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

Daniel writes:

" First -next pull for 3.7. Highlights:
- hsw hdmi improvements (Paulo)
- ips/rps locking rework and cleanups
- rc6 on ilk by default again
- hw context&dp&dpff support for hsw (Ben)
- GET_PARAM_HAS_SEMAPHORES (Chris)
- gen6+ pipe_control improvements (Chris)
- set_cacheing ioctl and assorted support code (Chris)
- cleanups around the busy/idle/pm code (Chris&me)
- flushing_list removal, hopefully for good (Chris)
- read_reg ioctl (Ben)
- support the ns2501 dvo (Thomas Richter)
- avoid the costly gen6+ "missed IRQ" workaround where we don't need a
  race-free seqno readback (Chris)
- various bits&pieces, mostly early patches from the modeset rework branch"

* 'for-airlied' of git://people.freedesktop.org/~danvet/drm-intel: (54 commits)
  drm/i915: don't grab dev->struct_mutex for userspace forcewak
  drm/i915: try harder to find WR PLL clock settings
  drm/i915: use the correct encoder type when comparing
  drm/i915: Lazily apply the SNB+ seqno w/a
  drm/i915: enable rc6 on ilk again
  drm/i915: fix up ilk drps/ips locking
  drm/i915: DE_PCU_EVENT irq is ilk-only
  drm/i915: kill dev_priv->mchdev_lock
  drm/i915: move all rps state into dev_priv->rps
  drm/i915: use mutex_lock_interruptible for debugfs files
  drm/i915: fixup up debugfs rps state handling
  drm/i915: properly guard ilk ips state
  drm/i915: add parentheses around PIXCLK_GATE definitions
  drm/i915: reindent Haswell register definitions
  drm/i915: completely reset the value of DDI_FUNC_CTL
  drm/i915: correctly set the DDI_FUNC_CTL bpc field
  drm/i915: set the DDI sync polarity bits
  drm/i915: fix pipe DDI mode select
  drm/i915: dump the device info
  drm/i915: fixup desired rps frequency computation
  ...

drivers/gpu/drm/i915/Makefile

@@ -40,6 +40,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \
 	  dvo_ivch.o \
 	  dvo_tfp410.o \
 	  dvo_sil164.o \
+	  dvo_ns2501.o \
 	  i915_gem_dmabuf.o
 
 i915-$(CONFIG_COMPAT)   += i915_ioc32.o

drivers/gpu/drm/i915/dvo.h

@@ -140,5 +140,6 @@ extern struct intel_dvo_dev_ops ch7xxx_ops;
 extern struct intel_dvo_dev_ops ivch_ops;
 extern struct intel_dvo_dev_ops tfp410_ops;
 extern struct intel_dvo_dev_ops ch7017_ops;
+extern struct intel_dvo_dev_ops ns2501_ops;
 
 #endif /* _INTEL_DVO_H */

drivers/gpu/drm/i915/i915_debugfs.c

@@ -44,7 +44,6 @@
 
 enum {
 	ACTIVE_LIST,
-	FLUSHING_LIST,
 	INACTIVE_LIST,
 	PINNED_LIST,
 };
@@ -62,28 +61,11 @@ static int i915_capabilities(struct seq_file *m, void *data)
 
 	seq_printf(m, "gen: %d\n", info->gen);
 	seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev));
-#define B(x) seq_printf(m, #x ": %s\n", yesno(info->x))
-	B(is_mobile);
-	B(is_i85x);
-	B(is_i915g);
-	B(is_i945gm);
-	B(is_g33);
-	B(need_gfx_hws);
-	B(is_g4x);
-	B(is_pineview);
-	B(is_broadwater);
-	B(is_crestline);
-	B(has_fbc);
-	B(has_pipe_cxsr);
-	B(has_hotplug);
-	B(cursor_needs_physical);
-	B(has_overlay);
-	B(overlay_needs_physical);
-	B(supports_tv);
-	B(has_bsd_ring);
-	B(has_blt_ring);
-	B(has_llc);
-#undef B
+#define DEV_INFO_FLAG(x) seq_printf(m, #x ": %s\n", yesno(info->x))
+#define DEV_INFO_SEP ;
+	DEV_INFO_FLAGS;
+#undef DEV_INFO_FLAG
+#undef DEV_INFO_SEP
 
 	return 0;
 }
@@ -121,14 +103,15 @@ static const char *cache_level_str(int type)
 static void
 describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 {
-	seq_printf(m, "%p: %s%s %8zdKiB %04x %04x %d %d%s%s%s",
+	seq_printf(m, "%p: %s%s %8zdKiB %04x %04x %d %d %d%s%s%s",
 		   &obj->base,
 		   get_pin_flag(obj),
 		   get_tiling_flag(obj),
 		   obj->base.size / 1024,
 		   obj->base.read_domains,
 		   obj->base.write_domain,
-		   obj->last_rendering_seqno,
+		   obj->last_read_seqno,
+		   obj->last_write_seqno,
 		   obj->last_fenced_seqno,
 		   cache_level_str(obj->cache_level),
 		   obj->dirty ? " dirty" : "",
@@ -177,10 +160,6 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 		seq_printf(m, "Inactive:\n");
 		head = &dev_priv->mm.inactive_list;
 		break;
-	case FLUSHING_LIST:
-		seq_printf(m, "Flushing:\n");
-		head = &dev_priv->mm.flushing_list;
-		break;
 	default:
 		mutex_unlock(&dev->struct_mutex);
 		return -EINVAL;
@@ -238,7 +217,6 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 
 	size = count = mappable_size = mappable_count = 0;
 	count_objects(&dev_priv->mm.active_list, mm_list);
-	count_objects(&dev_priv->mm.flushing_list, mm_list);
 	seq_printf(m, "  %u [%u] active objects, %zu [%zu] bytes\n",
 		   count, mappable_count, size, mappable_size);
 
@@ -413,7 +391,7 @@ static void i915_ring_seqno_info(struct seq_file *m,
 {
 	if (ring->get_seqno) {
 		seq_printf(m, "Current sequence (%s): %d\n",
-			   ring->name, ring->get_seqno(ring));
+			   ring->name, ring->get_seqno(ring, false));
 	}
 }
 
@@ -630,12 +608,12 @@ 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%s",
+		seq_printf(m, "  %08x %8u %04x %04x %x %x%s%s%s%s%s%s%s",
 			   err->gtt_offset,
 			   err->size,
 			   err->read_domains,
 			   err->write_domain,
-			   err->seqno,
+			   err->rseqno, err->wseqno,
 			   pin_flag(err->pinned),
 			   tiling_flag(err->tiling),
 			   dirty_flag(err->dirty),
@@ -799,10 +777,14 @@ i915_error_state_write(struct file *filp,
 	struct seq_file *m = filp->private_data;
 	struct i915_error_state_file_priv *error_priv = m->private;
 	struct drm_device *dev = error_priv->dev;
+	int ret;
 
 	DRM_DEBUG_DRIVER("Resetting error state\n");
 
-	mutex_lock(&dev->struct_mutex);
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
 	i915_destroy_error_state(dev);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1292,7 +1274,8 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 
 	seq_printf(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\n");
 
-	for (gpu_freq = dev_priv->min_delay; gpu_freq <= dev_priv->max_delay;
+	for (gpu_freq = dev_priv->rps.min_delay;
+	     gpu_freq <= dev_priv->rps.max_delay;
 	     gpu_freq++) {
 		I915_WRITE(GEN6_PCODE_DATA, gpu_freq);
 		I915_WRITE(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY |
@@ -1472,8 +1455,12 @@ 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;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
-	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",
@@ -1674,7 +1661,7 @@ i915_ring_stop_write(struct file *filp,
 	struct drm_device *dev = filp->private_data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	char buf[20];
-	int val = 0;
+	int val = 0, ret;
 
 	if (cnt > 0) {
 		if (cnt > sizeof(buf) - 1)
@@ -1689,7 +1676,10 @@ i915_ring_stop_write(struct file *filp,
 
 	DRM_DEBUG_DRIVER("Stopping rings 0x%08x\n", val);
 
-	mutex_lock(&dev->struct_mutex);
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
 	dev_priv->stop_rings = val;
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1713,10 +1703,18 @@ i915_max_freq_read(struct file *filp,
 	struct drm_device *dev = filp->private_data;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	char buf[80];
-	int len;
+	int len, ret;
+
+	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+		return -ENODEV;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	len = snprintf(buf, sizeof(buf),
-		       "max freq: %d\n", dev_priv->max_delay * 50);
+		       "max freq: %d\n", dev_priv->rps.max_delay * 50);
+	mutex_unlock(&dev->struct_mutex);
 
 	if (len > sizeof(buf))
 		len = sizeof(buf);
@@ -1733,7 +1731,10 @@ i915_max_freq_write(struct file *filp,
 	struct drm_device *dev = filp->private_data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	char buf[20];
-	int val = 1;
+	int val = 1, ret;
+
+	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+		return -ENODEV;
 
 	if (cnt > 0) {
 		if (cnt > sizeof(buf) - 1)
@@ -1748,12 +1749,17 @@ i915_max_freq_write(struct file *filp,
 
 	DRM_DEBUG_DRIVER("Manually setting max freq to %d\n", val);
 
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
 	/*
 	 * Turbo will still be enabled, but won't go above the set value.
 	 */
-	dev_priv->max_delay = val / 50;
+	dev_priv->rps.max_delay = val / 50;
 
 	gen6_set_rps(dev, val / 50);
+	mutex_unlock(&dev->struct_mutex);
 
 	return cnt;
 }
@@ -1773,10 +1779,18 @@ i915_min_freq_read(struct file *filp, char __user *ubuf, size_t max,
 	struct drm_device *dev = filp->private_data;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	char buf[80];
-	int len;
+	int len, ret;
+
+	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+		return -ENODEV;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	len = snprintf(buf, sizeof(buf),
-		       "min freq: %d\n", dev_priv->min_delay * 50);
+		       "min freq: %d\n", dev_priv->rps.min_delay * 50);
+	mutex_unlock(&dev->struct_mutex);
 
 	if (len > sizeof(buf))
 		len = sizeof(buf);
@@ -1791,7 +1805,10 @@ i915_min_freq_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	struct drm_device *dev = filp->private_data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	char buf[20];
-	int val = 1;
+	int val = 1, ret;
+
+	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+		return -ENODEV;
 
 	if (cnt > 0) {
 		if (cnt > sizeof(buf) - 1)
@@ -1806,12 +1823,17 @@ i915_min_freq_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	DRM_DEBUG_DRIVER("Manually setting min freq to %d\n", val);
 
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
 	/*
 	 * Turbo will still be enabled, but won't go below the set value.
 	 */
-	dev_priv->min_delay = val / 50;
+	dev_priv->rps.min_delay = val / 50;
 
 	gen6_set_rps(dev, val / 50);
+	mutex_unlock(&dev->struct_mutex);
 
 	return cnt;
 }
@@ -1834,9 +1856,15 @@ i915_cache_sharing_read(struct file *filp,
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	char buf[80];
 	u32 snpcr;
-	int len;
+	int len, ret;
+
+	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+		return -ENODEV;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
-	mutex_lock(&dev_priv->dev->struct_mutex);
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 	mutex_unlock(&dev_priv->dev->struct_mutex);
 
@@ -1862,6 +1890,9 @@ i915_cache_sharing_write(struct file *filp,
 	u32 snpcr;
 	int val = 1;
 
+	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+		return -ENODEV;
+
 	if (cnt > 0) {
 		if (cnt > sizeof(buf) - 1)
 			return -EINVAL;
@@ -1925,16 +1956,11 @@ static int i915_forcewake_open(struct inode *inode, struct file *file)
 {
 	struct drm_device *dev = inode->i_private;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
 
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
 
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 	gen6_gt_force_wake_get(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
@@ -1947,16 +1973,7 @@ static int i915_forcewake_release(struct inode *inode, struct file *file)
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
 
-	/*
-	 * It's bad that we can potentially hang userspace if struct_mutex gets
-	 * forever stuck.  However, if we cannot acquire this lock it means that
-	 * almost certainly the driver has hung, is not unload-able. Therefore
-	 * hanging here is probably a minor inconvenience not to be seen my
-	 * almost every user.
-	 */
-	mutex_lock(&dev->struct_mutex);
 	gen6_gt_force_wake_put(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
@@ -2006,7 +2023,6 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_gtt", i915_gem_gtt_info, 0},
 	{"i915_gem_pinned", i915_gem_gtt_info, 0, (void *) PINNED_LIST},
 	{"i915_gem_active", i915_gem_object_list_info, 0, (void *) ACTIVE_LIST},
-	{"i915_gem_flushing", i915_gem_object_list_info, 0, (void *) FLUSHING_LIST},
 	{"i915_gem_inactive", i915_gem_object_list_info, 0, (void *) INACTIVE_LIST},
 	{"i915_gem_pageflip", i915_gem_pageflip_info, 0},
 	{"i915_gem_request", i915_gem_request_info, 0},
@@ -2067,6 +2083,7 @@ int i915_debugfs_init(struct drm_minor *minor)
 				  &i915_cache_sharing_fops);
 	if (ret)
 		return ret;
+
 	ret = i915_debugfs_create(minor->debugfs_root, minor,
 				  "i915_ring_stop",
 				  &i915_ring_stop_fops);

drivers/gpu/drm/i915/i915_dma.c

@@ -1009,6 +1009,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_WAIT_TIMEOUT:
 		value = 1;
 		break;
+	case I915_PARAM_HAS_SEMAPHORES:
+		value = i915_semaphore_is_enabled(dev);
+		break;
 	default:
 		DRM_DEBUG_DRIVER("Unknown parameter %d\n",
 				 param->param);
@@ -1425,6 +1428,21 @@ static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
 	kfree(ap);
 }
 
+static void i915_dump_device_info(struct drm_i915_private *dev_priv)
+{
+	const struct intel_device_info *info = dev_priv->info;
+
+#define DEV_INFO_FLAG(name) info->name ? #name "," : ""
+#define DEV_INFO_SEP ,
+	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x flags="
+			 "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
+			 info->gen,
+			 dev_priv->dev->pdev->device,
+			 DEV_INFO_FLAGS);
+#undef DEV_INFO_FLAG
+#undef DEV_INFO_SEP
+}
+
 /**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
@@ -1449,7 +1467,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (info->gen >= 6 && !drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
-
 	/* i915 has 4 more counters */
 	dev->counters += 4;
 	dev->types[6] = _DRM_STAT_IRQ;
@@ -1465,6 +1482,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	dev_priv->dev = dev;
 	dev_priv->info = info;
 
+	i915_dump_device_info(dev_priv);
+
 	if (i915_get_bridge_dev(dev)) {
 		ret = -EIO;
 		goto free_priv;
@@ -1586,7 +1605,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->error_lock);
-	spin_lock_init(&dev_priv->rps_lock);
+	spin_lock_init(&dev_priv->rps.lock);
 
 	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
 		dev_priv->num_pipe = 3;
@@ -1835,6 +1854,8 @@ struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_PIN, i915_gem_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_UNPIN, i915_gem_unpin_ioctl, DRM_AUTH|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_CACHEING, i915_gem_set_cacheing_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_CACHEING, i915_gem_get_cacheing_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, i915_gem_entervt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, i915_gem_leavevt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED),
@@ -1857,6 +1878,7 @@ struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED),
 };
 
 int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);

drivers/gpu/drm/i915/i915_drv.c

@@ -1060,7 +1060,7 @@ static bool IS_DISPLAYREG(u32 reg)
 	 * This should make it easier to transition modules over to the
 	 * new register block scheme, since we can do it incrementally.
 	 */
-	if (reg >= 0x180000)
+	if (reg >= VLV_DISPLAY_BASE)
 		return false;
 
 	if (reg >= RENDER_RING_BASE &&
@@ -1180,3 +1180,49 @@ __i915_write(16, w)
 __i915_write(32, l)
 __i915_write(64, q)
 #undef __i915_write
+
+static const struct register_whitelist {
+	uint64_t offset;
+	uint32_t size;
+	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
+} whitelist[] = {
+	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0xF0 },
+};
+
+int i915_reg_read_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_reg_read *reg = data;
+	struct register_whitelist const *entry = whitelist;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
+		if (entry->offset == reg->offset &&
+		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(whitelist))
+		return -EINVAL;
+
+	switch (entry->size) {
+	case 8:
+		reg->val = I915_READ64(reg->offset);
+		break;
+	case 4:
+		reg->val = I915_READ(reg->offset);
+		break;
+	case 2:
+		reg->val = I915_READ16(reg->offset);
+		break;
+	case 1:
+		reg->val = I915_READ8(reg->offset);
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}

drivers/gpu/drm/i915/i915_drv.h

@@ -109,6 +109,7 @@ struct intel_pch_pll {
 
 #define WATCH_COHERENCY	0
 #define WATCH_LISTS	0
+#define WATCH_GTT	0
 
 #define I915_GEM_PHYS_CURSOR_0 1
 #define I915_GEM_PHYS_CURSOR_1 2
@@ -221,7 +222,7 @@ struct drm_i915_error_state {
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;
-		u32 seqno;
+		u32 rseqno, wseqno;
 		u32 gtt_offset;
 		u32 read_domains;
 		u32 write_domain;
@@ -248,7 +249,6 @@ struct drm_i915_display_funcs {
 	void (*update_wm)(struct drm_device *dev);
 	void (*update_sprite_wm)(struct drm_device *dev, int pipe,
 				 uint32_t sprite_width, int pixel_size);
-	void (*sanitize_pm)(struct drm_device *dev);
 	void (*update_linetime_wm)(struct drm_device *dev, int pipe,
 				 struct drm_display_mode *mode);
 	int (*crtc_mode_set)(struct drm_crtc *crtc,
@@ -279,6 +279,32 @@ struct drm_i915_gt_funcs {
 	void (*force_wake_put)(struct drm_i915_private *dev_priv);
 };
 
+#define DEV_INFO_FLAGS \
+	DEV_INFO_FLAG(is_mobile) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_i85x) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_i915g) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_i945gm) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_g33) DEV_INFO_SEP \
+	DEV_INFO_FLAG(need_gfx_hws) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_g4x) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_pineview) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_broadwater) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_crestline) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_ivybridge) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_valleyview) DEV_INFO_SEP \
+	DEV_INFO_FLAG(is_haswell) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_force_wake) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_fbc) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_pipe_cxsr) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_hotplug) DEV_INFO_SEP \
+	DEV_INFO_FLAG(cursor_needs_physical) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_overlay) DEV_INFO_SEP \
+	DEV_INFO_FLAG(overlay_needs_physical) DEV_INFO_SEP \
+	DEV_INFO_FLAG(supports_tv) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_bsd_ring) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_blt_ring) DEV_INFO_SEP \
+	DEV_INFO_FLAG(has_llc)
+
 struct intel_device_info {
 	u8 gen;
 	u8 is_mobile:1;
@@ -695,17 +721,6 @@ typedef struct drm_i915_private {
 		 */
 		struct list_head active_list;
 
-		/**
-		 * List of objects which are not in the ringbuffer but which
-		 * still have a write_domain which needs to be flushed before
-		 * unbinding.
-		 *
-		 * last_rendering_seqno is 0 while an object is in this list.
-		 *
-		 * A reference is held on the buffer while on this list.
-		 */
-		struct list_head flushing_list;
-
 		/**
 		 * LRU list of objects which are not in the ringbuffer and
 		 * are ready to unbind, but are still in the GTT.
@@ -796,9 +811,6 @@ typedef struct drm_i915_private {
 	bool lvds_downclock_avail;
 	/* indicates the reduced downclock for LVDS*/
 	int lvds_downclock;
-	struct work_struct idle_work;
-	struct timer_list idle_timer;
-	bool busy;
 	u16 orig_clock;
 	int child_dev_num;
 	struct child_device_config *child_dev;
@@ -807,9 +819,21 @@ typedef struct drm_i915_private {
 
 	bool mchbar_need_disable;
 
-	struct work_struct rps_work;
-	spinlock_t rps_lock;
-	u32 pm_iir;
+	/* gen6+ rps state */
+	struct {
+		struct work_struct work;
+		u32 pm_iir;
+		/* lock - irqsave spinlock that protectects the work_struct and
+		 * pm_iir. */
+		spinlock_t lock;
+
+		/* The below variables an all the rps hw state are protected by
+		 * dev->struct mutext. */
+		u8 cur_delay;
+		u8 min_delay;
+		u8 max_delay;
+	} rps;
+
 
 	u8 cur_delay;
 	u8 min_delay;
@@ -826,7 +850,6 @@ typedef struct drm_i915_private {
 	int c_m;
 	int r_t;
 	u8 corr;
-	spinlock_t *mchdev_lock;
 
 	enum no_fbc_reason no_fbc_reason;
 
@@ -861,9 +884,9 @@ enum hdmi_force_audio {
 };
 
 enum i915_cache_level {
-	I915_CACHE_NONE,
+	I915_CACHE_NONE = 0,
 	I915_CACHE_LLC,
-	I915_CACHE_LLC_MLC, /* gen6+ */
+	I915_CACHE_LLC_MLC, /* gen6+, in docs at least! */
 };
 
 struct drm_i915_gem_object {
@@ -873,18 +896,16 @@ struct drm_i915_gem_object {
 	struct drm_mm_node *gtt_space;
 	struct list_head gtt_list;
 
-	/** This object's place on the active/flushing/inactive lists */
+	/** This object's place on the active/inactive lists */
 	struct list_head ring_list;
 	struct list_head mm_list;
-	/** This object's place on GPU write list */
-	struct list_head gpu_write_list;
 	/** This object's place in the batchbuffer or on the eviction list */
 	struct list_head exec_list;
 
 	/**
-	 * This is set if the object is on the active or flushing lists
-	 * (has pending rendering), and is not set if it's on inactive (ready
-	 * to be unbound).
+	 * This is set if the object is on the active lists (has pending
+	 * rendering and so a non-zero seqno), and is not set if it i s on
+	 * inactive (ready to be unbound) list.
 	 */
 	unsigned int active:1;
 
@@ -894,12 +915,6 @@ struct drm_i915_gem_object {
 	 */
 	unsigned int dirty:1;
 
-	/**
-	 * This is set if the object has been written to since the last
-	 * GPU flush.
-	 */
-	unsigned int pending_gpu_write:1;
-
 	/**
 	 * Fence register bits (if any) for this object.  Will be set
 	 * as needed when mapped into the GTT.
@@ -992,7 +1007,8 @@ struct drm_i915_gem_object {
 	struct intel_ring_buffer *ring;
 
