Merge branch 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel into drm-next

Daniel writes:
As promised a stash of (mostly) fixes. Two pieces of non-fixes included:
- A notch more gtt refactoring from Ben, beating to death with igt in our
  nightly testing.
- Support for display display-less server chips (again from Ben). New hw
  support which is only likely to break itself ;-)

Otherwise just tons of fixes:
- hpd irq storm mitigation from Egbert Eich. Your -next tree already has
  the infrastructure, this here just supplies the logic.
- sdvo hw state check fix from Egbert Eich
- fb cb tune settings for the pch pll clocks on cpt/ppt
- "Bring a bigger gun" coherence workaround for multi-threade, mulit-core
  & thrashing tiled gtt cpu access from Chris.
- Update haswell mPHY code.
- l3$ caching for context objects on ivb/hsw (Chris).
- dp aux refclock fix for haswell (Jani)
- moar overclocking fixes for snb/ivb (Ben)
- ecobits ppgtt pte caching control fixes from Ville
- fence stride check fixes and limit improvements (Ville)
- fix up crtc force restoring, potentially resulting in tons of hw state
  check WARNs
- OOPS fix for NULL derefencing of fb pointers when force-restoring a crtc
  when other crtcs are disabled and the force-restored crtc is _not_ the
  first one.
- Fix pfit disabling on gen2/3.
- Haswell ring freq scaling fixes (Chris).
- backlight init/teardown fix (failed eDP init killed the lvds backlight)
  from Jani
- cpt/ppt fdi polarity fixes from Paulo (should help a lot of the FDI link
  train failures).
- And a bunch of smaller things all over.
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel: (56 commits)
  drm/i915: fix bpc vs. bpp confusion in intel_crtc_compute_config
  drm/i915: move cpu_transcoder to the pipe configuration
  drm/i915: preserve the PBC bits of TRANS_CHICKEN2
  drm/i915: set CPT FDI RX polarity bits based on VBT
  drm/i915: Add Reenable Timer to turn Hotplug Detection back on (v4)
  drm/i915: Disable HPD interrupt on pin when irq storm is detected (v3)
  drm/i915: Mask out the HPD irq bits before setting them individually.
  drm/i915: (re)init HPD interrupt storm statistics
  drm/i915: Add HPD IRQ storm detection (v5)
  drm/i915: WARN when LPT-LP is not paired with ULT CPU
  drm/i915: don't intel_crt_init on any ULT machines
  drm/i915: remove comment about IVB link training from intel_pm.c
  drm/i915: VLV doesn't have LLC
  drm/i915: Scale ring, rather than ia, frequency on Haswell
  drm/i915: shorten debugfs output simple attributes
  drm/i915: Fixup pfit disabling for gen2/3
  drm/i915: Fixup Oops in the pipe config computation
  drm/i915: ensure single initialization and cleanup of backlight device
  drm/i915: don't touch the PF regs if the power well is down
  drm/i915: add intel_using_power_well
  ...

drivers/gpu/drm/i915/i915_debugfs.c

@@ -901,7 +901,7 @@ i915_next_seqno_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_next_seqno_fops,
 			i915_next_seqno_get, i915_next_seqno_set,
-			"next_seqno :  0x%llx\n");
+			"0x%llx\n");
 
 static int i915_rstdby_delays(struct seq_file *m, void *unused)
 {
@@ -1006,6 +1006,9 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		max_freq = rp_state_cap & 0xff;
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
 			   max_freq * GT_FREQUENCY_MULTIPLIER);
+
+		seq_printf(m, "Max overclocked frequency: %dMHz\n",
+			   dev_priv->rps.hw_max * GT_FREQUENCY_MULTIPLIER);
 	} else {
 		seq_printf(m, "no P-state info available\n");
 	}
@@ -1354,7 +1357,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	if (ret)
 		return ret;
 
-	seq_printf(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\n");
+	seq_printf(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
 
 	for (gpu_freq = dev_priv->rps.min_delay;
 	     gpu_freq <= dev_priv->rps.max_delay;
@@ -1363,7 +1366,10 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 		sandybridge_pcode_read(dev_priv,
 				       GEN6_PCODE_READ_MIN_FREQ_TABLE,
 				       &ia_freq);
-		seq_printf(m, "%d\t\t%d\n", gpu_freq * GT_FREQUENCY_MULTIPLIER, ia_freq * 100);
+		seq_printf(m, "%d\t\t%d\t\t\t\t%d\n",
+			   gpu_freq * GT_FREQUENCY_MULTIPLIER,
+			   ((ia_freq >> 0) & 0xff) * 100,
+			   ((ia_freq >> 8) & 0xff) * 100);
 	}
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -1687,7 +1693,7 @@ i915_wedged_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops,
 			i915_wedged_get, i915_wedged_set,
-			"wedged :  %llu\n");
+			"%llu\n");
 
 static int
 i915_ring_stop_get(void *data, u64 *val)
@@ -1841,7 +1847,7 @@ i915_max_freq_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_max_freq_fops,
 			i915_max_freq_get, i915_max_freq_set,
-			"max freq: %llu\n");
+			"%llu\n");
 
 static int
 i915_min_freq_get(void *data, u64 *val)
@@ -1892,7 +1898,7 @@ i915_min_freq_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_min_freq_fops,
 			i915_min_freq_get, i915_min_freq_set,
-			"min freq: %llu\n");
+			"%llu\n");
 
 static int
 i915_cache_sharing_get(void *data, u64 *val)

drivers/gpu/drm/i915/i915_dma.c

@@ -1322,6 +1322,10 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	/* Always safe in the mode setting case. */
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
 	dev->vblank_disable_allowed = 1;
+	if (INTEL_INFO(dev)->num_pipes == 0) {
+		dev_priv->mm.suspended = 0;
+		return 0;
+	}
 
 	ret = intel_fbdev_init(dev);
 	if (ret)
@@ -1514,6 +1518,28 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto free_priv;
 	}
 
+	mmio_bar = IS_GEN2(dev) ? 1 : 0;
+	/* Before gen4, the registers and the GTT are behind different BARs.
+	 * However, from gen4 onwards, the registers and the GTT are shared
+	 * in the same BAR, so we want to restrict this ioremap from
+	 * clobbering the GTT which we want ioremap_wc instead. Fortunately,
+	 * the register BAR remains the same size for all the earlier
+	 * generations up to Ironlake.
+	 */
+	if (info->gen < 5)
+		mmio_size = 512*1024;
+	else
+		mmio_size = 2*1024*1024;
+
+	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, mmio_size);
+	if (!dev_priv->regs) {
+		DRM_ERROR("failed to map registers\n");
+		ret = -EIO;
+		goto put_bridge;
+	}
+
+	intel_early_sanitize_regs(dev);
+
 	ret = i915_gem_gtt_init(dev);
 	if (ret)
 		goto put_bridge;
@@ -1538,28 +1564,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
 		dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32));
 
