Merge tag 'drm-intel-next-2015-10-10' of git://anongit.freedesktop.org/drm-intel into drm-next

- dmc fixes from Animesh (not yet all) for deeper sleep states
- piles of prep patches from Ville to make mmio functions type-safe
- more fbc work from Paulo all over
- w/a shuffling from Arun Siluvery
- first part of atomic watermark updates from Matt and Ville (later parts had to
  be dropped again unfortunately)
- lots of patches to prepare bxt dsi support ( Shashank Sharma)
- userptr fixes from Chris
- audio rate interface between i915/snd_hda plus kerneldoc (Libin Yang)
- shrinker improvements and fixes (Chris Wilson)
- lots and lots of small patches all over

* tag 'drm-intel-next-2015-10-10' of git://anongit.freedesktop.org/drm-intel: (134 commits)
  drm/i915: Update DRIVER_DATE to 20151010
  drm/i915: Partial revert of atomic watermark series
  drm/i915: Early exit from semaphore_waits_for for execlist mode.
  drm/i915: Remove wrong warning from i915_gem_context_clean
  drm/i915: Determine the stolen memory base address on gen2
  drm/i915: fix FBC buffer size checks
  drm/i915: fix CFB size calculation
  drm/i915: remove pre-atomic check from SKL update_primary_plane
  drm/i915: don't allocate fbcon from stolen memory if it's too big
  Revert "drm/i915: Call encoder hotplug for init and resume cases"
  Revert "drm/i915: Add hot_plug hook for hdmi encoder"
  drm/i915: use error path
  drm/i915/irq: Fix misspelled word register in kernel-doc
  drm/i915/irq: Fix kernel-doc warnings
  drm/i915: Hook up ring workaround writes at context creation time on Gen6-7.
  drm/i915: Don't warn if the workaround list is empty.
  drm/i915: Resurrect golden context on gen6/7
  drm/i915/chv: remove pre-production hardware workarounds
  drm/i915/snb: remove pre-production hardware workaround
  drm/i915/bxt: Set time interval unit to 0.833us
  ...

Documentation/DocBook/drm.tmpl

@@ -3989,6 +3989,7 @@ int num_ioctls;</synopsis>
 	<title>High Definition Audio</title>
 !Pdrivers/gpu/drm/i915/intel_audio.c High Definition Audio over HDMI and Display Port
 !Idrivers/gpu/drm/i915/intel_audio.c
+!Iinclude/drm/i915_component.h
       </sect2>
       <sect2>
 	<title>Panel Self Refresh PSR (PSR/SRD)</title>

drivers/gpu/drm/i915/dvo.h

@@ -94,8 +94,8 @@ struct intel_dvo_dev_ops {
 	 * after this function is called.
 	 */
 	void (*mode_set)(struct intel_dvo_device *dvo,
-			 struct drm_display_mode *mode,
-			 struct drm_display_mode *adjusted_mode);
+			 const struct drm_display_mode *mode,
+			 const struct drm_display_mode *adjusted_mode);
 
 	/*
 	 * Probe for a connected output, and return detect_status.

drivers/gpu/drm/i915/dvo_ch7017.c

@@ -255,8 +255,8 @@ static enum drm_mode_status ch7017_mode_valid(struct intel_dvo_device *dvo,
 }
 
 static void ch7017_mode_set(struct intel_dvo_device *dvo,
-			    struct drm_display_mode *mode,
-			    struct drm_display_mode *adjusted_mode)
+			    const struct drm_display_mode *mode,
+			    const struct drm_display_mode *adjusted_mode)
 {
 	uint8_t lvds_pll_feedback_div, lvds_pll_vco_control;
 	uint8_t outputs_enable, lvds_control_2, lvds_power_down;

drivers/gpu/drm/i915/dvo_ch7xxx.c

@@ -275,8 +275,8 @@ static enum drm_mode_status ch7xxx_mode_valid(struct intel_dvo_device *dvo,
 }
 
 static void ch7xxx_mode_set(struct intel_dvo_device *dvo,
-			    struct drm_display_mode *mode,
-			    struct drm_display_mode *adjusted_mode)
+			    const struct drm_display_mode *mode,
+			    const struct drm_display_mode *adjusted_mode)
 {
 	uint8_t tvco, tpcp, tpd, tlpf, idf;
 

drivers/gpu/drm/i915/dvo_ivch.c

@@ -394,8 +394,8 @@ static bool ivch_get_hw_state(struct intel_dvo_device *dvo)
 }
 
 static void ivch_mode_set(struct intel_dvo_device *dvo,
-			  struct drm_display_mode *mode,
-			  struct drm_display_mode *adjusted_mode)
+			  const struct drm_display_mode *mode,
+			  const struct drm_display_mode *adjusted_mode)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
 	uint16_t vr40 = 0;
@@ -414,16 +414,16 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 	vr40 = (VR40_STALL_ENABLE | VR40_VERTICAL_INTERP_ENABLE |
 		VR40_HORIZONTAL_INTERP_ENABLE);
 
-	if (mode->hdisplay != adjusted_mode->hdisplay ||
-	    mode->vdisplay != adjusted_mode->vdisplay) {
+	if (mode->hdisplay != adjusted_mode->crtc_hdisplay ||
+	    mode->vdisplay != adjusted_mode->crtc_vdisplay) {
 		uint16_t x_ratio, y_ratio;
 
 		vr01 |= VR01_PANEL_FIT_ENABLE;
 		vr40 |= VR40_CLOCK_GATING_ENABLE;
 		x_ratio = (((mode->hdisplay - 1) << 16) /
-			   (adjusted_mode->hdisplay - 1)) >> 2;
+			   (adjusted_mode->crtc_hdisplay - 1)) >> 2;
 		y_ratio = (((mode->vdisplay - 1) << 16) /
-			   (adjusted_mode->vdisplay - 1)) >> 2;
+			   (adjusted_mode->crtc_vdisplay - 1)) >> 2;
 		ivch_write(dvo, VR42, x_ratio);
 		ivch_write(dvo, VR41, y_ratio);
 	} else {

drivers/gpu/drm/i915/dvo_ns2501.c

@@ -546,8 +546,8 @@ static enum drm_mode_status ns2501_mode_valid(struct intel_dvo_device *dvo,
 }
 
 static void ns2501_mode_set(struct intel_dvo_device *dvo,
-			    struct drm_display_mode *mode,
-			    struct drm_display_mode *adjusted_mode)
+			    const struct drm_display_mode *mode,
+			    const struct drm_display_mode *adjusted_mode)
 {
 	const struct ns2501_configuration *conf;
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);

drivers/gpu/drm/i915/dvo_sil164.c

@@ -190,8 +190,8 @@ static enum drm_mode_status sil164_mode_valid(struct intel_dvo_device *dvo,
 }
 
 static void sil164_mode_set(struct intel_dvo_device *dvo,
-			    struct drm_display_mode *mode,
-			    struct drm_display_mode *adjusted_mode)
+			    const struct drm_display_mode *mode,
+			    const struct drm_display_mode *adjusted_mode)
 {
 	/* As long as the basics are set up, since we don't have clock
 	 * dependencies in the mode setup, we can just leave the

drivers/gpu/drm/i915/dvo_tfp410.c

@@ -222,8 +222,8 @@ static enum drm_mode_status tfp410_mode_valid(struct intel_dvo_device *dvo,
 }
 
 static void tfp410_mode_set(struct intel_dvo_device *dvo,
-			    struct drm_display_mode *mode,
-			    struct drm_display_mode *adjusted_mode)
+			    const struct drm_display_mode *mode,
+			    const struct drm_display_mode *adjusted_mode)
 {
 	/* As long as the basics are set up, since we don't have clock dependencies
 	* in the mode setup, we can just leave the registers alone and everything

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -448,6 +448,9 @@ static const struct drm_i915_reg_descriptor gen7_render_regs[] = {
 	REG32(GEN7_3DPRIM_INSTANCE_COUNT),
 	REG32(GEN7_3DPRIM_START_INSTANCE),
 	REG32(GEN7_3DPRIM_BASE_VERTEX),
+	REG32(GEN7_GPGPU_DISPATCHDIMX),
+	REG32(GEN7_GPGPU_DISPATCHDIMY),
+	REG32(GEN7_GPGPU_DISPATCHDIMZ),
 	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(0)),
 	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(1)),
 	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(2)),
@@ -1214,6 +1217,7 @@ int i915_cmd_parser_get_version(void)
 	 *    MI_PREDICATE_SRC1 registers.
 	 * 3. Allow access to the GPGPU_THREADS_DISPATCHED register.
 	 * 4. L3 atomic chicken bits of HSW_SCRATCH1 and HSW_ROW_CHICKEN3.
+	 * 5. GPGPU dispatch compute indirect registers.
 	 */
-	return 4;
+	return 5;
 }

drivers/gpu/drm/i915/i915_debugfs.c

@@ -253,7 +253,11 @@ static int obj_rank_by_stolen(void *priv,
 	struct drm_i915_gem_object *b =
 		container_of(B, struct drm_i915_gem_object, obj_exec_link);
 
-	return a->stolen->start - b->stolen->start;
+	if (a->stolen->start < b->stolen->start)
+		return -1;
+	if (a->stolen->start > b->stolen->start)
+		return 1;
+	return 0;
 }
 
 static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
@@ -1308,6 +1312,10 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_puts(m, "no P-state info available\n");
 	}
 
+	seq_printf(m, "Current CD clock frequency: %d kHz\n", dev_priv->cdclk_freq);
+	seq_printf(m, "Max CD clock frequency: %d kHz\n", dev_priv->max_cdclk_freq);
+	seq_printf(m, "Max pixel clock frequency: %d kHz\n", dev_priv->max_dotclk_freq);
+
 out:
 	intel_runtime_pm_put(dev_priv);
 	return ret;
@@ -2230,10 +2238,9 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 	for_each_ring(ring, dev_priv, unused) {
 		seq_printf(m, "%s\n", ring->name);
 		for (i = 0; i < 4; i++) {
-			u32 offset = 0x270 + i * 8;
-			u64 pdp = I915_READ(ring->mmio_base + offset + 4);
+			u64 pdp = I915_READ(GEN8_RING_PDP_UDW(ring, i));
 			pdp <<= 32;
-			pdp |= I915_READ(ring->mmio_base + offset);
+			pdp |= I915_READ(GEN8_RING_PDP_LDW(ring, i));
 			seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp);
 		}
 	}
@@ -2290,18 +2297,21 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 		struct task_struct *task;
 
 		task = get_pid_task(file->pid, PIDTYPE_PID);
-		if (!task)
-			return -ESRCH;
+		if (!task) {
+			ret = -ESRCH;
+			goto out_put;
+		}
 		seq_printf(m, "\nproc: %s\n", task->comm);
 		put_task_struct(task);
 		idr_for_each(&file_priv->context_idr, per_file_ctx,
 			     (void *)(unsigned long)m);
 	}
 
+out_put:
 	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
-	return 0;
+	return ret;
 }
 
 static int count_irq_waiters(struct drm_i915_private *i915)
@@ -2909,7 +2919,7 @@ static bool cursor_active(struct drm_device *dev, int pipe)
 	u32 state;
 
 	if (IS_845G(dev) || IS_I865G(dev))
-		state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
+		state = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE;
 	else
 		state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
 
@@ -3147,7 +3157,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 				   skl_ddb_entry_size(entry));
 		}
 
-		entry = &ddb->cursor[pipe];
+		entry = &ddb->plane[pipe][PLANE_CURSOR];
 		seq_printf(m, "  %-13s%8u%8u%8u\n", "Cursor", entry->start,
 			   entry->end, skl_ddb_entry_size(entry));
 	}
@@ -5040,13 +5050,38 @@ static void gen9_sseu_device_status(struct drm_device *dev,
 	}
 }
 
+static void broadwell_sseu_device_status(struct drm_device *dev,
+					 struct sseu_dev_status *stat)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int s;
+	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
+
+	stat->slice_total = hweight32(slice_info & GEN8_LSLICESTAT_MASK);
+
+	if (stat->slice_total) {
+		stat->subslice_per_slice = INTEL_INFO(dev)->subslice_per_slice;
+		stat->subslice_total = stat->slice_total *
+				       stat->subslice_per_slice;
+		stat->eu_per_subslice = INTEL_INFO(dev)->eu_per_subslice;
+		stat->eu_total = stat->eu_per_subslice * stat->subslice_total;
+
+		/* subtract fused off EU(s) from enabled slice(s) */
+		for (s = 0; s < stat->slice_total; s++) {
+			u8 subslice_7eu = INTEL_INFO(dev)->subslice_7eu[s];
+
+			stat->eu_total -= hweight8(subslice_7eu);
+		}
+	}
+}
+
 static int i915_sseu_status(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 sseu_dev_status stat;
 
-	if ((INTEL_INFO(dev)->gen < 8) || IS_BROADWELL(dev))
+	if (INTEL_INFO(dev)->gen < 8)
 		return -ENODEV;
 
 	seq_puts(m, "SSEU Device Info\n");
@@ -5071,6 +5106,8 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 	memset(&stat, 0, sizeof(stat));
 	if (IS_CHERRYVIEW(dev)) {
 		cherryview_sseu_device_status(dev, &stat);
+	} else if (IS_BROADWELL(dev)) {
+		broadwell_sseu_device_status(dev, &stat);
 	} else if (INTEL_INFO(dev)->gen >= 9) {
 		gen9_sseu_device_status(dev, &stat);
 	}

drivers/gpu/drm/i915/i915_dma.c

@@ -673,6 +673,82 @@ static void gen9_sseu_info_init(struct drm_device *dev)
 	info->has_eu_pg = (info->eu_per_subslice > 2);
 }
 
+static void broadwell_sseu_info_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_device_info *info;
+	const int s_max = 3, ss_max = 3, eu_max = 8;
+	int s, ss;
+	u32 fuse2, eu_disable[s_max], s_enable, ss_disable;
+
+	fuse2 = I915_READ(GEN8_FUSE2);
+	s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
+	ss_disable = (fuse2 & GEN8_F2_SS_DIS_MASK) >> GEN8_F2_SS_DIS_SHIFT;
+
+	eu_disable[0] = I915_READ(GEN8_EU_DISABLE0) & GEN8_EU_DIS0_S0_MASK;
+	eu_disable[1] = (I915_READ(GEN8_EU_DISABLE0) >> GEN8_EU_DIS0_S1_SHIFT) |
+			((I915_READ(GEN8_EU_DISABLE1) & GEN8_EU_DIS1_S1_MASK) <<
+			 (32 - GEN8_EU_DIS0_S1_SHIFT));
+	eu_disable[2] = (I915_READ(GEN8_EU_DISABLE1) >> GEN8_EU_DIS1_S2_SHIFT) |
+			((I915_READ(GEN8_EU_DISABLE2) & GEN8_EU_DIS2_S2_MASK) <<
+			 (32 - GEN8_EU_DIS1_S2_SHIFT));
+
+
+	info = (struct intel_device_info *)&dev_priv->info;
+	info->slice_total = hweight32(s_enable);
+
+	/*
+	 * The subslice disable field is global, i.e. it applies
+	 * to each of the enabled slices.
+	 */
+	info->subslice_per_slice = ss_max - hweight32(ss_disable);
+	info->subslice_total = info->slice_total * info->subslice_per_slice;
+
+	/*
+	 * Iterate through enabled slices and subslices to
+	 * count the total enabled EU.
+	 */
+	for (s = 0; s < s_max; s++) {
+		if (!(s_enable & (0x1 << s)))
+			/* skip disabled slice */
+			continue;
+
+		for (ss = 0; ss < ss_max; ss++) {
+			u32 n_disabled;
+
+			if (ss_disable & (0x1 << ss))
+				/* skip disabled subslice */
+				continue;
+
+			n_disabled = hweight8(eu_disable[s] >> (ss * eu_max));
+
+			/*
+			 * Record which subslices have 7 EUs.
+			 */
+			if (eu_max - n_disabled == 7)
+				info->subslice_7eu[s] |= 1 << ss;
+
+			info->eu_total += eu_max - n_disabled;
+		}
+	}
+
+	/*
+	 * BDW is expected to always have a uniform distribution of EU across
+	 * subslices with the exception that any one EU in any one subslice may
+	 * be fused off for die recovery.
+	 */
+	info->eu_per_subslice = info->subslice_total ?
+		DIV_ROUND_UP(info->eu_total, info->subslice_total) : 0;
+
+	/*
+	 * BDW supports slice power gating on devices with more than
+	 * one slice.
+	 */
+	info->has_slice_pg = (info->slice_total > 1);
+	info->has_subslice_pg = 0;
+	info->has_eu_pg = 0;
+}
+
 /*
  * Determine various intel_device_info fields at runtime.
  *
@@ -743,6 +819,8 @@ static void intel_device_info_runtime_init(struct drm_device *dev)
 	/* Initialize slice/subslice/EU info */
 	if (IS_CHERRYVIEW(dev))
 		cherryview_sseu_info_init(dev);
+	else if (IS_BROADWELL(dev))
+		broadwell_sseu_info_init(dev);
 	else if (INTEL_INFO(dev)->gen >= 9)
 		gen9_sseu_info_init(dev);
 
@@ -818,6 +896,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	mutex_init(&dev_priv->sb_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 	mutex_init(&dev_priv->csr_lock);
+	mutex_init(&dev_priv->av_mutex);
 
 	intel_pm_setup(dev);
 
@@ -1045,11 +1124,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 put_bridge:
 	pci_dev_put(dev_priv->bridge_dev);
 free_priv:
-	if (dev_priv->requests)
 	kmem_cache_destroy(dev_priv->requests);
-	if (dev_priv->vmas)
 	kmem_cache_destroy(dev_priv->vmas);
-	if (dev_priv->objects)
 	kmem_cache_destroy(dev_priv->objects);
 	kfree(dev_priv);
 	return ret;
@@ -1141,13 +1217,9 @@ int i915_driver_unload(struct drm_device *dev)
 	if (dev_priv->regs != NULL)
 		pci_iounmap(dev->pdev, dev_priv->regs);
 
-	if (dev_priv->requests)
 	kmem_cache_destroy(dev_priv->requests);
-	if (dev_priv->vmas)
 	kmem_cache_destroy(dev_priv->vmas);
-	if (dev_priv->objects)
 	kmem_cache_destroy(dev_priv->objects);
-
 	pci_dev_put(dev_priv->bridge_dev);
 	kfree(dev_priv);
 

drivers/gpu/drm/i915/i915_drv.c

@@ -443,6 +443,34 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 
 MODULE_DEVICE_TABLE(pci, pciidlist);
 
+static enum intel_pch intel_virt_detect_pch(struct drm_device *dev)
+{
+	enum intel_pch ret = PCH_NOP;
+
+	/*
+	 * In a virtualized passthrough environment we can be in a
+	 * setup where the ISA bridge is not able to be passed through.
+	 * In this case, a south bridge can be emulated and we have to
+	 * make an educated guess as to which PCH is really there.
+	 */
+
+	if (IS_GEN5(dev)) {
+		ret = PCH_IBX;
+		DRM_DEBUG_KMS("Assuming Ibex Peak PCH\n");
+	} else if (IS_GEN6(dev) || IS_IVYBRIDGE(dev)) {
+		ret = PCH_CPT;
+		DRM_DEBUG_KMS("Assuming CouarPoint PCH\n");
+	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+		ret = PCH_LPT;
+		DRM_DEBUG_KMS("Assuming LynxPoint PCH\n");
+	} else if (IS_SKYLAKE(dev)) {
+		ret = PCH_SPT;
+		DRM_DEBUG_KMS("Assuming SunrisePoint PCH\n");
+	}
+
+	return ret;
+}
+
 void intel_detect_pch(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -503,6 +531,8 @@ void intel_detect_pch(struct drm_device *dev)
 				dev_priv->pch_type = PCH_SPT;
 				DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
 				WARN_ON(!IS_SKYLAKE(dev));
+			} else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE) {
+				dev_priv->pch_type = intel_virt_detect_pch(dev);
 			} else
 				continue;
 
@@ -608,6 +638,8 @@ static int i915_drm_suspend(struct drm_device *dev)
 		return error;
 	}
 
+	intel_guc_suspend(dev);
+
 	intel_suspend_gt_powersave(dev);
 
 	/*
@@ -737,6 +769,8 @@ static int i915_drm_resume(struct drm_device *dev)
 	}
 	mutex_unlock(&dev->struct_mutex);
 
+	intel_guc_resume(dev);
+
 	intel_modeset_init_hw(dev);
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -1021,12 +1055,6 @@ static int skl_suspend_complete(struct drm_i915_private *dev_priv)
 {
 	/* Enabling DC6 is not a hard requirement to enter runtime D3 */
 
-	/*
-	 * This is to ensure that CSR isn't identified as loaded before
-	 * CSR-loading program is called during runtime-resume.
-	 */
-	intel_csr_load_status_set(dev_priv, FW_UNINITIALIZED);
-
 	skl_uninit_cdclk(dev_priv);
 
 	return 0;
@@ -1476,6 +1504,8 @@ static int intel_runtime_suspend(struct device *device)
 	i915_gem_release_all_mmaps(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
+	intel_guc_suspend(dev);
+
 	intel_suspend_gt_powersave(dev);
 	intel_runtime_pm_disable_interrupts(dev_priv);
 
@@ -1535,6 +1565,8 @@ static int intel_runtime_resume(struct device *device)
 	intel_opregion_notify_adapter(dev, PCI_D0);
 	dev_priv->pm.suspended = false;
 
+	intel_guc_resume(dev);
+
 	if (IS_GEN6(dev_priv))
 		intel_init_pch_refclk(dev);
 

drivers/gpu/drm/i915/i915_drv.h

@@ -57,7 +57,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20150928"
+#define DRIVER_DATE		"20151010"
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -131,17 +131,17 @@ enum transcoder {
 #define transcoder_name(t) ((t) + 'A')
 
 /*
- * This is the maximum (across all platforms) number of planes (primary +
- * sprites) that can be active at the same time on one pipe.
- *
- * This value doesn't count the cursor plane.
+ * I915_MAX_PLANES in the enum below is the maximum (across all platforms)
+ * number of planes per CRTC.  Not all platforms really have this many planes,
+ * which means some arrays of size I915_MAX_PLANES may have unused entries
+ * between the topmost sprite plane and the cursor plane.
  */
-#define I915_MAX_PLANES	4
-
 enum plane {
 	PLANE_A = 0,
 	PLANE_B,
 	PLANE_C,
+	PLANE_CURSOR,
+	I915_MAX_PLANES,
 };
 #define plane_name(p) ((p) + 'A')
 
