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

Pull drm fixes from Dave Airlie:
 "A bunch of intel and radeon fixes, along with two fixes to TTM code.

  The correct fix for the Intel ironlake failure is in this, and should
  make things more stable, along with some misc radeon fixes."

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  ttm: on move memory failure don't leave a node dangling
  ttm: don't destroy old mm_node on memcpy failure
  Revert "drm/radeon: do not move bo to different placement at each cs"
  drm/i915: fix FORCEWAKE posting reads
  drm/i915: Invalidate the relocation presumed_offsets along the slow path
  drm/i915/eDP: do not write power sequence registers for ghost eDP
  drm/radeon: improve semaphore debugging on lockup
  drm/radeon: allow FP16 color clear registers on r500
  drm/radeon: clear reset flags if engines are idle
  drm/i915: Record DERRMR, FORCEWAKE and RING_CTL in error-state

19 files changed, 140 insertions, 32 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e6a11ca85eaf..7944d301518a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -641,6 +641,7 @@ static void i915_ring_error_state(struct seq_file *m,
 	seq_printf(m, "%s command stream:\n", ring_str(ring));
 	seq_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
 	seq_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
+	seq_printf(m, "  CTL: 0x%08x\n", error->ctl[ring]);
 	seq_printf(m, "  ACTHD: 0x%08x\n", error->acthd[ring]);
 	seq_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
 	seq_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
@@ -693,6 +694,8 @@ static int i915_error_state(struct seq_file *m, void *unused)
 	seq_printf(m, "EIR: 0x%08x\n", error->eir);
 	seq_printf(m, "IER: 0x%08x\n", error->ier);
 	seq_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
+	seq_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
+	seq_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
 	seq_printf(m, "CCID: 0x%08x\n", error->ccid);
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ed3059575576..12ab3bdea54d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -188,10 +188,13 @@ struct drm_i915_error_state {
 	u32 pgtbl_er;
 	u32 ier;
 	u32 ccid;
+	u32 derrmr;
+	u32 forcewake;
 	bool waiting[I915_NUM_RINGS];
 	u32 pipestat[I915_MAX_PIPES];
 	u32 tail[I915_NUM_RINGS];
 	u32 head[I915_NUM_RINGS];
+	u32 ctl[I915_NUM_RINGS];
 	u32 ipeir[I915_NUM_RINGS];
 	u32 ipehr[I915_NUM_RINGS];
 	u32 instdone[I915_NUM_RINGS];
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d6a994a07393..26d08bb58218 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -539,6 +539,8 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 	total = 0;
 	for (i = 0; i < count; i++) {
 		struct drm_i915_gem_relocation_entry __user *user_relocs;
+		u64 invalid_offset = (u64)-1;
+		int j;
 
 		user_relocs = (void __user *)(uintptr_t)exec[i].relocs_ptr;
 
@@ -549,6 +551,25 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 			goto err;
 		}
 
+		/* As we do not update the known relocation offsets after
+		 * relocating (due to the complexities in lock handling),
+		 * we need to mark them as invalid now so that we force the
+		 * relocation processing next time. Just in case the target
+		 * object is evicted and then rebound into its old
+		 * presumed_offset before the next execbuffer - if that
+		 * happened we would make the mistake of assuming that the
+		 * relocations were valid.
+		 */
+		for (j = 0; j < exec[i].relocation_count; j++) {
+			if (copy_to_user(&user_relocs[j].presumed_offset,
+					 &invalid_offset,
+					 sizeof(invalid_offset))) {
+				ret = -EFAULT;
+				mutex_lock(&dev->struct_mutex);
+				goto err;
+			}
+		}
+
 		reloc_offset[i] = total;
 		total += exec[i].relocation_count;
 	}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2220dec3e5d9..fe843389c7b4 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1157,6 +1157,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 	error->acthd[ring->id] = intel_ring_get_active_head(ring);
 	error->head[ring->id] = I915_READ_HEAD(ring);
 	error->tail[ring->id] = I915_READ_TAIL(ring);
+	error->ctl[ring->id] = I915_READ_CTL(ring);
 
 	error->cpu_ring_head[ring->id] = ring->head;
 	error->cpu_ring_tail[ring->id] = ring->tail;
@@ -1251,6 +1252,16 @@ static void i915_capture_error_state(struct drm_device *dev)
 	else
 		error->ier = I915_READ(IER);
 
+	if (INTEL_INFO(dev)->gen >= 6)
+		error->derrmr = I915_READ(DERRMR);
+
+	if (IS_VALLEYVIEW(dev))
+		error->forcewake = I915_READ(FORCEWAKE_VLV);
+	else if (INTEL_INFO(dev)->gen >= 7)
+		error->forcewake = I915_READ(FORCEWAKE_MT);
+	else if (INTEL_INFO(dev)->gen == 6)
+		error->forcewake = I915_READ(FORCEWAKE);
+
 	for_each_pipe(pipe)
 		error->pipestat[pipe] = I915_READ(PIPESTAT(pipe));
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 186ee5c85b51..b401788e1791 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -512,6 +512,8 @@
 #define GEN7_ERR_INT	0x44040
 #define   ERR_INT_MMIO_UNCLAIMED (1<<13)
 
+#define DERRMR		0x44050
+
 /* GM45+ chicken bits -- debug workaround bits that may be required
  * for various sorts of correct behavior.  The top 16 bits of each are
  * the enables for writing to the corresponding low bit.
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 1b63d55318a0..fb3715b4b09d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2579,7 +2579,8 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 
 static void
 intel_dp_init_panel_power_sequencer(struct drm_device *dev,
-				    struct intel_dp *intel_dp)
+				    struct intel_dp *intel_dp,
+				    struct edp_power_seq *out)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct edp_power_seq cur, vbt, spec, final;
@@ -2650,16 +2651,35 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev,
 	intel_dp->panel_power_cycle_delay = get_delay(t11_t12);
 #undef get_delay
 
+	DRM_DEBUG_KMS("panel power up delay %d, power down delay %d, power cycle delay %d\n",
+		      intel_dp->panel_power_up_delay, intel_dp->panel_power_down_delay,
+		      intel_dp->panel_power_cycle_delay);
+
+	DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
+		      intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
+
+	if (out)
+		*out = final;
+}
+
+static void
+intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
+					      struct intel_dp *intel_dp,
+					      struct edp_power_seq *seq)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 pp_on, pp_off, pp_div;
+
 	/* And finally store the new values in the power sequencer. */
-	pp_on = (final.t1_t3 << PANEL_POWER_UP_DELAY_SHIFT) |
-		(final.t8 << PANEL_LIGHT_ON_DELAY_SHIFT);
-	pp_off = (final.t9 << PANEL_LIGHT_OFF_DELAY_SHIFT) |
-		 (final.t10 << PANEL_POWER_DOWN_DELAY_SHIFT);
+	pp_on = (seq->t1_t3 << PANEL_POWER_UP_DELAY_SHIFT) |
+		(seq->t8 << PANEL_LIGHT_ON_DELAY_SHIFT);
+	pp_off = (seq->t9 << PANEL_LIGHT_OFF_DELAY_SHIFT) |
+		 (seq->t10 << PANEL_POWER_DOWN_DELAY_SHIFT);
 	/* Compute the divisor for the pp clock, simply match the Bspec
 	 * formula. */
 	pp_div = ((100 * intel_pch_rawclk(dev))/2 - 1)
 			<< PP_REFERENCE_DIVIDER_SHIFT;
-	pp_div |= (DIV_ROUND_UP(final.t11_t12, 1000)
+	pp_div |= (DIV_ROUND_UP(seq->t11_t12, 1000)
 			<< PANEL_POWER_CYCLE_DELAY_SHIFT);
 
 	/* Haswell doesn't have any port selection bits for the panel
@@ -2675,14 +2695,6 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev,
 	I915_WRITE(PCH_PP_OFF_DELAYS, pp_off);
 	I915_WRITE(PCH_PP_DIVISOR, pp_div);
 
-
-	DRM_DEBUG_KMS("panel power up delay %d, power down delay %d, power cycle delay %d\n",
-		      intel_dp->panel_power_up_delay, intel_dp->panel_power_down_delay,
-		      intel_dp->panel_power_cycle_delay);
-
-	DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
-		      intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
-
 	DRM_DEBUG_KMS("panel power sequencer register settings: PP_ON %#x, PP_OFF %#x, PP_DIV %#x\n",
 		      I915_READ(PCH_PP_ON_DELAYS),
 		      I915_READ(PCH_PP_OFF_DELAYS),
@@ -2699,6 +2711,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_display_mode *fixed_mode = NULL;
+	struct edp_power_seq power_seq = { 0 };
 	enum port port = intel_dig_port->port;
 	const char *name = NULL;
 	int type;
@@ -2771,7 +2784,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	}
 
 	if (is_edp(intel_dp))
-		intel_dp_init_panel_power_sequencer(dev, intel_dp);
+		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
 
 	intel_dp_i2c_init(intel_dp, intel_connector, name);
 
@@ -2798,6 +2811,10 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 			return;
 		}
 
+		/* We now know it's not a ghost, init power sequence regs. */
+		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+							      &power_seq);
+
 		ironlake_edp_panel_vdd_on(intel_dp);
 		edid = drm_get_edid(connector, &intel_dp->adapter);
 		if (edid) {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index e83a11794172..3280cffe50f4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4250,7 +4250,8 @@ static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(0xffff));
-	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	POSTING_READ(ECOBUS);
 }
 
 static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
@@ -4267,7 +4268,8 @@ static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	POSTING_READ(ECOBUS);
 
 	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & 1),
 			    FORCEWAKE_ACK_TIMEOUT_MS))
@@ -4304,14 +4306,16 @@ void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
 static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	/* gen6_gt_check_fifodbg doubles as the POSTING_READ */
+	/* something from same cacheline, but !FORCEWAKE */
+	POSTING_READ(ECOBUS);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
 static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	/* gen6_gt_check_fifodbg doubles as the POSTING_READ */
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	POSTING_READ(ECOBUS);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
@@ -4351,6 +4355,8 @@ int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
 static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(0xffff));
+	/* something from same cacheline, but !FORCEWAKE_VLV */
+	POSTING_READ(FORCEWAKE_ACK_VLV);
 }
 
 static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
@@ -4371,7 +4377,8 @@ static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
 static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	/* The below doubles as a POSTING_READ */
+	/* something from same cacheline, but !FORCEWAKE_VLV */
+	POSTING_READ(FORCEWAKE_ACK_VLV);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 061fa0a28900..4d0e60adbc6d 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2401,6 +2401,12 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct evergreen_mc_save save;
 
+	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+
+	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
+		reset_mask &= ~RADEON_RESET_DMA;
+
 	if (reset_mask == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 896f1cbc58a5..59acabb45c9b 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1409,6 +1409,12 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct evergreen_mc_save save;
 
+	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+
+	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
+		reset_mask &= ~RADEON_RESET_DMA;
+
 	if (reset_mask == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 537e259b3837..3cb9d6089373 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1378,6 +1378,12 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct rv515_mc_save save;
 
+	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+
+	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
+		reset_mask &= ~RADEON_RESET_DMA;
+
 	if (reset_mask == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 34e52304a525..a08f657329a0 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -324,7 +324,6 @@ struct radeon_bo {
 	struct list_head		list;
 	/* Protected by tbo.reserved */
 	u32				placements[3];
-	u32				busy_placements[3];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
@@ -654,6 +653,8 @@ struct radeon_ring {
 	u32			ptr_reg_mask;
 	u32			nop;
 	u32			idx;
+	u64			last_semaphore_signal_addr;
+	u64			last_semaphore_wait_addr;
 };
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index dff6cf77f953..d9bf96ee299a 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -69,9 +69,10 @@
  *   2.26.0 - r600-eg: fix htile size computation
  *   2.27.0 - r600-SI: Add CS ioctl support for async DMA
  *   2.28.0 - r600-eg: Add MEM_WRITE packet support
+ *   2.29.0 - R500 FP16 color clear registers
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	28
+#define KMS_DRIVER_MINOR	29
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 883c95d8d90f..d3aface2d12d 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -84,6 +84,7 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	rbo->placement.fpfn = 0;
 	rbo->placement.lpfn = 0;
 	rbo->placement.placement = rbo->placements;
+	rbo->placement.busy_placement = rbo->placements;
 	if (domain & RADEON_GEM_DOMAIN_VRAM)
 		rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
 					TTM_PL_FLAG_VRAM;
@@ -104,14 +105,6 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	if (!c)
 		rbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	rbo->placement.num_placement = c;
-
-	c = 0;
-	rbo->placement.busy_placement = rbo->busy_placements;
-	if (rbo->rdev->flags & RADEON_IS_AGP) {
-		rbo->busy_placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_TT;
-	} else {
-		rbo->busy_placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_TT;
-	}
 	rbo->placement.num_busy_placement = c;
 }
 
@@ -357,6 +350,7 @@ int radeon_bo_list_validate(struct list_head *head)
 {
 	struct radeon_bo_list *lobj;
 	struct radeon_bo *bo;
+	u32 domain;
 	int r;
 
 	r = ttm_eu_reserve_buffers(head);
@@ -366,9 +360,17 @@ int radeon_bo_list_validate(struct list_head *head)
 	list_for_each_entry(lobj, head, tv.head) {
 		bo = lobj->bo;
 		if (!bo->pin_count) {
+			domain = lobj->wdomain ? lobj->wdomain : lobj->rdomain;
+			
+		retry:
+			radeon_ttm_placement_from_domain(bo, domain);
 			r = ttm_bo_validate(&bo->tbo, &bo->placement,
 						true, false);
 			if (unlikely(r)) {
+				if (r != -ERESTARTSYS && domain == RADEON_GEM_DOMAIN_VRAM) {
+					domain |= RADEON_GEM_DOMAIN_GTT;
+					goto retry;
+				}
 				return r;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 141f2b6a9cf2..2430d80b1871 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -784,6 +784,8 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	}
 	seq_printf(m, "driver's copy of the wptr: 0x%08x [%5d]\n", ring->wptr, ring->wptr);
 	seq_printf(m, "driver's copy of the rptr: 0x%08x [%5d]\n", ring->rptr, ring->rptr);
+	seq_printf(m, "last semaphore signal addr : 0x%016llx\n", ring->last_semaphore_signal_addr);
+	seq_printf(m, "last semaphore wait addr   : 0x%016llx\n", ring->last_semaphore_wait_addr);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
 	seq_printf(m, "%u dwords in ring\n", count);
 	/* print 8 dw before current rptr as often it's the last executed
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 97f3ece81cd2..8dcc20f53d73 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -95,6 +95,10 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 	/* we assume caller has already allocated space on waiters ring */
 	radeon_semaphore_emit_wait(rdev, waiter, semaphore);
 
+	/* for debugging lockup only, used by sysfs debug files */
+	rdev->ring[signaler].last_semaphore_signal_addr = semaphore->gpu_addr;
+	rdev->ring[waiter].last_semaphore_wait_addr = semaphore->gpu_addr;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/reg_srcs/rv515 b/drivers/gpu/drm/radeon/reg_srcs/rv515
index 911a8fbd32bb..78d5e99d759d 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/rv515
+++ b/drivers/gpu/drm/radeon/reg_srcs/rv515
@@ -324,6 +324,8 @@ rv515 0x6d40
 0x46AC US_OUT_FMT_2
 0x46B0 US_OUT_FMT_3
 0x46B4 US_W_FMT
+0x46C0 RB3D_COLOR_CLEAR_VALUE_AR
+0x46C4 RB3D_COLOR_CLEAR_VALUE_GB
 0x4BC0 FG_FOG_BLEND
 0x4BC4 FG_FOG_FACTOR
 0x4BC8 FG_FOG_COLOR_R
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 3240a3d64f30..ae8b48205a6c 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2215,6 +2215,12 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct evergreen_mc_save save;
 
+	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+
+	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
+		reset_mask &= ~RADEON_RESET_DMA;
+
 	if (reset_mask == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 33d20be87db5..52b20b12c83a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -434,6 +434,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 			bo->mem = tmp_mem;
 			bdev->driver->move_notify(bo, mem);
 			bo->mem = *mem;
+			*mem = tmp_mem;
 		}
 
 		goto out_err;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index d73d6e3e17b2..44420fca7dfa 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -344,8 +344,12 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 
 	if (ttm->state == tt_unpopulated) {
 		ret = ttm->bdev->driver->ttm_tt_populate(ttm);
-		if (ret)
+		if (ret) {
+			/* if we fail here don't nuke the mm node
+			 * as the bo still owns it */
+			old_copy.mm_node = NULL;
 			goto out1;
+		}
 	}
 
 	add = 0;
@@ -371,8 +375,11 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 						   prot);
 		} else
 			ret = ttm_copy_io_page(new_iomap, old_iomap, page);
-		if (ret)
+		if (ret) {
+			/* failing here, means keep old copy as-is */
+			old_copy.mm_node = NULL;
 			goto out1;
+		}
 	}
 	mb();
 out2: