diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 74724aacb8ae..f4babed2f557 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -726,7 +726,8 @@ int drm_dp_aux_register_i2c_bus(struct drm_dp_aux *aux)
 	aux->ddc.dev.parent = aux->dev;
 	aux->ddc.dev.of_node = aux->dev->of_node;
 
-	strncpy(aux->ddc.name, dev_name(aux->dev), sizeof(aux->ddc.name));
+	strlcpy(aux->ddc.name, aux->name ? aux->name : dev_name(aux->dev),
+		sizeof(aux->ddc.name));
 
 	return i2c_add_adapter(&aux->ddc);
 }
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 69c1287f1262..4cf6d020d513 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -402,7 +402,7 @@ int i915_parse_cmds(struct intel_ring_buffer *ring,
 			length = ((*cmd & desc->length.mask) + LENGTH_BIAS);
 
 		if ((batch_end - cmd) < length) {
-			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%d batchlen=%ld\n",
+			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%d batchlen=%td\n",
 					 *cmd,
 					 length,
 					 (unsigned long)(batch_end - cmd));
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index cacd4974cf23..d04786db9627 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -299,28 +299,62 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 } while (0)
 
 struct file_stats {
+	struct drm_i915_file_private *file_priv;
 	int count;
-	size_t total, active, inactive, unbound;
+	size_t total, unbound;
+	size_t global, shared;
+	size_t active, inactive;
 };
 
 static int per_file_stats(int id, void *ptr, void *data)
 {
 	struct drm_i915_gem_object *obj = ptr;
 	struct file_stats *stats = data;
+	struct i915_vma *vma;
 
 	stats->count++;
 	stats->total += obj->base.size;
 
-	if (i915_gem_obj_ggtt_bound(obj)) {
-		if (!list_empty(&obj->ring_list))
-			stats->active += obj->base.size;
-		else
-			stats->inactive += obj->base.size;
+	if (obj->base.name || obj->base.dma_buf)
+		stats->shared += obj->base.size;
+
+	if (USES_FULL_PPGTT(obj->base.dev)) {
+		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+			struct i915_hw_ppgtt *ppgtt;
+
+			if (!drm_mm_node_allocated(&vma->node))
+				continue;
+
+			if (i915_is_ggtt(vma->vm)) {
+				stats->global += obj->base.size;
+				continue;
+			}
+
+			ppgtt = container_of(vma->vm, struct i915_hw_ppgtt, base);
+			if (ppgtt->ctx && ppgtt->ctx->file_priv != stats->file_priv)
+				continue;
+
+			if (obj->ring) /* XXX per-vma statistic */
+				stats->active += obj->base.size;
+			else
+				stats->inactive += obj->base.size;
+
+			return 0;
+		}
 	} else {
-		if (!list_empty(&obj->global_list))
-			stats->unbound += obj->base.size;
+		if (i915_gem_obj_ggtt_bound(obj)) {
+			stats->global += obj->base.size;
+			if (obj->ring)
+				stats->active += obj->base.size;
+			else
+				stats->inactive += obj->base.size;
+			return 0;
+		}
 	}
 
+	if (!list_empty(&obj->global_list))
+		stats->unbound += obj->base.size;
+
 	return 0;
 }
 
@@ -411,6 +445,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		struct task_struct *task;
 
 		memset(&stats, 0, sizeof(stats));
+		stats.file_priv = file->driver_priv;
 		idr_for_each(&file->object_idr, per_file_stats, &stats);
 		/*
 		 * Although we have a valid reference on file->pid, that does
@@ -420,12 +455,14 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		 */
 		rcu_read_lock();
 		task = pid_task(file->pid, PIDTYPE_PID);
-		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu unbound)\n",
+		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu global, %zu shared, %zu unbound)\n",
 			   task ? task->comm : "<unknown>",
 			   stats.count,
 			   stats.total,
 			   stats.active,
 			   stats.inactive,
+			   stats.global,
+			   stats.shared,
 			   stats.unbound);
 		rcu_read_unlock();
 	}
@@ -1026,7 +1063,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 			   max_freq * GT_FREQUENCY_MULTIPLIER);
 
 		seq_printf(m, "Max overclocked frequency: %dMHz\n",
-			   dev_priv->rps.hw_max * GT_FREQUENCY_MULTIPLIER);
+			   dev_priv->rps.max_freq * GT_FREQUENCY_MULTIPLIER);
 	} else if (IS_VALLEYVIEW(dev)) {
 		u32 freq_sts, val;
 
@@ -1498,8 +1535,8 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 
 	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
 
-	for (gpu_freq = dev_priv->rps.min_delay;
-	     gpu_freq <= dev_priv->rps.max_delay;
+	for (gpu_freq = dev_priv->rps.min_freq_softlimit;
+	     gpu_freq <= dev_priv->rps.max_freq_softlimit;
 	     gpu_freq++) {
 		ia_freq = gpu_freq;
 		sandybridge_pcode_read(dev_priv,
@@ -2012,15 +2049,9 @@ static int i915_pc8_status(struct seq_file *m, void *unused)
 		return 0;
 	}
 
-	mutex_lock(&dev_priv->pc8.lock);
-	seq_printf(m, "Requirements met: %s\n",
-		   yesno(dev_priv->pc8.requirements_met));
 	seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->mm.busy));
-	seq_printf(m, "Disable count: %d\n", dev_priv->pc8.disable_count);
 	seq_printf(m, "IRQs disabled: %s\n",
-		   yesno(dev_priv->pc8.irqs_disabled));
-	seq_printf(m, "Enabled: %s\n", yesno(dev_priv->pc8.enabled));
-	mutex_unlock(&dev_priv->pc8.lock);
+		   yesno(dev_priv->pm.irqs_disabled));
 
 	return 0;
 }
@@ -2248,24 +2279,67 @@ static void intel_connector_info(struct seq_file *m,
 		intel_seq_print_mode(m, 2, mode);
 }
 
+static bool cursor_active(struct drm_device *dev, int pipe)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 state;
+
+	if (IS_845G(dev) || IS_I865G(dev))
+		state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
+	else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev))
+		state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
+	else
+		state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
+
+	return state;
+}
+
+static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 pos;
+
+	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev))
+		pos = I915_READ(CURPOS_IVB(pipe));
+	else
+		pos = I915_READ(CURPOS(pipe));
+
+	*x = (pos >> CURSOR_X_SHIFT) & CURSOR_POS_MASK;
+	if (pos & (CURSOR_POS_SIGN << CURSOR_X_SHIFT))
+		*x = -*x;
+
+	*y = (pos >> CURSOR_Y_SHIFT) & CURSOR_POS_MASK;
+	if (pos & (CURSOR_POS_SIGN << CURSOR_Y_SHIFT))
+		*y = -*y;
+
+	return cursor_active(dev, pipe);
+}
+
 static int i915_display_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_crtc *crtc;
+	struct intel_crtc *crtc;
 	struct drm_connector *connector;
 
 	drm_modeset_lock_all(dev);
 	seq_printf(m, "CRTC info\n");
 	seq_printf(m, "---------\n");
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+		bool active;
+		int x, y;
 
 		seq_printf(m, "CRTC %d: pipe: %c, active: %s\n",
-			   crtc->base.id, pipe_name(intel_crtc->pipe),
-			   intel_crtc->active ? "yes" : "no");
-		if (intel_crtc->active)
-			intel_crtc_info(m, intel_crtc);
+			   crtc->base.base.id, pipe_name(crtc->pipe),
+			   yesno(crtc->active));
+		if (crtc->active)
+			intel_crtc_info(m, crtc);
+
+		active = cursor_position(dev, crtc->pipe, &x, &y);
+		seq_printf(m, "\tcursor visible? %s, position (%d, %d), addr 0x%08x, active? %s\n",
+			   yesno(crtc->cursor_visible),
+			   x, y, crtc->cursor_addr,
+			   yesno(active));
 	}
 
 	seq_printf(m, "\n");
@@ -2603,8 +2677,6 @@ static int vlv_pipe_crc_ctl_reg(struct drm_device *dev,
 	if (need_stable_symbols) {
 		uint32_t tmp = I915_READ(PORT_DFT2_G4X);
 
-		WARN_ON(!IS_G4X(dev));
-
 		tmp |= DC_BALANCE_RESET_VLV;
 		if (pipe == PIPE_A)
 			tmp |= PIPE_A_SCRAMBLE_RESET;
@@ -3414,9 +3486,9 @@ i915_max_freq_get(void *data, u64 *val)
 		return ret;
 
 	if (IS_VALLEYVIEW(dev))
-		*val = vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay);
+		*val = vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq_softlimit);
 	else
-		*val = dev_priv->rps.max_delay * GT_FREQUENCY_MULTIPLIER;
+		*val = dev_priv->rps.max_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return 0;
@@ -3453,16 +3525,16 @@ i915_max_freq_set(void *data, u64 val)
 		do_div(val, GT_FREQUENCY_MULTIPLIER);
 
 		rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		hw_max = dev_priv->rps.hw_max;
+		hw_max = dev_priv->rps.max_freq;
 		hw_min = (rp_state_cap >> 16) & 0xff;
 	}
 
-	if (val < hw_min || val > hw_max || val < dev_priv->rps.min_delay) {
+	if (val < hw_min || val > hw_max || val < dev_priv->rps.min_freq_softlimit) {
 		mutex_unlock(&dev_priv->rps.hw_lock);
 		return -EINVAL;
 	}
 
-	dev_priv->rps.max_delay = val;
+	dev_priv->rps.max_freq_softlimit = val;
 
 	if (IS_VALLEYVIEW(dev))
 		valleyview_set_rps(dev, val);
@@ -3495,9 +3567,9 @@ i915_min_freq_get(void *data, u64 *val)
 		return ret;
 
 	if (IS_VALLEYVIEW(dev))
-		*val = vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay);
+		*val = vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq_softlimit);
 	else
-		*val = dev_priv->rps.min_delay * GT_FREQUENCY_MULTIPLIER;
+		*val = dev_priv->rps.min_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return 0;
@@ -3534,16 +3606,16 @@ i915_min_freq_set(void *data, u64 val)
 		do_div(val, GT_FREQUENCY_MULTIPLIER);
 
 		rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		hw_max = dev_priv->rps.hw_max;
+		hw_max = dev_priv->rps.max_freq;
 		hw_min = (rp_state_cap >> 16) & 0xff;
 	}
 
-	if (val < hw_min || val > hw_max || val > dev_priv->rps.max_delay) {
+	if (val < hw_min || val > hw_max || val > dev_priv->rps.max_freq_softlimit) {
 		mutex_unlock(&dev_priv->rps.hw_lock);
 		return -EINVAL;
 	}
 
-	dev_priv->rps.min_delay = val;
+	dev_priv->rps.min_freq_softlimit = val;
 
 	if (IS_VALLEYVIEW(dev))
 		valleyview_set_rps(dev, val);
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index e4d2b9f15ae2..4e0a26a83500 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1187,6 +1187,9 @@ intel_setup_mchbar(struct drm_device *dev)
 	u32 temp;
 	bool enabled;
 
+	if (IS_VALLEYVIEW(dev))
+		return;
+
 	dev_priv->mchbar_need_disable = false;
 
 	if (IS_I915G(dev) || IS_I915GM(dev)) {
@@ -1608,8 +1611,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto put_bridge;
 	}
 
-	intel_uncore_early_sanitize(dev);
-
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(dev);
 
@@ -1822,8 +1823,6 @@ int i915_driver_unload(struct drm_device *dev)
 	cancel_work_sync(&dev_priv->gpu_error.work);
 	i915_destroy_error_state(dev);
 
-	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
-
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 658fe24961eb..fa5d0ed76378 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -428,7 +428,6 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	/* We do a lot of poking in a lot of registers, make sure they work
 	 * properly. */
-	hsw_disable_package_c8(dev_priv);
 	intel_display_set_init_power(dev_priv, true);
 
 	drm_kms_helper_poll_disable(dev);
@@ -467,6 +466,7 @@ static int i915_drm_freeze(struct drm_device *dev)
 	i915_save_state(dev);
 
 	intel_opregion_fini(dev);
+	intel_uncore_fini(dev);
 
 	console_lock();
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED);
@@ -603,10 +603,6 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		schedule_work(&dev_priv->console_resume_work);
 	}
 
-	/* Undo what we did at i915_drm_freeze so the refcount goes back to the
-	 * expected level. */
-	hsw_enable_package_c8(dev_priv);
-
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
@@ -848,6 +844,9 @@ static int i915_runtime_suspend(struct device *device)
 
 	DRM_DEBUG_KMS("Suspending device\n");
 
+	if (HAS_PC8(dev))
+		hsw_enable_pc8(dev_priv);
+
 	i915_gem_release_all_mmaps(dev_priv);
 
 	del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
@@ -862,6 +861,7 @@ static int i915_runtime_suspend(struct device *device)
 	 */
 	intel_opregion_notify_adapter(dev, PCI_D1);
 
+	DRM_DEBUG_KMS("Device suspended\n");
 	return 0;
 }
 
@@ -878,6 +878,10 @@ static int i915_runtime_resume(struct device *device)
 	intel_opregion_notify_adapter(dev, PCI_D0);
 	dev_priv->pm.suspended = false;
 
+	if (HAS_PC8(dev))
+		hsw_disable_pc8(dev_priv);
+
+	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 2a319ba91a71..3f62be0fb5c5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -406,6 +406,7 @@ struct drm_i915_error_state {
 
 struct intel_connector;
 struct intel_crtc_config;
+struct intel_plane_config;
 struct intel_crtc;
 struct intel_limit;
 struct dpll;
@@ -444,6 +445,8 @@ struct drm_i915_display_funcs {
 	 * fills out the pipe-config with the hw state. */
 	bool (*get_pipe_config)(struct intel_crtc *,
 				struct intel_crtc_config *);
+	void (*get_plane_config)(struct intel_crtc *,
+				 struct intel_plane_config *);
 	int (*crtc_mode_set)(struct drm_crtc *crtc,
 			     int x, int y,
 			     struct drm_framebuffer *old_fb);
@@ -459,8 +462,9 @@ struct drm_i915_display_funcs {
 			  struct drm_framebuffer *fb,
 			  struct drm_i915_gem_object *obj,
 			  uint32_t flags);
-	int (*update_plane)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-			    int x, int y);
+	int (*update_primary_plane)(struct drm_crtc *crtc,
+				    struct drm_framebuffer *fb,
+				    int x, int y);
 	void (*hpd_irq_setup)(struct drm_device *dev);
 	/* clock updates for mode set */
 	/* cursor updates */
@@ -721,6 +725,8 @@ struct i915_hw_ppgtt {
 		dma_addr_t *gen8_pt_dma_addr[4];
 	};
 
+	struct i915_hw_context *ctx;
+
 	int (*enable)(struct i915_hw_ppgtt *ppgtt);
 	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
 			 struct intel_ring_buffer *ring,
@@ -976,13 +982,24 @@ struct intel_gen6_power_mgmt {
 	struct work_struct work;
 	u32 pm_iir;
 
-	u8 cur_delay;
-	u8 min_delay;
-	u8 max_delay;
-	u8 rpe_delay;
-	u8 rp1_delay;
-	u8 rp0_delay;
-	u8 hw_max;
+	/* Frequencies are stored in potentially platform dependent multiples.
+	 * In other words, *_freq needs to be multiplied by X to be interesting.
+	 * Soft limits are those which are used for the dynamic reclocking done
+	 * by the driver (raise frequencies under heavy loads, and lower for
+	 * lighter loads). Hard limits are those imposed by the hardware.
+	 *
+	 * A distinction is made for overclocking, which is never enabled by
+	 * default, and is considered to be above the hard limit if it's
+	 * possible at all.
+	 */
+	u8 cur_freq;		/* Current frequency (cached, may not == HW) */
+	u8 min_freq_softlimit;	/* Minimum frequency permitted by the driver */
+	u8 max_freq_softlimit;	/* Max frequency permitted by the driver */
+	u8 max_freq;		/* Maximum frequency, RP0 if not overclocking */
+	u8 min_freq;		/* AKA RPn. Minimum frequency */
+	u8 efficient_freq;	/* AKA RPe. Pre-determined balanced frequency */
+	u8 rp1_freq;		/* "less than" RP0 power/freqency */
+	u8 rp0_freq;		/* Non-overclocked max frequency. */
 
 	bool rp_up_masked;
 	bool rp_down_masked;
@@ -1333,43 +1350,19 @@ struct ilk_wm_values {
 };
 
 /*
- * This struct tracks the state needed for the Package C8+ feature.
+ * This struct helps tracking the state needed for runtime PM, which puts the
+ * device in PCI D3 state. Notice that when this happens, nothing on the
+ * graphics device works, even register access, so we don't get interrupts nor
+ * anything else.
  *
- * Package states C8 and deeper are really deep PC states that can only be
- * reached when all the devices on the system allow it, so even if the graphics
- * device allows PC8+, it doesn't mean the system will actually get to these
- * states.
+ * Every piece of our code that needs to actually touch the hardware needs to
+ * either call intel_runtime_pm_get or call intel_display_power_get with the
+ * appropriate power domain.
  *
- * Our driver only allows PC8+ when all the outputs are disabled, the power well
- * is disabled and the GPU is idle. When these conditions are met, we manually
- * do the other conditions: disable the interrupts, clocks and switch LCPLL
- * refclk to Fclk.
- *
- * When we really reach PC8 or deeper states (not just when we allow it) we lose
- * the state of some registers, so when we come back from PC8+ we need to
- * restore this state. We don't get into PC8+ if we're not in RC6, so we don't
- * need to take care of the registers kept by RC6.
- *
- * The interrupt disabling is part of the requirements. We can only leave the
- * PCH HPD interrupts enabled. If we're in PC8+ and we get another interrupt we
- * can lock the machine.
- *
- * Ideally every piece of our code that needs PC8+ disabled would call
- * hsw_disable_package_c8, which would increment disable_count and prevent the
- * system from reaching PC8+. But we don't have a symmetric way to do this for
- * everything, so we have the requirements_met variable. When we switch
- * requirements_met to true we decrease disable_count, and increase it in the
- * opposite case. The requirements_met variable is true when all the CRTCs,
- * encoders and the power well are disabled.
- *
- * In addition to everything, we only actually enable PC8+ if disable_count
- * stays at zero for at least some seconds. This is implemented with the
- * enable_work variable. We do this so we don't enable/disable PC8 dozens of
- * consecutive times when all screens are disabled and some background app
- * queries the state of our connectors, or we have some application constantly
- * waking up to use the GPU. Only after the enable_work function actually
- * enables PC8+ the "enable" variable will become true, which means that it can
- * be false even if disable_count is 0.
+ * Our driver uses the autosuspend delay feature, which means we'll only really
+ * suspend if we stay with zero refcount for a certain amount of time. The
+ * default value is currently very conservative (see intel_init_runtime_pm), but
+ * it can be changed with the standard runtime PM files from sysfs.
  *
  * The irqs_disabled variable becomes true exactly after we disable the IRQs and
  * goes back to false exactly before we reenable the IRQs. We use this variable
@@ -1379,16 +1372,11 @@ struct ilk_wm_values {
  * inside struct regsave so when we restore the IRQs they will contain the
  * latest expected values.
  *
- * For more, read "Display Sequences for Package C8" on our documentation.
+ * For more, read the Documentation/power/runtime_pm.txt.
  */
-struct i915_package_c8 {
-	bool requirements_met;
+struct i915_runtime_pm {
+	bool suspended;
 	bool irqs_disabled;
-	/* Only true after the delayed work task actually enables it. */
-	bool enabled;
-	int disable_count;
-	struct mutex lock;
-	struct delayed_work enable_work;
 
 	struct {
 		uint32_t deimr;
@@ -1399,10 +1387,6 @@ struct i915_package_c8 {
 	} regsave;
 };
 
