Merge tag 'drm-intel-next-fixes-2014-10-03' of git://anongit.freedesktop.org/drm-intel into drm-next

Bunch of fixes for 3.18. Major parts:
- ppgtt fixes (but full ppgtt is for 3.19) from Chris, Michel, ...
- hdmi pixel replication fixes (Clint Taylor)
- leftover i830M patches from Ville
- small things all over

* tag 'drm-intel-next-fixes-2014-10-03' of git://anongit.freedesktop.org/drm-intel: (21 commits)
  drm/i915: Enable pixel replicated modes on BDW and HSW.
  drm/i915: Don't spam dmesg with rps messages on vlv/chv
  drm/i915: Do not leak pages when freeing userptr objects
  drm/i915: Do not store the error pointer for a failed userptr registration
  Revert "drm/i915/bdw: BDW Software Turbo"
  drm/i915/bdw: Cleanup pre prod workarounds
  drm/i915: Use EIO instead of EAGAIN for sink CRC error.
  drm/i915: Extend BIOS stolen mem handling to all platform
  drm/i915: Match GTT space sanity checker with implementation
  drm/i915: HSW always use GGTT selector for secure batches
  drm/i915: add cherryview specfic forcewake in execlists_elsp_write
  drm/i915: fix another use-after-free in i915_gem_evict_everything
  drm/i915: Don't reinit hpd interrupts after gpu reset
  drm/i915: Wrap -EIO send-vblank event for failed pageflip in spinlock
  drm/i915: Drop any active reference before unbinding
  drm/i915: Objects on the unbound list may still have an active reference
  drm/i915/edp: use lane count and link rate from DPCD for eDP
  drm/i915/dp: add missing \n in the TPS3 debug message
  drm/i915/hdmi, dp: Do not dereference the encoder in the connector destroy
  drm/i915: Limit the watermark to at least 8 entries on gen2/3
  ...

15 files changed, 297 insertions, 399 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2cbc85f3b237..063b44817e08 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3826,7 +3826,6 @@ i915_drop_caches_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj, *next;
 	int ret;
 
 	DRM_DEBUG("Dropping caches: 0x%08llx\n", val);
@@ -3846,36 +3845,11 @@ i915_drop_caches_set(void *data, u64 val)
 	if (val & (DROP_RETIRE | DROP_ACTIVE))
 		i915_gem_retire_requests(dev);
 
-	if (val & DROP_BOUND) {
-		list_for_each_entry_safe(obj, next, &dev_priv->mm.bound_list,
-					 global_list) {
-			struct i915_vma *vma, *v;
+	if (val & DROP_BOUND)
+		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
 
-			ret = 0;
-			drm_gem_object_reference(&obj->base);
-			list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link) {
-				if (vma->pin_count)
-					continue;
-
-				ret = i915_vma_unbind(vma);
-				if (ret)
-					break;
-			}
-			drm_gem_object_unreference(&obj->base);
-			if (ret)
-				goto unlock;
-		}
-	}
-
-	if (val & DROP_UNBOUND) {
-		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)
-					goto unlock;
-			}
-	}
+	if (val & DROP_UNBOUND)
+		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND);
 
 unlock:
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 3870c7359a16..055d5e7fbf12 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -871,8 +871,6 @@ int i915_reset(struct drm_device *dev)
 		 */
 		if (INTEL_INFO(dev)->gen > 5)
 			intel_reset_gt_powersave(dev);
-
-		intel_hpd_init(dev);
 	} else {
 		mutex_unlock(&dev->struct_mutex);
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 19c0dd8e255e..16a6f6d187a1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -946,23 +946,6 @@ struct intel_rps_ei {
 	u32 media_c0;
 };
 
-struct intel_rps_bdw_cal {
-	u32 it_threshold_pct; /* interrupt, in percentage */
-	u32 eval_interval; /* evaluation interval, in us */
-	u32 last_ts;
-	u32 last_c0;
-	bool is_up;
-};
-
-struct intel_rps_bdw_turbo {
-	struct intel_rps_bdw_cal up;
-	struct intel_rps_bdw_cal down;
-	struct timer_list flip_timer;
-	u32 timeout;
-	atomic_t flip_received;
-	struct work_struct work_max_freq;
-};
-
 struct intel_gen6_power_mgmt {
 	/* work and pm_iir are protected by dev_priv->irq_lock */
 	struct work_struct work;
@@ -996,9 +979,6 @@ struct intel_gen6_power_mgmt {
 	bool enabled;
 	struct delayed_work delayed_resume_work;
 
-	bool is_bdw_sw_turbo;	/* Switch of BDW software turbo */
-	struct intel_rps_bdw_turbo sw_turbo; /* Calculate RP interrupt timing */
-
 	/* manual wa residency calculations */
 	struct intel_rps_ei up_ei, down_ei;
 
