEC_RING_MASK) - 1];
 
 	if (!intel_ring_initialized(ring)) {
@@ -1058,14 +1104,22 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	case I915_EXEC_CONSTANTS_REL_GENERAL:
 	case I915_EXEC_CONSTANTS_ABSOLUTE:
 	case I915_EXEC_CONSTANTS_REL_SURFACE:
-		if (ring == &dev_priv->ring[RCS] &&
-		    mode != dev_priv->relative_constants_mode) {
-			if (INTEL_INFO(dev)->gen < 4)
+		if (mode != 0 && ring != &dev_priv->ring[RCS]) {
+			DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
+			return -EINVAL;
+		}
+
+		if (mode != dev_priv->relative_constants_mode) {
+			if (INTEL_INFO(dev)->gen < 4) {
+				DRM_DEBUG("no rel constants on pre-gen4\n");
 				return -EINVAL;
+			}
 
 			if (INTEL_INFO(dev)->gen > 5 &&
-			    mode == I915_EXEC_CONSTANTS_REL_SURFACE)
+			    mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
+				DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
 				return -EINVAL;
+			}
 
 			/* The HW changed the meaning on this bit on gen6 */
 			if (INTEL_INFO(dev)->gen >= 6)
@@ -1113,6 +1167,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			ret = -EFAULT;
 			goto pre_mutex_err;
 		}
+	} else {
+		if (args->DR1 || args->DR4 || args->cliprects_ptr) {
+			DRM_DEBUG("0 cliprects but dirt in cliprects fields\n");
+			return -EINVAL;
+		}
 	}
 
 	intel_runtime_pm_get(dev_priv);
@@ -1390,6 +1449,11 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	if (args->rsvd2 != 0) {
+		DRM_DEBUG("dirty rvsd2 field\n");
+		return -EINVAL;
+	}
+
 	exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count,
 			     GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
 	if (exec2_list == NULL)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0d514ff9b94c..496916298e8a 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -68,10 +68,19 @@ static inline gen8_gtt_pte_t gen8_pte_encode(dma_addr_t addr,
 {
 	gen8_gtt_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0;
 	pte |= addr;
-	if (level != I915_CACHE_NONE)
-		pte |= PPAT_CACHED_INDEX;
-	else
+
+	switch (level) {
+	case I915_CACHE_NONE:
 		pte |= PPAT_UNCACHED_INDEX;
+		break;
+	case I915_CACHE_WT:
+		pte |= PPAT_DISPLAY_ELLC_INDEX;
+		break;
+	default:
+		pte |= PPAT_CACHED_INDEX;
+		break;
+	}
+
 	return pte;
 }
 
@@ -1368,7 +1377,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 		(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
 	struct sg_page_iter sg_iter;
-	dma_addr_t addr;
+	dma_addr_t addr = 0;
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_dma_address(sg_iter.sg) +
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 4865ade71f29..2d819858c19b 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -42,6 +42,7 @@ static const char *ring_str(int ring)
 	case VCS: return "bsd";
 	case BCS: return "blt";
 	case VECS: return "vebox";
+	case VCS2: return "bsd2";
 	default: return "";
 	}
 }
@@ -756,14 +757,14 @@ static void i915_record_ring_state(struct drm_device *dev,
 			= I915_READ(RING_SYNC_0(ring->mmio_base));
 		ering->semaphore_mboxes[1]
 			= I915_READ(RING_SYNC_1(ring->mmio_base));
-		ering->semaphore_seqno[0] = ring->sync_seqno[0];
-		ering->semaphore_seqno[1] = ring->sync_seqno[1];
+		ering->semaphore_seqno[0] = ring->semaphore.sync_seqno[0];
+		ering->semaphore_seqno[1] = ring->semaphore.sync_seqno[1];
 	}
 
 	if (HAS_VEBOX(dev)) {
 		ering->semaphore_mboxes[2] =
 			I915_READ(RING_SYNC_2(ring->mmio_base));
-		ering->semaphore_seqno[2] = ring->sync_seqno[2];
+		ering->semaphore_seqno[2] = ring->semaphore.sync_seqno[2];
 	}
 
 	if (INTEL_INFO(dev)->gen >= 4) {
@@ -1028,7 +1029,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error)
 {
 	struct drm_device *dev = dev_priv->dev;
-	int pipe;
 
 	/* General organization
 	 * 1. Registers specific to a single generation
@@ -1053,9 +1053,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 		error->gfx_mode = I915_READ(GFX_MODE);
 	}
 
-	if (IS_GEN2(dev))
-		error->ier = I915_READ16(IER);
-
 	/* 2: Registers which belong to multiple generations */
 	if (INTEL_INFO(dev)->gen >= 7)
 		error->forcewake = I915_READ(FORCEWAKE_MT);
@@ -1079,9 +1076,10 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 	if (HAS_PCH_SPLIT(dev))
 		error->ier = I915_READ(DEIER) | I915_READ(GTIER);
 	else {
-		error->ier = I915_READ(IER);
-		for_each_pipe(pipe)
-			error->pipestat[pipe] = I915_READ(PIPESTAT(pipe));
+		if (IS_GEN2(dev))
+			error->ier = I915_READ16(IER);
+		else
+			error->ier = I915_READ(IER);
 	}
 
 	/* 4: Everything else */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index afa55199b829..2d7618366b75 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -751,24 +751,32 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe)
 /* raw reads, only for fast reads of display block, no need for forcewake etc. */
 #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
 
-static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
+static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 {
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t status;
-	int reg;
+	const struct drm_display_mode *mode = &crtc->config.adjusted_mode;
+	enum pipe pipe = crtc->pipe;
+	int vtotal = mode->crtc_vtotal;
+	int position;
 
-	if (INTEL_INFO(dev)->gen >= 8) {
-		status = GEN8_PIPE_VBLANK;
-		reg = GEN8_DE_PIPE_ISR(pipe);
-	} else if (INTEL_INFO(dev)->gen >= 7) {
-		status = DE_PIPE_VBLANK_IVB(pipe);
-		reg = DEISR;
-	} else {
-		status = DE_PIPE_VBLANK(pipe);
-		reg = DEISR;
-	}
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		vtotal /= 2;
+
+	if (IS_GEN2(dev))
+		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
+	else
+		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
-	return __raw_i915_read32(dev_priv, reg) & status;
+	/*
+	 * Scanline counter increments at leading edge of hsync, and
+	 * it starts counting from vtotal-1 on the first active line.
+	 * That means the scanline counter value is always one less
+	 * than what we would expect. Ie. just after start of vblank,
+	 * which also occurs at start of hsync (on the last active line),
+	 * the scanline counter will read vblank_start-1.
+	 */
+	return (position + 1) % vtotal;
 }
 
 static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
@@ -780,7 +788,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	const struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode;
 	int position;
-	int vbl_start, vbl_end, htotal, vtotal;
+	int vbl_start, vbl_end, hsync_start, htotal, vtotal;
 	bool in_vbl = true;
 	int ret = 0;
 	unsigned long irqflags;
@@ -792,6 +800,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	}
 
 	htotal = mode->crtc_htotal;
+	hsync_start = mode->crtc_hsync_start;
 	vtotal = mode->crtc_vtotal;
 	vbl_start = mode->crtc_vblank_start;
 	vbl_end = mode->crtc_vblank_end;
@@ -810,7 +819,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	 * following code must not block on uncore.lock.
 	 */
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
-	
+
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
 
 	/* Get optional system timestamp before query. */
@@ -821,68 +830,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 		/* No obvious pixelcount register. Only query vertical
 		 * scanout position from Display scan line register.
 		 */
-		if (IS_GEN2(dev))
-			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
-		else
-			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
-
-		if (HAS_DDI(dev)) {
-			/*
-			 * On HSW HDMI outputs there seems to be a 2 line
-			 * difference, whereas eDP has the normal 1 line
-			 * difference that earlier platforms have. External
-			 * DP is unknown. For now just check for the 2 line
-			 * difference case on all output types on HSW+.
-			 *
-			 * This might misinterpret the scanline counter being
-			 * one line too far along on eDP, but that's less
-			 * dangerous than the alternative since that would lead
-			 * the vblank timestamp code astray when it sees a
-			 * scanline count before vblank_start during a vblank
-			 * interrupt.
-			 */
-			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
-			if ((in_vbl && (position == vbl_start - 2 ||
-					position == vbl_start - 1)) ||
-			    (!in_vbl && (position == vbl_end - 2 ||
-					 position == vbl_end - 1)))
-				position = (position + 2) % vtotal;
-		} else if (HAS_PCH_SPLIT(dev)) {
-			/*
-			 * The scanline counter increments at the leading edge
-			 * of hsync, ie. it completely misses the active portion
-			 * of the line. Fix up the counter at both edges of vblank
-			 * to get a more accurate picture whether we're in vblank
-			 * or not.
-			 */
-			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
-			if ((in_vbl && position == vbl_start - 1) ||
-			    (!in_vbl && position == vbl_end - 1))
-				position = (position + 1) % vtotal;
-		} else {
-			/*
-			 * ISR vblank status bits don't work the way we'd want
-			 * them to work on non-PCH platforms (for
-			 * ilk_pipe_in_vblank_locked()), and there doesn't
-			 * appear any other way to determine if we're currently
-			 * in vblank.
-			 *
-			 * Instead let's assume that we're already in vblank if
-			 * we got called from the vblank interrupt and the
-			 * scanline counter value indicates that we're on the
-			 * line just prior to vblank start. This should result
-			 * in the correct answer, unless the vblank interrupt
-			 * delivery really got delayed for almost exactly one
-			 * full frame/field.
-			 */
-			if (flags & DRM_CALLED_FROM_VBLIRQ &&
-			    position == vbl_start - 1) {
-				position = (position + 1) % vtotal;
-
-				/* Signal this correction as "applied". */
-				ret |= 0x8;
-			}
-		}
+		position = __intel_get_crtc_scanline(intel_crtc);
 	} else {
 		/* Have access to pixelcount since start of frame.
 		 * We can split this into vertical and horizontal
@@ -894,6 +842,17 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 		vbl_start *= htotal;
 		vbl_end *= htotal;
 		vtotal *= htotal;
+
+		/*
+		 * Start of vblank interrupt is triggered at start of hsync,
+		 * just prior to the first active line of vblank. However we
+		 * consider lines to start at the leading edge of horizontal
+		 * active. So, should we get here before we've crossed into
+		 * the horizontal active of the first line in vblank, we would
+		 * not set the DRM_SCANOUTPOS_INVBL flag. In order to fix that,
+		 * always add htotal-hsync_start to the current pixel position.
+		 */
+		position = (position + htotal - hsync_start) % vtotal;
 	}
 
 	/* Get optional system timestamp after query. */
@@ -932,6 +891,19 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	return ret;
 }
 
+int intel_get_crtc_scanline(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	unsigned long irqflags;
+	int position;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	position = __intel_get_crtc_scanline(crtc);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+
+	return position;
+}
+
 static int i915_get_vblank_timestamp(struct drm_device *dev, int pipe,
 			      int *max_error,
 			      struct timeval *vblank_time,
@@ -1347,13 +1319,16 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 			DRM_ERROR("The master control interrupt lied (GT0)!\n");
 	}
 
-	if (master_ctl & GEN8_GT_VCS1_IRQ) {
+	if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
 		tmp = I915_READ(GEN8_GT_IIR(1));
 		if (tmp) {
 			ret = IRQ_HANDLED;
 			vcs = tmp >> GEN8_VCS1_IRQ_SHIFT;
 			if (vcs & GT_RENDER_USER_INTERRUPT)
 				notify_ring(dev, &dev_priv->ring[VCS]);
+			vcs = tmp >> GEN8_VCS2_IRQ_SHIFT;
+			if (vcs & GT_RENDER_USER_INTERRUPT)
+				notify_ring(dev, &dev_priv->ring[VCS2]);
 			I915_WRITE(GEN8_GT_IIR(1), tmp);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT1)!\n");
@@ -1581,6 +1556,19 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 	}
 }
 
+static bool intel_pipe_handle_vblank(struct drm_device *dev, enum pipe pipe)
+{
+	struct intel_crtc *crtc;
+
+	if (!drm_handle_vblank(dev, pipe))
+		return false;
+
+	crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe));
+	wake_up(&crtc->vbl_wait);
+
+	return true;
+}
+
 static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1632,7 +1620,7 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 
 	for_each_pipe(pipe) {
 		if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS)
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		if (pipe_stats[pipe] & PLANE_FLIP_DONE_INT_STATUS_VLV) {
 			intel_prepare_page_flip(dev, pipe);
@@ -1875,7 +1863,7 @@ static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir)
 
 	for_each_pipe(pipe) {
 		if (de_iir & DE_PIPE_VBLANK(pipe))
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		if (de_iir & DE_PIPE_FIFO_UNDERRUN(pipe))
 			if (intel_set_cpu_fifo_underrun_reporting(dev, pipe, false))
@@ -1925,7 +1913,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 
 	for_each_pipe(pipe) {
 		if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)))
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		/* plane/pipes map 1:1 on ilk+ */
 		if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) {
@@ -2068,7 +2056,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 
 		pipe_iir = I915_READ(GEN8_DE_PIPE_IIR(pipe));
 		if (pipe_iir & GEN8_PIPE_VBLANK)
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		if (pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE) {
 			intel_prepare_page_flip(dev, pipe);
@@ -2185,6 +2173,14 @@ static void i915_error_work_func(struct work_struct *work)
 				   reset_event);
 
