Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intel

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intel: (58 commits)
  drm/i915,intel_agp: Add support for Sandybridge D0
  drm/i915: fix render pipe control notify on sandybridge
  agp/intel: set 40-bit dma mask on Sandybridge
  drm/i915: Remove the conflicting BUG_ON()
  drm/i915/suspend: s/IS_IRONLAKE/HAS_PCH_SPLIT/
  drm/i915/suspend: Flush register writes before busy-waiting.
  i915: disable DAC on Ironlake also when doing CRT load detection.
  drm/i915: wait for actual vblank, not just 20ms
  drm/i915: make sure eDP PLL is enabled at the right time
  drm/i915: fix VGA plane disable for Ironlake+
  drm/i915: eDP mode set sequence corrections
  drm/i915: add panel reset workaround
  drm/i915: Enable RC6 on Ironlake.
  drm/i915/sdvo: Only set is_lvds if we have a valid fixed mode.
  drm/i915: Set up a render context on Ironlake
  drm/i915 invalidate indirect state pointers at end of ring exec
  drm/i915: Wake-up wait_request() from elapsed hang-check (v2)
  drm/i915: Apply i830 errata for cursor alignment
  drm/i915: Only update i845/i865 CURBASE when disabled (v2)
  drm/i915: FBC is updated within set_base() so remove second call in mode_set()
  ...

28 files changed, 2663 insertions, 2417 deletions

diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c
index ddf5def1b0d..710af89b176 100644
--- a/drivers/char/agp/intel-agp.c
+++ b/drivers/char/agp/intel-agp.c
@@ -819,13 +819,16 @@ static const struct intel_driver_description {
 	    "Sandybridge", NULL, &intel_gen6_driver },
 	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_IG,
 	    "Sandybridge", NULL, &intel_gen6_driver },
+	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_D0_IG,
+	    "Sandybridge", NULL, &intel_gen6_driver },
 	{ 0, 0, NULL, NULL, NULL }
 };
 
 static int __devinit intel_gmch_probe(struct pci_dev *pdev,
 				      struct agp_bridge_data *bridge)
 {
-	int i;
+	int i, mask;
+
 	bridge->driver = NULL;
 
 	for (i = 0; intel_agp_chipsets[i].name != NULL; i++) {
@@ -845,14 +848,19 @@ static int __devinit intel_gmch_probe(struct pci_dev *pdev,
 
 	dev_info(&pdev->dev, "Intel %s Chipset\n", intel_agp_chipsets[i].name);
 
-	if (bridge->driver->mask_memory == intel_i965_mask_memory) {
-		if (pci_set_dma_mask(intel_private.pcidev, DMA_BIT_MASK(36)))
-			dev_err(&intel_private.pcidev->dev,
-				"set gfx device dma mask 36bit failed!\n");
-		else
-			pci_set_consistent_dma_mask(intel_private.pcidev,
-						    DMA_BIT_MASK(36));
-	}
+	if (bridge->driver->mask_memory == intel_gen6_mask_memory)
+		mask = 40;
+	else if (bridge->driver->mask_memory == intel_i965_mask_memory)
+		mask = 36;
+	else
+		mask = 32;
+
+	if (pci_set_dma_mask(intel_private.pcidev, DMA_BIT_MASK(mask)))
+		dev_err(&intel_private.pcidev->dev,
+			"set gfx device dma mask %d-bit failed!\n", mask);
+	else
+		pci_set_consistent_dma_mask(intel_private.pcidev,
+					    DMA_BIT_MASK(mask));
 
 	return 1;
 }
diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index c05e3e51826..08d47532e60 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -204,6 +204,7 @@
 #define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_IG  0x0102
 #define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB  0x0104
 #define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_IG  0x0106
+#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_D0_IG  0x0126
 
 /* cover 915 and 945 variants */
 #define IS_I915 (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_E7221_HB || \
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index da78f2c0d90..5c8e53458ed 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -8,6 +8,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o \
           i915_suspend.o \
 	  i915_gem.o \
 	  i915_gem_debug.o \
+	  i915_gem_evict.o \
 	  i915_gem_tiling.o \
 	  i915_trace_points.o \
 	  intel_display.o \
@@ -18,6 +19,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o \
 	  intel_hdmi.o \
 	  intel_sdvo.o \
 	  intel_modes.o \
+	  intel_panel.o \
 	  intel_i2c.o \
 	  intel_fb.o \
 	  intel_tv.o \
diff --git a/drivers/gpu/drm/i915/dvo.h b/drivers/gpu/drm/i915/dvo.h
index 0d6ff640e1c..8c2ad014c47 100644
--- a/drivers/gpu/drm/i915/dvo.h
+++ b/drivers/gpu/drm/i915/dvo.h
@@ -30,20 +30,17 @@
 #include "intel_drv.h"
 
 struct intel_dvo_device {
-	char *name;
+	const char *name;
 	int type;
 	/* DVOA/B/C output register */
 	u32 dvo_reg;
 	/* GPIO register used for i2c bus to control this device */
 	u32 gpio;
 	int slave_addr;
-	struct i2c_adapter *i2c_bus;
 
 	const struct intel_dvo_dev_ops *dev_ops;
 	void *dev_priv;
-
-	struct drm_display_mode *panel_fixed_mode;
-	bool panel_wants_dither;
+	struct i2c_adapter *i2c_bus;
 };
 
 struct intel_dvo_dev_ops {
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9214119c015..92d5605a34d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -467,6 +467,9 @@ static int i915_error_state(struct seq_file *m, void *unused)
 		}
 	}
 
+	if (error->overlay)
+		intel_overlay_print_error_state(m, error->overlay);
+
 out:
 	spin_unlock_irqrestore(&dev_priv->error_lock, flags);
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index f19ffe87af3..44af317731b 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -499,6 +499,13 @@ static int i915_dispatch_batchbuffer(struct drm_device * dev,
 		}
 	}
 
+
+	if (IS_G4X(dev) || IS_IRONLAKE(dev)) {
+		BEGIN_LP_RING(2);
+		OUT_RING(MI_FLUSH | MI_NO_WRITE_FLUSH | MI_INVALIDATE_ISP);
+		OUT_RING(MI_NOOP);
+		ADVANCE_LP_RING();
+	}
 	i915_emit_breadcrumb(dev);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5044f653e8e..00befce8fbb 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -181,6 +181,7 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x0046, &intel_ironlake_m_info),
 	INTEL_VGA_DEVICE(0x0102, &intel_sandybridge_d_info),
 	INTEL_VGA_DEVICE(0x0106, &intel_sandybridge_m_info),
+	INTEL_VGA_DEVICE(0x0126, &intel_sandybridge_m_info),
 	{0, 0, 0}
 };
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 906663b9929..047cd7ce7e1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -113,6 +113,9 @@ struct intel_opregion {
 	int enabled;
 };
 
+struct intel_overlay;
+struct intel_overlay_error_state;
+
 struct drm_i915_master_private {
 	drm_local_map_t *sarea;
 	struct _drm_i915_sarea *sarea_priv;
@@ -166,6 +169,7 @@ struct drm_i915_error_state {
 		u32 purgeable:1;
 	} *active_bo;
 	u32 active_bo_count;
+	struct intel_overlay_error_state *overlay;
 };
 
 struct drm_i915_display_funcs {
@@ -186,8 +190,6 @@ struct drm_i915_display_funcs {
 	/* clock gating init */
 };
 
-struct intel_overlay;
-
 struct intel_device_info {
 	u8 is_mobile : 1;
 	u8 is_i8xx : 1;
@@ -242,6 +244,7 @@ typedef struct drm_i915_private {
 	struct pci_dev *bridge_dev;
 	struct intel_ring_buffer render_ring;
 	struct intel_ring_buffer bsd_ring;
+	uint32_t next_seqno;
 
 	drm_dma_handle_t *status_page_dmah;
 	void *seqno_page;
@@ -251,6 +254,7 @@ typedef struct drm_i915_private {
 	drm_local_map_t hws_map;
 	struct drm_gem_object *seqno_obj;
 	struct drm_gem_object *pwrctx;
+	struct drm_gem_object *renderctx;
 
 	struct resource mch_res;
 
@@ -285,6 +289,9 @@ typedef struct drm_i915_private {
 	unsigned int sr01, adpa, ppcr, dvob, dvoc, lvds;
 	int vblank_pipe;
 	int num_pipe;
+	u32 flush_rings;
+#define FLUSH_RENDER_RING	0x1
+#define FLUSH_BSD_RING		0x2
 
 	/* For hangcheck timer */
 #define DRM_I915_HANGCHECK_PERIOD 75 /* in jiffies */
@@ -568,8 +575,6 @@ typedef struct drm_i915_private {
 		 */
 		struct delayed_work retire_work;
 
-		uint32_t next_gem_seqno;
-
 		/**
 		 * Waiting sequence number, if any
 		 */
@@ -610,6 +615,8 @@ typedef struct drm_i915_private {
 	struct sdvo_device_mapping sdvo_mappings[2];
 	/* indicate whether the LVDS_BORDER should be enabled or not */
 	unsigned int lvds_border_bits;
+	/* Panel fitter placement and size for Ironlake+ */
+	u32 pch_pf_pos, pch_pf_size;
 
 	struct drm_crtc *plane_to_crtc_mapping[2];
 	struct drm_crtc *pipe_to_crtc_mapping[2];
@@ -669,6 +676,8 @@ struct drm_i915_gem_object {
 	struct list_head list;
 	/** This object's place on GPU write list */
 	struct list_head gpu_write_list;
+	/** This object's place on eviction list */
+	struct list_head evict_list;
 
 	/**
 	 * This is set if the object is on the active or flushing lists
@@ -978,6 +987,7 @@ int i915_gem_init_ringbuffer(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int i915_gem_do_init(struct drm_device *dev, unsigned long start,
 		     unsigned long end);
+int i915_gpu_idle(struct drm_device *dev);
 int i915_gem_idle(struct drm_device *dev);
 uint32_t i915_add_request(struct drm_device *dev,
 		struct drm_file *file_priv,
@@ -991,7 +1001,9 @@ int i915_gem_object_set_to_gtt_domain(struct drm_gem_object *obj,
 				      int write);
 int i915_gem_object_set_to_display_plane(struct drm_gem_object *obj);
 int i915_gem_attach_phys_object(struct drm_device *dev,
-				struct drm_gem_object *obj, int id);
+				struct drm_gem_object *obj,
+				int id,
+				int align);
 void i915_gem_detach_phys_object(struct drm_device *dev,
 				 struct drm_gem_object *obj);
 void i915_gem_free_all_phys_object(struct drm_device *dev);
@@ -1003,6 +1015,11 @@ int i915_gem_object_flush_write_domain(struct drm_gem_object *obj);
 void i915_gem_shrinker_init(void);
 void i915_gem_shrinker_exit(void);
 
+/* i915_gem_evict.c */
+int i915_gem_evict_something(struct drm_device *dev, int min_size, unsigned alignment);
+int i915_gem_evict_everything(struct drm_device *dev);
+int i915_gem_evict_inactive(struct drm_device *dev);
+
 /* i915_gem_tiling.c */
 void i915_gem_detect_bit_6_swizzle(struct drm_device *dev);
 void i915_gem_object_do_bit_17_swizzle(struct drm_gem_object *obj);
@@ -1066,6 +1083,10 @@ extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
 extern void intel_detect_pch (struct drm_device *dev);
 extern int intel_trans_dp_port_sel (struct drm_crtc *crtc);
 
+/* overlay */
+extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
+extern void intel_overlay_print_error_state(struct seq_file *m, struct intel_overlay_error_state *error);
+
 /**
  * Lock test for when it's just for synchronization of ring access.
  *
@@ -1092,26 +1113,26 @@ extern int intel_trans_dp_port_sel (struct drm_crtc *crtc);
 #define I915_VERBOSE 0
 
 #define BEGIN_LP_RING(n)  do { \
-	drm_i915_private_t *dev_priv = dev->dev_private;                \
+	drm_i915_private_t *dev_priv__ = dev->dev_private;                \
 	if (I915_VERBOSE)						\
 		DRM_DEBUG("   BEGIN_LP_RING %x\n", (int)(n));		\
-	intel_ring_begin(dev, &dev_priv->render_ring, (n));		\
+	intel_ring_begin(dev, &dev_priv__->render_ring, (n));		\
 } while (0)
 
 
 #define OUT_RING(x) do {						\
-	drm_i915_private_t *dev_priv = dev->dev_private;		\
+	drm_i915_private_t *dev_priv__ = dev->dev_private;		\
 	if (I915_VERBOSE)						\
 		DRM_DEBUG("   OUT_RING %x\n", (int)(x));		\
-	intel_ring_emit(dev, &dev_priv->render_ring, x);		\
+	intel_ring_emit(dev, &dev_priv__->render_ring, x);		\
 } while (0)
 
 #define ADVANCE_LP_RING() do {						\
-	drm_i915_private_t *dev_priv = dev->dev_private;                \
+	drm_i915_private_t *dev_priv__ = dev->dev_private;                \
 	if (I915_VERBOSE)						\
 		DRM_DEBUG("ADVANCE_LP_RING %x\n",			\
-				dev_priv->render_ring.tail);		\
-	intel_ring_advance(dev, &dev_priv->render_ring);		\
+				dev_priv__->render_ring.tail);		\
+	intel_ring_advance(dev, &dev_priv__->render_ring);		\
 } while(0)
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0758c7802e6..df5a7135c26 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -35,6 +35,7 @@
 #include <linux/swap.h>
 #include <linux/pci.h>
 
+static uint32_t i915_gem_get_gtt_alignment(struct drm_gem_object *obj);
 static int i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj);
 static void i915_gem_object_flush_gtt_write_domain(struct drm_gem_object *obj);
 static void i915_gem_object_flush_cpu_write_domain(struct drm_gem_object *obj);
@@ -48,8 +49,6 @@ static int i915_gem_object_wait_rendering(struct drm_gem_object *obj);
 static int i915_gem_object_bind_to_gtt(struct drm_gem_object *obj,
 					   unsigned alignment);
 static void i915_gem_clear_fence_reg(struct drm_gem_object *obj);
-static int i915_gem_evict_something(struct drm_device *dev, int min_size);
-static int i915_gem_evict_from_inactive_list(struct drm_device *dev);
 static int i915_gem_phys_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
 				struct drm_i915_gem_pwrite *args,
 				struct drm_file *file_priv);
@@ -58,6 +57,14 @@ static void i915_gem_free_object_tail(struct drm_gem_object *obj);
 static LIST_HEAD(shrink_list);
 static DEFINE_SPINLOCK(shrink_list_lock);
 
+static inline bool
+i915_gem_object_is_inactive(struct drm_i915_gem_object *obj_priv)
+{
+	return obj_priv->gtt_space &&
+		!obj_priv->active &&
+		obj_priv->pin_count == 0;
+}
+
 int i915_gem_do_init(struct drm_device *dev, unsigned long start,
 		     unsigned long end)
 {
@@ -313,7 +320,8 @@ i915_gem_object_get_pages_or_evict(struct drm_gem_object *obj)
 	if (ret == -ENOMEM) {
 		struct drm_device *dev = obj->dev;
 
-		ret = i915_gem_evict_something(dev, obj->size);
+		ret = i915_gem_evict_something(dev, obj->size,
+					       i915_gem_get_gtt_alignment(obj));
 		if (ret)
 			return ret;
 
@@ -1036,6 +1044,11 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 		ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0);
 	}
 
+	
+	/* Maintain LRU order of "inactive" objects */
+	if (ret == 0 && i915_gem_object_is_inactive(obj_priv))
+		list_move_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
+
 	drm_gem_object_unreference(obj);
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
@@ -1137,7 +1150,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct drm_device *dev = obj->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj_priv = to_intel_bo(obj);
 	pgoff_t page_offset;
 	unsigned long pfn;
@@ -1155,8 +1168,6 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		if (ret)
 			goto unlock;
 
-		list_add_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
-
 		ret = i915_gem_object_set_to_gtt_domain(obj, write);
 		if (ret)
 			goto unlock;
@@ -1169,6 +1180,9 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 			goto unlock;
 	}
 
+	if (i915_gem_object_is_inactive(obj_priv))
+		list_move_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
+
 	pfn = ((dev->agp->base + obj_priv->gtt_offset) >> PAGE_SHIFT) +
 		page_offset;
 
@@ -1363,7 +1377,6 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv)
 {
 	struct drm_i915_gem_mmap_gtt *args = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_gem_object *obj;
 	struct drm_i915_gem_object *obj_priv;
 	int ret;
@@ -1409,7 +1422,6 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
 			mutex_unlock(&dev->struct_mutex);
 			return ret;
 		}
-		list_add_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
 	}
 
 	drm_gem_object_unreference(obj);
@@ -1493,9 +1505,16 @@ i915_gem_object_truncate(struct drm_gem_object *obj)
 	struct drm_i915_gem_object *obj_priv = to_intel_bo(obj);
 	struct inode *inode;
 
+	/* Our goal here is to return as much of the memory as
+	 * is possible back to the system as we are called from OOM.
+	 * To do this we must instruct the shmfs to drop all of its
+	 * backing pages, *now*. Here we mirror the actions taken
+	 * when by shmem_delete_inode() to release the backing store.
+	 */
 	inode = obj->filp->f_path.dentry->d_inode;
-	if (inode->i_op->truncate)
-		inode->i_op->truncate (inode);
+	truncate_inode_pages(inode->i_mapping, 0);
+	if (inode->i_op->truncate_range)
+		inode->i_op->truncate_range(inode, 0, (loff_t)-1);
 
 	obj_priv->madv = __I915_MADV_PURGED;
 }
@@ -1887,19 +1906,6 @@ i915_gem_flush(struct drm_device *dev,
 				flush_domains);
 }
 
-static void
-i915_gem_flush_ring(struct drm_device *dev,
-	       uint32_t invalidate_domains,
-	       uint32_t flush_domains,
-	       struct intel_ring_buffer *ring)
-{
-	if (flush_domains & I915_GEM_DOMAIN_CPU)
-		drm_agp_chipset_flush(dev);
-	ring->flush(dev, ring,
-			invalidate_domains,
-			flush_domains);
-}
-
 /**
  * Ensures that all rendering to the object has completed and the object is
  * safe to unbind from the GTT or access from the CPU.
@@ -1973,8 +1979,6 @@ i915_gem_object_unbind(struct drm_gem_object *obj)
 	 * cause memory corruption through use-after-free.
 	 */
 
-	BUG_ON(obj_priv->active);
-
 	/* release the fence reg _after_ flushing */
 	if (obj_priv->fence_reg != I915_FENCE_REG_NONE)
 		i915_gem_clear_fence_reg(obj);
@@ -2010,34 +2014,7 @@ i915_gem_object_unbind(struct drm_gem_object *obj)
 	return ret;
 }
 
-static struct drm_gem_object *
-i915_gem_find_inactive_object(struct drm_device *dev, int min_size)
-{
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj_priv;
-	struct drm_gem_object *best = NULL;
-	struct drm_gem_object *first = NULL;
-
-	/* Try to find the smallest clean object */
-	list_for_each_entry(obj_priv, &dev_priv->mm.inactive_list, list) {
-		struct drm_gem_object *obj = &obj_priv->base;
-		if (obj->size >= min_size) {
-			if ((!obj_priv->dirty ||
-			     i915_gem_object_is_purgeable(obj_priv)) &&
-			    (!best || obj->size < best->size)) {
-				best = obj;
-				if (best->size == min_size)
-					return best;
-			}
-			if (!first)
-			    first = obj;
-		}
-	}
-
-	return best ? best : first;
-}
-
-static int
+int
 i915_gpu_idle(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -2078,155 +2055,6 @@ i915_gpu_idle(struct drm_device *dev)
 	return ret;
 }
 
-static int
-i915_gem_evict_everything(struct drm_device *dev)
-{
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
-	bool lists_empty;
-
-	spin_lock(&dev_priv->mm.active_list_lock);
-	lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
-		       list_empty(&dev_priv->mm.flushing_list) &&
-		       list_empty(&dev_priv->render_ring.active_list) &&
-		       (!HAS_BSD(dev)
-			|| list_empty(&dev_priv->bsd_ring.active_list)));
-	spin_unlock(&dev_priv->mm.active_list_lock);
-
-	if (lists_empty)
-		return -ENOSPC;
-
-	/* Flush everything (on to the inactive lists) and evict */
-	ret = i915_gpu_idle(dev);
-	if (ret)
-		return ret;
-
-	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
-
-	ret = i915_gem_evict_from_inactive_list(dev);
-	if (ret)
-		return ret;
-
-	spin_lock(&dev_priv->mm.active_list_lock);
-	lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
-		       list_empty(&dev_priv->mm.flushing_list) &&
-		       list_empty(&dev_priv->render_ring.active_list) &&
-		       (!HAS_BSD(dev)
-			|| list_empty(&dev_priv->bsd_ring.active_list)));
-	spin_unlock(&dev_priv->mm.active_list_lock);
-	BUG_ON(!lists_empty);
-
-	return 0;
-}
-
-static int
-i915_gem_evict_something(struct drm_device *dev, int min_size)
-{
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_gem_object *obj;
-	int ret;
-
-	struct intel_ring_buffer *render_ring = &dev_priv->render_ring;
-	struct intel_ring_buffer *bsd_ring = &dev_priv->bsd_ring;
-	for (;;) {
-		i915_gem_retire_requests(dev);
-
-		/* If there's an inactive buffer available now, grab it
-		 * and be done.
-		 */
-		obj = i915_gem_find_inactive_object(dev, min_size);
-		if (obj) {
-			struct drm_i915_gem_object *obj_priv;
-
-#if WATCH_LRU
-			DRM_INFO("%s: evicting %p\n", __func__, obj);
-#endif
-			obj_priv = to_intel_bo(obj);
-			BUG_ON(obj_priv->pin_count != 0);
-			BUG_ON(obj_priv->active);
-
-			/* Wait on the rendering and unbind the buffer. */
-			return i915_gem_object_unbind(obj);
-		}
-
-		/* If we didn't get anything, but the ring is still processing
-		 * things, wait for the next to finish and hopefully leave us
-		 * a buffer to evict.
-		 */
-		if (!list_empty(&render_ring->request_list)) {
-			struct drm_i915_gem_request *request;
-
-			request = list_first_entry(&render_ring->request_list,
-						   struct drm_i915_gem_request,
-						   list);
-
-			ret = i915_wait_request(dev,
-					request->seqno, request->ring);
-			if (ret)
-				return ret;
-
-			continue;
-		}
-
-		if (HAS_BSD(dev) && !list_empty(&bsd_ring->request_list)) {
-			struct drm_i915_gem_request *request;
-
-			request = list_first_entry(&bsd_ring->request_list,
-						   struct drm_i915_gem_request,
-						   list);
-
-			ret = i915_wait_request(dev,
-					request->seqno, request->ring);
-			if (ret)
-				return ret;
-
-			continue;
-		}
-
-		/* If we didn't have anything on the request list but there
-		 * are buffers awaiting a flush, emit one and try again.
-		 * When we wait on it, those buffers waiting for that flush
-		 * will get moved to inactive.
-		 */
-		if (!list_empty(&dev_priv->mm.flushing_list)) {
-			struct drm_i915_gem_object *obj_priv;
-
-			/* Find an object that we can immediately reuse */
-			list_for_each_entry(obj_priv, &dev_priv->mm.flushing_list, list) {
-				obj = &obj_priv->base;
-				if (obj->size >= min_size)
-					break;
-
-				obj = NULL;
-			}
-
-			if (obj != NULL) {
-				uint32_t seqno;
-
-				i915_gem_flush_ring(dev,
-					       obj->write_domain,
-					       obj->write_domain,
-					       obj_priv->ring);
-				seqno = i915_add_request(dev, NULL,
-						obj->write_domain,
-						obj_priv->ring);
-				if (seqno == 0)
-					return -ENOMEM;
-				continue;
-			}
-		}
-
-		/* If we didn't do any of the above, there's no single buffer
-		 * large enough to swap out for the new one, so just evict
-		 * everything and start again. (This should be rare.)
-		 */
-		if (!list_empty (&dev_priv->mm.inactive_list))
-			return i915_gem_evict_from_inactive_list(dev);
-		else
-			return i915_gem_evict_everything(dev);
-	}
-}
-
 int
 i915_gem_object_get_pages(struct drm_gem_object *obj,
 			  gfp_t gfpmask)
@@ -2666,7 +2494,7 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 #if WATCH_LRU
 		DRM_INFO("%s: GTT full, evicting something\n", __func__);
 #endif
-		ret = i915_gem_evict_something(dev, obj->size);
+		ret = i915_gem_evict_something(dev, obj->size, alignment);
 		if (ret)
 			return ret;
 
@@ -2684,7 +2512,8 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 
 		if (ret == -ENOMEM) {
 			/* first try to clear up some space from the GTT */
-			ret = i915_gem_evict_something(dev, obj->size);
+			ret = i915_gem_evict_something(dev, obj->size,
+						       alignment);
 			if (ret) {
 				/* now try to shrink everyone else */
 				if (gfpmask) {
@@ -2714,7 +2543,7 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 		drm_mm_put_block(obj_priv->gtt_space);
 		obj_priv->gtt_space = NULL;
 
-		ret = i915_gem_evict_something(dev, obj->size);
+		ret = i915_gem_evict_something(dev, obj->size, alignment);
 		if (ret)
 			return ret;
 
@@ -2723,6 +2552,9 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 	atomic_inc(&dev->gtt_count);
 	atomic_add(obj->size, &dev->gtt_memory);
 
