diff --git a/Documentation/i2c/ten-bit-addresses b/Documentation/i2c/ten-bit-addresses
index e989070..cdfe139 100644
--- a/Documentation/i2c/ten-bit-addresses
+++ b/Documentation/i2c/ten-bit-addresses
@@ -1,22 +1,24 @@
 The I2C protocol knows about two kinds of device addresses: normal 7 bit
 addresses, and an extended set of 10 bit addresses. The sets of addresses
 do not intersect: the 7 bit address 0x10 is not the same as the 10 bit
-address 0x10 (though a single device could respond to both of them). You
-select a 10 bit address by adding an extra byte after the address
-byte:
-  S Addr7 Rd/Wr ....
-becomes
-  S 11110 Addr10 Rd/Wr
-S is the start bit, Rd/Wr the read/write bit, and if you count the number
-of bits, you will see the there are 8 after the S bit for 7 bit addresses,
-and 16 after the S bit for 10 bit addresses.
+address 0x10 (though a single device could respond to both of them).
 
-WARNING! The current 10 bit address support is EXPERIMENTAL. There are
-several places in the code that will cause SEVERE PROBLEMS with 10 bit
-addresses, even though there is some basic handling and hooks. Also,
-almost no supported adapter handles the 10 bit addresses correctly.
+I2C messages to and from 10-bit address devices have a different format.
+See the I2C specification for the details.
 
-As soon as a real 10 bit address device is spotted 'in the wild', we
-can and will add proper support. Right now, 10 bit address devices
-are defined by the I2C protocol, but we have never seen a single device
-which supports them.
+The current 10 bit address support is minimal. It should work, however
+you can expect some problems along the way:
+* Not all bus drivers support 10-bit addresses. Some don't because the
+  hardware doesn't support them (SMBus doesn't require 10-bit address
+  support for example), some don't because nobody bothered adding the
+  code (or it's there but not working properly.) Software implementation
+  (i2c-algo-bit) is known to work.
+* Some optional features do not support 10-bit addresses. This is the
+  case of automatic detection and instantiation of devices by their,
+  drivers, for example.
+* Many user-space packages (for example i2c-tools) lack support for
+  10-bit addresses.
+
+Note that 10-bit address devices are still pretty rare, so the limitations
+listed above could stay for a long time, maybe even forever if nobody
+needs them to be fixed.
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index ec55595..43b8758 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -67,7 +67,7 @@
 	struct device *dev = &pdev->dev;
 	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	const struct platform_device_id *id = platform_get_device_id(pdev);
-	struct ata_port_info pi = ahci_port_info[id->driver_data];
+	struct ata_port_info pi = ahci_port_info[id ? id->driver_data : 0];
 	const struct ata_port_info *ppi[] = { &pi, NULL };
 	struct ahci_host_priv *hpriv;
 	struct ata_host *host;
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 63d5327..4cadfa2 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2533,10 +2533,12 @@
 	if (rc)
 		goto out;
 
+#ifdef CONFIG_ATA_BMDMA
 	if (bmdma)
 		/* prepare and activate BMDMA host */
 		rc = ata_pci_bmdma_prepare_host(pdev, ppi, &host);
 	else
+#endif
 		/* prepare and activate SFF host */
 		rc = ata_pci_sff_prepare_host(pdev, ppi, &host);
 	if (rc)
@@ -2544,10 +2546,12 @@
 	host->private_data = host_priv;
 	host->flags |= hflags;
 
+#ifdef CONFIG_ATA_BMDMA
 	if (bmdma) {
 		pci_set_master(pdev);
 		rc = ata_pci_sff_activate_host(host, ata_bmdma_interrupt, sht);
 	} else
+#endif
 		rc = ata_pci_sff_activate_host(host, ata_sff_interrupt, sht);
 out:
 	if (rc == 0)
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 405c63b..8323fc3 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1873,6 +1873,10 @@
 	}
 
 	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 4f40f1c..d09a6e0 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -636,11 +636,16 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 			   (delayfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -962,13 +984,19 @@
 	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 @@
 	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 @@
 	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 e9c2cfe..15bfa91 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -68,7 +68,7 @@
 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 @@
 		"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 @@
 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 06a37f4..4a9c1b9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -126,6 +126,9 @@
 	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 @@
 	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 @@
 		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 @@
 	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 @@
 	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 @@
 	 * 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 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 d18b07a..8359dc7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1745,7 +1745,7 @@
 	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 @@
 			 * 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 @@
 	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 @@
 	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 9ee2729..b40004b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -824,6 +824,7 @@
 
 	/* 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 5a09416..b080cc8 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 f8f602d..7886e4f 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -370,6 +370,7 @@
 
 	/* 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 @@
 
 	/* 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 981b1f1..e77a863 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2933,7 +2933,8 @@
 
 	/* 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 @@
 				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 @@
 			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 @@
 			/* 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 @@
 		 */
 		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 @@
 
 	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 @@
 	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 @@
 	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 09b318b..4d0358f 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -59,7 +59,6 @@
 	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 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 @@
 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 @@
 			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 @@
 		  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 @@
 			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->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;
 	}
 }
 
+#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)
+{
+	struct drm_device *dev = intel_dp->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	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 (_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));
+	}
+}
+
+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)
 {
-	unsigned long	off_time;
-	unsigned long	delay;
-
 	DRM_DEBUG_KMS("Wait for panel power off time\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_OFF_MASK, IDLE_OFF_VALUE);
+}
 
-	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;
-	}
+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);
+}
 
-	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);
+
+/* 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 @@
 	     "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 @@
 	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 @@
 		/* 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 @@
 						 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 @@
 
 	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 @@
 	}
 }
 
-/* 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 @@
 	}
 
 	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_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);
+	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);
 
-		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 |= 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 @@
 	 * 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 @@
 		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 @@
 {
 	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 @@
 	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 @@
 	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 @@
 			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 @@
  * 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 @@
 }
 
 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 @@
  * 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 @@
 }
 
 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 @@
 			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 @@
 }
 
 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 @@
 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 @@
 			 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 @@
 
 	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 @@
 	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 @@
 		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 @@
 		/* 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 @@
 		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 @@
 	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 @@
 			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 @@
 			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 @@
 		}
 
 		/* 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 @@
 
 	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 @@
 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 @@
 		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 @@
 			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 @@
 			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 @@
 
 		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 @@
 		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 499d4c0..21f60b7 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_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 7fdfa8e..38e1bda 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -480,21 +480,23 @@
 		}
 		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 @@
 	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 @@
 					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 400b26d..c93bc64 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -701,16 +701,21 @@
 			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;
+		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;
+			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 @@
 		/* 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;
+
+			tmp = idx_value & ~(0x7 << 16);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
 		}
-
-		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;
 		i = (reg - 0x4E38) >> 2;
 		track->cb[i].pitch = idx_value & 0x3FFE;
 		switch (((idx_value >> 21) & 0xF)) {
@@ -843,25 +850,26 @@
 		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 (!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_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;
 		}
-
-		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 0a2e023..cb1acff 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -941,7 +941,8 @@
 		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 @@
 	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 @@
 	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 @@
 					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 fc5a1d6..8227e76 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -611,7 +611,8 @@
 	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 fecd705..d24baf3 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -62,6 +62,87 @@
 	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 @@
 		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 @@
 	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 @@
 
 		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;
-				}
-			}
+			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
-			/* 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 = radeon_get_bus_rec_for_i2c_gpio(gpio);
 
-			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;
+			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 ccaa243..29afd71 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -93,7 +93,7 @@
 {
 	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 @@
 			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 @@
 					       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 @@
 			  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 a0b35e9..71499fc 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 617b646..0bb0f5f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -574,10 +574,16 @@
 		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 bdde899..111d956 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -991,14 +991,20 @@
 				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/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index 85584a5..525c734 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -488,7 +488,7 @@
 
 	if (flags & I2C_M_TEN) {
 		/* a ten bit address */
-		addr = 0xf0 | ((msg->addr >> 7) & 0x03);
+		addr = 0xf0 | ((msg->addr >> 7) & 0x06);
 		bit_dbg(2, &i2c_adap->dev, "addr0: %d\n", addr);
 		/* try extended address code...*/
 		ret = try_address(i2c_adap, addr, retries);
@@ -498,7 +498,7 @@
 			return -ENXIO;
 		}
 		/* the remaining 8 bit address */
-		ret = i2c_outb(i2c_adap, msg->addr & 0x7f);
+		ret = i2c_outb(i2c_adap, msg->addr & 0xff);
 		if ((ret != 1) && !nak_ok) {
 			/* the chip did not ack / xmission error occurred */
 			dev_err(&i2c_adap->dev, "died at 2nd address code\n");
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 131079a..1e56061 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -539,8 +539,10 @@
 	client->dev.type = &i2c_client_type;
 	client->dev.of_node = info->of_node;
 
+	/* For 10-bit clients, add an arbitrary offset to avoid collisions */
 	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
-		     client->addr);
+		     client->addr | ((client->flags & I2C_CLIENT_TEN)
+				     ? 0xa000 : 0));
 	status = device_register(&client->dev);
 	if (status)
 		goto out_err;
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index c90ce50..57a45ce8 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -579,7 +579,7 @@
 	return 0;
 }
 
-int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
+static int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
 			 void *data)
 {
 	struct device *dev = data;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index b6f9749..f02b523 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -76,6 +76,7 @@
 
 config PCI_PRI
 	bool "PCI PRI support"
+	depends on PCI
 	select PCI_ATS
 	help
 	  PRI is the PCI Page Request Interface. It allows PCI devices that are
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 596172b..fce1c54 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -459,8 +459,17 @@
 {
 	acpi_status status;
 	unsigned long long tmp;
+	struct acpi_pci_root *root;
 	acpi_handle dummy_handle;
 
+	/*
+	 * We shouldn't use this bridge if PCIe native hotplug control has been
+	 * granted by the BIOS for it.
+	 */
+	root = acpi_pci_find_root(handle);
+	if (root && (root->osc_control_set & OSC_PCI_EXPRESS_NATIVE_HP_CONTROL))
+		return -ENODEV;
+
 	/* if the bridge doesn't have _STA, we assume it is always there */
 	status = acpi_get_handle(handle, "_STA", &dummy_handle);
 	if (ACPI_SUCCESS(status)) {
@@ -1376,13 +1385,23 @@
 static acpi_status
 find_root_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
+	struct acpi_pci_root *root;
 	int *count = (int *)context;
 
-	if (acpi_is_root_bridge(handle)) {
-		acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
-				handle_hotplug_event_bridge, NULL);
-			(*count)++;
-	}
+	if (!acpi_is_root_bridge(handle))
+		return AE_OK;
+
+	root = acpi_pci_find_root(handle);
+	if (!root)
+		return AE_OK;
+
+	if (root->osc_control_set & OSC_PCI_EXPRESS_NATIVE_HP_CONTROL)
+		return AE_OK;
+
+	(*count)++;
+	acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+				    handle_hotplug_event_bridge, NULL);
+
 	return AE_OK ;
 }
 
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 1e9c9aa..085dbb5 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -213,9 +213,6 @@
 		goto err_exit;
 	}
 
-	/* Wait for 1 second after checking link training status */
-	msleep(1000);
-
 	/* Check for a power fault */
 	if (ctrl->power_fault_detected || pciehp_query_power_fault(p_slot)) {
 		ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(p_slot));
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 96dc473..7b14148 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -280,6 +280,14 @@
         else
                 msleep(1000);
 
+	/*
+	 * Need to wait for 1000 ms after Data Link Layer Link Active
+	 * (DLLLA) bit reads 1b before sending configuration request.
+	 * We need it before checking Link Training (LT) bit becuase
+	 * LT is still set even after DLLLA bit is set on some platform.
+	 */
+	msleep(1000);
+
 	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
 	if (retval) {
 		ctrl_err(ctrl, "Cannot read LNKSTATUS register\n");
@@ -294,6 +302,16 @@
 		return retval;
 	}
 
+	/*
+	 * If the port supports Link speeds greater than 5.0 GT/s, we
+	 * must wait for 100 ms after Link training completes before
+	 * sending configuration request.
+	 */
+	if (ctrl->pcie->port->subordinate->max_bus_speed > PCIE_SPEED_5_0GT)
+		msleep(100);
+
+	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
+
 	return retval;
 }
 
@@ -484,7 +502,6 @@
 	u16 slot_cmd;
 	u16 cmd_mask;
 	u16 slot_status;
-	u16 lnk_status;
 	int retval = 0;
 
 	/* Clear sticky power-fault bit from previous power failures */
@@ -516,14 +533,6 @@
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
 
-	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
-	if (retval) {
-		ctrl_err(ctrl, "%s: Cannot read LNKSTA register\n",
-				__func__);
-		return retval;
-	}
-	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
-
 	return retval;
 }
 
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index aca972b..dd7e0c5 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -278,8 +278,8 @@
 
 static int is_shpc_capable(struct pci_dev *dev)
 {
-	if ((dev->vendor == PCI_VENDOR_ID_AMD) || (dev->device ==
-						PCI_DEVICE_ID_AMD_GOLAM_7450))
+	if (dev->vendor == PCI_VENDOR_ID_AMD &&
+	    dev->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
 		return 1;
 	if (!pci_find_capability(dev, PCI_CAP_ID_SHPC))
 		return 0;
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 36547f0..75ba231 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -944,8 +944,8 @@
 	ctrl->pci_dev = pdev;  /* pci_dev of the P2P bridge */
 	ctrl_dbg(ctrl, "Hotplug Controller:\n");
 
-	if ((pdev->vendor == PCI_VENDOR_ID_AMD) || (pdev->device ==
-				PCI_DEVICE_ID_AMD_GOLAM_7450)) {
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    pdev->device == PCI_DEVICE_ID_AMD_GOLAM_7450) {
 		/* amd shpc driver doesn't use Base Offset; assume 0 */
 		ctrl->mmio_base = pci_resource_start(pdev, 0);
 		ctrl->mmio_size = pci_resource_len(pdev, 0);
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
index 66d2d60..b552aae 100644
--- a/drivers/regulator/tps65910-regulator.c
+++ b/drivers/regulator/tps65910-regulator.c
@@ -664,10 +664,10 @@
 
 	switch (id) {
 	case TPS65910_REG_VDD1:
-		dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
 		if (dcdc_mult == 1)
 			dcdc_mult--;
-		vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+		vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3;
 
 		tps65910_modify_bits(pmic, TPS65910_VDD1,
 				(dcdc_mult << VDD1_VGAIN_SEL_SHIFT),
@@ -675,10 +675,10 @@
 		tps65910_reg_write(pmic, TPS65910_VDD1_OP, vsel);
 		break;
 	case TPS65910_REG_VDD2:
-		dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
 		if (dcdc_mult == 1)
 			dcdc_mult--;
-		vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+		vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3;
 
 		tps65910_modify_bits(pmic, TPS65910_VDD2,
 				(dcdc_mult << VDD2_VGAIN_SEL_SHIFT),
@@ -756,9 +756,9 @@
 	switch (id) {
 	case TPS65910_REG_VDD1:
 	case TPS65910_REG_VDD2:
-		mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
 		volt = VDD1_2_MIN_VOLT +
-				(selector % VDD1_2_NUM_VOLTS) * VDD1_2_OFFSET;
+				(selector % VDD1_2_NUM_VOLT_FINE) * VDD1_2_OFFSET;
 		break;
 	case TPS65911_REG_VDDCTRL:
 		volt = VDDCTRL_MIN_VOLT + (selector * VDDCTRL_OFFSET);
@@ -947,6 +947,8 @@
 
 		if (i == TPS65910_REG_VDD1 || i == TPS65910_REG_VDD2) {
 			pmic->desc[i].ops = &tps65910_ops_dcdc;
+			pmic->desc[i].n_voltages = VDD1_2_NUM_VOLT_FINE *
+							VDD1_2_NUM_VOLT_COARSE;
 		} else if (i == TPS65910_REG_VDD3) {
 			if (tps65910_chip_id(tps65910) == TPS65910)
 				pmic->desc[i].ops = &tps65910_ops_vdd3;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 58609bd..2a83425 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -967,7 +967,7 @@
 
 /**
  * ecryptfs_new_file_context
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_inode: The eCryptfs inode
  *
  * If the crypto context for the file has not yet been established,
  * this is where we do that.  Establishing a new crypto context
@@ -984,13 +984,13 @@
  *
  * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry)
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-	    &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+	    &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 	    &ecryptfs_superblock_to_private(
-		    ecryptfs_dentry->d_sb)->mount_crypt_stat;
+		    ecryptfs_inode->i_sb)->mount_crypt_stat;
 	int cipher_name_len;
 	int rc = 0;
 
@@ -1299,12 +1299,12 @@
 }
 
 static int
-ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry,
+ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode,
 				    char *virt, size_t virt_len)
 {
 	int rc;
 
-	rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt,
+	rc = ecryptfs_write_lower(ecryptfs_inode, virt,
 				  0, virt_len);
 	if (rc < 0)
 		printk(KERN_ERR "%s: Error attempting to write header "
@@ -1338,7 +1338,8 @@
 
 /**
  * ecryptfs_write_metadata
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_dentry: The eCryptfs dentry, which should be negative
+ * @ecryptfs_inode: The newly created eCryptfs inode
  *
  * Write the file headers out.  This will likely involve a userspace
  * callout, in which the session key is encrypted with one or more
@@ -1348,10 +1349,11 @@
  *
  * Returns zero on success; non-zero on error
  */
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+			    struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-		&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+		&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	unsigned int order;
 	char *virt;
 	size_t virt_len;
@@ -1391,7 +1393,7 @@
 		rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
 						      size);
 	else
-		rc = ecryptfs_write_metadata_to_contents(ecryptfs_dentry, virt,
+		rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt,
 							 virt_len);
 	if (rc) {
 		printk(KERN_ERR "%s: Error writing metadata out to lower file; "
@@ -1943,7 +1945,7 @@
 
 /* We could either offset on every reverse map or just pad some 0x00's
  * at the front here */
-static const unsigned char filename_rev_map[] = {
+static const unsigned char filename_rev_map[256] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 7 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 15 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 23 */
@@ -1959,7 +1961,7 @@
 	0x00, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, /* 103 */
 	0x2D, 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, /* 111 */
 	0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, /* 119 */
-	0x3D, 0x3E, 0x3F
+	0x3D, 0x3E, 0x3F /* 123 - 255 initialized to 0x00 */
 };
 
 /**
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 54481a3..a9f29b1 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -584,9 +584,10 @@
 int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode);
 int ecryptfs_encrypt_page(struct page *page);
 int ecryptfs_decrypt_page(struct page *page);
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry);
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+			    struct inode *ecryptfs_inode);
 int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode);
 void ecryptfs_write_crypt_stat_flags(char *page_virt,
 				     struct ecryptfs_crypt_stat *crypt_stat,
 				     size_t *written);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index c6ac98c..d3f95f9 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -139,6 +139,27 @@
 	return rc;
 }
 
+static void ecryptfs_vma_close(struct vm_area_struct *vma)
+{
+	filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct ecryptfs_file_vm_ops = {
+	.close		= ecryptfs_vma_close,
+	.fault		= filemap_fault,
+};
+
+static int ecryptfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int rc;
+
+	rc = generic_file_mmap(file, vma);
+	if (!rc)
+		vma->vm_ops = &ecryptfs_file_vm_ops;
+
+	return rc;
+}
+
 struct kmem_cache *ecryptfs_file_info_cache;
 
 /**
@@ -349,7 +370,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_file_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a36d327..32f90a3 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -172,22 +172,23 @@
  * it. It will also update the eCryptfs directory inode to mimic the
  * stat of the lower directory inode.
  *
- * Returns zero on success; non-zero on error condition
+ * Returns the new eCryptfs inode on success; an ERR_PTR on error condition
  */
-static int
+static struct inode *
 ecryptfs_do_create(struct inode *directory_inode,
 		   struct dentry *ecryptfs_dentry, int mode)
 {
 	int rc;
 	struct dentry *lower_dentry;
 	struct dentry *lower_dir_dentry;
+	struct inode *inode;
 
 	lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
 	if (IS_ERR(lower_dir_dentry)) {
 		ecryptfs_printk(KERN_ERR, "Error locking directory of "
 				"dentry\n");
-		rc = PTR_ERR(lower_dir_dentry);
+		inode = ERR_CAST(lower_dir_dentry);
 		goto out;
 	}
 	rc = ecryptfs_create_underlying_file(lower_dir_dentry->d_inode,
@@ -195,20 +196,19 @@
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
 		       "rc = [%d]\n", __func__, rc);
+		inode = ERR_PTR(rc);
 		goto out_lock;
 	}
-	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-				directory_inode->i_sb);
-	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Failure in ecryptfs_interpose\n");
+	inode = __ecryptfs_get_inode(lower_dentry->d_inode,
+				     directory_inode->i_sb);
+	if (IS_ERR(inode))
 		goto out_lock;
-	}
 	fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
 	fsstack_copy_inode_size(directory_inode, lower_dir_dentry->d_inode);
 out_lock:
 	unlock_dir(lower_dir_dentry);
 out:
-	return rc;
+	return inode;
 }
 
 /**
@@ -219,26 +219,26 @@
  *
  * Returns zero on success
  */
-static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
+static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
+				    struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-		&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+		&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	int rc = 0;
 
-	if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
+	if (S_ISDIR(ecryptfs_inode->i_mode)) {
 		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
 		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
 		goto out;
 	}
 	ecryptfs_printk(KERN_DEBUG, "Initializing crypto context\n");
-	rc = ecryptfs_new_file_context(ecryptfs_dentry);
+	rc = ecryptfs_new_file_context(ecryptfs_inode);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error creating new file "
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
-	rc = ecryptfs_get_lower_file(ecryptfs_dentry,
-				     ecryptfs_dentry->d_inode);
+	rc = ecryptfs_get_lower_file(ecryptfs_dentry, ecryptfs_inode);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
@@ -246,10 +246,10 @@
 			ecryptfs_dentry->d_name.name, rc);
 		goto out;
 	}
-	rc = ecryptfs_write_metadata(ecryptfs_dentry);
+	rc = ecryptfs_write_metadata(ecryptfs_dentry, ecryptfs_inode);
 	if (rc)
 		printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
-	ecryptfs_put_lower_file(ecryptfs_dentry->d_inode);
+	ecryptfs_put_lower_file(ecryptfs_inode);
 out:
 	return rc;
 }
@@ -269,18 +269,28 @@
 ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		int mode, struct nameidata *nd)
 {
+	struct inode *ecryptfs_inode;
 	int rc;
 
-	/* ecryptfs_do_create() calls ecryptfs_interpose() */
-	rc = ecryptfs_do_create(directory_inode, ecryptfs_dentry, mode);
-	if (unlikely(rc)) {
+	ecryptfs_inode = ecryptfs_do_create(directory_inode, ecryptfs_dentry,
+					    mode);
+	if (unlikely(IS_ERR(ecryptfs_inode))) {
 		ecryptfs_printk(KERN_WARNING, "Failed to create file in"
 				"lower filesystem\n");
+		rc = PTR_ERR(ecryptfs_inode);
 		goto out;
 	}
 	/* At this point, a file exists on "disk"; we need to make sure
 	 * that this on disk file is prepared to be an ecryptfs file */
-	rc = ecryptfs_initialize_file(ecryptfs_dentry);
+	rc = ecryptfs_initialize_file(ecryptfs_dentry, ecryptfs_inode);
+	if (rc) {
+		drop_nlink(ecryptfs_inode);
+		unlock_new_inode(ecryptfs_inode);
+		iput(ecryptfs_inode);
+		goto out;
+	}
+	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+	unlock_new_inode(ecryptfs_inode);
 out:
 	return rc;
 }
diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h
index d30bedf..ddd46db 100644
--- a/include/drm/drm_mode.h
+++ b/include/drm/drm_mode.h
@@ -235,6 +235,8 @@
 #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 b65be60..be94be6 100644
--- a/include/drm/radeon_drm.h
+++ b/include/drm/radeon_drm.h
@@ -874,6 +874,10 @@
 
 #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;
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index a81bf6d..07d103a 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -432,9 +432,6 @@
 /* Internal numbers to terminate lists */
 #define I2C_CLIENT_END		0xfffeU
 
-/* The numbers to use to set I2C bus address */
-#define ANY_I2C_BUS		0xffff
-
 /* Construct an I2C_CLIENT_END-terminated array of i2c addresses */
 #define I2C_ADDRS(addr, addrs...) \
 	((const unsigned short []){ addr, ## addrs, I2C_CLIENT_END })
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 82b4c88..8bf2cb9 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -243,7 +243,8 @@
 
 
 /*Registers VDD1, VDD2 voltage values definitions */
-#define VDD1_2_NUM_VOLTS				73
+#define VDD1_2_NUM_VOLT_FINE				73
+#define VDD1_2_NUM_VOLT_COARSE				3
 #define VDD1_2_MIN_VOLT					6000
 #define VDD1_2_OFFSET					125
 
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index e3d0b38..7ef6872 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -12,7 +12,7 @@
 	unsigned int is_enabled:1;      /* Enable bit is set */
 };
 
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
 
 extern int pci_enable_ats(struct pci_dev *dev, int ps);
 extern void pci_disable_ats(struct pci_dev *dev);
@@ -29,7 +29,7 @@
 	return dev->ats && dev->ats->is_enabled;
 }
 
-#else /* CONFIG_PCI_IOV */
+#else /* CONFIG_PCI_ATS */
 
 static inline int pci_enable_ats(struct pci_dev *dev, int ps)
 {
@@ -50,7 +50,7 @@
 	return 0;
 }
 
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_ATS */
 
 #ifdef CONFIG_PCI_PRI
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 337df0d..7cda65b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -338,7 +338,7 @@
 	struct list_head msi_list;
 #endif
 	struct pci_vpd *vpd;
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
 	union {
 		struct pci_sriov *sriov;	/* SR-IOV capability related */
 		struct pci_dev *physfn;	/* the PF this VF is associated with */
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 30e2bef..8b4c253 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -747,6 +747,18 @@
     # Add space to evaluate the character before $
     $option = " $option";
     my $retval = "";
+    my $repeated = 0;
+    my $parent = 0;
+
+    foreach my $test (keys %repeat_tests) {
+	if ($i >= $test &&
+	    $i < $test + $repeat_tests{$test}) {
+
+	    $repeated = 1;
+	    $parent = $test;
+	    last;
+	}
+    }
 
     while ($option =~ /(.*?[^\\])\$\{(.*?)\}(.*)/) {
 	my $start = $1;
@@ -760,10 +772,14 @@
 	# otherwise see if the default OPT (without [$i]) exists.
 
 	my $o = "$var\[$i\]";
+	my $parento = "$var\[$parent\]";
 
 	if (defined($opt{$o})) {
 	    $o = $opt{$o};
 	    $retval = "$retval$o";
+	} elsif ($repeated && defined($opt{$parento})) {
+	    $o = $opt{$parento};
+	    $retval = "$retval$o";
 	} elsif (defined($opt{$var})) {
 	    $o = $opt{$var};
 	    $retval = "$retval$o";