-	mmio_bar = IS_GEN2(dev) ? 1 : 0;
-	/* Before gen4, the registers and the GTT are behind different BARs.
-	 * However, from gen4 onwards, the registers and the GTT are shared
-	 * in the same BAR, so we want to restrict this ioremap from
-	 * clobbering the GTT which we want ioremap_wc instead. Fortunately,
-	 * the register BAR remains the same size for all the earlier
-	 * generations up to Ironlake.
-	 */
-	if (info->gen < 5)
-		mmio_size = 512*1024;
-	else
-		mmio_size = 2*1024*1024;
-
-	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, mmio_size);
-	if (!dev_priv->regs) {
-		DRM_ERROR("failed to map registers\n");
-		ret = -EIO;
-		goto put_gmch;
-	}
-
-	intel_early_sanitize_regs(dev);
-
 	aperture_size = dev_priv->gtt.mappable_end;
 
 	dev_priv->gtt.mappable =
@@ -1634,9 +1638,11 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (IS_VALLEYVIEW(dev))
 		dev_priv->num_plane = 2;
 
+	if (INTEL_INFO(dev)->num_pipes) {
 		ret = drm_vblank_init(dev, INTEL_INFO(dev)->num_pipes);
 		if (ret)
 			goto out_gem_unload;
+	}
 
 	/* Start out suspended */
 	dev_priv->mm.suspended = 1;
@@ -1651,9 +1657,11 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	i915_setup_sysfs(dev);
 
+	if (INTEL_INFO(dev)->num_pipes) {
 		/* Must be done after probing outputs */
 		intel_opregion_init(dev);
 		acpi_video_register();
+	}
 
 	if (IS_GEN5(dev))
 		intel_gpu_ips_init(dev_priv);
@@ -1678,10 +1686,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		dev_priv->mm.gtt_mtrr = -1;
 	}
 	io_mapping_free(dev_priv->gtt.mappable);
+	dev_priv->gtt.gtt_remove(dev);
 out_rmmap:
 	pci_iounmap(dev->pdev, dev_priv->regs);
-put_gmch:
-	dev_priv->gtt.gtt_remove(dev);
 put_bridge:
 	pci_dev_put(dev_priv->bridge_dev);
 free_priv:

drivers/gpu/drm/i915/i915_drv.c

@@ -140,6 +140,16 @@ extern int intel_agp_enabled;
 	.subdevice = PCI_ANY_ID,		\
 	.driver_data = (unsigned long) info }
 
+#define INTEL_QUANTA_VGA_DEVICE(info) {		\
+	.class = PCI_BASE_CLASS_DISPLAY << 16,	\
+	.class_mask = 0xff0000,			\
+	.vendor = 0x8086,			\
+	.device = 0x16a,			\
+	.subvendor = 0x152d,			\
+	.subdevice = 0x8990,			\
+	.driver_data = (unsigned long) info }
+
+
 static const struct intel_device_info intel_i830_info = {
 	.gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2,
 	.has_overlay = 1, .overlay_needs_physical = 1,
@@ -272,12 +282,19 @@ static const struct intel_device_info intel_ivybridge_m_info = {
 	.is_mobile = 1,
 };
 
+static const struct intel_device_info intel_ivybridge_q_info = {
+	GEN7_FEATURES,
+	.is_ivybridge = 1,
+	.num_pipes = 0, /* legal, last one wins */
+};
+
 static const struct intel_device_info intel_valleyview_m_info = {
 	GEN7_FEATURES,
 	.is_mobile = 1,
 	.num_pipes = 2,
 	.is_valleyview = 1,
 	.display_mmio_offset = VLV_DISPLAY_BASE,
+	.has_llc = 0, /* legal, last one wins */
 };
 
 static const struct intel_device_info intel_valleyview_d_info = {
@@ -285,6 +302,7 @@ static const struct intel_device_info intel_valleyview_d_info = {
 	.num_pipes = 2,
 	.is_valleyview = 1,
 	.display_mmio_offset = VLV_DISPLAY_BASE,
+	.has_llc = 0, /* legal, last one wins */
 };
 
 static const struct intel_device_info intel_haswell_d_info = {
@@ -342,6 +360,7 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x0152, &intel_ivybridge_d_info), /* GT1 desktop */
 	INTEL_VGA_DEVICE(0x0162, &intel_ivybridge_d_info), /* GT2 desktop */
 	INTEL_VGA_DEVICE(0x015a, &intel_ivybridge_d_info), /* GT1 server */
+	INTEL_QUANTA_VGA_DEVICE(&intel_ivybridge_q_info), /* Quanta transcode */
 	INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */
 	INTEL_VGA_DEVICE(0x0402, &intel_haswell_d_info), /* GT1 desktop */
 	INTEL_VGA_DEVICE(0x0412, &intel_haswell_d_info), /* GT2 desktop */
@@ -397,6 +416,15 @@ void intel_detect_pch(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct pci_dev *pch;
 
+	/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
+	 * (which really amounts to a PCH but no South Display).
+	 */
+	if (INTEL_INFO(dev)->num_pipes == 0) {
+		dev_priv->pch_type = PCH_NOP;
+		dev_priv->num_pch_pll = 0;
+		return;
+	}
+
 	/*
 	 * The reason to probe ISA bridge instead of Dev31:Fun0 is to
 	 * make graphics device passthrough work easy for VMM, that only
@@ -431,11 +459,13 @@ void intel_detect_pch(struct drm_device *dev)
 				dev_priv->num_pch_pll = 0;
 				DRM_DEBUG_KMS("Found LynxPoint PCH\n");
 				WARN_ON(!IS_HASWELL(dev));
+				WARN_ON(IS_ULT(dev));
 			} else if (id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_LPT;
 				dev_priv->num_pch_pll = 0;
 				DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
 				WARN_ON(!IS_HASWELL(dev));
+				WARN_ON(!IS_ULT(dev));
 			}
 			BUG_ON(dev_priv->num_pch_pll > I915_NUM_PLLS);
 		}
@@ -901,7 +931,11 @@ int i915_reset(struct drm_device *dev)
 			ring->init(ring);
 
 		i915_gem_context_init(dev);
-		i915_gem_init_ppgtt(dev);
+		if (dev_priv->mm.aliasing_ppgtt) {
+			ret = dev_priv->mm.aliasing_ppgtt->enable(dev);
+			if (ret)
+				i915_gem_cleanup_aliasing_ppgtt(dev);
+		}
 
 		/*
 		 * It would make sense to re-init all the other hw state, at

drivers/gpu/drm/i915/i915_drv.h

@@ -195,9 +195,9 @@ struct drm_i915_master_private {
 	struct _drm_i915_sarea *sarea_priv;
 };
 #define I915_FENCE_REG_NONE -1
-#define I915_MAX_NUM_FENCES 16
-/* 16 fences + sign bit for FENCE_REG_NONE */
-#define I915_MAX_NUM_FENCE_BITS 5
+#define I915_MAX_NUM_FENCES 32
+/* 32 fences + sign bit for FENCE_REG_NONE */
+#define I915_MAX_NUM_FENCE_BITS 6
 
 struct drm_i915_fence_reg {
 	struct list_head lru_list;
@@ -449,6 +449,7 @@ struct i915_hw_ppgtt {
 			       struct sg_table *st,
 			       unsigned int pg_start,
 			       enum i915_cache_level cache_level);
+	int (*enable)(struct drm_device *dev);
 	void (*cleanup)(struct i915_hw_ppgtt *ppgtt);
 };
 
@@ -479,6 +480,7 @@ enum intel_pch {
 	PCH_IBX,	/* Ibexpeak PCH */
 	PCH_CPT,	/* Cougarpoint PCH */
 	PCH_LPT,	/* Lynxpoint PCH */
+	PCH_NOP,
 };
 
 enum intel_sbi_destination {
@@ -666,6 +668,7 @@ struct intel_gen6_power_mgmt {
 	u8 cur_delay;
 	u8 min_delay;
 	u8 max_delay;
+	u8 hw_max;
 
 	struct delayed_work delayed_resume_work;
 
@@ -929,6 +932,16 @@ typedef struct drm_i915_private {
 
 	struct work_struct hotplug_work;
 	bool enable_hotplug_processing;
+	struct {
+		unsigned long hpd_last_jiffies;
+		int hpd_cnt;
+		enum {
+			HPD_ENABLED = 0,
+			HPD_DISABLED = 1,
+			HPD_MARK_DISABLED = 2
+		} hpd_mark;
+	} hpd_stats[HPD_NUM_PINS];
+	struct timer_list hotplug_reenable_timer;
 
 	int num_pch_pll;
 	int num_plane;
@@ -963,6 +976,7 @@ typedef struct drm_i915_private {
 	unsigned int int_crt_support:1;
 	unsigned int lvds_use_ssc:1;
 	unsigned int display_clock_mode:1;
+	unsigned int fdi_rx_polarity_inverted:1;
 	int lvds_ssc_freq;
 	unsigned int bios_lvds_val; /* initial [PCH_]LVDS reg val in VBIOS */
 	struct {
@@ -1373,6 +1387,7 @@ struct drm_i915_file_private {
 #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT)
 #define HAS_PCH_CPT(dev) (INTEL_PCH_TYPE(dev) == PCH_CPT)
 #define HAS_PCH_IBX(dev) (INTEL_PCH_TYPE(dev) == PCH_IBX)
+#define HAS_PCH_NOP(dev) (INTEL_PCH_TYPE(dev) == PCH_NOP)
 #define HAS_PCH_SPLIT(dev) (INTEL_PCH_TYPE(dev) != PCH_NONE)
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
@@ -1640,7 +1655,6 @@ int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
 void i915_gem_l3_remap(struct drm_device *dev);
 void i915_gem_init_swizzling(struct drm_device *dev);
-void i915_gem_init_ppgtt(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
 int __must_check i915_gem_idle(struct drm_device *dev);

drivers/gpu/drm/i915/i915_gem.c

@@ -2683,17 +2683,35 @@ static inline int fence_number(struct drm_i915_private *dev_priv,
 	return fence - dev_priv->fence_regs;
 }
 
+static void i915_gem_write_fence__ipi(void *data)
+{
+	wbinvd();
+}
+
 static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
-	int reg = fence_number(dev_priv, fence);
-
-	i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL);
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int fence_reg = fence_number(dev_priv, fence);
+
+	/* In order to fully serialize access to the fenced region and
+	 * the update to the fence register we need to take extreme
+	 * measures on SNB+. In theory, the write to the fence register
+	 * flushes all memory transactions before, and coupled with the
+	 * mb() placed around the register write we serialise all memory
+	 * operations with respect to the changes in the tiler. Yet, on
+	 * SNB+ we need to take a step further and emit an explicit wbinvd()
+	 * on each processor in order to manually flush all memory
+	 * transactions before updating the fence register.
+	 */
+	if (HAS_LLC(obj->base.dev))
+		on_each_cpu(i915_gem_write_fence__ipi, NULL, 1);
+	i915_gem_write_fence(dev, fence_reg, enable ? obj : NULL);
 
 	if (enable) {
-		obj->fence_reg = reg;
+		obj->fence_reg = fence_reg;
 		fence->obj = obj;
 		list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list);
 	} else {
@@ -3992,6 +4010,12 @@ i915_gem_init_hw(struct drm_device *dev)
 	if (IS_HASWELL(dev) && (I915_READ(0x120010) == 1))
 		I915_WRITE(0x9008, I915_READ(0x9008) | 0xf0000);
 
+	if (HAS_PCH_NOP(dev)) {
+		u32 temp = I915_READ(GEN7_MSG_CTL);
+		temp &= ~(WAIT_FOR_PCH_FLR_ACK | WAIT_FOR_PCH_RESET_ACK);
+		I915_WRITE(GEN7_MSG_CTL, temp);
+	}
+
 	i915_gem_l3_remap(dev);
 
 	i915_gem_init_swizzling(dev);
@@ -4005,7 +4029,13 @@ i915_gem_init_hw(struct drm_device *dev)
 	 * contexts before PPGTT.
 	 */
 	i915_gem_context_init(dev);
-	i915_gem_init_ppgtt(dev);
+	if (dev_priv->mm.aliasing_ppgtt) {
+		ret = dev_priv->mm.aliasing_ppgtt->enable(dev);
+		if (ret) {
+			i915_gem_cleanup_aliasing_ppgtt(dev);
+			DRM_INFO("PPGTT enable failed. This is not fatal, but unexpected\n");
+		}
+	}
 
 	return 0;
 }
@@ -4160,7 +4190,9 @@ i915_gem_load(struct drm_device *dev)
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		dev_priv->fence_reg_start = 3;
 
-	if (INTEL_INFO(dev)->gen >= 4 || IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
+	if (INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev))
+		dev_priv->num_fence_regs = 32;
+	else if (INTEL_INFO(dev)->gen >= 4 || IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
 		dev_priv->num_fence_regs = 16;
 	else
 		dev_priv->num_fence_regs = 8;

drivers/gpu/drm/i915/i915_gem_context.c

@@ -152,6 +152,13 @@ create_hw_context(struct drm_device *dev,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (INTEL_INFO(dev)->gen >= 7) {
+		ret = i915_gem_object_set_cache_level(ctx->obj,
+						      I915_CACHE_LLC_MLC);
+		if (ret)
+			goto err_out;
+	}
+
 	/* The ring associated with the context object is handled by the normal
 	 * object tracking code. We give an initial ring value simple to pass an
 	 * assertion in the context switch code.

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -28,7 +28,7 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-typedef uint32_t gtt_pte_t;
+typedef uint32_t gen6_gtt_pte_t;
 
 /* PPGTT stuff */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
@@ -44,11 +44,11 @@ typedef uint32_t gtt_pte_t;
 #define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
 #define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
 
-static inline gtt_pte_t gen6_pte_encode(struct drm_device *dev,
+static inline gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
 					     dma_addr_t addr,
 					     enum i915_cache_level level)
 {
-	gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -72,17 +72,84 @@ static inline gtt_pte_t gen6_pte_encode(struct drm_device *dev,
 		BUG();
 	}
 
-
 	return pte;
 }
 
+static int gen6_ppgtt_enable(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t pd_offset;
+	struct intel_ring_buffer *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	gen6_gtt_pte_t __iomem *pd_addr;
+	uint32_t pd_entry;
+	int i;
+
+	pd_addr = (gen6_gtt_pte_t __iomem*)dev_priv->gtt.gsm +
+		ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+
+		pt_addr = ppgtt->pt_dma_addr[i];
+		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
+		pd_entry |= GEN6_PDE_VALID;
+
+		writel(pd_entry, pd_addr + i);
+	}
+	readl(pd_addr);
+
+	pd_offset = ppgtt->pd_offset;
+	pd_offset /= 64; /* in cachelines, */
+	pd_offset <<= 16;
+
+	if (INTEL_INFO(dev)->gen == 6) {
+		uint32_t ecochk, gab_ctl, ecobits;
+
+		ecobits = I915_READ(GAC_ECO_BITS);
+		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_SNB_BIT |
+					 ECOBITS_PPGTT_CACHE64B);
+
+		gab_ctl = I915_READ(GAB_CTL);
+		I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);
+
+		ecochk = I915_READ(GAM_ECOCHK);
+		I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT |
+				       ECOCHK_PPGTT_CACHE64B);
+		I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+	} else if (INTEL_INFO(dev)->gen >= 7) {
+		uint32_t ecochk, ecobits;
+
+		ecobits = I915_READ(GAC_ECO_BITS);
+		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
+
+		ecochk = I915_READ(GAM_ECOCHK);
+		if (IS_HASWELL(dev)) {
+			ecochk |= ECOCHK_PPGTT_WB_HSW;
+		} else {
+			ecochk |= ECOCHK_PPGTT_LLC_IVB;
+			ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
+		}
+		I915_WRITE(GAM_ECOCHK, ecochk);
+		/* GFX_MODE is per-ring on gen7+ */
+	}
+
+	for_each_ring(ring, dev_priv, i) {
+		if (INTEL_INFO(dev)->gen >= 7)
+			I915_WRITE(RING_MODE_GEN7(ring),
+				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+
+		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
+		I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset);
+	}
+	return 0;
+}
+
 /* PPGTT support for Sandybdrige/Gen6 and later */
 static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
 				   unsigned first_entry,
 				   unsigned num_entries)
 {
-	gtt_pte_t *pt_vaddr;
-	gtt_pte_t scratch_pte;
+	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
@@ -114,7 +181,7 @@ static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt,
 				      unsigned first_entry,
 				      enum i915_cache_level cache_level)
 {
-	gtt_pte_t *pt_vaddr;
+	gen6_gtt_pte_t *pt_vaddr;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	struct sg_page_iter sg_iter;
@@ -170,6 +237,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		gtt_total_entries(dev_priv->gtt) - I915_PPGTT_PD_ENTRIES;
 
 	ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES;
+	ppgtt->enable = gen6_ppgtt_enable;
 	ppgtt->clear_range = gen6_ppgtt_clear_range;
 	ppgtt->insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->cleanup = gen6_ppgtt_cleanup;
@@ -203,12 +271,10 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		ppgtt->pt_dma_addr[i] = pt_addr;
 	}
 
-	ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma;
-
 	ppgtt->clear_range(ppgtt, 0,
 			   ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES);
 
-	ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(gtt_pte_t);
+	ppgtt->pd_offset = first_pd_entry_in_global_pt * sizeof(gen6_gtt_pte_t);
 
 	return 0;
 
@@ -240,8 +306,13 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 		return -ENOMEM;
 
 	ppgtt->dev = dev;
+	ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma;
 
+	if (INTEL_INFO(dev)->gen < 8)
 		ret = gen6_ppgtt_init(ppgtt);
+	else
+		BUG();
+
 	if (ret)
 		kfree(ppgtt);
 	else
@@ -259,6 +330,7 @@ void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
 		return;
 
 	ppgtt->cleanup(ppgtt);
+	dev_priv->mm.aliasing_ppgtt = NULL;
 }
 
 void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
@@ -278,64 +350,6 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			   obj->base.size >> PAGE_SHIFT);
 }
 
-void i915_gem_init_ppgtt(struct drm_device *dev)
-{
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	uint32_t pd_offset;
-	struct intel_ring_buffer *ring;
-	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
-	gtt_pte_t __iomem *pd_addr;
-	uint32_t pd_entry;
-	int i;
-
-	if (!dev_priv->mm.aliasing_ppgtt)
-		return;
-
-
-	pd_addr = (gtt_pte_t __iomem*)dev_priv->gtt.gsm + ppgtt->pd_offset/sizeof(gtt_pte_t);
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		dma_addr_t pt_addr;
-
-		pt_addr = ppgtt->pt_dma_addr[i];
-		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
-		pd_entry |= GEN6_PDE_VALID;
-
-		writel(pd_entry, pd_addr + i);
-	}
-	readl(pd_addr);
-
-	pd_offset = ppgtt->pd_offset;
-	pd_offset /= 64; /* in cachelines, */
-	pd_offset <<= 16;
-
-	if (INTEL_INFO(dev)->gen == 6) {
-		uint32_t ecochk, gab_ctl, ecobits;
-
-		ecobits = I915_READ(GAC_ECO_BITS);
-		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
-
-		gab_ctl = I915_READ(GAB_CTL);
-		I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);
-
-		ecochk = I915_READ(GAM_ECOCHK);
-		I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT |
-				       ECOCHK_PPGTT_CACHE64B);
-		I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-	} else if (INTEL_INFO(dev)->gen >= 7) {
-		I915_WRITE(GAM_ECOCHK, ECOCHK_PPGTT_CACHE64B);
-		/* GFX_MODE is per-ring on gen7+ */
-	}
-
-	for_each_ring(ring, dev_priv, i) {
-		if (INTEL_INFO(dev)->gen >= 7)
-			I915_WRITE(RING_MODE_GEN7(ring),
-				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-
-		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
-		I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset);
-	}
-}
-
 extern int intel_iommu_gfx_mapped;
 /* Certain Gen5 chipsets require require idling the GPU before
  * unmapping anything from the GTT when VT-d is enabled.
@@ -416,8 +430,8 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev,
 				     enum i915_cache_level level)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	gtt_pte_t __iomem *gtt_entries =
-		(gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
+	gen6_gtt_pte_t __iomem *gtt_entries =
+		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
 	struct sg_page_iter sg_iter;
 	dma_addr_t addr;
@@ -451,8 +465,8 @@ static void gen6_ggtt_clear_range(struct drm_device *dev,
 				  unsigned int num_entries)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	gtt_pte_t scratch_pte;
-	gtt_pte_t __iomem *gtt_base = (gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
+	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
+		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
 	int i;
 
