Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (31 commits)
  drm: integer overflow in drm_mode_dirtyfb_ioctl()
  drivers/gpu/vga/vgaarb.c: add missing kfree
  drm/radeon/kms/atom: unify i2c gpio table handling
  drm/radeon/kms: fix up gpio i2c mask bits for r4xx for real
  ttm: Don't return the bo reserved on error path
  drm/radeon/kms: add a CS ioctl flag not to rewrite tiling flags in the CS
  drm/i915: Fix inconsistent backlight level during disabled
  drm, i915: Fix memory leak in i915_gem_busy_ioctl().
  drm/i915: Use DPCD value for max DP lanes.
  drm/i915: Initiate DP link training only on the lanes we'll be using
  drm/i915: Remove trailing white space
  drm/i915: Try harder during dp pattern 1 link training
  drm/i915: Make DP prepare/commit consistent with DP dpms
  drm/i915: Let panel power sequencing hardware do its job
  drm/i915: Treat PCH eDP like DP in most places
  drm/i915: Remove link_status field from intel_dp structure
  drm/i915: Move common PCH_PP_CONTROL setup to ironlake_get_pp_control
  drm/i915: Module parameters using '-1' as default must be signed type
  drm/i915: Turn on another required clock gating bit on gen6.
  drm/i915: Turn on a required 3D clock gating bit on Sandybridge.
  ...

22 files changed, 600 insertions, 432 deletions

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 405c63b9d539..8323fc389840 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1873,6 +1873,10 @@ int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
 	}
 
 	if (num_clips && clips_ptr) {
+		if (num_clips < 0 || num_clips > DRM_MODE_FB_DIRTY_MAX_CLIPS) {
+			ret = -EINVAL;
+			goto out_err1;
+		}
 		clips = kzalloc(num_clips * sizeof(*clips), GFP_KERNEL);
 		if (!clips) {
 			ret = -ENOMEM;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 4f40f1ce1d8e..d09a6e02dc95 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -636,11 +636,16 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring;
+	int ret;
 
 	ring = &dev_priv->ring[(uintptr_t)node->info_ent->data];
 	if (ring->size == 0)
 		return 0;
 
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
 	seq_printf(m, "Ring %s:\n", ring->name);
 	seq_printf(m, "  Head :    %08x\n", I915_READ_HEAD(ring) & HEAD_ADDR);
 	seq_printf(m, "  Tail :    %08x\n", I915_READ_TAIL(ring) & TAIL_ADDR);
@@ -654,6 +659,8 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data)
 	seq_printf(m, "  Control : %08x\n", I915_READ_CTL(ring));
 	seq_printf(m, "  Start :   %08x\n", I915_READ_START(ring));
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -842,7 +849,16 @@ static int i915_rstdby_delays(struct seq_file *m, void *unused)
 	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;
-	u16 crstanddelay = I915_READ16(CRSTANDVID);
+	u16 crstanddelay;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	crstanddelay = I915_READ16(CRSTANDVID);
+
+	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "w/ctx: %d, w/o ctx: %d\n", (crstanddelay >> 8) & 0x3f, (crstanddelay & 0x3f));
 
@@ -940,7 +956,11 @@ static int i915_delayfreq_table(struct seq_file *m, void *unused)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 delayfreq;
-	int i;
+	int ret, i;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < 16; i++) {
 		delayfreq = I915_READ(PXVFREQ_BASE + i * 4);
@@ -948,6 +968,8 @@ static int i915_delayfreq_table(struct seq_file *m, void *unused)
 			   (delayfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -962,13 +984,19 @@ static int i915_inttoext_table(struct seq_file *m, void *unused)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 inttoext;
-	int i;
+	int ret, i;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	for (i = 1; i <= 32; i++) {
 		inttoext = I915_READ(INTTOEXT_BASE_ILK + i * 4);
 		seq_printf(m, "INTTOEXT%02d: 0x%08x\n", i, inttoext);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -977,9 +1005,19 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 	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;
-	u32 rgvmodectl = I915_READ(MEMMODECTL);
-	u32 rstdbyctl = I915_READ(RSTDBYCTL);
-	u16 crstandvid = I915_READ16(CRSTANDVID);
+	u32 rgvmodectl, rstdbyctl;
+	u16 crstandvid;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	rgvmodectl = I915_READ(MEMMODECTL);
+	rstdbyctl = I915_READ(RSTDBYCTL);
+	crstandvid = I915_READ16(CRSTANDVID);
+
+	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "HD boost: %s\n", (rgvmodectl & MEMMODE_BOOST_EN) ?
 		   "yes" : "no");
@@ -1167,9 +1205,16 @@ static int i915_gfxec(struct seq_file *m, void *unused)
 	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;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	seq_printf(m, "GFXEC: %ld\n", (unsigned long)I915_READ(0x112f4));
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index e9c2cfe45daa..15bfa9145d2b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -68,7 +68,7 @@ module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 MODULE_PARM_DESC(i915_enable_rc6,
 		"Enable power-saving render C-state 6 (default: true)");
 
-unsigned int i915_enable_fbc __read_mostly = -1;
+int i915_enable_fbc __read_mostly = -1;
 module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
 MODULE_PARM_DESC(i915_enable_fbc,
 		"Enable frame buffer compression for power savings "
@@ -80,7 +80,7 @@ MODULE_PARM_DESC(lvds_downclock,
 		"Use panel (LVDS/eDP) downclocking for power savings "
 		"(default: false)");
 
-unsigned int i915_panel_use_ssc __read_mostly = -1;
+int i915_panel_use_ssc __read_mostly = -1;
 module_param_named(lvds_use_ssc, i915_panel_use_ssc, int, 0600);
 MODULE_PARM_DESC(lvds_use_ssc,
 		"Use Spread Spectrum Clock with panels [LVDS/eDP] "
@@ -107,7 +107,7 @@ static struct drm_driver driver;
 extern int intel_agp_enabled;
 
 #define INTEL_VGA_DEVICE(id, info) {		\
-	.class = PCI_CLASS_DISPLAY_VGA << 8,	\
+	.class = PCI_BASE_CLASS_DISPLAY << 16,	\
 	.class_mask = 0xff0000,			\
 	.vendor = 0x8086,			\
 	.device = id,				\
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 06a37f4fd74b..4a9c1b979804 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -126,6 +126,9 @@ struct drm_i915_master_private {
 	struct _drm_i915_sarea *sarea_priv;
 };
 #define I915_FENCE_REG_NONE -1
+#define I915_MAX_NUM_FENCES 16
+/* 16 fences + sign bit for FENCE_REG_NONE */
+#define I915_MAX_NUM_FENCE_BITS 5
 
 struct drm_i915_fence_reg {
 	struct list_head lru_list;
@@ -168,7 +171,7 @@ struct drm_i915_error_state {
 	u32 instdone1;
 	u32 seqno;
 	u64 bbaddr;
-	u64 fence[16];
+	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
 	struct drm_i915_error_object {
 		int page_count;
@@ -182,7 +185,7 @@ struct drm_i915_error_state {
 		u32 gtt_offset;
 		u32 read_domains;
 		u32 write_domain;
-		s32 fence_reg:5;
+		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
 		s32 pinned:2;
 		u32 tiling:2;
 		u32 dirty:1;
@@ -375,7 +378,7 @@ typedef struct drm_i915_private {
 	struct notifier_block lid_notifier;
 
 	int crt_ddc_pin;
-	struct drm_i915_fence_reg fence_regs[16]; /* assume 965 */
+	struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */
 	int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */
 	int num_fence_regs; /* 8 on pre-965, 16 otherwise */
 
@@ -506,7 +509,7 @@ typedef struct drm_i915_private {
 	u8 saveAR[21];
 	u8 saveDACMASK;
 	u8 saveCR[37];
-	uint64_t saveFENCE[16];
+	uint64_t saveFENCE[I915_MAX_NUM_FENCES];
 	u32 saveCURACNTR;
 	u32 saveCURAPOS;
 	u32 saveCURABASE;
@@ -777,10 +780,8 @@ struct drm_i915_gem_object {
 	 * Fence register bits (if any) for this object.  Will be set
 	 * as needed when mapped into the GTT.
 	 * Protected by dev->struct_mutex.
-	 *
-	 * Size: 4 bits for 16 fences + sign (for FENCE_REG_NONE)
 	 */
-	signed int fence_reg:5;
+	signed int fence_reg:I915_MAX_NUM_FENCE_BITS;
 
