Merge commit 'v2.6.38-rc8' into perf/core

Merge reason: Merge latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

24 files changed, 226 insertions, 67 deletions

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 6977a1ce9d9..f73ef4390db 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -672,7 +672,7 @@ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info)
 	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 @@ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info)
 		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/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 3dadfa2a852..28d1d3c24d6 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -164,8 +164,10 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * available. In that case we can't account for this and just
 	 * hope for the best.
 	 */
-	if ((vblrc > 0) && (abs(diff_ns) > 1000000))
+	if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
 		atomic_inc(&dev->_vblank_count[crtc]);
+		smp_mb__after_atomic_inc();
+	}
 
 	/* Invalidate all timestamps while vblank irq's are off. */
 	clear_vblank_timestamps(dev, crtc);
@@ -491,6 +493,12 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc)
 	/* Dot clock in Hz: */
 	dotclock = (u64) crtc->hwmode.clock * 1000;
 
+	/* Fields of interlaced scanout modes are only halve a frame duration.
+	 * Double the dotclock to get halve the frame-/line-/pixelduration.
+	 */
+	if (crtc->hwmode.flags & DRM_MODE_FLAG_INTERLACE)
+		dotclock *= 2;
+
 	/* Valid dotclock? */
 	if (dotclock > 0) {
 		/* Convert scanline length in pixels and video dot clock to
@@ -603,14 +611,6 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 		return -EAGAIN;
 	}
 
-	/* Don't know yet how to handle interlaced or
-	 * double scan modes. Just no-op for now.
-	 */
-	if (mode->flags & (DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLSCAN)) {
-		DRM_DEBUG("crtc %d: Noop due to unsupported mode.\n", crtc);
-		return -ENOTSUPP;
-	}
-
 	/* Get current scanout position with system timestamp.
 	 * Repeat query up to DRM_TIMESTAMP_MAXRETRIES times
 	 * if single query takes longer than max_error nanoseconds.
@@ -858,10 +858,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 	if (rc) {
 		tslot = atomic_read(&dev->_vblank_count[crtc]) + diff;
 		vblanktimestamp(dev, crtc, tslot) = t_vblank;
-		smp_wmb();
 	}
 
+	smp_mb__before_atomic_inc();
 	atomic_add(diff, &dev->_vblank_count[crtc]);
+	smp_mb__after_atomic_inc();
 }
 
 /**
@@ -1011,7 +1012,8 @@ int drm_modeset_ctl(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv)
 {
 	struct drm_modeset_ctl *modeset = data;
-	int crtc, ret = 0;
+	int ret = 0;
+	unsigned int crtc;
 
 	/* If drm_vblank_init() hasn't been called yet, just no-op */
 	if (!dev->num_crtcs)
@@ -1293,15 +1295,16 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	 * e.g., due to spurious vblank interrupts. We need to
 	 * ignore those for accounting.
 	 */
-	if (abs(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
+	if (abs64(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
 		/* Store new timestamp in ringbuffer. */
 		vblanktimestamp(dev, crtc, vblcount + 1) = tvblank;
-		smp_wmb();
 
 		/* Increment cooked vblank count. This also atomically commits
 		 * the timestamp computed above.
 		 */
+		smp_mb__before_atomic_inc();
 		atomic_inc(&dev->_vblank_count[crtc]);
+		smp_mb__after_atomic_inc();
 	} else {
 		DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
 			  crtc, (int) diff_ns);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3601466c550..4ff9b6cc973 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -865,7 +865,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		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 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		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_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 17bd766f208..e33d9be7df3 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1895,6 +1895,17 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (IS_GEN2(dev))
 		dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30));
 
+	/* 965GM sometimes incorrectly writes to hardware status page (HWS)
+	 * using 32bit addressing, overwriting memory if HWS is located
+	 * above 4GB.
+	 *
+	 * The documentation also mentions an issue with undefined
+	 * behaviour if any general state is accessed within a page above 4GB,
+	 * which also needs to be handled carefully.
+	 */
+	if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
+		dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32));
+
 	mmio_bar = IS_GEN2(dev) ? 1 : 0;
 	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, 0);
 	if (!dev_priv->regs) {
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0ad533f06af..22ec066adae 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -46,6 +46,9 @@ module_param_named(fbpercrtc, i915_fbpercrtc, int, 0400);
 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 intel_detect_pch (struct drm_device *dev)
 	}
 }
 
-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 @@ void __gen6_force_wake_get(struct drm_i915_private *dev_priv)
 		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 65dfe81d003..456f4048483 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -956,6 +956,7 @@ extern struct drm_ioctl_desc i915_ioctls[];
 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_detach_phys_object(struct drm_device *dev,
 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 @@ __i915_write(64, q)
  * 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 cf4f74c7c6f..36e66cc5225 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1398,7 +1398,7 @@ i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj)
  * 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 d2f445e825f..50ab1614571 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -772,8 +772,8 @@ i915_gem_execbuffer_sync_rings(struct drm_i915_gem_object *obj,
 	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 22a32b9932c..d64843e18df 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -349,14 +349,27 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 			(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_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 97f946dcc1a..8a9e08bf1cf 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -316,6 +316,8 @@ static void i915_hotplug_work_func(struct work_struct *work)
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *encoder;
 
+	DRM_DEBUG_KMS("running encoder hotplug functions\n");
+
 	list_for_each_entry(encoder, &mode_config->encoder_list, base.head)
 		if (encoder->hot_plug)
 			encoder->hot_plug(encoder);
@@ -1649,9 +1651,7 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 	} else {
 		hotplug_mask = SDE_CRT_HOTPLUG | SDE_PORTB_HOTPLUG |
 			       SDE_PORTC_HOTPLUG | SDE_PORTD_HOTPLUG;
-		hotplug_mask |= SDE_AUX_MASK | SDE_FDI_MASK | SDE_TRANS_MASK;
-		I915_WRITE(FDI_RXA_IMR, 0);
-		I915_WRITE(FDI_RXB_IMR, 0);
+		hotplug_mask |= SDE_AUX_MASK;
 	}
 
 	dev_priv->pch_irq_mask = ~hotplug_mask;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 729d4233b76..3e6f486f460 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 3b006536b3d..49fb54fd9a1 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1219,7 +1219,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
 	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 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
 			 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)
@@ -1630,19 +1630,19 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		struct drm_i915_gem_object *obj = to_intel_framebuffer(old_fb)->obj;
 
 		wait_event(dev_priv->pending_flip_queue,
+			   atomic_read(&dev_priv->mm.wedged) ||
 			   atomic_read(&obj->pending_flip) == 0);
 
 		/* Big Hammer, we also need to ensure that any pending
 		 * MI_WAIT_FOR_EVENT inside a user batch buffer on the
 		 * current scanout is retired before unpinning the old
 		 * framebuffer.
+		 *
+		 * This should only fail upon a hung GPU, in which case we
+		 * can safely continue.
 		 */
 		ret = i915_gem_object_flush_gpu(obj, false);
-		if (ret) {
-			i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj);
-			mutex_unlock(&dev->struct_mutex);
-			return ret;
-		}
+		(void) ret;
 	}
 
 	ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y,
@@ -2045,6 +2045,31 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 		   atomic_read(&obj->pending_flip) == 0);
 }
 
+static bool intel_crtc_driving_pch(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct intel_encoder *encoder;
+
+	/*
+	 * If there's a non-PCH eDP on this crtc, it must be DP_A, and that
+	 * must be driven by its own crtc; no sharing is possible.
+	 */
+	list_for_each_entry(encoder, &mode_config->encoder_list, base.head) {
+		if (encoder->base.crtc != crtc)
+			continue;
+
+		switch (encoder->type) {
+		case INTEL_OUTPUT_EDP:
+			if (!intel_encoder_is_pch_edp(&encoder->base))
+				return false;
+			continue;
+		}
+	}
+
+	return true;
+}
+
 static void ironlake_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -2053,6 +2078,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	int pipe = intel_crtc->pipe;
 	int plane = intel_crtc->plane;
 	u32 reg, temp;
+	bool is_pch_port = false;
 
 	if (intel_crtc->active)
 		return;
@@ -2066,7 +2092,56 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 			I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN);
 	}
 
-	ironlake_fdi_enable(crtc);
+	is_pch_port = intel_crtc_driving_pch(crtc);
+
+	if (is_pch_port)
+		ironlake_fdi_enable(crtc);
+	else {
+		/* disable CPU FDI tx and PCH FDI rx */
+		reg = FDI_TX_CTL(pipe);
+		temp = I915_READ(reg);
+		I915_WRITE(reg, temp & ~FDI_TX_ENABLE);
+		POSTING_READ(reg);
+
+		reg = FDI_RX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~(0x7 << 16);
+		temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11;
+		I915_WRITE(reg, temp & ~FDI_RX_ENABLE);
+
+		POSTING_READ(reg);
+		udelay(100);
+
+		/* Ironlake workaround, disable clock pointer after downing FDI */
+		if (HAS_PCH_IBX(dev))
+			I915_WRITE(FDI_RX_CHICKEN(pipe),
+				   I915_READ(FDI_RX_CHICKEN(pipe) &
+					     ~FDI_RX_PHASE_SYNC_POINTER_ENABLE));
+
+		/* still set train pattern 1 */
+		reg = FDI_TX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~FDI_LINK_TRAIN_NONE;
+		temp |= FDI_LINK_TRAIN_PATTERN_1;
+		I915_WRITE(reg, temp);
+
+		reg = FDI_RX_CTL(pipe);
+		temp = I915_READ(reg);
+		if (HAS_PCH_CPT(dev)) {
+			temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+			temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
+		} else {
+			temp &= ~FDI_LINK_TRAIN_NONE;
+			temp |= FDI_LINK_TRAIN_PATTERN_1;
+		}
+		/* BPC in FDI rx is consistent with that in PIPECONF */
+		temp &= ~(0x07 << 16);
+		temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11;
+		I915_WRITE(reg, temp);
+
+		POSTING_READ(reg);
+		udelay(100);
+	}
 
 	/* Enable panel fitting for LVDS */
 	if (dev_priv->pch_pf_size &&
@@ -2100,6 +2175,10 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 		intel_flush_display_plane(dev, plane);
 	}
 
+	/* Skip the PCH stuff if possible */
+	if (!is_pch_port)
+		goto done;
+
 	/* For PCH output, training FDI link */
 	if (IS_GEN6(dev))
 		gen6_fdi_link_train(crtc);
@@ -2184,7 +2263,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	I915_WRITE(reg, temp | TRANS_ENABLE);
 	if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100))
 		DRM_ERROR("failed to enable transcoder %d\n", pipe);
-
+done:
 	intel_crtc_load_lut(crtc);
 	intel_update_fbc(dev);
 	intel_crtc_update_cursor(crtc, true);
@@ -6203,7 +6282,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	 * 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);
@@ -6301,7 +6380,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	/* 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)
@@ -6496,7 +6575,7 @@ static void ironlake_disable_rc6(struct drm_device *dev)
 		POSTING_READ(RSTDBYCTL);
 	}
 
-	ironlake_disable_rc6(dev);
+	ironlake_teardown_rc6(dev);
 }
 
 static int ironlake_setup_rc6(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6d6fde85a63..34306865a5d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -14,22 +14,23 @@ struct  intel_hw_status_page {
 	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_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index d38a4d9f9b0..a52184007f5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -49,7 +49,10 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
 		DRM_ERROR("bo %p still attached to GEM object\n", bo);
 
 	nv10_mem_put_tile_region(dev, nvbo->tile, NULL);
-	nouveau_vm_put(&nvbo->vma);
+	if (nvbo->vma.node) {
+		nouveau_vm_unmap(&nvbo->vma);
+		nouveau_vm_put(&nvbo->vma);
+	}
 	kfree(nvbo);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.c b/drivers/gpu/drm/nouveau/nouveau_dma.c
index 65699bfaaae..b368ed74aad 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.c
@@ -83,7 +83,8 @@ nouveau_dma_init(struct nouveau_channel *chan)
 		return ret;
 
 	/* NV_MEMORY_TO_MEMORY_FORMAT requires a notifier object */
-	ret = nouveau_notifier_alloc(chan, NvNotify0, 32, &chan->m2mf_ntfy);
+	ret = nouveau_notifier_alloc(chan, NvNotify0, 32, 0xfd0, 0x1000,
+				     &chan->m2mf_ntfy);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 9821fcacc3d..982d70b1272 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -852,7 +852,8 @@ extern const struct ttm_mem_type_manager_func nouveau_vram_manager;
 extern int  nouveau_notifier_init_channel(struct nouveau_channel *);
 extern void nouveau_notifier_takedown_channel(struct nouveau_channel *);
 extern int  nouveau_notifier_alloc(struct nouveau_channel *, uint32_t handle,
-				   int cout, uint32_t *offset);
+				   int cout, uint32_t start, uint32_t end,
+				   uint32_t *offset);
 extern int  nouveau_notifier_offset(struct nouveau_gpuobj *, uint32_t *);
 extern int  nouveau_ioctl_notifier_alloc(struct drm_device *, void *data,
 					 struct drm_file *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 26347b7cd87..b0fb9bdcddb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -725,8 +725,10 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 	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 8844b50c3e5..7609756b6fa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mm.c
@@ -123,7 +123,7 @@ nouveau_mm_get(struct nouveau_mm *rmm, int type, u32 size, u32 size_nc,
 		return 0;
 	}
 
-	return -ENOMEM;
+	return -ENOSPC;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nouveau_notifier.c b/drivers/gpu/drm/nouveau/nouveau_notifier.c
index fe29d604b82..5ea167623a8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_notifier.c
+++ b/drivers/gpu/drm/nouveau/nouveau_notifier.c
@@ -96,7 +96,8 @@ nouveau_notifier_gpuobj_dtor(struct drm_device *dev,
 
 int
 nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle,
-		       int size, uint32_t *b_offset)
+		       int size, uint32_t start, uint32_t end,
+		       uint32_t *b_offset)
 {
 	struct drm_device *dev = chan->dev;
 	struct nouveau_gpuobj *nobj = NULL;
@@ -104,9 +105,10 @@ nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle,
 	uint32_t offset;
 	int target, ret;
 
-	mem = drm_mm_search_free(&chan->notifier_heap, size, 0, 0);
+	mem = drm_mm_search_free_in_range(&chan->notifier_heap, size, 0,
+					  start, end, 0);
 	if (mem)
-		mem = drm_mm_get_block(mem, size, 0);
+		mem = drm_mm_get_block_range(mem, size, 0, start, end);
 	if (!mem) {
 		NV_ERROR(dev, "Channel %d notifier block full\n", chan->id);
 		return -ENOMEM;
@@ -177,7 +179,8 @@ nouveau_ioctl_notifier_alloc(struct drm_device *dev, void *data,
 	if (IS_ERR(chan))
 		return PTR_ERR(chan);
 
-	ret = nouveau_notifier_alloc(chan, na->handle, na->size, &na->offset);
+	ret = nouveau_notifier_alloc(chan, na->handle, na->size, 0, 0x1000,
+				     &na->offset);
 	nouveau_channel_put(&chan);
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c
index ea0041810ae..e57caa2a00e 100644
--- a/drivers/gpu/drm/nouveau/nv50_instmem.c
+++ b/drivers/gpu/drm/nouveau/nv50_instmem.c
@@ -403,16 +403,24 @@ nv50_instmem_unmap(struct nouveau_gpuobj *gpuobj)
 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 459ff08241e..6144156f255 100644
--- a/drivers/gpu/drm/nouveau/nv50_vm.c
+++ b/drivers/gpu/drm/nouveau/nv50_vm.c
@@ -169,7 +169,11 @@ nv50_vm_flush(struct nouveau_vm *vm)
 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);
 }
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 56deae5bf02..93fa735c8c1 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3490,7 +3490,7 @@ void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track
 		track->num_texture = 16;
 		track->maxy = 4096;
 		track->separate_cube = 0;
-		track->aaresolve = true;
+		track->aaresolve = false;
 		track->aa.robj = NULL;
 	}
 
@@ -3801,8 +3801,6 @@ static int r100_startup(struct radeon_device *rdev)
 	r100_mc_program(rdev);
 	/* Resume clock */
 	r100_clock_startup(rdev);
-	/* Initialize GPU configuration (# pipes, ...) */
-//	r100_gpu_init(rdev);
 	/* Initialize GART (initialize after TTM so we can allocate
 	 * memory through TTM but finalize after TTM) */
 	r100_enable_bm(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 0e657095de7..3e7e7f9eb78 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -971,7 +971,7 @@ void radeon_compute_pll_legacy(struct radeon_pll *pll,
 		max_fractional_feed_div = pll->max_frac_feedback_div;
 	}
 
-	for (post_div = min_post_div; post_div <= max_post_div; ++post_div) {
+	for (post_div = max_post_div; post_div >= min_post_div; --post_div) {
 		uint32_t ref_div;
 
 		if ((pll->flags & RADEON_PLL_NO_ODD_POST_DIV) && (post_div & 1))
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 66324b5bb5b..cc44bdfec80 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -113,11 +113,14 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev,
 	u32 tiling_flags = 0;
 	int ret;
 	int aligned_size, size;
+	int height = mode_cmd->height;
 
 	/* need to align pitch with crtc limits */
 	mode_cmd->pitch = radeon_align_pitch(rdev, mode_cmd->width, mode_cmd->bpp, fb_tiled) * ((mode_cmd->bpp + 1) / 8);
 
-	size = mode_cmd->pitch * mode_cmd->height;
+	if (rdev->family >= CHIP_R600)
+		height = ALIGN(mode_cmd->height, 8);
+	size = mode_cmd->pitch * height;
 	aligned_size = ALIGN(size, PAGE_SIZE);
 	ret = radeon_gem_object_create(rdev, aligned_size, 0,
 				       RADEON_GEM_DOMAIN_VRAM,