@@ -626,9 +640,12 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
 
 	if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) {
 		int ret;
+
+		if (INTEL_INFO(dev)->gen <= 7) {
 			/* PPGTT pdes are stolen from global gtt ptes, so shrink the
 			 * aperture accordingly when using aliasing ppgtt. */
 			gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
+		}
 
 		i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
 
@@ -736,10 +753,12 @@ static int gen6_gmch_probe(struct drm_device *dev,
 	else
 		*stolen = gen6_get_stolen_size(snb_gmch_ctl);
 
-	*gtt_total = (gtt_size / sizeof(gtt_pte_t)) << PAGE_SHIFT;
+	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
+
+	/* For Modern GENs the PTEs and register space are split in the BAR */
+	gtt_bus_addr = pci_resource_start(dev->pdev, 0) +
+		(pci_resource_len(dev->pdev, 0) / 2);
 
-	/* For GEN6+ the PTEs for the ggtt live at 2MB + BAR0 */
-	gtt_bus_addr = pci_resource_start(dev->pdev, 0) + (2<<20);
 	dev_priv->gtt.gsm = ioremap_wc(gtt_bus_addr, gtt_size);
 	if (!dev_priv->gtt.gsm) {
 		DRM_ERROR("Failed to map the gtt page table\n");
@@ -796,7 +815,6 @@ int i915_gem_gtt_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_gtt *gtt = &dev_priv->gtt;
-	unsigned long gtt_size;
 	int ret;
 
 	if (INTEL_INFO(dev)->gen <= 5) {
@@ -814,8 +832,6 @@ int i915_gem_gtt_init(struct drm_device *dev)
 	if (ret)
 		return ret;
 
-	gtt_size = (dev_priv->gtt.total >> PAGE_SHIFT) * sizeof(gtt_pte_t);
-
 	/* GMADR is the PCI mmio aperture into the global GTT. */
 	DRM_INFO("Memory usable by graphics device = %zdM\n",
 		 dev_priv->gtt.total >> 20);

drivers/gpu/drm/i915/i915_gem_tiling.c

@@ -217,9 +217,12 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 		tile_width = 512;
 
 	/* check maximum stride & object size */
-	if (INTEL_INFO(dev)->gen >= 4) {
-		/* i965 stores the end address of the gtt mapping in the fence
+	/* i965+ stores the end address of the gtt mapping in the fence
 	 * reg, so dont bother to check the size */
+	if (INTEL_INFO(dev)->gen >= 7) {
+		if (stride / 128 > GEN7_FENCE_MAX_PITCH_VAL)
+			return false;
+	} else if (INTEL_INFO(dev)->gen >= 4) {
 		if (stride / 128 > I965_FENCE_MAX_PITCH_VAL)
 			return false;
 	} else {
@@ -235,6 +238,9 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 		}
 	}
 
+	if (stride < tile_width)
+		return false;
+
 	/* 965+ just needs multiples of tile width */
 	if (INTEL_INFO(dev)->gen >= 4) {
 		if (stride & (tile_width - 1))
@@ -243,9 +249,6 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 	}
 
 	/* Pre-965 needs power of two tile widths */
-	if (stride < tile_width)
-		return false;
-
 	if (stride & (stride - 1))
 		return false;
 

drivers/gpu/drm/i915/i915_reg.h

@@ -125,8 +125,14 @@
 #define   HSW_ECOCHK_ARB_PRIO_SOL	(1<<6)
 #define   ECOCHK_PPGTT_CACHE64B		(0x3<<3)
 #define   ECOCHK_PPGTT_CACHE4B		(0x0<<3)
+#define   ECOCHK_PPGTT_GFDT_IVB		(0x1<<4)
+#define   ECOCHK_PPGTT_LLC_IVB		(0x1<<3)
+#define   ECOCHK_PPGTT_UC_HSW		(0x1<<3)
+#define   ECOCHK_PPGTT_WT_HSW		(0x2<<3)
+#define   ECOCHK_PPGTT_WB_HSW		(0x3<<3)
 
 #define GAC_ECO_BITS			0x14090
+#define   ECOBITS_SNB_BIT		(1<<13)
 #define   ECOBITS_PPGTT_CACHE64B	(3<<8)
 #define   ECOBITS_PPGTT_CACHE4B		(0<<8)
 
@@ -424,6 +430,7 @@
 
 #define FENCE_REG_SANDYBRIDGE_0		0x100000
 #define   SANDYBRIDGE_FENCE_PITCH_SHIFT	32
+#define   GEN7_FENCE_MAX_PITCH_VAL	0x0800
 
 /* control register for cpu gtt access */
 #define TILECTL				0x101000
@@ -1203,6 +1210,9 @@
 
 #define MCHBAR_MIRROR_BASE_SNB	0x140000
 
+/* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */
+#define DCLK 0x5e04
+
 /** 915-945 and GM965 MCH register controlling DRAM channel access */
 #define DCC			0x10200
 #define DCC_ADDRESSING_MODE_SINGLE_CHANNEL		(0 << 0)
@@ -3568,6 +3578,9 @@
 #define DISP_ARB_CTL	0x45000
 #define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
 #define  DISP_FBC_WM_DIS		(1<<15)
+#define GEN7_MSG_CTL	0x45010
+#define  WAIT_FOR_PCH_RESET_ACK		(1<<1)
+#define  WAIT_FOR_PCH_FLR_ACK		(1<<0)
 
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		0x7010
@@ -3947,7 +3960,10 @@
 #define _TRANSB_CHICKEN2	 0xf1064
 #define TRANS_CHICKEN2(pipe) _PIPE(pipe, _TRANSA_CHICKEN2, _TRANSB_CHICKEN2)
 #define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1<<31)
-
+#define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1<<29)
+#define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3<<27)
+#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1<<26)
+#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1<<25)
 
 #define SOUTH_CHICKEN1		0xc2000
 #define  FDIA_PHASE_SYNC_SHIFT_OVR	19
@@ -4380,6 +4396,7 @@
 #define   GEN6_DECODE_RC6_VID(vids)		(((vids) * 5) + 245)
 #define GEN6_PCODE_DATA				0x138128
 #define   GEN6_PCODE_FREQ_IA_RATIO_SHIFT	8
+#define   GEN6_PCODE_FREQ_RING_RATIO_SHIFT	16
 