 	/**
 	 * Advice: are the backing pages purgeable?
@@ -999,10 +1000,10 @@ extern int i915_panel_ignore_lid __read_mostly;
 extern unsigned int i915_powersave __read_mostly;
 extern unsigned int i915_semaphores __read_mostly;
 extern unsigned int i915_lvds_downclock __read_mostly;
-extern unsigned int i915_panel_use_ssc __read_mostly;
+extern int i915_panel_use_ssc __read_mostly;
 extern int i915_vbt_sdvo_panel_type __read_mostly;
 extern unsigned int i915_enable_rc6 __read_mostly;
-extern unsigned int i915_enable_fbc __read_mostly;
+extern int i915_enable_fbc __read_mostly;
 extern bool i915_enable_hangcheck __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d18b07adcffa..8359dc777041 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1745,7 +1745,7 @@ static void i915_gem_reset_fences(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	for (i = 0; i < 16; i++) {
+	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
 		struct drm_i915_gem_object *obj = reg->obj;
 
@@ -3512,9 +3512,11 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 			 * so emit a request to do so.
 			 */
 			request = kzalloc(sizeof(*request), GFP_KERNEL);
-			if (request)
+			if (request) {
 				ret = i915_add_request(obj->ring, NULL, request);
-			else
+				if (ret)
+					kfree(request);
+			} else
 				ret = -ENOMEM;
 		}
 
@@ -3613,7 +3615,7 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
 
-	if (IS_GEN6(dev)) {
+	if (IS_GEN6(dev) || IS_GEN7(dev)) {
 		/* On Gen6, we can have the GPU use the LLC (the CPU
 		 * cache) for about a 10% performance improvement
 		 * compared to uncached.  Graphics requests other than
@@ -3877,7 +3879,7 @@ i915_gem_load(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev_priv->mm.gtt_list);
 	for (i = 0; i < I915_NUM_RINGS; i++)
 		init_ring_lists(&dev_priv->ring[i]);
-	for (i = 0; i < 16; i++)
+	for (i = 0; i < I915_MAX_NUM_FENCES; i++)
 		INIT_LIST_HEAD(&dev_priv->fence_regs[i].lru_list);
 	INIT_DELAYED_WORK(&dev_priv->mm.retire_work,
 			  i915_gem_retire_work_handler);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 9ee2729fe5c6..b40004b55977 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -824,6 +824,7 @@ static void i915_gem_record_fences(struct drm_device *dev,
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5a09416e611f..b080cc824001 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1553,12 +1553,21 @@
  */
 #define   PP_READY		(1 << 30)
 #define   PP_SEQUENCE_NONE	(0 << 28)
-#define   PP_SEQUENCE_ON	(1 << 28)
-#define   PP_SEQUENCE_OFF	(2 << 28)
-#define   PP_SEQUENCE_MASK	0x30000000
+#define   PP_SEQUENCE_POWER_UP	(1 << 28)
+#define   PP_SEQUENCE_POWER_DOWN (2 << 28)
+#define   PP_SEQUENCE_MASK	(3 << 28)
+#define   PP_SEQUENCE_SHIFT	28
 #define   PP_CYCLE_DELAY_ACTIVE	(1 << 27)
-#define   PP_SEQUENCE_STATE_ON_IDLE (1 << 3)
 #define   PP_SEQUENCE_STATE_MASK 0x0000000f
+#define   PP_SEQUENCE_STATE_OFF_IDLE	(0x0 << 0)
+#define   PP_SEQUENCE_STATE_OFF_S0_1	(0x1 << 0)
+#define   PP_SEQUENCE_STATE_OFF_S0_2	(0x2 << 0)
+#define   PP_SEQUENCE_STATE_OFF_S0_3	(0x3 << 0)
+#define   PP_SEQUENCE_STATE_ON_IDLE	(0x8 << 0)
+#define   PP_SEQUENCE_STATE_ON_S1_0	(0x9 << 0)
+#define   PP_SEQUENCE_STATE_ON_S1_2	(0xa << 0)
+#define   PP_SEQUENCE_STATE_ON_S1_3	(0xb << 0)
+#define   PP_SEQUENCE_STATE_RESET	(0xf << 0)
 #define PP_CONTROL	0x61204
 #define   POWER_TARGET_ON	(1 << 0)
 #define PP_ON_DELAYS	0x61208
@@ -3444,6 +3453,10 @@
 #define  GT_FIFO_FREE_ENTRIES			0x120008
 #define    GT_FIFO_NUM_RESERVED_ENTRIES		20
 
+#define GEN6_UCGCTL2				0x9404
+# define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE		(1 << 12)
+# define GEN6_RCCUNIT_CLOCK_GATE_DISABLE		(1 << 11)
+
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
 #define   GEN6_FREQUENCY(x)			((x)<<25)
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index f8f602d76650..7886e4fb60e3 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -370,6 +370,7 @@ static void i915_save_modeset_reg(struct drm_device *dev)
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
@@ -404,6 +405,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev)
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->saveFENCE[i]);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 981b1f1c04d8..e77a863a3833 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2933,7 +2933,8 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 
 	/* For PCH DP, enable TRANS_DP_CTL */
 	if (HAS_PCH_CPT(dev) &&
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) {
+	    (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
+	     intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) {
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) >> 5;
 		reg = TRANS_DP_CTL(pipe);
 		temp = I915_READ(reg);
@@ -4711,7 +4712,7 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 				lvds_bpc = 6;
 
 			if (lvds_bpc < display_bpc) {
-				DRM_DEBUG_DRIVER("clamping display bpc (was %d) to LVDS (%d)\n", display_bpc, lvds_bpc);
+				DRM_DEBUG_KMS("clamping display bpc (was %d) to LVDS (%d)\n", display_bpc, lvds_bpc);
 				display_bpc = lvds_bpc;
 			}
 			continue;
@@ -4722,7 +4723,7 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			unsigned int edp_bpc = dev_priv->edp.bpp / 3;
 
 			if (edp_bpc < display_bpc) {
-				DRM_DEBUG_DRIVER("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
+				DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
 				display_bpc = edp_bpc;
 			}
 			continue;
@@ -4737,7 +4738,7 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			/* Don't use an invalid EDID bpc value */
 			if (connector->display_info.bpc &&
 			    connector->display_info.bpc < display_bpc) {
-				DRM_DEBUG_DRIVER("clamping display bpc (was %d) to EDID reported max of %d\n", display_bpc, connector->display_info.bpc);
+				DRM_DEBUG_KMS("clamping display bpc (was %d) to EDID reported max of %d\n", display_bpc, connector->display_info.bpc);
 				display_bpc = connector->display_info.bpc;
 			}
 		}
@@ -4748,10 +4749,10 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 		 */
 		if (intel_encoder->type == INTEL_OUTPUT_HDMI) {
 			if (display_bpc > 8 && display_bpc < 12) {
-				DRM_DEBUG_DRIVER("forcing bpc to 12 for HDMI\n");
+				DRM_DEBUG_KMS("forcing bpc to 12 for HDMI\n");
 				display_bpc = 12;
 			} else {
-				DRM_DEBUG_DRIVER("forcing bpc to 8 for HDMI\n");
+				DRM_DEBUG_KMS("forcing bpc to 8 for HDMI\n");
 				display_bpc = 8;
 			}
 		}
@@ -4789,8 +4790,8 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 
 	display_bpc = min(display_bpc, bpc);
 
-	DRM_DEBUG_DRIVER("setting pipe bpc to %d (max display bpc %d)\n",
-			 bpc, display_bpc);
+	DRM_DEBUG_KMS("setting pipe bpc to %d (max display bpc %d)\n",
+		      bpc, display_bpc);
 
 	*pipe_bpp = display_bpc * 3;
 
@@ -5671,7 +5672,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	pipeconf &= ~PIPECONF_DITHER_TYPE_MASK;
 	if ((is_lvds && dev_priv->lvds_dither) || dither) {
 		pipeconf |= PIPECONF_DITHER_EN;
-		pipeconf |= PIPECONF_DITHER_TYPE_ST1;
+		pipeconf |= PIPECONF_DITHER_TYPE_SP;
 	}
 	if (is_dp || intel_encoder_is_pch_edp(&has_edp_encoder->base)) {
 		intel_dp_set_m_n(crtc, mode, adjusted_mode);
@@ -8148,6 +8149,20 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(WM2_LP_ILK, 0);
 	I915_WRITE(WM1_LP_ILK, 0);
 