-struct i915_runtime_pm {
-	bool suspended;
-};
-
 enum intel_pipe_crc_source {
 	INTEL_PIPE_CRC_SOURCE_NONE,
 	INTEL_PIPE_CRC_SOURCE_PLANE1,
@@ -1610,6 +1594,7 @@ typedef struct drm_i915_private {
 
 	u32 fdi_rx_config;
 
+	u32 suspend_count;
 	struct i915_suspend_saved_registers regfile;
 
 	struct {
@@ -1629,8 +1614,6 @@ typedef struct drm_i915_private {
 		struct ilk_wm_values hw;
 	} wm;
 
-	struct i915_package_c8 pc8;
-
 	struct i915_runtime_pm pm;
 
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
@@ -1638,8 +1621,6 @@ typedef struct drm_i915_private {
 	struct i915_dri1_state dri1;
 	/* Old ums support infrastructure, same warning applies. */
 	struct i915_ums_state ums;
-
-	u32 suspend_count;
 } drm_i915_private_t;
 
 static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
@@ -2092,8 +2073,6 @@ struct i915_params {
 	unsigned int preliminary_hw_support;
 	int disable_power_well;
 	int enable_ips;
-	int enable_pc8;
-	int pc8_timeout;
 	int invert_brightness;
 	int enable_cmd_parser;
 	/* leave bools at the end to not create holes */
@@ -2757,6 +2736,12 @@ void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine);
 #define I915_READ_NOTRACE(reg)		dev_priv->uncore.funcs.mmio_readl(dev_priv, (reg), false)
 #define I915_WRITE_NOTRACE(reg, val)	dev_priv->uncore.funcs.mmio_writel(dev_priv, (reg), (val), false)
 
+/* Be very careful with read/write 64-bit values. On 32-bit machines, they
+ * will be implemented using 2 32-bit writes in an arbitrary order with
+ * an arbitrary delay between them. This can cause the hardware to
+ * act upon the intermediate value, possibly leading to corruption and
+ * machine death. You have been warned.
+ */
 #define I915_WRITE64(reg, val)	dev_priv->uncore.funcs.mmio_writeq(dev_priv, (reg), (val), true)
 #define I915_READ64(reg)	dev_priv->uncore.funcs.mmio_readq(dev_priv, (reg), true)
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9c52f68df66c..33bbaa0d4412 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -510,12 +510,10 @@ i915_gem_shmem_pread(struct drm_device *dev,
 
 		mutex_lock(&dev->struct_mutex);
 
-next_page:
-		mark_page_accessed(page);
-
 		if (ret)
 			goto out;
 
+next_page:
 		remain -= page_length;
 		user_data += page_length;
 		offset += page_length;
@@ -695,9 +693,8 @@ shmem_pwrite_fast(struct page *page, int shmem_page_offset, int page_length,
 	if (needs_clflush_before)
 		drm_clflush_virt_range(vaddr + shmem_page_offset,
 				       page_length);
-	ret = __copy_from_user_inatomic_nocache(vaddr + shmem_page_offset,
-						user_data,
-						page_length);
+	ret = __copy_from_user_inatomic(vaddr + shmem_page_offset,
+					user_data, page_length);
 	if (needs_clflush_after)
 		drm_clflush_virt_range(vaddr + shmem_page_offset,
 				       page_length);
@@ -831,13 +828,10 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 
 		mutex_lock(&dev->struct_mutex);
 
-next_page:
-		set_page_dirty(page);
-		mark_page_accessed(page);
-
 		if (ret)
 			goto out;
 
+next_page:
 		remain -= page_length;
 		user_data += page_length;
 		offset += page_length;
@@ -1041,7 +1035,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	unsigned long timeout_expire;
 	int ret;
 
-	WARN(dev_priv->pc8.irqs_disabled, "IRQs disabled\n");
+	WARN(dev_priv->pm.irqs_disabled, "IRQs disabled\n");
 
 	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
 		return 0;
@@ -3473,7 +3467,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level)
 {
 	struct drm_device *dev = obj->base.dev;
-	struct i915_vma *vma;
+	struct i915_vma *vma, *next;
 	int ret;
 
 	if (obj->cache_level == cache_level)
@@ -3484,13 +3478,11 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return -EBUSY;
 	}
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
 		if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) {
 			ret = i915_vma_unbind(vma);
 			if (ret)
 				return ret;
-
-			break;
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index ce41cff84346..6043062ffce7 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -215,6 +215,7 @@ create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx)
 		return ERR_PTR(ret);
 	}
 
+	ppgtt->ctx = ctx;
 	return ppgtt;
 }
 
@@ -775,9 +776,11 @@ int i915_switch_context(struct intel_ring_buffer *ring,
 
 	BUG_ON(file && to == NULL);
 
-	/* We have the fake context, but don't supports switching. */
-	if (!HAS_HW_CONTEXTS(ring->dev))
+	/* We have the fake context */
+	if (!HAS_HW_CONTEXTS(ring->dev)) {
+		ring->last_context = to;
 		return 0;
+	}
 
 	return do_switch(ring, to);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 63a6dc7a6bb6..ee535514aa41 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -30,6 +30,8 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv);
+
 bool intel_enable_ppgtt(struct drm_device *dev, bool full)
 {
 	if (i915.enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
@@ -1191,9 +1193,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
-	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
 	ppgtt->base.start = 0;
-	ppgtt->base.total = GEN6_PPGTT_PD_ENTRIES * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
+	ppgtt->base.total =  ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
 	ppgtt->debug_dump = gen6_dump_ppgtt;
 
 	ppgtt->pd_offset =
@@ -1214,6 +1215,7 @@ int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
 	int ret = 0;
 
 	ppgtt->base.dev = dev;
+	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
 
 	if (INTEL_INFO(dev)->gen < 8)
 		ret = gen6_ppgtt_init(ppgtt);
@@ -1243,8 +1245,6 @@ ppgtt_bind_vma(struct i915_vma *vma,
 	       enum i915_cache_level cache_level,
 	       u32 flags)
 {
-	WARN_ON(flags);
-
 	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
 				cache_level);
 }
@@ -1372,8 +1372,10 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	}
 
 
-	if (INTEL_INFO(dev)->gen >= 8)
+	if (INTEL_INFO(dev)->gen >= 8) {
+		gen8_setup_private_ppat(dev_priv);
 		return;
+	}
 
 	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
 		/* TODO: Perhaps it shouldn't be gen6 specific */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 144a5e2bc7ef..baf1ca690dc5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -850,10 +850,12 @@ static void i915_record_ring_state(struct drm_device *dev,
 			}
 			break;
 		case 7:
-			ering->vm_info.pp_dir_base = RING_PP_DIR_BASE(ring);
+			ering->vm_info.pp_dir_base =
+				I915_READ(RING_PP_DIR_BASE(ring));
 			break;
 		case 6:
-			ering->vm_info.pp_dir_base = RING_PP_DIR_BASE_READ(ring);
+			ering->vm_info.pp_dir_base =
+				I915_READ(RING_PP_DIR_BASE_READ(ring));
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 15d5e61eb415..acebe511e4ef 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -86,9 +86,9 @@ ironlake_enable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pc8.irqs_disabled) {
+	if (dev_priv->pm.irqs_disabled) {
 		WARN(1, "IRQs disabled\n");
-		dev_priv->pc8.regsave.deimr &= ~mask;
+		dev_priv->pm.regsave.deimr &= ~mask;
 		return;
 	}
 
@@ -104,9 +104,9 @@ ironlake_disable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pc8.irqs_disabled) {
+	if (dev_priv->pm.irqs_disabled) {
 		WARN(1, "IRQs disabled\n");
-		dev_priv->pc8.regsave.deimr |= mask;
+		dev_priv->pm.regsave.deimr |= mask;
 		return;
 	}
 
@@ -129,10 +129,10 @@ static void ilk_update_gt_irq(struct drm_i915_private *dev_priv,
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pc8.irqs_disabled) {
+	if (dev_priv->pm.irqs_disabled) {
 		WARN(1, "IRQs disabled\n");
-		dev_priv->pc8.regsave.gtimr &= ~interrupt_mask;
-		dev_priv->pc8.regsave.gtimr |= (~enabled_irq_mask &
+		dev_priv->pm.regsave.gtimr &= ~interrupt_mask;
+		dev_priv->pm.regsave.gtimr |= (~enabled_irq_mask &
 						interrupt_mask);
 		return;
 	}
@@ -167,10 +167,10 @@ static void snb_update_pm_irq(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pc8.irqs_disabled) {
+	if (dev_priv->pm.irqs_disabled) {
 		WARN(1, "IRQs disabled\n");
-		dev_priv->pc8.regsave.gen6_pmimr &= ~interrupt_mask;
-		dev_priv->pc8.regsave.gen6_pmimr |= (~enabled_irq_mask &
+		dev_priv->pm.regsave.gen6_pmimr &= ~interrupt_mask;
+		dev_priv->pm.regsave.gen6_pmimr |= (~enabled_irq_mask &
 						     interrupt_mask);
 		return;
 	}
@@ -313,11 +313,11 @@ static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pc8.irqs_disabled &&
+	if (dev_priv->pm.irqs_disabled &&
 	    (interrupt_mask & SDE_HOTPLUG_MASK_CPT)) {
 		WARN(1, "IRQs disabled\n");
-		dev_priv->pc8.regsave.sdeimr &= ~interrupt_mask;
-		dev_priv->pc8.regsave.sdeimr |= (~enabled_irq_mask &
+		dev_priv->pm.regsave.sdeimr &= ~interrupt_mask;
+		dev_priv->pm.regsave.sdeimr |= (~enabled_irq_mask &
 						 interrupt_mask);
 		return;
 	}
@@ -1075,7 +1075,7 @@ void gen6_set_pm_mask(struct drm_i915_private *dev_priv,
 			     u32 pm_iir, int new_delay)
 {
 	if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
-		if (new_delay >= dev_priv->rps.max_delay) {
+		if (new_delay >= dev_priv->rps.max_freq_softlimit) {
 			/* Mask UP THRESHOLD Interrupts */
 			I915_WRITE(GEN6_PMINTRMSK,
 				   I915_READ(GEN6_PMINTRMSK) |
@@ -1090,7 +1090,7 @@ void gen6_set_pm_mask(struct drm_i915_private *dev_priv,
 			dev_priv->rps.rp_down_masked = false;
 		}
 	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
-		if (new_delay <= dev_priv->rps.min_delay) {
+		if (new_delay <= dev_priv->rps.min_freq_softlimit) {
 			/* Mask DOWN THRESHOLD Interrupts */
 			I915_WRITE(GEN6_PMINTRMSK,
 				   I915_READ(GEN6_PMINTRMSK) |
@@ -1136,38 +1136,39 @@ static void gen6_pm_rps_work(struct work_struct *work)
 			adj *= 2;
 		else
 			adj = 1;
-		new_delay = dev_priv->rps.cur_delay + adj;
+		new_delay = dev_priv->rps.cur_freq + adj;
 
 		/*
 		 * For better performance, jump directly
 		 * to RPe if we're below it.
 		 */
-		if (new_delay < dev_priv->rps.rpe_delay)
-			new_delay = dev_priv->rps.rpe_delay;
+		if (new_delay < dev_priv->rps.efficient_freq)
+			new_delay = dev_priv->rps.efficient_freq;
 	} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
-		if (dev_priv->rps.cur_delay > dev_priv->rps.rpe_delay)
-			new_delay = dev_priv->rps.rpe_delay;
+		if (dev_priv->rps.cur_freq > dev_priv->rps.efficient_freq)
+			new_delay = dev_priv->rps.efficient_freq;
 		else
-			new_delay = dev_priv->rps.min_delay;
+			new_delay = dev_priv->rps.min_freq_softlimit;
 		adj = 0;
 	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
 		if (adj < 0)
 			adj *= 2;
 		else
 			adj = -1;
-		new_delay = dev_priv->rps.cur_delay + adj;
+		new_delay = dev_priv->rps.cur_freq + adj;
 	} else { /* unknown event */
-		new_delay = dev_priv->rps.cur_delay;
+		new_delay = dev_priv->rps.cur_freq;
 	}
 
 	/* sysfs frequency interfaces may have snuck in while servicing the
 	 * interrupt
 	 */
 	new_delay = clamp_t(int, new_delay,
-			    dev_priv->rps.min_delay, dev_priv->rps.max_delay);
+			    dev_priv->rps.min_freq_softlimit,
+			    dev_priv->rps.max_freq_softlimit);
 
 	gen6_set_pm_mask(dev_priv, pm_iir, new_delay);
-	dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_delay;
+	dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_freq;
 
 	if (IS_VALLEYVIEW(dev_priv->dev))
 		valleyview_set_rps(dev_priv->dev, new_delay);
@@ -3074,7 +3075,7 @@ static void valleyview_display_irqs_uninstall(struct drm_i915_private *dev_priv)
 
 	iir_mask = I915_DISPLAY_PORT_INTERRUPT |
 		   I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		   I915_DISPLAY_PIPE_A_EVENT_INTERRUPT;
+		   I915_DISPLAY_PIPE_B_EVENT_INTERRUPT;
 
 	dev_priv->irq_mask |= iir_mask;
 	I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
@@ -4118,32 +4119,32 @@ void intel_hpd_init(struct drm_device *dev)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-/* Disable interrupts so we can allow Package C8+. */
-void hsw_pc8_disable_interrupts(struct drm_device *dev)
+/* Disable interrupts so we can allow runtime PM. */
+void hsw_runtime_pm_disable_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 
-	dev_priv->pc8.regsave.deimr = I915_READ(DEIMR);
-	dev_priv->pc8.regsave.sdeimr = I915_READ(SDEIMR);
-	dev_priv->pc8.regsave.gtimr = I915_READ(GTIMR);
-	dev_priv->pc8.regsave.gtier = I915_READ(GTIER);
-	dev_priv->pc8.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR);
+	dev_priv->pm.regsave.deimr = I915_READ(DEIMR);
+	dev_priv->pm.regsave.sdeimr = I915_READ(SDEIMR);
+	dev_priv->pm.regsave.gtimr = I915_READ(GTIMR);
+	dev_priv->pm.regsave.gtier = I915_READ(GTIER);
+	dev_priv->pm.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR);
 
 	ironlake_disable_display_irq(dev_priv, 0xffffffff);
 	ibx_disable_display_interrupt(dev_priv, 0xffffffff);
 	ilk_disable_gt_irq(dev_priv, 0xffffffff);
 	snb_disable_pm_irq(dev_priv, 0xffffffff);
 
-	dev_priv->pc8.irqs_disabled = true;
+	dev_priv->pm.irqs_disabled = true;
 
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-/* Restore interrupts so we can recover from Package C8+. */
-void hsw_pc8_restore_interrupts(struct drm_device *dev)
+/* Restore interrupts so we can recover from runtime PM. */
+void hsw_runtime_pm_restore_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
@@ -4163,13 +4164,13 @@ void hsw_pc8_restore_interrupts(struct drm_device *dev)
 	val = I915_READ(GEN6_PMIMR);
 	WARN(val != 0xffffffff, "GEN6_PMIMR is 0x%08x\n", val);
 
-	dev_priv->pc8.irqs_disabled = false;
+	dev_priv->pm.irqs_disabled = false;
 
-	ironlake_enable_display_irq(dev_priv, ~dev_priv->pc8.regsave.deimr);
-	ibx_enable_display_interrupt(dev_priv, ~dev_priv->pc8.regsave.sdeimr);
-	ilk_enable_gt_irq(dev_priv, ~dev_priv->pc8.regsave.gtimr);
-	snb_enable_pm_irq(dev_priv, ~dev_priv->pc8.regsave.gen6_pmimr);
-	I915_WRITE(GTIER, dev_priv->pc8.regsave.gtier);
+	ironlake_enable_display_irq(dev_priv, ~dev_priv->pm.regsave.deimr);
+	ibx_enable_display_interrupt(dev_priv, ~dev_priv->pm.regsave.sdeimr);
+	ilk_enable_gt_irq(dev_priv, ~dev_priv->pm.regsave.gtimr);
+	snb_enable_pm_irq(dev_priv, ~dev_priv->pm.regsave.gen6_pmimr);
+	I915_WRITE(GTIER, dev_priv->pm.regsave.gtier);
 
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index a66ffb652bee..d1d7980f0e01 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -42,8 +42,6 @@ struct i915_params i915 __read_mostly = {
 	.disable_power_well = 1,
 	.enable_ips = 1,
 	.fastboot = 0,
-	.enable_pc8 = 1,
-	.pc8_timeout = 5000,
 	.prefault_disable = 0,
 	.reset = true,
 	.invert_brightness = 0,
@@ -135,14 +133,6 @@ module_param_named(fastboot, i915.fastboot, bool, 0600);
 MODULE_PARM_DESC(fastboot,
 	"Try to skip unnecessary mode sets at boot time (default: false)");
 
-module_param_named(enable_pc8, i915.enable_pc8, int, 0600);
-MODULE_PARM_DESC(enable_pc8,
-	"Enable support for low power package C states (PC8+) (default: true)");
-
-module_param_named(pc8_timeout, i915.pc8_timeout, int, 0600);
-MODULE_PARM_DESC(pc8_timeout,
-	"Number of msecs of idleness required to enter PC8+ (default: 5000)");
-
 module_param_named(prefault_disable, i915.prefault_disable, bool, 0600);
 MODULE_PARM_DESC(prefault_disable,
 	"Disable page prefaulting for pread/pwrite/reloc (default:false). "
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 146609ab42bb..74f7d853eb58 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -748,6 +748,7 @@ enum punit_power_well {
 #define RING_INSTPS(base)	((base)+0x70)
 #define RING_DMA_FADD(base)	((base)+0x78)
 #define RING_INSTPM(base)	((base)+0xc0)
+#define RING_MI_MODE(base)	((base)+0x9c)
 #define INSTPS		0x02070 /* 965+ only */
 #define INSTDONE1	0x0207c /* 965+ only */
 #define ACTHD_I965	0x02074
@@ -824,6 +825,7 @@ enum punit_power_well {
 # define VS_TIMER_DISPATCH				(1 << 6)
 # define MI_FLUSH_ENABLE				(1 << 12)
 # define ASYNC_FLIP_PERF_DISABLE			(1 << 14)
+# define MODE_IDLE					(1 << 9)
 