@@ -628,10 +628,6 @@ struct drm_i915_display_funcs {
 			  struct dpll *match_clock,
 			  struct dpll *best_clock);
 	void (*update_wm)(struct drm_crtc *crtc);
-	void (*update_sprite_wm)(struct drm_plane *plane,
-				 struct drm_crtc *crtc,
-				 uint32_t sprite_width, uint32_t sprite_height,
-				 int pixel_size, bool enable, bool scaled);
 	int (*modeset_calc_cdclk)(struct drm_atomic_state *state);
 	void (*modeset_commit_cdclk)(struct drm_atomic_state *state);
 	/* Returns the active state of the crtc, and if the crtc is active,
@@ -646,7 +642,7 @@ struct drm_i915_display_funcs {
 	void (*crtc_disable)(struct drm_crtc *crtc);
 	void (*audio_codec_enable)(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
-				   struct drm_display_mode *mode);
+				   const struct drm_display_mode *adjusted_mode);
 	void (*audio_codec_disable)(struct intel_encoder *encoder);
 	void (*fdi_link_train)(struct drm_crtc *crtc);
 	void (*init_clock_gating)(struct drm_device *dev);
@@ -664,15 +660,6 @@ struct drm_i915_display_funcs {
 	/* render clock increase/decrease */
 	/* display clock increase/decrease */
 	/* pll clock increase/decrease */
-
-	int (*setup_backlight)(struct intel_connector *connector, enum pipe pipe);
-	uint32_t (*get_backlight)(struct intel_connector *connector);
-	void (*set_backlight)(struct intel_connector *connector,
-			      uint32_t level);
-	void (*disable_backlight)(struct intel_connector *connector);
-	void (*enable_backlight)(struct intel_connector *connector);
-	uint32_t (*backlight_hz_to_pwm)(struct intel_connector *connector,
-					uint32_t hz);
 };
 
 enum forcewake_domain_id {
@@ -1146,7 +1133,6 @@ struct intel_gen6_power_mgmt {
 	u8 efficient_freq;	/* AKA RPe. Pre-determined balanced frequency */
 	u8 rp1_freq;		/* "less than" RP0 power/freqency */
 	u8 rp0_freq;		/* Non-overclocked max frequency. */
-	u32 cz_freq;
 
 	u8 up_threshold; /* Current %busy required to uplock */
 	u8 down_threshold; /* Current %busy required to downclock */
@@ -1588,8 +1574,7 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1,
 struct skl_ddb_allocation {
 	struct skl_ddb_entry pipe[I915_MAX_PIPES];
 	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* packed/uv */
-	struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* y-plane */
-	struct skl_ddb_entry cursor[I915_MAX_PIPES];
+	struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES];
 };
 
 struct skl_wm_values {
@@ -1597,18 +1582,13 @@ struct skl_wm_values {
 	struct skl_ddb_allocation ddb;
 	uint32_t wm_linetime[I915_MAX_PIPES];
 	uint32_t plane[I915_MAX_PIPES][I915_MAX_PLANES][8];
-	uint32_t cursor[I915_MAX_PIPES][8];
 	uint32_t plane_trans[I915_MAX_PIPES][I915_MAX_PLANES];
-	uint32_t cursor_trans[I915_MAX_PIPES];
 };
 
 struct skl_wm_level {
 	bool plane_en[I915_MAX_PLANES];
-	bool cursor_en;
 	uint16_t plane_res_b[I915_MAX_PLANES];
 	uint8_t plane_res_l[I915_MAX_PLANES];
-	uint16_t cursor_res_b;
-	uint8_t cursor_res_l;
 };
 
 /*
@@ -1809,6 +1789,7 @@ struct drm_i915_private {
 	unsigned int cdclk_freq, max_cdclk_freq;
 	unsigned int max_dotclk_freq;
 	unsigned int hpll_freq;
+	unsigned int czclk_freq;
 
 	/**
 	 * wq - Driver workqueue for GEM.
@@ -1897,6 +1878,11 @@ struct drm_i915_private {
 	/* hda/i915 audio component */
 	struct i915_audio_component *audio_component;
 	bool audio_component_registered;
+	/**
+	 * av_mutex - mutex for audio/video sync
+	 *
+	 */
+	struct mutex av_mutex;
 
 	uint32_t hw_context_size;
 	struct list_head context_list;
@@ -1959,6 +1945,9 @@ struct drm_i915_private {
 
 	bool edp_low_vswing;
 
+	/* perform PHY state sanity checks? */
+	bool chv_phy_assert[2];
+
 	/*
 	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
 	 * will be rejected. Instead look for a better place.
@@ -2607,6 +2596,7 @@ struct drm_i915_cmd_table {
 #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE		0x9c00
 #define INTEL_PCH_SPT_DEVICE_ID_TYPE		0xA100
 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE		0x9D00
+#define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
 
 #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type)
 #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT)
@@ -2824,6 +2814,8 @@ void i915_gem_vma_destroy(struct i915_vma *vma);
 #define PIN_OFFSET_BIAS	(1<<3)
 #define PIN_USER	(1<<4)
 #define PIN_UPDATE	(1<<5)
+#define PIN_ZONE_4G	(1<<6)
+#define PIN_HIGH	(1<<7)
 #define PIN_OFFSET_MASK (~4095)
 int __must_check
 i915_gem_object_pin(struct drm_i915_gem_object *obj,
@@ -2839,6 +2831,11 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 		  u32 flags);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
+/*
+ * BEWARE: Do not use the function below unless you can _absolutely_
+ * _guarantee_ VMA in question is _not in use_ anywhere.
+ */
+int __must_check __i915_vma_unbind_no_wait(struct i915_vma *vma);
 int i915_gem_object_put_pages(struct drm_i915_gem_object *obj);
 void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv);
 void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
@@ -3167,7 +3164,6 @@ int __must_check i915_gem_evict_something(struct drm_device *dev,
 					  unsigned long end,
 					  unsigned flags);
 int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
-int i915_gem_evict_everything(struct drm_device *dev);
 
 /* belongs in i915_gem_gtt.h */
 static inline void i915_gem_chipset_flush(struct drm_device *dev)
@@ -3198,11 +3194,12 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 
 /* i915_gem_shrinker.c */
 unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
-			      long target,
+			      unsigned long target,
 			      unsigned flags);
 #define I915_SHRINK_PURGEABLE 0x1
 #define I915_SHRINK_UNBOUND 0x2
 #define I915_SHRINK_BOUND 0x4
+#define I915_SHRINK_ACTIVE 0x8
 unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 void i915_gem_shrinker_init(struct drm_i915_private *dev_priv);
 

drivers/gpu/drm/i915/i915_gem.c

@@ -3208,7 +3208,7 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj)
 					    old_write_domain);
 }
 
-int i915_vma_unbind(struct i915_vma *vma)
+static int __i915_vma_unbind(struct i915_vma *vma, bool wait)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
@@ -3227,9 +3227,11 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	BUG_ON(obj->pages == NULL);
 
+	if (wait) {
 		ret = i915_gem_object_wait_rendering(obj, false);
 		if (ret)
 			return ret;
+	}
 
 	if (i915_is_ggtt(vma->vm) &&
 	    vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) {
@@ -3274,6 +3276,16 @@ int i915_vma_unbind(struct i915_vma *vma)
 	return 0;
 }
 
+int i915_vma_unbind(struct i915_vma *vma)
+{
+	return __i915_vma_unbind(vma, true);
+}
+
+int __i915_vma_unbind_no_wait(struct i915_vma *vma)
+{
+	return __i915_vma_unbind(vma, false);
+}
+
 int i915_gpu_idle(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3354,11 +3366,9 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 fence_alignment, unfenced_alignment;
+	u32 search_flag, alloc_flag;
+	u64 start, end;
 	u64 size, fence_size;
-	u64 start =
-		flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
-	u64 end =
-		flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total;
 	struct i915_vma *vma;
 	int ret;
 
@@ -3398,6 +3408,13 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 		size = flags & PIN_MAPPABLE ? fence_size : obj->base.size;
 	}
 
+	start = flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
+	end = vm->total;
+	if (flags & PIN_MAPPABLE)
+		end = min_t(u64, end, dev_priv->gtt.mappable_end);
+	if (flags & PIN_ZONE_4G)
+		end = min_t(u64, end, (1ULL << 32));
+
 	if (alignment == 0)
 		alignment = flags & PIN_MAPPABLE ? fence_alignment :
 						unfenced_alignment;
@@ -3433,13 +3450,21 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		goto err_unpin;
 
+	if (flags & PIN_HIGH) {
+		search_flag = DRM_MM_SEARCH_BELOW;
+		alloc_flag = DRM_MM_CREATE_TOP;
+	} else {
+		search_flag = DRM_MM_SEARCH_DEFAULT;
+		alloc_flag = DRM_MM_CREATE_DEFAULT;
+	}
+
 search_free:
 	ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
 						  size, alignment,
 						  obj->cache_level,
 						  start, end,
-						  DRM_MM_SEARCH_DEFAULT,
-						  DRM_MM_CREATE_DEFAULT);
+						  search_flag,
+						  alloc_flag);
 	if (ret) {
 		ret = i915_gem_evict_something(dev, vm, size, alignment,
 					       obj->cache_level,
@@ -4533,22 +4558,6 @@ void i915_gem_init_swizzling(struct drm_device *dev)
 		BUG();
 }
 
-static bool
-intel_enable_blt(struct drm_device *dev)
-{
-	if (!HAS_BLT(dev))
-		return false;
-
-	/* The blitter was dysfunctional on early prototypes */
-	if (IS_GEN6(dev) && dev->pdev->revision < 8) {
-		DRM_INFO("BLT not supported on this pre-production hardware;"
-			 " graphics performance will be degraded.\n");
-		return false;
-	}
-
-	return true;
-}
-
 static void init_unused_ring(struct drm_device *dev, u32 base)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4591,7 +4600,7 @@ int i915_gem_init_rings(struct drm_device *dev)
 			goto cleanup_render_ring;
 	}
 
-	if (intel_enable_blt(dev)) {
+	if (HAS_BLT(dev)) {
 		ret = intel_init_blt_ring_buffer(dev);
 		if (ret)
 			goto cleanup_bsd_ring;

drivers/gpu/drm/i915/i915_gem_context.c

@@ -133,6 +133,23 @@ static int get_context_size(struct drm_device *dev)
 	return ret;
 }
 
+static void i915_gem_context_clean(struct intel_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
+	struct i915_vma *vma, *next;
+
+	if (!ppgtt)
+		return;
+
+	WARN_ON(!list_empty(&ppgtt->base.active_list));
+
+	list_for_each_entry_safe(vma, next, &ppgtt->base.inactive_list,
+				 mm_list) {
+		if (WARN_ON(__i915_vma_unbind_no_wait(vma)))
+			break;
+	}
+}
+
 void i915_gem_context_free(struct kref *ctx_ref)
 {
 	struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
@@ -142,6 +159,13 @@ void i915_gem_context_free(struct kref *ctx_ref)
 	if (i915.enable_execlists)
 		intel_lr_context_free(ctx);
 
+	/*
+	 * This context is going away and we need to remove all VMAs still
+	 * around. This is to handle imported shared objects for which
+	 * destructor did not run when their handles were closed.
+	 */
+	i915_gem_context_clean(ctx);
+
 	i915_ppgtt_put(ctx->ppgtt);
 
 	if (ctx->legacy_hw_ctx.rcs_state)

drivers/gpu/drm/i915/i915_gem_evict.c

@@ -237,48 +237,3 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle)
 
 	return 0;
 }
-
-/**
- * i915_gem_evict_everything - Try to evict all objects
- * @dev: Device to evict objects for
- *
- * This functions tries to evict all gem objects from all address spaces. Used
- * by the shrinker as a last-ditch effort and for suspend, before releasing the
- * backing storage of all unbound objects.
- */
-int
-i915_gem_evict_everything(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_address_space *vm, *v;
-	bool lists_empty = true;
-	int ret;
-
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
-		lists_empty = (list_empty(&vm->inactive_list) &&
-			       list_empty(&vm->active_list));
-		if (!lists_empty)
-			lists_empty = false;
-	}
-
-	if (lists_empty)
-		return -ENOSPC;
-
-	trace_i915_gem_evict_everything(dev);
-
-	/* The gpu_idle will flush everything in the write domain to the
-	 * active list. Then we must move everything off the active list
-	 * with retire requests.
-	 */
-	ret = i915_gpu_idle(dev);
-	if (ret)
-		return ret;
-
-	i915_gem_retire_requests(dev);
-
-	/* Having flushed everything, unbind() should never raise an error */
-	list_for_each_entry_safe(vm, v, &dev_priv->vm_list, global_link)
-		WARN_ON(i915_gem_evict_vm(vm, false));
-
-	return 0;
-}

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -590,10 +590,17 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
 		flags |= PIN_GLOBAL;
 
 	if (!drm_mm_node_allocated(&vma->node)) {
+		/* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
+		 * limit address to the first 4GBs for unflagged objects.
+		 */
+		if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0)
+			flags |= PIN_ZONE_4G;
 		if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
 			flags |= PIN_GLOBAL | PIN_MAPPABLE;
 		if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
 			flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
+		if ((flags & PIN_MAPPABLE) == 0)
+			flags |= PIN_HIGH;
 	}
 
 	ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags);
@@ -671,6 +678,10 @@ eb_vma_misplaced(struct i915_vma *vma)
 	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
 		return !only_mappable_for_reloc(entry->flags);
 
+	if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0 &&
+	    (vma->node.start + vma->node.size - 1) >> 32)
+		return true;
+
 	return false;
 }
 
@@ -934,7 +945,21 @@ i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 	if (exec->flags & __I915_EXEC_UNKNOWN_FLAGS)
 		return false;
 
-	return ((exec->batch_start_offset | exec->batch_len) & 0x7) == 0;
+	/* Kernel clipping was a DRI1 misfeature */
+	if (exec->num_cliprects || exec->cliprects_ptr)
+		return false;
+
+	if (exec->DR4 == 0xffffffff) {
+		DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
+		exec->DR4 = 0;
+	}
+	if (exec->DR1 || exec->DR4)
+		return false;
+
+	if ((exec->batch_start_offset | exec->batch_len) & 0x7)
+		return false;
+
+	return true;
 }
 
 static int
@@ -1098,47 +1123,6 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 	return 0;
 }
 
-static int
-i915_emit_box(struct drm_i915_gem_request *req,
-	      struct drm_clip_rect *box,
-	      int DR1, int DR4)
-{
-	struct intel_engine_cs *ring = req->ring;
-	int ret;
-
-	if (box->y2 <= box->y1 || box->x2 <= box->x1 ||
-	    box->y2 <= 0 || box->x2 <= 0) {
-		DRM_ERROR("Bad box %d,%d..%d,%d\n",
-			  box->x1, box->y1, box->x2, box->y2);
-		return -EINVAL;
-	}
-
-	if (INTEL_INFO(ring->dev)->gen >= 4) {
-		ret = intel_ring_begin(req, 4);
-		if (ret)
-			return ret;
-
-		intel_ring_emit(ring, GFX_OP_DRAWRECT_INFO_I965);
-		intel_ring_emit(ring, (box->x1 & 0xffff) | box->y1 << 16);
-		intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
-		intel_ring_emit(ring, DR4);
-	} else {
-		ret = intel_ring_begin(req, 6);
-		if (ret)
-			return ret;
-
-		intel_ring_emit(ring, GFX_OP_DRAWRECT_INFO);
-		intel_ring_emit(ring, DR1);
-		intel_ring_emit(ring, (box->x1 & 0xffff) | box->y1 << 16);
-		intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
-		intel_ring_emit(ring, DR4);
-		intel_ring_emit(ring, 0);
-	}
-	intel_ring_advance(ring);
-
-	return 0;
-}
-
 static struct drm_i915_gem_object*
 i915_gem_execbuffer_parse(struct intel_engine_cs *ring,
 			  struct drm_i915_gem_exec_object2 *shadow_exec_entry,
@@ -1197,65 +1181,21 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 			       struct drm_i915_gem_execbuffer2 *args,
 			       struct list_head *vmas)
 {
-	struct drm_clip_rect *cliprects = NULL;
 	struct drm_device *dev = params->dev;
 	struct intel_engine_cs *ring = params->ring;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u64 exec_start, exec_len;
 	int instp_mode;
 	u32 instp_mask;
-	int i, ret = 0;
-
-	if (args->num_cliprects != 0) {
-		if (ring != &dev_priv->ring[RCS]) {
-			DRM_DEBUG("clip rectangles are only valid with the render ring\n");
-			return -EINVAL;
-		}
-
-		if (INTEL_INFO(dev)->gen >= 5) {
-			DRM_DEBUG("clip rectangles are only valid on pre-gen5\n");
-			return -EINVAL;
-		}
-
-		if (args->num_cliprects > UINT_MAX / sizeof(*cliprects)) {
-			DRM_DEBUG("execbuf with %u cliprects\n",
-				  args->num_cliprects);
-			return -EINVAL;
-		}
-
-		cliprects = kcalloc(args->num_cliprects,
-				    sizeof(*cliprects),
-				    GFP_KERNEL);
-		if (cliprects == NULL) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (copy_from_user(cliprects,
-				   to_user_ptr(args->cliprects_ptr),
-				   sizeof(*cliprects)*args->num_cliprects)) {
-			ret = -EFAULT;
-			goto error;
-		}
-	} else {
-		if (args->DR4 == 0xffffffff) {
-			DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
-			args->DR4 = 0;
-		}
-
-		if (args->DR1 || args->DR4 || args->cliprects_ptr) {
-			DRM_DEBUG("0 cliprects but dirt in cliprects fields\n");
-			return -EINVAL;
-		}
-	}
+	int ret;
 
 	ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
 	if (ret)
-		goto error;
+		return ret;
 
 	ret = i915_switch_context(params->request);
 	if (ret)
-		goto error;
+		return ret;
 
 	WARN(params->ctx->ppgtt && params->ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
 	     "%s didn't clear reload\n", ring->name);
@@ -1268,22 +1208,19 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 	case I915_EXEC_CONSTANTS_REL_SURFACE:
 		if (instp_mode != 0 && ring != &dev_priv->ring[RCS]) {
 			DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
-			ret = -EINVAL;
-			goto error;
+			return -EINVAL;
 		}
 
 		if (instp_mode != dev_priv->relative_constants_mode) {
 			if (INTEL_INFO(dev)->gen < 4) {
 				DRM_DEBUG("no rel constants on pre-gen4\n");
-				ret = -EINVAL;
-				goto error;
+				return -EINVAL;
 			}
 
 			if (INTEL_INFO(dev)->gen > 5 &&
 			    instp_mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
 				DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
-				ret = -EINVAL;
-				goto error;
+				return -EINVAL;
 			}
 
 			/* The HW changed the meaning on this bit on gen6 */
@@ -1293,15 +1230,14 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 		break;
 	default:
 		DRM_DEBUG("execbuf with unknown constants: %d\n", instp_mode);
-		ret = -EINVAL;
-		goto error;
+		return -EINVAL;
 	}
 
 	if (ring == &dev_priv->ring[RCS] &&
 	    instp_mode != dev_priv->relative_constants_mode) {
 		ret = intel_ring_begin(params->request, 4);
 		if (ret)
-			goto error;
+			return ret;
 
 		intel_ring_emit(ring, MI_NOOP);
 		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
@@ -1315,42 +1251,25 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 	if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
 		ret = i915_reset_gen7_sol_offsets(dev, params->request);
 		if (ret)
-			goto error;
+			return ret;
 	}
 
 	exec_len   = args->batch_len;
 	exec_start = params->batch_obj_vm_offset +
 		     params->args_batch_start_offset;
 
-	if (cliprects) {
-		for (i = 0; i < args->num_cliprects; i++) {
-			ret = i915_emit_box(params->request, &cliprects[i],
-					    args->DR1, args->DR4);
-			if (ret)
-				goto error;
-
-			ret = ring->dispatch_execbuffer(params->request,
-							exec_start, exec_len,
-							params->dispatch_flags);
-			if (ret)
-				goto error;
-		}
-	} else {
 	ret = ring->dispatch_execbuffer(params->request,
 					exec_start, exec_len,
 					params->dispatch_flags);
 	if (ret)
 		return ret;
-	}
 
 	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
 
 	i915_gem_execbuffer_move_to_active(vmas, params->request);
 	i915_gem_execbuffer_retire_commands(params);
 
-error:
-	kfree(cliprects);
-	return ret;
+	return 0;
 }
 
 /**

drivers/gpu/drm/i915/i915_gem_fence.c

@@ -59,19 +59,19 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 				 struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int fence_reg;
+	int fence_reg_lo, fence_reg_hi;
 	int fence_pitch_shift;
 
 	if (INTEL_INFO(dev)->gen >= 6) {
-		fence_reg = FENCE_REG_SANDYBRIDGE_0;
-		fence_pitch_shift = SANDYBRIDGE_FENCE_PITCH_SHIFT;
+		fence_reg_lo = FENCE_REG_GEN6_LO(reg);
+		fence_reg_hi = FENCE_REG_GEN6_HI(reg);
+		fence_pitch_shift = GEN6_FENCE_PITCH_SHIFT;
 	} else {
-		fence_reg = FENCE_REG_965_0;
+		fence_reg_lo = FENCE_REG_965_LO(reg);
+		fence_reg_hi = FENCE_REG_965_HI(reg);
 		fence_pitch_shift = I965_FENCE_PITCH_SHIFT;
 	}
 
-	fence_reg += reg * 8;
-
 	/* To w/a incoherency with non-atomic 64-bit register updates,
 	 * we split the 64-bit update into two 32-bit writes. In order
 	 * for a partial fence not to be evaluated between writes, we
@@ -81,8 +81,8 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	 * For extra levels of paranoia, we make sure each step lands
 	 * before applying the next step.
 	 */
-	I915_WRITE(fence_reg, 0);
-	POSTING_READ(fence_reg);
+	I915_WRITE(fence_reg_lo, 0);
+	POSTING_READ(fence_reg_lo);
 
 	if (obj) {
 		u32 size = i915_gem_obj_ggtt_size(obj);
@@ -103,14 +103,14 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
 		val |= I965_FENCE_REG_VALID;
 
-		I915_WRITE(fence_reg + 4, val >> 32);
-		POSTING_READ(fence_reg + 4);
+		I915_WRITE(fence_reg_hi, val >> 32);
+		POSTING_READ(fence_reg_hi);
 
-		I915_WRITE(fence_reg + 0, val);
-		POSTING_READ(fence_reg);
+		I915_WRITE(fence_reg_lo, val);
+		POSTING_READ(fence_reg_lo);
 	} else {
-		I915_WRITE(fence_reg + 4, 0);
-		POSTING_READ(fence_reg + 4);
+		I915_WRITE(fence_reg_hi, 0);
+		POSTING_READ(fence_reg_hi);
 	}
 }
 
@@ -149,13 +149,8 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 	} else
 		val = 0;
 
