Merge tag 'drm-intel-next-2013-06-18' of git://people.freedesktop.org/~danvet/drm-intel into drm-next

Last 3.11 feature pull. I have a few odds bits and pieces and fixes in my
queue, I'll sort them out later on to see what's for 3.11-fixes and what's
for 3.12. But nothing to hold this here up imo.

Highlights:
- more hangcheck work from Mika and Chris to prepare for arb robustness
- trickle feed fixes from Ville
- first parts of the shared pch pll rework, with some basic hw state
  readout and cross-checking (this shuts up the confused pch pll refcount
  WARN that Linus just recently forwarded)
- Haswell audio power well support from Wang Xingchao (alsa bits acked by
  Takashi)
- some cleanups and asserts sprinkling around the plane/gamma enabling
  sequence from Ville
- more gtt refactoring from Ben
- clear up the adjusted->mode vs. pixel clock vs. port clock confusion
- 30bpp support, this time for real hopefully

* tag 'drm-intel-next-2013-06-18' of git://people.freedesktop.org/~danvet/drm-intel: (97 commits)
  drm/i915: remove a superflous semi-colon
  drm/i915: Kill useless "Enable panel fitter" comments
  drm/i915: Remove extra "ring" from error message
  drm/i915: simplify the reduced clock handling for pch plls
  drm/i915: stop killing pfit on i9xx
  drm/i915: explicitly set up PIPECONF (and gamma table) on haswell
  drm/i915: set up PIPECONF explicitly for i9xx/vlv platforms
  drm/i915: set up PIPECONF explicitly on ilk-ivb
  drm/i915: find guilty batch buffer on ring resets
  drm/i915: store ring hangcheck action
  drm/i915: add batch bo to i915_add_request()
  drm/i915: change i915_add_request to macro
  drm/i915: add i915_gem_context_get_hang_stats()
  drm/i915: add struct i915_ctx_hang_stats
  drm/i915: Try harder to disable trickle feed on VLV
  drm/i915: fix up pch pll enabling for pixel multipliers
  drm/i915: hw state readout and cross-checking for shared dplls
  drm/i915: WARN on lack of shared dpll
  drm/i915: split up intel_modeset_check_state
  drm/i915: extract readout_hw_state from setup_hw_state
  ...

Conflicts:
	drivers/gpu/drm/i915/intel_display.c
	drivers/gpu/drm/i915/intel_fb.c
	drivers/gpu/drm/i915/intel_sdvo.c

drivers/gpu/drm/i915/i915_debugfs.c

@@ -196,6 +196,32 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 	} \
 } while (0)
 
+struct file_stats {
+	int count;
+	size_t total, active, inactive, unbound;
+};
+
+static int per_file_stats(int id, void *ptr, void *data)
+{
+	struct drm_i915_gem_object *obj = ptr;
+	struct file_stats *stats = data;
+
+	stats->count++;
+	stats->total += obj->base.size;
+
+	if (obj->gtt_space) {
+		if (!list_empty(&obj->ring_list))
+			stats->active += obj->base.size;
+		else
+			stats->inactive += obj->base.size;
+	} else {
+		if (!list_empty(&obj->global_list))
+			stats->unbound += obj->base.size;
+	}
+
+	return 0;
+}
+
 static int i915_gem_object_info(struct seq_file *m, void* data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -204,6 +230,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	u32 count, mappable_count, purgeable_count;
 	size_t size, mappable_size, purgeable_size;
 	struct drm_i915_gem_object *obj;
+	struct drm_file *file;
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -215,7 +242,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   dev_priv->mm.object_memory);
 
 	size = count = mappable_size = mappable_count = 0;
-	count_objects(&dev_priv->mm.bound_list, gtt_list);
+	count_objects(&dev_priv->mm.bound_list, global_list);
 	seq_printf(m, "%u [%u] objects, %zu [%zu] bytes in gtt\n",
 		   count, mappable_count, size, mappable_size);
 
@@ -230,7 +257,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   count, mappable_count, size, mappable_size);
 
 	size = count = purgeable_size = purgeable_count = 0;
-	list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
 		size += obj->base.size, ++count;
 		if (obj->madv == I915_MADV_DONTNEED)
 			purgeable_size += obj->base.size, ++purgeable_count;
@@ -238,7 +265,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	seq_printf(m, "%u unbound objects, %zu bytes\n", count, size);
 
 	size = count = mappable_size = mappable_count = 0;
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if (obj->fault_mappable) {
 			size += obj->gtt_space->size;
 			++count;
@@ -263,6 +290,21 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   dev_priv->gtt.total,
 		   dev_priv->gtt.mappable_end - dev_priv->gtt.start);
 
+	seq_printf(m, "\n");
+	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
+		struct file_stats stats;
+
+		memset(&stats, 0, sizeof(stats));
+		idr_for_each(&file->object_idr, per_file_stats, &stats);
+		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu unbound)\n",
+			   get_pid_task(file->pid, PIDTYPE_PID)->comm,
+			   stats.count,
+			   stats.total,
+			   stats.active,
+			   stats.inactive,
+			   stats.unbound);
+	}
+
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -283,7 +325,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void* data)
 		return ret;
 
 	total_obj_size = total_gtt_size = count = 0;
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if (list == PINNED_LIST && obj->pin_count == 0)
 			continue;
 
@@ -1944,7 +1986,8 @@ i915_drop_caches_set(void *data, u64 val)
 	}
 
 	if (val & DROP_UNBOUND) {
-		list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+		list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
+					 global_list)
 			if (obj->pages_pin_count == 0) {
 				ret = i915_gem_object_put_pages(obj);
 				if (ret)

drivers/gpu/drm/i915/i915_dma.c

@@ -1001,8 +1001,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		value = 1;
 		break;
 	default:
-		DRM_DEBUG_DRIVER("Unknown parameter %d\n",
-				 param->param);
+		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
 	}
 
@@ -1633,6 +1632,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	/* Start out suspended */
 	dev_priv->mm.suspended = 1;
 
+	if (HAS_POWER_WELL(dev))
+		i915_init_power_well(dev);
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		ret = i915_load_modeset_init(dev);
 		if (ret < 0) {
@@ -1684,6 +1686,9 @@ int i915_driver_unload(struct drm_device *dev)
 
 	intel_gpu_ips_teardown();
 
+	if (HAS_POWER_WELL(dev))
+		i915_remove_power_well(dev);
+
 	i915_teardown_sysfs(dev);
 
 	if (dev_priv->mm.inactive_shrinker.shrink)
@@ -1775,7 +1780,7 @@ int i915_driver_open(struct drm_device *dev, struct drm_file *file)
 	struct drm_i915_file_private *file_priv;
 
 	DRM_DEBUG_DRIVER("\n");
-	file_priv = kmalloc(sizeof(*file_priv), GFP_KERNEL);
+	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
 	if (!file_priv)
 		return -ENOMEM;
 

drivers/gpu/drm/i915/i915_drv.c

@@ -457,7 +457,6 @@ void intel_detect_pch(struct drm_device *dev)
 	 */
 	if (INTEL_INFO(dev)->num_pipes == 0) {
 		dev_priv->pch_type = PCH_NOP;
-		dev_priv->num_pch_pll = 0;
 		return;
 	}
 
@@ -476,34 +475,28 @@ void intel_detect_pch(struct drm_device *dev)
 
 			if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_IBX;
-				dev_priv->num_pch_pll = 2;
 				DRM_DEBUG_KMS("Found Ibex Peak PCH\n");
 				WARN_ON(!IS_GEN5(dev));
 			} else if (id == INTEL_PCH_CPT_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_CPT;
-				dev_priv->num_pch_pll = 2;
 				DRM_DEBUG_KMS("Found CougarPoint PCH\n");
 				WARN_ON(!(IS_GEN6(dev) || IS_IVYBRIDGE(dev)));
 			} else if (id == INTEL_PCH_PPT_DEVICE_ID_TYPE) {
 				/* PantherPoint is CPT compatible */
 				dev_priv->pch_type = PCH_CPT;
-				dev_priv->num_pch_pll = 2;
 				DRM_DEBUG_KMS("Found PatherPoint PCH\n");
 				WARN_ON(!(IS_GEN6(dev) || IS_IVYBRIDGE(dev)));
 			} else if (id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_LPT;
-				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);
 		}
 		pci_dev_put(pch);
 	}
@@ -570,7 +563,7 @@ static int i915_drm_freeze(struct drm_device *dev)
 	intel_opregion_fini(dev);
 
 	console_lock();
-	intel_fbdev_set_suspend(dev, 1);
+	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED);
 	console_unlock();
 
 	return 0;
@@ -614,7 +607,7 @@ void intel_console_resume(struct work_struct *work)
 	struct drm_device *dev = dev_priv->dev;
 
 	console_lock();
-	intel_fbdev_set_suspend(dev, 0);
+	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING);
 	console_unlock();
 }
 
@@ -683,7 +676,7 @@ static int __i915_drm_thaw(struct drm_device *dev)
 	 * path of resume if possible.
 	 */
 	if (console_trylock()) {
-		intel_fbdev_set_suspend(dev, 0);
+		intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING);
 		console_unlock();
 	} else {
 		schedule_work(&dev_priv->console_resume_work);

drivers/gpu/drm/i915/i915_drv.h

@@ -132,15 +132,38 @@ enum hpd_pin {
 	list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
 		if ((intel_encoder)->base.crtc == (__crtc))
 
-struct intel_pch_pll {
+struct drm_i915_private;
+
+enum intel_dpll_id {
+	DPLL_ID_PRIVATE = -1, /* non-shared dpll in use */
+	/* real shared dpll ids must be >= 0 */
+	DPLL_ID_PCH_PLL_A,
+	DPLL_ID_PCH_PLL_B,
+};
+#define I915_NUM_PLLS 2
+
+struct intel_dpll_hw_state {
+	uint32_t dpll;
+	uint32_t fp0;
+	uint32_t fp1;
+};
+
+struct intel_shared_dpll {
 	int refcount; /* count of number of CRTCs sharing this PLL */
 	int active; /* count of number of active CRTCs (i.e. DPMS on) */
 	bool on; /* is the PLL actually active? Disabled during modeset */
-	int pll_reg;
-	int fp0_reg;
-	int fp1_reg;
+	const char *name;
+	/* should match the index in the dev_priv->shared_dplls array */
+	enum intel_dpll_id id;
+	struct intel_dpll_hw_state hw_state;
+	void (*enable)(struct drm_i915_private *dev_priv,
+		       struct intel_shared_dpll *pll);
+	void (*disable)(struct drm_i915_private *dev_priv,
+			struct intel_shared_dpll *pll);
+	bool (*get_hw_state)(struct drm_i915_private *dev_priv,
+			     struct intel_shared_dpll *pll,
+			     struct intel_dpll_hw_state *hw_state);
 };
-#define I915_NUM_PLLS 2
 
 /* Used by dp and fdi links */
 struct intel_link_m_n {
@@ -195,7 +218,6 @@ struct opregion_header;
 struct opregion_acpi;
 struct opregion_swsci;
 struct opregion_asle;
-struct drm_i915_private;
 
 struct intel_opregion {
 	struct opregion_header __iomem *header;
@@ -306,6 +328,8 @@ struct drm_i915_error_state {
 
 struct intel_crtc_config;
 struct intel_crtc;
+struct intel_limit;
+struct dpll;
 
 struct drm_i915_display_funcs {
 	bool (*fbc_enabled)(struct drm_device *dev);
@@ -313,6 +337,24 @@ struct drm_i915_display_funcs {
 	void (*disable_fbc)(struct drm_device *dev);
 	int (*get_display_clock_speed)(struct drm_device *dev);
 	int (*get_fifo_size)(struct drm_device *dev, int plane);
+	/**
+	 * find_dpll() - Find the best values for the PLL
+	 * @limit: limits for the PLL
+	 * @crtc: current CRTC
+	 * @target: target frequency in kHz
+	 * @refclk: reference clock frequency in kHz
+	 * @match_clock: if provided, @best_clock P divider must
+	 *               match the P divider from @match_clock
+	 *               used for LVDS downclocking
+	 * @best_clock: best PLL values found
+	 *
+	 * Returns true on success, false on failure.
+	 */
+	bool (*find_dpll)(const struct intel_limit *limit,
+			  struct drm_crtc *crtc,
+			  int target, int refclk,
+			  struct dpll *match_clock,
+			  struct dpll *best_clock);
 	void (*update_wm)(struct drm_device *dev);
 	void (*update_sprite_wm)(struct drm_device *dev, int pipe,
 				 uint32_t sprite_width, int pixel_size,
@@ -466,6 +508,13 @@ struct i915_hw_ppgtt {
 	void (*cleanup)(struct i915_hw_ppgtt *ppgtt);
 };
 
