Merge tag 'drm-intel-next-2014-03-21' of git://anongit.freedesktop.org/drm-intel into drm-next

- Inherit/reuse firmwar framebuffers (for real this time) from Jesse, less
  flicker for fastbooting.
- More flexible cloning for hdmi (Ville).
- Some PPGTT fixes from Ben.
- Ring init fixes from Naresh Kumar.
- set_cache_level regression fixes for the vma conversion from Ville&Chris.
- Conversion to the new dp aux helpers (Jani).
- Unification of runtime pm with pc8 support from Paulo, prep work for runtime
  pm on other platforms than HSW.
- Larger cursor sizes (Sagar Kamble).
- Piles of improvements and fixes all over, as usual.

* tag 'drm-intel-next-2014-03-21' of git://anongit.freedesktop.org/drm-intel: (75 commits)
  drm/i915: Include a note about the dangers of I915_READ64/I915_WRITE64
  drm/i915/sdvo: fix questionable return value check
  drm/i915: Fix unsafe loop iteration over vma whilst unbinding them
  drm/i915: Enabling 128x128 and 256x256 ARGB Cursor Support
  drm/i915: Print how many objects are shared in per-process stats
  drm/i915: Per-process stats work better when evaluated per-process
  drm/i915: remove rps local variables
  drm/i915: Remove extraneous MMIO for RPS
  drm/i915: Rename and comment all the RPS *stuff*
  drm/i915: Store the HW min frequency as min_freq
  drm/i915: Fix coding style for RPS
  drm/i915: Reorganize the overclock code
  drm/i915: init pm.suspended earlier
  drm/i915: update the PC8 and runtime PM documentation
  drm/i915: rename __hsw_do_{en, dis}able_pc8
  drm/i915: kill struct i915_package_c8
  drm/i915: move pc8.irqs_disabled to pm.irqs_disabled
  drm/i915: remove dev_priv->pc8.enabled
  drm/i915: don't get/put PC8 when getting/putting power wells
  drm/i915: make intel_aux_display_runtime_get get runtime PM, not PC8
  ...

Conflicts:
	drivers/gpu/drm/i915/intel_display.c
	drivers/gpu/drm/i915/intel_dp.c

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);
 }

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));

drivers/gpu/drm/i915/i915_debugfs.c

@@ -299,27 +299,61 @@ 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))
+	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 (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);

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);
 

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;
 }
 

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);
@@ -459,7 +462,8 @@ 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 (*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 */
@@ -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.
- *
- * 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 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.
+ * 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.
  *
- * 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.
+ * 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.
  *
- * 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)
 

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;
 		}
 	}
 

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);
 }

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 */

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;
 		}
 	}

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);
 }

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). "

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

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);
 

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,

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

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)

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);

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);
 

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);

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)
@@ -523,6 +648,7 @@ 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;
+	if (dev_priv->fbdev)
 		drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
 }
 
@@ -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);

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;

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))

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));

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,

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);
 

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 */

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)
+	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 &&
-	    --dev_priv->uncore.fw_mediacount != 0)
+	}
+
+	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;
 }
 

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;