+	/* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
+	 * gating disable must be set.  Failure to set it results in
+	 * flickering pixels due to Z write ordering failures after
+	 * some amount of runtime in the Mesa "fire" demo, and Unigine
+	 * Sanctuary and Tropics, and apparently anything else with
+	 * alpha test or pixel discard.
+	 *
+	 * According to the spec, bit 11 (RCCUNIT) must also be set,
+	 * but we didn't debug actual testcases to find it out.
+	 */
+	I915_WRITE(GEN6_UCGCTL2,
+		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
+		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
+
 	/*
 	 * According to the spec the following bits should be
 	 * set in order to enable memory self-refresh and fbc:
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 09b318b0227f..4d0358fad937 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -59,7 +59,6 @@ struct intel_dp {
 	struct i2c_algo_dp_aux_data algo;
 	bool is_pch_edp;
 	uint8_t	train_set[4];
-	uint8_t link_status[DP_LINK_STATUS_SIZE];
 	int panel_power_up_delay;
 	int panel_power_down_delay;
 	int panel_power_cycle_delay;
@@ -68,7 +67,6 @@ struct intel_dp {
 	struct drm_display_mode *panel_fixed_mode;  /* for eDP */
 	struct delayed_work panel_vdd_work;
 	bool want_panel_vdd;
-	unsigned long panel_off_jiffies;
 };
 
 /**
@@ -157,16 +155,12 @@ intel_edp_link_config(struct intel_encoder *intel_encoder,
 static int
 intel_dp_max_lane_count(struct intel_dp *intel_dp)
 {
-	int max_lane_count = 4;
-
-	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11) {
-		max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
-		switch (max_lane_count) {
-		case 1: case 2: case 4:
-			break;
-		default:
-			max_lane_count = 4;
-		}
+	int max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
+	switch (max_lane_count) {
+	case 1: case 2: case 4:
+		break;
+	default:
+		max_lane_count = 4;
 	}
 	return max_lane_count;
 }
@@ -768,12 +762,11 @@ intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode,
 			continue;
 
 		intel_dp = enc_to_intel_dp(encoder);
-		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT) {
+		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT ||
+		    intel_dp->base.type == INTEL_OUTPUT_EDP)
+		{
 			lane_count = intel_dp->lane_count;
 			break;
-		} else if (is_edp(intel_dp)) {
-			lane_count = dev_priv->edp.lanes;
-			break;
 		}
 	}
 
@@ -810,6 +803,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		  struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_crtc *crtc = intel_dp->base.base.crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -822,18 +816,31 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 			ironlake_edp_pll_off(encoder);
 	}
 
-	intel_dp->DP = DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
-	intel_dp->DP |= intel_dp->color_range;
+	/*
+	 * There are three kinds of DP registers:
+	 *
+	 * 	IBX PCH
+	 * 	CPU
+	 * 	CPT PCH
+	 *
+	 * IBX PCH and CPU are the same for almost everything,
+	 * except that the CPU DP PLL is configured in this
+	 * register
+	 *
+	 * CPT PCH is quite different, having many bits moved
+	 * to the TRANS_DP_CTL register instead. That
+	 * configuration happens (oddly) in ironlake_pch_enable
+	 */
 
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
-		intel_dp->DP |= DP_SYNC_HS_HIGH;
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
-		intel_dp->DP |= DP_SYNC_VS_HIGH;
+	/* Preserve the BIOS-computed detected bit. This is
+	 * supposed to be read-only.
+	 */
+	intel_dp->DP = I915_READ(intel_dp->output_reg) & DP_DETECTED;
+	intel_dp->DP |=  DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
 
-	if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
-		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
-	else
-		intel_dp->DP |= DP_LINK_TRAIN_OFF;
+	/* Handle DP bits in common between all three register formats */
+
+	intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
 
 	switch (intel_dp->lane_count) {
 	case 1:
@@ -852,59 +859,106 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
 		intel_write_eld(encoder, adjusted_mode);
 	}
-
 	memset(intel_dp->link_configuration, 0, DP_LINK_CONFIGURATION_SIZE);
 	intel_dp->link_configuration[0] = intel_dp->link_bw;
 	intel_dp->link_configuration[1] = intel_dp->lane_count;
 	intel_dp->link_configuration[8] = DP_SET_ANSI_8B10B;
-
 	/*
 	 * Check for DPCD version > 1.1 and enhanced framing support
 	 */
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
 	    (intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP)) {
 		intel_dp->link_configuration[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
-		intel_dp->DP |= DP_ENHANCED_FRAMING;
 	}
 
-	/* CPT DP's pipe select is decided in TRANS_DP_CTL */
-	if (intel_crtc->pipe == 1 && !HAS_PCH_CPT(dev))
-		intel_dp->DP |= DP_PIPEB_SELECT;
+	/* Split out the IBX/CPU vs CPT settings */
 
-	if (is_cpu_edp(intel_dp)) {
-		/* don't miss out required setting for eDP */
-		intel_dp->DP |= DP_PLL_ENABLE;
-		if (adjusted_mode->clock < 200000)
-			intel_dp->DP |= DP_PLL_FREQ_160MHZ;
-		else
-			intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+	if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
+		intel_dp->DP |= intel_dp->color_range;
+
+		if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+			intel_dp->DP |= DP_SYNC_HS_HIGH;
+		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+			intel_dp->DP |= DP_SYNC_VS_HIGH;
+		intel_dp->DP |= DP_LINK_TRAIN_OFF;
+
+		if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
+			intel_dp->DP |= DP_ENHANCED_FRAMING;
+
+		if (intel_crtc->pipe == 1)
+			intel_dp->DP |= DP_PIPEB_SELECT;
+
+		if (is_cpu_edp(intel_dp)) {
+			/* don't miss out required setting for eDP */
+			intel_dp->DP |= DP_PLL_ENABLE;
+			if (adjusted_mode->clock < 200000)
+				intel_dp->DP |= DP_PLL_FREQ_160MHZ;
+			else
+				intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+		}
+	} else {
+		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
 	}
 }
 
-static void ironlake_wait_panel_off(struct intel_dp *intel_dp)
+#define IDLE_ON_MASK		(PP_ON | 0 	  | PP_SEQUENCE_MASK | 0                     | PP_SEQUENCE_STATE_MASK)
+#define IDLE_ON_VALUE   	(PP_ON | 0 	  | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_ON_IDLE)
+
+#define IDLE_OFF_MASK		(PP_ON | 0        | PP_SEQUENCE_MASK | 0                     | PP_SEQUENCE_STATE_MASK)
+#define IDLE_OFF_VALUE		(0     | 0        | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_OFF_IDLE)
+
+#define IDLE_CYCLE_MASK		(PP_ON | 0        | PP_SEQUENCE_MASK | PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK)
+#define IDLE_CYCLE_VALUE	(0     | 0        | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_OFF_IDLE)
+
+static void ironlake_wait_panel_status(struct intel_dp *intel_dp,
+				       u32 mask,
+				       u32 value)
 {
-	unsigned long	off_time;
-	unsigned long	delay;
+	struct drm_device *dev = intel_dp->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	DRM_DEBUG_KMS("Wait for panel power off time\n");
+	DRM_DEBUG_KMS("mask %08x value %08x status %08x control %08x\n",
+		      mask, value,
+		      I915_READ(PCH_PP_STATUS),
+		      I915_READ(PCH_PP_CONTROL));
 
-	if (ironlake_edp_have_panel_power(intel_dp) ||
-	    ironlake_edp_have_panel_vdd(intel_dp))
-	{
-		DRM_DEBUG_KMS("Panel still on, no delay needed\n");
-		return;
+	if (_wait_for((I915_READ(PCH_PP_STATUS) & mask) == value, 5000, 10)) {
+		DRM_ERROR("Panel status timeout: status %08x control %08x\n",
+			  I915_READ(PCH_PP_STATUS),
+			  I915_READ(PCH_PP_CONTROL));
 	}
+}
 
