Merge tag 'v3.12' into drm-intel-next

I want to merge in the new Broadwell support as a late hw enabling
pull request. But since the internal branch was based upon our
drm-intel-nightly integration branch I need to resolve all the
oustanding conflicts in drm/i915 with a backmerge to make the 60+
patches apply properly.

We'll propably have some fun because Linus will come up with a
slightly different merge solution.

Conflicts:
	drivers/gpu/drm/i915/i915_dma.c
	drivers/gpu/drm/i915/i915_drv.c
	drivers/gpu/drm/i915/intel_crt.c
	drivers/gpu/drm/i915/intel_ddi.c
	drivers/gpu/drm/i915/intel_display.c
	drivers/gpu/drm/i915/intel_dp.c
	drivers/gpu/drm/i915/intel_drv.h

All rather simple adjacent lines changed or partial backports from
-next to -fixes, with the exception of the thaw code in i915_dma.c.
That one needed a bit of shuffling to restore the intent.

Oh and the massive header file reordering in intel_drv.h is a bit
trouble. But not much.

v2: Also don't forget the fixup for the silent conflict that results
in compile fail ...

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

39 files changed, 365 insertions, 209 deletions

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index b55f138bd99..05e197d32c4 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -61,7 +61,7 @@ static int drm_version(struct drm_device *dev, void *data,
 
 /** Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
-	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
@@ -332,9 +332,16 @@ long drm_ioctl(struct file *filp,
 		cmd = ioctl->cmd_drv;
 	}
 	else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) {
+		u32 drv_size;
+
 		ioctl = &drm_ioctls[nr];
-		cmd = ioctl->cmd;
+
+		drv_size = _IOC_SIZE(ioctl->cmd);
 		usize = asize = _IOC_SIZE(cmd);
+		if (drv_size > asize)
+			asize = drv_size;
+
+		cmd = ioctl->cmd;
 	} else
 		goto err_i1;
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 72035234545..0a19401aff8 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -412,14 +412,6 @@ static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode)
 		return;
 
 	/*
-	 * fbdev->blank can be called from irq context in case of a panic.
-	 * Since we already have our own special panic handler which will
-	 * restore the fbdev console mode completely, just bail out early.
-	 */
-	if (oops_in_progress)
-		return;
-
-	/*
 	 * For each CRTC in this fb, turn the connectors on/off.
 	 */
 	drm_modeset_lock_all(dev);
diff --git a/drivers/gpu/drm/gma500/gtt.c b/drivers/gpu/drm/gma500/gtt.c
index 92babac362e..2db731f0093 100644
--- a/drivers/gpu/drm/gma500/gtt.c
+++ b/drivers/gpu/drm/gma500/gtt.c
@@ -204,6 +204,7 @@ static int psb_gtt_attach_pages(struct gtt_range *gt)
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
+	gt->npage = gt->gem.size / PAGE_SIZE;
 	gt->pages = pages;
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 6eecce70fa7..0cab2d04513 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1290,12 +1290,9 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	 * then we do not take part in VGA arbitration and the
 	 * vga_client_register() fails with -ENODEV.
 	 */
-	if (!HAS_PCH_SPLIT(dev)) {
-		ret = vga_client_register(dev->pdev, dev, NULL,
-					  i915_vga_set_decode);
-		if (ret && ret != -ENODEV)
-			goto out;
-	}
+	ret = vga_client_register(dev->pdev, dev, NULL, i915_vga_set_decode);
+	if (ret && ret != -ENODEV)
+		goto out;
 
 	intel_register_dsm_handler();
 
@@ -1316,9 +1313,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	intel_power_domains_init_hw(dev);
 
-	/* Keep VGA alive until i915_disable_vga_mem() */
-	intel_display_power_get(dev, POWER_DOMAIN_VGA);
-
 	/* Important: The output setup functions called by modeset_init need
 	 * working irqs for e.g. gmbus and dp aux transfers. */
 	intel_modeset_init(dev);
@@ -1358,13 +1352,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	 */
 	intel_fbdev_initial_config(dev);
 
-	/*
-	 * Must do this after fbcon init so that
-	 * vgacon_save_screen() works during the handover.
-	 */
-	i915_disable_vga_mem(dev);
-	intel_display_power_put(dev, POWER_DOMAIN_VGA);
-
 	/* Only enable hotplug handling once the fbdev is fully set up. */
 	dev_priv->enable_hotplug_processing = true;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 1041644030b..a0804fa1e30 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -508,6 +508,8 @@ static int i915_drm_freeze(struct drm_device *dev)
 		intel_modeset_suspend_hw(dev);
 	}
 
+	i915_gem_suspend_gtt_mappings(dev);
+
 	i915_save_state(dev);
 
 	intel_opregion_fini(dev);
@@ -656,6 +658,9 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 
 static int i915_drm_thaw(struct drm_device *dev)
 {
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		i915_check_and_clear_faults(dev);
+
 	return __i915_drm_thaw(dev, true);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f2324bc4680..b12d942ab09 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -528,10 +528,12 @@ struct i915_address_space {
 
 	/* FIXME: Need a more generic return type */
 	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
-				     enum i915_cache_level level);
+				     enum i915_cache_level level,
+				     bool valid); /* Create a valid PTE */
 	void (*clear_range)(struct i915_address_space *vm,
 			    unsigned int first_entry,
-			    unsigned int num_entries);
+			    unsigned int num_entries,
+			    bool use_scratch);
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
 			       unsigned int first_entry,
@@ -2182,6 +2184,8 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
 void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			      struct drm_i915_gem_object *obj);
 
+void i915_check_and_clear_faults(struct drm_device *dev);
+void i915_gem_suspend_gtt_mappings(struct drm_device *dev);
 void i915_gem_restore_gtt_mappings(struct drm_device *dev);
 int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj);
 void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e999496532c..c4c42e7cbd7 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -58,9 +58,10 @@
 #define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
 
 static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -79,9 +80,10 @@ static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 }
 
 static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -105,9 +107,10 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
 
 static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	/* Mark the page as writeable.  Other platforms don't have a
@@ -122,9 +125,10 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 }
 
 static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	if (level != I915_CACHE_NONE)
@@ -134,9 +138,10 @@ static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 }
 
 static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
-				      enum i915_cache_level level)
+				      enum i915_cache_level level,
+				      bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -236,7 +241,8 @@ static int gen6_ppgtt_enable(struct drm_device *dev)
 /* PPGTT support for Sandybdrige/Gen6 and later */
 static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 				   unsigned first_entry,
-				   unsigned num_entries)
+				   unsigned num_entries,
+				   bool use_scratch)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
@@ -245,7 +251,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
 
 	while (num_entries) {
 		last_pte = first_pte + num_entries;
@@ -282,7 +288,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 		dma_addr_t page_addr;
 
 		page_addr = sg_page_iter_dma_address(&sg_iter);
-		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level);
+		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level, true);
 		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
 			kunmap_atomic(pt_vaddr);
 			act_pt++;
@@ -367,7 +373,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	}
 
 	ppgtt->base.clear_range(&ppgtt->base, 0,
-				ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES);
+				ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES, true);
 
 	ppgtt->pd_offset = first_pd_entry_in_global_pt * sizeof(gen6_gtt_pte_t);
 
@@ -444,7 +450,8 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 {
 	ppgtt->base.clear_range(&ppgtt->base,
 				i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
-				obj->base.size >> PAGE_SHIFT);
+				obj->base.size >> PAGE_SHIFT,
+				true);
 }
 
 extern int intel_iommu_gfx_mapped;
@@ -485,15 +492,65 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible)
 		dev_priv->mm.interruptible = interruptible;
 }
 
+void i915_check_and_clear_faults(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring;
+	int i;
+
+	if (INTEL_INFO(dev)->gen < 6)
+		return;
+
+	for_each_ring(ring, dev_priv, i) {
+		u32 fault_reg;
+		fault_reg = I915_READ(RING_FAULT_REG(ring));
+		if (fault_reg & RING_FAULT_VALID) {
+			DRM_DEBUG_DRIVER("Unexpected fault\n"
+					 "\tAddr: 0x%08lx\\n"
+					 "\tAddress space: %s\n"
+					 "\tSource ID: %d\n"
+					 "\tType: %d\n",
+					 fault_reg & PAGE_MASK,
+					 fault_reg & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT",
+					 RING_FAULT_SRCID(fault_reg),
+					 RING_FAULT_FAULT_TYPE(fault_reg));
+			I915_WRITE(RING_FAULT_REG(ring),
+				   fault_reg & ~RING_FAULT_VALID);
+		}
+	}
+	POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS]));
+}
+
+void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Don't bother messing with faults pre GEN6 as we have little
+	 * documentation supporting that it's a good idea.
+	 */
+	if (INTEL_INFO(dev)->gen < 6)
+		return;
+
+	i915_check_and_clear_faults(dev);
+
+	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
+				       dev_priv->gtt.base.start / PAGE_SIZE,
+				       dev_priv->gtt.base.total / PAGE_SIZE,
+				       false);
+}
+
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 
+	i915_check_and_clear_faults(dev);
+
 	/* First fill our portion of the GTT with scratch pages */
 	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
 				       dev_priv->gtt.base.start / PAGE_SIZE,
-				       dev_priv->gtt.base.total / PAGE_SIZE);
+				       dev_priv->gtt.base.total / PAGE_SIZE,
+				       true);
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		i915_gem_clflush_object(obj, obj->pin_display);
@@ -536,7 +593,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_page_iter_dma_address(&sg_iter);
-		iowrite32(vm->pte_encode(addr, level), &gtt_entries[i]);
+		iowrite32(vm->pte_encode(addr, level, true), &gtt_entries[i]);
 		i++;
 	}
 
@@ -548,7 +605,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	 */
 	if (i != 0)
 		WARN_ON(readl(&gtt_entries[i-1]) !=
-			vm->pte_encode(addr, level));
+			vm->pte_encode(addr, level, true));
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -560,7 +617,8 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  unsigned int first_entry,
-				  unsigned int num_entries)
+				  unsigned int num_entries,
+				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
@@ -573,7 +631,8 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 		 first_entry, num_entries, max_entries))
 		num_entries = max_entries;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch);
+
 	for (i = 0; i < num_entries; i++)
 		iowrite32(scratch_pte, &gtt_base[i]);
 	readl(gtt_base);
@@ -594,7 +653,8 @@ static void i915_ggtt_insert_entries(struct i915_address_space *vm,
 
 static void i915_ggtt_clear_range(struct i915_address_space *vm,
 				  unsigned int first_entry,
-				  unsigned int num_entries)
+				  unsigned int num_entries,
+				  bool unused)
 {
 	intel_gtt_clear_range(first_entry, num_entries);
 }
@@ -622,7 +682,8 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 
 	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
 				       entry,
-				       obj->base.size >> PAGE_SHIFT);
+				       obj->base.size >> PAGE_SHIFT,
+				       true);
 
 	obj->has_global_gtt_mapping = 0;
 }
@@ -709,11 +770,11 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 		const unsigned long count = (hole_end - hole_start) / PAGE_SIZE;
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
 			      hole_start, hole_end);
-		ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count);
+		ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count, true);
 	}
 
 	/* And finally clear the reserved guard page */
-	ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1);
+	ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1, true);
 }
 
 static bool
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4328e3bd63b..3f303ba995c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -657,6 +657,10 @@
 #define   ARB_MODE_SWIZZLE_IVB	(1<<5)
 #define RENDER_HWS_PGA_GEN7	(0x04080)
 #define RING_FAULT_REG(ring)	(0x4094 + 0x100*(ring)->id)
+#define   RING_FAULT_GTTSEL_MASK (1<<11)
+#define   RING_FAULT_SRCID(x)	((x >> 3) & 0xff)
+#define   RING_FAULT_FAULT_TYPE(x) ((x >> 1) & 0x3)
+#define   RING_FAULT_VALID	(1<<0)
 #define DONE_REG		0x40b0
 #define BSD_HWS_PGA_GEN7	(0x04180)
 #define BLT_HWS_PGA_GEN7	(0x04280)
@@ -4044,6 +4048,9 @@
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
 
+#define HSW_SCRATCH1				0xb038
+#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
+
 #define HSW_FUSE_STRAP		0x42014
 #define  HSW_CDCLK_LIMIT	(1 << 24)
 
@@ -4439,7 +4446,9 @@
 #define FDI_RX_CHICKEN(pipe) _PIPE(pipe, _FDI_RXA_CHICKEN, _FDI_RXB_CHICKEN)
 
 #define SOUTH_DSPCLK_GATE_D	0xc2020
+#define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1<<30)
 #define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1<<29)
+#define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1<<14)
 #define  PCH_LP_PARTITION_LEVEL_DISABLE  (1<<12)
 
 /* CPU: FDI_TX */
@@ -4895,6 +4904,9 @@
 #define GEN7_ROW_CHICKEN2_GT2		0xf4f4
 #define   DOP_CLOCK_GATING_DISABLE	(1<<0)
 
+#define HSW_ROW_CHICKEN3		0xe49c
+#define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
+
 #define G4X_AUD_VID_DID			(dev_priv->info->display_mmio_offset + 0x62020)
 #define INTEL_AUDIO_DEVCL		0x808629FB
 #define INTEL_AUDIO_DEVBLC		0x80862801
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 40a8f59fa41..f34252d134b 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2421,9 +2421,10 @@ static void intel_fdi_normal_train(struct drm_crtc *crtc)
 			   FDI_FE_ERRC_ENABLE);
 }
 
-static bool pipe_has_enabled_pch(struct intel_crtc *intel_crtc)
+static bool pipe_has_enabled_pch(struct intel_crtc *crtc)
 {
-	return intel_crtc->base.enabled && intel_crtc->config.has_pch_encoder;
+	return crtc->base.enabled && crtc->active &&
+		crtc->config.has_pch_encoder;
 }
 
 static void ivb_modeset_global_resources(struct drm_device *dev)
@@ -3074,6 +3075,48 @@ static void ironlake_pch_transcoder_set_timings(struct intel_crtc *crtc,
 		   I915_READ(VSYNCSHIFT(cpu_transcoder)));
 }
 
+static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t temp;
+
+	temp = I915_READ(SOUTH_CHICKEN1);
+	if (temp & FDI_BC_BIFURCATION_SELECT)
+		return;
+
+	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE);
+	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE);
+
+	temp |= FDI_BC_BIFURCATION_SELECT;
+	DRM_DEBUG_KMS("enabling fdi C rx\n");
+	I915_WRITE(SOUTH_CHICKEN1, temp);
+	POSTING_READ(SOUTH_CHICKEN1);
+}
+
+static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
+{
+	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	switch (intel_crtc->pipe) {
+	case PIPE_A:
+		break;
+	case PIPE_B:
+		if (intel_crtc->config.fdi_lanes > 2)
+			WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT);
+		else
+			cpt_enable_fdi_bc_bifurcation(dev);
+
+		break;
+	case PIPE_C:
+		cpt_enable_fdi_bc_bifurcation(dev);
+
+		break;
+	default:
+		BUG();
+	}
+}
+
 /*
  * Enable PCH resources required for PCH ports:
  *   - PCH PLLs
@@ -3092,6 +3135,9 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 
 	assert_pch_transcoder_disabled(dev_priv, pipe);
 
+	if (IS_IVYBRIDGE(dev))
+		ivybridge_update_fdi_bc_bifurcation(intel_crtc);
+
 	/* Write the TU size bits before fdi link training, so that error
 	 * detection works. */
 	I915_WRITE(FDI_RX_TUSIZE1(pipe),
@@ -4156,8 +4202,6 @@ static void intel_connector_check_state(struct intel_connector *connector)
  * consider. */
 void intel_connector_dpms(struct drm_connector *connector, int mode)
 {
-	struct intel_encoder *encoder = intel_attached_encoder(connector);
-
 	/* All the simple cases only support two dpms states. */
 	if (mode != DRM_MODE_DPMS_ON)
 		mode = DRM_MODE_DPMS_OFF;
@@ -4168,10 +4212,8 @@ void intel_connector_dpms(struct drm_connector *connector, int mode)
 	connector->dpms = mode;
 
 	/* Only need to change hw state when actually enabled */
-	if (encoder->base.crtc)
-		intel_encoder_dpms(encoder, mode);
-	else
-		WARN_ON(encoder->connectors_active != false);
+	if (connector->encoder)
+		intel_encoder_dpms(to_intel_encoder(connector->encoder), mode);
 
 	intel_modeset_check_state(connector->dev);
 }
@@ -5849,48 +5891,6 @@ static bool ironlake_compute_clocks(struct drm_crtc *crtc,
 	return true;
 }
 
-static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t temp;
-
-	temp = I915_READ(SOUTH_CHICKEN1);
-	if (temp & FDI_BC_BIFURCATION_SELECT)
-		return;
-
-	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE);
-	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE);
-
-	temp |= FDI_BC_BIFURCATION_SELECT;
-	DRM_DEBUG_KMS("enabling fdi C rx\n");
-	I915_WRITE(SOUTH_CHICKEN1, temp);
-	POSTING_READ(SOUTH_CHICKEN1);
-}
-
-static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
-{
-	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	switch (intel_crtc->pipe) {
-	case PIPE_A:
-		break;
-	case PIPE_B:
-		if (intel_crtc->config.fdi_lanes > 2)
-			WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT);
-		else
-			cpt_enable_fdi_bc_bifurcation(dev);
-
-		break;
-	case PIPE_C:
-		cpt_enable_fdi_bc_bifurcation(dev);
-
-		break;
-	default:
-		BUG();
-	}
-}
-
 int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp)
 {
 	/*
@@ -6079,9 +6079,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 					     &intel_crtc->config.fdi_m_n);
 	}
 
-	if (IS_IVYBRIDGE(dev))
-		ivybridge_update_fdi_bc_bifurcation(intel_crtc);
-
 	ironlake_set_pipeconf(crtc);
 
 	/* Set up the display plane register */
@@ -10498,33 +10495,6 @@ static void i915_disable_vga(struct drm_device *dev)
 	POSTING_READ(vga_reg);
 }
 
-static void i915_enable_vga_mem(struct drm_device *dev)
-{
-	/* Enable VGA memory on Intel HD */
-	if (HAS_PCH_SPLIT(dev)) {
-		vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO);
-		outb(inb(VGA_MSR_READ) | VGA_MSR_MEM_EN, VGA_MSR_WRITE);
-		vga_set_legacy_decoding(dev->pdev, VGA_RSRC_LEGACY_IO |
-						   VGA_RSRC_LEGACY_MEM |
-						   VGA_RSRC_NORMAL_IO |
-						   VGA_RSRC_NORMAL_MEM);
-		vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
-	}
-}
-
-void i915_disable_vga_mem(struct drm_device *dev)
-{
-	/* Disable VGA memory on Intel HD */
-	if (HAS_PCH_SPLIT(dev)) {
-		vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO);
-		outb(inb(VGA_MSR_READ) & ~VGA_MSR_MEM_EN, VGA_MSR_WRITE);
-		vga_set_legacy_decoding(dev->pdev, VGA_RSRC_LEGACY_IO |
-						   VGA_RSRC_NORMAL_IO |
-						   VGA_RSRC_NORMAL_MEM);
-		vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
-	}
-}
-
 void intel_modeset_init_hw(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -10810,7 +10780,6 @@ void i915_redisable_vga(struct drm_device *dev)
 	if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
 		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
 		i915_disable_vga(dev);
-		i915_disable_vga_mem(dev);
 	}
 }
 
@@ -11017,8 +10986,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	intel_disable_fbc(dev);
 
-	i915_enable_vga_mem(dev);
-
 	intel_disable_gt_powersave(dev);
 
 	ironlake_teardown_rc6(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 68357777e74..7619eae35b2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1484,6 +1484,26 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 		ironlake_check_encoder_dotclock(pipe_config, dotclock);
 
 	pipe_config->adjusted_mode.crtc_clock = dotclock;
+
+	if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp &&
+	    pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) {
+		/*
+		 * This is a big fat ugly hack.
+		 *
+		 * Some machines in UEFI boot mode provide us a VBT that has 18
+		 * bpp and 1.62 GHz link bandwidth for eDP, which for reasons
+		 * unknown we fail to light up. Yet the same BIOS boots up with
+		 * 24 bpp and 2.7 GHz link. Use the same bpp as the BIOS uses as
+		 * max, not what it tells us to use.
+		 *
+		 * Note: This will still be broken if the eDP panel is not lit
+		 * up by the BIOS, and thus we can't get the mode at module
+		 * load.
+		 */
+		DRM_DEBUG_KMS("pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n",
+			      pipe_config->pipe_bpp, dev_priv->vbt.edp_bpp);
+		dev_priv->vbt.edp_bpp = pipe_config->pipe_bpp;
+	}
 }
 
 static bool is_edp_psr(struct drm_device *dev)
@@ -1551,7 +1571,7 @@ static void intel_edp_psr_setup(struct intel_dp *intel_dp)
 
 	/* Avoid continuous PSR exit by masking memup and hpd */
 	I915_WRITE(EDP_PSR_DEBUG_CTL(dev), EDP_PSR_DEBUG_MASK_MEMUP |
-		   EDP_PSR_DEBUG_MASK_HPD);
+		   EDP_PSR_DEBUG_MASK_HPD | EDP_PSR_DEBUG_MASK_LPSP);
 
 	intel_dp->psr_setup_done = true;
 }
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index ae0c843dd26..b0ef5583308 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -707,6 +707,22 @@ static const struct dmi_system_id intel_no_lvds[] = {
 	},
 	{
 		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D410PT",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_MATCH(DMI_BOARD_NAME, "D410PT"),
+		},
+	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D425KT",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "D425KT"),
+		},
+	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
 		.ident = "Intel D510MO",
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 97009ee387c..09ac9e79830 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5008,7 +5008,9 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 	 * gating for the panel power sequencer or it will fail to
 	 * start up when no ports are active.
 	 */
-	I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE);
+	I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE |
+		   PCH_DPLUNIT_CLOCK_GATE_DISABLE |
+		   PCH_CPUNIT_CLOCK_GATE_DISABLE);
 	I915_WRITE(SOUTH_CHICKEN2, I915_READ(SOUTH_CHICKEN2) |
 		   DPLS_EDP_PPS_FIX_DIS);
 	/* The below fixes the weird display corruption, a few pixels shifted
@@ -5202,6 +5204,11 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
 			GEN7_WA_L3_CHICKEN_MODE);
 
+	/* L3 caching of data atomics doesn't work -- disable it. */
+	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+	I915_WRITE(HSW_ROW_CHICKEN3,
+		   _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
index 37712a6df92..e290cfa4ace 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
@@ -113,7 +113,7 @@ nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine,
 		pmc->use_msi = false;
 		break;
 	default:
-		pmc->use_msi = nouveau_boolopt(device->cfgopt, "NvMSI", true);
+		pmc->use_msi = nouveau_boolopt(device->cfgopt, "NvMSI", false);
 		if (pmc->use_msi) {
 			pmc->use_msi = pci_enable_msi(device->pdev) == 0;
 			if (pmc->use_msi) {
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 32923d2f600..5e891b226ac 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -707,24 +707,37 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 	switch (connector->connector_type) {
 	case DRM_MODE_CONNECTOR_DVII:
 	case DRM_MODE_CONNECTOR_HDMIB: /* HDMI-B is basically DL-DVI; analog works fine */
-		if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) ||
-		    (drm_detect_hdmi_monitor(radeon_connector->edid) &&
-		     (radeon_connector->audio == RADEON_AUDIO_AUTO)))
-			return ATOM_ENCODER_MODE_HDMI;
-		else if (radeon_connector->use_digital)
+		if (radeon_audio != 0) {
+			if (radeon_connector->use_digital &&
+			    (radeon_connector->audio == RADEON_AUDIO_ENABLE))
+				return ATOM_ENCODER_MODE_HDMI;
+			else if (drm_detect_hdmi_monitor(radeon_connector->edid) &&
+				 (radeon_connector->audio == RADEON_AUDIO_AUTO))
+				return ATOM_ENCODER_MODE_HDMI;
+			else if (radeon_connector->use_digital)
+				return ATOM_ENCODER_MODE_DVI;
+			else
+				return ATOM_ENCODER_MODE_CRT;
+		} else if (radeon_connector->use_digital) {
 			return ATOM_ENCODER_MODE_DVI;
-		else
+		} else {
 			return ATOM_ENCODER_MODE_CRT;
+		}
 		break;
 	case DRM_MODE_CONNECTOR_DVID:
 	case DRM_MODE_CONNECTOR_HDMIA:
 	default:
-		if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) ||
-		    (drm_detect_hdmi_monitor(radeon_connector->edid) &&
-		     (radeon_connector->audio == RADEON_AUDIO_AUTO)))
-			return ATOM_ENCODER_MODE_HDMI;
-		else
+		if (radeon_audio != 0) {
+			if (radeon_connector->audio == RADEON_AUDIO_ENABLE)
+				return ATOM_ENCODER_MODE_HDMI;
+			else if (drm_detect_hdmi_monitor(radeon_connector->edid) &&
+				 (radeon_connector->audio == RADEON_AUDIO_AUTO))
+				return ATOM_ENCODER_MODE_HDMI;
+			else
+				return ATOM_ENCODER_MODE_DVI;
+		} else {
 			return ATOM_ENCODER_MODE_DVI;
+		}
 		break;
 	case DRM_MODE_CONNECTOR_LVDS:
 		return ATOM_ENCODER_MODE_LVDS;
@@ -732,14 +745,19 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 	case DRM_MODE_CONNECTOR_DisplayPort:
 		dig_connector = radeon_connector->con_priv;
 		if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
-		    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP))
+		    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
 			return ATOM_ENCODER_MODE_DP;
-		else if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) ||
-			 (drm_detect_hdmi_monitor(radeon_connector->edid) &&
-			  (radeon_connector->audio == RADEON_AUDIO_AUTO)))
-			return ATOM_ENCODER_MODE_HDMI;
-		else
+		} else if (radeon_audio != 0) {
+			if (radeon_connector->audio == RADEON_AUDIO_ENABLE)
+				return ATOM_ENCODER_MODE_HDMI;
+			else if (drm_detect_hdmi_monitor(radeon_connector->edid) &&
+				 (radeon_connector->audio == RADEON_AUDIO_AUTO))
+				return ATOM_ENCODER_MODE_HDMI;
+			else
+				return ATOM_ENCODER_MODE_DVI;
+		} else {
 			return ATOM_ENCODER_MODE_DVI;
+		}
 		break;
 	case DRM_MODE_CONNECTOR_eDP:
 		return ATOM_ENCODER_MODE_DP;
@@ -1655,7 +1673,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			 * does the same thing and more.
 			 */
 			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) &&
-			    (rdev->family != CHIP_RS880))
+			    (rdev->family != CHIP_RS780) && (rdev->family != CHIP_RS880))
 				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index b162e98a295..9b6950d9b3c 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -1930,7 +1930,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			tmp = RREG32(MC_PMG_CMD_MRS);
@@ -1945,7 +1945,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		case MC_SEQ_RESERVE_M >> 2:
@@ -1959,7 +1959,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index d02fd1c045d..9cd2bc989ac 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -77,6 +77,8 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev);
 static void cik_program_aspm(struct radeon_device *rdev);
 static void cik_init_pg(struct radeon_device *rdev);
 static void cik_init_cg(struct radeon_device *rdev);
+static void cik_fini_pg(struct radeon_device *rdev);
+static void cik_fini_cg(struct radeon_device *rdev);
 static void cik_enable_gui_idle_interrupt(struct radeon_device *rdev,
 					  bool enable);
 
@@ -1692,6 +1694,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 			       fw_name);
 			release_firmware(rdev->smc_fw);
 			rdev->smc_fw = NULL;
+			err = 0;
 		} else if (rdev->smc_fw->size != smc_req_size) {
 			printk(KERN_ERR
 			       "cik_smc: Bogus length %zu in firmware \"%s\"\n",
@@ -3180,6 +3183,7 @@ int cik_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
 	if (r) {
 		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
+		radeon_scratch_free(rdev, scratch);
 		return r;
 	}
 	ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1);
@@ -3196,6 +3200,8 @@ int cik_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	r = radeon_fence_wait(ib.fence, false);
 	if (r) {
 		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+		radeon_scratch_free(rdev, scratch);
+		radeon_ib_free(rdev, &ib);
 		return r;
 	}
 	for (i = 0; i < rdev->usec_timeout; i++) {
@@ -4185,6 +4191,10 @@ static void cik_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	/* disable CG/PG */
+	cik_fini_pg(rdev);
+	cik_fini_cg(rdev);
+
 	/* stop the rlc */
 	cik_rlc_stop(rdev);
 
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 85a69d2ea3d..9fcd338c0fc 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -113,6 +113,9 @@ void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	u8 *sadb;
 	int sad_count;
 
+	/* XXX: setting this register causes hangs on some asics */
+	return;
+
 	if (!dig->afmt->pin)
 		return;
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 555164e270a..b5c67a99dda 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3131,7 +3131,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.sx_max_export_size = 256;
 		rdev->config.evergreen.sx_max_export_pos_size = 64;
 		rdev->config.evergreen.sx_max_export_smx_size = 192;
-		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.max_hw_contexts = 4;
 		rdev->config.evergreen.sq_num_cf_insts = 2;
 
 		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index f71ce390aeb..57fcc4b16a5 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -67,6 +67,9 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	u8 *sadb;
 	int sad_count;
 
+	/* XXX: setting this register causes hangs on some asics */
+	return;
+
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
 		if (connector->encoder == encoder)
 			radeon_connector = to_radeon_connector(connector);
@@ -288,8 +291,8 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
 	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
-	       HDMI_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI_ACR_SOURCE); /* select SW CTS value */
+	       HDMI_ACR_SOURCE | /* select SW CTS value */
+	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 8768fd6a1e2..4f6d2962767 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -1501,7 +1501,7 @@
  * 6. COMMAND [29:22] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1516,7 +1516,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 71399065db0..b41905573cd 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2635,7 +2635,7 @@ int kv_dpm_init(struct radeon_device *rdev)
 	pi->caps_sclk_ds = true;
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
-	pi->bapm_enable = true;
+	pi->bapm_enable = false;
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 93c1f9ef5da..cac2866d79d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -804,6 +804,7 @@ int ni_init_microcode(struct radeon_device *rdev)
 			       fw_name);
 			release_firmware(rdev->smc_fw);
 			rdev->smc_fw = NULL;
+			err = 0;
 		} else if (rdev->smc_fw->size != smc_req_size) {
 			printk(KERN_ERR
 			       "ni_mc: Bogus length %zu in firmware \"%s\"\n",
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 2a1b1876b43..f9be22062df 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2302,6 +2302,7 @@ int r600_init_microcode(struct radeon_device *rdev)
 			       fw_name);
 			release_firmware(rdev->smc_fw);
 			rdev->smc_fw = NULL;
+			err = 0;
 		} else if (rdev->smc_fw->size != smc_req_size) {
 			printk(KERN_ERR
 			       "smc: Bogus length %zu in firmware \"%s\"\n",
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index b0fa6002af3..06022e3b9c3 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -57,15 +57,15 @@ enum r600_hdmi_iec_status_bits {
 static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
     /*	     32kHz	  44.1kHz	48kHz    */
     /* Clock      N     CTS      N     CTS      N     CTS */
-    {  25174,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
+    {  25175,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
     {  25200,  4096,  25200,  6272,  28000,  6144,  25200 }, /*  25.20       MHz */
     {  27000,  4096,  27000,  6272,  30000,  6144,  27000 }, /*  27.00       MHz */
     {  27027,  4096,  27027,  6272,  30030,  6144,  27027 }, /*  27.00*1.001 MHz */
     {  54000,  4096,  54000,  6272,  60000,  6144,  54000 }, /*  54.00       MHz */
     {  54054,  4096,  54054,  6272,  60060,  6144,  54054 }, /*  54.00*1.001 MHz */
-    {  74175, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
+    {  74176, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
     {  74250,  4096,  74250,  6272,  82500,  6144,  74250 }, /*  74.25       MHz */
-    { 148351, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
+    { 148352, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
     { 148500,  4096, 148500,  6272, 165000,  6144, 148500 }, /* 148.50       MHz */
     {      0,  4096,      0,  6272,      0,  6144,      0 }  /* Other */
 };
@@ -75,8 +75,15 @@ static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
  */
 static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq)
 {
-	if (*CTS == 0)
-		*CTS = clock * N / (128 * freq) * 1000;
+	u64 n;
+	u32 d;
+
+	if (*CTS == 0) {
+		n = (u64)clock * (u64)N * 1000ULL;
+		d = 128 * freq;
+		do_div(n, d);
+		*CTS = n;
+	}
 	DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n",
 		  N, *CTS, freq);
 }
@@ -302,6 +309,9 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	u8 *sadb;
 	int sad_count;
 
+	/* XXX: setting this register causes hangs on some asics */
+	return;
+
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
 		if (connector->encoder == encoder)
 			radeon_connector = to_radeon_connector(connector);
@@ -444,8 +454,8 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	}
 
 	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
-	       HDMI0_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI0_ACR_SOURCE); /* select SW CTS value */
+	       HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+	       HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
 	       HDMI0_NULL_SEND | /* send null packets when required */
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index e673fe26ea8..7b3c7b5932c 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1523,7 +1523,7 @@
  */
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a400ac1c414..24f4960f59e 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1272,8 +1272,8 @@ struct radeon_blacklist_clocks
 struct radeon_clock_and_voltage_limits {
 	u32 sclk;
 	u32 mclk;
-	u32 vddc;
-	u32 vddci;
+	u16 vddc;
+	u16 vddci;
 };
 
 struct radeon_clock_array {
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 79159b5da05..64565732cb9 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1658,9 +1658,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.underscan_vborder_property,
 						      0);
-			drm_object_attach_property(&radeon_connector->base.base,
-						   rdev->mode_info.audio_property,
-						   RADEON_AUDIO_DISABLE);
+			if (radeon_audio != 0)
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.audio_property,
+							   (radeon_audio == 1) ?
+							   RADEON_AUDIO_AUTO :
+							   RADEON_AUDIO_DISABLE);
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
 			if (connector_type == DRM_MODE_CONNECTOR_HDMIB)
@@ -1754,10 +1757,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 							      rdev->mode_info.underscan_vborder_property,
 							      0);
 			}
-			if (ASIC_IS_DCE2(rdev)) {
+			if (ASIC_IS_DCE2(rdev) && (radeon_audio != 0)) {
 				drm_object_attach_property(&radeon_connector->base.base,
-							      rdev->mode_info.audio_property,
-							      RADEON_AUDIO_DISABLE);
+							   rdev->mode_info.audio_property,
+							   (radeon_audio == 1) ?
+							   RADEON_AUDIO_AUTO :
+							   RADEON_AUDIO_DISABLE);
 			}
 			if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 				radeon_connector->dac_load_detect = true;
@@ -1799,10 +1804,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 							      rdev->mode_info.underscan_vborder_property,
 							      0);
 			}
-			if (ASIC_IS_DCE2(rdev)) {
+			if (ASIC_IS_DCE2(rdev) && (radeon_audio != 0)) {
 				drm_object_attach_property(&radeon_connector->base.base,
-							      rdev->mode_info.audio_property,
-							      RADEON_AUDIO_DISABLE);
+							   rdev->mode_info.audio_property,
+							   (radeon_audio == 1) ?
+							   RADEON_AUDIO_AUTO :
+							   RADEON_AUDIO_DISABLE);
 			}
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
@@ -1843,10 +1850,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 							      rdev->mode_info.underscan_vborder_property,
 							      0);
 			}
-			if (ASIC_IS_DCE2(rdev)) {
+			if (ASIC_IS_DCE2(rdev) && (radeon_audio != 0)) {
 				drm_object_attach_property(&radeon_connector->base.base,
-							      rdev->mode_info.audio_property,
-							      RADEON_AUDIO_DISABLE);
+							   rdev->mode_info.audio_property,
+							   (radeon_audio == 1) ?
+							   RADEON_AUDIO_AUTO :
+							   RADEON_AUDIO_DISABLE);
 			}
 			connector->interlace_allowed = true;
 			/* in theory with a DP to VGA converter... */
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 66c22283663..80285e35bc6 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -85,9 +85,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		   VRAM, also but everything into VRAM on AGP cards to avoid
 		   image corruptions */
 		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
-		    p->rdev->family < CHIP_PALM &&
 		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
-
+			/* TODO: is this still needed for NI+ ? */
 			p->relocs[i].lobj.domain =
 				RADEON_GEM_DOMAIN_VRAM;
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 22f685827b7..b01f231c2f1 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -152,7 +152,7 @@ int radeon_benchmarking = 0;
 int radeon_testing = 0;
 int radeon_connector_table = 0;
 int radeon_tv = 1;
-int radeon_audio = 1;
+int radeon_audio = -1;
 int radeon_disp_priority = 0;
 int radeon_hw_i2c = 0;
 int radeon_pcie_gen2 = -1;
@@ -195,7 +195,7 @@ module_param_named(connector_table, radeon_connector_table, int, 0444);
 MODULE_PARM_DESC(tv, "TV enable (0 = disable)");
 module_param_named(tv, radeon_tv, int, 0444);
 
-MODULE_PARM_DESC(audio, "Audio enable (1 = enable)");
+MODULE_PARM_DESC(audio, "Audio enable (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(audio, radeon_audio, int, 0444);
 
 MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)");
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index ac07ad1d4f8..4f6b7fc7ad3 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -945,6 +945,8 @@ void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 		if (enable) {
 			mutex_lock(&rdev->pm.mutex);
 			rdev->pm.dpm.uvd_active = true;
+			/* disable this for now */
+#if 0
 			if ((rdev->pm.dpm.sd == 1) && (rdev->pm.dpm.hd == 0))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_SD;
 			else if ((rdev->pm.dpm.sd == 2) && (rdev->pm.dpm.hd == 0))
@@ -954,6 +956,7 @@ void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 			else if ((rdev->pm.dpm.sd == 0) && (rdev->pm.dpm.hd == 2))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD2;
 			else
+#endif
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD;
 			rdev->pm.dpm.state = dpm_state;
 			mutex_unlock(&rdev->pm.mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index f4d6bcee900..12e8099a082 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -36,8 +36,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 	struct radeon_bo *vram_obj = NULL;
 	struct radeon_bo **gtt_obj = NULL;
 	uint64_t gtt_addr, vram_addr;
-	unsigned i, n, size;
-	int r, ring;
+	unsigned n, size;
+	int i, r, ring;
 
 	switch (flag) {
 	case RADEON_TEST_COPY_DMA:
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index a0f11856ddd..308eff5be1b 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -476,7 +476,8 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
-	if (p->rdev->family < CHIP_PALM && (cmd == 0 || cmd == 0x3) &&
+	/* TODO: is this still necessary on NI+ ? */
+	if ((cmd == 0 || cmd == 0x3) &&
 	    (start >> 28) != (p->rdev->uvd.gpu_addr >> 28)) {
 		DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n",
 			  start, end);
@@ -798,7 +799,8 @@ void radeon_uvd_note_usage(struct radeon_device *rdev)
 		    (rdev->pm.dpm.hd != hd)) {
 			rdev->pm.dpm.sd = sd;
 			rdev->pm.dpm.hd = hd;
-			streams_changed = true;
+			/* disable this for now */
+			/*streams_changed = true;*/
 		}
 	}
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index c354c109496..d96f7cbca0a 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -85,6 +85,9 @@ extern void si_dma_vm_set_page(struct radeon_device *rdev,
 			       uint32_t incr, uint32_t flags);
 static void si_enable_gui_idle_interrupt(struct radeon_device *rdev,
 					 bool enable);
+static void si_fini_pg(struct radeon_device *rdev);
+static void si_fini_cg(struct radeon_device *rdev);
+static void si_rlc_stop(struct radeon_device *rdev);
 
 static const u32 verde_rlc_save_restore_register_list[] =
 {
@@ -1678,6 +1681,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		       fw_name);
 		release_firmware(rdev->smc_fw);
 		rdev->smc_fw = NULL;
+		err = 0;
 	} else if (rdev->smc_fw->size != smc_req_size) {
 		printk(KERN_ERR
 		       "si_smc: Bogus length %zu in firmware \"%s\"\n",
@@ -3608,6 +3612,13 @@ static void si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	/* disable PG/CG */
+	si_fini_pg(rdev);
+	si_fini_cg(rdev);
+
+	/* stop the rlc */
+	si_rlc_stop(rdev);
+
 	/* Disable CP parsing/prefetching */
 	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT | CP_CE_HALT);
 
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 9ace28702c7..2332aa1bf93 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -5208,7 +5208,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			if (!pi->mem_gddr5) {
@@ -5218,7 +5218,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] =
 						(table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16;
 				j++;
-				if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+				if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 					return -EINVAL;
 			}
 			break;
@@ -5231,7 +5231,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					(temp_reg & 0xffff0000) |
 					(table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
 			j++;
-			if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 52d2ab6b67a..7e2e0ea66a0 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -1553,7 +1553,7 @@
  * 6. COMMAND [30:21] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1568,7 +1568,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 7f998bf1cc9..9364129ba29 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1868,7 +1868,7 @@ int trinity_dpm_init(struct radeon_device *rdev)
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++)
 		pi->at[i] = TRINITY_AT_DFLT;
 
-	pi->enable_bapm = true;
+	pi->enable_bapm = false;
 	pi->enable_nbps_policy = true;
 	pi->enable_sclk_ds = true;
 	pi->enable_gfx_power_gating = true;
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index 3100fa9cb52..7266805d978 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -212,8 +212,8 @@ int uvd_v1_0_start(struct radeon_device *rdev)
 	/* enable VCPU clock */
 	WREG32(UVD_VCPU_CNTL,  1 << 9);
 
-	/* enable UMC and NC0 */
-	WREG32_P(UVD_LMI_CTRL2, 1 << 13, ~((1 << 8) | (1 << 13)));
+	/* enable UMC */
+	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
 
 	/* boot up the VCPU */
 	WREG32(UVD_SOFT_RESET, 0);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 1a90f0a2f7e..0508f93b979 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -740,9 +740,17 @@ static void vmw_postclose(struct drm_device *dev,
 	struct vmw_fpriv *vmw_fp;
 
 	vmw_fp = vmw_fpriv(file_priv);
-	ttm_object_file_release(&vmw_fp->tfile);
-	if (vmw_fp->locked_master)
+
+	if (vmw_fp->locked_master) {
+		struct vmw_master *vmaster =
+			vmw_master(vmw_fp->locked_master);
+
+		ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
+		ttm_vt_unlock(&vmaster->lock);
 		drm_master_put(&vmw_fp->locked_master);
+	}
+
+	ttm_object_file_release(&vmw_fp->tfile);
 	kfree(vmw_fp);
 }
 
@@ -925,14 +933,13 @@ static void vmw_master_drop(struct drm_device *dev,
 
 	vmw_fp->locked_master = drm_master_get(file_priv->master);
 	ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile);
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
 	if (unlikely((ret != 0))) {
 		DRM_ERROR("Unable to lock TTM at VT switch.\n");
 		drm_master_put(&vmw_fp->locked_master);
 	}
 
-	ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
+	ttm_lock_set_kill(&vmaster->lock, false, SIGTERM);
+	vmw_execbuf_release_pinned_bo(dev_priv);
 
 	if (!dev_priv->enable_fb) {
 		ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 0e67cf41065..37fb4befec8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -970,7 +970,7 @@ void vmw_resource_unreserve(struct vmw_resource *res,
 	if (new_backup)
 		res->backup_offset = new_backup_offset;
 
-	if (!res->func->may_evict)
+	if (!res->func->may_evict || res->id == -1)
 		return;
 
 	write_lock(&dev_priv->resource_lock);