@@ -2369,6 +2349,12 @@ int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 void i915_gem_load(struct drm_device *dev);
+unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
+			      long target,
+			      unsigned flags);
+#define I915_SHRINK_PURGEABLE 0x1
+#define I915_SHRINK_UNBOUND 0x2
+#define I915_SHRINK_BOUND 0x4
 void *i915_gem_object_alloc(struct drm_device *dev);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
@@ -2823,8 +2809,6 @@ extern void intel_disable_fbc(struct drm_device *dev);
 extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
 extern void intel_init_pch_refclk(struct drm_device *dev);
 extern void gen6_set_rps(struct drm_device *dev, u8 val);
-extern void bdw_software_turbo(struct drm_device *dev);
-extern void gen8_flip_interrupt(struct drm_device *dev);
 extern void valleyview_set_rps(struct drm_device *dev, u8 val);
 extern void intel_set_memory_cxsr(struct drm_i915_private *dev_priv,
 				  bool enable);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4ca3a6dcf10b..28f91df2604d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -60,7 +60,6 @@ static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker,
 static int i915_gem_shrinker_oom(struct notifier_block *nb,
 				 unsigned long event,
 				 void *ptr);
-static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
 static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 
 static bool cpu_cache_is_coherent(struct drm_device *dev,
@@ -1741,7 +1740,11 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 	 * offsets on purgeable objects by truncating it and marking it purged,
 	 * which prevents userspace from ever using that object again.
 	 */
-	i915_gem_purge(dev_priv, obj->base.size >> PAGE_SHIFT);
+	i915_gem_shrink(dev_priv,
+			obj->base.size >> PAGE_SHIFT,
+			I915_SHRINK_BOUND |
+			I915_SHRINK_UNBOUND |
+			I915_SHRINK_PURGEABLE);
 	ret = drm_gem_create_mmap_offset(&obj->base);
 	if (ret != -ENOSPC)
 		goto out;
@@ -1938,12 +1941,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-static unsigned long
-__i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
-		  bool purgeable_only)
+unsigned long
+i915_gem_shrink(struct drm_i915_private *dev_priv,
+		long target, unsigned flags)
 {
-	struct list_head still_in_list;
-	struct drm_i915_gem_object *obj;
+	const bool purgeable_only = flags & I915_SHRINK_PURGEABLE;
 	unsigned long count = 0;
 
 	/*
@@ -1965,62 +1967,68 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 	 * dev->struct_mutex and so we won't ever be able to observe an
 	 * object on the bound_list with a reference count equals 0.
 	 */
-	INIT_LIST_HEAD(&still_in_list);
-	while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
-		obj = list_first_entry(&dev_priv->mm.unbound_list,
-				       typeof(*obj), global_list);
-		list_move_tail(&obj->global_list, &still_in_list);
+	if (flags & I915_SHRINK_UNBOUND) {
+		struct list_head still_in_list;
 
-		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
-			continue;
+		INIT_LIST_HEAD(&still_in_list);
+		while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
+			struct drm_i915_gem_object *obj;
 
-		drm_gem_object_reference(&obj->base);
+			obj = list_first_entry(&dev_priv->mm.unbound_list,
+					       typeof(*obj), global_list);
+			list_move_tail(&obj->global_list, &still_in_list);
 
-		if (i915_gem_object_put_pages(obj) == 0)
-			count += obj->base.size >> PAGE_SHIFT;
+			if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+				continue;
+
+			drm_gem_object_reference(&obj->base);
 
-		drm_gem_object_unreference(&obj->base);
+			if (i915_gem_object_put_pages(obj) == 0)
+				count += obj->base.size >> PAGE_SHIFT;
+
+			drm_gem_object_unreference(&obj->base);
+		}
+		list_splice(&still_in_list, &dev_priv->mm.unbound_list);
 	}
-	list_splice(&still_in_list, &dev_priv->mm.unbound_list);
 
-	INIT_LIST_HEAD(&still_in_list);
-	while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
-		struct i915_vma *vma, *v;
+	if (flags & I915_SHRINK_BOUND) {
+		struct list_head still_in_list;
 
-		obj = list_first_entry(&dev_priv->mm.bound_list,
-				       typeof(*obj), global_list);
-		list_move_tail(&obj->global_list, &still_in_list);
+		INIT_LIST_HEAD(&still_in_list);
+		while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
+			struct drm_i915_gem_object *obj;
+			struct i915_vma *vma, *v;
 
-		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
-			continue;
+			obj = list_first_entry(&dev_priv->mm.bound_list,
+					       typeof(*obj), global_list);
+			list_move_tail(&obj->global_list, &still_in_list);
 
-		drm_gem_object_reference(&obj->base);
+			if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+				continue;
 
-		list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
-			if (i915_vma_unbind(vma))
-				break;
+			drm_gem_object_reference(&obj->base);
 
-		if (i915_gem_object_put_pages(obj) == 0)
-			count += obj->base.size >> PAGE_SHIFT;
+			list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
+				if (i915_vma_unbind(vma))
+					break;
+
+			if (i915_gem_object_put_pages(obj) == 0)
+				count += obj->base.size >> PAGE_SHIFT;
 
-		drm_gem_object_unreference(&obj->base);
+			drm_gem_object_unreference(&obj->base);
+		}
+		list_splice(&still_in_list, &dev_priv->mm.bound_list);
 	}
-	list_splice(&still_in_list, &dev_priv->mm.bound_list);
 
 	return count;
 }
 
 static unsigned long
-i915_gem_purge(struct drm_i915_private *dev_priv, long target)
-{
-	return __i915_gem_shrink(dev_priv, target, true);
-}
-
-static unsigned long
 i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 {
 	i915_gem_evict_everything(dev_priv->dev);
-	return __i915_gem_shrink(dev_priv, LONG_MAX, false);
+	return i915_gem_shrink(dev_priv, LONG_MAX,
+			       I915_SHRINK_BOUND | I915_SHRINK_UNBOUND);
 }
 
 static int
@@ -2067,7 +2075,11 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	for (i = 0; i < page_count; i++) {
 		page = shmem_read_mapping_page_gfp(mapping, i, gfp);
 		if (IS_ERR(page)) {
-			i915_gem_purge(dev_priv, page_count);
+			i915_gem_shrink(dev_priv,
+					page_count,
+					I915_SHRINK_BOUND |
+					I915_SHRINK_UNBOUND |
+					I915_SHRINK_PURGEABLE);
 			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
 		}
 		if (IS_ERR(page)) {
@@ -2944,6 +2956,9 @@ int i915_vma_unbind(struct i915_vma *vma)
 	 * cause memory corruption through use-after-free.
 	 */
 