 		/*
+		 * In most cases it's guaranteed that we get here with an RPM
+		 * reference held, for example because there is a pending GPU
+		 * request that won't finish until the reset is done. This
+		 * isn't the case at least when we get here by doing a
+		 * simulated reset via debugs, so get an RPM reference.
+		 */
+		intel_runtime_pm_get(dev_priv);
+		/*
 		 * All state reset _must_ be completed before we update the
 		 * reset counter, for otherwise waiters might miss the reset
 		 * pending state and not properly drop locks, resulting in
@@ -2194,6 +2190,8 @@ static void i915_error_work_func(struct work_struct *work)
 
 		intel_display_handle_reset(dev);
 
+		intel_runtime_pm_put(dev_priv);
+
 		if (ret == 0) {
 			/*
 			 * After all the gem state is reset, increment the reset
@@ -2597,8 +2595,7 @@ semaphore_wait_to_signaller_ring(struct intel_ring_buffer *ring, u32 ipehr)
 			if(ring == signaller)
 				continue;
 
-			if (sync_bits ==
-			    signaller->semaphore_register[ring->id])
+			if (sync_bits == signaller->semaphore.mbox.wait[ring->id])
 				return signaller;
 		}
 	}
@@ -3315,6 +3312,8 @@ static void valleyview_irq_uninstall(struct drm_device *dev)
 	if (!dev_priv)
 		return;
 
+	I915_WRITE(VLV_MASTER_IER, 0);
+
 	intel_hpd_irq_uninstall(dev_priv);
 
 	for_each_pipe(pipe)
@@ -3404,7 +3403,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
-	if (!drm_handle_vblank(dev, pipe))
+	if (!intel_pipe_handle_vblank(dev, pipe))
 		return false;
 
 	if ((iir & flip_pending) == 0)
@@ -3589,7 +3588,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
-	if (!drm_handle_vblank(dev, pipe))
+	if (!intel_pipe_handle_vblank(dev, pipe))
 		return false;
 
 	if ((iir & flip_pending) == 0)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 8f845556503e..0eff337a5720 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -760,6 +760,7 @@ enum punit_power_well {
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
 #define GEN6_BSD_RING_BASE	0x12000
+#define GEN8_BSD2_RING_BASE	0x1c000
 #define VEBOX_RING_BASE		0x1a000
 #define BLT_RING_BASE		0x22000
 #define RING_TAIL(base)		((base)+0x30)
@@ -4996,9 +4997,15 @@ enum punit_power_well {
 #define  FORCEWAKE_ACK_HSW			0x130044
 #define  FORCEWAKE_ACK				0x130090
 #define  VLV_GTLC_WAKE_CTRL			0x130090
+#define   VLV_GTLC_RENDER_CTX_EXISTS		(1 << 25)
+#define   VLV_GTLC_MEDIA_CTX_EXISTS		(1 << 24)
+#define   VLV_GTLC_ALLOWWAKEREQ			(1 << 0)
+
 #define  VLV_GTLC_PW_STATUS			0x130094
-#define VLV_GTLC_PW_RENDER_STATUS_MASK		0x80
-#define VLV_GTLC_PW_MEDIA_STATUS_MASK		0x20
+#define   VLV_GTLC_ALLOWWAKEACK			(1 << 0)
+#define   VLV_GTLC_ALLOWWAKEERR			(1 << 1)
+#define   VLV_GTLC_PW_MEDIA_STATUS_MASK		(1 << 5)
+#define   VLV_GTLC_PW_RENDER_STATUS_MASK	(1 << 7)
 #define  FORCEWAKE_MT				0xa188 /* multi-threaded */
 #define   FORCEWAKE_KERNEL			0x1
 #define   FORCEWAKE_USER			0x2
@@ -5130,6 +5137,9 @@ enum punit_power_well {
 #define   VLV_MEDIA_RC6_COUNT_EN		(1<<1)
 #define   VLV_RENDER_RC6_COUNT_EN		(1<<0)
 #define GEN6_GT_GFX_RC6				0x138108
+#define VLV_GT_RENDER_RC6			0x138108
+#define VLV_GT_MEDIA_RC6			0x13810C
+
 #define GEN6_GT_GFX_RC6p			0x13810C
 #define GEN6_GT_GFX_RC6pp			0x138110
 
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 9c57029f6f4b..3620997e43f5 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -263,6 +263,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
 
+	intel_runtime_pm_get(dev_priv);
+
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev)) {
 		u32 freq;
@@ -273,6 +275,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
+	intel_runtime_pm_put(dev_priv);
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 23c26f1f8b37..b29d7b1828f1 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -7,6 +7,7 @@
 
 #include <drm/drmP.h>
 #include "i915_drv.h"
+#include "intel_drv.h"
 #include "intel_ringbuffer.h"
 
 #undef TRACE_SYSTEM
@@ -14,6 +15,80 @@
 #define TRACE_SYSTEM_STRING __stringify(TRACE_SYSTEM)
 #define TRACE_INCLUDE_FILE i915_trace
 
+/* pipe updates */
+
+TRACE_EVENT(i915_pipe_update_start,
+	    TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max),
+	    TP_ARGS(crtc, min, max),
+
+	    TP_STRUCT__entry(
+			     __field(enum pipe, pipe)
+			     __field(u32, frame)
+			     __field(u32, scanline)
+			     __field(u32, min)
+			     __field(u32, max)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pipe = crtc->pipe;
+			   __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
+										       crtc->pipe);
+			   __entry->scanline = intel_get_crtc_scanline(crtc);
+			   __entry->min = min;
+			   __entry->max = max;
+			   ),
+
+	    TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u",
+		      pipe_name(__entry->pipe), __entry->frame,
+		       __entry->scanline, __entry->min, __entry->max)
+);
+
+TRACE_EVENT(i915_pipe_update_vblank_evaded,
+	    TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max, u32 frame),
+	    TP_ARGS(crtc, min, max, frame),
+
+	    TP_STRUCT__entry(
+			     __field(enum pipe, pipe)
+			     __field(u32, frame)
+			     __field(u32, scanline)
+			     __field(u32, min)
+			     __field(u32, max)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pipe = crtc->pipe;
+			   __entry->frame = frame;
+			   __entry->scanline = intel_get_crtc_scanline(crtc);
+			   __entry->min = min;
+			   __entry->max = max;
+			   ),
+
+	    TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u",
+		      pipe_name(__entry->pipe), __entry->frame,
+		       __entry->scanline, __entry->min, __entry->max)
+);
+
+TRACE_EVENT(i915_pipe_update_end,
+	    TP_PROTO(struct intel_crtc *crtc, u32 frame),
+	    TP_ARGS(crtc, frame),
+
+	    TP_STRUCT__entry(
+			     __field(enum pipe, pipe)
+			     __field(u32, frame)
+			     __field(u32, scanline)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pipe = crtc->pipe;
+			   __entry->frame = frame;
+			   __entry->scanline = intel_get_crtc_scanline(crtc);
+			   ),
+
+	    TP_printk("pipe %c, frame=%u, scanline=%u",
+		      pipe_name(__entry->pipe), __entry->frame,
+		      __entry->scanline)
+);
+
 /* object tracking */
 
 TRACE_EVENT(i915_gem_object_create,
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index fba9efd09e87..2945f57c53ee 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -49,13 +49,19 @@ find_section(struct bdb_header *bdb, int section_id)
 	total = bdb->bdb_size;
 
 	/* walk the sections looking for section_id */
-	while (index < total) {
+	while (index + 3 < total) {
 		current_id = *(base + index);
 		index++;
+
 		current_size = *((u16 *)(base + index));
 		index += 2;
+
+		if (index + current_size > total)
+			return NULL;
+
 		if (current_id == section_id)
 			return base + index;
+
 		index += current_size;
 	}
 
@@ -1099,6 +1105,46 @@ static const struct dmi_system_id intel_no_opregion_vbt[] = {
 	{ }
 };
 
+static struct bdb_header *validate_vbt(char *base, size_t size,
+				       struct vbt_header *vbt,
+				       const char *source)
+{
+	size_t offset;
+	struct bdb_header *bdb;
+
+	if (vbt == NULL) {
+		DRM_DEBUG_DRIVER("VBT signature missing\n");
+		return NULL;
+	}
+
+	offset = (char *)vbt - base;
+	if (offset + sizeof(struct vbt_header) > size) {
+		DRM_DEBUG_DRIVER("VBT header incomplete\n");
+		return NULL;
+	}
+
+	if (memcmp(vbt->signature, "$VBT", 4)) {
+		DRM_DEBUG_DRIVER("VBT invalid signature\n");
+		return NULL;
+	}
+
+	offset += vbt->bdb_offset;
+	if (offset + sizeof(struct bdb_header) > size) {
+		DRM_DEBUG_DRIVER("BDB header incomplete\n");
+		return NULL;
+	}
+
+	bdb = (struct bdb_header *)(base + offset);
+	if (offset + bdb->bdb_size > size) {
+		DRM_DEBUG_DRIVER("BDB incomplete\n");
+		return NULL;
+	}
+
+	DRM_DEBUG_KMS("Using VBT from %s: %20s\n",
+		      source, vbt->signature);
+	return bdb;
+}
+
 /**
  * intel_parse_bios - find VBT and initialize settings from the BIOS
  * @dev: DRM device
@@ -1122,20 +1168,13 @@ intel_parse_bios(struct drm_device *dev)
 	init_vbt_defaults(dev_priv);
 
 	/* XXX Should this validation be moved to intel_opregion.c? */
-	if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt) {
-		struct vbt_header *vbt = dev_priv->opregion.vbt;
-		if (memcmp(vbt->signature, "$VBT", 4) == 0) {
-			DRM_DEBUG_KMS("Using VBT from OpRegion: %20s\n",
-					 vbt->signature);
-			bdb = (struct bdb_header *)((char *)vbt + vbt->bdb_offset);
-		} else
-			dev_priv->opregion.vbt = NULL;
-	}
+	if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt)
+		bdb = validate_vbt((char *)dev_priv->opregion.header, OPREGION_SIZE,
+				   (struct vbt_header *)dev_priv->opregion.vbt,
+				   "OpRegion");
 
 	if (bdb == NULL) {
-		struct vbt_header *vbt = NULL;
-		size_t size;
-		int i;
+		size_t i, size;
 
 		bios = pci_map_rom(pdev, &size);
 		if (!bios)
@@ -1143,19 +1182,18 @@ intel_parse_bios(struct drm_device *dev)
 
 		/* Scour memory looking for the VBT signature */
 		for (i = 0; i + 4 < size; i++) {
-			if (!memcmp(bios + i, "$VBT", 4)) {
-				vbt = (struct vbt_header *)(bios + i);
+			if (memcmp(bios + i, "$VBT", 4) == 0) {
+				bdb = validate_vbt(bios, size,
+						   (struct vbt_header *)(bios + i),
+						   "PCI ROM");
 				break;
 			}
 		}
 
-		if (!vbt) {
-			DRM_DEBUG_DRIVER("VBT signature missing\n");
+		if (!bdb) {
 			pci_unmap_rom(pdev, bios);
 			return -1;
 		}
-
-		bdb = (struct bdb_header *)(bios + i + vbt->bdb_offset);
 	}
 
 	/* Grab useful general definitions */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index aa5a3dc43342..22d8347f7838 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -144,28 +144,49 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	u32 temp;
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
+	u32 adpa;
+
+	if (INTEL_INFO(dev)->gen >= 5)
+		adpa = ADPA_HOTPLUG_BITS;
+	else
+		adpa = 0;
 
-	temp = I915_READ(crt->adpa_reg);
-	temp &= ~(ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE);
-	temp &= ~ADPA_DAC_ENABLE;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+		adpa |= ADPA_HSYNC_ACTIVE_HIGH;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+		adpa |= ADPA_VSYNC_ACTIVE_HIGH;
+
+	/* For CPT allow 3 pipe config, for others just use A or B */
+	if (HAS_PCH_LPT(dev))
+		; /* Those bits don't exist here */
+	else if (HAS_PCH_CPT(dev))
+		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
+	else if (crtc->pipe == 0)
+		adpa |= ADPA_PIPE_A_SELECT;
+	else
+		adpa |= ADPA_PIPE_B_SELECT;
+
+	if (!HAS_PCH_SPLIT(dev))
+		I915_WRITE(BCLRPAT(crtc->pipe), 0);
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
-		temp |= ADPA_DAC_ENABLE;
+		adpa |= ADPA_DAC_ENABLE;
 		break;
 	case DRM_MODE_DPMS_STANDBY:
-		temp |= ADPA_DAC_ENABLE | ADPA_HSYNC_CNTL_DISABLE;
+		adpa |= ADPA_DAC_ENABLE | ADPA_HSYNC_CNTL_DISABLE;
 		break;
 	case DRM_MODE_DPMS_SUSPEND:
-		temp |= ADPA_DAC_ENABLE | ADPA_VSYNC_CNTL_DISABLE;
+		adpa |= ADPA_DAC_ENABLE | ADPA_VSYNC_CNTL_DISABLE;
 		break;
 	case DRM_MODE_DPMS_OFF:
-		temp |= ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE;
+		adpa |= ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE;
 		break;
 	}
 