+	/* keep track of bounds object by adding it to the inactive list */
+	list_add_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
+
 	/* Assert that the object is not currently in any GPU domain. As it
 	 * wasn't in the GTT, there shouldn't be any way it could have been in
 	 * a GPU cache
@@ -3117,6 +2949,7 @@ static void
 i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj)
 {
 	struct drm_device		*dev = obj->dev;
+	drm_i915_private_t		*dev_priv = dev->dev_private;
 	struct drm_i915_gem_object	*obj_priv = to_intel_bo(obj);
 	uint32_t			invalidate_domains = 0;
 	uint32_t			flush_domains = 0;
@@ -3179,6 +3012,13 @@ i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj)
 		obj->pending_write_domain = obj->write_domain;
 	obj->read_domains = obj->pending_read_domains;
 
+	if (flush_domains & I915_GEM_GPU_DOMAINS) {
+		if (obj_priv->ring == &dev_priv->render_ring)
+			dev_priv->flush_rings |= FLUSH_RENDER_RING;
+		else if (obj_priv->ring == &dev_priv->bsd_ring)
+			dev_priv->flush_rings |= FLUSH_BSD_RING;
+	}
+
 	dev->invalidate_domains |= invalidate_domains;
 	dev->flush_domains |= flush_domains;
 #if WATCH_BUF
@@ -3718,7 +3558,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		ring = &dev_priv->render_ring;
 	}
 
-
 	if (args->buffer_count < 1) {
 		DRM_ERROR("execbuf with %d buffers\n", args->buffer_count);
 		return -EINVAL;
@@ -3892,6 +3731,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	 */
 	dev->invalidate_domains = 0;
 	dev->flush_domains = 0;
+	dev_priv->flush_rings = 0;
 
 	for (i = 0; i < args->buffer_count; i++) {
 		struct drm_gem_object *obj = object_list[i];
@@ -3912,16 +3752,14 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		i915_gem_flush(dev,
 			       dev->invalidate_domains,
 			       dev->flush_domains);
-		if (dev->flush_domains & I915_GEM_GPU_DOMAINS) {
+		if (dev_priv->flush_rings & FLUSH_RENDER_RING)
 			(void)i915_add_request(dev, file_priv,
-					dev->flush_domains,
-					&dev_priv->render_ring);
-
-			if (HAS_BSD(dev))
-				(void)i915_add_request(dev, file_priv,
-						dev->flush_domains,
-						&dev_priv->bsd_ring);
-		}
+					       dev->flush_domains,
+					       &dev_priv->render_ring);
+		if (dev_priv->flush_rings & FLUSH_BSD_RING)
+			(void)i915_add_request(dev, file_priv,
+					       dev->flush_domains,
+					       &dev_priv->bsd_ring);
 	}
 
 	for (i = 0; i < args->buffer_count; i++) {
@@ -4192,6 +4030,10 @@ i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment)
 		if (alignment == 0)
 			alignment = i915_gem_get_gtt_alignment(obj);
 		if (obj_priv->gtt_offset & (alignment - 1)) {
+			WARN(obj_priv->pin_count,
+			     "bo is already pinned with incorrect alignment:"
+			     " offset=%x, req.alignment=%x\n",
+			     obj_priv->gtt_offset, alignment);
 			ret = i915_gem_object_unbind(obj);
 			if (ret)
 				return ret;
@@ -4213,8 +4055,7 @@ i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment)
 		atomic_inc(&dev->pin_count);
 		atomic_add(obj->size, &dev->pin_memory);
 		if (!obj_priv->active &&
-		    (obj->write_domain & I915_GEM_GPU_DOMAINS) == 0 &&
-		    !list_empty(&obj_priv->list))
+		    (obj->write_domain & I915_GEM_GPU_DOMAINS) == 0)
 			list_del_init(&obj_priv->list);
 	}
 	i915_verify_inactive(dev, __FILE__, __LINE__);
@@ -4359,22 +4200,34 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 	}
 
 	mutex_lock(&dev->struct_mutex);
-	/* Update the active list for the hardware's current position.
-	 * Otherwise this only updates on a delayed timer or when irqs are
-	 * actually unmasked, and our working set ends up being larger than
-	 * required.
-	 */
-	i915_gem_retire_requests(dev);
 
-	obj_priv = to_intel_bo(obj);
-	/* Don't count being on the flushing list against the object being
-	 * done.  Otherwise, a buffer left on the flush