+	/* Throw away the active reference before moving to the unbound list */
+	i915_gem_object_retire(obj);
+
 	if (i915_is_ggtt(vma->vm)) {
 		i915_gem_object_finish_gtt(obj);
 
@@ -3336,17 +3351,20 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-static bool i915_gem_valid_gtt_space(struct drm_device *dev,
-				     struct drm_mm_node *gtt_space,
+static bool i915_gem_valid_gtt_space(struct i915_vma *vma,
 				     unsigned long cache_level)
 {
+	struct drm_mm_node *gtt_space = &vma->node;
 	struct drm_mm_node *other;
 
-	/* On non-LLC machines we have to be careful when putting differing
-	 * types of snoopable memory together to avoid the prefetcher
-	 * crossing memory domains and dying.
+	/*
+	 * On some machines we have to be careful when putting differing types
+	 * of snoopable memory together to avoid the prefetcher crossing memory
+	 * domains and dying. During vm initialisation, we decide whether or not
+	 * these constraints apply and set the drm_mm.color_adjust
+	 * appropriately.
 	 */
-	if (HAS_LLC(dev))
+	if (vma->vm->mm.color_adjust == NULL)
 		return true;
 
 	if (!drm_mm_node_allocated(gtt_space))
@@ -3484,8 +3502,7 @@ search_free:
 
 		goto err_free_vma;
 	}
-	if (WARN_ON(!i915_gem_valid_gtt_space(dev, &vma->node,
-					      obj->cache_level))) {
+	if (WARN_ON(!i915_gem_valid_gtt_space(vma, obj->cache_level))) {
 		ret = -EINVAL;
 		goto err_remove_node;
 	}
@@ -3695,7 +3712,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 	}
 
 	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
-		if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) {
+		if (!i915_gem_valid_gtt_space(vma, cache_level)) {
 			ret = i915_vma_unbind(vma);
 			if (ret)
 				return ret;
@@ -5261,11 +5278,16 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	if (!i915_gem_shrinker_lock(dev, &unlock))
 		return SHRINK_STOP;
 
-	freed = i915_gem_purge(dev_priv, sc->nr_to_scan);
+	freed = i915_gem_shrink(dev_priv,
+				sc->nr_to_scan,
+				I915_SHRINK_BOUND |
+				I915_SHRINK_UNBOUND |
+				I915_SHRINK_PURGEABLE);
 	if (freed < sc->nr_to_scan)
-		freed += __i915_gem_shrink(dev_priv,
-					   sc->nr_to_scan - freed,
-					   false);
+		freed += i915_gem_shrink(dev_priv,
+					 sc->nr_to_scan - freed,
+					 I915_SHRINK_BOUND |
+					 I915_SHRINK_UNBOUND);
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index bbf4b12d842e..886ff2ee7a28 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -243,7 +243,7 @@ int
 i915_gem_evict_everything(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_address_space *vm;
+	struct i915_address_space *vm, *v;
 	bool lists_empty = true;
 	int ret;
 
@@ -270,7 +270,7 @@ i915_gem_evict_everything(struct drm_device *dev)
 	i915_gem_retire_requests(dev);
 
 	/* Having flushed everything, unbind() should never raise an error */
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+	list_for_each_entry_safe(vm, v, &dev_priv->vm_list, global_link)
 		WARN_ON(i915_gem_evict_vm(vm, false));
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 21c025a209c0..85fda6b803e4 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -289,6 +289,7 @@ void i915_gem_cleanup_stolen(struct drm_device *dev)
 int i915_gem_init_stolen(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 tmp;
 	int bios_reserved = 0;
 
 #ifdef CONFIG_INTEL_IOMMU
@@ -308,8 +309,16 @@ int i915_gem_init_stolen(struct drm_device *dev)
 	DRM_DEBUG_KMS("found %zd bytes of stolen memory at %08lx\n",
 		      dev_priv->gtt.stolen_size, dev_priv->mm.stolen_base);
 
-	if (IS_VALLEYVIEW(dev))
-		bios_reserved = 1024*1024; /* top 1M on VLV/BYT */
+	if (INTEL_INFO(dev)->gen >= 8) {
+		tmp = I915_READ(GEN7_BIOS_RESERVED);
+		tmp >>= GEN8_BIOS_RESERVED_SHIFT;
+		tmp &= GEN8_BIOS_RESERVED_MASK;
+		bios_reserved = (1024*1024) << tmp;
+	} else if (IS_GEN7(dev)) {
+		tmp = I915_READ(GEN7_BIOS_RESERVED);
+		bios_reserved = tmp & GEN7_BIOS_RESERVED_256K ?
+			256*1024 : 1024*1024;
+	}
 
 	if (WARN_ON(bios_reserved > dev_priv->gtt.stolen_size))
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index d38413997379..d182058383a9 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -293,15 +293,23 @@ i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 static struct i915_mmu_notifier *
 i915_mmu_notifier_find(struct i915_mm_struct *mm)
 {
-	if (mm->mn == NULL) {
-		down_write(&mm->mm->mmap_sem);
-		mutex_lock(&to_i915(mm->dev)->mm_lock);
-		if (mm->mn == NULL)
-			mm->mn = i915_mmu_notifier_create(mm->mm);
-		mutex_unlock(&to_i915(mm->dev)->mm_lock);
-		up_write(&mm->mm->mmap_sem);
+	struct i915_mmu_notifier *mn = mm->mn;
+
+	mn = mm->mn;
+	if (mn)
+		return mn;
+
+	down_write(&mm->mm->mmap_sem);
+	mutex_lock(&to_i915(mm->dev)->mm_lock);
+	if ((mn = mm->mn) == NULL) {
+		mn = i915_mmu_notifier_create(mm->mm);
+		if (!IS_ERR(mn))
+			mm->mn = mn;
 	}
-	return mm->mn;
+	mutex_unlock(&to_i915(mm->dev)->mm_lock);
+	up_write(&mm->mm->mmap_sem);
+
+	return mn;
 }
 
 static int
@@ -681,16 +689,15 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 static void
 i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 {
-	struct scatterlist *sg;
-	int i;
+	struct sg_page_iter sg_iter;
 