+struct i915_ctx_hang_stats {
+	/* This context had batch pending when hang was declared */
+	unsigned batch_pending;
+
+	/* This context had batch active when hang was declared */
+	unsigned batch_active;
+};
 
 /* This must match up with the value previously used for execbuf2.rsvd1. */
 #define DEFAULT_CONTEXT_ID 0
@@ -476,6 +525,7 @@ struct i915_hw_context {
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
+	struct i915_ctx_hang_stats hang_stats;
 };
 
 enum no_fbc_reason {
@@ -720,6 +770,15 @@ struct intel_ilk_power_mgmt {
 	struct drm_i915_gem_object *renderctx;
 };
 
+/* Power well structure for haswell */
+struct i915_power_well {
+	struct drm_device *device;
+	spinlock_t lock;
+	/* power well enable/disable usage count */
+	int count;
+	int i915_request;
+};
+
 struct i915_dri1_state {
 	unsigned allow_batchbuffer : 1;
 	u32 __iomem *gfx_hws_cpu_addr;
@@ -842,7 +901,6 @@ struct i915_gpu_error {
 #define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
 #define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
 	struct timer_list hangcheck_timer;
-	int hangcheck_count;
 
 	/* For reset and error_state handling. */
 	spinlock_t lock;
@@ -998,7 +1056,6 @@ typedef struct drm_i915_private {
 	u32 hpd_event_bits;
 	struct timer_list hotplug_reenable_timer;
 
-	int num_pch_pll;
 	int num_plane;
 
 	unsigned long cfb_size;
@@ -1059,7 +1116,8 @@ typedef struct drm_i915_private {
 	struct drm_crtc *pipe_to_crtc_mapping[3];
 	wait_queue_head_t pending_flip_queue;
 
-	struct intel_pch_pll pch_plls[I915_NUM_PLLS];
+	int num_shared_dpll;
+	struct intel_shared_dpll shared_dplls[I915_NUM_PLLS];
 	struct intel_ddi_plls ddi_plls;
 
 	/* Reclocking support */
@@ -1080,6 +1138,9 @@ typedef struct drm_i915_private {
 	 * mchdev_lock in intel_pm.c */
 	struct intel_ilk_power_mgmt ips;
 
+	/* Haswell power well */
+	struct i915_power_well power_well;
+
 	enum no_fbc_reason no_fbc_reason;
 
 	struct drm_mm_node *compressed_fb;
@@ -1154,7 +1215,7 @@ struct drm_i915_gem_object {
 	struct drm_mm_node *gtt_space;
 	/** Stolen memory for this object, instead of being backed by shmem. */
 	struct drm_mm_node *stolen;
-	struct list_head gtt_list;
+	struct list_head global_list;
 
 	/** This object's place on the active/inactive lists */
 	struct list_head ring_list;
@@ -1301,12 +1362,18 @@ struct drm_i915_gem_request {
 	/** GEM sequence number associated with this request. */
 	uint32_t seqno;
 
-	/** Postion in the ringbuffer of the end of the request */
+	/** Position in the ringbuffer of the start of the request */
+	u32 head;
+
+	/** Position in the ringbuffer of the end of the request */
 	u32 tail;
 
 	/** Context related to this request */
 	struct i915_hw_context *ctx;
 
+	/** Batch buffer related to this request if any */
+	struct drm_i915_gem_object *batch_obj;
+
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
 
@@ -1324,6 +1391,8 @@ struct drm_i915_file_private {
 		struct list_head request_list;
 	} mm;
 	struct idr context_idr;
+
+	struct i915_ctx_hang_stats hang_stats;
 };
 
 #define INTEL_INFO(dev)	(((struct drm_i915_private *) (dev)->dev_private)->info)
@@ -1660,6 +1729,7 @@ i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
 {
 	if (obj->fence_reg != I915_FENCE_REG_NONE) {
 		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0);
 		dev_priv->fence_regs[obj->fence_reg].pin_count--;
 	}
 }
@@ -1692,9 +1762,12 @@ void i915_gem_init_swizzling(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);
-int i915_add_request(struct intel_ring_buffer *ring,
-		     struct drm_file *file,
-		     u32 *seqno);
+int __i915_add_request(struct intel_ring_buffer *ring,
+		       struct drm_file *file,
+		       struct drm_i915_gem_object *batch_obj,
+		       u32 *seqno);
+#define i915_add_request(ring, seqno) \
+	__i915_add_request(ring, NULL, NULL, seqno)
 int __must_check i915_wait_seqno(struct intel_ring_buffer *ring,
 				 uint32_t seqno);
 int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -1748,6 +1821,10 @@ static inline void i915_gem_context_unreference(struct i915_hw_context *ctx)
 	kref_put(&ctx->ref, i915_gem_context_free);
 }
 
+struct i915_ctx_hang_stats * __must_check
+i915_gem_context_get_hang_stats(struct intel_ring_buffer *ring,
+				struct drm_file *file,
+				u32 id);
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file);
 int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,

drivers/gpu/drm/i915/i915_gem.c

@@ -176,7 +176,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 
 	pinned = 0;
 	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
 		if (obj->pin_count)
 			pinned += obj->gtt_space->size;
 	mutex_unlock(&dev->struct_mutex);
@@ -956,7 +956,7 @@ i915_gem_check_olr(struct intel_ring_buffer *ring, u32 seqno)
 
 	ret = 0;
 	if (seqno == ring->outstanding_lazy_request)
-		ret = i915_add_request(ring, NULL, NULL);
+		ret = i915_add_request(ring, NULL);
 
 	return ret;
 }
@@ -1676,7 +1676,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	/* ->put_pages might need to allocate memory for the bit17 swizzle
 	 * array, hence protect them from being reaped by removing them from gtt
 	 * lists early. */
-	list_del(&obj->gtt_list);
+	list_del(&obj->global_list);
 
 	ops->put_pages(obj);
 	obj->pages = NULL;
@@ -1696,7 +1696,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 
 	list_for_each_entry_safe(obj, next,
 				 &dev_priv->mm.unbound_list,
-				 gtt_list) {
+				 global_list) {
 		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
 		    i915_gem_object_put_pages(obj) == 0) {
 			count += obj->base.size >> PAGE_SHIFT;
@@ -1733,7 +1733,8 @@ i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 
 	i915_gem_evict_everything(dev_priv->dev);
 
-	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
+				 global_list)
 		i915_gem_object_put_pages(obj);
 }
 
@@ -1858,7 +1859,7 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 	if (ret)
 		return ret;
 
-	list_add_tail(&obj->gtt_list, &dev_priv->mm.unbound_list);
+	list_add_tail(&obj->global_list, &dev_priv->mm.unbound_list);
 	return 0;
 }
 
@@ -1996,17 +1997,18 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
 	return 0;
 }
 
-int
-i915_add_request(struct intel_ring_buffer *ring,
-		 struct drm_file *file,
-		 u32 *out_seqno)
+int __i915_add_request(struct intel_ring_buffer *ring,
+		       struct drm_file *file,
+		       struct drm_i915_gem_object *obj,
+		       u32 *out_seqno)
 {
 	drm_i915_private_t *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *request;
-	u32 request_ring_position;
+	u32 request_ring_position, request_start;
 	int was_empty;
 	int ret;
 
+	request_start = intel_ring_get_tail(ring);
 	/*
 	 * Emit any outstanding flushes - execbuf can fail to emit the flush
 	 * after having emitted the batchbuffer command. Hence we need to fix
@@ -2038,8 +2040,17 @@ i915_add_request(struct intel_ring_buffer *ring,
 
 	request->seqno = intel_ring_get_seqno(ring);
 	request->ring = ring;
+	request->head = request_start;
 	request->tail = request_ring_position;
 	request->ctx = ring->last_context;
+	request->batch_obj = obj;
+
+	/* Whilst this request exists, batch_obj will be on the
+	 * active_list, and so will hold the active reference. Only when this
+	 * request is retired will the the batch_obj be moved onto the
+	 * inactive_list and lose its active reference. Hence we do not need
+	 * to explicitly hold another reference here.
+	 */
 
 	if (request->ctx)
 		i915_gem_context_reference(request->ctx);
@@ -2096,6 +2107,94 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 	spin_unlock(&file_priv->mm.lock);
 }
 
+static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj)
+{
+	if (acthd >= obj->gtt_offset &&
+	    acthd < obj->gtt_offset + obj->base.size)
+		return true;
+
+	return false;
+}
+
+static bool i915_head_inside_request(const u32 acthd_unmasked,
+				     const u32 request_start,
+				     const u32 request_end)
+{
+	const u32 acthd = acthd_unmasked & HEAD_ADDR;
+
+	if (request_start < request_end) {
+		if (acthd >= request_start && acthd < request_end)
+			return true;
+	} else if (request_start > request_end) {
+		if (acthd >= request_start || acthd < request_end)
+			return true;
+	}
+
+	return false;
+}
+
+static bool i915_request_guilty(struct drm_i915_gem_request *request,
+				const u32 acthd, bool *inside)
+{
+	/* There is a possibility that unmasked head address
+	 * pointing inside the ring, matches the batch_obj address range.
+	 * However this is extremely unlikely.
+	 */
+
+	if (request->batch_obj) {
+		if (i915_head_inside_object(acthd, request->batch_obj)) {
+			*inside = true;
+			return true;
+		}
+	}
+
+	if (i915_head_inside_request(acthd, request->head, request->tail)) {
+		*inside = false;
+		return true;
+	}
+
+	return false;
+}
+
+static void i915_set_reset_status(struct intel_ring_buffer *ring,
+				  struct drm_i915_gem_request *request,
+				  u32 acthd)
+{
+	struct i915_ctx_hang_stats *hs = NULL;
+	bool inside, guilty;
+
+	/* Innocent until proven guilty */
+	guilty = false;
+
+	if (ring->hangcheck.action != wait &&
+	    i915_request_guilty(request, acthd, &inside)) {
+		DRM_ERROR("%s hung %s bo (0x%x ctx %d) at 0x%x\n",
+			  ring->name,
+			  inside ? "inside" : "flushing",
+			  request->batch_obj ?
+			  request->batch_obj->gtt_offset : 0,
+			  request->ctx ? request->ctx->id : 0,
+			  acthd);
+
+		guilty = true;
+	}
+
+	/* If contexts are disabled or this is the default context, use
+	 * file_priv->reset_state
+	 */
+	if (request->ctx && request->ctx->id != DEFAULT_CONTEXT_ID)
+		hs = &request->ctx->hang_stats;
+	else if (request->file_priv)
+		hs = &request->file_priv->hang_stats;
+
+	if (hs) {
+		if (guilty)
+			hs->batch_active++;
+		else
+			hs->batch_pending++;
+	}
+}
+
 static void i915_gem_free_request(struct drm_i915_gem_request *request)
 {
 	list_del(&request->list);
@@ -2110,6 +2209,12 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request)
 static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
 				      struct intel_ring_buffer *ring)
 {
+	u32 completed_seqno;
+	u32 acthd;
+
+	acthd = intel_ring_get_active_head(ring);
+	completed_seqno = ring->get_seqno(ring, false);
+
 	while (!list_empty(&ring->request_list)) {
 		struct drm_i915_gem_request *request;
 
@@ -2117,6 +2222,9 @@ static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
 					   struct drm_i915_gem_request,
 					   list);
 
+		if (request->seqno > completed_seqno)
+			i915_set_reset_status(ring, request, acthd);
+
 		i915_gem_free_request(request);
 	}
 
@@ -2276,7 +2384,7 @@ i915_gem_retire_work_handler(struct work_struct *work)
 	idle = true;
 	for_each_ring(ring, dev_priv, i) {
 		if (ring->gpu_caches_dirty)
-			i915_add_request(ring, NULL, NULL);
+			i915_add_request(ring, NULL);
 
 		idle &= list_empty(&ring->request_list);
 	}
@@ -2508,9 +2616,10 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 		obj->has_aliasing_ppgtt_mapping = 0;
 	}
 	i915_gem_gtt_finish_object(obj);
+	i915_gem_object_unpin_pages(obj);
 
 	list_del(&obj->mm_list);
-	list_move_tail(&obj->gtt_list, &dev_priv->mm.unbound_list);
+	list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
 	/* Avoid an unnecessary call to unbind on rebind. */
 	obj->map_and_fenceable = true;
 
@@ -2918,7 +3027,7 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 	struct drm_i915_gem_object *obj;
 	int err = 0;
 
-	list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.gtt_list, global_list) {
 		if (obj->gtt_space == NULL) {
 			printk(KERN_ERR "object found on GTT list with no space reserved\n");
 			err++;
@@ -3042,7 +3151,7 @@ search_free:
 		return ret;
 	}
 
