diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9717bf42f846..11ae06aac1f1 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -564,45 +564,6 @@ static int i915_hws_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static void i915_dump_object(struct seq_file *m,
-			     struct io_mapping *mapping,
-			     struct drm_i915_gem_object *obj)
-{
-	int page, page_count, i;
-
-	page_count = obj->base.size / PAGE_SIZE;
-	for (page = 0; page < page_count; page++) {
-		u32 *mem = io_mapping_map_wc(mapping,
-					     obj->gtt_offset + page * PAGE_SIZE);
-		for (i = 0; i < PAGE_SIZE; i += 4)
-			seq_printf(m, "%08x :  %08x\n", i, mem[i / 4]);
-		io_mapping_unmap(mem);
-	}
-}
-
-static int i915_batchbuffer_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
-	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
-		if (obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) {
-		    seq_printf(m, "--- gtt_offset = 0x%08x\n", obj->gtt_offset);
-		    i915_dump_object(m, dev_priv->mm.gtt_mapping, obj);
-		}
-	}
-
-	mutex_unlock(&dev->struct_mutex);
-	return 0;
-}
-
 static int i915_ringbuffer_data(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -669,9 +630,9 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data)
 static const char *ring_str(int ring)
 {
 	switch (ring) {
-	case RING_RENDER: return " render";
-	case RING_BSD: return " bsd";
-	case RING_BLT: return " blt";
+	case RCS: return "render";
+	case VCS: return "bsd";
+	case BCS: return "blt";
 	default: return "";
 	}
 }
@@ -714,7 +675,7 @@ static void print_error_buffers(struct seq_file *m,
 	seq_printf(m, "%s [%d]:\n", name, count);
 
 	while (count--) {
-		seq_printf(m, "  %08x %8u %04x %04x %08x%s%s%s%s%s%s",
+		seq_printf(m, "  %08x %8u %04x %04x %08x%s%s%s%s%s%s%s",
 			   err->gtt_offset,
 			   err->size,
 			   err->read_domains,
@@ -724,6 +685,7 @@ static void print_error_buffers(struct seq_file *m,
 			   tiling_flag(err->tiling),
 			   dirty_flag(err->dirty),
 			   purgeable_flag(err->purgeable),
+			   err->ring != -1 ? " " : "",
 			   ring_str(err->ring),
 			   cache_level_str(err->cache_level));
 
@@ -737,6 +699,32 @@ static void print_error_buffers(struct seq_file *m,
 	}
 }
 
+static void i915_ring_error_state(struct seq_file *m,
+				  struct drm_device *dev,
+				  struct drm_i915_error_state *error,
+				  unsigned ring)
+{
+	seq_printf(m, "%s command stream:\n", ring_str(ring));
+	seq_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
+	seq_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
+	seq_printf(m, "  ACTHD: 0x%08x\n", error->acthd[ring]);
+	seq_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
+	seq_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
+	seq_printf(m, "  INSTDONE: 0x%08x\n", error->instdone[ring]);
+	if (ring == RCS && INTEL_INFO(dev)->gen >= 4) {
+		seq_printf(m, "  INSTDONE1: 0x%08x\n", error->instdone1);
+		seq_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr);
+	}
+	if (INTEL_INFO(dev)->gen >= 4)
+		seq_printf(m, "  INSTPS: 0x%08x\n", error->instps[ring]);
+	seq_printf(m, "  INSTPM: 0x%08x\n", error->instpm[ring]);
+	if (INTEL_INFO(dev)->gen >= 6) {
+		seq_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
+		seq_printf(m, "  FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
+	}
+	seq_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
+}
+
 static int i915_error_state(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -759,36 +747,21 @@ static int i915_error_state(struct seq_file *m, void *unused)
 	seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
 	seq_printf(m, "EIR: 0x%08x\n", error->eir);
 	seq_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
-	if (INTEL_INFO(dev)->gen >= 6) {
-		seq_printf(m, "ERROR: 0x%08x\n", error->error);
-		seq_printf(m, "Blitter command stream:\n");
-		seq_printf(m, "  ACTHD:    0x%08x\n", error->bcs_acthd);
-		seq_printf(m, "  IPEIR:    0x%08x\n", error->bcs_ipeir);
-		seq_printf(m, "  IPEHR:    0x%08x\n", error->bcs_ipehr);
-		seq_printf(m, "  INSTDONE: 0x%08x\n", error->bcs_instdone);
-		seq_printf(m, "  seqno:    0x%08x\n", error->bcs_seqno);
-		seq_printf(m, "Video (BSD) command stream:\n");
-		seq_printf(m, "  ACTHD:    0x%08x\n", error->vcs_acthd);
-		seq_printf(m, "  IPEIR:    0x%08x\n", error->vcs_ipeir);
-		seq_printf(m, "  IPEHR:    0x%08x\n", error->vcs_ipehr);
-		seq_printf(m, "  INSTDONE: 0x%08x\n", error->vcs_instdone);
-		seq_printf(m, "  seqno:    0x%08x\n", error->vcs_seqno);
-	}
-	seq_printf(m, "Render command stream:\n");
-	seq_printf(m, "  ACTHD: 0x%08x\n", error->acthd);
-	seq_printf(m, "  IPEIR: 0x%08x\n", error->ipeir);
-	seq_printf(m, "  IPEHR: 0x%08x\n", error->ipehr);
-	seq_printf(m, "  INSTDONE: 0x%08x\n", error->instdone);
-	if (INTEL_INFO(dev)->gen >= 4) {
-		seq_printf(m, "  INSTDONE1: 0x%08x\n", error->instdone1);
-		seq_printf(m, "  INSTPS: 0x%08x\n", error->instps);
-	}
-	seq_printf(m, "  INSTPM: 0x%08x\n", error->instpm);
-	seq_printf(m, "  seqno: 0x%08x\n", error->seqno);
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++)
 		seq_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
 
+	if (INTEL_INFO(dev)->gen >= 6) {
+		seq_printf(m, "ERROR: 0x%08x\n", error->error);
+		seq_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
+	}
+
+	i915_ring_error_state(m, dev, error, RCS);
+	if (HAS_BLT(dev))
+		i915_ring_error_state(m, dev, error, BCS);
+	if (HAS_BSD(dev))
+		i915_ring_error_state(m, dev, error, VCS);
+
 	if (error->active_bo)
 		print_error_buffers(m, "Active",
 				    error->active_bo,
@@ -1415,9 +1388,58 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 	return 0;
 }
 
+static const char *swizzle_string(unsigned swizzle)
+{
+	switch(swizzle) {
+	case I915_BIT_6_SWIZZLE_NONE:
+		return "none";
+	case I915_BIT_6_SWIZZLE_9:
+		return "bit9";
+	case I915_BIT_6_SWIZZLE_9_10:
+		return "bit9/bit10";
+	case I915_BIT_6_SWIZZLE_9_11:
+		return "bit9/bit11";
+	case I915_BIT_6_SWIZZLE_9_10_11:
+		return "bit9/bit10/bit11";
+	case I915_BIT_6_SWIZZLE_9_17:
+		return "bit9/bit17";
+	case I915_BIT_6_SWIZZLE_9_10_17:
+		return "bit9/bit10/bit17";
+	case I915_BIT_6_SWIZZLE_UNKNOWN:
+		return "unkown";
+	}
+
+	return "bug";
+}
+
+static int i915_swizzle_info(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	mutex_lock(&dev->struct_mutex);
+	seq_printf(m, "bit6 swizzle for X-tiling = %s\n",
+		   swizzle_string(dev_priv->mm.bit_6_swizzle_x));
+	seq_printf(m, "bit6 swizzle for Y-tiling = %s\n",
+		   swizzle_string(dev_priv->mm.bit_6_swizzle_y));
+
+	if (IS_GEN3(dev) || IS_GEN4(dev)) {
+		seq_printf(m, "DDC = 0x%08x\n",
+			   I915_READ(DCC));
+		seq_printf(m, "C0DRB3 = 0x%04x\n",
+			   I915_READ16(C0DRB3));
+		seq_printf(m, "C1DRB3 = 0x%04x\n",
+			   I915_READ16(C1DRB3));
+	}
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
 static int
-i915_wedged_open(struct inode *inode,
-		 struct file *filp)
+i915_debugfs_common_open(struct inode *inode,
+			 struct file *filp)
 {
 	filp->private_data = inode->i_private;
 	return 0;
@@ -1473,20 +1495,12 @@ i915_wedged_write(struct file *filp,
 
 static const struct file_operations i915_wedged_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_wedged_open,
+	.open = i915_debugfs_common_open,
 	.read = i915_wedged_read,
 	.write = i915_wedged_write,
 	.llseek = default_llseek,
 };
 
-static int
-i915_max_freq_open(struct inode *inode,
-		   struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t
 i915_max_freq_read(struct file *filp,
 		   char __user *ubuf,
@@ -1543,20 +1557,12 @@ i915_max_freq_write(struct file *filp,
 
 static const struct file_operations i915_max_freq_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_max_freq_open,
+	.open = i915_debugfs_common_open,
 	.read = i915_max_freq_read,
 	.write = i915_max_freq_write,
 	.llseek = default_llseek,
 };
 
-static int
-i915_cache_sharing_open(struct inode *inode,
-		   struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t
 i915_cache_sharing_read(struct file *filp,
 		   char __user *ubuf,
@@ -1622,7 +1628,7 @@ i915_cache_sharing_write(struct file *filp,
 
 static const struct file_operations i915_cache_sharing_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_cache_sharing_open,
+	.open = i915_debugfs_common_open,
 	.read = i915_cache_sharing_read,
 	.write = i915_cache_sharing_write,
 	.llseek = default_llseek,
@@ -1654,21 +1660,6 @@ drm_add_fake_info_node(struct drm_minor *minor,
 	return 0;
 }
 
-static int i915_wedged_create(struct dentry *root, struct drm_minor *minor)
-{
-	struct drm_device *dev = minor->dev;
-	struct dentry *ent;
-
-	ent = debugfs_create_file("i915_wedged",
-				  S_IRUGO | S_IWUSR,
-				  root, dev,
-				  &i915_wedged_fops);
-	if (IS_ERR(ent))
-		return PTR_ERR(ent);
-
-	return drm_add_fake_info_node(minor, ent, &i915_wedged_fops);
-}
-
 static int i915_forcewake_open(struct inode *inode, struct file *file)
 {
 	struct drm_device *dev = inode->i_private;
@@ -1730,34 +1721,22 @@ static int i915_forcewake_create(struct dentry *root, struct drm_minor *minor)
 	return drm_add_fake_info_node(minor, ent, &i915_forcewake_fops);
 }
 
-static int i915_max_freq_create(struct dentry *root, struct drm_minor *minor)
+static int i915_debugfs_create(struct dentry *root,
+			       struct drm_minor *minor,
+			       const char *name,
+			       const struct file_operations *fops)
 {
 	struct drm_device *dev = minor->dev;
 	struct dentry *ent;
 
-	ent = debugfs_create_file("i915_max_freq",
+	ent = debugfs_create_file(name,
 				  S_IRUGO | S_IWUSR,
 				  root, dev,
-				  &i915_max_freq_fops);
+				  fops);
 	if (IS_ERR(ent))
 		return PTR_ERR(ent);
 
-	return drm_add_fake_info_node(minor, ent, &i915_max_freq_fops);
-}
-
-static int i915_cache_sharing_create(struct dentry *root, struct drm_minor *minor)
-{
-	struct drm_device *dev = minor->dev;
-	struct dentry *ent;
-
-	ent = debugfs_create_file("i915_cache_sharing",
-				  S_IRUGO | S_IWUSR,
-				  root, dev,
-				  &i915_cache_sharing_fops);
-	if (IS_ERR(ent))
-		return PTR_ERR(ent);
-
-	return drm_add_fake_info_node(minor, ent, &i915_cache_sharing_fops);
+	return drm_add_fake_info_node(minor, ent, fops);
 }
 
 static struct drm_info_list i915_debugfs_list[] = {
@@ -1783,7 +1762,6 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_bsd_ringbuffer_info", i915_ringbuffer_info, 0, (void *)VCS},
 	{"i915_blt_ringbuffer_data", i915_ringbuffer_data, 0, (void *)BCS},
 	{"i915_blt_ringbuffer_info", i915_ringbuffer_info, 0, (void *)BCS},
-	{"i915_batchbuffers", i915_batchbuffer_info, 0},
 	{"i915_error_state", i915_error_state, 0},
 	{"i915_rstdby_delays", i915_rstdby_delays, 0},
 	{"i915_cur_delayinfo", i915_cur_delayinfo, 0},
@@ -1799,6 +1777,7 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_framebuffer", i915_gem_framebuffer_info, 0},
 	{"i915_context_status", i915_context_status, 0},
 	{"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0},
+	{"i915_swizzle_info", i915_swizzle_info, 0},
 };
 #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
 
@@ -1806,17 +1785,25 @@ int i915_debugfs_init(struct drm_minor *minor)
 {
 	int ret;
 
-	ret = i915_wedged_create(minor->debugfs_root, minor);
+	ret = i915_debugfs_create(minor->debugfs_root, minor,
+				  "i915_wedged",
+				  &i915_wedged_fops);
 	if (ret)
 		return ret;
 
 	ret = i915_forcewake_create(minor->debugfs_root, minor);
 	if (ret)
 		return ret;
-	ret = i915_max_freq_create(minor->debugfs_root, minor);
+
+	ret = i915_debugfs_create(minor->debugfs_root, minor,
+				  "i915_max_freq",
+				  &i915_max_freq_fops);
 	if (ret)
 		return ret;
-	ret = i915_cache_sharing_create(minor->debugfs_root, minor);
+
+	ret = i915_debugfs_create(minor->debugfs_root, minor,
+				  "i915_cache_sharing",
+				  &i915_cache_sharing_fops);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 448848cbc1db..8919dcc07ed8 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -2132,7 +2132,7 @@ int i915_driver_unload(struct drm_device *dev)
 		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
 
 	mutex_lock(&dev->struct_mutex);
-	ret = i915_gpu_idle(dev);
+	ret = i915_gpu_idle(dev, true);
 	if (ret)
 		DRM_ERROR("failed to idle hardware: %d\n", ret);
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 32737a37edd0..68a5338ea867 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -135,6 +135,7 @@ struct drm_i915_fence_reg {
 	struct list_head lru_list;
 	struct drm_i915_gem_object *obj;
 	uint32_t setup_seqno;
+	int pin_count;
 };
 
 struct sdvo_device_mapping {
@@ -152,26 +153,21 @@ struct drm_i915_error_state {
 	u32 eir;
 	u32 pgtbl_er;
 	u32 pipestat[I915_MAX_PIPES];
-	u32 ipeir;
-	u32 ipehr;
-	u32 instdone;
-	u32 acthd;
+	u32 tail[I915_NUM_RINGS];
+	u32 head[I915_NUM_RINGS];
+	u32 ipeir[I915_NUM_RINGS];
+	u32 ipehr[I915_NUM_RINGS];
+	u32 instdone[I915_NUM_RINGS];
+	u32 acthd[I915_NUM_RINGS];
 	u32 error; /* gen6+ */
-	u32 bcs_acthd; /* gen6+ blt engine */
-	u32 bcs_ipehr;
-	u32 bcs_ipeir;
-	u32 bcs_instdone;
-	u32 bcs_seqno;
-	u32 vcs_acthd; /* gen6+ bsd engine */
-	u32 vcs_ipehr;
-	u32 vcs_ipeir;
-	u32 vcs_instdone;
-	u32 vcs_seqno;
-	u32 instpm;
-	u32 instps;
+	u32 instpm[I915_NUM_RINGS];
+	u32 instps[I915_NUM_RINGS];
 	u32 instdone1;
-	u32 seqno;
+	u32 seqno[I915_NUM_RINGS];
 	u64 bbaddr;
+	u32 fault_reg[I915_NUM_RINGS];
+	u32 done_reg;
+	u32 faddr[I915_NUM_RINGS];
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
 	struct drm_i915_error_object {
@@ -1170,6 +1166,24 @@ int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj,
 					   struct intel_ring_buffer *pipelined);
 int __must_check i915_gem_object_put_fence(struct drm_i915_gem_object *obj);
 
+static inline void
+i915_gem_object_pin_fence(struct drm_i915_gem_object *obj)
+{
+	if (obj->fence_reg != I915_FENCE_REG_NONE) {
+		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		dev_priv->fence_regs[obj->fence_reg].pin_count++;
+	}
+}
+
+static inline void
+i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
+{
+	if (obj->fence_reg != I915_FENCE_REG_NONE) {
+		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		dev_priv->fence_regs[obj->fence_reg].pin_count--;
+	}
+}
+
 void i915_gem_retire_requests(struct drm_device *dev);
 void i915_gem_reset(struct drm_device *dev);
 void i915_gem_clflush_object(struct drm_i915_gem_object *obj);
@@ -1183,13 +1197,14 @@ void i915_gem_do_init(struct drm_device *dev,
 		      unsigned long start,
 		      unsigned long mappable_end,
 		      unsigned long end);
-int __must_check i915_gpu_idle(struct drm_device *dev);
+int __must_check i915_gpu_idle(struct drm_device *dev, bool do_retire);
 int __must_check i915_gem_idle(struct drm_device *dev);
 int __must_check i915_add_request(struct intel_ring_buffer *ring,
 				  struct drm_file *file,
 				  struct drm_i915_gem_request *request);
 int __must_check i915_wait_request(struct intel_ring_buffer *ring,
-				   uint32_t seqno);
+				   uint32_t seqno,
+				   bool do_retire);
 int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 int __must_check
 i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index eb98a7f55cfe..51a2b0c2a30d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -58,6 +58,7 @@ static void i915_gem_free_object_tail(struct drm_i915_gem_object *obj);
 
 static int i915_gem_inactive_shrink(struct shrinker *shrinker,
 				    struct shrink_control *sc);
+static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
 
 /* some bookkeeping */
 static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
@@ -258,73 +259,6 @@ static int i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 		obj->tiling_mode != I915_TILING_NONE;
 }
 
-static inline void
-slow_shmem_copy(struct page *dst_page,
-		int dst_offset,
-		struct page *src_page,
-		int src_offset,
-		int length)
-{
-	char *dst_vaddr, *src_vaddr;
-
-	dst_vaddr = kmap(dst_page);
-	src_vaddr = kmap(src_page);
-
-	memcpy(dst_vaddr + dst_offset, src_vaddr + src_offset, length);
-
-	kunmap(src_page);
-	kunmap(dst_page);
-}
-
-static inline void
-slow_shmem_bit17_copy(struct page *gpu_page,
-		      int gpu_offset,
-		      struct page *cpu_page,
-		      int cpu_offset,
-		      int length,
-		      int is_read)
-{
-	char *gpu_vaddr, *cpu_vaddr;
-
-	/* Use the unswizzled path if this page isn't affected. */
-	if ((page_to_phys(gpu_page) & (1 << 17)) == 0) {
-		if (is_read)
-			return slow_shmem_copy(cpu_page, cpu_offset,
-					       gpu_page, gpu_offset, length);
-		else
-			return slow_shmem_copy(gpu_page, gpu_offset,
-					       cpu_page, cpu_offset, length);
-	}
-
-	gpu_vaddr = kmap(gpu_page);
-	cpu_vaddr = kmap(cpu_page);
-
-	/* Copy the data, XORing A6 with A17 (1). The user already knows he's
-	 * XORing with the other bits (A9 for Y, A9 and A10 for X)
-	 */
-	while (length > 0) {
-		int cacheline_end = ALIGN(gpu_offset + 1, 64);
-		int this_length = min(cacheline_end - gpu_offset, length);
-		int swizzled_gpu_offset = gpu_offset ^ 64;
-
-		if (is_read) {
-			memcpy(cpu_vaddr + cpu_offset,
-			       gpu_vaddr + swizzled_gpu_offset,
-			       this_length);
-		} else {
-			memcpy(gpu_vaddr + swizzled_gpu_offset,
-			       cpu_vaddr + cpu_offset,
-			       this_length);
-		}
-		cpu_offset += this_length;
-		gpu_offset += this_length;
-		length -= this_length;
-	}
-
-	kunmap(cpu_page);
-	kunmap(gpu_page);
-}
-
 /**
  * This is the fast shmem pread path, which attempts to copy_from_user directly
  * from the backing pages of the object to the user's address space.  On a
@@ -385,6 +319,58 @@ i915_gem_shmem_pread_fast(struct drm_device *dev,
 	return 0;
 }
 
+static inline int
+__copy_to_user_swizzled(char __user *cpu_vaddr,
+			const char *gpu_vaddr, int gpu_offset,
+			int length)
+{
+	int ret, cpu_offset = 0;
+
+	while (length > 0) {
+		int cacheline_end = ALIGN(gpu_offset + 1, 64);
+		int this_length = min(cacheline_end - gpu_offset, length);
+		int swizzled_gpu_offset = gpu_offset ^ 64;
+
+		ret = __copy_to_user(cpu_vaddr + cpu_offset,
+				     gpu_vaddr + swizzled_gpu_offset,
+				     this_length);
+		if (ret)
+			return ret + length;
+
+		cpu_offset += this_length;
+		gpu_offset += this_length;
+		length -= this_length;
+	}
+
+	return 0;
+}
+
+static inline int
+__copy_from_user_swizzled(char __user *gpu_vaddr, int gpu_offset,
+			  const char *cpu_vaddr,
+			  int length)
+{
+	int ret, cpu_offset = 0;
+
+	while (length > 0) {
+		int cacheline_end = ALIGN(gpu_offset + 1, 64);
+		int this_length = min(cacheline_end - gpu_offset, length);
+		int swizzled_gpu_offset = gpu_offset ^ 64;
+
+		ret = __copy_from_user(gpu_vaddr + swizzled_gpu_offset,
+				       cpu_vaddr + cpu_offset,
+				       this_length);
+		if (ret)
+			return ret + length;
+
+		cpu_offset += this_length;
+		gpu_offset += this_length;
+		length -= this_length;
+	}
+
+	return 0;
+}
+
 /**
  * This is the fallback shmem pread path, which allocates temporary storage
  * in kernel space to copy_to_user into outside of the struct_mutex, so we
@@ -398,72 +384,34 @@ i915_gem_shmem_pread_slow(struct drm_device *dev,
 			  struct drm_file *file)
 {
 	struct address_space *mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping;
-	struct mm_struct *mm = current->mm;
-	struct page **user_pages;
+	char __user *user_data;
 	ssize_t remain;
-	loff_t offset, pinned_pages, i;
-	loff_t first_data_page, last_data_page, num_pages;
-	int shmem_page_offset;
-	int data_page_index, data_page_offset;
-	int page_length;
-	int ret;
-	uint64_t data_ptr = args->data_ptr;
-	int do_bit17_swizzling;
+	loff_t offset;
+	int shmem_page_offset, page_length, ret;
+	int obj_do_bit17_swizzling, page_do_bit17_swizzling;
 
+	user_data = (char __user *) (uintptr_t) args->data_ptr;
 	remain = args->size;
 
-	/* Pin the user pages containing the data.  We can't fault while
-	 * holding the struct mutex, yet we want to hold it while
-	 * dereferencing the user data.
-	 */
-	first_data_page = data_ptr / PAGE_SIZE;
-	last_data_page = (data_ptr + args->size - 1) / PAGE_SIZE;
-	num_pages = last_data_page - first_data_page + 1;
-
-	user_pages = drm_malloc_ab(num_pages, sizeof(struct page *));
-	if (user_pages == NULL)
-		return -ENOMEM;
-
-	mutex_unlock(&dev->struct_mutex);
-	down_read(&mm->mmap_sem);
-	pinned_pages = get_user_pages(current, mm, (uintptr_t)args->data_ptr,
-				      num_pages, 1, 0, user_pages, NULL);
-	up_read(&mm->mmap_sem);
-	mutex_lock(&dev->struct_mutex);
-	if (pinned_pages < num_pages) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	ret = i915_gem_object_set_cpu_read_domain_range(obj,
-							args->offset,
-							args->size);
-	if (ret)
-		goto out;
-
-	do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
+	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
 
 	offset = args->offset;
 
+	mutex_unlock(&dev->struct_mutex);
+
 	while (remain > 0) {
 		struct page *page;
+		char *vaddr;
 
 		/* Operation in this page
 		 *
 		 * shmem_page_offset = offset within page in shmem file
-		 * data_page_index = page number in get_user_pages return
-		 * data_page_offset = offset with data_page_index page.
 		 * page_length = bytes to copy for this page
 		 */
 		shmem_page_offset = offset_in_page(offset);
-		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = offset_in_page(data_ptr);
-
 		page_length = remain;
 		if ((shmem_page_offset + page_length) > PAGE_SIZE)
 			page_length = PAGE_SIZE - shmem_page_offset;
-		if ((data_page_offset + page_length) > PAGE_SIZE)
-			page_length = PAGE_SIZE - data_page_offset;
 
 		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
 		if (IS_ERR(page)) {
@@ -471,36 +419,38 @@ i915_gem_shmem_pread_slow(struct drm_device *dev,
 			goto out;
 		}
 
-		if (do_bit17_swizzling) {
-			slow_shmem_bit17_copy(page,
-					      shmem_page_offset,
-					      user_pages[data_page_index],
-					      data_page_offset,
-					      page_length,
-					      1);
-		} else {
-			slow_shmem_copy(user_pages[data_page_index],
-					data_page_offset,
-					page,
-					shmem_page_offset,
-					page_length);
-		}
+		page_do_bit17_swizzling = obj_do_bit17_swizzling &&
+			(page_to_phys(page) & (1 << 17)) != 0;
+
+		vaddr = kmap(page);
+		if (page_do_bit17_swizzling)
+			ret = __copy_to_user_swizzled(user_data,
+						      vaddr, shmem_page_offset,
+						      page_length);
+		else
+			ret = __copy_to_user(user_data,
+					     vaddr + shmem_page_offset,
+					     page_length);
+		kunmap(page);
 
 		mark_page_accessed(page);
 		page_cache_release(page);
 
+		if (ret) {
+			ret = -EFAULT;
+			goto out;
+		}
+
 		remain -= page_length;
-		data_ptr += page_length;
+		user_data += page_length;
 		offset += page_length;
 	}
 
 out:
-	for (i = 0; i < pinned_pages; i++) {
-		SetPageDirty(user_pages[i]);
-		mark_page_accessed(user_pages[i]);
-		page_cache_release(user_pages[i]);
-	}
-	drm_free_large(user_pages);
+	mutex_lock(&dev->struct_mutex);
+	/* Fixup: Kill any reinstated backing storage pages */
+	if (obj->madv == __I915_MADV_PURGED)
+		i915_gem_object_truncate(obj);
 
 	return ret;
 }
@@ -841,71 +791,36 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev,
 			   struct drm_file *file)
 {
 	struct address_space *mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping;
-	struct mm_struct *mm = current->mm;
-	struct page **user_pages;
 	ssize_t remain;
-	loff_t offset, pinned_pages, i;
-	loff_t first_data_page, last_data_page, num_pages;
-	int shmem_page_offset;
-	int data_page_index,  data_page_offset;
-	int page_length;
-	int ret;
-	uint64_t data_ptr = args->data_ptr;
-	int do_bit17_swizzling;
+	loff_t offset;
+	char __user *user_data;
+	int shmem_page_offset, page_length, ret;
+	int obj_do_bit17_swizzling, page_do_bit17_swizzling;
 