 	BUG_ON(obj->userptr.work != NULL);
 
 	if (obj->madv != I915_MADV_WILLNEED)
 		obj->dirty = 0;
 
-	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) {
-		struct page *page = sg_page(sg);
+	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
 
 		if (obj->dirty)
 			set_page_dirty(page);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c96ddc953531..3201986bf25e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1979,27 +1979,6 @@ static void i9xx_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
 				     res1, res2);
 }
 
-void gen8_flip_interrupt(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (!dev_priv->rps.is_bdw_sw_turbo)
-		return;
-
-	if(atomic_read(&dev_priv->rps.sw_turbo.flip_received)) {
-		mod_timer(&dev_priv->rps.sw_turbo.flip_timer,
-				usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies);
-	}
-	else {
-		dev_priv->rps.sw_turbo.flip_timer.expires =
-				usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies;
-		add_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		atomic_set(&dev_priv->rps.sw_turbo.flip_received, true);
-	}
-
-	bdw_software_turbo(dev);
-}
-
 /* The RPS events need forcewake, so we add them to a work queue and mask their
  * IMR bits until the work is done. Other interrupts can be processed without
  * the work queue. */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b65bdfc23ccb..c01e5f31430e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -143,6 +143,14 @@
 #define GAB_CTL				0x24000
 #define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1<<8)
 
+#define GEN7_BIOS_RESERVED		0x1082C0
+#define GEN7_BIOS_RESERVED_1M		(0 << 5)
+#define GEN7_BIOS_RESERVED_256K		(1 << 5)
+#define GEN8_BIOS_RESERVED_SHIFT       7
+#define GEN7_BIOS_RESERVED_MASK        0x1
+#define GEN8_BIOS_RESERVED_MASK        0x3
+
+
 /* VGA stuff */
 
 #define VGA_ST01_MDA 0x3ba
@@ -2435,6 +2443,7 @@ enum punit_power_well {
 #define _PIPEASRC	0x6001c
 #define _BCLRPAT_A	0x60020
 #define _VSYNCSHIFT_A	0x60028
+#define _PIPE_MULT_A	0x6002c
 
 /* Pipe B timing regs */
 #define _HTOTAL_B	0x61000
@@ -2446,6 +2455,7 @@ enum punit_power_well {
 #define _PIPEBSRC	0x6101c
 #define _BCLRPAT_B	0x61020
 #define _VSYNCSHIFT_B	0x61028
+#define _PIPE_MULT_B	0x6102c
 
 #define TRANSCODER_A_OFFSET 0x60000
 #define TRANSCODER_B_OFFSET 0x61000
@@ -2466,6 +2476,7 @@ enum punit_power_well {
 #define BCLRPAT(trans) _TRANSCODER2(trans, _BCLRPAT_A)
 #define VSYNCSHIFT(trans) _TRANSCODER2(trans, _VSYNCSHIFT_A)
 #define PIPESRC(trans) _TRANSCODER2(trans, _PIPEASRC)
+#define PIPE_MULT(trans) _TRANSCODER2(trans, _PIPE_MULT_A)
 
 /* HSW+ eDP PSR registers */
 #define EDP_PSR_BASE(dev)                       (IS_HASWELL(dev) ? 0x64800 : 0x6f800)
@@ -5577,10 +5588,6 @@ enum punit_power_well {
 #define GEN8_UCGCTL6				0x9430
 #define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
 
-#define TIMESTAMP_CTR		0x44070
-#define FREQ_1_28_US(us)	(((us) * 100) >> 7)
-#define MCHBAR_PCU_C0		(MCHBAR_MIRROR_BASE_SNB + 0x5960)
-
 #define GEN6_GFXPAUSE				0xA000
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1386086ec245..507370513f3d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1612,6 +1612,18 @@ static void chv_enable_pll(struct intel_crtc *crtc)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static int intel_num_dvo_pipes(struct drm_device *dev)
+{
+	struct intel_crtc *crtc;
+	int count = 0;
+
+	for_each_intel_crtc(dev, crtc)
+		count += crtc->active &&
+			intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO);
+
+	return count;
+}
+
 static void i9xx_enable_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -1628,7 +1640,18 @@ static void i9xx_enable_pll(struct intel_crtc *crtc)
 	if (IS_MOBILE(dev) && !IS_I830(dev))
 		assert_panel_unlocked(dev_priv, crtc->pipe);
 
-	I915_WRITE(reg, dpll);
+	/* Enable DVO 2x clock on both PLLs if necessary */
+	if (IS_I830(dev) && intel_num_dvo_pipes(dev) > 0) {
+		/*
+		 * It appears to be important that we don't enable this
+		 * for the current pipe before otherwise configuring the
+		 * PLL. No idea how this should be handled if multiple
+		 * DVO outputs are enabled simultaneosly.
+		 */
+		dpll |= DPLL_DVO_2X_MODE;
+		I915_WRITE(DPLL(!crtc->pipe),
+			   I915_READ(DPLL(!crtc->pipe)) | DPLL_DVO_2X_MODE);
+	}
 
 	/* Wait for the clocks to stabilize. */
 	POSTING_READ(reg);
@@ -1667,8 +1690,22 @@ static void i9xx_enable_pll(struct intel_crtc *crtc)
  *
  * Note!  This is for pre-ILK only.
  */
-static void i9xx_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
+static void i9xx_disable_pll(struct intel_crtc *crtc)
 {
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum pipe pipe = crtc->pipe;
+
+	/* Disable DVO 2x clock on both PLLs if necessary */
+	if (IS_I830(dev) &&
+	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO) &&
+	    intel_num_dvo_pipes(dev) == 1) {
+		I915_WRITE(DPLL(PIPE_B),
+			   I915_READ(DPLL(PIPE_B)) & ~DPLL_DVO_2X_MODE);
+		I915_WRITE(DPLL(PIPE_A),
+			   I915_READ(DPLL(PIPE_A)) & ~DPLL_DVO_2X_MODE);
+	}
+
 	/* Don't disable pipe or pipe PLLs if needed */
 	if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
 	    (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
@@ -4185,6 +4222,11 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 
 	intel_set_pipe_timings(intel_crtc);
 
+	if (intel_crtc->config.cpu_transcoder != TRANSCODER_EDP) {
+		I915_WRITE(PIPE_MULT(intel_crtc->config.cpu_transcoder),
+			   intel_crtc->config.pixel_multiplier - 1);
+	}
+
 	if (intel_crtc->config.has_pch_encoder) {
 		intel_cpu_transcoder_set_m_n(intel_crtc,
 				     &intel_crtc->config.fdi_m_n, NULL);
@@ -4941,7 +4983,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 		else if (IS_VALLEYVIEW(dev))
 			vlv_disable_pll(dev_priv, pipe);
 		else
-			i9xx_disable_pll(dev_priv, pipe);
+			i9xx_disable_pll(intel_crtc);
 	}
 
 	if (!IS_GEN2(dev))
@@ -5945,7 +5987,7 @@ static void i8xx_update_pll(struct intel_crtc *crtc,
 			dpll |= PLL_P2_DIVIDE_BY_4;
 	}
 
-	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO))
+	if (!IS_I830(dev) && intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO))
 		dpll |= DPLL_DVO_2X_MODE;
 
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) &&
@@ -6451,6 +6493,14 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	}
 	pipe_config->dpll_hw_state.dpll = I915_READ(DPLL(crtc->pipe));
 	if (!IS_VALLEYVIEW(dev)) {
+		/*
+		 * DPLL_DVO_2X_MODE must be enabled for both DPLLs
+		 * on 830. Filter it out here so that we don't
+		 * report errors due to that.
+		 */
+		if (IS_I830(dev))
+			pipe_config->dpll_hw_state.dpll &= ~DPLL_DVO_2X_MODE;
+
 		pipe_config->dpll_hw_state.fp0 = I915_READ(FP0(crtc->pipe));
 		pipe_config->dpll_hw_state.fp1 = I915_READ(FP1(crtc->pipe));
 	} else {
@@ -7845,7 +7895,12 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
 			(I915_READ(IPS_CTL) & IPS_ENABLE);
 
-	pipe_config->pixel_multiplier = 1;
+	if (pipe_config->cpu_transcoder != TRANSCODER_EDP) {
+		pipe_config->pixel_multiplier =
+			I915_READ(PIPE_MULT(pipe_config->cpu_transcoder)) + 1;
+	} else {
+		pipe_config->pixel_multiplier = 1;
+	}
 
 	return true;
 }
@@ -9881,9 +9936,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	unsigned long flags;
 	int ret;
 
-	//trigger software GT busyness calculation
-	gen8_flip_interrupt(dev);
-
 	/*
 	 * drm_mode_page_flip_ioctl() should already catch this, but double
 	 * check to be safe.  In the future we may enable pageflipping from
@@ -10039,8 +10091,11 @@ free_work:
 out_hang:
 		intel_crtc_wait_for_pending_flips(crtc);
 		ret = intel_pipe_set_base(crtc, crtc->x, crtc->y, fb);
-		if (ret == 0 && event)
+		if (ret == 0 && event) {
+			spin_lock_irqsave(&dev->event_lock, flags);
 			drm_send_vblank_event(dev, pipe, event);
+			spin_unlock_irqrestore(&dev->event_lock, flags);
+		}
 	}
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2a26774ddb68..59754451ae50 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1068,23 +1068,15 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			bpp = dev_priv->vbt.edp_bpp;
 		}
 
-		if (IS_BROADWELL(dev)) {
-			/* Yes, it's an ugly hack. */
-			min_lane_count = max_lane_count;
-			DRM_DEBUG_KMS("forcing lane count to max (%u) on BDW\n",
-				      min_lane_count);
-		} else if (dev_priv->vbt.edp_lanes) {
-			min_lane_count = min(dev_priv->vbt.edp_lanes,
-					     max_lane_count);
-			DRM_DEBUG_KMS("using min %u lanes per VBT\n",
-				      min_lane_count);
-		}
-
-		if (dev_priv->vbt.edp_rate) {
-			min_clock = min(dev_priv->vbt.edp_rate >> 3, max_clock);
-			DRM_DEBUG_KMS("using min %02x link bw per VBT\n",
-				      bws[min_clock]);
-		}
+		/*
+		 * Use the maximum clock and number of lanes the eDP panel
+		 * advertizes being capable of. The panels are generally
+		 * designed to support only a single clock and lane
+		 * configuration, and typically these values correspond to the
+		 * native resolution of the panel.
+		 */
+		min_lane_count = max_lane_count;
+		min_clock = max_clock;
 	}
 
 	for (; bpp >= 6*3; bpp -= 2*3) {
@@ -3732,7 +3724,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x12 &&
 	    intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED) {
 		intel_dp->use_tps3 = true;
-		DRM_DEBUG_KMS("Displayport TPS3 supported");
+		DRM_DEBUG_KMS("Displayport TPS3 supported\n");
 	} else
 		intel_dp->use_tps3 = false;
 