-	I915_WRITE(crt->adpa_reg, temp);
+	I915_WRITE(crt->adpa_reg, adpa);
 }
 
 static void intel_disable_crt(struct intel_encoder *encoder)
@@ -274,42 +295,6 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_crt_mode_set(struct intel_encoder *encoder)
-{
-
-	struct drm_device *dev = encoder->base.dev;
-	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
-	u32 adpa;
-
-	if (INTEL_INFO(dev)->gen >= 5)
-		adpa = ADPA_HOTPLUG_BITS;
-	else
-		adpa = 0;
-
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
-		adpa |= ADPA_HSYNC_ACTIVE_HIGH;
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
-		adpa |= ADPA_VSYNC_ACTIVE_HIGH;
-
-	/* For CPT allow 3 pipe config, for others just use A or B */
-	if (HAS_PCH_LPT(dev))
-		; /* Those bits don't exist here */
-	else if (HAS_PCH_CPT(dev))
-		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
-	else if (crtc->pipe == 0)
-		adpa |= ADPA_PIPE_A_SELECT;
-	else
-		adpa |= ADPA_PIPE_B_SELECT;
-
-	if (!HAS_PCH_SPLIT(dev))
-		I915_WRITE(BCLRPAT(crtc->pipe), 0);
-
-	I915_WRITE(crt->adpa_reg, adpa);
-}
-
 static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
@@ -867,7 +852,6 @@ void intel_crt_init(struct drm_device *dev)
 		crt->adpa_reg = ADPA;
 
 	crt->base.compute_config = intel_crt_compute_config;
-	crt->base.mode_set = intel_crt_mode_set;
 	crt->base.disable = intel_disable_crt;
 	crt->base.enable = intel_enable_crt;
 	if (I915_HAS_HOTPLUG(dev))
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b39d0367dd68..72b5c34d8ce7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1880,14 +1880,14 @@ static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv,
 	/* If the pipe isn't enabled, we can't pump pixels and may hang */
 	assert_pipe_enabled(dev_priv, pipe);
 
-	WARN(intel_crtc->primary_enabled, "Primary plane already enabled\n");
+	if (intel_crtc->primary_enabled)
+		return;
 
 	intel_crtc->primary_enabled = true;
 
 	reg = DSPCNTR(plane);
 	val = I915_READ(reg);
-	if (val & DISPLAY_PLANE_ENABLE)
-		return;
+	WARN_ON(val & DISPLAY_PLANE_ENABLE);
 
 	I915_WRITE(reg, val | DISPLAY_PLANE_ENABLE);
 	intel_flush_primary_plane(dev_priv, plane);
@@ -1910,14 +1910,14 @@ static void intel_disable_primary_hw_plane(struct drm_i915_private *dev_priv,
 	int reg;
 	u32 val;
 
-	WARN(!intel_crtc->primary_enabled, "Primary plane already disabled\n");
+	if (!intel_crtc->primary_enabled)
+		return;
 
 	intel_crtc->primary_enabled = false;
 
 	reg = DSPCNTR(plane);
 	val = I915_READ(reg);
-	if ((val & DISPLAY_PLANE_ENABLE) == 0)
-		return;
+	WARN_ON((val & DISPLAY_PLANE_ENABLE) == 0);
 
 	I915_WRITE(reg, val & ~DISPLAY_PLANE_ENABLE);
 	intel_flush_primary_plane(dev_priv, plane);
@@ -2599,12 +2599,10 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 	u32 reg, temp, tries;
 
-	/* FDI needs bits from pipe & plane first */
+	/* FDI needs bits from pipe first */
 	assert_pipe_enabled(dev_priv, pipe);
-	assert_plane_enabled(dev_priv, plane);
 
 	/* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit
 	   for train result */
@@ -7036,7 +7034,6 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv)
 	}
 
 	lpt_disable_clkout_dp(dev);
-	intel_runtime_pm_disable_interrupts(dev);
 	hsw_disable_lcpll(dev_priv, true, true);
 }
 
@@ -7048,7 +7045,6 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 	DRM_DEBUG_KMS("Disabling package C8+\n");
 
 	hsw_restore_lcpll(dev_priv);
-	intel_runtime_pm_restore_interrupts(dev);
 	lpt_init_pch_refclk(dev);
 
 	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
@@ -7058,10 +7054,6 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 	}
 
 	intel_prepare_ddi(dev);
-	i915_gem_init_swizzling(dev);
-	mutex_lock(&dev_priv->rps.hw_lock);
-	gen6_update_ring_freq(dev);
-	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 static void snb_modeset_global_resources(struct drm_device *dev)
@@ -7216,7 +7208,9 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc,
 			encoder->base.base.id,
 			drm_get_encoder_name(&encoder->base),
 			mode->base.id, mode->name);
-		encoder->mode_set(encoder);
+
+		if (encoder->mode_set)
+			encoder->mode_set(encoder);
 	}
 
 	return 0;
@@ -10570,6 +10564,8 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 		intel_crtc->plane = !pipe;
 	}
 
+	init_waitqueue_head(&intel_crtc->vbl_wait);
+
 	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
 	       dev_priv->plane_to_crtc_mapping[intel_crtc->plane] != NULL);
 	dev_priv->plane_to_crtc_mapping[intel_crtc->plane] = &intel_crtc->base;
@@ -11258,9 +11254,7 @@ void intel_modeset_init_hw(struct drm_device *dev)
 
 	intel_reset_dpio(dev);
 
-	mutex_lock(&dev->struct_mutex);
 	intel_enable_gt_powersave(dev);
-	mutex_unlock(&dev->struct_mutex);
 }
 
 void intel_modeset_suspend_hw(struct drm_device *dev)
@@ -11589,6 +11583,16 @@ void i915_redisable_vga(struct drm_device *dev)
 	i915_redisable_vga_power_on(dev);
 }
 
+static bool primary_get_hw_state(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+
+	if (!crtc->active)
+		return false;
+
+	return I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE;
+}
+
 static void intel_modeset_readout_hw_state(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -11608,7 +11612,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 								 &crtc->config);
 
 		crtc->base.enabled = crtc->active;
-		crtc->primary_enabled = crtc->active;
+		crtc->primary_enabled = primary_get_hw_state(crtc);
 
 		DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n",
 			      crtc->base.base.id,
@@ -11911,6 +11915,7 @@ struct intel_display_error_state {
 	struct intel_pipe_error_state {
 		bool power_domain_on;
 		u32 source;
+		u32 stat;
 	} pipe[I915_MAX_PIPES];
 
 	struct intel_plane_error_state {
@@ -11992,6 +11997,9 @@ intel_display_capture_error_state(struct drm_device *dev)
 		}
 
 		error->pipe[i].source = I915_READ(PIPESRC(i));
+
+		if (!HAS_PCH_SPLIT(dev))
+			error->pipe[i].stat = I915_READ(PIPESTAT(i));
 	}
 
 	error->num_transcoders = INTEL_INFO(dev)->num_pipes;
@@ -12042,6 +12050,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  Power: %s\n",
 			   error->pipe[i].power_domain_on ? "on" : "off");
 		err_printf(m, "  SRC: %08x\n", error->pipe[i].source);
+		err_printf(m, "  STAT: %08x\n", error->pipe[i].stat);
 
 		err_printf(m, "Plane [%d]:\n", i);
 		err_printf(m, "  CNTR: %08x\n", error->plane[i].control);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 44df493ad399..34ed143ab479 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -313,8 +313,12 @@ static bool edp_have_panel_vdd(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
+	enum intel_display_power_domain power_domain;
 
-	return !dev_priv->pm.suspended &&
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	return intel_display_power_enabled(dev_priv, power_domain) &&
 	       (I915_READ(_pp_ctrl_reg(intel_dp)) & EDP_FORCE_VDD) != 0;
 }
 
@@ -2779,9 +2783,6 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 	}
 	POSTING_READ(intel_dp->output_reg);
 
-	/* We don't really know why we're doing this */
-	intel_wait_for_vblank(dev, intel_crtc->pipe);
-
 	if (HAS_PCH_IBX(dev) &&
 	    I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
 		struct drm_crtc *crtc = intel_dig_port->base.base.crtc;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b885df150910..d8b540b891d1 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -401,6 +401,8 @@ struct intel_crtc {
 		/* watermarks currently being used  */
 		struct intel_pipe_wm active;
 	} wm;
+
+	wait_queue_head_t vbl_wait;
 };
 
 struct intel_plane_wm_parameters {
@@ -653,6 +655,7 @@ void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void intel_runtime_pm_disable_interrupts(struct drm_device *dev);
 void intel_runtime_pm_restore_interrupts(struct drm_device *dev);
+int intel_get_crtc_scanline(struct intel_crtc *crtc);
 
 
 /* intel_crt.c */
@@ -925,6 +928,7 @@ void intel_init_gt_powersave(struct drm_device *dev);
 void intel_cleanup_gt_powersave(struct drm_device *dev);
 void intel_enable_gt_powersave(struct drm_device *dev);
 void intel_disable_gt_powersave(struct drm_device *dev);
+void intel_reset_gt_powersave(struct drm_device *dev);
 void ironlake_teardown_rc6(struct drm_device *dev);
 void gen6_update_ring_freq(struct drm_device *dev);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);
@@ -932,6 +936,7 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv);
 void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
 void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
 void intel_init_runtime_pm(struct drm_i915_private *dev_priv);
 void intel_fini_runtime_pm(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 7fe3feedfe03..1604235d58e6 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -285,7 +285,7 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_dvo_mode_set(struct intel_encoder *encoder)
+static void intel_dvo_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -475,7 +475,7 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_encoder->get_hw_state = intel_dvo_get_hw_state;
 	intel_encoder->get_config = intel_dvo_get_config;
 	intel_encoder->compute_config = intel_dvo_compute_config;
-	intel_encoder->mode_set = intel_dvo_mode_set;
+	intel_encoder->pre_enable = intel_dvo_pre_enable;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
 	intel_connector->unregister = intel_connector_unregister;
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75c1c766b507..834c49c2beb7 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1931,6 +1931,16 @@ static void ilk_compute_wm_maximums(const struct drm_device *dev,
 	max->fbc = ilk_fbc_wm_reg_max(dev);
 }
 
+static void ilk_compute_wm_reg_maximums(struct drm_device *dev,
+					int level,
+					struct ilk_wm_maximums *max)
+{
+	max->pri = ilk_plane_wm_reg_max(dev, level, false);
+	max->spr = ilk_plane_wm_reg_max(dev, level, true);
+	max->cur = ilk_cursor_wm_reg_max(dev, level);
+	max->fbc = ilk_fbc_wm_reg_max(dev);
+}
+
 static bool ilk_validate_wm_level(int level,
 				  const struct ilk_wm_maximums *max,
 				  struct intel_wm_level *result)
@@ -2188,9 +2198,6 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc,
 	};
 	struct ilk_wm_maximums max;
 
-	/* LP0 watermarks always use 1/2 DDB partitioning */
-	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
-
 	pipe_wm->pipe_enabled = params->active;
 	pipe_wm->sprites_enabled = params->spr.enabled;
 	pipe_wm->sprites_scaled = params->spr.scaled;
@@ -2203,15 +2210,37 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc,
 	if (params->spr.scaled)
 		max_level = 0;
 
-	for (level = 0; level <= max_level; level++)
-		ilk_compute_wm_level(dev_priv, level, params,
-				     &pipe_wm->wm[level]);
+	ilk_compute_wm_level(dev_priv, 0, params, &pipe_wm->wm[0]);
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc);
 
+	/* LP0 watermarks always use 1/2 DDB partitioning */
+	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
+
 	/* At least LP0 must be valid */
-	return ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]);
+	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]))
+		return false;
+
+	ilk_compute_wm_reg_maximums(dev, 1, &max);
+
+	for (level = 1; level <= max_level; level++) {
+		struct intel_wm_level wm = {};
+
+		ilk_compute_wm_level(dev_priv, level, params, &wm);
+
+		/*
+		 * Disable any watermark level that exceeds the
+		 * register maximums since such watermarks are
+		 * always invalid.
+		 */
+		if (!ilk_validate_wm_level(level, &max, &wm))
+			break;
+
+		pipe_wm->wm[level] = wm;
+	}
+
+	return true;
 }
 