-	list_move_tail(&obj->gtt_list, &dev_priv->mm.bound_list);
+	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
 	obj->gtt_space = node;
@@ -3057,7 +3166,6 @@ search_free:
 
 	obj->map_and_fenceable = mappable && fenceable;
 
-	i915_gem_object_unpin_pages(obj);
 	trace_i915_gem_object_bind(obj, map_and_fenceable);
 	i915_gem_verify_gtt(dev);
 	return 0;
@@ -3757,7 +3865,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			  const struct drm_i915_gem_object_ops *ops)
 {
 	INIT_LIST_HEAD(&obj->mm_list);
-	INIT_LIST_HEAD(&obj->gtt_list);
+	INIT_LIST_HEAD(&obj->global_list);
 	INIT_LIST_HEAD(&obj->ring_list);
 	INIT_LIST_HEAD(&obj->exec_list);
 
@@ -3857,7 +3965,13 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 		dev_priv->mm.interruptible = was_interruptible;
 	}
 
-	obj->pages_pin_count = 0;
+	/* Stolen objects don't hold a ref, but do hold pin count. Fix that up
+	 * before progressing. */
+	if (obj->stolen)
+		i915_gem_object_unpin_pages(obj);
+
+	if (WARN_ON(obj->pages_pin_count))
+		obj->pages_pin_count = 0;
 	i915_gem_object_put_pages(obj);
 	i915_gem_object_free_mmap_offset(obj);
 	i915_gem_object_release_stolen(obj);
@@ -4498,10 +4612,10 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 	}
 
 	cnt = 0;
-	list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
 		if (obj->pages_pin_count == 0)
 			cnt += obj->base.size >> PAGE_SHIFT;
-	list_for_each_entry(obj, &dev_priv->mm.inactive_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.inactive_list, global_list)
 		if (obj->pin_count == 0 && obj->pages_pin_count == 0)
 			cnt += obj->base.size >> PAGE_SHIFT;
 

drivers/gpu/drm/i915/i915_gem_context.c

@@ -303,6 +303,34 @@ static int context_idr_cleanup(int id, void *p, void *data)
 	return 0;
 }
 
+struct i915_ctx_hang_stats *
+i915_gem_context_get_hang_stats(struct intel_ring_buffer *ring,
+				struct drm_file *file,
+				u32 id)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct drm_i915_file_private *file_priv = file->driver_priv;
+	struct i915_hw_context *to;
+
+	if (dev_priv->hw_contexts_disabled)
+		return ERR_PTR(-ENOENT);
+
+	if (ring->id != RCS)
+		return ERR_PTR(-EINVAL);
+
+	if (file == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (id == DEFAULT_CONTEXT_ID)
+		return &file_priv->hang_stats;
+
+	to = i915_gem_context_get(file->driver_priv, id);
+	if (to == NULL)
+		return ERR_PTR(-ENOENT);
+
+	return &to->hang_stats;
+}
+
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
@@ -427,7 +455,7 @@ static int do_switch(struct i915_hw_context *to)
 		from->obj->dirty = 1;
 		BUG_ON(from->obj->ring != ring);
 
-		ret = i915_add_request(ring, NULL, NULL);
+		ret = i915_add_request(ring, NULL);
 		if (ret) {
 			/* Too late, we've already scheduled a context switch.
 			 * Try to undo the change so that the hw state is

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -786,7 +786,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 			obj->dirty = 1;
 			obj->last_write_seqno = intel_ring_get_seqno(ring);
 			if (obj->pin_count) /* check for potential scanout */
-				intel_mark_fb_busy(obj);
+				intel_mark_fb_busy(obj, ring);
 		}
 
 		trace_i915_gem_object_change_domain(obj, old_read, old_write);
@@ -796,13 +796,14 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 static void
 i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 				    struct drm_file *file,
-				    struct intel_ring_buffer *ring)
+				    struct intel_ring_buffer *ring,
+				    struct drm_i915_gem_object *obj)
 {
 	/* Unconditionally force add_request to emit a full flush. */
 	ring->gpu_caches_dirty = true;
 
 	/* Add a breadcrumb for the completion of the batch buffer */
-	(void)i915_add_request(ring, file, NULL);
+	(void)__i915_add_request(ring, file, obj, NULL);
 }
 
 static int
@@ -1083,7 +1084,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags);
 
 	i915_gem_execbuffer_move_to_active(&eb->objects, ring);
-	i915_gem_execbuffer_retire_commands(dev, file, ring);
+	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
 
 err:
 	eb_destroy(eb);

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -439,7 +439,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	dev_priv->gtt.gtt_clear_range(dev, dev_priv->gtt.start / PAGE_SIZE,
 				      dev_priv->gtt.total / PAGE_SIZE);
 
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		i915_gem_clflush_object(obj);
 		i915_gem_gtt_bind_object(obj, obj->cache_level);
 	}
@@ -631,7 +631,7 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 		dev_priv->mm.gtt_space.color_adjust = i915_gtt_color_adjust;
 
 	/* Mark any preallocated objects as occupied */
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
 			      obj->gtt_offset, obj->base.size);
 

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -279,7 +279,7 @@ _i915_gem_object_create_stolen(struct drm_device *dev,
 		goto cleanup;
 
 	obj->has_dma_mapping = true;
-	obj->pages_pin_count = 1;
+	i915_gem_object_pin_pages(obj);
 	obj->stolen = stolen;
 
 	obj->base.write_domain = I915_GEM_DOMAIN_GTT;
@@ -383,7 +383,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	obj->gtt_offset = gtt_offset;
 	obj->has_global_gtt_mapping = 1;
 
-	list_add_tail(&obj->gtt_list, &dev_priv->mm.bound_list);
+	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
 	return obj;

drivers/gpu/drm/i915/i915_irq.c

@@ -683,7 +683,6 @@ static void notify_ring(struct drm_device *dev,
 
 	wake_up_all(&ring->irq_queue);
 	if (i915_enable_hangcheck) {
-		dev_priv->gpu_error.hangcheck_count = 0;
 		mod_timer(&dev_priv->gpu_error.hangcheck_timer,
 			  round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
 	}
@@ -1656,7 +1655,7 @@ static u32 capture_pinned_bo(struct drm_i915_error_buffer *err,
 	struct drm_i915_gem_object *obj;
 	int i = 0;
 
-	list_for_each_entry(obj, head, gtt_list) {
+	list_for_each_entry(obj, head, global_list) {
 		if (obj->pin_count == 0)
 			continue;
 
@@ -1798,7 +1797,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
 	if (ring->id != RCS || !error->ccid)
 		return;
 
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if ((error->ccid & PAGE_MASK) == obj->gtt_offset) {
 			ering->ctx = i915_error_object_create_sized(dev_priv,
 								    obj, 1);
@@ -1935,7 +1934,7 @@ static void i915_capture_error_state(struct drm_device *dev)
 	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list)
 		i++;
 	error->active_bo_count = i;
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
 		if (obj->pin_count)
 			i++;
 	error->pinned_bo_count = i - error->active_bo_count;
@@ -2315,38 +2314,28 @@ ring_last_seqno(struct intel_ring_buffer *ring)
 			  struct drm_i915_gem_request, list)->seqno;
 }
 
-static bool i915_hangcheck_ring_idle(struct intel_ring_buffer *ring,
-				     u32 ring_seqno, bool *err)
+static bool
+ring_idle(struct intel_ring_buffer *ring, u32 seqno)
 {
-	if (list_empty(&ring->request_list) ||
-	    i915_seqno_passed(ring_seqno, ring_last_seqno(ring))) {
-		/* Issue a wake-up to catch stuck h/w. */
-		if (waitqueue_active(&ring->irq_queue)) {
-			DRM_ERROR("Hangcheck timer elapsed... %s idle\n",
-				  ring->name);
-			wake_up_all(&ring->irq_queue);
-			*err = true;
-		}
-		return true;
-	}
-	return false;
+	return (list_empty(&ring->request_list) ||
+		i915_seqno_passed(seqno, ring_last_seqno(ring)));
 }
 
-static bool semaphore_passed(struct intel_ring_buffer *ring)
+static struct intel_ring_buffer *
+semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	u32 acthd = intel_ring_get_active_head(ring) & HEAD_ADDR;
-	struct intel_ring_buffer *signaller;
-	u32 cmd, ipehr, acthd_min;
+	u32 cmd, ipehr, acthd, acthd_min;
 
 	ipehr = I915_READ(RING_IPEHR(ring->mmio_base));
 	if ((ipehr & ~(0x3 << 16)) !=
 	    (MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE | MI_SEMAPHORE_REGISTER))
-		return false;
+		return NULL;
 
 	/* ACTHD is likely pointing to the dword after the actual command,
 	 * so scan backwards until we find the MBOX.
 	 */
+	acthd = intel_ring_get_active_head(ring) & HEAD_ADDR;
 	acthd_min = max((int)acthd - 3 * 4, 0);
 	do {
 		cmd = ioread32(ring->virtual_start + acthd);
@@ -2355,128 +2344,216 @@ static bool semaphore_passed(struct intel_ring_buffer *ring)
 
 		acthd -= 4;
 		if (acthd < acthd_min)
-			return false;
+			return NULL;
 	} while (1);
 
-	signaller = &dev_priv->ring[(ring->id + (((ipehr >> 17) & 1) + 1)) % 3];
-	return i915_seqno_passed(signaller->get_seqno(signaller, false),
-				 ioread32(ring->virtual_start+acthd+4)+1);
+	*seqno = ioread32(ring->virtual_start+acthd+4)+1;
+	return &dev_priv->ring[(ring->id + (((ipehr >> 17) & 1) + 1)) % 3];
 }
 
-static bool kick_ring(struct intel_ring_buffer *ring)
+static int semaphore_passed(struct intel_ring_buffer *ring)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 tmp = I915_READ_CTL(ring);
-	if (tmp & RING_WAIT) {
-		DRM_ERROR("Kicking stuck wait on %s\n",
-			  ring->name);
-		I915_WRITE_CTL(ring, tmp);
-		return true;
-	}
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct intel_ring_buffer *signaller;
+	u32 seqno, ctl;
 
-	if (INTEL_INFO(dev)->gen >= 6 &&
-	    tmp & RING_WAIT_SEMAPHORE &&
-	    semaphore_passed(ring)) {
-		DRM_ERROR("Kicking stuck semaphore on %s\n",
-			  ring->name);
-		I915_WRITE_CTL(ring, tmp);
-		return true;
-	}
-	return false;
+	ring->hangcheck.deadlock = true;
+
+	signaller = semaphore_waits_for(ring, &seqno);
+	if (signaller == NULL || signaller->hangcheck.deadlock)
+		return -1;
+
+	/* cursory check for an unkickable deadlock */
+	ctl = I915_READ_CTL(signaller);
+	if (ctl & RING_WAIT_SEMAPHORE && semaphore_passed(signaller) < 0)
+		return -1;
+
+	return i915_seqno_passed(signaller->get_seqno(signaller, false), seqno);
 }
 
-static bool i915_hangcheck_ring_hung(struct intel_ring_buffer *ring)
+static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
 {
-	if (IS_GEN2(ring->dev))
-		return false;
+	struct intel_ring_buffer *ring;
+	int i;
 
-	/* Is the chip hanging on a WAIT_FOR_EVENT?
-	 * If so we can simply poke the RB_WAIT bit
-	 * and break the hang. This should work on
-	 * all but the second generation chipsets.
-	 */
-	return !kick_ring(ring);
+	for_each_ring(ring, dev_priv, i)
+		ring->hangcheck.deadlock = false;
 }
 
-static bool i915_hangcheck_hung(struct drm_device *dev)
+static enum intel_ring_hangcheck_action
+ring_stuck(struct intel_ring_buffer *ring, u32 acthd)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 tmp;
 
-	if (dev_priv->gpu_error.hangcheck_count++ > 1) {
-		bool hung = true;
-		struct intel_ring_buffer *ring;
-		int i;
+	if (ring->hangcheck.acthd != acthd)
+		return active;
 
-		DRM_ERROR("Hangcheck timer elapsed... GPU hung\n");
-		i915_handle_error(dev, true);
+	if (IS_GEN2(dev))
+		return hung;
 
-		for_each_ring(ring, dev_priv, i)
-			hung &= i915_hangcheck_ring_hung(ring);
+	/* Is the chip hanging on a WAIT_FOR_EVENT?
+	 * If so we can simply poke the RB_WAIT bit
+	 * and break the hang. This should work on
+	 * all but the second generation chipsets.
+	 */
+	tmp = I915_READ_CTL(ring);
+	if (tmp & RING_WAIT) {
+		DRM_ERROR("Kicking stuck wait on %s\n",
+			  ring->name);
+		I915_WRITE_CTL(ring, tmp);
+		return kick;
+	}
 
-		return hung;
+	if (INTEL_INFO(dev)->gen >= 6 && tmp & RING_WAIT_SEMAPHORE) {
+		switch (semaphore_passed(ring)) {
+		default:
+			return hung;
+		case 1:
+			DRM_ERROR("Kicking stuck semaphore on %s\n",
+				  ring->name);
+			I915_WRITE_CTL(ring, tmp);
+			return kick;
+		case 0:
+			return wait;
+		}
 	}
 
-	return false;
+	return hung;
 }
 
 /**
  * This is called when the chip hasn't reported back with completed
- * batchbuffers in a long time. The first time this is called we simply record
- * ACTHD. If ACTHD hasn't changed by the time the hangcheck timer elapses
- * again, we assume the chip is wedged and try to fix it.
+ * batchbuffers in a long time. We keep track per ring seqno progress and
+ * if there are no progress, hangcheck score for that ring is increased.
+ * Further, acthd is inspected to see if the ring is stuck. On stuck case
+ * we kick the ring. If we see no progress on three subsequent calls
+ * we assume chip is wedged and try to fix it by resetting the chip.
  */
 void i915_hangcheck_elapsed(unsigned long data)
 {
 	struct drm_device *dev = (struct drm_device *)data;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring;
-	bool err = false, idle;
 	int i;
-	u32 seqno[I915_NUM_RINGS];
-	bool work_done;
+	int busy_count = 0, rings_hung = 0;
+	bool stuck[I915_NUM_RINGS] = { 0 };
+#define BUSY 1
+#define KICK 5
+#define HUNG 20
+#define FIRE 30
 
 	if (!i915_enable_hangcheck)
 		return;
 
-	idle = true;
 	for_each_ring(ring, dev_priv, i) {
-		seqno[i] = ring->get_seqno(ring, false);
-		idle &= i915_hangcheck_ring_idle(ring, seqno[i], &err);
-	}
-
-	/* If all work is done then ACTHD clearly hasn't advanced. */
-	if (idle) {
-		if (err) {
-			if (i915_hangcheck_hung(dev))
-				return;
-
-			goto repeat;
+		u32 seqno, acthd;
+		bool busy = true;
+
+		semaphore_clear_deadlocks(dev_priv);
+
+		seqno = ring->get_seqno(ring, false);
+		acthd = intel_ring_get_active_head(ring);
+
+		if (ring->hangcheck.seqno == seqno) {
+			if (ring_idle(ring, seqno)) {
+				if (waitqueue_active(&ring->irq_queue)) {
+					/* Issue a wake-up to catch stuck h/w. */
+					DRM_ERROR("Hangcheck timer elapsed... %s idle\n",
+						  ring->name);
+					wake_up_all(&ring->irq_queue);
+					ring->hangcheck.score += HUNG;
+				} else
+					busy = false;
+			} else {
+				int score;
+
+				/* We always increment the hangcheck score
+				 * if the ring is busy and still processing
+				 * the same request, so that no single request
+				 * can run indefinitely (such as a chain of
+				 * batches). The only time we do not increment
+				 * the hangcheck score on this ring, if this
+				 * ring is in a legitimate wait for another
+				 * ring. In that case the waiting ring is a
+				 * victim and we want to be sure we catch the
+				 * right culprit. Then every time we do kick
+				 * the ring, add a small increment to the
+				 * score so that we can catch a batch that is
+				 * being repeatedly kicked and so responsible
+				 * for stalling the machine.
+				 */
+				ring->hangcheck.action = ring_stuck(ring,
+								    acthd);
+
+				switch (ring->hangcheck.action) {
+				case wait:
+					score = 0;
+					break;
+				case active:
+					score = BUSY;
+					break;
+				case kick:
+					score = KICK;
+					break;
+				case hung:
+					score = HUNG;
+					stuck[i] = true;
+					break;
+				}
+				ring->hangcheck.score += score;
+			}
+		} else {
+			/* Gradually reduce the count so that we catch DoS
+			 * attempts across multiple batches.
+			 */
+			if (ring->hangcheck.score > 0)
+				ring->hangcheck.score--;
 		}
 
-		dev_priv->gpu_error.hangcheck_count = 0;
-		return;
+		ring->hangcheck.seqno = seqno;
+		ring->hangcheck.acthd = acthd;
+		busy_count += busy;
 	}
 
-	work_done = false;
 	for_each_ring(ring, dev_priv, i) {
-		if (ring->hangcheck.seqno != seqno[i]) {
-			work_done = true;
-			ring->hangcheck.seqno = seqno[i];
+		if (ring->hangcheck.score > FIRE) {
+			DRM_ERROR("%s on %s\n",
+				  stuck[i] ? "stuck" : "no progress",
+				  ring->name);
+			rings_hung++;
 		}
 	}
 
-	if (!work_done) {
-		if (i915_hangcheck_hung(dev))
-			return;
-	} else {
-		dev_priv->gpu_error.hangcheck_count = 0;
-	}
+	if (rings_hung)
+		return i915_handle_error(dev, true);
 
-repeat:
-	/* Reset timer case chip hangs without another request being added */
-	mod_timer(&dev_priv->gpu_error.hangcheck_timer,
-		  round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
+	if (busy_count)
+		/* Reset timer case chip hangs without another request
+		 * being added */
+		mod_timer(&dev_priv->gpu_error.hangcheck_timer,
+			  round_jiffies_up(jiffies +
+					   DRM_I915_HANGCHECK_JIFFIES));
+}
+
+static void ibx_irq_preinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_PCH_NOP(dev))
+		return;
+
+	/* south display irq */
+	I915_WRITE(SDEIMR, 0xffffffff);
+	/*
+	 * SDEIER is also touched by the interrupt handler to work around missed
+	 * PCH interrupts. Hence we can't update it after the interrupt handler
+	 * is enabled - instead we unconditionally enable all PCH interrupt
+	 * sources here, but then only unmask them as needed with SDEIMR.
+	 */
+	I915_WRITE(SDEIER, 0xffffffff);
+	POSTING_READ(SDEIER);
 }
 
 /* drm_dma.h hooks
@@ -2500,16 +2577,7 @@ static void ironlake_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(GTIER, 0x0);
 	POSTING_READ(GTIER);
 
-	/* south display irq */
-	I915_WRITE(SDEIMR, 0xffffffff);
-	/*
-	 * SDEIER is also touched by the interrupt handler to work around missed
-	 * PCH interrupts. Hence we can't update it after the interrupt handler
-	 * is enabled - instead we unconditionally enable all PCH interrupt
-	 * sources here, but then only unmask them as needed with SDEIMR.
-	 */
-	I915_WRITE(SDEIER, 0xffffffff);
-	POSTING_READ(SDEIER);
+	ibx_irq_preinstall(dev);
 }
 
 static void ivybridge_irq_preinstall(struct drm_device *dev)
@@ -2536,19 +2604,7 @@ static void ivybridge_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(GEN6_PMIER, 0x0);
 	POSTING_READ(GEN6_PMIER);
 
-	if (HAS_PCH_NOP(dev))
-		return;
-
-	/* south display irq */
-	I915_WRITE(SDEIMR, 0xffffffff);
-	/*
-	 * SDEIER is also touched by the interrupt handler to work around missed
-	 * PCH interrupts. Hence we can't update it after the interrupt handler
-	 * is enabled - instead we unconditionally enable all PCH interrupt
-	 * sources here, but then only unmask them as needed with SDEIMR.
-	 */
-	I915_WRITE(SDEIER, 0xffffffff);
-	POSTING_READ(SDEIER);
+	ibx_irq_preinstall(dev);
 }
 
 static void valleyview_irq_preinstall(struct drm_device *dev)

drivers/gpu/drm/i915/i915_reg.h

@@ -147,15 +147,9 @@
 #define   VGA_MSR_MEM_EN (1<<1)
 #define   VGA_MSR_CGA_MODE (1<<0)
 
-/*
- * SR01 is the only VGA register touched on non-UMS setups.
- * VLV doesn't do UMS, so the sequencer index/data registers
- * are the only VGA registers which need to include
- * display_mmio_offset.
- */
-#define VGA_SR_INDEX (dev_priv->info->display_mmio_offset + 0x3c4)
+#define VGA_SR_INDEX 0x3c4
 #define SR01			1
-#define VGA_SR_DATA (dev_priv->info->display_mmio_offset + 0x3c5)
+#define VGA_SR_DATA 0x3c5
 
 #define VGA_AR_INDEX 0x3c0
 #define   VGA_AR_VID_EN (1<<5)
@@ -1026,6 +1020,10 @@
 #define IPS_CTL		0x43408
 #define   IPS_ENABLE	(1 << 31)
 
+#define MSG_FBC_REND_STATE	0x50380
+#define   FBC_REND_NUKE		(1<<2)
+#define   FBC_REND_CACHE_CLEAN	(1<<1)
+
 #define _HSW_PIPE_SLICE_CHICKEN_1_A	0x420B0
 #define _HSW_PIPE_SLICE_CHICKEN_1_B	0x420B4
 #define   HSW_BYPASS_FBC_QUEUE		(1<<22)
@@ -1256,7 +1254,7 @@
 #define  DSTATE_PLL_D3_OFF			(1<<3)
 #define  DSTATE_GFX_CLOCK_GATING		(1<<1)
 #define  DSTATE_DOT_CLOCK_GATING		(1<<0)
-#define DSPCLK_GATE_D		0x6200
+#define DSPCLK_GATE_D	(dev_priv->info->display_mmio_offset + 0x6200)
 # define DPUNIT_B_CLOCK_GATE_DISABLE		(1 << 30) /* 965 */
 # define VSUNIT_CLOCK_GATE_DISABLE		(1 << 29) /* 965 */
 # define VRHUNIT_CLOCK_GATE_DISABLE		(1 << 28) /* 965 */
@@ -1369,6 +1367,8 @@
 #define FW_BLC_SELF_VLV		(VLV_DISPLAY_BASE + 0x6500)
 #define  FW_CSPWRDWNEN		(1<<15)
 
+#define MI_ARB_VLV		(VLV_DISPLAY_BASE + 0x6504)
+
 /*
  * Palette regs
  */
@@ -3672,9 +3672,9 @@
 #define _GAMMA_MODE_B		0x4ac80
 #define GAMMA_MODE(pipe) _PIPE(pipe, _GAMMA_MODE_A, _GAMMA_MODE_B)
 #define GAMMA_MODE_MODE_MASK	(3 << 0)
-#define GAMMA_MODE_MODE_8bit	(0 << 0)
-#define GAMMA_MODE_MODE_10bit	(1 << 0)
-#define GAMMA_MODE_MODE_12bit	(2 << 0)
+#define GAMMA_MODE_MODE_8BIT	(0 << 0)
+#define GAMMA_MODE_MODE_10BIT	(1 << 0)
+#define GAMMA_MODE_MODE_12BIT	(2 << 0)
 #define GAMMA_MODE_MODE_SPLIT	(3 << 0)
 
 /* interrupts */
@@ -3932,15 +3932,15 @@
 
 #define _PCH_DPLL_A              0xc6014
 #define _PCH_DPLL_B              0xc6018
-#define _PCH_DPLL(pll) (pll == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
+#define PCH_DPLL(pll) (pll == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
 
 #define _PCH_FPA0                0xc6040
 #define  FP_CB_TUNE		(0x3<<22)
 #define _PCH_FPA1                0xc6044
 #define _PCH_FPB0                0xc6048
 #define _PCH_FPB1                0xc604c
-#define _PCH_FP0(pll) (pll == 0 ? _PCH_FPA0 : _PCH_FPB0)
-#define _PCH_FP1(pll) (pll == 0 ? _PCH_FPA1 : _PCH_FPB1)
+#define PCH_FP0(pll) (pll == 0 ? _PCH_FPA0 : _PCH_FPB0)
+#define PCH_FP1(pll) (pll == 0 ? _PCH_FPA1 : _PCH_FPB1)
 
 #define PCH_DPLL_TEST           0xc606c
 
@@ -3980,15 +3980,9 @@
 #define PCH_SSC4_AUX_PARMS      0xc6214
 
 #define PCH_DPLL_SEL		0xc7000
-#define  TRANSA_DPLL_ENABLE	(1<<3)
-#define	 TRANSA_DPLLB_SEL	(1<<0)
-#define	 TRANSA_DPLLA_SEL	0
-#define  TRANSB_DPLL_ENABLE	(1<<7)
-#define	 TRANSB_DPLLB_SEL	(1<<4)
-#define	 TRANSB_DPLLA_SEL	(0)
-#define  TRANSC_DPLL_ENABLE	(1<<11)
-#define	 TRANSC_DPLLB_SEL	(1<<8)
-#define	 TRANSC_DPLLA_SEL	(0)
+#define	 TRANS_DPLLB_SEL(pipe)		(1 << (pipe * 4))
+#define	 TRANS_DPLLA_SEL(pipe)		0
+#define  TRANS_DPLL_ENABLE(pipe)	(1 << (pipe * 4 + 3))
 
 /* transcoder */
 

drivers/gpu/drm/i915/i915_ums.c

@@ -41,7 +41,7 @@ static bool i915_pipe_enabled(struct drm_device *dev, enum pipe pipe)
 		return false;
 
 	if (HAS_PCH_SPLIT(dev))
-		dpll_reg = _PCH_DPLL(pipe);
+		dpll_reg = PCH_DPLL(pipe);
 	else
 		dpll_reg = (pipe == PIPE_A) ? _DPLL_A : _DPLL_B;
 

drivers/gpu/drm/i915/intel_ddi.c

@@ -624,7 +624,7 @@ intel_ddi_calculate_wrpll(int clock /* in Hz */,
 		      clock, *p_out, *n2_out, *r2_out);
 }
 
-bool intel_ddi_pll_mode_set(struct drm_crtc *crtc, int clock)
+bool intel_ddi_pll_mode_set(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
@@ -634,6 +634,7 @@ bool intel_ddi_pll_mode_set(struct drm_crtc *crtc, int clock)
 	int type = intel_encoder->type;
 	enum pipe pipe = intel_crtc->pipe;
 	uint32_t reg, val;
+	int clock = intel_crtc->config.port_clock;
 
 	/* TODO: reuse PLLs when possible (compare values) */
 
@@ -1278,7 +1279,6 @@ static void intel_ddi_get_config(struct intel_encoder *encoder,
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
 	pipe_config->adjusted_mode.flags |= flags;
-	pipe_config->pixel_multiplier = 1;
 }
 
 static void intel_ddi_destroy(struct drm_encoder *encoder)

drivers/gpu/drm/i915/intel_dp.c

@@ -677,7 +677,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0;
 	int bpp, mode_rate;
 	static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
-	int target_clock, link_avail, link_clock;
+	int link_avail, link_clock;
 
 	if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev) && port != PORT_A)
 		pipe_config->has_pch_encoder = true;
@@ -694,8 +694,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			intel_pch_panel_fitting(intel_crtc, pipe_config,
 						intel_connector->panel.fitting_mode);
 	}
-	/* We need to take the panel's fixed mode into account. */
-	target_clock = adjusted_mode->clock;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return false;
@@ -706,12 +704,12 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 
 	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
 	 * bpc in between. */
-	bpp = min_t(int, 8*3, pipe_config->pipe_bpp);
+	bpp = pipe_config->pipe_bpp;
 	if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp)
 		bpp = min_t(int, bpp, dev_priv->vbt.edp_bpp);
 
 	for (; bpp >= 6*3; bpp -= 2*3) {
-		mode_rate = intel_dp_link_required(target_clock, bpp);
+		mode_rate = intel_dp_link_required(adjusted_mode->clock, bpp);
 
 		for (clock = 0; clock <= max_clock; clock++) {
 			for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
@@ -746,18 +744,17 @@ found:
 
 	intel_dp->link_bw = bws[clock];
 	intel_dp->lane_count = lane_count;
-	adjusted_mode->clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw);
 	pipe_config->pipe_bpp = bpp;
-	pipe_config->pixel_target_clock = target_clock;
+	pipe_config->port_clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw);
 
 	DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n",
 		      intel_dp->link_bw, intel_dp->lane_count,
-		      adjusted_mode->clock, bpp);
+		      pipe_config->port_clock, bpp);
 	DRM_DEBUG_KMS("DP link bw required %i available %i\n",
 		      mode_rate, link_avail);
 
 	intel_link_compute_m_n(bpp, lane_count,
-			       target_clock, adjusted_mode->clock,
+			       adjusted_mode->clock, pipe_config->port_clock,
 			       &pipe_config->dp_m_n);
 
 	intel_dp_set_clock(encoder, pipe_config, intel_dp->link_bw);
@@ -780,24 +777,28 @@ void intel_dp_init_link_config(struct intel_dp *intel_dp)
 	}
 }
 
-static void ironlake_set_pll_edp(struct drm_crtc *crtc, int clock)
+static void ironlake_set_pll_cpu_edp(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = crtc->dev;
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc);
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 dpa_ctl;
 
-	DRM_DEBUG_KMS("eDP PLL enable for clock %d\n", clock);
+	DRM_DEBUG_KMS("eDP PLL enable for clock %d\n", crtc->config.port_clock);
 	dpa_ctl = I915_READ(DP_A);
 	dpa_ctl &= ~DP_PLL_FREQ_MASK;
 
-	if (clock < 200000) {
+	if (crtc->config.port_clock == 162000) {
 		/* For a long time we've carried around a ILK-DevA w/a for the
 		 * 160MHz clock. If we're really unlucky, it's still required.
 		 */
 		DRM_DEBUG_KMS("160MHz cpu eDP clock, might need ilk devA w/a\n");
 		dpa_ctl |= DP_PLL_FREQ_160MHZ;
+		intel_dp->DP |= DP_PLL_FREQ_160MHZ;
 	} else {
 		dpa_ctl |= DP_PLL_FREQ_270MHZ;
+		intel_dp->DP |= DP_PLL_FREQ_270MHZ;
 	}
 
 	I915_WRITE(DP_A, dpa_ctl);
@@ -814,8 +815,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = dp_to_dig_port(intel_dp)->port;
-	struct drm_crtc *crtc = encoder->crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_crtc *crtc = to_intel_crtc(encoder->crtc);
 
 	/*
 	 * There are four kinds of DP registers:
@@ -845,7 +845,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 
 	if (intel_dp->has_audio) {
 		DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n",
-				 pipe_name(intel_crtc->pipe));
+				 pipe_name(crtc->pipe));
 		intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
 		intel_write_eld(encoder, adjusted_mode);
 	}
@@ -864,13 +864,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
-		intel_dp->DP |= intel_crtc->pipe << 29;
-
-		/* don't miss out required setting for eDP */
-		if (adjusted_mode->clock < 200000)
-			intel_dp->DP |= DP_PLL_FREQ_160MHZ;
-		else
-			intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+		intel_dp->DP |= crtc->pipe << 29;
 	} else if (!HAS_PCH_CPT(dev) || port == PORT_A) {
 		if (!HAS_PCH_SPLIT(dev) && !IS_VALLEYVIEW(dev))
 			intel_dp->DP |= intel_dp->color_range;
@@ -884,22 +878,14 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
-		if (intel_crtc->pipe == 1)
+		if (crtc->pipe == 1)
 			intel_dp->DP |= DP_PIPEB_SELECT;
-
-		if (port == PORT_A && !IS_VALLEYVIEW(dev)) {
-			/* don't miss out required setting for eDP */
-			if (adjusted_mode->clock < 200000)
-				intel_dp->DP |= DP_PLL_FREQ_160MHZ;
-			else
-				intel_dp->DP |= DP_PLL_FREQ_270MHZ;
-		}
 	} else {
 		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
 	}
 
 	if (port == PORT_A && !IS_VALLEYVIEW(dev))
-		ironlake_set_pll_edp(crtc, adjusted_mode->clock);
+		ironlake_set_pll_cpu_edp(intel_dp);
 }
 
 #define IDLE_ON_MASK		(PP_ON | 0 	  | PP_SEQUENCE_MASK | 0                     | PP_SEQUENCE_STATE_MASK)

drivers/gpu/drm/i915/intel_drv.h

@@ -140,7 +140,8 @@ struct intel_encoder {
 	 * it is connected to in the pipe parameter. */
 	bool (*get_hw_state)(struct intel_encoder *, enum pipe *pipe);
 	/* Reconstructs the equivalent mode flags for the current hardware
-	 * state. */
+	 * state. This must be called _after_ display->get_pipe_config has
+	 * pre-filled the pipe config. */
 	void (*get_config)(struct intel_encoder *,
 			   struct intel_crtc_config *pipe_config);
 	int crtc_mask;
@@ -193,6 +194,17 @@ typedef struct dpll {
 } intel_clock_t;
 
 struct intel_crtc_config {
+	/**
+	 * quirks - bitfield with hw state readout quirks
+	 *
+	 * For various reasons the hw state readout code might not be able to
+	 * completely faithfully read out the current state. These cases are
+	 * tracked with quirk flags so that fastboot and state checker can act
+	 * accordingly.
+	 */
+#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */
+	unsigned long quirks;
+
 	struct drm_display_mode requested_mode;
 	struct drm_display_mode adjusted_mode;
 	/* This flag must be set by the encoder's compute_config callback if it
@@ -241,14 +253,21 @@ struct intel_crtc_config {
 	 * haswell. */
 	struct dpll dpll;
 
+	/* Selected dpll when shared or DPLL_ID_PRIVATE. */
+	enum intel_dpll_id shared_dpll;
+
+	/* Actual register state of the dpll, for shared dpll cross-checking. */
+	struct intel_dpll_hw_state dpll_hw_state;
+
 	int pipe_bpp;
 	struct intel_link_m_n dp_m_n;
-	/**
-	 * This is currently used by DP and HDMI encoders since those can have a
-	 * target pixel clock != the port link clock (which is currently stored
-	 * in adjusted_mode->clock).
+
+	/*
+	 * Frequence the dpll for the port should run at. Differs from the
+	 * adjusted dotclock e.g. for DP or 12bpc hdmi mode.
 	 */
-	int pixel_target_clock;
+	int port_clock;
+
 	/* Used by SDVO (and if we ever fix it, HDMI). */
 	unsigned pixel_multiplier;
 
@@ -304,8 +323,6 @@ struct intel_crtc {
 
 	struct intel_crtc_config config;
 
-	/* We can share PLLs across outputs if the timings match */
-	struct intel_pch_pll *pch_pll;
 	uint32_t ddi_pll_sel;
 
 	/* reset counter value when the last flip was submitted */
@@ -562,9 +579,10 @@ extern bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg,
 extern void intel_dvo_init(struct drm_device *dev);
 extern void intel_tv_init(struct drm_device *dev);
 extern void intel_mark_busy(struct drm_device *dev);
-extern void intel_mark_fb_busy(struct drm_i915_gem_object *obj);
+extern void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
+			       struct intel_ring_buffer *ring);
 extern void intel_mark_idle(struct drm_device *dev);
-extern bool intel_lvds_init(struct drm_device *dev);
+extern void intel_lvds_init(struct drm_device *dev);
 extern bool intel_is_dual_link_lvds(struct drm_device *dev);
 extern void intel_dp_init(struct drm_device *dev, int output_reg,
 			  enum port port);
@@ -628,11 +646,11 @@ extern void intel_crtc_load_lut(struct drm_crtc *crtc);
 extern void intel_crtc_update_dpms(struct drm_crtc *crtc);
 extern void intel_encoder_destroy(struct drm_encoder *encoder);
 extern void intel_encoder_dpms(struct intel_encoder *encoder, int mode);
-extern bool intel_encoder_check_is_cloned(struct intel_encoder *encoder);
 extern void intel_connector_dpms(struct drm_connector *, int mode);
 extern bool intel_connector_get_hw_state(struct intel_connector *connector);
 extern void intel_modeset_check_state(struct drm_device *dev);
 extern void intel_plane_restore(struct drm_plane *plane);
+extern void intel_plane_disable(struct drm_plane *plane);
 
 
 static inline struct intel_encoder *intel_attached_encoder(struct drm_connector *connector)
@@ -767,6 +785,10 @@ 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);
 
+/* Power well */
+extern int i915_init_power_well(struct drm_device *dev);
+extern void i915_remove_power_well(struct drm_device *dev);
+
 extern bool intel_display_power_enabled(struct drm_device *dev,
 					enum intel_display_power_domain domain);
 extern void intel_init_power_well(struct drm_device *dev);
@@ -786,7 +808,7 @@ extern void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
 extern void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc);
 extern void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc);
 extern void intel_ddi_setup_hw_pll_state(struct drm_device *dev);
-extern bool intel_ddi_pll_mode_set(struct drm_crtc *crtc, int clock);
+extern bool intel_ddi_pll_mode_set(struct drm_crtc *crtc);
 extern void intel_ddi_put_crtc_pll(struct drm_crtc *crtc);
 extern void intel_ddi_set_pipe_settings(struct drm_crtc *crtc);
 extern void intel_ddi_prepare_link_retrain(struct drm_encoder *encoder);

drivers/gpu/drm/i915/intel_fb.c

@@ -60,8 +60,9 @@ static struct fb_ops intelfb_ops = {
 static int intelfb_create(struct drm_fb_helper *helper,
 			  struct drm_fb_helper_surface_size *sizes)
 {
-	struct intel_fbdev *ifbdev = (struct intel_fbdev *)helper;
-	struct drm_device *dev = ifbdev->helper.dev;
+	struct intel_fbdev *ifbdev =
+		container_of(helper, struct intel_fbdev, helper);
+	struct drm_device *dev = helper->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct fb_info *info;
 	struct drm_framebuffer *fb;
@@ -108,7 +109,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out_unpin;
 	}
 
-	info->par = ifbdev;
+	info->par = helper;
 
 	ret = intel_framebuffer_init(dev, &ifbdev->ifb, &mode_cmd, obj);
 	if (ret)
@@ -217,7 +218,7 @@ static void intel_fbdev_destroy(struct drm_device *dev,
 int intel_fbdev_init(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
 	ifbdev = kzalloc(sizeof(struct intel_fbdev), GFP_KERNEL);
@@ -242,7 +243,7 @@ int intel_fbdev_init(struct drm_device *dev)
 
 void intel_fbdev_initial_config(struct drm_device *dev)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	/* Due to peculiar init order wrt to hpd handling this is separate. */
 	drm_fb_helper_initial_config(&dev_priv->fbdev->helper, 32);
@@ -250,7 +251,7 @@ void intel_fbdev_initial_config(struct drm_device *dev)
 
 void intel_fbdev_fini(struct drm_device *dev)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	if (!dev_priv->fbdev)
 		return;
 
@@ -261,7 +262,7 @@ void intel_fbdev_fini(struct drm_device *dev)
 
 void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 	struct fb_info *info;
 
@@ -274,7 +275,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 	 * been restored from swap. If the object is stolen however, it will be
 	 * full of whatever garbage was left in there.
 	 */
-	if (!state && ifbdev->ifb.obj->stolen)
+	if (state == FBINFO_STATE_RUNNING && ifbdev->ifb.obj->stolen)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	fb_set_suspend(info, state);
@@ -284,14 +285,14 @@ MODULE_LICENSE("GPL and additional rights");
 
 void intel_fb_output_poll_changed(struct drm_device *dev)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
 }
 
 void intel_fb_restore_mode(struct drm_device *dev)
 {
 	int ret;
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (INTEL_INFO(dev)->num_pipes == 0)
 		return;

drivers/gpu/drm/i915/intel_hdmi.c

@@ -835,9 +835,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 		desired_bpp = 12*3;
 
 		/* Need to adjust the port link by 1.5x for 12bpc. */
-		adjusted_mode->clock = clock_12bpc;
-		pipe_config->pixel_target_clock =
-			pipe_config->requested_mode.clock;
+		pipe_config->port_clock = clock_12bpc;
 	} else {
 		DRM_DEBUG_KMS("picking bpc to 8 for HDMI output\n");
 		desired_bpp = 8*3;

drivers/gpu/drm/i915/intel_lvds.c

@@ -264,9 +264,6 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 		return false;
 	}
 
-	if (intel_encoder_check_is_cloned(&lvds_encoder->base))
-		return false;
-
 	if ((I915_READ(lvds_encoder->reg) & LVDS_A3_POWER_MASK) ==
 	    LVDS_A3_POWER_UP)
 		lvds_bpp = 8*3;
@@ -880,7 +877,7 @@ static bool intel_lvds_supported(struct drm_device *dev)
  * Create the connector, register the LVDS DDC bus, and try to figure out what
  * modes we can display on the LVDS panel (if present).
  */
-bool intel_lvds_init(struct drm_device *dev)
+void intel_lvds_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_lvds_encoder *lvds_encoder;
@@ -898,35 +895,35 @@ bool intel_lvds_init(struct drm_device *dev)
 	u8 pin;
 
 	if (!intel_lvds_supported(dev))
-		return false;
+		return;
 
 	/* Skip init on machines we know falsely report LVDS */
 	if (dmi_check_system(intel_no_lvds))
-		return false;
+		return;
 
 	pin = GMBUS_PORT_PANEL;
 	if (!lvds_is_present_in_vbt(dev, &pin)) {
 		DRM_DEBUG_KMS("LVDS is not present in VBT\n");
-		return false;
+		return;
 	}
 
 	if (HAS_PCH_SPLIT(dev)) {
 		if ((I915_READ(PCH_LVDS) & LVDS_DETECTED) == 0)
-			return false;
+			return;
 		if (dev_priv->vbt.edp_support) {
 			DRM_DEBUG_KMS("disable LVDS for eDP support\n");
-			return false;
+			return;
 		}
 	}
 
 	lvds_encoder = kzalloc(sizeof(struct intel_lvds_encoder), GFP_KERNEL);
 	if (!lvds_encoder)
-		return false;
+		return;
 
 	lvds_connector = kzalloc(sizeof(struct intel_lvds_connector), GFP_KERNEL);
 	if (!lvds_connector) {
 		kfree(lvds_encoder);
-		return false;
+		return;
 	}
 
 	lvds_encoder->attached_connector = lvds_connector;
@@ -1097,7 +1094,7 @@ out:
 	intel_panel_init(&intel_connector->panel, fixed_mode);
 	intel_panel_setup_backlight(connector);
 
-	return true;
+	return;
 
 failed:
 	DRM_DEBUG_KMS("No LVDS modes found, disabling.\n");
@@ -1107,5 +1104,5 @@ failed:
 		drm_mode_destroy(dev, fixed_mode);
 	kfree(lvds_encoder);
 	kfree(lvds_connector);
-	return false;
+	return;
 }

drivers/gpu/drm/i915/intel_opregion.c

@@ -312,7 +312,7 @@ static void intel_didl_outputs(struct drm_device *dev)
 	list_for_each_entry(acpi_cdev, &acpi_video_bus->children, node) {
 		if (i >= 8) {
 			dev_printk(KERN_ERR, &dev->pdev->dev,
-				    "More than 8 outputs detected\n");
+				   "More than 8 outputs detected via ACPI\n");
 			return;
 		}
 		status =
@@ -339,7 +339,7 @@ blind_set:
 		int output_type = ACPI_OTHER_OUTPUT;
 		if (i >= 8) {
 			dev_printk(KERN_ERR, &dev->pdev->dev,
-				    "More than 8 outputs detected\n");
+				   "More than 8 outputs in connector list\n");
 			return;
 		}
 		switch (connector->connector_type) {

drivers/gpu/drm/i915/intel_overlay.c

@@ -217,7 +217,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 	int ret;
 
 	BUG_ON(overlay->last_flip_req);
-	ret = i915_add_request(ring, NULL, &overlay->last_flip_req);
+	ret = i915_add_request(ring, &overlay->last_flip_req);
 	if (ret)
 		return ret;
 
@@ -286,7 +286,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
 	intel_ring_emit(ring, flip_addr);
 	intel_ring_advance(ring);
 
-	return i915_add_request(ring, NULL, &overlay->last_flip_req);
+	return i915_add_request(ring, &overlay->last_flip_req);
 }
 
 static void intel_overlay_release_old_vid_tail(struct intel_overlay *overlay)

drivers/gpu/drm/i915/intel_pm.c

@@ -274,7 +274,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID);
+	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset);
 
 	I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X |
 		   IVB_DPFC_CTL_FENCE_EN |
@@ -431,7 +431,7 @@ void intel_disable_fbc(struct drm_device *dev)
  *   - no pixel mulitply/line duplication
  *   - no alpha buffer discard
  *   - no dual wide
- *   - framebuffer <= 2048 in width, 1536 in height
+ *   - framebuffer <= max_hdisplay in width, max_vdisplay in height
  *
  * We can't assume that any compression will take place (worst case),
  * so the compressed buffer has to be the same size as the uncompressed
@@ -449,6 +449,7 @@ void intel_update_fbc(struct drm_device *dev)
 	struct intel_framebuffer *intel_fb;
 	struct drm_i915_gem_object *obj;
 	int enable_fbc;
+	unsigned int max_hdisplay, max_vdisplay;
 
 	if (!i915_powersave)
 		return;
@@ -507,8 +508,16 @@ void intel_update_fbc(struct drm_device *dev)
 		dev_priv->no_fbc_reason = FBC_UNSUPPORTED_MODE;
 		goto out_disable;
 	}
-	if ((crtc->mode.hdisplay > 2048) ||
-	    (crtc->mode.vdisplay > 1536)) {
+
+	if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) {
+		max_hdisplay = 4096;
+		max_vdisplay = 2048;
+	} else {
+		max_hdisplay = 2048;
+		max_vdisplay = 1536;
+	}
+	if ((crtc->mode.hdisplay > max_hdisplay) ||
+	    (crtc->mode.vdisplay > max_vdisplay)) {
 		DRM_DEBUG_KMS("mode too large for compression, disabling\n");
 		dev_priv->no_fbc_reason = FBC_MODE_TOO_LARGE;
 		goto out_disable;
@@ -2078,10 +2087,7 @@ static uint32_t hsw_wm_get_pixel_rate(struct drm_device *dev,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t pixel_rate, pfit_size;
 
-	if (intel_crtc->config.pixel_target_clock)
-		pixel_rate = intel_crtc->config.pixel_target_clock;
-	else
-		pixel_rate = intel_crtc->config.adjusted_mode.clock;
+	pixel_rate = intel_crtc->config.adjusted_mode.clock;
 
 	/* We only use IF-ID interlacing. If we ever use PF-ID we'll need to
 	 * adjust the pixel_rate here. */
@@ -4381,6 +4387,19 @@ static void ibx_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE);
 }
 
+static void g4x_disable_trickle_feed(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe;
+
+	for_each_pipe(pipe) {
+		I915_WRITE(DSPCNTR(pipe),
+			   I915_READ(DSPCNTR(pipe)) |
+			   DISPPLANE_TRICKLE_FEED_DISABLE);
+		intel_flush_display_plane(dev_priv, pipe);
+	}
+}
+
 static void ironlake_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4444,6 +4463,8 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(CACHE_MODE_0,
 		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
 
+	g4x_disable_trickle_feed(dev);
+
 	ibx_init_clock_gating(dev);
 }
 
@@ -4498,7 +4519,6 @@ static void gen6_check_mch_setup(struct drm_device *dev)
 static void gen6_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipe;
 	uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
 
 	I915_WRITE(ILK_DSPCLK_GATE_D, dspclk_gate);
@@ -4574,12 +4594,7 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
 		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
 
-	for_each_pipe(pipe) {
-		I915_WRITE(DSPCNTR(pipe),
-			   I915_READ(DSPCNTR(pipe)) |
-			   DISPPLANE_TRICKLE_FEED_DISABLE);
-		intel_flush_display_plane(dev_priv, pipe);
-	}
+	g4x_disable_trickle_feed(dev);
 
 	/* The default value should be 0x200 according to docs, but the two
 	 * platforms I checked have a 0 for this. (Maybe BIOS overrides?) */
@@ -4640,7 +4655,6 @@ static void lpt_suspend_hw(struct drm_device *dev)
 static void haswell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipe;
 
 	I915_WRITE(WM3_LP_ILK, 0);
 	I915_WRITE(WM2_LP_ILK, 0);
@@ -4666,12 +4680,7 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 			GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	for_each_pipe(pipe) {
-		I915_WRITE(DSPCNTR(pipe),
-			   I915_READ(DSPCNTR(pipe)) |
-			   DISPPLANE_TRICKLE_FEED_DISABLE);
-		intel_flush_display_plane(dev_priv, pipe);
-	}
+	g4x_disable_trickle_feed(dev);
 
 	/* WaVSRefCountFullforceMissDisable:hsw */
 	gen7_setup_fixed_func_scheduler(dev_priv);
@@ -4697,7 +4706,6 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 static void ivybridge_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipe;
 	uint32_t snpcr;
 
 	I915_WRITE(WM3_LP_ILK, 0);
@@ -4766,12 +4774,7 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 			GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	for_each_pipe(pipe) {
-		I915_WRITE(DSPCNTR(pipe),
-			   I915_READ(DSPCNTR(pipe)) |
-			   DISPPLANE_TRICKLE_FEED_DISABLE);
-		intel_flush_display_plane(dev_priv, pipe);
-	}
+	g4x_disable_trickle_feed(dev);
 
 	/* WaMbcDriverBootEnable:ivb */
 	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
@@ -4798,13 +4801,8 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 static void valleyview_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipe;
-
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
 
-	I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
+	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableEarlyCull:vlv */
 	I915_WRITE(_3D_CHICKEN3,
@@ -4875,12 +4873,7 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 
 	I915_WRITE(GEN7_UCGCTL4, GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
 