@@ -3808,21 +3800,21 @@ int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc)
 	u8 buf[1];
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, buf) < 0)
-		return -EAGAIN;
+		return -EIO;
 
 	if (!(buf[0] & DP_TEST_CRC_SUPPORTED))
 		return -ENOTTY;
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
 			       DP_TEST_SINK_START) < 0)
-		return -EAGAIN;
+		return -EIO;
 
 	/* Wait 2 vblanks to be sure we will have the correct CRC value */
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0)
-		return -EAGAIN;
+		return -EIO;
 
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, 0);
 	return 0;
@@ -4395,7 +4387,7 @@ intel_dp_connector_destroy(struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 
-	intel_dp_unset_edid(intel_attached_dp(connector));
+	kfree(intel_connector->detect_edid);
 
 	if (!IS_ERR_OR_NULL(intel_connector->edid))
 		kfree(intel_connector->edid);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index c5861736b4b0..7fed5bedc10f 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1501,7 +1501,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder)
 
 static void intel_hdmi_destroy(struct drm_connector *connector)
 {
-	intel_hdmi_unset_edid(connector);
+	kfree(to_intel_connector(connector)->detect_edid);
 	drm_connector_cleanup(connector);
 	kfree(connector);
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index bd1b28d99920..bafd38b5703e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -300,8 +300,18 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
 	 * Instead, we do the runtime_pm_get/put when creating/destroying requests.
 	 */
 	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
-	if (dev_priv->uncore.forcewake_count++ == 0)
-		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
+	if (IS_CHERRYVIEW(dev_priv->dev)) {
+		if (dev_priv->uncore.fw_rendercount++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							      FORCEWAKE_RENDER);
+		if (dev_priv->uncore.fw_mediacount++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							      FORCEWAKE_MEDIA);
+	} else {
+		if (dev_priv->uncore.forcewake_count++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							      FORCEWAKE_ALL);
+	}
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
 
 	I915_WRITE(RING_ELSP(ring), desc[1]);
@@ -315,8 +325,19 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
 
 	/* Release Force Wakeup (see the big comment above). */
 	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
-	if (--dev_priv->uncore.forcewake_count == 0)
-		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
+	if (IS_CHERRYVIEW(dev_priv->dev)) {
+		if (--dev_priv->uncore.fw_rendercount == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							      FORCEWAKE_RENDER);
+		if (--dev_priv->uncore.fw_mediacount == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							      FORCEWAKE_MEDIA);
+	} else {
+		if (--dev_priv->uncore.forcewake_count == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							      FORCEWAKE_ALL);
+	}
+
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 45f71e6dc544..c27b6140bfd1 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1070,6 +1070,17 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz,
 		wm_size = wm->max_wm;
 	if (wm_size <= 0)
 		wm_size = wm->default_wm;
+
+	/*
+	 * Bspec seems to indicate that the value shouldn't be lower than
+	 * 'burst size + 1'. Certainly 830 is quite unhappy with low values.
+	 * Lets go for 8 which is the burst size since certain platforms
+	 * already use a hardcoded 8 (which is what the spec says should be
+	 * done).
+	 */
+	if (wm_size <= 8)
+		wm_size = 8;
+
 	return wm_size;
 }
 
@@ -2274,6 +2285,7 @@ int ilk_wm_max_level(const struct drm_device *dev)
 	else
 		return 2;
 }
+
 static void intel_print_wm_latency(struct drm_device *dev,
 				   const char *name,
 				   const uint16_t wm[5])
@@ -3242,9 +3254,6 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 {
 	int new_power;
 
-	if (dev_priv->rps.is_bdw_sw_turbo)
-		return;
-
 	new_power = dev_priv->rps.power;
 	switch (dev_priv->rps.power) {
 	case LOW_POWER:
@@ -3452,11 +3461,8 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 			valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
 		else if (IS_VALLEYVIEW(dev))
 			vlv_set_rps_idle(dev_priv);
-		else if (!dev_priv->rps.is_bdw_sw_turbo
-					|| atomic_read(&dev_priv->rps.sw_turbo.flip_received)){
+		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
-		}
-
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3470,11 +3476,8 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
 	if (dev_priv->rps.enabled) {
 		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
-		else if (!dev_priv->rps.is_bdw_sw_turbo
-					|| atomic_read(&dev_priv->rps.sw_turbo.flip_received)){
+		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
-		}
-
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3488,17 +3491,18 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
 	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
 
-	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
-			 dev_priv->rps.cur_freq,
-			 vlv_gpu_freq(dev_priv, val), val);
-
 	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
 		      "Odd GPU freq value\n"))
 		val &= ~1;
 
-	if (val != dev_priv->rps.cur_freq)
+	if (val != dev_priv->rps.cur_freq) {
+		DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
+				 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+				 dev_priv->rps.cur_freq,
+				 vlv_gpu_freq(dev_priv, val), val);
+
 		vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+	}
 
 	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
 
@@ -3509,26 +3513,21 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 static void gen8_disable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	if (IS_BROADWELL(dev) && dev_priv->rps.is_bdw_sw_turbo){
-		if (atomic_read(&dev_priv->rps.sw_turbo.flip_received))
-			del_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		dev_priv-> rps.is_bdw_sw_turbo = false;
-	} else {
-		I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
-		I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
-					   ~dev_priv->pm_rps_events);
-		/* Complete PM interrupt masking here doesn't race with the rps work
-		 * item again unmasking PM interrupts because that is using a different
-		 * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
-		 * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
-		 * gen8_enable_rps will clean up. */
 
-		spin_lock_irq(&dev_priv->irq_lock);
-		dev_priv->rps.pm_iir = 0;
-		spin_unlock_irq(&dev_priv->irq_lock);
+	I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
+	I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
+				   ~dev_priv->pm_rps_events);
+	/* Complete PM interrupt masking here doesn't race with the rps work
+	 * item again unmasking PM interrupts because that is using a different
+	 * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
+	 * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
+	 * gen8_enable_rps will clean up. */
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	dev_priv->rps.pm_iir = 0;
+	spin_unlock_irq(&dev_priv->irq_lock);
 
-		I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
-	}
+	I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
 }
 
 static void gen6_disable_rps_interrupts(struct drm_device *dev)
@@ -3686,111 +3685,13 @@ static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_c
 		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
 }
 
-static void bdw_sw_calculate_freq(struct drm_device *dev,
-		struct intel_rps_bdw_cal *c, u32 *cur_time, u32 *c0)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u64 busy = 0;
-	u32 busyness_pct = 0;
-	u32 elapsed_time = 0;
-	u16 new_freq = 0;
-
-	if (!c || !cur_time || !c0)
-		return;
-
-	if (0 == c->last_c0)
-		goto out;
-
-	/* Check Evaluation interval */
-	elapsed_time = *cur_time - c->last_ts;
-	if (elapsed_time < c->eval_interval)
-		return;
-
-	mutex_lock(&dev_priv->rps.hw_lock);
-
-	/*
-	 * c0 unit in 32*1.28 usec, elapsed_time unit in 1 usec.
-	 * Whole busyness_pct calculation should be
-	 *     busy = ((u64)(*c0 - c->last_c0) << 5 << 7) / 100;
-	 *     busyness_pct = (u32)(busy * 100 / elapsed_time);
-	 * The final formula is to simplify CPU calculation
-	 */
-	busy = (u64)(*c0 - c->last_c0) << 12;
-	do_div(busy, elapsed_time);
-	busyness_pct = (u32)busy;
-
-	if (c->is_up && busyness_pct >= c->it_threshold_pct)
-		new_freq = (u16)dev_priv->rps.cur_freq + 3;
-	if (!c->is_up && busyness_pct <= c->it_threshold_pct)
-		new_freq = (u16)dev_priv->rps.cur_freq - 1;
-
-	/* Adjust to new frequency busyness and compare with threshold */
-	if (0 != new_freq) {
-		if (new_freq > dev_priv->rps.max_freq_softlimit)
-			new_freq = dev_priv->rps.max_freq_softlimit;
-		else if (new_freq < dev_priv->rps.min_freq_softlimit)
-			new_freq = dev_priv->rps.min_freq_softlimit;
-
-		gen6_set_rps(dev, new_freq);
-	}
-
-	mutex_unlock(&dev_priv->rps.hw_lock);
-
-out:
-	c->last_c0 = *c0;
-	c->last_ts = *cur_time;
-}
-
-static void gen8_set_frequency_RP0(struct work_struct *work)
-{
-	struct intel_rps_bdw_turbo *p_bdw_turbo =
-			container_of(work, struct intel_rps_bdw_turbo, work_max_freq);
-	struct intel_gen6_power_mgmt *p_power_mgmt =
-			container_of(p_bdw_turbo, struct intel_gen6_power_mgmt, sw_turbo);
-	struct drm_i915_private *dev_priv =
-			container_of(p_power_mgmt, struct drm_i915_private, rps);
-
-	mutex_lock(&dev_priv->rps.hw_lock);
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.rp0_freq);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-}
-
-static void flip_active_timeout_handler(unsigned long var)
-{
-	struct drm_i915_private *dev_priv = (struct drm_i915_private *) var;
-
-	del_timer(&dev_priv->rps.sw_turbo.flip_timer);
-	atomic_set(&dev_priv->rps.sw_turbo.flip_received, false);
-
-	queue_work(dev_priv->wq, &dev_priv->rps.sw_turbo.work_max_freq);
-}
-
-void bdw_software_turbo(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	u32 current_time = I915_READ(TIMESTAMP_CTR); /* unit in usec */
-	u32 current_c0 = I915_READ(MCHBAR_PCU_C0); /* unit in 32*1.28 usec */
-
-	bdw_sw_calculate_freq(dev, &dev_priv->rps.sw_turbo.up,
-			&current_time, &current_c0);
-	bdw_sw_calculate_freq(dev, &dev_priv->rps.sw_turbo.down,
-			&current_time, &current_c0);
-}
-
 static void gen8_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
 	uint32_t rc6_mask = 0, rp_state_cap;
-	uint32_t threshold_up_pct, threshold_down_pct;
-	uint32_t ei_up, ei_down; /* up and down evaluation interval */
-	u32 rp_ctl_flag;
 	int unused;
 
-	/* Use software Turbo for BDW */
-	dev_priv->rps.is_bdw_sw_turbo = IS_BROADWELL(dev);
-
 	/* 1a: Software RC state - RC0 */
 	I915_WRITE(GEN6_RC_STATE, 0);
 
@@ -3834,74 +3735,35 @@ static void gen8_enable_rps(struct drm_device *dev)
 		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
 	I915_WRITE(GEN6_RC_VIDEO_FREQ,
 		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
-	ei_up = 84480; /* 84.48ms */
-	ei_down = 448000;
-	threshold_up_pct = 90; /* x percent busy */
-	threshold_down_pct = 70;
-
-	if (dev_priv->rps.is_bdw_sw_turbo) {
-		dev_priv->rps.sw_turbo.up.it_threshold_pct = threshold_up_pct;
-		dev_priv->rps.sw_turbo.up.eval_interval = ei_up;
-		dev_priv->rps.sw_turbo.up.is_up = true;
-		dev_priv->rps.sw_turbo.up.last_ts = 0;
-		dev_priv->rps.sw_turbo.up.last_c0 = 0;
-
-		dev_priv->rps.sw_turbo.down.it_threshold_pct = threshold_down_pct;
-		dev_priv->rps.sw_turbo.down.eval_interval = ei_down;
-		dev_priv->rps.sw_turbo.down.is_up = false;
-		dev_priv->rps.sw_turbo.down.last_ts = 0;
-		dev_priv->rps.sw_turbo.down.last_c0 = 0;
-
-		/* Start the timer to track if flip comes*/
-		dev_priv->rps.sw_turbo.timeout = 200*1000; /* in us */
-
-		init_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		dev_priv->rps.sw_turbo.flip_timer.function = flip_active_timeout_handler;
-		dev_priv->rps.sw_turbo.flip_timer.data  = (unsigned long) dev_priv;
-		dev_priv->rps.sw_turbo.flip_timer.expires =
-			usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies;
-		add_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		INIT_WORK(&dev_priv->rps.sw_turbo.work_max_freq, gen8_set_frequency_RP0);
-
-		atomic_set(&dev_priv->rps.sw_turbo.flip_received, true);
-	} else {
-		/* NB: Docs say 1s, and 1000000 - which aren't equivalent
-		 * 1 second timeout*/
-		I915_WRITE(GEN6_RP_DOWN_TIMEOUT, FREQ_1_28_US(1000000));
+	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
+	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
 
-		/* Docs recommend 900MHz, and 300 MHz respectively */
-		I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-			   dev_priv->rps.max_freq_softlimit << 24 |
-			   dev_priv->rps.min_freq_softlimit << 16);
+	/* Docs recommend 900MHz, and 300 MHz respectively */
+	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
+		   dev_priv->rps.max_freq_softlimit << 24 |
+		   dev_priv->rps.min_freq_softlimit << 16);
 
-		I915_WRITE(GEN6_RP_UP_THRESHOLD,
-			FREQ_1_28_US(ei_up * threshold_up_pct / 100));
-		I915_WRITE(GEN6_RP_DOWN_THRESHOLD,
-			FREQ_1_28_US(ei_down * threshold_down_pct / 100));
-		I915_WRITE(GEN6_RP_UP_EI,
-			FREQ_1_28_US(ei_up));
-		I915_WRITE(GEN6_RP_DOWN_EI,
-			FREQ_1_28_US(ei_down));
+	I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
+	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
+	I915_WRITE(GEN6_RP_UP_EI, 66000); /* 84.48ms, XXX: random? */
+	I915_WRITE(GEN6_RP_DOWN_EI, 350000); /* 448ms, XXX: random? */
 
-		I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-	}
+	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 
 	/* 5: Enable RPS */
-	rp_ctl_flag = GEN6_RP_MEDIA_TURBO |
-					GEN6_RP_MEDIA_HW_NORMAL_MODE |
-					GEN6_RP_MEDIA_IS_GFX |
-					GEN6_RP_UP_BUSY_AVG |
-					GEN6_RP_DOWN_IDLE_AVG;
-	if (!dev_priv->rps.is_bdw_sw_turbo)
-		rp_ctl_flag |= GEN6_RP_ENABLE;
-
-	I915_WRITE(GEN6_RP_CONTROL, rp_ctl_flag);
-
-	/* 6: Ring frequency + overclocking
-	 * (our driver does this later */
+	I915_WRITE(GEN6_RP_CONTROL,
+		   GEN6_RP_MEDIA_TURBO |
+		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+		   GEN6_RP_MEDIA_IS_GFX |
+		   GEN6_RP_ENABLE |
+		   GEN6_RP_UP_BUSY_AVG |
+		   GEN6_RP_DOWN_IDLE_AVG);
+
+	/* 6: Ring frequency + overclocking (our driver does this later */
+
 	gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8);
-	if (!dev_priv->rps.is_bdw_sw_turbo)
-		gen8_enable_rps_interrupts(dev);
+
+	gen8_enable_rps_interrupts(dev);
 
 	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
@@ -5375,8 +5237,6 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 			     rps.delayed_resume_work.work);
 	struct drm_device *dev = dev_priv->dev;
 
-	dev_priv->rps.is_bdw_sw_turbo = false;
-
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	if (IS_CHERRYVIEW(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 109de2eeb9a8..6dc981f0671e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 * update the number of dwords required based on the
 	 * actual number of workarounds applied
 	 */
-	ret = intel_ring_begin(ring, 24);
+	ret = intel_ring_begin(ring, 18);
 	if (ret)
 		return ret;
 
@@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
-	/*
-	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
-	 * pre-production hardware
-	 */
 	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
-			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
-					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
-
-	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
-	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
-			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for for a possible hang in the unlikely event a TLB
@@ -2203,8 +2192,9 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
 		return ret;
 
 	intel_ring_emit(ring,
-			MI_BATCH_BUFFER_START | MI_BATCH_PPGTT_HSW |
-			(flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_HSW));
+			MI_BATCH_BUFFER_START |
+			(flags & I915_DISPATCH_SECURE ?
+			 0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW));
 	/* bit0-7 is the length on GEN6+ */
 	intel_ring_emit(ring, offset);
 	intel_ring_advance(ring);