 /*
@@ -2223,6 +2252,8 @@ static void ilk_merge_wm_level(struct drm_device *dev,
 {
 	const struct intel_crtc *intel_crtc;
 
+	ret_wm->enable = true;
+
 	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) {
 		const struct intel_pipe_wm *active = &intel_crtc->wm.active;
 		const struct intel_wm_level *wm = &active->wm[level];
@@ -2230,16 +2261,19 @@ static void ilk_merge_wm_level(struct drm_device *dev,
 		if (!active->pipe_enabled)
 			continue;
 
+		/*
+		 * The watermark values may have been used in the past,
+		 * so we must maintain them in the registers for some
+		 * time even if the level is now disabled.
+		 */
 		if (!wm->enable)
-			return;
+			ret_wm->enable = false;
 
 		ret_wm->pri_val = max(ret_wm->pri_val, wm->pri_val);
 		ret_wm->spr_val = max(ret_wm->spr_val, wm->spr_val);
 		ret_wm->cur_val = max(ret_wm->cur_val, wm->cur_val);
 		ret_wm->fbc_val = max(ret_wm->fbc_val, wm->fbc_val);
 	}
-
-	ret_wm->enable = true;
 }
 
 /*
@@ -2251,6 +2285,7 @@ static void ilk_wm_merge(struct drm_device *dev,
 			 struct intel_pipe_wm *merged)
 {
 	int level, max_level = ilk_wm_max_level(dev);
+	int last_enabled_level = max_level;
 
 	/* ILK/SNB/IVB: LP1+ watermarks only w/ single pipe */
 	if ((INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev)) &&
@@ -2266,15 +2301,19 @@ static void ilk_wm_merge(struct drm_device *dev,
 
 		ilk_merge_wm_level(dev, level, wm);
 
-		if (!ilk_validate_wm_level(level, max, wm))
-			break;
+		if (level > last_enabled_level)
+			wm->enable = false;
+		else if (!ilk_validate_wm_level(level, max, wm))
+			/* make sure all following levels get disabled */
+			last_enabled_level = level - 1;
 
 		/*
 		 * The spec says it is preferred to disable
 		 * FBC WMs instead of disabling a WM level.
 		 */
 		if (wm->fbc_val > max->fbc) {
-			merged->fbc_wm_enabled = false;
+			if (wm->enable)
+				merged->fbc_wm_enabled = false;
 			wm->fbc_val = 0;
 		}
 	}
@@ -2329,14 +2368,19 @@ static void ilk_compute_wm_results(struct drm_device *dev,
 		level = ilk_wm_lp_to_level(wm_lp, merged);
 
 		r = &merged->wm[level];
-		if (!r->enable)
-			break;
 
-		results->wm_lp[wm_lp - 1] = WM3_LP_EN |
+		/*
+		 * Maintain the watermark values even if the level is
+		 * disabled. Doing otherwise could cause underruns.
+		 */
+		results->wm_lp[wm_lp - 1] =
 			(ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) |
 			(r->pri_val << WM1_LP_SR_SHIFT) |
 			r->cur_val;
 
+		if (r->enable)
+			results->wm_lp[wm_lp - 1] |= WM1_LP_SR_EN;
+
 		if (INTEL_INFO(dev)->gen >= 8)
 			results->wm_lp[wm_lp - 1] |=
 				r->fbc_val << WM1_LP_FBC_SHIFT_BDW;
@@ -2344,6 +2388,10 @@ static void ilk_compute_wm_results(struct drm_device *dev,
 			results->wm_lp[wm_lp - 1] |=
 				r->fbc_val << WM1_LP_FBC_SHIFT;
 
+		/*
+		 * Always set WM1S_LP_EN when spr_val != 0, even if the
+		 * level is disabled. Doing otherwise could cause underruns.
+		 */
 		if (INTEL_INFO(dev)->gen <= 6 && r->spr_val) {
 			WARN_ON(wm_lp != 1);
 			results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val;
@@ -3129,16 +3177,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 	/* Mask turbo interrupt so that they will not come in between */
 	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 
-	/* Bring up the Gfx clock */
-	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG,
-		I915_READ(VLV_GTLC_SURVIVABILITY_REG) |
-				VLV_GFX_CLK_FORCE_ON_BIT);
-
-	if (wait_for(((VLV_GFX_CLK_STATUS_BIT &
-		I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 5)) {
-			DRM_ERROR("GFX_CLK_ON request timed out\n");
-		return;
-	}
+	vlv_force_gfx_clock(dev_priv, true);
 
 	dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit;
 
@@ -3149,10 +3188,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 				& GENFREQSTATUS) == 0, 5))
 		DRM_ERROR("timed out waiting for Punit\n");
 
-	/* Release the Gfx clock */
-	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG,
-		I915_READ(VLV_GTLC_SURVIVABILITY_REG) &
-				~VLV_GFX_CLK_FORCE_ON_BIT);
+	vlv_force_gfx_clock(dev_priv, false);
 
 	I915_WRITE(GEN6_PMINTRMSK,
 		   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
@@ -3250,21 +3286,48 @@ static void valleyview_disable_rps(struct drm_device *dev)
 
 static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
 {
+	if (IS_VALLEYVIEW(dev)) {
+		if (mode & (GEN7_RC_CTL_TO_MODE | GEN6_RC_CTL_EI_MODE(1)))
+			mode = GEN6_RC_CTL_RC6_ENABLE;
+		else
+			mode = 0;
+	}
 	DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n",
 		 (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
 		 (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
 		 (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
 }
 
-int intel_enable_rc6(const struct drm_device *dev)
+static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
 {
 	/* No RC6 before Ironlake */
 	if (INTEL_INFO(dev)->gen < 5)
 		return 0;
 
+	/* RC6 is only on Ironlake mobile not on desktop */
+	if (INTEL_INFO(dev)->gen == 5 && !IS_IRONLAKE_M(dev))
+		return 0;
+
+	/* Disable RC6 on Broadwell for now */
+	if (IS_BROADWELL(dev))
+		return 0;
+
 	/* Respect the kernel parameter if it is set */
-	if (i915.enable_rc6 >= 0)
-		return i915.enable_rc6;
+	if (enable_rc6 >= 0) {
+		int mask;
+
+		if (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev))
+			mask = INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE |
+			       INTEL_RC6pp_ENABLE;
+		else
+			mask = INTEL_RC6_ENABLE;
+
+		if ((enable_rc6 & mask) != enable_rc6)
+			DRM_INFO("Adjusting RC6 mask to %d (requested %d, valid %d)\n",
+				 enable_rc6, enable_rc6 & mask, mask);
+
+		return enable_rc6 & mask;
+	}
 
 	/* Disable RC6 on Ironlake */
 	if (INTEL_INFO(dev)->gen == 5)
@@ -3276,6 +3339,11 @@ int intel_enable_rc6(const struct drm_device *dev)
 	return INTEL_RC6_ENABLE;
 }
 
+int intel_enable_rc6(const struct drm_device *dev)
+{
+	return i915.enable_rc6;
+}
+
 static void gen6_enable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3497,7 +3565,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-void gen6_update_ring_freq(struct drm_device *dev)
+static void __gen6_update_ring_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
@@ -3567,6 +3635,18 @@ void gen6_update_ring_freq(struct drm_device *dev)
 	}
 }
 
+void gen6_update_ring_freq(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (INTEL_INFO(dev)->gen < 6 || IS_VALLEYVIEW(dev))
+		return;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+	__gen6_update_ring_freq(dev);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
 int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
@@ -3661,6 +3741,45 @@ static void valleyview_cleanup_pctx(struct drm_device *dev)
 	dev_priv->vlv_pctx = NULL;
 }
 
+static void valleyview_init_gt_powersave(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	valleyview_setup_pctx(dev);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv);
+	dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
+	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
+			 dev_priv->rps.max_freq);
+
+	dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv);
+	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
+
+	dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv);
+	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
+			 dev_priv->rps.min_freq);
+
+	/* Preserve min/max settings in case of re-init */
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
+
+	if (dev_priv->rps.min_freq_softlimit == 0)
+		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
+{
+	valleyview_cleanup_pctx(dev);
+}
+
 static void valleyview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3727,29 +3846,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
 			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
 			 dev_priv->rps.cur_freq);
 
-	dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv);
-	dev_priv->rps.rp0_freq  = dev_priv->rps.max_freq;
-	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
-			 dev_priv->rps.max_freq);
-
-	dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv);
-	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
-			 dev_priv->rps.efficient_freq);
-
-	dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv);
-	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
-			 dev_priv->rps.min_freq);
-
-	/* Preserve min/max settings in case of re-init */
-	if (dev_priv->rps.max_freq_softlimit == 0)
-		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
-
-	if (dev_priv->rps.min_freq_softlimit == 0)
-		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
-
 	DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
 			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
 			 dev_priv->rps.efficient_freq);
@@ -3876,7 +3972,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
 	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
 
-	intel_print_rc6_info(dev, INTEL_RC6_ENABLE);
+	intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
 }
 
 static unsigned long intel_pxfreq(u32 vidfreq)
@@ -4490,14 +4586,16 @@ static void intel_init_emon(struct drm_device *dev)
 
 void intel_init_gt_powersave(struct drm_device *dev)
 {
+	i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
+
 	if (IS_VALLEYVIEW(dev))
-		valleyview_setup_pctx(dev);
+		valleyview_init_gt_powersave(dev);
 }
 
 void intel_cleanup_gt_powersave(struct drm_device *dev)
 {
 	if (IS_VALLEYVIEW(dev))
-		valleyview_cleanup_pctx(dev);
+		valleyview_cleanup_gt_powersave(dev);
 }
 
 void intel_disable_gt_powersave(struct drm_device *dev)
@@ -4510,7 +4608,7 @@ void intel_disable_gt_powersave(struct drm_device *dev)
 	if (IS_IRONLAKE_M(dev)) {
 		ironlake_disable_drps(dev);
 		ironlake_disable_rc6(dev);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
+	} else if (IS_GEN6(dev) || IS_GEN7(dev)) {
 		cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
 		cancel_work_sync(&dev_priv->rps.work);
 		mutex_lock(&dev_priv->rps.hw_lock);
@@ -4536,13 +4634,15 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 		valleyview_enable_rps(dev);
 	} else if (IS_BROADWELL(dev)) {
 		gen8_enable_rps(dev);
-		gen6_update_ring_freq(dev);
+		__gen6_update_ring_freq(dev);
 	} else {
 		gen6_enable_rps(dev);
-		gen6_update_ring_freq(dev);
+		__gen6_update_ring_freq(dev);
 	}
 	dev_priv->rps.enabled = true;
 	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 void intel_enable_gt_powersave(struct drm_device *dev)
@@ -4550,20 +4650,38 @@ void intel_enable_gt_powersave(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (IS_IRONLAKE_M(dev)) {
+		mutex_lock(&dev->struct_mutex);
 		ironlake_enable_drps(dev);
 		ironlake_enable_rc6(dev);
 		intel_init_emon(dev);
+		mutex_unlock(&dev->struct_mutex);
 	} else if (IS_GEN6(dev) || IS_GEN7(dev)) {
 		/*
 		 * PCU communication is slow and this doesn't need to be
 		 * done at any specific time, so do this out of our fast path
 		 * to make resume and init faster.
+		 *
+		 * We depend on the HW RC6 power context save/restore
+		 * mechanism when entering D3 through runtime PM suspend. So
+		 * disable RPM until RPS/RC6 is properly setup. We can only
+		 * get here via the driver load/system resume/runtime resume
+		 * paths, so the _noresume version is enough (and in case of
+		 * runtime resume it's necessary).
 		 */
-		schedule_delayed_work(&dev_priv->rps.delayed_resume_work,
-				      round_jiffies_up_relative(HZ));
+		if (schedule_delayed_work(&dev_priv->rps.delayed_resume_work,
+					   round_jiffies_up_relative(HZ)))
+			intel_runtime_pm_get_noresume(dev_priv);
 	}
 }
 
+void intel_reset_gt_powersave(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	dev_priv->rps.enabled = false;
+	intel_enable_gt_powersave(dev);
+}
+
 static void ibx_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4918,6 +5036,10 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
 		   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
 
+	/* WaDisableDopClockGating:bdw May not be needed for production */
+	I915_WRITE(GEN7_ROW_CHICKEN2,
+		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+
 	/* WaSwitchSolVfFArbitrationPriority:bdw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -5622,11 +5744,13 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv,
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	/*
-	 * During driver initialization we need to defer enabling hotplug
-	 * processing until fbdev is set up.
+	 * During driver initialization/resume we can avoid restoring the
+	 * part of the HW/SW state that will be inited anyway explicitly.
 	 */
-	if (dev_priv->enable_hotplug_processing)
-		intel_hpd_init(dev_priv->dev);
+	if (dev_priv->power_domains.initializing)
+		return;
+
+	intel_hpd_init(dev_priv->dev);
 
 	i915_redisable_vga_power_on(dev_priv->dev);
 }
@@ -5990,9 +6114,13 @@ static void intel_power_domains_resume(struct drm_i915_private *dev_priv)
 
 void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+
+	power_domains->initializing = true;
 	/* For now, we need the power well to be always enabled. */
 	intel_display_set_init_power(dev_priv, true);
 	intel_power_domains_resume(dev_priv);
+	power_domains->initializing = false;
 }
 
 void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
@@ -6017,6 +6145,18 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
 	WARN(dev_priv->pm.suspended, "Device still suspended.\n");
 }
 