 #define VLV_IOSF_DOORBELL_REQ			0x182100
 #define   IOSF_DEVFN_SHIFT			24

drivers/gpu/drm/i915/i915_sysfs.c

@@ -239,7 +239,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev);
 	struct drm_device *dev = minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val, rp_state_cap, hw_max, hw_min;
+	u32 val, rp_state_cap, hw_max, hw_min, non_oc_max;
 	ssize_t ret;
 
 	ret = kstrtou32(buf, 0, &val);
@@ -251,7 +251,8 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-	hw_max = (rp_state_cap & 0xff);
+	hw_max = dev_priv->rps.hw_max;
+	non_oc_max = (rp_state_cap & 0xff);
 	hw_min = ((rp_state_cap & 0xff0000) >> 16);
 
 	if (val < hw_min || val > hw_max || val < dev_priv->rps.min_delay) {
@@ -259,6 +260,10 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 		return -EINVAL;
 	}
 
+	if (val > non_oc_max)
+		DRM_DEBUG("User requested overclocking to %d\n",
+			  val * GT_FREQUENCY_MULTIPLIER);
+
 	if (dev_priv->rps.cur_delay > val)
 		gen6_set_rps(dev_priv->dev, val);
 
@@ -302,7 +307,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-	hw_max = (rp_state_cap & 0xff);
+	hw_max = dev_priv->rps.hw_max;
 	hw_min = ((rp_state_cap & 0xff0000) >> 16);
 
 	if (val < hw_min || val > hw_max || val > dev_priv->rps.max_delay) {

drivers/gpu/drm/i915/intel_bios.c

@@ -351,12 +351,14 @@ parse_general_features(struct drm_i915_private *dev_priv,
 		dev_priv->lvds_ssc_freq =
 			intel_bios_ssc_frequency(dev, general->ssc_freq);
 		dev_priv->display_clock_mode = general->display_clock_mode;
-		DRM_DEBUG_KMS("BDB_GENERAL_FEATURES int_tv_support %d int_crt_support %d lvds_use_ssc %d lvds_ssc_freq %d display_clock_mode %d\n",
+		dev_priv->fdi_rx_polarity_inverted = general->fdi_rx_polarity_inverted;
+		DRM_DEBUG_KMS("BDB_GENERAL_FEATURES int_tv_support %d int_crt_support %d lvds_use_ssc %d lvds_ssc_freq %d display_clock_mode %d fdi_rx_polarity_inverted %d\n",
 			      dev_priv->int_tv_support,
 			      dev_priv->int_crt_support,
 			      dev_priv->lvds_use_ssc,
 			      dev_priv->lvds_ssc_freq,
-			      dev_priv->display_clock_mode);
+			      dev_priv->display_clock_mode,
+			      dev_priv->fdi_rx_polarity_inverted);
 	}
 }
 
@@ -692,6 +694,9 @@ intel_parse_bios(struct drm_device *dev)
 	struct bdb_header *bdb = NULL;
 	u8 __iomem *bios = NULL;
 
+	if (HAS_PCH_NOP(dev))
+		return -ENODEV;
+
 	init_vbt_defaults(dev_priv);
 
 	/* XXX Should this validation be moved to intel_opregion.c? */

drivers/gpu/drm/i915/intel_bios.h

@@ -127,7 +127,9 @@ struct bdb_general_features {
         /* bits 3 */
 	u8 disable_smooth_vision:1;
 	u8 single_dvi:1;
-	u8 rsvd9:6; /* finish byte */
+	u8 rsvd9:1;
+	u8 fdi_rx_polarity_inverted:1;
+	u8 rsvd10:4; /* finish byte */
 
         /* bits 4 */
 	u8 legacy_monitor_detect;

drivers/gpu/drm/i915/intel_crt.c

@@ -787,10 +787,8 @@ void intel_crt_init(struct drm_device *dev)
 
 	drm_sysfs_connector_add(connector);
 
-	if (I915_HAS_HOTPLUG(dev))
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
-	else
-		connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+	if (!I915_HAS_HOTPLUG(dev))
+		intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
 	/*
 	 * Configure the automatic hotplug detection stuff

drivers/gpu/drm/i915/intel_ddi.c

@@ -924,7 +924,7 @@ void intel_ddi_set_pipe_settings(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
-	enum transcoder cpu_transcoder = intel_crtc->cpu_transcoder;
+	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
 	int type = intel_encoder->type;
 	uint32_t temp;
 
@@ -958,7 +958,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc)
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
 	enum pipe pipe = intel_crtc->pipe;
-	enum transcoder cpu_transcoder = intel_crtc->cpu_transcoder;
+	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	int type = intel_encoder->type;
 	uint32_t temp;
@@ -1223,7 +1223,7 @@ void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
 	struct drm_i915_private *dev_priv = crtc->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->cpu_transcoder;
+	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
 
 	if (cpu_transcoder != TRANSCODER_EDP)
 		I915_WRITE(TRANS_CLK_SEL(cpu_transcoder),
@@ -1233,7 +1233,7 @@ void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
 void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc)
 {
 	struct drm_i915_private *dev_priv = intel_crtc->base.dev->dev_private;
-	enum transcoder cpu_transcoder = intel_crtc->cpu_transcoder;
+	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
 
 	if (cpu_transcoder != TRANSCODER_EDP)
 		I915_WRITE(TRANS_CLK_SEL(cpu_transcoder),

drivers/gpu/drm/i915/intel_dp.c

@@ -353,10 +353,14 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 			aux_clock_divider = 200; /* SNB & IVB eDP input clock at 400Mhz */
 		else
 			aux_clock_divider = 225; /* eDP input clock at 450Mhz */
-	} else if (HAS_PCH_SPLIT(dev))
+	} else if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
+		/* Workaround for non-ULT HSW */
+		aux_clock_divider = 74;
+	} else if (HAS_PCH_SPLIT(dev)) {
 		aux_clock_divider = DIV_ROUND_UP(intel_pch_rawclk(dev), 2);
-	else
+	} else {
 		aux_clock_divider = intel_hrawclk(dev) / 2;
+	}
 
 	if (IS_GEN6(dev))
 		precharge = 3;
@@ -2470,17 +2474,14 @@ intel_dp_set_property(struct drm_connector *connector,
 static void
 intel_dp_destroy(struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 
 	if (!IS_ERR_OR_NULL(intel_connector->edid))
 		kfree(intel_connector->edid);
 
-	if (is_edp(intel_dp)) {
-		intel_panel_destroy_backlight(dev);
+	if (is_edp(intel_dp))
 		intel_panel_fini(&intel_connector->panel);
-	}
 
 	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
@@ -2789,7 +2790,6 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
 	drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
 
-	connector->polled = DRM_CONNECTOR_POLL_HPD;
 	connector->interlace_allowed = true;
 	connector->doublescan_allowed = 0;
 

drivers/gpu/drm/i915/intel_drv.h

@@ -171,6 +171,10 @@ struct intel_connector {
 
 	/* Cached EDID for eDP and LVDS. May hold ERR_PTR for invalid EDID. */
 	struct edid *edid;
+
+	/* since POLL and HPD connectors may use the same HPD line keep the native
+	   state of connector->polled in case hotplug storm detection changes it */
+	u8 polled;
 };
 
 struct intel_crtc_config {
@@ -184,6 +188,10 @@ struct intel_crtc_config {
 	 * between pch encoders and cpu encoders. */
 	bool has_pch_encoder;
 
+	/* CPU Transcoder for the pipe. Currently this can only differ from the
+	 * pipe on Haswell (where we have a special eDP transcoder). */
+	enum transcoder cpu_transcoder;
+
 	/*
 	 * Use reduced/limited/broadcast rbg range, compressing from the full
 	 * range fed into the crtcs.
@@ -222,7 +230,6 @@ struct intel_crtc {
 	struct drm_crtc base;
 	enum pipe pipe;
 	enum plane plane;
-	enum transcoder cpu_transcoder;
 	u8 lut_r[256], lut_g[256], lut_b[256];
 	/*
 	 * Whether the crtc and the connected output pipeline is active. Implies
@@ -693,6 +700,7 @@ extern void intel_update_fbc(struct drm_device *dev);
 extern void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
 extern void intel_gpu_ips_teardown(void);
 
+extern bool intel_using_power_well(struct drm_device *dev);
 extern void intel_init_power_well(struct drm_device *dev);
 extern void intel_set_power_well(struct drm_device *dev, bool enable);
 extern void intel_enable_gt_powersave(struct drm_device *dev);

drivers/gpu/drm/i915/intel_fb.c

@@ -283,6 +283,9 @@ void intel_fb_restore_mode(struct drm_device *dev)
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_plane *plane;
 
+	if (INTEL_INFO(dev)->num_pipes == 0)
+		return;
+
 	drm_modeset_lock_all(dev);
 
 	ret = drm_fb_helper_restore_fbdev_mode(&dev_priv->fbdev->helper);

drivers/gpu/drm/i915/intel_hdmi.c

@@ -294,8 +294,8 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(intel_crtc->cpu_transcoder);
-	u32 data_reg = hsw_infoframe_data_reg(frame, intel_crtc->cpu_transcoder);
+	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(intel_crtc->config.cpu_transcoder);
+	u32 data_reg = hsw_infoframe_data_reg(frame, intel_crtc->config.cpu_transcoder);
 	unsigned int i, len = DIP_HEADER_SIZE + frame->len;
 	u32 val = I915_READ(ctl_reg);
 
@@ -570,7 +570,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
-	u32 reg = HSW_TVIDEO_DIP_CTL(intel_crtc->cpu_transcoder);
+	u32 reg = HSW_TVIDEO_DIP_CTL(intel_crtc->config.cpu_transcoder);
 	u32 val = I915_READ(reg);
 
 	assert_hdmi_port_disabled(intel_hdmi);
@@ -998,7 +998,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 			   DRM_MODE_CONNECTOR_HDMIA);
 	drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs);
 
-	connector->polled = DRM_CONNECTOR_POLL_HPD;
 	connector->interlace_allowed = 1;
 	connector->doublescan_allowed = 0;
 

drivers/gpu/drm/i915/intel_i2c.c

@@ -522,7 +522,9 @@ int intel_setup_gmbus(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret, i;
 
-	if (HAS_PCH_SPLIT(dev))
+	if (HAS_PCH_NOP(dev))
+		return 0;
+	else if (HAS_PCH_SPLIT(dev))
 		dev_priv->gpio_mmio_base = PCH_GPIOA - GPIOA;
 	else if (IS_VALLEYVIEW(dev))
 		dev_priv->gpio_mmio_base = VLV_DISPLAY_BASE;

drivers/gpu/drm/i915/intel_lvds.c

@@ -631,7 +631,6 @@ static void intel_lvds_destroy(struct drm_connector *connector)
 	if (!IS_ERR_OR_NULL(lvds_connector->base.edid))
 		kfree(lvds_connector->base.edid);
 
-	intel_panel_destroy_backlight(connector->dev);
 	intel_panel_fini(&lvds_connector->base.panel);
 
 	drm_sysfs_connector_remove(connector);

drivers/gpu/drm/i915/intel_panel.c

@@ -428,6 +428,9 @@ int intel_panel_setup_backlight(struct drm_connector *connector)
 
 	intel_panel_init_backlight(dev);
 
+	if (WARN_ON(dev_priv->backlight.device))
+		return -ENODEV;
+
 	memset(&props, 0, sizeof(props));
 	props.type = BACKLIGHT_RAW;
 	props.brightness = dev_priv->backlight.level;
@@ -453,8 +456,10 @@ int intel_panel_setup_backlight(struct drm_connector *connector)
 void intel_panel_destroy_backlight(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	if (dev_priv->backlight.device)
+	if (dev_priv->backlight.device) {
 		backlight_device_unregister(dev_priv->backlight.device);
+		dev_priv->backlight.device = NULL;
+	}
 }
 #else
 int intel_panel_setup_backlight(struct drm_connector *connector)

drivers/gpu/drm/i915/intel_pm.c

@@ -2558,8 +2558,8 @@ static void gen6_enable_rps(struct drm_device *dev)
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
 	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 
-	/* In units of 100MHz */
-	dev_priv->rps.max_delay = rp_state_cap & 0xff;
+	/* In units of 50MHz */
+	dev_priv->rps.hw_max = dev_priv->rps.max_delay = rp_state_cap & 0xff;
 	dev_priv->rps.min_delay = (rp_state_cap & 0xff0000) >> 16;
 	dev_priv->rps.cur_delay = 0;
 
@@ -2643,10 +2643,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 		pcu_mbox = 0;
 		ret = sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS, &pcu_mbox);
 		if (!ret && (pcu_mbox & (1<<31))) { /* OC supported */
-			DRM_DEBUG_DRIVER("overclocking supported, adjusting frequency max from %dMHz to %dMHz\n",
+			DRM_DEBUG_DRIVER("Overclocking supported. Max: %dMHz, Overclock max: %dMHz\n",
 					 (dev_priv->rps.max_delay & 0xff) * 50,
 					 (pcu_mbox & 0xff) * 50);
-			dev_priv->rps.max_delay = pcu_mbox & 0xff;
+			dev_priv->rps.hw_max = pcu_mbox & 0xff;
 		}
 	} else {
 		DRM_DEBUG_DRIVER("Failed to set the min frequency\n");
@@ -2684,8 +2684,8 @@ static void gen6_update_ring_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
-	int gpu_freq;
-	unsigned int ia_freq, max_ia_freq;
+	unsigned int gpu_freq;
+	unsigned int max_ia_freq, min_ring_freq;
 	int scaling_factor = 180;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -2701,6 +2701,10 @@ static void gen6_update_ring_freq(struct drm_device *dev)
 	/* Convert from kHz to MHz */
 	max_ia_freq /= 1000;
 
+	min_ring_freq = I915_READ(MCHBAR_MIRROR_BASE_SNB + DCLK);
+	/* convert DDR frequency from units of 133.3MHz to bandwidth */
+	min_ring_freq = (2 * 4 * min_ring_freq + 2) / 3;
+
 	/*
 	 * For each potential GPU frequency, load a ring frequency we'd like
 	 * to use for memory access.  We do this by specifying the IA frequency
@@ -2709,21 +2713,32 @@ static void gen6_update_ring_freq(struct drm_device *dev)
 	for (gpu_freq = dev_priv->rps.max_delay; gpu_freq >= dev_priv->rps.min_delay;
 	     gpu_freq--) {
 		int diff = dev_priv->rps.max_delay - gpu_freq;
+		unsigned int ia_freq = 0, ring_freq = 0;
 
-		/*
-		 * For GPU frequencies less than 750MHz, just use the lowest
-		 * ring freq.
+		if (IS_HASWELL(dev)) {
+			ring_freq = (gpu_freq * 5 + 3) / 4;
+			ring_freq = max(min_ring_freq, ring_freq);
+			/* leave ia_freq as the default, chosen by cpufreq */
+		} else {
+			/* On older processors, there is no separate ring
+			 * clock domain, so in order to boost the bandwidth
+			 * of the ring, we need to upclock the CPU (ia_freq).
+			 *
+			 * For GPU frequencies less than 750MHz,
+			 * just use the lowest ring freq.
 			 */
 			if (gpu_freq < min_freq)
 				ia_freq = 800;
 			else
 				ia_freq = max_ia_freq - ((diff * scaling_factor) / 2);
 			ia_freq = DIV_ROUND_CLOSEST(ia_freq, 100);
-		ia_freq <<= GEN6_PCODE_FREQ_IA_RATIO_SHIFT;
+		}
 
 		sandybridge_pcode_write(dev_priv,
 					GEN6_PCODE_WRITE_MIN_FREQ_TABLE,
-					ia_freq | gpu_freq);
+					ia_freq << GEN6_PCODE_FREQ_IA_RATIO_SHIFT |
+					ring_freq << GEN6_PCODE_FREQ_RING_RATIO_SHIFT |
+					gpu_freq);
 	}
 }
 
@@ -3575,6 +3590,7 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
+	uint32_t val;
 
 	/*
 	 * On Ibex Peak and Cougar Point, we need to disable clock
@@ -3587,8 +3603,17 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 	/* The below fixes the weird display corruption, a few pixels shifted
 	 * downward, on (only) LVDS of some HP laptops with IVY.
 	 */
-	for_each_pipe(pipe)
-		I915_WRITE(TRANS_CHICKEN2(pipe), TRANS_CHICKEN2_TIMING_OVERRIDE);
+	for_each_pipe(pipe) {
+		val = I915_READ(TRANS_CHICKEN2(pipe));
+		val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
+		val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
+		if (dev_priv->fdi_rx_polarity_inverted)
+			val |= TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
+		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+		val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER;
+		val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH;
+		I915_WRITE(TRANS_CHICKEN2(pipe), val);
+	}
 	/* WADP0ClockGatingDisable */
 	for_each_pipe(pipe) {
 		I915_WRITE(TRANS_CHICKEN1(pipe),
@@ -3890,6 +3915,7 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 	snpcr |= GEN6_MBC_SNPCR_MED;
 	I915_WRITE(GEN6_MBCUNIT_SNPCR, snpcr);
 
+	if (!HAS_PCH_NOP(dev))
 		cpt_init_clock_gating(dev);
 
 	gen6_check_mch_setup(dev);
@@ -4084,6 +4110,22 @@ void intel_init_clock_gating(struct drm_device *dev)
 	dev_priv->display.init_clock_gating(dev);
 }
 
+/**
+ * We should only use the power well if we explicitly asked the hardware to
+ * enable it, so check if it's enabled and also check if we've requested it to
+ * be enabled.
+ */
+bool intel_using_power_well(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_HASWELL(dev))
+		return I915_READ(HSW_PWR_WELL_DRIVER) ==
+		       (HSW_PWR_WELL_ENABLE | HSW_PWR_WELL_STATE);
+	else
+		return true;
+}
+
 void intel_set_power_well(struct drm_device *dev, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4190,7 +4232,6 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = gen6_init_clock_gating;
 		} else if (IS_IVYBRIDGE(dev)) {
-			/* FIXME: detect B0+ stepping and use auto training */
 			if (SNB_READ_WM0_LATENCY()) {
 				dev_priv->display.update_wm = ivybridge_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;

drivers/gpu/drm/i915/intel_sdvo.c

@@ -1231,12 +1231,8 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(&connector->base);
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(&connector->base);
-	struct drm_i915_private *dev_priv = intel_sdvo->base.base.dev->dev_private;
 	u16 active_outputs;
 
-	if (!(I915_READ(intel_sdvo->sdvo_reg) & SDVO_ENABLE))
-		return false;
-
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
 	if (active_outputs & intel_sdvo_connector->output_flag)
@@ -1251,11 +1247,13 @@ static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	u16 active_outputs;
 	u32 tmp;
 
 	tmp = I915_READ(intel_sdvo->sdvo_reg);
+	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
-	if (!(tmp & SDVO_ENABLE))
+	if (!(tmp & SDVO_ENABLE) && (active_outputs == 0))
 		return false;
 
 	if (HAS_PCH_CPT(dev))
@@ -2276,7 +2274,6 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 	connector = &intel_connector->base;
 	if (intel_sdvo_get_hotplug_support(intel_sdvo) &
 		intel_sdvo_connector->output_flag) {
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
 		intel_sdvo->hotplug_active |= intel_sdvo_connector->output_flag;
 		/* Some SDVO devices have one-shot hotplug interrupts.
 		 * Ensure that they get re-enabled when an interrupt happens.
@@ -2284,7 +2281,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 		intel_encoder->hot_plug = intel_sdvo_enable_hotplug;
 		intel_sdvo_enable_hotplug(intel_encoder);
 	} else {
-		connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
+		intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 	}
 	encoder->encoder_type = DRM_MODE_ENCODER_TMDS;
 	connector->connector_type = DRM_MODE_CONNECTOR_DVID;
@@ -2353,7 +2350,7 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device)
 
 	intel_connector = &intel_sdvo_connector->base;
 	connector = &intel_connector->base;
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+	intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 	encoder->encoder_type = DRM_MODE_ENCODER_DAC;
 	connector->connector_type = DRM_MODE_CONNECTOR_VGA;
 
@@ -2746,7 +2743,6 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 	struct intel_sdvo *intel_sdvo;
 	u32 hotplug_mask;
 	int i;
-
 	intel_sdvo = kzalloc(sizeof(struct intel_sdvo), GFP_KERNEL);
 	if (!intel_sdvo)
 		return false;

drivers/gpu/drm/i915/intel_tv.c

@@ -1613,7 +1613,7 @@ intel_tv_init(struct drm_device *dev)
 	 *
 	 * More recent chipsets favour HDMI rather than integrated S-Video.
 	 */
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+	intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
 	drm_connector_init(dev, connector, &intel_tv_connector_funcs,
 			   DRM_MODE_CONNECTOR_SVIDEO);