-	off_time = intel_dp->panel_off_jiffies + msecs_to_jiffies(intel_dp->panel_power_down_delay);
-	if (time_after(jiffies, off_time)) {
-		DRM_DEBUG_KMS("Time already passed");
-		return;
-	}
-	delay = jiffies_to_msecs(off_time - jiffies);
-	if (delay > intel_dp->panel_power_down_delay)
-		delay = intel_dp->panel_power_down_delay;
-	DRM_DEBUG_KMS("Waiting an additional %ld ms\n", delay);
-	msleep(delay);
+static void ironlake_wait_panel_on(struct intel_dp *intel_dp)
+{
+	DRM_DEBUG_KMS("Wait for panel power on\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_ON_MASK, IDLE_ON_VALUE);
+}
+
+static void ironlake_wait_panel_off(struct intel_dp *intel_dp)
+{
+	DRM_DEBUG_KMS("Wait for panel power off time\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_OFF_MASK, IDLE_OFF_VALUE);
+}
+
+static void ironlake_wait_panel_power_cycle(struct intel_dp *intel_dp)
+{
+	DRM_DEBUG_KMS("Wait for panel power cycle\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_CYCLE_MASK, IDLE_CYCLE_VALUE);
+}
+
+
+/* Read the current pp_control value, unlocking the register if it
+ * is locked
+ */
+
+static  u32 ironlake_get_pp_control(struct drm_i915_private *dev_priv)
+{
+	u32	control = I915_READ(PCH_PP_CONTROL);
+
+	control &= ~PANEL_UNLOCK_MASK;
+	control |= PANEL_UNLOCK_REGS;
+	return control;
 }
 
 static void ironlake_edp_panel_vdd_on(struct intel_dp *intel_dp)
@@ -921,15 +975,16 @@ static void ironlake_edp_panel_vdd_on(struct intel_dp *intel_dp)
 	     "eDP VDD already requested on\n");
 
 	intel_dp->want_panel_vdd = true;
+
 	if (ironlake_edp_have_panel_vdd(intel_dp)) {
 		DRM_DEBUG_KMS("eDP VDD already on\n");
 		return;
 	}
 
-	ironlake_wait_panel_off(intel_dp);
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	if (!ironlake_edp_have_panel_power(intel_dp))
+		ironlake_wait_panel_power_cycle(intel_dp);
+
+	pp = ironlake_get_pp_control(dev_priv);
 	pp |= EDP_FORCE_VDD;
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
@@ -952,9 +1007,7 @@ static void ironlake_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	u32 pp;
 
 	if (!intel_dp->want_panel_vdd && ironlake_edp_have_panel_vdd(intel_dp)) {
-		pp = I915_READ(PCH_PP_CONTROL);
-		pp &= ~PANEL_UNLOCK_MASK;
-		pp |= PANEL_UNLOCK_REGS;
+		pp = ironlake_get_pp_control(dev_priv);
 		pp &= ~EDP_FORCE_VDD;
 		I915_WRITE(PCH_PP_CONTROL, pp);
 		POSTING_READ(PCH_PP_CONTROL);
@@ -962,7 +1015,8 @@ static void ironlake_panel_vdd_off_sync(struct intel_dp *intel_dp)
 		/* Make sure sequencer is idle before allowing subsequent activity */
 		DRM_DEBUG_KMS("PCH_PP_STATUS: 0x%08x PCH_PP_CONTROL: 0x%08x\n",
 			      I915_READ(PCH_PP_STATUS), I915_READ(PCH_PP_CONTROL));
-		intel_dp->panel_off_jiffies = jiffies;
+
+		msleep(intel_dp->panel_power_down_delay);
 	}
 }
 
@@ -972,9 +1026,9 @@ static void ironlake_panel_vdd_work(struct work_struct *__work)
 						 struct intel_dp, panel_vdd_work);
 	struct drm_device *dev = intel_dp->base.base.dev;
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&dev->mode_config.mutex);
 	ironlake_panel_vdd_off_sync(intel_dp);
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev->mode_config.mutex);
 }
 
 static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
@@ -984,7 +1038,7 @@ static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 
 	DRM_DEBUG_KMS("Turn eDP VDD off %d\n", intel_dp->want_panel_vdd);
 	WARN(!intel_dp->want_panel_vdd, "eDP VDD not forced on");
-	
+
 	intel_dp->want_panel_vdd = false;
 
 	if (sync) {
@@ -1000,23 +1054,25 @@ static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 	}
 }
 
-/* Returns true if the panel was already on when called */
 static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 pp, idle_on_mask = PP_ON | PP_SEQUENCE_STATE_ON_IDLE;
+	u32 pp;
 
 	if (!is_edp(intel_dp))
 		return;
-	if (ironlake_edp_have_panel_power(intel_dp))
+
+	DRM_DEBUG_KMS("Turn eDP power on\n");
+
+	if (ironlake_edp_have_panel_power(intel_dp)) {
+		DRM_DEBUG_KMS("eDP power already on\n");
 		return;
+	}
 
-	ironlake_wait_panel_off(intel_dp);
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	ironlake_wait_panel_power_cycle(intel_dp);
 
+	pp = ironlake_get_pp_control(dev_priv);
 	if (IS_GEN5(dev)) {
 		/* ILK workaround: disable reset around power sequence */
 		pp &= ~PANEL_POWER_RESET;
@@ -1025,13 +1081,13 @@ static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
 	}
 
 	pp |= POWER_TARGET_ON;
+	if (!IS_GEN5(dev))
+		pp |= PANEL_POWER_RESET;
+
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
 
-	if (wait_for((I915_READ(PCH_PP_STATUS) & idle_on_mask) == idle_on_mask,
-		     5000))
-		DRM_ERROR("panel on wait timed out: 0x%08x\n",
-			  I915_READ(PCH_PP_STATUS));
+	ironlake_wait_panel_on(intel_dp);
 
 	if (IS_GEN5(dev)) {
 		pp |= PANEL_POWER_RESET; /* restore panel reset bit */
@@ -1040,46 +1096,25 @@ static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
 	}
 }
 
-static void ironlake_edp_panel_off(struct drm_encoder *encoder)
+static void ironlake_edp_panel_off(struct intel_dp *intel_dp)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = intel_dp->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 pp, idle_off_mask = PP_ON | PP_SEQUENCE_MASK |
-		PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK;
+	u32 pp;
 
 	if (!is_edp(intel_dp))
 		return;
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
 
-	if (IS_GEN5(dev)) {
-		/* ILK workaround: disable reset around power sequence */
-		pp &= ~PANEL_POWER_RESET;
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-	}
+	DRM_DEBUG_KMS("Turn eDP power off\n");
 
-	intel_dp->panel_off_jiffies = jiffies;
+	WARN(intel_dp->want_panel_vdd, "Cannot turn power off while VDD is on\n");
 
-	if (IS_GEN5(dev)) {
-		pp &= ~POWER_TARGET_ON;
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-		pp &= ~POWER_TARGET_ON;
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-		msleep(intel_dp->panel_power_cycle_delay);
-
-		if (wait_for((I915_READ(PCH_PP_STATUS) & idle_off_mask) == 0, 5000))
-			DRM_ERROR("panel off wait timed out: 0x%08x\n",
-				  I915_READ(PCH_PP_STATUS));
+	pp = ironlake_get_pp_control(dev_priv);
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	I915_WRITE(PCH_PP_CONTROL, pp);
+	POSTING_READ(PCH_PP_CONTROL);
 
-		pp |= PANEL_POWER_RESET; /* restore panel reset bit */
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-	}
+	ironlake_wait_panel_off(intel_dp);
 }
 
 static void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1099,9 +1134,7 @@ static void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
 	 * allowing it to appear.
 	 */
 	msleep(intel_dp->backlight_on_delay);
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	pp = ironlake_get_pp_control(dev_priv);
 	pp |= EDP_BLC_ENABLE;
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
@@ -1117,9 +1150,7 @@ static void ironlake_edp_backlight_off(struct intel_dp *intel_dp)
 		return;
 
 	DRM_DEBUG_KMS("\n");
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	pp = ironlake_get_pp_control(dev_priv);
 	pp &= ~EDP_BLC_ENABLE;
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
@@ -1187,17 +1218,18 @@ static void intel_dp_prepare(struct drm_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
+	ironlake_edp_backlight_off(intel_dp);
+	ironlake_edp_panel_off(intel_dp);
+
 	/* Wake up the sink first */
 	ironlake_edp_panel_vdd_on(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+	intel_dp_link_down(intel_dp);
 	ironlake_edp_panel_vdd_off(intel_dp, false);
 