+void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	if (!HAS_RUNTIME_PM(dev))
+		return;
+
+	WARN(dev_priv->pm.suspended, "Getting nosync-ref while suspended.\n");
+	pm_runtime_get_noresume(device);
+}
+
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -6039,6 +6179,15 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv)
 
 	pm_runtime_set_active(device);
 
+	/*
+	 * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
+	 * requirement.
+	 */
+	if (!intel_enable_rc6(dev)) {
+		DRM_INFO("RC6 disabled, disabling runtime PM support\n");
+		return;
+	}
+
 	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
 	pm_runtime_mark_last_busy(device);
 	pm_runtime_use_autosuspend(device);
@@ -6054,6 +6203,9 @@ void intel_fini_runtime_pm(struct drm_i915_private *dev_priv)
 	if (!HAS_RUNTIME_PM(dev))
 		return;
 
+	if (!intel_enable_rc6(dev))
+		return;
+
 	/* Make sure we're not suspended first. */
 	pm_runtime_get_sync(device);
 	pm_runtime_disable(device);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index eb3dd26b94de..40a7aa4db589 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -33,6 +33,13 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
+ * but keeps the logic simple. Indeed, the whole purpose of this macro is just
+ * to give some inclination as to some of the magic values used in the various
+ * workarounds!
+ */
+#define CACHELINE_BYTES 64
+
 static inline int ring_space(struct intel_ring_buffer *ring)
 {
 	int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE);
@@ -179,7 +186,7 @@ gen4_render_ring_flush(struct intel_ring_buffer *ring,
 static int
 intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
 {
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 
@@ -216,7 +223,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
                          u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	/* Force SNB workarounds for PIPE_CONTROL flushes */
@@ -310,7 +317,7 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 		       u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	/*
@@ -371,7 +378,7 @@ gen8_render_ring_flush(struct intel_ring_buffer *ring,
 		       u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	flags |= PIPE_CONTROL_CS_STALL;
@@ -516,12 +523,11 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		     I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) &&
 		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
-				"ctl %08x head %08x tail %08x start %08x\n",
-				ring->name,
-				I915_READ_CTL(ring),
-				I915_READ_HEAD(ring),
-				I915_READ_TAIL(ring),
-				I915_READ_START(ring));
+			  "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08lx]\n",
+			  ring->name,
+			  I915_READ_CTL(ring), I915_READ_CTL(ring) & RING_VALID,
+			  I915_READ_HEAD(ring), I915_READ_TAIL(ring),
+			  I915_READ_START(ring), (unsigned long)i915_gem_obj_ggtt_offset(obj));
 		ret = -EIO;
 		goto out;
 	}
@@ -657,20 +663,44 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 	ring->scratch.obj = NULL;
 }
 
-static void
-update_mboxes(struct intel_ring_buffer *ring,
-	      u32 mmio_offset)
+static int gen6_signal(struct intel_ring_buffer *signaller,
+		       unsigned int num_dwords)
 {
-/* NB: In order to be able to do semaphore MBOX updates for varying number
- * of rings, it's easiest if we round up each individual update to a
- * multiple of 2 (since ring updates must always be a multiple of 2)
- * even though the actual update only requires 3 dwords.
- */
+	struct drm_device *dev = signaller->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *useless;
+	int i, ret;
+
+	/* NB: In order to be able to do semaphore MBOX updates for varying
+	 * number of rings, it's easiest if we round up each individual update
+	 * to a multiple of 2 (since ring updates must always be a multiple of
+	 * 2) even though the actual update only requires 3 dwords.
+	 */
 #define MBOX_UPDATE_DWORDS 4
-	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, mmio_offset);
-	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
-	intel_ring_emit(ring, MI_NOOP);
+	if (i915_semaphore_is_enabled(dev))
+		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
+
+	ret = intel_ring_begin(signaller, num_dwords);
+	if (ret)
+		return ret;
+#undef MBOX_UPDATE_DWORDS
+
+	for_each_ring(useless, dev_priv, i) {
+		u32 mbox_reg = signaller->semaphore.mbox.signal[i];
+		if (mbox_reg != GEN6_NOSYNC) {
+			intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
+			intel_ring_emit(signaller, mbox_reg);
+			intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
+			intel_ring_emit(signaller, MI_NOOP);
+		} else {
+			intel_ring_emit(signaller, MI_NOOP);
+			intel_ring_emit(signaller, MI_NOOP);
+			intel_ring_emit(signaller, MI_NOOP);
+			intel_ring_emit(signaller, MI_NOOP);
+		}
+	}
+
+	return 0;
 }
 
 /**
@@ -685,27 +715,12 @@ update_mboxes(struct intel_ring_buffer *ring,
 static int
 gen6_add_request(struct intel_ring_buffer *ring)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *useless;
-	int i, ret, num_dwords = 4;
-
-	if (i915_semaphore_is_enabled(dev))
-		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
-#undef MBOX_UPDATE_DWORDS
+	int ret;
 
-	ret = intel_ring_begin(ring, num_dwords);
+	ret = ring->semaphore.signal(ring, 4);
 	if (ret)
 		return ret;
 
-	if (i915_semaphore_is_enabled(dev)) {
-		for_each_ring(useless, dev_priv, i) {
-			u32 mbox_reg = ring->signal_mbox[i];
-			if (mbox_reg != GEN6_NOSYNC)
-				update_mboxes(ring, mbox_reg);
-		}
-	}
-
 	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
 	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
@@ -734,10 +749,11 @@ gen6_ring_sync(struct intel_ring_buffer *waiter,
 	       struct intel_ring_buffer *signaller,
 	       u32 seqno)
 {
-	int ret;
 	u32 dw1 = MI_SEMAPHORE_MBOX |
 		  MI_SEMAPHORE_COMPARE |
 		  MI_SEMAPHORE_REGISTER;
+	u32 wait_mbox = signaller->semaphore.mbox.wait[waiter->id];
+	int ret;
 
 	/* Throughout all of the GEM code, seqno passed implies our current
 	 * seqno is >= the last seqno executed. However for hardware the
@@ -745,8 +761,7 @@ gen6_ring_sync(struct intel_ring_buffer *waiter,
 	 */
 	seqno -= 1;
 
-	WARN_ON(signaller->semaphore_register[waiter->id] ==
-		MI_SEMAPHORE_SYNC_INVALID);
+	WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID);
 
 	ret = intel_ring_begin(waiter, 4);
 	if (ret)
@@ -754,9 +769,7 @@ gen6_ring_sync(struct intel_ring_buffer *waiter,
 
 	/* If seqno wrap happened, omit the wait with no-ops */
 	if (likely(!i915_gem_has_seqno_wrapped(waiter->dev, seqno))) {
-		intel_ring_emit(waiter,
-				dw1 |
-				signaller->semaphore_register[waiter->id]);
+		intel_ring_emit(waiter, dw1 | wait_mbox);
 		intel_ring_emit(waiter, seqno);
 		intel_ring_emit(waiter, 0);
 		intel_ring_emit(waiter, MI_NOOP);
@@ -783,7 +796,7 @@ do {									\
 static int
 pc_render_add_request(struct intel_ring_buffer *ring)
 {
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	/* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently
@@ -805,15 +818,15 @@ pc_render_add_request(struct intel_ring_buffer *ring)
 	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
 	intel_ring_emit(ring, 0);
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128; /* write to separate cachelines */
+	scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
 
 	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
@@ -988,6 +1001,11 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 		case BCS:
 			mmio = BLT_HWS_PGA_GEN7;
 			break;
+		/*
+		 * VCS2 actually doesn't exist on Gen7. Only shut up
+		 * gcc switch check warning
+		 */
+		case VCS2:
 		case VCS:
 			mmio = BSD_HWS_PGA_GEN7;
 			break;
@@ -1192,7 +1210,7 @@ gen8_ring_put_irq(struct intel_ring_buffer *ring)
 
 static int
 i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			 u32 offset, u32 length,
+			 u64 offset, u32 length,
 			 unsigned flags)
 {
 	int ret;
@@ -1215,7 +1233,7 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
 #define I830_BATCH_LIMIT (256*1024)
 static int
 i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
-				u32 offset, u32 len,
+				u64 offset, u32 len,
 				unsigned flags)
 {
 	int ret;
@@ -1266,7 +1284,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 static int
 i915_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			 u32 offset, u32 len,
+			 u64 offset, u32 len,
 			 unsigned flags)
 {
 	int ret;
@@ -1298,45 +1316,39 @@ static void cleanup_status_page(struct intel_ring_buffer *ring)
 
 static int init_status_page(struct intel_ring_buffer *ring)
 {
-	struct drm_device *dev = ring->dev;
 	struct drm_i915_gem_object *obj;
-	int ret;
 
-	obj = i915_gem_alloc_object(dev, 4096);
-	if (obj == NULL) {
-		DRM_ERROR("Failed to allocate status page\n");
-		ret = -ENOMEM;
-		goto err;
-	}
+	if ((obj = ring->status_page.obj) == NULL) {
+		int ret;
 
-	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-	if (ret)
-		goto err_unref;
+		obj = i915_gem_alloc_object(ring->dev, 4096);
+		if (obj == NULL) {
+			DRM_ERROR("Failed to allocate status page\n");
+			return -ENOMEM;
+		}
 
-	ret = i915_gem_obj_ggtt_pin(obj, 4096, 0);
-	if (ret)
-		goto err_unref;
+		ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
+		if (ret)
+			goto err_unref;
+
+		ret = i915_gem_obj_ggtt_pin(obj, 4096, 0);
+		if (ret) {
+err_unref:
+			drm_gem_object_unreference(&obj->base);
+			return ret;
+		}
+
+		ring->status_page.obj = obj;
+	}
 
 	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
-	if (ring->status_page.page_addr == NULL) {
-		ret = -ENOMEM;
-		goto err_unpin;
-	}
-	ring->status_page.obj = obj;
 	memset(ring->status_page.page_addr, 0, PAGE_SIZE);
 
 	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
 			ring->name, ring->status_page.gfx_addr);
 
 	return 0;
-
-err_unpin:
-	i915_gem_object_ggtt_unpin(obj);
-err_unref:
-	drm_gem_object_unreference(&obj->base);
-err:
-	return ret;
 }
 
 static int init_phys_status_page(struct intel_ring_buffer *ring)
@@ -1356,44 +1368,23 @@ static int init_phys_status_page(struct intel_ring_buffer *ring)
 	return 0;
 }
 
-static int intel_init_ring_buffer(struct drm_device *dev,
-				  struct intel_ring_buffer *ring)
+static int allocate_ring_buffer(struct intel_ring_buffer *ring)
 {
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	ring->dev = dev;
-	INIT_LIST_HEAD(&ring->active_list);
-	INIT_LIST_HEAD(&ring->request_list);
-	ring->size = 32 * PAGE_SIZE;
-	memset(ring->sync_seqno, 0, sizeof(ring->sync_seqno));
-
-	init_waitqueue_head(&ring->irq_queue);
-
-	if (I915_NEED_GFX_HWS(dev)) {
-		ret = init_status_page(ring);
-		if (ret)
-			return ret;
-	} else {
-		BUG_ON(ring->id != RCS);
-		ret = init_phys_status_page(ring);
-		if (ret)
-			return ret;
-	}
+	if (ring->obj)
+		return 0;
 
 	obj = NULL;
 	if (!HAS_LLC(dev))
 		obj = i915_gem_object_create_stolen(dev, ring->size);
 	if (obj == NULL)
 		obj = i915_gem_alloc_object(dev, ring->size);
-	if (obj == NULL) {
-		DRM_ERROR("Failed to allocate ringbuffer\n");
-		ret = -ENOMEM;
-		goto err_hws;
-	}
-
-	ring->obj = obj;
+	if (obj == NULL)
+		return -ENOMEM;
 
 	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
 	if (ret)
@@ -1407,55 +1398,72 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   ring->size);
 	if (ring->virtual_start == NULL) {
-		DRM_ERROR("Failed to map ringbuffer.\n");
 		ret = -EINVAL;
 		goto err_unpin;
 	}
 
-	ret = ring->init(ring);
-	if (ret)
-		goto err_unmap;
+	ring->obj = obj;
+	return 0;
+
+err_unpin:
+	i915_gem_object_ggtt_unpin(obj);
+err_unref:
+	drm_gem_object_unreference(&obj->base);
+	return ret;
+}
+
+static int intel_init_ring_buffer(struct drm_device *dev,
+				  struct intel_ring_buffer *ring)
+{
+	int ret;
+
+	ring->dev = dev;
+	INIT_LIST_HEAD(&ring->active_list);
+	INIT_LIST_HEAD(&ring->request_list);
+	ring->size = 32 * PAGE_SIZE;
+	memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
+
+	init_waitqueue_head(&ring->irq_queue);
+
+	if (I915_NEED_GFX_HWS(dev)) {
+		ret = init_status_page(ring);
+		if (ret)
+			return ret;
+	} else {
+		BUG_ON(ring->id != RCS);
+		ret = init_phys_status_page(ring);
+		if (ret)
+			return ret;
+	}
+
+	ret = allocate_ring_buffer(ring);
+	if (ret) {
+		DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret);
+		return ret;
+	}
 
 	/* Workaround an erratum on the i830 which causes a hang if
 	 * the TAIL pointer points to within the last 2 cachelines
 	 * of the buffer.
 	 */
 	ring->effective_size = ring->size;
-	if (IS_I830(ring->dev) || IS_845G(ring->dev))
-		ring->effective_size -= 128;
+	if (IS_I830(dev) || IS_845G(dev))
+		ring->effective_size -= 2 * CACHELINE_BYTES;
 
 	i915_cmd_parser_init_ring(ring);
 
-	return 0;
-
-err_unmap:
-	iounmap(ring->virtual_start);
-err_unpin:
-	i915_gem_object_ggtt_unpin(obj);
-err_unref:
-	drm_gem_object_unreference(&obj->base);
-	ring->obj = NULL;
-err_hws:
-	cleanup_status_page(ring);
-	return ret;
+	return ring->init(ring);
 }
 
 void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring)
 {
-	struct drm_i915_private *dev_priv;
-	int ret;
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
 
 	if (ring->obj == NULL)
 		return;
 
-	/* Disable the ring buffer. The ring must be idle at this point */
-	dev_priv = ring->dev->dev_private;
-	ret = intel_ring_idle(ring);
-	if (ret && !i915_reset_in_progress(&dev_priv->gpu_error))
-		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
-			  ring->name, ret);
-
-	I915_WRITE_CTL(ring, 0);
+	intel_stop_ring_buffer(ring);
+	WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
 
 	iounmap(ring->virtual_start);
 
@@ -1683,12 +1691,13 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 /* Align the ring tail to a cacheline boundary */
 int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
 {
-	int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t);
+	int num_dwords = (ring->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t);
 	int ret;
 
 	if (num_dwords == 0)
 		return 0;
 
+	num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords;
 	ret = intel_ring_begin(ring, num_dwords);
 	if (ret)
 		return ret;
@@ -1788,7 +1797,7 @@ static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring,
 
 static int
 gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len,
+			      u64 offset, u32 len,
 			      unsigned flags)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -1802,8 +1811,8 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 	/* FIXME(BDW): Address space and security selectors. */
 	intel_ring_emit(ring, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8));
-	intel_ring_emit(ring, offset);
-	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, lower_32_bits(offset));
+	intel_ring_emit(ring, upper_32_bits(offset));
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
 
@@ -1812,7 +1821,7 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 static int
 hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len,
+			      u64 offset, u32 len,
 			      unsigned flags)
 {
 	int ret;
@@ -1833,7 +1842,7 @@ hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 static int
 gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len,
+			      u64 offset, u32 len,
 			      unsigned flags)
 {
 	int ret;
@@ -1919,15 +1928,24 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
-		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
-		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
-		ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_RVE;
-		ring->signal_mbox[RCS] = GEN6_NOSYNC;
-		ring->signal_mbox[VCS] = GEN6_VRSYNC;
-		ring->signal_mbox[BCS] = GEN6_BRSYNC;
-		ring->signal_mbox[VECS] = GEN6_VERSYNC;
+		ring->semaphore.sync_to = gen6_ring_sync;
+		ring->semaphore.signal = gen6_signal;
+		/*
+		 * The current semaphore is only applied on pre-gen8 platform.
+		 * And there is no VCS2 ring on the pre-gen8 platform. So the
+		 * semaphore between RCS and VCS2 is initialized as INVALID.
+		 * Gen8 will initialize the sema between VCS2 and RCS later.
+		 */
+		ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_RV;
+		ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_RB;
+		ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_RVE;
+		ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.signal[RCS] = GEN6_NOSYNC;
+		ring->semaphore.mbox.signal[VCS] = GEN6_VRSYNC;
+		ring->semaphore.mbox.signal[BCS] = GEN6_BRSYNC;
+		ring->semaphore.mbox.signal[VECS] = GEN6_VERSYNC;
+		ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
@@ -2045,7 +2063,7 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	ring->size = size;
 	ring->effective_size = ring->size;
 	if (IS_I830(ring->dev) || IS_845G(ring->dev))
-		ring->effective_size -= 128;
+		ring->effective_size -= 2 * CACHELINE_BYTES;
 
 	ring->virtual_start = ioremap_wc(start, size);
 	if (ring->virtual_start == NULL) {
@@ -2095,15 +2113,24 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 			ring->dispatch_execbuffer =
 				gen6_ring_dispatch_execbuffer;
 		}
-		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
-		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
-		ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_VVE;
-		ring->signal_mbox[RCS] = GEN6_RVSYNC;
-		ring->signal_mbox[VCS] = GEN6_NOSYNC;
-		ring->signal_mbox[BCS] = GEN6_BVSYNC;
-		ring->signal_mbox[VECS] = GEN6_VEVSYNC;
+		ring->semaphore.sync_to = gen6_ring_sync;
+		ring->semaphore.signal = gen6_signal;
+		/*
+		 * The current semaphore is only applied on pre-gen8 platform.
+		 * And there is no VCS2 ring on the pre-gen8 platform. So the
+		 * semaphore between VCS and VCS2 is initialized as INVALID.
+		 * Gen8 will initialize the sema between VCS2 and VCS later.
+		 */
+		ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VR;
+		ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VB;
+		ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_VVE;
+		ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.signal[RCS] = GEN6_RVSYNC;
+		ring->semaphore.mbox.signal[VCS] = GEN6_NOSYNC;
+		ring->semaphore.mbox.signal[BCS] = GEN6_BVSYNC;
+		ring->semaphore.mbox.signal[VECS] = GEN6_VEVSYNC;
+		ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	} else {
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
@@ -2126,6 +2153,58 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 	return intel_init_ring_buffer(dev, ring);
 }
 
+/**
+ * Initialize the second BSD ring for Broadwell GT3.
+ * It is noted that this only exists on Broadwell GT3.
+ */
+int intel_init_bsd2_ring_buffer(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring = &dev_priv->ring[VCS2];
+
+	if ((INTEL_INFO(dev)->gen != 8)) {
+		DRM_ERROR("No dual-BSD ring on non-BDW machine\n");
+		return -EINVAL;
+	}
+
+	ring->name = "bds2_ring";
+	ring->id = VCS2;
+
+	ring->write_tail = ring_write_tail;
+	ring->mmio_base = GEN8_BSD2_RING_BASE;
+	ring->flush = gen6_bsd_ring_flush;
+	ring->add_request = gen6_add_request;
+	ring->get_seqno = gen6_ring_get_seqno;
+	ring->set_seqno = ring_set_seqno;
+	ring->irq_enable_mask =
+			GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
+	ring->irq_get = gen8_ring_get_irq;
+	ring->irq_put = gen8_ring_put_irq;
+	ring->dispatch_execbuffer =
+			gen8_ring_dispatch_execbuffer;
+	ring->semaphore.sync_to = gen6_ring_sync;
+	/*
+	 * The current semaphore is only applied on the pre-gen8. And there
+	 * is no bsd2 ring on the pre-gen8. So now the semaphore_register
+	 * between VCS2 and other ring is initialized as invalid.
+	 * Gen8 will initialize the sema between VCS2 and other ring later.
+	 */
+	ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.signal[RCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[BCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VECS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
+
+	ring->init = init_ring_common;
+
+	return intel_init_ring_buffer(dev, ring);
+}
+
 int intel_init_blt_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2152,15 +2231,24 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 		ring->irq_put = gen6_ring_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	}
-	ring->sync_to = gen6_ring_sync;
-	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
-	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
-	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_BVE;
-	ring->signal_mbox[RCS] = GEN6_RBSYNC;
-	ring->signal_mbox[VCS] = GEN6_VBSYNC;
-	ring->signal_mbox[BCS] = GEN6_NOSYNC;
-	ring->signal_mbox[VECS] = GEN6_VEBSYNC;
+	ring->semaphore.sync_to = gen6_ring_sync;
+	ring->semaphore.signal = gen6_signal;
+	/*
+	 * The current semaphore is only applied on pre-gen8 platform. And
+	 * there is no VCS2 ring on the pre-gen8 platform. So the semaphore
+	 * between BCS and VCS2 is initialized as INVALID.
+	 * Gen8 will initialize the sema between BCS and VCS2 later.
+	 */
+	ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_BR;
+	ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_BV;
+	ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_BVE;
+	ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.signal[RCS] = GEN6_RBSYNC;
+	ring->semaphore.mbox.signal[VCS] = GEN6_VBSYNC;
+	ring->semaphore.mbox.signal[BCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VECS] = GEN6_VEBSYNC;
+	ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
@@ -2193,15 +2281,18 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 		ring->irq_put = hsw_vebox_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	}
-	ring->sync_to = gen6_ring_sync;
-	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VER;
-	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_VEV;
-	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VEB;
-	ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->signal_mbox[RCS] = GEN6_RVESYNC;
-	ring->signal_mbox[VCS] = GEN6_VVESYNC;
-	ring->signal_mbox[BCS] = GEN6_BVESYNC;
-	ring->signal_mbox[VECS] = GEN6_NOSYNC;
+	ring->semaphore.sync_to = gen6_ring_sync;
+	ring->semaphore.signal = gen6_signal;
+	ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VER;
+	ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_VEV;
+	ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VEB;
+	ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.signal[RCS] = GEN6_RVESYNC;
+	ring->semaphore.mbox.signal[VCS] = GEN6_VVESYNC;
+	ring->semaphore.mbox.signal[BCS] = GEN6_BVESYNC;
+	ring->semaphore.mbox.signal[VECS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
@@ -2244,3 +2335,19 @@ intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring)
 	ring->gpu_caches_dirty = false;
 	return 0;
 }
+
+void
+intel_stop_ring_buffer(struct intel_ring_buffer *ring)
+{
+	int ret;
+
+	if (!intel_ring_initialized(ring))
+		return;
+
+	ret = intel_ring_idle(ring);
+	if (ret && !i915_reset_in_progress(&to_i915(ring->dev)->gpu_error))
+		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
+			  ring->name, ret);
+
+	stop_ring(ring);
+}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 413cdc74ed53..72c3c15f6240 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -61,8 +61,10 @@ struct  intel_ring_buffer {
 		VCS,
 		BCS,
 		VECS,
+		VCS2
 	} id;
-#define I915_NUM_RINGS 4
+#define I915_NUM_RINGS 5
+#define LAST_USER_RING (VECS + 1)
 	u32		mmio_base;
 	void		__iomem *virtual_start;
 	struct		drm_device *dev;
@@ -88,7 +90,6 @@ struct  intel_ring_buffer {
 	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
 	u32		trace_irq_seqno;
-	u32		sync_seqno[I915_NUM_RINGS-1];
 	bool __must_check (*irq_get)(struct intel_ring_buffer *ring);
 	void		(*irq_put)(struct intel_ring_buffer *ring);
 
@@ -111,19 +112,30 @@ struct  intel_ring_buffer {
 	void		(*set_seqno)(struct intel_ring_buffer *ring,
 				     u32 seqno);
 	int		(*dispatch_execbuffer)(struct intel_ring_buffer *ring,
-					       u32 offset, u32 length,
+					       u64 offset, u32 length,
 					       unsigned flags);
 #define I915_DISPATCH_SECURE 0x1
 #define I915_DISPATCH_PINNED 0x2
 	void		(*cleanup)(struct intel_ring_buffer *ring);
-	int		(*sync_to)(struct intel_ring_buffer *ring,
+
+	struct {
+		u32	sync_seqno[I915_NUM_RINGS-1];
+
+		struct {
+			/* our mbox written by others */
+			u32		wait[I915_NUM_RINGS];
+			/* mboxes this ring signals to */
+			u32		signal[I915_NUM_RINGS];
+		} mbox;
+
+		/* AKA wait() */
+		int	(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,
 				   u32 seqno);
-
-	/* our mbox written by others */
-	u32		semaphore_register[I915_NUM_RINGS];
-	/* mboxes this ring signals to */
-	u32		signal_mbox[I915_NUM_RINGS];
+		int	(*signal)(struct intel_ring_buffer *signaller,
+				  /* num_dwords needed by caller */
+				  unsigned int num_dwords);
+	} semaphore;
 
