Merge tag 'v3.10.17' into dev-kernel-3.10

This is the 3.10.17 stable release

Conflicts:
	drivers/usb/host/xhci.c

Change-Id: I6bd3b15ff92a0b94568b9d02e9bb1036becfca20

18 files changed, 218 insertions, 92 deletions

diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 32501f6ec991..16023986d301 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -50,7 +50,7 @@ static char *pre_emph_names[] = {
  * or from atom. Note that atom operates on
  * dw units.
  */
-static void radeon_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
+void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
 	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
@@ -100,7 +100,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 
 	base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1);
 
-	radeon_copy_swap(base, send, send_bytes, true);
+	radeon_atom_copy_swap(base, send, send_bytes, true);
 
 	args.v1.lpAuxRequest = cpu_to_le16((u16)(0 + 4));
 	args.v1.lpDataOut = cpu_to_le16((u16)(16 + 4));
@@ -137,7 +137,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 		recv_bytes = recv_size;
 
 	if (recv && recv_size)
-		radeon_copy_swap(recv, base + 16, recv_bytes, false);
+		radeon_atom_copy_swap(recv, base + 16, recv_bytes, false);
 
 	return recv_bytes;
 }
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 4120d355cadd..c272d8832605 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1636,8 +1636,12 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-			/* some early dce3.2 boards have a bug in their transmitter control table */
-			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730))
+			/* some dce3.x boards have a bug in their transmitter control table.
+			 * ACTION_ENABLE_OUTPUT can probably be dropped since ACTION_ENABLE
+			 * does the same thing and more.
+			 */
+			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) &&
+			    (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/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index 082338df708a..2ca389d19258 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -27,6 +27,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+extern void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le);
+
 #define TARGET_HW_I2C_CLOCK 50
 
 /* these are a limitation of ProcessI2cChannelTransaction not the hw */
@@ -77,7 +79,7 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	}
 
 	if (!(flags & HW_I2C_WRITE))
-		memcpy(buf, base, num);
+		radeon_atom_copy_swap(buf, base, num, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 687b421f75c3..8b6b0ba6ae40 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1718,7 +1718,8 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev,
 					struct drm_display_mode *mode,
 					struct drm_display_mode *other_mode)
 {
-	u32 tmp;
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -1741,18 +1742,34 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev,
 	 * non-linked crtcs for maximum line buffer allocation.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (other_mode)
+		if (other_mode) {
 			tmp = 0; /* 1/2 */
-		else
+			buffer_alloc = 1;
+		} else {
 			tmp = 2; /* whole */
-	} else
+			buffer_alloc = 2;
+		}
+	} else {
 		tmp = 0;
+		buffer_alloc = 0;
+	}
 
 	/* second controller of the pair uses second half of the lb */
 	if (radeon_crtc->crtc_id % 2)
 		tmp += 4;
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, tmp);
 
+	if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+		WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+		       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+		for (i = 0; i < rdev->usec_timeout; i++) {
+			if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+			    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+				break;
+			udelay(1);
+		}
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -2973,7 +2990,7 @@ 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/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 75c05631146d..150e3186bec0 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -810,6 +810,10 @@
 #       define LATENCY_LOW_WATERMARK(x)                   ((x) << 0)
 #       define LATENCY_HIGH_WATERMARK(x)                  ((x) << 16)
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define IH_RB_CNTL                                        0x3e00
 #       define IH_RB_ENABLE                               (1 << 0)
 #       define IH_IB_SIZE(x)                              ((x) << 1) /* log2 */
@@ -1100,7 +1104,7 @@
  * 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)
@@ -1115,7 +1119,7 @@
 #              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/r100.c b/drivers/gpu/drm/radeon/r100.c
index d0314ecbd7c1..46470dd7c710 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2935,9 +2935,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
 	seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
 	seq_printf(m, "%u dwords in ring\n", count);
-	for (j = 0; j <= count; j++) {
-		i = (rdp + j) & ring->ptr_mask;
-		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+	if (ring->ready) {
+		for (j = 0; j <= count; j++) {
+			i = (rdp + j) & ring->ptr_mask;
+			seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index b9b1139da356..0efe2a93ca97 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -238,9 +238,19 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
 	 * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
 	 */
-	if (ASIC_IS_DCE3(rdev)) {
+	if (ASIC_IS_DCE32(rdev)) {
+		if (dig->dig_encoder == 0) {
+			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+		} else {
+			WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+		}
+	} else if (ASIC_IS_DCE3(rdev)) {
 		/* according to the reg specs, this should DCE3.2 only, but in
-		 * practice it seems to cover DCE3.0 as well.
+		 * practice it seems to cover DCE3.0/3.1 as well.
 		 */
 		if (dig->dig_encoder == 0) {
 			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
@@ -252,7 +262,7 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
 		}
 	} else {
-		/* according to the reg specs, this should be DCE2.0 and DCE3.0 */
+		/* according to the reg specs, this should be DCE2.0 and DCE3.0/3.1 */
 		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
 		       AUDIO_DTO_MODULE(clock / 10));
 	}
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 79df558f8c40..2fd2241b6df9 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1259,7 +1259,7 @@
  */
 #              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_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index dea6f63c9724..239a4074f122 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -715,13 +715,16 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev)
 								(ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT *)
 								(ctx->bios + data_offset +
 								 le16_to_cpu(router_obj->asObjects[k].usSrcDstTableOffset));
+							u8 *num_dst_objs = (u8 *)
+								((u8 *)router_src_dst_table + 1 +
+								 (router_src_dst_table->ucNumberOfSrc * 2));
+							u16 *dst_objs = (u16 *)(num_dst_objs + 1);
 							int enum_id;
 
 							router.router_id = router_obj_id;
-							for (enum_id = 0; enum_id < router_src_dst_table->ucNumberOfDst;
-							     enum_id++) {
+							for (enum_id = 0; enum_id < (*num_dst_objs); enum_id++) {
 								if (le16_to_cpu(path->usConnObjectId) ==
-								    le16_to_cpu(router_src_dst_table->usDstObjectID[enum_id]))
+								    le16_to_cpu(dst_objs[enum_id]))
 									break;
 							}
 
@@ -1651,7 +1654,9 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct
 								kfree(edid);
 						}
 					}
-					record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
+					record += fake_edid_record->ucFakeEDIDLength ?
+						fake_edid_record->ucFakeEDIDLength + 2 :
+						sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
 					break;
 				case LCD_PANEL_RESOLUTION_RECORD_TYPE:
 					panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2399f25ec037..5a87c9fc78d3 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1489,6 +1489,24 @@ static const struct drm_connector_funcs radeon_dp_connector_funcs = {
 	.force = radeon_dvi_force,
 };
 
+static const struct drm_connector_funcs radeon_edp_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = radeon_dp_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = radeon_lvds_set_property,
+	.destroy = radeon_dp_connector_destroy,
+	.force = radeon_dvi_force,
+};
+
+static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = radeon_dp_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = radeon_lvds_set_property,
+	.destroy = radeon_dp_connector_destroy,
+	.force = radeon_dvi_force,
+};
+
 void
 radeon_add_atom_connector(struct drm_device *dev,
 			  uint32_t connector_id,
@@ -1580,8 +1598,6 @@ radeon_add_atom_connector(struct drm_device *dev,
 			goto failed;
 		radeon_dig_connector->igp_lane_info = igp_lane_info;
 		radeon_connector->con_priv = radeon_dig_connector;
-		drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			/* add DP i2c bus */
 			if (connector_type == DRM_MODE_CONNECTOR_eDP)
@@ -1598,6 +1614,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_VGA:
 		case DRM_MODE_CONNECTOR_DVIA:
 		default:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			radeon_connector->dac_load_detect = true;
@@ -1610,6 +1630,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_HDMIA:
 		case DRM_MODE_CONNECTOR_HDMIB:
 		case DRM_MODE_CONNECTOR_DisplayPort:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.underscan_property,
 						      UNDERSCAN_OFF);
@@ -1634,6 +1658,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 			break;
 		case DRM_MODE_CONNECTOR_LVDS:
 		case DRM_MODE_CONNECTOR_eDP:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_lvds_bridge_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      dev->mode_config.scaling_mode_property,
 						      DRM_MODE_SCALE_FULLSCREEN);
@@ -1797,7 +1825,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
+			drm_connector_init(dev, &radeon_connector->base, &radeon_edp_connector_funcs, connector_type);
 			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				/* add DP i2c bus */
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 7e265a58141f..fe36f1d9496d 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -80,9 +80,11 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		p->relocs[i].lobj.bo = p->relocs[i].robj;
 		p->relocs[i].lobj.written = !!r->write_domain;
 
-		/* the first reloc of an UVD job is the
-		   msg and that must be in VRAM */
-		if (p->ring == R600_RING_TYPE_UVD_INDEX && i == 0) {
+		/* the first reloc of an UVD job is the msg and that must be in
+		   VRAM, also but everything into VRAM on AGP cards to avoid
+		   image corruptions */
+		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
+		    (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_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b0dc0b6cb4e0..8df1525f71d2 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1196,13 +1196,22 @@ int radeon_device_init(struct radeon_device *rdev,
 			return r;
 	}
 	if ((radeon_testing & 1)) {
-		radeon_test_moves(rdev);
+		if (rdev->accel_working)
+			radeon_test_moves(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping move tests\n");
 	}
 	if ((radeon_testing & 2)) {
-		radeon_test_syncing(rdev);
+		if (rdev->accel_working)
+			radeon_test_syncing(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping sync tests\n");
 	}
 	if (radeon_benchmarking) {
-		radeon_benchmark(rdev, radeon_benchmarking);
+		if (rdev->accel_working)
+			radeon_benchmark(rdev, radeon_benchmarking);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 4f2d4f4c1dab..7e292d899209 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -414,6 +414,9 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		value = rdev->config.si.tile_mode_array;
 		value_size = sizeof(uint32_t)*32;
 		break;
+	case RADEON_INFO_SI_CP_DMA_COMPUTE:
+		*value = 1;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 83f6295a0e5e..6e0f4809bda0 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -823,9 +823,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	 * packet that is the root issue
 	 */
 	i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
-	for (j = 0; j <= (count + 32); j++) {
-		seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
-		i = (i + 1) & ring->ptr_mask;
+	if (ring->ready) {
+		for (j = 0; j <= (count + 32); j++) {
+			seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
+			i = (i + 1) & ring->ptr_mask;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index bbed4af8d0bc..f9ebf2bf8b57 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -37,8 +37,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 	struct radeon_bo **gtt_obj = NULL;
 	struct radeon_fence *fence = 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/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 233a9b9fa1f7..b8074a8ec75a 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -174,10 +174,13 @@ int rs400_gart_enable(struct radeon_device *rdev)
 	/* FIXME: according to doc we should set HIDE_MMCFG_BAR=0,
 	 * AGPMODE30=0 & AGP30ENHANCED=0 in NB_CNTL */
 	if ((rdev->family == CHIP_RS690) || (rdev->family == CHIP_RS740)) {
-		WREG32_MC(RS480_MC_MISC_CNTL,
-			  (RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN));
+		tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+		tmp |= RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN;
+		WREG32_MC(RS480_MC_MISC_CNTL, tmp);
 	} else {
-		WREG32_MC(RS480_MC_MISC_CNTL, RS480_GART_INDEX_REG_EN);
+		tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+		tmp |= RS480_GART_INDEX_REG_EN;
+		WREG32_MC(RS480_MC_MISC_CNTL, tmp);
 	}
 	/* Enable gart */
 	WREG32_MC(RS480_AGP_ADDRESS_SPACE_SIZE, (RS480_GART_EN | size_reg));
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1a96a16b9996..f054a3b6c4b8 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1467,7 +1467,8 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev,
 				   struct drm_display_mode *mode,
 				   struct drm_display_mode *other_mode)
 {
-	u32 tmp;
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -1482,16 +1483,30 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev,
 	 * non-linked crtcs for maximum line buffer allocation.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (other_mode)
+		if (other_mode) {
 			tmp = 0; /* 1/2 */
-		else
+			buffer_alloc = 1;
+		} else {
 			tmp = 2; /* whole */
-	} else
+			buffer_alloc = 2;
+		}
+	} else {
 		tmp = 0;
+		buffer_alloc = 0;
+	}
 
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset,
 	       DC_LB_MEMORY_CONFIG(tmp));
 
+	WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+	       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+		    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+			break;
+		udelay(1);
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -3796,13 +3811,64 @@ static int si_vm_packet3_ce_check(struct radeon_device *rdev,
 	return 0;
 }
 
+static int si_vm_packet3_cp_dma_check(u32 *ib, u32 idx)
+{
+	u32 start_reg, reg, i;
+	u32 command = ib[idx + 4];
+	u32 info = ib[idx + 1];
+	u32 idx_value = ib[idx];
+	if (command & PACKET3_CP_DMA_CMD_SAS) {
+		/* src address space is register */
+		if (((info & 0x60000000) >> 29) == 0) {
+			start_reg = idx_value << 2;
+			if (command & PACKET3_CP_DMA_CMD_SAIC) {
+				reg = start_reg;
+				if (!si_vm_reg_valid(reg)) {
+					DRM_ERROR("CP DMA Bad SRC register\n");
+					return -EINVAL;
+				}
+			} else {
+				for (i = 0; i < (command & 0x1fffff); i++) {
+					reg = start_reg + (4 * i);
+					if (!si_vm_reg_valid(reg)) {
+						DRM_ERROR("CP DMA Bad SRC register\n");
+						return -EINVAL;
+					}
+				}
+			}
+		}
+	}
+	if (command & PACKET3_CP_DMA_CMD_DAS) {
+		/* dst address space is register */
+		if (((info & 0x00300000) >> 20) == 0) {
+			start_reg = ib[idx + 2];
+			if (command & PACKET3_CP_DMA_CMD_DAIC) {
+				reg = start_reg;
+				if (!si_vm_reg_valid(reg)) {
+					DRM_ERROR("CP DMA Bad DST register\n");
+					return -EINVAL;
+				}
+			} else {
+				for (i = 0; i < (command & 0x1fffff); i++) {
+					reg = start_reg + (4 * i);
+				if (!si_vm_reg_valid(reg)) {
+						DRM_ERROR("CP DMA Bad DST register\n");
+						return -EINVAL;
+					}
+				}
+			}
+		}
+	}
+	return 0;
+}
+
 static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 				   u32 *ib, struct radeon_cs_packet *pkt)
 {
+	int r;
 	u32 idx = pkt->idx + 1;
 	u32 idx_value = ib[idx];
 	u32 start_reg, end_reg, reg, i;
-	u32 command, info;
 
 	switch (pkt->opcode) {
 	case PACKET3_NOP:
@@ -3903,50 +3969,9 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 		}
 		break;
 	case PACKET3_CP_DMA:
-		command = ib[idx + 4];
-		info = ib[idx + 1];
-		if (command & PACKET3_CP_DMA_CMD_SAS) {
-			/* src address space is register */
-			if (((info & 0x60000000) >> 29) == 0) {
-				start_reg = idx_value << 2;
-				if (command & PACKET3_CP_DMA_CMD_SAIC) {
-					reg = start_reg;
-					if (!si_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad SRC register\n");
-						return -EINVAL;
-					}
-				} else {
-					for (i = 0; i < (command & 0x1fffff); i++) {
-						reg = start_reg + (4 * i);
-						if (!si_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad SRC register\n");
-							return -EINVAL;
-						}
-					}
-				}
-			}
-		}
-		if (command & PACKET3_CP_DMA_CMD_DAS) {
-			/* dst address space is register */
-			if (((info & 0x00300000) >> 20) == 0) {
-				start_reg = ib[idx + 2];
-				if (command & PACKET3_CP_DMA_CMD_DAIC) {
-					reg = start_reg;
-					if (!si_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad DST register\n");
-						return -EINVAL;
-					}
-				} else {
-					for (i = 0; i < (command & 0x1fffff); i++) {
-						reg = start_reg + (4 * i);
-						if (!si_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad DST register\n");
-							return -EINVAL;
-						}
-					}
-				}
-			}
-		}
+		r = si_vm_packet3_cp_dma_check(ib, idx);
+		if (r)
+			return r;
 		break;
 	default:
 		DRM_ERROR("Invalid GFX packet3: 0x%x\n", pkt->opcode);
@@ -3958,6 +3983,7 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 				       u32 *ib, struct radeon_cs_packet *pkt)
 {
+	int r;
 	u32 idx = pkt->idx + 1;
 	u32 idx_value = ib[idx];
 	u32 start_reg, reg, i;
@@ -4030,6 +4056,11 @@ static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 				return -EINVAL;
 		}
 		break;
+	case PACKET3_CP_DMA:
+		r = si_vm_packet3_cp_dma_check(ib, idx);
+		if (r)
+			return r;
+		break;
 	default:
 		DRM_ERROR("Invalid Compute packet3: 0x%x\n", pkt->opcode);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 8f2d7d4f9b28..495f41f2900b 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -97,6 +97,10 @@
 
 #define DMIF_ADDR_CALC  				0xC00
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define	SRBM_STATUS				        0xE50
 #define		GRBM_RQ_PENDING 			(1 << 5)
 #define		VMC_BUSY 				(1 << 8)
@@ -924,7 +928,7 @@
  * 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)
@@ -939,7 +943,7 @@
 #              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