+	user_data = (char __user *) (uintptr_t) args->data_ptr;
 	remain = args->size;
 
-	/* Pin the user pages containing the data.  We can't fault while
-	 * holding the struct mutex, and all of the pwrite implementations
-	 * want to hold it while dereferencing the user data.
-	 */
-	first_data_page = data_ptr / PAGE_SIZE;
-	last_data_page = (data_ptr + args->size - 1) / PAGE_SIZE;
-	num_pages = last_data_page - first_data_page + 1;
-
-	user_pages = drm_malloc_ab(num_pages, sizeof(struct page *));
-	if (user_pages == NULL)
-		return -ENOMEM;
-
-	mutex_unlock(&dev->struct_mutex);
-	down_read(&mm->mmap_sem);
-	pinned_pages = get_user_pages(current, mm, (uintptr_t)args->data_ptr,
-				      num_pages, 0, 0, user_pages, NULL);
-	up_read(&mm->mmap_sem);
-	mutex_lock(&dev->struct_mutex);
-	if (pinned_pages < num_pages) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
-	if (ret)
-		goto out;
-
-	do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
+	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
 
 	offset = args->offset;
 	obj->dirty = 1;
 
+	mutex_unlock(&dev->struct_mutex);
+
 	while (remain > 0) {
 		struct page *page;
+		char *vaddr;
 
 		/* Operation in this page
 		 *
 		 * shmem_page_offset = offset within page in shmem file
-		 * data_page_index = page number in get_user_pages return
-		 * data_page_offset = offset with data_page_index page.
 		 * page_length = bytes to copy for this page
 		 */
 		shmem_page_offset = offset_in_page(offset);
-		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((shmem_page_offset + page_length) > PAGE_SIZE)
 			page_length = PAGE_SIZE - shmem_page_offset;
-		if ((data_page_offset + page_length) > PAGE_SIZE)
-			page_length = PAGE_SIZE - data_page_offset;
 
 		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
 		if (IS_ERR(page)) {
@@ -913,34 +828,45 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev,
 			goto out;
 		}
 
-		if (do_bit17_swizzling) {
-			slow_shmem_bit17_copy(page,
-					      shmem_page_offset,
-					      user_pages[data_page_index],
-					      data_page_offset,
-					      page_length,
-					      0);
-		} else {
-			slow_shmem_copy(page,
-					shmem_page_offset,
-					user_pages[data_page_index],
-					data_page_offset,
-					page_length);
-		}
+		page_do_bit17_swizzling = obj_do_bit17_swizzling &&
+			(page_to_phys(page) & (1 << 17)) != 0;
+
+		vaddr = kmap(page);
+		if (page_do_bit17_swizzling)
+			ret = __copy_from_user_swizzled(vaddr, shmem_page_offset,
+							user_data,
+							page_length);
+		else
+			ret = __copy_from_user(vaddr + shmem_page_offset,
+					       user_data,
+					       page_length);
+		kunmap(page);
 
 		set_page_dirty(page);
 		mark_page_accessed(page);
 		page_cache_release(page);
 
+		if (ret) {
+			ret = -EFAULT;
+			goto out;
+		}
+
 		remain -= page_length;
-		data_ptr += page_length;
+		user_data += page_length;
 		offset += page_length;
 	}
 
 out:
-	for (i = 0; i < pinned_pages; i++)
-		page_cache_release(user_pages[i]);
-	drm_free_large(user_pages);
+	mutex_lock(&dev->struct_mutex);
+	/* Fixup: Kill any reinstated backing storage pages */
+	if (obj->madv == __I915_MADV_PURGED)
+		i915_gem_object_truncate(obj);
+	/* and flush dirty cachelines in case the object isn't in the cpu write
+	 * domain anymore. */
+	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+		i915_gem_clflush_object(obj);
+		intel_gtt_chipset_flush();
+	}
 
 	return ret;
 }
@@ -996,10 +922,13 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 	 * pread/pwrite currently are reading and writing from the CPU
 	 * perspective, requiring manual detiling by the client.
 	 */
-	if (obj->phys_obj)
+	if (obj->phys_obj) {
 		ret = i915_gem_phys_pwrite(dev, obj, args, file);
-	else if (obj->gtt_space &&
-		 obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+		goto out;
+	}
+
+	if (obj->gtt_space &&
+	    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
 		ret = i915_gem_object_pin(obj, 0, true);
 		if (ret)
 			goto out;
@@ -1018,18 +947,24 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 
 out_unpin:
 		i915_gem_object_unpin(obj);
-	} else {
-		ret = i915_gem_object_set_to_cpu_domain(obj, 1);
-		if (ret)
-			goto out;
 
-		ret = -EFAULT;
-		if (!i915_gem_object_needs_bit17_swizzle(obj))
-			ret = i915_gem_shmem_pwrite_fast(dev, obj, args, file);
-		if (ret == -EFAULT)
-			ret = i915_gem_shmem_pwrite_slow(dev, obj, args, file);
+		if (ret != -EFAULT)
+			goto out;
+		/* Fall through to the shmfs paths because the gtt paths might
+		 * fail with non-page-backed user pointers (e.g. gtt mappings
+		 * when moving data between textures). */
 	}
 
+	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+	if (ret)
+		goto out;
+
+	ret = -EFAULT;
+	if (!i915_gem_object_needs_bit17_swizzle(obj))
+		ret = i915_gem_shmem_pwrite_fast(dev, obj, args, file);
+	if (ret == -EFAULT)
+		ret = i915_gem_shmem_pwrite_slow(dev, obj, args, file);
+
 out:
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -1141,7 +1076,6 @@ int
 i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 		    struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_mmap *args = data;
 	struct drm_gem_object *obj;
 	unsigned long addr;
@@ -1153,11 +1087,6 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 	if (obj == NULL)
 		return -ENOENT;
 
-	if (obj->size > dev_priv->mm.gtt_mappable_end) {
-		drm_gem_object_unreference_unlocked(obj);
-		return -E2BIG;
-	}
-
 	down_write(&current->mm->mmap_sem);
 	addr = do_mmap(obj->filp, 0, args->size,
 		       PROT_READ | PROT_WRITE, MAP_SHARED,
@@ -1943,7 +1872,8 @@ i915_gem_retire_work_handler(struct work_struct *work)
  */
 int
 i915_wait_request(struct intel_ring_buffer *ring,
-		  uint32_t seqno)
+		  uint32_t seqno,
+		  bool do_retire)
 {
 	drm_i915_private_t *dev_priv = ring->dev->dev_private;
 	u32 ier;
@@ -2027,7 +1957,7 @@ i915_wait_request(struct intel_ring_buffer *ring,
 	 * buffer to have made it to the inactive list, and we would need
 	 * a separate wait queue to handle that.
 	 */
-	if (ret == 0)
+	if (ret == 0 && do_retire)
 		i915_gem_retire_requests_ring(ring);
 
 	return ret;
@@ -2051,7 +1981,8 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj)
 	 * it.
 	 */
 	if (obj->active) {
-		ret = i915_wait_request(obj->ring, obj->last_rendering_seqno);
+		ret = i915_wait_request(obj->ring, obj->last_rendering_seqno,
+					true);
 		if (ret)
 			return ret;
 	}
@@ -2172,7 +2103,7 @@ i915_gem_flush_ring(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-static int i915_ring_idle(struct intel_ring_buffer *ring)
+static int i915_ring_idle(struct intel_ring_buffer *ring, bool do_retire)
 {
 	int ret;
 
@@ -2186,18 +2117,18 @@ static int i915_ring_idle(struct intel_ring_buffer *ring)
 			return ret;
 	}
 
-	return i915_wait_request(ring, i915_gem_next_request_seqno(ring));
+	return i915_wait_request(ring, i915_gem_next_request_seqno(ring),
+				 do_retire);
 }
 
-int
-i915_gpu_idle(struct drm_device *dev)
+int i915_gpu_idle(struct drm_device *dev, bool do_retire)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	int ret, i;
 
 	/* Flush everything onto the inactive list. */
 	for (i = 0; i < I915_NUM_RINGS; i++) {
-		ret = i915_ring_idle(&dev_priv->ring[i]);
+		ret = i915_ring_idle(&dev_priv->ring[i], do_retire);
 		if (ret)
 			return ret;
 	}
@@ -2400,7 +2331,8 @@ i915_gem_object_flush_fence(struct drm_i915_gem_object *obj,
 		if (!ring_passed_seqno(obj->last_fenced_ring,
 				       obj->last_fenced_seqno)) {
 			ret = i915_wait_request(obj->last_fenced_ring,
-						obj->last_fenced_seqno);
+						obj->last_fenced_seqno,
+						true);
 			if (ret)
 				return ret;
 		}
@@ -2432,6 +2364,8 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj)
 
 	if (obj->fence_reg != I915_FENCE_REG_NONE) {
 		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+
+		WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count);
 		i915_gem_clear_fence_reg(obj->base.dev,
 					 &dev_priv->fence_regs[obj->fence_reg]);
 
@@ -2456,7 +2390,7 @@ i915_find_fence_reg(struct drm_device *dev,
 		if (!reg->obj)
 			return reg;
 
-		if (!reg->obj->pin_count)
+		if (!reg->pin_count)
 			avail = reg;
 	}
 
@@ -2466,7 +2400,7 @@ i915_find_fence_reg(struct drm_device *dev,
 	/* None available, try to steal one or wait for a user to finish */
 	avail = first = NULL;
 	list_for_each_entry(reg, &dev_priv->mm.fence_list, lru_list) {
-		if (reg->obj->pin_count)
+		if (reg->pin_count)
 			continue;
 
 		if (first == NULL)
@@ -2541,7 +2475,8 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj,
 				if (!ring_passed_seqno(obj->last_fenced_ring,
 						       reg->setup_seqno)) {
 					ret = i915_wait_request(obj->last_fenced_ring,
-								reg->setup_seqno);
+								reg->setup_seqno,
+								true);
 					if (ret)
 						return ret;
 				}
@@ -2560,7 +2495,7 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj,
 
 	reg = i915_find_fence_reg(dev, pipelined);
 	if (reg == NULL)
-		return -ENOSPC;
+		return -EDEADLK;
 
 	ret = i915_gem_object_flush_fence(obj, pipelined);
 	if (ret)
@@ -2660,6 +2595,7 @@ i915_gem_clear_fence_reg(struct drm_device *dev,
 	list_del_init(&reg->lru_list);
 	reg->obj = NULL;
 	reg->setup_seqno = 0;
+	reg->pin_count = 0;
 }
 
 /**
@@ -3710,7 +3646,7 @@ i915_gem_idle(struct drm_device *dev)
 		return 0;
 	}
 
-	ret = i915_gpu_idle(dev);
+	ret = i915_gpu_idle(dev, true);
 	if (ret) {
 		mutex_unlock(&dev->struct_mutex);
 		return ret;
@@ -4201,7 +4137,7 @@ rescan:
 		 * This has a dramatic impact to reduce the number of
 		 * OOM-killer events whilst running the GPU aggressively.
 		 */
-		if (i915_gpu_idle(dev) == 0)
+		if (i915_gpu_idle(dev, true) == 0)
 			goto rescan;
 	}
 	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 ead5d00f91b0..097119caa36a 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -195,7 +195,7 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
 	trace_i915_gem_evict_everything(dev, purgeable_only);
 
 	/* Flush everything (on to the inactive lists) and evict */
-	ret = i915_gpu_idle(dev);
+	ret = i915_gpu_idle(dev, true);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 65e1f0043f9d..c719df19b3de 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -203,9 +203,9 @@ i915_gem_object_set_to_gpu_domain(struct drm_i915_gem_object *obj,
 	cd->invalidate_domains |= invalidate_domains;
 	cd->flush_domains |= flush_domains;
 	if (flush_domains & I915_GEM_GPU_DOMAINS)
-		cd->flush_rings |= obj->ring->id;
+		cd->flush_rings |= intel_ring_flag(obj->ring);
 	if (invalidate_domains & I915_GEM_GPU_DOMAINS)
-		cd->flush_rings |= ring->id;
+		cd->flush_rings |= intel_ring_flag(ring);
 }
 
 struct eb_objects {
@@ -303,8 +303,9 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			  reloc->write_domain);
 		return ret;
 	}
-	if (unlikely((reloc->write_domain | reloc->read_domains) & I915_GEM_DOMAIN_CPU)) {
-		DRM_ERROR("reloc with read/write CPU domains: "
+	if (unlikely((reloc->write_domain | reloc->read_domains)
+		     & ~I915_GEM_GPU_DOMAINS)) {
+		DRM_ERROR("reloc with read/write non-GPU domains: "
 			  "obj %p target %d offset %d "
 			  "read %08x write %08x",
 			  obj, reloc->target_handle,
@@ -461,6 +462,54 @@ i915_gem_execbuffer_relocate(struct drm_device *dev,
 	return ret;
 }
 
+#define  __EXEC_OBJECT_HAS_FENCE (1<<31)
+
+static int
+pin_and_fence_object(struct drm_i915_gem_object *obj,
+		     struct intel_ring_buffer *ring)
+{
+	struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+	bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
+	bool need_fence, need_mappable;
+	int ret;
+
+	need_fence =
+		has_fenced_gpu_access &&
+		entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
+		obj->tiling_mode != I915_TILING_NONE;
+	need_mappable =
+		entry->relocation_count ? true : need_fence;
+
+	ret = i915_gem_object_pin(obj, entry->alignment, need_mappable);
+	if (ret)
+		return ret;
+
+	if (has_fenced_gpu_access) {
+		if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
+			if (obj->tiling_mode) {
+				ret = i915_gem_object_get_fence(obj, ring);
+				if (ret)
+					goto err_unpin;
+
+				entry->flags |= __EXEC_OBJECT_HAS_FENCE;
+				i915_gem_object_pin_fence(obj);
+			} else {
+				ret = i915_gem_object_put_fence(obj);
+				if (ret)
+					goto err_unpin;
+			}
+		}
+		obj->pending_fenced_gpu_access = need_fence;
+	}
+
+	entry->offset = obj->gtt_offset;
+	return 0;
+
+err_unpin:
+	i915_gem_object_unpin(obj);
+	return ret;
+}
+
 static int
 i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			    struct drm_file *file,
@@ -518,6 +567,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 		list_for_each_entry(obj, objects, exec_list) {
 			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 			bool need_fence, need_mappable;
+
 			if (!obj->gtt_space)
 				continue;
 
@@ -532,58 +582,47 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			    (need_mappable && !obj->map_and_fenceable))
 				ret = i915_gem_object_unbind(obj);
 			else
-				ret = i915_gem_object_pin(obj,
-							  entry->alignment,
-							  need_mappable);
+				ret = pin_and_fence_object(obj, ring);
 			if (ret)
 				goto err;
-
-			entry++;
 		}
 
 		/* Bind fresh objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
-			bool need_fence;
+			if (obj->gtt_space)
+				continue;
 
-			need_fence =
-				has_fenced_gpu_access &&
-				entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
-				obj->tiling_mode != I915_TILING_NONE;
+			ret = pin_and_fence_object(obj, ring);
+			if (ret) {
+				int ret_ignore;
 
-			if (!obj->gtt_space) {
-				bool need_mappable =
-					entry->relocation_count ? true : need_fence;
-
-				ret = i915_gem_object_pin(obj,
-							  entry->alignment,
-							  need_mappable);
-				if (ret)
-					break;
+				/* This can potentially raise a harmless
+				 * -EINVAL if we failed to bind in the above
+				 * call. It cannot raise -EINTR since we know
+				 * that the bo is freshly bound and so will
+				 * not need to be flushed or waited upon.
+				 */
+				ret_ignore = i915_gem_object_unbind(obj);
+				(void)ret_ignore;
+				WARN_ON(obj->gtt_space);
+				break;
 			}
-
-			if (has_fenced_gpu_access) {
-				if (need_fence) {
-					ret = i915_gem_object_get_fence(obj, ring);
-					if (ret)
-						break;
-				} else if (entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
-					   obj->tiling_mode == I915_TILING_NONE) {
-					/* XXX pipelined! */
-					ret = i915_gem_object_put_fence(obj);
-					if (ret)
-						break;
-				}
-				obj->pending_fenced_gpu_access = need_fence;
-			}
-
-			entry->offset = obj->gtt_offset;
 		}
 
 		/* Decrement pin count for bound objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			if (obj->gtt_space)
-				i915_gem_object_unpin(obj);
+			struct drm_i915_gem_exec_object2 *entry;
+
+			if (!obj->gtt_space)
+				continue;
+
+			entry = obj->exec_entry;
+			if (entry->flags & __EXEC_OBJECT_HAS_FENCE) {
+				i915_gem_object_unpin_fence(obj);
+				entry->flags &= ~__EXEC_OBJECT_HAS_FENCE;
+			}
+
+			i915_gem_object_unpin(obj);
 		}
 
 		if (ret != -ENOSPC || retry > 1)
@@ -600,16 +639,19 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 	} while (1);
 
 err:
-	obj = list_entry(obj->exec_list.prev,
-			 struct drm_i915_gem_object,
-			 exec_list);
-	while (objects != &obj->exec_list) {
-		if (obj->gtt_space)
-			i915_gem_object_unpin(obj);
+	list_for_each_entry_continue_reverse(obj, objects, exec_list) {
+		struct drm_i915_gem_exec_object2 *entry;
 
-		obj = list_entry(obj->exec_list.prev,
-				 struct drm_i915_gem_object,
-				 exec_list);
+		if (!obj->gtt_space)
+			continue;
+
+		entry = obj->exec_entry;
+		if (entry->flags & __EXEC_OBJECT_HAS_FENCE) {
+			i915_gem_object_unpin_fence(obj);
+			entry->flags &= ~__EXEC_OBJECT_HAS_FENCE;
+		}
+
+		i915_gem_object_unpin(obj);
 	}
 
 	return ret;
@@ -1186,7 +1228,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			 * so every billion or so execbuffers, we need to stall
 			 * the GPU in order to reset the counters.
 			 */
-			ret = i915_gpu_idle(dev);
+			ret = i915_gpu_idle(dev, true);
 			if (ret)
 				goto err;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 6042c5e6d278..11bddd5a5a6a 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -55,7 +55,7 @@ static bool do_idling(struct drm_i915_private *dev_priv)
 
 	if (unlikely(dev_priv->mm.gtt->do_idle_maps)) {
 		dev_priv->mm.interruptible = false;
-		if (i915_gpu_idle(dev_priv->dev)) {
+		if (i915_gpu_idle(dev_priv->dev, false)) {
 			DRM_ERROR("Couldn't idle GPU\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 31d334d9d9da..861223bf3944 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -107,10 +107,10 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 		 */
 		swizzle_x = I915_BIT_6_SWIZZLE_NONE;
 		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
-	} else if (IS_MOBILE(dev)) {
+	} else if (IS_MOBILE(dev) || (IS_GEN3(dev) && !IS_G33(dev))) {
 		uint32_t dcc;
 