 #define GEN6_GT_MODE	0x20d0
 #define GEN7_GT_MODE	0x7008
@@ -3551,7 +3553,11 @@ enum punit_power_well {
 /* New style CUR*CNTR flags */
 #define   CURSOR_MODE		0x27
 #define   CURSOR_MODE_DISABLE   0x00
+#define   CURSOR_MODE_128_32B_AX 0x02
+#define   CURSOR_MODE_256_32B_AX 0x03
 #define   CURSOR_MODE_64_32B_AX 0x07
+#define   CURSOR_MODE_128_ARGB_AX ((1 << 5) | CURSOR_MODE_128_32B_AX)
+#define   CURSOR_MODE_256_ARGB_AX ((1 << 5) | CURSOR_MODE_256_32B_AX)
 #define   CURSOR_MODE_64_ARGB_AX ((1 << 5) | CURSOR_MODE_64_32B_AX)
 #define   MCURSOR_PIPE_SELECT	(1 << 28)
 #define   MCURSOR_PIPE_A	0x00
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 0c741f4eefb0..9c57029f6f4b 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -269,7 +269,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 		ret = vlv_gpu_freq(dev_priv, (freq >> 8) & 0xff);
 	} else {
-		ret = dev_priv->rps.cur_delay * GT_FREQUENCY_MULTIPLIER;
+		ret = dev_priv->rps.cur_freq * GT_FREQUENCY_MULTIPLIER;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -284,7 +284,7 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay));
+			vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq));
 }
 
 static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
@@ -298,9 +298,9 @@ static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev))
-		ret = vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay);
+		ret = vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq_softlimit);
 	else
-		ret = dev_priv->rps.max_delay * GT_FREQUENCY_MULTIPLIER;
+		ret = dev_priv->rps.max_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", ret);
@@ -313,7 +313,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val, rp_state_cap, hw_max, hw_min, non_oc_max;
+	u32 val;
 	ssize_t ret;
 
 	ret = kstrtou32(buf, 0, &val);
@@ -324,44 +324,35 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
-	if (IS_VALLEYVIEW(dev_priv->dev)) {
+	if (IS_VALLEYVIEW(dev_priv->dev))
 		val = vlv_freq_opcode(dev_priv, val);
-
-		hw_max = valleyview_rps_max_freq(dev_priv);
-		hw_min = valleyview_rps_min_freq(dev_priv);
-		non_oc_max = hw_max;
-	} else {
+	else
 		val /= GT_FREQUENCY_MULTIPLIER;
 
-		rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		hw_max = dev_priv->rps.hw_max;
-		non_oc_max = (rp_state_cap & 0xff);
-		hw_min = ((rp_state_cap & 0xff0000) >> 16);
-	}
-
-	if (val < hw_min || val > hw_max ||
-	    val < dev_priv->rps.min_delay) {
+	if (val < dev_priv->rps.min_freq ||
+	    val > dev_priv->rps.max_freq ||
+	    val < dev_priv->rps.min_freq_softlimit) {
 		mutex_unlock(&dev_priv->rps.hw_lock);
 		return -EINVAL;
 	}
 
-	if (val > non_oc_max)
+	if (val > dev_priv->rps.rp0_freq)
 		DRM_DEBUG("User requested overclocking to %d\n",
 			  val * GT_FREQUENCY_MULTIPLIER);
 
-	dev_priv->rps.max_delay = val;
+	dev_priv->rps.max_freq_softlimit = val;
 
-	if (dev_priv->rps.cur_delay > val) {
+	if (dev_priv->rps.cur_freq > val) {
 		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev, val);
 		else
 			gen6_set_rps(dev, val);
+	} else if (!IS_VALLEYVIEW(dev)) {
+		/* We still need gen6_set_rps to process the new max_delay and
+		 * update the interrupt limits even though frequency request is
+		 * unchanged. */
+		gen6_set_rps(dev, dev_priv->rps.cur_freq);
 	}
-	else if (!IS_VALLEYVIEW(dev))
-		/* We still need gen6_set_rps to process the new max_delay
-		   and update the interrupt limits even though frequency
-		   request is unchanged. */
-		gen6_set_rps(dev, dev_priv->rps.cur_delay);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -379,9 +370,9 @@ static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev))
-		ret = vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay);
+		ret = vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq_softlimit);
 	else
-		ret = dev_priv->rps.min_delay * GT_FREQUENCY_MULTIPLIER;
+		ret = dev_priv->rps.min_freq_softlimit * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", ret);
@@ -394,7 +385,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val, rp_state_cap, hw_max, hw_min;
+	u32 val;
 	ssize_t ret;
 
 	ret = kstrtou32(buf, 0, &val);
@@ -405,37 +396,31 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
-	if (IS_VALLEYVIEW(dev)) {
+	if (IS_VALLEYVIEW(dev))
 		val = vlv_freq_opcode(dev_priv, val);
-
-		hw_max = valleyview_rps_max_freq(dev_priv);
-		hw_min = valleyview_rps_min_freq(dev_priv);
-	} else {
+	else
 		val /= GT_FREQUENCY_MULTIPLIER;
 
-		rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		hw_max = dev_priv->rps.hw_max;
-		hw_min = ((rp_state_cap & 0xff0000) >> 16);
-	}
-
-	if (val < hw_min || val > hw_max || val > dev_priv->rps.max_delay) {
+	if (val < dev_priv->rps.min_freq ||
+	    val > dev_priv->rps.max_freq ||
+	    val > dev_priv->rps.max_freq_softlimit) {
 		mutex_unlock(&dev_priv->rps.hw_lock);
 		return -EINVAL;
 	}
 
-	dev_priv->rps.min_delay = val;
+	dev_priv->rps.min_freq_softlimit = val;
 
-	if (dev_priv->rps.cur_delay < val) {
+	if (dev_priv->rps.cur_freq < val) {
 		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev, val);
 		else
 			gen6_set_rps(dev, val);
+	} else if (!IS_VALLEYVIEW(dev)) {
+		/* We still need gen6_set_rps to process the new min_delay and
+		 * update the interrupt limits even though frequency request is
+		 * unchanged. */
+		gen6_set_rps(dev, dev_priv->rps.cur_freq);
 	}
-	else if (!IS_VALLEYVIEW(dev))
-		/* We still need gen6_set_rps to process the new min_delay
-		   and update the interrupt limits even though frequency
-		   request is unchanged. */
-		gen6_set_rps(dev, dev_priv->rps.cur_delay);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index b95a380958db..23c26f1f8b37 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -238,14 +238,16 @@ TRACE_EVENT(i915_gem_evict_vm,
 	    TP_ARGS(vm),
 
 	    TP_STRUCT__entry(
+			     __field(u32, dev)
 			     __field(struct i915_address_space *, vm)
 			    ),
 
 	    TP_fast_assign(
+			   __entry->dev = vm->dev->primary->index;
 			   __entry->vm = vm;
 			  ),
 
-	    TP_printk("dev=%d, vm=%p", __entry->vm->dev->primary->index, __entry->vm)
+	    TP_printk("dev=%d, vm=%p", __entry->dev, __entry->vm)
 );
 
 TRACE_EVENT(i915_gem_ring_sync_to,
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 4ef6d69c078d..4b4e8f0f9621 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -839,7 +839,7 @@ void intel_crt_init(struct drm_device *dev)
 	intel_connector_attach_encoder(intel_connector, &crt->base);
 
 	crt->base.type = INTEL_OUTPUT_ANALOG;
-	crt->base.cloneable = true;
+	crt->base.cloneable = (1 << INTEL_OUTPUT_DVO) | (1 << INTEL_OUTPUT_HDMI);
 	if (IS_I830(dev))
 		crt->base.crtc_mask = (1 << 0);
 	else
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e2665e09d5df..070bf2e78d61 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1340,6 +1340,7 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder)
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+		intel_edp_panel_vdd_on(intel_dp);
 		intel_edp_panel_off(intel_dp);
 	}
 
@@ -1717,7 +1718,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 
 	intel_encoder->type = INTEL_OUTPUT_UNKNOWN;
 	intel_encoder->crtc_mask =  (1 << 0) | (1 << 1) | (1 << 2);
-	intel_encoder->cloneable = false;
+	intel_encoder->cloneable = 0;
 	intel_encoder->hot_plug = intel_ddi_hot_plug;
 
 	if (init_dp)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3ffe5a6124f1..6332383abae9 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -741,7 +741,7 @@ bool intel_crtc_active(struct drm_crtc *crtc)
 	 * We can ditch the adjusted_mode.crtc_clock check as soon
 	 * as Haswell has gained clock readout/fastboot support.
 	 *
-	 * We can ditch the crtc->fb check as soon as we can
+	 * We can ditch the crtc->primary->fb check as soon as we can
 	 * properly reconstruct framebuffers.
 	 */
 	return intel_crtc->active && crtc->primary->fb &&
@@ -1166,7 +1166,7 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 	if (INTEL_INFO(dev)->gen >= 4) {
 		reg = DSPCNTR(pipe);
 		val = I915_READ(reg);
-		WARN((val & DISPLAY_PLANE_ENABLE),
+		WARN(val & DISPLAY_PLANE_ENABLE,
 		     "plane %c assertion failure, should be disabled but not\n",
 		     plane_name(pipe));
 		return;
@@ -1195,20 +1195,20 @@ static void assert_sprites_disabled(struct drm_i915_private *dev_priv,
 		for_each_sprite(pipe, sprite) {
 			reg = SPCNTR(pipe, sprite);
 			val = I915_READ(reg);
-			WARN((val & SP_ENABLE),
+			WARN(val & SP_ENABLE,
 			     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
 			     sprite_name(pipe, sprite), pipe_name(pipe));
 		}
 	} else if (INTEL_INFO(dev)->gen >= 7) {
 		reg = SPRCTL(pipe);
 		val = I915_READ(reg);
-		WARN((val & SPRITE_ENABLE),
+		WARN(val & SPRITE_ENABLE,
 		     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
 		     plane_name(pipe), pipe_name(pipe));
 	} else if (INTEL_INFO(dev)->gen >= 5) {
 		reg = DVSCNTR(pipe);
 		val = I915_READ(reg);
-		WARN((val & DVS_ENABLE),
+		WARN(val & DVS_ENABLE,
 		     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
 		     plane_name(pipe), pipe_name(pipe));
 	}
@@ -1872,15 +1872,15 @@ void intel_flush_primary_plane(struct drm_i915_private *dev_priv,
 }
 
 /**
- * intel_enable_primary_plane - enable the primary plane on a given pipe
+ * intel_enable_primary_hw_plane - enable the primary plane on a given pipe
  * @dev_priv: i915 private structure
  * @plane: plane to enable
  * @pipe: pipe being fed
  *
  * Enable @plane on @pipe, making sure that @pipe is running first.
  */
-static void intel_enable_primary_plane(struct drm_i915_private *dev_priv,
-				       enum plane plane, enum pipe pipe)
+static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv,
+					  enum plane plane, enum pipe pipe)
 {
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
@@ -1905,15 +1905,15 @@ static void intel_enable_primary_plane(struct drm_i915_private *dev_priv,
 }
 
 /**
- * intel_disable_primary_plane - disable the primary plane
+ * intel_disable_primary_hw_plane - disable the primary hardware plane
  * @dev_priv: i915 private structure
  * @plane: plane to disable
  * @pipe: pipe consuming the data
  *
  * Disable @plane; should be an independent operation.
  */
-static void intel_disable_primary_plane(struct drm_i915_private *dev_priv,
-					enum plane plane, enum pipe pipe)
+static void intel_disable_primary_hw_plane(struct drm_i915_private *dev_priv,
+					   enum plane plane, enum pipe pipe)
 {
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
@@ -2047,8 +2047,114 @@ unsigned long intel_gen4_compute_page_offset(int *x, int *y,
 	}
 }
 
-static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-			     int x, int y)
+int intel_format_to_fourcc(int format)
+{
+	switch (format) {
+	case DISPPLANE_8BPP:
+		return DRM_FORMAT_C8;
+	case DISPPLANE_BGRX555:
+		return DRM_FORMAT_XRGB1555;
+	case DISPPLANE_BGRX565:
+		return DRM_FORMAT_RGB565;
+	default:
+	case DISPPLANE_BGRX888:
+		return DRM_FORMAT_XRGB8888;
+	case DISPPLANE_RGBX888:
+		return DRM_FORMAT_XBGR8888;
+	case DISPPLANE_BGRX101010:
+		return DRM_FORMAT_XRGB2101010;
+	case DISPPLANE_RGBX101010:
+		return DRM_FORMAT_XBGR2101010;
+	}
+}
+
+static bool intel_alloc_plane_obj(struct intel_crtc *crtc,
+				  struct intel_plane_config *plane_config)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_gem_object *obj = NULL;
+	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
+	u32 base = plane_config->base;
+
+	if (plane_config->size == 0)
+		return false;
+
+	obj = i915_gem_object_create_stolen_for_preallocated(dev, base, base,
+							     plane_config->size);
+	if (!obj)
+		return false;
+
+	if (plane_config->tiled) {
+		obj->tiling_mode = I915_TILING_X;
+		obj->stride = crtc->base.primary->fb->pitches[0];
+	}
+
+	mode_cmd.pixel_format = crtc->base.primary->fb->pixel_format;
+	mode_cmd.width = crtc->base.primary->fb->width;
+	mode_cmd.height = crtc->base.primary->fb->height;
+	mode_cmd.pitches[0] = crtc->base.primary->fb->pitches[0];
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (intel_framebuffer_init(dev, to_intel_framebuffer(crtc->base.primary->fb),
+				   &mode_cmd, obj)) {
+		DRM_DEBUG_KMS("intel fb init failed\n");
+		goto out_unref_obj;
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+
+	DRM_DEBUG_KMS("plane fb obj %p\n", obj);
+	return true;
+
+out_unref_obj:
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+	return false;
+}
+
+static void intel_find_plane_obj(struct intel_crtc *intel_crtc,
+				 struct intel_plane_config *plane_config)
+{
+	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_crtc *c;
+	struct intel_crtc *i;
+	struct intel_framebuffer *fb;
+
+	if (!intel_crtc->base.primary->fb)
+		return;
+
+	if (intel_alloc_plane_obj(intel_crtc, plane_config))
+		return;
+
+	kfree(intel_crtc->base.primary->fb);
+	intel_crtc->base.primary->fb = NULL;
+
+	/*
+	 * Failed to alloc the obj, check to see if we should share
+	 * an fb with another CRTC instead
+	 */
+	list_for_each_entry(c, &dev->mode_config.crtc_list, head) {
+		i = to_intel_crtc(c);
+
+		if (c == &intel_crtc->base)
+			continue;
+
+		if (!i->active || !c->primary->fb)
+			continue;
+
+		fb = to_intel_framebuffer(c->primary->fb);
+		if (i915_gem_obj_ggtt_offset(fb->obj) == plane_config->base) {
+			drm_framebuffer_reference(c->primary->fb);
+			intel_crtc->base.primary->fb = c->primary->fb;
+			break;
+		}
+	}
+}
+
+static int i9xx_update_primary_plane(struct drm_crtc *crtc,
+				     struct drm_framebuffer *fb,
+				     int x, int y)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2147,8 +2253,9 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	return 0;
 }
 
-static int ironlake_update_plane(struct drm_crtc *crtc,
-				 struct drm_framebuffer *fb, int x, int y)
+static int ironlake_update_primary_plane(struct drm_crtc *crtc,
+					 struct drm_framebuffer *fb,
+					 int x, int y)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2252,7 +2359,7 @@ intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		dev_priv->display.disable_fbc(dev);
 	intel_increase_pllclock(crtc);
 
-	return dev_priv->display.update_plane(crtc, fb, x, y);
+	return dev_priv->display.update_primary_plane(crtc, fb, x, y);
 }
 
 void intel_display_handle_reset(struct drm_device *dev)
@@ -2289,11 +2396,13 @@ void intel_display_handle_reset(struct drm_device *dev)
 		/*
 		 * FIXME: Once we have proper support for primary planes (and
 		 * disabling them without disabling the entire crtc) allow again
-		 * a NULL crtc->fb.
+		 * a NULL crtc->primary->fb.
 		 */
 		if (intel_crtc->active && crtc->primary->fb)
-			dev_priv->display.update_plane(crtc, crtc->primary->fb,
-						       crtc->x, crtc->y);
+			dev_priv->display.update_primary_plane(crtc,
+							       crtc->primary->fb,
+							       crtc->x,
+							       crtc->y);
 		mutex_unlock(&crtc->mutex);
 	}
 }
@@ -2372,8 +2481,8 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	ret = intel_pin_and_fence_fb_obj(dev,
 					 to_intel_framebuffer(fb)->obj,
 					 NULL);
+	mutex_unlock(&dev->struct_mutex);
 	if (ret != 0) {
-		mutex_unlock(&dev->struct_mutex);
 		DRM_ERROR("pin & fence failed\n");
 		return ret;
 	}
@@ -2409,8 +2518,9 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		intel_crtc->config.pipe_src_h = adjusted_mode->crtc_vdisplay;
 	}
 
-	ret = dev_priv->display.update_plane(crtc, fb, x, y);
+	ret = dev_priv->display.update_primary_plane(crtc, fb, x, y);
 	if (ret) {
+		mutex_lock(&dev->struct_mutex);
 		intel_unpin_fb_obj(to_intel_framebuffer(fb)->obj);
 		mutex_unlock(&dev->struct_mutex);
 		DRM_ERROR("failed to update base address\n");
@@ -2425,9 +2535,12 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	if (old_fb) {
 		if (intel_crtc->active && old_fb != fb)
 			intel_wait_for_vblank(dev, intel_crtc->pipe);
+		mutex_lock(&dev->struct_mutex);
 		intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj);
+		mutex_unlock(&dev->struct_mutex);
 	}
 
+	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
 	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
@@ -3592,7 +3705,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 
 	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
-	intel_enable_primary_plane(dev_priv, plane, pipe);
+	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
 	intel_crtc_update_cursor(crtc, true);
 
@@ -3634,7 +3747,7 @@ static void haswell_crtc_enable_planes(struct drm_crtc *crtc)
 	int pipe = intel_crtc->pipe;
 	int plane = intel_crtc->plane;
 
-	intel_enable_primary_plane(dev_priv, plane, pipe);
+	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
 	intel_crtc_update_cursor(crtc, true);
 
@@ -3664,7 +3777,7 @@ static void haswell_crtc_disable_planes(struct drm_crtc *crtc)
 
 	intel_crtc_update_cursor(crtc, false);
 	intel_disable_planes(crtc);
-	intel_disable_primary_plane(dev_priv, plane, pipe);
+	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
 }
 
 /*
@@ -3792,7 +3905,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 
 	intel_crtc_update_cursor(crtc, false);
 	intel_disable_planes(crtc);
-	intel_disable_primary_plane(dev_priv, plane, pipe);
+	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
 
 	if (intel_crtc->config.has_pch_encoder)
 		intel_set_pch_fifo_underrun_reporting(dev, pipe, false);
@@ -4275,7 +4388,7 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
-	intel_enable_primary_plane(dev_priv, plane, pipe);
+	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
 	intel_crtc_update_cursor(crtc, true);
 
@@ -4314,7 +4427,7 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
-	intel_enable_primary_plane(dev_priv, plane, pipe);
+	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
 	/* The fixup needs to happen before cursor is enabled */
 	if (IS_G4X(dev))
@@ -4370,7 +4483,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 	intel_crtc_dpms_overlay(intel_crtc, false);
 	intel_crtc_update_cursor(crtc, false);
 	intel_disable_planes(crtc);
-	intel_disable_primary_plane(dev_priv, plane, pipe);
+	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
 
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, false);
 	intel_disable_pipe(dev_priv, pipe);
@@ -5611,6 +5724,67 @@ static void vlv_crtc_clock_get(struct intel_crtc *crtc,
 	pipe_config->port_clock = clock.dot / 5;
 }
 
+static void i9xx_get_plane_config(struct intel_crtc *crtc,
+				  struct intel_plane_config *plane_config)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val, base, offset;
+	int pipe = crtc->pipe, plane = crtc->plane;
+	int fourcc, pixel_format;
+	int aligned_height;
+
+	crtc->base.primary->fb = kzalloc(sizeof(struct intel_framebuffer), GFP_KERNEL);
+	if (!crtc->base.primary->fb) {
+		DRM_DEBUG_KMS("failed to alloc fb\n");
+		return;
+	}
+
+	val = I915_READ(DSPCNTR(plane));
+
+	if (INTEL_INFO(dev)->gen >= 4)
+		if (val & DISPPLANE_TILED)
+			plane_config->tiled = true;
+
+	pixel_format = val & DISPPLANE_PIXFORMAT_MASK;
+	fourcc = intel_format_to_fourcc(pixel_format);
+	crtc->base.primary->fb->pixel_format = fourcc;
+	crtc->base.primary->fb->bits_per_pixel =
+		drm_format_plane_cpp(fourcc, 0) * 8;
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		if (plane_config->tiled)
+			offset = I915_READ(DSPTILEOFF(plane));
+		else
+			offset = I915_READ(DSPLINOFF(plane));
+		base = I915_READ(DSPSURF(plane)) & 0xfffff000;
+	} else {
+		base = I915_READ(DSPADDR(plane));
+	}
+	plane_config->base = base;
+
+	val = I915_READ(PIPESRC(pipe));
+	crtc->base.primary->fb->width = ((val >> 16) & 0xfff) + 1;
+	crtc->base.primary->fb->height = ((val >> 0) & 0xfff) + 1;
+
+	val = I915_READ(DSPSTRIDE(pipe));
+	crtc->base.primary->fb->pitches[0] = val & 0xffffff80;
+
+	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
+					    plane_config->tiled);
+
+	plane_config->size = ALIGN(crtc->base.primary->fb->pitches[0] *
+				   aligned_height, PAGE_SIZE);
+
+	DRM_DEBUG_KMS("pipe/plane %d/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
+		      pipe, plane, crtc->base.primary->fb->width,
+		      crtc->base.primary->fb->height,
+		      crtc->base.primary->fb->bits_per_pixel, base,
+		      crtc->base.primary->fb->pitches[0],
+		      plane_config->size);
+
+}
+
 static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 				 struct intel_crtc_config *pipe_config)
 {
@@ -6558,6 +6732,66 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc,
 	}
 }
 
+static void ironlake_get_plane_config(struct intel_crtc *crtc,
+				      struct intel_plane_config *plane_config)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val, base, offset;
+	int pipe = crtc->pipe, plane = crtc->plane;
+	int fourcc, pixel_format;
+	int aligned_height;
+
+	crtc->base.primary->fb = kzalloc(sizeof(struct intel_framebuffer), GFP_KERNEL);
+	if (!crtc->base.primary->fb) {
+		DRM_DEBUG_KMS("failed to alloc fb\n");
+		return;
+	}
+
+	val = I915_READ(DSPCNTR(plane));
+
+	if (INTEL_INFO(dev)->gen >= 4)
+		if (val & DISPPLANE_TILED)
+			plane_config->tiled = true;
+
+	pixel_format = val & DISPPLANE_PIXFORMAT_MASK;
+	fourcc = intel_format_to_fourcc(pixel_format);
+	crtc->base.primary->fb->pixel_format = fourcc;
+	crtc->base.primary->fb->bits_per_pixel =
+		drm_format_plane_cpp(fourcc, 0) * 8;
+
+	base = I915_READ(DSPSURF(plane)) & 0xfffff000;
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+		offset = I915_READ(DSPOFFSET(plane));
+	} else {
+		if (plane_config->tiled)
+			offset = I915_READ(DSPTILEOFF(plane));
+		else
+			offset = I915_READ(DSPLINOFF(plane));
+	}
+	plane_config->base = base;
+
+	val = I915_READ(PIPESRC(pipe));
+	crtc->base.primary->fb->width = ((val >> 16) & 0xfff) + 1;
+	crtc->base.primary->fb->height = ((val >> 0) & 0xfff) + 1;
+
+	val = I915_READ(DSPSTRIDE(pipe));
+	crtc->base.primary->fb->pitches[0] = val & 0xffffff80;
+
+	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
+					    plane_config->tiled);
+
+	plane_config->size = ALIGN(crtc->base.primary->fb->pitches[0] *
+				   aligned_height, PAGE_SIZE);
+
+	DRM_DEBUG_KMS("pipe/plane %d/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
+		      pipe, plane, crtc->base.primary->fb->width,
+		      crtc->base.primary->fb->height,
+		      crtc->base.primary->fb->bits_per_pixel, base,
+		      crtc->base.primary->fb->pitches[0],
+		      plane_config->size);
+}
+
 static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 				     struct intel_crtc_config *pipe_config)
 {
@@ -6732,6 +6966,7 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
 static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 {
 	uint32_t val;
+	unsigned long irqflags;
 
 	val = I915_READ(LCPLL_CTL);
 
@@ -6739,9 +6974,22 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 		    LCPLL_POWER_DOWN_ALLOW)) == LCPLL_PLL_LOCK)
 		return;
 
-	/* Make sure we're not on PC8 state before disabling PC8, otherwise
-	 * we'll hang the machine! */
-	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+	/*
+	 * Make sure we're not on PC8 state before disabling PC8, otherwise
+	 * we'll hang the machine. To prevent PC8 state, just enable force_wake.
+	 *
+	 * The other problem is that hsw_restore_lcpll() is called as part of
+	 * the runtime PM resume sequence, so we can't just call
+	 * gen6_gt_force_wake_get() because that function calls
+	 * intel_runtime_pm_get(), and we can't change the runtime PM refcount
+	 * while we are on the resume sequence. So to solve this problem we have
+	 * to call special forcewake code that doesn't touch runtime PM and
+	 * doesn't enable the forcewake delayed work.
+	 */
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (dev_priv->uncore.forcewake_count++ == 0)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
 	if (val & LCPLL_POWER_DOWN_ALLOW) {
 		val &= ~LCPLL_POWER_DOWN_ALLOW;
@@ -6775,26 +7023,45 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 			DRM_ERROR("Switching back to LCPLL failed\n");
 	}
 
-	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+	/* See the big comment above. */
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (--dev_priv->uncore.forcewake_count == 0)
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
-void hsw_enable_pc8_work(struct work_struct *__work)
+/*
+ * Package states C8 and deeper are really deep PC states that can only be
+ * reached when all the devices on the system allow it, so even if the graphics
+ * device allows PC8+, it doesn't mean the system will actually get to these
+ * states. Our driver only allows PC8+ when going into runtime PM.
+ *
+ * The requirements for PC8+ are that all the outputs are disabled, the power
+ * well is disabled and most interrupts are disabled, and these are also
+ * requirements for runtime PM. When these conditions are met, we manually do
+ * the other conditions: disable the interrupts, clocks and switch LCPLL refclk
+ * to Fclk. If we're in PC8+ and we get an non-hotplug interrupt, we can hard
+ * hang the machine.
+ *
+ * When we really reach PC8 or deeper states (not just when we allow it) we lose
+ * the state of some registers, so when we come back from PC8+ we need to
+ * restore this state. We don't get into PC8+ if we're not in RC6, so we don't
+ * need to take care of the registers kept by RC6. Notice that this happens even
+ * if we don't put the device in PCI D3 state (which is what currently happens
+ * because of the runtime PM support).
+ *
+ * For more, read "Display Sequences for Package C8" on the hardware
+ * documentation.
+ */
+void hsw_enable_pc8(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv =
-		container_of(to_delayed_work(__work), struct drm_i915_private,
-			     pc8.enable_work);
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t val;
 
 	WARN_ON(!HAS_PC8(dev));
 
-	if (dev_priv->pc8.enabled)
-		return;
-
 	DRM_DEBUG_KMS("Enabling package C8+\n");
 
-	dev_priv->pc8.enabled = true;
-
 	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
 		val = I915_READ(SOUTH_DSPCLK_GATE_D);
 		val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
@@ -6802,51 +7069,21 @@ void hsw_enable_pc8_work(struct work_struct *__work)
 	}
 
 	lpt_disable_clkout_dp(dev);
-	hsw_pc8_disable_interrupts(dev);
+	hsw_runtime_pm_disable_interrupts(dev);
 	hsw_disable_lcpll(dev_priv, true, true);
-
-	intel_runtime_pm_put(dev_priv);
 }
 
-static void __hsw_enable_package_c8(struct drm_i915_private *dev_priv)
-{
-	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
-	WARN(dev_priv->pc8.disable_count < 1,
-	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
-
-	dev_priv->pc8.disable_count--;
-	if (dev_priv->pc8.disable_count != 0)
-		return;
-
-	schedule_delayed_work(&dev_priv->pc8.enable_work,
-			      msecs_to_jiffies(i915.pc8_timeout));
-}
-
-static void __hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t val;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
-	WARN(dev_priv->pc8.disable_count < 0,
-	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
-
-	dev_priv->pc8.disable_count++;
-	if (dev_priv->pc8.disable_count != 1)
-		return;
-
 	WARN_ON(!HAS_PC8(dev));
 
-	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
-	if (!dev_priv->pc8.enabled)
-		return;
-
 	DRM_DEBUG_KMS("Disabling package C8+\n");
 
-	intel_runtime_pm_get(dev_priv);
-
 	hsw_restore_lcpll(dev_priv);
-	hsw_pc8_restore_interrupts(dev);
+	hsw_runtime_pm_restore_interrupts(dev);
 	lpt_init_pch_refclk(dev);
 
 	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
@@ -6860,89 +7097,11 @@ static void __hsw_disable_package_c8(struct drm_i915_private *dev_priv)
 	mutex_lock(&dev_priv->rps.hw_lock);
 	gen6_update_ring_freq(dev);
 	mutex_unlock(&dev_priv->rps.hw_lock);
-	dev_priv->pc8.enabled = false;
-}
-
-void hsw_enable_package_c8(struct drm_i915_private *dev_priv)
-{
-	if (!HAS_PC8(dev_priv->dev))
-		return;
-
-	mutex_lock(&dev_priv->pc8.lock);
-	__hsw_enable_package_c8(dev_priv);
-	mutex_unlock(&dev_priv->pc8.lock);
-}
-
-void hsw_disable_package_c8(struct drm_i915_private *dev_priv)
-{
-	if (!HAS_PC8(dev_priv->dev))
-		return;
-
-	mutex_lock(&dev_priv->pc8.lock);
-	__hsw_disable_package_c8(dev_priv);
-	mutex_unlock(&dev_priv->pc8.lock);
-}
-
-static bool hsw_can_enable_package_c8(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-	struct intel_crtc *crtc;
-	uint32_t val;
-
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
-		if (crtc->base.enabled)
-			return false;
-
-	/* This case is still possible since we have the i915.disable_power_well
-	 * parameter and also the KVMr or something else might be requesting the
-	 * power well. */
-	val = I915_READ(HSW_PWR_WELL_DRIVER);
-	if (val != 0) {
-		DRM_DEBUG_KMS("Not enabling PC8: power well on\n");
-		return false;
-	}
-
-	return true;
-}
-
-/* Since we're called from modeset_global_resources there's no way to
- * symmetrically increase and decrease the refcount, so we use
- * dev_priv->pc8.requirements_met to track whether we already have the refcount
- * or not.
- */
-static void hsw_update_package_c8(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	bool allow;
-
-	if (!HAS_PC8(dev_priv->dev))
-		return;
-
-	if (!i915.enable_pc8)
-		return;
-
-	mutex_lock(&dev_priv->pc8.lock);
-
-	allow = hsw_can_enable_package_c8(dev_priv);
-
-	if (allow == dev_priv->pc8.requirements_met)
-		goto done;
-
-	dev_priv->pc8.requirements_met = allow;
-
-	if (allow)
-		__hsw_enable_package_c8(dev_priv);
-	else
-		__hsw_disable_package_c8(dev_priv);
-
-done:
-	mutex_unlock(&dev_priv->pc8.lock);
 }
 
 static void haswell_modeset_global_resources(struct drm_device *dev)
 {
 	modeset_update_crtc_power_domains(dev);
-	hsw_update_package_c8(dev);
 }
 
 static int haswell_crtc_mode_set(struct drm_crtc *crtc,
@@ -7446,10 +7605,26 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 	bool visible = base != 0;
 
 	if (intel_crtc->cursor_visible != visible) {
+		int16_t width = intel_crtc->cursor_width;
 		uint32_t cntl = I915_READ(CURCNTR(pipe));
 		if (base) {
 			cntl &= ~(CURSOR_MODE | MCURSOR_PIPE_SELECT);
-			cntl |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE;
+			cntl |= MCURSOR_GAMMA_ENABLE;
+
+			switch (width) {
+			case 64:
+				cntl |= CURSOR_MODE_64_ARGB_AX;
+				break;
+			case 128:
+				cntl |= CURSOR_MODE_128_ARGB_AX;
+				break;
+			case 256:
+				cntl |= CURSOR_MODE_256_ARGB_AX;
+				break;
+			default:
+				WARN_ON(1);
+				return;
+			}
 			cntl |= pipe << 28; /* Connect to correct pipe */
 		} else {
 			cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE);
@@ -7474,10 +7649,25 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
 	bool visible = base != 0;
 
 	if (intel_crtc->cursor_visible != visible) {
+		int16_t width = intel_crtc->cursor_width;
 		uint32_t cntl = I915_READ(CURCNTR_IVB(pipe));
 		if (base) {
 			cntl &= ~CURSOR_MODE;
-			cntl |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE;
+			cntl |= MCURSOR_GAMMA_ENABLE;
+			switch (width) {
+			case 64:
+				cntl |= CURSOR_MODE_64_ARGB_AX;
+				break;
+			case 128:
+				cntl |= CURSOR_MODE_128_ARGB_AX;
+				break;
+			case 256:
+				cntl |= CURSOR_MODE_256_ARGB_AX;
+				break;
+			default:
+				WARN_ON(1);
+				return;
+			}
 		} else {
 			cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE);
 			cntl |= CURSOR_MODE_DISABLE;
@@ -7573,9 +7763,11 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 		goto finish;
 	}
 
-	/* Currently we only support 64x64 cursors */
-	if (width != 64 || height != 64) {
-		DRM_ERROR("we currently only support 64x64 cursors\n");
+	/* Check for which cursor types we support */
+	if (!((width == 64 && height == 64) ||
+			(width == 128 && height == 128 && !IS_GEN2(dev)) ||
+			(width == 256 && height == 256 && !IS_GEN2(dev)))) {
+		DRM_DEBUG("Cursor dimension not supported\n");
 		return -EINVAL;
 	}
 
@@ -8230,7 +8422,7 @@ void intel_mark_busy(struct drm_device *dev)
 	if (dev_priv->mm.busy)
 		return;
 
-	hsw_disable_package_c8(dev_priv);
+	intel_runtime_pm_get(dev_priv);
 	i915_update_gfx_val(dev_priv);
 	dev_priv->mm.busy = true;
 }
@@ -8259,7 +8451,7 @@ void intel_mark_idle(struct drm_device *dev)
 		gen6_rps_idle(dev->dev_private);
 
 out:
-	hsw_enable_package_c8(dev_priv);
+	intel_runtime_pm_put(dev_priv);
 }
 
 void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
@@ -9015,23 +9207,47 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 	DRM_DEBUG_KMS("double wide: %i\n", pipe_config->double_wide);
 }
 
-static bool check_encoder_cloning(struct drm_crtc *crtc)
+static bool encoders_cloneable(const struct intel_encoder *a,
+			       const struct intel_encoder *b)
 {
-	int num_encoders = 0;
-	bool uncloneable_encoders = false;
-	struct intel_encoder *encoder;
+	/* masks could be asymmetric, so check both ways */
+	return a == b || (a->cloneable & (1 << b->type) &&
+			  b->cloneable & (1 << a->type));
+}
 
-	list_for_each_entry(encoder, &crtc->dev->mode_config.encoder_list,
-			    base.head) {
-		if (&encoder->new_crtc->base != crtc)
+static bool check_single_encoder_cloning(struct intel_crtc *crtc,
+					 struct intel_encoder *encoder)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct intel_encoder *source_encoder;
+
+	list_for_each_entry(source_encoder,
+			    &dev->mode_config.encoder_list, base.head) {
+		if (source_encoder->new_crtc != crtc)
 			continue;
 
-		num_encoders++;
-		if (!encoder->cloneable)
-			uncloneable_encoders = true;
+		if (!encoders_cloneable(encoder, source_encoder))
+			return false;
 	}
 
-	return !(num_encoders > 1 && uncloneable_encoders);
+	return true;
+}
+
+static bool check_encoder_cloning(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct intel_encoder *encoder;
+
+	list_for_each_entry(encoder,
+			    &dev->mode_config.encoder_list, base.head) {
+		if (encoder->new_crtc != crtc)
+			continue;
+
+		if (!check_single_encoder_cloning(crtc, encoder))
+			return false;
+	}
+
+	return true;
 }
 
 static struct intel_crtc_config *
@@ -9045,7 +9261,7 @@ intel_modeset_pipe_config(struct drm_crtc *crtc,
 	int plane_bpp, ret = -EINVAL;
 	bool retry = true;
 
-	if (!check_encoder_cloning(crtc)) {
+	if (!check_encoder_cloning(to_intel_crtc(crtc))) {
 		DRM_DEBUG_KMS("rejecting invalid cloning configuration\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -10337,6 +10553,16 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 
 	drm_crtc_init(dev, &intel_crtc->base, &intel_crtc_funcs);
 
+	if (IS_GEN2(dev)) {
+		intel_crtc->max_cursor_width = GEN2_CURSOR_WIDTH;
+		intel_crtc->max_cursor_height = GEN2_CURSOR_HEIGHT;
+	} else {
+		intel_crtc->max_cursor_width = CURSOR_WIDTH;
+		intel_crtc->max_cursor_height = CURSOR_HEIGHT;
+	}
+	dev->mode_config.cursor_width = intel_crtc->max_cursor_width;
+	dev->mode_config.cursor_height = intel_crtc->max_cursor_height;
+
 	drm_mode_crtc_set_gamma_size(&intel_crtc->base, 256);
 	for (i = 0; i < 256; i++) {
 		intel_crtc->lut_r[i] = i;
@@ -10408,12 +10634,7 @@ static int intel_encoder_clones(struct intel_encoder *encoder)
 
 	list_for_each_entry(source_encoder,
 			    &dev->mode_config.encoder_list, base.head) {
-
-		if (encoder == source_encoder)
-			index_mask |= (1 << entry);
-
-		/* Intel hw has only one MUX where enocoders could be cloned. */
-		if (encoder->cloneable && source_encoder->cloneable)
+		if (encoders_cloneable(encoder, source_encoder))
 			index_mask |= (1 << entry);
 
 		entry++;
@@ -10770,32 +10991,40 @@ static void intel_init_display(struct drm_device *dev)
 
 	if (HAS_DDI(dev)) {
 		dev_priv->display.get_pipe_config = haswell_get_pipe_config;
+		dev_priv->display.get_plane_config = ironlake_get_plane_config;
 		dev_priv->display.crtc_mode_set = haswell_crtc_mode_set;
 		dev_priv->display.crtc_enable = haswell_crtc_enable;
 		dev_priv->display.crtc_disable = haswell_crtc_disable;
 		dev_priv->display.off = haswell_crtc_off;
-		dev_priv->display.update_plane = ironlake_update_plane;
+		dev_priv->display.update_primary_plane =
+			ironlake_update_primary_plane;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		dev_priv->display.get_pipe_config = ironlake_get_pipe_config;
+		dev_priv->display.get_plane_config = ironlake_get_plane_config;
 		dev_priv->display.crtc_mode_set = ironlake_crtc_mode_set;
 		dev_priv->display.crtc_enable = ironlake_crtc_enable;
 		dev_priv->display.crtc_disable = ironlake_crtc_disable;
 		dev_priv->display.off = ironlake_crtc_off;
-		dev_priv->display.update_plane = ironlake_update_plane;
+		dev_priv->display.update_primary_plane =
+			ironlake_update_primary_plane;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
+		dev_priv->display.get_plane_config = i9xx_get_plane_config;
 		dev_priv->display.crtc_mode_set = i9xx_crtc_mode_set;
 		dev_priv->display.crtc_enable = valleyview_crtc_enable;
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
 		dev_priv->display.off = i9xx_crtc_off;
-		dev_priv->display.update_plane = i9xx_update_plane;
+		dev_priv->display.update_primary_plane =
+			i9xx_update_primary_plane;
 	} else {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
+		dev_priv->display.get_plane_config = i9xx_get_plane_config;
 		dev_priv->display.crtc_mode_set = i9xx_crtc_mode_set;
 		dev_priv->display.crtc_enable = i9xx_crtc_enable;
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
 		dev_priv->display.off = i9xx_crtc_off;
-		dev_priv->display.update_plane = i9xx_update_plane;
+		dev_priv->display.update_primary_plane =
+			i9xx_update_primary_plane;
 	}
 
 	/* Returns the core display clock speed */
@@ -11053,6 +11282,7 @@ void intel_modeset_init(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int sprite, ret;
 	enum pipe pipe;
+	struct intel_crtc *crtc;
 
 	drm_mode_config_init(dev);
 
@@ -11115,6 +11345,29 @@ void intel_modeset_init(struct drm_device *dev)
 	mutex_lock(&dev->mode_config.mutex);
 	intel_modeset_setup_hw_state(dev, false);
 	mutex_unlock(&dev->mode_config.mutex);
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
+			    base.head) {
+		if (!crtc->active)
+			continue;
+
+		/*
+		 * Note that reserving the BIOS fb up front prevents us
+		 * from stuffing other stolen allocations like the ring
+		 * on top.  This prevents some ugliness at boot time, and
+		 * can even allow for smooth boot transitions if the BIOS
+		 * fb is large enough for the active pipe configuration.
+		 */
+		if (dev_priv->display.get_plane_config) {
+			dev_priv->display.get_plane_config(crtc,
+							   &crtc->plane_config);
+			/*
+			 * If the fb is shared between multiple heads, we'll
+			 * just get the first one.
+			 */
+			intel_find_plane_obj(crtc, &crtc->plane_config);
+		}
+	}
 }
 
 static void
@@ -11484,9 +11737,32 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 
 void intel_modeset_gem_init(struct drm_device *dev)
 {
+	struct drm_crtc *c;
+	struct intel_framebuffer *fb;
+
 	intel_modeset_init_hw(dev);
 
 	intel_setup_overlay(dev);
+
+	/*
+	 * Make sure any fbs we allocated at startup are properly
+	 * pinned & fenced.  When we do the allocation it's too early
+	 * for this.
+	 */
+	mutex_lock(&dev->struct_mutex);
+	list_for_each_entry(c, &dev->mode_config.crtc_list, head) {
+		if (!c->primary->fb)
+			continue;
+
+		fb = to_intel_framebuffer(c->primary->fb);
+		if (intel_pin_and_fence_fb_obj(dev, fb->obj, NULL)) {
+			DRM_ERROR("failed to pin boot fb on pipe %d\n",
+				  to_intel_crtc(c)->pipe);
+			drm_framebuffer_unreference(c->primary->fb);
+			c->primary->fb = NULL;
+		}
+	}
+	mutex_unlock(&dev->struct_mutex);
 }
 
 void intel_connector_unregister(struct intel_connector *intel_connector)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f2fedc06976b..5ce5e5be7e88 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -91,7 +91,7 @@ static struct intel_dp *intel_attached_dp(struct drm_connector *connector)
 }
 
 static void intel_dp_link_down(struct intel_dp *intel_dp);
-static void edp_panel_vdd_on(struct intel_dp *intel_dp);
+static bool _edp_panel_vdd_on(struct intel_dp *intel_dp);
 static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync);
 
 static int
@@ -460,6 +460,9 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	uint32_t status;
 	int try, clock = 0;
 	bool has_aux_irq = HAS_AUX_IRQ(dev);
+	bool vdd;
+
+	vdd = _edp_panel_vdd_on(intel_dp);
 
 	/* dp aux is extremely sensitive to irq latency, hence request the
 	 * lowest possible wakeup latency and so prevent the cpu from going into
@@ -565,223 +568,130 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
 	intel_aux_display_runtime_put(dev_priv);
 
+	if (vdd)
+		edp_panel_vdd_off(intel_dp, false);
+
 	return ret;
 }
 
-/* Write data to the aux channel in native mode */
-static int
-intel_dp_aux_native_write(struct intel_dp *intel_dp,
-			  uint16_t address, uint8_t *send, int send_bytes)
+#define HEADER_SIZE	4
+static ssize_t
+intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 {
+	struct intel_dp *intel_dp = container_of(aux, struct intel_dp, aux);
+	uint8_t txbuf[20], rxbuf[20];
+	size_t txsize, rxsize;
 	int ret;
-	uint8_t	msg[20];
-	int msg_bytes;
-	uint8_t	ack;
-	int retry;
 
-	if (WARN_ON(send_bytes > 16))
-		return -E2BIG;
+	txbuf[0] = msg->request << 4;
+	txbuf[1] = msg->address >> 8;
+	txbuf[2] = msg->address & 0xff;
+	txbuf[3] = msg->size - 1;
 
-	intel_dp_check_edp(intel_dp);
-	msg[0] = DP_AUX_NATIVE_WRITE << 4;
-	msg[1] = address >> 8;
-	msg[2] = address & 0xff;
-	msg[3] = send_bytes - 1;
-	memcpy(&msg[4], send, send_bytes);
-	msg_bytes = send_bytes + 4;
-	for (retry = 0; retry < 7; retry++) {
-		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1);
-		if (ret < 0)
-			return ret;
-		ack >>= 4;
-		if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK)
-			return send_bytes;
-		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
-			usleep_range(400, 500);
-		else
-			return -EIO;
-	}
+	switch (msg->request & ~DP_AUX_I2C_MOT) {
+	case DP_AUX_NATIVE_WRITE:
+	case DP_AUX_I2C_WRITE:
+		txsize = HEADER_SIZE + msg->size;
+		rxsize = 1;
 
-	DRM_ERROR("too many retries, giving up\n");
-	return -EIO;
-}
+		if (WARN_ON(txsize > 20))
+			return -E2BIG;
 
-/* Write a single byte to the aux channel in native mode */
-static int
-intel_dp_aux_native_write_1(struct intel_dp *intel_dp,
-			    uint16_t address, uint8_t byte)
-{
-	return intel_dp_aux_native_write(intel_dp, address, &byte, 1);
-}
+		memcpy(txbuf + HEADER_SIZE, msg->buffer, msg->size);
 
-/* read bytes from a native aux channel */
-static int
-intel_dp_aux_native_read(struct intel_dp *intel_dp,
-			 uint16_t address, uint8_t *recv, int recv_bytes)
-{
-	uint8_t msg[4];
-	int msg_bytes;
-	uint8_t reply[20];
-	int reply_bytes;
-	uint8_t ack;
-	int ret;
-	int retry;
+		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize);
+		if (ret > 0) {
+			msg->reply = rxbuf[0] >> 4;
 
-	if (WARN_ON(recv_bytes > 19))
-		return -E2BIG;
-
-	intel_dp_check_edp(intel_dp);
-	msg[0] = DP_AUX_NATIVE_READ << 4;
-	msg[1] = address >> 8;
-	msg[2] = address & 0xff;
-	msg[3] = recv_bytes - 1;
-
-	msg_bytes = 4;
-	reply_bytes = recv_bytes + 1;
-
-	for (retry = 0; retry < 7; retry++) {
-		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes,
-				      reply, reply_bytes);
-		if (ret == 0)
-			return -EPROTO;
-		if (ret < 0)
-			return ret;
-		ack = reply[0] >> 4;
-		if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK) {
-			memcpy(recv, reply + 1, ret - 1);
-			return ret - 1;
+			/* Return payload size. */
+			ret = msg->size;
 		}
-		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
-			usleep_range(400, 500);
-		else
-			return -EIO;
+		break;
+
+	case DP_AUX_NATIVE_READ:
+	case DP_AUX_I2C_READ:
+		txsize = HEADER_SIZE;
+		rxsize = msg->size + 1;
+
+		if (WARN_ON(rxsize > 20))
+			return -E2BIG;
+
+		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize);
+		if (ret > 0) {
+			msg->reply = rxbuf[0] >> 4;
+			/*
+			 * Assume happy day, and copy the data. The caller is
+			 * expected to check msg->reply before touching it.
+			 *
+			 * Return payload size.
+			 */
+			ret--;
+			memcpy(msg->buffer, rxbuf + 1, ret);
+		}
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
 	}
 
-	DRM_ERROR("too many retries, giving up\n");
-	return -EIO;
+	return ret;
 }
 
-static int
-intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
-		    uint8_t write_byte, uint8_t *read_byte)
+static void
+intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 {
-	struct i2c_algo_dp_aux_data *algo_data = adapter->algo_data;
-	struct intel_dp *intel_dp = container_of(adapter,
-						struct intel_dp,
-						adapter);
-	uint16_t address = algo_data->address;
-	uint8_t msg[5];
-	uint8_t reply[2];
-	unsigned retry;
-	int msg_bytes;
-	int reply_bytes;
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	enum port port = intel_dig_port->port;
+	const char *name = NULL;
 	int ret;
 
-	edp_panel_vdd_on(intel_dp);
-	intel_dp_check_edp(intel_dp);
-	/* Set up the command byte */
-	if (mode & MODE_I2C_READ)
-		msg[0] = DP_AUX_I2C_READ << 4;
-	else
-		msg[0] = DP_AUX_I2C_WRITE << 4;
-
-	if (!(mode & MODE_I2C_STOP))
-		msg[0] |= DP_AUX_I2C_MOT << 4;
-
-	msg[1] = address >> 8;
-	msg[2] = address;
-
-	switch (mode) {
-	case MODE_I2C_WRITE:
-		msg[3] = 0;
-		msg[4] = write_byte;
-		msg_bytes = 5;
-		reply_bytes = 1;
+	switch (port) {
+	case PORT_A:
+		intel_dp->aux_ch_ctl_reg = DPA_AUX_CH_CTL;
+		name = "DPDDC-A";
 		break;
-	case MODE_I2C_READ:
-		msg[3] = 0;
-		msg_bytes = 4;
-		reply_bytes = 2;
+	case PORT_B:
+		intel_dp->aux_ch_ctl_reg = PCH_DPB_AUX_CH_CTL;
+		name = "DPDDC-B";
+		break;
+	case PORT_C:
+		intel_dp->aux_ch_ctl_reg = PCH_DPC_AUX_CH_CTL;
+		name = "DPDDC-C";
+		break;
+	case PORT_D:
+		intel_dp->aux_ch_ctl_reg = PCH_DPD_AUX_CH_CTL;
+		name = "DPDDC-D";
 		break;
 	default:
-		msg_bytes = 3;
-		reply_bytes = 1;
-		break;
+		BUG();
 	}
 
-	/*
-	 * DP1.2 sections 2.7.7.1.5.6.1 and 2.7.7.1.6.6.1: A DP Source device is
-	 * required to retry at least seven times upon receiving AUX_DEFER
-	 * before giving up the AUX transaction.
-	 */
-	for (retry = 0; retry < 7; retry++) {
-		ret = intel_dp_aux_ch(intel_dp,
-				      msg, msg_bytes,
-				      reply, reply_bytes);
-		if (ret < 0) {
-			DRM_DEBUG_KMS("aux_ch failed %d\n", ret);
-			goto out;
-		}
+	if (!HAS_DDI(dev))
+		intel_dp->aux_ch_ctl_reg = intel_dp->output_reg + 0x10;
 
-		switch ((reply[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK) {
-		case DP_AUX_NATIVE_REPLY_ACK:
-			/* I2C-over-AUX Reply field is only valid
-			 * when paired with AUX ACK.
-			 */
-			break;
-		case DP_AUX_NATIVE_REPLY_NACK:
-			DRM_DEBUG_KMS("aux_ch native nack\n");
-			ret = -EREMOTEIO;
-			goto out;
-		case DP_AUX_NATIVE_REPLY_DEFER:
-			/*
-			 * For now, just give more slack to branch devices. We
-			 * could check the DPCD for I2C bit rate capabilities,
-			 * and if available, adjust the interval. We could also
-			 * be more careful with DP-to-Legacy adapters where a
-			 * long legacy cable may force very low I2C bit rates.
-			 */
-			if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
-			    DP_DWN_STRM_PORT_PRESENT)
-				usleep_range(500, 600);
-			else
-				usleep_range(300, 400);
-			continue;
-		default:
-			DRM_ERROR("aux_ch invalid native reply 0x%02x\n",
-				  reply[0]);
-			ret = -EREMOTEIO;
-			goto out;
-		}
+	intel_dp->aux.name = name;
+	intel_dp->aux.dev = dev->dev;
+	intel_dp->aux.transfer = intel_dp_aux_transfer;
 
-		switch ((reply[0] >> 4) & DP_AUX_I2C_REPLY_MASK) {
-		case DP_AUX_I2C_REPLY_ACK:
-			if (mode == MODE_I2C_READ) {
-				*read_byte = reply[1];
-			}
-			ret = reply_bytes - 1;
-			goto out;
-		case DP_AUX_I2C_REPLY_NACK:
-			DRM_DEBUG_KMS("aux_i2c nack\n");
-			ret = -EREMOTEIO;
-			goto out;
-		case DP_AUX_I2C_REPLY_DEFER:
-			DRM_DEBUG_KMS("aux_i2c defer\n");
-			udelay(100);
-			break;
-		default:
-			DRM_ERROR("aux_i2c invalid reply 0x%02x\n", reply[0]);
-			ret = -EREMOTEIO;
-			goto out;
-		}
+	DRM_DEBUG_KMS("registering %s bus for %s\n", name,
+		      connector->base.kdev->kobj.name);
+
+	ret = drm_dp_aux_register_i2c_bus(&intel_dp->aux);
+	if (ret < 0) {
+		DRM_ERROR("drm_dp_aux_register_i2c_bus() for %s failed (%d)\n",
+			  name, ret);
+		return;
 	}
 
-	DRM_ERROR("too many retries, giving up\n");
-	ret = -EREMOTEIO;
-
-out:
-	edp_panel_vdd_off(intel_dp, false);
-	return ret;
+	ret = sysfs_create_link(&connector->base.kdev->kobj,
+				&intel_dp->aux.ddc.dev.kobj,
+				intel_dp->aux.ddc.dev.kobj.name);
+	if (ret < 0) {
+		DRM_ERROR("sysfs_create_link() for %s failed (%d)\n", name, ret);
+		drm_dp_aux_unregister_i2c_bus(&intel_dp->aux);
+	}
 }
 
 static void
@@ -790,43 +700,10 @@ intel_dp_connector_unregister(struct intel_connector *intel_connector)
 	struct intel_dp *intel_dp = intel_attached_dp(&intel_connector->base);
 
 	sysfs_remove_link(&intel_connector->base.kdev->kobj,
-			  intel_dp->adapter.dev.kobj.name);
+			  intel_dp->aux.ddc.dev.kobj.name);
 	intel_connector_unregister(intel_connector);
 }
 
-static int
-intel_dp_i2c_init(struct intel_dp *intel_dp,
-		  struct intel_connector *intel_connector, const char *name)
-{
-	int	ret;
-
-	DRM_DEBUG_KMS("i2c_init %s\n", name);
-	intel_dp->algo.running = false;
-	intel_dp->algo.address = 0;
-	intel_dp->algo.aux_ch = intel_dp_i2c_aux_ch;
-
-	memset(&intel_dp->adapter, '\0', sizeof(intel_dp->adapter));
-	intel_dp->adapter.owner = THIS_MODULE;
-	intel_dp->adapter.class = I2C_CLASS_DDC;
-	strncpy(intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
-	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
-	intel_dp->adapter.algo_data = &intel_dp->algo;
-	intel_dp->adapter.dev.parent = intel_connector->base.dev->dev;
-
-	ret = i2c_dp_aux_add_bus(&intel_dp->adapter);
-	if (ret < 0)
-		return ret;
-
-	ret = sysfs_create_link(&intel_connector->base.kdev->kobj,
-				&intel_dp->adapter.dev.kobj,
-				intel_dp->adapter.dev.kobj.name);
-
-	if (ret < 0)
-		i2c_del_adapter(&intel_dp->adapter);
-
-	return ret;
-}
-
 static void
 intel_dp_set_clock(struct intel_encoder *encoder,
 		   struct intel_crtc_config *pipe_config, int link_bw)
@@ -1162,23 +1039,21 @@ static  u32 ironlake_get_pp_control(struct intel_dp *intel_dp)
 	return control;
 }
 
-static void edp_panel_vdd_on(struct intel_dp *intel_dp)
+static bool _edp_panel_vdd_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 pp;
 	u32 pp_stat_reg, pp_ctrl_reg;
+	bool need_to_disable = !intel_dp->want_panel_vdd;
 
 	if (!is_edp(intel_dp))
-		return;
-
-	WARN(intel_dp->want_panel_vdd,
-	     "eDP VDD already requested on\n");
+		return false;
 
 	intel_dp->want_panel_vdd = true;
 
 	if (edp_have_panel_vdd(intel_dp))
-		return;
+		return need_to_disable;
 
 	intel_runtime_pm_get(dev_priv);
 
@@ -1204,6 +1079,17 @@ static void edp_panel_vdd_on(struct intel_dp *intel_dp)
 		DRM_DEBUG_KMS("eDP was not running\n");
 		msleep(intel_dp->panel_power_up_delay);
 	}
+
+	return need_to_disable;
+}
+
+void intel_edp_panel_vdd_on(struct intel_dp *intel_dp)
+{
+	if (is_edp(intel_dp)) {
+		bool vdd = _edp_panel_vdd_on(intel_dp);
+
+		WARN(!vdd, "eDP VDD already requested on\n");
+	}
 }
 
 static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
@@ -1330,6 +1216,8 @@ void intel_edp_panel_off(struct intel_dp *intel_dp)
 
 	edp_wait_backlight_off(intel_dp);
 
+	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
+
 	pp = ironlake_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
 	 * panels get very unhappy and cease to work. */
@@ -1338,11 +1226,16 @@ void intel_edp_panel_off(struct intel_dp *intel_dp)
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
+	intel_dp->want_panel_vdd = false;
+
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
 
 	intel_dp->last_power_cycle = jiffies;
 	wait_panel_off(intel_dp);
+
+	/* We got a reference when we enabled the VDD. */
+	intel_runtime_pm_put(dev_priv);
 }
 
 void intel_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1459,8 +1352,8 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 		return;
 
 	if (mode != DRM_MODE_DPMS_ON) {
-		ret = intel_dp_aux_native_write_1(intel_dp, DP_SET_POWER,
-						  DP_SET_POWER_D3);
+		ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER,
+					 DP_SET_POWER_D3);
 		if (ret != 1)
 			DRM_DEBUG_DRIVER("failed to write sink power state\n");
 	} else {
@@ -1469,9 +1362,8 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 		 * time to wake up.
 		 */
 		for (i = 0; i < 3; i++) {
-			ret = intel_dp_aux_native_write_1(intel_dp,
-							  DP_SET_POWER,
-							  DP_SET_POWER_D0);
+			ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER,
+						 DP_SET_POWER_D0);
 			if (ret == 1)
 				break;
 			msleep(1);
@@ -1695,13 +1587,11 @@ static void intel_edp_psr_enable_sink(struct intel_dp *intel_dp)
 
 	/* Enable PSR in sink */
 	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT)
-		intel_dp_aux_native_write_1(intel_dp, DP_PSR_EN_CFG,
-					    DP_PSR_ENABLE &
-					    ~DP_PSR_MAIN_LINK_ACTIVE);
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
+				   DP_PSR_ENABLE & ~DP_PSR_MAIN_LINK_ACTIVE);
 	else
-		intel_dp_aux_native_write_1(intel_dp, DP_PSR_EN_CFG,
-					    DP_PSR_ENABLE |
-					    DP_PSR_MAIN_LINK_ACTIVE);
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
+				   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
 
 	/* Setup AUX registers */
 	I915_WRITE(EDP_PSR_AUX_DATA1(dev), EDP_PSR_DPCD_COMMAND);
@@ -1876,11 +1766,10 @@ static void intel_disable_dp(struct intel_encoder *encoder)
 
 	/* Make sure the panel is off before trying to change the mode. But also
 	 * ensure that we have vdd while we switch off the panel. */
-	edp_panel_vdd_on(intel_dp);
+	intel_edp_panel_vdd_on(intel_dp);
 	intel_edp_backlight_off(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 	intel_edp_panel_off(intel_dp);
-	edp_panel_vdd_off(intel_dp, true);
 
 	/* cpu edp my only be disable _after_ the cpu pipe/plane is disabled. */
 	if (!(port == PORT_A || IS_VALLEYVIEW(dev)))
@@ -1910,7 +1799,7 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 	if (WARN_ON(dp_reg & DP_PORT_EN))
 		return;
 
-	edp_panel_vdd_on(intel_dp);
+	intel_edp_panel_vdd_on(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 	intel_dp_start_link_train(intel_dp);
 	intel_edp_panel_on(intel_dp);
@@ -2013,26 +1902,25 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder)
 /*
  * Native read with retry for link status and receiver capability reads for
  * cases where the sink may still be asleep.
+ *
+ * Sinks are *supposed* to come up within 1ms from an off state, but we're also
+ * supposed to retry 3 times per the spec.
  */
-static bool
-intel_dp_aux_native_read_retry(struct intel_dp *intel_dp, uint16_t address,
-			       uint8_t *recv, int recv_bytes)
+static ssize_t
+intel_dp_dpcd_read_wake(struct drm_dp_aux *aux, unsigned int offset,
+			void *buffer, size_t size)
 {
-	int ret, i;
+	ssize_t ret;
+	int i;
 
-	/*
-	 * Sinks are *supposed* to come up within 1ms from an off state,
-	 * but we're also supposed to retry 3 times per the spec.
-	 */
 	for (i = 0; i < 3; i++) {
-		ret = intel_dp_aux_native_read(intel_dp, address, recv,
-					       recv_bytes);
-		if (ret == recv_bytes)
-			return true;
+		ret = drm_dp_dpcd_read(aux, offset, buffer, size);
+		if (ret == size)
+			return ret;
 		msleep(1);
 	}
 
-	return false;
+	return ret;
 }
 
 /*
@@ -2042,10 +1930,10 @@ intel_dp_aux_native_read_retry(struct intel_dp *intel_dp, uint16_t address,
 static bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
-	return intel_dp_aux_native_read_retry(intel_dp,
-					      DP_LANE0_1_STATUS,
-					      link_status,
-					      DP_LINK_STATUS_SIZE);
+	return intel_dp_dpcd_read_wake(&intel_dp->aux,
+				       DP_LANE0_1_STATUS,
+				       link_status,
+				       DP_LINK_STATUS_SIZE) == DP_LINK_STATUS_SIZE;
 }
 
 /*
@@ -2559,8 +2447,8 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 		len = intel_dp->lane_count + 1;
 	}
 
-	ret = intel_dp_aux_native_write(intel_dp, DP_TRAINING_PATTERN_SET,
-					buf, len);
+	ret = drm_dp_dpcd_write(&intel_dp->aux, DP_TRAINING_PATTERN_SET,
+				buf, len);
 
 	return ret == len;
 }
@@ -2589,9 +2477,8 @@ intel_dp_update_link_train(struct intel_dp *intel_dp, uint32_t *DP,
 	I915_WRITE(intel_dp->output_reg, *DP);
 	POSTING_READ(intel_dp->output_reg);
 
-	ret = intel_dp_aux_native_write(intel_dp, DP_TRAINING_LANE0_SET,
-					intel_dp->train_set,
-					intel_dp->lane_count);
+	ret = drm_dp_dpcd_write(&intel_dp->aux, DP_TRAINING_LANE0_SET,
+				intel_dp->train_set, intel_dp->lane_count);
 
 	return ret == intel_dp->lane_count;
 }
@@ -2647,11 +2534,11 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	link_config[1] = intel_dp->lane_count;
 	if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
 		link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
-	intel_dp_aux_native_write(intel_dp, DP_LINK_BW_SET, link_config, 2);
+	drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2);
 
 	link_config[0] = 0;
 	link_config[1] = DP_SET_ANSI_8B10B;
-	intel_dp_aux_native_write(intel_dp, DP_DOWNSPREAD_CTRL, link_config, 2);
+	drm_dp_dpcd_write(&intel_dp->aux, DP_DOWNSPREAD_CTRL, link_config, 2);
 
 	DP |= DP_PORT_EN;
 
@@ -2894,8 +2781,8 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 
 	char dpcd_hex_dump[sizeof(intel_dp->dpcd) * 3];
 
-	if (intel_dp_aux_native_read_retry(intel_dp, 0x000, intel_dp->dpcd,
-					   sizeof(intel_dp->dpcd)) == 0)
+	if (intel_dp_dpcd_read_wake(&intel_dp->aux, 0x000, intel_dp->dpcd,
+				    sizeof(intel_dp->dpcd)) < 0)
 		return false; /* aux transfer failed */
 
 	hex_dump_to_buffer(intel_dp->dpcd, sizeof(intel_dp->dpcd),
@@ -2908,9 +2795,9 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	/* Check if the panel supports PSR */
 	memset(intel_dp->psr_dpcd, 0, sizeof(intel_dp->psr_dpcd));
 	if (is_edp(intel_dp)) {
-		intel_dp_aux_native_read_retry(intel_dp, DP_PSR_SUPPORT,
-					       intel_dp->psr_dpcd,
-					       sizeof(intel_dp->psr_dpcd));
+		intel_dp_dpcd_read_wake(&intel_dp->aux, DP_PSR_SUPPORT,
+					intel_dp->psr_dpcd,
+					sizeof(intel_dp->psr_dpcd));
 		if (intel_dp->psr_dpcd[0] & DP_PSR_IS_SUPPORTED) {
 			dev_priv->psr.sink_support = true;
 			DRM_DEBUG_KMS("Detected EDP PSR Panel.\n");
@@ -2932,9 +2819,9 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] == 0x10)
 		return true; /* no per-port downstream info */
 
-	if (intel_dp_aux_native_read_retry(intel_dp, DP_DOWNSTREAM_PORT_0,
-					   intel_dp->downstream_ports,
-					   DP_MAX_DOWNSTREAM_PORTS) == 0)
+	if (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_DOWNSTREAM_PORT_0,
+				    intel_dp->downstream_ports,
+				    DP_MAX_DOWNSTREAM_PORTS) < 0)
 		return false; /* downstream port status fetch failed */
 
 	return true;
@@ -2948,13 +2835,13 @@ intel_dp_probe_oui(struct intel_dp *intel_dp)
 	if (!(intel_dp->dpcd[DP_DOWN_STREAM_PORT_COUNT] & DP_OUI_SUPPORT))
 		return;
 
-	edp_panel_vdd_on(intel_dp);
+	intel_edp_panel_vdd_on(intel_dp);
 
-	if (intel_dp_aux_native_read_retry(intel_dp, DP_SINK_OUI, buf, 3))
+	if (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_SINK_OUI, buf, 3) == 3)
 		DRM_DEBUG_KMS("Sink OUI: %02hx%02hx%02hx\n",
 			      buf[0], buf[1], buf[2]);
 
-	if (intel_dp_aux_native_read_retry(intel_dp, DP_BRANCH_OUI, buf, 3))
+	if (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_BRANCH_OUI, buf, 3) == 3)
 		DRM_DEBUG_KMS("Branch OUI: %02hx%02hx%02hx\n",
 			      buf[0], buf[1], buf[2]);
 
@@ -2969,46 +2856,40 @@ int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc)
 		to_intel_crtc(intel_dig_port->base.base.crtc);
 	u8 buf[1];
 
-	if (!intel_dp_aux_native_read(intel_dp, DP_TEST_SINK_MISC, buf, 1))
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, buf) < 0)
 		return -EAGAIN;
 
 	if (!(buf[0] & DP_TEST_CRC_SUPPORTED))
 		return -ENOTTY;
 
-	if (!intel_dp_aux_native_write_1(intel_dp, DP_TEST_SINK,
-					 DP_TEST_SINK_START))
+	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
+			       DP_TEST_SINK_START) < 0)
 		return -EAGAIN;
 
 	/* Wait 2 vblanks to be sure we will have the correct CRC value */
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 
-	if (!intel_dp_aux_native_read(intel_dp, DP_TEST_CRC_R_CR, crc, 6))
+	if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0)
 		return -EAGAIN;
 
-	intel_dp_aux_native_write_1(intel_dp, DP_TEST_SINK, 0);
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, 0);
 	return 0;
 }
 
 static bool
 intel_dp_get_sink_irq(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 {
-	int ret;
-
-	ret = intel_dp_aux_native_read_retry(intel_dp,
-					     DP_DEVICE_SERVICE_IRQ_VECTOR,
-					     sink_irq_vector, 1);
-	if (!ret)
-		return false;
-
-	return true;
+	return intel_dp_dpcd_read_wake(&intel_dp->aux,
+				       DP_DEVICE_SERVICE_IRQ_VECTOR,
+				       sink_irq_vector, 1) == 1;
 }
 
 static void
 intel_dp_handle_test_request(struct intel_dp *intel_dp)
 {
 	/* NAK by default */
-	intel_dp_aux_native_write_1(intel_dp, DP_TEST_RESPONSE, DP_TEST_NAK);
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_RESPONSE, DP_TEST_NAK);
 }
 
 /*
@@ -3047,9 +2928,9 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
 	    intel_dp_get_sink_irq(intel_dp, &sink_irq_vector)) {
 		/* Clear interrupt source */
-		intel_dp_aux_native_write_1(intel_dp,
-					    DP_DEVICE_SERVICE_IRQ_VECTOR,
-					    sink_irq_vector);
+		drm_dp_dpcd_writeb(&intel_dp->aux,
+				   DP_DEVICE_SERVICE_IRQ_VECTOR,
+				   sink_irq_vector);
 
 		if (sink_irq_vector & DP_AUTOMATED_TEST_REQUEST)
 			intel_dp_handle_test_request(intel_dp);
@@ -3084,15 +2965,17 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
 	    intel_dp->downstream_ports[0] & DP_DS_PORT_HPD) {
 		uint8_t reg;
-		if (!intel_dp_aux_native_read_retry(intel_dp, DP_SINK_COUNT,
-						    &reg, 1))
+
+		if (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_SINK_COUNT,
+					    &reg, 1) < 0)
 			return connector_status_unknown;
+
 		return DP_GET_SINK_COUNT(reg) ? connector_status_connected
 					      : connector_status_disconnected;
 	}
 
 	/* If no HPD, poke DDC gently */
-	if (drm_probe_ddc(&intel_dp->adapter))
+	if (drm_probe_ddc(&intel_dp->aux.ddc))
 		return connector_status_connected;
 
 	/* Well we tried, say unknown for unreliable port types */
@@ -3260,7 +3143,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	if (intel_dp->force_audio != HDMI_AUDIO_AUTO) {
 		intel_dp->has_audio = (intel_dp->force_audio == HDMI_AUDIO_ON);
 	} else {
-		edid = intel_dp_get_edid(connector, &intel_dp->adapter);
+		edid = intel_dp_get_edid(connector, &intel_dp->aux.ddc);
 		if (edid) {
 			intel_dp->has_audio = drm_detect_monitor_audio(edid);
 			kfree(edid);
@@ -3296,7 +3179,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 	power_domain = intel_display_port_power_domain(intel_encoder);
 	intel_display_power_get(dev_priv, power_domain);
 
-	ret = intel_dp_get_edid_modes(connector, &intel_dp->adapter);
+	ret = intel_dp_get_edid_modes(connector, &intel_dp->aux.ddc);
 	intel_display_power_put(dev_priv, power_domain);
 	if (ret)
 		return ret;
@@ -3329,7 +3212,7 @@ intel_dp_detect_audio(struct drm_connector *connector)
 	power_domain = intel_display_port_power_domain(intel_encoder);
 	intel_display_power_get(dev_priv, power_domain);
 
-	edid = intel_dp_get_edid(connector, &intel_dp->adapter);
+	edid = intel_dp_get_edid(connector, &intel_dp->aux.ddc);
 	if (edid) {
 		has_audio = drm_detect_monitor_audio(edid);
 		kfree(edid);
@@ -3451,7 +3334,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 
-	i2c_del_adapter(&intel_dp->adapter);
+	drm_dp_aux_unregister_i2c_bus(&intel_dp->aux);
 	drm_encoder_cleanup(encoder);
 	if (is_edp(intel_dp)) {
 		cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
@@ -3745,7 +3628,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 		return true;
 
 	/* Cache DPCD and EDID for edp. */
-	edp_panel_vdd_on(intel_dp);
+	intel_edp_panel_vdd_on(intel_dp);
 	has_dpcd = intel_dp_get_dpcd(intel_dp);
 	edp_panel_vdd_off(intel_dp, false);
 
@@ -3764,7 +3647,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, power_seq);
 
 	mutex_lock(&dev->mode_config.mutex);
-	edid = drm_get_edid(connector, &intel_dp->adapter);
+	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
 			drm_mode_connector_update_edid_property(connector,
@@ -3813,8 +3696,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum port port = intel_dig_port->port;
 	struct edp_power_seq power_seq = { 0 };
-	const char *name = NULL;
-	int type, error;
+	int type;
 
 	/* intel_dp vfuncs */
 	if (IS_VALLEYVIEW(dev))
@@ -3867,43 +3749,19 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
 	intel_connector->unregister = intel_dp_connector_unregister;
 
-	intel_dp->aux_ch_ctl_reg = intel_dp->output_reg + 0x10;
-	if (HAS_DDI(dev)) {
-		switch (intel_dig_port->port) {
-		case PORT_A:
-			intel_dp->aux_ch_ctl_reg = DPA_AUX_CH_CTL;
-			break;
-		case PORT_B:
-			intel_dp->aux_ch_ctl_reg = PCH_DPB_AUX_CH_CTL;
-			break;
-		case PORT_C:
-			intel_dp->aux_ch_ctl_reg = PCH_DPC_AUX_CH_CTL;
-			break;
-		case PORT_D:
-			intel_dp->aux_ch_ctl_reg = PCH_DPD_AUX_CH_CTL;
-			break;
-		default:
-			BUG();
-		}
-	}
-
-	/* Set up the DDC bus. */
+	/* Set up the hotplug pin. */
 	switch (port) {
 	case PORT_A:
 		intel_encoder->hpd_pin = HPD_PORT_A;
-		name = "DPDDC-A";
 		break;
 	case PORT_B:
 		intel_encoder->hpd_pin = HPD_PORT_B;
-		name = "DPDDC-B";
 		break;
 	case PORT_C:
 		intel_encoder->hpd_pin = HPD_PORT_C;
-		name = "DPDDC-C";
 		break;
 	case PORT_D:
 		intel_encoder->hpd_pin = HPD_PORT_D;
-		name = "DPDDC-D";
 		break;
 	default:
 		BUG();
@@ -3914,14 +3772,12 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
 	}
 
-	error = intel_dp_i2c_init(intel_dp, intel_connector, name);
-	WARN(error, "intel_dp_i2c_init failed with error %d for port %c\n",
-	     error, port_name(port));
+	intel_dp_aux_init(intel_dp, intel_connector);
 
 	intel_dp->psr_setup_done = false;
 
 	if (!intel_edp_init_connector(intel_dp, intel_connector, &power_seq)) {
-		i2c_del_adapter(&intel_dp->adapter);
+		drm_dp_aux_unregister_i2c_bus(&intel_dp->aux);
 		if (is_edp(intel_dp)) {
 			cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
 			mutex_lock(&dev->mode_config.mutex);
@@ -3991,7 +3847,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 
 	intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
-	intel_encoder->cloneable = false;
+	intel_encoder->cloneable = 0;
 	intel_encoder->hot_plug = intel_dp_hot_plug;
 
 	if (!intel_dp_init_connector(intel_dig_port, intel_connector)) {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9c7090590776..fa9910481ab0 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -78,6 +78,12 @@
 #define MAX_OUTPUTS 6
 /* maximum connectors per crtcs in the mode set */
 
+/* Maximum cursor sizes */
+#define GEN2_CURSOR_WIDTH 64
+#define GEN2_CURSOR_HEIGHT 64
+#define CURSOR_WIDTH 256
+#define CURSOR_HEIGHT 256
+
 #define INTEL_I2C_BUS_DVO 1
 #define INTEL_I2C_BUS_SDVO 2
 
@@ -113,6 +119,7 @@ struct intel_fbdev {
 	struct intel_framebuffer *fb;
 	struct list_head fbdev_list;
 	struct drm_display_mode *our_mode;
+	int preferred_bpp;
 };
 
 struct intel_encoder {
@@ -124,11 +131,7 @@ struct intel_encoder {
 	struct intel_crtc *new_crtc;
 
 	int type;
-	/*
-	 * Intel hw has only one MUX where encoders could be clone, hence a
-	 * simple flag is enough to compute the possible_clones mask.
-	 */
-	bool cloneable;
+	unsigned int cloneable;
 	bool connectors_active;
 	void (*hot_plug)(struct intel_encoder *);
 	bool (*compute_config)(struct intel_encoder *,
@@ -218,6 +221,12 @@ typedef struct dpll {
 	int	p;
 } intel_clock_t;
 
+struct intel_plane_config {
+	bool tiled;
+	int size;
+	u32 base;
+};
+
 struct intel_crtc_config {
 	/**
 	 * quirks - bitfield with hw state readout quirks
@@ -364,8 +373,10 @@ struct intel_crtc {
 	uint32_t cursor_addr;
 	int16_t cursor_x, cursor_y;
 	int16_t cursor_width, cursor_height;
+	int16_t max_cursor_width, max_cursor_height;
 	bool cursor_visible;
 
+	struct intel_plane_config plane_config;
 	struct intel_crtc_config config;
 	struct intel_crtc_config *new_config;
 	bool new_enabled;
@@ -485,8 +496,7 @@ struct intel_dp {
 	uint8_t dpcd[DP_RECEIVER_CAP_SIZE];
 	uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE];
 	uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS];
-	struct i2c_adapter adapter;
-	struct i2c_algo_dp_aux_data algo;
+	struct drm_dp_aux aux;
 	uint8_t train_set[4];
 	int panel_power_up_delay;
 	int panel_power_down_delay;
@@ -618,8 +628,8 @@ void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 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 hsw_pc8_disable_interrupts(struct drm_device *dev);
-void hsw_pc8_restore_interrupts(struct drm_device *dev);
+void hsw_runtime_pm_disable_interrupts(struct drm_device *dev);
+void hsw_runtime_pm_restore_interrupts(struct drm_device *dev);
 
 
 /* intel_crt.c */
@@ -722,9 +732,8 @@ unsigned long intel_gen4_compute_page_offset(int *x, int *y,
 					     unsigned int bpp,
 					     unsigned int pitch);
 void intel_display_handle_reset(struct drm_device *dev);
-void hsw_enable_pc8_work(struct work_struct *__work);
-void hsw_enable_package_c8(struct drm_i915_private *dev_priv);
-void hsw_disable_package_c8(struct drm_i915_private *dev_priv);
+void hsw_enable_pc8(struct drm_i915_private *dev_priv);
+void hsw_disable_pc8(struct drm_i915_private *dev_priv);
 void intel_dp_get_m_n(struct intel_crtc *crtc,
 		      struct intel_crtc_config *pipe_config);
 int intel_dotclock_calculate(int link_freq, const struct intel_link_m_n *m_n);
@@ -740,6 +749,7 @@ intel_display_port_power_domain(struct intel_encoder *intel_encoder);
 int valleyview_get_vco(struct drm_i915_private *dev_priv);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_config *pipe_config);
+int intel_format_to_fourcc(int format);
 
 /* intel_dp.c */
 void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
@@ -757,6 +767,7 @@ bool intel_dp_compute_config(struct intel_encoder *encoder,
 bool intel_dp_is_edp(struct drm_device *dev, enum port port);
 void intel_edp_backlight_on(struct intel_dp *intel_dp);
 void intel_edp_backlight_off(struct intel_dp *intel_dp);
+void intel_edp_panel_vdd_on(struct intel_dp *intel_dp);
 void intel_edp_panel_on(struct intel_dp *intel_dp);
 void intel_edp_panel_off(struct intel_dp *intel_dp);
 void intel_edp_psr_enable(struct intel_dp *intel_dp);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index cf7322e95278..33656647f8bc 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -620,7 +620,7 @@ bool intel_dsi_init(struct drm_device *dev)
 	intel_encoder->type = INTEL_OUTPUT_DSI;
 	intel_encoder->crtc_mask = (1 << 0); /* XXX */
 
-	intel_encoder->cloneable = false;
+	intel_encoder->cloneable = 0;
 	drm_connector_init(dev, connector, &intel_dsi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 86eeb8b7d435..7fe3feedfe03 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -522,14 +522,15 @@ void intel_dvo_init(struct drm_device *dev)
 		intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
 		switch (dvo->type) {
 		case INTEL_DVO_CHIP_TMDS:
-			intel_encoder->cloneable = true;
+			intel_encoder->cloneable = (1 << INTEL_OUTPUT_ANALOG) |
+				(1 << INTEL_OUTPUT_DVO);
 			drm_connector_init(dev, connector,
 					   &intel_dvo_connector_funcs,
 					   DRM_MODE_CONNECTOR_DVII);
 			encoder_type = DRM_MODE_ENCODER_TMDS;
 			break;
 		case INTEL_DVO_CHIP_LVDS:
-			intel_encoder->cloneable = false;
+			intel_encoder->cloneable = 0;
 			drm_connector_init(dev, connector,
 					   &intel_dvo_connector_funcs,
 					   DRM_MODE_CONNECTOR_LVDS);
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 6b5beed28d70..2b1d42dbfe13 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -128,6 +128,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	struct drm_framebuffer *fb;
 	struct drm_i915_gem_object *obj;
 	int size, ret;
+	bool prealloc = false;
 
 	mutex_lock(&dev->struct_mutex);
 
@@ -139,6 +140,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		intel_fb = ifbdev->fb;
 	} else {
 		DRM_DEBUG_KMS("re-using BIOS fb\n");
+		prealloc = true;
 		sizes->fb_width = intel_fb->base.width;
 		sizes->fb_height = intel_fb->base.height;
 	}
@@ -200,7 +202,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	 * If the object is stolen however, it will be full of whatever
 	 * garbage was left in there.
 	 */
-	if (ifbdev->fb->obj->stolen)
+	if (ifbdev->fb->obj->stolen && !prealloc)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
@@ -454,27 +456,149 @@ static void intel_fbdev_destroy(struct drm_device *dev,
 	drm_framebuffer_remove(&ifbdev->fb->base);
 }
 
+/*
+ * Build an intel_fbdev struct using a BIOS allocated framebuffer, if possible.
+ * The core display code will have read out the current plane configuration,
+ * so we use that to figure out if there's an object for us to use as the
+ * fb, and if so, we re-use it for the fbdev configuration.
+ *
+ * Note we only support a single fb shared across pipes for boot (mostly for
+ * fbcon), so we just find the biggest and use that.
+ */
+static bool intel_fbdev_init_bios(struct drm_device *dev,
+				 struct intel_fbdev *ifbdev)
+{
+	struct intel_framebuffer *fb = NULL;
+	struct drm_crtc *crtc;
+	struct intel_crtc *intel_crtc;
+	struct intel_plane_config *plane_config = NULL;
+	unsigned int max_size = 0;
+
+	if (!i915.fastboot)
+		return false;
+
+	/* Find the largest fb */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		intel_crtc = to_intel_crtc(crtc);
+
+		if (!intel_crtc->active || !crtc->primary->fb) {
+			DRM_DEBUG_KMS("pipe %c not active or no fb, skipping\n",
+				      pipe_name(intel_crtc->pipe));
+			continue;
+		}
+
+		if (intel_crtc->plane_config.size > max_size) {
+			DRM_DEBUG_KMS("found possible fb from plane %c\n",
+				      pipe_name(intel_crtc->pipe));
+			plane_config = &intel_crtc->plane_config;
+			fb = to_intel_framebuffer(crtc->primary->fb);
+			max_size = plane_config->size;
+		}
+	}
+
+	if (!fb) {
+		DRM_DEBUG_KMS("no active fbs found, not using BIOS config\n");
+		goto out;
+	}
+
+	/* Now make sure all the pipes will fit into it */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		unsigned int cur_size;
+
+		intel_crtc = to_intel_crtc(crtc);
+
+		if (!intel_crtc->active) {
+			DRM_DEBUG_KMS("pipe %c not active, skipping\n",
+				      pipe_name(intel_crtc->pipe));
+			continue;
+		}
+
+		DRM_DEBUG_KMS("checking plane %c for BIOS fb\n",
+			      pipe_name(intel_crtc->pipe));
+
+		/*
+		 * See if the plane fb we found above will fit on this
+		 * pipe.  Note we need to use the selected fb's bpp rather
+		 * than the current pipe's, since they could be different.
+		 */
+		cur_size = intel_crtc->config.adjusted_mode.crtc_hdisplay *
+			intel_crtc->config.adjusted_mode.crtc_vdisplay;
+		DRM_DEBUG_KMS("pipe %c area: %d\n", pipe_name(intel_crtc->pipe),
+			      cur_size);
+		cur_size *= fb->base.bits_per_pixel / 8;
+		DRM_DEBUG_KMS("total size %d (bpp %d)\n", cur_size,
+			      fb->base.bits_per_pixel / 8);
+
+		if (cur_size > max_size) {
+			DRM_DEBUG_KMS("fb not big enough for plane %c (%d vs %d)\n",
+				      pipe_name(intel_crtc->pipe),
+				      cur_size, max_size);
+			plane_config = NULL;
+			fb = NULL;
+			break;
+		}
+
+		DRM_DEBUG_KMS("fb big enough for plane %c (%d >= %d)\n",
+			      pipe_name(intel_crtc->pipe),
+			      max_size, cur_size);
+	}
+
+	if (!fb) {
+		DRM_DEBUG_KMS("BIOS fb not suitable for all pipes, not using\n");
+		goto out;
+	}
+
+	ifbdev->preferred_bpp = fb->base.bits_per_pixel;
+	ifbdev->fb = fb;
+
+	drm_framebuffer_reference(&ifbdev->fb->base);
+
+	/* Final pass to check if any active pipes don't have fbs */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		intel_crtc = to_intel_crtc(crtc);
+
+		if (!intel_crtc->active)
+			continue;
+
+		WARN(!crtc->primary->fb,
+		     "re-used BIOS config but lost an fb on crtc %d\n",
+		     crtc->base.id);
+	}
+
+
+	DRM_DEBUG_KMS("using BIOS fb for initial console\n");
+	return true;
+
+out:
+
+	return false;
+}
+
 int intel_fbdev_init(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	ifbdev = kzalloc(sizeof(*ifbdev), GFP_KERNEL);
-	if (!ifbdev)
+	if (WARN_ON(INTEL_INFO(dev)->num_pipes == 0))
+		return -ENODEV;
+
+	ifbdev = kzalloc(sizeof(struct intel_fbdev), GFP_KERNEL);
+	if (ifbdev == NULL)
 		return -ENOMEM;
 
-	dev_priv->fbdev = ifbdev;
 	ifbdev->helper.funcs = &intel_fb_helper_funcs;
+	if (!intel_fbdev_init_bios(dev, ifbdev))
+		ifbdev->preferred_bpp = 32;
 
 	ret = drm_fb_helper_init(dev, &ifbdev->helper,
-				 INTEL_INFO(dev)->num_pipes,
-				 4);
+				 INTEL_INFO(dev)->num_pipes, 4);
 	if (ret) {
 		kfree(ifbdev);
 		return ret;
 	}
 
+	dev_priv->fbdev = ifbdev;
 	drm_fb_helper_single_add_all_connectors(&ifbdev->helper);
 
 	return 0;
@@ -483,9 +607,10 @@ int intel_fbdev_init(struct drm_device *dev)
 void intel_fbdev_initial_config(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 
 	/* Due to peculiar init order wrt to hpd handling this is separate. */
-	drm_fb_helper_initial_config(&dev_priv->fbdev->helper, 32);
+	drm_fb_helper_initial_config(&ifbdev->helper, ifbdev->preferred_bpp);
 }
 
 void intel_fbdev_fini(struct drm_device *dev)
@@ -523,7 +648,8 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 void intel_fbdev_output_poll_changed(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
+	if (dev_priv->fbdev)
+		drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
 }
 
 void intel_fbdev_restore_mode(struct drm_device *dev)
@@ -531,7 +657,7 @@ void intel_fbdev_restore_mode(struct drm_device *dev)
 	int ret;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (INTEL_INFO(dev)->num_pipes == 0)
+	if (!dev_priv->fbdev)
 		return;
 
 	drm_modeset_lock_all(dev);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ceb479733991..b0413e190625 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -848,6 +848,30 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
+static bool hdmi_12bpc_possible(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct intel_encoder *encoder;
+	int count = 0, count_hdmi = 0;
+
+	if (!HAS_PCH_SPLIT(dev))
+		return false;
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
+		if (encoder->new_crtc != crtc)
+			continue;
+
+		count_hdmi += encoder->type == INTEL_OUTPUT_HDMI;
+		count++;
+	}
+
+	/*
+	 * HDMI 12bpc affects the clocks, so it's only possible
+	 * when not cloning with other encoder types.
+	 */
+	return count_hdmi > 0 && count_hdmi == count;
+}
+
 bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 			       struct intel_crtc_config *pipe_config)
 {
@@ -880,7 +904,8 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	 * within limits.
 	 */
 	if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink &&
-	    clock_12bpc <= portclock_limit && HAS_PCH_SPLIT(dev)) {
+	    clock_12bpc <= portclock_limit &&
+	    hdmi_12bpc_possible(encoder->new_crtc)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
 
@@ -1318,7 +1343,14 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 
 	intel_encoder->type = INTEL_OUTPUT_HDMI;
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
-	intel_encoder->cloneable = false;
+	intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG;
+	/*
+	 * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems
+	 * to work on real hardware. And since g4x can send infoframes to
+	 * only one port anyway, nothing is lost by allowing it.
+	 */
+	if (IS_G4X(dev))
+		intel_encoder->cloneable |= 1 << INTEL_OUTPUT_HDMI;
 
 	intel_dig_port->port = port;
 	intel_dig_port->hdmi.hdmi_reg = hdmi_reg;
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 48293d2cbf41..f1ecf916474a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -963,7 +963,7 @@ void intel_lvds_init(struct drm_device *dev)
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_LVDS;
 
-	intel_encoder->cloneable = false;
+	intel_encoder->cloneable = 0;
 	if (HAS_PCH_SPLIT(dev))
 		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
 	else if (IS_GEN4(dev))
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f070d5d769ce..6e73125fc782 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2085,7 +2085,7 @@ static void intel_print_wm_latency(struct drm_device *dev,
 	}
 }
 
-static void intel_setup_wm_latency(struct drm_device *dev)
+static void ilk_setup_wm_latency(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -2907,9 +2907,9 @@ static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 	 * the hw runs at the minimal clock before selecting the desired
 	 * frequency, if the down threshold expires in that window we will not
 	 * receive a down interrupt. */
-	limits = dev_priv->rps.max_delay << 24;
-	if (val <= dev_priv->rps.min_delay)
-		limits |= dev_priv->rps.min_delay << 16;
+	limits = dev_priv->rps.max_freq_softlimit << 24;
+	if (val <= dev_priv->rps.min_freq_softlimit)
+		limits |= dev_priv->rps.min_freq_softlimit << 16;
 
 	return limits;
 }
@@ -2921,26 +2921,26 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 	new_power = dev_priv->rps.power;
 	switch (dev_priv->rps.power) {
 	case LOW_POWER:
-		if (val > dev_priv->rps.rpe_delay + 1 && val > dev_priv->rps.cur_delay)
+		if (val > dev_priv->rps.efficient_freq + 1 && val > dev_priv->rps.cur_freq)
 			new_power = BETWEEN;
 		break;
 
 	case BETWEEN:
-		if (val <= dev_priv->rps.rpe_delay && val < dev_priv->rps.cur_delay)
+		if (val <= dev_priv->rps.efficient_freq && val < dev_priv->rps.cur_freq)
 			new_power = LOW_POWER;
-		else if (val >= dev_priv->rps.rp0_delay && val > dev_priv->rps.cur_delay)
+		else if (val >= dev_priv->rps.rp0_freq && val > dev_priv->rps.cur_freq)
 			new_power = HIGH_POWER;
 		break;
 
 	case HIGH_POWER:
-		if (val < (dev_priv->rps.rp1_delay + dev_priv->rps.rp0_delay) >> 1 && val < dev_priv->rps.cur_delay)
+		if (val < (dev_priv->rps.rp1_freq + dev_priv->rps.rp0_freq) >> 1 && val < dev_priv->rps.cur_freq)
 			new_power = BETWEEN;
 		break;
 	}
 	/* Max/min bins are special */
-	if (val == dev_priv->rps.min_delay)
+	if (val == dev_priv->rps.min_freq_softlimit)
 		new_power = LOW_POWER;
-	if (val == dev_priv->rps.max_delay)
+	if (val == dev_priv->rps.max_freq_softlimit)
 		new_power = HIGH_POWER;
 	if (new_power == dev_priv->rps.power)
 		return;
@@ -3014,10 +3014,10 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-	WARN_ON(val > dev_priv->rps.max_delay);
-	WARN_ON(val < dev_priv->rps.min_delay);
+	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
+	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
 
-	if (val == dev_priv->rps.cur_delay) {
+	if (val == dev_priv->rps.cur_freq) {
 		/* min/max delay may still have been modified so be sure to
 		 * write the limits value */
 		I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
@@ -3045,7 +3045,7 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 
 	POSTING_READ(GEN6_RPNSWREQ);
 
-	dev_priv->rps.cur_delay = val;
+	dev_priv->rps.cur_freq = val;
 
 	trace_intel_gpu_freq_change(val * 50);
 }
@@ -3065,7 +3065,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 	 * When we are idle.  Drop to min voltage state.
 	 */
 
-	if (dev_priv->rps.cur_delay <= dev_priv->rps.min_delay)
+	if (dev_priv->rps.cur_freq <= dev_priv->rps.min_freq_softlimit)
 		return;
 
 	/* Mask turbo interrupt so that they will not come in between */
@@ -3082,10 +3082,10 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 		return;
 	}
 
-	dev_priv->rps.cur_delay = dev_priv->rps.min_delay;
+	dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit;
 
 	vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ,
-					dev_priv->rps.min_delay);
+					dev_priv->rps.min_freq_softlimit);
 
 	if (wait_for(((vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS))
 				& GENFREQSTATUS) == 0, 5))
@@ -3099,7 +3099,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 	/* Unmask Up interrupts */
 	dev_priv->rps.rp_up_masked = true;
 	gen6_set_pm_mask(dev_priv, GEN6_PM_RP_DOWN_THRESHOLD,
-						dev_priv->rps.min_delay);
+						dev_priv->rps.min_freq_softlimit);
 }
 
 void gen6_rps_idle(struct drm_i915_private *dev_priv)
@@ -3111,7 +3111,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 		if (IS_VALLEYVIEW(dev))
 			vlv_set_rps_idle(dev_priv);
 		else
-			gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
+			gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3124,9 +3124,9 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
 		if (IS_VALLEYVIEW(dev))
-			valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
+			valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
 		else
-			gen6_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
+			gen6_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3137,20 +3137,20 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-	WARN_ON(val > dev_priv->rps.max_delay);
-	WARN_ON(val < dev_priv->rps.min_delay);
+	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
+	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
 
 	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
-			 dev_priv->rps.cur_delay,
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+			 dev_priv->rps.cur_freq,
 			 vlv_gpu_freq(dev_priv, val), val);
 
-	if (val == dev_priv->rps.cur_delay)
+	if (val == dev_priv->rps.cur_freq)
 		return;
 
 	vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
 
-	dev_priv->rps.cur_delay = val;
+	dev_priv->rps.cur_freq = val;
 
 	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
 }
@@ -3292,8 +3292,8 @@ static void gen8_enable_rps(struct drm_device *dev)
 
 	/* Docs recommend 900MHz, and 300 MHz respectively */
 	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-		   dev_priv->rps.max_delay << 24 |
-		   dev_priv->rps.min_delay << 16);
+		   dev_priv->rps.max_freq_softlimit << 24 |
+		   dev_priv->rps.min_freq_softlimit << 16);
 
 	I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
 	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
@@ -3324,9 +3324,9 @@ static void gen6_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring;
-	u32 rp_state_cap, hw_max, hw_min;
+	u32 rp_state_cap;
 	u32 gt_perf_status;
-	u32 rc6vids, pcu_mbox, rc6_mask = 0;
+	u32 rc6vids, pcu_mbox = 0, rc6_mask = 0;
 	u32 gtfifodbg;
 	int rc6_mode;
 	int i, ret;
@@ -3352,20 +3352,23 @@ static void gen6_enable_rps(struct drm_device *dev)
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
 	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 
-	/* In units of 50MHz */
-	dev_priv->rps.hw_max = hw_max = rp_state_cap & 0xff;
-	hw_min = (rp_state_cap >> 16) & 0xff;
-	dev_priv->rps.rp1_delay = (rp_state_cap >>  8) & 0xff;
-	dev_priv->rps.rp0_delay = (rp_state_cap >>  0) & 0xff;
-	dev_priv->rps.rpe_delay = dev_priv->rps.rp1_delay;
-	dev_priv->rps.cur_delay = 0;
+	/* All of these values are in units of 50MHz */
+	dev_priv->rps.cur_freq		= 0;
+	/* static values from HW: RP0 < RPe < RP1 < RPn (min_freq) */
+	dev_priv->rps.rp1_freq		= (rp_state_cap >>  8) & 0xff;
+	dev_priv->rps.rp0_freq		= (rp_state_cap >>  0) & 0xff;
+	dev_priv->rps.min_freq		= (rp_state_cap >> 16) & 0xff;
+	/* XXX: only BYT has a special efficient freq */
+	dev_priv->rps.efficient_freq	= dev_priv->rps.rp1_freq;
+	/* hw_max = RP0 until we check for overclocking */
+	dev_priv->rps.max_freq		= dev_priv->rps.rp0_freq;
 
 	/* Preserve min/max settings in case of re-init */
-	if (dev_priv->rps.max_delay == 0)
-		dev_priv->rps.max_delay = hw_max;
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
 
-	if (dev_priv->rps.min_delay == 0)
-		dev_priv->rps.min_delay = hw_min;
+	if (dev_priv->rps.min_freq_softlimit == 0)
+		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
 
 	/* disable the counters and set deterministic thresholds */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -3414,21 +3417,19 @@ static void gen6_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 
 	ret = sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_MIN_FREQ_TABLE, 0);
-	if (!ret) {
-		pcu_mbox = 0;
-		ret = sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS, &pcu_mbox);
-		if (!ret && (pcu_mbox & (1<<31))) { /* OC supported */
-			DRM_DEBUG_DRIVER("Overclocking supported. Max: %dMHz, Overclock max: %dMHz\n",
-					 (dev_priv->rps.max_delay & 0xff) * 50,
-					 (pcu_mbox & 0xff) * 50);
-			dev_priv->rps.hw_max = pcu_mbox & 0xff;
-		}
-	} else {
+	if (ret)
 		DRM_DEBUG_DRIVER("Failed to set the min frequency\n");
+
+	ret = sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS, &pcu_mbox);
+	if (!ret && (pcu_mbox & (1<<31))) { /* OC supported */
+		DRM_DEBUG_DRIVER("Overclocking supported. Max: %dMHz, Overclock max: %dMHz\n",
+				 (dev_priv->rps.max_freq_softlimit & 0xff) * 50,
+				 (pcu_mbox & 0xff) * 50);
+		dev_priv->rps.max_freq = pcu_mbox & 0xff;
 	}
 
 	dev_priv->rps.power = HIGH_POWER; /* force a reset */
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
+	gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
 
 	gen6_enable_rps_interrupts(dev);
 
@@ -3484,9 +3485,9 @@ void gen6_update_ring_freq(struct drm_device *dev)
 	 * to use for memory access.  We do this by specifying the IA frequency
 	 * the PCU should use as a reference to determine the ring frequency.
 	 */
-	for (gpu_freq = dev_priv->rps.max_delay; gpu_freq >= dev_priv->rps.min_delay;
+	for (gpu_freq = dev_priv->rps.max_freq_softlimit; gpu_freq >= dev_priv->rps.min_freq_softlimit;
 	     gpu_freq--) {
-		int diff = dev_priv->rps.max_delay - gpu_freq;
+		int diff = dev_priv->rps.max_freq_softlimit - gpu_freq;
 		unsigned int ia_freq = 0, ring_freq = 0;
 
 		if (INTEL_INFO(dev)->gen >= 8) {
@@ -3597,7 +3598,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring;
-	u32 gtfifodbg, val, hw_max, hw_min, rc6_mode = 0;
+	u32 gtfifodbg, val, rc6_mode = 0;
 	int i;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -3652,38 +3653,39 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
 	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
 
-	dev_priv->rps.cur_delay = (val >> 8) & 0xff;
+	dev_priv->rps.cur_freq = (val >> 8) & 0xff;
 	DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
-			 dev_priv->rps.cur_delay);
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+			 dev_priv->rps.cur_freq);
 
-	dev_priv->rps.hw_max = hw_max = valleyview_rps_max_freq(dev_priv);
+	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, hw_max),
-			 hw_max);
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
+			 dev_priv->rps.max_freq);
 
-	dev_priv->rps.rpe_delay = valleyview_rps_rpe_freq(dev_priv);
+	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.rpe_delay),
-			 dev_priv->rps.rpe_delay);
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
 
-	hw_min = valleyview_rps_min_freq(dev_priv);
+	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, hw_min),
-			 hw_min);
+			 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_delay == 0)
-		dev_priv->rps.max_delay = hw_max;
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
 
-	if (dev_priv->rps.min_delay == 0)
-		dev_priv->rps.min_delay = hw_min;
+	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.rpe_delay),
-			 dev_priv->rps.rpe_delay);
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
 
-	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
+	valleyview_set_rps(dev_priv->dev, dev_priv->rps.efficient_freq);
 
 	dev_priv->rps.rp_up_masked = false;
 	dev_priv->rps.rp_down_masked = false;
@@ -4124,7 +4126,7 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
 
 	assert_spin_locked(&mchdev_lock);
 
-	pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_delay * 4));
+	pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_freq * 4));
 	pxvid = (pxvid >> 24) & 0x7f;
 	ext_v = pvid_to_extvid(dev_priv, pxvid);
 
@@ -5345,8 +5347,6 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 	bool is_enabled, enable_requested;
 	uint32_t tmp;
 
-	WARN_ON(dev_priv->pc8.enabled);
-
 	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
 	is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED;
 	enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST;
@@ -5391,7 +5391,6 @@ static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv,
 static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 				  struct i915_power_well *power_well)
 {
-	hsw_disable_package_c8(dev_priv);
 	hsw_set_power_well(dev_priv, power_well, true);
 }
 
@@ -5399,7 +5398,6 @@ static void hsw_power_well_disable(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
 	hsw_set_power_well(dev_priv, power_well, false);
-	hsw_enable_package_c8(dev_priv);
 }
 
 static void i9xx_always_on_power_well_noop(struct drm_i915_private *dev_priv,
@@ -5577,6 +5575,8 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
 	struct i915_power_well *power_well;
 	int i;
 
+	intel_runtime_pm_get(dev_priv);
+
 	power_domains = &dev_priv->power_domains;
 
 	mutex_lock(&power_domains->lock);
@@ -5621,6 +5621,8 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	}
 
 	mutex_unlock(&power_domains->lock);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 static struct i915_power_domains *hsw_pwr;
@@ -5884,15 +5886,14 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
 	intel_power_domains_resume(dev_priv);
 }
 
-/* Disables PC8 so we can use the GMBUS and DP AUX interrupts. */
 void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
 {
-	hsw_disable_package_c8(dev_priv);
+	intel_runtime_pm_get(dev_priv);
 }
 
 void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
 {
-	hsw_enable_package_c8(dev_priv);
+	intel_runtime_pm_put(dev_priv);
 }
 
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
@@ -5924,8 +5925,6 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = dev_priv->dev;
 	struct device *device = &dev->pdev->dev;
 
-	dev_priv->pm.suspended = false;
-
 	if (!HAS_RUNTIME_PM(dev))
 		return;
 
@@ -5934,6 +5933,8 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv)
 	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
 	pm_runtime_mark_last_busy(device);
 	pm_runtime_use_autosuspend(device);
+
+	pm_runtime_put_autosuspend(device);
 }
 
 void intel_fini_runtime_pm(struct drm_i915_private *dev_priv)
@@ -5985,7 +5986,7 @@ void intel_init_pm(struct drm_device *dev)
 
 	/* For FIFO watermark updates */
 	if (HAS_PCH_SPLIT(dev)) {
-		intel_setup_wm_latency(dev);
+		ilk_setup_wm_latency(dev);
 
 		if ((IS_GEN5(dev) && dev_priv->wm.pri_latency[1] &&
 		     dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) ||
@@ -6156,12 +6157,9 @@ void intel_pm_setup(struct drm_device *dev)
 
 	mutex_init(&dev_priv->rps.hw_lock);
 
-	mutex_init(&dev_priv->pc8.lock);
-	dev_priv->pc8.requirements_met = false;
-	dev_priv->pc8.irqs_disabled = false;
-	dev_priv->pc8.enabled = false;
-	dev_priv->pc8.disable_count = 1; /* requirements_met */
-	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
 	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
 			  intel_gen6_powersave_work);
+
+	dev_priv->pm.suspended = false;
+	dev_priv->pm.irqs_disabled = false;
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 859092130c18..4eb3e062b4e3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -440,15 +440,17 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 
 	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
-	if (I915_NEED_GFX_HWS(dev))
-		intel_ring_setup_status_page(ring);
-	else
-		ring_setup_phys_status_page(ring);
-
 	/* Stop the ring if it's running. */
 	I915_WRITE_CTL(ring, 0);
 	I915_WRITE_HEAD(ring, 0);
 	ring->write_tail(ring, 0);
+	if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000))
+		DRM_ERROR("%s :timed out trying to stop ring\n", ring->name);
+
+	if (I915_NEED_GFX_HWS(dev))
+		intel_ring_setup_status_page(ring);
+	else
+		ring_setup_phys_status_page(ring);
 
 	head = I915_READ_HEAD(ring) & HEAD_ADDR;
 
@@ -979,9 +981,19 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 	I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
 	POSTING_READ(mmio);
 
-	/* Flush the TLB for this page */
-	if (INTEL_INFO(dev)->gen >= 6) {
+	/*
+	 * Flush the TLB for this page
+	 *
+	 * FIXME: These two bits have disappeared on gen8, so a question
+	 * arises: do we still need this and if so how should we go about
+	 * invalidating the TLB?
+	 */
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8) {
 		u32 reg = RING_INSTPM(ring->mmio_base);
+
+		/* ring should be idle before issuing a sync flush*/
+		WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
+
 		I915_WRITE(reg,
 			   _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
 					      INSTPM_SYNC_FLUSH));
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 09af92099c1b..f11ceb230db4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -33,6 +33,8 @@ struct  intel_hw_status_page {
 #define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
 #define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
 
+#define I915_READ_MODE(ring) I915_READ(RING_MI_MODE((ring)->mmio_base))
+
 enum intel_ring_hangcheck_action {
 	HANGCHECK_IDLE = 0,
 	HANGCHECK_WAIT,
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 825853d82a4d..d27155adf5db 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1461,7 +1461,7 @@ static void intel_enable_sdvo(struct intel_encoder *encoder)
 	u32 temp;
 	bool input1, input2;
 	int i;
-	u8 status;
+	bool success;
 
 	temp = I915_READ(intel_sdvo->sdvo_reg);
 	if ((temp & SDVO_ENABLE) == 0) {
@@ -1475,12 +1475,12 @@ static void intel_enable_sdvo(struct intel_encoder *encoder)
 	for (i = 0; i < 2; i++)
 		intel_wait_for_vblank(dev, intel_crtc->pipe);
 
-	status = intel_sdvo_get_trained_inputs(intel_sdvo, &input1, &input2);
+	success = intel_sdvo_get_trained_inputs(intel_sdvo, &input1, &input2);
 	/* Warn if the device reported failure to sync.
 	 * A lot of SDVO devices fail to notify of sync, but it's
 	 * a given it the status is a success, we succeeded.
 	 */
-	if (status == SDVO_CMD_STATUS_SUCCESS && !input1) {
+	if (success && !input1) {
 		DRM_DEBUG_KMS("First %s output reported failure to "
 				"sync\n", SDVO_NAME(intel_sdvo));
 	}
@@ -3032,7 +3032,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 	 * simplistic anyway to express such constraints, so just give up on
 	 * cloning for SDVO encoders.
 	 */
-	intel_sdvo->base.cloneable = false;
+	intel_sdvo->base.cloneable = 0;
 
 	intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo, sdvo_reg);
 
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index b64fc1c6ff3f..5be4ab218054 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1639,9 +1639,8 @@ intel_tv_init(struct drm_device *dev)
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
-	intel_encoder->cloneable = false;
+	intel_encoder->cloneable = 0;
 	intel_encoder->base.possible_crtcs = ((1 << 0) | (1 << 1));
-	intel_encoder->base.possible_clones = (1 << INTEL_OUTPUT_TVOUT);
 	intel_tv->type = DRM_MODE_CONNECTOR_Unknown;
 
 	/* BIOS margin values */
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 7861d97600e1..c3832d9270a6 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -280,12 +280,17 @@ void vlv_force_wake_put(struct drm_i915_private *dev_priv,
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
-	if (fw_engine & FORCEWAKE_RENDER &&
-	    --dev_priv->uncore.fw_rendercount != 0)
-		fw_engine &= ~FORCEWAKE_RENDER;
-	if (fw_engine & FORCEWAKE_MEDIA &&
-	    --dev_priv->uncore.fw_mediacount != 0)
-		fw_engine &= ~FORCEWAKE_MEDIA;
+	if (fw_engine & FORCEWAKE_RENDER) {
+		WARN_ON(!dev_priv->uncore.fw_rendercount);
+		if (--dev_priv->uncore.fw_rendercount != 0)
+			fw_engine &= ~FORCEWAKE_RENDER;
+	}
+
+	if (fw_engine & FORCEWAKE_MEDIA) {
+		WARN_ON(!dev_priv->uncore.fw_mediacount);
+		if (--dev_priv->uncore.fw_mediacount != 0)
+			fw_engine &= ~FORCEWAKE_MEDIA;
+	}
 
 	if (fw_engine)
 		dev_priv->uncore.funcs.force_wake_put(dev_priv, fw_engine);
@@ -301,6 +306,8 @@ static void gen6_force_wake_timer(unsigned long arg)
 	assert_device_not_suspended(dev_priv);
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	WARN_ON(!dev_priv->uncore.forcewake_count);
+
 	if (--dev_priv->uncore.forcewake_count == 0)
 		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
@@ -308,9 +315,17 @@ static void gen6_force_wake_timer(unsigned long arg)
 	intel_runtime_pm_put(dev_priv);
 }
 
-static void intel_uncore_forcewake_reset(struct drm_device *dev)
+static void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+
+	del_timer_sync(&dev_priv->uncore.force_wake_timer);
+
+	/* Hold uncore.lock across reset to prevent any register access
+	 * with forcewake not set correctly
+	 */
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
 	if (IS_VALLEYVIEW(dev))
 		vlv_force_wake_reset(dev_priv);
@@ -319,6 +334,35 @@ static void intel_uncore_forcewake_reset(struct drm_device *dev)
 
 	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_GEN8(dev))
 		__gen7_gt_force_wake_mt_reset(dev_priv);
+
+	if (restore) { /* If reset with a user forcewake, try to restore */
+		unsigned fw = 0;
+
+		if (IS_VALLEYVIEW(dev)) {
+			if (dev_priv->uncore.fw_rendercount)
+				fw |= FORCEWAKE_RENDER;
+
+			if (dev_priv->uncore.fw_mediacount)
+				fw |= FORCEWAKE_MEDIA;
+		} else {
+			if (dev_priv->uncore.forcewake_count)
+				fw = FORCEWAKE_ALL;
+		}
+
+		if (fw)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv, fw);
+
+		if (IS_GEN6(dev) || IS_GEN7(dev))
+			dev_priv->uncore.fifo_count =
+				__raw_i915_read32(dev_priv, GTFIFOCTL) &
+				GT_FIFO_FREE_ENTRIES_MASK;
+	} else {
+		dev_priv->uncore.forcewake_count = 0;
+		dev_priv->uncore.fw_rendercount = 0;
+		dev_priv->uncore.fw_mediacount = 0;
+	}
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
 void intel_uncore_early_sanitize(struct drm_device *dev)
@@ -344,7 +388,7 @@ void intel_uncore_early_sanitize(struct drm_device *dev)
 		__raw_i915_write32(dev_priv, GTFIFODBG,
 				   __raw_i915_read32(dev_priv, GTFIFODBG));
 
-	intel_uncore_forcewake_reset(dev);
+	intel_uncore_forcewake_reset(dev, false);
 }
 
 void intel_uncore_sanitize(struct drm_device *dev)
@@ -415,6 +459,8 @@ void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
 
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	WARN_ON(!dev_priv->uncore.forcewake_count);
+
 	if (--dev_priv->uncore.forcewake_count == 0) {
 		dev_priv->uncore.forcewake_count++;
 		delayed = true;
@@ -690,6 +736,8 @@ void intel_uncore_init(struct drm_device *dev)
 	setup_timer(&dev_priv->uncore.force_wake_timer,
 		    gen6_force_wake_timer, (unsigned long)dev_priv);
 
+	intel_uncore_early_sanitize(dev);
+
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __vlv_force_wake_get;
 		dev_priv->uncore.funcs.force_wake_put = __vlv_force_wake_put;
@@ -798,13 +846,9 @@ void intel_uncore_init(struct drm_device *dev)
 
 void intel_uncore_fini(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	del_timer_sync(&dev_priv->uncore.force_wake_timer);
-
 	/* Paranoia: make sure we have disabled everything before we exit. */
 	intel_uncore_sanitize(dev);
-	intel_uncore_forcewake_reset(dev);
+	intel_uncore_forcewake_reset(dev, false);
 }
 
 static const struct register_whitelist {
@@ -953,13 +997,6 @@ static int gen6_do_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int	ret;
-	unsigned long irqflags;
-	u32 fw_engine = 0;
-
-	/* Hold uncore.lock across reset to prevent any register access
-	 * with forcewake not set correctly
-	 */
-	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
 	/* Reset the chip */
 
@@ -972,29 +1009,8 @@ static int gen6_do_reset(struct drm_device *dev)
 	/* Spin waiting for the device to ack the reset request */
 	ret = wait_for((__raw_i915_read32(dev_priv, GEN6_GDRST) & GEN6_GRDOM_FULL) == 0, 500);
 
-	intel_uncore_forcewake_reset(dev);
+	intel_uncore_forcewake_reset(dev, true);
 
-	/* If reset with a user forcewake, try to restore */
-	if (IS_VALLEYVIEW(dev)) {
-		if (dev_priv->uncore.fw_rendercount)
-			fw_engine |= FORCEWAKE_RENDER;
-
-		if (dev_priv->uncore.fw_mediacount)
-			fw_engine |= FORCEWAKE_MEDIA;
-	} else {
-		if (dev_priv->uncore.forcewake_count)
-			fw_engine = FORCEWAKE_ALL;
-	}
-
-	if (fw_engine)
-		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_engine);
-
-	if (IS_GEN6(dev) || IS_GEN7(dev))
-		dev_priv->uncore.fifo_count =
-			__raw_i915_read32(dev_priv, GTFIFOCTL) &
-			GT_FIFO_FREE_ENTRIES_MASK;
-
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 	return ret;
 }
 
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 42947566e755..b4f58914bf7d 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -438,6 +438,9 @@ struct drm_dp_aux_msg {
  * The .dev field should be set to a pointer to the device that implements
  * the AUX channel.
  *
+ * The .name field may be used to specify the name of the I2C adapter. If set to
+ * NULL, dev_name() of .dev will be used.
+ *
  * Drivers provide a hardware-specific implementation of how transactions
  * are executed via the .transfer() function. A pointer to a drm_dp_aux_msg
  * structure describing the transaction is passed into this function. Upon
@@ -455,6 +458,7 @@ struct drm_dp_aux_msg {
  * should call drm_dp_aux_unregister_i2c_bus() to remove the I2C adapter.
  */
 struct drm_dp_aux {
+	const char *name;
 	struct i2c_adapter ddc;
 	struct device *dev;