 	/** Breadcrumb of last rendering to the buffer. */
-	uint32_t last_rendering_seqno;
+	uint32_t last_read_seqno;
+	uint32_t last_write_seqno;
 	/** Breadcrumb of last fenced GPU access to the buffer. */
 	uint32_t last_fenced_seqno;
 
@@ -1135,6 +1151,8 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
+#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+
 #include "i915_trace.h"
 
 /**
@@ -1256,6 +1274,10 @@ int i915_gem_unpin_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 int i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
+int i915_gem_get_cacheing_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file);
+int i915_gem_set_cacheing_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file);
 int i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv);
 int i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
@@ -1274,9 +1296,6 @@ int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 void i915_gem_load(struct drm_device *dev);
 int i915_gem_init_object(struct drm_gem_object *obj);
-int __must_check i915_gem_flush_ring(struct intel_ring_buffer *ring,
-				     uint32_t invalidate_domains,
-				     uint32_t flush_domains);
 struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 						  size_t size);
 void i915_gem_free_object(struct drm_gem_object *obj);
@@ -1291,7 +1310,6 @@ void i915_gem_lastclose(struct drm_device *dev);
 int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj,
 				  gfp_t gfpmask);
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
-int __must_check i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj);
 int i915_gem_object_sync(struct drm_i915_gem_object *obj,
 			 struct intel_ring_buffer *to);
 void i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
@@ -1358,9 +1376,9 @@ void i915_gem_init_ppgtt(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
 int __must_check i915_gem_idle(struct drm_device *dev);
-int __must_check i915_add_request(struct intel_ring_buffer *ring,
-				  struct drm_file *file,
-				  struct drm_i915_gem_request *request);
+int i915_add_request(struct intel_ring_buffer *ring,
+		     struct drm_file *file,
+		     struct drm_i915_gem_request *request);
 int __must_check i915_wait_seqno(struct intel_ring_buffer *ring,
 				 uint32_t seqno);
 int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -1429,7 +1447,9 @@ void i915_gem_init_global_gtt(struct drm_device *dev,
 
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
-					  unsigned alignment, bool mappable);
+					  unsigned alignment,
+					  unsigned cache_level,
+					  bool mappable);
 int i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only);
 
 /* i915_gem_stolen.c */
@@ -1529,6 +1549,8 @@ extern int intel_trans_dp_port_sel(struct drm_crtc *crtc);
 extern int intel_enable_rc6(const struct drm_device *dev);
 
 extern bool i915_semaphore_is_enabled(struct drm_device *dev);
+int i915_reg_read_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file);
 
 /* overlay */
 #ifdef CONFIG_DEBUG_FS

drivers/gpu/drm/i915/i915_gem_context.c

@@ -97,8 +97,7 @@
 
 static struct i915_hw_context *
 i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
-static int do_switch(struct drm_i915_gem_object *from_obj,
-		     struct i915_hw_context *to, u32 seqno);
+static int do_switch(struct i915_hw_context *to);
 
 static int get_context_size(struct drm_device *dev)
 {
@@ -113,7 +112,10 @@ static int get_context_size(struct drm_device *dev)
 		break;
 	case 7:
 		reg = I915_READ(GEN7_CXT_SIZE);
-		ret = GEN7_CXT_TOTAL_SIZE(reg) * 64;
+		if (IS_HASWELL(dev))
+			ret = HSW_CXT_TOTAL_SIZE(reg) * 64;
+		else
+			ret = GEN7_CXT_TOTAL_SIZE(reg) * 64;
 		break;
 	default:
 		BUG();
@@ -220,19 +222,20 @@ static int create_default_context(struct drm_i915_private *dev_priv)
 	 */
 	dev_priv->ring[RCS].default_context = ctx;
 	ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false);
-	if (ret) {
-		do_destroy(ctx);
-		return ret;
-	}
+	if (ret)
+		goto err_destroy;
 
-	ret = do_switch(NULL, ctx, 0);
-	if (ret) {
-		i915_gem_object_unpin(ctx->obj);
-		do_destroy(ctx);
-	} else {
-		DRM_DEBUG_DRIVER("Default HW context loaded\n");
-	}
+	ret = do_switch(ctx);
+	if (ret)
+		goto err_unpin;
 
+	DRM_DEBUG_DRIVER("Default HW context loaded\n");
+	return 0;
+
+err_unpin:
+	i915_gem_object_unpin(ctx->obj);
+err_destroy:
+	do_destroy(ctx);
 	return ret;
 }
 
@@ -359,17 +362,18 @@ mi_set_context(struct intel_ring_buffer *ring,
 	return ret;
 }
 
-static int do_switch(struct drm_i915_gem_object *from_obj,
-		     struct i915_hw_context *to,
-		     u32 seqno)
+static int do_switch(struct i915_hw_context *to)
 {
-	struct intel_ring_buffer *ring = NULL;
+	struct intel_ring_buffer *ring = to->ring;
+	struct drm_i915_gem_object *from_obj = ring->last_context_obj;
 	u32 hw_flags = 0;
 	int ret;
 
-	BUG_ON(to == NULL);
 	BUG_ON(from_obj != NULL && from_obj->pin_count == 0);
 
+	if (from_obj == to->obj)
+		return 0;
+
 	ret = i915_gem_object_pin(to->obj, CONTEXT_ALIGN, false);
 	if (ret)
 		return ret;
@@ -393,7 +397,6 @@ static int do_switch(struct drm_i915_gem_object *from_obj,
 	else if (WARN_ON_ONCE(from_obj == to->obj)) /* not yet expected */
 		hw_flags |= MI_FORCE_RESTORE;
 
-	ring = to->ring;
 	ret = mi_set_context(ring, to, hw_flags);
 	if (ret) {
 		i915_gem_object_unpin(to->obj);
@@ -407,6 +410,7 @@ static int do_switch(struct drm_i915_gem_object *from_obj,
 	 * MI_SET_CONTEXT instead of when the next seqno has completed.
 	 */
 	if (from_obj != NULL) {
+		u32 seqno = i915_gem_next_request_seqno(ring);
 		from_obj->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
 		i915_gem_object_move_to_active(from_obj, ring, seqno);
 		/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
@@ -417,7 +421,7 @@ static int do_switch(struct drm_i915_gem_object *from_obj,
 		 * swapped, but there is no way to do that yet.
 		 */
 		from_obj->dirty = 1;
-		BUG_ON(from_obj->ring != to->ring);
+		BUG_ON(from_obj->ring != ring);
 		i915_gem_object_unpin(from_obj);
 
 		drm_gem_object_unreference(&from_obj->base);
@@ -448,9 +452,7 @@ int i915_switch_context(struct intel_ring_buffer *ring,
 			int to_id)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	struct drm_i915_file_private *file_priv = NULL;
 	struct i915_hw_context *to;
-	struct drm_i915_gem_object *from_obj = ring->last_context_obj;
 
 	if (dev_priv->hw_contexts_disabled)
 		return 0;
@@ -458,21 +460,18 @@ int i915_switch_context(struct intel_ring_buffer *ring,
 	if (ring != &dev_priv->ring[RCS])
 		return 0;
 
-	if (file)
-		file_priv = file->driver_priv;
-
 	if (to_id == DEFAULT_CONTEXT_ID) {
 		to = ring->default_context;
 	} else {
-		to = i915_gem_context_get(file_priv, to_id);
+		if (file == NULL)
+			return -EINVAL;
+
+		to = i915_gem_context_get(file->driver_priv, to_id);
 		if (to == NULL)
 			return -ENOENT;
 	}
 
-	if (from_obj == to->obj)
-		return 0;
-
-	return do_switch(from_obj, to, i915_gem_next_request_seqno(to->ring));
+	return do_switch(to);
 }
 
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,

drivers/gpu/drm/i915/i915_gem_evict.c

@@ -44,7 +44,8 @@ mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind)
 
 int
 i915_gem_evict_something(struct drm_device *dev, int min_size,
-			 unsigned alignment, bool mappable)
+			 unsigned alignment, unsigned cache_level,
+			 bool mappable)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct list_head eviction_list, unwind_list;
@@ -79,11 +80,11 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
 	INIT_LIST_HEAD(&unwind_list);
 	if (mappable)
 		drm_mm_init_scan_with_range(&dev_priv->mm.gtt_space,
-					    min_size, alignment, 0,
+					    min_size, alignment, cache_level,
 					    0, dev_priv->mm.gtt_mappable_end);
 	else
 		drm_mm_init_scan(&dev_priv->mm.gtt_space,
-				 min_size, alignment, 0);
+				 min_size, alignment, cache_level);
 
 	/* First see if there is a large enough contiguous idle region... */
 	list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list) {
@@ -93,23 +94,6 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
 
 	/* Now merge in the soon-to-be-expired objects... */
 	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
-		/* Does the object require an outstanding flush? */
-		if (obj->base.write_domain)
-			continue;
-
-		if (mark_free(obj, &unwind_list))
-			goto found;
-	}
-
-	/* Finally add anything with a pending flush (in order of retirement) */
-	list_for_each_entry(obj, &dev_priv->mm.flushing_list, mm_list) {
-		if (mark_free(obj, &unwind_list))
-			goto found;
-	}
-	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
-		if (!obj->base.write_domain)
-			continue;
-
 		if (mark_free(obj, &unwind_list))
 			goto found;
 	}
@@ -172,7 +156,6 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
 	int ret;
 
 	lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
-		       list_empty(&dev_priv->mm.flushing_list) &&
 		       list_empty(&dev_priv->mm.active_list));
 	if (lists_empty)
 		return -ENOSPC;
@@ -189,8 +172,6 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
 
 	i915_gem_retire_requests(dev);
 
-	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
-
 	/* Having flushed everything, unbind() should never raise an error */
 	list_for_each_entry_safe(obj, next,
 				 &dev_priv->mm.inactive_list, mm_list) {

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -34,180 +34,6 @@
 #include "intel_drv.h"
 #include <linux/dma_remapping.h>
 
-struct change_domains {
-	uint32_t invalidate_domains;
-	uint32_t flush_domains;
-	uint32_t flush_rings;
-	uint32_t flips;
-};
-
-/*
- * Set the next domain for the specified object. This
- * may not actually perform the necessary flushing/invaliding though,
- * as that may want to be batched with other set_domain operations
- *
- * This is (we hope) the only really tricky part of gem. The goal
- * is fairly simple -- track which caches hold bits of the object
- * and make sure they remain coherent. A few concrete examples may
- * help to explain how it works. For shorthand, we use the notation
- * (read_domains, write_domain), e.g. (CPU, CPU) to indicate the
- * a pair of read and write domain masks.
- *
- * Case 1: the batch buffer
- *
- *	1. Allocated
- *	2. Written by CPU
- *	3. Mapped to GTT
- *	4. Read by GPU
- *	5. Unmapped from GTT
- *	6. Freed
- *
- *	Let's take these a step at a time
- *
- *	1. Allocated
- *		Pages allocated from the kernel may still have
- *		cache contents, so we set them to (CPU, CPU) always.
- *	2. Written by CPU (using pwrite)
- *		The pwrite function calls set_domain (CPU, CPU) and
- *		this function does nothing (as nothing changes)
- *	3. Mapped by GTT
- *		This function asserts that the object is not
- *		currently in any GPU-based read or write domains
- *	4. Read by GPU
- *		i915_gem_execbuffer calls set_domain (COMMAND, 0).
- *		As write_domain is zero, this function adds in the
- *		current read domains (CPU+COMMAND, 0).
- *		flush_domains is set to CPU.
- *		invalidate_domains is set to COMMAND
- *		clflush is run to get data out of the CPU caches
- *		then i915_dev_set_domain calls i915_gem_flush to
- *		emit an MI_FLUSH and drm_agp_chipset_flush
- *	5. Unmapped from GTT
- *		i915_gem_object_unbind calls set_domain (CPU, CPU)
- *		flush_domains and invalidate_domains end up both zero
- *		so no flushing/invalidating happens
- *	6. Freed
- *		yay, done
- *
- * Case 2: The shared render buffer
- *
- *	1. Allocated
- *	2. Mapped to GTT
- *	3. Read/written by GPU
- *	4. set_domain to (CPU,CPU)
- *	5. Read/written by CPU
- *	6. Read/written by GPU
- *
- *	1. Allocated
- *		Same as last example, (CPU, CPU)
- *	2. Mapped to GTT
- *		Nothing changes (assertions find that it is not in the GPU)
- *	3. Read/written by GPU
- *		execbuffer calls set_domain (RENDER, RENDER)
- *		flush_domains gets CPU
- *		invalidate_domains gets GPU
- *		clflush (obj)
- *		MI_FLUSH and drm_agp_chipset_flush
- *	4. set_domain (CPU, CPU)
- *		flush_domains gets GPU
- *		invalidate_domains gets CPU
- *		wait_rendering (obj) to make sure all drawing is complete.
- *		This will include an MI_FLUSH to get the data from GPU
- *		to memory
- *		clflush (obj) to invalidate the CPU cache
- *		Another MI_FLUSH in i915_gem_flush (eliminate this somehow?)
- *	5. Read/written by CPU
- *		cache lines are loaded and dirtied
- *	6. Read written by GPU
- *		Same as last GPU access
- *
- * Case 3: The constant buffer
- *
- *	1. Allocated
- *	2. Written by CPU
- *	3. Read by GPU
- *	4. Updated (written) by CPU again
- *	5. Read by GPU
- *
- *	1. Allocated
- *		(CPU, CPU)
- *	2. Written by CPU
- *		(CPU, CPU)
- *	3. Read by GPU
- *		(CPU+RENDER, 0)
- *		flush_domains = CPU
- *		invalidate_domains = RENDER
- *		clflush (obj)
- *		MI_FLUSH
- *		drm_agp_chipset_flush
- *	4. Updated (written) by CPU again
- *		(CPU, CPU)
- *		flush_domains = 0 (no previous write domain)
- *		invalidate_domains = 0 (no new read domains)
- *	5. Read by GPU
- *		(CPU+RENDER, 0)
- *		flush_domains = CPU
- *		invalidate_domains = RENDER
- *		clflush (obj)
- *		MI_FLUSH
- *		drm_agp_chipset_flush
- */
-static void
-i915_gem_object_set_to_gpu_domain(struct drm_i915_gem_object *obj,
-				  struct intel_ring_buffer *ring,
-				  struct change_domains *cd)
-{
-	uint32_t invalidate_domains = 0, flush_domains = 0;
-
-	/*
-	 * If the object isn't moving to a new write domain,
-	 * let the object stay in multiple read domains
-	 */
-	if (obj->base.pending_write_domain == 0)
-		obj->base.pending_read_domains |= obj->base.read_domains;
-
-	/*
-	 * Flush the current write domain if
-	 * the new read domains don't match. Invalidate
-	 * any read domains which differ from the old
-	 * write domain
-	 */
-	if (obj->base.write_domain &&
-	    (((obj->base.write_domain != obj->base.pending_read_domains ||
-	       obj->ring != ring)) ||
-	     (obj->fenced_gpu_access && !obj->pending_fenced_gpu_access))) {
-		flush_domains |= obj->base.write_domain;
-		invalidate_domains |=
-			obj->base.pending_read_domains & ~obj->base.write_domain;
-	}
-	/*
-	 * Invalidate any read caches which may have
-	 * stale data. That is, any new read domains.
-	 */
-	invalidate_domains |= obj->base.pending_read_domains & ~obj->base.read_domains;
-	if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_CPU)
-		i915_gem_clflush_object(obj);
-
-	if (obj->base.pending_write_domain)
-		cd->flips |= atomic_read(&obj->pending_flip);
-
-	/* The actual obj->write_domain will be updated with
-	 * pending_write_domain after we emit the accumulated flush for all
-	 * of our domain changes in execbuffers (which clears objects'
-	 * write_domains).  So if we have a current write domain that we
-	 * aren't changing, set pending_write_domain to that.
-	 */
-	if (flush_domains == 0 && obj->base.pending_write_domain == 0)
-		obj->base.pending_write_domain = obj->base.write_domain;
-
-	cd->invalidate_domains |= invalidate_domains;
-	cd->flush_domains |= flush_domains;
-	if (flush_domains & I915_GEM_GPU_DOMAINS)
-		cd->flush_rings |= intel_ring_flag(obj->ring);
-	if (invalidate_domains & I915_GEM_GPU_DOMAINS)
-		cd->flush_rings |= intel_ring_flag(ring);
-}
-
 struct eb_objects {
 	int and;
 	struct hlist_head buckets[0];
@@ -587,6 +413,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 
 		obj->base.pending_read_domains = 0;
 		obj->base.pending_write_domain = 0;
+		obj->pending_fenced_gpu_access = false;
 	}
 	list_splice(&ordered_objects, objects);
 
@@ -810,18 +637,6 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 	return ret;
 }
 
-static void
-i915_gem_execbuffer_flush(struct drm_device *dev,
-			  uint32_t invalidate_domains,
-			  uint32_t flush_domains)
-{
-	if (flush_domains & I915_GEM_DOMAIN_CPU)
-		intel_gtt_chipset_flush();
-
-	if (flush_domains & I915_GEM_DOMAIN_GTT)
-		wmb();
-}
-
 static int
 i915_gem_execbuffer_wait_for_flips(struct intel_ring_buffer *ring, u32 flips)
 {
@@ -854,48 +669,45 @@ i915_gem_execbuffer_wait_for_flips(struct intel_ring_buffer *ring, u32 flips)
 	return 0;
 }
 
-
 static int
 i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 				struct list_head *objects)
 {
 	struct drm_i915_gem_object *obj;
-	struct change_domains cd;
+	uint32_t flush_domains = 0;
+	uint32_t flips = 0;
 	int ret;
 
-	memset(&cd, 0, sizeof(cd));
-	list_for_each_entry(obj, objects, exec_list)
-		i915_gem_object_set_to_gpu_domain(obj, ring, &cd);
-
-	if (cd.invalidate_domains | cd.flush_domains) {
-		i915_gem_execbuffer_flush(ring->dev,
-					  cd.invalidate_domains,
-					  cd.flush_domains);
-	}
-
-	if (cd.flips) {
-		ret = i915_gem_execbuffer_wait_for_flips(ring, cd.flips);
+	list_for_each_entry(obj, objects, exec_list) {
+		ret = i915_gem_object_sync(obj, ring);
 		if (ret)
 			return ret;
+
+		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
+			i915_gem_clflush_object(obj);
+
+		if (obj->base.pending_write_domain)
+			flips |= atomic_read(&obj->pending_flip);
+
+		flush_domains |= obj->base.write_domain;
 	}
 
-	list_for_each_entry(obj, objects, exec_list) {
-		ret = i915_gem_object_sync(obj, ring);
+	if (flips) {
+		ret = i915_gem_execbuffer_wait_for_flips(ring, flips);
 		if (ret)
 			return ret;
 	}
 
+	if (flush_domains & I915_GEM_DOMAIN_CPU)
+		intel_gtt_chipset_flush();
+
+	if (flush_domains & I915_GEM_DOMAIN_GTT)
+		wmb();
+
 	/* Unconditionally invalidate gpu caches and ensure that we do flush
 	 * any residual writes from the previous batch.
 	 */
-	ret = i915_gem_flush_ring(ring,
-				  I915_GEM_GPU_DOMAINS,
-				  ring->gpu_caches_dirty ? I915_GEM_GPU_DOMAINS : 0);
-	if (ret)
-		return ret;
-
-	ring->gpu_caches_dirty = false;
-	return 0;
+	return intel_ring_invalidate_all_caches(ring);
 }
 
 static bool
@@ -943,9 +755,8 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 	struct drm_i915_gem_object *obj;
 
 	list_for_each_entry(obj, objects, exec_list) {
-		  u32 old_read = obj->base.read_domains;
-		  u32 old_write = obj->base.write_domain;
-
+		u32 old_read = obj->base.read_domains;
+		u32 old_write = obj->base.write_domain;
 
 		obj->base.read_domains = obj->base.pending_read_domains;
 		obj->base.write_domain = obj->base.pending_write_domain;
@@ -954,17 +765,13 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 		i915_gem_object_move_to_active(obj, ring, seqno);
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
-			obj->pending_gpu_write = true;
-			list_move_tail(&obj->gpu_write_list,
-				       &ring->gpu_write_list);
+			obj->last_write_seqno = seqno;
 			if (obj->pin_count) /* check for potential scanout */
-				intel_mark_busy(ring->dev, obj);
+				intel_mark_fb_busy(obj);
 		}
 
 		trace_i915_gem_object_change_domain(obj, old_read, old_write);
 	}
-
-	intel_mark_busy(ring->dev, NULL);
 }
 
 static void
@@ -972,16 +779,11 @@ i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 				    struct drm_file *file,
 				    struct intel_ring_buffer *ring)
 {
-	struct drm_i915_gem_request *request;
-
 	/* Unconditionally force add_request to emit a full flush. */
 	ring->gpu_caches_dirty = true;
 
 	/* Add a breadcrumb for the completion of the batch buffer */
-	request = kzalloc(sizeof(*request), GFP_KERNEL);
-	if (request == NULL || i915_add_request(ring, file, request)) {
-		kfree(request);
-	}
+	(void)i915_add_request(ring, file, NULL);
 }
 
 static int

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -423,6 +423,23 @@ void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj)
 	undo_idling(dev_priv, interruptible);
 }
 
+static void i915_gtt_color_adjust(struct drm_mm_node *node,
+				  unsigned long color,
+				  unsigned long *start,
+				  unsigned long *end)
+{
+	if (node->color != color)
+		*start += 4096;
+
+	if (!list_empty(&node->node_list)) {
+		node = list_entry(node->node_list.next,
+				  struct drm_mm_node,
+				  node_list);
+		if (node->allocated && node->color != color)
+			*end -= 4096;
+	}
+}
+
 void i915_gem_init_global_gtt(struct drm_device *dev,
 			      unsigned long start,
 			      unsigned long mappable_end,
@@ -432,6 +449,8 @@ void i915_gem_init_global_gtt(struct drm_device *dev,
 
 	/* Substract the guard page ... */
 	drm_mm_init(&dev_priv->mm.gtt_space, start, end - start - PAGE_SIZE);
+	if (!HAS_LLC(dev))
+		dev_priv->mm.gtt_space.color_adjust = i915_gtt_color_adjust;
 
 	dev_priv->mm.gtt_start = start;
 	dev_priv->mm.gtt_mappable_end = mappable_end;

drivers/gpu/drm/i915/i915_irq.c

@@ -296,11 +296,21 @@ static void i915_hotplug_work_func(struct work_struct *work)
 	drm_helper_hpd_irq_event(dev);
 }
 
-static void i915_handle_rps_change(struct drm_device *dev)
+/* defined intel_pm.c */
+extern spinlock_t mchdev_lock;
+
+static void ironlake_handle_rps_change(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 busy_up, busy_down, max_avg, min_avg;
-	u8 new_delay = dev_priv->cur_delay;
+	u8 new_delay;
+	unsigned long flags;
+
+	spin_lock_irqsave(&mchdev_lock, flags);
+
+	I915_WRITE16(MEMINTRSTS, I915_READ(MEMINTRSTS));
+
+	new_delay = dev_priv->cur_delay;
 
 	I915_WRITE16(MEMINTRSTS, MEMINT_EVAL_CHG);
 	busy_up = I915_READ(RCPREVBSYTUPAVG);
@@ -324,6 +334,8 @@ static void i915_handle_rps_change(struct drm_device *dev)
 	if (ironlake_set_drps(dev, new_delay))
 		dev_priv->cur_delay = new_delay;
 
+	spin_unlock_irqrestore(&mchdev_lock, flags);
+
 	return;
 }
 
@@ -335,7 +347,7 @@ static void notify_ring(struct drm_device *dev,
 	if (ring->obj == NULL)
 		return;
 
-	trace_i915_gem_request_complete(ring, ring->get_seqno(ring));
+	trace_i915_gem_request_complete(ring, ring->get_seqno(ring, false));
 
 	wake_up_all(&ring->irq_queue);
 	if (i915_enable_hangcheck) {
@@ -349,16 +361,16 @@ static void notify_ring(struct drm_device *dev,
 static void gen6_pm_rps_work(struct work_struct *work)
 {
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
-						    rps_work);
+						    rps.work);
 	u32 pm_iir, pm_imr;
 	u8 new_delay;
 
-	spin_lock_irq(&dev_priv->rps_lock);
-	pm_iir = dev_priv->pm_iir;
-	dev_priv->pm_iir = 0;
+	spin_lock_irq(&dev_priv->rps.lock);
+	pm_iir = dev_priv->rps.pm_iir;
+	dev_priv->rps.pm_iir = 0;
 	pm_imr = I915_READ(GEN6_PMIMR);
 	I915_WRITE(GEN6_PMIMR, 0);
-	spin_unlock_irq(&dev_priv->rps_lock);
+	spin_unlock_irq(&dev_priv->rps.lock);
 
 	if ((pm_iir & GEN6_PM_DEFERRED_EVENTS) == 0)
 		return;
@@ -366,9 +378,9 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	mutex_lock(&dev_priv->dev->struct_mutex);
 
 	if (pm_iir & GEN6_PM_RP_UP_THRESHOLD)
-		new_delay = dev_priv->cur_delay + 1;
+		new_delay = dev_priv->rps.cur_delay + 1;
 	else
-		new_delay = dev_priv->cur_delay - 1;
+		new_delay = dev_priv->rps.cur_delay - 1;
 
 	gen6_set_rps(dev_priv->dev, new_delay);
 
@@ -444,7 +456,7 @@ static void ivybridge_handle_parity_error(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	unsigned long flags;
 
-	if (!IS_IVYBRIDGE(dev))
+	if (!HAS_L3_GPU_CACHE(dev))
 		return;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
@@ -488,19 +500,19 @@ static void gen6_queue_rps_work(struct drm_i915_private *dev_priv,
 	 * IIR bits should never already be set because IMR should
 	 * prevent an interrupt from being shown in IIR. The warning
 	 * displays a case where we've unsafely cleared
-	 * dev_priv->pm_iir. Although missing an interrupt of the same
+	 * dev_priv->rps.pm_iir. Although missing an interrupt of the same
 	 * type is not a problem, it displays a problem in the logic.
 	 *
-	 * The mask bit in IMR is cleared by rps_work.
+	 * The mask bit in IMR is cleared by dev_priv->rps.work.
 	 */
 
-	spin_lock_irqsave(&dev_priv->rps_lock, flags);
-	dev_priv->pm_iir |= pm_iir;
-	I915_WRITE(GEN6_PMIMR, dev_priv->pm_iir);
+	spin_lock_irqsave(&dev_priv->rps.lock, flags);
+	dev_priv->rps.pm_iir |= pm_iir;
+	I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
 	POSTING_READ(GEN6_PMIMR);
-	spin_unlock_irqrestore(&dev_priv->rps_lock, flags);
+	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
 
-	queue_work(dev_priv->wq, &dev_priv->rps_work);
+	queue_work(dev_priv->wq, &dev_priv->rps.work);
 }
 
 static irqreturn_t valleyview_irq_handler(DRM_IRQ_ARGS)
@@ -793,10 +805,8 @@ static irqreturn_t ironlake_irq_handler(DRM_IRQ_ARGS)
 			ibx_irq_handler(dev, pch_iir);
 	}
 
-	if (de_iir & DE_PCU_EVENT) {
-		I915_WRITE16(MEMINTRSTS, I915_READ(MEMINTRSTS));
-		i915_handle_rps_change(dev);
-	}
+	if (IS_GEN5(dev) &&  de_iir & DE_PCU_EVENT)
+		ironlake_handle_rps_change(dev);
 
 	if (IS_GEN6(dev) && pm_iir & GEN6_PM_DEFERRED_EVENTS)
 		gen6_queue_rps_work(dev_priv, pm_iir);
@@ -949,7 +959,8 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 {
 	err->size = obj->base.size;
 	err->name = obj->base.name;
-	err->seqno = obj->last_rendering_seqno;
+	err->rseqno = obj->last_read_seqno;
+	err->wseqno = obj->last_write_seqno;
 	err->gtt_offset = obj->gtt_offset;
 	err->read_domains = obj->base.read_domains;
 	err->write_domain = obj->base.write_domain;
@@ -1039,12 +1050,12 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 	if (!ring->get_seqno)
 		return NULL;
 
-	seqno = ring->get_seqno(ring);
+	seqno = ring->get_seqno(ring, false);
 	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
 		if (obj->ring != ring)
 			continue;
 
-		if (i915_seqno_passed(seqno, obj->last_rendering_seqno))
+		if (i915_seqno_passed(seqno, obj->last_read_seqno))
 			continue;
 
 		if ((obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) == 0)
@@ -1093,7 +1104,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 
 	error->waiting[ring->id] = waitqueue_active(&ring->irq_queue);
 	error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base));
-	error->seqno[ring->id] = ring->get_seqno(ring);
+	error->seqno[ring->id] = ring->get_seqno(ring, false);
 	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);
@@ -1590,7 +1601,8 @@ ring_last_seqno(struct intel_ring_buffer *ring)
 static bool i915_hangcheck_ring_idle(struct intel_ring_buffer *ring, bool *err)
 {
 	if (list_empty(&ring->request_list) ||
-	    i915_seqno_passed(ring->get_seqno(ring), ring_last_seqno(ring))) {
+	    i915_seqno_passed(ring->get_seqno(ring, false),
+			      ring_last_seqno(ring))) {
 		/* Issue a wake-up to catch stuck h/w. */
 		if (waitqueue_active(&ring->irq_queue)) {
 			DRM_ERROR("Hangcheck timer elapsed... %s idle\n",
@@ -2647,7 +2659,7 @@ void intel_irq_init(struct drm_device *dev)
 
 	INIT_WORK(&dev_priv->hotplug_work, i915_hotplug_work_func);
 	INIT_WORK(&dev_priv->error_work, i915_error_work_func);
-	INIT_WORK(&dev_priv->rps_work, gen6_pm_rps_work);
+	INIT_WORK(&dev_priv->rps.work, gen6_pm_rps_work);
 	INIT_WORK(&dev_priv->parity_error_work, ivybridge_parity_work);
 
 	dev->driver->get_vblank_counter = i915_get_vblank_counter;

drivers/gpu/drm/i915/i915_sysfs.c

@@ -213,7 +213,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 
-	if (IS_IVYBRIDGE(dev)) {
+	if (HAS_L3_GPU_CACHE(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");

drivers/gpu/drm/i915/intel_crt.c

@@ -47,6 +47,7 @@
 struct intel_crt {
 	struct intel_encoder base;
 	bool force_hotplug_required;
+	u32 adpa_reg;
 };
 
 static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
@@ -55,6 +56,11 @@ static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
 			    struct intel_crt, base);
 }
 
+static struct intel_crt *intel_encoder_to_crt(struct intel_encoder *encoder)
+{
+	return container_of(encoder, struct intel_crt, base);
+}
+
 static void pch_crt_dpms(struct drm_encoder *encoder, int mode)
 {
 	struct drm_device *dev = encoder->dev;
@@ -145,19 +151,15 @@ static void intel_crt_mode_set(struct drm_encoder *encoder,
 
 	struct drm_device *dev = encoder->dev;
 	struct drm_crtc *crtc = encoder->crtc;
+	struct intel_crt *crt =
+		intel_encoder_to_crt(to_intel_encoder(encoder));
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int dpll_md_reg;
 	u32 adpa, dpll_md;
-	u32 adpa_reg;
 
 	dpll_md_reg = DPLL_MD(intel_crtc->pipe);
 
-	if (HAS_PCH_SPLIT(dev))
-		adpa_reg = PCH_ADPA;
-	else
-		adpa_reg = ADPA;
-
 	/*
 	 * Disable separate mode multiplier used when cloning SDVO to CRT
 	 * XXX this needs to be adjusted when we really are cloning
@@ -185,7 +187,7 @@ static void intel_crt_mode_set(struct drm_encoder *encoder,
 	if (!HAS_PCH_SPLIT(dev))
 		I915_WRITE(BCLRPAT(intel_crtc->pipe), 0);
 
-	I915_WRITE(adpa_reg, adpa);
+	I915_WRITE(crt->adpa_reg, adpa);
 }
 
 static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
@@ -658,9 +660,7 @@ void intel_crt_init(struct drm_device *dev)
 	intel_connector_attach_encoder(intel_connector, &crt->base);
 
 	crt->base.type = INTEL_OUTPUT_ANALOG;
-	crt->base.clone_mask = (1 << INTEL_SDVO_NON_TV_CLONE_BIT |
-				1 << INTEL_ANALOG_CLONE_BIT |
-				1 << INTEL_SDVO_LVDS_CLONE_BIT);
+	crt->base.cloneable = true;
 	if (IS_HASWELL(dev))
 		crt->base.crtc_mask = (1 << 0);
 	else
@@ -677,6 +677,13 @@ void intel_crt_init(struct drm_device *dev)
 	else
 		encoder_helper_funcs = &gmch_encoder_funcs;
 
+	if (HAS_PCH_SPLIT(dev))
+		crt->adpa_reg = PCH_ADPA;
+	else if (IS_VALLEYVIEW(dev))
+		crt->adpa_reg = VLV_ADPA;
+	else
+		crt->adpa_reg = ADPA;
+
 	drm_encoder_helper_add(&crt->base.base, encoder_helper_funcs);
 	drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
 

drivers/gpu/drm/i915/intel_ddi.c

@@ -250,7 +250,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	case PORT_B:
 	case PORT_C:
 	case PORT_D:
-		intel_hdmi_init(dev, DDI_BUF_CTL(port));
+		intel_hdmi_init(dev, DDI_BUF_CTL(port), port);
 		break;
 	default:
 		DRM_DEBUG_DRIVER("No handlers defined for port %d, skipping DDI initialization\n",
@@ -267,7 +267,8 @@ struct wrpll_tmds_clock {
 	u16 r2;		/* Reference divider */
 };
 
-/* Table of matching values for WRPLL clocks programming for each frequency */
+/* Table of matching values for WRPLL clocks programming for each frequency.
+ * The code assumes this table is sorted. */
 static const struct wrpll_tmds_clock wrpll_tmds_clock_table[] = {
 	{19750,	38,	25,	18},
 	{20000,	48,	32,	18},
@@ -277,7 +278,6 @@ static const struct wrpll_tmds_clock wrpll_tmds_clock_table[] = {
 	{23000,	36,	23,	15},
 	{23500,	40,	40,	23},
 	{23750,	26,	16,	14},
-	{23750,	26,	16,	14},
 	{24000,	36,	24,	15},
 	{25000,	36,	25,	15},
 	{25175,	26,	40,	33},
@@ -437,7 +437,6 @@ static const struct wrpll_tmds_clock wrpll_tmds_clock_table[] = {
 	{108000,	8,	24,	15},
 	{108108,	8,	173,	108},
 	{109000,	6,	23,	19},
-	{109000,	6,	23,	19},
 	{110000,	6,	22,	18},
 	{110013,	6,	22,	18},
 	{110250,	8,	49,	30},
@@ -614,7 +613,6 @@ static const struct wrpll_tmds_clock wrpll_tmds_clock_table[] = {
 	{218250,	4,	42,	26},
 	{218750,	4,	34,	21},
 	{219000,	4,	47,	29},
-	{219000,	4,	47,	29},
 	{220000,	4,	44,	27},
 	{220640,	4,	49,	30},
 	{220750,	4,	36,	22},
@@ -658,7 +656,7 @@ void intel_ddi_mode_set(struct drm_encoder *encoder,
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	int port = intel_hdmi->ddi_port;
 	int pipe = intel_crtc->pipe;
-	int p, n2, r2, valid=0;
+	int p, n2, r2;
 	u32 temp, i;
 
 	/* On Haswell, we need to enable the clocks and prepare DDI function to
@@ -666,26 +664,23 @@ void intel_ddi_mode_set(struct drm_encoder *encoder,
 	 */
 	DRM_DEBUG_KMS("Preparing HDMI DDI mode for Haswell on port %c, pipe %c\n", port_name(port), pipe_name(pipe));
 
-	for (i=0; i < ARRAY_SIZE(wrpll_tmds_clock_table); i++) {
-		if (crtc->mode.clock == wrpll_tmds_clock_table[i].clock) {
-			p = wrpll_tmds_clock_table[i].p;
-			n2 = wrpll_tmds_clock_table[i].n2;
-			r2 = wrpll_tmds_clock_table[i].r2;
+	for (i = 0; i < ARRAY_SIZE(wrpll_tmds_clock_table); i++)
+		if (crtc->mode.clock <= wrpll_tmds_clock_table[i].clock)
+			break;
 
-			DRM_DEBUG_KMS("WR PLL clock: found settings for %dKHz refresh rate: p=%d, n2=%d, r2=%d\n",
-					crtc->mode.clock,
-					p, n2, r2);
+	if (i == ARRAY_SIZE(wrpll_tmds_clock_table))
+		i--;
 
-			valid = 1;
-			break;
-		}
-	}
+	p = wrpll_tmds_clock_table[i].p;
+	n2 = wrpll_tmds_clock_table[i].n2;
+	r2 = wrpll_tmds_clock_table[i].r2;
 
-	if (!valid) {
-		DRM_ERROR("Unable to find WR PLL clock settings for %dKHz refresh rate\n",
-				crtc->mode.clock);
-		return;
-	}
+	if (wrpll_tmds_clock_table[i].clock != crtc->mode.clock)
+		DRM_INFO("WR PLL: using settings for %dKHz on %dKHz mode\n",
+			 wrpll_tmds_clock_table[i].clock, crtc->mode.clock);
+
+	DRM_DEBUG_KMS("WR PLL: %dKHz refresh rate with p=%d, n2=%d r2=%d\n",
+		      crtc->mode.clock, p, n2, r2);
 
 	/* Enable LCPLL if disabled */
 	temp = I915_READ(LCPLL_CTL);
@@ -723,15 +718,35 @@ void intel_ddi_mode_set(struct drm_encoder *encoder,
 	}
 
 	/* Enable PIPE_DDI_FUNC_CTL for the pipe to work in HDMI mode */
-	temp = I915_READ(DDI_FUNC_CTL(pipe));
-	temp &= ~PIPE_DDI_PORT_MASK;
-	temp &= ~PIPE_DDI_BPC_12;
-	temp |= PIPE_DDI_SELECT_PORT(port) |
-			PIPE_DDI_MODE_SELECT_HDMI |
-			((intel_crtc->bpp > 24) ?
-				PIPE_DDI_BPC_12 :
-				PIPE_DDI_BPC_8) |
-			PIPE_DDI_FUNC_ENABLE;
+	temp = PIPE_DDI_FUNC_ENABLE | PIPE_DDI_SELECT_PORT(port);
+
+	switch (intel_crtc->bpp) {
+	case 18:
+		temp |= PIPE_DDI_BPC_6;
+		break;
+	case 24:
+		temp |= PIPE_DDI_BPC_8;
+		break;
+	case 30:
+		temp |= PIPE_DDI_BPC_10;
+		break;
+	case 36:
+		temp |= PIPE_DDI_BPC_12;
+		break;
+	default:
+		WARN(1, "%d bpp unsupported by pipe DDI function\n",
+		     intel_crtc->bpp);
+	}
+
+	if (intel_hdmi->has_hdmi_sink)
+		temp |= PIPE_DDI_MODE_SELECT_HDMI;
+	else
+		temp |= PIPE_DDI_MODE_SELECT_DVI;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+		temp |= PIPE_DDI_PVSYNC;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+		temp |= PIPE_DDI_PHSYNC;
 
 	I915_WRITE(DDI_FUNC_CTL(pipe), temp);
 

drivers/gpu/drm/i915/intel_dp.c

@@ -36,42 +36,10 @@
 #include "intel_drv.h"
 #include "i915_drm.h"
 #include "i915_drv.h"
-#include "drm_dp_helper.h"
 
-#define DP_RECEIVER_CAP_SIZE	0xf
 #define DP_LINK_STATUS_SIZE	6
 #define DP_LINK_CHECK_TIMEOUT	(10 * 1000)
 
-#define DP_LINK_CONFIGURATION_SIZE	9
-
-struct intel_dp {
-	struct intel_encoder base;
-	uint32_t output_reg;
-	uint32_t DP;
-	uint8_t  link_configuration[DP_LINK_CONFIGURATION_SIZE];
-	bool has_audio;
-	enum hdmi_force_audio force_audio;
-	uint32_t color_range;
-	int dpms_mode;
-	uint8_t link_bw;
-	uint8_t lane_count;
-	uint8_t dpcd[DP_RECEIVER_CAP_SIZE];
-	struct i2c_adapter adapter;
-	struct i2c_algo_dp_aux_data algo;
-	bool is_pch_edp;
-	uint8_t	train_set[4];
-	int panel_power_up_delay;
-	int panel_power_down_delay;
-	int panel_power_cycle_delay;
-	int backlight_on_delay;
-	int backlight_off_delay;
-	struct drm_display_mode *panel_fixed_mode;  /* for eDP */
-	struct delayed_work panel_vdd_work;
-	bool want_panel_vdd;
-	struct edid *edid; /* cached EDID for eDP */
-	int edid_mode_count;
-};
-
 /**
  * is_edp - is the given port attached to an eDP panel (either CPU or PCH)
  * @intel_dp: DP struct
@@ -1668,6 +1636,45 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp))) {
+		dp_reg_value &= ~DP_LINK_TRAIN_MASK_CPT;
+
+		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		case DP_TRAINING_PATTERN_DISABLE:
+			dp_reg_value |= DP_LINK_TRAIN_OFF_CPT;
+			break;
+		case DP_TRAINING_PATTERN_1:
+			dp_reg_value |= DP_LINK_TRAIN_PAT_1_CPT;
+			break;
+		case DP_TRAINING_PATTERN_2:
+			dp_reg_value |= DP_LINK_TRAIN_PAT_2_CPT;
+			break;
+		case DP_TRAINING_PATTERN_3:
+			DRM_ERROR("DP training pattern 3 not supported\n");
+			dp_reg_value |= DP_LINK_TRAIN_PAT_2_CPT;
+			break;
+		}
+
+	} else {
+		dp_reg_value &= ~DP_LINK_TRAIN_MASK;
+
+		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		case DP_TRAINING_PATTERN_DISABLE:
+			dp_reg_value |= DP_LINK_TRAIN_OFF;
+			break;
+		case DP_TRAINING_PATTERN_1:
+			dp_reg_value |= DP_LINK_TRAIN_PAT_1;
+			break;
+		case DP_TRAINING_PATTERN_2:
+			dp_reg_value |= DP_LINK_TRAIN_PAT_2;
+			break;
+		case DP_TRAINING_PATTERN_3:
+			DRM_ERROR("DP training pattern 3 not supported\n");
+			dp_reg_value |= DP_LINK_TRAIN_PAT_2;
+			break;
+		}
+	}
+
 	I915_WRITE(intel_dp->output_reg, dp_reg_value);
 	POSTING_READ(intel_dp->output_reg);
 
@@ -1675,12 +1682,15 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 				    DP_TRAINING_PATTERN_SET,
 				    dp_train_pat);
 
-	ret = intel_dp_aux_native_write(intel_dp,
-					DP_TRAINING_LANE0_SET,
-					intel_dp->train_set,
-					intel_dp->lane_count);
-	if (ret != intel_dp->lane_count)
-		return false;
+	if ((dp_train_pat & DP_TRAINING_PATTERN_MASK) !=
+	    DP_TRAINING_PATTERN_DISABLE) {
+		ret = intel_dp_aux_native_write(intel_dp,
+						DP_TRAINING_LANE0_SET,
+						intel_dp->train_set,
+						intel_dp->lane_count);
+		if (ret != intel_dp->lane_count)
+			return false;
+	}
 
 	return true;
 }
@@ -1696,7 +1706,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	uint8_t voltage;
 	bool clock_recovery = false;
 	int voltage_tries, loop_tries;
-	u32 reg;
 	uint32_t DP = intel_dp->DP;
 
 	/*
@@ -1717,10 +1726,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 
 	DP |= DP_PORT_EN;
 
-	if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
-		DP &= ~DP_LINK_TRAIN_MASK_CPT;
-	else
-		DP &= ~DP_LINK_TRAIN_MASK;
 	memset(intel_dp->train_set, 0, 4);
 	voltage = 0xff;
 	voltage_tries = 0;
@@ -1744,12 +1749,7 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 			DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
 		}
 
-		if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
-			reg = DP | DP_LINK_TRAIN_PAT_1_CPT;
-		else
-			reg = DP | DP_LINK_TRAIN_PAT_1;
-
-		if (!intel_dp_set_link_train(intel_dp, reg,
+		if (!intel_dp_set_link_train(intel_dp, DP,
 					     DP_TRAINING_PATTERN_1 |
 					     DP_LINK_SCRAMBLING_DISABLE))
 			break;
@@ -1804,10 +1804,8 @@ static void
 intel_dp_complete_link_train(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool channel_eq = false;
 	int tries, cr_tries;
-	u32 reg;
 	uint32_t DP = intel_dp->DP;
 
 	/* channel equalization */
@@ -1836,13 +1834,8 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
 		}
 
-		if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
-			reg = DP | DP_LINK_TRAIN_PAT_2_CPT;
-		else
-			reg = DP | DP_LINK_TRAIN_PAT_2;
-
 		/* channel eq pattern */
-		if (!intel_dp_set_link_train(intel_dp, reg,
+		if (!intel_dp_set_link_train(intel_dp, DP,
 					     DP_TRAINING_PATTERN_2 |
 					     DP_LINK_SCRAMBLING_DISABLE))
 			break;
@@ -1877,15 +1870,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 		++tries;
 	}
 
-	if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
-		reg = DP | DP_LINK_TRAIN_OFF_CPT;
-	else
-		reg = DP | DP_LINK_TRAIN_OFF;
-
-	I915_WRITE(intel_dp->output_reg, reg);
-	POSTING_READ(intel_dp->output_reg);
-	intel_dp_aux_native_write_1(intel_dp,
-				    DP_TRAINING_PATTERN_SET, DP_TRAINING_PATTERN_DISABLE);
+	intel_dp_set_link_train(intel_dp, DP, DP_TRAINING_PATTERN_DISABLE);
 }
 
 static void
@@ -2441,7 +2426,7 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 }
 
 void
-intel_dp_init(struct drm_device *dev, int output_reg)
+intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_connector *connector;
@@ -2456,6 +2441,7 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 		return;
 
 	intel_dp->output_reg = output_reg;
+	intel_dp->port = port;
 	intel_dp->dpms_mode = -1;
 
 	intel_connector = kzalloc(sizeof(struct intel_connector), GFP_KERNEL);
@@ -2483,18 +2469,10 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 
-	if (output_reg == DP_B || output_reg == PCH_DP_B)
-		intel_encoder->clone_mask = (1 << INTEL_DP_B_CLONE_BIT);
-	else if (output_reg == DP_C || output_reg == PCH_DP_C)
-		intel_encoder->clone_mask = (1 << INTEL_DP_C_CLONE_BIT);
-	else if (output_reg == DP_D || output_reg == PCH_DP_D)
-		intel_encoder->clone_mask = (1 << INTEL_DP_D_CLONE_BIT);
+	intel_encoder->cloneable = false;
 
-	if (is_edp(intel_dp)) {
-		intel_encoder->clone_mask = (1 << INTEL_EDP_CLONE_BIT);
-		INIT_DELAYED_WORK(&intel_dp->panel_vdd_work,
-				  ironlake_panel_vdd_work);
-	}
+	INIT_DELAYED_WORK(&intel_dp->panel_vdd_work,
+			  ironlake_panel_vdd_work);
 
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
 
@@ -2509,28 +2487,25 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 	drm_sysfs_connector_add(connector);
 
 	/* Set up the DDC bus. */
-	switch (output_reg) {
-		case DP_A:
-			name = "DPDDC-A";
-			break;
-		case DP_B:
-		case PCH_DP_B:
-			dev_priv->hotplug_supported_mask |=
-				DPB_HOTPLUG_INT_STATUS;
-			name = "DPDDC-B";
-			break;
-		case DP_C:
-		case PCH_DP_C:
-			dev_priv->hotplug_supported_mask |=
-				DPC_HOTPLUG_INT_STATUS;
-			name = "DPDDC-C";
-			break;
-		case DP_D:
-		case PCH_DP_D:
-			dev_priv->hotplug_supported_mask |=
-				DPD_HOTPLUG_INT_STATUS;
-			name = "DPDDC-D";
-			break;
+	switch (port) {
+	case PORT_A:
+		name = "DPDDC-A";
+		break;
+	case PORT_B:
+		dev_priv->hotplug_supported_mask |= DPB_HOTPLUG_INT_STATUS;
+		name = "DPDDC-B";
+		break;
+	case PORT_C:
+		dev_priv->hotplug_supported_mask |= DPC_HOTPLUG_INT_STATUS;
+		name = "DPDDC-C";
+		break;
+	case PORT_D:
+		dev_priv->hotplug_supported_mask |= DPD_HOTPLUG_INT_STATUS;
+		name = "DPDDC-D";
+		break;
+	default:
+		WARN(1, "Invalid port %c\n", port_name(port));
+		break;
 	}
 
 	intel_dp_i2c_init(intel_dp, intel_connector, name);

drivers/gpu/drm/i915/intel_drv.h

@@ -31,6 +31,7 @@
 #include "drm_crtc.h"
 #include "drm_crtc_helper.h"
 #include "drm_fb_helper.h"
+#include "drm_dp_helper.h"
 
 #define _wait_for(COND, MS, W) ({ \
 	unsigned long timeout__ = jiffies + msecs_to_jiffies(MS);	\
@@ -90,25 +91,6 @@
 #define INTEL_OUTPUT_DISPLAYPORT 7
 #define INTEL_OUTPUT_EDP 8
 
-/* Intel Pipe Clone Bit */
-#define INTEL_HDMIB_CLONE_BIT 1
-#define INTEL_HDMIC_CLONE_BIT 2
-#define INTEL_HDMID_CLONE_BIT 3
-#define INTEL_HDMIE_CLONE_BIT 4
-#define INTEL_HDMIF_CLONE_BIT 5
-#define INTEL_SDVO_NON_TV_CLONE_BIT 6
-#define INTEL_SDVO_TV_CLONE_BIT 7
-#define INTEL_SDVO_LVDS_CLONE_BIT 8
-#define INTEL_ANALOG_CLONE_BIT 9
-#define INTEL_TV_CLONE_BIT 10
-#define INTEL_DP_B_CLONE_BIT 11
-#define INTEL_DP_C_CLONE_BIT 12
-#define INTEL_DP_D_CLONE_BIT 13
-#define INTEL_LVDS_CLONE_BIT 14
-#define INTEL_DVO_TMDS_CLONE_BIT 15
-#define INTEL_DVO_LVDS_CLONE_BIT 16
-#define INTEL_EDP_CLONE_BIT 17
-
 #define INTEL_DVO_CHIP_NONE 0
 #define INTEL_DVO_CHIP_LVDS 1
 #define INTEL_DVO_CHIP_TMDS 2
@@ -153,9 +135,13 @@ struct intel_encoder {
 	struct drm_encoder base;
 	int type;
 	bool needs_tv_clock;
+	/*
+	 * Intel hw has only one MUX where encoders could be clone, hence a
+	 * simple flag is enough to compute the possible_clones mask.
+	 */
+	bool cloneable;
 	void (*hot_plug)(struct intel_encoder *);
 	int crtc_mask;
-	int clone_mask;
 };
 
 struct intel_connector {
@@ -171,8 +157,6 @@ struct intel_crtc {
 	int dpms_mode;
 	bool active; /* is the crtc on? independent of the dpms mode */
 	bool primary_disabled; /* is the crtc obscured by a plane? */
-	bool busy; /* is scanout buffer being updated frequently? */
-	struct timer_list idle_timer;
 	bool lowfreq_avail;
 	struct intel_overlay *overlay;
 	struct intel_unpin_work *unpin_work;
@@ -311,6 +295,38 @@ struct intel_hdmi {
 			       struct drm_display_mode *adjusted_mode);
 };
 
+#define DP_RECEIVER_CAP_SIZE		0xf
+#define DP_LINK_CONFIGURATION_SIZE	9
+
+struct intel_dp {
+	struct intel_encoder base;
+	uint32_t output_reg;
+	uint32_t DP;
+	uint8_t  link_configuration[DP_LINK_CONFIGURATION_SIZE];
+	bool has_audio;
+	enum hdmi_force_audio force_audio;
+	enum port port;
+	uint32_t color_range;
+	int dpms_mode;
+	uint8_t link_bw;
+	uint8_t lane_count;
+	uint8_t dpcd[DP_RECEIVER_CAP_SIZE];
+	struct i2c_adapter adapter;
+	struct i2c_algo_dp_aux_data algo;
+	bool is_pch_edp;
+	uint8_t train_set[4];
+	int panel_power_up_delay;
+	int panel_power_down_delay;
+	int panel_power_cycle_delay;
+	int backlight_on_delay;
+	int backlight_off_delay;
+	struct drm_display_mode *panel_fixed_mode;  /* for eDP */
+	struct delayed_work panel_vdd_work;
+	bool want_panel_vdd;
+	struct edid *edid; /* cached EDID for eDP */
+	int edid_mode_count;
+};
+
 static inline struct drm_crtc *
 intel_get_crtc_for_pipe(struct drm_device *dev, int pipe)
 {
@@ -348,17 +364,21 @@ extern void intel_attach_force_audio_property(struct drm_connector *connector);
 extern void intel_attach_broadcast_rgb_property(struct drm_connector *connector);
 
 extern void intel_crt_init(struct drm_device *dev);
-extern void intel_hdmi_init(struct drm_device *dev, int sdvox_reg);
+extern void intel_hdmi_init(struct drm_device *dev,
+			    int sdvox_reg, enum port port);
 extern struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
 extern void intel_dip_infoframe_csum(struct dip_infoframe *avi_if);
 extern bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg,
 			    bool is_sdvob);
 extern void intel_dvo_init(struct drm_device *dev);
 extern void intel_tv_init(struct drm_device *dev);
-extern void intel_mark_busy(struct drm_device *dev,
-			    struct drm_i915_gem_object *obj);
+extern void intel_mark_busy(struct drm_device *dev);
+extern void intel_mark_idle(struct drm_device *dev);
+extern void intel_mark_fb_busy(struct drm_i915_gem_object *obj);
+extern void intel_mark_fb_idle(struct drm_i915_gem_object *obj);
 extern bool intel_lvds_init(struct drm_device *dev);
-extern void intel_dp_init(struct drm_device *dev, int dp_reg);
+extern void intel_dp_init(struct drm_device *dev, int output_reg,
+			  enum port port);
 void
 intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode,
 		 struct drm_display_mode *adjusted_mode);
@@ -371,8 +391,6 @@ extern int intel_plane_init(struct drm_device *dev, enum pipe pipe);
 extern void intel_flush_display_plane(struct drm_i915_private *dev_priv,
 				      enum plane plane);
 
-void intel_sanitize_pm(struct drm_device *dev);
-
 /* intel_panel.c */
 extern void intel_fixed_panel_mode(struct drm_display_mode *fixed_mode,
 				   struct drm_display_mode *adjusted_mode);

drivers/gpu/drm/i915/intel_dvo.c

@@ -37,6 +37,7 @@
 #define SIL164_ADDR	0x38
 #define CH7xxx_ADDR	0x76
 #define TFP410_ADDR	0x38
+#define NS2501_ADDR     0x38
 
 static const struct intel_dvo_device intel_dvo_devices[] = {
 	{
@@ -74,7 +75,14 @@ static const struct intel_dvo_device intel_dvo_devices[] = {
 		.slave_addr = 0x75,
 		.gpio = GMBUS_PORT_DPB,
 		.dev_ops = &ch7017_ops,
-	}
+	},
+	{
+	        .type = INTEL_DVO_CHIP_TMDS,
+		.name = "ns2501",
+		.dvo_reg = DVOC,
+		.slave_addr = NS2501_ADDR,
+		.dev_ops = &ns2501_ops,
+       }
 };
 
 struct intel_dvo {
@@ -396,17 +404,14 @@ void intel_dvo_init(struct drm_device *dev)
 		intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
 		switch (dvo->type) {
 		case INTEL_DVO_CHIP_TMDS:
-			intel_encoder->clone_mask =
-				(1 << INTEL_DVO_TMDS_CLONE_BIT) |
-				(1 << INTEL_ANALOG_CLONE_BIT);
+			intel_encoder->cloneable = true;
 			drm_connector_init(dev, connector,
 					   &intel_dvo_connector_funcs,
 					   DRM_MODE_CONNECTOR_DVII);
 			encoder_type = DRM_MODE_ENCODER_TMDS;
 			break;
 		case INTEL_DVO_CHIP_LVDS:
-			intel_encoder->clone_mask =
-				(1 << INTEL_DVO_LVDS_CLONE_BIT);
+			intel_encoder->cloneable = false;
 			drm_connector_init(dev, connector,
 					   &intel_dvo_connector_funcs,
 					   DRM_MODE_CONNECTOR_LVDS);

drivers/gpu/drm/i915/intel_hdmi.c

@@ -889,7 +889,7 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 	intel_attach_broadcast_rgb_property(connector);
 }
 
