diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index b1970596a782..0b9621c9aeea 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1143,31 +1143,53 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	}
 
 	if (tiling_flags & RADEON_TILING_MACRO) {
-		if (rdev->family >= CHIP_BONAIRE)
-			tmp = rdev->config.cik.tile_config;
-		else if (rdev->family >= CHIP_TAHITI)
-			tmp = rdev->config.si.tile_config;
-		else if (rdev->family >= CHIP_CAYMAN)
-			tmp = rdev->config.cayman.tile_config;
-		else
-			tmp = rdev->config.evergreen.tile_config;
+		evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
 
-		switch ((tmp & 0xf0) >> 4) {
-		case 0: /* 4 banks */
-			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
-			break;
-		case 1: /* 8 banks */
-		default:
-			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
-			break;
-		case 2: /* 16 banks */
-			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
-			break;
+		/* Set NUM_BANKS. */
+		if (rdev->family >= CHIP_BONAIRE) {
+			unsigned tileb, index, num_banks, tile_split_bytes;
+
+			/* Calculate the macrotile mode index. */
+			tile_split_bytes = 64 << tile_split;
+			tileb = 8 * 8 * target_fb->bits_per_pixel / 8;
+			tileb = min(tile_split_bytes, tileb);
+
+			for (index = 0; tileb > 64; index++) {
+				tileb >>= 1;
+			}
+
+			if (index >= 16) {
+				DRM_ERROR("Wrong screen bpp (%u) or tile split (%u)\n",
+					  target_fb->bits_per_pixel, tile_split);
+				return -EINVAL;
+			}
+
+			num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+			fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks);
+		} else {
+			/* SI and older. */
+			if (rdev->family >= CHIP_TAHITI)
+				tmp = rdev->config.si.tile_config;
+			else if (rdev->family >= CHIP_CAYMAN)
+				tmp = rdev->config.cayman.tile_config;
+			else
+				tmp = rdev->config.evergreen.tile_config;
+
+			switch ((tmp & 0xf0) >> 4) {
+			case 0: /* 4 banks */
+				fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
+				break;
+			case 1: /* 8 banks */
+			default:
+				fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
+				break;
+			case 2: /* 16 banks */
+				fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
+				break;
+			}
 		}
 
 		fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1);
-
-		evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
 		fb_format |= EVERGREEN_GRPH_TILE_SPLIT(tile_split);
 		fb_format |= EVERGREEN_GRPH_BANK_WIDTH(bankw);
 		fb_format |= EVERGREEN_GRPH_BANK_HEIGHT(bankh);
@@ -1180,19 +1202,12 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 		fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1);
 
 	if (rdev->family >= CHIP_BONAIRE) {
-		u32 num_pipe_configs = rdev->config.cik.max_tile_pipes;
-		u32 num_rb = rdev->config.cik.max_backends_per_se;
-		if (num_pipe_configs > 8)
-			num_pipe_configs = 8;
-		if (num_pipe_configs == 8)
-			fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P8_32x32_16x16);
-		else if (num_pipe_configs == 4) {
-			if (num_rb == 4)
-				fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_16x16);
-			else if (num_rb < 4)
-				fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_8x16);
-		} else if (num_pipe_configs == 2)
-			fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P2);
+		/* Read the pipe config from the 2D TILED SCANOUT mode.
+		 * It should be the same for the other modes too, but not all
+		 * modes set the pipe config field. */
+		u32 pipe_config = (rdev->config.cik.tile_mode_array[10] >> 6) & 0x1f;
+
+		fb_format |= CIK_GRPH_PIPE_CONFIG(pipe_config);
 	} else if ((rdev->family == CHIP_TAHITI) ||
 		   (rdev->family == CHIP_PITCAIRN))
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16);
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index b43a3a3c9067..e950fabd7f5e 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3057,7 +3057,7 @@ static u32 cik_create_bitmask(u32 bit_width)
  * Returns the disabled RB bitmask.
  */
 static u32 cik_get_rb_disabled(struct radeon_device *rdev,
-			      u32 max_rb_num, u32 se_num,
+			      u32 max_rb_num_per_se,
 			      u32 sh_per_se)
 {
 	u32 data, mask;
@@ -3071,7 +3071,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev,
 
 	data >>= BACKEND_DISABLE_SHIFT;
 
-	mask = cik_create_bitmask(max_rb_num / se_num / sh_per_se);
+	mask = cik_create_bitmask(max_rb_num_per_se / sh_per_se);
 
 	return data & mask;
 }
@@ -3088,7 +3088,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev,
  */
 static void cik_setup_rb(struct radeon_device *rdev,
 			 u32 se_num, u32 sh_per_se,
-			 u32 max_rb_num)
+			 u32 max_rb_num_per_se)
 {
 	int i, j;
 	u32 data, mask;
@@ -3098,7 +3098,7 @@ static void cik_setup_rb(struct radeon_device *rdev,
 	for (i = 0; i < se_num; i++) {
 		for (j = 0; j < sh_per_se; j++) {
 			cik_select_se_sh(rdev, i, j);
-			data = cik_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+			data = cik_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se);
 			if (rdev->family == CHIP_HAWAII)
 				disabled_rbs |= data << ((i * sh_per_se + j) * HAWAII_RB_BITMAP_WIDTH_PER_SH);
 			else
@@ -3108,12 +3108,14 @@ static void cik_setup_rb(struct radeon_device *rdev,
 	cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
 
 	mask = 1;
-	for (i = 0; i < max_rb_num; i++) {
+	for (i = 0; i < max_rb_num_per_se * se_num; i++) {
 		if (!(disabled_rbs & mask))
 			enabled_rbs |= mask;
 		mask <<= 1;
 	}
 
+	rdev->config.cik.backend_enable_mask = enabled_rbs;
+
 	for (i = 0; i < se_num; i++) {
 		cik_select_se_sh(rdev, i, 0xffffffff);
 		data = 0;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b1f990d0eaa1..45e1f447bc79 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1940,7 +1940,7 @@ struct si_asic {
 	unsigned sc_earlyz_tile_fifo_size;
 
 	unsigned num_tile_pipes;
-	unsigned num_backends_per_se;
+	unsigned backend_enable_mask;
 	unsigned backend_disable_mask_per_asic;
 	unsigned backend_map;
 	unsigned num_texture_channel_caches;
@@ -1970,7 +1970,7 @@ struct cik_asic {
 	unsigned sc_earlyz_tile_fifo_size;
 
 	unsigned num_tile_pipes;
-	unsigned num_backends_per_se;
+	unsigned backend_enable_mask;
 	unsigned backend_disable_mask_per_asic;
 	unsigned backend_map;
 	unsigned num_texture_channel_caches;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 1958b36ad0e5..db39ea36bf22 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -77,9 +77,10 @@
  *   2.33.0 - Add SI tiling mode array query
  *   2.34.0 - Add CIK tiling mode array query
  *   2.35.0 - Add CIK macrotile mode array query
+ *   2.36.0 - Fix CIK DCE tiling setup
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	35
+#define KMS_DRIVER_MINOR	36
 #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_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 55d0b474bd37..21d593c0ecaf 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -461,6 +461,15 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	case RADEON_INFO_SI_CP_DMA_COMPUTE:
 		*value = 1;
 		break;
+	case RADEON_INFO_SI_BACKEND_ENABLED_MASK:
+		if (rdev->family >= CHIP_BONAIRE) {
+			*value = rdev->config.cik.backend_enable_mask;
+		} else if (rdev->family >= CHIP_TAHITI) {
+			*value = rdev->config.si.backend_enable_mask;
+		} else {
+			DRM_DEBUG_KMS("BACKEND_ENABLED_MASK is si+ only!\n");
+		}
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 373d088bac66..b9c0529b4a2e 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -473,7 +473,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
-	if ((start >> 28) != (end >> 28)) {
+	if ((start >> 28) != ((end - 1) >> 28)) {
 		DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n",
 			  start, end);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index a36736dab5e0..85e1edfaa3be 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2811,7 +2811,7 @@ static void si_setup_spi(struct radeon_device *rdev,
 }
 
 static u32 si_get_rb_disabled(struct radeon_device *rdev,
-			      u32 max_rb_num, u32 se_num,
+			      u32 max_rb_num_per_se,
 			      u32 sh_per_se)
 {
 	u32 data, mask;
@@ -2825,14 +2825,14 @@ static u32 si_get_rb_disabled(struct radeon_device *rdev,
 
 	data >>= BACKEND_DISABLE_SHIFT;
 
-	mask = si_create_bitmask(max_rb_num / se_num / sh_per_se);
+	mask = si_create_bitmask(max_rb_num_per_se / sh_per_se);
 
 	return data & mask;
 }
 
 static void si_setup_rb(struct radeon_device *rdev,
 			u32 se_num, u32 sh_per_se,
-			u32 max_rb_num)
+			u32 max_rb_num_per_se)
 {
 	int i, j;
 	u32 data, mask;
@@ -2842,19 +2842,21 @@ static void si_setup_rb(struct radeon_device *rdev,
 	for (i = 0; i < se_num; i++) {
 		for (j = 0; j < sh_per_se; j++) {
 			si_select_se_sh(rdev, i, j);
-			data = si_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+			data = si_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se);
 			disabled_rbs |= data << ((i * sh_per_se + j) * TAHITI_RB_BITMAP_WIDTH_PER_SH);
 		}
 	}
 	si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
 
 	mask = 1;
-	for (i = 0; i < max_rb_num; i++) {
+	for (i = 0; i < max_rb_num_per_se * se_num; i++) {
 		if (!(disabled_rbs & mask))
 			enabled_rbs |= mask;
 		mask <<= 1;
 	}
 
+	rdev->config.si.backend_enable_mask = enabled_rbs;
+
 	for (i = 0; i < se_num; i++) {
 		si_select_se_sh(rdev, i, 0xffffffff);
 		data = 0;
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 87578c109e48..49376aec2fbb 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -600,7 +600,7 @@
 	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
-	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 2f3f7ea8c77b..fe421e8a431b 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -983,6 +983,8 @@ struct drm_radeon_cs {
 #define RADEON_INFO_SI_CP_DMA_COMPUTE	0x17
 /* CIK macrotile mode array */
 #define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY	0x18
+/* query the number of render backends */
+#define RADEON_INFO_SI_BACKEND_ENABLED_MASK	0x19
 
 
 struct drm_radeon_info {