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

Some fixes for 3.8:
- Watermark fixups from Chris Wilson (4 pieces).
- 2 snb workarounds, seem to be recently added to our internal DB.
- workaround for the infamous i830/i845 hang, seems now finally solid!
  Based on Chris' fix for SNA, now also for UXA/mesa&old SNA.
- Some more fixlets for shrinker-pulls-the-rug issues (Chris&me).
- Fix dma-buf flags when exporting (you).
- Disable the VGA plane if it's enabled on lid open - similar fix in
  spirit to the one I've sent you last weeek, BIOS' really like to mess
  with the display when closing the lid (awesome debug work from Krzysztof
  Mazur).

* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel:
  drm/i915: disable shrinker lock stealing for create_mmap_offset
  drm/i915: optionally disable shrinker lock stealing
  drm/i915: fix flags in dma buf exporting
  i915: ensure that VGA plane is disabled
  drm/i915: Preallocate the drm_mm_node prior to manipulating the GTT drm_mm manager
  drm: Export routines for inserting preallocated nodes into the mm manager
  drm/i915: don't disable disconnected outputs
  drm/i915: Implement workaround for broken CS tlb on i830/845
  drm/i915: Implement WaSetupGtModeTdRowDispatch
  drm/i915: Implement WaDisableHiZPlanesWhenMSAAEnabled
  drm/i915: Prefer CRTC 'active' rather than 'enabled' during WM computations
  drm/i915: Clear self-refresh watermarks when disabled
  drm/i915: Double the cursor self-refresh latency on Valleyview
  drm/i915: Fixup cursor latency used for IVB lp3 watermarks

12 files changed, 325 insertions, 84 deletions

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 0761a03cdbb2..2bf9670ba29b 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -184,19 +184,27 @@ EXPORT_SYMBOL(drm_mm_get_block_generic);
  * -ENOSPC if no suitable free area is available. The preallocated memory node
  * must be cleared.
  */
-int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
-		       unsigned long size, unsigned alignment)
+int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
+			       unsigned long size, unsigned alignment,
+			       unsigned long color)
 {
 	struct drm_mm_node *hole_node;
 
-	hole_node = drm_mm_search_free(mm, size, alignment, false);
+	hole_node = drm_mm_search_free_generic(mm, size, alignment,
+					       color, 0);
 	if (!hole_node)
 		return -ENOSPC;
 
-	drm_mm_insert_helper(hole_node, node, size, alignment, 0);
-
+	drm_mm_insert_helper(hole_node, node, size, alignment, color);
 	return 0;
 }
+EXPORT_SYMBOL(drm_mm_insert_node_generic);
+
+int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
+		       unsigned long size, unsigned alignment)
+{
+	return drm_mm_insert_node_generic(mm, node, size, alignment, 0);
+}
 EXPORT_SYMBOL(drm_mm_insert_node);
 
 static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
@@ -275,22 +283,31 @@ EXPORT_SYMBOL(drm_mm_get_block_range_generic);
  * -ENOSPC if no suitable free area is available. This is for range
  * restricted allocations. The preallocated memory node must be cleared.
  */
-int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
-				unsigned long size, unsigned alignment,
-				unsigned long start, unsigned long end)
+int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node,
+					unsigned long size, unsigned alignment, unsigned long color,
+					unsigned long start, unsigned long end)
 {
 	struct drm_mm_node *hole_node;
 
-	hole_node = drm_mm_search_free_in_range(mm, size, alignment,
-						start, end, false);
+	hole_node = drm_mm_search_free_in_range_generic(mm,
+							size, alignment, color,
+							start, end, 0);
 	if (!hole_node)
 		return -ENOSPC;
 
-	drm_mm_insert_helper_range(hole_node, node, size, alignment, 0,
+	drm_mm_insert_helper_range(hole_node, node,
+				   size, alignment, color,
 				   start, end);
-
 	return 0;
 }
+EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic);
+
+int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
+				unsigned long size, unsigned alignment,
+				unsigned long start, unsigned long end)
+{
+	return drm_mm_insert_node_in_range_generic(mm, node, size, alignment, 0, start, end);
+}
 EXPORT_SYMBOL(drm_mm_insert_node_in_range);
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 8f63cd5de4b4..99daa896105d 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -989,6 +989,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_SECURE_BATCHES:
 		value = capable(CAP_SYS_ADMIN);
 		break;
+	case I915_PARAM_HAS_PINNED_BATCHES:
+		value = 1;
+		break;
 	default:
 		DRM_DEBUG_DRIVER("Unknown parameter %d\n",
 				 param->param);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 557843dd4b2e..ed3059575576 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -780,6 +780,7 @@ typedef struct drm_i915_private {
 		struct i915_hw_ppgtt *aliasing_ppgtt;
 
 		struct shrinker inactive_shrinker;
+		bool shrinker_no_lock_stealing;
 