-		/* On mobile 9xx chipsets, channel interleave by the CPU is
+		/* On 9xx chipsets, channel interleave by the CPU is
 		 * determined by DCC.  For single-channel, neither the CPU
 		 * nor the GPU do swizzling.  For dual channel interleaved,
 		 * the GPU's interleave is bit 9 and 10 for X tiled, and bit
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5bd4361ea84d..6442ff269642 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -720,7 +720,6 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 	reloc_offset = src->gtt_offset;
 	for (page = 0; page < page_count; page++) {
 		unsigned long flags;
-		void __iomem *s;
 		void *d;
 
 		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
@@ -728,10 +727,29 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 			goto unwind;
 
 		local_irq_save(flags);
-		s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping,
-					     reloc_offset);
-		memcpy_fromio(d, s, PAGE_SIZE);
-		io_mapping_unmap_atomic(s);
+		if (reloc_offset < dev_priv->mm.gtt_mappable_end) {
+			void __iomem *s;
+
+			/* Simply ignore tiling or any overlapping fence.
+			 * It's part of the error state, and this hopefully
+			 * captures what the GPU read.
+			 */
+
+			s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping,
+						     reloc_offset);
+			memcpy_fromio(d, s, PAGE_SIZE);
+			io_mapping_unmap_atomic(s);
+		} else {
+			void *s;
+
+			drm_clflush_pages(&src->pages[page], 1);
+
+			s = kmap_atomic(src->pages[page]);
+			memcpy(d, s, PAGE_SIZE);
+			kunmap_atomic(s);
+
+			drm_clflush_pages(&src->pages[page], 1);
+		}
 		local_irq_restore(flags);
 
 		dst->pages[page] = d;
@@ -804,7 +822,7 @@ static u32 capture_bo_list(struct drm_i915_error_buffer *err,
 		err->tiling = obj->tiling_mode;
 		err->dirty = obj->dirty;
 		err->purgeable = obj->madv != I915_MADV_WILLNEED;
-		err->ring = obj->ring ? obj->ring->id : 0;
+		err->ring = obj->ring ? obj->ring->id : -1;
 		err->cache_level = obj->cache_level;
 
 		if (++i == count)
@@ -876,6 +894,39 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 	return NULL;
 }
 
+static void i915_record_ring_state(struct drm_device *dev,
+				   struct drm_i915_error_state *error,
+				   struct intel_ring_buffer *ring)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (INTEL_INFO(dev)->gen >= 6) {
+		error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base));
+		error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring));
+	}
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base));
+		error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base));
+		error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base));
+		error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base));
+		if (ring->id == RCS) {
+			error->instdone1 = I915_READ(INSTDONE1);
+			error->bbaddr = I915_READ64(BB_ADDR);
+		}
+	} else {
+		error->ipeir[ring->id] = I915_READ(IPEIR);
+		error->ipehr[ring->id] = I915_READ(IPEHR);
+		error->instdone[ring->id] = I915_READ(INSTDONE);
+	}
+
+	error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base));
+	error->seqno[ring->id] = ring->get_seqno(ring);
+	error->acthd[ring->id] = intel_ring_get_active_head(ring);
+	error->head[ring->id] = I915_READ_HEAD(ring);
+	error->tail[ring->id] = I915_READ_TAIL(ring);
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -900,7 +951,7 @@ static void i915_capture_error_state(struct drm_device *dev)
 		return;
 
 	/* Account for pipe specific data like PIPE*STAT */
-	error = kmalloc(sizeof(*error), GFP_ATOMIC);
+	error = kzalloc(sizeof(*error), GFP_ATOMIC);
 	if (!error) {
 		DRM_DEBUG_DRIVER("out of memory, not capturing error state\n");
 		return;
@@ -909,47 +960,22 @@ static void i915_capture_error_state(struct drm_device *dev)
 	DRM_INFO("capturing error event; look for more information in /debug/dri/%d/i915_error_state\n",
 		 dev->primary->index);
 
-	error->seqno = dev_priv->ring[RCS].get_seqno(&dev_priv->ring[RCS]);
 	error->eir = I915_READ(EIR);
 	error->pgtbl_er = I915_READ(PGTBL_ER);
 	for_each_pipe(pipe)
 		error->pipestat[pipe] = I915_READ(PIPESTAT(pipe));
-	error->instpm = I915_READ(INSTPM);
-	error->error = 0;
+
 	if (INTEL_INFO(dev)->gen >= 6) {
 		error->error = I915_READ(ERROR_GEN6);
-
-		error->bcs_acthd = I915_READ(BCS_ACTHD);
-		error->bcs_ipehr = I915_READ(BCS_IPEHR);
-		error->bcs_ipeir = I915_READ(BCS_IPEIR);
-		error->bcs_instdone = I915_READ(BCS_INSTDONE);
-		error->bcs_seqno = 0;
-		if (dev_priv->ring[BCS].get_seqno)
-			error->bcs_seqno = dev_priv->ring[BCS].get_seqno(&dev_priv->ring[BCS]);
-
-		error->vcs_acthd = I915_READ(VCS_ACTHD);
-		error->vcs_ipehr = I915_READ(VCS_IPEHR);
-		error->vcs_ipeir = I915_READ(VCS_IPEIR);
-		error->vcs_instdone = I915_READ(VCS_INSTDONE);
-		error->vcs_seqno = 0;
-		if (dev_priv->ring[VCS].get_seqno)
-			error->vcs_seqno = dev_priv->ring[VCS].get_seqno(&dev_priv->ring[VCS]);
-	}
-	if (INTEL_INFO(dev)->gen >= 4) {
-		error->ipeir = I915_READ(IPEIR_I965);
-		error->ipehr = I915_READ(IPEHR_I965);
-		error->instdone = I915_READ(INSTDONE_I965);
-		error->instps = I915_READ(INSTPS);
-		error->instdone1 = I915_READ(INSTDONE1);
-		error->acthd = I915_READ(ACTHD_I965);
-		error->bbaddr = I915_READ64(BB_ADDR);
-	} else {
-		error->ipeir = I915_READ(IPEIR);
-		error->ipehr = I915_READ(IPEHR);
-		error->instdone = I915_READ(INSTDONE);
-		error->acthd = I915_READ(ACTHD);
-		error->bbaddr = 0;
+		error->done_reg = I915_READ(DONE_REG);
 	}
+
+	i915_record_ring_state(dev, error, &dev_priv->ring[RCS]);
+	if (HAS_BLT(dev))
+		i915_record_ring_state(dev, error, &dev_priv->ring[BCS]);
+	if (HAS_BSD(dev))
+		i915_record_ring_state(dev, error, &dev_priv->ring[VCS]);
+
 	i915_gem_record_fences(dev, error);
 
 	/* Record the active batch and ring buffers */
@@ -1017,11 +1043,12 @@ void i915_destroy_error_state(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error;
+	unsigned long flags;
 
-	spin_lock(&dev_priv->error_lock);
+	spin_lock_irqsave(&dev_priv->error_lock, flags);
 	error = dev_priv->first_error;
 	dev_priv->first_error = NULL;
-	spin_unlock(&dev_priv->error_lock);
+	spin_unlock_irqrestore(&dev_priv->error_lock, flags);
 
 	if (error)
 		i915_error_state_free(dev, error);
@@ -1698,6 +1725,7 @@ void i915_hangcheck_elapsed(unsigned long data)
 	    dev_priv->last_instdone1 == instdone1) {
 		if (dev_priv->hangcheck_count++ > 1) {
 			DRM_ERROR("Hangcheck timer elapsed... GPU hung\n");
+			i915_handle_error(dev, true);
 
 			if (!IS_GEN2(dev)) {
 				/* Is the chip hanging on a WAIT_FOR_EVENT?
@@ -1705,7 +1733,6 @@ void i915_hangcheck_elapsed(unsigned long data)
 				 * and break the hang. This should work on
 				 * all but the second generation chipsets.
 				 */
-
 				if (kick_ring(&dev_priv->ring[RCS]))
 					goto repeat;
 
@@ -1718,7 +1745,6 @@ void i915_hangcheck_elapsed(unsigned long data)
 					goto repeat;
 			}
 
-			i915_handle_error(dev, true);
 			return;
 		}
 	} else {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c3afb783cb9d..f9607387c00c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -319,6 +319,8 @@
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
 #define RENDER_HWS_PGA_GEN7	(0x04080)
+#define RING_FAULT_REG(ring)	(0x4094 + 0x100*(ring)->id)
+#define DONE_REG		0x40b0
 #define BSD_HWS_PGA_GEN7	(0x04180)
 #define BLT_HWS_PGA_GEN7	(0x04280)
 #define RING_ACTHD(base)	((base)+0x74)
@@ -352,6 +354,12 @@
 #define IPEIR_I965	0x02064
 #define IPEHR_I965	0x02068
 #define INSTDONE_I965	0x0206c
+#define RING_IPEIR(base)	((base)+0x64)
+#define RING_IPEHR(base)	((base)+0x68)
+#define RING_INSTDONE(base)	((base)+0x6c)
+#define RING_INSTPS(base)	((base)+0x70)
+#define RING_DMA_FADD(base)	((base)+0x78)
+#define RING_INSTPM(base)	((base)+0xc0)
 #define INSTPS		0x02070 /* 965+ only */
 #define INSTDONE1	0x0207c /* 965+ only */
 #define ACTHD_I965	0x02074
@@ -365,14 +373,6 @@
 #define INSTDONE	0x02090
 #define NOPID		0x02094
 #define HWSTAM		0x02098
-#define VCS_INSTDONE	0x1206C
-#define VCS_IPEIR	0x12064
-#define VCS_IPEHR	0x12068
-#define VCS_ACTHD	0x12074
-#define BCS_INSTDONE	0x2206C
-#define BCS_IPEIR	0x22064
-#define BCS_IPEHR	0x22068
-#define BCS_ACTHD	0x22074
 
 #define ERROR_GEN6	0x040a0
 
@@ -391,7 +391,7 @@
 
 #define MI_MODE		0x0209c
 # define VS_TIMER_DISPATCH				(1 << 6)
-# define MI_FLUSH_ENABLE				(1 << 11)
+# define MI_FLUSH_ENABLE				(1 << 12)
 
 #define GFX_MODE	0x02520
 #define GFX_MODE_GEN7	0x0229c
@@ -3742,4 +3742,16 @@
  */
 #define GEN7_SO_WRITE_OFFSET(n)		(0x5280 + (n) * 4)
 
+#define IBX_AUD_CONFIG_A			0xe2000
+#define CPT_AUD_CONFIG_A			0xe5000
+#define   AUD_CONFIG_N_VALUE_INDEX		(1 << 29)
+#define   AUD_CONFIG_N_PROG_ENABLE		(1 << 28)
+#define   AUD_CONFIG_UPPER_N_SHIFT		20
+#define   AUD_CONFIG_UPPER_N_VALUE		(0xff << 20)
+#define   AUD_CONFIG_LOWER_N_SHIFT		4
+#define   AUD_CONFIG_LOWER_N_VALUE		(0xfff << 4)
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI_SHIFT	16
+#define   AUD_CONFIG_PIXEL_CLOCK_HDMI		(0xf << 16)
+#define   AUD_CONFIG_DISABLE_NCTS		(1 << 3)
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5ba19df199e4..dfa67449827a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -936,6 +936,10 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	u32 val;
 	bool cur_state;
 
+	/* if we need the pipe A quirk it must be always on */
+	if (pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE)
+		state = true;
+
 	reg = PIPECONF(pipe);
 	val = I915_READ(reg);
 	cur_state = !!(val & PIPECONF_ENABLE);
@@ -2037,6 +2041,8 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev,
 		ret = i915_gem_object_get_fence(obj, pipelined);
 		if (ret)
 			goto err_unpin;
+
+		i915_gem_object_pin_fence(obj);
 	}
 
 	dev_priv->mm.interruptible = true;
@@ -2049,6 +2055,12 @@ err_interruptible:
 	return ret;
 }
 
+void intel_unpin_fb_obj(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_unpin_fence(obj);
+	i915_gem_object_unpin(obj);
+}
+
 static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 			     int x, int y)
 {
@@ -2280,7 +2292,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y,
 					 LEAVE_ATOMIC_MODE_SET);
 	if (ret) {
-		i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj);
+		intel_unpin_fb_obj(to_intel_framebuffer(crtc->fb)->obj);
 		mutex_unlock(&dev->struct_mutex);
 		DRM_ERROR("failed to update base address\n");
 		return ret;
@@ -2288,7 +2300,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 
 	if (old_fb) {
 		intel_wait_for_vblank(dev, intel_crtc->pipe);
-		i915_gem_object_unpin(to_intel_framebuffer(old_fb)->obj);
+		intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj);
 	}
 
 	mutex_unlock(&dev->struct_mutex);
@@ -3351,7 +3363,7 @@ static void intel_crtc_disable(struct drm_crtc *crtc)
 
 	if (crtc->fb) {
 		mutex_lock(&dev->struct_mutex);
-		i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj);
+		intel_unpin_fb_obj(to_intel_framebuffer(crtc->fb)->obj);
 		mutex_unlock(&dev->struct_mutex);
 	}
 }
@@ -4548,6 +4560,7 @@ void sandybridge_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;
 	unsigned int enabled;
 
@@ -4556,8 +4569,10 @@ void sandybridge_update_wm(struct drm_device *dev)
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
-		I915_WRITE(WM0_PIPEA_ILK,
-			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | 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);
@@ -4568,8 +4583,10 @@ void sandybridge_update_wm(struct drm_device *dev)
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
-		I915_WRITE(WM0_PIPEB_ILK,
-			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | 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);
@@ -4582,8 +4599,10 @@ void sandybridge_update_wm(struct drm_device *dev)
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
-		I915_WRITE(WM0_PIPEC_IVB,
-			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
+		val = I915_READ(WM0_PIPEC_IVB);
+		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
+		I915_WRITE(WM0_PIPEC_IVB, val |
+			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
 		DRM_DEBUG_KMS("FIFO watermarks For pipe C -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
@@ -4727,6 +4746,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	u32 val;
 	int sprite_wm, reg;
 	int ret;
 
@@ -4753,7 +4773,9 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 		return;
 	}
 
-	I915_WRITE(reg, I915_READ(reg) | (sprite_wm << WM0_PIPE_SPRITE_SHIFT));
+	val = I915_READ(reg);
+	val &= ~WM0_PIPE_SPRITE_MASK;
+	I915_WRITE(reg, val | (sprite_wm << WM0_PIPE_SPRITE_SHIFT));
 	DRM_DEBUG_KMS("sprite watermarks For pipe %d - %d\n", pipe, sprite_wm);
 
 
@@ -6130,15 +6152,18 @@ static void ironlake_write_eld(struct drm_connector *connector,
 	uint32_t i;
 	int len;
 	int hdmiw_hdmiedid;
+	int aud_config;
 	int aud_cntl_st;
 	int aud_cntrl_st2;
 
 	if (HAS_PCH_IBX(connector->dev)) {
 		hdmiw_hdmiedid = IBX_HDMIW_HDMIEDID_A;
+		aud_config = IBX_AUD_CONFIG_A;
 		aud_cntl_st = IBX_AUD_CNTL_ST_A;
 		aud_cntrl_st2 = IBX_AUD_CNTL_ST2;
 	} else {
 		hdmiw_hdmiedid = CPT_HDMIW_HDMIEDID_A;
+		aud_config = CPT_AUD_CONFIG_A;
 		aud_cntl_st = CPT_AUD_CNTL_ST_A;
 		aud_cntrl_st2 = CPT_AUD_CNTRL_ST2;
 	}
@@ -6146,6 +6171,7 @@ static void ironlake_write_eld(struct drm_connector *connector,
 	i = to_intel_crtc(crtc)->pipe;
 	hdmiw_hdmiedid += i * 0x100;
 	aud_cntl_st += i * 0x100;
+	aud_config += i * 0x100;
 
 	DRM_DEBUG_DRIVER("ELD on pipe %c\n", pipe_name(i));
 
@@ -6165,7 +6191,9 @@ static void ironlake_write_eld(struct drm_connector *connector,
 	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) {
 		DRM_DEBUG_DRIVER("ELD: DisplayPort detected\n");
 		eld[5] |= (1 << 2);	/* Conn_Type, 0x1 = DisplayPort */
-	}
+		I915_WRITE(aud_config, AUD_CONFIG_N_VALUE_INDEX); /* 0x1 = DP */
+	} else
+		I915_WRITE(aud_config, 0);
 
 	if (intel_eld_uptodate(connector,
 			       aud_cntrl_st2, eldv,
@@ -7141,7 +7169,7 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 		container_of(__work, struct intel_unpin_work, work);
 
 	mutex_lock(&work->dev->struct_mutex);
-	i915_gem_object_unpin(work->old_fb_obj);
+	intel_unpin_fb_obj(work->old_fb_obj);
 	drm_gem_object_unreference(&work->pending_flip_obj->base);
 	drm_gem_object_unreference(&work->old_fb_obj->base);
 
@@ -7291,7 +7319,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 		 MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	OUT_RING(fb->pitches[0]);
 	OUT_RING(obj->gtt_offset + offset);
-	OUT_RING(MI_NOOP);
+	OUT_RING(0); /* aux display base address, unused */
 	ADVANCE_LP_RING();
 out:
 	return ret;
@@ -7883,7 +7911,8 @@ int intel_framebuffer_init(struct drm_device *dev,
 	case DRM_FORMAT_VYUY:
 		break;
 	default:
-		DRM_ERROR("unsupported pixel format\n");
+		DRM_DEBUG_KMS("unsupported pixel format %u\n",
+				mode_cmd->pixel_format);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 1348705faf6b..9cec6c3937fa 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -374,6 +374,7 @@ extern void intel_init_emon(struct drm_device *dev);
 extern int intel_pin_and_fence_fb_obj(struct drm_device *dev,
 				      struct drm_i915_gem_object *obj,
 				      struct intel_ring_buffer *pipelined);
+extern void intel_unpin_fb_obj(struct drm_i915_gem_object *obj);
 
 extern int intel_framebuffer_init(struct drm_device *dev,
 				  struct intel_framebuffer *ifb,
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index cdf17d4cc1f7..23a543cdfa99 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -227,7 +227,8 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 	}
 	overlay->last_flip_req = request->seqno;
 	overlay->flip_tail = tail;
-	ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req);
+	ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req,
+				true);
 	if (ret)
 		return ret;
 
@@ -448,7 +449,8 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
 	if (overlay->last_flip_req == 0)
 		return 0;
 
-	ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req);
+	ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req,
+				true);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 1ab842c6032e..4956f1bff522 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -399,8 +399,6 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 
 	if (INTEL_INFO(dev)->gen > 3) {
 		int mode = VS_TIMER_DISPATCH << 16 | VS_TIMER_DISPATCH;
-		if (IS_GEN6(dev) || IS_GEN7(dev))
-			mode |= MI_FLUSH_ENABLE << 16 | MI_FLUSH_ENABLE;
 		I915_WRITE(MI_MODE, mode);
 		if (IS_GEN7(dev))
 			I915_WRITE(GFX_MODE_GEN7,
@@ -744,13 +742,13 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 	 */
 	if (IS_GEN7(dev)) {
 		switch (ring->id) {
-		case RING_RENDER:
+		case RCS:
 			mmio = RENDER_HWS_PGA_GEN7;
 			break;
-		case RING_BLT:
+		case BCS:
 			mmio = BLT_HWS_PGA_GEN7;
 			break;
-		case RING_BSD:
+		case VCS:
 			mmio = BSD_HWS_PGA_GEN7;
 			break;
 		}
@@ -1212,7 +1210,7 @@ void intel_ring_advance(struct intel_ring_buffer *ring)
 
 static const struct intel_ring_buffer render_ring = {
 	.name			= "render ring",
-	.id			= RING_RENDER,
+	.id			= RCS,
 	.mmio_base		= RENDER_RING_BASE,
 	.size			= 32 * PAGE_SIZE,
 	.init			= init_render_ring,
@@ -1235,7 +1233,7 @@ static const struct intel_ring_buffer render_ring = {
 
 static const struct intel_ring_buffer bsd_ring = {
 	.name                   = "bsd ring",
-	.id			= RING_BSD,
+	.id			= VCS,
 	.mmio_base		= BSD_RING_BASE,
 	.size			= 32 * PAGE_SIZE,
 	.init			= init_ring_common,
@@ -1345,7 +1343,7 @@ gen6_bsd_ring_put_irq(struct intel_ring_buffer *ring)
 /* ring buffer for Video Codec for Gen6+ */
 static const struct intel_ring_buffer gen6_bsd_ring = {
 	.name			= "gen6 bsd ring",
-	.id			= RING_BSD,
+	.id			= VCS,
 	.mmio_base		= GEN6_BSD_RING_BASE,
 	.size			= 32 * PAGE_SIZE,
 	.init			= init_ring_common,
@@ -1381,79 +1379,13 @@ blt_ring_put_irq(struct intel_ring_buffer *ring)
 			  GEN6_BLITTER_USER_INTERRUPT);
 }
 
-
-/* Workaround for some stepping of SNB,
- * each time when BLT engine ring tail moved,
- * the first command in the ring to be parsed
- * should be MI_BATCH_BUFFER_START
- */
-#define NEED_BLT_WORKAROUND(dev) \
-	(IS_GEN6(dev) && (dev->pdev->revision < 8))
-
-static inline struct drm_i915_gem_object *
-to_blt_workaround(struct intel_ring_buffer *ring)
-{
-	return ring->private;
-}
-
-static int blt_ring_init(struct intel_ring_buffer *ring)
-{
-	if (NEED_BLT_WORKAROUND(ring->dev)) {
-		struct drm_i915_gem_object *obj;
-		u32 *ptr;
-		int ret;
-
-		obj = i915_gem_alloc_object(ring->dev, 4096);
-		if (obj == NULL)
-			return -ENOMEM;
-
-		ret = i915_gem_object_pin(obj, 4096, true);
-		if (ret) {
-			drm_gem_object_unreference(&obj->base);
-			return ret;
-		}
-
-		ptr = kmap(obj->pages[0]);
-		*ptr++ = MI_BATCH_BUFFER_END;
-		*ptr++ = MI_NOOP;
-		kunmap(obj->pages[0]);
-
-		ret = i915_gem_object_set_to_gtt_domain(obj, false);
-		if (ret) {
-			i915_gem_object_unpin(obj);
-			drm_gem_object_unreference(&obj->base);
-			return ret;
-		}
-
-		ring->private = obj;
-	}
-
-	return init_ring_common(ring);
-}
-
-static int blt_ring_begin(struct intel_ring_buffer *ring,
-			  int num_dwords)
-{
-	if (ring->private) {
-		int ret = intel_ring_begin(ring, num_dwords+2);
-		if (ret)
-			return ret;
-
-		intel_ring_emit(ring, MI_BATCH_BUFFER_START);
-		intel_ring_emit(ring, to_blt_workaround(ring)->gtt_offset);
-
-		return 0;
-	} else
-		return intel_ring_begin(ring, 4);
-}
-
 static int blt_ring_flush(struct intel_ring_buffer *ring,
 			  u32 invalidate, u32 flush)
 {
 	uint32_t cmd;
 	int ret;
 
-	ret = blt_ring_begin(ring, 4);
+	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		return ret;
 
@@ -1468,22 +1400,12 @@ static int blt_ring_flush(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-static void blt_ring_cleanup(struct intel_ring_buffer *ring)
-{
-	if (!ring->private)
-		return;
-
-	i915_gem_object_unpin(ring->private);
-	drm_gem_object_unreference(ring->private);
-	ring->private = NULL;
-}
-
 static const struct intel_ring_buffer gen6_blt_ring = {
 	.name			= "blt ring",
-	.id			= RING_BLT,
+	.id			= BCS,
 	.mmio_base		= BLT_RING_BASE,
 	.size			= 32 * PAGE_SIZE,
-	.init			= blt_ring_init,
+	.init			= init_ring_common,
 	.write_tail		= ring_write_tail,
 	.flush			= blt_ring_flush,
 	.add_request		= gen6_add_request,
@@ -1491,7 +1413,6 @@ static const struct intel_ring_buffer gen6_blt_ring = {
 	.irq_get		= blt_ring_get_irq,
 	.irq_put		= blt_ring_put_irq,
 	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
-	.cleanup		= blt_ring_cleanup,
 	.sync_to		= gen6_blt_ring_sync_to,
 	.semaphore_register	= {MI_SEMAPHORE_SYNC_BR,
 				   MI_SEMAPHORE_SYNC_BV,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 68281c96c558..c8b9cc0cd0dc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -1,13 +1,6 @@
 #ifndef _INTEL_RINGBUFFER_H_
 #define _INTEL_RINGBUFFER_H_
 
-enum {
-	RCS = 0x0,
-	VCS,
-	BCS,
-	I915_NUM_RINGS,
-};
-
 struct  intel_hw_status_page {
 	u32	__iomem	*page_addr;
 	unsigned int	gfx_addr;
@@ -36,10 +29,11 @@ struct  intel_hw_status_page {
 struct  intel_ring_buffer {
 	const char	*name;
 	enum intel_ring_id {
-		RING_RENDER = 0x1,
-		RING_BSD = 0x2,
-		RING_BLT = 0x4,
+		RCS = 0x0,
+		VCS,
+		BCS,
 	} id;
+#define I915_NUM_RINGS 3
 	u32		mmio_base;
 	void		__iomem *virtual_start;
 	struct		drm_device *dev;
@@ -119,6 +113,12 @@ struct  intel_ring_buffer {
 	void *private;
 };
 
+static inline unsigned
+intel_ring_flag(struct intel_ring_buffer *ring)
+{
+	return 1 << ring->id;
+}
+
 static inline u32
 intel_ring_sync_index(struct intel_ring_buffer *ring,
 		      struct intel_ring_buffer *other)
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 2288abf88cce..98444ab68bc3 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -501,7 +501,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 			intel_wait_for_vblank(dev, to_intel_crtc(crtc)->pipe);
 			mutex_lock(&dev->struct_mutex);
 		}
-		i915_gem_object_unpin(old_obj);
+		intel_unpin_fb_obj(old_obj);
 	}
 
 out_unlock:
@@ -528,7 +528,7 @@ intel_disable_plane(struct drm_plane *plane)
 		goto out;
 
 	mutex_lock(&dev->struct_mutex);
-	i915_gem_object_unpin(intel_plane->obj);
+	intel_unpin_fb_obj(intel_plane->obj);
 	intel_plane->obj = NULL;
 	mutex_unlock(&dev->struct_mutex);
 out: