Merge branch 'fbcon-locking-fixes' of ssh://people.freedesktop.org/~airlied/linux into drm-next

This pulls in most of Linus tree up to -rc6, this fixes the worst lockdep
reported issues and re-enables fbcon lockdep.

(not the fbcon maintainer)
* 'fbcon-locking-fixes' of ssh://people.freedesktop.org/~airlied/linux: (529 commits)
  Revert "Revert "console: implement lockdep support for console_lock""
  fbcon: fix locking harder
  fb: Yet another band-aid for fixing lockdep mess
  fb: rework locking to fix lock ordering on takeover

18 files changed, 114 insertions, 26 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 061fa0a28900..a2d478e8692a 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1313,14 +1313,18 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
 				if (!(tmp & EVERGREEN_CRTC_BLANK_DATA_EN)) {
 					radeon_wait_for_vblank(rdev, i);
 					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
 				if (!(tmp & EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE)) {
 					radeon_wait_for_vblank(rdev, i);
 					tmp |= EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			}
 			/* wait for the next frame */
@@ -1345,6 +1349,8 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
 		blackout &= ~BLACKOUT_MODE_MASK;
 		WREG32(MC_SHARED_BLACKOUT_CNTL, blackout | 1);
 	}
+	/* wait for the MC to settle */
+	udelay(100);
 }
 
 void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save)
@@ -1378,11 +1384,15 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s
 			if (ASIC_IS_DCE6(rdev)) {
 				tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]);
 				tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 				WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
 				tmp &= ~EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 				WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 			}
 			/* wait for the next frame */
 			frame_count = radeon_get_vblank_counter(rdev, i);
@@ -2036,9 +2046,20 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 	WREG32(DMA_TILING_CONFIG, gb_addr_config);
 
-	tmp = gb_addr_config & NUM_PIPES_MASK;
-	tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
-					EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
+	if ((rdev->config.evergreen.max_backends == 1) &&
+	    (rdev->flags & RADEON_IS_IGP)) {
+		if ((disabled_rb_mask & 3) == 1) {
+			/* RB0 disabled, RB1 enabled */
+			tmp = 0x11111111;
+		} else {
+			/* RB1 disabled, RB0 enabled */
+			tmp = 0x00000000;
+		}
+	} else {
+		tmp = gb_addr_config & NUM_PIPES_MASK;
+		tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
+						EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
+	}
 	WREG32(GB_BACKEND_MAP, tmp);
 
 	WREG32(CGTS_SYS_TCC_DISABLE, 0);
@@ -2401,6 +2422,12 @@ 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..835992d8d067 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1216,7 +1216,7 @@ void cayman_dma_stop(struct radeon_device *rdev)
 int cayman_dma_resume(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring;
-	u32 rb_cntl, dma_cntl;
+	u32 rb_cntl, dma_cntl, ib_cntl;
 	u32 rb_bufsz;
 	u32 reg_offset, wb_offset;
 	int i, r;
@@ -1265,7 +1265,11 @@ int cayman_dma_resume(struct radeon_device *rdev)
 		WREG32(DMA_RB_BASE + reg_offset, ring->gpu_addr >> 8);
 
 		/* enable DMA IBs */
-		WREG32(DMA_IB_CNTL + reg_offset, DMA_IB_ENABLE | CMD_VMID_FORCE);
+		ib_cntl = DMA_IB_ENABLE | CMD_VMID_FORCE;
+#ifdef __BIG_ENDIAN
+		ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+		WREG32(DMA_IB_CNTL + reg_offset, ib_cntl);
 
 		dma_cntl = RREG32(DMA_CNTL + reg_offset);
 		dma_cntl &= ~CTXEMPTY_INT_ENABLE;
@@ -1409,6 +1413,12 @@ 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..becb03e8b32f 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;
 
@@ -1456,12 +1462,15 @@ u32 r6xx_remap_render_backend(struct radeon_device *rdev,
 			      u32 disabled_rb_mask)
 {
 	u32 rendering_pipe_num, rb_num_width, req_rb_num;
-	u32 pipe_rb_ratio, pipe_rb_remain;
+	u32 pipe_rb_ratio, pipe_rb_remain, tmp;
 	u32 data = 0, mask = 1 << (max_rb_num - 1);
 	unsigned i, j;
 
 	/* mask out the RBs that don't exist on that asic */
-	disabled_rb_mask |= (0xff << max_rb_num) & 0xff;
+	tmp = disabled_rb_mask | ((0xff << max_rb_num) & 0xff);
+	/* make sure at least one RB is available */
+	if ((tmp & 0xff) != 0xff)
+		disabled_rb_mask = tmp;
 
 	rendering_pipe_num = 1 << tiling_pipe_num;
 	req_rb_num = total_max_rb_num - r600_count_pipe_bits(disabled_rb_mask);
@@ -2307,7 +2316,7 @@ void r600_dma_stop(struct radeon_device *rdev)
 int r600_dma_resume(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
-	u32 rb_cntl, dma_cntl;
+	u32 rb_cntl, dma_cntl, ib_cntl;
 	u32 rb_bufsz;
 	int r;
 
@@ -2347,7 +2356,11 @@ int r600_dma_resume(struct radeon_device *rdev)
 	WREG32(DMA_RB_BASE, ring->gpu_addr >> 8);
 
 	/* enable DMA IBs */
-	WREG32(DMA_IB_CNTL, DMA_IB_ENABLE);
+	ib_cntl = DMA_IB_ENABLE;
+#ifdef __BIG_ENDIAN
+	ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+	WREG32(DMA_IB_CNTL, ib_cntl);
 
 	dma_cntl = RREG32(DMA_CNTL);
 	dma_cntl &= ~CTXEMPTY_INT_ENABLE;
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_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 9056fafb00ea..0b202c07fe50 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1445,7 +1445,7 @@ static struct radeon_asic cayman_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1572,7 +1572,7 @@ static struct radeon_asic trinity_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1699,7 +1699,7 @@ static struct radeon_asic si_asic = {
 	.vm = {
 		.init = &si_vm_init,
 		.fini = &si_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &si_vm_set_page,
 	},
 	.ring = {
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 33a56a09ff10..3e403bdda58f 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -2470,6 +2470,14 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev)
 								   1),
 								  ATOM_DEVICE_CRT1_SUPPORT);
 				}
+				/* RV100 board with external TDMS bit mis-set.
+				 * Actually uses internal TMDS, clear the bit.
+				 */
+				if (dev->pdev->device == 0x5159 &&
+				    dev->pdev->subsystem_vendor == 0x1014 &&
+				    dev->pdev->subsystem_device == 0x029A) {
+					tmp &= ~(1 << 4);
+				}
 				if ((tmp >> 4) & 0x1) {
 					devices |= ATOM_DEVICE_DFP2_SUPPORT;
 					radeon_add_legacy_encoder(dev,
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 469661fd1903..5407459e56d2 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -286,6 +286,8 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			    p->chunks[p->chunk_ib_idx].kpage[1] == NULL) {
 				kfree(p->chunks[p->chunk_ib_idx].kpage[0]);
 				kfree(p->chunks[p->chunk_ib_idx].kpage[1]);
+				p->chunks[p->chunk_ib_idx].kpage[0] = NULL;
+				p->chunks[p->chunk_ib_idx].kpage[1] = NULL;
 				return -ENOMEM;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index c1680e6d76ad..b097d5b4ff39 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -241,7 +241,8 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 		y = 0;
 	}
 
-	if (ASIC_IS_AVIVO(rdev)) {
+	/* fixed on DCE6 and newer */
+	if (ASIC_IS_AVIVO(rdev) && !ASIC_IS_DCE6(rdev)) {
 		int i = 0;
 		struct drm_crtc *crtc_p;
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index edfc54e41842..0d6562bb0c93 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -429,7 +429,8 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
-	if (efi_enabled && rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
+	if (efi_enabled(EFI_BOOT) &&
+	    rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
 		return false;
 
 	/* first check CRTCs */
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 12ec3effb409..e38fd559f1ab 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1115,14 +1115,16 @@ radeon_user_framebuffer_create(struct drm_device *dev,
 	}
 
 	radeon_fb = kzalloc(sizeof(*radeon_fb), GFP_KERNEL);
-	if (radeon_fb == NULL)
+	if (radeon_fb == NULL) {
+		drm_gem_object_unreference_unlocked(obj);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	ret = radeon_framebuffer_init(dev, radeon_fb, mode_cmd, obj);
 	if (ret) {
 		kfree(radeon_fb);
 		drm_gem_object_unreference_unlocked(obj);
-		return NULL;
+		return ERR_PTR(ret);
 	}
 
 	return &radeon_fb->base;
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..cd72062d5a91 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -377,6 +377,9 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi
 {
 	int r;
 
+	/* make sure we aren't trying to allocate more space than there is on the ring */
+	if (ndw > (ring->ring_size / 4))
+		return -ENOMEM;
 	/* Align requested size with padding so unlock_commit can
 	 * pad safely */
 	ndw = (ndw + ring->align_mask) & ~ring->align_mask;
@@ -784,6 +787,8 @@ 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/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index 0f656b111c15..a072fa8c46b0 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -1,5 +1,6 @@
 cayman 0x9400
 0x0000802C GRBM_GFX_INDEX
+0x00008040 WAIT_UNTIL
 0x000084FC CP_STRMOUT_CNTL
 0x000085F0 CP_COHER_CNTL
 0x000085F4 CP_COHER_SIZE
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/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 2bb6d0e84b3d..435ed3551364 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -336,6 +336,8 @@ void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save)
 				WREG32(R600_CITF_CNTL, blackout);
 		}
 	}
+	/* wait for the MC to settle */
+	udelay(100);
 }
 
 void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
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;