 		/**
 		 * List of objects currently involved in rendering.
@@ -1100,6 +1101,7 @@ struct drm_i915_gem_object {
 	 */
 	atomic_t pending_flip;
 };
+#define to_gem_object(obj) (&((struct drm_i915_gem_object *)(obj))->base)
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
@@ -1166,6 +1168,9 @@ struct drm_i915_file_private {
 #define IS_IVB_GT1(dev)		((dev)->pci_device == 0x0156 || \
 				 (dev)->pci_device == 0x0152 ||	\
 				 (dev)->pci_device == 0x015a)
+#define IS_SNB_GT1(dev)		((dev)->pci_device == 0x0102 || \
+				 (dev)->pci_device == 0x0106 ||	\
+				 (dev)->pci_device == 0x010A)
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
@@ -1196,6 +1201,9 @@ struct drm_i915_file_private {
 #define HAS_OVERLAY(dev)		(INTEL_INFO(dev)->has_overlay)
 #define OVERLAY_NEEDS_PHYSICAL(dev)	(INTEL_INFO(dev)->overlay_needs_physical)
 
+/* Early gen2 have a totally busted CS tlb and require pinned batches. */
+#define HAS_BROKEN_CS_TLB(dev)		(IS_I830(dev) || IS_845G(dev))
+
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
  */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 742206e45103..da3c82e301b1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1517,9 +1517,11 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 	if (obj->base.map_list.map)
 		return 0;
 
+	dev_priv->mm.shrinker_no_lock_stealing = true;
+
 	ret = drm_gem_create_mmap_offset(&obj->base);
 	if (ret != -ENOSPC)
-		return ret;
+		goto out;
 
 	/* Badly fragmented mmap space? The only way we can recover
 	 * space is by destroying unwanted objects. We can't randomly release
@@ -1531,10 +1533,14 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 	i915_gem_purge(dev_priv, obj->base.size >> PAGE_SHIFT);
 	ret = drm_gem_create_mmap_offset(&obj->base);
 	if (ret != -ENOSPC)
-		return ret;
+		goto out;
 
 	i915_gem_shrink_all(dev_priv);
-	return drm_gem_create_mmap_offset(&obj->base);
+	ret = drm_gem_create_mmap_offset(&obj->base);
+out:
+	dev_priv->mm.shrinker_no_lock_stealing = false;
+
+	return ret;
 }
 
 static void i915_gem_object_free_mmap_offset(struct drm_i915_gem_object *obj)
@@ -2890,7 +2896,7 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_mm_node *free_space;
+	struct drm_mm_node *node;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
 	bool mappable, fenceable;
 	int ret;
@@ -2936,66 +2942,54 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_pin_pages(obj);
 
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (node == NULL) {
+		i915_gem_object_unpin_pages(obj);
+		return -ENOMEM;
+	}
+
  search_free:
 	if (map_and_fenceable)
-		free_space = drm_mm_search_free_in_range_color(&dev_priv->mm.gtt_space,
-							       size, alignment, obj->cache_level,
-							       0, dev_priv->mm.gtt_mappable_end,
-							       false);
+		ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
+							  size, alignment, obj->cache_level,
+							  0, dev_priv->mm.gtt_mappable_end);
 	else
-		free_space = drm_mm_search_free_color(&dev_priv->mm.gtt_space,
-						      size, alignment, obj->cache_level,
-						      false);
-
-	if (free_space != NULL) {
-		if (map_and_fenceable)
-			free_space =
-				drm_mm_get_block_range_generic(free_space,
-							       size, alignment, obj->cache_level,
-							       0, dev_priv->mm.gtt_mappable_end,
-							       false);
-		else
-			free_space =
-				drm_mm_get_block_generic(free_space,
-							 size, alignment, obj->cache_level,
-							 false);
-	}
-	if (free_space == NULL) {
+		ret = drm_mm_insert_node_generic(&dev_priv->mm.gtt_space, node,
+						 size, alignment, obj->cache_level);
+	if (ret) {
 		ret = i915_gem_evict_something(dev, size, alignment,
 					       obj->cache_level,
 					       map_and_fenceable,
 					       nonblocking);
-		if (ret) {
-			i915_gem_object_unpin_pages(obj);
-			return ret;
-		}
+		if (ret == 0)
+			goto search_free;
 
-		goto search_free;
+		i915_gem_object_unpin_pages(obj);
+		kfree(node);
+		return ret;
 	}
-	if (WARN_ON(!i915_gem_valid_gtt_space(dev,
-					      free_space,
-					      obj->cache_level))) {
+	if (WARN_ON(!i915_gem_valid_gtt_space(dev, node, obj->cache_level))) {
 		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(free_space);
+		drm_mm_put_block(node);
 		return -EINVAL;
 	}
 
 	ret = i915_gem_gtt_prepare_object(obj);
 	if (ret) {
 		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(free_space);
+		drm_mm_put_block(node);
 		return ret;
 	}
 
 	list_move_tail(&obj->gtt_list, &dev_priv->mm.bound_list);
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
-	obj->gtt_space = free_space;
-	obj->gtt_offset = free_space->start;
+	obj->gtt_space = node;
+	obj->gtt_offset = node->start;
 
 	fenceable =
-		free_space->size == fence_size &&
-		(free_space->start & (fence_alignment - 1)) == 0;
+		node->size == fence_size &&
+		(node->start & (fence_alignment - 1)) == 0;
 
 	mappable =
 		obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end;
@@ -4392,6 +4386,9 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 		if (!mutex_is_locked_by(&dev->struct_mutex, current))
 			return 0;
 
+		if (dev_priv->mm.shrinker_no_lock_stealing)
+			return 0;
+
 		unlock = false;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 773ef77b6c22..7be4241e8242 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -226,7 +226,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 {
 	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
 
-	return dma_buf_export(obj, &i915_dmabuf_ops, obj->base.size, 0600);
+	return dma_buf_export(obj, &i915_dmabuf_ops, obj->base.size, flags);
 }
 
 static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index ee8f97f0539e..d6a994a07393 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -808,6 +808,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 		flags |= I915_DISPATCH_SECURE;
 	}
+	if (args->flags & I915_EXEC_IS_PINNED)
+		flags |= I915_DISPATCH_PINNED;
 
 	switch (args->flags & I915_EXEC_RING_MASK) {
 	case I915_EXEC_DEFAULT:
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index a4dc97f8b9f0..2220dec3e5d9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1087,6 +1087,18 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 	if (!ring->get_seqno)
 		return NULL;
 
+	if (HAS_BROKEN_CS_TLB(dev_priv->dev)) {
+		u32 acthd = I915_READ(ACTHD);
+
+		if (WARN_ON(ring->id != RCS))
+			return NULL;
+
+		obj = ring->private;
+		if (acthd >= obj->gtt_offset &&
+		    acthd < obj->gtt_offset + obj->base.size)
+			return i915_error_object_create(dev_priv, obj);
+	}
+
 	seqno = ring->get_seqno(ring, false);
 	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
 		if (obj->ring != ring)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3f75cfaf1c3f..186ee5c85b51 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -517,6 +517,7 @@
  * the enables for writing to the corresponding low bit.
  */
 #define _3D_CHICKEN	0x02084
+#define  _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB	(1 << 10)
 #define _3D_CHICKEN2	0x0208c
 /* Disables pipelining of read flushes past the SF-WIZ interface.
  * Required on all Ironlake steppings according to the B-Spec, but the
@@ -532,7 +533,8 @@
 # define MI_FLUSH_ENABLE				(1 << 12)
 
 #define GEN6_GT_MODE	0x20d0
-#define   GEN6_GT_MODE_HI	(1 << 9)
+#define   GEN6_GT_MODE_HI				(1 << 9)
+#define   GEN6_TD_FOUR_ROW_DISPATCH_DISABLE		(1 << 5)
 
 #define GFX_MODE	0x02520
 #define GFX_MODE_GEN7	0x0229c
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5d127e068950..a9fb046b94a1 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8144,10 +8144,6 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 			DRM_DEBUG_KMS("encoder changed, full mode switch\n");
 			config->mode_changed = true;
 		}
-
-		/* Disable all disconnected encoders. */
-		if (connector->base.status == connector_status_disconnected)
-			connector->new_encoder = NULL;
 	}
 	/* connector->new_encoder is now updated for all connectors. */
 
@@ -9167,6 +9163,23 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 	 * the crtc fixup. */
 }
 
+static void i915_redisable_vga(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 vga_reg;
+
+	if (HAS_PCH_SPLIT(dev))
+		vga_reg = CPU_VGACNTRL;
+	else
+		vga_reg = VGACNTRL;
+
+	if (I915_READ(vga_reg) != VGA_DISP_DISABLE) {
+		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
+		I915_WRITE(vga_reg, VGA_DISP_DISABLE);
+		POSTING_READ(vga_reg);
+	}
+}
+
 /* Scan out the current hw modeset state, sanitizes it and maps it into the drm
  * and i915 state tracking structures. */
 void intel_modeset_setup_hw_state(struct drm_device *dev,
@@ -9275,6 +9288,8 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 			intel_set_mode(&crtc->base, &crtc->base.mode,
 				       crtc->base.x, crtc->base.y, crtc->base.fb);
 		}
+
+		i915_redisable_vga(dev);
 	} else {
 		intel_modeset_update_staged_output_state(dev);
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 496caa73eb70..e6f54ffab3ba 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -405,7 +405,7 @@ void intel_update_fbc(struct drm_device *dev)
 	 *   - going to an unsupported config (interlace, pixel multiply, etc.)
 	 */
 	list_for_each_entry(tmp_crtc, &dev->mode_config.crtc_list, head) {
-		if (tmp_crtc->enabled &&
+		if (to_intel_crtc(tmp_crtc)->active &&
 		    !to_intel_crtc(tmp_crtc)->primary_disabled &&
 		    tmp_crtc->fb) {
 			if (crtc) {
@@ -992,7 +992,7 @@ static struct drm_crtc *single_enabled_crtc(struct drm_device *dev)
 	struct drm_crtc *crtc, *enabled = NULL;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		if (crtc->enabled && crtc->fb) {
+		if (to_intel_crtc(crtc)->active && crtc->fb) {
 			if (enabled)
 				return NULL;
 			enabled = crtc;
@@ -1086,7 +1086,7 @@ static bool g4x_compute_wm0(struct drm_device *dev,
 	int entries, tlb_miss;
 
 	crtc = intel_get_crtc_for_plane(dev, plane);
-	if (crtc->fb == NULL || !crtc->enabled) {
+	if (crtc->fb == NULL || !to_intel_crtc(crtc)->active) {
 		*cursor_wm = cursor->guard_size;
 		*plane_wm = display->guard_size;
 		return false;
@@ -1215,7 +1215,7 @@ static bool vlv_compute_drain_latency(struct drm_device *dev,
 	int entries;
 
 	crtc = intel_get_crtc_for_plane(dev, plane);
-	if (crtc->fb == NULL || !crtc->enabled)
+	if (crtc->fb == NULL || !to_intel_crtc(crtc)->active)
 		return false;
 
 	clock = crtc->mode.clock;	/* VESA DOT Clock */
@@ -1286,6 +1286,7 @@ static void valleyview_update_wm(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int planea_wm, planeb_wm, cursora_wm, cursorb_wm;
 	int plane_sr, cursor_sr;
+	int ignore_plane_sr, ignore_cursor_sr;
 	unsigned int enabled = 0;
 
 	vlv_update_drain_latency(dev);
@@ -1302,17 +1303,23 @@ static void valleyview_update_wm(struct drm_device *dev)
 			    &planeb_wm, &cursorb_wm))
 		enabled |= 2;
 
-	plane_sr = cursor_sr = 0;
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
 			     sr_latency_ns,
 			     &valleyview_wm_info,
 			     &valleyview_cursor_wm_info,
-			     &plane_sr, &cursor_sr))
+			     &plane_sr, &ignore_cursor_sr) &&
+	    g4x_compute_srwm(dev, ffs(enabled) - 1,
+			     2*sr_latency_ns,
+			     &valleyview_wm_info,
+			     &valleyview_cursor_wm_info,
+			     &ignore_plane_sr, &cursor_sr)) {
 		I915_WRITE(FW_BLC_SELF_VLV, FW_CSPWRDWNEN);
-	else
+	} else {
 		I915_WRITE(FW_BLC_SELF_VLV,
 			   I915_READ(FW_BLC_SELF_VLV) & ~FW_CSPWRDWNEN);
+		plane_sr = cursor_sr = 0;
+	}
 
 	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
 		      planea_wm, cursora_wm,
@@ -1352,17 +1359,18 @@ static void g4x_update_wm(struct drm_device *dev)
 			    &planeb_wm, &cursorb_wm))
 		enabled |= 2;
 
-	plane_sr = cursor_sr = 0;
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
 			     sr_latency_ns,
 			     &g4x_wm_info,
 			     &g4x_cursor_wm_info,
-			     &plane_sr, &cursor_sr))
+			     &plane_sr, &cursor_sr)) {
 		I915_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN);
-	else
+	} else {
 		I915_WRITE(FW_BLC_SELF,
 			   I915_READ(FW_BLC_SELF) & ~FW_BLC_SELF_EN);
+		plane_sr = cursor_sr = 0;
+	}
 
 	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
 		      planea_wm, cursora_wm,
@@ -1468,7 +1476,7 @@ static void i9xx_update_wm(struct drm_device *dev)
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 0);
 	crtc = intel_get_crtc_for_plane(dev, 0);
-	if (crtc->enabled && crtc->fb) {
+	if (to_intel_crtc(crtc)->active && crtc->fb) {
 		int cpp = crtc->fb->bits_per_pixel / 8;
 		if (IS_GEN2(dev))
 			cpp = 4;
@@ -1482,7 +1490,7 @@ static void i9xx_update_wm(struct drm_device *dev)
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 1);
 	crtc = intel_get_crtc_for_plane(dev, 1);
-	if (crtc->enabled && crtc->fb) {
+	if (to_intel_crtc(crtc)->active && crtc->fb) {
 		int cpp = crtc->fb->bits_per_pixel / 8;
 		if (IS_GEN2(dev))
 			cpp = 4;
@@ -1811,8 +1819,110 @@ static void sandybridge_update_wm(struct drm_device *dev)
 		enabled |= 2;
 	}
 
-	if ((dev_priv->num_pipe == 3) &&
-	    g4x_compute_wm0(dev, 2,
+	/*
+	 * Calculate and update the self-refresh watermark only when one
+	 * display plane is used.
+	 *
+	 * SNB support 3 levels of watermark.
+	 *
+	 * WM1/WM2/WM2 watermarks have to be enabled in the ascending order,
+	 * and disabled in the descending order
+	 *
+	 */
+	I915_WRITE(WM3_LP_ILK, 0);
+	I915_WRITE(WM2_LP_ILK, 0);
+	I915_WRITE(WM1_LP_ILK, 0);
+
+	if (!single_plane_enabled(enabled) ||
+	    dev_priv->sprite_scaling_enabled)
+		return;
+	enabled = ffs(enabled) - 1;
+
+	/* WM1 */
+	if (!ironlake_compute_srwm(dev, 1, enabled,
+				   SNB_READ_WM1_LATENCY() * 500,
+				   &sandybridge_display_srwm_info,
+				   &sandybridge_cursor_srwm_info,
+				   &fbc_wm, &plane_wm, &cursor_wm))
+		return;
+
+	I915_WRITE(WM1_LP_ILK,
+		   WM1_LP_SR_EN |
+		   (SNB_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (fbc_wm << WM1_LP_FBC_SHIFT) |
+		   (plane_wm << WM1_LP_SR_SHIFT) |
+		   cursor_wm);
+
+	/* WM2 */
+	if (!ironlake_compute_srwm(dev, 2, enabled,
+				   SNB_READ_WM2_LATENCY() * 500,
+				   &sandybridge_display_srwm_info,
+				   &sandybridge_cursor_srwm_info,
+				   &fbc_wm, &plane_wm, &cursor_wm))
+		return;
+
+	I915_WRITE(WM2_LP_ILK,
+		   WM2_LP_EN |
+		   (SNB_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (fbc_wm << WM1_LP_FBC_SHIFT) |
+		   (plane_wm << WM1_LP_SR_SHIFT) |
+		   cursor_wm);
+
+	/* WM3 */
+	if (!ironlake_compute_srwm(dev, 3, enabled,
+				   SNB_READ_WM3_LATENCY() * 500,
+				   &sandybridge_display_srwm_info,
+				   &sandybridge_cursor_srwm_info,
+				   &fbc_wm, &plane_wm, &cursor_wm))
+		return;
+
+	I915_WRITE(WM3_LP_ILK,
+		   WM3_LP_EN |
+		   (SNB_READ_WM3_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (fbc_wm << WM1_LP_FBC_SHIFT) |
+		   (plane_wm << WM1_LP_SR_SHIFT) |
+		   cursor_wm);
+}
+
+static void ivybridge_update_wm(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	u32 val;
+	int fbc_wm, plane_wm, cursor_wm;
+	int ignore_fbc_wm, ignore_plane_wm, ignore_cursor_wm;
+	unsigned int enabled;
+
+	enabled = 0;
+	if (g4x_compute_wm0(dev, 0,
+			    &sandybridge_display_wm_info, latency,
+			    &sandybridge_cursor_wm_info, latency,
+			    &plane_wm, &cursor_wm)) {
+		val = I915_READ(WM0_PIPEA_ILK);
+		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
+		I915_WRITE(WM0_PIPEA_ILK, val |
+			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
+		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
+			      " plane %d, " "cursor: %d\n",
+			      plane_wm, cursor_wm);
+		enabled |= 1;
+	}
+
+	if (g4x_compute_wm0(dev, 1,
+			    &sandybridge_display_wm_info, latency,
+			    &sandybridge_cursor_wm_info, latency,
+			    &plane_wm, &cursor_wm)) {
+		val = I915_READ(WM0_PIPEB_ILK);
+		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
+		I915_WRITE(WM0_PIPEB_ILK, val |
+			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
+		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
+			      " plane %d, cursor: %d\n",
+			      plane_wm, cursor_wm);
+		enabled |= 2;
+	}
+
+	if (g4x_compute_wm0(dev, 2,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1875,12 +1985,17 @@ static void sandybridge_update_wm(struct drm_device *dev)
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
-	/* WM3 */
+	/* WM3, note we have to correct the cursor latency */
 	if (!ironlake_compute_srwm(dev, 3, enabled,
 				   SNB_READ_WM3_LATENCY() * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
+				   &fbc_wm, &plane_wm, &ignore_cursor_wm) ||
+	    !ironlake_compute_srwm(dev, 3, enabled,
+				   2 * SNB_READ_WM3_LATENCY() * 500,
+				   &sandybridge_display_srwm_info,
+				   &sandybridge_cursor_srwm_info,
+				   &ignore_fbc_wm, &ignore_plane_wm, &cursor_wm))
 		return;
 
 	I915_WRITE(WM3_LP_ILK,
@@ -1929,7 +2044,7 @@ sandybridge_compute_sprite_wm(struct drm_device *dev, int plane,
 	int entries, tlb_miss;
 
 	crtc = intel_get_crtc_for_plane(dev, plane);
-	if (crtc->fb == NULL || !crtc->enabled) {
+	if (crtc->fb == NULL || !to_intel_crtc(crtc)->active) {
 		*sprite_wm = display->guard_size;
 		return false;
 	}
@@ -3471,6 +3586,15 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 		   I915_READ(ILK_DISPLAY_CHICKEN2) |
 		   ILK_ELPIN_409_SELECT);
 
+	/* WaDisableHiZPlanesWhenMSAAEnabled */
+	I915_WRITE(_3D_CHICKEN,
+		   _MASKED_BIT_ENABLE(_3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB));
+
+	/* WaSetupGtModeTdRowDispatch */
+	if (IS_SNB_GT1(dev))
+		I915_WRITE(GEN6_GT_MODE,
+			   _MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE));
+
 	I915_WRITE(WM3_LP_ILK, 0);
 	I915_WRITE(WM2_LP_ILK, 0);
 	I915_WRITE(WM1_LP_ILK, 0);
@@ -3999,7 +4123,7 @@ void intel_init_pm(struct drm_device *dev)
 		} else if (IS_IVYBRIDGE(dev)) {
 			/* FIXME: detect B0+ stepping and use auto training */
 			if (SNB_READ_WM0_LATENCY()) {
-				dev_priv->display.update_wm = sandybridge_update_wm;
+				dev_priv->display.update_wm = ivybridge_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
 			} else {
 				DRM_DEBUG_KMS("Failed to read display plane latency. "
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 2346b920bd86..ae253e04c391 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -547,9 +547,14 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 
 static void render_ring_cleanup(struct intel_ring_buffer *ring)
 {
+	struct drm_device *dev = ring->dev;
+
 	if (!ring->private)
 		return;
 
+	if (HAS_BROKEN_CS_TLB(dev))
+		drm_gem_object_unreference(to_gem_object(ring->private));
+
 	cleanup_pipe_control(ring);
 }
 
@@ -969,6 +974,8 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+/* Just userspace ABI convention to limit the wa batch bo to a resonable size */
+#define I830_BATCH_LIMIT (256*1024)
 static int
 i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 				u32 offset, u32 len,
@@ -976,15 +983,47 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 {
 	int ret;
 
-	ret = intel_ring_begin(ring, 4);
-	if (ret)
-		return ret;
+	if (flags & I915_DISPATCH_PINNED) {
+		ret = intel_ring_begin(ring, 4);
+		if (ret)
+			return ret;
 
-	intel_ring_emit(ring, MI_BATCH_BUFFER);
-	intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
-	intel_ring_emit(ring, offset + len - 8);
-	intel_ring_emit(ring, 0);
-	intel_ring_advance(ring);
+		intel_ring_emit(ring, MI_BATCH_BUFFER);
+		intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+		intel_ring_emit(ring, offset + len - 8);
+		intel_ring_emit(ring, MI_NOOP);
+		intel_ring_advance(ring);
+	} else {
+		struct drm_i915_gem_object *obj = ring->private;
+		u32 cs_offset = obj->gtt_offset;
+
+		if (len > I830_BATCH_LIMIT)
+			return -ENOSPC;
+
+		ret = intel_ring_begin(ring, 9+3);
+		if (ret)
+			return ret;
+		/* Blit the batch (which has now all relocs applied) to the stable batch
+		 * scratch bo area (so that the CS never stumbles over its tlb
+		 * invalidation bug) ... */
+		intel_ring_emit(ring, XY_SRC_COPY_BLT_CMD |
+				XY_SRC_COPY_BLT_WRITE_ALPHA |
+				XY_SRC_COPY_BLT_WRITE_RGB);
+		intel_ring_emit(ring, BLT_DEPTH_32 | BLT_ROP_GXCOPY | 4096);
+		intel_ring_emit(ring, 0);
+		intel_ring_emit(ring, (DIV_ROUND_UP(len, 4096) << 16) | 1024);
+		intel_ring_emit(ring, cs_offset);
+		intel_ring_emit(ring, 0);
+		intel_ring_emit(ring, 4096);
+		intel_ring_emit(ring, offset);
+		intel_ring_emit(ring, MI_FLUSH);
+
+		/* ... and execute it. */
+		intel_ring_emit(ring, MI_BATCH_BUFFER);
+		intel_ring_emit(ring, cs_offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+		intel_ring_emit(ring, cs_offset + len - 8);
+		intel_ring_advance(ring);
+	}
 
 	return 0;
 }
@@ -1596,6 +1635,27 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 	ring->init = init_render_ring;
 	ring->cleanup = render_ring_cleanup;
 
+	/* Workaround batchbuffer to combat CS tlb bug. */
+	if (HAS_BROKEN_CS_TLB(dev)) {
+		struct drm_i915_gem_object *obj;
+		int ret;
+
+		obj = i915_gem_alloc_object(dev, I830_BATCH_LIMIT);
+		if (obj == NULL) {
+			DRM_ERROR("Failed to allocate batch bo\n");
+			return -ENOMEM;
+		}
+
+		ret = i915_gem_object_pin(obj, 0, true, false);
+		if (ret != 0) {
+			drm_gem_object_unreference(&obj->base);
+			DRM_ERROR("Failed to ping batch bo\n");
+			return ret;
+		}
+
+		ring->private = obj;
+	}
+
 	return intel_init_ring_buffer(dev, ring);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 526182ed0c6d..6af87cd05725 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -94,6 +94,7 @@ struct  intel_ring_buffer {
 					       u32 offset, u32 length,
 					       unsigned flags);
 #define I915_DISPATCH_SECURE 0x1
+#define I915_DISPATCH_PINNED 0x2
 	void		(*cleanup)(struct intel_ring_buffer *ring);
 	int		(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,