 	/* Make sure the panel is off before trying to
 	 * change the mode
 	 */
-	ironlake_edp_backlight_off(intel_dp);
-	intel_dp_link_down(intel_dp);
-	ironlake_edp_panel_off(encoder);
 }
 
 static void intel_dp_commit(struct drm_encoder *encoder)
@@ -1211,7 +1243,6 @@ static void intel_dp_commit(struct drm_encoder *encoder)
 	intel_dp_start_link_train(intel_dp);
 	ironlake_edp_panel_on(intel_dp);
 	ironlake_edp_panel_vdd_off(intel_dp, true);
-
 	intel_dp_complete_link_train(intel_dp);
 	ironlake_edp_backlight_on(intel_dp);
 
@@ -1230,16 +1261,20 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 	uint32_t dp_reg = I915_READ(intel_dp->output_reg);
 
 	if (mode != DRM_MODE_DPMS_ON) {
+		ironlake_edp_backlight_off(intel_dp);
+		ironlake_edp_panel_off(intel_dp);
+
 		ironlake_edp_panel_vdd_on(intel_dp);
-		if (is_edp(intel_dp))
-			ironlake_edp_backlight_off(intel_dp);
 		intel_dp_sink_dpms(intel_dp, mode);
 		intel_dp_link_down(intel_dp);
-		ironlake_edp_panel_off(encoder);
-		if (is_edp(intel_dp) && !is_pch_edp(intel_dp))
-			ironlake_edp_pll_off(encoder);
 		ironlake_edp_panel_vdd_off(intel_dp, false);
+
+		if (is_cpu_edp(intel_dp))
+			ironlake_edp_pll_off(encoder);
 	} else {
+		if (is_cpu_edp(intel_dp))
+			ironlake_edp_pll_on(encoder);
+
 		ironlake_edp_panel_vdd_on(intel_dp);
 		intel_dp_sink_dpms(intel_dp, mode);
 		if (!(dp_reg & DP_PORT_EN)) {
@@ -1247,7 +1282,6 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 			ironlake_edp_panel_on(intel_dp);
 			ironlake_edp_panel_vdd_off(intel_dp, true);
 			intel_dp_complete_link_train(intel_dp);
-			ironlake_edp_backlight_on(intel_dp);
 		} else
 			ironlake_edp_panel_vdd_off(intel_dp, false);
 		ironlake_edp_backlight_on(intel_dp);
@@ -1285,11 +1319,11 @@ intel_dp_aux_native_read_retry(struct intel_dp *intel_dp, uint16_t address,
  * link status information
  */
 static bool
-intel_dp_get_link_status(struct intel_dp *intel_dp)
+intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
 	return intel_dp_aux_native_read_retry(intel_dp,
 					      DP_LANE0_1_STATUS,
-					      intel_dp->link_status,
+					      link_status,
 					      DP_LINK_STATUS_SIZE);
 }
 
@@ -1301,27 +1335,25 @@ intel_dp_link_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
 }
 
 static uint8_t
-intel_get_adjust_request_voltage(uint8_t link_status[DP_LINK_STATUS_SIZE],
+intel_get_adjust_request_voltage(uint8_t adjust_request[2],
 				 int lane)
 {
-	int	    i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
 	int	    s = ((lane & 1) ?
 			 DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT :
 			 DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT);
-	uint8_t l = intel_dp_link_status(link_status, i);
+	uint8_t l = adjust_request[lane>>1];
 
 	return ((l >> s) & 3) << DP_TRAIN_VOLTAGE_SWING_SHIFT;
 }
 
 static uint8_t
-intel_get_adjust_request_pre_emphasis(uint8_t link_status[DP_LINK_STATUS_SIZE],
+intel_get_adjust_request_pre_emphasis(uint8_t adjust_request[2],
 				      int lane)
 {
-	int	    i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
 	int	    s = ((lane & 1) ?
 			 DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT :
 			 DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT);
-	uint8_t l = intel_dp_link_status(link_status, i);
+	uint8_t l = adjust_request[lane>>1];
 
 	return ((l >> s) & 3) << DP_TRAIN_PRE_EMPHASIS_SHIFT;
 }
@@ -1344,6 +1376,7 @@ static char	*link_train_names[] = {
  * a maximum voltage of 800mV and a maximum pre-emphasis of 6dB
  */
 #define I830_DP_VOLTAGE_MAX	    DP_TRAIN_VOLTAGE_SWING_800
+#define I830_DP_VOLTAGE_MAX_CPT	    DP_TRAIN_VOLTAGE_SWING_1200
 
 static uint8_t
 intel_dp_pre_emphasis_max(uint8_t voltage_swing)
@@ -1362,15 +1395,18 @@ intel_dp_pre_emphasis_max(uint8_t voltage_swing)
 }
 
 static void
-intel_get_adjust_train(struct intel_dp *intel_dp)
+intel_get_adjust_train(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
+	struct drm_device *dev = intel_dp->base.base.dev;
 	uint8_t v = 0;
 	uint8_t p = 0;
 	int lane;
+	uint8_t	*adjust_request = link_status + (DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS);
+	int voltage_max;
 
 	for (lane = 0; lane < intel_dp->lane_count; lane++) {
-		uint8_t this_v = intel_get_adjust_request_voltage(intel_dp->link_status, lane);
-		uint8_t this_p = intel_get_adjust_request_pre_emphasis(intel_dp->link_status, lane);
+		uint8_t this_v = intel_get_adjust_request_voltage(adjust_request, lane);
+		uint8_t this_p = intel_get_adjust_request_pre_emphasis(adjust_request, lane);
 
 		if (this_v > v)
 			v = this_v;
@@ -1378,8 +1414,12 @@ intel_get_adjust_train(struct intel_dp *intel_dp)
 			p = this_p;
 	}
 
-	if (v >= I830_DP_VOLTAGE_MAX)
-		v = I830_DP_VOLTAGE_MAX | DP_TRAIN_MAX_SWING_REACHED;
+	if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+		voltage_max = I830_DP_VOLTAGE_MAX_CPT;
+	else
+		voltage_max = I830_DP_VOLTAGE_MAX;
+	if (v >= voltage_max)
+		v = voltage_max | DP_TRAIN_MAX_SWING_REACHED;
 
 	if (p >= intel_dp_pre_emphasis_max(v))
 		p = intel_dp_pre_emphasis_max(v) | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
@@ -1389,7 +1429,7 @@ intel_get_adjust_train(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-intel_dp_signal_levels(uint8_t train_set, int lane_count)
+intel_dp_signal_levels(uint8_t train_set)
 {
 	uint32_t	signal_levels = 0;
 
@@ -1458,9 +1498,8 @@ static uint8_t
 intel_get_lane_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
 		      int lane)
 {
-	int i = DP_LANE0_1_STATUS + (lane >> 1);
 	int s = (lane & 1) * 4;
-	uint8_t l = intel_dp_link_status(link_status, i);
+	uint8_t l = link_status[lane>>1];
 
 	return (l >> s) & 0xf;
 }
@@ -1485,18 +1524,18 @@ intel_clock_recovery_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_count
 			 DP_LANE_CHANNEL_EQ_DONE|\
 			 DP_LANE_SYMBOL_LOCKED)
 static bool
-intel_channel_eq_ok(struct intel_dp *intel_dp)
+intel_channel_eq_ok(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
 	uint8_t lane_align;
 	uint8_t lane_status;
 	int lane;
 
-	lane_align = intel_dp_link_status(intel_dp->link_status,
+	lane_align = intel_dp_link_status(link_status,
 					  DP_LANE_ALIGN_STATUS_UPDATED);
 	if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0)
 		return false;
 	for (lane = 0; lane < intel_dp->lane_count; lane++) {
-		lane_status = intel_get_lane_status(intel_dp->link_status, lane);
+		lane_status = intel_get_lane_status(link_status, lane);
 		if ((lane_status & CHANNEL_EQ_BITS) != CHANNEL_EQ_BITS)
 			return false;
 	}
@@ -1521,8 +1560,9 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 
 	ret = intel_dp_aux_native_write(intel_dp,
 					DP_TRAINING_LANE0_SET,
-					intel_dp->train_set, 4);
-	if (ret != 4)
+					intel_dp->train_set,
+					intel_dp->lane_count);
+	if (ret != intel_dp->lane_count)
 		return false;
 
 	return true;
@@ -1538,7 +1578,7 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	int i;
 	uint8_t voltage;
 	bool clock_recovery = false;
-	int tries;
+	int voltage_tries, loop_tries;
 	u32 reg;
 	uint32_t DP = intel_dp->DP;
 
@@ -1565,16 +1605,20 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		DP &= ~DP_LINK_TRAIN_MASK;
 	memset(intel_dp->train_set, 0, 4);
 	voltage = 0xff;
-	tries = 0;
+	voltage_tries = 0;
+	loop_tries = 0;
 	clock_recovery = false;
 	for (;;) {
 		/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
+		uint8_t	    link_status[DP_LINK_STATUS_SIZE];
 		uint32_t    signal_levels;
-		if (IS_GEN6(dev) && is_edp(intel_dp)) {
+
+		if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
 			signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
 			DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
 		} else {
-			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0], intel_dp->lane_count);
+			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0]);
+			DRM_DEBUG_KMS("training pattern 1 signal levels %08x\n", signal_levels);
 			DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
 		}
 
@@ -1590,10 +1634,13 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		/* Set training pattern 1 */
 
 		udelay(100);
-		if (!intel_dp_get_link_status(intel_dp))
+		if (!intel_dp_get_link_status(intel_dp, link_status)) {
+			DRM_ERROR("failed to get link status\n");
 			break;
+		}
 
-		if (intel_clock_recovery_ok(intel_dp->link_status, intel_dp->lane_count)) {
+		if (intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
+			DRM_DEBUG_KMS("clock recovery OK\n");
 			clock_recovery = true;
 			break;
 		}
@@ -1602,20 +1649,30 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		for (i = 0; i < intel_dp->lane_count; i++)
 			if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0)
 				break;
-		if (i == intel_dp->lane_count)
-			break;
+		if (i == intel_dp->lane_count) {
+			++loop_tries;
+			if (loop_tries == 5) {
+				DRM_DEBUG_KMS("too many full retries, give up\n");
+				break;
+			}
+			memset(intel_dp->train_set, 0, 4);
+			voltage_tries = 0;
+			continue;
+		}
 
 		/* Check to see if we've tried the same voltage 5 times */
 		if ((intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK) == voltage) {
-			++tries;
-			if (tries == 5)
+			++voltage_tries;
+			if (voltage_tries == 5) {
+				DRM_DEBUG_KMS("too many voltage retries, give up\n");
 				break;
+			}
 		} else
-			tries = 0;
+			voltage_tries = 0;
 		voltage = intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK;
 
 		/* Compute new intel_dp->train_set as requested by target */
-		intel_get_adjust_train(intel_dp);
+		intel_get_adjust_train(intel_dp, link_status);
 	}
 
 	intel_dp->DP = DP;
@@ -1638,6 +1695,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 	for (;;) {
 		/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
 		uint32_t    signal_levels;
+		uint8_t	    link_status[DP_LINK_STATUS_SIZE];
 
 		if (cr_tries > 5) {
 			DRM_ERROR("failed to train DP, aborting\n");
@@ -1645,11 +1703,11 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			break;
 		}
 
-		if (IS_GEN6(dev) && is_edp(intel_dp)) {
+		if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
 			signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
 			DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
 		} else {
-			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0], intel_dp->lane_count);
+			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0]);
 			DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
 		}
 
@@ -1665,17 +1723,17 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			break;
 
 		udelay(400);
-		if (!intel_dp_get_link_status(intel_dp))
+		if (!intel_dp_get_link_status(intel_dp, link_status))
 			break;
 
 		/* Make sure clock is still ok */
-		if (!intel_clock_recovery_ok(intel_dp->link_status, intel_dp->lane_count)) {
+		if (!intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
 			intel_dp_start_link_train(intel_dp);
 			cr_tries++;
 			continue;
 		}
 
-		if (intel_channel_eq_ok(intel_dp)) {
+		if (intel_channel_eq_ok(intel_dp, link_status)) {
 			channel_eq = true;
 			break;
 		}
@@ -1690,7 +1748,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 		}
 
 		/* Compute new intel_dp->train_set as requested by target */
-		intel_get_adjust_train(intel_dp);
+		intel_get_adjust_train(intel_dp, link_status);
 		++tries;
 	}
 
@@ -1735,8 +1793,12 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 
 	msleep(17);
 
-	if (is_edp(intel_dp))
-		DP |= DP_LINK_TRAIN_OFF;
+	if (is_edp(intel_dp)) {
+		if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+			DP |= DP_LINK_TRAIN_OFF_CPT;
+		else
+			DP |= DP_LINK_TRAIN_OFF;
+	}
 
 	if (!HAS_PCH_CPT(dev) &&
 	    I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
@@ -1822,6 +1884,7 @@ static void
 intel_dp_check_link_status(struct intel_dp *intel_dp)
 {
 	u8 sink_irq_vector;
+	u8 link_status[DP_LINK_STATUS_SIZE];
 
 	if (intel_dp->dpms_mode != DRM_MODE_DPMS_ON)
 		return;
@@ -1830,7 +1893,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 		return;
 
 	/* Try to read receiver status if the link appears to be up */
-	if (!intel_dp_get_link_status(intel_dp)) {
+	if (!intel_dp_get_link_status(intel_dp, link_status)) {
 		intel_dp_link_down(intel_dp);
 		return;
 	}
@@ -1855,7 +1918,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
-	if (!intel_channel_eq_ok(intel_dp)) {
+	if (!intel_channel_eq_ok(intel_dp, link_status)) {
 		DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n",
 			      drm_get_encoder_name(&intel_dp->base.base));
 		intel_dp_start_link_train(intel_dp);
@@ -2179,7 +2242,8 @@ intel_trans_dp_port_sel(struct drm_crtc *crtc)
 			continue;
 
 		intel_dp = enc_to_intel_dp(encoder);
-		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT)
+		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT ||
+		    intel_dp->base.type == INTEL_OUTPUT_EDP)
 			return intel_dp->output_reg;
 	}
 
@@ -2321,7 +2385,7 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 
 		cur.t8 = (pp_on & PANEL_LIGHT_ON_DELAY_MASK) >>
 			PANEL_LIGHT_ON_DELAY_SHIFT;
-		
+
 		cur.t9 = (pp_off & PANEL_LIGHT_OFF_DELAY_MASK) >>
 			PANEL_LIGHT_OFF_DELAY_SHIFT;
 
@@ -2354,11 +2418,10 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 		DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
 			      intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
 
-		intel_dp->panel_off_jiffies = jiffies - intel_dp->panel_power_down_delay;
-
 		ironlake_edp_panel_vdd_on(intel_dp);
 		ret = intel_dp_get_dpcd(intel_dp);
 		ironlake_edp_panel_vdd_off(intel_dp, false);
+
 		if (ret) {
 			if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11)
 				dev_priv->no_aux_handshake =
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 499d4c0dbeeb..21f60b7d69a3 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -326,7 +326,8 @@ static int intel_panel_update_status(struct backlight_device *bd)
 static int intel_panel_get_brightness(struct backlight_device *bd)
 {
 	struct drm_device *dev = bl_get_data(bd);
-	return intel_panel_get_backlight(dev);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	return dev_priv->backlight_level;
 }
 
 static const struct backlight_ops intel_panel_bl_ops = {
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 7fdfa8ea7570..38e1bda73d33 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -480,21 +480,23 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		}
 		break;
 	case DB_Z_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		track->db_z_info = radeon_get_ib_value(p, idx);
-		ib[idx] &= ~Z_ARRAY_MODE(0xf);
-		track->db_z_info &= ~Z_ARRAY_MODE(0xf);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else {
-			ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			ib[idx] &= ~Z_ARRAY_MODE(0xf);
+			track->db_z_info &= ~Z_ARRAY_MODE(0xf);
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+				track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+			} else {
+				ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+			}
 		}
 		break;
 	case DB_STENCIL_INFO:
@@ -607,40 +609,44 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR5_INFO:
 	case CB_COLOR6_INFO:
 	case CB_COLOR7_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		tmp = (reg - CB_COLOR0_INFO) / 0x3c;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+			} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+			}
 		}
 		break;
 	case CB_COLOR8_INFO:
 	case CB_COLOR9_INFO:
 	case CB_COLOR10_INFO:
 	case CB_COLOR11_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+			} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+			}
 		}
 		break;
 	case CB_COLOR0_PITCH:
@@ -1311,10 +1317,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 					return -EINVAL;
 				}
 				ib[idx+1+(i*8)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
-				if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-					ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-				else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-					ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				if (!p->keep_tiling_flags) {
+					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+						ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+					else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+						ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				}
 				texture = reloc->robj;
 				/* tex mip base */
 				r = evergreen_cs_packet_next_reloc(p, &reloc);
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 400b26df652a..c93bc64707e1 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -701,16 +701,21 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			return r;
 		}
 
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= R300_TXO_MACRO_TILE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= R300_TXO_MICRO_TILE;
-		else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
-			tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
-
-		tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+		if (p->keep_tiling_flags) {
+			ib[idx] = (idx_value & 31) | /* keep the 1st 5 bits */
+				  ((idx_value & ~31) + (u32)reloc->lobj.gpu_offset);
+		} else {
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= R300_TXO_MACRO_TILE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= R300_TXO_MICRO_TILE;
+			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+				tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
+
+			tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		}
 		track->textures[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -760,24 +765,26 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		/* RB3D_COLORPITCH1 */
 		/* RB3D_COLORPITCH2 */
 		/* RB3D_COLORPITCH3 */
-		r = r100_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
-			return r;
-		}
+		if (!p->keep_tiling_flags) {
+			r = r100_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+					  idx, reg);
+				r100_cs_dump_packet(p, pkt);
+				return r;
+			}
 
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= R300_COLOR_TILE_ENABLE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= R300_COLOR_MICROTILE_ENABLE;
-		else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
-			tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= R300_COLOR_TILE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= R300_COLOR_MICROTILE_ENABLE;
+			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+				tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
 
-		tmp = idx_value & ~(0x7 << 16);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+			tmp = idx_value & ~(0x7 << 16);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		}
 		i = (reg - 0x4E38) >> 2;
 		track->cb[i].pitch = idx_value & 0x3FFE;
 		switch (((idx_value >> 21) & 0xF)) {
@@ -843,25 +850,26 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		break;
 	case 0x4F24:
 		/* ZB_DEPTHPITCH */
-		r = r100_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
-			return r;
-		}
-
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= R300_DEPTHMACROTILE_ENABLE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= R300_DEPTHMICROTILE_TILED;
-		else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
-			tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
+		if (!p->keep_tiling_flags) {
+			r = r100_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+					  idx, reg);
+				r100_cs_dump_packet(p, pkt);
+				return r;
+			}
 
-		tmp = idx_value & ~(0x7 << 16);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= R300_DEPTHMACROTILE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= R300_DEPTHMICROTILE_TILED;
+			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+				tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
 
+			tmp = idx_value & ~(0x7 << 16);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		}
 		track->zb.pitch = idx_value & 0x3FFC;
 		track->zb_dirty = true;
 		break;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 0a2e023c1557..cb1acffd2430 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -941,7 +941,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_depth_control = radeon_get_ib_value(p, idx);
 		break;
 	case R_028010_DB_DEPTH_INFO:
-		if (r600_cs_packet_next_is_pkt3_nop(p)) {
+		if (!p->keep_tiling_flags &&
+		    r600_cs_packet_next_is_pkt3_nop(p)) {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
@@ -992,7 +993,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_0280B4_CB_COLOR5_INFO:
 	case R_0280B8_CB_COLOR6_INFO:
 	case R_0280BC_CB_COLOR7_INFO:
-		if (r600_cs_packet_next_is_pkt3_nop(p)) {
+		if (!p->keep_tiling_flags &&
+		     r600_cs_packet_next_is_pkt3_nop(p)) {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
@@ -1291,10 +1293,12 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 	mip_offset <<= 8;
 
 	word0 = radeon_get_ib_value(p, idx + 0);
-	if (tiling_flags & RADEON_TILING_MACRO)
-		word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
-	else if (tiling_flags & RADEON_TILING_MICRO)
-		word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+	if (!p->keep_tiling_flags) {
+		if (tiling_flags & RADEON_TILING_MACRO)
+			word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
+		else if (tiling_flags & RADEON_TILING_MICRO)
+			word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+	}
 	word1 = radeon_get_ib_value(p, idx + 1);
 	w0 = G_038000_TEX_WIDTH(word0) + 1;
 	h0 = G_038004_TEX_HEIGHT(word1) + 1;
@@ -1621,10 +1625,12 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 					return -EINVAL;
 				}
 				base_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
-				if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-					ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
-				else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-					ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+				if (!p->keep_tiling_flags) {
+					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+						ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
+					else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+						ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+				}
 				texture = reloc->robj;
 				/* tex mip base */
 				r = r600_cs_packet_next_reloc(p, &reloc);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index fc5a1d642cb5..8227e76b5c70 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -611,7 +611,8 @@ struct radeon_cs_parser {
 	struct radeon_ib	*ib;
 	void			*track;
 	unsigned		family;
-	int parser_error;
+	int			parser_error;
+	bool			keep_tiling_flags;
 };
 
 extern int radeon_cs_update_pages(struct radeon_cs_parser *p, int pg_idx);
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index fecd705a1a5f..d24baf30efcb 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -62,6 +62,87 @@ union atom_supported_devices {
 	struct _ATOM_SUPPORTED_DEVICES_INFO_2d1 info_2d1;
 };
 
+static void radeon_lookup_i2c_gpio_quirks(struct radeon_device *rdev,
+					  ATOM_GPIO_I2C_ASSIGMENT *gpio,
+					  u8 index)
+{
+	/* r4xx mask is technically not used by the hw, so patch in the legacy mask bits */
+	if ((rdev->family == CHIP_R420) ||
+	    (rdev->family == CHIP_R423) ||
+	    (rdev->family == CHIP_RV410)) {
+		if ((le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0018) ||
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0019) ||
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x001a)) {
+			gpio->ucClkMaskShift = 0x19;
+			gpio->ucDataMaskShift = 0x18;
+		}
+	}
+
+	/* some evergreen boards have bad data for this entry */
+	if (ASIC_IS_DCE4(rdev)) {
+		if ((index == 7) &&
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
+		    (gpio->sucI2cId.ucAccess == 0)) {
+			gpio->sucI2cId.ucAccess = 0x97;
+			gpio->ucDataMaskShift = 8;
+			gpio->ucDataEnShift = 8;
+			gpio->ucDataY_Shift = 8;
+			gpio->ucDataA_Shift = 8;
+		}
+	}
+
+	/* some DCE3 boards have bad data for this entry */
+	if (ASIC_IS_DCE3(rdev)) {
+		if ((index == 4) &&
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
+		    (gpio->sucI2cId.ucAccess == 0x94))
+			gpio->sucI2cId.ucAccess = 0x14;
+	}
+}
+
+static struct radeon_i2c_bus_rec radeon_get_bus_rec_for_i2c_gpio(ATOM_GPIO_I2C_ASSIGMENT *gpio)
+{
+	struct radeon_i2c_bus_rec i2c;
+
+	memset(&i2c, 0, sizeof(struct radeon_i2c_bus_rec));
+
+	i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
+	i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
+	i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
+	i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
+	i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
+	i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
+	i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
+	i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
+	i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
+	i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
+	i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
+	i2c.en_data_mask = (1 << gpio->ucDataEnShift);
+	i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
+	i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
+	i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
+	i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
+
+	if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
+		i2c.hw_capable = true;
+	else
+		i2c.hw_capable = false;
+
+	if (gpio->sucI2cId.ucAccess == 0xa0)
+		i2c.mm_i2c = true;
+	else
+		i2c.mm_i2c = false;
+
+	i2c.i2c_id = gpio->sucI2cId.ucAccess;
+
+	if (i2c.mask_clk_reg)
+		i2c.valid = true;
+	else
+		i2c.valid = false;
+
+	return i2c;
+}
+
 static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rdev,
 							       uint8_t id)
 {
@@ -85,71 +166,10 @@ static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rd
 		for (i = 0; i < num_indices; i++) {
 			gpio = &i2c_info->asGPIO_Info[i];
 
-			/* r4xx mask is technically not used by the hw, so patch in the legacy mask bits */
-			if ((rdev->family == CHIP_R420) ||
-			    (rdev->family == CHIP_R423) ||
-			    (rdev->family == CHIP_RV410)) {
-				if ((le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0018) ||
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0019) ||
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x001a)) {
-					gpio->ucClkMaskShift = 0x19;
-					gpio->ucDataMaskShift = 0x18;
-				}
-			}
-
-			/* some evergreen boards have bad data for this entry */
-			if (ASIC_IS_DCE4(rdev)) {
-				if ((i == 7) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
-				    (gpio->sucI2cId.ucAccess == 0)) {
-					gpio->sucI2cId.ucAccess = 0x97;
-					gpio->ucDataMaskShift = 8;
-					gpio->ucDataEnShift = 8;
-					gpio->ucDataY_Shift = 8;
-					gpio->ucDataA_Shift = 8;
-				}
-			}
-
-			/* some DCE3 boards have bad data for this entry */
-			if (ASIC_IS_DCE3(rdev)) {
-				if ((i == 4) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
-				    (gpio->sucI2cId.ucAccess == 0x94))
-					gpio->sucI2cId.ucAccess = 0x14;
-			}
+			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
 			if (gpio->sucI2cId.ucAccess == id) {
-				i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
-				i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
-				i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
-				i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
-				i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
-				i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
-				i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
-				i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
-				i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
-				i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
-				i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
-				i2c.en_data_mask = (1 << gpio->ucDataEnShift);
-				i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
-				i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
-				i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
-				i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
-
-				if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
-					i2c.hw_capable = true;
-				else
-					i2c.hw_capable = false;
-
-				if (gpio->sucI2cId.ucAccess == 0xa0)
-					i2c.mm_i2c = true;
-				else
-					i2c.mm_i2c = false;
-
-				i2c.i2c_id = gpio->sucI2cId.ucAccess;
-
-				if (i2c.mask_clk_reg)
-					i2c.valid = true;
+				i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
 				break;
 			}
 		}
@@ -169,8 +189,6 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 	int i, num_indices;
 	char stmp[32];
 
-	memset(&i2c, 0, sizeof(struct radeon_i2c_bus_rec));
-
 	if (atom_parse_data_header(ctx, index, &size, NULL, NULL, &data_offset)) {
 		i2c_info = (struct _ATOM_GPIO_I2C_INFO *)(ctx->bios + data_offset);
 
@@ -179,60 +197,12 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 
 		for (i = 0; i < num_indices; i++) {
 			gpio = &i2c_info->asGPIO_Info[i];
-			i2c.valid = false;
-
-			/* some evergreen boards have bad data for this entry */
-			if (ASIC_IS_DCE4(rdev)) {
-				if ((i == 7) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
-				    (gpio->sucI2cId.ucAccess == 0)) {
-					gpio->sucI2cId.ucAccess = 0x97;
-					gpio->ucDataMaskShift = 8;
-					gpio->ucDataEnShift = 8;
-					gpio->ucDataY_Shift = 8;
-					gpio->ucDataA_Shift = 8;
-				}
-			}
 
-			/* some DCE3 boards have bad data for this entry */
-			if (ASIC_IS_DCE3(rdev)) {
-				if ((i == 4) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
-				    (gpio->sucI2cId.ucAccess == 0x94))
-					gpio->sucI2cId.ucAccess = 0x14;
-			}
-
-			i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
-			i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
-			i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
-			i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
-			i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
-			i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
-			i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
-			i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
-			i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
-			i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
-			i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
-			i2c.en_data_mask = (1 << gpio->ucDataEnShift);
-			i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
-			i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
-			i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
-			i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
-
-			if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
-				i2c.hw_capable = true;
-			else
-				i2c.hw_capable = false;
-
-			if (gpio->sucI2cId.ucAccess == 0xa0)
-				i2c.mm_i2c = true;
-			else
-				i2c.mm_i2c = false;
+			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
-			i2c.i2c_id = gpio->sucI2cId.ucAccess;
+			i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
 
-			if (i2c.mask_clk_reg) {
-				i2c.valid = true;
+			if (i2c.valid) {
 				sprintf(stmp, "0x%x", i2c.i2c_id);
 				rdev->i2c_bus[i] = radeon_i2c_create(rdev->ddev, &i2c, stmp);
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ccaa243c1442..29afd71e0840 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -93,7 +93,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 {
 	struct drm_radeon_cs *cs = data;
 	uint64_t *chunk_array_ptr;
-	unsigned size, i;
+	unsigned size, i, flags = 0;
 
 	if (!cs->num_chunks) {
 		return 0;
@@ -140,6 +140,10 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			if (p->chunks[i].length_dw == 0)
 				return -EINVAL;
 		}
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS &&
+		    !p->chunks[i].length_dw) {
+			return -EINVAL;
+		}
 
 		p->chunks[i].length_dw = user_chunk.length_dw;
 		p->chunks[i].user_ptr = (void __user *)(unsigned long)user_chunk.chunk_data;
@@ -155,6 +159,9 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 					       p->chunks[i].user_ptr, size)) {
 				return -EFAULT;
 			}
+			if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
+				flags = p->chunks[i].kdata[0];
+			}
 		} else {
 			p->chunks[i].kpage[0] = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			p->chunks[i].kpage[1] = kmalloc(PAGE_SIZE, GFP_KERNEL);
@@ -174,6 +181,8 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			  p->chunks[p->chunk_ib_idx].length_dw);
 		return -EINVAL;
 	}
+
+	p->keep_tiling_flags = (flags & RADEON_CS_KEEP_TILING_FLAGS) != 0;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index a0b35e909489..71499fc3daf5 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -53,9 +53,10 @@
  *   2.9.0 - r600 tiling (s3tc,rgtc) working, SET_PREDICATION packet 3 on r600 + eg, backend query
  *   2.10.0 - fusion 2D tiling
  *   2.11.0 - backend map, initial compute support for the CS checker
+ *   2.12.0 - RADEON_CS_KEEP_TILING_FLAGS
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	11
+#define KMS_DRIVER_MINOR	12
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 617b64678fc6..0bb0f5f713e6 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -574,10 +574,16 @@ retry:
 		return ret;
 
 	spin_lock(&glob->lru_lock);
+
+	if (unlikely(list_empty(&bo->ddestroy))) {
+		spin_unlock(&glob->lru_lock);
+		return 0;
+	}
+
 	ret = ttm_bo_reserve_locked(bo, interruptible,
 				    no_wait_reserve, false, 0);
 
-	if (unlikely(ret != 0) || list_empty(&bo->ddestroy)) {
+	if (unlikely(ret != 0)) {
 		spin_unlock(&glob->lru_lock);
 		return ret;
 	}
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index bdde899af72e..111d956d8e7d 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -991,14 +991,20 @@ static ssize_t vga_arb_write(struct file *file, const char __user * buf,
 				uc = &priv->cards[i];
 		}
 
-		if (!uc)
-			return -EINVAL;
+		if (!uc) {
+			ret_val = -EINVAL;
+			goto done;
+		}
 
-		if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0)
-			return -EINVAL;
+		if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0) {
+			ret_val = -EINVAL;
+			goto done;
+		}
 
-		if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0)
-			return -EINVAL;
+		if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0) {
+			ret_val = -EINVAL;
+			goto done;
+		}
 
 		vga_put(pdev, io_state);
 
diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h
index d30bedfeb7ef..ddd46db65b57 100644
--- a/include/drm/drm_mode.h
+++ b/include/drm/drm_mode.h
@@ -235,6 +235,8 @@ struct drm_mode_fb_cmd {
 #define DRM_MODE_FB_DIRTY_ANNOTATE_FILL 0x02
 #define DRM_MODE_FB_DIRTY_FLAGS         0x03
 
+#define DRM_MODE_FB_DIRTY_MAX_CLIPS     256
+
 /*
  * Mark a region of a framebuffer as dirty.
  *
diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h
index b65be6054a18..be94be6d6f17 100644
--- a/include/drm/radeon_drm.h
+++ b/include/drm/radeon_drm.h
@@ -874,6 +874,10 @@ struct drm_radeon_gem_pwrite {
 
 #define RADEON_CHUNK_ID_RELOCS	0x01
 #define RADEON_CHUNK_ID_IB	0x02
+#define RADEON_CHUNK_ID_FLAGS	0x03
+
+/* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */
+#define RADEON_CS_KEEP_TILING_FLAGS 0x01
 
 struct drm_radeon_cs_chunk {
 	uint32_t		chunk_id;