-	if (reg < 8)
-		reg = FENCE_REG_830_0 + reg * 4;
-	else
-		reg = FENCE_REG_945_8 + (reg - 8) * 4;
-
-	I915_WRITE(reg, val);
-	POSTING_READ(reg);
+	I915_WRITE(FENCE_REG(reg), val);
+	POSTING_READ(FENCE_REG(reg));
 }
 
 static void i830_write_fence_reg(struct drm_device *dev, int reg,
@@ -186,8 +181,8 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg,
 	} else
 		val = 0;
 
-	I915_WRITE(FENCE_REG_830_0 + reg * 4, val);
-	POSTING_READ(FENCE_REG_830_0 + reg * 4);
+	I915_WRITE(FENCE_REG(reg), val);
+	POSTING_READ(FENCE_REG(reg));
 }
 
 inline static bool i915_gem_object_needs_mb(struct drm_i915_gem_object *obj)

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -2889,8 +2889,8 @@ static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
 
 	/* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
 	 * write would work. */
-	I915_WRITE(GEN8_PRIVATE_PAT, pat);
-	I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32);
+	I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
+	I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
 }
 
 static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
@@ -2924,8 +2924,8 @@ static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
 	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
 	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
 
-	I915_WRITE(GEN8_PRIVATE_PAT, pat);
-	I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32);
+	I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
+	I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
 }
 
 static int gen8_gmch_probe(struct drm_device *dev,

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -394,7 +394,8 @@ struct i915_hw_ppgtt {
  */
 #define gen6_for_each_pde(pt, pd, start, length, temp, iter) \
 	for (iter = gen6_pde_index(start); \
-	     pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES; \
+	     length > 0 && iter < I915_PDES ? \
+			(pt = (pd)->page_table[iter]), 1 : 0; \
 	     iter++, \
 	     temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT) - start, \
 	     temp = min_t(unsigned, temp, length), \
@@ -459,7 +460,8 @@ static inline uint32_t gen6_pde_index(uint32_t addr)
  */
 #define gen8_for_each_pde(pt, pd, start, length, temp, iter)		\
 	for (iter = gen8_pde_index(start); \
-	     pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES;	\
+	     length > 0 && iter < I915_PDES ? \
+			(pt = (pd)->page_table[iter]), 1 : 0; \
 	     iter++,				\
 	     temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT) - start,	\
 	     temp = min(temp, length),					\
@@ -467,8 +469,8 @@ static inline uint32_t gen6_pde_index(uint32_t addr)
 
 #define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter)	\
 	for (iter = gen8_pdpe_index(start); \
-	     pd = (pdp)->page_directory[iter], \
-	     length > 0 && (iter < I915_PDPES_PER_PDP(dev)); \
+	     length > 0 && (iter < I915_PDPES_PER_PDP(dev)) ? \
+			(pd = (pdp)->page_directory[iter]), 1 : 0; \
 	     iter++,				\
 	     temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start,	\
 	     temp = min(temp, length),					\
@@ -476,8 +478,8 @@ static inline uint32_t gen6_pde_index(uint32_t addr)
 
 #define gen8_for_each_pml4e(pdp, pml4, start, length, temp, iter)	\
 	for (iter = gen8_pml4e_index(start);	\
-	     pdp = (pml4)->pdps[iter], \
-	     length > 0 && iter < GEN8_PML4ES_PER_PML4; \
+	     length > 0 && iter < GEN8_PML4ES_PER_PML4 ? \
+			(pdp = (pml4)->pdps[iter]), 1 : 0; \
 	     iter++,				\
 	     temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT) - start,	\
 	     temp = min(temp, length),					\

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -73,7 +73,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
  */
 unsigned long
 i915_gem_shrink(struct drm_i915_private *dev_priv,
-		long target, unsigned flags)
+		unsigned long target, unsigned flags)
 {
 	const struct {
 		struct list_head *list;
@@ -85,6 +85,9 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 	}, *phase;
 	unsigned long count = 0;
 
+	trace_i915_gem_shrink(dev_priv, target, flags);
+	i915_gem_retire_requests(dev_priv->dev);
+
 	/*
 	 * As we may completely rewrite the (un)bound list whilst unbinding
 	 * (due to retiring requests) we have to strictly process only
@@ -123,6 +126,9 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 			    obj->madv != I915_MADV_DONTNEED)
 				continue;
 
+			if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active)
+				continue;
+
 			drm_gem_object_reference(&obj->base);
 
 			/* For the unbound phase, this should be a no-op! */
@@ -139,11 +145,13 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		list_splice(&still_in_list, phase->list);
 	}
 
+	i915_gem_retire_requests(dev_priv->dev);
+
 	return count;
 }
 
 /**
- * i915_gem_shrink - Shrink buffer object caches completely
+ * i915_gem_shrink_all - Shrink buffer object caches completely
  * @dev_priv: i915 device
  *
  * This is a simple wraper around i915_gem_shrink() to aggressively shrink all
@@ -158,9 +166,10 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
  */
 unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 {
-	i915_gem_evict_everything(dev_priv->dev);
-	return i915_gem_shrink(dev_priv, LONG_MAX,
-			       I915_SHRINK_BOUND | I915_SHRINK_UNBOUND);
+	return i915_gem_shrink(dev_priv, -1UL,
+			       I915_SHRINK_BOUND |
+			       I915_SHRINK_UNBOUND |
+			       I915_SHRINK_ACTIVE);
 }
 
 static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
@@ -213,7 +222,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 			count += obj->base.size >> PAGE_SHIFT;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (obj->pages_pin_count == num_vma_bound(obj))
+		if (!obj->active && obj->pages_pin_count == num_vma_bound(obj))
 			count += obj->base.size >> PAGE_SHIFT;
 	}
 

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -30,6 +30,9 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
+#define KB(x) ((x) * 1024)
+#define MB(x) (KB(x) * 1024)
+
 /*
  * The BIOS typically reserves some of the system's memory for the exclusive
  * use of the integrated graphics. This memory is no longer available for
@@ -51,6 +54,11 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return -ENODEV;
 
+	/* See the comment at the drm_mm_init() call for more about this check.
+	 * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */
+	if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096)
+		start = 4096;
+
 	mutex_lock(&dev_priv->mm.stolen_lock);
 	ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node, size,
 					  alignment, start, end,
@@ -86,24 +94,91 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 	/* Almost universally we can find the Graphics Base of Stolen Memory
 	 * at offset 0x5c in the igfx configuration space. On a few (desktop)
 	 * machines this is also mirrored in the bridge device at different
-	 * locations, or in the MCHBAR. On gen2, the layout is again slightly
-	 * different with the Graphics Segment immediately following Top of
-	 * Memory (or Top of Usable DRAM). Note it appears that TOUD is only
-	 * reported by 865g, so we just use the top of memory as determined
-	 * by the e820 probe.
+	 * locations, or in the MCHBAR.
+	 *
+	 * On 865 we just check the TOUD register.
+	 *
+	 * On 830/845/85x the stolen memory base isn't available in any
+	 * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size.
 	 *
-	 * XXX However gen2 requires an unavailable symbol.
 	 */
 	base = 0;
 	if (INTEL_INFO(dev)->gen >= 3) {
 		/* Read Graphics Base of Stolen Memory directly */
 		pci_read_config_dword(dev->pdev, 0x5c, &base);
 		base &= ~((1<<20) - 1);
-	} else { /* GEN2 */
-#if 0
-		/* Stolen is immediately above Top of Memory */
-		base = max_low_pfn_mapped << PAGE_SHIFT;
-#endif
+	} else if (IS_I865G(dev)) {
+		u16 toud = 0;
+
+		/*
+		 * FIXME is the graphics stolen memory region
+		 * always at TOUD? Ie. is it always the last
+		 * one to be allocated by the BIOS?
+		 */
+		pci_bus_read_config_word(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I865_TOUD, &toud);
+
+		base = toud << 16;
+	} else if (IS_I85X(dev)) {
+		u32 tseg_size = 0;
+		u32 tom;
+		u8 tmp;
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I85X_ESMRAMC, &tmp);
+
+		if (tmp & TSEG_ENABLE)
+			tseg_size = MB(1);
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 1),
+					 I85X_DRB3, &tmp);
+		tom = tmp * MB(32);
+
+		base = tom - tseg_size - dev_priv->gtt.stolen_size;
+	} else if (IS_845G(dev)) {
+		u32 tseg_size = 0;
+		u32 tom;
+		u8 tmp;
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I845_ESMRAMC, &tmp);
+
+		if (tmp & TSEG_ENABLE) {
+			switch (tmp & I845_TSEG_SIZE_MASK) {
+			case I845_TSEG_SIZE_512K:
+				tseg_size = KB(512);
+				break;
+			case I845_TSEG_SIZE_1M:
+				tseg_size = MB(1);
+				break;
+			}
+		}
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I830_DRB3, &tmp);
+		tom = tmp * MB(32);
+
+		base = tom - tseg_size - dev_priv->gtt.stolen_size;
+	} else if (IS_I830(dev)) {
+		u32 tseg_size = 0;
+		u32 tom;
+		u8 tmp;
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I830_ESMRAMC, &tmp);
+
+		if (tmp & TSEG_ENABLE) {
+			if (tmp & I830_TSEG_SIZE_1M)
+				tseg_size = MB(1);
+			else
+				tseg_size = KB(512);
+		}
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I830_DRB3, &tmp);
+		tom = tmp * MB(32);
+
+		base = tom - tseg_size - dev_priv->gtt.stolen_size;
 	}
 
 	if (base == 0)
@@ -393,7 +468,17 @@ int i915_gem_init_stolen(struct drm_device *dev)
 	dev_priv->gtt.stolen_usable_size = dev_priv->gtt.stolen_size -
 					   reserved_total;
 
-	/* Basic memrange allocator for stolen space */
+	/*
+	 * Basic memrange allocator for stolen space.
+	 *
+	 * TODO: Notice that some platforms require us to not use the first page
+	 * of the stolen memory but their BIOSes may still put the framebuffer
+	 * on the first page. So we don't reserve this page for now because of
+	 * that. Our current solution is to just prevent new nodes from being
+	 * inserted on the first page - see the check we have at
+	 * i915_gem_stolen_insert_node_in_range(). We may want to fix the fbcon
+	 * problem later.
+	 */
 	drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_usable_size);
 
 	return 0;

drivers/gpu/drm/i915/i915_gem_userptr.c

@@ -50,7 +50,6 @@ struct i915_mmu_notifier {
 	struct mmu_notifier mn;
 	struct rb_root objects;
 	struct list_head linear;
-	unsigned long serial;
 	bool has_linear;
 };
 
@@ -59,13 +58,16 @@ struct i915_mmu_object {
 	struct interval_tree_node it;
 	struct list_head link;
 	struct drm_i915_gem_object *obj;
+	struct work_struct work;
+	bool active;
 	bool is_linear;
 };
 
-static unsigned long cancel_userptr(struct drm_i915_gem_object *obj)
+static void __cancel_userptr__worker(struct work_struct *work)
 {
+	struct i915_mmu_object *mo = container_of(work, typeof(*mo), work);
+	struct drm_i915_gem_object *obj = mo->obj;
 	struct drm_device *dev = obj->base.dev;
-	unsigned long end;
 
 	mutex_lock(&dev->struct_mutex);
 	/* Cancel any active worker and force us to re-evaluate gup */
@@ -88,45 +90,28 @@ static unsigned long cancel_userptr(struct drm_i915_gem_object *obj)
 		dev_priv->mm.interruptible = was_interruptible;
 	}
 
-	end = obj->userptr.ptr + obj->base.size;
-
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
-
-	return end;
 }
 
-static void *invalidate_range__linear(struct i915_mmu_notifier *mn,
-				      struct mm_struct *mm,
-				      unsigned long start,
-				      unsigned long end)
+static unsigned long cancel_userptr(struct i915_mmu_object *mo)
 {
-	struct i915_mmu_object *mo;
-	unsigned long serial;
-
-restart:
-	serial = mn->serial;
-	list_for_each_entry(mo, &mn->linear, link) {
-		struct drm_i915_gem_object *obj;
+	unsigned long end = mo->obj->userptr.ptr + mo->obj->base.size;
 
-		if (mo->it.last < start || mo->it.start > end)
-			continue;
-
-		obj = mo->obj;
-
-		if (!kref_get_unless_zero(&obj->base.refcount))
-			continue;
-
-		spin_unlock(&mn->lock);
-
-		cancel_userptr(obj);
-
-		spin_lock(&mn->lock);
-		if (serial != mn->serial)
-			goto restart;
+	/* The mmu_object is released late when destroying the
+	 * GEM object so it is entirely possible to gain a
+	 * reference on an object in the process of being freed
+	 * since our serialisation is via the spinlock and not
+	 * the struct_mutex - and consequently use it after it
+	 * is freed and then double free it.
+	 */
+	if (mo->active && kref_get_unless_zero(&mo->obj->base.refcount)) {
+		schedule_work(&mo->work);
+		/* only schedule one work packet to avoid the refleak */
+		mo->active = false;
 	}
 
-	return NULL;
+	return end;
 }
 
 static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
@@ -134,46 +119,32 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 						       unsigned long start,
 						       unsigned long end)
 {
-	struct i915_mmu_notifier *mn = container_of(_mn, struct i915_mmu_notifier, mn);
-	struct interval_tree_node *it = NULL;
-	unsigned long next = start;
-	unsigned long serial = 0;
+	struct i915_mmu_notifier *mn =
+		container_of(_mn, struct i915_mmu_notifier, mn);
+	struct i915_mmu_object *mo;
 
-	end--; /* interval ranges are inclusive, but invalidate range is exclusive */
-	while (next < end) {
-		struct drm_i915_gem_object *obj = NULL;
+	/* interval ranges are inclusive, but invalidate range is exclusive */
+	end--;
 
 	spin_lock(&mn->lock);
-		if (mn->has_linear)
-			it = invalidate_range__linear(mn, mm, start, end);
-		else if (serial == mn->serial)
-			it = interval_tree_iter_next(it, next, end);
-		else
-			it = interval_tree_iter_first(&mn->objects, start, end);
-		if (it != NULL) {
-			obj = container_of(it, struct i915_mmu_object, it)->obj;
-
-			/* The mmu_object is released late when destroying the
-			 * GEM object so it is entirely possible to gain a
-			 * reference on an object in the process of being freed
-			 * since our serialisation is via the spinlock and not
-			 * the struct_mutex - and consequently use it after it
-			 * is freed and then double free it.
-			 */
-			if (!kref_get_unless_zero(&obj->base.refcount)) {
-				spin_unlock(&mn->lock);
-				serial = 0;
+	if (mn->has_linear) {
+		list_for_each_entry(mo, &mn->linear, link) {
+			if (mo->it.last < start || mo->it.start > end)
 				continue;
-			}
 
-			serial = mn->serial;
+			cancel_userptr(mo);
 		}
-		spin_unlock(&mn->lock);
-		if (obj == NULL)
-			return;
+	} else {
+		struct interval_tree_node *it;
 
-		next = cancel_userptr(obj);
+		it = interval_tree_iter_first(&mn->objects, start, end);
+		while (it) {
+			mo = container_of(it, struct i915_mmu_object, it);
+			start = cancel_userptr(mo);
+			it = interval_tree_iter_next(it, start, end);
 		}
+	}
+	spin_unlock(&mn->lock);
 }
 
 static const struct mmu_notifier_ops i915_gem_userptr_notifier = {
@@ -193,7 +164,6 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 	spin_lock_init(&mn->lock);
 	mn->mn.ops = &i915_gem_userptr_notifier;
 	mn->objects = RB_ROOT;
-	mn->serial = 1;
 	INIT_LIST_HEAD(&mn->linear);
 	mn->has_linear = false;
 
@@ -207,12 +177,6 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 	return mn;
 }
 
-static void __i915_mmu_notifier_update_serial(struct i915_mmu_notifier *mn)
-{
-	if (++mn->serial == 0)
-		mn->serial = 1;
-}
-
 static int
 i915_mmu_notifier_add(struct drm_device *dev,
 		      struct i915_mmu_notifier *mn,
@@ -259,10 +223,9 @@ i915_mmu_notifier_add(struct drm_device *dev,
 	} else
 		interval_tree_insert(&mo->it, &mn->objects);
 
-	if (ret == 0) {
+	if (ret == 0)
 		list_add(&mo->link, &mn->linear);
-		__i915_mmu_notifier_update_serial(mn);
-	}
+
 	spin_unlock(&mn->lock);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -290,7 +253,6 @@ i915_mmu_notifier_del(struct i915_mmu_notifier *mn,
 		mn->has_linear = i915_mmu_notifier_has_linear(mn);
 	else
 		interval_tree_remove(&mo->it, &mn->objects);
-	__i915_mmu_notifier_update_serial(mn);
 	spin_unlock(&mn->lock);
 }
 
@@ -357,6 +319,7 @@ i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj,
 	mo->it.start = obj->userptr.ptr;
 	mo->it.last = mo->it.start + obj->base.size - 1;
 	mo->obj = obj;
+	INIT_WORK(&mo->work, __cancel_userptr__worker);
 
 	ret = i915_mmu_notifier_add(obj->base.dev, mn, mo);
 	if (ret) {
@@ -565,31 +528,65 @@ __i915_gem_userptr_set_pages(struct drm_i915_gem_object *obj,
 	return ret;
 }
 
+static int
+__i915_gem_userptr_set_active(struct drm_i915_gem_object *obj,
+			      bool value)
+{
+	int ret = 0;
+
+	/* During mm_invalidate_range we need to cancel any userptr that
+	 * overlaps the range being invalidated. Doing so requires the
+	 * struct_mutex, and that risks recursion. In order to cause
+	 * recursion, the user must alias the userptr address space with
+	 * a GTT mmapping (possible with a MAP_FIXED) - then when we have
+	 * to invalidate that mmaping, mm_invalidate_range is called with
+	 * the userptr address *and* the struct_mutex held.  To prevent that
+	 * we set a flag under the i915_mmu_notifier spinlock to indicate
+	 * whether this object is valid.
+	 */
+#if defined(CONFIG_MMU_NOTIFIER)
+	if (obj->userptr.mmu_object == NULL)
+		return 0;
+
+	spin_lock(&obj->userptr.mmu_object->mn->lock);
+	/* In order to serialise get_pages with an outstanding
+	 * cancel_userptr, we must drop the struct_mutex and try again.
+	 */
+	if (!value || !work_pending(&obj->userptr.mmu_object->work))
+		obj->userptr.mmu_object->active = value;
+	else
+		ret = -EAGAIN;
+	spin_unlock(&obj->userptr.mmu_object->mn->lock);
+#endif
+
+	return ret;
+}
+
 static void
 __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 {
 	struct get_pages_work *work = container_of(_work, typeof(*work), work);
 	struct drm_i915_gem_object *obj = work->obj;
 	struct drm_device *dev = obj->base.dev;
-	const int num_pages = obj->base.size >> PAGE_SHIFT;
+	const int npages = obj->base.size >> PAGE_SHIFT;
 	struct page **pvec;
 	int pinned, ret;
 
 	ret = -ENOMEM;
 	pinned = 0;
 
-	pvec = kmalloc(num_pages*sizeof(struct page *),
+	pvec = kmalloc(npages*sizeof(struct page *),
 		       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
 	if (pvec == NULL)
-		pvec = drm_malloc_ab(num_pages, sizeof(struct page *));
+		pvec = drm_malloc_ab(npages, sizeof(struct page *));
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
 		down_read(&mm->mmap_sem);
-		while (pinned < num_pages) {
+		while (pinned < npages) {
 			ret = get_user_pages(work->task, mm,
 					     obj->userptr.ptr + pinned * PAGE_SIZE,
-					     num_pages - pinned,
+					     npages - pinned,
 					     !obj->userptr.read_only, 0,
 					     pvec + pinned, NULL);
 			if (ret < 0)
@@ -601,20 +598,22 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	}
 
 	mutex_lock(&dev->struct_mutex);
-	if (obj->userptr.work != &work->work) {
-		ret = 0;
-	} else if (pinned == num_pages) {
-		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
+	if (obj->userptr.work == &work->work) {
+		if (pinned == npages) {
+			ret = __i915_gem_userptr_set_pages(obj, pvec, npages);
 			if (ret == 0) {
-			list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list);
+				list_add_tail(&obj->global_list,
+					      &to_i915(dev)->mm.unbound_list);
 				obj->get_page.sg = obj->pages->sgl;
 				obj->get_page.last = 0;
-
 				pinned = 0;
 			}
 		}
-
 		obj->userptr.work = ERR_PTR(ret);
+		if (ret)
+			__i915_gem_userptr_set_active(obj, false);
+	}
+
 	obj->userptr.workers--;
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
@@ -627,48 +626,11 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 }
 
 static int
-i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
+__i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj,
+				      bool *active)
 {
-	const int num_pages = obj->base.size >> PAGE_SHIFT;
-	struct page **pvec;
-	int pinned, ret;
-
-	/* If userspace should engineer that these pages are replaced in
-	 * the vma between us binding this page into the GTT and completion
-	 * of rendering... Their loss. If they change the mapping of their
-	 * pages they need to create a new bo to point to the new vma.
-	 *
-	 * However, that still leaves open the possibility of the vma
-	 * being copied upon fork. Which falls under the same userspace
-	 * synchronisation issue as a regular bo, except that this time
-	 * the process may not be expecting that a particular piece of
-	 * memory is tied to the GPU.
-	 *
-	 * Fortunately, we can hook into the mmu_notifier in order to
-	 * discard the page references prior to anything nasty happening
-	 * to the vma (discard or cloning) which should prevent the more
-	 * egregious cases from causing harm.
-	 */
-
-	pvec = NULL;
-	pinned = 0;
-	if (obj->userptr.mm->mm == current->mm) {
-		pvec = kmalloc(num_pages*sizeof(struct page *),
-			       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
-		if (pvec == NULL) {
-			pvec = drm_malloc_ab(num_pages, sizeof(struct page *));
-			if (pvec == NULL)
-				return -ENOMEM;
-		}
+	struct get_pages_work *work;
 
-		pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages,
-					       !obj->userptr.read_only, pvec);
-	}
-	if (pinned < num_pages) {
-		if (pinned < 0) {
-			ret = pinned;
-			pinned = 0;
-		} else {
 	/* Spawn a worker so that we can acquire the
 	 * user pages without holding our mutex. Access
 	 * to the user pages requires mmap_sem, and we have
@@ -688,13 +650,13 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 	 * that error back to this function through
 	 * obj->userptr.work = ERR_PTR.
 	 */
-			ret = -EAGAIN;
-			if (obj->userptr.work == NULL &&
-			    obj->userptr.workers < I915_GEM_USERPTR_MAX_WORKERS) {
-				struct get_pages_work *work;
+	if (obj->userptr.workers >= I915_GEM_USERPTR_MAX_WORKERS)
+		return -EAGAIN;
 
 	work = kmalloc(sizeof(*work), GFP_KERNEL);
-				if (work != NULL) {
+	if (work == NULL)
+		return -ENOMEM;
+
 	obj->userptr.work = &work->work;
 	obj->userptr.workers++;
 
@@ -706,24 +668,78 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 
 	INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker);
 	schedule_work(&work->work);
-				} else
-					ret = -ENOMEM;
-			} else {
+
+	*active = true;
+	return -EAGAIN;
+}
+
+static int
+i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
+{
+	const int num_pages = obj->base.size >> PAGE_SHIFT;
+	struct page **pvec;
+	int pinned, ret;
+	bool active;
+
+	/* If userspace should engineer that these pages are replaced in
+	 * the vma between us binding this page into the GTT and completion
+	 * of rendering... Their loss. If they change the mapping of their
+	 * pages they need to create a new bo to point to the new vma.
+	 *
+	 * However, that still leaves open the possibility of the vma
+	 * being copied upon fork. Which falls under the same userspace
+	 * synchronisation issue as a regular bo, except that this time
+	 * the process may not be expecting that a particular piece of
+	 * memory is tied to the GPU.
+	 *
+	 * Fortunately, we can hook into the mmu_notifier in order to
+	 * discard the page references prior to anything nasty happening
+	 * to the vma (discard or cloning) which should prevent the more
+	 * egregious cases from causing harm.
+	 */
 	if (IS_ERR(obj->userptr.work)) {
+		/* active flag will have been dropped already by the worker */
 		ret = PTR_ERR(obj->userptr.work);
 		obj->userptr.work = NULL;
+		return ret;
 	}
-			}
-		}
-	} else {
-		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
-		if (ret == 0) {
-			obj->userptr.work = NULL;
+	if (obj->userptr.work)
+		/* active flag should still be held for the pending work */
+		return -EAGAIN;
+
+	/* Let the mmu-notifier know that we have begun and need cancellation */
+	ret = __i915_gem_userptr_set_active(obj, true);
+	if (ret)
+		return ret;
+
+	pvec = NULL;
 	pinned = 0;
+	if (obj->userptr.mm->mm == current->mm) {
+		pvec = kmalloc(num_pages*sizeof(struct page *),
+			       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
+		if (pvec == NULL) {
+			pvec = drm_malloc_ab(num_pages, sizeof(struct page *));
+			if (pvec == NULL) {
+				__i915_gem_userptr_set_active(obj, false);
+				return -ENOMEM;
 			}
 		}
 
+		pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages,
+					       !obj->userptr.read_only, pvec);
+	}
+
+	active = false;
+	if (pinned < 0)
+		ret = pinned, pinned = 0;
+	else if (pinned < num_pages)
+		ret = __i915_gem_userptr_get_pages_schedule(obj, &active);
+	else
+		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
+	if (ret) {
+		__i915_gem_userptr_set_active(obj, active);
 		release_pages(pvec, pinned, 0);
+	}
 	drm_free_large(pvec);
 	return ret;
 }
@@ -734,6 +750,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 	struct sg_page_iter sg_iter;
 
 	BUG_ON(obj->userptr.work != NULL);
+	__i915_gem_userptr_set_active(obj, false);
 
 	if (obj->madv != I915_MADV_WILLNEED)
 		obj->dirty = 0;

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -792,20 +792,15 @@ static void i915_gem_record_fences(struct drm_device *dev,
 	int i;
 
 	if (IS_GEN3(dev) || IS_GEN2(dev)) {
-		for (i = 0; i < 8; i++)
-			error->fence[i] = I915_READ(FENCE_REG_830_0 + (i * 4));
-		if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
-			for (i = 0; i < 8; i++)
-				error->fence[i+8] = I915_READ(FENCE_REG_945_8 +
-							      (i * 4));
-	} else if (IS_GEN5(dev) || IS_GEN4(dev))
-		for (i = 0; i < 16; i++)
-			error->fence[i] = I915_READ64(FENCE_REG_965_0 +
-						      (i * 8));
-	else if (INTEL_INFO(dev)->gen >= 6)
 		for (i = 0; i < dev_priv->num_fence_regs; i++)
-			error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 +
-						      (i * 8));
+			error->fence[i] = I915_READ(FENCE_REG(i));
+	} else if (IS_GEN5(dev) || IS_GEN4(dev)) {
+		for (i = 0; i < dev_priv->num_fence_regs; i++)
+			error->fence[i] = I915_READ64(FENCE_REG_965_LO(i));
+	} else if (INTEL_INFO(dev)->gen >= 6) {
+		for (i = 0; i < dev_priv->num_fence_regs; i++)
+			error->fence[i] = I915_READ64(FENCE_REG_GEN6_LO(i));
+	}
 }
 
 
@@ -891,7 +886,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 		ering->faddr = I915_READ(DMA_FADD_I8XX);
 		ering->ipeir = I915_READ(IPEIR);
 		ering->ipehr = I915_READ(IPEHR);
-		ering->instdone = I915_READ(INSTDONE);
+		ering->instdone = I915_READ(GEN2_INSTDONE);
 	}
 
 	ering->waiting = waitqueue_active(&ring->irq_queue);
@@ -1393,12 +1388,12 @@ void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone)
 	memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG);
 
 	if (IS_GEN2(dev) || IS_GEN3(dev))
-		instdone[0] = I915_READ(INSTDONE);
+		instdone[0] = I915_READ(GEN2_INSTDONE);
 	else if (IS_GEN4(dev) || IS_GEN5(dev) || IS_GEN6(dev)) {
-		instdone[0] = I915_READ(INSTDONE_I965);
-		instdone[1] = I915_READ(INSTDONE1);
+		instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE));
+		instdone[1] = I915_READ(GEN4_INSTDONE1);
 	} else if (INTEL_INFO(dev)->gen >= 7) {
-		instdone[0] = I915_READ(GEN7_INSTDONE_1);
+		instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE));
 		instdone[1] = I915_READ(GEN7_SC_INSTDONE);
 		instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE);
 		instdone[3] = I915_READ(GEN7_ROW_INSTDONE);

drivers/gpu/drm/i915/i915_guc_reg.h

@@ -37,10 +37,11 @@
 #define   GS_UKERNEL_READY		  (0xF0 << GS_UKERNEL_SHIFT)
 #define   GS_MIA_SHIFT			16
 #define   GS_MIA_MASK			  (0x07 << GS_MIA_SHIFT)
+#define   GS_MIA_CORE_STATE		  (1 << GS_MIA_SHIFT)
 
 #define SOFT_SCRATCH(n)			(0xc180 + ((n) * 4))
 
-#define UOS_RSA_SCRATCH_0		0xc200
+#define UOS_RSA_SCRATCH(i)		(0xc200 + (i) * 4)
 #define DMA_ADDR_0_LOW			0xc300
 #define DMA_ADDR_0_HIGH			0xc304
 #define DMA_ADDR_1_LOW			0xc308

drivers/gpu/drm/i915/i915_guc_submission.c

@@ -155,12 +155,21 @@ static int host2guc_sample_forcewake(struct intel_guc *guc,
 				     struct i915_guc_client *client)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct drm_device *dev = dev_priv->dev;
 	u32 data[2];
 
 	data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE;
-	data[1] = (intel_enable_rc6(dev_priv->dev)) ? 1 : 0;
+	/* WaRsDisableCoarsePowerGating:skl,bxt */
+	if (!intel_enable_rc6(dev_priv->dev) ||
+	    (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) ||
+	    (IS_SKL_GT3(dev) && (INTEL_REVID(dev) <= SKL_REVID_E0)) ||
+	    (IS_SKL_GT4(dev) && (INTEL_REVID(dev) <= SKL_REVID_E0)))
+		data[1] = 0;
+	else
+		/* bit 0 and 1 are for Render and Media domain separately */
+		data[1] = GUC_FORCEWAKE_RENDER | GUC_FORCEWAKE_MEDIA;
 
-	return host2guc_action(guc, data, 2);
+	return host2guc_action(guc, data, ARRAY_SIZE(data));
 }
 
 /*
@@ -914,3 +923,53 @@ void i915_guc_submission_fini(struct drm_device *dev)
 	gem_release_guc_obj(guc->ctx_pool_obj);
 	guc->ctx_pool_obj = NULL;
 }
+
+/**
+ * intel_guc_suspend() - notify GuC entering suspend state
+ * @dev:	drm device
+ */
+int intel_guc_suspend(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_context *ctx;
+	u32 data[3];
+
+	if (!i915.enable_guc_submission)
+		return 0;
+
+	ctx = dev_priv->ring[RCS].default_context;
+
+	data[0] = HOST2GUC_ACTION_ENTER_S_STATE;
+	/* any value greater than GUC_POWER_D0 */
+	data[1] = GUC_POWER_D1;
+	/* first page is shared data with GuC */
+	data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state);
+
+	return host2guc_action(guc, data, ARRAY_SIZE(data));
+}
+
+
+/**
+ * intel_guc_resume() - notify GuC resuming from suspend state
+ * @dev:	drm device
+ */
+int intel_guc_resume(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_context *ctx;
+	u32 data[3];
+
+	if (!i915.enable_guc_submission)
+		return 0;
+
+	ctx = dev_priv->ring[RCS].default_context;
+
+	data[0] = HOST2GUC_ACTION_EXIT_S_STATE;
+	data[1] = GUC_POWER_D0;
+	/* first page is shared data with GuC */
+	data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state);
+
+	return host2guc_action(guc, data, ARRAY_SIZE(data));
+}

drivers/gpu/drm/i915/i915_irq.c

@@ -581,6 +581,7 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 
 /**
  * i915_enable_asle_pipestat - enable ASLE pipestat for OpRegion
+ * @dev: drm device
  */
 static void i915_enable_asle_pipestat(struct drm_device *dev)
 {
@@ -997,12 +998,16 @@ static bool vlv_c0_above(struct drm_i915_private *dev_priv,
 			 int threshold)
 {
 	u64 time, c0;
+	unsigned int mul = 100;
 
 	if (old->cz_clock == 0)
 		return false;
 
+	if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
+		mul <<= 8;
+
 	time = now->cz_clock - old->cz_clock;
-	time *= threshold * dev_priv->mem_freq;
+	time *= threshold * dev_priv->czclk_freq;
 
 	/* Workload can be split between render + media, e.g. SwapBuffers
 	 * being blitted in X after being rendered in mesa. To account for
@@ -1010,7 +1015,7 @@ static bool vlv_c0_above(struct drm_i915_private *dev_priv,
 	 */
 	c0 = now->render_c0 - old->render_c0;
 	c0 += now->media_c0 - old->media_c0;
-	c0 *= 100 * VLV_CZ_CLOCK_TO_MILLI_SEC * 4 / 1000;
+	c0 *= mul * VLV_CZ_CLOCK_TO_MILLI_SEC;
 
 	return c0 >= time;
 }
@@ -2388,6 +2393,7 @@ static void i915_error_wake_up(struct drm_i915_private *dev_priv,
 
 /**
  * i915_reset_and_wakeup - do process context error handling work
+ * @dev: drm device
  *
  * Fire an error uevent so userspace can see that a hang or error
  * was detected.
@@ -2565,7 +2571,7 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
  * i915_handle_error - handle a gpu error
  * @dev: drm device
  *
- * Do some basic checking of regsiter state at error time and
+ * Do some basic checking of register state at error time and
  * dump it to the syslog.  Also call i915_capture_error_state() to make
  * sure we get a record and make it available in debugfs.  Fire a uevent
  * so userspace knows something bad happened (should trigger collection
@@ -2778,6 +2784,26 @@ semaphore_waits_for(struct intel_engine_cs *ring, u32 *seqno)
 	u64 offset = 0;
 	int i, backwards;
 
+	/*
+	 * This function does not support execlist mode - any attempt to
+	 * proceed further into this function will result in a kernel panic
+	 * when dereferencing ring->buffer, which is not set up in execlist
+	 * mode.
+	 *
+	 * The correct way of doing it would be to derive the currently
+	 * executing ring buffer from the current context, which is derived
+	 * from the currently running request. Unfortunately, to get the
+	 * current request we would have to grab the struct_mutex before doing
+	 * anything else, which would be ill-advised since some other thread
+	 * might have grabbed it already and managed to hang itself, causing
+	 * the hang checker to deadlock.
+	 *
+	 * Therefore, this function does not support execlist mode in its
+	 * current form. Just return NULL and move on.
+	 */
+	if (ring->buffer == NULL)
+		return NULL;
+
 	ipehr = I915_READ(RING_IPEHR(ring->mmio_base));
 	if (!ipehr_is_semaphore_wait(ring->dev, ipehr))
 		return NULL;

drivers/gpu/drm/i915/i915_reg.h

@@ -105,7 +105,7 @@
 #define  GRDOM_RESET_STATUS (1<<1)
 #define  GRDOM_RESET_ENABLE (1<<0)
 
-#define ILK_GDSR 0x2ca4 /* MCHBAR offset */
+#define ILK_GDSR (MCHBAR_MIRROR_BASE + 0x2ca4)
 #define  ILK_GRDOM_FULL		(0<<1)
 #define  ILK_GRDOM_RENDER	(1<<1)
 #define  ILK_GRDOM_MEDIA	(3<<1)
@@ -536,6 +536,10 @@
 #define GEN7_3DPRIM_START_INSTANCE      0x243C
 #define GEN7_3DPRIM_BASE_VERTEX         0x2440
 
+#define GEN7_GPGPU_DISPATCHDIMX         0x2500
+#define GEN7_GPGPU_DISPATCHDIMY         0x2504
+#define GEN7_GPGPU_DISPATCHDIMZ         0x2508
+
 #define OACONTROL 0x2360
 
 #define _GEN7_PIPEA_DE_LOAD_SL	0x70068
@@ -728,12 +732,13 @@ enum skl_disp_power_wells {
 #define  DSI_PLL_N1_DIV_MASK			(3 << 16)
 #define  DSI_PLL_M1_DIV_SHIFT			0
 #define  DSI_PLL_M1_DIV_MASK			(0x1ff << 0)
+#define CCK_CZ_CLOCK_CONTROL			0x62
 #define CCK_DISPLAY_CLOCK_CONTROL		0x6b
-#define  DISPLAY_TRUNK_FORCE_ON			(1 << 17)
-#define  DISPLAY_TRUNK_FORCE_OFF		(1 << 16)
-#define  DISPLAY_FREQUENCY_STATUS		(0x1f << 8)
-#define  DISPLAY_FREQUENCY_STATUS_SHIFT		8
-#define  DISPLAY_FREQUENCY_VALUES		(0x1f << 0)
+#define  CCK_TRUNK_FORCE_ON			(1 << 17)
+#define  CCK_TRUNK_FORCE_OFF			(1 << 16)
+#define  CCK_FREQUENCY_STATUS			(0x1f << 8)
+#define  CCK_FREQUENCY_STATUS_SHIFT		8
+#define  CCK_FREQUENCY_VALUES			(0x1f << 0)
 
 /**
  * DOC: DPIO
@@ -1395,7 +1400,8 @@ enum skl_disp_power_wells {
 #define BXT_PORT_TX_DW3_LN0(port)	_PORT3(port, _PORT_TX_DW3_LN0_A,  \
 						     _PORT_TX_DW3_LN0_B,  \
 						     _PORT_TX_DW3_LN0_C)
-#define   UNIQE_TRANGE_EN_METHOD	(1 << 27)
+#define   SCALE_DCOMP_METHOD		(1 << 26)
+#define   UNIQUE_TRANGE_EN_METHOD	(1 << 27)
 
 #define _PORT_TX_DW4_LN0_A		0x162510
 #define _PORT_TX_DW4_LN0_B		0x6C510
@@ -1436,9 +1442,15 @@ enum skl_disp_power_wells {
 
 /*
  * Fence registers
+ * [0-7]  @ 0x2000 gen2,gen3
+ * [8-15] @ 0x3000 945,g33,pnv
+ *
+ * [0-15] @ 0x3000 gen4,gen5
+ *
+ * [0-15] @ 0x100000 gen6,vlv,chv
+ * [0-31] @ 0x100000 gen7+
  */
-#define FENCE_REG_830_0			0x2000
-#define FENCE_REG_945_8			0x3000
+#define FENCE_REG(i)			(0x2000 + (((i) & 8) << 9) + ((i) & 7) * 4)
 #define   I830_FENCE_START_MASK		0x07f80000
 #define   I830_FENCE_TILING_Y_SHIFT	12
 #define   I830_FENCE_SIZE_BITS(size)	((ffs((size) >> 19) - 1) << 8)
@@ -1451,14 +1463,16 @@ enum skl_disp_power_wells {
 #define   I915_FENCE_START_MASK		0x0ff00000
 #define   I915_FENCE_SIZE_BITS(size)	((ffs((size) >> 20) - 1) << 8)
 
-#define FENCE_REG_965_0			0x03000
+#define FENCE_REG_965_LO(i)		(0x03000 + (i) * 8)
+#define FENCE_REG_965_HI(i)		(0x03000 + (i) * 8 + 4)
 #define   I965_FENCE_PITCH_SHIFT	2
 #define   I965_FENCE_TILING_Y_SHIFT	1
 #define   I965_FENCE_REG_VALID		(1<<0)
 #define   I965_FENCE_MAX_PITCH_VAL	0x0400
 
-#define FENCE_REG_SANDYBRIDGE_0		0x100000
-#define   SANDYBRIDGE_FENCE_PITCH_SHIFT	32
+#define FENCE_REG_GEN6_LO(i)	(0x100000 + (i) * 8)
+#define FENCE_REG_GEN6_HI(i)	(0x100000 + (i) * 8 + 4)
+#define   GEN6_FENCE_PITCH_SHIFT	32
 #define   GEN7_FENCE_MAX_PITCH_VAL	0x0800
 
 
@@ -1542,7 +1556,8 @@ enum skl_disp_power_wells {
 #define   RING_FAULT_FAULT_TYPE(x) ((x >> 1) & 0x3)
 #define   RING_FAULT_VALID	(1<<0)
 #define DONE_REG		0x40b0
-#define GEN8_PRIVATE_PAT	0x40e0
+#define GEN8_PRIVATE_PAT_LO	0x40e0
+#define GEN8_PRIVATE_PAT_HI	(0x40e0 + 4)
 #define BSD_HWS_PGA_GEN7	(0x04180)
 #define BLT_HWS_PGA_GEN7	(0x04280)
 #define VEBOX_HWS_PGA_GEN7	(0x04380)
@@ -1582,14 +1597,17 @@ enum skl_disp_power_wells {
 #endif
 #define IPEIR_I965	0x02064
 #define IPEHR_I965	0x02068
-#define INSTDONE_I965	0x0206c
-#define GEN7_INSTDONE_1		0x0206c
 #define GEN7_SC_INSTDONE	0x07100
 #define GEN7_SAMPLER_INSTDONE	0x0e160
 #define GEN7_ROW_INSTDONE	0x0e164
 #define I915_NUM_INSTDONE_REG	4
 #define RING_IPEIR(base)	((base)+0x64)
 #define RING_IPEHR(base)	((base)+0x68)
+/*
+ * On GEN4, only the render ring INSTDONE exists and has a different
+ * layout than the GEN7+ version.
+ * The GEN2 counterpart of this register is GEN2_INSTDONE.
+ */
 #define RING_INSTDONE(base)	((base)+0x6c)
 #define RING_INSTPS(base)	((base)+0x70)
 #define RING_DMA_FADD(base)	((base)+0x78)
@@ -1597,7 +1615,7 @@ enum skl_disp_power_wells {
 #define RING_INSTPM(base)	((base)+0xc0)
 #define RING_MI_MODE(base)	((base)+0x9c)
 #define INSTPS		0x02070 /* 965+ only */
-#define INSTDONE1	0x0207c /* 965+ only */
+#define GEN4_INSTDONE1	0x0207c /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	0x02074
 #define HWS_PGA		0x02080
 #define HWS_ADDRESS_MASK	0xfffff000
@@ -1606,7 +1624,7 @@ enum skl_disp_power_wells {
 #define   PWRCTX_EN	(1<<0)
 #define IPEIR		0x02088
 #define IPEHR		0x0208c
-#define INSTDONE	0x02090
+#define GEN2_INSTDONE	0x02090
 #define NOPID		0x02094
 #define HWSTAM		0x02098
 #define DMA_FADD_I8XX	0x020d0
@@ -1876,12 +1894,27 @@ enum skl_disp_power_wells {
 #define   CHV_FGT_EU_DIS_SS1_R1_MASK	(0xf << CHV_FGT_EU_DIS_SS1_R1_SHIFT)
 
 #define GEN8_FUSE2			0x9120
+#define   GEN8_F2_SS_DIS_SHIFT		21
+#define   GEN8_F2_SS_DIS_MASK		(0x7 << GEN8_F2_SS_DIS_SHIFT)
 #define   GEN8_F2_S_ENA_SHIFT		25
 #define   GEN8_F2_S_ENA_MASK		(0x7 << GEN8_F2_S_ENA_SHIFT)
 
 #define   GEN9_F2_SS_DIS_SHIFT		20
 #define   GEN9_F2_SS_DIS_MASK		(0xf << GEN9_F2_SS_DIS_SHIFT)
 
+#define GEN8_EU_DISABLE0		0x9134
+#define   GEN8_EU_DIS0_S0_MASK		0xffffff
+#define   GEN8_EU_DIS0_S1_SHIFT		24
+#define   GEN8_EU_DIS0_S1_MASK		(0xff << GEN8_EU_DIS0_S1_SHIFT)
+
+#define GEN8_EU_DISABLE1		0x9138
+#define   GEN8_EU_DIS1_S1_MASK		0xffff
+#define   GEN8_EU_DIS1_S2_SHIFT		16
+#define   GEN8_EU_DIS1_S2_MASK		(0xffff << GEN8_EU_DIS1_S2_SHIFT)
+
+#define GEN8_EU_DISABLE2		0x913c
+#define   GEN8_EU_DIS2_S2_MASK		0xff
+
 #define GEN9_EU_DISABLE(slice)		(0x9134 + (slice)*0x4)
 
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	0x12050
@@ -2475,8 +2508,8 @@ enum skl_disp_power_wells {
 #define PALETTE_A_OFFSET 0xa000
 #define PALETTE_B_OFFSET 0xa800
 #define CHV_PALETTE_C_OFFSET 0xc000
-#define PALETTE(pipe) (dev_priv->info.palette_offsets[pipe] + \
-		       dev_priv->info.display_mmio_offset)
+#define PALETTE(pipe, i) (dev_priv->info.palette_offsets[pipe] + \
+			  dev_priv->info.display_mmio_offset + (i) * 4)
 
 /* MCH MMIO space */
 
@@ -2807,8 +2840,11 @@ enum skl_disp_power_wells {
 
 #define INTERVAL_1_28_US(us)	(((us) * 100) >> 7)
 #define INTERVAL_1_33_US(us)	(((us) * 3)   >> 2)
+#define INTERVAL_0_833_US(us)	(((us) * 6) / 5)
 #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
-				INTERVAL_1_33_US(us) : \
+				(IS_BROXTON(dev_priv) ? \
+				INTERVAL_0_833_US(us) : \
+				INTERVAL_1_33_US(us)) : \
 				INTERVAL_1_28_US(us))
 
 /*
@@ -3264,7 +3300,9 @@ enum skl_disp_power_wells {
 #define GEN3_SDVOC	0x61160
 #define GEN4_HDMIB	GEN3_SDVOB
 #define GEN4_HDMIC	GEN3_SDVOC
-#define CHV_HDMID	0x6116C
+#define VLV_HDMIB	(VLV_DISPLAY_BASE + GEN4_HDMIB)
+#define VLV_HDMIC	(VLV_DISPLAY_BASE + GEN4_HDMIC)
+#define CHV_HDMID	(VLV_DISPLAY_BASE + 0x6116C)
 #define PCH_SDVOB	0xe1140
 #define PCH_HDMIB	PCH_SDVOB
 #define PCH_HDMIC	0xe1150
@@ -3596,17 +3634,29 @@ enum skl_disp_power_wells {
 #define UTIL_PIN_CTL		0x48400
 #define   UTIL_PIN_ENABLE	(1 << 31)
 
+#define   UTIL_PIN_PIPE(x)     ((x) << 29)
+#define   UTIL_PIN_PIPE_MASK   (3 << 29)
+#define   UTIL_PIN_MODE_PWM    (1 << 24)
+#define   UTIL_PIN_MODE_MASK   (0xf << 24)
+#define   UTIL_PIN_POLARITY    (1 << 22)
+
 /* BXT backlight register definition. */
-#define BXT_BLC_PWM_CTL1			0xC8250
+#define _BXT_BLC_PWM_CTL1			0xC8250
 #define   BXT_BLC_PWM_ENABLE			(1 << 31)
 #define   BXT_BLC_PWM_POLARITY			(1 << 29)
-#define BXT_BLC_PWM_FREQ1			0xC8254
-#define BXT_BLC_PWM_DUTY1			0xC8258
+#define _BXT_BLC_PWM_FREQ1			0xC8254
+#define _BXT_BLC_PWM_DUTY1			0xC8258
 
-#define BXT_BLC_PWM_CTL2			0xC8350
-#define BXT_BLC_PWM_FREQ2			0xC8354
-#define BXT_BLC_PWM_DUTY2			0xC8358
+#define _BXT_BLC_PWM_CTL2			0xC8350
+#define _BXT_BLC_PWM_FREQ2			0xC8354
+#define _BXT_BLC_PWM_DUTY2			0xC8358
 
+#define BXT_BLC_PWM_CTL(controller)    _PIPE(controller, \
+					_BXT_BLC_PWM_CTL1, _BXT_BLC_PWM_CTL2)
+#define BXT_BLC_PWM_FREQ(controller)   _PIPE(controller, \
+					_BXT_BLC_PWM_FREQ1, _BXT_BLC_PWM_FREQ2)
+#define BXT_BLC_PWM_DUTY(controller)   _PIPE(controller, \
+					_BXT_BLC_PWM_DUTY1, _BXT_BLC_PWM_DUTY2)
 
 #define PCH_GTC_CTL		0xe7000
 #define   PCH_GTC_ENABLE	(1 << 31)
@@ -4093,6 +4143,10 @@ enum skl_disp_power_wells {
 #define DP_C				0x64200
 #define DP_D				0x64300
 
+#define VLV_DP_B			(VLV_DISPLAY_BASE + DP_B)
+#define VLV_DP_C			(VLV_DISPLAY_BASE + DP_C)
+#define CHV_DP_D			(VLV_DISPLAY_BASE + DP_D)
+
 #define   DP_PORT_EN			(1 << 31)
 #define   DP_PIPEB_SELECT		(1 << 30)
 #define   DP_PIPE_MASK			(1 << 30)
@@ -5631,7 +5685,7 @@ enum skl_disp_power_wells {
 /* legacy palette */
 #define _LGC_PALETTE_A           0x4a000
 #define _LGC_PALETTE_B           0x4a800
-#define LGC_PALETTE(pipe) _PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B)
+#define LGC_PALETTE(pipe, i) (_PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B) + (i) * 4)
 
 #define _GAMMA_MODE_A		0x4a480
 #define _GAMMA_MODE_B		0x4ac80
@@ -6868,6 +6922,9 @@ enum skl_disp_power_wells {
 #define   GEN6_RC6			3
 #define   GEN6_RC7			4
 
+#define GEN8_GT_SLICE_INFO		0x138064
+#define   GEN8_LSLICESTAT_MASK		0x7
+
 #define CHV_POWER_SS0_SIG1		0xa720
 #define CHV_POWER_SS1_SIG1		0xa728
 #define   CHV_SS_PG_ENABLE		(1<<1)
@@ -7403,8 +7460,8 @@ enum skl_disp_power_wells {
 #define  DPLL_CFGCR2_PDIV_7 (4<<2)
 #define  DPLL_CFGCR2_CENTRAL_FREQ_MASK	(3)
 
-#define GET_CFG_CR1_REG(id) (DPLL1_CFGCR1 + (id - SKL_DPLL1) * 8)
-#define GET_CFG_CR2_REG(id) (DPLL1_CFGCR2 + (id - SKL_DPLL1) * 8)
+#define DPLL_CFGCR1(id) (DPLL1_CFGCR1 + ((id) - SKL_DPLL1) * 8)
+#define DPLL_CFGCR2(id) (DPLL1_CFGCR2 + ((id) - SKL_DPLL1) * 8)
 
 /* BXT display engine PLL */
 #define BXT_DE_PLL_CTL			0x6d000
@@ -7509,6 +7566,68 @@ enum skl_disp_power_wells {
 
 #define _MIPI_PORT(port, a, c)	_PORT3(port, a, 0, c)	/* ports A and C only */
 
+/* BXT MIPI clock controls */
+#define BXT_MAX_VAR_OUTPUT_KHZ			39500
+
+#define BXT_MIPI_CLOCK_CTL			0x46090
+#define  BXT_MIPI1_DIV_SHIFT			26
+#define  BXT_MIPI2_DIV_SHIFT			10
+#define  BXT_MIPI_DIV_SHIFT(port)		\
+			_MIPI_PORT(port, BXT_MIPI1_DIV_SHIFT, \
+					BXT_MIPI2_DIV_SHIFT)
+/* Var clock divider to generate TX source. Result must be < 39.5 M */
+#define  BXT_MIPI1_ESCLK_VAR_DIV_MASK		(0x3F << 26)
+#define  BXT_MIPI2_ESCLK_VAR_DIV_MASK		(0x3F << 10)
+#define  BXT_MIPI_ESCLK_VAR_DIV_MASK(port)	\
+			_MIPI_PORT(port, BXT_MIPI1_ESCLK_VAR_DIV_MASK, \
+						BXT_MIPI2_ESCLK_VAR_DIV_MASK)
+
+#define  BXT_MIPI_ESCLK_VAR_DIV(port, val)	\
+			(val << BXT_MIPI_DIV_SHIFT(port))
+/* TX control divider to select actual TX clock output from (8x/var) */
+#define  BXT_MIPI1_TX_ESCLK_SHIFT		21
+#define  BXT_MIPI2_TX_ESCLK_SHIFT		5
+#define  BXT_MIPI_TX_ESCLK_SHIFT(port)		\
+			_MIPI_PORT(port, BXT_MIPI1_TX_ESCLK_SHIFT, \
+					BXT_MIPI2_TX_ESCLK_SHIFT)
+#define  BXT_MIPI1_TX_ESCLK_FIXDIV_MASK		(3 << 21)
+#define  BXT_MIPI2_TX_ESCLK_FIXDIV_MASK		(3 << 5)
+#define  BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port)	\
+			_MIPI_PORT(port, BXT_MIPI1_TX_ESCLK_FIXDIV_MASK, \
+						BXT_MIPI2_TX_ESCLK_FIXDIV_MASK)
+#define  BXT_MIPI_TX_ESCLK_8XDIV_BY2(port)	\
+		(0x0 << BXT_MIPI_TX_ESCLK_SHIFT(port))
+#define  BXT_MIPI_TX_ESCLK_8XDIV_BY4(port)	\
+		(0x1 << BXT_MIPI_TX_ESCLK_SHIFT(port))
+#define  BXT_MIPI_TX_ESCLK_8XDIV_BY8(port)	\
+		(0x2 << BXT_MIPI_TX_ESCLK_SHIFT(port))
+/* RX control divider to select actual RX clock output from 8x*/
+#define  BXT_MIPI1_RX_ESCLK_SHIFT		19
+#define  BXT_MIPI2_RX_ESCLK_SHIFT		3
+#define  BXT_MIPI_RX_ESCLK_SHIFT(port)		\
+			_MIPI_PORT(port, BXT_MIPI1_RX_ESCLK_SHIFT, \
+					BXT_MIPI2_RX_ESCLK_SHIFT)
+#define  BXT_MIPI1_RX_ESCLK_FIXDIV_MASK		(3 << 19)
+#define  BXT_MIPI2_RX_ESCLK_FIXDIV_MASK		(3 << 3)
+#define  BXT_MIPI_RX_ESCLK_FIXDIV_MASK(port)	\
+		(3 << BXT_MIPI_RX_ESCLK_SHIFT(port))
+#define  BXT_MIPI_RX_ESCLK_8X_BY2(port)	\
+		(1 << BXT_MIPI_RX_ESCLK_SHIFT(port))
+#define  BXT_MIPI_RX_ESCLK_8X_BY3(port)	\
+		(2 << BXT_MIPI_RX_ESCLK_SHIFT(port))
+#define  BXT_MIPI_RX_ESCLK_8X_BY4(port)	\
+		(3 << BXT_MIPI_RX_ESCLK_SHIFT(port))
+/* BXT-A WA: Always prog DPHY dividers to 00 */
+#define  BXT_MIPI1_DPHY_DIV_SHIFT		16
+#define  BXT_MIPI2_DPHY_DIV_SHIFT		0
+#define  BXT_MIPI_DPHY_DIV_SHIFT(port)		\
+			_MIPI_PORT(port, BXT_MIPI1_DPHY_DIV_SHIFT, \
+					BXT_MIPI2_DPHY_DIV_SHIFT)
+#define  BXT_MIPI_1_DPHY_DIVIDER_MASK		(3 << 16)
+#define  BXT_MIPI_2_DPHY_DIVIDER_MASK		(3 << 0)
+#define  BXT_MIPI_DPHY_DIVIDER_MASK(port)	\
+		(3 << BXT_MIPI_DPHY_DIV_SHIFT(port))
+
 /* BXT MIPI mode configure */
 #define  _BXT_MIPIA_TRANS_HACTIVE			0x6B0F8
 #define  _BXT_MIPIC_TRANS_HACTIVE			0x6B8F8
@@ -7550,6 +7669,13 @@ enum skl_disp_power_wells {
 #define _MIPIA_PORT_CTRL			(VLV_DISPLAY_BASE + 0x61190)
 #define _MIPIC_PORT_CTRL			(VLV_DISPLAY_BASE + 0x61700)
 #define MIPI_PORT_CTRL(port)	_MIPI_PORT(port, _MIPIA_PORT_CTRL, _MIPIC_PORT_CTRL)
+
+ /* BXT port control */
+#define _BXT_MIPIA_PORT_CTRL				0x6B0C0
+#define _BXT_MIPIC_PORT_CTRL				0x6B8C0
+#define BXT_MIPI_PORT_CTRL(tc)	_MIPI_PORT(tc, _BXT_MIPIA_PORT_CTRL, \
+						_BXT_MIPIC_PORT_CTRL)
+
 #define  DPI_ENABLE					(1 << 31) /* A + C */
 #define  MIPIA_MIPI4DPHY_DELAY_COUNT_SHIFT		27
 #define  MIPIA_MIPI4DPHY_DELAY_COUNT_MASK		(0xf << 27)

drivers/gpu/drm/i915/i915_sysfs.c

@@ -39,7 +39,7 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u64 raw_time; /* 32b value may overflow during fixed point math */
-	u64 units = 128ULL, div = 100000ULL, bias = 100ULL;
+	u64 units = 128ULL, div = 100000ULL;
 	u32 ret;
 
 	if (!intel_enable_rc6(dev))
@@ -49,41 +49,19 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg)
 
 	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
 	if (IS_VALLEYVIEW(dev)) {
-		u32 clk_reg, czcount_30ns;
-
-		if (IS_CHERRYVIEW(dev))
-			clk_reg = CHV_CLK_CTL1;
-		else
-			clk_reg = VLV_CLK_CTL2;
-
-		czcount_30ns = I915_READ(clk_reg) >> CLK_CTL2_CZCOUNT_30NS_SHIFT;
-
-		if (!czcount_30ns) {
-			WARN(!czcount_30ns, "bogus CZ count value");
-			ret = 0;
-			goto out;
-		}
-
-		if (IS_CHERRYVIEW(dev) && czcount_30ns == 1) {
-			/* Special case for 320Mhz */
-			div = 10000000ULL;
-			units = 3125ULL;
-		} else {
-			czcount_30ns += 1;
-			div = 1000000ULL;
-			units = DIV_ROUND_UP_ULL(30ULL * bias, czcount_30ns);
-		}
+		units = 1;
+		div = dev_priv->czclk_freq;
 
 		if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
 			units <<= 8;
-
-		div = div * bias;
+	} else if (IS_BROXTON(dev)) {
+		units = 1;
+		div = 1200;		/* 833.33ns */
 	}
 
 	raw_time = I915_READ(reg) * units;
 	ret = DIV_ROUND_UP_ULL(raw_time, div);
 
-out:
 	intel_runtime_pm_put(dev_priv);
 	return ret;
 }

drivers/gpu/drm/i915/i915_trace.h

@@ -107,6 +107,26 @@ TRACE_EVENT(i915_gem_object_create,
 	    TP_printk("obj=%p, size=%u", __entry->obj, __entry->size)
 );
 
+TRACE_EVENT(i915_gem_shrink,
+	    TP_PROTO(struct drm_i915_private *i915, unsigned long target, unsigned flags),
+	    TP_ARGS(i915, target, flags),
+
+	    TP_STRUCT__entry(
+			     __field(int, dev)
+			     __field(unsigned long, target)
+			     __field(unsigned, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = i915->dev->primary->index;
+			   __entry->target = target;
+			   __entry->flags = flags;
+			   ),
+
+	    TP_printk("dev=%d, target=%lu, flags=%x",
+		      __entry->dev, __entry->target, __entry->flags)
+);
+
 TRACE_EVENT(i915_vma_bind,
 	    TP_PROTO(struct i915_vma *vma, unsigned flags),
 	    TP_ARGS(vma, flags),

drivers/gpu/drm/i915/intel_atomic.c

@@ -94,6 +94,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base);
 
 	crtc_state->update_pipe = false;
+	crtc_state->disable_lp_wm = false;
 
 	return &crtc_state->base;
 }

drivers/gpu/drm/i915/intel_audio.c

@@ -50,6 +50,11 @@
  * co-operation between the graphics and audio drivers is handled via audio
  * related registers. (The notable exception is the power management, not
  * covered here.)
+ *
+ * The struct i915_audio_component is used to interact between the graphics
+ * and audio drivers. The struct i915_audio_component_ops *ops in it is
+ * defined in graphics driver and called in audio driver. The
+ * struct i915_audio_component_audio_ops *audio_ops is called from i915 driver.
  */
 
 static const struct {
@@ -68,18 +73,44 @@ static const struct {
 	{ 148500, AUD_CONFIG_PIXEL_CLOCK_HDMI_148500 },
 };
 
+/* HDMI N/CTS table */
+#define TMDS_297M 297000
+#define TMDS_296M DIV_ROUND_UP(297000 * 1000, 1001)
+static const struct {
+	int sample_rate;
+	int clock;
+	int n;
+	int cts;
+} aud_ncts[] = {
+	{ 44100, TMDS_296M, 4459, 234375 },
+	{ 44100, TMDS_297M, 4704, 247500 },
+	{ 48000, TMDS_296M, 5824, 281250 },
+	{ 48000, TMDS_297M, 5120, 247500 },
+	{ 32000, TMDS_296M, 5824, 421875 },
+	{ 32000, TMDS_297M, 3072, 222750 },
+	{ 88200, TMDS_296M, 8918, 234375 },
+	{ 88200, TMDS_297M, 9408, 247500 },
+	{ 96000, TMDS_296M, 11648, 281250 },
+	{ 96000, TMDS_297M, 10240, 247500 },
+	{ 176400, TMDS_296M, 17836, 234375 },
+	{ 176400, TMDS_297M, 18816, 247500 },
+	{ 192000, TMDS_296M, 23296, 281250 },
+	{ 192000, TMDS_297M, 20480, 247500 },
+};
+
 /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */
-static u32 audio_config_hdmi_pixel_clock(struct drm_display_mode *mode)
+static u32 audio_config_hdmi_pixel_clock(const struct drm_display_mode *adjusted_mode)
 {
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(hdmi_audio_clock); i++) {
-		if (mode->clock == hdmi_audio_clock[i].clock)
+		if (adjusted_mode->crtc_clock == hdmi_audio_clock[i].clock)
 			break;
 	}
 
 	if (i == ARRAY_SIZE(hdmi_audio_clock)) {
-		DRM_DEBUG_KMS("HDMI audio pixel clock setting for %d not found, falling back to defaults\n", mode->clock);
+		DRM_DEBUG_KMS("HDMI audio pixel clock setting for %d not found, falling back to defaults\n",
+			      adjusted_mode->crtc_clock);
 		i = 1;
 	}
 
@@ -90,6 +121,45 @@ static u32 audio_config_hdmi_pixel_clock(struct drm_display_mode *mode)
 	return hdmi_audio_clock[i].config;
 }
 
+static int audio_config_get_n(const struct drm_display_mode *mode, int rate)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(aud_ncts); i++) {
+		if ((rate == aud_ncts[i].sample_rate) &&
+			(mode->clock == aud_ncts[i].clock)) {
+			return aud_ncts[i].n;
+		}
+	}
+	return 0;
+}
+
+static uint32_t audio_config_setup_n_reg(int n, uint32_t val)
+{
+	int n_low, n_up;
+	uint32_t tmp = val;
+
+	n_low = n & 0xfff;
+	n_up = (n >> 12) & 0xff;
+	tmp &= ~(AUD_CONFIG_UPPER_N_MASK | AUD_CONFIG_LOWER_N_MASK);
+	tmp |= ((n_up << AUD_CONFIG_UPPER_N_SHIFT) |
+			(n_low << AUD_CONFIG_LOWER_N_SHIFT) |
+			AUD_CONFIG_N_PROG_ENABLE);
+	return tmp;
+}
+
+/* check whether N/CTS/M need be set manually */
+static bool audio_rate_need_prog(struct intel_crtc *crtc,
+				 const struct drm_display_mode *mode)
+{
+	if (((mode->clock == TMDS_297M) ||
+		 (mode->clock == TMDS_296M)) &&
+		intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI))
+		return true;
+	else
+		return false;
+}
+
 static bool intel_eld_uptodate(struct drm_connector *connector,
 			       int reg_eldv, uint32_t bits_eldv,
 			       int reg_elda, uint32_t bits_elda,
@@ -138,7 +208,7 @@ static void g4x_audio_codec_disable(struct intel_encoder *encoder)
 
 static void g4x_audio_codec_enable(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
-				   struct drm_display_mode *mode)
+				   const struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
 	uint8_t *eld = connector->eld;
@@ -184,6 +254,8 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder)
 
 	DRM_DEBUG_KMS("Disable audio codec on pipe %c\n", pipe_name(pipe));
 
+	mutex_lock(&dev_priv->av_mutex);
+
 	/* Disable timestamps */
 	tmp = I915_READ(HSW_AUD_CFG(pipe));
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
@@ -199,22 +271,31 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder)
 	tmp &= ~AUDIO_ELD_VALID(pipe);
 	tmp &= ~AUDIO_OUTPUT_ENABLE(pipe);
 	I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp);
+
+	mutex_unlock(&dev_priv->av_mutex);
 }
 
 static void hsw_audio_codec_enable(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
-				   struct drm_display_mode *mode)
+				   const struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum pipe pipe = intel_crtc->pipe;
+	struct i915_audio_component *acomp = dev_priv->audio_component;
 	const uint8_t *eld = connector->eld;
+	struct intel_digital_port *intel_dig_port =
+		enc_to_dig_port(&encoder->base);
+	enum port port = intel_dig_port->port;
 	uint32_t tmp;
 	int len, i;
+	int n, rate;
 
 	DRM_DEBUG_KMS("Enable audio codec on pipe %c, %u bytes ELD\n",
 		      pipe_name(pipe), drm_eld_size(eld));
 
+	mutex_lock(&dev_priv->av_mutex);
+
 	/* Enable audio presence detect, invalidate ELD */
 	tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
 	tmp |= AUDIO_OUTPUT_ENABLE(pipe);
@@ -246,13 +327,32 @@ static void hsw_audio_codec_enable(struct drm_connector *connector,
 	/* Enable timestamps */
 	tmp = I915_READ(HSW_AUD_CFG(pipe));
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
-	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
 	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
 	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	else
-		tmp |= audio_config_hdmi_pixel_clock(mode);
+		tmp |= audio_config_hdmi_pixel_clock(adjusted_mode);
+
+	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
+	if (audio_rate_need_prog(intel_crtc, adjusted_mode)) {
+		if (!acomp)
+			rate = 0;
+		else if (port >= PORT_A && port <= PORT_E)
+			rate = acomp->aud_sample_rate[port];
+		else {
+			DRM_ERROR("invalid port: %d\n", port);
+			rate = 0;
+		}
+		n = audio_config_get_n(adjusted_mode, rate);
+		if (n != 0)
+			tmp = audio_config_setup_n_reg(n, tmp);
+		else
+			DRM_DEBUG_KMS("no suitable N value is found\n");
+	}
+
 	I915_WRITE(HSW_AUD_CFG(pipe), tmp);
+
+	mutex_unlock(&dev_priv->av_mutex);
 }
 
 static void ilk_audio_codec_disable(struct intel_encoder *encoder)
@@ -304,7 +404,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder)
 
 static void ilk_audio_codec_enable(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
-				   struct drm_display_mode *mode)
+				   const struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
@@ -381,7 +481,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector,
 	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	else
-		tmp |= audio_config_hdmi_pixel_clock(mode);
+		tmp |= audio_config_hdmi_pixel_clock(adjusted_mode);
 	I915_WRITE(aud_config, tmp);
 }
 
@@ -396,7 +496,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->crtc);
-	struct drm_display_mode *mode = &crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	struct drm_connector *connector;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -419,10 +519,11 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT))
 		connector->eld[5] |= (1 << 2);
 
-	connector->eld[6] = drm_av_sync_delay(connector, mode) / 2;
+	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
 
 	if (dev_priv->display.audio_codec_enable)
-		dev_priv->display.audio_codec_enable(connector, intel_encoder, mode);
+		dev_priv->display.audio_codec_enable(connector, intel_encoder,
+						     adjusted_mode);
 
 	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify)
 		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, (int) port);
@@ -527,12 +628,91 @@ static int i915_audio_component_get_cdclk_freq(struct device *dev)
 	return ret;
 }
 
+static int i915_audio_component_sync_audio_rate(struct device *dev,
+						int port, int rate)
+{
+	struct drm_i915_private *dev_priv = dev_to_i915(dev);
+	struct drm_device *drm_dev = dev_priv->dev;
+	struct intel_encoder *intel_encoder;
+	struct intel_digital_port *intel_dig_port;
+	struct intel_crtc *crtc;
+	struct drm_display_mode *mode;
+	struct i915_audio_component *acomp = dev_priv->audio_component;
+	enum pipe pipe = -1;
+	u32 tmp;
+	int n;
+
+	/* HSW, BDW SKL need this fix */
+	if (!IS_SKYLAKE(dev_priv) &&
+		!IS_BROADWELL(dev_priv) &&
+		!IS_HASWELL(dev_priv))
+		return 0;
+
+	mutex_lock(&dev_priv->av_mutex);
+	/* 1. get the pipe */
+	for_each_intel_encoder(drm_dev, intel_encoder) {
+		if (intel_encoder->type != INTEL_OUTPUT_HDMI)
+			continue;
+		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+		if (port == intel_dig_port->port) {
+			crtc = to_intel_crtc(intel_encoder->base.crtc);
+			if (!crtc) {
+				DRM_DEBUG_KMS("%s: crtc is NULL\n", __func__);
+				continue;
+			}
+			pipe = crtc->pipe;
+			break;
+		}
+	}
+
+	if (pipe == INVALID_PIPE) {
+		DRM_DEBUG_KMS("no pipe for the port %c\n", port_name(port));
+		mutex_unlock(&dev_priv->av_mutex);
+		return -ENODEV;
+	}
+	DRM_DEBUG_KMS("pipe %c connects port %c\n",
+				  pipe_name(pipe), port_name(port));
+	mode = &crtc->config->base.adjusted_mode;
+
+	/* port must be valid now, otherwise the pipe will be invalid */
+	acomp->aud_sample_rate[port] = rate;
+
+	/* 2. check whether to set the N/CTS/M manually or not */
+	if (!audio_rate_need_prog(crtc, mode)) {
+		tmp = I915_READ(HSW_AUD_CFG(pipe));
+		tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
+		I915_WRITE(HSW_AUD_CFG(pipe), tmp);
+		mutex_unlock(&dev_priv->av_mutex);
+		return 0;
+	}
+
+	n = audio_config_get_n(mode, rate);
+	if (n == 0) {
+		DRM_DEBUG_KMS("Using automatic mode for N value on port %c\n",
+					  port_name(port));
+		tmp = I915_READ(HSW_AUD_CFG(pipe));
+		tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
+		I915_WRITE(HSW_AUD_CFG(pipe), tmp);
+		mutex_unlock(&dev_priv->av_mutex);
+		return 0;
+	}
+
+	/* 3. set the N/CTS/M */
+	tmp = I915_READ(HSW_AUD_CFG(pipe));
+	tmp = audio_config_setup_n_reg(n, tmp);
+	I915_WRITE(HSW_AUD_CFG(pipe), tmp);
+
+	mutex_unlock(&dev_priv->av_mutex);
+	return 0;
+}
+
 static const struct i915_audio_component_ops i915_audio_component_ops = {
 	.owner		= THIS_MODULE,
 	.get_power	= i915_audio_component_get_power,
 	.put_power	= i915_audio_component_put_power,
 	.codec_wake_override = i915_audio_component_codec_wake_override,
 	.get_cdclk_freq	= i915_audio_component_get_cdclk_freq,
+	.sync_audio_rate = i915_audio_component_sync_audio_rate,
 };
 
 static int i915_audio_component_bind(struct device *i915_dev,
@@ -540,6 +720,7 @@ static int i915_audio_component_bind(struct device *i915_dev,
 {
 	struct i915_audio_component *acomp = data;
 	struct drm_i915_private *dev_priv = dev_to_i915(i915_dev);
+	int i;
 
 	if (WARN_ON(acomp->ops || acomp->dev))
 		return -EEXIST;
@@ -547,6 +728,9 @@ static int i915_audio_component_bind(struct device *i915_dev,
 	drm_modeset_lock_all(dev_priv->dev);
 	acomp->ops = &i915_audio_component_ops;
 	acomp->dev = i915_dev;
+	BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS);
+	for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++)
+		acomp->aud_sample_rate[i] = 0;
 	dev_priv->audio_component = acomp;
 	drm_modeset_unlock_all(dev_priv->dev);
 

drivers/gpu/drm/i915/intel_crt.c

@@ -158,7 +158,7 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	u32 adpa;
 
 	if (INTEL_INFO(dev)->gen >= 5)
@@ -890,7 +890,7 @@ void intel_crt_init(struct drm_device *dev)
 		u32 fdi_config = FDI_RX_POLARITY_REVERSED_LPT |
 				 FDI_RX_LINK_REVERSAL_OVERRIDE;
 
-		dev_priv->fdi_rx_config = I915_READ(_FDI_RXA_CTL) & fdi_config;
+		dev_priv->fdi_rx_config = I915_READ(FDI_RX_CTL(PIPE_A)) & fdi_config;
 	}
 
 	intel_crt_reset(connector);

drivers/gpu/drm/i915/intel_csr.c

@@ -265,6 +265,15 @@ void intel_csr_load_program(struct drm_device *dev)
 		return;
 	}
 
+	/*
+	 * FIXME: Firmware gets lost on S3/S4, but not when entering system
+	 * standby or suspend-to-idle (which is just like forced runtime pm).
+	 * Unfortunately the ACPI subsystem doesn't yet give us a way to
+	 * differentiate this, hence figure it out with this hack.
+	 */
+	if (I915_READ(CSR_PROGRAM(0)))
+		return;
+
 	mutex_lock(&dev_priv->csr_lock);
 	fw_size = dev_priv->csr.dmc_fw_size;
 	for (i = 0; i < fw_size; i++)

drivers/gpu/drm/i915/intel_ddi.c

@@ -256,9 +256,6 @@ struct bxt_ddi_buf_trans {
 	bool default_index; /* true if the entry represents default value */
 };
 
-/* BSpec does not define separate vswing/pre-emphasis values for eDP.
- * Using DP values for eDP as well.
- */
 static const struct bxt_ddi_buf_trans bxt_ddi_translations_dp[] = {
 					/* Idx	NT mV diff	db  */
 	{ 52,  0x9A, 0, 128, true  },	/* 0:	400		0   */
@@ -273,6 +270,20 @@ static const struct bxt_ddi_buf_trans bxt_ddi_translations_dp[] = {
 	{ 154, 0x9A, 1, 128, false },	/* 9:	1200		0   */
 };
 
+static const struct bxt_ddi_buf_trans bxt_ddi_translations_edp[] = {
+					/* Idx	NT mV diff	db  */
+	{ 26, 0, 0, 128, false },	/* 0:	200		0   */
+	{ 38, 0, 0, 112, false },	/* 1:	200		1.5 */
+	{ 48, 0, 0, 96,  false },	/* 2:	200		4   */
+	{ 54, 0, 0, 69,  false },	/* 3:	200		6   */
+	{ 32, 0, 0, 128, false },	/* 4:	250		0   */
+	{ 48, 0, 0, 104, false },	/* 5:	250		1.5 */
+	{ 54, 0, 0, 85,  false },	/* 6:	250		4   */
+	{ 43, 0, 0, 128, false },	/* 7:	300		0   */
+	{ 54, 0, 0, 101, false },	/* 8:	300		1.5 */
+	{ 48, 0, 0, 128, false },	/* 9:	300		0   */
+};
+
 /* BSpec has 2 recommended values - entries 0 and 8.
  * Using the entry with higher vswing.
  */
@@ -298,21 +309,26 @@ static void ddi_get_encoder_port(struct intel_encoder *intel_encoder,
 				 enum port *port)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
-	int type = intel_encoder->type;
 
-	if (type == INTEL_OUTPUT_DP_MST) {
+	switch (intel_encoder->type) {
+	case INTEL_OUTPUT_DP_MST:
 		*dig_port = enc_to_mst(encoder)->primary;
 		*port = (*dig_port)->port;
-	} else if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP ||
-	    type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_UNKNOWN) {
+		break;
+	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_EDP:
+	case INTEL_OUTPUT_HDMI:
+	case INTEL_OUTPUT_UNKNOWN:
 		*dig_port = enc_to_dig_port(encoder);
 		*port = (*dig_port)->port;
-	} else if (type == INTEL_OUTPUT_ANALOG) {
+		break;
+	case INTEL_OUTPUT_ANALOG:
 		*dig_port = NULL;
 		*port = PORT_E;
-	} else {
-		DRM_ERROR("Invalid DDI encoder type %d\n", type);
-		BUG();
+		break;
+	default:
+		WARN(1, "Invalid DDI encoder type %d\n", intel_encoder->type);
+		break;
 	}
 }
 
@@ -542,8 +558,10 @@ void intel_prepare_ddi(struct drm_device *dev)
 		enum port port;
 		bool supports_hdmi;
 
-		ddi_get_encoder_port(intel_encoder, &intel_dig_port, &port);
+		if (intel_encoder->type == INTEL_OUTPUT_DSI)
+			continue;
 
+		ddi_get_encoder_port(intel_encoder, &intel_dig_port, &port);
 		if (visited[port])
 			continue;
 
@@ -592,7 +610,7 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 	 *
 	 * WaFDIAutoLinkSetTimingOverrride:hsw
 	 */
-	I915_WRITE(_FDI_RXA_MISC, FDI_RX_PWRDN_LANE1_VAL(2) |
+	I915_WRITE(FDI_RX_MISC(PIPE_A), FDI_RX_PWRDN_LANE1_VAL(2) |
 				  FDI_RX_PWRDN_LANE0_VAL(2) |
 				  FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90);
 
@@ -600,13 +618,13 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 	rx_ctl_val = dev_priv->fdi_rx_config | FDI_RX_ENHANCE_FRAME_ENABLE |
 		     FDI_RX_PLL_ENABLE |
 		     FDI_DP_PORT_WIDTH(intel_crtc->config->fdi_lanes);
-	I915_WRITE(_FDI_RXA_CTL, rx_ctl_val);
-	POSTING_READ(_FDI_RXA_CTL);
+	I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val);
+	POSTING_READ(FDI_RX_CTL(PIPE_A));
 	udelay(220);
 
 	/* Switch from Rawclk to PCDclk */
 	rx_ctl_val |= FDI_PCDCLK;
-	I915_WRITE(_FDI_RXA_CTL, rx_ctl_val);
+	I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val);
 
 	/* Configure Port Clock Select */
 	I915_WRITE(PORT_CLK_SEL(PORT_E), intel_crtc->config->ddi_pll_sel);
@@ -635,21 +653,21 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 		udelay(600);
 
 		/* Program PCH FDI Receiver TU */
-		I915_WRITE(_FDI_RXA_TUSIZE1, TU_SIZE(64));
+		I915_WRITE(FDI_RX_TUSIZE1(PIPE_A), TU_SIZE(64));
 
 		/* Enable PCH FDI Receiver with auto-training */
 		rx_ctl_val |= FDI_RX_ENABLE | FDI_LINK_TRAIN_AUTO;
-		I915_WRITE(_FDI_RXA_CTL, rx_ctl_val);
-		POSTING_READ(_FDI_RXA_CTL);
+		I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val);
+		POSTING_READ(FDI_RX_CTL(PIPE_A));
 
 		/* Wait for FDI receiver lane calibration */
 		udelay(30);
 
 		/* Unset FDI_RX_MISC pwrdn lanes */
-		temp = I915_READ(_FDI_RXA_MISC);
+		temp = I915_READ(FDI_RX_MISC(PIPE_A));
 		temp &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK);
-		I915_WRITE(_FDI_RXA_MISC, temp);
-		POSTING_READ(_FDI_RXA_MISC);
+		I915_WRITE(FDI_RX_MISC(PIPE_A), temp);
+		POSTING_READ(FDI_RX_MISC(PIPE_A));
 
 		/* Wait for FDI auto training time */
 		udelay(5);
@@ -683,15 +701,15 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 		intel_wait_ddi_buf_idle(dev_priv, PORT_E);
 
 		rx_ctl_val &= ~FDI_RX_ENABLE;
-		I915_WRITE(_FDI_RXA_CTL, rx_ctl_val);
-		POSTING_READ(_FDI_RXA_CTL);
+		I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val);
+		POSTING_READ(FDI_RX_CTL(PIPE_A));
 
 		/* Reset FDI_RX_MISC pwrdn lanes */
-		temp = I915_READ(_FDI_RXA_MISC);
+		temp = I915_READ(FDI_RX_MISC(PIPE_A));
 		temp &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK);
 		temp |= FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2);
-		I915_WRITE(_FDI_RXA_MISC, temp);
-		POSTING_READ(_FDI_RXA_MISC);
+		I915_WRITE(FDI_RX_MISC(PIPE_A), temp);
+		POSTING_READ(FDI_RX_MISC(PIPE_A));
 	}
 
 	DRM_ERROR("FDI link training failed!\n");
@@ -953,8 +971,8 @@ static int skl_calc_wrpll_link(struct drm_i915_private *dev_priv,
 	uint32_t cfgcr1_val, cfgcr2_val;
 	uint32_t p0, p1, p2, dco_freq;
 
-	cfgcr1_reg = GET_CFG_CR1_REG(dpll);
-	cfgcr2_reg = GET_CFG_CR2_REG(dpll);
+	cfgcr1_reg = DPLL_CFGCR1(dpll);
+	cfgcr2_reg = DPLL_CFGCR2(dpll);
 
 	cfgcr1_val = I915_READ(cfgcr1_reg);
 	cfgcr2_val = I915_READ(cfgcr2_reg);
@@ -2027,7 +2045,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
 {
 	struct drm_crtc *crtc = &intel_crtc->base;
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
@@ -2112,7 +2131,11 @@ static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level,
 	u32 n_entries, i;
 	uint32_t val;
 
-	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
+	if (type == INTEL_OUTPUT_EDP && dev_priv->edp_low_vswing) {
+		n_entries = ARRAY_SIZE(bxt_ddi_translations_edp);
+		ddi_translations = bxt_ddi_translations_edp;
+	} else if (type == INTEL_OUTPUT_DISPLAYPORT
+			|| type == INTEL_OUTPUT_EDP) {
 		n_entries = ARRAY_SIZE(bxt_ddi_translations_dp);
 		ddi_translations = bxt_ddi_translations_dp;
 	} else if (type == INTEL_OUTPUT_HDMI) {
@@ -2150,9 +2173,13 @@ static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level,
 	I915_WRITE(BXT_PORT_TX_DW2_GRP(port), val);
 
 	val = I915_READ(BXT_PORT_TX_DW3_LN0(port));
-	val &= ~UNIQE_TRANGE_EN_METHOD;
+	val &= ~SCALE_DCOMP_METHOD;
 	if (ddi_translations[level].enable)
-		val |= UNIQE_TRANGE_EN_METHOD;
+		val |= SCALE_DCOMP_METHOD;
+
+	if ((val & UNIQUE_TRANGE_EN_METHOD) && !(val & SCALE_DCOMP_METHOD))
+		DRM_ERROR("Disabled scaling while ouniqetrangenmethod was set");
+
 	I915_WRITE(BXT_PORT_TX_DW3_GRP(port), val);
 
 	val = I915_READ(BXT_PORT_TX_DW4_LN0(port));
@@ -2293,7 +2320,6 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 		intel_dp_start_link_train(intel_dp);
-		intel_dp_complete_link_train(intel_dp);
 		if (port != PORT_A || INTEL_INFO(dev)->gen >= 9)
 			intel_dp_stop_link_train(intel_dp);
 	} else if (type == INTEL_OUTPUT_HDMI) {
@@ -2480,20 +2506,20 @@ static const struct skl_dpll_regs skl_dpll_regs[3] = {
 	{
 		/* DPLL 1 */
 		.ctl = LCPLL2_CTL,
-		.cfgcr1 = DPLL1_CFGCR1,
-		.cfgcr2 = DPLL1_CFGCR2,
+		.cfgcr1 = DPLL_CFGCR1(SKL_DPLL1),
+		.cfgcr2 = DPLL_CFGCR2(SKL_DPLL1),
 	},
 	{
 		/* DPLL 2 */
 		.ctl = WRPLL_CTL1,
-		.cfgcr1 = DPLL2_CFGCR1,
-		.cfgcr2 = DPLL2_CFGCR2,
+		.cfgcr1 = DPLL_CFGCR1(SKL_DPLL2),
+		.cfgcr2 = DPLL_CFGCR2(SKL_DPLL2),
 	},
 	{
 		/* DPLL 3 */
 		.ctl = WRPLL_CTL2,
-		.cfgcr1 = DPLL3_CFGCR1,
-		.cfgcr2 = DPLL3_CFGCR2,
+		.cfgcr1 = DPLL_CFGCR1(SKL_DPLL3),
+		.cfgcr2 = DPLL_CFGCR2(SKL_DPLL3),
 	},
 };
 
@@ -2999,22 +3025,22 @@ void intel_ddi_fdi_disable(struct drm_crtc *crtc)
 
 	intel_ddi_post_disable(intel_encoder);
 
-	val = I915_READ(_FDI_RXA_CTL);
+	val = I915_READ(FDI_RX_CTL(PIPE_A));
 	val &= ~FDI_RX_ENABLE;
-	I915_WRITE(_FDI_RXA_CTL, val);
+	I915_WRITE(FDI_RX_CTL(PIPE_A), val);
 
-	val = I915_READ(_FDI_RXA_MISC);
+	val = I915_READ(FDI_RX_MISC(PIPE_A));
 	val &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK);
 	val |= FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2);
-	I915_WRITE(_FDI_RXA_MISC, val);
+	I915_WRITE(FDI_RX_MISC(PIPE_A), val);
 
-	val = I915_READ(_FDI_RXA_CTL);
+	val = I915_READ(FDI_RX_CTL(PIPE_A));
 	val &= ~FDI_PCDCLK;
-	I915_WRITE(_FDI_RXA_CTL, val);
+	I915_WRITE(FDI_RX_CTL(PIPE_A), val);
 
-	val = I915_READ(_FDI_RXA_CTL);
+	val = I915_READ(FDI_RX_CTL(PIPE_A));
 	val &= ~FDI_RX_PLL_ENABLE;
-	I915_WRITE(_FDI_RXA_CTL, val);
+	I915_WRITE(FDI_RX_CTL(PIPE_A), val);
 }
 
 void intel_ddi_get_config(struct intel_encoder *encoder,

drivers/gpu/drm/i915/intel_dp.c

@@ -1587,7 +1587,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder)
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 
 	intel_dp_set_link_params(intel_dp, crtc->config);
 
@@ -2604,7 +2604,6 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 	intel_dp_start_link_train(intel_dp);
-	intel_dp_complete_link_train(intel_dp);
 	intel_dp_stop_link_train(intel_dp);
 
 	if (crtc->config->has_audio) {
@@ -3417,11 +3416,6 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
 		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
 	}
 
-	/* LRC Bypass */
-	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30);
-	val |= DPIO_LRC_BYPASS;
-	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val);
-
 	mutex_unlock(&dev_priv->sb_lock);
 
 	return 0;
@@ -3696,8 +3690,8 @@ static void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 }
 
 /* Enable corresponding port and start training pattern 1 */
-void
-intel_dp_start_link_train(struct intel_dp *intel_dp)
+static void
+intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 {
 	struct drm_encoder *encoder = &dp_to_dig_port(intel_dp)->base.base;
 	struct drm_device *dev = encoder->dev;
@@ -3810,8 +3804,8 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	intel_dp->DP = DP;
 }
 
-void
-intel_dp_complete_link_train(struct intel_dp *intel_dp)
+static void
+intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
@@ -3864,7 +3858,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 		if (!drm_dp_clock_recovery_ok(link_status,
 					      intel_dp->lane_count)) {
 			intel_dp->train_set_valid = false;
-			intel_dp_start_link_train(intel_dp);
+			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp, &DP,
 						training_pattern |
 						DP_LINK_SCRAMBLING_DISABLE);
@@ -3881,7 +3875,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 		/* Try 5 times, then try clock recovery if that fails */
 		if (tries > 5) {
 			intel_dp->train_set_valid = false;
-			intel_dp_start_link_train(intel_dp);
+			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp, &DP,
 						training_pattern |
 						DP_LINK_SCRAMBLING_DISABLE);
@@ -3914,6 +3908,13 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp)
 				DP_TRAINING_PATTERN_DISABLE);
 }
 
+void
+intel_dp_start_link_train(struct intel_dp *intel_dp)
+{
+	intel_dp_link_training_clock_recovery(intel_dp);
+	intel_dp_link_training_channel_equalization(intel_dp);
+}
+
 static void
 intel_dp_link_down(struct intel_dp *intel_dp)
 {
@@ -4382,7 +4383,6 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp)
 			    !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) {
 				DRM_DEBUG_KMS("channel EQ not ok, retraining\n");
 				intel_dp_start_link_train(intel_dp);
-				intel_dp_complete_link_train(intel_dp);
 				intel_dp_stop_link_train(intel_dp);
 			}
 
@@ -4473,7 +4473,6 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 		DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n",
 			      intel_encoder->base.name);
 		intel_dp_start_link_train(intel_dp);
-		intel_dp_complete_link_train(intel_dp);
 		intel_dp_stop_link_train(intel_dp);
 	}
 }
@@ -6000,7 +5999,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	}
 
 	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
-	intel_connector->panel.backlight_power = intel_edp_backlight_power;
+	intel_connector->panel.backlight.power = intel_edp_backlight_power;
 	intel_panel_setup_backlight(connector, pipe);
 
 	return true;
@@ -6169,10 +6168,8 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 		return;
 
 	intel_connector = intel_connector_alloc();
-	if (!intel_connector) {
-		kfree(intel_dig_port);
-		return;
-	}
+	if (!intel_connector)
+		goto err_connector_alloc;
 
 	intel_encoder = &intel_dig_port->base;
 	encoder = &intel_encoder->base;
@@ -6220,11 +6217,18 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 	intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
 	dev_priv->hotplug.irq_port[port] = intel_dig_port;
 
-	if (!intel_dp_init_connector(intel_dig_port, intel_connector)) {
+	if (!intel_dp_init_connector(intel_dig_port, intel_connector))
+		goto err_init_connector;
+
+	return;
+
+err_init_connector:
 	drm_encoder_cleanup(encoder);
-		kfree(intel_dig_port);
 	kfree(intel_connector);
-	}
+err_connector_alloc:
+	kfree(intel_dig_port);
+
+	return;
 }
 
 void intel_dp_mst_suspend(struct drm_device *dev)

drivers/gpu/drm/i915/intel_dp_mst.c

@@ -40,7 +40,7 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
 	struct drm_atomic_state *state;
 	int bpp, i;
 	int lane_count, slots;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
 	struct drm_connector *drm_connector;
 	struct intel_connector *connector, *found = NULL;
 	struct drm_connector_state *connector_state;
@@ -78,7 +78,7 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
 		return false;
 	}
 
-	mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->clock, bpp);
+	mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp);
 
 	pipe_config->pbn = mst_pbn;
 	slots = drm_dp_find_vcpi_slots(&intel_dp->mst_mgr, mst_pbn);
@@ -188,7 +188,6 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder)
 
 
 		intel_dp_start_link_train(intel_dp);
-		intel_dp_complete_link_train(intel_dp);
 		intel_dp_stop_link_train(intel_dp);
 	}
 

drivers/gpu/drm/i915/intel_drv.h

@@ -179,12 +179,22 @@ struct intel_panel {
 		bool active_low_pwm;
 
 		/* PWM chip */
+		bool util_pin_active_low;	/* bxt+ */
+		u8 controller;		/* bxt+ only */
 		struct pwm_device *pwm;
 
 		struct backlight_device *device;
-	} backlight;
 
-	void (*backlight_power)(struct intel_connector *, bool enable);
+		/* Connector and platform specific backlight functions */
+		int (*setup)(struct intel_connector *connector, enum pipe pipe);
+		uint32_t (*get)(struct intel_connector *connector);
+		void (*set)(struct intel_connector *connector, uint32_t level);
+		void (*disable)(struct intel_connector *connector);
+		void (*enable)(struct intel_connector *connector);
+		uint32_t (*hz_to_pwm)(struct intel_connector *connector,
+				      uint32_t hz);
+		void (*power)(struct intel_connector *, bool enable);
+	} backlight;
 };
 
 struct intel_connector {
@@ -458,6 +468,9 @@ struct intel_crtc_state {
 
 	/* w/a for waiting 2 vblanks during crtc enable */
 	enum pipe hsw_workaround_pipe;
+
+	/* IVB sprite scaling w/a (WaCxSRDisabledForSpriteScaling:ivb) */
+	bool disable_lp_wm;
 };
 
 struct vlv_wm_state {
@@ -683,7 +696,7 @@ struct intel_hdmi {
 				const void *frame, ssize_t len);
 	void (*set_infoframes)(struct drm_encoder *encoder,
 			       bool enable,
-			       struct drm_display_mode *adjusted_mode);
+			       const struct drm_display_mode *adjusted_mode);
 	bool (*infoframe_enabled)(struct drm_encoder *encoder);
 };
 
@@ -1191,7 +1204,6 @@ bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 void intel_dp_set_link_params(struct intel_dp *intel_dp,
 			      const struct intel_crtc_state *pipe_config);
 void intel_dp_start_link_train(struct intel_dp *intel_dp);
-void intel_dp_complete_link_train(struct intel_dp *intel_dp);
 void intel_dp_stop_link_train(struct intel_dp *intel_dp);
 void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 void intel_dp_encoder_destroy(struct drm_encoder *encoder);
@@ -1300,6 +1312,7 @@ int intel_connector_update_modes(struct drm_connector *connector,
 int intel_ddc_get_modes(struct drm_connector *c, struct i2c_adapter *adapter);
 void intel_attach_force_audio_property(struct drm_connector *connector);
 void intel_attach_broadcast_rgb_property(struct drm_connector *connector);
+void intel_attach_aspect_ratio_property(struct drm_connector *connector);
 
 
 /* intel_overlay.c */
@@ -1332,7 +1345,6 @@ int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe)
 void intel_panel_enable_backlight(struct intel_connector *connector);
 void intel_panel_disable_backlight(struct intel_connector *connector);
 void intel_panel_destroy_backlight(struct drm_connector *connector);
-void intel_panel_init_backlight_funcs(struct drm_device *dev);
 enum drm_connector_status intel_panel_detect(struct drm_device *dev);
 extern struct drm_display_mode *intel_find_panel_downclock(
 				struct drm_device *dev,
@@ -1387,12 +1399,6 @@ void intel_init_clock_gating(struct drm_device *dev);
 void intel_suspend_hw(struct drm_device *dev);
 int ilk_wm_max_level(const struct drm_device *dev);
 void intel_update_watermarks(struct drm_crtc *crtc);
-void intel_update_sprite_watermarks(struct drm_plane *plane,
-				    struct drm_crtc *crtc,
-				    uint32_t sprite_width,
-				    uint32_t sprite_height,
-				    int pixel_size,
-				    bool enabled, bool scaled);
 void intel_init_pm(struct drm_device *dev);
 void intel_pm_setup(struct drm_device *dev);
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv);

drivers/gpu/drm/i915/intel_dsi.c

@@ -282,58 +282,46 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_dsi_port_enable(struct intel_encoder *encoder)
+static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
-	u32 temp;
+	u32 val;
 
-	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
-		temp = I915_READ(VLV_CHICKEN_3);
-		temp &= ~PIXEL_OVERLAP_CNT_MASK |
-					intel_dsi->pixel_overlap <<
-					PIXEL_OVERLAP_CNT_SHIFT;
-		I915_WRITE(VLV_CHICKEN_3, temp);
-	}
+	DRM_DEBUG_KMS("\n");
 
+	/* Exit Low power state in 4 steps*/
 	for_each_dsi_port(port, intel_dsi->ports) {
-		temp = I915_READ(MIPI_PORT_CTRL(port));
-		temp &= ~LANE_CONFIGURATION_MASK;
-		temp &= ~DUAL_LINK_MODE_MASK;
 
-		if (intel_dsi->ports == ((1 << PORT_A) | (1 << PORT_C))) {
-			temp |= (intel_dsi->dual_link - 1)
-						<< DUAL_LINK_MODE_SHIFT;
-			temp |= intel_crtc->pipe ?
-					LANE_CONFIGURATION_DUAL_LINK_B :
-					LANE_CONFIGURATION_DUAL_LINK_A;
-		}
-		/* assert ip_tg_enable signal */
-		I915_WRITE(MIPI_PORT_CTRL(port), temp | DPI_ENABLE);
-		POSTING_READ(MIPI_PORT_CTRL(port));
-	}
-}
+		/* 1. Enable MIPI PHY transparent latch */
+		val = I915_READ(BXT_MIPI_PORT_CTRL(port));
+		I915_WRITE(BXT_MIPI_PORT_CTRL(port), val | LP_OUTPUT_HOLD);
+		usleep_range(2000, 2500);
 
-static void intel_dsi_port_disable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 temp;
+		/* 2. Enter ULPS */
+		val = I915_READ(MIPI_DEVICE_READY(port));
+		val &= ~ULPS_STATE_MASK;
+		val |= (ULPS_STATE_ENTER | DEVICE_READY);
+		I915_WRITE(MIPI_DEVICE_READY(port), val);
+		usleep_range(2, 3);
+
+		/* 3. Exit ULPS */
+		val = I915_READ(MIPI_DEVICE_READY(port));
+		val &= ~ULPS_STATE_MASK;
+		val |= (ULPS_STATE_EXIT | DEVICE_READY);
+		I915_WRITE(MIPI_DEVICE_READY(port), val);
+		usleep_range(1000, 1500);
 
-	for_each_dsi_port(port, intel_dsi->ports) {
-		/* de-assert ip_tg_enable signal */
-		temp = I915_READ(MIPI_PORT_CTRL(port));
-		I915_WRITE(MIPI_PORT_CTRL(port), temp & ~DPI_ENABLE);
-		POSTING_READ(MIPI_PORT_CTRL(port));
+		/* Clear ULPS and set device ready */
+		val = I915_READ(MIPI_DEVICE_READY(port));
+		val &= ~ULPS_STATE_MASK;
+		val |= DEVICE_READY;
+		I915_WRITE(MIPI_DEVICE_READY(port), val);
 	}
 }
 
-static void intel_dsi_device_ready(struct intel_encoder *encoder)
+static void vlv_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -372,6 +360,75 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 	}
 }
 
+static void intel_dsi_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+
+	if (IS_VALLEYVIEW(dev))
+		vlv_dsi_device_ready(encoder);
+	else if (IS_BROXTON(dev))
+		bxt_dsi_device_ready(encoder);
+}
+
+static void intel_dsi_port_enable(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 temp;
+	u32 port_ctrl;
+
+	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
+		temp = I915_READ(VLV_CHICKEN_3);
+		temp &= ~PIXEL_OVERLAP_CNT_MASK |
+					intel_dsi->pixel_overlap <<
+					PIXEL_OVERLAP_CNT_SHIFT;
+		I915_WRITE(VLV_CHICKEN_3, temp);
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		port_ctrl = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) :
+						MIPI_PORT_CTRL(port);
+
+		temp = I915_READ(port_ctrl);
+
+		temp &= ~LANE_CONFIGURATION_MASK;
+		temp &= ~DUAL_LINK_MODE_MASK;
+
+		if (intel_dsi->ports == ((1 << PORT_A) | (1 << PORT_C))) {
+			temp |= (intel_dsi->dual_link - 1)
+						<< DUAL_LINK_MODE_SHIFT;
+			temp |= intel_crtc->pipe ?
+					LANE_CONFIGURATION_DUAL_LINK_B :
+					LANE_CONFIGURATION_DUAL_LINK_A;
+		}
+		/* assert ip_tg_enable signal */
+		I915_WRITE(port_ctrl, temp | DPI_ENABLE);
+		POSTING_READ(port_ctrl);
+	}
+}
+
+static void intel_dsi_port_disable(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 temp;
+	u32 port_ctrl;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		/* de-assert ip_tg_enable signal */
+		port_ctrl = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) :
+						MIPI_PORT_CTRL(port);
+		temp = I915_READ(port_ctrl);
+		I915_WRITE(port_ctrl, temp & ~DPI_ENABLE);
+		POSTING_READ(port_ctrl);
+	}
+}
+
 static void intel_dsi_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
@@ -419,19 +476,24 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder)
 
 	msleep(intel_dsi->panel_on_delay);
 
-	/* Disable DPOunit clock gating, can stall pipe
-	 * and we need DPLL REFA always enabled */
+	if (IS_VALLEYVIEW(dev)) {
+		/*
+		 * Disable DPOunit clock gating, can stall pipe
+		 * and we need DPLL REFA always enabled
+		 */
 		tmp = I915_READ(DPLL(pipe));
 		tmp |= DPLL_REF_CLK_ENABLE_VLV;
 		I915_WRITE(DPLL(pipe), tmp);
 
 		/* update the hw state for DPLL */
-	intel_crtc->config->dpll_hw_state.dpll = DPLL_INTEGRATED_REF_CLK_VLV |
+		intel_crtc->config->dpll_hw_state.dpll =
+				DPLL_INTEGRATED_REF_CLK_VLV |
 					DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
 
 		tmp = I915_READ(DSPCLK_GATE_D);
 		tmp |= DPOUNIT_CLOCK_GATE_DISABLE;
 		I915_WRITE(DSPCLK_GATE_D, tmp);
+	}
 
 	/* put device in ready state */
 	intel_dsi_device_ready(encoder);
@@ -495,12 +557,7 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 		/* Panel commands can be sent when clock is in LP11 */
 		I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
 
-		temp = I915_READ(MIPI_CTRL(port));
-		temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
-		I915_WRITE(MIPI_CTRL(port), temp |
-			   intel_dsi->escape_clk_div <<
-			   ESCAPE_CLOCK_DIVIDER_SHIFT);
-
+		intel_dsi_reset_clocks(encoder, port);
 		I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 
 		temp = I915_READ(MIPI_DSI_FUNC_PRG(port));
@@ -519,10 +576,12 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 
 static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
+	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 	u32 val;
+	u32 port_ctrl = 0;
 
 	DRM_DEBUG_KMS("\n");
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -539,18 +598,22 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 							ULPS_STATE_ENTER);
 		usleep_range(2000, 2500);
 
+		if (IS_BROXTON(dev))
+			port_ctrl = BXT_MIPI_PORT_CTRL(port);
+		else if (IS_VALLEYVIEW(dev))
+			/* Common bit for both MIPI Port A & MIPI Port C */
+			port_ctrl = MIPI_PORT_CTRL(PORT_A);
+
 		/* Wait till Clock lanes are in LP-00 state for MIPI Port A
 		 * only. MIPI Port C has no similar bit for checking
 		 */
-		if (wait_for(((I915_READ(MIPI_PORT_CTRL(PORT_A)) & AFE_LATCHOUT)
+		if (wait_for(((I915_READ(port_ctrl) & AFE_LATCHOUT)
 						== 0x00000), 30))
 			DRM_ERROR("DSI LP not going Low\n");
 
-		/* Disable MIPI PHY transparent latch
-		 * Common bit for both MIPI Port A & MIPI Port C
-		 */
-		val = I915_READ(MIPI_PORT_CTRL(PORT_A));
-		I915_WRITE(MIPI_PORT_CTRL(PORT_A), val & ~LP_OUTPUT_HOLD);
+		/* Disable MIPI PHY transparent latch */
+		val = I915_READ(port_ctrl);
+		I915_WRITE(port_ctrl, val & ~LP_OUTPUT_HOLD);
 		usleep_range(1000, 1500);
 
 		I915_WRITE(MIPI_DEVICE_READY(port), 0x00);
@@ -593,7 +656,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
 	enum intel_display_power_domain power_domain;
-	u32 dpi_enabled, func;
+	u32 dpi_enabled, func, ctrl_reg;
 	enum port port;
 
 	DRM_DEBUG_KMS("\n");
@@ -605,8 +668,9 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	/* XXX: this only works for one DSI output */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		func = I915_READ(MIPI_DSI_FUNC_PRG(port));
-		dpi_enabled = I915_READ(MIPI_PORT_CTRL(port)) &
-							DPI_ENABLE;
+		ctrl_reg = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) :
+						MIPI_PORT_CTRL(port);
+		dpi_enabled = I915_READ(ctrl_reg) & DPI_ENABLE;
 
 		/* Due to some hardware limitations on BYT, MIPI Port C DPI
 		 * Enable bit does not get set. To check whether DSI Port C
@@ -631,7 +695,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 static void intel_dsi_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
-	u32 pclk;
+	u32 pclk = 0;
 	DRM_DEBUG_KMS("\n");
 
 	/*
@@ -640,7 +704,11 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 	 */
 	pipe_config->dpll_hw_state.dpll_md = 0;
 
+	if (IS_BROXTON(encoder->base.dev))
+		pclk = bxt_get_dsi_pclk(encoder, pipe_config->pipe_bpp);
+	else if (IS_VALLEYVIEW(encoder->base.dev))
 		pclk = vlv_get_dsi_pclk(encoder, pipe_config->pipe_bpp);
+
 	if (!pclk)
 		return;
 
@@ -698,7 +766,7 @@ static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count,
 }
 
 static void set_dsi_timings(struct drm_encoder *encoder,
-			    const struct drm_display_mode *mode)
+			    const struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -710,10 +778,10 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 
 	u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
 
-	hactive = mode->hdisplay;
-	hfp = mode->hsync_start - mode->hdisplay;
-	hsync = mode->hsync_end - mode->hsync_start;
-	hbp = mode->htotal - mode->hsync_end;
+	hactive = adjusted_mode->crtc_hdisplay;
+	hfp = adjusted_mode->crtc_hsync_start - adjusted_mode->crtc_hdisplay;
+	hsync = adjusted_mode->crtc_hsync_end - adjusted_mode->crtc_hsync_start;
+	hbp = adjusted_mode->crtc_htotal - adjusted_mode->crtc_hsync_end;
 
 	if (intel_dsi->dual_link) {
 		hactive /= 2;
@@ -724,9 +792,9 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 		hbp /= 2;
 	}
 
-	vfp = mode->vsync_start - mode->vdisplay;
-	vsync = mode->vsync_end - mode->vsync_start;
-	vbp = mode->vtotal - mode->vsync_end;
+	vfp = adjusted_mode->crtc_vsync_start - adjusted_mode->crtc_vdisplay;
+	vsync = adjusted_mode->crtc_vsync_end - adjusted_mode->crtc_vsync_start;
+	vbp = adjusted_mode->crtc_vtotal - adjusted_mode->crtc_vsync_end;
 
 	/* horizontal values are in terms of high speed byte clock */
 	hactive = txbyteclkhs(hactive, bpp, lane_count,
@@ -745,11 +813,11 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 			 * whereas these values should be based on resolution.
 			 */
 			I915_WRITE(BXT_MIPI_TRANS_HACTIVE(port),
-					mode->hdisplay);
+				   adjusted_mode->crtc_hdisplay);
 			I915_WRITE(BXT_MIPI_TRANS_VACTIVE(port),
-					mode->vdisplay);
+				   adjusted_mode->crtc_vdisplay);
 			I915_WRITE(BXT_MIPI_TRANS_VTOTAL(port),
-					mode->vtotal);
+				   adjusted_mode->crtc_vtotal);
 		}
 
 		I915_WRITE(MIPI_HACTIVE_AREA_COUNT(port), hactive);
@@ -774,8 +842,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	struct drm_display_mode *adjusted_mode =
-		&intel_crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
 	enum port port;
 	unsigned int bpp = intel_crtc->config->pipe_bpp;
 	u32 val, tmp;
@@ -783,7 +850,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 
 	DRM_DEBUG_KMS("pipe %c\n", pipe_name(intel_crtc->pipe));
 
-	mode_hdisplay = adjusted_mode->hdisplay;
+	mode_hdisplay = adjusted_mode->crtc_hdisplay;
 
 	if (intel_dsi->dual_link) {
 		mode_hdisplay /= 2;
@@ -833,7 +900,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 		I915_WRITE(MIPI_DPHY_PARAM(port), intel_dsi->dphy_reg);
 
 		I915_WRITE(MIPI_DPI_RESOLUTION(port),
-			adjusted_mode->vdisplay << VERTICAL_ADDRESS_SHIFT |
+			adjusted_mode->crtc_vdisplay << VERTICAL_ADDRESS_SHIFT |
 			mode_hdisplay << HORIZONTAL_ADDRESS_SHIFT);
 	}
 
@@ -879,13 +946,13 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 		if (is_vid_mode(intel_dsi) &&
 			intel_dsi->video_mode_format == VIDEO_MODE_BURST) {
 			I915_WRITE(MIPI_HS_TX_TIMEOUT(port),
-				txbyteclkhs(adjusted_mode->htotal, bpp,
+				txbyteclkhs(adjusted_mode->crtc_htotal, bpp,
 					    intel_dsi->lane_count,
 					    intel_dsi->burst_mode_ratio) + 1);
 		} else {
 			I915_WRITE(MIPI_HS_TX_TIMEOUT(port),
-				txbyteclkhs(adjusted_mode->vtotal *
-					adjusted_mode->htotal,
+				txbyteclkhs(adjusted_mode->crtc_vtotal *
+					    adjusted_mode->crtc_htotal,
 					    bpp, intel_dsi->lane_count,
 					    intel_dsi->burst_mode_ratio) + 1);
 		}

drivers/gpu/drm/i915/intel_dsi.h

@@ -127,6 +127,9 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 extern void intel_enable_dsi_pll(struct intel_encoder *encoder);
 extern void intel_disable_dsi_pll(struct intel_encoder *encoder);
 extern u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp);
+extern u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp);
+extern void intel_dsi_reset_clocks(struct intel_encoder *encoder,
+							enum port port);
 
 struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id);
 

drivers/gpu/drm/i915/intel_dsi_pll.c

@@ -384,6 +384,90 @@ u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
 	return pclk;
 }
 
+u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
+{
+	u32 pclk;
+	u32 dsi_clk;
+	u32 dsi_ratio;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+
+	/* Divide by zero */
+	if (!pipe_bpp) {
+		DRM_ERROR("Invalid BPP(0)\n");
+		return 0;
+	}
+
+	dsi_ratio = I915_READ(BXT_DSI_PLL_CTL) &
+				BXT_DSI_PLL_RATIO_MASK;
+
+	/* Invalid DSI ratio ? */
+	if (dsi_ratio < BXT_DSI_PLL_RATIO_MIN ||
+			dsi_ratio > BXT_DSI_PLL_RATIO_MAX) {
+		DRM_ERROR("Invalid DSI pll ratio(%u) programmed\n", dsi_ratio);
+		return 0;
+	}
+
+	dsi_clk = (dsi_ratio * BXT_REF_CLOCK_KHZ) / 2;
+
+	/* pixel_format and pipe_bpp should agree */
+	assert_bpp_mismatch(intel_dsi->pixel_format, pipe_bpp);
+
+	pclk = DIV_ROUND_CLOSEST(dsi_clk * intel_dsi->lane_count, pipe_bpp);
+
+	DRM_DEBUG_DRIVER("Calculated pclk=%u\n", pclk);
+	return pclk;
+}
+
+static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+{
+	u32 temp;
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+
+	temp = I915_READ(MIPI_CTRL(port));
+	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
+	I915_WRITE(MIPI_CTRL(port), temp |
+			intel_dsi->escape_clk_div <<
+			ESCAPE_CLOCK_DIVIDER_SHIFT);
+}
+
+/* Program BXT Mipi clocks and dividers */
+static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port)
+{
+	u32 tmp;
+	u32 divider;
+	u32 dsi_rate;
+	u32 pll_ratio;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Clear old configurations */
+	tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
+	tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port));
+	tmp &= ~(BXT_MIPI_RX_ESCLK_FIXDIV_MASK(port));
+	tmp &= ~(BXT_MIPI_ESCLK_VAR_DIV_MASK(port));
+	tmp &= ~(BXT_MIPI_DPHY_DIVIDER_MASK(port));
+
+	/* Get the current DSI rate(actual) */
+	pll_ratio = I915_READ(BXT_DSI_PLL_CTL) &
+				BXT_DSI_PLL_RATIO_MASK;
+	dsi_rate = (BXT_REF_CLOCK_KHZ * pll_ratio) / 2;
+
+	/* Max possible output of clock is 39.5 MHz, program value -1 */
+	divider = (dsi_rate / BXT_MAX_VAR_OUTPUT_KHZ) - 1;
+	tmp |= BXT_MIPI_ESCLK_VAR_DIV(port, divider);
+
+	/*
+	 * Tx escape clock must be as close to 20MHz possible, but should
+	 * not exceed it. Hence select divide by 2
+	 */
+	tmp |= BXT_MIPI_TX_ESCLK_8XDIV_BY2(port);
+
+	tmp |= BXT_MIPI_RX_ESCLK_8X_BY3(port);
+
+	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
+}
+
 static bool bxt_configure_dsi_pll(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
@@ -435,6 +519,8 @@ static bool bxt_configure_dsi_pll(struct intel_encoder *encoder)
 static void bxt_enable_dsi_pll(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
 	u32 val;
 
 	DRM_DEBUG_KMS("\n");
@@ -453,6 +539,10 @@ static void bxt_enable_dsi_pll(struct intel_encoder *encoder)
 		return;
 	}
 
+	/* Program TX, RX, Dphy clocks */
+	for_each_dsi_port(port, intel_dsi->ports)
+		bxt_dsi_program_clocks(encoder->base.dev, port);
+
 	/* Enable DSI PLL */
 	val = I915_READ(BXT_DSI_PLL_ENABLE);
 	val |= BXT_DSI_PLL_DO_ENABLE;
@@ -486,3 +576,29 @@ void intel_disable_dsi_pll(struct intel_encoder *encoder)
 	else if (IS_BROXTON(dev))
 		bxt_disable_dsi_pll(encoder);
 }
+
+static void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+{
+	u32 tmp;
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Clear old configurations */
+	tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
+	tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port));
+	tmp &= ~(BXT_MIPI_RX_ESCLK_FIXDIV_MASK(port));
+	tmp &= ~(BXT_MIPI_ESCLK_VAR_DIV_MASK(port));
+	tmp &= ~(BXT_MIPI_DPHY_DIVIDER_MASK(port));
+	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
+	I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
+}
+
+void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+{
+	struct drm_device *dev = encoder->base.dev;
+
+	if (IS_BROXTON(dev))
+		bxt_dsi_reset_clocks(encoder, port);
+	else if (IS_VALLEYVIEW(dev))
+		vlv_dsi_reset_clocks(encoder, port);
+}

drivers/gpu/drm/i915/intel_dvo.c

@@ -97,7 +97,8 @@ struct intel_dvo {
 
 	struct intel_dvo_device dev;
 
-	struct drm_display_mode *panel_fixed_mode;
+	struct intel_connector *attached_connector;
+
 	bool panel_wants_dither;
 };
 
@@ -201,6 +202,8 @@ intel_dvo_mode_valid(struct drm_connector *connector,
 		     struct drm_display_mode *mode)
 {
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+	const struct drm_display_mode *fixed_mode =
+		to_intel_connector(connector)->panel.fixed_mode;
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 	int target_clock = mode->clock;
 
@@ -209,13 +212,13 @@ intel_dvo_mode_valid(struct drm_connector *connector,
 
 	/* XXX: Validate clock range */
 
-	if (intel_dvo->panel_fixed_mode) {
-		if (mode->hdisplay > intel_dvo->panel_fixed_mode->hdisplay)
+	if (fixed_mode) {
+		if (mode->hdisplay > fixed_mode->hdisplay)
 			return MODE_PANEL;
-		if (mode->vdisplay > intel_dvo->panel_fixed_mode->vdisplay)
+		if (mode->vdisplay > fixed_mode->vdisplay)
 			return MODE_PANEL;
 
-		target_clock = intel_dvo->panel_fixed_mode->clock;
+		target_clock = fixed_mode->clock;
 	}
 
 	if (target_clock > max_dotclk)
@@ -228,6 +231,8 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config)
 {
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
+	const struct drm_display_mode *fixed_mode =
+		intel_dvo->attached_connector->panel.fixed_mode;
 	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
 
 	/* If we have timings from the BIOS for the panel, put them in
@@ -235,21 +240,8 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 	 * with the panel scaling set up to source from the H/VDisplay
 	 * of the original mode.
 	 */
-	if (intel_dvo->panel_fixed_mode != NULL) {
-#define C(x) adjusted_mode->x = intel_dvo->panel_fixed_mode->x
-		C(hdisplay);
-		C(hsync_start);
-		C(hsync_end);
-		C(htotal);
-		C(vdisplay);
-		C(vsync_start);
-		C(vsync_end);
-		C(vtotal);
-		C(clock);
-#undef C
-
-		drm_mode_set_crtcinfo(adjusted_mode, 0);
-	}
+	if (fixed_mode)
+		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
 
 	return true;
 }
@@ -259,7 +251,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	int pipe = crtc->pipe;
 	u32 dvo_val;
@@ -293,11 +285,11 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder)
 		dvo_val |= DVO_VSYNC_ACTIVE_HIGH;
 
 	/*I915_WRITE(DVOB_SRCDIM,
-	  (adjusted_mode->hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) |
-	  (adjusted_mode->VDisplay << DVO_SRCDIM_VERTICAL_SHIFT));*/
+	  (adjusted_mode->crtc_hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) |
+	  (adjusted_mode->crtc_vdisplay << DVO_SRCDIM_VERTICAL_SHIFT));*/
 	I915_WRITE(dvo_srcdim_reg,
-		   (adjusted_mode->hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) |
-		   (adjusted_mode->vdisplay << DVO_SRCDIM_VERTICAL_SHIFT));
+		   (adjusted_mode->crtc_hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) |
+		   (adjusted_mode->crtc_vdisplay << DVO_SRCDIM_VERTICAL_SHIFT));
 	/*I915_WRITE(DVOB, dvo_val);*/
 	I915_WRITE(dvo_reg, dvo_val);
 }
@@ -318,8 +310,9 @@ intel_dvo_detect(struct drm_connector *connector, bool force)
 
 static int intel_dvo_get_modes(struct drm_connector *connector)
 {
-	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	const struct drm_display_mode *fixed_mode =
+		to_intel_connector(connector)->panel.fixed_mode;
 
 	/* We should probably have an i2c driver get_modes function for those
 	 * devices which will have a fixed set of modes determined by the chip
@@ -331,9 +324,9 @@ static int intel_dvo_get_modes(struct drm_connector *connector)
 	if (!list_empty(&connector->probed_modes))
 		return 1;
 
-	if (intel_dvo->panel_fixed_mode != NULL) {
+	if (fixed_mode) {
 		struct drm_display_mode *mode;
-		mode = drm_mode_duplicate(connector->dev, intel_dvo->panel_fixed_mode);
+		mode = drm_mode_duplicate(connector->dev, fixed_mode);
 		if (mode) {
 			drm_mode_probed_add(connector, mode);
 			return 1;
@@ -346,6 +339,7 @@ static int intel_dvo_get_modes(struct drm_connector *connector)
 static void intel_dvo_destroy(struct drm_connector *connector)
 {
 	drm_connector_cleanup(connector);
+	intel_panel_fini(&to_intel_connector(connector)->panel);
 	kfree(connector);
 }
 
@@ -372,8 +366,6 @@ static void intel_dvo_enc_destroy(struct drm_encoder *encoder)
 	if (intel_dvo->dev.dev_ops->destroy)
 		intel_dvo->dev.dev_ops->destroy(&intel_dvo->dev);
 
-	kfree(intel_dvo->panel_fixed_mode);
-
 	intel_encoder_destroy(encoder);
 }
 
@@ -438,6 +430,8 @@ void intel_dvo_init(struct drm_device *dev)
 		return;
 	}
 
+	intel_dvo->attached_connector = intel_connector;
+
 	intel_encoder = &intel_dvo->base;
 	drm_encoder_init(dev, &intel_encoder->base,
 			 &intel_dvo_enc_funcs, encoder_type);
@@ -542,8 +536,9 @@ void intel_dvo_init(struct drm_device *dev)
 			 * headers, likely), so for now, just get the current
 			 * mode being output through DVO.
 			 */
-			intel_dvo->panel_fixed_mode =
-				intel_dvo_get_current_mode(connector);
+			intel_panel_init(&intel_connector->panel,
+					 intel_dvo_get_current_mode(connector),
+					 NULL);
 			intel_dvo->panel_wants_dither = true;
 		}
 

drivers/gpu/drm/i915/intel_fbc.c

@@ -41,6 +41,11 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
+static inline bool fbc_supported(struct drm_i915_private *dev_priv)
+{
+	return dev_priv->fbc.enable_fbc != NULL;
+}
+
 /*
  * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
  * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
@@ -439,7 +444,7 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv)
  */
 void intel_fbc_disable(struct drm_i915_private *dev_priv)
 {
-	if (!dev_priv->fbc.enable_fbc)
+	if (!fbc_supported(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->fbc.lock);
@@ -457,7 +462,7 @@ void intel_fbc_disable_crtc(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
 
-	if (!dev_priv->fbc.enable_fbc)
+	if (!fbc_supported(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->fbc.lock);
@@ -685,7 +690,7 @@ static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 
 void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 {
-	if (!dev_priv->fbc.enable_fbc)
+	if (!fbc_supported(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->fbc.lock);
@@ -693,16 +698,61 @@ void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->fbc.lock);
 }
 
-static int intel_fbc_setup_cfb(struct drm_i915_private *dev_priv, int size,
-			       int fb_cpp)
+/*
+ * For SKL+, the plane source size used by the hardware is based on the value we
+ * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value
+ * we wrote to PIPESRC.
+ */
+static void intel_fbc_get_plane_source_size(struct intel_crtc *crtc,
+					    int *width, int *height)
 {
+	struct intel_plane_state *plane_state =
+			to_intel_plane_state(crtc->base.primary->state);
+	int w, h;
+
+	if (intel_rotation_90_or_270(plane_state->base.rotation)) {
+		w = drm_rect_height(&plane_state->src) >> 16;
+		h = drm_rect_width(&plane_state->src) >> 16;
+	} else {
+		w = drm_rect_width(&plane_state->src) >> 16;
+		h = drm_rect_height(&plane_state->src) >> 16;
+	}
+
+	if (width)
+		*width = w;
+	if (height)
+		*height = h;
+}
+
+static int intel_fbc_calculate_cfb_size(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_framebuffer *fb = crtc->base.primary->fb;
+	int lines;
+
+	intel_fbc_get_plane_source_size(crtc, NULL, &lines);
+	if (INTEL_INFO(dev_priv)->gen >= 7)
+		lines = min(lines, 2048);
+
+	return lines * fb->pitches[0];
+}
+
+static int intel_fbc_setup_cfb(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_framebuffer *fb = crtc->base.primary->fb;
+	int size, cpp;
+
+	size = intel_fbc_calculate_cfb_size(crtc);
+	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+
 	if (size <= dev_priv->fbc.uncompressed_size)
 		return 0;
 
 	/* Release any current block */
 	__intel_fbc_cleanup_cfb(dev_priv);
 
-	return intel_fbc_alloc_cfb(dev_priv, size, fb_cpp);
+	return intel_fbc_alloc_cfb(dev_priv, size, cpp);
 }
 
 static bool stride_is_valid(struct drm_i915_private *dev_priv,
@@ -749,6 +799,35 @@ static bool pixel_format_is_valid(struct drm_framebuffer *fb)
 	}
 }
 
+/*
+ * For some reason, the hardware tracking starts looking at whatever we
+ * programmed as the display plane base address register. It does not look at
+ * the X and Y offset registers. That's why we look at the crtc->adjusted{x,y}
+ * variables instead of just looking at the pipe/plane size.
+ */
+static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	unsigned int effective_w, effective_h, max_w, max_h;
+
+	if (INTEL_INFO(dev_priv)->gen >= 8 || IS_HASWELL(dev_priv)) {
+		max_w = 4096;
+		max_h = 4096;
+	} else if (IS_G4X(dev_priv) || INTEL_INFO(dev_priv)->gen >= 5) {
+		max_w = 4096;
+		max_h = 2048;
+	} else {
+		max_w = 2048;
+		max_h = 1536;
+	}
+
+	intel_fbc_get_plane_source_size(crtc, &effective_w, &effective_h);
+	effective_w += crtc->adjusted_x;
+	effective_h += crtc->adjusted_y;
+
+	return effective_w <= max_w && effective_h <= max_h;
+}
+
 /**
  * __intel_fbc_update - enable/disable FBC as needed, unlocked
  * @dev_priv: i915 device instance
@@ -775,7 +854,6 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv)
 	struct drm_framebuffer *fb;
 	struct drm_i915_gem_object *obj;
 	const struct drm_display_mode *adjusted_mode;
-	unsigned int max_width, max_height;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock));
 
@@ -824,21 +902,11 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv)
 		goto out_disable;
 	}
 
-	if (INTEL_INFO(dev_priv)->gen >= 8 || IS_HASWELL(dev_priv)) {
-		max_width = 4096;
-		max_height = 4096;
-	} else if (IS_G4X(dev_priv) || INTEL_INFO(dev_priv)->gen >= 5) {
-		max_width = 4096;
-		max_height = 2048;
-	} else {
-		max_width = 2048;
-		max_height = 1536;
-	}
-	if (intel_crtc->config->pipe_src_w > max_width ||
-	    intel_crtc->config->pipe_src_h > max_height) {
+	if (!intel_fbc_hw_tracking_covers_screen(intel_crtc)) {
 		set_no_fbc_reason(dev_priv, FBC_MODE_TOO_LARGE);
 		goto out_disable;
 	}
+
 	if ((INTEL_INFO(dev_priv)->gen < 4 || HAS_DDI(dev_priv)) &&
 	    intel_crtc->plane != PLANE_A) {
 		set_no_fbc_reason(dev_priv, FBC_BAD_PLANE);
@@ -883,8 +951,7 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv)
 		goto out_disable;
 	}
 
-	if (intel_fbc_setup_cfb(dev_priv, obj->base.size,
-				drm_format_plane_cpp(fb->pixel_format, 0))) {
+	if (intel_fbc_setup_cfb(intel_crtc)) {
 		set_no_fbc_reason(dev_priv, FBC_STOLEN_TOO_SMALL);
 		goto out_disable;
 	}
@@ -948,7 +1015,7 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv)
  */
 void intel_fbc_update(struct drm_i915_private *dev_priv)
 {
-	if (!dev_priv->fbc.enable_fbc)
+	if (!fbc_supported(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->fbc.lock);
@@ -962,7 +1029,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 {
 	unsigned int fbc_bits;
 
-	if (!dev_priv->fbc.enable_fbc)
+	if (!fbc_supported(dev_priv))
 		return;
 
 	if (origin == ORIGIN_GTT)
@@ -989,7 +1056,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 void intel_fbc_flush(struct drm_i915_private *dev_priv,
 		     unsigned int frontbuffer_bits, enum fb_op_origin origin)
 {
-	if (!dev_priv->fbc.enable_fbc)
+	if (!fbc_supported(dev_priv))
 		return;
 
 	if (origin == ORIGIN_GTT)

drivers/gpu/drm/i915/intel_fbdev.c

@@ -121,8 +121,9 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 		container_of(helper, struct intel_fbdev, helper);
 	struct drm_framebuffer *fb;
 	struct drm_device *dev = helper->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_mode_fb_cmd2 mode_cmd = {};
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_gem_object *obj = NULL;
 	int size, ret;
 
 	/* we don't do packed 24bpp */
@@ -139,6 +140,11 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 
 	size = mode_cmd.pitches[0] * mode_cmd.height;
 	size = PAGE_ALIGN(size);
+
+	/* If the FB is too big, just don't use it since fbdev is not very
+	 * important and we should probably use that space with FBC or other
+	 * features. */
+	if (size * 2 < dev_priv->gtt.stolen_usable_size)
 		obj = i915_gem_object_create_stolen(dev, size);
 	if (obj == NULL)
 		obj = i915_gem_alloc_object(dev, size);

drivers/gpu/drm/i915/intel_guc.h

@@ -110,6 +110,8 @@ extern void intel_guc_ucode_init(struct drm_device *dev);
 extern int intel_guc_ucode_load(struct drm_device *dev);
 extern void intel_guc_ucode_fini(struct drm_device *dev);
 extern const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status);
+extern int intel_guc_suspend(struct drm_device *dev);
+extern int intel_guc_resume(struct drm_device *dev);
 
 /* i915_guc_submission.c */
 int i915_guc_submission_init(struct drm_device *dev);

drivers/gpu/drm/i915/intel_guc_fwif.h

@@ -218,12 +218,23 @@ struct guc_context_desc {
 	u64 desc_private;
 } __packed;
 
+#define GUC_FORCEWAKE_RENDER	(1 << 0)
+#define GUC_FORCEWAKE_MEDIA	(1 << 1)
+
+#define GUC_POWER_UNSPECIFIED	0
+#define GUC_POWER_D0		1
+#define GUC_POWER_D1		2
+#define GUC_POWER_D2		3
+#define GUC_POWER_D3		4
+
 /* This Action will be programmed in C180 - SOFT_SCRATCH_O_REG */
 enum host2guc_action {
 	HOST2GUC_ACTION_DEFAULT = 0x0,
 	HOST2GUC_ACTION_SAMPLE_FORCEWAKE = 0x6,
 	HOST2GUC_ACTION_ALLOCATE_DOORBELL = 0x10,
 	HOST2GUC_ACTION_DEALLOCATE_DOORBELL = 0x20,
+	HOST2GUC_ACTION_ENTER_S_STATE = 0x501,
+	HOST2GUC_ACTION_EXIT_S_STATE = 0x502,
 	HOST2GUC_ACTION_SLPC_REQUEST = 0x3003,
 	HOST2GUC_ACTION_LIMIT
 };

drivers/gpu/drm/i915/intel_guc_loader.c

@@ -90,9 +90,6 @@ static void direct_interrupts_to_host(struct drm_i915_private *dev_priv)
 	for_each_ring(ring, dev_priv, i)
 		I915_WRITE(RING_MODE_GEN7(ring), irqs);
 
-	/* tell DE to send nothing to GuC */
-	I915_WRITE(DE_GUCRMR, ~0);
-
 	/* route all GT interrupts to the host */
 	I915_WRITE(GUC_BCS_RCS_IER, 0);
 	I915_WRITE(GUC_VCS2_VCS1_IER, 0);
@@ -110,13 +107,6 @@ static void direct_interrupts_to_guc(struct drm_i915_private *dev_priv)
 	for_each_ring(ring, dev_priv, i)
 		I915_WRITE(RING_MODE_GEN7(ring), irqs);
 
-	/* tell DE to send (all) flip_done to GuC */
-	irqs = DERRMR_PIPEA_PRI_FLIP_DONE | DERRMR_PIPEA_SPR_FLIP_DONE |
-	       DERRMR_PIPEB_PRI_FLIP_DONE | DERRMR_PIPEB_SPR_FLIP_DONE |
-	       DERRMR_PIPEC_PRI_FLIP_DONE | DERRMR_PIPEC_SPR_FLIP_DONE;
-	/* Unmasked bits will cause GuC response message to be sent */
-	I915_WRITE(DE_GUCRMR, ~irqs);
-
 	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
 	irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
 	       GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
@@ -209,9 +199,10 @@ static inline bool guc_ucode_response(struct drm_i915_private *dev_priv,
 				      u32 *status)
 {
 	u32 val = I915_READ(GUC_STATUS);
+	u32 uk_val = val & GS_UKERNEL_MASK;
 	*status = val;
-	return ((val & GS_UKERNEL_MASK) == GS_UKERNEL_READY ||
-		(val & GS_UKERNEL_MASK) == GS_UKERNEL_LAPIC_DONE);
+	return (uk_val == GS_UKERNEL_READY ||
+		((val & GS_MIA_CORE_STATE) && uk_val == GS_UKERNEL_LAPIC_DONE));
 }
 
 /*
@@ -257,7 +248,7 @@ static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
 	/* Copy RSA signature from the fw image to HW for verification */
 	sg_pcopy_to_buffer(sg->sgl, sg->nents, rsa, UOS_RSA_SIG_SIZE, offset);
 	for (i = 0; i < UOS_RSA_SIG_SIZE / sizeof(u32); i++)
-		I915_WRITE(UOS_RSA_SCRATCH_0 + i * sizeof(u32), rsa[i]);
+		I915_WRITE(UOS_RSA_SCRATCH(i), rsa[i]);
 
 	/* Set the source address for the new blob */
 	offset = i915_gem_obj_ggtt_offset(fw_obj);
@@ -392,7 +383,6 @@ int intel_guc_ucode_load(struct drm_device *dev)
 		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
 
 	direct_interrupts_to_host(dev_priv);
-	i915_guc_submission_disable(dev);
 
 	if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_NONE)
 		return 0;
@@ -442,6 +432,9 @@ int intel_guc_ucode_load(struct drm_device *dev)
 		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
 
 	if (i915.enable_guc_submission) {
+		/* The execbuf_client will be recreated. Release it first. */
+		i915_guc_submission_disable(dev);
+
 		err = i915_guc_submission_enable(dev);
 		if (err)
 			goto fail;

drivers/gpu/drm/i915/intel_lrc.c

@@ -904,21 +904,6 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
 		return -EINVAL;
 	}
 
-	if (args->num_cliprects != 0) {
-		DRM_DEBUG("clip rectangles are only valid on pre-gen5\n");
-		return -EINVAL;
-	} else {
-		if (args->DR4 == 0xffffffff) {
-			DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
-			args->DR4 = 0;
-		}
-
-		if (args->DR1 || args->DR4 || args->cliprects_ptr) {
-			DRM_DEBUG("0 cliprects but dirt in cliprects fields\n");
-			return -EINVAL;
-		}
-	}
-
 	if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
 		DRM_DEBUG("sol reset is gen7 only\n");
 		return -EINVAL;

drivers/gpu/drm/i915/intel_lvds.c

@@ -139,8 +139,7 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	const struct drm_display_mode *adjusted_mode =
-		&crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	int pipe = crtc->pipe;
 	u32 temp;
 

drivers/gpu/drm/i915/intel_modes.c

@@ -126,3 +126,12 @@ intel_attach_broadcast_rgb_property(struct drm_connector *connector)
 
 	drm_object_attach_property(&connector->base, prop, 0);
 }
+
+void
+intel_attach_aspect_ratio_property(struct drm_connector *connector)
+{
+	if (!drm_mode_create_aspect_ratio_property(connector->dev))
+		drm_object_attach_property(&connector->base,
+			connector->dev->mode_config.aspect_ratio_property,
+			DRM_MODE_PICTURE_ASPECT_NONE);
+}

drivers/gpu/drm/i915/intel_opregion.c

@@ -341,7 +341,11 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 	if (!HAS_DDI(dev))
 		return 0;
 
+	if (intel_encoder->type == INTEL_OUTPUT_DSI)
+		port = 0;
+	else
 		port = intel_ddi_get_encoder_port(intel_encoder);
+
 	if (port == PORT_E)  {
 		port = 0;
 	} else {
@@ -363,6 +367,7 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 		type = DISPLAY_TYPE_EXTERNAL_FLAT_PANEL;
 		break;
 	case INTEL_OUTPUT_EDP:
+	case INTEL_OUTPUT_DSI:
 		type = DISPLAY_TYPE_INTERNAL_FLAT_PANEL;
 		break;
 	default:

include/uapi/drm/i915_drm.h

@@ -690,7 +690,8 @@ struct drm_i915_gem_exec_object2 {
 #define EXEC_OBJECT_NEEDS_FENCE (1<<0)
 #define EXEC_OBJECT_NEEDS_GTT	(1<<1)
 #define EXEC_OBJECT_WRITE	(1<<2)
-#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_WRITE<<1)
+#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_SUPPORTS_48B_ADDRESS<<1)
 	__u64 flags;
 
 	__u64 rsvd1;