-void intel_hdmi_init(struct drm_device *dev, int sdvox_reg)
+void intel_hdmi_init(struct drm_device *dev, int sdvox_reg, enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_connector *connector;
@@ -923,48 +923,25 @@ void intel_hdmi_init(struct drm_device *dev, int sdvox_reg)
 	connector->doublescan_allowed = 0;
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
 
-	/* Set up the DDC bus. */
-	if (sdvox_reg == SDVOB) {
-		intel_encoder->clone_mask = (1 << INTEL_HDMIB_CLONE_BIT);
-		intel_hdmi->ddc_bus = GMBUS_PORT_DPB;
-		dev_priv->hotplug_supported_mask |= HDMIB_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == SDVOC) {
-		intel_encoder->clone_mask = (1 << INTEL_HDMIC_CLONE_BIT);
-		intel_hdmi->ddc_bus = GMBUS_PORT_DPC;
-		dev_priv->hotplug_supported_mask |= HDMIC_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == HDMIB) {
-		intel_encoder->clone_mask = (1 << INTEL_HDMID_CLONE_BIT);
-		intel_hdmi->ddc_bus = GMBUS_PORT_DPB;
-		dev_priv->hotplug_supported_mask |= HDMIB_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == HDMIC) {
-		intel_encoder->clone_mask = (1 << INTEL_HDMIE_CLONE_BIT);
-		intel_hdmi->ddc_bus = GMBUS_PORT_DPC;
-		dev_priv->hotplug_supported_mask |= HDMIC_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == HDMID) {
-		intel_encoder->clone_mask = (1 << INTEL_HDMIF_CLONE_BIT);
-		intel_hdmi->ddc_bus = GMBUS_PORT_DPD;
-		dev_priv->hotplug_supported_mask |= HDMID_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == DDI_BUF_CTL(PORT_B)) {
-		DRM_DEBUG_DRIVER("LPT: detected output on DDI B\n");
-		intel_encoder->clone_mask = (1 << INTEL_HDMIB_CLONE_BIT);
+	intel_encoder->cloneable = false;
+
+	intel_hdmi->ddi_port = port;
+	switch (port) {
+	case PORT_B:
 		intel_hdmi->ddc_bus = GMBUS_PORT_DPB;
-		intel_hdmi->ddi_port = PORT_B;
 		dev_priv->hotplug_supported_mask |= HDMIB_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == DDI_BUF_CTL(PORT_C)) {
-		DRM_DEBUG_DRIVER("LPT: detected output on DDI C\n");
-		intel_encoder->clone_mask = (1 << INTEL_HDMIC_CLONE_BIT);
+		break;
+	case PORT_C:
 		intel_hdmi->ddc_bus = GMBUS_PORT_DPC;
-		intel_hdmi->ddi_port = PORT_C;
 		dev_priv->hotplug_supported_mask |= HDMIC_HOTPLUG_INT_STATUS;
-	} else if (sdvox_reg == DDI_BUF_CTL(PORT_D)) {
-		DRM_DEBUG_DRIVER("LPT: detected output on DDI D\n");
-		intel_encoder->clone_mask = (1 << INTEL_HDMID_CLONE_BIT);
+		break;
+	case PORT_D:
 		intel_hdmi->ddc_bus = GMBUS_PORT_DPD;
-		intel_hdmi->ddi_port = PORT_D;
 		dev_priv->hotplug_supported_mask |= HDMID_HOTPLUG_INT_STATUS;
-	} else {
-		/* If we got an unknown sdvox_reg, things are pretty much broken
-		 * in a way that we should let the kernel know about it */
+		break;
+	case PORT_A:
+		/* Internal port only for eDP. */
+	default:
 		BUG();
 	}
 

drivers/gpu/drm/i915/intel_lvds.c

@@ -967,7 +967,7 @@ bool intel_lvds_init(struct drm_device *dev)
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_LVDS;
 
-	intel_encoder->clone_mask = (1 << INTEL_LVDS_CLONE_BIT);
+	intel_encoder->cloneable = false;
 	if (HAS_PCH_SPLIT(dev))
 		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
 	else if (IS_GEN4(dev))

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -218,11 +218,6 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 	u32 scratch_addr = pc->gtt_offset + 128;
 	int ret;
 
-	/* Force SNB workarounds for PIPE_CONTROL flushes */
-	ret = intel_emit_post_sync_nonzero_flush(ring);
-	if (ret)
-		return ret;
-
 	/* Just flush everything.  Experiments have shown that reducing the
 	 * number of bits based on the write domains has little performance
 	 * impact.
@@ -262,6 +257,20 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+static int
+gen6_render_ring_flush__wa(struct intel_ring_buffer *ring,
+			   u32 invalidate_domains, u32 flush_domains)
+{
+	int ret;
+
+	/* Force SNB workarounds for PIPE_CONTROL flushes */
+	ret = intel_emit_post_sync_nonzero_flush(ring);
+	if (ret)
+		return ret;
+
+	return gen6_render_ring_flush(ring, invalidate_domains, flush_domains);
+}
+
 static void ring_write_tail(struct intel_ring_buffer *ring,
 			    u32 value)
 {
@@ -462,7 +471,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (IS_IVYBRIDGE(dev))
+	if (HAS_L3_GPU_CACHE(dev))
 		I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
 
 	return ret;
@@ -628,26 +637,24 @@ pc_render_add_request(struct intel_ring_buffer *ring,
 }
 
 static u32
-gen6_ring_get_seqno(struct intel_ring_buffer *ring)
+gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
-	struct drm_device *dev = ring->dev;
-
 	/* Workaround to force correct ordering between irq and seqno writes on
 	 * ivb (and maybe also on snb) by reading from a CS register (like
 	 * ACTHD) before reading the status page. */
-	if (IS_GEN6(dev) || IS_GEN7(dev))
+	if (!lazy_coherency)
 		intel_ring_get_active_head(ring);
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
 
 static u32
-ring_get_seqno(struct intel_ring_buffer *ring)
+ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
 
 static u32
-pc_render_get_seqno(struct intel_ring_buffer *ring)
+pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
 	struct pipe_control *pc = ring->private;
 	return pc->cpu_page[0];
@@ -852,7 +859,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (IS_IVYBRIDGE(dev) && ring->id == RCS)
+		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~(ring->irq_enable_mask |
 						GEN6_RENDER_L3_PARITY_ERROR));
 		else
@@ -875,7 +882,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (IS_IVYBRIDGE(dev) && ring->id == RCS)
+		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
 		else
 			I915_WRITE_IMR(ring, ~0);
@@ -1010,7 +1017,6 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
-	INIT_LIST_HEAD(&ring->gpu_write_list);
 	ring->size = 32 * PAGE_SIZE;
 
 	init_waitqueue_head(&ring->irq_queue);
@@ -1380,6 +1386,8 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen >= 6) {
 		ring->add_request = gen6_add_request;
 		ring->flush = gen6_render_ring_flush;
+		if (INTEL_INFO(dev)->gen == 6)
+			ring->flush = gen6_render_ring_flush__wa;
 		ring->irq_get = gen6_ring_get_irq;
 		ring->irq_put = gen6_ring_put_irq;
 		ring->irq_enable_mask = GT_USER_INTERRUPT;
@@ -1481,7 +1489,6 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
-	INIT_LIST_HEAD(&ring->gpu_write_list);
 
 	ring->size = size;
 	ring->effective_size = ring->size;
@@ -1574,3 +1581,41 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 
 	return intel_init_ring_buffer(dev, ring);
 }
+
+int
+intel_ring_flush_all_caches(struct intel_ring_buffer *ring)
+{
+	int ret;
+
+	if (!ring->gpu_caches_dirty)
+		return 0;
+
+	ret = ring->flush(ring, 0, I915_GEM_GPU_DOMAINS);
+	if (ret)
+		return ret;
+
+	trace_i915_gem_ring_flush(ring, 0, I915_GEM_GPU_DOMAINS);
+
+	ring->gpu_caches_dirty = false;
+	return 0;
+}
+
+int
+intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring)
+{
+	uint32_t flush_domains;
+	int ret;
+
+	flush_domains = 0;
+	if (ring->gpu_caches_dirty)
+		flush_domains = I915_GEM_GPU_DOMAINS;
+
+	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+	if (ret)
+		return ret;
+
+	trace_i915_gem_ring_flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+
+	ring->gpu_caches_dirty = false;
+	return 0;
+}

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -72,7 +72,14 @@ struct  intel_ring_buffer {
 				  u32	flush_domains);
 	int		(*add_request)(struct intel_ring_buffer *ring,
 				       u32 *seqno);
-	u32		(*get_seqno)(struct intel_ring_buffer *ring);
+	/* Some chipsets are not quite as coherent as advertised and need
+	 * an expensive kick to force a true read of the up-to-date seqno.
+	 * However, the up-to-date seqno is not always required and the last
+	 * seen value is good enough. Note that the seqno will always be
+	 * monotonic, even if not coherent.
+	 */
+	u32		(*get_seqno)(struct intel_ring_buffer *ring,
+				     bool lazy_coherency);
 	int		(*dispatch_execbuffer)(struct intel_ring_buffer *ring,
 					       u32 offset, u32 length);
 	void		(*cleanup)(struct intel_ring_buffer *ring);
@@ -100,15 +107,6 @@ struct  intel_ring_buffer {
 	 */
 	struct list_head request_list;
 
-	/**
-	 * List of objects currently pending a GPU write flush.
-	 *
-	 * All elements on this list will belong to either the
-	 * active_list or flushing_list, last_rendering_seqno can
-	 * be used to differentiate between the two elements.
-	 */
-	struct list_head gpu_write_list;
-
 	/**
 	 * Do we have some not yet emitted requests outstanding?
 	 */
@@ -204,6 +202,8 @@ static inline void intel_ring_emit(struct intel_ring_buffer *ring,
 void intel_ring_advance(struct intel_ring_buffer *ring);
 
 u32 intel_ring_get_seqno(struct intel_ring_buffer *ring);
+int intel_ring_flush_all_caches(struct intel_ring_buffer *ring);
+int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring);
 
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);

drivers/gpu/drm/i915/intel_tv.c

@@ -1622,7 +1622,7 @@ intel_tv_init(struct drm_device *dev)
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
-	intel_encoder->clone_mask = (1 << INTEL_TV_CLONE_BIT);
+	intel_encoder->cloneable = false;
 	intel_encoder->base.possible_crtcs = ((1 << 0) | (1 << 1));
 	intel_encoder->base.possible_clones = (1 << INTEL_OUTPUT_TVOUT);
 	intel_tv->type = DRM_MODE_CONNECTOR_Unknown;