Merge tag 'v3.13' into stable-3.14

Linux 3.13 Conflicts: security/selinux/hooks.c Trivial merge issue in selinux_inet_conn_request() likely due to me including patches that I sent to the stable folks in my next tree resulting in the patch hitting twice (I think). Thankfully it was an easy fix this time, but regardless, lesson learned, I will not do that again.
author: Paul Moore <pmoore@redhat.com> 2014-01-28 14:44:16 -0500
committer: Paul Moore <pmoore@redhat.com> 2014-02-05 10:39:48 -0500
commit: 825e587af2e90e9b953849f3347a01d8f383d577 (patch)
tree: e48942a05882da47544e179c6a0c920e00137a6a /drivers/gpu/drm/radeon
parent: 8ed814602876bec9bad2649ca17f34b499357a1c (diff)
parent: d8ec26d7f8287f5788a494f56e8814210f0e64be (diff)
69 files changed, 3046 insertions, 1436 deletions
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index af10f8571d8..92be50c39ff 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -1711,7 +1711,9 @@ typedef struct _PIXEL_CLOCK_PARAMETERS_V6
 #define PIXEL_CLOCK_V6_MISC_HDMI_BPP_MASK           0x0c
 #define PIXEL_CLOCK_V6_MISC_HDMI_24BPP              0x00
 #define PIXEL_CLOCK_V6_MISC_HDMI_36BPP              0x04
+#define PIXEL_CLOCK_V6_MISC_HDMI_36BPP_V6           0x08    //for V6, the correct defintion for 36bpp should be 2 for 36bpp(2:1)
 #define PIXEL_CLOCK_V6_MISC_HDMI_30BPP              0x08
+#define PIXEL_CLOCK_V6_MISC_HDMI_30BPP_V6           0x04    //for V6, the correct defintion for 30bpp should be 1 for 36bpp(5:4)
 #define PIXEL_CLOCK_V6_MISC_HDMI_48BPP              0x0c
 #define PIXEL_CLOCK_V6_MISC_REF_DIV_SRC             0x10
 #define PIXEL_CLOCK_V6_MISC_GEN_DPREFCLK            0x40
@@ -2223,7 +2225,7 @@ typedef struct	_SET_VOLTAGE_PARAMETERS_V2
   USHORT   usVoltageLevel;              // real voltage level
 }SET_VOLTAGE_PARAMETERS_V2;
 
-
+// used by both SetVoltageTable v1.3 and v1.4
 typedef struct	_SET_VOLTAGE_PARAMETERS_V1_3
 {
   UCHAR    ucVoltageType;               // To tell which voltage to set up, VDDC/MVDDC/MVDDQ/VDDCI
@@ -2290,15 +2292,36 @@ typedef struct  _GET_LEAKAGE_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_1
 #define	ATOM_GET_VOLTAGE_VID                0x00
 #define ATOM_GET_VOTLAGE_INIT_SEQ           0x03
 #define ATOM_GET_VOLTTAGE_PHASE_PHASE_VID   0x04
-// for SI, this state map to 0xff02 voltage state in Power Play table, which is power boost state
-#define	ATOM_GET_VOLTAGE_STATE0_LEAKAGE_VID 0x10
+#define ATOM_GET_VOLTAGE_SVID2              0x07        //Get SVI2 Regulator Info
 
+// for SI, this state map to 0xff02 voltage state in Power Play table, which is power boost state
+#define ATOM_GET_VOLTAGE_STATE0_LEAKAGE_VID 0x10
 // for SI, this state map to 0xff01 voltage state in Power Play table, which is performance state
 #define	ATOM_GET_VOLTAGE_STATE1_LEAKAGE_VID 0x11
-// undefined power state
+
 #define	ATOM_GET_VOLTAGE_STATE2_LEAKAGE_VID 0x12
 #define	ATOM_GET_VOLTAGE_STATE3_LEAKAGE_VID 0x13
 
+// New Added from CI Hawaii for GetVoltageInfoTable, input parameter structure
+typedef struct  _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2
+{
+  UCHAR    ucVoltageType;               // Input: To tell which voltage to set up, VDDC/MVDDC/MVDDQ/VDDCI
+  UCHAR    ucVoltageMode;               // Input: Indicate action: Get voltage info
+  USHORT   usVoltageLevel;              // Input: real voltage level in unit of mv or Voltage Phase (0, 1, 2, .. ) or Leakage Id 
+  ULONG    ulSCLKFreq;                  // Input: when ucVoltageMode= ATOM_GET_VOLTAGE_EVV_VOLTAGE, DPM state SCLK frequency, Define in PPTable SCLK/Voltage dependence table
+}GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2;
+
+// New in GetVoltageInfo v1.2 ucVoltageMode
+#define ATOM_GET_VOLTAGE_EVV_VOLTAGE        0x09        
+
+// New Added from CI Hawaii for EVV feature 
+typedef struct  _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2
+{
+  USHORT   usVoltageLevel;                               // real voltage level in unit of mv
+  USHORT   usVoltageId;                                  // Voltage Id programmed in Voltage Regulator
+  ULONG    ulReseved;
+}GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2;
+
 /****************************************************************************/	
 // Structures used by TVEncoderControlTable
 /****************************************************************************/	
@@ -3864,6 +3887,8 @@ typedef struct _ATOM_GPIO_PIN_ASSIGNMENT
 #define PP_AC_DC_SWITCH_GPIO_PINID          60
 //from SMU7.x, if ucGPIO_ID=VDDC_REGULATOR_VRHOT_GPIO_PINID in GPIO_LUTable, VRHot feature is enable
 #define VDDC_VRHOT_GPIO_PINID               61
+//if ucGPIO_ID=VDDC_PCC_GPIO_PINID in GPIO_LUTable, Peak Current Control feature is enabled
+#define VDDC_PCC_GPIO_PINID                 62
 
 typedef struct _ATOM_GPIO_PIN_LUT
 {
@@ -4169,10 +4194,10 @@ typedef struct _ATOM_COMMON_RECORD_HEADER
 #define ATOM_OBJECT_LINK_RECORD_TYPE                   18 //Once this record is present under one object, it indicats the oobject is linked to another obj described by the record
 #define ATOM_CONNECTOR_REMOTE_CAP_RECORD_TYPE          19
 #define ATOM_ENCODER_CAP_RECORD_TYPE                   20
-
+#define ATOM_BRACKET_LAYOUT_RECORD_TYPE                21
 
 //Must be updated when new record type is added,equal to that record definition!
-#define ATOM_MAX_OBJECT_RECORD_NUMBER             ATOM_ENCODER_CAP_RECORD_TYPE
+#define ATOM_MAX_OBJECT_RECORD_NUMBER             ATOM_BRACKET_LAYOUT_RECORD_TYPE
 
 typedef struct  _ATOM_I2C_RECORD
 {
@@ -4397,6 +4422,31 @@ typedef struct _ATOM_CONNECTOR_REMOTE_CAP_RECORD
   USHORT                      usReserved;
 }ATOM_CONNECTOR_REMOTE_CAP_RECORD;
 
+typedef struct  _ATOM_CONNECTOR_LAYOUT_INFO
+{
+   USHORT usConnectorObjectId;
+   UCHAR  ucConnectorType;
+   UCHAR  ucPosition;
+}ATOM_CONNECTOR_LAYOUT_INFO;
+
+// define ATOM_CONNECTOR_LAYOUT_INFO.ucConnectorType to describe the display connector size
+#define CONNECTOR_TYPE_DVI_D                 1
+#define CONNECTOR_TYPE_DVI_I                 2
+#define CONNECTOR_TYPE_VGA                   3
+#define CONNECTOR_TYPE_HDMI                  4
+#define CONNECTOR_TYPE_DISPLAY_PORT          5
+#define CONNECTOR_TYPE_MINI_DISPLAY_PORT     6
+
+typedef struct  _ATOM_BRACKET_LAYOUT_RECORD
+{
+  ATOM_COMMON_RECORD_HEADER   sheader;
+  UCHAR                       ucLength;
+  UCHAR                       ucWidth;
+  UCHAR                       ucConnNum;
+  UCHAR                       ucReserved;
+  ATOM_CONNECTOR_LAYOUT_INFO  asConnInfo[1];
+}ATOM_BRACKET_LAYOUT_RECORD;
+
 /****************************************************************************/	
 // ASIC voltage data table
 /****************************************************************************/	
@@ -4524,8 +4574,9 @@ typedef struct _ATOM_VOLTAGE_OBJECT_HEADER_V3{
 #define VOLTAGE_OBJ_VR_I2C_INIT_SEQ          3        //VOLTAGE REGULATOR INIT sequece through I2C -> ATOM_I2C_VOLTAGE_OBJECT_V3
 #define VOLTAGE_OBJ_PHASE_LUT                4        //Set Vregulator Phase lookup table ->ATOM_GPIO_VOLTAGE_OBJECT_V3
 #define VOLTAGE_OBJ_SVID2                    7        //Indicate voltage control by SVID2 ->ATOM_SVID2_VOLTAGE_OBJECT_V3
-#define	VOLTAGE_OBJ_PWRBOOST_LEAKAGE_LUT     0x10     //Powerboost Voltage and LeakageId lookup table->ATOM_LEAKAGE_VOLTAGE_OBJECT_V3
-#define	VOLTAGE_OBJ_HIGH_STATE_LEAKAGE_LUT   0x11     //High voltage state Voltage and LeakageId lookup table->ATOM_LEAKAGE_VOLTAGE_OBJECT_V3
+#define VOLTAGE_OBJ_EVV                      8 
+#define VOLTAGE_OBJ_PWRBOOST_LEAKAGE_LUT     0x10     //Powerboost Voltage and LeakageId lookup table->ATOM_LEAKAGE_VOLTAGE_OBJECT_V3
+#define VOLTAGE_OBJ_HIGH_STATE_LEAKAGE_LUT   0x11     //High voltage state Voltage and LeakageId lookup table->ATOM_LEAKAGE_VOLTAGE_OBJECT_V3
 #define VOLTAGE_OBJ_HIGH1_STATE_LEAKAGE_LUT  0x12     //High1 voltage state Voltage and LeakageId lookup table->ATOM_LEAKAGE_VOLTAGE_OBJECT_V3
 
 typedef struct  _VOLTAGE_LUT_ENTRY_V2
@@ -4552,6 +4603,10 @@ typedef struct  _ATOM_I2C_VOLTAGE_OBJECT_V3
    VOLTAGE_LUT_ENTRY asVolI2cLut[1];        // end with 0xff
 }ATOM_I2C_VOLTAGE_OBJECT_V3;
 
+// ATOM_I2C_VOLTAGE_OBJECT_V3.ucVoltageControlFlag
+#define VOLTAGE_DATA_ONE_BYTE                0
+#define VOLTAGE_DATA_TWO_BYTE                1
+
 typedef struct  _ATOM_GPIO_VOLTAGE_OBJECT_V3
 {
    ATOM_VOLTAGE_OBJECT_HEADER_V3 sHeader;   // voltage mode = VOLTAGE_OBJ_GPIO_LUT or VOLTAGE_OBJ_PHASE_LUT
@@ -4584,7 +4639,8 @@ typedef struct  _ATOM_SVID2_VOLTAGE_OBJECT_V3
 // 1:0  offset trim, 
    USHORT   usLoadLine_PSI;    
 // GPU GPIO pin Id to SVID2 regulator VRHot pin. possible value 0~31. 0 means GPIO0, 31 means GPIO31
-   UCHAR    ucReserved[2];
+   UCHAR    ucSVDGpioId;     //0~31 indicate GPIO0~31
+   UCHAR    ucSVCGpioId;     //0~31 indicate GPIO0~31
    ULONG    ulReserved;
 }ATOM_SVID2_VOLTAGE_OBJECT_V3;
 
@@ -4637,6 +4693,49 @@ typedef struct  _ATOM_ASIC_PROFILING_INFO_V2_1
   USHORT usElbVDDCI_LevelArrayOffset;    // offset of 2 dimension voltage level USHORT array
 }ATOM_ASIC_PROFILING_INFO_V2_1;
 
+typedef struct  _ATOM_ASIC_PROFILING_INFO_V3_1
+{
+  ATOM_COMMON_TABLE_HEADER         asHeader; 
+  ULONG  ulEvvDerateTdp;
+  ULONG  ulEvvDerateTdc;
+  ULONG  ulBoardCoreTemp;
+  ULONG  ulMaxVddc;
+  ULONG  ulMinVddc;
+  ULONG  ulLoadLineSlop;
+  ULONG  ulLeakageTemp;
+  ULONG  ulLeakageVoltage;
+  ULONG  ulCACmEncodeRange;
+  ULONG  ulCACmEncodeAverage;
+  ULONG  ulCACbEncodeRange;
+  ULONG  ulCACbEncodeAverage;
+  ULONG  ulKt_bEncodeRange;
+  ULONG  ulKt_bEncodeAverage;
+  ULONG  ulKv_mEncodeRange;
+  ULONG  ulKv_mEncodeAverage;
+  ULONG  ulKv_bEncodeRange;
+  ULONG  ulKv_bEncodeAverage;
+  ULONG  ulLkgEncodeLn_MaxDivMin;
+  ULONG  ulLkgEncodeMin;
+  ULONG  ulEfuseLogisticAlpha;
+  USHORT usPowerDpm0;
+  USHORT usCurrentDpm0;
+  USHORT usPowerDpm1;
+  USHORT usCurrentDpm1;
+  USHORT usPowerDpm2;
+  USHORT usCurrentDpm2;
+  USHORT usPowerDpm3;
+  USHORT usCurrentDpm3;
+  USHORT usPowerDpm4;
+  USHORT usCurrentDpm4;
+  USHORT usPowerDpm5;
+  USHORT usCurrentDpm5;
+  USHORT usPowerDpm6;
+  USHORT usCurrentDpm6;
+  USHORT usPowerDpm7;
+  USHORT usCurrentDpm7;
+}ATOM_ASIC_PROFILING_INFO_V3_1;
+
+
 typedef struct _ATOM_POWER_SOURCE_OBJECT
 {
 	UCHAR	ucPwrSrcId;													// Power source
@@ -5808,6 +5907,8 @@ typedef struct _ATOM_ASIC_INTERNAL_SS_INFO_V3
 #define ATOM_S7_DOS_MODE_PIXEL_DEPTHb0      0x0C
 #define ATOM_S7_DOS_MODE_PIXEL_FORMATb0     0xF0
 #define ATOM_S7_DOS_8BIT_DAC_ENb1           0x01
+#define ATOM_S7_ASIC_INIT_COMPLETEb1        0x02
+#define ATOM_S7_ASIC_INIT_COMPLETE_MASK     0x00000200
 #define ATOM_S7_DOS_MODE_NUMBERw1           0x0FFFF
 
 #define ATOM_S7_DOS_8BIT_DAC_EN_SHIFT       8
@@ -6242,6 +6343,7 @@ typedef struct _ATOM_MC_INIT_PARAM_TABLE
 #define _128Mx32            0x53
 #define _256Mx8             0x61
 #define _256Mx16            0x62
+#define _512Mx8             0x71
 
 #define SAMSUNG             0x1
 #define INFINEON            0x2
@@ -6987,9 +7089,10 @@ typedef struct _ATOM_DISP_OUT_INFO_V3
   UCHAR  ucMaxDispEngineNum;
   UCHAR  ucMaxActiveDispEngineNum;
   UCHAR  ucMaxPPLLNum;
-  UCHAR  ucCoreRefClkSource;                          // value of CORE_REF_CLK_SOURCE
-  UCHAR  ucReserved[3];
-	ASIC_TRANSMITTER_INFO_V2  asTransmitterInfo[1];     // for alligment only
+  UCHAR  ucCoreRefClkSource;                    // value of CORE_REF_CLK_SOURCE
+  UCHAR  ucDispCaps;
+  UCHAR  ucReserved[2];
+  ASIC_TRANSMITTER_INFO_V2  asTransmitterInfo[1];     // for alligment only
 }ATOM_DISP_OUT_INFO_V3;
 
 //ucDispCaps
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index bf87f6d435f..0b9621c9aee 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);
@@ -1180,23 +1202,18 @@ 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);
-	else if (rdev->family == CHIP_VERDE)
+	else if ((rdev->family == CHIP_VERDE) ||
+		 (rdev->family == CHIP_OLAND) ||
+		 (rdev->family == CHIP_HAINAN)) /* for completeness.  HAINAN has no display hw */
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16);
 
 	switch (radeon_crtc->crtc_id) {
@@ -1753,7 +1770,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				if (pll != ATOM_PPLL_INVALID)
 					return pll;
 			}
-		} else {
+		} else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */
 			/* use the same PPLL for all monitors with the same clock */
 			pll = radeon_get_shared_nondp_ppll(crtc);
 			if (pll != ATOM_PPLL_INVALID)
@@ -1910,6 +1927,21 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	int i;
 
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	if (crtc->fb) {
+		int r;
+		struct radeon_framebuffer *radeon_fb;
+		struct radeon_bo *rbo;
+
+		radeon_fb = to_radeon_framebuffer(crtc->fb);
+		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		r = radeon_bo_reserve(rbo, false);
+		if (unlikely(r))
+			DRM_ERROR("failed to reserve rbo before unpin\n");
+		else {
+			radeon_bo_unpin(rbo);
+			radeon_bo_unreserve(rbo);
+		}
+	}
 	/* disable the GRPH */
 	if (ASIC_IS_DCE4(rdev))
 		WREG32(EVERGREEN_GRPH_ENABLE + radeon_crtc->crtc_offset, 0);
@@ -1940,7 +1972,9 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 		break;
 	case ATOM_PPLL0:
 		/* disable the ppll */
-		if ((rdev->family == CHIP_ARUBA) || (rdev->family == CHIP_BONAIRE))
+		if ((rdev->family == CHIP_ARUBA) ||
+		    (rdev->family == CHIP_BONAIRE) ||
+		    (rdev->family == CHIP_HAWAII))
 			atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
 						  0, 0, ATOM_DISABLE, 0, 0, 0, 0, 0, false, &ss);
 		break;
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 00885417fff..fb3ae07a146 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -690,8 +690,7 @@ static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
 
 	/* set the lane count on the sink */
 	tmp = dp_info->dp_lane_count;
-	if (dp_info->dpcd[DP_DPCD_REV] >= 0x11 &&
-	    dp_info->dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP)
+	if (drm_dp_enhanced_frame_cap(dp_info->dpcd))
 		tmp |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
 	radeon_write_dpcd_reg(dp_info->radeon_connector, DP_LANE_COUNT_SET, tmp);
 
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 5e891b226ac..a42d61571f4 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -213,7 +213,7 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	props.type = BACKLIGHT_RAW;
 	snprintf(bl_name, sizeof(bl_name),
 		 "radeon_bl%d", dev->primary->index);
-	bd = backlight_device_register(bl_name, &drm_connector->kdev,
+	bd = backlight_device_register(bl_name, drm_connector->kdev,
 				       pdata, &radeon_atom_backlight_ops, &props);
 	if (IS_ERR(bd)) {
 		DRM_ERROR("Backlight registration failed\n");
@@ -1662,19 +1662,11 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
 			/* enable the transmitter */
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		} else {
 			/* setup and enable the encoder and transmitter */
 			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 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_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) {
 			if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
@@ -1692,16 +1684,11 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
-			/* disable the transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-		} else if (ASIC_IS_DCE4(rdev)) {
+		if (ASIC_IS_DCE4(rdev)) {
 			/* disable the transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
 		} else {
 			/* disable the encoder and transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
 			atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0);
 		}
@@ -2410,6 +2397,15 @@ static void radeon_atom_encoder_prepare(struct drm_encoder *encoder)
 
 	/* this is needed for the pll/ss setup to work correctly in some cases */
 	atombios_set_encoder_crtc_source(encoder);
+	/* set up the FMT blocks */
+	if (ASIC_IS_DCE8(rdev))
+		dce8_program_fmt(encoder);
+	else if (ASIC_IS_DCE4(rdev))
+		dce4_program_fmt(encoder);
+	else if (ASIC_IS_DCE3(rdev))
+		dce3_program_fmt(encoder);
+	else if (ASIC_IS_AVIVO(rdev))
+		avivo_program_fmt(encoder);
 }
 
 static void radeon_atom_encoder_commit(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index deaf98cdca3..f685035dbe3 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -44,7 +44,7 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args;
 	int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction);
 	unsigned char *base;
-	u16 out;
+	u16 out = cpu_to_le16(0);
 
 	memset(&args, 0, sizeof(args));
 
@@ -55,9 +55,14 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 			DRM_ERROR("hw i2c: tried to write too many bytes (%d vs 3)\n", num);
 			return -EINVAL;
 		}
-		args.ucRegIndex = buf[0];
-		if (num > 1)
-			memcpy(&out, &buf[1], num - 1);
+		if (buf == NULL)
+			args.ucRegIndex = 0;
+		else
+			args.ucRegIndex = buf[0];
+		if (num)
+			num--;
+		if (num)
+			memcpy(&out, &buf[1], num);
 		args.lpI2CDataOut = cpu_to_le16(out);
 	} else {
 		if (num > ATOM_MAX_HW_I2C_READ) {
@@ -94,14 +99,14 @@ int radeon_atom_hw_i2c_xfer(struct i2c_adapter *i2c_adap,
 	struct radeon_i2c_chan *i2c = i2c_get_adapdata(i2c_adap);
 	struct i2c_msg *p;
 	int i, remaining, current_count, buffer_offset, max_bytes, ret;
-	u8 buf = 0, flags;
+	u8 flags;
 
 	/* check for bus probe */
 	p = &msgs[0];
 	if ((num == 1) && (p->len == 0)) {
 		ret = radeon_process_i2c_ch(i2c,
 					    p->addr, HW_I2C_WRITE,
-					    &buf, 1);
+					    NULL, 0);
 		if (ret)
 			return ret;
 		else
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 51e947a97ed..1ed47997635 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -40,6 +40,20 @@
 #define VOLTAGE_VID_OFFSET_SCALE1    625
 #define VOLTAGE_VID_OFFSET_SCALE2    100
 
+static const struct ci_pt_defaults defaults_hawaii_xt =
+{
+	1, 0xF, 0xFD, 0x19, 5, 0x14, 0, 0xB0000,
+	{ 0x84,  0x0,   0x0,   0x7F,  0x0,   0x0,   0x5A,  0x60,  0x51,  0x8E,  0x79,  0x6B,  0x5F,  0x90,  0x79  },
+	{ 0x1EA, 0x1EA, 0x1EA, 0x224, 0x224, 0x224, 0x24F, 0x24F, 0x24F, 0x28E, 0x28E, 0x28E, 0x2BC, 0x2BC, 0x2BC }
+};
+
+static const struct ci_pt_defaults defaults_hawaii_pro =
+{
+	1, 0xF, 0xFD, 0x19, 5, 0x14, 0, 0x65062,
+	{ 0x93,  0x0,   0x0,   0x97,  0x0,   0x0,   0x6B,  0x60,  0x51,  0x95,  0x79,  0x6B,  0x5F,  0x90,  0x79  },
+	{ 0x1EA, 0x1EA, 0x1EA, 0x224, 0x224, 0x224, 0x24F, 0x24F, 0x24F, 0x28E, 0x28E, 0x28E, 0x2BC, 0x2BC, 0x2BC }
+};
+
 static const struct ci_pt_defaults defaults_bonaire_xt =
 {
 	1, 0xF, 0xFD, 0x19, 5, 45, 0, 0xB0000,
@@ -187,22 +201,38 @@ static void ci_initialize_powertune_defaults(struct radeon_device *rdev)
 	struct ci_power_info *pi = ci_get_pi(rdev);
 
 	switch (rdev->pdev->device) {
-        case 0x6650:
-        case 0x6658:
-        case 0x665C:
-        default:
+	case 0x6650:
+	case 0x6658:
+	case 0x665C:
+	default:
 		pi->powertune_defaults = &defaults_bonaire_xt;
 		break;
-        case 0x6651:
-        case 0x665D:
+	case 0x6651:
+	case 0x665D:
 		pi->powertune_defaults = &defaults_bonaire_pro;
 		break;
-        case 0x6640:
+	case 0x6640:
 		pi->powertune_defaults = &defaults_saturn_xt;
 		break;
-        case 0x6641:
+	case 0x6641:
 		pi->powertune_defaults = &defaults_saturn_pro;
 		break;
+	case 0x67B8:
+	case 0x67B0:
+	case 0x67A0:
+	case 0x67A1:
+	case 0x67A2:
+	case 0x67A8:
+	case 0x67A9:
+	case 0x67AA:
+	case 0x67B9:
+	case 0x67BE:
+		pi->powertune_defaults = &defaults_hawaii_xt;
+		break;
+	case 0x67BA:
+	case 0x67B1:
+		pi->powertune_defaults = &defaults_hawaii_pro;
+		break;
 	}
 
 	pi->dte_tj_offset = 0;
@@ -5142,9 +5172,15 @@ int ci_dpm_init(struct radeon_device *rdev)
 	rdev->pm.dpm.dyn_state.valid_mclk_values.count = 0;
 	rdev->pm.dpm.dyn_state.valid_mclk_values.values = NULL;
 
-	pi->thermal_temp_setting.temperature_low = 99500;
-	pi->thermal_temp_setting.temperature_high = 100000;
-	pi->thermal_temp_setting.temperature_shutdown = 104000;
+	if (rdev->family == CHIP_HAWAII) {
+		pi->thermal_temp_setting.temperature_low = 94500;
+		pi->thermal_temp_setting.temperature_high = 95000;
+		pi->thermal_temp_setting.temperature_shutdown = 104000;
+	} else {
+		pi->thermal_temp_setting.temperature_low = 99500;
+		pi->thermal_temp_setting.temperature_high = 100000;
+		pi->thermal_temp_setting.temperature_shutdown = 104000;
+	}
 
 	pi->uvd_enabled = false;
 
diff --git a/drivers/gpu/drm/radeon/ci_smc.c b/drivers/gpu/drm/radeon/ci_smc.c
index 252e10a41cf..9c745dd2243 100644
--- a/drivers/gpu/drm/radeon/ci_smc.c
+++ b/drivers/gpu/drm/radeon/ci_smc.c
@@ -217,6 +217,10 @@ int ci_load_smc_ucode(struct radeon_device *rdev, u32 limit)
 		ucode_start_address = BONAIRE_SMC_UCODE_START;
 		ucode_size = BONAIRE_SMC_UCODE_SIZE;
 		break;
+	case CHIP_HAWAII:
+		ucode_start_address = HAWAII_SMC_UCODE_START;
+		ucode_size = HAWAII_SMC_UCODE_SIZE;
+		break;
 	default:
 		DRM_ERROR("unknown asic in smc ucode loader\n");
 		BUG();
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 9cd2bc989ac..e950fabd7f5 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -41,6 +41,14 @@ MODULE_FIRMWARE("radeon/BONAIRE_mc.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_rlc.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_sdma.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_smc.bin");
+MODULE_FIRMWARE("radeon/HAWAII_pfp.bin");
+MODULE_FIRMWARE("radeon/HAWAII_me.bin");
+MODULE_FIRMWARE("radeon/HAWAII_ce.bin");
+MODULE_FIRMWARE("radeon/HAWAII_mec.bin");
+MODULE_FIRMWARE("radeon/HAWAII_mc.bin");
+MODULE_FIRMWARE("radeon/HAWAII_rlc.bin");
+MODULE_FIRMWARE("radeon/HAWAII_sdma.bin");
+MODULE_FIRMWARE("radeon/HAWAII_smc.bin");
 MODULE_FIRMWARE("radeon/KAVERI_pfp.bin");
 MODULE_FIRMWARE("radeon/KAVERI_me.bin");
 MODULE_FIRMWARE("radeon/KAVERI_ce.bin");
@@ -67,11 +75,6 @@ extern void si_init_uvd_internal_cg(struct radeon_device *rdev);
 extern int cik_sdma_resume(struct radeon_device *rdev);
 extern void cik_sdma_enable(struct radeon_device *rdev, bool enable);
 extern void cik_sdma_fini(struct radeon_device *rdev);
-extern void cik_sdma_vm_set_page(struct radeon_device *rdev,
-				 struct radeon_ib *ib,
-				 uint64_t pe,
-				 uint64_t addr, unsigned count,
-				 uint32_t incr, uint32_t flags);
 static void cik_rlc_stop(struct radeon_device *rdev);
 static void cik_pcie_gen3_enable(struct radeon_device *rdev);
 static void cik_program_aspm(struct radeon_device *rdev);
@@ -1302,6 +1305,171 @@ static const u32 kalindi_mgcg_cgcg_init[] =
 	0xd80c, 0xff000ff0, 0x00000100
 };
 
+static const u32 hawaii_golden_spm_registers[] =
+{
+	0x30800, 0xe0ffffff, 0xe0000000
+};
+
+static const u32 hawaii_golden_common_registers[] =
+{
+	0x30800, 0xffffffff, 0xe0000000,
+	0x28350, 0xffffffff, 0x3a00161a,
+	0x28354, 0xffffffff, 0x0000002e,
+	0x9a10, 0xffffffff, 0x00018208,
+	0x98f8, 0xffffffff, 0x12011003
+};
+
+static const u32 hawaii_golden_registers[] =
+{
+	0x3354, 0x00000333, 0x00000333,
+	0x9a10, 0x00010000, 0x00058208,
+	0x9830, 0xffffffff, 0x00000000,
+	0x9834, 0xf00fffff, 0x00000400,
+	0x9838, 0x0002021c, 0x00020200,
+	0xc78, 0x00000080, 0x00000000,
+	0x5bb0, 0x000000f0, 0x00000070,
+	0x5bc0, 0xf0311fff, 0x80300000,
+	0x350c, 0x00810000, 0x408af000,
+	0x7030, 0x31000111, 0x00000011,
+	0x2f48, 0x73773777, 0x12010001,
+	0x2120, 0x0000007f, 0x0000001b,
+	0x21dc, 0x00007fb6, 0x00002191,
+	0x3628, 0x0000003f, 0x0000000a,
+	0x362c, 0x0000003f, 0x0000000a,
+	0x2ae4, 0x00073ffe, 0x000022a2,
+	0x240c, 0x000007ff, 0x00000000,
+	0x8bf0, 0x00002001, 0x00000001,
+	0x8b24, 0xffffffff, 0x00ffffff,
+	0x30a04, 0x0000ff0f, 0x00000000,
+	0x28a4c, 0x07ffffff, 0x06000000,
+	0x3e78, 0x00000001, 0x00000002,
+	0xc768, 0x00000008, 0x00000008,
+	0xc770, 0x00000f00, 0x00000800,
+	0xc774, 0x00000f00, 0x00000800,
+	0xc798, 0x00ffffff, 0x00ff7fbf,
+	0xc79c, 0x00ffffff, 0x00ff7faf,
+	0x8c00, 0x000000ff, 0x00000800,
+	0xe40, 0x00001fff, 0x00001fff,
+	0x9060, 0x0000007f, 0x00000020,
+	0x9508, 0x00010000, 0x00010000,
+	0xae00, 0x00100000, 0x000ff07c,
+	0xac14, 0x000003ff, 0x0000000f,
+	0xac10, 0xffffffff, 0x7564fdec,
+	0xac0c, 0xffffffff, 0x3120b9a8,
+	0xac08, 0x20000000, 0x0f9c0000
+};
+
+static const u32 hawaii_mgcg_cgcg_init[] =
+{
+	0xc420, 0xffffffff, 0xfffffffd,
+	0x30800, 0xffffffff, 0xe0000000,
+	0x3c2a0, 0xffffffff, 0x00000100,
+	0x3c208, 0xffffffff, 0x00000100,
+	0x3c2c0, 0xffffffff, 0x00000100,
+	0x3c2c8, 0xffffffff, 0x00000100,
+	0x3c2c4, 0xffffffff, 0x00000100,
+	0x55e4, 0xffffffff, 0x00200100,
+	0x3c280, 0xffffffff, 0x00000100,
+	0x3c214, 0xffffffff, 0x06000100,
+	0x3c220, 0xffffffff, 0x00000100,
+	0x3c218, 0xffffffff, 0x06000100,
+	0x3c204, 0xffffffff, 0x00000100,
+	0x3c2e0, 0xffffffff, 0x00000100,
+	0x3c224, 0xffffffff, 0x00000100,
+	0x3c200, 0xffffffff, 0x00000100,
+	0x3c230, 0xffffffff, 0x00000100,
+	0x3c234, 0xffffffff, 0x00000100,
+	0x3c250, 0xffffffff, 0x00000100,
+	0x3c254, 0xffffffff, 0x00000100,
+	0x3c258, 0xffffffff, 0x00000100,
+	0x3c25c, 0xffffffff, 0x00000100,
+	0x3c260, 0xffffffff, 0x00000100,
+	0x3c27c, 0xffffffff, 0x00000100,
+	0x3c278, 0xffffffff, 0x00000100,
+	0x3c210, 0xffffffff, 0x06000100,
+	0x3c290, 0xffffffff, 0x00000100,
+	0x3c274, 0xffffffff, 0x00000100,
+	0x3c2b4, 0xffffffff, 0x00000100,
+	0x3c2b0, 0xffffffff, 0x00000100,
+	0x3c270, 0xffffffff, 0x00000100,
+	0x30800, 0xffffffff, 0xe0000000,
+	0x3c020, 0xffffffff, 0x00010000,
+	0x3c024, 0xffffffff, 0x00030002,
+	0x3c028, 0xffffffff, 0x00040007,
+	0x3c02c, 0xffffffff, 0x00060005,
+	0x3c030, 0xffffffff, 0x00090008,
+	0x3c034, 0xffffffff, 0x00010000,
+	0x3c038, 0xffffffff, 0x00030002,
+	0x3c03c, 0xffffffff, 0x00040007,
+	0x3c040, 0xffffffff, 0x00060005,
+	0x3c044, 0xffffffff, 0x00090008,
+	0x3c048, 0xffffffff, 0x00010000,
+	0x3c04c, 0xffffffff, 0x00030002,
+	0x3c050, 0xffffffff, 0x00040007,
+	0x3c054, 0xffffffff, 0x00060005,
+	0x3c058, 0xffffffff, 0x00090008,
+	0x3c05c, 0xffffffff, 0x00010000,
+	0x3c060, 0xffffffff, 0x00030002,
+	0x3c064, 0xffffffff, 0x00040007,
+	0x3c068, 0xffffffff, 0x00060005,
+	0x3c06c, 0xffffffff, 0x00090008,
+	0x3c070, 0xffffffff, 0x00010000,
+	0x3c074, 0xffffffff, 0x00030002,
+	0x3c078, 0xffffffff, 0x00040007,
+	0x3c07c, 0xffffffff, 0x00060005,
+	0x3c080, 0xffffffff, 0x00090008,
+	0x3c084, 0xffffffff, 0x00010000,
+	0x3c088, 0xffffffff, 0x00030002,
+	0x3c08c, 0xffffffff, 0x00040007,
+	0x3c090, 0xffffffff, 0x00060005,
+	0x3c094, 0xffffffff, 0x00090008,
+	0x3c098, 0xffffffff, 0x00010000,
+	0x3c09c, 0xffffffff, 0x00030002,
+	0x3c0a0, 0xffffffff, 0x00040007,
+	0x3c0a4, 0xffffffff, 0x00060005,
+	0x3c0a8, 0xffffffff, 0x00090008,
+	0x3c0ac, 0xffffffff, 0x00010000,
+	0x3c0b0, 0xffffffff, 0x00030002,
+	0x3c0b4, 0xffffffff, 0x00040007,
+	0x3c0b8, 0xffffffff, 0x00060005,
+	0x3c0bc, 0xffffffff, 0x00090008,
+	0x3c0c0, 0xffffffff, 0x00010000,
+	0x3c0c4, 0xffffffff, 0x00030002,
+	0x3c0c8, 0xffffffff, 0x00040007,
+	0x3c0cc, 0xffffffff, 0x00060005,
+	0x3c0d0, 0xffffffff, 0x00090008,
+	0x3c0d4, 0xffffffff, 0x00010000,
+	0x3c0d8, 0xffffffff, 0x00030002,
+	0x3c0dc, 0xffffffff, 0x00040007,
+	0x3c0e0, 0xffffffff, 0x00060005,
+	0x3c0e4, 0xffffffff, 0x00090008,
+	0x3c0e8, 0xffffffff, 0x00010000,
+	0x3c0ec, 0xffffffff, 0x00030002,
+	0x3c0f0, 0xffffffff, 0x00040007,
+	0x3c0f4, 0xffffffff, 0x00060005,
+	0x3c0f8, 0xffffffff, 0x00090008,
+	0xc318, 0xffffffff, 0x00020200,
+	0x3350, 0xffffffff, 0x00000200,
+	0x15c0, 0xffffffff, 0x00000400,
+	0x55e8, 0xffffffff, 0x00000000,
+	0x2f50, 0xffffffff, 0x00000902,
+	0x3c000, 0xffffffff, 0x96940200,
+	0x8708, 0xffffffff, 0x00900100,
+	0xc424, 0xffffffff, 0x0020003f,
+	0x38, 0xffffffff, 0x0140001c,
+	0x3c, 0x000f0000, 0x000f0000,
+	0x220, 0xffffffff, 0xc060000c,
+	0x224, 0xc0000fff, 0x00000100,
+	0xf90, 0xffffffff, 0x00000100,
+	0xf98, 0x00000101, 0x00000000,
+	0x20a8, 0xffffffff, 0x00000104,
+	0x55e4, 0xff000fff, 0x00000100,
+	0x30cc, 0xc0000fff, 0x00000104,
+	0xc1e4, 0x00000001, 0x00000001,
+	0xd00c, 0xff000ff0, 0x00000100,
+	0xd80c, 0xff000ff0, 0x00000100
+};
+
 static void cik_init_golden_registers(struct radeon_device *rdev)
 {
 	switch (rdev->family) {
@@ -1347,6 +1515,20 @@ static void cik_init_golden_registers(struct radeon_device *rdev)
 						 spectre_golden_spm_registers,
 						 (const u32)ARRAY_SIZE(spectre_golden_spm_registers));
 		break;
+	case CHIP_HAWAII:
+		radeon_program_register_sequence(rdev,
+						 hawaii_mgcg_cgcg_init,
+						 (const u32)ARRAY_SIZE(hawaii_mgcg_cgcg_init));
+		radeon_program_register_sequence(rdev,
+						 hawaii_golden_registers,
+						 (const u32)ARRAY_SIZE(hawaii_golden_registers));
+		radeon_program_register_sequence(rdev,
+						 hawaii_golden_common_registers,
+						 (const u32)ARRAY_SIZE(hawaii_golden_common_registers));
+		radeon_program_register_sequence(rdev,
+						 hawaii_golden_spm_registers,
+						 (const u32)ARRAY_SIZE(hawaii_golden_spm_registers));
+		break;
 	default:
 		break;
 	}
@@ -1378,17 +1560,17 @@ u32 cik_get_xclk(struct radeon_device *rdev)
  * cik_mm_rdoorbell - read a doorbell dword
  *
  * @rdev: radeon_device pointer
- * @offset: byte offset into the aperture
+ * @index: doorbell index
  *
  * Returns the value in the doorbell aperture at the
- * requested offset (CIK).
+ * requested doorbell index (CIK).
  */
-u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 offset)
+u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 index)
 {
-	if (offset < rdev->doorbell.size) {
-		return readl(((void __iomem *)rdev->doorbell.ptr) + offset);
+	if (index < rdev->doorbell.num_doorbells) {
+		return readl(rdev->doorbell.ptr + index);
 	} else {
-		DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", offset);
+		DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", index);
 		return 0;
 	}
 }
@@ -1397,18 +1579,18 @@ u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 offset)
  * cik_mm_wdoorbell - write a doorbell dword
  *
  * @rdev: radeon_device pointer
- * @offset: byte offset into the aperture
+ * @index: doorbell index
  * @v: value to write
  *
  * Writes @v to the doorbell aperture at the
- * requested offset (CIK).
+ * requested doorbell index (CIK).
  */
-void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v)
+void cik_mm_wdoorbell(struct radeon_device *rdev, u32 index, u32 v)
 {
-	if (offset < rdev->doorbell.size) {
-		writel(v, ((void __iomem *)rdev->doorbell.ptr) + offset);
+	if (index < rdev->doorbell.num_doorbells) {
+		writel(v, rdev->doorbell.ptr + index);
 	} else {
-		DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", offset);
+		DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", index);
 	}
 }
 
@@ -1454,6 +1636,35 @@ static const u32 bonaire_io_mc_regs[BONAIRE_IO_MC_REGS_SIZE][2] =
 	{0x0000009f, 0x00b48000}
 };
 
+#define HAWAII_IO_MC_REGS_SIZE 22
+
+static const u32 hawaii_io_mc_regs[HAWAII_IO_MC_REGS_SIZE][2] =
+{
+	{0x0000007d, 0x40000000},
+	{0x0000007e, 0x40180304},
+	{0x0000007f, 0x0000ff00},
+	{0x00000081, 0x00000000},
+	{0x00000083, 0x00000800},
+	{0x00000086, 0x00000000},
+	{0x00000087, 0x00000100},
+	{0x00000088, 0x00020100},
+	{0x00000089, 0x00000000},
+	{0x0000008b, 0x00040000},
+	{0x0000008c, 0x00000100},
+	{0x0000008e, 0xff010000},
+	{0x00000090, 0xffffefff},
+	{0x00000091, 0xfff3efff},
+	{0x00000092, 0xfff3efbf},
+	{0x00000093, 0xf7ffffff},
+	{0x00000094, 0xffffff7f},
+	{0x00000095, 0x00000fff},
+	{0x00000096, 0x00116fff},
+	{0x00000097, 0x60010000},
+	{0x00000098, 0x10010000},
+	{0x0000009f, 0x00c79000}
+};
+
+
 /**
  * cik_srbm_select - select specific register instances
  *
@@ -1498,11 +1709,17 @@ static int ci_mc_load_microcode(struct radeon_device *rdev)
 
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
-	default:
 		io_mc_regs = (u32 *)&bonaire_io_mc_regs;
 		ucode_size = CIK_MC_UCODE_SIZE;
 		regs_size = BONAIRE_IO_MC_REGS_SIZE;
 		break;
+	case CHIP_HAWAII:
+		io_mc_regs = (u32 *)&hawaii_io_mc_regs;
+		ucode_size = HAWAII_MC_UCODE_SIZE;
+		regs_size = HAWAII_IO_MC_REGS_SIZE;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	running = RREG32(MC_SEQ_SUP_CNTL) & RUN_MASK;
@@ -1564,8 +1781,8 @@ static int cik_init_microcode(struct radeon_device *rdev)
 {
 	const char *chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size,
-		mec_req_size, rlc_req_size, mc_req_size,
-		sdma_req_size, smc_req_size;
+		mec_req_size, rlc_req_size, mc_req_size = 0,
+		sdma_req_size, smc_req_size = 0;
 	char fw_name[30];
 	int err;
 
@@ -1583,6 +1800,17 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(BONAIRE_SMC_UCODE_SIZE, 4);
 		break;
+	case CHIP_HAWAII:
+		chip_name = "HAWAII";
+		pfp_req_size = CIK_PFP_UCODE_SIZE * 4;
+		me_req_size = CIK_ME_UCODE_SIZE * 4;
+		ce_req_size = CIK_CE_UCODE_SIZE * 4;
+		mec_req_size = CIK_MEC_UCODE_SIZE * 4;
+		rlc_req_size = BONAIRE_RLC_UCODE_SIZE * 4;
+		mc_req_size = HAWAII_MC_UCODE_SIZE * 4;
+		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
+		smc_req_size = ALIGN(HAWAII_SMC_UCODE_SIZE, 4);
+		break;
 	case CHIP_KAVERI:
 		chip_name = "KAVERI";
 		pfp_req_size = CIK_PFP_UCODE_SIZE * 4;
@@ -1763,9 +1991,227 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 
 	num_pipe_configs = rdev->config.cik.max_tile_pipes;
 	if (num_pipe_configs > 8)
-		num_pipe_configs = 8; /* ??? */
+		num_pipe_configs = 16;
 
-	if (num_pipe_configs == 8) {
+	if (num_pipe_configs == 16) {
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B));
+				break;
+			case 1:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B));
+				break;
+			case 2:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B));
+				break;
+			case 3:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B));
+				break;
+			case 4:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 5:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 6:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B));
+				break;
+			case 7:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 8:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16));
+				break;
+			case 9:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING));
+				break;
+			case 10:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 11:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_8x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 12:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 13:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING));
+				break;
+			case 14:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 16:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_8x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 17:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 27:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING));
+				break;
+			case 28:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 29:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_8x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 30:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_2D_TILED_THIN1) |
+						 MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						 PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						 SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			rdev->config.cik.tile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(GB_TILE_MODE0 + (reg_offset * 4), gb_tile_moden);
+		}
+		for (reg_offset = 0; reg_offset < num_secondary_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 1:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 2:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 3:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 4:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 5:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 6:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 8:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 9:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 10:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 11:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 12:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 13:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 14:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
+		}
+	} else if (num_pipe_configs == 8) {
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
 			case 0:
@@ -1981,6 +2427,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if (num_pipe_configs == 4) {
@@ -2327,6 +2774,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if (num_pipe_configs == 2) {
@@ -2544,6 +2992,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else
@@ -2608,7 +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;
@@ -2622,7 +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;
 }
@@ -2639,7 +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;
@@ -2649,24 +3098,35 @@ 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);
-			disabled_rbs |= data << ((i * sh_per_se + j) * CIK_RB_BITMAP_WIDTH_PER_SH);
+			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
+				disabled_rbs |= data << ((i * sh_per_se + j) * CIK_RB_BITMAP_WIDTH_PER_SH);
 		}
 	}
 	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;
 		for (j = 0; j < sh_per_se; j++) {
 			switch (enabled_rbs & 3) {
+			case 0:
+				if (j == 0)
+					data |= PKR_MAP(RASTER_CONFIG_RB_MAP_3);
+				else
+					data |= PKR_MAP(RASTER_CONFIG_RB_MAP_0);
+				break;
 			case 1:
 				data |= (RASTER_CONFIG_RB_MAP_0 << (i * sh_per_se + j) * 2);
 				break;
@@ -2719,6 +3179,23 @@ static void cik_gpu_init(struct radeon_device *rdev)
 		rdev->config.cik.sc_earlyz_tile_fifo_size = 0x130;
 		gb_addr_config = BONAIRE_GB_ADDR_CONFIG_GOLDEN;
 		break;
+	case CHIP_HAWAII:
+		rdev->config.cik.max_shader_engines = 4;
+		rdev->config.cik.max_tile_pipes = 16;
+		rdev->config.cik.max_cu_per_sh = 11;
+		rdev->config.cik.max_sh_per_se = 1;
+		rdev->config.cik.max_backends_per_se = 4;
+		rdev->config.cik.max_texture_channel_caches = 16;
+		rdev->config.cik.max_gprs = 256;
+		rdev->config.cik.max_gs_threads = 32;
+		rdev->config.cik.max_hw_contexts = 8;
+
+		rdev->config.cik.sc_prim_fifo_size_frontend = 0x20;
+		rdev->config.cik.sc_prim_fifo_size_backend = 0x100;
+		rdev->config.cik.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.cik.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = HAWAII_GB_ADDR_CONFIG_GOLDEN;
+		break;
 	case CHIP_KAVERI:
 		rdev->config.cik.max_shader_engines = 1;
 		rdev->config.cik.max_tile_pipes = 4;
@@ -3084,17 +3561,98 @@ void cik_fence_compute_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, 0);
 }
 
-void cik_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait)
 {
+/* TODO: figure out why semaphore cause lockups */
+#if 0
 	uint64_t addr = semaphore->gpu_addr;
 	unsigned sel = emit_wait ? PACKET3_SEM_SEL_WAIT : PACKET3_SEM_SEL_SIGNAL;
 
 	radeon_ring_write(ring, PACKET3(PACKET3_MEM_SEMAPHORE, 1));
 	radeon_ring_write(ring, addr & 0xffffffff);
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | sel);
+
+	return true;
+#else
+	return false;
+#endif
+}
+
+/**
+ * cik_copy_cpdma - copy pages using the CP DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the CP DMA engine (CIK+).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int cik_copy_cpdma(struct radeon_device *rdev,
+		   uint64_t src_offset, uint64_t dst_offset,
+		   unsigned num_gpu_pages,
+		   struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.blit_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_bytes, cur_size_in_bytes, control;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
+	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);
+	r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_bytes = size_in_bytes;
+		if (cur_size_in_bytes > 0x1fffff)
+			cur_size_in_bytes = 0x1fffff;
+		size_in_bytes -= cur_size_in_bytes;
+		control = 0;
+		if (size_in_bytes == 0)
+			control |= PACKET3_DMA_DATA_CP_SYNC;
+		radeon_ring_write(ring, PACKET3(PACKET3_DMA_DATA, 5));
+		radeon_ring_write(ring, control);
+		radeon_ring_write(ring, lower_32_bits(src_offset));
+		radeon_ring_write(ring, upper_32_bits(src_offset));
+		radeon_ring_write(ring, lower_32_bits(dst_offset));
+		radeon_ring_write(ring, upper_32_bits(dst_offset));
+		radeon_ring_write(ring, cur_size_in_bytes);
+		src_offset += cur_size_in_bytes;
+		dst_offset += cur_size_in_bytes;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
 }
 
 /*
@@ -3403,7 +3961,8 @@ static int cik_cp_gfx_resume(struct radeon_device *rdev)
 	int r;
 
 	WREG32(CP_SEM_WAIT_TIMER, 0x0);
-	WREG32(CP_SEM_INCOMPLETE_TIMER_CNTL, 0x0);
+	if (rdev->family != CHIP_HAWAII)
+		WREG32(CP_SEM_INCOMPLETE_TIMER_CNTL, 0x0);
 
 	/* Set the write pointer delay */
 	WREG32(CP_RB_WPTR_DELAY, 0);
@@ -3500,7 +4059,7 @@ void cik_compute_ring_set_wptr(struct radeon_device *rdev,
 			       struct radeon_ring *ring)
 {
 	rdev->wb.wb[ring->wptr_offs/4] = cpu_to_le32(ring->wptr);
-	WDOORBELL32(ring->doorbell_offset, ring->wptr);
+	WDOORBELL32(ring->doorbell_index, ring->wptr);
 }
 
 /**
@@ -3841,10 +4400,6 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 			return r;
 		}
 
-		/* doorbell offset */
-		rdev->ring[idx].doorbell_offset =
-			(rdev->ring[idx].doorbell_page_num * PAGE_SIZE) + 0;
-
 		/* init the mqd struct */
 		memset(buf, 0, sizeof(struct bonaire_mqd));
 
@@ -3956,7 +4511,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 				RREG32(CP_HQD_PQ_DOORBELL_CONTROL);
 			mqd->queue_state.cp_hqd_pq_doorbell_control &= ~DOORBELL_OFFSET_MASK;
 			mqd->queue_state.cp_hqd_pq_doorbell_control |=
-				DOORBELL_OFFSET(rdev->ring[idx].doorbell_offset / 4);
+				DOORBELL_OFFSET(rdev->ring[idx].doorbell_index);
 			mqd->queue_state.cp_hqd_pq_doorbell_control |= DOORBELL_EN;
 			mqd->queue_state.cp_hqd_pq_doorbell_control &=
 				~(DOORBELL_SOURCE | DOORBELL_HIT);
@@ -4740,12 +5295,17 @@ void cik_vm_fini(struct radeon_device *rdev)
 static void cik_vm_decode_fault(struct radeon_device *rdev,
 				u32 status, u32 addr, u32 mc_client)
 {
-	u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
+	u32 mc_id;
 	u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
 	u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
 	char block[5] = { mc_client >> 24, (mc_client >> 16) & 0xff,
 		(mc_client >> 8) & 0xff, mc_client & 0xff, 0 };
 
+	if (rdev->family == CHIP_HAWAII)
+		mc_id = (status & HAWAII_MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
+	else
+		mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
+
 	printk("VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
 	       protections, vmid, addr,
 	       (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
@@ -4834,62 +5394,6 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	}
 }
 
-/**
- * cik_vm_set_page - update the page tables using sDMA
- *
- * @rdev: radeon_device pointer
- * @ib: indirect buffer to fill with commands
- * @pe: addr of the page entry
- * @addr: dst addr to write into pe
- * @count: number of page entries to update
- * @incr: increase next addr by incr bytes
- * @flags: access flags
- *
- * Update the page tables using CP or sDMA (CIK).
- */
-void cik_vm_set_page(struct radeon_device *rdev,
-		     struct radeon_ib *ib,
-		     uint64_t pe,
-		     uint64_t addr, unsigned count,
-		     uint32_t incr, uint32_t flags)
-{
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	uint64_t value;
-	unsigned ndw;
-
-	if (rdev->asic->vm.pt_ring_index == RADEON_RING_TYPE_GFX_INDEX) {
-		/* CP */
-		while (count) {
-			ndw = 2 + count * 2;
-			if (ndw > 0x3FFE)
-				ndw = 0x3FFE;
-
-			ib->ptr[ib->length_dw++] = PACKET3(PACKET3_WRITE_DATA, ndw);
-			ib->ptr[ib->length_dw++] = (WRITE_DATA_ENGINE_SEL(0) |
-						    WRITE_DATA_DST_SEL(1));
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-			for (; ndw > 2; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= r600_flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		/* DMA */
-		cik_sdma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
-	}
-}
-
 /*
  * RLC
  * The RLC is a multi-purpose microengine that handles a
@@ -5058,6 +5562,7 @@ static int cik_rlc_resume(struct radeon_device *rdev)
 
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
 	default:
 		size = BONAIRE_RLC_UCODE_SIZE;
 		break;
@@ -5556,7 +6061,7 @@ void cik_init_cp_pg_table(struct radeon_device *rdev)
 		}
 
 		for (i = 0; i < CP_ME_TABLE_SIZE; i ++) {
-			dst_ptr[bo_offset + i] = be32_to_cpu(fw_data[table_offset + i]);
+			dst_ptr[bo_offset + i] = cpu_to_le32(be32_to_cpu(fw_data[table_offset + i]));
 		}
 		bo_offset += CP_ME_TABLE_SIZE;
 	}
@@ -5778,52 +6283,57 @@ void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
 	if (buffer == NULL)
 		return;
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_BEGIN_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_BEGIN_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CONTEXT_CONTROL, 1);
-	buffer[count++] = 0x80000000;
-	buffer[count++] = 0x80000000;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CONTEXT_CONTROL, 1));
+	buffer[count++] = cpu_to_le32(0x80000000);
+	buffer[count++] = cpu_to_le32(0x80000000);
 
 	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
 		for (ext = sect->section; ext->extent != NULL; ++ext) {
 			if (sect->id == SECT_CONTEXT) {
-				buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count);
-				buffer[count++] = ext->reg_index - 0xa000;
+				buffer[count++] =
+					cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count));
+				buffer[count++] = cpu_to_le32(ext->reg_index - 0xa000);
 				for (i = 0; i < ext->reg_count; i++)
-					buffer[count++] = ext->extent[i];
+					buffer[count++] = cpu_to_le32(ext->extent[i]);
 			} else {
 				return;
 			}
 		}
 	}
 
-	buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, 2);
-	buffer[count++] = PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, 2));
+	buffer[count++] = cpu_to_le32(PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
-		buffer[count++] = 0x16000012;
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x16000012);
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	case CHIP_KAVERI:
-		buffer[count++] = 0x00000000; /* XXX */
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000); /* XXX */
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	case CHIP_KABINI:
-		buffer[count++] = 0x00000000; /* XXX */
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000); /* XXX */
+		buffer[count++] = cpu_to_le32(0x00000000);
+		break;
+	case CHIP_HAWAII:
+		buffer[count++] = 0x3a00161a;
+		buffer[count++] = 0x0000002e;
 		break;
 	default:
-		buffer[count++] = 0x00000000;
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000);
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	}
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_END_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CLEAR_STATE, 0);
-	buffer[count++] = 0;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CLEAR_STATE, 0));
+	buffer[count++] = cpu_to_le32(0);
 }
 
 static void cik_init_pg(struct radeon_device *rdev)
@@ -7118,7 +7628,7 @@ static int cik_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     CP_RB0_RPTR, CP_RB0_WPTR,
-			     RADEON_CP_PACKET2);
+			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
 
@@ -7332,14 +7842,14 @@ int cik_init(struct radeon_device *rdev)
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
 	ring->ring_obj = NULL;
 	r600_ring_init(rdev, ring, 1024 * 1024);
-	r = radeon_doorbell_get(rdev, &ring->doorbell_page_num);
+	r = radeon_doorbell_get(rdev, &ring->doorbell_index);
 	if (r)
 		return r;
 
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
 	ring->ring_obj = NULL;
 	r600_ring_init(rdev, ring, 1024 * 1024);
-	r = radeon_doorbell_get(rdev, &ring->doorbell_page_num);
+	r = radeon_doorbell_get(rdev, &ring->doorbell_index);
 	if (r)
 		return r;
 
@@ -7428,6 +7938,70 @@ void cik_fini(struct radeon_device *rdev)
 	rdev->bios = NULL;
 }
 
+void dce8_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS/eDP FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	/* not needed for analog */
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2))
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH(0));
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH(0));
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_RGB_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH(1));
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH(1));
+		break;
+	case 10:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_RGB_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH(2));
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH(2));
+		break;
+	default:
+		/* not needed */
+		break;
+	}
+
+	WREG32(FMT_BIT_DEPTH_CONTROL + radeon_crtc->crtc_offset, tmp);
+}
+
 /* display watermark setup */
 /**
  * dce8_line_buffer_adjust - Set up the line buffer
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index b6286068e11..d08b83c6267 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -25,6 +25,7 @@
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
+#include "radeon_trace.h"
 #include "cikd.h"
 
 /* sdma */
@@ -101,14 +102,6 @@ void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
-	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(1) |
-			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
-	u32 ref_and_mask;
-
-	if (fence->ring == R600_RING_TYPE_DMA_INDEX)
-		ref_and_mask = SDMA0;
-	else
-		ref_and_mask = SDMA1;
 
 	/* write the fence */
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_FENCE, 0, 0));
@@ -118,12 +111,12 @@ void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
 	/* generate an interrupt */
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_TRAP, 0, 0));
 	/* flush HDP */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
-	radeon_ring_write(ring, GPU_HDP_FLUSH_DONE);
-	radeon_ring_write(ring, GPU_HDP_FLUSH_REQ);
-	radeon_ring_write(ring, ref_and_mask); /* REFERENCE */
-	radeon_ring_write(ring, ref_and_mask); /* MASK */
-	radeon_ring_write(ring, (4 << 16) | 10); /* RETRY_COUNT, POLL_INTERVAL */
+	/* We should be using the new POLL_REG_MEM special op packet here
+	 * but it causes sDMA to hang sometimes
+	 */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
+	radeon_ring_write(ring, 0);
 }
 
 /**
@@ -137,7 +130,7 @@ void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
  * Add a DMA semaphore packet to the ring wait on or signal
  * other rings (CIK).
  */
-void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
 				  struct radeon_ring *ring,
 				  struct radeon_semaphore *semaphore,
 				  bool emit_wait)
@@ -148,6 +141,8 @@ void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SEMAPHORE, 0, extra_bits));
 	radeon_ring_write(ring, addr & 0xfffffff8);
 	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+
+	return true;
 }
 
 /**
@@ -450,13 +445,8 @@ int cik_copy_dma(struct radeon_device *rdev,
 		return r;
 	}
 
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
 		cur_size_in_bytes = size_in_bytes;
@@ -468,7 +458,7 @@ int cik_copy_dma(struct radeon_device *rdev,
 		radeon_ring_write(ring, 0); /* src/dst endian swap */
 		radeon_ring_write(ring, src_offset & 0xffffffff);
 		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff);
-		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, dst_offset & 0xffffffff);
 		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff);
 		src_offset += cur_size_in_bytes;
 		dst_offset += cur_size_in_bytes;
@@ -653,11 +643,12 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			  uint64_t addr, unsigned count,
 			  uint32_t incr, uint32_t flags)
 {
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
 
-	if (flags & RADEON_VM_PAGE_SYSTEM) {
+	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
+
+	if (flags & R600_PTE_SYSTEM) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -669,16 +660,10 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
 			ib->ptr[ib->length_dw++] = ndw;
 			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
 				addr += incr;
-				value |= r600_flags;
+				value |= flags;
 				ib->ptr[ib->length_dw++] = value;
 				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
@@ -689,7 +674,7 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			if (ndw > 0x7FFFF)
 				ndw = 0x7FFFF;
 
-			if (flags & RADEON_VM_PAGE_VALID)
+			if (flags & R600_PTE_VALID)
 				value = addr;
 			else
 				value = 0;
@@ -697,7 +682,7 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_GENERATE_PTE_PDE, 0, 0);
 			ib->ptr[ib->length_dw++] = pe; /* dst addr */
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = flags; /* mask */
 			ib->ptr[ib->length_dw++] = 0;
 			ib->ptr[ib->length_dw++] = value; /* value */
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
@@ -724,18 +709,10 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
 	struct radeon_ring *ring = &rdev->ring[ridx];
-	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(1) |
-			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
-	u32 ref_and_mask;
 
 	if (vm == NULL)
 		return;
 
-	if (ridx == R600_RING_TYPE_DMA_INDEX)
-		ref_and_mask = SDMA0;
-	else
-		ref_and_mask = SDMA1;
-
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
 	if (vm->id < 8) {
 		radeon_ring_write(ring, (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
@@ -770,12 +747,12 @@ void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm
 	radeon_ring_write(ring, VMID(0));
 
 	/* flush HDP */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
-	radeon_ring_write(ring, GPU_HDP_FLUSH_DONE);
-	radeon_ring_write(ring, GPU_HDP_FLUSH_REQ);
-	radeon_ring_write(ring, ref_and_mask); /* REFERENCE */
-	radeon_ring_write(ring, ref_and_mask); /* MASK */
-	radeon_ring_write(ring, (4 << 16) | 10); /* RETRY_COUNT, POLL_INTERVAL */
+	/* We should be using the new POLL_REG_MEM special op packet here
+	 * but it causes sDMA to hang sometimes
+	 */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
+	radeon_ring_write(ring, 0);
 
 	/* flush TLB */
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 203d2a09a1f..5964af5e5b2 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -25,8 +25,10 @@
 #define CIK_H
 
 #define BONAIRE_GB_ADDR_CONFIG_GOLDEN        0x12010001
+#define HAWAII_GB_ADDR_CONFIG_GOLDEN         0x12011003
 
-#define CIK_RB_BITMAP_WIDTH_PER_SH  2
+#define CIK_RB_BITMAP_WIDTH_PER_SH     2
+#define HAWAII_RB_BITMAP_WIDTH_PER_SH  4
 
 /* DIDT IND registers */
 #define DIDT_SQ_CTRL0                                     0x0
@@ -499,6 +501,7 @@
 		 * bit 4: write
 		 */
 #define		MEMORY_CLIENT_ID_MASK			(0xff << 12)
+#define		HAWAII_MEMORY_CLIENT_ID_MASK		(0x1ff << 12)
 #define		MEMORY_CLIENT_ID_SHIFT			12
 #define		MEMORY_CLIENT_RW_MASK			(1 << 24)
 #define		MEMORY_CLIENT_RW_SHIFT			24
@@ -906,6 +909,39 @@
 #define DPG_PIPE_STUTTER_CONTROL                          0x6cd4
 #       define STUTTER_ENABLE                             (1 << 0)
 
+/* DCE8 FMT blocks */
+#define FMT_DYNAMIC_EXP_CNTL                 0x6fb4
+#       define FMT_DYNAMIC_EXP_EN            (1 << 0)
+#       define FMT_DYNAMIC_EXP_MODE          (1 << 4)
+        /* 0 = 10bit -> 12bit, 1 = 8bit -> 12bit */
+#define FMT_CONTROL                          0x6fb8
+#       define FMT_PIXEL_ENCODING            (1 << 16)
+        /* 0 = RGB 4:4:4 or YCbCr 4:4:4, 1 = YCbCr 4:2:2 */
+#define FMT_BIT_DEPTH_CONTROL                0x6fc8
+#       define FMT_TRUNCATE_EN               (1 << 0)
+#       define FMT_TRUNCATE_MODE             (1 << 1)
+#       define FMT_TRUNCATE_DEPTH(x)         ((x) << 4) /* 0 - 18bpp, 1 - 24bpp, 2 - 30bpp */
+#       define FMT_SPATIAL_DITHER_EN         (1 << 8)
+#       define FMT_SPATIAL_DITHER_MODE(x)    ((x) << 9)
+#       define FMT_SPATIAL_DITHER_DEPTH(x)   ((x) << 11) /* 0 - 18bpp, 1 - 24bpp, 2 - 30bpp */
+#       define FMT_FRAME_RANDOM_ENABLE       (1 << 13)
+#       define FMT_RGB_RANDOM_ENABLE         (1 << 14)
+#       define FMT_HIGHPASS_RANDOM_ENABLE    (1 << 15)
+#       define FMT_TEMPORAL_DITHER_EN        (1 << 16)
+#       define FMT_TEMPORAL_DITHER_DEPTH(x)  ((x) << 17) /* 0 - 18bpp, 1 - 24bpp, 2 - 30bpp */
+#       define FMT_TEMPORAL_DITHER_OFFSET(x) ((x) << 21)
+#       define FMT_TEMPORAL_LEVEL            (1 << 24)
+#       define FMT_TEMPORAL_DITHER_RESET     (1 << 25)
+#       define FMT_25FRC_SEL(x)              ((x) << 26)
+#       define FMT_50FRC_SEL(x)              ((x) << 28)
+#       define FMT_75FRC_SEL(x)              ((x) << 30)
+#define FMT_CLAMP_CONTROL                    0x6fe4
+#       define FMT_CLAMP_DATA_EN             (1 << 0)
+#       define FMT_CLAMP_COLOR_FORMAT(x)     ((x) << 16)
+#       define FMT_CLAMP_6BPC                0
+#       define FMT_CLAMP_8BPC                1
+#       define FMT_CLAMP_10BPC               2
+
 #define	GRBM_CNTL					0x8000
 #define		GRBM_READ_TIMEOUT(x)				((x) << 0)
 
@@ -1129,6 +1165,8 @@
 #              define	ADDR_SURF_P8_32x32_16x16		12
 #              define	ADDR_SURF_P8_32x32_16x32		13
 #              define	ADDR_SURF_P8_32x64_32x32		14
+#              define	ADDR_SURF_P16_32x32_8x16		16
+#              define	ADDR_SURF_P16_32x32_16x16		17
 #       define TILE_SPLIT(x)					((x) << 11)
 #              define	ADDR_SURF_TILE_SPLIT_64B		0
 #              define	ADDR_SURF_TILE_SPLIT_128B		1
@@ -1422,6 +1460,7 @@
 #       define RASTER_CONFIG_RB_MAP_1                   1
 #       define RASTER_CONFIG_RB_MAP_2                   2
 #       define RASTER_CONFIG_RB_MAP_3                   3
+#define		PKR_MAP(x)				((x) << 8)
 
 #define VGT_EVENT_INITIATOR                             0x28a90
 #       define SAMPLE_STREAMOUTSTATS1                   (1 << 0)
@@ -1714,6 +1753,68 @@
 #              define PACKET3_PREAMBLE_BEGIN_CLEAR_STATE     (2 << 28)
 #              define PACKET3_PREAMBLE_END_CLEAR_STATE       (3 << 28)
 #define	PACKET3_DMA_DATA				0x50
+/* 1. header
+ * 2. CONTROL
+ * 3. SRC_ADDR_LO or DATA [31:0]
+ * 4. SRC_ADDR_HI [31:0]
+ * 5. DST_ADDR_LO [31:0]
+ * 6. DST_ADDR_HI [7:0]
+ * 7. COMMAND [30:21] | BYTE_COUNT [20:0]
+ */
+/* CONTROL */
+#              define PACKET3_DMA_DATA_ENGINE(x)     ((x) << 0)
+                /* 0 - ME
+		 * 1 - PFP
+		 */
+#              define PACKET3_DMA_DATA_SRC_CACHE_POLICY(x) ((x) << 13)
+                /* 0 - LRU
+		 * 1 - Stream
+		 * 2 - Bypass
+		 */
+#              define PACKET3_DMA_DATA_SRC_VOLATILE (1 << 15)
+#              define PACKET3_DMA_DATA_DST_SEL(x)  ((x) << 20)
+                /* 0 - DST_ADDR using DAS
+		 * 1 - GDS
+		 * 3 - DST_ADDR using L2
+		 */
+#              define PACKET3_DMA_DATA_DST_CACHE_POLICY(x) ((x) << 25)
+                /* 0 - LRU
+		 * 1 - Stream
+		 * 2 - Bypass
+		 */
+#              define PACKET3_DMA_DATA_DST_VOLATILE (1 << 27)
+#              define PACKET3_DMA_DATA_SRC_SEL(x)  ((x) << 29)
+                /* 0 - SRC_ADDR using SAS
+		 * 1 - GDS
+		 * 2 - DATA
+		 * 3 - SRC_ADDR using L2
+		 */
+#              define PACKET3_DMA_DATA_CP_SYNC     (1 << 31)
+/* COMMAND */
+#              define PACKET3_DMA_DATA_DIS_WC      (1 << 21)
+#              define PACKET3_DMA_DATA_CMD_SRC_SWAP(x) ((x) << 22)
+                /* 0 - none
+		 * 1 - 8 in 16
+		 * 2 - 8 in 32
+		 * 3 - 8 in 64
+		 */
+#              define PACKET3_DMA_DATA_CMD_DST_SWAP(x) ((x) << 24)
+                /* 0 - none
+		 * 1 - 8 in 16
+		 * 2 - 8 in 32
+		 * 3 - 8 in 64
+		 */
+#              define PACKET3_DMA_DATA_CMD_SAS     (1 << 26)
+                /* 0 - memory
+		 * 1 - register
+		 */
+#              define PACKET3_DMA_DATA_CMD_DAS     (1 << 27)
+                /* 0 - memory
+		 * 1 - register
+		 */
+#              define PACKET3_DMA_DATA_CMD_SAIC    (1 << 28)
+#              define PACKET3_DMA_DATA_CMD_DAIC    (1 << 29)
+#              define PACKET3_DMA_DATA_CMD_RAW_WAIT  (1 << 30)
 #define	PACKET3_AQUIRE_MEM				0x58
 #define	PACKET3_REWIND					0x59
 #define	PACKET3_LOAD_UCONFIG_REG			0x5E
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index 91bb470de0a..920e1e4a52c 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -299,7 +299,9 @@ void cypress_program_response_times(struct radeon_device *rdev)
 static int cypress_pcie_performance_request(struct radeon_device *rdev,
 					    u8 perf_req, bool advertise)
 {
+#if defined(CONFIG_ACPI)
 	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+#endif
 	u32 tmp;
 
 	udelay(10);
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 9fcd338c0fc..713a5d35990 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -93,15 +93,60 @@ void dce6_afmt_select_pin(struct drm_encoder *encoder)
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset = dig->afmt->offset;
+	u32 offset;
 
-	if (!dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
+	offset = dig->afmt->offset;
+
 	WREG32(AFMT_AUDIO_SRC_CONTROL + offset,
 	       AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id));
 }
 
+void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
+				    struct drm_display_mode *mode)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp = 0, offset;
+
+	if (!dig || !dig->afmt || !dig->afmt->pin)
+		return;
+
+	offset = dig->afmt->pin->offset;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		if (connector->latency_present[1])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
+				AUDIO_LIPSYNC(connector->audio_latency[1]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	} else {
+		if (connector->latency_present[0])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[0]) |
+				AUDIO_LIPSYNC(connector->audio_latency[0]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	}
+	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
+}
+
 void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
@@ -113,10 +158,7 @@ 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)
+	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
 	offset = dig->afmt->pin->offset;
@@ -132,7 +174,7 @@ void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
 		return;
 	}
@@ -177,7 +219,7 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder)
 		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
 	};
 
-	if (!dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
 	offset = dig->afmt->pin->offset;
@@ -193,7 +235,7 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 		return;
 	}
@@ -201,20 +243,30 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder)
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 value = 0;
+		u8 stereo_freqs = 0;
+		int max_channels = -1;
 		int j;
 
 		for (j = 0; j < sad_count; j++) {
 			struct cea_sad *sad = &sads[j];
 
 			if (sad->format == eld_reg_to_type[i][1]) {
-				value = MAX_CHANNELS(sad->channels) |
-					DESCRIPTOR_BYTE_2(sad->byte2) |
-					SUPPORTED_FREQUENCIES(sad->freq);
+				if (sad->channels > max_channels) {
+					value = MAX_CHANNELS(sad->channels) |
+						DESCRIPTOR_BYTE_2(sad->byte2) |
+						SUPPORTED_FREQUENCIES(sad->freq);
+					max_channels = sad->channels;
+				}
+
 				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
-					value |= SUPPORTED_FREQUENCIES_STEREO(sad->freq);
-				break;
+					stereo_freqs |= sad->freq;
+				else
+					break;
 			}
 		}
+
+		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
+
 		WREG32_ENDPOINT(offset, eld_reg_to_type[i][0], value);
 	}
 
@@ -256,7 +308,9 @@ int dce6_audio_init(struct radeon_device *rdev)
 	rdev->audio.enabled = true;
 
 	if (ASIC_IS_DCE8(rdev))
-		rdev->audio.num_pins = 7;
+		rdev->audio.num_pins = 6;
+	else if (ASIC_IS_DCE61(rdev))
+		rdev->audio.num_pins = 4;
 	else
 		rdev->audio.num_pins = 6;
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index b5c67a99dda..9702e55e924 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1174,23 +1174,72 @@ int evergreen_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 
 void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev)
 {
-	u16 ctl, v;
-	int err;
-
-	err = pcie_capability_read_word(rdev->pdev, PCI_EXP_DEVCTL, &ctl);
-	if (err)
-		return;
-
-	v = (ctl & PCI_EXP_DEVCTL_READRQ) >> 12;
+	int readrq;
+	u16 v;
 
+	readrq = pcie_get_readrq(rdev->pdev);
+	v = ffs(readrq) - 8;
 	/* if bios or OS sets MAX_READ_REQUEST_SIZE to an invalid value, fix it
 	 * to avoid hangs or perfomance issues
 	 */
-	if ((v == 0) || (v == 6) || (v == 7)) {
-		ctl &= ~PCI_EXP_DEVCTL_READRQ;
-		ctl |= (2 << 12);
-		pcie_capability_write_word(rdev->pdev, PCI_EXP_DEVCTL, ctl);
+	if ((v == 0) || (v == 6) || (v == 7))
+		pcie_set_readrq(rdev->pdev, 512);
+}
+
+void dce4_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
 	}
+
+	/* LVDS/eDP FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	/* not needed for analog */
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2))
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN);
+		else
+			tmp |= FMT_TRUNCATE_EN;
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_RGB_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH);
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH);
+		break;
+	case 10:
+	default:
+		/* not needed */
+		break;
+	}
+
+	WREG32(FMT_BIT_DEPTH_CONTROL + radeon_crtc->crtc_offset, tmp);
 }
 
 static bool dce4_is_in_vblank(struct radeon_device *rdev, int crtc)
@@ -3963,7 +4012,7 @@ int sumo_rlc_init(struct radeon_device *rdev)
 		if (rdev->family >= CHIP_TAHITI) {
 			/* SI */
 			for (i = 0; i < rdev->rlc.reg_list_size; i++)
-				dst_ptr[i] = src_ptr[i];
+				dst_ptr[i] = cpu_to_le32(src_ptr[i]);
 		} else {
 			/* ON/LN/TN */
 			/* format:
@@ -3977,10 +4026,10 @@ int sumo_rlc_init(struct radeon_device *rdev)
 				if (i < dws)
 					data |= (src_ptr[i] >> 2) << 16;
 				j = (((i - 1) * 3) / 2);
-				dst_ptr[j] = data;
+				dst_ptr[j] = cpu_to_le32(data);
 			}
 			j = ((i * 3) / 2);
-			dst_ptr[j] = RLC_SAVE_RESTORE_LIST_END_MARKER;
+			dst_ptr[j] = cpu_to_le32(RLC_SAVE_RESTORE_LIST_END_MARKER);
 		}
 		radeon_bo_kunmap(rdev->rlc.save_restore_obj);
 		radeon_bo_unreserve(rdev->rlc.save_restore_obj);
@@ -4042,40 +4091,40 @@ int sumo_rlc_init(struct radeon_device *rdev)
 			cik_get_csb_buffer(rdev, dst_ptr);
 		} else if (rdev->family >= CHIP_TAHITI) {
 			reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + 256;
-			dst_ptr[0] = upper_32_bits(reg_list_mc_addr);
-			dst_ptr[1] = lower_32_bits(reg_list_mc_addr);
-			dst_ptr[2] = rdev->rlc.clear_state_size;
+			dst_ptr[0] = cpu_to_le32(upper_32_bits(reg_list_mc_addr));
+			dst_ptr[1] = cpu_to_le32(lower_32_bits(reg_list_mc_addr));
+			dst_ptr[2] = cpu_to_le32(rdev->rlc.clear_state_size);
 			si_get_csb_buffer(rdev, &dst_ptr[(256/4)]);
 		} else {
 			reg_list_hdr_blk_index = 0;
 			reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + (reg_list_blk_index * 4);
 			data = upper_32_bits(reg_list_mc_addr);
-			dst_ptr[reg_list_hdr_blk_index] = data;
+			dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 			reg_list_hdr_blk_index++;
 			for (i = 0; cs_data[i].section != NULL; i++) {
 				for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
 					reg_num = cs_data[i].section[j].reg_count;
 					data = reg_list_mc_addr & 0xffffffff;
-					dst_ptr[reg_list_hdr_blk_index] = data;
+					dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 					reg_list_hdr_blk_index++;
 
 					data = (cs_data[i].section[j].reg_index * 4) & 0xffffffff;
-					dst_ptr[reg_list_hdr_blk_index] = data;
+					dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 					reg_list_hdr_blk_index++;
 
 					data = 0x08000000 | (reg_num * 4);
-					dst_ptr[reg_list_hdr_blk_index] = data;
+					dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 					reg_list_hdr_blk_index++;
 
 					for (k = 0; k < reg_num; k++) {
 						data = cs_data[i].section[j].extent[k];
-						dst_ptr[reg_list_blk_index + k] = data;
+						dst_ptr[reg_list_blk_index + k] = cpu_to_le32(data);
 					}
 					reg_list_mc_addr += reg_num * 4;
 					reg_list_blk_index += reg_num;
 				}
 			}
-			dst_ptr[reg_list_hdr_blk_index] = RLC_CLEAR_STATE_END_MARKER;
+			dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(RLC_CLEAR_STATE_END_MARKER);
 		}
 		radeon_bo_kunmap(rdev->rlc.clear_state_obj);
 		radeon_bo_unreserve(rdev->rlc.clear_state_obj);
diff --git a/drivers/gpu/drm/radeon/evergreen_dma.c b/drivers/gpu/drm/radeon/evergreen_dma.c
index 6a0656d00ed..a37b5443638 100644
--- a/drivers/gpu/drm/radeon/evergreen_dma.c
+++ b/drivers/gpu/drm/radeon/evergreen_dma.c
@@ -131,13 +131,8 @@ int evergreen_copy_dma(struct radeon_device *rdev,
 		return r;
 	}
 
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
 		cur_size_in_dw = size_in_dw;
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 57fcc4b16a5..0c6d5cef4cf 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -35,6 +35,8 @@
 extern void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder);
 extern void dce6_afmt_write_sad_regs(struct drm_encoder *encoder);
 extern void dce6_afmt_select_pin(struct drm_encoder *encoder);
+extern void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
+					   struct drm_display_mode *mode);
 
 /*
  * update the N and CTS parameters for a given pixel clock rate
@@ -58,6 +60,42 @@ static void evergreen_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t cloc
 	WREG32(HDMI_ACR_48_1 + offset, acr.n_48khz);
 }
 
+static void dce4_afmt_write_latency_fields(struct drm_encoder *encoder,
+					   struct drm_display_mode *mode)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp = 0;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		if (connector->latency_present[1])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
+				AUDIO_LIPSYNC(connector->audio_latency[1]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	} else {
+		if (connector->latency_present[0])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[0]) |
+				AUDIO_LIPSYNC(connector->audio_latency[0]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	}
+	WREG32(AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_LIPSYNC, tmp);
+}
+
 static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
@@ -67,12 +105,11 @@ 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)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -81,7 +118,7 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
 		return;
 	}
@@ -124,8 +161,10 @@ static void evergreen_hdmi_write_sad_regs(struct drm_encoder *encoder)
 	};
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -134,7 +173,7 @@ static void evergreen_hdmi_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 		return;
 	}
@@ -142,20 +181,30 @@ static void evergreen_hdmi_write_sad_regs(struct drm_encoder *encoder)
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 value = 0;
+		u8 stereo_freqs = 0;
+		int max_channels = -1;
 		int j;
 
 		for (j = 0; j < sad_count; j++) {
 			struct cea_sad *sad = &sads[j];
 
 			if (sad->format == eld_reg_to_type[i][1]) {
-				value = MAX_CHANNELS(sad->channels) |
-					DESCRIPTOR_BYTE_2(sad->byte2) |
-					SUPPORTED_FREQUENCIES(sad->freq);
+				if (sad->channels > max_channels) {
+					value = MAX_CHANNELS(sad->channels) |
+						DESCRIPTOR_BYTE_2(sad->byte2) |
+						SUPPORTED_FREQUENCIES(sad->freq);
+					max_channels = sad->channels;
+				}
+
 				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
-					value |= SUPPORTED_FREQUENCIES_STEREO(sad->freq);
-				break;
+					stereo_freqs |= sad->freq;
+				else
+					break;
 			}
 		}
+
+		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
+
 		WREG32(eld_reg_to_type[i][0], value);
 	}
 
@@ -324,8 +373,10 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	if (ASIC_IS_DCE6(rdev)) {
 		dce6_afmt_select_pin(encoder);
 		dce6_afmt_write_sad_regs(encoder);
+		dce6_afmt_write_latency_fields(encoder, mode);
 	} else {
 		evergreen_hdmi_write_sad_regs(encoder);
+		dce4_afmt_write_latency_fields(encoder, mode);
 	}
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 4f6d2962767..17f99079899 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -750,6 +750,44 @@
  * bit6 = 192 kHz
  */
 
+#define AZ_CHANNEL_COUNT_CONTROL                          0x5fe4
+#       define HBR_CHANNEL_COUNT(x)                       (((x) & 0x7) << 0)
+#       define COMPRESSED_CHANNEL_COUNT(x)                (((x) & 0x7) << 4)
+/* HBR_CHANNEL_COUNT, COMPRESSED_CHANNEL_COUNT
+ * 0   = use stream header
+ * 1-7 = channel count - 1
+ */
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_LIPSYNC         0x5fe8
+#       define VIDEO_LIPSYNC(x)                           (((x) & 0xff) << 0)
+#       define AUDIO_LIPSYNC(x)                           (((x) & 0xff) << 8)
+/* VIDEO_LIPSYNC, AUDIO_LIPSYNC
+ * 0   = invalid
+ * x   = legal delay value
+ * 255 = sync not supported
+ */
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_HBR             0x5fec
+#       define HBR_CAPABLE                                (1 << 0) /* enabled by default */
+
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_AV_ASSOCIATION0 0x5ff4
+#       define DISPLAY0_TYPE(x)                           (((x) & 0x3) << 0)
+#       define DISPLAY_TYPE_NONE                   0
+#       define DISPLAY_TYPE_HDMI                   1
+#       define DISPLAY_TYPE_DP                     2
+#       define DISPLAY0_ID(x)                             (((x) & 0x3f) << 2)
+#       define DISPLAY1_TYPE(x)                           (((x) & 0x3) << 8)
+#       define DISPLAY1_ID(x)                             (((x) & 0x3f) << 10)
+#       define DISPLAY2_TYPE(x)                           (((x) & 0x3) << 16)
+#       define DISPLAY2_ID(x)                             (((x) & 0x3f) << 18)
+#       define DISPLAY3_TYPE(x)                           (((x) & 0x3) << 24)
+#       define DISPLAY3_ID(x)                             (((x) & 0x3f) << 26)
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_AV_ASSOCIATION1 0x5ff8
+#       define DISPLAY4_TYPE(x)                           (((x) & 0x3) << 0)
+#       define DISPLAY4_ID(x)                             (((x) & 0x3f) << 2)
+#       define DISPLAY5_TYPE(x)                           (((x) & 0x3) << 8)
+#       define DISPLAY5_ID(x)                             (((x) & 0x3f) << 10)
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_AV_NUMBER       0x5ffc
+#       define NUMBER_OF_DISPLAY_ID(x)                    (((x) & 0x7) << 0)
+
 #define AZ_HOT_PLUG_CONTROL                               0x5e78
 #       define AZ_FORCE_CODEC_WAKE                        (1 << 0)
 #       define PIN0_JACK_DETECTION_ENABLE                 (1 << 4)
@@ -1312,6 +1350,38 @@
 #       define DC_HPDx_RX_INT_TIMER(x)                    ((x) << 16)
 #       define DC_HPDx_EN                                 (1 << 28)
 
+/* DCE4/5/6 FMT blocks */
+#define FMT_DYNAMIC_EXP_CNTL                 0x6fb4
+#       define FMT_DYNAMIC_EXP_EN            (1 << 0)
+#       define FMT_DYNAMIC_EXP_MODE          (1 << 4)
+        /* 0 = 10bit -> 12bit, 1 = 8bit -> 12bit */
+#define FMT_CONTROL                          0x6fb8
+#       define FMT_PIXEL_ENCODING            (1 << 16)
+        /* 0 = RGB 4:4:4 or YCbCr 4:4:4, 1 = YCbCr 4:2:2 */
+#define FMT_BIT_DEPTH_CONTROL                0x6fc8
+#       define FMT_TRUNCATE_EN               (1 << 0)
+#       define FMT_TRUNCATE_DEPTH            (1 << 4)
+#       define FMT_SPATIAL_DITHER_EN         (1 << 8)
+#       define FMT_SPATIAL_DITHER_MODE(x)    ((x) << 9)
+#       define FMT_SPATIAL_DITHER_DEPTH      (1 << 12)
+#       define FMT_FRAME_RANDOM_ENABLE       (1 << 13)
+#       define FMT_RGB_RANDOM_ENABLE         (1 << 14)
+#       define FMT_HIGHPASS_RANDOM_ENABLE    (1 << 15)
+#       define FMT_TEMPORAL_DITHER_EN        (1 << 16)
+#       define FMT_TEMPORAL_DITHER_DEPTH     (1 << 20)
+#       define FMT_TEMPORAL_DITHER_OFFSET(x) ((x) << 21)
+#       define FMT_TEMPORAL_LEVEL            (1 << 24)
+#       define FMT_TEMPORAL_DITHER_RESET     (1 << 25)
+#       define FMT_25FRC_SEL(x)              ((x) << 26)
+#       define FMT_50FRC_SEL(x)              ((x) << 28)
+#       define FMT_75FRC_SEL(x)              ((x) << 30)
+#define FMT_CLAMP_CONTROL                    0x6fe4
+#       define FMT_CLAMP_DATA_EN             (1 << 0)
+#       define FMT_CLAMP_COLOR_FORMAT(x)     ((x) << 16)
+#       define FMT_CLAMP_6BPC                0
+#       define FMT_CLAMP_8BPC                1
+#       define FMT_CLAMP_10BPC               2
+
 /* ASYNC DMA */
 #define DMA_RB_RPTR                                       0xd008
 #define DMA_RB_WPTR                                       0xd00c
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index cac2866d79d..f59a9e9fccf 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -174,11 +174,6 @@ extern void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
 extern void evergreen_program_aspm(struct radeon_device *rdev);
 extern void sumo_rlc_fini(struct radeon_device *rdev);
 extern int sumo_rlc_init(struct radeon_device *rdev);
-extern void cayman_dma_vm_set_page(struct radeon_device *rdev,
-				   struct radeon_ib *ib,
-				   uint64_t pe,
-				   uint64_t addr, unsigned count,
-				   uint32_t incr, uint32_t flags);
 
 /* Firmware Names */
 MODULE_FIRMWARE("radeon/BARTS_pfp.bin");
@@ -900,6 +895,10 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 		    (rdev->pdev->device == 0x999C)) {
 			rdev->config.cayman.max_simds_per_se = 6;
 			rdev->config.cayman.max_backends_per_se = 2;
+			rdev->config.cayman.max_hw_contexts = 8;
+			rdev->config.cayman.sx_max_export_size = 256;
+			rdev->config.cayman.sx_max_export_pos_size = 64;
+			rdev->config.cayman.sx_max_export_smx_size = 192;
 		} else if ((rdev->pdev->device == 0x9903) ||
 			   (rdev->pdev->device == 0x9904) ||
 			   (rdev->pdev->device == 0x990A) ||
@@ -910,6 +909,10 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x999D)) {
 			rdev->config.cayman.max_simds_per_se = 4;
 			rdev->config.cayman.max_backends_per_se = 2;
+			rdev->config.cayman.max_hw_contexts = 8;
+			rdev->config.cayman.sx_max_export_size = 256;
+			rdev->config.cayman.sx_max_export_pos_size = 64;
+			rdev->config.cayman.sx_max_export_smx_size = 192;
 		} else if ((rdev->pdev->device == 0x9919) ||
 			   (rdev->pdev->device == 0x9990) ||
 			   (rdev->pdev->device == 0x9991) ||
@@ -920,9 +923,17 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x99A0)) {
 			rdev->config.cayman.max_simds_per_se = 3;
 			rdev->config.cayman.max_backends_per_se = 1;
+			rdev->config.cayman.max_hw_contexts = 4;
+			rdev->config.cayman.sx_max_export_size = 128;
+			rdev->config.cayman.sx_max_export_pos_size = 32;
+			rdev->config.cayman.sx_max_export_smx_size = 96;
 		} else {
 			rdev->config.cayman.max_simds_per_se = 2;
 			rdev->config.cayman.max_backends_per_se = 1;
+			rdev->config.cayman.max_hw_contexts = 4;
+			rdev->config.cayman.sx_max_export_size = 128;
+			rdev->config.cayman.sx_max_export_pos_size = 32;
+			rdev->config.cayman.sx_max_export_smx_size = 96;
 		}
 		rdev->config.cayman.max_texture_channel_caches = 2;
 		rdev->config.cayman.max_gprs = 256;
@@ -930,10 +941,6 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 		rdev->config.cayman.max_gs_threads = 32;
 		rdev->config.cayman.max_stack_entries = 512;
 		rdev->config.cayman.sx_num_of_sets = 8;
-		rdev->config.cayman.sx_max_export_size = 256;
-		rdev->config.cayman.sx_max_export_pos_size = 64;
-		rdev->config.cayman.sx_max_export_smx_size = 192;
-		rdev->config.cayman.max_hw_contexts = 8;
 		rdev->config.cayman.sq_num_cf_insts = 2;
 
 		rdev->config.cayman.sc_prim_fifo_size = 0x40;
@@ -2400,77 +2407,6 @@ void cayman_vm_decode_fault(struct radeon_device *rdev,
 	       block, mc_id);
 }
 
-#define R600_ENTRY_VALID   (1 << 0)
-#define R600_PTE_SYSTEM    (1 << 1)
-#define R600_PTE_SNOOPED   (1 << 2)
-#define R600_PTE_READABLE  (1 << 5)
-#define R600_PTE_WRITEABLE (1 << 6)
-
-uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags)
-{
-	uint32_t r600_flags = 0;
-	r600_flags |= (flags & RADEON_VM_PAGE_VALID) ? R600_ENTRY_VALID : 0;
-	r600_flags |= (flags & RADEON_VM_PAGE_READABLE) ? R600_PTE_READABLE : 0;
-	r600_flags |= (flags & RADEON_VM_PAGE_WRITEABLE) ? R600_PTE_WRITEABLE : 0;
-	if (flags & RADEON_VM_PAGE_SYSTEM) {
-		r600_flags |= R600_PTE_SYSTEM;
-		r600_flags |= (flags & RADEON_VM_PAGE_SNOOPED) ? R600_PTE_SNOOPED : 0;
-	}
-	return r600_flags;
-}
-
-/**
- * cayman_vm_set_page - update the page tables using the CP
- *
- * @rdev: radeon_device pointer
- * @ib: indirect buffer to fill with commands
- * @pe: addr of the page entry
- * @addr: dst addr to write into pe
- * @count: number of page entries to update
- * @incr: increase next addr by incr bytes
- * @flags: access flags
- *
- * Update the page tables using the CP (cayman/TN).
- */
-void cayman_vm_set_page(struct radeon_device *rdev,
-			struct radeon_ib *ib,
-			uint64_t pe,
-			uint64_t addr, unsigned count,
-			uint32_t incr, uint32_t flags)
-{
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	uint64_t value;
-	unsigned ndw;
-
-	if (rdev->asic->vm.pt_ring_index == RADEON_RING_TYPE_GFX_INDEX) {
-		while (count) {
-			ndw = 1 + count * 2;
-			if (ndw > 0x3FFF)
-				ndw = 0x3FFF;
-
-			ib->ptr[ib->length_dw++] = PACKET3(PACKET3_ME_WRITE, ndw);
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			for (; ndw > 1; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= r600_flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		cayman_dma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
-	}
-}
-
 /**
  * cayman_vm_flush - vm flush using the CP
  *
diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
index dd6e9688fbe..bdeb65ed365 100644
--- a/drivers/gpu/drm/radeon/ni_dma.c
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -24,6 +24,7 @@
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
+#include "radeon_trace.h"
 #include "nid.h"
 
 u32 cayman_gpu_check_soft_reset(struct radeon_device *rdev);
@@ -245,8 +246,7 @@ bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
  * @addr: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
- * @flags: access flags
- * @r600_flags: hw access flags 
+ * @flags: hw access flags 
  *
  * Update the page tables using the DMA (cayman/TN).
  */
@@ -256,11 +256,12 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			    uint64_t addr, unsigned count,
 			    uint32_t incr, uint32_t flags)
 {
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
 
-	if ((flags & RADEON_VM_PAGE_SYSTEM) || (count == 1)) {
+	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
+
+	if ((flags & R600_PTE_SYSTEM) || (count == 1)) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -271,16 +272,16 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = pe;
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
 			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
+				if (flags & R600_PTE_SYSTEM) {
 					value = radeon_vm_map_gart(rdev, addr);
 					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
+				} else if (flags & R600_PTE_VALID) {
 					value = addr;
 				} else {
 					value = 0;
 				}
 				addr += incr;
-				value |= r600_flags;
+				value |= flags;
 				ib->ptr[ib->length_dw++] = value;
 				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
@@ -291,7 +292,7 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			if (ndw > 0xFFFFE)
 				ndw = 0xFFFFE;
 
-			if (flags & RADEON_VM_PAGE_VALID)
+			if (flags & R600_PTE_VALID)
 				value = addr;
 			else
 				value = 0;
@@ -299,7 +300,7 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
 			ib->ptr[ib->length_dw++] = pe; /* dst addr */
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = flags; /* mask */
 			ib->ptr[ib->length_dw++] = 0;
 			ib->ptr[ib->length_dw++] = value; /* value */
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index f2633902815..49c4d48f54d 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -785,8 +785,8 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 	struct ni_ps *ps = ni_get_ps(rps);
 	struct radeon_clock_and_voltage_limits *max_limits;
 	bool disable_mclk_switching;
-	u32 mclk, sclk;
-	u16 vddc, vddci;
+	u32 mclk;
+	u16 vddci;
 	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
@@ -839,24 +839,14 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 
 	/* XXX validate the min clocks required for display */
 
+	/* adjust low state */
 	if (disable_mclk_switching) {
-		mclk  = ps->performance_levels[ps->performance_level_count - 1].mclk;
-		sclk = ps->performance_levels[0].sclk;
-		vddc = ps->performance_levels[0].vddc;
-		vddci = ps->performance_levels[ps->performance_level_count - 1].vddci;
-	} else {
-		sclk = ps->performance_levels[0].sclk;
-		mclk = ps->performance_levels[0].mclk;
-		vddc = ps->performance_levels[0].vddc;
-		vddci = ps->performance_levels[0].vddci;
+		ps->performance_levels[0].mclk =
+			ps->performance_levels[ps->performance_level_count - 1].mclk;
+		ps->performance_levels[0].vddci =
+			ps->performance_levels[ps->performance_level_count - 1].vddci;
 	}
 
-	/* adjusted low state */
-	ps->performance_levels[0].sclk = sclk;
-	ps->performance_levels[0].mclk = mclk;
-	ps->performance_levels[0].vddc = vddc;
-	ps->performance_levels[0].vddci = vddci;
-
 	btc_skip_blacklist_clocks(rdev, max_limits->sclk, max_limits->mclk,
 				  &ps->performance_levels[0].sclk,
 				  &ps->performance_levels[0].mclk);
@@ -868,11 +858,15 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 			ps->performance_levels[i].vddc = ps->performance_levels[i - 1].vddc;
 	}
 
+	/* adjust remaining states */
 	if (disable_mclk_switching) {
 		mclk = ps->performance_levels[0].mclk;
+		vddci = ps->performance_levels[0].vddci;
 		for (i = 1; i < ps->performance_level_count; i++) {
 			if (mclk < ps->performance_levels[i].mclk)
 				mclk = ps->performance_levels[i].mclk;
+			if (vddci < ps->performance_levels[i].vddci)
+				vddci = ps->performance_levels[i].vddci;
 		}
 		for (i = 0; i < ps->performance_level_count; i++) {
 			ps->performance_levels[i].mclk = mclk;
@@ -3445,9 +3439,9 @@ static int ni_enable_smc_cac(struct radeon_device *rdev,
 static int ni_pcie_performance_request(struct radeon_device *rdev,
 				       u8 perf_req, bool advertise)
 {
+#if defined(CONFIG_ACPI)
 	struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
 
-#if defined(CONFIG_ACPI)
 	if ((perf_req == PCIE_PERF_REQ_PECI_GEN1) ||
             (perf_req == PCIE_PERF_REQ_PECI_GEN2)) {
 		if (eg_pi->pcie_performance_request_registered == false)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index d71333033b2..10abc4d5a6c 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -869,13 +869,14 @@ void r100_fence_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, RADEON_SW_INT_FIRE);
 }
 
-void r100_semaphore_ring_emit(struct radeon_device *rdev,
+bool r100_semaphore_ring_emit(struct radeon_device *rdev,
 			      struct radeon_ring *ring,
 			      struct radeon_semaphore *semaphore,
 			      bool emit_wait)
 {
 	/* Unused on older asics, since we don't have semaphores or multiple rings */
 	BUG();
+	return false;
 }
 
 int r100_copy_blit(struct radeon_device *rdev,
@@ -1434,7 +1435,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
 	if (!obj) {
 		DRM_ERROR("cannot find crtc %d\n", crtc_id);
-		return -EINVAL;
+		return -ENOENT;
 	}
 	crtc = obj_to_crtc(obj);
 	radeon_crtc = to_radeon_crtc(crtc);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index f9be22062df..9ad06732a78 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -124,6 +124,59 @@ int r600_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 	return 0;
 }
 
+void dce3_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	/* not needed for analog */
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2))
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= FMT_SPATIAL_DITHER_EN;
+		else
+			tmp |= FMT_TRUNCATE_EN;
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH);
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH);
+		break;
+	case 10:
+	default:
+		/* not needed */
+		break;
+	}
+
+	WREG32(FMT_BIT_DEPTH_CONTROL + radeon_crtc->crtc_offset, tmp);
+}
+
 /* get temperature in millidegrees */
 int rv6xx_get_temp(struct radeon_device *rdev)
 {
@@ -2597,7 +2650,7 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	}
 }
 
-void r600_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_semaphore_ring_emit(struct radeon_device *rdev,
 			      struct radeon_ring *ring,
 			      struct radeon_semaphore *semaphore,
 			      bool emit_wait)
@@ -2611,6 +2664,8 @@ void r600_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, PACKET3(PACKET3_MEM_SEMAPHORE, 1));
 	radeon_ring_write(ring, addr & 0xffffffff);
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | sel);
+
+	return true;
 }
 
 /**
@@ -2653,13 +2708,8 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 		return r;
 	}
 
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
 	radeon_ring_write(ring, (WAIT_UNTIL - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 01a3ec83f28..5dceea6f71a 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -887,7 +887,7 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 	obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
 	if (!obj) {
 		DRM_ERROR("cannot find crtc %d\n", crtc_id);
-		return -EINVAL;
+		return -ENOENT;
 	}
 	crtc = obj_to_crtc(obj);
 	radeon_crtc = to_radeon_crtc(crtc);
@@ -2328,13 +2328,8 @@ static void r600_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 	unsigned i;
 
 	kfree(parser->relocs);
-	for (i = 0; i < parser->nchunks; i++) {
-		kfree(parser->chunks[i].kdata);
-		if (parser->rdev && (parser->rdev->flags & RADEON_IS_AGP)) {
-			kfree(parser->chunks[i].kpage[0]);
-			kfree(parser->chunks[i].kpage[1]);
-		}
-	}
+	for (i = 0; i < parser->nchunks; i++)
+		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
 	kfree(parser->chunks_array);
 }
@@ -2391,13 +2386,12 @@ int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp,
 	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
 	parser.ib.length_dw = ib_chunk->length_dw;
 	*l = parser.ib.length_dw;
-	r = r600_cs_parse(&parser);
-	if (r) {
-		DRM_ERROR("Invalid command stream !\n");
+	if (DRM_COPY_FROM_USER(ib, ib_chunk->user_ptr, ib_chunk->length_dw * 4)) {
+		r = -EFAULT;
 		r600_cs_parser_fini(&parser, r);
 		return r;
 	}
-	r = radeon_cs_finish_pages(&parser);
+	r = r600_cs_parse(&parser);
 	if (r) {
 		DRM_ERROR("Invalid command stream !\n");
 		r600_cs_parser_fini(&parser, r);
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
index 3b317456512..7844d15c139 100644
--- a/drivers/gpu/drm/radeon/r600_dma.c
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -311,7 +311,7 @@ void r600_dma_fence_ring_emit(struct radeon_device *rdev,
  * Add a DMA semaphore packet to the ring wait on or signal
  * other rings (r6xx-SI).
  */
-void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
 				  struct radeon_ring *ring,
 				  struct radeon_semaphore *semaphore,
 				  bool emit_wait)
@@ -322,6 +322,8 @@ void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SEMAPHORE, 0, s, 0));
 	radeon_ring_write(ring, addr & 0xfffffffc);
 	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
+
+	return true;
 }
 
 /**
@@ -462,13 +464,8 @@ int r600_copy_dma(struct radeon_device *rdev,
 		return r;
 	}
 
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
 		cur_size_in_dw = size_in_dw;
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 06022e3b9c3..b7d3ecba43e 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -24,6 +24,7 @@
  * Authors: Christian König
  */
 #include <linux/hdmi.h>
+#include <linux/gcd.h>
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
 #include "radeon.h"
@@ -57,35 +58,57 @@ 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 */
-    {  25175,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
+    {  25175,  4096,  25175, 28224, 125875,  6144,  25175 }, /*  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 */
-    {  74176, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
+    {  74176,  4096,  74176,  5733,  75335,  6144,  74176 }, /*  74.25/1.001 MHz */
     {  74250,  4096,  74250,  6272,  82500,  6144,  74250 }, /*  74.25       MHz */
-    { 148352, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
+    { 148352,  4096, 148352,  5733, 150670,  6144, 148352 }, /* 148.50/1.001 MHz */
     { 148500,  4096, 148500,  6272, 165000,  6144, 148500 }, /* 148.50       MHz */
-    {      0,  4096,      0,  6272,      0,  6144,      0 }  /* Other */
 };
 
+
 /*
- * calculate CTS value if it's not found in the table
+ * calculate CTS and N values if they are not found in the table
  */
-static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq)
+static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int *N, int freq)
 {
-	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);
+	int n, cts;
+	unsigned long div, mul;
+
+	/* Safe, but overly large values */
+	n = 128 * freq;
+	cts = clock * 1000;
+
+	/* Smallest valid fraction */
+	div = gcd(n, cts);
+
+	n /= div;
+	cts /= div;
+
+	/*
+	 * The optimal N is 128*freq/1000. Calculate the closest larger
+	 * value that doesn't truncate any bits.
+	 */
+	mul = ((128*freq/1000) + (n-1))/n;
+
+	n *= mul;
+	cts *= mul;
+
+	/* Check that we are in spec (not always possible) */
+	if (n < (128*freq/1500))
+		printk(KERN_WARNING "Calculated ACR N value is too small. You may experience audio problems.\n");
+	if (n > (128*freq/300))
+		printk(KERN_WARNING "Calculated ACR N value is too large. You may experience audio problems.\n");
+
+	*N = n;
+	*CTS = cts;
+
+	DRM_DEBUG("Calculated ACR timing N=%d CTS=%d for frequency %d\n",
+		  *N, *CTS, freq);
 }
 
 struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock)
@@ -93,15 +116,16 @@ struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock)
 	struct radeon_hdmi_acr res;
 	u8 i;
 
-	for (i = 0; r600_hdmi_predefined_acr[i].clock != clock &&
-	     r600_hdmi_predefined_acr[i].clock != 0; i++)
-		;
-	res = r600_hdmi_predefined_acr[i];
+	/* Precalculated values for common clocks */
+	for (i = 0; i < ARRAY_SIZE(r600_hdmi_predefined_acr); i++) {
+		if (r600_hdmi_predefined_acr[i].clock == clock)
+			return r600_hdmi_predefined_acr[i];
+	}
 
-	/* In case some CTS are missing */
-	r600_hdmi_calc_cts(clock, &res.cts_32khz, res.n_32khz, 32000);
-	r600_hdmi_calc_cts(clock, &res.cts_44_1khz, res.n_44_1khz, 44100);
-	r600_hdmi_calc_cts(clock, &res.cts_48khz, res.n_48khz, 48000);
+	/* And odd clocks get manually calculated */
+	r600_hdmi_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000);
+	r600_hdmi_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100);
+	r600_hdmi_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000);
 
 	return res;
 }
@@ -280,9 +304,9 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 			WREG32(DCCG_AUDIO_DTO1_MODULE, dto_modulo);
 			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
 		}
-	} else if (ASIC_IS_DCE3(rdev)) {
+	} else {
 		/* according to the reg specs, this should DCE3.2 only, but in
-		 * practice it seems to cover DCE3.0/3.1 as well.
+		 * practice it seems to cover DCE2.0/3.0/3.1 as well.
 		 */
 		if (dig->dig_encoder == 0) {
 			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
@@ -293,10 +317,6 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 			WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
 			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
 		}
-	} else {
-		/* 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));
 	}
 }
 
@@ -313,8 +333,10 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	return;
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -366,8 +388,10 @@ static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
 	};
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -384,20 +408,30 @@ static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 value = 0;
+		u8 stereo_freqs = 0;
+		int max_channels = -1;
 		int j;
 
 		for (j = 0; j < sad_count; j++) {
 			struct cea_sad *sad = &sads[j];
 
 			if (sad->format == eld_reg_to_type[i][1]) {
-				value = MAX_CHANNELS(sad->channels) |
-					DESCRIPTOR_BYTE_2(sad->byte2) |
-					SUPPORTED_FREQUENCIES(sad->freq);
+				if (sad->channels > max_channels) {
+					value = MAX_CHANNELS(sad->channels) |
+						DESCRIPTOR_BYTE_2(sad->byte2) |
+						SUPPORTED_FREQUENCIES(sad->freq);
+					max_channels = sad->channels;
+				}
+
 				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
-					value |= SUPPORTED_FREQUENCIES_STEREO(sad->freq);
-				break;
+					stereo_freqs |= sad->freq;
+				else
+					break;
 			}
 		}
+
+		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
+
 		WREG32(eld_reg_to_type[i][0], value);
 	}
 
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 7b3c7b5932c..ebe38724a97 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1199,6 +1199,34 @@
 #       define AFMT_AZ_FORMAT_WTRIG_ACK      (1 << 29)
 #       define AFMT_AZ_AUDIO_ENABLE_CHG_ACK  (1 << 30)
 
+/* DCE3 FMT blocks */
+#define FMT_CONTROL                          0x6700
+#       define FMT_PIXEL_ENCODING            (1 << 16)
+        /* 0 = RGB 4:4:4 or YCbCr 4:4:4, 1 = YCbCr 4:2:2 */
+#define FMT_BIT_DEPTH_CONTROL                0x6710
+#       define FMT_TRUNCATE_EN               (1 << 0)
+#       define FMT_TRUNCATE_DEPTH            (1 << 4)
+#       define FMT_SPATIAL_DITHER_EN         (1 << 8)
+#       define FMT_SPATIAL_DITHER_MODE(x)    ((x) << 9)
+#       define FMT_SPATIAL_DITHER_DEPTH      (1 << 12)
+#       define FMT_FRAME_RANDOM_ENABLE       (1 << 13)
+#       define FMT_RGB_RANDOM_ENABLE         (1 << 14)
+#       define FMT_HIGHPASS_RANDOM_ENABLE    (1 << 15)
+#       define FMT_TEMPORAL_DITHER_EN        (1 << 16)
+#       define FMT_TEMPORAL_DITHER_DEPTH     (1 << 20)
+#       define FMT_TEMPORAL_DITHER_OFFSET(x) ((x) << 21)
+#       define FMT_TEMPORAL_LEVEL            (1 << 24)
+#       define FMT_TEMPORAL_DITHER_RESET     (1 << 25)
+#       define FMT_25FRC_SEL(x)              ((x) << 26)
+#       define FMT_50FRC_SEL(x)              ((x) << 28)
+#       define FMT_75FRC_SEL(x)              ((x) << 30)
+#define FMT_CLAMP_CONTROL                    0x672c
+#       define FMT_CLAMP_DATA_EN             (1 << 0)
+#       define FMT_CLAMP_COLOR_FORMAT(x)     ((x) << 16)
+#       define FMT_CLAMP_6BPC                0
+#       define FMT_CLAMP_8BPC                1
+#       define FMT_CLAMP_10BPC               2
+
 /* Power management */
 #define CG_SPLL_FUNC_CNTL                                 0x600
 #       define SPLL_RESET                                (1 << 0)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 24f4960f59e..45e1f447bc7 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -98,6 +98,7 @@ extern int radeon_lockup_timeout;
 extern int radeon_fastfb;
 extern int radeon_dpm;
 extern int radeon_aspm;
+extern int radeon_runtime_pm;
 
 /*
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
@@ -327,7 +328,6 @@ struct radeon_fence_driver {
 	/* sync_seq is protected by ring emission lock */
 	uint64_t			sync_seq[RADEON_NUM_RINGS];
 	atomic64_t			last_seq;
-	unsigned long			last_activity;
 	bool				initialized;
 };
 
@@ -348,6 +348,7 @@ int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence **fence, i
 void radeon_fence_process(struct radeon_device *rdev, int ring);
 bool radeon_fence_signaled(struct radeon_fence *fence);
 int radeon_fence_wait(struct radeon_fence *fence, bool interruptible);
+int radeon_fence_wait_locked(struct radeon_fence *fence);
 int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring);
 int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring);
 int radeon_fence_wait_any(struct radeon_device *rdev,
@@ -548,17 +549,20 @@ struct radeon_semaphore {
 	struct radeon_sa_bo		*sa_bo;
 	signed				waiters;
 	uint64_t			gpu_addr;
+	struct radeon_fence		*sync_to[RADEON_NUM_RINGS];
 };
 
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore);
-void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
 				  struct radeon_semaphore *semaphore);
-void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 				struct radeon_semaphore *semaphore);
+void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
+			      struct radeon_fence *fence);
 int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				struct radeon_semaphore *semaphore,
-				int signaler, int waiter);
+				int waiting_ring);
 void radeon_semaphore_free(struct radeon_device *rdev,
 			   struct radeon_semaphore **semaphore,
 			   struct radeon_fence *fence);
@@ -645,13 +649,15 @@ void radeon_scratch_free(struct radeon_device *rdev, uint32_t reg);
 /*
  * GPU doorbell structures, functions & helpers
  */
+#define RADEON_MAX_DOORBELLS 1024	/* Reserve at most 1024 doorbell slots for radeon-owned rings. */
+
 struct radeon_doorbell {
-	u32			num_pages;
-	bool			free[1024];
 	/* doorbell mmio */
-	resource_size_t			base;
-	resource_size_t			size;
-	void __iomem			*ptr;
+	resource_size_t		base;
+	resource_size_t		size;
+	u32 __iomem		*ptr;
+	u32			num_doorbells;	/* Number of doorbells actually reserved for radeon. */
+	unsigned long		used[DIV_ROUND_UP(RADEON_MAX_DOORBELLS, BITS_PER_LONG)];
 };
 
 int radeon_doorbell_get(struct radeon_device *rdev, u32 *page);
@@ -765,7 +771,6 @@ struct radeon_ib {
 	struct radeon_fence		*fence;
 	struct radeon_vm		*vm;
 	bool				is_const_ib;
-	struct radeon_fence		*sync_to[RADEON_NUM_RINGS];
 	struct radeon_semaphore		*semaphore;
 };
 
@@ -799,8 +804,7 @@ struct radeon_ring {
 	u32 pipe;
 	u32 queue;
 	struct radeon_bo	*mqd_obj;
-	u32 doorbell_page_num;
-	u32 doorbell_offset;
+	u32 doorbell_index;
 	unsigned		wptr_offs;
 };
 
@@ -832,6 +836,12 @@ struct radeon_mec {
 #define RADEON_VM_PTB_ALIGN_MASK (RADEON_VM_PTB_ALIGN_SIZE - 1)
 #define RADEON_VM_PTB_ALIGN(a) (((a) + RADEON_VM_PTB_ALIGN_MASK) & ~RADEON_VM_PTB_ALIGN_MASK)
 
+#define R600_PTE_VALID		(1 << 0)
+#define R600_PTE_SYSTEM		(1 << 1)
+#define R600_PTE_SNOOPED	(1 << 2)
+#define R600_PTE_READABLE	(1 << 5)
+#define R600_PTE_WRITEABLE	(1 << 6)
+
 struct radeon_vm {
 	struct list_head		list;
 	struct list_head		va;
@@ -915,7 +925,6 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib *ib, struct radeon_vm *vm,
 		  unsigned size);
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
-void radeon_ib_sync_to(struct radeon_ib *ib, struct radeon_fence *fence);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 		       struct radeon_ib *const_ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);
@@ -967,12 +976,8 @@ struct radeon_cs_reloc {
 struct radeon_cs_chunk {
 	uint32_t		chunk_id;
 	uint32_t		length_dw;
-	int			kpage_idx[2];
-	uint32_t		*kpage[2];
 	uint32_t		*kdata;
 	void __user		*user_ptr;
-	int			last_copied_page;
-	int			last_page_index;
 };
 
 struct radeon_cs_parser {
@@ -1007,8 +1012,15 @@ struct radeon_cs_parser {
 	struct ww_acquire_ctx	ticket;
 };
 
-extern int radeon_cs_finish_pages(struct radeon_cs_parser *p);
-extern u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx);
+static inline u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
+{
+	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
+
+	if (ibc->kdata)
+		return ibc->kdata[idx];
+	return p->ib.ptr[idx];
+}
+
 
 struct radeon_cs_packet {
 	unsigned	idx;
@@ -1629,7 +1641,7 @@ struct radeon_asic_ring {
 	/* command emmit functions */
 	void (*ib_execute)(struct radeon_device *rdev, struct radeon_ib *ib);
 	void (*emit_fence)(struct radeon_device *rdev, struct radeon_fence *fence);
-	void (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
+	bool (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
 			       struct radeon_semaphore *semaphore, bool emit_wait);
 	void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 
@@ -1675,8 +1687,6 @@ struct radeon_asic {
 	struct {
 		int (*init)(struct radeon_device *rdev);
 		void (*fini)(struct radeon_device *rdev);
-
-		u32 pt_ring_index;
 		void (*set_page)(struct radeon_device *rdev,
 				 struct radeon_ib *ib,
 				 uint64_t pe,
@@ -1930,7 +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;
@@ -1960,7 +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;
@@ -1972,6 +1982,7 @@ struct cik_asic {
 
 	unsigned tile_config;
 	uint32_t tile_mode_array[32];
+	uint32_t macrotile_mode_array[16];
 };
 
 union radeon_asic_config {
@@ -2170,6 +2181,7 @@ struct radeon_device {
 	bool				need_dma32;
 	bool				accel_working;
 	bool				fastfb_working; /* IGP feature*/
+	bool				needs_reset;
 	struct radeon_surface_reg surface_regs[RADEON_GEM_MAX_SURFACES];
 	const struct firmware *me_fw;	/* all family ME firmware */
 	const struct firmware *pfp_fw;	/* r6/700 PFP firmware */
@@ -2212,6 +2224,9 @@ struct radeon_device {
 	/* clock, powergating flags */
 	u32 cg_flags;
 	u32 pg_flags;
+
+	struct dev_pm_domain vga_pm_domain;
+	bool have_disp_power_ref;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -2228,8 +2243,8 @@ void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v,
 u32 r100_io_rreg(struct radeon_device *rdev, u32 reg);
 void r100_io_wreg(struct radeon_device *rdev, u32 reg, u32 v);
 
-u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 offset);
-void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v);
+u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 index);
+void cik_mm_wdoorbell(struct radeon_device *rdev, u32 index, u32 v);
 
 /*
  * Cast helper
@@ -2292,8 +2307,8 @@ void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v);
 #define RREG32_IO(reg) r100_io_rreg(rdev, (reg))
 #define WREG32_IO(reg, v) r100_io_wreg(rdev, (reg), (v))
 
-#define RDOORBELL32(offset) cik_mm_rdoorbell(rdev, (offset))
-#define WDOORBELL32(offset, v) cik_mm_wdoorbell(rdev, (offset), (v))
+#define RDOORBELL32(index) cik_mm_rdoorbell(rdev, (index))
+#define WDOORBELL32(index, v) cik_mm_wdoorbell(rdev, (index), (v))
 
 /*
  * Indirect registers accessor
@@ -2673,8 +2688,8 @@ extern void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain);
 extern bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo);
 extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base);
 extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
-extern int radeon_resume_kms(struct drm_device *dev);
-extern int radeon_suspend_kms(struct drm_device *dev, pm_message_t state);
+extern int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
+extern int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon);
 extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size);
 extern void radeon_program_register_sequence(struct radeon_device *rdev,
 					     const u32 *registers,
@@ -2695,10 +2710,10 @@ void radeon_vm_fence(struct radeon_device *rdev,
 		     struct radeon_vm *vm,
 		     struct radeon_fence *fence);
 uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr);
-int radeon_vm_bo_update_pte(struct radeon_device *rdev,
-			    struct radeon_vm *vm,
-			    struct radeon_bo *bo,
-			    struct ttm_mem_reg *mem);
+int radeon_vm_bo_update(struct radeon_device *rdev,
+			struct radeon_vm *vm,
+			struct radeon_bo *bo,
+			struct ttm_mem_reg *mem);
 void radeon_vm_bo_invalidate(struct radeon_device *rdev,
 			     struct radeon_bo *bo);
 struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 10f98c7742d..98a9074b306 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -369,7 +369,7 @@ int radeon_atif_handler(struct radeon_device *rdev,
 		return NOTIFY_DONE;
 
 	/* Check pending SBIOS requests */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 	count = radeon_atif_get_sbios_requests(handle, &req);
 
 	if (count <= 0)
@@ -556,7 +556,7 @@ int radeon_acpi_pcie_notify_device_ready(struct radeon_device *rdev)
 	struct radeon_atcs *atcs = &rdev->atcs;
 
 	/* Get the device handle */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 	if (!handle)
 		return -EINVAL;
 
@@ -596,7 +596,7 @@ int radeon_acpi_pcie_performance_request(struct radeon_device *rdev,
 	u32 retry = 3;
 
 	/* Get the device handle */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 	if (!handle)
 		return -EINVAL;
 
@@ -699,7 +699,7 @@ int radeon_acpi_init(struct radeon_device *rdev)
 	int ret;
 
 	/* Get the device handle */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 
 	/* No need to proceed if we're sure that ATIF is not supported */
 	if (!ASIC_IS_AVIVO(rdev) || !rdev->bios || !handle)
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 8f7e04538fd..c0425bb6223 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1622,8 +1622,7 @@ static struct radeon_asic cayman_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cayman_vm_set_page,
+		.set_page = &cayman_dma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &cayman_gfx_ring,
@@ -1723,8 +1722,7 @@ static struct radeon_asic trinity_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cayman_vm_set_page,
+		.set_page = &cayman_dma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &cayman_gfx_ring,
@@ -1854,8 +1852,7 @@ static struct radeon_asic si_asic = {
 	.vm = {
 		.init = &si_vm_init,
 		.fini = &si_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &si_vm_set_page,
+		.set_page = &si_dma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &si_gfx_ring,
@@ -1879,7 +1876,7 @@ static struct radeon_asic si_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = NULL,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &si_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2000,8 +1997,7 @@ static struct radeon_asic ci_asic = {
 	.vm = {
 		.init = &cik_vm_init,
 		.fini = &cik_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cik_vm_set_page,
+		.set_page = &cik_sdma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &ci_gfx_ring,
@@ -2019,11 +2015,13 @@ static struct radeon_asic ci_asic = {
 		.bandwidth_update = &dce8_bandwidth_update,
 		.get_vblank_counter = &evergreen_get_vblank_counter,
 		.wait_for_vblank = &dce4_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 		.hdmi_enable = &evergreen_hdmi_enable,
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = NULL,
+		.blit = &cik_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &cik_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2100,8 +2098,7 @@ static struct radeon_asic kv_asic = {
 	.vm = {
 		.init = &cik_vm_init,
 		.fini = &cik_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cik_vm_set_page,
+		.set_page = &cik_sdma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &ci_gfx_ring,
@@ -2119,11 +2116,13 @@ static struct radeon_asic kv_asic = {
 		.bandwidth_update = &dce8_bandwidth_update,
 		.get_vblank_counter = &evergreen_get_vblank_counter,
 		.wait_for_vblank = &dce4_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 		.hdmi_enable = &evergreen_hdmi_enable,
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = NULL,
+		.blit = &cik_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &cik_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2442,27 +2441,48 @@ int radeon_asic_init(struct radeon_device *rdev)
 		}
 		break;
 	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
 		rdev->asic = &ci_asic;
 		rdev->num_crtc = 6;
 		rdev->has_uvd = true;
-		rdev->cg_flags =
-			RADEON_CG_SUPPORT_GFX_MGCG |
-			RADEON_CG_SUPPORT_GFX_MGLS |
-			/*RADEON_CG_SUPPORT_GFX_CGCG |*/
-			RADEON_CG_SUPPORT_GFX_CGLS |
-			RADEON_CG_SUPPORT_GFX_CGTS |
-			RADEON_CG_SUPPORT_GFX_CGTS_LS |
-			RADEON_CG_SUPPORT_GFX_CP_LS |
-			RADEON_CG_SUPPORT_MC_LS |
-			RADEON_CG_SUPPORT_MC_MGCG |
-			RADEON_CG_SUPPORT_SDMA_MGCG |
-			RADEON_CG_SUPPORT_SDMA_LS |
-			RADEON_CG_SUPPORT_BIF_LS |
-			RADEON_CG_SUPPORT_VCE_MGCG |
-			RADEON_CG_SUPPORT_UVD_MGCG |
-			RADEON_CG_SUPPORT_HDP_LS |
-			RADEON_CG_SUPPORT_HDP_MGCG;
-		rdev->pg_flags = 0;
+		if (rdev->family == CHIP_BONAIRE) {
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CGTS_LS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_MC_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_SDMA_LS |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+		} else {
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_MC_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_SDMA_LS |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+		}
 		break;
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 70c29d5e080..c9fd97b5807 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -80,7 +80,7 @@ int r100_irq_set(struct radeon_device *rdev);
 int r100_irq_process(struct radeon_device *rdev);
 void r100_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence);
-void r100_semaphore_ring_emit(struct radeon_device *rdev,
+bool r100_semaphore_ring_emit(struct radeon_device *rdev,
 			      struct radeon_ring *cp,
 			      struct radeon_semaphore *semaphore,
 			      bool emit_wait);
@@ -313,13 +313,13 @@ int r600_cs_parse(struct radeon_cs_parser *p);
 int r600_dma_cs_parse(struct radeon_cs_parser *p);
 void r600_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence);
-void r600_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_semaphore_ring_emit(struct radeon_device *rdev,
 			      struct radeon_ring *cp,
 			      struct radeon_semaphore *semaphore,
 			      bool emit_wait);
 void r600_dma_fence_ring_emit(struct radeon_device *rdev,
 			      struct radeon_fence *fence);
-void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
 				  struct radeon_ring *ring,
 				  struct radeon_semaphore *semaphore,
 				  bool emit_wait);
@@ -566,10 +566,6 @@ int sumo_dpm_force_performance_level(struct radeon_device *rdev,
  */
 void cayman_fence_ring_emit(struct radeon_device *rdev,
 			    struct radeon_fence *fence);
-void cayman_uvd_semaphore_emit(struct radeon_device *rdev,
-			       struct radeon_ring *ring,
-			       struct radeon_semaphore *semaphore,
-			       bool emit_wait);
 void cayman_pcie_gart_tlb_flush(struct radeon_device *rdev);
 int cayman_init(struct radeon_device *rdev);
 void cayman_fini(struct radeon_device *rdev);
@@ -581,17 +577,18 @@ int cayman_vm_init(struct radeon_device *rdev);
 void cayman_vm_fini(struct radeon_device *rdev);
 void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags);
-void cayman_vm_set_page(struct radeon_device *rdev,
-			struct radeon_ib *ib,
-			uint64_t pe,
-			uint64_t addr, unsigned count,
-			uint32_t incr, uint32_t flags);
 int evergreen_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 void cayman_dma_ring_ib_execute(struct radeon_device *rdev,
 				struct radeon_ib *ib);
 bool cayman_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
 bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
+void cayman_dma_vm_set_page(struct radeon_device *rdev,
+			    struct radeon_ib *ib,
+			    uint64_t pe,
+			    uint64_t addr, unsigned count,
+			    uint32_t incr, uint32_t flags);
+
 void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 
 int ni_dpm_init(struct radeon_device *rdev);
@@ -653,17 +650,17 @@ int si_irq_set(struct radeon_device *rdev);
 int si_irq_process(struct radeon_device *rdev);
 int si_vm_init(struct radeon_device *rdev);
 void si_vm_fini(struct radeon_device *rdev);
-void si_vm_set_page(struct radeon_device *rdev,
-		    struct radeon_ib *ib,
-		    uint64_t pe,
-		    uint64_t addr, unsigned count,
-		    uint32_t incr, uint32_t flags);
 void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 int si_copy_dma(struct radeon_device *rdev,
 		uint64_t src_offset, uint64_t dst_offset,
 		unsigned num_gpu_pages,
 		struct radeon_fence **fence);
+void si_dma_vm_set_page(struct radeon_device *rdev,
+			struct radeon_ib *ib,
+			uint64_t pe,
+			uint64_t addr, unsigned count,
+			uint32_t incr, uint32_t flags);
 void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 u32 si_get_xclk(struct radeon_device *rdev);
 uint64_t si_get_gpu_clock_counter(struct radeon_device *rdev);
@@ -696,7 +693,7 @@ void cik_pciep_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int cik_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
 void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
 			      struct radeon_fence *fence);
-void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
 				  struct radeon_ring *ring,
 				  struct radeon_semaphore *semaphore,
 				  bool emit_wait);
@@ -705,6 +702,10 @@ int cik_copy_dma(struct radeon_device *rdev,
 		 uint64_t src_offset, uint64_t dst_offset,
 		 unsigned num_gpu_pages,
 		 struct radeon_fence **fence);
+int cik_copy_cpdma(struct radeon_device *rdev,
+		   uint64_t src_offset, uint64_t dst_offset,
+		   unsigned num_gpu_pages,
+		   struct radeon_fence **fence);
 int cik_sdma_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
 int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 bool cik_sdma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
@@ -712,7 +713,7 @@ void cik_fence_gfx_ring_emit(struct radeon_device *rdev,
 			     struct radeon_fence *fence);
 void cik_fence_compute_ring_emit(struct radeon_device *rdev,
 				 struct radeon_fence *fence);
-void cik_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 			     struct radeon_ring *cp,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait);
@@ -731,11 +732,11 @@ int cik_irq_process(struct radeon_device *rdev);
 int cik_vm_init(struct radeon_device *rdev);
 void cik_vm_fini(struct radeon_device *rdev);
 void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
-void cik_vm_set_page(struct radeon_device *rdev,
-		     struct radeon_ib *ib,
-		     uint64_t pe,
-		     uint64_t addr, unsigned count,
-		     uint32_t incr, uint32_t flags);
+void cik_sdma_vm_set_page(struct radeon_device *rdev,
+			  struct radeon_ib *ib,
+			  uint64_t pe,
+			  uint64_t addr, unsigned count,
+			  uint32_t incr, uint32_t flags);
 void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 int cik_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 u32 cik_compute_ring_get_rptr(struct radeon_device *rdev,
@@ -802,7 +803,7 @@ void uvd_v1_0_stop(struct radeon_device *rdev);
 
 int uvd_v1_0_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
 int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
-void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait);
@@ -814,7 +815,7 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev,
 			 struct radeon_fence *fence);
 
 /* uvd v3.1 */
-void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait);
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index f79ee184ffd..5c39bf7c3d8 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -2918,7 +2918,7 @@ int radeon_atom_get_memory_pll_dividers(struct radeon_device *rdev,
 			mpll_param->dll_speed = args.ucDllSpeed;
 			mpll_param->bwcntl = args.ucBWCntl;
 			mpll_param->vco_mode =
-				(args.ucPllCntlFlag & MPLL_CNTL_FLAG_VCO_MODE_MASK) ? 1 : 0;
+				(args.ucPllCntlFlag & MPLL_CNTL_FLAG_VCO_MODE_MASK);
 			mpll_param->yclk_sel =
 				(args.ucPllCntlFlag & MPLL_CNTL_FLAG_BYPASS_DQ_PLL) ? 1 : 0;
 			mpll_param->qdr =
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index d96070bf838..485848f889f 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -8,8 +8,7 @@
  */
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
-#include <acpi/acpi.h>
-#include <acpi/acpi_bus.h>
+#include <linux/acpi.h>
 #include <linux/pci.h>
 
 #include "radeon_acpi.h"
@@ -34,6 +33,7 @@ static struct radeon_atpx_priv {
 	bool atpx_detected;
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
+	acpi_handle other_handle;
 	struct radeon_atpx atpx;
 } radeon_atpx_priv;
 
@@ -59,6 +59,10 @@ struct atpx_mux {
 	u16 mux;
 } __packed;
 
+bool radeon_is_px(void) {
+	return radeon_atpx_priv.atpx_detected;
+}
+
 /**
  * radeon_atpx_call - call an ATPX method
  *
@@ -443,14 +447,15 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 	acpi_handle dhandle, atpx_handle;
 	acpi_status status;
 
-	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
 
 	status = acpi_get_handle(dhandle, "ATPX", &atpx_handle);
-	if (ACPI_FAILURE(status))
+	if (ACPI_FAILURE(status)) {
+		radeon_atpx_priv.other_handle = dhandle;
 		return false;
-
+	}
 	radeon_atpx_priv.dhandle = dhandle;
 	radeon_atpx_priv.atpx.handle = atpx_handle;
 	return true;
@@ -489,7 +494,7 @@ static int radeon_atpx_init(void)
  */
 static int radeon_atpx_get_client_id(struct pci_dev *pdev)
 {
-	if (radeon_atpx_priv.dhandle == DEVICE_ACPI_HANDLE(&pdev->dev))
+	if (radeon_atpx_priv.dhandle == ACPI_HANDLE(&pdev->dev))
 		return VGA_SWITCHEROO_IGD;
 	else
 		return VGA_SWITCHEROO_DIS;
@@ -527,6 +532,16 @@ static bool radeon_atpx_detect(void)
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		radeon_atpx_priv.atpx_detected = true;
+		/*
+		 * On some systems hotplug events are generated for the device
+		 * being switched off when ATPX is executed.  They cause ACPI
+		 * hotplug to trigger and attempt to remove the device from
+		 * the system, which causes it to break down.  Prevent that from
+		 * happening by setting the no_hotplug flag for the involved
+		 * ACPI device objects.
+		 */
+		acpi_bus_no_hotplug(radeon_atpx_priv.dhandle);
+		acpi_bus_no_hotplug(radeon_atpx_priv.other_handle);
 		return true;
 	}
 	return false;
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 061b227dae0..b3633d9a531 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -185,7 +185,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 		return false;
 
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
-		dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+		dhandle = ACPI_HANDLE(&pdev->dev);
 		if (!dhandle)
 			continue;
 
@@ -499,7 +499,7 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev)
 	crtc_ext_cntl = RREG32(RADEON_CRTC_EXT_CNTL);
 	fp2_gen_cntl = 0;
 
-	if (rdev->ddev->pci_device == PCI_DEVICE_ID_ATI_RADEON_QY) {
+	if (rdev->ddev->pdev->device == PCI_DEVICE_ID_ATI_RADEON_QY) {
 		fp2_gen_cntl = RREG32(RADEON_FP2_GEN_CNTL);
 	}
 
@@ -536,7 +536,7 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev)
 		(RADEON_CRTC_SYNC_TRISTAT |
 		 RADEON_CRTC_DISPLAY_DIS)));
 
-	if (rdev->ddev->pci_device == PCI_DEVICE_ID_ATI_RADEON_QY) {
+	if (rdev->ddev->pdev->device == PCI_DEVICE_ID_ATI_RADEON_QY) {
 		WREG32(RADEON_FP2_GEN_CNTL, (fp2_gen_cntl & ~RADEON_FP2_ON));
 	}
 
@@ -554,7 +554,7 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev)
 		WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl);
 	}
 	WREG32(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl);
-	if (rdev->ddev->pci_device == PCI_DEVICE_ID_ATI_RADEON_QY) {
+	if (rdev->ddev->pdev->device == PCI_DEVICE_ID_ATI_RADEON_QY) {
 		WREG32(RADEON_FP2_GEN_CNTL, fp2_gen_cntl);
 	}
 	return r;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 64565732cb9..20a768ac89a 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -31,6 +31,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+#include <linux/pm_runtime.h>
+
 extern void
 radeon_combios_connected_scratch_regs(struct drm_connector *connector,
 				      struct drm_encoder *encoder,
@@ -411,6 +413,21 @@ static int radeon_connector_set_property(struct drm_connector *connector, struct
 		}
 	}
 
+	if (property == rdev->mode_info.dither_property) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		/* need to find digital encoder on connector */
+		encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS);
+		if (!encoder)
+			return 0;
+
+		radeon_encoder = to_radeon_encoder(encoder);
+
+		if (radeon_connector->dither != val) {
+			radeon_connector->dither = val;
+			radeon_property_change_mode(&radeon_encoder->base);
+		}
+	}
+
 	if (property == rdev->mode_info.underscan_property) {
 		/* need to find digital encoder on connector */
 		encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS);
@@ -626,6 +643,11 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
 	enum drm_connector_status ret = connector_status_disconnected;
+	int r;
+
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
 
 	if (encoder) {
 		struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
@@ -651,6 +673,8 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 	/* check acpi lid status ??? */
 
 	radeon_connector_update_scratch_regs(connector, ret);
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
 	return ret;
 }
 
@@ -750,6 +774,11 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder_helper_funcs *encoder_funcs;
 	bool dret = false;
 	enum drm_connector_status ret = connector_status_disconnected;
+	int r;
+
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
 
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)
@@ -790,9 +819,8 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 			 * detected a monitor via load.
 			 */
 			if (radeon_connector->detected_by_load)
-				return connector->status;
-			else
-				return ret;
+				ret = connector->status;
+			goto out;
 		}
 
 		if (radeon_connector->dac_load_detect && encoder) {
@@ -817,6 +845,11 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	}
 
 	radeon_connector_update_scratch_regs(connector, ret);
+
+out:
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
 	return ret;
 }
 
@@ -873,10 +906,15 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	enum drm_connector_status ret = connector_status_disconnected;
+	int r;
 
 	if (!radeon_connector->dac_load_detect)
 		return ret;
 
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
+
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)
 		ret = connector_status_disconnected;
@@ -887,6 +925,8 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	if (ret == connector_status_connected)
 		ret = radeon_connector_analog_encoder_conflict_solve(connector, encoder, ret, false);
 	radeon_connector_update_scratch_regs(connector, ret);
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
 	return ret;
 }
 
@@ -954,12 +994,18 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder *encoder = NULL;
 	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct drm_mode_object *obj;
-	int i;
+	int i, r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	if (!force && radeon_check_hpd_status_unchanged(connector))
-		return connector->status;
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
+
+	if (!force && radeon_check_hpd_status_unchanged(connector)) {
+		ret = connector->status;
+		goto exit;
+	}
 
 	if (radeon_connector->ddc_bus)
 		dret = radeon_ddc_probe(radeon_connector, false);
@@ -1110,6 +1156,11 @@ out:
 
 	/* updated in get modes as well since we need to know if it's analog or digital */
 	radeon_connector_update_scratch_regs(connector, ret);
+
+exit:
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
 	return ret;
 }
 
@@ -1377,9 +1428,16 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
 	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
+	int r;
 
-	if (!force && radeon_check_hpd_status_unchanged(connector))
-		return connector->status;
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
+
+	if (!force && radeon_check_hpd_status_unchanged(connector)) {
+		ret = connector->status;
+		goto out;
+	}
 
 	if (radeon_connector->edid) {
 		kfree(radeon_connector->edid);
@@ -1443,6 +1501,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	}
 
 	radeon_connector_update_scratch_regs(connector, ret);
+out:
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
 	return ret;
 }
 
@@ -1658,12 +1720,16 @@ 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.dither_property,
+						   RADEON_FMT_DITHER_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);
+							   RADEON_AUDIO_AUTO);
+
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
 			if (connector_type == DRM_MODE_CONNECTOR_HDMIB)
@@ -1760,9 +1826,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 			if (ASIC_IS_DCE2(rdev) && (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);
+							   RADEON_AUDIO_AUTO);
+			}
+			if (ASIC_IS_AVIVO(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.dither_property,
+							   RADEON_FMT_DITHER_DISABLE);
 			}
 			if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 				radeon_connector->dac_load_detect = true;
@@ -1807,9 +1876,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 			if (ASIC_IS_DCE2(rdev) && (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);
+							   RADEON_AUDIO_AUTO);
+			}
+			if (ASIC_IS_AVIVO(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.dither_property,
+							   RADEON_FMT_DITHER_DISABLE);
 			}
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
@@ -1853,9 +1925,13 @@ radeon_add_atom_connector(struct drm_device *dev,
 			if (ASIC_IS_DCE2(rdev) && (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);
+							   RADEON_AUDIO_AUTO);
+			}
+			if (ASIC_IS_AVIVO(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.dither_property,
+							   RADEON_FMT_DITHER_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 80285e35bc6..0b366169d64 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -159,7 +159,8 @@ static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 		if (!p->relocs[i].robj)
 			continue;
 
-		radeon_ib_sync_to(&p->ib, p->relocs[i].robj->tbo.sync_obj);
+		radeon_semaphore_sync_to(p->ib.semaphore,
+					 p->relocs[i].robj->tbo.sync_obj);
 	}
 }
 
@@ -212,9 +213,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			return -EFAULT;
 		}
 		p->chunks[i].length_dw = user_chunk.length_dw;
-		p->chunks[i].kdata = NULL;
 		p->chunks[i].chunk_id = user_chunk.chunk_id;
-		p->chunks[i].user_ptr = (void __user *)(unsigned long)user_chunk.chunk_data;
 		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_RELOCS) {
 			p->chunk_relocs_idx = i;
 		}
@@ -237,25 +236,31 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 				return -EINVAL;
 		}
 
-		cdata = (uint32_t *)(unsigned long)user_chunk.chunk_data;
-		if ((p->chunks[i].chunk_id == RADEON_CHUNK_ID_RELOCS) ||
-		    (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS)) {
-			size = p->chunks[i].length_dw * sizeof(uint32_t);
-			p->chunks[i].kdata = kmalloc(size, GFP_KERNEL);
-			if (p->chunks[i].kdata == NULL) {
-				return -ENOMEM;
-			}
-			if (DRM_COPY_FROM_USER(p->chunks[i].kdata,
-					       p->chunks[i].user_ptr, size)) {
-				return -EFAULT;
-			}
-			if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
-				p->cs_flags = p->chunks[i].kdata[0];
-				if (p->chunks[i].length_dw > 1)
-					ring = p->chunks[i].kdata[1];
-				if (p->chunks[i].length_dw > 2)
-					priority = (s32)p->chunks[i].kdata[2];
-			}
+		size = p->chunks[i].length_dw;
+		cdata = (void __user *)(unsigned long)user_chunk.chunk_data;
+		p->chunks[i].user_ptr = cdata;
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_CONST_IB)
+			continue;
+
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_IB) {
+			if (!p->rdev || !(p->rdev->flags & RADEON_IS_AGP))
+				continue;
+		}
+
+		p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t));
+		size *= sizeof(uint32_t);
+		if (p->chunks[i].kdata == NULL) {
+			return -ENOMEM;
+		}
+		if (DRM_COPY_FROM_USER(p->chunks[i].kdata, cdata, size)) {
+			return -EFAULT;
+		}
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
+			p->cs_flags = p->chunks[i].kdata[0];
+			if (p->chunks[i].length_dw > 1)
+				ring = p->chunks[i].kdata[1];
+			if (p->chunks[i].length_dw > 2)
+				priority = (s32)p->chunks[i].kdata[2];
 		}
 	}
 
@@ -278,34 +283,6 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 		}
 	}
 
-	/* deal with non-vm */
-	if ((p->chunk_ib_idx != -1) &&
-	    ((p->cs_flags & RADEON_CS_USE_VM) == 0) &&
-	    (p->chunks[p->chunk_ib_idx].chunk_id == RADEON_CHUNK_ID_IB)) {
-		if (p->chunks[p->chunk_ib_idx].length_dw > (16 * 1024)) {
-			DRM_ERROR("cs IB too big: %d\n",
-				  p->chunks[p->chunk_ib_idx].length_dw);
-			return -EINVAL;
-		}
-		if (p->rdev && (p->rdev->flags & RADEON_IS_AGP)) {
-			p->chunks[p->chunk_ib_idx].kpage[0] = kmalloc(PAGE_SIZE, GFP_KERNEL);
-			p->chunks[p->chunk_ib_idx].kpage[1] = kmalloc(PAGE_SIZE, GFP_KERNEL);
-			if (p->chunks[p->chunk_ib_idx].kpage[0] == NULL ||
-			    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;
-			}
-		}
-		p->chunks[p->chunk_ib_idx].kpage_idx[0] = -1;
-		p->chunks[p->chunk_ib_idx].kpage_idx[1] = -1;
-		p->chunks[p->chunk_ib_idx].last_copied_page = -1;
-		p->chunks[p->chunk_ib_idx].last_page_index =
-			((p->chunks[p->chunk_ib_idx].length_dw * 4) - 1) / PAGE_SIZE;
-	}
-
 	return 0;
 }
 
@@ -339,13 +316,8 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
 	kfree(parser->track);
 	kfree(parser->relocs);
 	kfree(parser->relocs_ptr);
-	for (i = 0; i < parser->nchunks; i++) {
-		kfree(parser->chunks[i].kdata);
-		if ((parser->rdev->flags & RADEON_IS_AGP)) {
-			kfree(parser->chunks[i].kpage[0]);
-			kfree(parser->chunks[i].kpage[1]);
-		}
-	}
+	for (i = 0; i < parser->nchunks; i++)
+		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
 	kfree(parser->chunks_array);
 	radeon_ib_free(parser->rdev, &parser->ib);
@@ -355,7 +327,6 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
 static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 			      struct radeon_cs_parser *parser)
 {
-	struct radeon_cs_chunk *ib_chunk;
 	int r;
 
 	if (parser->chunk_ib_idx == -1)
@@ -364,28 +335,11 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 	if (parser->cs_flags & RADEON_CS_USE_VM)
 		return 0;
 
-	ib_chunk = &parser->chunks[parser->chunk_ib_idx];
-	/* Copy the packet into the IB, the parser will read from the
-	 * input memory (cached) and write to the IB (which can be
-	 * uncached).
-	 */
-	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
-			   NULL, ib_chunk->length_dw * 4);
-	if (r) {
-		DRM_ERROR("Failed to get ib !\n");
-		return r;
-	}
-	parser->ib.length_dw = ib_chunk->length_dw;
 	r = radeon_cs_parse(rdev, parser->ring, parser);
 	if (r || parser->parser_error) {
 		DRM_ERROR("Invalid command stream !\n");
 		return r;
 	}
-	r = radeon_cs_finish_pages(parser);
-	if (r) {
-		DRM_ERROR("Invalid command stream !\n");
-		return r;
-	}
 
 	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
 		radeon_uvd_note_usage(rdev);
@@ -406,13 +360,13 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
 	struct radeon_bo *bo;
 	int r;
 
-	r = radeon_vm_bo_update_pte(rdev, vm, rdev->ring_tmp_bo.bo, &rdev->ring_tmp_bo.bo->tbo.mem);
+	r = radeon_vm_bo_update(rdev, vm, rdev->ring_tmp_bo.bo, &rdev->ring_tmp_bo.bo->tbo.mem);
 	if (r) {
 		return r;
 	}
 	list_for_each_entry(lobj, &parser->validated, tv.head) {
 		bo = lobj->bo;
-		r = radeon_vm_bo_update_pte(parser->rdev, vm, bo, &bo->tbo.mem);
+		r = radeon_vm_bo_update(parser->rdev, vm, bo, &bo->tbo.mem);
 		if (r) {
 			return r;
 		}
@@ -423,7 +377,6 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
 static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 				 struct radeon_cs_parser *parser)
 {
-	struct radeon_cs_chunk *ib_chunk;
 	struct radeon_fpriv *fpriv = parser->filp->driver_priv;
 	struct radeon_vm *vm = &fpriv->vm;
 	int r;
@@ -433,49 +386,13 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0)
 		return 0;
 
-	if ((rdev->family >= CHIP_TAHITI) &&
-	    (parser->chunk_const_ib_idx != -1)) {
-		ib_chunk = &parser->chunks[parser->chunk_const_ib_idx];
-		if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
-			DRM_ERROR("cs IB CONST too big: %d\n", ib_chunk->length_dw);
-			return -EINVAL;
-		}
-		r =  radeon_ib_get(rdev, parser->ring, &parser->const_ib,
-				   vm, ib_chunk->length_dw * 4);
-		if (r) {
-			DRM_ERROR("Failed to get const ib !\n");
-			return r;
-		}
-		parser->const_ib.is_const_ib = true;
-		parser->const_ib.length_dw = ib_chunk->length_dw;
-		/* Copy the packet into the IB */
-		if (DRM_COPY_FROM_USER(parser->const_ib.ptr, ib_chunk->user_ptr,
-				       ib_chunk->length_dw * 4)) {
-			return -EFAULT;
-		}
+	if (parser->const_ib.length_dw) {
 		r = radeon_ring_ib_parse(rdev, parser->ring, &parser->const_ib);
 		if (r) {
 			return r;
 		}
 	}
 
-	ib_chunk = &parser->chunks[parser->chunk_ib_idx];
-	if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
-		DRM_ERROR("cs IB too big: %d\n", ib_chunk->length_dw);
-		return -EINVAL;
-	}
-	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
-			   vm, ib_chunk->length_dw * 4);
-	if (r) {
-		DRM_ERROR("Failed to get ib !\n");
-		return r;
-	}
-	parser->ib.length_dw = ib_chunk->length_dw;
-	/* Copy the packet into the IB */
-	if (DRM_COPY_FROM_USER(parser->ib.ptr, ib_chunk->user_ptr,
-			       ib_chunk->length_dw * 4)) {
-		return -EFAULT;
-	}
 	r = radeon_ring_ib_parse(rdev, parser->ring, &parser->ib);
 	if (r) {
 		return r;
@@ -495,9 +412,9 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		goto out;
 	}
 	radeon_cs_sync_rings(parser);
-	radeon_ib_sync_to(&parser->ib, vm->fence);
-	radeon_ib_sync_to(&parser->ib, radeon_vm_grab_id(
-		rdev, vm, parser->ring));
+	radeon_semaphore_sync_to(parser->ib.semaphore, vm->fence);
+	radeon_semaphore_sync_to(parser->ib.semaphore,
+				 radeon_vm_grab_id(rdev, vm, parser->ring));
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
@@ -527,6 +444,62 @@ static int radeon_cs_handle_lockup(struct radeon_device *rdev, int r)
 	return r;
 }
 
+static int radeon_cs_ib_fill(struct radeon_device *rdev, struct radeon_cs_parser *parser)
+{
+	struct radeon_cs_chunk *ib_chunk;
+	struct radeon_vm *vm = NULL;
+	int r;
+
+	if (parser->chunk_ib_idx == -1)
+		return 0;
+
+	if (parser->cs_flags & RADEON_CS_USE_VM) {
+		struct radeon_fpriv *fpriv = parser->filp->driver_priv;
+		vm = &fpriv->vm;
+
+		if ((rdev->family >= CHIP_TAHITI) &&
+		    (parser->chunk_const_ib_idx != -1)) {
+			ib_chunk = &parser->chunks[parser->chunk_const_ib_idx];
+			if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
+				DRM_ERROR("cs IB CONST too big: %d\n", ib_chunk->length_dw);
+				return -EINVAL;
+			}
+			r =  radeon_ib_get(rdev, parser->ring, &parser->const_ib,
+					   vm, ib_chunk->length_dw * 4);
+			if (r) {
+				DRM_ERROR("Failed to get const ib !\n");
+				return r;
+			}
+			parser->const_ib.is_const_ib = true;
+			parser->const_ib.length_dw = ib_chunk->length_dw;
+			if (DRM_COPY_FROM_USER(parser->const_ib.ptr,
+					       ib_chunk->user_ptr,
+					       ib_chunk->length_dw * 4))
+				return -EFAULT;
+		}
+
+		ib_chunk = &parser->chunks[parser->chunk_ib_idx];
+		if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
+			DRM_ERROR("cs IB too big: %d\n", ib_chunk->length_dw);
+			return -EINVAL;
+		}
+	}
+	ib_chunk = &parser->chunks[parser->chunk_ib_idx];
+
+	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
+			   vm, ib_chunk->length_dw * 4);
+	if (r) {
+		DRM_ERROR("Failed to get ib !\n");
+		return r;
+	}
+	parser->ib.length_dw = ib_chunk->length_dw;
+	if (ib_chunk->kdata)
+		memcpy(parser->ib.ptr, ib_chunk->kdata, ib_chunk->length_dw * 4);
+	else if (DRM_COPY_FROM_USER(parser->ib.ptr, ib_chunk->user_ptr, ib_chunk->length_dw * 4))
+		return -EFAULT;
+	return 0;
+}
+
 int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct radeon_device *rdev = dev->dev_private;
@@ -552,10 +525,15 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		r = radeon_cs_handle_lockup(rdev, r);
 		return r;
 	}
-	r = radeon_cs_parser_relocs(&parser);
-	if (r) {
-		if (r != -ERESTARTSYS)
+
+	r = radeon_cs_ib_fill(rdev, &parser);
+	if (!r) {
+		r = radeon_cs_parser_relocs(&parser);
+		if (r && r != -ERESTARTSYS)
 			DRM_ERROR("Failed to parse relocation %d!\n", r);
+	}
+
+	if (r) {
 		radeon_cs_parser_fini(&parser, r, false);
 		up_read(&rdev->exclusive_lock);
 		r = radeon_cs_handle_lockup(rdev, r);
@@ -579,97 +557,6 @@ out:
 	return r;
 }
 
-int radeon_cs_finish_pages(struct radeon_cs_parser *p)
-{
-	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
-	int i;
-	int size = PAGE_SIZE;
-
-	for (i = ibc->last_copied_page + 1; i <= ibc->last_page_index; i++) {
-		if (i == ibc->last_page_index) {
-			size = (ibc->length_dw * 4) % PAGE_SIZE;
-			if (size == 0)
-				size = PAGE_SIZE;
-		}
-		
-		if (DRM_COPY_FROM_USER(p->ib.ptr + (i * (PAGE_SIZE/4)),
-				       ibc->user_ptr + (i * PAGE_SIZE),
-				       size))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-static int radeon_cs_update_pages(struct radeon_cs_parser *p, int pg_idx)
-{
-	int new_page;
-	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
-	int i;
-	int size = PAGE_SIZE;
-	bool copy1 = (p->rdev && (p->rdev->flags & RADEON_IS_AGP)) ?
-		false : true;
-
-	for (i = ibc->last_copied_page + 1; i < pg_idx; i++) {
-		if (DRM_COPY_FROM_USER(p->ib.ptr + (i * (PAGE_SIZE/4)),
-				       ibc->user_ptr + (i * PAGE_SIZE),
-				       PAGE_SIZE)) {
-			p->parser_error = -EFAULT;
-			return 0;
-		}
-	}
-
-	if (pg_idx == ibc->last_page_index) {
-		size = (ibc->length_dw * 4) % PAGE_SIZE;
-		if (size == 0)
-			size = PAGE_SIZE;
-	}
-
-	new_page = ibc->kpage_idx[0] < ibc->kpage_idx[1] ? 0 : 1;
-	if (copy1)
-		ibc->kpage[new_page] = p->ib.ptr + (pg_idx * (PAGE_SIZE / 4));
-
-	if (DRM_COPY_FROM_USER(ibc->kpage[new_page],
-			       ibc->user_ptr + (pg_idx * PAGE_SIZE),
-			       size)) {
-		p->parser_error = -EFAULT;
-		return 0;
-	}
-
-	/* copy to IB for non single case */
-	if (!copy1)
-		memcpy((void *)(p->ib.ptr+(pg_idx*(PAGE_SIZE/4))), ibc->kpage[new_page], size);
-
-	ibc->last_copied_page = pg_idx;
-	ibc->kpage_idx[new_page] = pg_idx;
-
-	return new_page;
-}
-
-u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
-{
-	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
-	u32 pg_idx, pg_offset;
-	u32 idx_value = 0;
-	int new_page;
-
-	pg_idx = (idx * 4) / PAGE_SIZE;
-	pg_offset = (idx * 4) % PAGE_SIZE;
-
-	if (ibc->kpage_idx[0] == pg_idx)
-		return ibc->kpage[0][pg_offset/4];
-	if (ibc->kpage_idx[1] == pg_idx)
-		return ibc->kpage[1][pg_offset/4];
-
-	new_page = radeon_cs_update_pages(p, pg_idx);
-	if (new_page < 0) {
-		p->parser_error = new_page;
-		return 0;
-	}
-
-	idx_value = ibc->kpage[new_page][pg_offset/4];
-	return idx_value;
-}
-
 /**
  * radeon_cs_packet_parse() - parse cp packet and point ib index to next packet
  * @parser:	parser structure holding parsing context.
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 841d0e09be3..39b033b441d 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -98,9 +98,16 @@ static const char radeon_family_name[][16] = {
 	"BONAIRE",
 	"KAVERI",
 	"KABINI",
+	"HAWAII",
 	"LAST",
 };
 
+#if defined(CONFIG_VGA_SWITCHEROO)
+bool radeon_is_px(void);
+#else
+static inline bool radeon_is_px(void) { return false; }
+#endif
+
 /**
  * radeon_program_register_sequence - program an array of registers.
  *
@@ -244,28 +251,23 @@ void radeon_scratch_free(struct radeon_device *rdev, uint32_t reg)
  */
 int radeon_doorbell_init(struct radeon_device *rdev)
 {
-	int i;
-
 	/* doorbell bar mapping */
 	rdev->doorbell.base = pci_resource_start(rdev->pdev, 2);
 	rdev->doorbell.size = pci_resource_len(rdev->pdev, 2);
 
-	/* limit to 4 MB for now */
-	if (rdev->doorbell.size > (4 * 1024 * 1024))
-		rdev->doorbell.size = 4 * 1024 * 1024;
+	rdev->doorbell.num_doorbells = min_t(u32, rdev->doorbell.size / sizeof(u32), RADEON_MAX_DOORBELLS);
+	if (rdev->doorbell.num_doorbells == 0)
+		return -EINVAL;
 
-	rdev->doorbell.ptr = ioremap(rdev->doorbell.base, rdev->doorbell.size);
+	rdev->doorbell.ptr = ioremap(rdev->doorbell.base, rdev->doorbell.num_doorbells * sizeof(u32));
 	if (rdev->doorbell.ptr == NULL) {
 		return -ENOMEM;
 	}
 	DRM_INFO("doorbell mmio base: 0x%08X\n", (uint32_t)rdev->doorbell.base);
 	DRM_INFO("doorbell mmio size: %u\n", (unsigned)rdev->doorbell.size);
 
-	rdev->doorbell.num_pages = rdev->doorbell.size / PAGE_SIZE;
+	memset(&rdev->doorbell.used, 0, sizeof(rdev->doorbell.used));
 
-	for (i = 0; i < rdev->doorbell.num_pages; i++) {
-		rdev->doorbell.free[i] = true;
-	}
 	return 0;
 }
 
@@ -283,40 +285,38 @@ void radeon_doorbell_fini(struct radeon_device *rdev)
 }
 
 /**
- * radeon_doorbell_get - Allocate a doorbell page
+ * radeon_doorbell_get - Allocate a doorbell entry
  *
  * @rdev: radeon_device pointer
- * @doorbell: doorbell page number
+ * @doorbell: doorbell index
  *
- * Allocate a doorbell page for use by the driver (all asics).
+ * Allocate a doorbell for use by the driver (all asics).
  * Returns 0 on success or -EINVAL on failure.
  */
 int radeon_doorbell_get(struct radeon_device *rdev, u32 *doorbell)
 {
-	int i;
-
-	for (i = 0; i < rdev->doorbell.num_pages; i++) {
-		if (rdev->doorbell.free[i]) {
-			rdev->doorbell.free[i] = false;
-			*doorbell = i;
-			return 0;
-		}
+	unsigned long offset = find_first_zero_bit(rdev->doorbell.used, rdev->doorbell.num_doorbells);
+	if (offset < rdev->doorbell.num_doorbells) {
+		__set_bit(offset, rdev->doorbell.used);
+		*doorbell = offset;
+		return 0;
+	} else {
+		return -EINVAL;
 	}
-	return -EINVAL;
 }
 
 /**
- * radeon_doorbell_free - Free a doorbell page
+ * radeon_doorbell_free - Free a doorbell entry
  *
  * @rdev: radeon_device pointer
- * @doorbell: doorbell page number
+ * @doorbell: doorbell index
  *
- * Free a doorbell page allocated for use by the driver (all asics)
+ * Free a doorbell allocated for use by the driver (all asics)
  */
 void radeon_doorbell_free(struct radeon_device *rdev, u32 doorbell)
 {
-	if (doorbell < rdev->doorbell.num_pages)
-		rdev->doorbell.free[doorbell] = true;
+	if (doorbell < rdev->doorbell.num_doorbells)
+		__clear_bit(doorbell, rdev->doorbell.used);
 }
 
 /*
@@ -1076,7 +1076,10 @@ static bool radeon_switcheroo_quirk_long_wakeup(struct pci_dev *pdev)
 static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
+
+	if (radeon_is_px() && state == VGA_SWITCHEROO_OFF)
+		return;
+
 	if (state == VGA_SWITCHEROO_ON) {
 		unsigned d3_delay = dev->pdev->d3_delay;
 
@@ -1087,7 +1090,7 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		if (d3_delay < 20 && radeon_switcheroo_quirk_long_wakeup(pdev))
 			dev->pdev->d3_delay = 20;
 
-		radeon_resume_kms(dev);
+		radeon_resume_kms(dev, true, true);
 
 		dev->pdev->d3_delay = d3_delay;
 
@@ -1097,7 +1100,7 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		printk(KERN_INFO "radeon: switched off\n");
 		drm_kms_helper_poll_disable(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		radeon_suspend_kms(dev, pmm);
+		radeon_suspend_kms(dev, true, true);
 		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
 	}
 }
@@ -1147,6 +1150,7 @@ int radeon_device_init(struct radeon_device *rdev,
 {
 	int r, i;
 	int dma_bits;
+	bool runtime = false;
 
 	rdev->shutdown = false;
 	rdev->dev = &pdev->dev;
@@ -1293,7 +1297,14 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
 	vga_client_register(rdev->pdev, rdev, NULL, radeon_vga_set_decode);
-	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, false);
+
+	if (radeon_runtime_pm == 1)
+		runtime = true;
+	if ((radeon_runtime_pm == -1) && radeon_is_px())
+		runtime = true;
+	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, runtime);
+	if (runtime)
+		vga_switcheroo_init_domain_pm_ops(rdev->dev, &rdev->vga_pm_domain);
 
 	r = radeon_init(rdev);
 	if (r)
@@ -1383,7 +1394,7 @@ void radeon_device_fini(struct radeon_device *rdev)
  * Returns 0 for success or an error on failure.
  * Called at driver suspend.
  */
-int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
+int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 {
 	struct radeon_device *rdev;
 	struct drm_crtc *crtc;
@@ -1394,9 +1405,7 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	if (dev == NULL || dev->dev_private == NULL) {
 		return -ENODEV;
 	}
-	if (state.event == PM_EVENT_PRETHAW) {
-		return 0;
-	}
+
 	rdev = dev->dev_private;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
@@ -1455,14 +1464,17 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	radeon_agp_suspend(rdev);
 
 	pci_save_state(dev->pdev);
-	if (state.event == PM_EVENT_SUSPEND) {
+	if (suspend) {
 		/* Shut down the device */
 		pci_disable_device(dev->pdev);
 		pci_set_power_state(dev->pdev, PCI_D3hot);
 	}
-	console_lock();
-	radeon_fbdev_set_suspend(rdev, 1);
-	console_unlock();
+
+	if (fbcon) {
+		console_lock();
+		radeon_fbdev_set_suspend(rdev, 1);
+		console_unlock();
+	}
 	return 0;
 }
 
@@ -1475,7 +1487,7 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
  * Returns 0 for success or an error on failure.
  * Called at driver resume.
  */
-int radeon_resume_kms(struct drm_device *dev)
+int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 {
 	struct drm_connector *connector;
 	struct radeon_device *rdev = dev->dev_private;
@@ -1484,12 +1496,17 @@ int radeon_resume_kms(struct drm_device *dev)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	console_lock();
-	pci_set_power_state(dev->pdev, PCI_D0);
-	pci_restore_state(dev->pdev);
-	if (pci_enable_device(dev->pdev)) {
-		console_unlock();
-		return -1;
+	if (fbcon) {
+		console_lock();
+	}
+	if (resume) {
+		pci_set_power_state(dev->pdev, PCI_D0);
+		pci_restore_state(dev->pdev);
+		if (pci_enable_device(dev->pdev)) {
+			if (fbcon)
+				console_unlock();
+			return -1;
+		}
 	}
 	/* resume AGP if in use */
 	radeon_agp_resume(rdev);
@@ -1502,9 +1519,11 @@ int radeon_resume_kms(struct drm_device *dev)
 	radeon_pm_resume(rdev);
 	radeon_restore_bios_scratch_regs(rdev);
 
-	radeon_fbdev_set_suspend(rdev, 0);
-	console_unlock();
-
+	if (fbcon) {
+		radeon_fbdev_set_suspend(rdev, 0);
+		console_unlock();
+	}
+       
 	/* init dig PHYs, disp eng pll */
 	if (rdev->is_atom_bios) {
 		radeon_atom_encoder_init(rdev);
@@ -1549,6 +1568,14 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	int resched;
 
 	down_write(&rdev->exclusive_lock);
+
+	if (!rdev->needs_reset) {
+		up_write(&rdev->exclusive_lock);
+		return 0;
+	}
+
+	rdev->needs_reset = false;
+
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 0d1aa050d41..7b253815a32 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -30,6 +30,7 @@
 #include "atom.h"
 #include <asm/div64.h>
 
+#include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
 
@@ -306,7 +307,7 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 	 */
 	if (update_pending &&
 	    (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id,
-							       &vpos, &hpos)) &&
+							       &vpos, &hpos, NULL, NULL)) &&
 	    ((vpos >= (99 * rdev->mode_info.crtcs[crtc_id]->base.hwmode.crtc_vdisplay)/100) ||
 	     (vpos < 0 && !ASIC_IS_AVIVO(rdev)))) {
 		/* crtc didn't flip in this target vblank interval,
@@ -494,11 +495,55 @@ unlock_free:
 	return r;
 }
 
+static int
+radeon_crtc_set_config(struct drm_mode_set *set)
+{
+	struct drm_device *dev;
+	struct radeon_device *rdev;
+	struct drm_crtc *crtc;
+	bool active = false;
+	int ret;
+
+	if (!set || !set->crtc)
+		return -EINVAL;
+
+	dev = set->crtc->dev;
+
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_crtc_helper_set_config(set);
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+		if (crtc->enabled)
+			active = true;
+
+	pm_runtime_mark_last_busy(dev->dev);
+
+	rdev = dev->dev_private;
+	/* if we have active crtcs and we don't have a power ref,
+	   take the current one */
+	if (active && !rdev->have_disp_power_ref) {
+		rdev->have_disp_power_ref = true;
+		return ret;
+	}
+	/* if we have no active crtcs, then drop the power ref
+	   we got before */
+	if (!active && rdev->have_disp_power_ref) {
+		pm_runtime_put_autosuspend(dev->dev);
+		rdev->have_disp_power_ref = false;
+	}
+
+	/* drop the power reference we got coming in here */
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
 static const struct drm_crtc_funcs radeon_crtc_funcs = {
 	.cursor_set = radeon_crtc_cursor_set,
 	.cursor_move = radeon_crtc_cursor_move,
 	.gamma_set = radeon_crtc_gamma_set,
-	.set_config = drm_crtc_helper_set_config,
+	.set_config = radeon_crtc_set_config,
 	.destroy = radeon_crtc_destroy,
 	.page_flip = radeon_crtc_page_flip,
 };
@@ -1178,6 +1223,12 @@ static struct drm_prop_enum_list radeon_audio_enum_list[] =
 	{ RADEON_AUDIO_AUTO, "auto" },
 };
 
+/* XXX support different dither options? spatial, temporal, both, etc. */
+static struct drm_prop_enum_list radeon_dither_enum_list[] =
+{	{ RADEON_FMT_DITHER_DISABLE, "off" },
+	{ RADEON_FMT_DITHER_ENABLE, "on" },
+};
+
 static int radeon_modeset_create_props(struct radeon_device *rdev)
 {
 	int sz;
@@ -1234,6 +1285,12 @@ static int radeon_modeset_create_props(struct radeon_device *rdev)
 					 "audio",
 					 radeon_audio_enum_list, sz);
 
+	sz = ARRAY_SIZE(radeon_dither_enum_list);
+	rdev->mode_info.dither_property =
+		drm_property_create_enum(rdev->ddev, 0,
+					 "dither",
+					 radeon_dither_enum_list, sz);
+
 	return 0;
 }
 
@@ -1539,12 +1596,17 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 }
 
 /*
- * Retrieve current video scanout position of crtc on a given gpu.
+ * Retrieve current video scanout position of crtc on a given gpu, and
+ * an optional accurate timestamp of when query happened.
  *
  * \param dev Device to query.
  * \param crtc Crtc to query.
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
+ * \param *stime Target location for timestamp taken immediately before
+ *               scanout position query. Can be NULL to skip timestamp.
+ * \param *etime Target location for timestamp taken immediately after
+ *               scanout position query. Can be NULL to skip timestamp.
  *
  * Returns vpos as a positive number while in active scanout area.
  * Returns vpos as a negative number inside vblank, counting the number
@@ -1560,7 +1622,8 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * unknown small number of scanlines wrt. real scanout position.
  *
  */
-int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, int *vpos, int *hpos)
+int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, int *vpos, int *hpos,
+			       ktime_t *stime, ktime_t *etime)
 {
 	u32 stat_crtc = 0, vbl = 0, position = 0;
 	int vbl_start, vbl_end, vtotal, ret = 0;
@@ -1568,6 +1631,12 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, int *vpos, int
 
 	struct radeon_device *rdev = dev->dev_private;
 
+	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+
+	/* Get optional system timestamp before query. */
+	if (stime)
+		*stime = ktime_get();
+
 	if (ASIC_IS_DCE4(rdev)) {
 		if (crtc == 0) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
@@ -1650,6 +1719,12 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, int *vpos, int
 		}
 	}
 
+	/* Get optional system timestamp after query. */
+	if (etime)
+		*etime = ktime_get();
+
+	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+
 	/* Decode into vertical and horizontal scanout position. */
 	*vpos = position & 0x1fff;
 	*hpos = (position >> 16) & 0x1fff;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 9c14a1ba1de..db39ea36bf2 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -36,8 +36,9 @@
 #include <drm/drm_pciids.h>
 #include <linux/console.h>
 #include <linux/module.h>
-
-
+#include <linux/pm_runtime.h>
+#include <linux/vga_switcheroo.h>
+#include "drm_crtc_helper.h"
 /*
  * KMS wrapper.
  * - 2.0.0 - initial interface
@@ -75,9 +76,11 @@
  *   2.32.0 - new info request for rings working
  *   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	34
+#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);
@@ -87,8 +90,8 @@ void radeon_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv);
 void radeon_driver_preclose_kms(struct drm_device *dev,
 				struct drm_file *file_priv);
-int radeon_suspend_kms(struct drm_device *dev, pm_message_t state);
-int radeon_resume_kms(struct drm_device *dev);
+int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon);
+int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
 u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc);
 int radeon_enable_vblank_kms(struct drm_device *dev, int crtc);
 void radeon_disable_vblank_kms(struct drm_device *dev, int crtc);
@@ -100,14 +103,14 @@ void radeon_driver_irq_preinstall_kms(struct drm_device *dev);
 int radeon_driver_irq_postinstall_kms(struct drm_device *dev);
 void radeon_driver_irq_uninstall_kms(struct drm_device *dev);
 irqreturn_t radeon_driver_irq_handler_kms(DRM_IRQ_ARGS);
-int radeon_gem_object_init(struct drm_gem_object *obj);
 void radeon_gem_object_free(struct drm_gem_object *obj);
 int radeon_gem_object_open(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 void radeon_gem_object_close(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
-				      int *vpos, int *hpos);
+				      int *vpos, int *hpos, ktime_t *stime,
+				      ktime_t *etime);
 extern const struct drm_ioctl_desc radeon_ioctls_kms[];
 extern int radeon_max_kms_ioctl;
 int radeon_mmap(struct file *filp, struct vm_area_struct *vma);
@@ -137,9 +140,11 @@ void radeon_debugfs_cleanup(struct drm_minor *minor);
 #if defined(CONFIG_VGA_SWITCHEROO)
 void radeon_register_atpx_handler(void);
 void radeon_unregister_atpx_handler(void);
+bool radeon_is_px(void);
 #else
 static inline void radeon_register_atpx_handler(void) {}
 static inline void radeon_unregister_atpx_handler(void) {}
+static inline bool radeon_is_px(void) { return false; }
 #endif
 
 int radeon_no_wb;
@@ -162,6 +167,7 @@ int radeon_lockup_timeout = 10000;
 int radeon_fastfb = 0;
 int radeon_dpm = -1;
 int radeon_aspm = -1;
+int radeon_runtime_pm = -1;
 
 MODULE_PARM_DESC(no_wb, "Disable AGP writeback for scratch registers");
 module_param_named(no_wb, radeon_no_wb, int, 0444);
@@ -223,6 +229,9 @@ module_param_named(dpm, radeon_dpm, int, 0444);
 MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(aspm, radeon_aspm, int, 0444);
 
+MODULE_PARM_DESC(runpm, "PX runtime pm (1 = force enable, 0 = disable, -1 = PX only default)");
+module_param_named(runpm, radeon_runtime_pm, int, 0444);
+
 static struct pci_device_id pciidlist[] = {
 	radeon_PCI_IDS
 };
@@ -259,6 +268,7 @@ static int radeon_resume(struct drm_device *dev)
 	return 0;
 }
 
+
 static const struct file_operations radeon_driver_old_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -353,25 +363,144 @@ radeon_pci_remove(struct pci_dev *pdev)
 	drm_put_dev(dev);
 }
 
-static int
-radeon_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+static int radeon_pmops_suspend(struct device *dev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
-	return radeon_suspend_kms(dev, state);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_suspend_kms(drm_dev, true, true);
 }
 
-static int
-radeon_pci_resume(struct pci_dev *pdev)
+static int radeon_pmops_resume(struct device *dev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
-	return radeon_resume_kms(dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_resume_kms(drm_dev, true, true);
+}
+
+static int radeon_pmops_freeze(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_suspend_kms(drm_dev, false, true);
+}
+
+static int radeon_pmops_thaw(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_resume_kms(drm_dev, false, true);
+}
+
+static int radeon_pmops_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
+
+	if (radeon_runtime_pm == 0)
+		return -EINVAL;
+
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+	drm_kms_helper_poll_disable(drm_dev);
+	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
+
+	ret = radeon_suspend_kms(drm_dev, false, false);
+	pci_save_state(pdev);
+	pci_disable_device(pdev);
+	pci_set_power_state(pdev, PCI_D3cold);
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+
+	return 0;
 }
 
+static int radeon_pmops_runtime_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
+
+	if (radeon_runtime_pm == 0)
+		return -EINVAL;
+
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+	pci_set_master(pdev);
+
+	ret = radeon_resume_kms(drm_dev, false, false);
+	drm_kms_helper_poll_enable(drm_dev);
+	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
+	return 0;
+}
+
+static int radeon_pmops_runtime_idle(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct drm_crtc *crtc;
+
+	if (radeon_runtime_pm == 0)
+		return -EBUSY;
+
+	/* are we PX enabled? */
+	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
+		DRM_DEBUG_DRIVER("failing to power off - not px\n");
+		return -EBUSY;
+	}
+
+	list_for_each_entry(crtc, &drm_dev->mode_config.crtc_list, head) {
+		if (crtc->enabled) {
+			DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
+			return -EBUSY;
+		}
+	}
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_autosuspend(dev);
+	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
+	return 1;
+}
+
+long radeon_drm_ioctl(struct file *filp,
+		      unsigned int cmd, unsigned long arg)
+{
+	struct drm_file *file_priv = filp->private_data;
+	struct drm_device *dev;
+	long ret;
+	dev = file_priv->minor->dev;
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_ioctl(filp, cmd, arg);
+	
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
+
+static const struct dev_pm_ops radeon_pm_ops = {
+	.suspend = radeon_pmops_suspend,
+	.resume = radeon_pmops_resume,
+	.freeze = radeon_pmops_freeze,
+	.thaw = radeon_pmops_thaw,
+	.poweroff = radeon_pmops_freeze,
+	.restore = radeon_pmops_resume,
+	.runtime_suspend = radeon_pmops_runtime_suspend,
+	.runtime_resume = radeon_pmops_runtime_resume,
+	.runtime_idle = radeon_pmops_runtime_idle,
+};
+
 static const struct file_operations radeon_driver_kms_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.release = drm_release,
-	.unlocked_ioctl = drm_ioctl,
+	.unlocked_ioctl = radeon_drm_ioctl,
 	.mmap = radeon_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
@@ -392,8 +521,6 @@ static struct drm_driver kms_driver = {
 	.postclose = radeon_driver_postclose_kms,
 	.lastclose = radeon_driver_lastclose_kms,
 	.unload = radeon_driver_unload_kms,
-	.suspend = radeon_suspend_kms,
-	.resume = radeon_resume_kms,
 	.get_vblank_counter = radeon_get_vblank_counter_kms,
 	.enable_vblank = radeon_enable_vblank_kms,
 	.disable_vblank = radeon_disable_vblank_kms,
@@ -408,7 +535,6 @@ static struct drm_driver kms_driver = {
 	.irq_uninstall = radeon_driver_irq_uninstall_kms,
 	.irq_handler = radeon_driver_irq_handler_kms,
 	.ioctls = radeon_ioctls_kms,
-	.gem_init_object = radeon_gem_object_init,
 	.gem_free_object = radeon_gem_object_free,
 	.gem_open_object = radeon_gem_object_open,
 	.gem_close_object = radeon_gem_object_close,
@@ -451,8 +577,7 @@ static struct pci_driver radeon_kms_pci_driver = {
 	.id_table = pciidlist,
 	.probe = radeon_pci_probe,
 	.remove = radeon_pci_remove,
-	.suspend = radeon_pci_suspend,
-	.resume = radeon_pci_resume,
+	.driver.pm = &radeon_pm_ops,
 };
 
 static int __init radeon_init(void)
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index b369d42f7de..00e0d449021 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -108,11 +108,15 @@
  * 1.31- Add support for num Z pipes from GET_PARAM
  * 1.32- fixes for rv740 setup
  * 1.33- Add r6xx/r7xx const buffer support
+ * 1.34- fix evergreen/cayman GS register
  */
 #define DRIVER_MAJOR		1
-#define DRIVER_MINOR		33
+#define DRIVER_MINOR		34
 #define DRIVER_PATCHLEVEL	0
 
+long radeon_drm_ioctl(struct file *filp,
+		      unsigned int cmd, unsigned long arg);
+
 /* The rest of the file is DEPRECATED! */
 #ifdef CONFIG_DRM_RADEON_UMS
 
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index 3c8289083f9..614ad549297 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -96,6 +96,7 @@ enum radeon_family {
 	CHIP_BONAIRE,
 	CHIP_KAVERI,
 	CHIP_KABINI,
+	CHIP_HAWAII,
 	CHIP_LAST,
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index ddb8f8e04eb..d3a86e43c01 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -190,10 +190,8 @@ void radeon_fence_process(struct radeon_device *rdev, int ring)
 		}
 	} while (atomic64_xchg(&rdev->fence_drv[ring].last_seq, seq) > seq);
 
-	if (wake) {
-		rdev->fence_drv[ring].last_activity = jiffies;
+	if (wake)
 		wake_up_all(&rdev->fence_queue);
-	}
 }
 
 /**
@@ -212,13 +210,13 @@ static void radeon_fence_destroy(struct kref *kref)
 }
 
 /**
- * radeon_fence_seq_signaled - check if a fence sequeuce number has signaled
+ * radeon_fence_seq_signaled - check if a fence sequence number has signaled
  *
  * @rdev: radeon device pointer
  * @seq: sequence number
  * @ring: ring index the fence is associated with
  *
- * Check if the last singled fence sequnce number is >= the requested
+ * Check if the last signaled fence sequnce number is >= the requested
  * sequence number (all asics).
  * Returns true if the fence has signaled (current fence value
  * is >= requested value) or false if it has not (current fence
@@ -263,113 +261,131 @@ bool radeon_fence_signaled(struct radeon_fence *fence)
 }
 
 /**
- * radeon_fence_wait_seq - wait for a specific sequence number
+ * radeon_fence_any_seq_signaled - check if any sequence number is signaled
  *
  * @rdev: radeon device pointer
- * @target_seq: sequence number we want to wait for
- * @ring: ring index the fence is associated with
+ * @seq: sequence numbers
+ *
+ * Check if the last signaled fence sequnce number is >= the requested
+ * sequence number (all asics).
+ * Returns true if any has signaled (current value is >= requested value)
+ * or false if it has not. Helper function for radeon_fence_wait_seq.
+ */
+static bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
+{
+	unsigned i;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (seq[i] && radeon_fence_seq_signaled(rdev, seq[i], i))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * radeon_fence_wait_seq - wait for a specific sequence numbers
+ *
+ * @rdev: radeon device pointer
+ * @target_seq: sequence number(s) we want to wait for
  * @intr: use interruptable sleep
  * @lock_ring: whether the ring should be locked or not
  *
- * Wait for the requested sequence number to be written (all asics).
+ * Wait for the requested sequence number(s) to be written by any ring
+ * (all asics).  Sequnce number array is indexed by ring id.
  * @intr selects whether to use interruptable (true) or non-interruptable
  * (false) sleep when waiting for the sequence number.  Helper function
- * for radeon_fence_wait(), et al.
+ * for radeon_fence_wait_*().
  * Returns 0 if the sequence number has passed, error for all other cases.
- * -EDEADLK is returned when a GPU lockup has been detected and the ring is
- * marked as not ready so no further jobs get scheduled until a successful
- * reset.
+ * -EDEADLK is returned when a GPU lockup has been detected.
  */
-static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 target_seq,
-				 unsigned ring, bool intr, bool lock_ring)
+static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 *target_seq,
+				 bool intr, bool lock_ring)
 {
-	unsigned long timeout, last_activity;
-	uint64_t seq;
-	unsigned i;
+	uint64_t last_seq[RADEON_NUM_RINGS];
 	bool signaled;
-	int r;
+	int i, r;
+
+	while (!radeon_fence_any_seq_signaled(rdev, target_seq)) {
 
-	while (target_seq > atomic64_read(&rdev->fence_drv[ring].last_seq)) {
-		if (!rdev->ring[ring].ready) {
-			return -EBUSY;
+		/* Save current sequence values, used to check for GPU lockups */
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			if (!target_seq[i])
+				continue;
+
+			last_seq[i] = atomic64_read(&rdev->fence_drv[i].last_seq);
+			trace_radeon_fence_wait_begin(rdev->ddev, target_seq[i]);
+			radeon_irq_kms_sw_irq_get(rdev, i);
 		}
 
-		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
-		if (time_after(rdev->fence_drv[ring].last_activity, timeout)) {
-			/* the normal case, timeout is somewhere before last_activity */
-			timeout = rdev->fence_drv[ring].last_activity - timeout;
+		if (intr) {
+			r = wait_event_interruptible_timeout(rdev->fence_queue, (
+				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq))
+				 || rdev->needs_reset), RADEON_FENCE_JIFFIES_TIMEOUT);
 		} else {
-			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
-			 * anyway we will just wait for the minimum amount and then check for a lockup
-			 */
-			timeout = 1;
+			r = wait_event_timeout(rdev->fence_queue, (
+				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq))
+				 || rdev->needs_reset), RADEON_FENCE_JIFFIES_TIMEOUT);
 		}
-		seq = atomic64_read(&rdev->fence_drv[ring].last_seq);
-		/* Save current last activity valuee, used to check for GPU lockups */
-		last_activity = rdev->fence_drv[ring].last_activity;
 
-		trace_radeon_fence_wait_begin(rdev->ddev, seq);
-		radeon_irq_kms_sw_irq_get(rdev, ring);
-		if (intr) {
-			r = wait_event_interruptible_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_seq_signaled(rdev, target_seq, ring)),
-				timeout);
-                } else {
-			r = wait_event_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_seq_signaled(rdev, target_seq, ring)),
-				timeout);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			if (!target_seq[i])
+				continue;
+
+			radeon_irq_kms_sw_irq_put(rdev, i);
+			trace_radeon_fence_wait_end(rdev->ddev, target_seq[i]);
 		}
-		radeon_irq_kms_sw_irq_put(rdev, ring);
-		if (unlikely(r < 0)) {
+
+		if (unlikely(r < 0))
 			return r;
-		}
-		trace_radeon_fence_wait_end(rdev->ddev, seq);
 
 		if (unlikely(!signaled)) {
+			if (rdev->needs_reset)
+				return -EDEADLK;
+
 			/* we were interrupted for some reason and fence
 			 * isn't signaled yet, resume waiting */
-			if (r) {
+			if (r)
 				continue;
+
+			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+				if (!target_seq[i])
+					continue;
+
+				if (last_seq[i] != atomic64_read(&rdev->fence_drv[i].last_seq))
+					break;
 			}
 
-			/* check if sequence value has changed since last_activity */
-			if (seq != atomic64_read(&rdev->fence_drv[ring].last_seq)) {
+			if (i != RADEON_NUM_RINGS)
 				continue;
-			}
 
-			if (lock_ring) {
+			if (lock_ring)
 				mutex_lock(&rdev->ring_lock);
-			}
 
-			/* test if somebody else has already decided that this is a lockup */
-			if (last_activity != rdev->fence_drv[ring].last_activity) {
-				if (lock_ring) {
-					mutex_unlock(&rdev->ring_lock);
-				}
-				continue;
+			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+				if (!target_seq[i])
+					continue;
+
+				if (radeon_ring_is_lockup(rdev, i, &rdev->ring[i]))
+					break;
 			}
 
-			if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
+			if (i < RADEON_NUM_RINGS) {
 				/* good news we believe it's a lockup */
-				dev_warn(rdev->dev, "GPU lockup (waiting for 0x%016llx last fence id 0x%016llx)\n",
-					 target_seq, seq);
-
-				/* change last activity so nobody else think there is a lockup */
-				for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-					rdev->fence_drv[i].last_activity = jiffies;
-				}
-
-				/* mark the ring as not ready any more */
-				rdev->ring[ring].ready = false;
-				if (lock_ring) {
+				dev_warn(rdev->dev, "GPU lockup (waiting for "
+					 "0x%016llx last fence id 0x%016llx on"
+					 " ring %d)\n",
+					 target_seq[i], last_seq[i], i);
+
+				/* remember that we need an reset */
+				rdev->needs_reset = true;
+				if (lock_ring)
 					mutex_unlock(&rdev->ring_lock);
-				}
+				wake_up_all(&rdev->fence_queue);
 				return -EDEADLK;
 			}
 
-			if (lock_ring) {
+			if (lock_ring)
 				mutex_unlock(&rdev->ring_lock);
-			}
 		}
 	}
 	return 0;
@@ -388,6 +404,7 @@ static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 target_seq,
  */
 int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 {
+	uint64_t seq[RADEON_NUM_RINGS] = {};
 	int r;
 
 	if (fence == NULL) {
@@ -395,147 +412,15 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 		return -EINVAL;
 	}
 
-	r = radeon_fence_wait_seq(fence->rdev, fence->seq,
-				  fence->ring, intr, true);
-	if (r) {
-		return r;
-	}
-	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
-	return 0;
-}
-
-static bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
-{
-	unsigned i;
+	seq[fence->ring] = fence->seq;
+	if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
+		return 0;
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (seq[i] && radeon_fence_seq_signaled(rdev, seq[i], i)) {
-			return true;
-		}
-	}
-	return false;
-}
-
-/**
- * radeon_fence_wait_any_seq - wait for a sequence number on any ring
- *
- * @rdev: radeon device pointer
- * @target_seq: sequence number(s) we want to wait for
- * @intr: use interruptable sleep
- *
- * Wait for the requested sequence number(s) to be written by any ring
- * (all asics).  Sequnce number array is indexed by ring id.
- * @intr selects whether to use interruptable (true) or non-interruptable
- * (false) sleep when waiting for the sequence number.  Helper function
- * for radeon_fence_wait_any(), et al.
- * Returns 0 if the sequence number has passed, error for all other cases.
- */
-static int radeon_fence_wait_any_seq(struct radeon_device *rdev,
-				     u64 *target_seq, bool intr)
-{
-	unsigned long timeout, last_activity, tmp;
-	unsigned i, ring = RADEON_NUM_RINGS;
-	bool signaled;
-	int r;
-
-	for (i = 0, last_activity = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (!target_seq[i]) {
-			continue;
-		}
-
-		/* use the most recent one as indicator */
-		if (time_after(rdev->fence_drv[i].last_activity, last_activity)) {
-			last_activity = rdev->fence_drv[i].last_activity;
-		}
-
-		/* For lockup detection just pick the lowest ring we are
-		 * actively waiting for
-		 */
-		if (i < ring) {
-			ring = i;
-		}
-	}
-
-	/* nothing to wait for ? */
-	if (ring == RADEON_NUM_RINGS) {
-		return -ENOENT;
-	}
-
-	while (!radeon_fence_any_seq_signaled(rdev, target_seq)) {
-		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
-		if (time_after(last_activity, timeout)) {
-			/* the normal case, timeout is somewhere before last_activity */
-			timeout = last_activity - timeout;
-		} else {
-			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
-			 * anyway we will just wait for the minimum amount and then check for a lockup
-			 */
-			timeout = 1;
-		}
-
-		trace_radeon_fence_wait_begin(rdev->ddev, target_seq[ring]);
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			if (target_seq[i]) {
-				radeon_irq_kms_sw_irq_get(rdev, i);
-			}
-		}
-		if (intr) {
-			r = wait_event_interruptible_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq)),
-				timeout);
-		} else {
-			r = wait_event_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq)),
-				timeout);
-		}
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			if (target_seq[i]) {
-				radeon_irq_kms_sw_irq_put(rdev, i);
-			}
-		}
-		if (unlikely(r < 0)) {
-			return r;
-		}
-		trace_radeon_fence_wait_end(rdev->ddev, target_seq[ring]);
-
-		if (unlikely(!signaled)) {
-			/* we were interrupted for some reason and fence
-			 * isn't signaled yet, resume waiting */
-			if (r) {
-				continue;
-			}
-
-			mutex_lock(&rdev->ring_lock);
-			for (i = 0, tmp = 0; i < RADEON_NUM_RINGS; ++i) {
-				if (time_after(rdev->fence_drv[i].last_activity, tmp)) {
-					tmp = rdev->fence_drv[i].last_activity;
-				}
-			}
-			/* test if somebody else has already decided that this is a lockup */
-			if (last_activity != tmp) {
-				last_activity = tmp;
-				mutex_unlock(&rdev->ring_lock);
-				continue;
-			}
-
-			if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
-				/* good news we believe it's a lockup */
-				dev_warn(rdev->dev, "GPU lockup (waiting for 0x%016llx)\n",
-					 target_seq[ring]);
-
-				/* change last activity so nobody else think there is a lockup */
-				for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-					rdev->fence_drv[i].last_activity = jiffies;
-				}
+	r = radeon_fence_wait_seq(fence->rdev, seq, intr, true);
+	if (r)
+		return r;
 
-				/* mark the ring as not ready any more */
-				rdev->ring[ring].ready = false;
-				mutex_unlock(&rdev->ring_lock);
-				return -EDEADLK;
-			}
-			mutex_unlock(&rdev->ring_lock);
-		}
-	}
+	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
 	return 0;
 }
 
@@ -557,7 +442,7 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 			  bool intr)
 {
 	uint64_t seq[RADEON_NUM_RINGS];
-	unsigned i;
+	unsigned i, num_rings = 0;
 	int r;
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -567,15 +452,19 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 			continue;
 		}
 
-		if (fences[i]->seq == RADEON_FENCE_SIGNALED_SEQ) {
-			/* something was allready signaled */
-			return 0;
-		}
-
 		seq[i] = fences[i]->seq;
+		++num_rings;
+
+		/* test if something was allready signaled */
+		if (seq[i] == RADEON_FENCE_SIGNALED_SEQ)
+			return 0;
 	}
 
-	r = radeon_fence_wait_any_seq(rdev, seq, intr);
+	/* nothing to wait for ? */
+	if (num_rings == 0)
+		return -ENOENT;
+
+	r = radeon_fence_wait_seq(rdev, seq, intr, true);
 	if (r) {
 		return r;
 	}
@@ -583,6 +472,36 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 }
 
 /**
+ * radeon_fence_wait_locked - wait for a fence to signal
+ *
+ * @fence: radeon fence object
+ *
+ * Wait for the requested fence to signal (all asics).
+ * Returns 0 if the fence has passed, error for all other cases.
+ */
+int radeon_fence_wait_locked(struct radeon_fence *fence)
+{
+	uint64_t seq[RADEON_NUM_RINGS] = {};
+	int r;
+
+	if (fence == NULL) {
+		WARN(1, "Querying an invalid fence : %p !\n", fence);
+		return -EINVAL;
+	}
+
+	seq[fence->ring] = fence->seq;
+	if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
+		return 0;
+
+	r = radeon_fence_wait_seq(fence->rdev, seq, false, false);
+	if (r)
+		return r;
+
+	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
+	return 0;
+}
+
+/**
  * radeon_fence_wait_next_locked - wait for the next fence to signal
  *
  * @rdev: radeon device pointer
@@ -594,15 +513,15 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
  */
 int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring)
 {
-	uint64_t seq;
+	uint64_t seq[RADEON_NUM_RINGS] = {};
 
-	seq = atomic64_read(&rdev->fence_drv[ring].last_seq) + 1ULL;
-	if (seq >= rdev->fence_drv[ring].sync_seq[ring]) {
+	seq[ring] = atomic64_read(&rdev->fence_drv[ring].last_seq) + 1ULL;
+	if (seq[ring] >= rdev->fence_drv[ring].sync_seq[ring]) {
 		/* nothing to wait for, last_seq is
 		   already the last emited fence */
 		return -ENOENT;
 	}
-	return radeon_fence_wait_seq(rdev, seq, ring, false, false);
+	return radeon_fence_wait_seq(rdev, seq, false, false);
 }
 
 /**
@@ -617,14 +536,18 @@ int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring)
  */
 int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring)
 {
-	uint64_t seq = rdev->fence_drv[ring].sync_seq[ring];
+	uint64_t seq[RADEON_NUM_RINGS] = {};
 	int r;
 
-	r = radeon_fence_wait_seq(rdev, seq, ring, false, false);
+	seq[ring] = rdev->fence_drv[ring].sync_seq[ring];
+	if (!seq[ring])
+		return 0;
+
+	r = radeon_fence_wait_seq(rdev, seq, false, false);
 	if (r) {
-		if (r == -EDEADLK) {
+		if (r == -EDEADLK)
 			return -EDEADLK;
-		}
+
 		dev_err(rdev->dev, "error waiting for ring[%d] to become idle (%d)\n",
 			ring, r);
 	}
@@ -826,7 +749,6 @@ static void radeon_fence_driver_init_ring(struct radeon_device *rdev, int ring)
 	for (i = 0; i < RADEON_NUM_RINGS; ++i)
 		rdev->fence_drv[ring].sync_seq[i] = 0;
 	atomic64_set(&rdev->fence_drv[ring].last_seq, 0);
-	rdev->fence_drv[ring].last_activity = jiffies;
 	rdev->fence_drv[ring].initialized = false;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index b990b1a2bd5..96e440061bd 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -29,6 +29,7 @@
 #include <drm/radeon_drm.h>
 #include "radeon.h"
 #include "radeon_reg.h"
+#include "radeon_trace.h"
 
 /*
  * GART
@@ -607,8 +608,8 @@ static int radeon_vm_evict(struct radeon_device *rdev, struct radeon_vm *vm)
  */
 int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 {
-	unsigned pd_size, pts_size;
-	u64 *pd_addr;
+	unsigned pd_size, pd_entries, pts_size;
+	struct radeon_ib ib;
 	int r;
 
 	if (vm == NULL) {
@@ -619,8 +620,10 @@ int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 		return 0;
 	}
 
-retry:
 	pd_size = radeon_vm_directory_size(rdev);
+	pd_entries = radeon_vm_num_pdes(rdev);
+
+retry:
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
 			     &vm->page_directory, pd_size,
 			     RADEON_VM_PTB_ALIGN_SIZE, false);
@@ -637,9 +640,31 @@ retry:
 	vm->pd_gpu_addr = radeon_sa_bo_gpu_addr(vm->page_directory);
 
 	/* Initially clear the page directory */
-	pd_addr = radeon_sa_bo_cpu_addr(vm->page_directory);
-	memset(pd_addr, 0, pd_size);
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib,
+			  NULL, pd_entries * 2 + 64);
+	if (r) {
+		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
+		return r;
+	}
+
+	ib.length_dw = 0;
+
+	radeon_asic_vm_set_page(rdev, &ib, vm->pd_gpu_addr,
+				0, pd_entries, 0, 0);
+
+	radeon_semaphore_sync_to(ib.semaphore, vm->fence);
+	r = radeon_ib_schedule(rdev, &ib, NULL);
+	if (r) {
+		radeon_ib_free(rdev, &ib);
+		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
+		return r;
+	}
+	radeon_fence_unref(&vm->fence);
+	vm->fence = radeon_fence_ref(ib.fence);
+	radeon_ib_free(rdev, &ib);
+	radeon_fence_unref(&vm->last_flush);
 
+	/* allocate page table array */
 	pts_size = radeon_vm_num_pdes(rdev) * sizeof(struct radeon_sa_bo *);
 	vm->page_tables = kzalloc(pts_size, GFP_KERNEL);
 
@@ -713,6 +738,7 @@ struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev,
 	for (i = 0; i < 2; ++i) {
 		if (choices[i]) {
 			vm->id = choices[i];
+			trace_radeon_vm_grab_id(vm->id, ring);
 			return rdev->vm_manager.active[choices[i]];
 		}
 	}
@@ -914,6 +940,26 @@ uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr)
 }
 
 /**
+ * radeon_vm_page_flags - translate page flags to what the hw uses
+ *
+ * @flags: flags comming from userspace
+ *
+ * Translate the flags the userspace ABI uses to hw flags.
+ */
+static uint32_t radeon_vm_page_flags(uint32_t flags)
+{
+        uint32_t hw_flags = 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_VALID) ? R600_PTE_VALID : 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_READABLE) ? R600_PTE_READABLE : 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_WRITEABLE) ? R600_PTE_WRITEABLE : 0;
+        if (flags & RADEON_VM_PAGE_SYSTEM) {
+                hw_flags |= R600_PTE_SYSTEM;
+                hw_flags |= (flags & RADEON_VM_PAGE_SNOOPED) ? R600_PTE_SNOOPED : 0;
+        }
+        return hw_flags;
+}
+
+/**
  * radeon_vm_update_pdes - make sure that page directory is valid
  *
  * @rdev: radeon_device pointer
@@ -974,7 +1020,11 @@ retry:
 			if (count) {
 				radeon_asic_vm_set_page(rdev, ib, last_pde,
 							last_pt, count, incr,
-							RADEON_VM_PAGE_VALID);
+							R600_PTE_VALID);
+
+				count *= RADEON_VM_PTE_COUNT;
+				radeon_asic_vm_set_page(rdev, ib, last_pt, 0,
+							count, 0, 0);
 			}
 
 			count = 1;
@@ -987,8 +1037,11 @@ retry:
 
 	if (count) {
 		radeon_asic_vm_set_page(rdev, ib, last_pde, last_pt, count,
-					incr, RADEON_VM_PAGE_VALID);
+					incr, R600_PTE_VALID);
 
+		count *= RADEON_VM_PTE_COUNT;
+		radeon_asic_vm_set_page(rdev, ib, last_pt, 0,
+					count, 0, 0);
 	}
 
 	return 0;
@@ -1065,7 +1118,7 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 }
 
 /**
- * radeon_vm_bo_update_pte - map a bo into the vm page table
+ * radeon_vm_bo_update - map a bo into the vm page table
  *
  * @rdev: radeon_device pointer
  * @vm: requested vm
@@ -1077,12 +1130,11 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
  *
  * Object have to be reserved & global and local mutex must be locked!
  */
-int radeon_vm_bo_update_pte(struct radeon_device *rdev,
-			    struct radeon_vm *vm,
-			    struct radeon_bo *bo,
-			    struct ttm_mem_reg *mem)
+int radeon_vm_bo_update(struct radeon_device *rdev,
+			struct radeon_vm *vm,
+			struct radeon_bo *bo,
+			struct ttm_mem_reg *mem)
 {
-	unsigned ridx = rdev->asic->vm.pt_ring_index;
 	struct radeon_ib ib;
 	struct radeon_bo_va *bo_va;
 	unsigned nptes, npdes, ndw;
@@ -1126,6 +1178,8 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 		bo_va->valid = false;
 	}
 
+	trace_radeon_vm_bo_update(bo_va);
+
 	nptes = radeon_bo_ngpu_pages(bo);
 
 	/* assume two extra pdes in case the mapping overlaps the borders */
@@ -1151,11 +1205,16 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 	/* reserve space for pde addresses */
 	ndw += npdes * 2;
 
+	/* reserve space for clearing new page tables */
+	ndw += npdes * 2 * RADEON_VM_PTE_COUNT;
+
 	/* update too big for an IB */
 	if (ndw > 0xfffff)
 		return -ENOMEM;
 
-	r = radeon_ib_get(rdev, ridx, &ib, NULL, ndw * 4);
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib, NULL, ndw * 4);
+	if (r)
+		return r;
 	ib.length_dw = 0;
 
 	r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
@@ -1165,9 +1224,9 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 	}
 
 	radeon_vm_update_ptes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset,
-			      addr, bo_va->flags);
+			      addr, radeon_vm_page_flags(bo_va->flags));
 
-	radeon_ib_sync_to(&ib, vm->fence);
+	radeon_semaphore_sync_to(ib.semaphore, vm->fence);
 	r = radeon_ib_schedule(rdev, &ib, NULL);
 	if (r) {
 		radeon_ib_free(rdev, &ib);
@@ -1202,7 +1261,7 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev,
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&bo_va->vm->mutex);
 	if (bo_va->soffset) {
-		r = radeon_vm_bo_update_pte(rdev, bo_va->vm, bo_va->bo, NULL);
+		r = radeon_vm_bo_update(rdev, bo_va->vm, bo_va->bo, NULL);
 	}
 	mutex_unlock(&rdev->vm_manager.lock);
 	list_del(&bo_va->vm_list);
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index dce99c8a583..805c5e566b9 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -29,13 +29,6 @@
 #include <drm/radeon_drm.h>
 #include "radeon.h"
 
-int radeon_gem_object_init(struct drm_gem_object *obj)
-{
-	BUG();
-
-	return 0;
-}
-
 void radeon_gem_object_free(struct drm_gem_object *gobj)
 {
 	struct radeon_bo *robj = gem_to_radeon_bo(gobj);
diff --git a/drivers/gpu/drm/radeon/radeon_ioc32.c b/drivers/gpu/drm/radeon/radeon_ioc32.c
index c180df8e84d..bdb0f93e73b 100644
--- a/drivers/gpu/drm/radeon/radeon_ioc32.c
+++ b/drivers/gpu/drm/radeon/radeon_ioc32.c
@@ -418,7 +418,7 @@ long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long
 	if (nr < DRM_COMMAND_BASE)
 		return drm_compat_ioctl(filp, cmd, arg);
 
-	ret = drm_ioctl(filp, cmd, arg);
+	ret = radeon_drm_ioctl(filp, cmd, arg);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index cc9e8482cf3..ec6240b0046 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -32,6 +32,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+#include <linux/pm_runtime.h>
+
 #define RADEON_WAIT_IDLE_TIMEOUT 200
 
 /**
@@ -47,8 +49,12 @@ irqreturn_t radeon_driver_irq_handler_kms(DRM_IRQ_ARGS)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	struct radeon_device *rdev = dev->dev_private;
+	irqreturn_t ret;
 
-	return radeon_irq_process(rdev);
+	ret = radeon_irq_process(rdev);
+	if (ret == IRQ_HANDLED)
+		pm_runtime_mark_last_busy(dev->dev);
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 61580ddc4eb..21d593c0eca 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -32,7 +32,7 @@
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
-
+#include <linux/pm_runtime.h>
 /**
  * radeon_driver_unload_kms - Main unload function for KMS.
  *
@@ -50,9 +50,14 @@ int radeon_driver_unload_kms(struct drm_device *dev)
 
 	if (rdev == NULL)
 		return 0;
+
 	if (rdev->rmmio == NULL)
 		goto done_free;
+
+	pm_runtime_get_sync(dev->dev);
+
 	radeon_acpi_fini(rdev);
+	
 	radeon_modeset_fini(rdev);
 	radeon_device_fini(rdev);
 
@@ -125,9 +130,20 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 				"Error during ACPI methods call\n");
 	}
 
+	if (radeon_runtime_pm != 0) {
+		pm_runtime_use_autosuspend(dev->dev);
+		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
+		pm_runtime_set_active(dev->dev);
+		pm_runtime_allow(dev->dev);
+		pm_runtime_mark_last_busy(dev->dev);
+		pm_runtime_put_autosuspend(dev->dev);
+	}
+
 out:
 	if (r)
 		radeon_driver_unload_kms(dev);
+
+
 	return r;
 }
 
@@ -191,7 +207,7 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	switch (info->request) {
 	case RADEON_INFO_DEVICE_ID:
-		*value = dev->pci_device;
+		*value = dev->pdev->device;
 		break;
 	case RADEON_INFO_NUM_GB_PIPES:
 		*value = rdev->num_gb_pipes;
@@ -324,7 +340,7 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		break;
 	case RADEON_INFO_BACKEND_MAP:
 		if (rdev->family >= CHIP_BONAIRE)
-			return -EINVAL;
+			*value = rdev->config.cik.backend_map;
 		else if (rdev->family >= CHIP_TAHITI)
 			*value = rdev->config.si.backend_map;
 		else if (rdev->family >= CHIP_CAYMAN)
@@ -433,9 +449,27 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			return -EINVAL;
 		}
 		break;
+	case RADEON_INFO_CIK_MACROTILE_MODE_ARRAY:
+		if (rdev->family >= CHIP_BONAIRE) {
+			value = rdev->config.cik.macrotile_mode_array;
+			value_size = sizeof(uint32_t)*16;
+		} else {
+			DRM_DEBUG_KMS("macrotile mode array is cik+ only!\n");
+			return -EINVAL;
+		}
+		break;
 	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;
@@ -475,9 +509,14 @@ void radeon_driver_lastclose_kms(struct drm_device *dev)
 int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 {
 	struct radeon_device *rdev = dev->dev_private;
+	int r;
 
 	file_priv->driver_priv = NULL;
 
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
+
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN) {
 		struct radeon_fpriv *fpriv;
@@ -506,6 +545,9 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 		file_priv->driver_priv = fpriv;
 	}
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 7cb178a34a0..0b158f98d28 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -422,6 +422,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 	/* Pin framebuffer & get tilling informations */
 	obj = radeon_fb->obj;
 	rbo = gem_to_radeon_bo(obj);
+retry:
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
 		return r;
@@ -430,6 +431,33 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 				     &base);
 	if (unlikely(r != 0)) {
 		radeon_bo_unreserve(rbo);
+
+		/* On old GPU like RN50 with little vram pining can fails because
+		 * current fb is taking all space needed. So instead of unpining
+		 * the old buffer after pining the new one, first unpin old one
+		 * and then retry pining new one.
+		 *
+		 * As only master can set mode only master can pin and it is
+		 * unlikely the master client will race with itself especialy
+		 * on those old gpu with single crtc.
+		 *
+		 * We don't shutdown the display controller because new buffer
+		 * will end up in same spot.
+		 */
+		if (!atomic && fb && fb != crtc->fb) {
+			struct radeon_bo *old_rbo;
+			unsigned long nsize, osize;
+
+			old_rbo = gem_to_radeon_bo(to_radeon_framebuffer(fb)->obj);
+			osize = radeon_bo_size(old_rbo);
+			nsize = radeon_bo_size(rbo);
+			if (nsize <= osize && !radeon_bo_reserve(old_rbo, false)) {
+				radeon_bo_unpin(old_rbo);
+				radeon_bo_unreserve(old_rbo);
+				fb = NULL;
+				goto retry;
+			}
+		}
 		return -EINVAL;
 	}
 	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
@@ -1056,6 +1084,26 @@ static void radeon_crtc_commit(struct drm_crtc *crtc)
 	}
 }
 
+static void radeon_crtc_disable(struct drm_crtc *crtc)
+{
+	radeon_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	if (crtc->fb) {
+		int r;
+		struct radeon_framebuffer *radeon_fb;
+		struct radeon_bo *rbo;
+
+		radeon_fb = to_radeon_framebuffer(crtc->fb);
+		rbo = gem_to_radeon_bo(radeon_fb->obj);
+		r = radeon_bo_reserve(rbo, false);
+		if (unlikely(r))
+			DRM_ERROR("failed to reserve rbo before unpin\n");
+		else {
+			radeon_bo_unpin(rbo);
+			radeon_bo_unreserve(rbo);
+		}
+	}
+}
+
 static const struct drm_crtc_helper_funcs legacy_helper_funcs = {
 	.dpms = radeon_crtc_dpms,
 	.mode_fixup = radeon_crtc_mode_fixup,
@@ -1065,6 +1113,7 @@ static const struct drm_crtc_helper_funcs legacy_helper_funcs = {
 	.prepare = radeon_crtc_prepare,
 	.commit = radeon_crtc_commit,
 	.load_lut = radeon_crtc_load_lut,
+	.disable = radeon_crtc_disable
 };
 
 
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index 62cd512f5c8..c89971d904c 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -392,7 +392,7 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
 	props.type = BACKLIGHT_RAW;
 	snprintf(bl_name, sizeof(bl_name),
 		 "radeon_bl%d", dev->primary->index);
-	bd = backlight_device_register(bl_name, &drm_connector->kdev,
+	bd = backlight_device_register(bl_name, drm_connector->kdev,
 				       pdata, &radeon_backlight_ops, &props);
 	if (IS_ERR(bd)) {
 		DRM_ERROR("Backlight registration failed\n");
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index ef63d3f00b2..3f0dd664af9 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -249,6 +249,8 @@ struct radeon_mode_info {
 	struct drm_property *underscan_vborder_property;
 	/* audio */
 	struct drm_property *audio_property;
+	/* FMT dithering */
+	struct drm_property *dither_property;
 	/* hardcoded DFP edid from BIOS */
 	struct edid *bios_hardcoded_edid;
 	int bios_hardcoded_edid_size;
@@ -479,6 +481,11 @@ enum radeon_connector_audio {
 	RADEON_AUDIO_AUTO = 2
 };
 
+enum radeon_connector_dither {
+	RADEON_FMT_DITHER_DISABLE = 0,
+	RADEON_FMT_DITHER_ENABLE = 1,
+};
+
 struct radeon_connector {
 	struct drm_connector base;
 	uint32_t connector_id;
@@ -498,6 +505,7 @@ struct radeon_connector {
 	struct radeon_router router;
 	struct radeon_i2c_chan *router_bus;
 	enum radeon_connector_audio audio;
+	enum radeon_connector_dither dither;
 };
 
 struct radeon_framebuffer {
@@ -758,7 +766,8 @@ extern int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 				   int x, int y);
 
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
-				      int *vpos, int *hpos);
+				      int *vpos, int *hpos, ktime_t *stime,
+				      ktime_t *etime);
 
 extern bool radeon_combios_check_hardcoded_edid(struct radeon_device *rdev);
 extern struct edid *
@@ -850,6 +859,12 @@ void radeon_legacy_tv_mode_set(struct drm_encoder *encoder,
 			       struct drm_display_mode *mode,
 			       struct drm_display_mode *adjusted_mode);
 
+/* fmt blocks */
+void avivo_program_fmt(struct drm_encoder *encoder);
+void dce3_program_fmt(struct drm_encoder *encoder);
+void dce4_program_fmt(struct drm_encoder *encoder);
+void dce8_program_fmt(struct drm_encoder *encoder);
+
 /* fbdev layer */
 int radeon_fbdev_init(struct radeon_device *rdev);
 void radeon_fbdev_fini(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 4f6b7fc7ad3..984097b907e 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -508,17 +508,21 @@ static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev,
 	} else if (strncmp("auto", buf, strlen("auto")) == 0) {
 		level = RADEON_DPM_FORCED_LEVEL_AUTO;
 	} else {
-		mutex_unlock(&rdev->pm.mutex);
 		count = -EINVAL;
 		goto fail;
 	}
 	if (rdev->asic->dpm.force_performance_level) {
+		if (rdev->pm.dpm.thermal_active) {
+			count = -EINVAL;
+			goto fail;
+		}
 		ret = radeon_dpm_force_performance_level(rdev, level);
 		if (ret)
 			count = -EINVAL;
 	}
-	mutex_unlock(&rdev->pm.mutex);
 fail:
+	mutex_unlock(&rdev->pm.mutex);
+
 	return count;
 }
 
@@ -533,8 +537,7 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
 				      char *buf)
 {
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct radeon_device *rdev = ddev->dev_private;
+	struct radeon_device *rdev = dev_get_drvdata(dev);
 	int temp;
 
 	if (rdev->asic->pm.get_temperature)
@@ -549,8 +552,7 @@ static ssize_t radeon_hwmon_show_temp_thresh(struct device *dev,
 					     struct device_attribute *attr,
 					     char *buf)
 {
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct radeon_device *rdev = ddev->dev_private;
+	struct radeon_device *rdev = dev_get_drvdata(dev);
 	int hyst = to_sensor_dev_attr(attr)->index;
 	int temp;
 
@@ -562,23 +564,14 @@ static ssize_t radeon_hwmon_show_temp_thresh(struct device *dev,
 	return snprintf(buf, PAGE_SIZE, "%d\n", temp);
 }
 
-static ssize_t radeon_hwmon_show_name(struct device *dev,
-				      struct device_attribute *attr,
-				      char *buf)
-{
-	return sprintf(buf, "radeon\n");
-}
-
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, radeon_hwmon_show_temp, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, radeon_hwmon_show_temp_thresh, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, radeon_hwmon_show_temp_thresh, NULL, 1);
-static SENSOR_DEVICE_ATTR(name, S_IRUGO, radeon_hwmon_show_name, NULL, 0);
 
 static struct attribute *hwmon_attributes[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
 	&sensor_dev_attr_temp1_crit.dev_attr.attr,
 	&sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
-	&sensor_dev_attr_name.dev_attr.attr,
 	NULL
 };
 
@@ -586,8 +579,7 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 					struct attribute *attr, int index)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct radeon_device *rdev = ddev->dev_private;
+	struct radeon_device *rdev = dev_get_drvdata(dev);
 
 	/* Skip limit attributes if DPM is not enabled */
 	if (rdev->pm.pm_method != PM_METHOD_DPM &&
@@ -603,11 +595,15 @@ static const struct attribute_group hwmon_attrgroup = {
 	.is_visible = hwmon_attributes_visible,
 };
 
+static const struct attribute_group *hwmon_groups[] = {
+	&hwmon_attrgroup,
+	NULL
+};
+
 static int radeon_hwmon_init(struct radeon_device *rdev)
 {
 	int err = 0;
-
-	rdev->pm.int_hwmon_dev = NULL;
+	struct device *hwmon_dev;
 
 	switch (rdev->pm.int_thermal_type) {
 	case THERMAL_TYPE_RV6XX:
@@ -620,20 +616,13 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	case THERMAL_TYPE_KV:
 		if (rdev->asic->pm.get_temperature == NULL)
 			return err;
-		rdev->pm.int_hwmon_dev = hwmon_device_register(rdev->dev);
-		if (IS_ERR(rdev->pm.int_hwmon_dev)) {
-			err = PTR_ERR(rdev->pm.int_hwmon_dev);
+		hwmon_dev = hwmon_device_register_with_groups(rdev->dev,
+							      "radeon", rdev,
+							      hwmon_groups);
+		if (IS_ERR(hwmon_dev)) {
+			err = PTR_ERR(hwmon_dev);
 			dev_err(rdev->dev,
 				"Unable to register hwmon device: %d\n", err);
-			break;
-		}
-		dev_set_drvdata(rdev->pm.int_hwmon_dev, rdev->ddev);
-		err = sysfs_create_group(&rdev->pm.int_hwmon_dev->kobj,
-					 &hwmon_attrgroup);
-		if (err) {
-			dev_err(rdev->dev,
-				"Unable to create hwmon sysfs file: %d\n", err);
-			hwmon_device_unregister(rdev->dev);
 		}
 		break;
 	default:
@@ -643,14 +632,6 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	return err;
 }
 
-static void radeon_hwmon_fini(struct radeon_device *rdev)
-{
-	if (rdev->pm.int_hwmon_dev) {
-		sysfs_remove_group(&rdev->pm.int_hwmon_dev->kobj, &hwmon_attrgroup);
-		hwmon_device_unregister(rdev->pm.int_hwmon_dev);
-	}
-}
-
 static void radeon_dpm_thermal_work_handler(struct work_struct *work)
 {
 	struct radeon_device *rdev =
@@ -881,11 +862,12 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 		}
 	}
 
-	printk("switching from power state:\n");
-	radeon_dpm_print_power_state(rdev, rdev->pm.dpm.current_ps);
-	printk("switching to power state:\n");
-	radeon_dpm_print_power_state(rdev, rdev->pm.dpm.requested_ps);
-
+	if (radeon_dpm == 1) {
+		printk("switching from power state:\n");
+		radeon_dpm_print_power_state(rdev, rdev->pm.dpm.current_ps);
+		printk("switching to power state:\n");
+		radeon_dpm_print_power_state(rdev, rdev->pm.dpm.requested_ps);
+	}
 	mutex_lock(&rdev->ddev->struct_mutex);
 	down_write(&rdev->pm.mclk_lock);
 	mutex_lock(&rdev->ring_lock);
@@ -918,12 +900,16 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 	radeon_dpm_post_set_power_state(rdev);
 
 	if (rdev->asic->dpm.force_performance_level) {
-		if (rdev->pm.dpm.thermal_active)
+		if (rdev->pm.dpm.thermal_active) {
+			enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
 			/* force low perf level for thermal */
 			radeon_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_LOW);
-		else
-			/* otherwise, enable auto */
-			radeon_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
+			/* save the user's level */
+			rdev->pm.dpm.forced_level = level;
+		} else {
+			/* otherwise, user selected level */
+			radeon_dpm_force_performance_level(rdev, rdev->pm.dpm.forced_level);
+		}
 	}
 
 done:
@@ -1179,7 +1165,8 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev)
 	mutex_lock(&rdev->pm.mutex);
 	radeon_dpm_init(rdev);
 	rdev->pm.dpm.current_ps = rdev->pm.dpm.requested_ps = rdev->pm.dpm.boot_ps;
-	radeon_dpm_print_power_states(rdev);
+	if (radeon_dpm == 1)
+		radeon_dpm_print_power_states(rdev);
 	radeon_dpm_setup_asic(rdev);
 	ret = radeon_dpm_enable(rdev);
 	mutex_unlock(&rdev->pm.mutex);
@@ -1241,6 +1228,23 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_RV670:
 	case CHIP_RS780:
 	case CHIP_RS880:
+	case CHIP_CAYMAN:
+	case CHIP_BONAIRE:
+	case CHIP_KABINI:
+	case CHIP_KAVERI:
+	case CHIP_HAWAII:
+		/* DPM requires the RLC, RV770+ dGPU requires SMC */
+		if (!rdev->rlc_fw)
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if ((rdev->family >= CHIP_RV770) &&
+			 (!(rdev->flags & RADEON_IS_IGP)) &&
+			 (!rdev->smc_fw))
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if (radeon_dpm == 1)
+			rdev->pm.pm_method = PM_METHOD_DPM;
+		else
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		break;
 	case CHIP_RV770:
 	case CHIP_RV730:
 	case CHIP_RV710:
@@ -1256,16 +1260,12 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_BARTS:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
-	case CHIP_CAYMAN:
 	case CHIP_ARUBA:
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
 	case CHIP_HAINAN:
-	case CHIP_BONAIRE:
-	case CHIP_KABINI:
-	case CHIP_KAVERI:
 		/* DPM requires the RLC, RV770+ dGPU requires SMC */
 		if (!rdev->rlc_fw)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
@@ -1273,10 +1273,10 @@ int radeon_pm_init(struct radeon_device *rdev)
 			 (!(rdev->flags & RADEON_IS_IGP)) &&
 			 (!rdev->smc_fw))
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
-		else if (radeon_dpm == 1)
-			rdev->pm.pm_method = PM_METHOD_DPM;
-		else
+		else if (radeon_dpm == 0)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else
+			rdev->pm.pm_method = PM_METHOD_DPM;
 		break;
 	default:
 		/* default to profile method */
@@ -1314,8 +1314,6 @@ static void radeon_pm_fini_old(struct radeon_device *rdev)
 
 	if (rdev->pm.power_state)
 		kfree(rdev->pm.power_state);
-
-	radeon_hwmon_fini(rdev);
 }
 
 static void radeon_pm_fini_dpm(struct radeon_device *rdev)
@@ -1335,8 +1333,6 @@ static void radeon_pm_fini_dpm(struct radeon_device *rdev)
 
 	if (rdev->pm.power_state)
 		kfree(rdev->pm.power_state);
-
-	radeon_hwmon_fini(rdev);
 }
 
 void radeon_pm_fini(struct radeon_device *rdev)
@@ -1468,7 +1464,7 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
 	 */
 	for (crtc = 0; (crtc < rdev->num_crtc) && in_vbl; crtc++) {
 		if (rdev->pm.active_crtcs & (1 << crtc)) {
-			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, &vpos, &hpos);
+			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, &vpos, &hpos, NULL, NULL);
 			if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
 			    !(vbl_status & DRM_SCANOUTPOS_INVBL))
 				in_vbl = false;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 18254e1c3e7..9214403ae17 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -61,7 +61,7 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib *ib, struct radeon_vm *vm,
 		  unsigned size)
 {
-	int i, r;
+	int r;
 
 	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
 	if (r) {
@@ -87,8 +87,6 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 		ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
 	}
 	ib->is_const_ib = false;
-	for (i = 0; i < RADEON_NUM_RINGS; ++i)
-		ib->sync_to[i] = NULL;
 
 	return 0;
 }
@@ -109,25 +107,6 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 }
 
 /**
- * radeon_ib_sync_to - sync to fence before executing the IB
- *
- * @ib: IB object to add fence to
- * @fence: fence to sync to
- *
- * Sync to the fence before executing the IB
- */
-void radeon_ib_sync_to(struct radeon_ib *ib, struct radeon_fence *fence)
-{
-	struct radeon_fence *other;
-
-	if (!fence)
-		return;
-
-	other = ib->sync_to[fence->ring];
-	ib->sync_to[fence->ring] = radeon_fence_later(fence, other);
-}
-
-/**
  * radeon_ib_schedule - schedule an IB (Indirect Buffer) on the ring
  *
  * @rdev: radeon_device pointer
@@ -151,8 +130,7 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 		       struct radeon_ib *const_ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
-	bool need_sync = false;
-	int i, r = 0;
+	int r = 0;
 
 	if (!ib->length_dw || !ring->ready) {
 		/* TODO: Nothings in the ib we should report. */
@@ -166,19 +144,15 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
 		return r;
 	}
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		struct radeon_fence *fence = ib->sync_to[i];
-		if (radeon_fence_need_sync(fence, ib->ring)) {
-			need_sync = true;
-			radeon_semaphore_sync_rings(rdev, ib->semaphore,
-						    fence->ring, ib->ring);
-			radeon_fence_note_sync(fence, ib->ring);
-		}
-	}
-	/* immediately free semaphore when we don't need to sync */
-	if (!need_sync) {
-		radeon_semaphore_free(rdev, &ib->semaphore, NULL);
+
+	/* sync with other rings */
+	r = radeon_semaphore_sync_rings(rdev, ib->semaphore, ib->ring);
+	if (r) {
+		dev_err(rdev->dev, "failed to sync rings (%d)\n", r);
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
 	}
+
 	/* if we can't remember our last VM flush then flush now! */
 	/* XXX figure out why we have to flush for every IB */
 	if (ib->vm /*&& !ib->vm->last_flush*/) {
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 8dcc20f53d7..2b42aa1914f 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -29,12 +29,12 @@
  */
 #include <drm/drmP.h>
 #include "radeon.h"
-
+#include "radeon_trace.h"
 
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore)
 {
-	int r;
+	int i, r;
 
 	*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
 	if (*semaphore == NULL) {
@@ -50,54 +50,121 @@ int radeon_semaphore_create(struct radeon_device *rdev,
 	(*semaphore)->waiters = 0;
 	(*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo);
 	*((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i)
+		(*semaphore)->sync_to[i] = NULL;
+
 	return 0;
 }
 
-void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_signal(struct radeon_device *rdev, int ridx,
 			          struct radeon_semaphore *semaphore)
 {
-	--semaphore->waiters;
-	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, false);
+	struct radeon_ring *ring = &rdev->ring[ridx];
+
+	trace_radeon_semaphore_signale(ridx, semaphore);
+
+	if (radeon_semaphore_ring_emit(rdev, ridx, ring, semaphore, false)) {
+		--semaphore->waiters;
+
+		/* for debugging lockup only, used by sysfs debug files */
+		ring->last_semaphore_signal_addr = semaphore->gpu_addr;
+		return true;
+	}
+	return false;
 }
 
-void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_wait(struct radeon_device *rdev, int ridx,
 			        struct radeon_semaphore *semaphore)
 {
-	++semaphore->waiters;
-	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
+	struct radeon_ring *ring = &rdev->ring[ridx];
+
+	trace_radeon_semaphore_wait(ridx, semaphore);
+
+	if (radeon_semaphore_ring_emit(rdev, ridx, ring, semaphore, true)) {
+		++semaphore->waiters;
+
+		/* for debugging lockup only, used by sysfs debug files */
+		ring->last_semaphore_wait_addr = semaphore->gpu_addr;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * radeon_semaphore_sync_to - use the semaphore to sync to a fence
+ *
+ * @semaphore: semaphore object to add fence to
+ * @fence: fence to sync to
+ *
+ * Sync to the fence using this semaphore object
+ */
+void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
+			      struct radeon_fence *fence)
+{
+        struct radeon_fence *other;
+
+        if (!fence)
+                return;
+
+        other = semaphore->sync_to[fence->ring];
+        semaphore->sync_to[fence->ring] = radeon_fence_later(fence, other);
 }
 
-/* caller must hold ring lock */
+/**
+ * radeon_semaphore_sync_rings - sync ring to all registered fences
+ *
+ * @rdev: radeon_device pointer
+ * @semaphore: semaphore object to use for sync
+ * @ring: ring that needs sync
+ *
+ * Ensure that all registered fences are signaled before letting
+ * the ring continue. The caller must hold the ring lock.
+ */
 int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				struct radeon_semaphore *semaphore,
-				int signaler, int waiter)
+				int ring)
 {
-	int r;
+	int i, r;
 
-	/* no need to signal and wait on the same ring */
-	if (signaler == waiter) {
-		return 0;
-	}
+        for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		struct radeon_fence *fence = semaphore->sync_to[i];
 
-	/* prevent GPU deadlocks */
-	if (!rdev->ring[signaler].ready) {
-		dev_err(rdev->dev, "Trying to sync to a disabled ring!");
-		return -EINVAL;
-	}
+		/* check if we really need to sync */
+                if (!radeon_fence_need_sync(fence, ring))
+			continue;
 
-	r = radeon_ring_alloc(rdev, &rdev->ring[signaler], 8);
-	if (r) {
-		return r;
-	}
-	radeon_semaphore_emit_signal(rdev, signaler, semaphore);
-	radeon_ring_commit(rdev, &rdev->ring[signaler]);
+		/* prevent GPU deadlocks */
+		if (!rdev->ring[i].ready) {
+			dev_err(rdev->dev, "Syncing to a disabled ring!");
+			return -EINVAL;
+		}
 
-	/* we assume caller has already allocated space on waiters ring */
-	radeon_semaphore_emit_wait(rdev, waiter, semaphore);
+		/* allocate enough space for sync command */
+		r = radeon_ring_alloc(rdev, &rdev->ring[i], 16);
+		if (r) {
+			return r;
+		}
 
-	/* 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;
+		/* emit the signal semaphore */
+		if (!radeon_semaphore_emit_signal(rdev, i, semaphore)) {
+			/* signaling wasn't successful wait manually */
+			radeon_ring_undo(&rdev->ring[i]);
+			radeon_fence_wait_locked(fence);
+			continue;
+		}
+
+		/* we assume caller has already allocated space on waiters ring */
+		if (!radeon_semaphore_emit_wait(rdev, ring, semaphore)) {
+			/* waiting wasn't successful wait manually */
+			radeon_ring_undo(&rdev->ring[i]);
+			radeon_fence_wait_locked(fence);
+			continue;
+		}
+
+		radeon_ring_commit(rdev, &rdev->ring[i]);
+		radeon_fence_note_sync(fence, ring);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h
index f7e36781596..0473257d407 100644
--- a/drivers/gpu/drm/radeon/radeon_trace.h
+++ b/drivers/gpu/drm/radeon/radeon_trace.h
@@ -47,6 +47,63 @@ TRACE_EVENT(radeon_cs,
 		      __entry->fences)
 );
 
+TRACE_EVENT(radeon_vm_grab_id,
+	    TP_PROTO(unsigned vmid, int ring),
+	    TP_ARGS(vmid, ring),
+	    TP_STRUCT__entry(
+			     __field(u32, vmid)
+			     __field(u32, ring)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->vmid = vmid;
+			   __entry->ring = ring;
+			   ),
+	    TP_printk("vmid=%u, ring=%u", __entry->vmid, __entry->ring)
+);
+
+TRACE_EVENT(radeon_vm_bo_update,
+	    TP_PROTO(struct radeon_bo_va *bo_va),
+	    TP_ARGS(bo_va),
+	    TP_STRUCT__entry(
+			     __field(u64, soffset)
+			     __field(u64, eoffset)
+			     __field(u32, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->soffset = bo_va->soffset;
+			   __entry->eoffset = bo_va->eoffset;
+			   __entry->flags = bo_va->flags;
+			   ),
+	    TP_printk("soffs=%010llx, eoffs=%010llx, flags=%08x",
+		      __entry->soffset, __entry->eoffset, __entry->flags)
+);
+
+TRACE_EVENT(radeon_vm_set_page,
+	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
+		     uint32_t incr, uint32_t flags),
+	    TP_ARGS(pe, addr, count, incr, flags),
+	    TP_STRUCT__entry(
+			     __field(u64, pe)
+			     __field(u64, addr)
+			     __field(u32, count)
+			     __field(u32, incr)
+			     __field(u32, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pe = pe;
+			   __entry->addr = addr;
+			   __entry->count = count;
+			   __entry->incr = incr;
+			   __entry->flags = flags;
+			   ),
+	    TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%08x, count=%u",
+		      __entry->pe, __entry->addr, __entry->incr,
+		      __entry->flags, __entry->count)
+);
+
 DECLARE_EVENT_CLASS(radeon_fence_request,
 
 	    TP_PROTO(struct drm_device *dev, u32 seqno),
@@ -87,6 +144,42 @@ DEFINE_EVENT(radeon_fence_request, radeon_fence_wait_end,
 	    TP_ARGS(dev, seqno)
 );
 
+DECLARE_EVENT_CLASS(radeon_semaphore_request,
+
+	    TP_PROTO(int ring, struct radeon_semaphore *sem),
+
+	    TP_ARGS(ring, sem),
+
+	    TP_STRUCT__entry(
+			     __field(int, ring)
+			     __field(signed, waiters)
+			     __field(uint64_t, gpu_addr)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->ring = ring;
+			   __entry->waiters = sem->waiters;
+			   __entry->gpu_addr = sem->gpu_addr;
+			   ),
+
+	    TP_printk("ring=%u, waiters=%d, addr=%010Lx", __entry->ring,
+		      __entry->waiters, __entry->gpu_addr)
+);
+
+DEFINE_EVENT(radeon_semaphore_request, radeon_semaphore_signale,
+
+	    TP_PROTO(int ring, struct radeon_semaphore *sem),
+
+	    TP_ARGS(ring, sem)
+);
+
+DEFINE_EVENT(radeon_semaphore_request, radeon_semaphore_wait,
+
+	    TP_PROTO(int ring, struct radeon_semaphore *sem),
+
+	    TP_ARGS(ring, sem)
+);
+
 #endif
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/radeon/radeon_ucode.h b/drivers/gpu/drm/radeon/radeon_ucode.h
index 33858364fe8..a77cd274dfc 100644
--- a/drivers/gpu/drm/radeon/radeon_ucode.h
+++ b/drivers/gpu/drm/radeon/radeon_ucode.h
@@ -59,6 +59,7 @@
 #define SI_MC_UCODE_SIZE             7769
 #define OLAND_MC_UCODE_SIZE          7863
 #define CIK_MC_UCODE_SIZE            7866
+#define HAWAII_MC_UCODE_SIZE         7933
 
 /* SDMA */
 #define CIK_SDMA_UCODE_SIZE          1050
@@ -143,4 +144,7 @@
 #define BONAIRE_SMC_UCODE_START      0x20000
 #define BONAIRE_SMC_UCODE_SIZE       0x1FDEC
 
+#define HAWAII_SMC_UCODE_START       0x20000
+#define HAWAII_SMC_UCODE_SIZE        0x1FDEC
+
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 308eff5be1b..b9c0529b4a2 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -97,6 +97,7 @@ int radeon_uvd_init(struct radeon_device *rdev)
 	case CHIP_BONAIRE:
 	case CHIP_KABINI:
 	case CHIP_KAVERI:
+	case CHIP_HAWAII:
 		fw_name = FIRMWARE_BONAIRE;
 		break;
 
@@ -240,6 +241,8 @@ void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)
 		if (handle != 0 && rdev->uvd.filp[i] == filp) {
 			struct radeon_fence *fence;
 
+			radeon_uvd_note_usage(rdev);
+
 			r = radeon_uvd_get_destroy_msg(rdev,
 				R600_RING_TYPE_UVD_INDEX, handle, &fence);
 			if (r) {
@@ -470,7 +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;
@@ -620,7 +623,7 @@ static int radeon_uvd_send_msg(struct radeon_device *rdev,
 	if (r) 
 		goto err;
 
-	r = radeon_ib_get(rdev, ring, &ib, NULL, 16);
+	r = radeon_ib_get(rdev, ring, &ib, NULL, 64);
 	if (r)
 		goto err;
 
diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index a072fa8c46b..d46b58d078a 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -21,7 +21,7 @@ cayman 0x9400
 0x000089AC VGT_COMPUTE_THREAD_GOURP_SIZE
 0x000089B0 VGT_HS_OFFCHIP_PARAM
 0x00008A14 PA_CL_ENHANCE
-0x00008A60 PA_SC_LINE_STIPPLE_VALUE
+0x00008A60 PA_SU_LINE_STIPPLE_VALUE
 0x00008B10 PA_SC_LINE_STIPPLE_STATE
 0x00008BF0 PA_SC_ENHANCE
 0x00008D8C SQ_DYN_GPR_CNTL_PS_FLUSH_REQ
@@ -532,7 +532,7 @@ cayman 0x9400
 0x00028B84 PA_SU_POLY_OFFSET_FRONT_OFFSET
 0x00028B88 PA_SU_POLY_OFFSET_BACK_SCALE
 0x00028B8C PA_SU_POLY_OFFSET_BACK_OFFSET
-0x00028B74 VGT_GS_INSTANCE_CNT
+0x00028B90 VGT_GS_INSTANCE_CNT
 0x00028BD4 PA_SC_CENTROID_PRIORITY_0
 0x00028BD8 PA_SC_CENTROID_PRIORITY_1
 0x00028BDC PA_SC_LINE_CNTL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/evergreen b/drivers/gpu/drm/radeon/reg_srcs/evergreen
index b912a37689b..57745c8761c 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/evergreen
+++ b/drivers/gpu/drm/radeon/reg_srcs/evergreen
@@ -22,7 +22,7 @@ evergreen 0x9400
 0x000089A4 VGT_COMPUTE_START_Z
 0x000089AC VGT_COMPUTE_THREAD_GOURP_SIZE
 0x00008A14 PA_CL_ENHANCE
-0x00008A60 PA_SC_LINE_STIPPLE_VALUE
+0x00008A60 PA_SU_LINE_STIPPLE_VALUE
 0x00008B10 PA_SC_LINE_STIPPLE_STATE
 0x00008BF0 PA_SC_ENHANCE
 0x00008D8C SQ_DYN_GPR_CNTL_PS_FLUSH_REQ
@@ -545,7 +545,7 @@ evergreen 0x9400
 0x00028B84 PA_SU_POLY_OFFSET_FRONT_OFFSET
 0x00028B88 PA_SU_POLY_OFFSET_BACK_SCALE
 0x00028B8C PA_SU_POLY_OFFSET_BACK_OFFSET
-0x00028B74 VGT_GS_INSTANCE_CNT
+0x00028B90 VGT_GS_INSTANCE_CNT
 0x00028C00 PA_SC_LINE_CNTL
 0x00028C08 PA_SU_VTX_CNTL
 0x00028C0C PA_CL_GB_VERT_CLIP_ADJ
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 6acba8017b9..76cc8d3aafe 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -153,6 +153,70 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	return RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING;
 }
 
+void avivo_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= AVIVO_TMDS_BIT_DEPTH_CONTROL_SPATIAL_DITHER_EN;
+		else
+			tmp |= AVIVO_TMDS_BIT_DEPTH_CONTROL_TRUNCATE_EN;
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (AVIVO_TMDS_BIT_DEPTH_CONTROL_SPATIAL_DITHER_EN |
+				AVIVO_TMDS_BIT_DEPTH_CONTROL_SPATIAL_DITHER_DEPTH);
+		else
+			tmp |= (AVIVO_TMDS_BIT_DEPTH_CONTROL_TRUNCATE_EN |
+				AVIVO_TMDS_BIT_DEPTH_CONTROL_TRUNCATE_DEPTH);
+		break;
+	case 10:
+	default:
+		/* not needed */
+		break;
+	}
+
+	switch (radeon_encoder->encoder_id) {
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1:
+		WREG32(AVIVO_TMDSA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	case ENCODER_OBJECT_ID_INTERNAL_LVTM1:
+		WREG32(AVIVO_LVTMA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
+		WREG32(AVIVO_DVOA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	case ENCODER_OBJECT_ID_INTERNAL_DDI:
+		WREG32(AVIVO_DDIA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	default:
+		break;
+	}
+}
+
 void rs600_pm_misc(struct radeon_device *rdev)
 {
 	int requested_index = rdev->pm.requested_power_state_index;
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 1447d794c22..e7dab069ccc 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -162,6 +162,16 @@ static void rs690_mc_init(struct radeon_device *rdev)
 	base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
 	base = G_000100_MC_FB_START(base) << 16;
 	rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
+	/* Some boards seem to be configured for 128MB of sideport memory,
+	 * but really only have 64MB.  Just skip the sideport and use
+	 * UMA memory.
+	 */
+	if (rdev->mc.igp_sideport_enabled &&
+	    (rdev->mc.real_vram_size == (384 * 1024 * 1024))) {
+		base += 128 * 1024 * 1024;
+		rdev->mc.real_vram_size -= 128 * 1024 * 1024;
+		rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
+	}
 
 	/* Use K8 direct mapping for fast fb access. */ 
 	rdev->fastfb_working = false;
@@ -345,9 +355,11 @@ static void rs690_crtc_bandwidth_compute(struct radeon_device *rdev,
 		if (max_bandwidth.full > rdev->pm.sideport_bandwidth.full &&
 			rdev->pm.sideport_bandwidth.full)
 			max_bandwidth = rdev->pm.sideport_bandwidth;
-		read_delay_latency.full = dfixed_const(370 * 800 * 1000);
-		read_delay_latency.full = dfixed_div(read_delay_latency,
-			rdev->pm.igp_sideport_mclk);
+		read_delay_latency.full = dfixed_const(370 * 800);
+		a.full = dfixed_const(1000);
+		b.full = dfixed_div(rdev->pm.igp_sideport_mclk, a);
+		read_delay_latency.full = dfixed_div(read_delay_latency, b);
+		read_delay_latency.full = dfixed_mul(read_delay_latency, a);
 	} else {
 		if (max_bandwidth.full > rdev->pm.k8_bandwidth.full &&
 			rdev->pm.k8_bandwidth.full)
@@ -488,14 +500,10 @@ static void rs690_compute_mode_priority(struct radeon_device *rdev,
 		}
 		if (wm0->priority_mark.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark.full;
-		if (dfixed_trunc(priority_mark02) < 0)
-			priority_mark02.full = 0;
 		if (wm0->priority_mark_max.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark_max.full;
 		if (wm1->priority_mark.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark.full;
-		if (dfixed_trunc(priority_mark12) < 0)
-			priority_mark12.full = 0;
 		if (wm1->priority_mark_max.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark_max.full;
 		*d1mode_priority_a_cnt = dfixed_trunc(priority_mark02);
@@ -526,8 +534,6 @@ static void rs690_compute_mode_priority(struct radeon_device *rdev,
 		}
 		if (wm0->priority_mark.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark.full;
-		if (dfixed_trunc(priority_mark02) < 0)
-			priority_mark02.full = 0;
 		if (wm0->priority_mark_max.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark_max.full;
 		*d1mode_priority_a_cnt = dfixed_trunc(priority_mark02);
@@ -555,8 +561,6 @@ static void rs690_compute_mode_priority(struct radeon_device *rdev,
 		}
 		if (wm1->priority_mark.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark.full;
-		if (dfixed_trunc(priority_mark12) < 0)
-			priority_mark12.full = 0;
 		if (wm1->priority_mark_max.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark_max.full;
 		*d2mode_priority_a_cnt = dfixed_trunc(priority_mark12);
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 873eb4b193b..5d1c316115e 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -1155,14 +1155,10 @@ static void rv515_compute_mode_priority(struct radeon_device *rdev,
 		}
 		if (wm0->priority_mark.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark.full;
-		if (dfixed_trunc(priority_mark02) < 0)
-			priority_mark02.full = 0;
 		if (wm0->priority_mark_max.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark_max.full;
 		if (wm1->priority_mark.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark.full;
-		if (dfixed_trunc(priority_mark12) < 0)
-			priority_mark12.full = 0;
 		if (wm1->priority_mark_max.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark_max.full;
 		*d1mode_priority_a_cnt = dfixed_trunc(priority_mark02);
@@ -1193,8 +1189,6 @@ static void rv515_compute_mode_priority(struct radeon_device *rdev,
 		}
 		if (wm0->priority_mark.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark.full;
-		if (dfixed_trunc(priority_mark02) < 0)
-			priority_mark02.full = 0;
 		if (wm0->priority_mark_max.full > priority_mark02.full)
 			priority_mark02.full = wm0->priority_mark_max.full;
 		*d1mode_priority_a_cnt = dfixed_trunc(priority_mark02);
@@ -1222,8 +1216,6 @@ static void rv515_compute_mode_priority(struct radeon_device *rdev,
 		}
 		if (wm1->priority_mark.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark.full;
-		if (dfixed_trunc(priority_mark12) < 0)
-			priority_mark12.full = 0;
 		if (wm1->priority_mark_max.full > priority_mark12.full)
 			priority_mark12.full = wm1->priority_mark_max.full;
 		*d2mode_priority_a_cnt = dfixed_trunc(priority_mark12);
diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c
index 5811d277a36..26633a02525 100644
--- a/drivers/gpu/drm/radeon/rv6xx_dpm.c
+++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c
@@ -407,9 +407,9 @@ static void rv6xx_enable_engine_feedback_and_reference_sync(struct radeon_device
 	WREG32_P(SPLL_CNTL_MODE, SPLL_DIV_SYNC, ~SPLL_DIV_SYNC);
 }
 
-static u64 rv6xx_clocks_per_unit(u32 unit)
+static u32 rv6xx_clocks_per_unit(u32 unit)
 {
-	u64 tmp = 1 << (2 * unit);
+	u32 tmp = 1 << (2 * unit);
 
 	return tmp;
 }
@@ -417,7 +417,7 @@ static u64 rv6xx_clocks_per_unit(u32 unit)
 static u32 rv6xx_scale_count_given_unit(struct radeon_device *rdev,
 					u32 unscaled_count, u32 unit)
 {
-	u32 count_per_unit = (u32)rv6xx_clocks_per_unit(unit);
+	u32 count_per_unit = rv6xx_clocks_per_unit(unit);
 
 	return (unscaled_count + count_per_unit - 1) / count_per_unit;
 }
diff --git a/drivers/gpu/drm/radeon/rv770_dma.c b/drivers/gpu/drm/radeon/rv770_dma.c
index f9b02e3d683..aca8cbe8a33 100644
--- a/drivers/gpu/drm/radeon/rv770_dma.c
+++ b/drivers/gpu/drm/radeon/rv770_dma.c
@@ -66,13 +66,8 @@ int rv770_copy_dma(struct radeon_device *rdev,
 		return r;
 	}
 
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
 		cur_size_in_dw = size_in_dw;
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 913b025ae9b..374499db20c 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2328,6 +2328,12 @@ void rv770_get_engine_memory_ss(struct radeon_device *rdev)
 	pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
 						       ASIC_INTERNAL_MEMORY_SS, 0);
 
+	/* disable ss, causes hangs on some cayman boards */
+	if (rdev->family == CHIP_CAYMAN) {
+		pi->sclk_ss = false;
+		pi->mclk_ss = false;
+	}
+
 	if (pi->sclk_ss || pi->mclk_ss)
 		pi->dynamic_ss = true;
 	else
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index d96f7cbca0a..85e1edfaa3b 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -78,11 +78,6 @@ extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_
 extern u32 evergreen_get_number_of_dram_channels(struct radeon_device *rdev);
 extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
 extern bool evergreen_is_display_hung(struct radeon_device *rdev);
-extern void si_dma_vm_set_page(struct radeon_device *rdev,
-			       struct radeon_ib *ib,
-			       uint64_t pe,
-			       uint64_t addr, unsigned count,
-			       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);
@@ -2816,7 +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;
@@ -2830,14 +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;
@@ -2847,19 +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;
@@ -3887,8 +3884,15 @@ static int si_mc_init(struct radeon_device *rdev)
 	rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
 	rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
 	/* size in MB on si */
-	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
-	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+	tmp = RREG32(CONFIG_MEMSIZE);
+	/* some boards may have garbage in the upper 16 bits */
+	if (tmp & 0xffff0000) {
+		DRM_INFO("Probable bad vram size: 0x%08x\n", tmp);
+		if (tmp & 0xffff)
+			tmp &= 0xffff;
+	}
+	rdev->mc.mc_vram_size = tmp * 1024ULL * 1024ULL;
+	rdev->mc.real_vram_size = rdev->mc.mc_vram_size;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
 	si_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
@@ -4673,61 +4677,6 @@ static void si_vm_decode_fault(struct radeon_device *rdev,
 	       block, mc_id);
 }
 
-/**
- * si_vm_set_page - update the page tables using the CP
- *
- * @rdev: radeon_device pointer
- * @ib: indirect buffer to fill with commands
- * @pe: addr of the page entry
- * @addr: dst addr to write into pe
- * @count: number of page entries to update
- * @incr: increase next addr by incr bytes
- * @flags: access flags
- *
- * Update the page tables using the CP (SI).
- */
-void si_vm_set_page(struct radeon_device *rdev,
-		    struct radeon_ib *ib,
-		    uint64_t pe,
-		    uint64_t addr, unsigned count,
-		    uint32_t incr, uint32_t flags)
-{
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	uint64_t value;
-	unsigned ndw;
-
-	if (rdev->asic->vm.pt_ring_index == RADEON_RING_TYPE_GFX_INDEX) {
-		while (count) {
-			ndw = 2 + count * 2;
-			if (ndw > 0x3FFE)
-				ndw = 0x3FFE;
-
-			ib->ptr[ib->length_dw++] = PACKET3(PACKET3_WRITE_DATA, ndw);
-			ib->ptr[ib->length_dw++] = (WRITE_DATA_ENGINE_SEL(0) |
-					WRITE_DATA_DST_SEL(1));
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-			for (; ndw > 2; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= r600_flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		/* DMA */
-		si_dma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
-	}
-}
-
 void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
 	struct radeon_ring *ring = &rdev->ring[ridx];
@@ -5372,52 +5321,53 @@ void si_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
 	if (buffer == NULL)
 		return;
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_BEGIN_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_BEGIN_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CONTEXT_CONTROL, 1);
-	buffer[count++] = 0x80000000;
-	buffer[count++] = 0x80000000;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CONTEXT_CONTROL, 1));
+	buffer[count++] = cpu_to_le32(0x80000000);
+	buffer[count++] = cpu_to_le32(0x80000000);
 
 	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
 		for (ext = sect->section; ext->extent != NULL; ++ext) {
 			if (sect->id == SECT_CONTEXT) {
-				buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count);
-				buffer[count++] = ext->reg_index - 0xa000;
+				buffer[count++] =
+					cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count));
+				buffer[count++] = cpu_to_le32(ext->reg_index - 0xa000);
 				for (i = 0; i < ext->reg_count; i++)
-					buffer[count++] = ext->extent[i];
+					buffer[count++] = cpu_to_le32(ext->extent[i]);
 			} else {
 				return;
 			}
 		}
 	}
 
-	buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, 1);
-	buffer[count++] = PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, 1));
+	buffer[count++] = cpu_to_le32(PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
-		buffer[count++] = 0x2a00126a;
+		buffer[count++] = cpu_to_le32(0x2a00126a);
 		break;
 	case CHIP_VERDE:
-		buffer[count++] = 0x0000124a;
+		buffer[count++] = cpu_to_le32(0x0000124a);
 		break;
 	case CHIP_OLAND:
-		buffer[count++] = 0x00000082;
+		buffer[count++] = cpu_to_le32(0x00000082);
 		break;
 	case CHIP_HAINAN:
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	default:
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	}
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_END_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CLEAR_STATE, 0);
-	buffer[count++] = 0;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CLEAR_STATE, 0));
+	buffer[count++] = cpu_to_le32(0);
 }
 
 static void si_init_pg(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index 49909d23dfc..59be2cfcbb4 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -24,6 +24,7 @@
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
+#include "radeon_trace.h"
 #include "sid.h"
 
 u32 si_gpu_check_soft_reset(struct radeon_device *rdev);
@@ -75,11 +76,12 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			uint64_t addr, unsigned count,
 			uint32_t incr, uint32_t flags)
 {
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
 
-	if (flags & RADEON_VM_PAGE_SYSTEM) {
+	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
+
+	if (flags & R600_PTE_SYSTEM) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -90,16 +92,10 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = pe;
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
 			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
 				addr += incr;
-				value |= r600_flags;
+				value |= flags;
 				ib->ptr[ib->length_dw++] = value;
 				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
@@ -110,7 +106,7 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			if (ndw > 0xFFFFE)
 				ndw = 0xFFFFE;
 
-			if (flags & RADEON_VM_PAGE_VALID)
+			if (flags & R600_PTE_VALID)
 				value = addr;
 			else
 				value = 0;
@@ -118,7 +114,7 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
 			ib->ptr[ib->length_dw++] = pe; /* dst addr */
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = flags; /* mask */
 			ib->ptr[ib->length_dw++] = 0;
 			ib->ptr[ib->length_dw++] = value; /* value */
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
@@ -199,13 +195,8 @@ int si_copy_dma(struct radeon_device *rdev,
 		return r;
 	}
 
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
+	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
 		cur_size_in_bytes = size_in_bytes;
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 2332aa1bf93..0b00c790fb7 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3589,7 +3589,12 @@ static void si_program_display_gap(struct radeon_device *rdev)
 		WREG32(DCCG_DISP_SLOW_SELECT_REG, tmp);
 	}
 
-	si_notify_smc_display_change(rdev, rdev->pm.dpm.new_active_crtc_count > 0);
+	/* Setting this to false forces the performance state to low if the crtcs are disabled.
+	 * This can be a problem on PowerXpress systems or if you want to use the card
+	 * for offscreen rendering or compute if there are no crtcs enabled.  Set it to
+	 * true for now so that performance scales even if the displays are off.
+	 */
+	si_notify_smc_display_change(rdev, true /*rdev->pm.dpm.new_active_crtc_count > 0*/);
 }
 
 static void si_enable_spread_spectrum(struct radeon_device *rdev, bool enable)
@@ -4553,7 +4558,7 @@ static int si_init_smc_table(struct radeon_device *rdev)
 		table->systemFlags |= PPSMC_SYSTEMFLAG_GDDR5;
 
 	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_REVERT_GPIO5_POLARITY)
-		table->systemFlags |= PPSMC_EXTRAFLAGS_AC2DC_GPIO5_POLARITY_HIGH;
+		table->extraFlags |= PPSMC_EXTRAFLAGS_AC2DC_GPIO5_POLARITY_HIGH;
 
 	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_VRHOT_GPIO_CONFIGURABLE) {
 		table->systemFlags |= PPSMC_SYSTEMFLAG_REGULATOR_HOT_PROG_GPIO;
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 7e2e0ea66a0..b322acc4809 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -478,7 +478,7 @@
 #define		STATE3_MASK				(0x1f << 15)
 #define		STATE3_SHIFT				15
 
-#define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x2808
+#define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x28e8
 #define		TRAIN_DONE_D0      			(1 << 30)
 #define		TRAIN_DONE_D1      			(1 << 31)
 
@@ -683,6 +683,51 @@
  * bit5 = 176.4 kHz
  * bit6 = 192 kHz
  */
+
+#define AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC         0x37
+#       define VIDEO_LIPSYNC(x)                           (((x) & 0xff) << 0)
+#       define AUDIO_LIPSYNC(x)                           (((x) & 0xff) << 8)
+/* VIDEO_LIPSYNC, AUDIO_LIPSYNC
+ * 0   = invalid
+ * x   = legal delay value
+ * 255 = sync not supported
+ */
+#define AZ_F0_CODEC_PIN_CONTROL_RESPONSE_HBR             0x38
+#       define HBR_CAPABLE                                (1 << 0) /* enabled by default */
+
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO0               0x3a
+#       define MANUFACTURER_ID(x)                        (((x) & 0xffff) << 0)
+#       define PRODUCT_ID(x)                             (((x) & 0xffff) << 16)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO1               0x3b
+#       define SINK_DESCRIPTION_LEN(x)                   (((x) & 0xff) << 0)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO2               0x3c
+#       define PORT_ID0(x)                               (((x) & 0xffffffff) << 0)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO3               0x3d
+#       define PORT_ID1(x)                               (((x) & 0xffffffff) << 0)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO4               0x3e
+#       define DESCRIPTION0(x)                           (((x) & 0xff) << 0)
+#       define DESCRIPTION1(x)                           (((x) & 0xff) << 8)
+#       define DESCRIPTION2(x)                           (((x) & 0xff) << 16)
+#       define DESCRIPTION3(x)                           (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO5               0x3f
+#       define DESCRIPTION4(x)                           (((x) & 0xff) << 0)
+#       define DESCRIPTION5(x)                           (((x) & 0xff) << 8)
+#       define DESCRIPTION6(x)                           (((x) & 0xff) << 16)
+#       define DESCRIPTION7(x)                           (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO6               0x40
+#       define DESCRIPTION8(x)                           (((x) & 0xff) << 0)
+#       define DESCRIPTION9(x)                           (((x) & 0xff) << 8)
+#       define DESCRIPTION10(x)                          (((x) & 0xff) << 16)
+#       define DESCRIPTION11(x)                          (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO7               0x41
+#       define DESCRIPTION12(x)                          (((x) & 0xff) << 0)
+#       define DESCRIPTION13(x)                          (((x) & 0xff) << 8)
+#       define DESCRIPTION14(x)                          (((x) & 0xff) << 16)
+#       define DESCRIPTION15(x)                          (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO8               0x42
+#       define DESCRIPTION16(x)                          (((x) & 0xff) << 0)
+#       define DESCRIPTION17(x)                          (((x) & 0xff) << 8)
+
 #define AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL          0x54
 #       define AUDIO_ENABLED                             (1 << 31)
 
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 9364129ba29..d700698a1f2 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1873,9 +1873,9 @@ int trinity_dpm_init(struct radeon_device *rdev)
 	pi->enable_sclk_ds = true;
 	pi->enable_gfx_power_gating = true;
 	pi->enable_gfx_clock_gating = true;
-	pi->enable_mg_clock_gating = true;
-	pi->enable_gfx_dynamic_mgpg = true; /* ??? */
-	pi->override_dynamic_mgpg = true;
+	pi->enable_mg_clock_gating = false;
+	pi->enable_gfx_dynamic_mgpg = false;
+	pi->override_dynamic_mgpg = false;
 	pi->enable_auto_thermal_throttling = true;
 	pi->voltage_drop_in_dce = false; /* need to restructure dpm/modeset interaction */
 	pi->uvd_dpm = true; /* ??? */
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index 7266805d978..d4a68af1a27 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -357,7 +357,7 @@ int uvd_v1_0_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
  *
  * Emit a semaphore command (either wait or signal) to the UVD ring.
  */
-void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait)
@@ -372,6 +372,8 @@ void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
 
 	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
 	radeon_ring_write(ring, emit_wait ? 1 : 0);
+
+	return true;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/uvd_v3_1.c b/drivers/gpu/drm/radeon/uvd_v3_1.c
index 5b6fa1f62d4..d722db2cf34 100644
--- a/drivers/gpu/drm/radeon/uvd_v3_1.c
+++ b/drivers/gpu/drm/radeon/uvd_v3_1.c
@@ -37,7 +37,7 @@
  *
  * Emit a semaphore command (either wait or signal) to the UVD ring.
  */
-void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait)
@@ -52,4 +52,6 @@ void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
 
 	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
 	radeon_ring_write(ring, 0x80 | (emit_wait ? 1 : 0));
+
+	return true;
 }
author	Paul Moore <pmoore@redhat.com>	2014-01-28 14:44:16 -0500
committer	Paul Moore <pmoore@redhat.com>	2014-02-05 10:39:48 -0500
commit	825e587af2e90e9b953849f3347a01d8f383d577 (patch)
tree	e48942a05882da47544e179c6a0c920e00137a6a /drivers/gpu/drm/radeon
parent	8ed814602876bec9bad2649ca17f34b499357a1c (diff)
parent	d8ec26d7f8287f5788a494f56e8814210f0e64be (diff)