 	/**
 	 * List of objects currently involved in rendering from the
@@ -263,6 +275,7 @@ intel_write_status_page(struct intel_ring_buffer *ring,
 #define I915_GEM_HWS_SCRATCH_INDEX	0x30
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
+void intel_stop_ring_buffer(struct intel_ring_buffer *ring);
 void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
 
 int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
@@ -286,6 +299,7 @@ int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring);
 
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
+int intel_init_bsd2_ring_buffer(struct drm_device *dev);
 int intel_init_blt_ring_buffer(struct drm_device *dev);
 int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 46be00d66df3..2bf09e8eb5ed 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1174,7 +1174,7 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
+static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2999,7 +2999,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 
 	intel_encoder->compute_config = intel_sdvo_compute_config;
 	intel_encoder->disable = intel_disable_sdvo;
-	intel_encoder->mode_set = intel_sdvo_mode_set;
+	intel_encoder->pre_enable = intel_sdvo_pre_enable;
 	intel_encoder->enable = intel_enable_sdvo;
 	intel_encoder->get_hw_state = intel_sdvo_get_hw_state;
 	intel_encoder->get_config = intel_sdvo_get_config;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 336ae6c602f2..213cd58f0412 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -37,6 +37,106 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
+static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs)
+{
+	/* paranoia */
+	if (!mode->crtc_htotal)
+		return 1;
+
+	return DIV_ROUND_UP(usecs * mode->crtc_clock, 1000 * mode->crtc_htotal);
+}
+
+static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count)
+{
+	struct drm_device *dev = crtc->base.dev;
+	const struct drm_display_mode *mode = &crtc->config.adjusted_mode;
+	enum pipe pipe = crtc->pipe;
+	long timeout = msecs_to_jiffies_timeout(1);
+	int scanline, min, max, vblank_start;
+	DEFINE_WAIT(wait);
+
+	WARN_ON(!mutex_is_locked(&crtc->base.mutex));
+
+	vblank_start = mode->crtc_vblank_start;
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		vblank_start = DIV_ROUND_UP(vblank_start, 2);
+
+	/* FIXME needs to be calibrated sensibly */
+	min = vblank_start - usecs_to_scanlines(mode, 100);
+	max = vblank_start - 1;
+
+	if (min <= 0 || max <= 0)
+		return false;
+
+	if (WARN_ON(drm_vblank_get(dev, pipe)))
+		return false;
+
+	local_irq_disable();
+
+	trace_i915_pipe_update_start(crtc, min, max);
+
+	for (;;) {
+		/*
+		 * prepare_to_wait() has a memory barrier, which guarantees
+		 * other CPUs can see the task state update by the time we
+		 * read the scanline.
+		 */
+		prepare_to_wait(&crtc->vbl_wait, &wait, TASK_UNINTERRUPTIBLE);
+
+		scanline = intel_get_crtc_scanline(crtc);
+		if (scanline < min || scanline > max)
+			break;
+
+		if (timeout <= 0) {
+			DRM_ERROR("Potential atomic update failure on pipe %c\n",
+				  pipe_name(crtc->pipe));
+			break;
+		}
+
+		local_irq_enable();
+
+		timeout = schedule_timeout(timeout);
+
+		local_irq_disable();
+	}
+
+	finish_wait(&crtc->vbl_wait, &wait);
+
+	drm_vblank_put(dev, pipe);
+
+	*start_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+
+	trace_i915_pipe_update_vblank_evaded(crtc, min, max, *start_vbl_count);
+
+	return true;
+}
+
+static void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count)
+{
+	struct drm_device *dev = crtc->base.dev;
+	enum pipe pipe = crtc->pipe;
+	u32 end_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+
+	trace_i915_pipe_update_end(crtc, end_vbl_count);
+
+	local_irq_enable();
+
+	if (start_vbl_count != end_vbl_count)
+		DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n",
+			  pipe_name(pipe), start_vbl_count, end_vbl_count);
+}
+
+static void intel_update_primary_plane(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	int reg = DSPCNTR(crtc->plane);
+
+	if (crtc->primary_enabled)
+		I915_WRITE(reg, I915_READ(reg) | DISPLAY_PLANE_ENABLE);
+	else
+		I915_WRITE(reg, I915_READ(reg) & ~DISPLAY_PLANE_ENABLE);
+}
+
 static void
 vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
@@ -48,11 +148,14 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 	struct drm_device *dev = dplane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
 	u32 sprctl;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	u32 start_vbl_count;
+	bool atomic_update;
 
 	sprctl = I915_READ(SPCNTR(pipe, plane));
 
@@ -131,6 +234,10 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 							fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
+
 	I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]);
 	I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x);
 
@@ -143,7 +250,11 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
 	I915_WRITE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
 		   sprsurf_offset);
-	POSTING_READ(SPSURF(pipe, plane));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 }
 
 static void
@@ -152,14 +263,25 @@ vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 	struct drm_device *dev = dplane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
+	u32 start_vbl_count;
+	bool atomic_update;
+
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
 
 	I915_WRITE(SPCNTR(pipe, plane), I915_READ(SPCNTR(pipe, plane)) &
 		   ~SP_ENABLE);
 	/* Activate double buffered register update */
 	I915_WRITE(SPSURF(pipe, plane), 0);
-	POSTING_READ(SPSURF(pipe, plane));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 
 	intel_update_sprite_watermarks(dplane, crtc, 0, 0, false, false);
 }
@@ -226,10 +348,13 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	u32 sprctl, sprscale = 0;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	u32 start_vbl_count;
+	bool atomic_update;
 
 	sprctl = I915_READ(SPRCTL(pipe));
 
@@ -299,6 +424,10 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 					       pixel_size, fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
+
 	I915_WRITE(SPRSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(SPRPOS(pipe), (crtc_y << 16) | crtc_x);
 
@@ -317,7 +446,11 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	I915_WRITE(SPRCTL(pipe), sprctl);
 	I915_WRITE(SPRSURF(pipe),
 		   i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
-	POSTING_READ(SPRSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 }
 
 static void
@@ -326,7 +459,14 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
+	u32 start_vbl_count;
+	bool atomic_update;
+
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
 
 	I915_WRITE(SPRCTL(pipe), I915_READ(SPRCTL(pipe)) & ~SPRITE_ENABLE);
 	/* Can't leave the scaler enabled... */
@@ -334,7 +474,11 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 		I915_WRITE(SPRSCALE(pipe), 0);
 	/* Activate double buffered register update */
 	I915_WRITE(SPRSURF(pipe), 0);
-	POSTING_READ(SPRSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 
 	/*
 	 * Avoid underruns when disabling the sprite.
@@ -410,10 +554,13 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	unsigned long dvssurf_offset, linear_offset;
 	u32 dvscntr, dvsscale;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	u32 start_vbl_count;
+	bool atomic_update;
 
 	dvscntr = I915_READ(DVSCNTR(pipe));
 
@@ -478,6 +625,10 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 					       pixel_size, fb->pitches[0]);
 	linear_offset -= dvssurf_offset;
 
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
+
 	I915_WRITE(DVSSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(DVSPOS(pipe), (crtc_y << 16) | crtc_x);
 
@@ -491,7 +642,11 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
 	I915_WRITE(DVSSURF(pipe),
 		   i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
-	POSTING_READ(DVSSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 }
 
 static void
@@ -500,14 +655,25 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
+	u32 start_vbl_count;
+	bool atomic_update;
+
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
 
 	I915_WRITE(DVSCNTR(pipe), I915_READ(DVSCNTR(pipe)) & ~DVS_ENABLE);
 	/* Disable the scaler */
 	I915_WRITE(DVSSCALE(pipe), 0);
 	/* Flush double buffered register updates */
 	I915_WRITE(DVSSURF(pipe), 0);
-	POSTING_READ(DVSSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 
 	/*
 	 * Avoid underruns when disabling the sprite.
@@ -519,20 +685,10 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 }
 
 static void
-intel_enable_primary(struct drm_crtc *crtc)
+intel_post_enable_primary(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int reg = DSPCNTR(intel_crtc->plane);
-
-	if (intel_crtc->primary_enabled)
-		return;
-
-	intel_crtc->primary_enabled = true;
-
-	I915_WRITE(reg, I915_READ(reg) | DISPLAY_PLANE_ENABLE);
-	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
 
 	/*
 	 * FIXME IPS should be fine as long as one plane is
@@ -551,17 +707,11 @@ intel_enable_primary(struct drm_crtc *crtc)
 }
 
 static void
-intel_disable_primary(struct drm_crtc *crtc)
+intel_pre_disable_primary(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int reg = DSPCNTR(intel_crtc->plane);
-
-	if (!intel_crtc->primary_enabled)
-		return;
-
-	intel_crtc->primary_enabled = false;
 
 	mutex_lock(&dev->struct_mutex);
 	if (dev_priv->fbc.plane == intel_crtc->plane)
@@ -575,9 +725,6 @@ intel_disable_primary(struct drm_crtc *crtc)
 	 * versa.
 	 */
 	hsw_disable_ips(intel_crtc);
-
-	I915_WRITE(reg, I915_READ(reg) & ~DISPLAY_PLANE_ENABLE);
-	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
 }
 
 static int
@@ -671,7 +818,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct drm_i915_gem_object *old_obj = intel_plane->obj;
 	int ret;
-	bool disable_primary = false;
+	bool primary_enabled;
 	bool visible;
 	int hscale, vscale;
 	int max_scale, min_scale;
@@ -842,8 +989,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	 * If the sprite is completely covering the primary plane,
 	 * we can disable the primary and save power.
 	 */
-	disable_primary = drm_rect_equals(&dst, &clip) && !colorkey_enabled(intel_plane);
-	WARN_ON(disable_primary && !visible && intel_crtc->active);
+	primary_enabled = !drm_rect_equals(&dst, &clip) || colorkey_enabled(intel_plane);
+	WARN_ON(!primary_enabled && !visible && intel_crtc->active);
 
 	mutex_lock(&dev->struct_mutex);
 
@@ -870,12 +1017,12 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	intel_plane->obj = obj;
 
 	if (intel_crtc->active) {
-		/*
-		 * Be sure to re-enable the primary before the sprite is no longer
-		 * covering it fully.
-		 */
-		if (!disable_primary)
-			intel_enable_primary(crtc);
+		bool primary_was_enabled = intel_crtc->primary_enabled;
+
+		intel_crtc->primary_enabled = primary_enabled;
+
+		if (primary_was_enabled && !primary_enabled)
+			intel_pre_disable_primary(crtc);
 
 		if (visible)
 			intel_plane->update_plane(plane, crtc, fb, obj,
@@ -884,8 +1031,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		else
 			intel_plane->disable_plane(plane, crtc);
 
-		if (disable_primary)
-			intel_disable_primary(crtc);
+		if (!primary_was_enabled && primary_enabled)
+			intel_post_enable_primary(crtc);
 	}
 
 	/* Unpin old obj after new one is active to avoid ugliness */
@@ -923,8 +1070,14 @@ intel_disable_plane(struct drm_plane *plane)
 	intel_crtc = to_intel_crtc(plane->crtc);
 
 	if (intel_crtc->active) {
-		intel_enable_primary(plane->crtc);
+		bool primary_was_enabled = intel_crtc->primary_enabled;
+
+		intel_crtc->primary_enabled = true;
+
 		intel_plane->disable_plane(plane, plane->crtc);
+
+		if (!primary_was_enabled && intel_crtc->primary_enabled)
+			intel_post_enable_primary(plane->crtc);
 	}
 
 	if (intel_plane->obj) {
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index bafe92e317d5..e0193e8020b8 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -934,7 +934,86 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_tv_mode_set(struct intel_encoder *encoder)
+static void
+set_tv_mode_timings(struct drm_i915_private *dev_priv,
+		    const struct tv_mode *tv_mode,
+		    bool burst_ena)
+{
+	u32 hctl1, hctl2, hctl3;
+	u32 vctl1, vctl2, vctl3, vctl4, vctl5, vctl6, vctl7;
+
+	hctl1 = (tv_mode->hsync_end << TV_HSYNC_END_SHIFT) |
+		(tv_mode->htotal << TV_HTOTAL_SHIFT);
+
+	hctl2 = (tv_mode->hburst_start << 16) |
+		(tv_mode->hburst_len << TV_HBURST_LEN_SHIFT);
+
+	if (burst_ena)
+		hctl2 |= TV_BURST_ENA;
+
+	hctl3 = (tv_mode->hblank_start << TV_HBLANK_START_SHIFT) |
+		(tv_mode->hblank_end << TV_HBLANK_END_SHIFT);
+
+	vctl1 = (tv_mode->nbr_end << TV_NBR_END_SHIFT) |
+		(tv_mode->vi_end_f1 << TV_VI_END_F1_SHIFT) |
+		(tv_mode->vi_end_f2 << TV_VI_END_F2_SHIFT);
+
+	vctl2 = (tv_mode->vsync_len << TV_VSYNC_LEN_SHIFT) |
+		(tv_mode->vsync_start_f1 << TV_VSYNC_START_F1_SHIFT) |
+		(tv_mode->vsync_start_f2 << TV_VSYNC_START_F2_SHIFT);
+
+	vctl3 = (tv_mode->veq_len << TV_VEQ_LEN_SHIFT) |
+		(tv_mode->veq_start_f1 << TV_VEQ_START_F1_SHIFT) |
+		(tv_mode->veq_start_f2 << TV_VEQ_START_F2_SHIFT);
+
+	if (tv_mode->veq_ena)
+		vctl3 |= TV_EQUAL_ENA;
+
+	vctl4 = (tv_mode->vburst_start_f1 << TV_VBURST_START_F1_SHIFT) |
+		(tv_mode->vburst_end_f1 << TV_VBURST_END_F1_SHIFT);
+
+	vctl5 = (tv_mode->vburst_start_f2 << TV_VBURST_START_F2_SHIFT) |
+		(tv_mode->vburst_end_f2 << TV_VBURST_END_F2_SHIFT);
+
+	vctl6 = (tv_mode->vburst_start_f3 << TV_VBURST_START_F3_SHIFT) |
+		(tv_mode->vburst_end_f3 << TV_VBURST_END_F3_SHIFT);
+
+	vctl7 = (tv_mode->vburst_start_f4 << TV_VBURST_START_F4_SHIFT) |
+		(tv_mode->vburst_end_f4 << TV_VBURST_END_F4_SHIFT);
+
+	I915_WRITE(TV_H_CTL_1, hctl1);
+	I915_WRITE(TV_H_CTL_2, hctl2);
+	I915_WRITE(TV_H_CTL_3, hctl3);
+	I915_WRITE(TV_V_CTL_1, vctl1);
+	I915_WRITE(TV_V_CTL_2, vctl2);
+	I915_WRITE(TV_V_CTL_3, vctl3);
+	I915_WRITE(TV_V_CTL_4, vctl4);
+	I915_WRITE(TV_V_CTL_5, vctl5);
+	I915_WRITE(TV_V_CTL_6, vctl6);
+	I915_WRITE(TV_V_CTL_7, vctl7);
+}
+
+static void set_color_conversion(struct drm_i915_private *dev_priv,
+				 const struct color_conversion *color_conversion)
+{
+	if (!color_conversion)
+		return;
+
+	I915_WRITE(TV_CSC_Y, (color_conversion->ry << 16) |
+		   color_conversion->gy);
+	I915_WRITE(TV_CSC_Y2, (color_conversion->by << 16) |
+		   color_conversion->ay);
+	I915_WRITE(TV_CSC_U, (color_conversion->ru << 16) |
+		   color_conversion->gu);
+	I915_WRITE(TV_CSC_U2, (color_conversion->bu << 16) |
+		   color_conversion->au);
+	I915_WRITE(TV_CSC_V, (color_conversion->rv << 16) |
+		   color_conversion->gv);
+	I915_WRITE(TV_CSC_V2, (color_conversion->bv << 16) |
+		   color_conversion->av);
+}
+
+static void intel_tv_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -942,14 +1021,13 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv);
 	u32 tv_ctl;
-	u32 hctl1, hctl2, hctl3;
-	u32 vctl1, vctl2, vctl3, vctl4, vctl5, vctl6, vctl7;
 	u32 scctl1, scctl2, scctl3;
 	int i, j;
 	const struct video_levels *video_levels;
 	const struct color_conversion *color_conversion;
 	bool burst_ena;
-	int pipe = intel_crtc->pipe;
+	int xpos = 0x0, ypos = 0x0;
+	unsigned int xsize, ysize;
 
 	if (!tv_mode)
 		return;	/* can't happen (mode_prepare prevents this) */
@@ -982,44 +1060,6 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		burst_ena = tv_mode->burst_ena;
 		break;
 	}
-	hctl1 = (tv_mode->hsync_end << TV_HSYNC_END_SHIFT) |
-		(tv_mode->htotal << TV_HTOTAL_SHIFT);
-
-	hctl2 = (tv_mode->hburst_start << 16) |
-		(tv_mode->hburst_len << TV_HBURST_LEN_SHIFT);
-
-	if (burst_ena)
-		hctl2 |= TV_BURST_ENA;
-
-	hctl3 = (tv_mode->hblank_start << TV_HBLANK_START_SHIFT) |
-		(tv_mode->hblank_end << TV_HBLANK_END_SHIFT);
-
-	vctl1 = (tv_mode->nbr_end << TV_NBR_END_SHIFT) |
-		(tv_mode->vi_end_f1 << TV_VI_END_F1_SHIFT) |
-		(tv_mode->vi_end_f2 << TV_VI_END_F2_SHIFT);
-
-	vctl2 = (tv_mode->vsync_len << TV_VSYNC_LEN_SHIFT) |
-		(tv_mode->vsync_start_f1 << TV_VSYNC_START_F1_SHIFT) |
-		(tv_mode->vsync_start_f2 << TV_VSYNC_START_F2_SHIFT);
-
-	vctl3 = (tv_mode->veq_len << TV_VEQ_LEN_SHIFT) |
-		(tv_mode->veq_start_f1 << TV_VEQ_START_F1_SHIFT) |
-		(tv_mode->veq_start_f2 << TV_VEQ_START_F2_SHIFT);
-
-	if (tv_mode->veq_ena)
-		vctl3 |= TV_EQUAL_ENA;
-
-	vctl4 = (tv_mode->vburst_start_f1 << TV_VBURST_START_F1_SHIFT) |
-		(tv_mode->vburst_end_f1 << TV_VBURST_END_F1_SHIFT);
-
-	vctl5 = (tv_mode->vburst_start_f2 << TV_VBURST_START_F2_SHIFT) |
-		(tv_mode->vburst_end_f2 << TV_VBURST_END_F2_SHIFT);
-
-	vctl6 = (tv_mode->vburst_start_f3 << TV_VBURST_START_F3_SHIFT) |
-		(tv_mode->vburst_end_f3 << TV_VBURST_END_F3_SHIFT);
-
-	vctl7 = (tv_mode->vburst_start_f4 << TV_VBURST_START_F4_SHIFT) |
-		(tv_mode->vburst_end_f4 << TV_VBURST_END_F4_SHIFT);
 
 	if (intel_crtc->pipe == 1)
 		tv_ctl |= TV_ENC_PIPEB_SELECT;
@@ -1051,37 +1091,16 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		tv_mode->dda3_inc << TV_SCDDA3_INC_SHIFT;
 
 	/* Enable two fixes for the chips that need them. */
-	if (dev->pdev->device < 0x2772)
+	if (IS_I915GM(dev))
 		tv_ctl |= TV_ENC_C0_FIX | TV_ENC_SDP_FIX;
 
-	I915_WRITE(TV_H_CTL_1, hctl1);
-	I915_WRITE(TV_H_CTL_2, hctl2);
-	I915_WRITE(TV_H_CTL_3, hctl3);
-	I915_WRITE(TV_V_CTL_1, vctl1);
-	I915_WRITE(TV_V_CTL_2, vctl2);
-	I915_WRITE(TV_V_CTL_3, vctl3);
-	I915_WRITE(TV_V_CTL_4, vctl4);
-	I915_WRITE(TV_V_CTL_5, vctl5);
-	I915_WRITE(TV_V_CTL_6, vctl6);
-	I915_WRITE(TV_V_CTL_7, vctl7);
+	set_tv_mode_timings(dev_priv, tv_mode, burst_ena);
+
 	I915_WRITE(TV_SC_CTL_1, scctl1);
 	I915_WRITE(TV_SC_CTL_2, scctl2);
 	I915_WRITE(TV_SC_CTL_3, scctl3);
 
-	if (color_conversion) {
-		I915_WRITE(TV_CSC_Y, (color_conversion->ry << 16) |
-			   color_conversion->gy);
-		I915_WRITE(TV_CSC_Y2, (color_conversion->by << 16) |
-			   color_conversion->ay);
-		I915_WRITE(TV_CSC_U, (color_conversion->ru << 16) |
-			   color_conversion->gu);
-		I915_WRITE(TV_CSC_U2, (color_conversion->bu << 16) |
-			   color_conversion->au);
-		I915_WRITE(TV_CSC_V, (color_conversion->rv << 16) |
-			   color_conversion->gv);
-		I915_WRITE(TV_CSC_V2, (color_conversion->bv << 16) |
-			   color_conversion->av);
-	}
+	set_color_conversion(dev_priv, color_conversion);
 
 	if (INTEL_INFO(dev)->gen >= 4)
 		I915_WRITE(TV_CLR_KNOBS, 0x00404000);
@@ -1092,46 +1111,25 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		I915_WRITE(TV_CLR_LEVEL,
 			   ((video_levels->black << TV_BLACK_LEVEL_SHIFT) |
 			    (video_levels->blank << TV_BLANK_LEVEL_SHIFT)));
-	{
-		int pipeconf_reg = PIPECONF(pipe);
-		int dspcntr_reg = DSPCNTR(intel_crtc->plane);
-		int pipeconf = I915_READ(pipeconf_reg);
-		int dspcntr = I915_READ(dspcntr_reg);
-		int xpos = 0x0, ypos = 0x0;
-		unsigned int xsize, ysize;
-		/* Pipe must be off here */
-		I915_WRITE(dspcntr_reg, dspcntr & ~DISPLAY_PLANE_ENABLE);
-		intel_flush_primary_plane(dev_priv, intel_crtc->plane);
-
-		/* Wait for vblank for the disable to take effect */
-		if (IS_GEN2(dev))
-			intel_wait_for_vblank(dev, intel_crtc->pipe);
-
-		I915_WRITE(pipeconf_reg, pipeconf & ~PIPECONF_ENABLE);
-		/* Wait for vblank for the disable to take effect. */
-		intel_wait_for_pipe_off(dev, intel_crtc->pipe);
-
-		/* Filter ctl must be set before TV_WIN_SIZE */
-		I915_WRITE(TV_FILTER_CTL_1, TV_AUTO_SCALE);
-		xsize = tv_mode->hblank_start - tv_mode->hblank_end;
-		if (tv_mode->progressive)
-			ysize = tv_mode->nbr_end + 1;
-		else
-			ysize = 2*tv_mode->nbr_end + 1;
-
-		xpos += intel_tv->margin[TV_MARGIN_LEFT];
-		ypos += intel_tv->margin[TV_MARGIN_TOP];
-		xsize -= (intel_tv->margin[TV_MARGIN_LEFT] +
-			  intel_tv->margin[TV_MARGIN_RIGHT]);
-		ysize -= (intel_tv->margin[TV_MARGIN_TOP] +
-			  intel_tv->margin[TV_MARGIN_BOTTOM]);
-		I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos);
-		I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize);
-
-		I915_WRITE(pipeconf_reg, pipeconf);
-		I915_WRITE(dspcntr_reg, dspcntr);
-		intel_flush_primary_plane(dev_priv, intel_crtc->plane);
-	}
+
+	assert_pipe_disabled(dev_priv, intel_crtc->pipe);
+
+	/* Filter ctl must be set before TV_WIN_SIZE */
+	I915_WRITE(TV_FILTER_CTL_1, TV_AUTO_SCALE);
+	xsize = tv_mode->hblank_start - tv_mode->hblank_end;
+	if (tv_mode->progressive)
+		ysize = tv_mode->nbr_end + 1;
+	else
+		ysize = 2*tv_mode->nbr_end + 1;
+
+	xpos += intel_tv->margin[TV_MARGIN_LEFT];
+	ypos += intel_tv->margin[TV_MARGIN_TOP];
+	xsize -= (intel_tv->margin[TV_MARGIN_LEFT] +
+		  intel_tv->margin[TV_MARGIN_RIGHT]);
+	ysize -= (intel_tv->margin[TV_MARGIN_TOP] +
+		  intel_tv->margin[TV_MARGIN_BOTTOM]);
+	I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos);
+	I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize);
 
 	j = 0;
 	for (i = 0; i < 60; i++)
@@ -1634,7 +1632,7 @@ intel_tv_init(struct drm_device *dev)
 
 	intel_encoder->compute_config = intel_tv_compute_config;
 	intel_encoder->get_config = intel_tv_get_config;
-	intel_encoder->mode_set = intel_tv_mode_set;
+	intel_encoder->pre_enable = intel_tv_pre_enable;
 	intel_encoder->enable = intel_enable_tv;
 	intel_encoder->disable = intel_disable_tv;
 	intel_encoder->get_hw_state = intel_tv_get_hw_state;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 2a72bab106d5..76dc185793ce 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -370,7 +370,7 @@ void intel_uncore_early_sanitize(struct drm_device *dev)
 	if (HAS_FPGA_DBG_UNCLAIMED(dev))
 		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
 
-	if (IS_HASWELL(dev) &&
+	if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) &&
 	    (__raw_i915_read32(dev_priv, HSW_EDRAM_PRESENT) == 1)) {
 		/* The docs do not explain exactly how the calculation can be
 		 * made. It is somewhat guessable, but for now, it's always