-	for_each_pipe(pipe) {
-		I915_WRITE(DSPCNTR(pipe),
-			   I915_READ(DSPCNTR(pipe)) |
-			   DISPPLANE_TRICKLE_FEED_DISABLE);
-		intel_flush_display_plane(dev_priv, pipe);
-	}
+	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
 
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
@@ -4922,6 +4915,8 @@ static void g4x_init_clock_gating(struct drm_device *dev)
 	/* WaDisableRenderCachePipelinedFlush */
 	I915_WRITE(CACHE_MODE_0,
 		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
+
+	g4x_disable_trickle_feed(dev);
 }
 
 static void crestline_init_clock_gating(struct drm_device *dev)
@@ -4933,6 +4928,8 @@ static void crestline_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(DSPCLK_GATE_D, 0);
 	I915_WRITE(RAMCLK_GATE_D, 0);
 	I915_WRITE16(DEUC, 0);
+	I915_WRITE(MI_ARB_STATE,
+		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
 }
 
 static void broadwater_init_clock_gating(struct drm_device *dev)
@@ -4945,6 +4942,8 @@ static void broadwater_init_clock_gating(struct drm_device *dev)
 		   I965_ISC_CLOCK_GATE_DISABLE |
 		   I965_FBC_CLOCK_GATE_DISABLE);
 	I915_WRITE(RENCLK_GATE_D2, 0);
+	I915_WRITE(MI_ARB_STATE,
+		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
 }
 
 static void gen3_init_clock_gating(struct drm_device *dev)
@@ -5022,18 +5021,12 @@ bool intel_display_power_enabled(struct drm_device *dev,
 	}
 }
 
-void intel_set_power_well(struct drm_device *dev, bool enable)
+static void __intel_set_power_well(struct drm_device *dev, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool is_enabled, enable_requested;
 	uint32_t tmp;
 
-	if (!HAS_POWER_WELL(dev))
-		return;
-
-	if (!i915_disable_power_well && !enable)
-		return;
-
 	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
 	is_enabled = tmp & HSW_PWR_WELL_STATE;
 	enable_requested = tmp & HSW_PWR_WELL_ENABLE;
@@ -5056,6 +5049,79 @@ void intel_set_power_well(struct drm_device *dev, bool enable)
 	}
 }
 
+static struct i915_power_well *hsw_pwr;
+
+/* Display audio driver power well request */
+void i915_request_power_well(void)
+{
+	if (WARN_ON(!hsw_pwr))
+		return;
+
+	spin_lock_irq(&hsw_pwr->lock);
+	if (!hsw_pwr->count++ &&
+			!hsw_pwr->i915_request)
+		__intel_set_power_well(hsw_pwr->device, true);
+	spin_unlock_irq(&hsw_pwr->lock);
+}
+EXPORT_SYMBOL_GPL(i915_request_power_well);
+
+/* Display audio driver power well release */
+void i915_release_power_well(void)
+{
+	if (WARN_ON(!hsw_pwr))
+		return;
+
+	spin_lock_irq(&hsw_pwr->lock);
+	WARN_ON(!hsw_pwr->count);
+	if (!--hsw_pwr->count &&
+		       !hsw_pwr->i915_request)
+		__intel_set_power_well(hsw_pwr->device, false);
+	spin_unlock_irq(&hsw_pwr->lock);
+}
+EXPORT_SYMBOL_GPL(i915_release_power_well);
+
+int i915_init_power_well(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	hsw_pwr = &dev_priv->power_well;
+
+	hsw_pwr->device = dev;
+	spin_lock_init(&hsw_pwr->lock);
+	hsw_pwr->count = 0;
+
+	return 0;
+}
+
+void i915_remove_power_well(struct drm_device *dev)
+{
+	hsw_pwr = NULL;
+}
+
+void intel_set_power_well(struct drm_device *dev, bool enable)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_power_well *power_well = &dev_priv->power_well;
+
+	if (!HAS_POWER_WELL(dev))
+		return;
+
+	if (!i915_disable_power_well && !enable)
+		return;
+
+	spin_lock_irq(&power_well->lock);
+	power_well->i915_request = enable;
+
+	/* only reject "disable" power well request */
+	if (power_well->count && !enable) {
+		spin_unlock_irq(&power_well->lock);
+		return;
+	}
+
+	__intel_set_power_well(dev, enable);
+	spin_unlock_irq(&power_well->lock);
+}
+
 /*
  * Starting with Haswell, we have a "Power Down Well" that can be turned off
  * when not needed anymore. We have 4 registers that can request the power well

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -280,6 +280,27 @@ gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring)
 	return 0;
 }
 
+static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value)
+{
+	int ret;
+
+	if (!ring->fbc_dirty)
+		return 0;
+
+	ret = intel_ring_begin(ring, 4);
+	if (ret)
+		return ret;
+	intel_ring_emit(ring, MI_NOOP);
+	/* WaFbcNukeOn3DBlt:ivb/hsw */
+	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+	intel_ring_emit(ring, MSG_FBC_REND_STATE);
+	intel_ring_emit(ring, value);
+	intel_ring_advance(ring);
+
+	ring->fbc_dirty = false;
+	return 0;
+}
+
 static int
 gen7_render_ring_flush(struct intel_ring_buffer *ring,
 		       u32 invalidate_domains, u32 flush_domains)
@@ -336,6 +357,9 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
+	if (flush_domains)
+		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
+
 	return 0;
 }
 
@@ -429,6 +453,8 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		ring->last_retired_head = -1;
 	}
 
+	memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
+
 out:
 	if (HAS_FORCE_WAKE(dev))
 		gen6_gt_force_wake_put(dev_priv);
@@ -1486,7 +1512,7 @@ int intel_ring_idle(struct intel_ring_buffer *ring)
 
 	/* We need to add any requests required to flush the objects and ring */
 	if (ring->outstanding_lazy_request) {
-		ret = i915_add_request(ring, NULL, NULL);
+		ret = i915_add_request(ring, NULL);
 		if (ret)
 			return ret;
 	}
@@ -1685,6 +1711,7 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 static int gen6_ring_flush(struct intel_ring_buffer *ring,
 			   u32 invalidate, u32 flush)
 {
+	struct drm_device *dev = ring->dev;
 	uint32_t cmd;
 	int ret;
 
@@ -1707,6 +1734,10 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, 0);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
+
+	if (IS_GEN7(dev) && flush)
+		return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
+
 	return 0;
 }
 

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -37,8 +37,14 @@ struct  intel_hw_status_page {
 #define I915_READ_SYNC_0(ring) I915_READ(RING_SYNC_0((ring)->mmio_base))
 #define I915_READ_SYNC_1(ring) I915_READ(RING_SYNC_1((ring)->mmio_base))
 
+enum intel_ring_hangcheck_action { wait, active, kick, hung };
+
 struct intel_ring_hangcheck {
+	bool deadlock;
 	u32 seqno;
+	u32 acthd;
+	int score;
+	enum intel_ring_hangcheck_action action;
 };
 
 struct  intel_ring_buffer {
@@ -138,6 +144,7 @@ struct  intel_ring_buffer {
 	 */
 	u32 outstanding_lazy_request;
 	bool gpu_caches_dirty;
+	bool fbc_dirty;
 
 	wait_queue_head_t irq_queue;
 

drivers/gpu/drm/i915/intel_sdvo.c

@@ -80,7 +80,7 @@ struct intel_sdvo {
 
 	/*
 	 * Capabilities of the SDVO device returned by
-	 * i830_sdvo_get_capabilities()
+	 * intel_sdvo_get_capabilities()
 	 */
 	struct intel_sdvo_caps caps;
 
@@ -1219,6 +1219,7 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 
 	switch (intel_crtc->config.pixel_multiplier) {
 	default:
+		WARN(1, "unknown pixel mutlipler specified\n");
 	case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break;
 	case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break;
 	case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break;
@@ -1276,7 +1277,7 @@ 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);
-	u16 active_outputs;
+	u16 active_outputs = 0;
 
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
@@ -1292,7 +1293,7 @@ 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;
+	u16 active_outputs = 0;
 	u32 tmp;
 
 	tmp = I915_READ(intel_sdvo->sdvo_reg);
@@ -1312,28 +1313,69 @@ static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 static void intel_sdvo_get_config(struct intel_encoder *encoder,
 				  struct intel_crtc_config *pipe_config)
 {
+	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);
 	struct intel_sdvo_dtd dtd;
-	u32 flags = 0;
+	int encoder_pixel_multiplier = 0;
+	u32 flags = 0, sdvox;
+	u8 val;
 	bool ret;
 
 	ret = intel_sdvo_get_input_timing(intel_sdvo, &dtd);
 	if (!ret) {
+		/* Some sdvo encoders are not spec compliant and don't
+		 * implement the mandatory get_timings function. */
 		DRM_DEBUG_DRIVER("failed to retrieve SDVO DTD\n");
-		return;
+		pipe_config->quirks |= PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS;
+	} else {
+		if (dtd.part2.dtd_flags & DTD_FLAG_HSYNC_POSITIVE)
+			flags |= DRM_MODE_FLAG_PHSYNC;
+		else
+			flags |= DRM_MODE_FLAG_NHSYNC;
+
+		if (dtd.part2.dtd_flags & DTD_FLAG_VSYNC_POSITIVE)
+			flags |= DRM_MODE_FLAG_PVSYNC;
+		else
+			flags |= DRM_MODE_FLAG_NVSYNC;
 	}
 
-	if (dtd.part2.dtd_flags & DTD_FLAG_HSYNC_POSITIVE)
-		flags |= DRM_MODE_FLAG_PHSYNC;
-	else
-		flags |= DRM_MODE_FLAG_NHSYNC;
+	pipe_config->adjusted_mode.flags |= flags;
 
-	if (dtd.part2.dtd_flags & DTD_FLAG_VSYNC_POSITIVE)
-		flags |= DRM_MODE_FLAG_PVSYNC;
-	else
-		flags |= DRM_MODE_FLAG_NVSYNC;
+	/*
+	 * pixel multiplier readout is tricky: Only on i915g/gm it is stored in
+	 * the sdvo port register, on all other platforms it is part of the dpll
+	 * state. Since the general pipe state readout happens before the
+	 * encoder->get_config we so already have a valid pixel multplier on all
+	 * other platfroms.
+	 */
+	if (IS_I915G(dev) || IS_I915GM(dev)) {
+		sdvox = I915_READ(intel_sdvo->sdvo_reg);
+		pipe_config->pixel_multiplier =
+			((sdvox & SDVO_PORT_MULTIPLY_MASK)
+			 >> SDVO_PORT_MULTIPLY_SHIFT) + 1;
+	}
 
-	pipe_config->adjusted_mode.flags |= flags;
+	/* Cross check the port pixel multiplier with the sdvo encoder state. */
+	intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT, &val, 1);
+	switch (val) {
+	case SDVO_CLOCK_RATE_MULT_1X:
+		encoder_pixel_multiplier = 1;
+		break;
+	case SDVO_CLOCK_RATE_MULT_2X:
+		encoder_pixel_multiplier = 2;
+		break;
+	case SDVO_CLOCK_RATE_MULT_4X:
+		encoder_pixel_multiplier = 4;
+		break;
+	}
+
+	if(HAS_PCH_SPLIT(dev))
+		return; /* no pixel multiplier readout support yet */
+
+	WARN(encoder_pixel_multiplier != pipe_config->pixel_multiplier,
+	     "SDVO pixel multiplier mismatch, port: %i, encoder: %i\n",
+	     pipe_config->pixel_multiplier, encoder_pixel_multiplier);
 }
 
 static void intel_disable_sdvo(struct intel_encoder *encoder)
@@ -2819,7 +2861,6 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_encoder *intel_encoder;
 	struct intel_sdvo *intel_sdvo;
-	u32 hotplug_mask;
 	int i;
 	intel_sdvo = kzalloc(sizeof(struct intel_sdvo), GFP_KERNEL);
 	if (!intel_sdvo)
@@ -2848,18 +2889,6 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 		}
 	}
 
-	hotplug_mask = 0;
-	if (IS_G4X(dev)) {
-		hotplug_mask = intel_sdvo->is_sdvob ?
-			SDVOB_HOTPLUG_INT_STATUS_G4X : SDVOC_HOTPLUG_INT_STATUS_G4X;
-	} else if (IS_GEN4(dev)) {
-		hotplug_mask = intel_sdvo->is_sdvob ?
-			SDVOB_HOTPLUG_INT_STATUS_I965 : SDVOC_HOTPLUG_INT_STATUS_I965;
-	} else {
-		hotplug_mask = intel_sdvo->is_sdvob ?
-			SDVOB_HOTPLUG_INT_STATUS_I915 : SDVOC_HOTPLUG_INT_STATUS_I915;
-	}
-
 	intel_encoder->compute_config = intel_sdvo_compute_config;
 	intel_encoder->disable = intel_disable_sdvo;
 	intel_encoder->mode_set = intel_sdvo_mode_set;

drivers/gpu/drm/i915/intel_sprite.c

@@ -957,6 +957,14 @@ void intel_plane_restore(struct drm_plane *plane)
 			   intel_plane->src_w, intel_plane->src_h);
 }
 
+void intel_plane_disable(struct drm_plane *plane)
+{
+	if (!plane->crtc || !plane->fb)
+		return;
+
+	intel_disable_plane(plane);
+}
+
 static const struct drm_plane_funcs intel_plane_funcs = {
 	.update_plane = intel_update_plane,
 	.disable_plane = intel_disable_plane,

drivers/gpu/drm/i915/intel_tv.c

@@ -914,9 +914,6 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 	if (!tv_mode)
 		return false;
 
-	if (intel_encoder_check_is_cloned(&intel_tv->base))
-		return false;
-
 	pipe_config->adjusted_mode.clock = tv_mode->clock;
 	DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
 	pipe_config->pipe_bpp = 8*3;

include/drm/i915_powerwell.h

@@ -0,0 +1,36 @@
+/**************************************************************************
+ *
+ * Copyright 2013 Intel Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ **************************************************************************/
+
+#ifndef _I915_POWERWELL_H_
+#define _I915_POWERWELL_H_
+
+/* For use by hda_i915 driver */
+extern void i915_request_power_well(void);
+extern void i915_release_power_well(void);
+
+#endif				/* _I915_POWERWELL_H_ */

sound/pci/hda/Kconfig

@@ -152,6 +152,16 @@ config SND_HDA_CODEC_HDMI
 	  snd-hda-codec-hdmi.
 	  This module is automatically loaded at probing.
 
+config SND_HDA_I915
+	bool "Build Display HD-audio controller/codec power well support for i915 cards"
+	depends on DRM_I915
+	help
+	  Say Y here to include full HDMI and DisplayPort HD-audio controller/codec
+	  power-well support for Intel Haswell graphics cards based on the i915 driver.
+
+	  Note that this option must be enabled for Intel Haswell C+ stepping machines, otherwise
+	  the GPU audio controller/codecs will not be initialized or damaged when exit from S3 mode.
+
 config SND_HDA_CODEC_CIRRUS
 	bool "Build Cirrus Logic codec support"
 	default y

sound/pci/hda/Makefile

@@ -1,4 +1,6 @@
 snd-hda-intel-objs := hda_intel.o
+# for haswell power well
+snd-hda-intel-$(CONFIG_SND_HDA_I915) +=	hda_i915.o
 
 snd-hda-codec-y := hda_codec.o hda_jack.o hda_auto_parser.o
 snd-hda-codec-$(CONFIG_SND_HDA_GENERIC) += hda_generic.o

sound/pci/hda/hda_i915.c

@@ -0,0 +1,75 @@
+/*
+ *  hda_i915.c - routines for Haswell HDA controller power well support
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the Free
+ *  Software Foundation; either version 2 of the License, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ *  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ *  for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software Foundation,
+ *  Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <sound/core.h>
+#include <drm/i915_powerwell.h>
+#include "hda_i915.h"
+
+static void (*get_power)(void);
+static void (*put_power)(void);
+
+void hda_display_power(bool enable)
+{
+	if (!get_power || !put_power)
+		return;
+
+	snd_printdd("HDA display power %s \n",
+			enable ? "Enable" : "Disable");
+	if (enable)
+		get_power();
+	else
+		put_power();
+}
+
+int hda_i915_init(void)
+{
+	int err = 0;
+
+	get_power = symbol_request(i915_request_power_well);
+	if (!get_power) {
+		snd_printk(KERN_WARNING "hda-i915: get_power symbol get fail\n");
+		return -ENODEV;
+	}
+
+	put_power = symbol_request(i915_release_power_well);
+	if (!put_power) {
+		symbol_put(i915_request_power_well);
+		get_power = NULL;
+		return -ENODEV;
+	}
+
+	snd_printd("HDA driver get symbol successfully from i915 module\n");
+
+	return err;
+}
+
+int hda_i915_exit(void)
+{
+	if (get_power) {
+		symbol_put(i915_request_power_well);
+		get_power = NULL;
+	}
+	if (put_power) {
+		symbol_put(i915_release_power_well);
+		put_power = NULL;
+	}
+
+	return 0;
+}

sound/pci/hda/hda_i915.h

@@ -0,0 +1,35 @@
+/*
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the Free
+ *  Software Foundation; either version 2 of the License, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *  more details.
+ *
+ *  You should have received a copy of the GNU General Public License along with
+ *  this program; if not, write to the Free Software Foundation, Inc., 59
+ *  Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+#ifndef __SOUND_HDA_I915_H
+#define __SOUND_HDA_I915_H
+
+#ifdef CONFIG_SND_HDA_I915
+void hda_display_power(bool enable);
+int hda_i915_init(void);
+int hda_i915_exit(void);
+#else
+static inline void hda_display_power(bool enable) {}
+static inline int hda_i915_init(void)
+{
+	return -ENODEV;
+}
+static inline int hda_i915_exit(void)
+{
+	return 0;
+}
+#endif
+
+#endif

sound/pci/hda/hda_intel.c

@@ -62,6 +62,7 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/firmware.h>
 #include "hda_codec.h"
+#include "hda_i915.h"
 
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
@@ -541,6 +542,10 @@ struct azx {
 	/* for pending irqs */
 	struct work_struct irq_pending_work;
 
+#ifdef CONFIG_SND_HDA_I915
+	struct work_struct probe_work;
+#endif
+
 	/* reboot notifier (for mysterious hangup problem at power-down) */
 	struct notifier_block reboot_notifier;
 
@@ -594,6 +599,7 @@ enum {
 #define AZX_DCAPS_4K_BDLE_BOUNDARY (1 << 23)	/* BDLE in 4k boundary */
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
+#define AZX_DCAPS_I915_POWERWELL (1 << 27)	/* HSW i915 power well support */
 
 /* quirks for Intel PCH */
 #define AZX_DCAPS_INTEL_PCH_NOPM \
@@ -2900,6 +2906,8 @@ static int azx_suspend(struct device *dev)
 	pci_disable_device(pci);
 	pci_save_state(pci);
 	pci_set_power_state(pci, PCI_D3hot);
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+		hda_display_power(false);
 	return 0;
 }
 
@@ -2912,6 +2920,8 @@ static int azx_resume(struct device *dev)
 	if (chip->disabled)
 		return 0;
 
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+		hda_display_power(true);
 	pci_set_power_state(pci, PCI_D0);
 	pci_restore_state(pci);
 	if (pci_enable_device(pci) < 0) {
@@ -2944,6 +2954,8 @@ static int azx_runtime_suspend(struct device *dev)
 
 	azx_stop_chip(chip);
 	azx_clear_irq_pending(chip);
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+		hda_display_power(false);
 	return 0;
 }
 
@@ -2952,6 +2964,8 @@ static int azx_runtime_resume(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+		hda_display_power(true);
 	azx_init_pci(chip);
 	azx_init_chip(chip, 1);
 	return 0;
@@ -3006,7 +3020,6 @@ static void azx_notifier_unregister(struct azx *chip)
 		unregister_reboot_notifier(&chip->reboot_notifier);
 }
 
-static int azx_first_init(struct azx *chip);
 static int azx_probe_continue(struct azx *chip);
 
 #ifdef SUPPORT_VGA_SWITCHEROO
@@ -3033,8 +3046,7 @@ static void azx_vs_set_state(struct pci_dev *pci,
 			snd_printk(KERN_INFO SFX
 				   "%s: Start delayed initialization\n",
 				   pci_name(chip->pci));
-			if (azx_first_init(chip) < 0 ||
-			    azx_probe_continue(chip) < 0) {
+			if (azx_probe_continue(chip) < 0) {
 				snd_printk(KERN_ERR SFX
 					   "%s: initialization error\n",
 					   pci_name(chip->pci));
@@ -3120,8 +3132,13 @@ static int register_vga_switcheroo(struct azx *chip)
  */
 static int azx_free(struct azx *chip)
 {
+	struct pci_dev *pci = chip->pci;
 	int i;
 
+	if ((chip->driver_caps & AZX_DCAPS_PM_RUNTIME)
+			&& chip->running)
+		pm_runtime_get_noresume(&pci->dev);
+
 	azx_del_card_list(chip);
 
 	azx_notifier_unregister(chip);
@@ -3173,6 +3190,10 @@ static int azx_free(struct azx *chip)
 	if (chip->fw)
 		release_firmware(chip->fw);
 #endif
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+		hda_display_power(false);
+		hda_i915_exit();
+	}
 	kfree(chip);
 
 	return 0;
@@ -3398,6 +3419,13 @@ static void azx_check_snoop_available(struct azx *chip)
 	}
 }
 
+#ifdef CONFIG_SND_HDA_I915
+static void azx_probe_work(struct work_struct *work)
+{
+	azx_probe_continue(container_of(work, struct azx, probe_work));
+}
+#endif
+
 /*
  * constructor
  */
@@ -3473,7 +3501,13 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 		return err;
 	}
 
+#ifdef CONFIG_SND_HDA_I915
+	/* continue probing in work context as may trigger request module */
+	INIT_WORK(&chip->probe_work, azx_probe_work);
+#endif
+
 	*rchip = chip;
+
 	return 0;
 }
 
@@ -3730,11 +3764,6 @@ static int azx_probe(struct pci_dev *pci,
 	}
 
 	probe_now = !chip->disabled;
-	if (probe_now) {
-		err = azx_first_init(chip);
-		if (err < 0)
-			goto out_free;
-	}
 
 #ifdef CONFIG_SND_HDA_PATCH_LOADER
 	if (patch[dev] && *patch[dev]) {
@@ -3749,15 +3778,22 @@ static int azx_probe(struct pci_dev *pci,
 	}
 #endif /* CONFIG_SND_HDA_PATCH_LOADER */
 
+	/* continue probing in work context, avoid request_module deadlock */
+	if (probe_now && (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)) {
+#ifdef CONFIG_SND_HDA_I915
+		probe_now = false;
+		schedule_work(&chip->probe_work);
+#else
+		snd_printk(KERN_ERR SFX "Haswell must build in CONFIG_SND_HDA_I915\n");
+#endif
+	}
+
 	if (probe_now) {
 		err = azx_probe_continue(chip);
 		if (err < 0)
 			goto out_free;
 	}
 
-	if (pci_dev_run_wake(pci))
-		pm_runtime_put_noidle(&pci->dev);
-
 	dev++;
 	complete_all(&chip->probe_wait);
 	return 0;
@@ -3770,9 +3806,24 @@ out_free:
 
 static int azx_probe_continue(struct azx *chip)
 {
+	struct pci_dev *pci = chip->pci;
 	int dev = chip->dev_index;
 	int err;
 
+	/* Request power well for Haswell HDA controller and codec */
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+		err = hda_i915_init();
+		if (err < 0) {
+			snd_printk(KERN_ERR SFX "Error request power-well from i915\n");
+			goto out_free;
+		}
+		hda_display_power(true);
+	}
+
+	err = azx_first_init(chip);
+	if (err < 0)
+		goto out_free;
+
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
 	chip->beep_mode = beep_mode[dev];
 #endif
@@ -3817,6 +3868,8 @@ static int azx_probe_continue(struct azx *chip)
 	power_down_all_codecs(chip);
 	azx_notifier_register(chip);
 	azx_add_card_list(chip);
+	if (chip->driver_caps & AZX_DCAPS_PM_RUNTIME)
+		pm_runtime_put_noidle(&pci->dev);
 
 	return 0;
 
@@ -3829,9 +3882,6 @@ static void azx_remove(struct pci_dev *pci)
 {
 	struct snd_card *card = pci_get_drvdata(pci);
 
-	if (pci_dev_run_wake(pci))
-		pm_runtime_get_noresume(&pci->dev);
-
 	if (card)
 		snd_card_free(card);
 	pci_set_drvdata(pci, NULL);
@@ -3864,11 +3914,14 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Haswell */
 	{ PCI_DEVICE(0x8086, 0x0a0c),
-	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH |
+	  AZX_DCAPS_I915_POWERWELL },
 	{ PCI_DEVICE(0x8086, 0x0c0c),
-	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH |
+	  AZX_DCAPS_I915_POWERWELL },
 	{ PCI_DEVICE(0x8086, 0x0d0c),
-	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH |
+	  AZX_DCAPS_I915_POWERWELL },
 	/* 5 Series/3400 */
 	{ PCI_DEVICE(0x8086, 0x3b56),
 	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },