diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 6977a1c..f73ef43 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -672,7 +672,7 @@
 	struct drm_crtc_helper_funcs *crtc_funcs;
 	u16 *red, *green, *blue, *transp;
 	struct drm_crtc *crtc;
-	int i, rc = 0;
+	int i, j, rc = 0;
 	int start;
 
 	for (i = 0; i < fb_helper->crtc_count; i++) {
@@ -685,7 +685,7 @@
 		transp = cmap->transp;
 		start = cmap->start;
 
-		for (i = 0; i < cmap->len; i++) {
+		for (j = 0; j < cmap->len; j++) {
 			u16 hred, hgreen, hblue, htransp = 0xffff;
 
 			hred = *red++;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3601466..4ff9b6c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -865,7 +865,7 @@
 		int max_freq;
 
 		/* RPSTAT1 is in the GT power well */
-		__gen6_force_wake_get(dev_priv);
+		__gen6_gt_force_wake_get(dev_priv);
 
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
 		seq_printf(m, "RPSTAT1: 0x%08x\n", I915_READ(GEN6_RPSTAT1));
@@ -888,7 +888,7 @@
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
 			   max_freq * 100);
 
-		__gen6_force_wake_put(dev_priv);
+		__gen6_gt_force_wake_put(dev_priv);
 	} else {
 		seq_printf(m, "no P-state info available\n");
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0ad533f..22ec066 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -46,6 +46,9 @@
 unsigned int i915_powersave = 1;
 module_param_named(powersave, i915_powersave, int, 0600);
 
+unsigned int i915_semaphores = 0;
+module_param_named(semaphores, i915_semaphores, int, 0600);
+
 unsigned int i915_enable_rc6 = 0;
 module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 
@@ -254,7 +257,7 @@
 	}
 }
 
-void __gen6_force_wake_get(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 {
 	int count;
 
@@ -270,12 +273,22 @@
 		udelay(10);
 }
 
-void __gen6_force_wake_put(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
 	POSTING_READ(FORCEWAKE);
 }
 
+void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
+{
+	int loop = 500;
+	u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+	while (fifo < 20 && loop--) {
+		udelay(10);
+		fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+	}
+}
+
 static int i915_drm_freeze(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 65dfe81..456f404 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -956,6 +956,7 @@
 extern int i915_max_ioctl;
 extern unsigned int i915_fbpercrtc;
 extern unsigned int i915_powersave;
+extern unsigned int i915_semaphores;
 extern unsigned int i915_lvds_downclock;
 extern unsigned int i915_panel_use_ssc;
 extern unsigned int i915_enable_rc6;
@@ -1177,6 +1178,9 @@
 void i915_gem_free_all_phys_object(struct drm_device *dev);
 void i915_gem_release(struct drm_device *dev, struct drm_file *file);
 
+uint32_t
+i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj);
+
 /* i915_gem_gtt.c */
 void i915_gem_restore_gtt_mappings(struct drm_device *dev);
 int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj);
@@ -1353,22 +1357,32 @@
  * must be set to prevent GT core from power down and stale values being
  * returned.
  */
-void __gen6_force_wake_get(struct drm_i915_private *dev_priv);
-void __gen6_force_wake_put (struct drm_i915_private *dev_priv);
-static inline u32 i915_safe_read(struct drm_i915_private *dev_priv, u32 reg)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
+
+static inline u32 i915_gt_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val;
 
 	if (dev_priv->info->gen >= 6) {
-		__gen6_force_wake_get(dev_priv);
+		__gen6_gt_force_wake_get(dev_priv);
 		val = I915_READ(reg);
-		__gen6_force_wake_put(dev_priv);
+		__gen6_gt_force_wake_put(dev_priv);
 	} else
 		val = I915_READ(reg);
 
 	return val;
 }
 
+static inline void i915_gt_write(struct drm_i915_private *dev_priv,
+				u32 reg, u32 val)
+{
+	if (dev_priv->info->gen >= 6)
+		__gen6_gt_wait_for_fifo(dev_priv);
+	I915_WRITE(reg, val);
+}
+
 static inline void
 i915_write(struct drm_i915_private *dev_priv, u32 reg, u64 val, int len)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index cf4f74c..36e66cc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1398,7 +1398,7 @@
  * Return the required GTT alignment for an object, only taking into account
  * unfenced tiled surface requirements.
  */
-static uint32_t
+uint32_t
 i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
 {
 	struct drm_device *dev = obj->base.dev;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d2f445e..50ab161 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -772,8 +772,8 @@
 	if (from == NULL || to == from)
 		return 0;
 
-	/* XXX gpu semaphores are currently causing hard hangs on SNB mobile */
-	if (INTEL_INFO(obj->base.dev)->gen < 6 || IS_MOBILE(obj->base.dev))
+	/* XXX gpu semaphores are implicated in various hard hangs on SNB */
+	if (INTEL_INFO(obj->base.dev)->gen < 6 || !i915_semaphores)
 		return i915_gem_object_wait_rendering(obj, true);
 
 	idx = intel_ring_sync_index(from, to);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 79a04fd..d64843e 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -184,7 +184,7 @@
 static bool
 i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 {
-	int tile_width, tile_height;
+	int tile_width;
 
 	/* Linear is always fine */
 	if (tiling_mode == I915_TILING_NONE)
@@ -215,20 +215,6 @@
 		}
 	}
 
-	if (IS_GEN2(dev) ||
-	    (tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)))
-		tile_height = 32;
-	else
-		tile_height = 8;
-	/* i8xx is strange: It has 2 interleaved rows of tiles, so needs an even
-	 * number of tile rows. */
-	if (IS_GEN2(dev))
-		tile_height *= 2;
-
-	/* Size needs to be aligned to a full tile row */
-	if (size & (tile_height * stride - 1))
-		return false;
-
 	/* 965+ just needs multiples of tile width */
 	if (INTEL_INFO(dev)->gen >= 4) {
 		if (stride & (tile_width - 1))
@@ -363,14 +349,27 @@
 			(obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end &&
 			 i915_gem_object_fence_ok(obj, args->tiling_mode));
 
-		obj->tiling_changed = true;
-		obj->tiling_mode = args->tiling_mode;
-		obj->stride = args->stride;
+		/* Rebind if we need a change of alignment */
+		if (!obj->map_and_fenceable) {
+			u32 unfenced_alignment =
+				i915_gem_get_unfenced_gtt_alignment(obj);
+			if (obj->gtt_offset & (unfenced_alignment - 1))
+				ret = i915_gem_object_unbind(obj);
+		}
+
+		if (ret == 0) {
+			obj->tiling_changed = true;
+			obj->tiling_mode = args->tiling_mode;
+			obj->stride = args->stride;
+		}
 	}
+	/* we have to maintain this existing ABI... */
+	args->stride = obj->stride;
+	args->tiling_mode = obj->tiling_mode;
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 
-	return 0;
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 729d423..3e6f486 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3261,6 +3261,8 @@
 #define  FORCEWAKE				0xA18C
 #define  FORCEWAKE_ACK				0x130090
 
+#define  GT_FIFO_FREE_ENTRIES			0x120008
+
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
 #define   GEN6_FREQUENCY(x)			((x)<<25)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e79b25b..49fb54f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1219,7 +1219,7 @@
 	u32 blt_ecoskpd;
 
 	/* Make sure blitter notifies FBC of writes */
-	__gen6_force_wake_get(dev_priv);
+	__gen6_gt_force_wake_get(dev_priv);
 	blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
 	blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
 		GEN6_BLITTER_LOCK_SHIFT;
@@ -1230,7 +1230,7 @@
 			 GEN6_BLITTER_LOCK_SHIFT);
 	I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
 	POSTING_READ(GEN6_BLITTER_ECOSKPD);
-	__gen6_force_wake_put(dev_priv);
+	__gen6_gt_force_wake_put(dev_priv);
 }
 
 static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
@@ -6282,7 +6282,7 @@
 	 * userspace...
 	 */
 	I915_WRITE(GEN6_RC_STATE, 0);
-	__gen6_force_wake_get(dev_priv);
+	__gen6_gt_force_wake_get(dev_priv);
 
 	/* disable the counters and set deterministic thresholds */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -6380,7 +6380,7 @@
 	/* enable all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);
 
-	__gen6_force_wake_put(dev_priv);
+	__gen6_gt_force_wake_put(dev_priv);
 }
 
 void intel_enable_clock_gating(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6d6fde8..3430686 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -14,22 +14,23 @@
 	struct		drm_i915_gem_object *obj;
 };
 
-#define I915_RING_READ(reg) i915_safe_read(dev_priv, reg)
+#define I915_RING_READ(reg) i915_gt_read(dev_priv, reg)
+#define I915_RING_WRITE(reg, val) i915_gt_write(dev_priv, reg, val)
 
 #define I915_READ_TAIL(ring) I915_RING_READ(RING_TAIL((ring)->mmio_base))
-#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val)
+#define I915_WRITE_TAIL(ring, val) I915_RING_WRITE(RING_TAIL((ring)->mmio_base), val)
 
 #define I915_READ_START(ring) I915_RING_READ(RING_START((ring)->mmio_base))
-#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val)
+#define I915_WRITE_START(ring, val) I915_RING_WRITE(RING_START((ring)->mmio_base), val)
 
 #define I915_READ_HEAD(ring)  I915_RING_READ(RING_HEAD((ring)->mmio_base))
-#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val)
+#define I915_WRITE_HEAD(ring, val) I915_RING_WRITE(RING_HEAD((ring)->mmio_base), val)
 
 #define I915_READ_CTL(ring) I915_RING_READ(RING_CTL((ring)->mmio_base))
-#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
+#define I915_WRITE_CTL(ring, val) I915_RING_WRITE(RING_CTL((ring)->mmio_base), val)
 
-#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
 #define I915_READ_IMR(ring) I915_RING_READ(RING_IMR((ring)->mmio_base))
+#define I915_WRITE_IMR(ring, val) I915_RING_WRITE(RING_IMR((ring)->mmio_base), val)
 
 #define I915_READ_NOPID(ring) I915_RING_READ(RING_NOPID((ring)->mmio_base))
 #define I915_READ_SYNC_0(ring) I915_RING_READ(RING_SYNC_0((ring)->mmio_base))
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 26347b7..b0fb9bd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -725,8 +725,10 @@
 	ret = vram->get(dev, mem->num_pages << PAGE_SHIFT,
 			mem->page_alignment << PAGE_SHIFT, size_nc,
 			(nvbo->tile_flags >> 8) & 0xff, &node);
-	if (ret)
-		return ret;
+	if (ret) {
+		mem->mm_node = NULL;
+		return (ret == -ENOSPC) ? 0 : ret;
+	}
 
 	node->page_shift = 12;
 	if (nvbo->vma.node)
diff --git a/drivers/gpu/drm/nouveau/nouveau_mm.c b/drivers/gpu/drm/nouveau/nouveau_mm.c
index 8844b50c..7609756 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mm.c
@@ -123,7 +123,7 @@
 		return 0;
 	}
 
-	return -ENOMEM;
+	return -ENOSPC;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c
index ea00418..e57caa2 100644
--- a/drivers/gpu/drm/nouveau/nv50_instmem.c
+++ b/drivers/gpu/drm/nouveau/nv50_instmem.c
@@ -403,16 +403,24 @@
 void
 nv50_instmem_flush(struct drm_device *dev)
 {
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+	spin_lock(&dev_priv->ramin_lock);
 	nv_wr32(dev, 0x00330c, 0x00000001);
 	if (!nv_wait(dev, 0x00330c, 0x00000002, 0x00000000))
 		NV_ERROR(dev, "PRAMIN flush timeout\n");
+	spin_unlock(&dev_priv->ramin_lock);
 }
 
 void
 nv84_instmem_flush(struct drm_device *dev)
 {
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+	spin_lock(&dev_priv->ramin_lock);
 	nv_wr32(dev, 0x070000, 0x00000001);
 	if (!nv_wait(dev, 0x070000, 0x00000002, 0x00000000))
 		NV_ERROR(dev, "PRAMIN flush timeout\n");
+	spin_unlock(&dev_priv->ramin_lock);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nv50_vm.c b/drivers/gpu/drm/nouveau/nv50_vm.c
index 459ff08..6144156 100644
--- a/drivers/gpu/drm/nouveau/nv50_vm.c
+++ b/drivers/gpu/drm/nouveau/nv50_vm.c
@@ -169,7 +169,11 @@
 void
 nv50_vm_flush_engine(struct drm_device *dev, int engine)
 {
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+	spin_lock(&dev_priv->ramin_lock);
 	nv_wr32(dev, 0x100c80, (engine << 16) | 1);
 	if (!nv_wait(dev, 0x100c80, 0x00000001, 0x00000000))
 		NV_ERROR(dev, "vm flush timeout: engine %d\n", engine);
+	spin_unlock(&dev_priv->ramin_lock);
 }