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

Pull drm merge (part 1) from Dave Airlie:
 "So first of all my tree and uapi stuff has a conflict mess, its my
  fault as the nouveau stuff didn't hit -next as were trying to rebase
  regressions out of it before we merged.

  Highlights:
   - SH mobile modesetting driver and associated helpers
   - some DRM core documentation
   - i915 modesetting rework, haswell hdmi, haswell and vlv fixes, write
     combined pte writing, ilk rc6 support,
   - nouveau: major driver rework into a hw core driver, makes features
     like SLI a lot saner to implement,
   - psb: add eDP/DP support for Cedarview
   - radeon: 2 layer page tables, async VM pte updates, better PLL
     selection for > 2 screens, better ACPI interactions

  The rest is general grab bag of fixes.

  So why part 1? well I have the exynos pull req which came in a bit
  late but was waiting for me to do something they shouldn't have and it
  looks fairly safe, and David Howells has some more header cleanups
  he'd like me to pull, that seem like a good idea, but I'd like to get
  this merge out of the way so -next dosen't get blocked."

Tons of conflicts mostly due to silly include line changes, but mostly
mindless.  A few other small semantic conflicts too, noted from Dave's
pre-merged branch.

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (447 commits)
  drm/nv98/crypt: fix fuc build with latest envyas
  drm/nouveau/devinit: fixup various issues with subdev ctor/init ordering
  drm/nv41/vm: fix and enable use of "real" pciegart
  drm/nv44/vm: fix and enable use of "real" pciegart
  drm/nv04/dmaobj: fixup vm target handling in preparation for nv4x pcie
  drm/nouveau: store supported dma mask in vmmgr
  drm/nvc0/ibus: initial implementation of subdev
  drm/nouveau/therm: add support for fan-control modes
  drm/nouveau/hwmon: rename pwm0* to pmw1* to follow hwmon's rules
  drm/nouveau/therm: calculate the pwm divisor on nv50+
  drm/nouveau/fan: rewrite the fan tachometer driver to get more precision, faster
  drm/nouveau/therm: move thermal-related functions to the therm subdev
  drm/nouveau/bios: parse the pwm divisor from the perf table
  drm/nouveau/therm: use the EXTDEV table to detect i2c monitoring devices
  drm/nouveau/therm: rework thermal table parsing
  drm/nouveau/gpio: expose the PWM/TOGGLE parameter found in the gpio vbios table
  drm/nouveau: fix pm initialization order
  drm/nouveau/bios: check that fixed tvdac gpio data is valid before using it
  drm/nouveau: log channel debug/error messages from client object rather than drm client
  drm/nouveau: have drm debugging macros build on top of core macros
  ...

55 files changed, 3546 insertions, 1509 deletions

diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 2817101fb167..96184d02c8d9 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -83,25 +83,19 @@ static void atombios_scaler_setup(struct drm_crtc *crtc)
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	ENABLE_SCALER_PS_ALLOCATION args;
 	int index = GetIndexIntoMasterTable(COMMAND, EnableScaler);
-
+	struct radeon_encoder *radeon_encoder =
+		to_radeon_encoder(radeon_crtc->encoder);
 	/* fixme - fill in enc_priv for atom dac */
 	enum radeon_tv_std tv_std = TV_STD_NTSC;
 	bool is_tv = false, is_cv = false;
-	struct drm_encoder *encoder;
 
 	if (!ASIC_IS_AVIVO(rdev) && radeon_crtc->crtc_id)
 		return;
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		/* find tv std */
-		if (encoder->crtc == crtc) {
-			struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-			if (radeon_encoder->active_device & ATOM_DEVICE_TV_SUPPORT) {
-				struct radeon_encoder_atom_dac *tv_dac = radeon_encoder->enc_priv;
-				tv_std = tv_dac->tv_std;
-				is_tv = true;
-			}
-		}
+	if (radeon_encoder->active_device & ATOM_DEVICE_TV_SUPPORT) {
+		struct radeon_encoder_atom_dac *tv_dac = radeon_encoder->enc_priv;
+		tv_std = tv_dac->tv_std;
+		is_tv = true;
 	}
 
 	memset(&args, 0, sizeof(args));
@@ -533,99 +527,87 @@ union adjust_pixel_clock {
 };
 
 static u32 atombios_adjust_pll(struct drm_crtc *crtc,
-			       struct drm_display_mode *mode,
-			       struct radeon_pll *pll,
-			       bool ss_enabled,
-			       struct radeon_atom_ss *ss)
+			       struct drm_display_mode *mode)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *encoder = NULL;
-	struct radeon_encoder *radeon_encoder = NULL;
-	struct drm_connector *connector = NULL;
+	struct drm_encoder *encoder = radeon_crtc->encoder;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	u32 adjusted_clock = mode->clock;
-	int encoder_mode = 0;
+	int encoder_mode = atombios_get_encoder_mode(encoder);
 	u32 dp_clock = mode->clock;
-	int bpc = 8;
-	bool is_duallink = false;
+	int bpc = radeon_get_monitor_bpc(connector);
+	bool is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
 
 	/* reset the pll flags */
-	pll->flags = 0;
+	radeon_crtc->pll_flags = 0;
 
 	if (ASIC_IS_AVIVO(rdev)) {
 		if ((rdev->family == CHIP_RS600) ||
 		    (rdev->family == CHIP_RS690) ||
 		    (rdev->family == CHIP_RS740))
-			pll->flags |= (/*RADEON_PLL_USE_FRAC_FB_DIV |*/
-				       RADEON_PLL_PREFER_CLOSEST_LOWER);
+			radeon_crtc->pll_flags |= (/*RADEON_PLL_USE_FRAC_FB_DIV |*/
+				RADEON_PLL_PREFER_CLOSEST_LOWER);
 
 		if (ASIC_IS_DCE32(rdev) && mode->clock > 200000)	/* range limits??? */
-			pll->flags |= RADEON_PLL_PREFER_HIGH_FB_DIV;
+			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_HIGH_FB_DIV;
 		else
-			pll->flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
+			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
 
 		if (rdev->family < CHIP_RV770)
-			pll->flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
+			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
 		/* use frac fb div on APUs */
 		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev))
-			pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
+			radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
 	} else {
-		pll->flags |= RADEON_PLL_LEGACY;
+		radeon_crtc->pll_flags |= RADEON_PLL_LEGACY;
 
 		if (mode->clock > 200000)	/* range limits??? */
-			pll->flags |= RADEON_PLL_PREFER_HIGH_FB_DIV;
+			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_HIGH_FB_DIV;
 		else
-			pll->flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
+			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->crtc == crtc) {
-			radeon_encoder = to_radeon_encoder(encoder);
-			connector = radeon_get_connector_for_encoder(encoder);
-			bpc = radeon_get_monitor_bpc(connector);
-			encoder_mode = atombios_get_encoder_mode(encoder);
-			is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
-			if ((radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT | ATOM_DEVICE_DFP_SUPPORT)) ||
-			    (radeon_encoder_get_dp_bridge_encoder_id(encoder) != ENCODER_OBJECT_ID_NONE)) {
-				if (connector) {
-					struct radeon_connector *radeon_connector = to_radeon_connector(connector);
-					struct radeon_connector_atom_dig *dig_connector =
-						radeon_connector->con_priv;
-
-					dp_clock = dig_connector->dp_clock;
-				}
-			}
+	if ((radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT | ATOM_DEVICE_DFP_SUPPORT)) ||
+	    (radeon_encoder_get_dp_bridge_encoder_id(encoder) != ENCODER_OBJECT_ID_NONE)) {
+		if (connector) {
+			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+			struct radeon_connector_atom_dig *dig_connector =
+				radeon_connector->con_priv;
 
-			/* use recommended ref_div for ss */
-			if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
-				if (ss_enabled) {
-					if (ss->refdiv) {
-						pll->flags |= RADEON_PLL_USE_REF_DIV;
-						pll->reference_div = ss->refdiv;
-						if (ASIC_IS_AVIVO(rdev))
-							pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
-					}
-				}
-			}
+			dp_clock = dig_connector->dp_clock;
+		}
+	}
 
-			if (ASIC_IS_AVIVO(rdev)) {
-				/* DVO wants 2x pixel clock if the DVO chip is in 12 bit mode */
-				if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1)
-					adjusted_clock = mode->clock * 2;
-				if (radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT))
-					pll->flags |= RADEON_PLL_PREFER_CLOSEST_LOWER;
-				if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
-					pll->flags |= RADEON_PLL_IS_LCD;
-			} else {
-				if (encoder->encoder_type != DRM_MODE_ENCODER_DAC)
-					pll->flags |= RADEON_PLL_NO_ODD_POST_DIV;
-				if (encoder->encoder_type == DRM_MODE_ENCODER_LVDS)
-					pll->flags |= RADEON_PLL_USE_REF_DIV;
+	/* use recommended ref_div for ss */
+	if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+		if (radeon_crtc->ss_enabled) {
+			if (radeon_crtc->ss.refdiv) {
+				radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
+				radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
+				if (ASIC_IS_AVIVO(rdev))
+					radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
 			}
-			break;
 		}
 	}
 
+	if (ASIC_IS_AVIVO(rdev)) {
+		/* DVO wants 2x pixel clock if the DVO chip is in 12 bit mode */
+		if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1)
+			adjusted_clock = mode->clock * 2;
+		if (radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT))
+			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_CLOSEST_LOWER;
+		if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
+			radeon_crtc->pll_flags |= RADEON_PLL_IS_LCD;
+	} else {
+		if (encoder->encoder_type != DRM_MODE_ENCODER_DAC)
+			radeon_crtc->pll_flags |= RADEON_PLL_NO_ODD_POST_DIV;
+		if (encoder->encoder_type == DRM_MODE_ENCODER_LVDS)
+			radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
+	}
+
 	/* DCE3+ has an AdjustDisplayPll that will adjust the pixel clock
 	 * accordingly based on the encoder/transmitter to work around
 	 * special hw requirements.
@@ -650,7 +632,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 				args.v1.usPixelClock = cpu_to_le16(mode->clock / 10);
 				args.v1.ucTransmitterID = radeon_encoder->encoder_id;
 				args.v1.ucEncodeMode = encoder_mode;
-				if (ss_enabled && ss->percentage)
+				if (radeon_crtc->ss_enabled && radeon_crtc->ss.percentage)
 					args.v1.ucConfig |=
 						ADJUST_DISPLAY_CONFIG_SS_ENABLE;
 
@@ -663,7 +645,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 				args.v3.sInput.ucTransmitterID = radeon_encoder->encoder_id;
 				args.v3.sInput.ucEncodeMode = encoder_mode;
 				args.v3.sInput.ucDispPllConfig = 0;
-				if (ss_enabled && ss->percentage)
+				if (radeon_crtc->ss_enabled && radeon_crtc->ss.percentage)
 					args.v3.sInput.ucDispPllConfig |=
 						DISPPLL_CONFIG_SS_ENABLE;
 				if (ENCODER_MODE_IS_DP(encoder_mode)) {
@@ -695,14 +677,14 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 						   index, (uint32_t *)&args);
 				adjusted_clock = le32_to_cpu(args.v3.sOutput.ulDispPllFreq) * 10;
 				if (args.v3.sOutput.ucRefDiv) {
-					pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
-					pll->flags |= RADEON_PLL_USE_REF_DIV;
-					pll->reference_div = args.v3.sOutput.ucRefDiv;
+					radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
+					radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
+					radeon_crtc->pll_reference_div = args.v3.sOutput.ucRefDiv;
 				}
 				if (args.v3.sOutput.ucPostDiv) {
-					pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
-					pll->flags |= RADEON_PLL_USE_POST_DIV;
-					pll->post_div = args.v3.sOutput.ucPostDiv;
+					radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
+					radeon_crtc->pll_flags |= RADEON_PLL_USE_POST_DIV;
+					radeon_crtc->pll_post_div = args.v3.sOutput.ucPostDiv;
 				}
 				break;
 			default:
@@ -837,7 +819,10 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v3.ucFracFbDiv = frac_fb_div;
 			args.v3.ucPostDiv = post_div;
 			args.v3.ucPpll = pll_id;
-			args.v3.ucMiscInfo = (pll_id << 2);
+			if (crtc_id == ATOM_CRTC2)
+				args.v3.ucMiscInfo = PIXEL_CLOCK_MISC_CRTC_SEL_CRTC2;
+			else
+				args.v3.ucMiscInfo = PIXEL_CLOCK_MISC_CRTC_SEL_CRTC1;
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v3.ucMiscInfo |= PIXEL_CLOCK_MISC_REF_DIV_SRC;
 			args.v3.ucTransmitterId = encoder_id;
@@ -907,58 +892,29 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 }
 
-static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode)
+static bool atombios_crtc_prepare_pll(struct drm_crtc *crtc, struct drm_display_mode *mode)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *encoder = NULL;
-	struct radeon_encoder *radeon_encoder = NULL;
-	u32 pll_clock = mode->clock;
-	u32 ref_div = 0, fb_div = 0, frac_fb_div = 0, post_div = 0;
-	struct radeon_pll *pll;
-	u32 adjusted_clock;
-	int encoder_mode = 0;
-	struct radeon_atom_ss ss;
-	bool ss_enabled = false;
-	int bpc = 8;
+	struct radeon_encoder *radeon_encoder =
+		to_radeon_encoder(radeon_crtc->encoder);
+	int encoder_mode = atombios_get_encoder_mode(radeon_crtc->encoder);
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->crtc == crtc) {
-			radeon_encoder = to_radeon_encoder(encoder);
-			encoder_mode = atombios_get_encoder_mode(encoder);
-			break;
-		}
-	}
-
-	if (!radeon_encoder)
-		return;
-
-	switch (radeon_crtc->pll_id) {
-	case ATOM_PPLL1:
-		pll = &rdev->clock.p1pll;
-		break;
-	case ATOM_PPLL2:
-		pll = &rdev->clock.p2pll;
-		break;
-	case ATOM_DCPLL:
-	case ATOM_PPLL_INVALID:
-	default:
-		pll = &rdev->clock.dcpll;
-		break;
-	}
+	radeon_crtc->bpc = 8;
+	radeon_crtc->ss_enabled = false;
 
 	if ((radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT | ATOM_DEVICE_DFP_SUPPORT)) ||
-	    (radeon_encoder_get_dp_bridge_encoder_id(encoder) != ENCODER_OBJECT_ID_NONE)) {
+	    (radeon_encoder_get_dp_bridge_encoder_id(radeon_crtc->encoder) != ENCODER_OBJECT_ID_NONE)) {
 		struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 		struct drm_connector *connector =
-			radeon_get_connector_for_encoder(encoder);
+			radeon_get_connector_for_encoder(radeon_crtc->encoder);
 		struct radeon_connector *radeon_connector =
 			to_radeon_connector(connector);
 		struct radeon_connector_atom_dig *dig_connector =
 			radeon_connector->con_priv;
 		int dp_clock;
-		bpc = radeon_get_monitor_bpc(connector);
+		radeon_crtc->bpc = radeon_get_monitor_bpc(connector);
 
 		switch (encoder_mode) {
 		case ATOM_ENCODER_MODE_DP_MST:
@@ -966,45 +922,54 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 			/* DP/eDP */
 			dp_clock = dig_connector->dp_clock / 10;
 			if (ASIC_IS_DCE4(rdev))
-				ss_enabled =
-					radeon_atombios_get_asic_ss_info(rdev, &ss,
+				radeon_crtc->ss_enabled =
+					radeon_atombios_get_asic_ss_info(rdev, &radeon_crtc->ss,
 									 ASIC_INTERNAL_SS_ON_DP,
 									 dp_clock);
 			else {
 				if (dp_clock == 16200) {
-					ss_enabled =
-						radeon_atombios_get_ppll_ss_info(rdev, &ss,
+					radeon_crtc->ss_enabled =
+						radeon_atombios_get_ppll_ss_info(rdev,
+										 &radeon_crtc->ss,
 										 ATOM_DP_SS_ID2);
-					if (!ss_enabled)
-						ss_enabled =
-							radeon_atombios_get_ppll_ss_info(rdev, &ss,
+					if (!radeon_crtc->ss_enabled)
+						radeon_crtc->ss_enabled =
+							radeon_atombios_get_ppll_ss_info(rdev,
+											 &radeon_crtc->ss,
 											 ATOM_DP_SS_ID1);
 				} else
-					ss_enabled =
-						radeon_atombios_get_ppll_ss_info(rdev, &ss,
+					radeon_crtc->ss_enabled =
+						radeon_atombios_get_ppll_ss_info(rdev,
+										 &radeon_crtc->ss,
 										 ATOM_DP_SS_ID1);
 			}
 			break;
 		case ATOM_ENCODER_MODE_LVDS:
 			if (ASIC_IS_DCE4(rdev))
-				ss_enabled = radeon_atombios_get_asic_ss_info(rdev, &ss,
-									      dig->lcd_ss_id,
-									      mode->clock / 10);
+				radeon_crtc->ss_enabled =
+					radeon_atombios_get_asic_ss_info(rdev,
+									 &radeon_crtc->ss,
+									 dig->lcd_ss_id,
+									 mode->clock / 10);
 			else
-				ss_enabled = radeon_atombios_get_ppll_ss_info(rdev, &ss,
-									      dig->lcd_ss_id);
+				radeon_crtc->ss_enabled =
+					radeon_atombios_get_ppll_ss_info(rdev,
+									 &radeon_crtc->ss,
+									 dig->lcd_ss_id);
 			break;
 		case ATOM_ENCODER_MODE_DVI:
 			if (ASIC_IS_DCE4(rdev))
-				ss_enabled =
-					radeon_atombios_get_asic_ss_info(rdev, &ss,
+				radeon_crtc->ss_enabled =
+					radeon_atombios_get_asic_ss_info(rdev,
+									 &radeon_crtc->ss,
 									 ASIC_INTERNAL_SS_ON_TMDS,
 									 mode->clock / 10);
 			break;
 		case ATOM_ENCODER_MODE_HDMI:
 			if (ASIC_IS_DCE4(rdev))
-				ss_enabled =
-					radeon_atombios_get_asic_ss_info(rdev, &ss,
+				radeon_crtc->ss_enabled =
+					radeon_atombios_get_asic_ss_info(rdev,
+									 &radeon_crtc->ss,
 									 ASIC_INTERNAL_SS_ON_HDMI,
 									 mode->clock / 10);
 			break;
@@ -1014,43 +979,80 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 	}
 
 	/* adjust pixel clock as needed */
-	adjusted_clock = atombios_adjust_pll(crtc, mode, pll, ss_enabled, &ss);
+	radeon_crtc->adjusted_clock = atombios_adjust_pll(crtc, mode);
+
+	return true;
+}
+
+static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode)
+{
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder =
+		to_radeon_encoder(radeon_crtc->encoder);
+	u32 pll_clock = mode->clock;
+	u32 ref_div = 0, fb_div = 0, frac_fb_div = 0, post_div = 0;
+	struct radeon_pll *pll;
+	int encoder_mode = atombios_get_encoder_mode(radeon_crtc->encoder);
+
+	switch (radeon_crtc->pll_id) {
+	case ATOM_PPLL1:
+		pll = &rdev->clock.p1pll;
+		break;
+	case ATOM_PPLL2:
+		pll = &rdev->clock.p2pll;
+		break;
+	case ATOM_DCPLL:
+	case ATOM_PPLL_INVALID:
+	default:
+		pll = &rdev->clock.dcpll;
+		break;
+	}
+
+	/* update pll params */
+	pll->flags = radeon_crtc->pll_flags;
+	pll->reference_div = radeon_crtc->pll_reference_div;
+	pll->post_div = radeon_crtc->pll_post_div;
 
 	if (radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT))
 		/* TV seems to prefer the legacy algo on some boards */
-		radeon_compute_pll_legacy(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
-					  &ref_div, &post_div);
+		radeon_compute_pll_legacy(pll, radeon_crtc->adjusted_clock, &pll_clock,
+					  &fb_div, &frac_fb_div, &ref_div, &post_div);
 	else if (ASIC_IS_AVIVO(rdev))
-		radeon_compute_pll_avivo(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
-					 &ref_div, &post_div);
+		radeon_compute_pll_avivo(pll, radeon_crtc->adjusted_clock, &pll_clock,
+					 &fb_div, &frac_fb_div, &ref_div, &post_div);
 	else
-		radeon_compute_pll_legacy(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
-					  &ref_div, &post_div);
+		radeon_compute_pll_legacy(pll, radeon_crtc->adjusted_clock, &pll_clock,
+					  &fb_div, &frac_fb_div, &ref_div, &post_div);
 
-	atombios_crtc_program_ss(rdev, ATOM_DISABLE, radeon_crtc->pll_id, radeon_crtc->crtc_id, &ss);
+	atombios_crtc_program_ss(rdev, ATOM_DISABLE, radeon_crtc->pll_id,
+				 radeon_crtc->crtc_id, &radeon_crtc->ss);
 
 	atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
 				  encoder_mode, radeon_encoder->encoder_id, mode->clock,
-				  ref_div, fb_div, frac_fb_div, post_div, bpc, ss_enabled, &ss);
+				  ref_div, fb_div, frac_fb_div, post_div,
+				  radeon_crtc->bpc, radeon_crtc->ss_enabled, &radeon_crtc->ss);
 
-	if (ss_enabled) {
+	if (radeon_crtc->ss_enabled) {
 		/* calculate ss amount and step size */
 		if (ASIC_IS_DCE4(rdev)) {
 			u32 step_size;
-			u32 amount = (((fb_div * 10) + frac_fb_div) * ss.percentage) / 10000;
-			ss.amount = (amount / 10) & ATOM_PPLL_SS_AMOUNT_V2_FBDIV_MASK;
-			ss.amount |= ((amount - (amount / 10)) << ATOM_PPLL_SS_AMOUNT_V2_NFRAC_SHIFT) &
+			u32 amount = (((fb_div * 10) + frac_fb_div) * radeon_crtc->ss.percentage) / 10000;
+			radeon_crtc->ss.amount = (amount / 10) & ATOM_PPLL_SS_AMOUNT_V2_FBDIV_MASK;
+			radeon_crtc->ss.amount |= ((amount - (amount / 10)) << ATOM_PPLL_SS_AMOUNT_V2_NFRAC_SHIFT) &
 				ATOM_PPLL_SS_AMOUNT_V2_NFRAC_MASK;
-			if (ss.type & ATOM_PPLL_SS_TYPE_V2_CENTRE_SPREAD)
-				step_size = (4 * amount * ref_div * (ss.rate * 2048)) /
+			if (radeon_crtc->ss.type & ATOM_PPLL_SS_TYPE_V2_CENTRE_SPREAD)
+				step_size = (4 * amount * ref_div * (radeon_crtc->ss.rate * 2048)) /
 					(125 * 25 * pll->reference_freq / 100);
 			else
-				step_size = (2 * amount * ref_div * (ss.rate * 2048)) /
+				step_size = (2 * amount * ref_div * (radeon_crtc->ss.rate * 2048)) /
 					(125 * 25 * pll->reference_freq / 100);
-			ss.step = step_size;
+			radeon_crtc->ss.step = step_size;
 		}
 
-		atombios_crtc_program_ss(rdev, ATOM_ENABLE, radeon_crtc->pll_id, radeon_crtc->crtc_id, &ss);
+		atombios_crtc_program_ss(rdev, ATOM_ENABLE, radeon_crtc->pll_id,
+					 radeon_crtc->crtc_id, &radeon_crtc->ss);
 	}
 }
 
@@ -1479,85 +1481,251 @@ static void radeon_legacy_atom_fixup(struct drm_crtc *crtc)
 	}
 }
 
+/**
+ * radeon_get_pll_use_mask - look up a mask of which pplls are in use
+ *
+ * @crtc: drm crtc
+ *
+ * Returns the mask of which PPLLs (Pixel PLLs) are in use.
+ */
+static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_crtc *test_crtc;
+	struct radeon_crtc *test_radeon_crtc;
+	u32 pll_in_use = 0;
+
+	list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
+		if (crtc == test_crtc)
+			continue;
+
+		test_radeon_crtc = to_radeon_crtc(test_crtc);
+		if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)
+			pll_in_use |= (1 << test_radeon_crtc->pll_id);
+	}
+	return pll_in_use;
+}
+
+/**
+ * radeon_get_shared_dp_ppll - return the PPLL used by another crtc for DP
+ *
+ * @crtc: drm crtc
+ *
+ * Returns the PPLL (Pixel PLL) used by another crtc/encoder which is
+ * also in DP mode.  For DP, a single PPLL can be used for all DP
+ * crtcs/encoders.
+ */
+static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_crtc *test_crtc;
+	struct radeon_crtc *test_radeon_crtc;
+
+	list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
+		if (crtc == test_crtc)
+			continue;
+		test_radeon_crtc = to_radeon_crtc(test_crtc);
+		if (test_radeon_crtc->encoder &&
+		    ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) {
+			/* for DP use the same PLL for all */
+			if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)
+				return test_radeon_crtc->pll_id;
+		}
+	}
+	return ATOM_PPLL_INVALID;
+}
+
+/**
+ * radeon_get_shared_nondp_ppll - return the PPLL used by another non-DP crtc
+ *
+ * @crtc: drm crtc
+ * @encoder: drm encoder
+ *
+ * Returns the PPLL (Pixel PLL) used by another non-DP crtc/encoder which can
+ * be shared (i.e., same clock).
+ */
+static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc)
+{
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct drm_crtc *test_crtc;
+	struct radeon_crtc *test_radeon_crtc;
+	u32 adjusted_clock, test_adjusted_clock;
+
+	adjusted_clock = radeon_crtc->adjusted_clock;
+
+	if (adjusted_clock == 0)
+		return ATOM_PPLL_INVALID;
+
+	list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
+		if (crtc == test_crtc)
+			continue;
+		test_radeon_crtc = to_radeon_crtc(test_crtc);
+		if (test_radeon_crtc->encoder &&
+		    !ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) {
+			/* check if we are already driving this connector with another crtc */
+			if (test_radeon_crtc->connector == radeon_crtc->connector) {
+				/* if we are, return that pll */
+				if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)
+					return test_radeon_crtc->pll_id;
+			}
+			/* for non-DP check the clock */
+			test_adjusted_clock = test_radeon_crtc->adjusted_clock;
+			if ((crtc->mode.clock == test_crtc->mode.clock) &&
+			    (adjusted_clock == test_adjusted_clock) &&
+			    (radeon_crtc->ss_enabled == test_radeon_crtc->ss_enabled) &&
+			    (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID))
+				return test_radeon_crtc->pll_id;
+		}
+	}
+	return ATOM_PPLL_INVALID;
+}
+
+/**
+ * radeon_atom_pick_pll - Allocate a PPLL for use by the crtc.
+ *
+ * @crtc: drm crtc
+ *
+ * Returns the PPLL (Pixel PLL) to be used by the crtc.  For DP monitors
+ * a single PPLL can be used for all DP crtcs/encoders.  For non-DP
+ * monitors a dedicated PPLL must be used.  If a particular board has
+ * an external DP PLL, return ATOM_PPLL_INVALID to skip PLL programming
+ * as there is no need to program the PLL itself.  If we are not able to
+ * allocate a PLL, return ATOM_PPLL_INVALID to skip PLL programming to
+ * avoid messing up an existing monitor.
+ *
+ * Asic specific PLL information
+ *
+ * DCE 6.1
+ * - PPLL2 is only available to UNIPHYA (both DP and non-DP)
+ * - PPLL0, PPLL1 are available for UNIPHYB/C/D/E/F (both DP and non-DP)
+ *
+ * DCE 6.0
+ * - PPLL0 is available to all UNIPHY (DP only)
+ * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC
+ *
+ * DCE 5.0
+ * - DCPLL is available to all UNIPHY (DP only)
+ * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC
+ *
+ * DCE 3.0/4.0/4.1
+ * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC
+ *
+ */
 static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *test_encoder;
-	struct drm_crtc *test_crtc;
-	uint32_t pll_in_use = 0;
+	struct radeon_encoder *radeon_encoder =
+		to_radeon_encoder(radeon_crtc->encoder);
+	u32 pll_in_use;
+	int pll;
 
 	if (ASIC_IS_DCE61(rdev)) {
-		list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) {
-			if (test_encoder->crtc && (test_encoder->crtc == crtc)) {
-				struct radeon_encoder *test_radeon_encoder =
-					to_radeon_encoder(test_encoder);
-				struct radeon_encoder_atom_dig *dig =
-					test_radeon_encoder->enc_priv;
-
-				if ((test_radeon_encoder->encoder_id ==
-				     ENCODER_OBJECT_ID_INTERNAL_UNIPHY) &&
-				    (dig->linkb == false)) /* UNIPHY A uses PPLL2 */
-					return ATOM_PPLL2;
+		struct radeon_encoder_atom_dig *dig =
+			radeon_encoder->enc_priv;
+
+		if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_UNIPHY) &&
+		    (dig->linkb == false))
+			/* UNIPHY A uses PPLL2 */
+			return ATOM_PPLL2;
+		else if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+			/* UNIPHY B/C/D/E/F */
+			if (rdev->clock.dp_extclk)
+				/* skip PPLL programming if using ext clock */
+				return ATOM_PPLL_INVALID;
+			else {
+				/* use the same PPLL for all DP monitors */
+				pll = radeon_get_shared_dp_ppll(crtc);
+				if (pll != ATOM_PPLL_INVALID)
+					return pll;
 			}
+		} else {
+			/* use the same PPLL for all monitors with the same clock */
+			pll = radeon_get_shared_nondp_ppll(crtc);
+			if (pll != ATOM_PPLL_INVALID)
+				return pll;
 		}
 		/* UNIPHY B/C/D/E/F */
-		list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
-			struct radeon_crtc *radeon_test_crtc;
-
-			if (crtc == test_crtc)
-				continue;
-
-			radeon_test_crtc = to_radeon_crtc(test_crtc);
-			if ((radeon_test_crtc->pll_id == ATOM_PPLL0) ||
-			    (radeon_test_crtc->pll_id == ATOM_PPLL1))
-				pll_in_use |= (1 << radeon_test_crtc->pll_id);
-		}
-		if (!(pll_in_use & 4))
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL0)))
 			return ATOM_PPLL0;
-		return ATOM_PPLL1;
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
+			return ATOM_PPLL1;
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
 	} else if (ASIC_IS_DCE4(rdev)) {
-		list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) {
-			if (test_encoder->crtc && (test_encoder->crtc == crtc)) {
-				/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
-				 * depending on the asic:
-				 * DCE4: PPLL or ext clock
-				 * DCE5: DCPLL or ext clock
-				 *
-				 * Setting ATOM_PPLL_INVALID will cause SetPixelClock to skip
-				 * PPLL/DCPLL programming and only program the DP DTO for the
-				 * crtc virtual pixel clock.
-				 */
-				if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) {
-					if (rdev->clock.dp_extclk)
-						return ATOM_PPLL_INVALID;
-					else if (ASIC_IS_DCE6(rdev))
-						return ATOM_PPLL0;
-					else if (ASIC_IS_DCE5(rdev))
-						return ATOM_DCPLL;
-				}
+		/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
+		 * depending on the asic:
+		 * DCE4: PPLL or ext clock
+		 * DCE5: PPLL, DCPLL, or ext clock
+		 * DCE6: PPLL, PPLL0, or ext clock
+		 *
+		 * Setting ATOM_PPLL_INVALID will cause SetPixelClock to skip
+		 * PPLL/DCPLL programming and only program the DP DTO for the
+		 * crtc virtual pixel clock.
+		 */
+		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+			if (rdev->clock.dp_extclk)
+				/* skip PPLL programming if using ext clock */
+				return ATOM_PPLL_INVALID;
+			else if (ASIC_IS_DCE6(rdev))
+				/* use PPLL0 for all DP */
+				return ATOM_PPLL0;
+			else if (ASIC_IS_DCE5(rdev))
+				/* use DCPLL for all DP */
+				return ATOM_DCPLL;
+			else {
+				/* use the same PPLL for all DP monitors */
+				pll = radeon_get_shared_dp_ppll(crtc);
+				if (pll != ATOM_PPLL_INVALID)
+					return pll;
 			}
+		} else {
+			/* use the same PPLL for all monitors with the same clock */
+			pll = radeon_get_shared_nondp_ppll(crtc);
+			if (pll != ATOM_PPLL_INVALID)
+				return pll;
 		}
-
-		/* otherwise, pick one of the plls */
-		list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
-			struct radeon_crtc *radeon_test_crtc;
-
-			if (crtc == test_crtc)
-				continue;
-
-			radeon_test_crtc = to_radeon_crtc(test_crtc);
-			if ((radeon_test_crtc->pll_id >= ATOM_PPLL1) &&
-			    (radeon_test_crtc->pll_id <= ATOM_PPLL2))
-				pll_in_use |= (1 << radeon_test_crtc->pll_id);
-		}
-		if (!(pll_in_use & 1))
+		/* all other cases */
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL2)))
+			return ATOM_PPLL2;
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
 			return ATOM_PPLL1;
-		return ATOM_PPLL2;
-	} else
-		return radeon_crtc->crtc_id;
-
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
+	} else {
+		if (ASIC_IS_AVIVO(rdev)) {
+			/* in DP mode, the DP ref clock can come from either PPLL
+			 * depending on the asic:
+			 * DCE3: PPLL1 or PPLL2
+			 */
+			if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+				/* use the same PPLL for all DP monitors */
+				pll = radeon_get_shared_dp_ppll(crtc);
+				if (pll != ATOM_PPLL_INVALID)
+					return pll;
+			} else {
+				/* use the same PPLL for all monitors with the same clock */
+				pll = radeon_get_shared_nondp_ppll(crtc);
+				if (pll != ATOM_PPLL_INVALID)
+					return pll;
+			}
+			/* all other cases */
+			pll_in_use = radeon_get_pll_use_mask(crtc);
+			if (!(pll_in_use & (1 << ATOM_PPLL2)))
+				return ATOM_PPLL2;
+			if (!(pll_in_use & (1 << ATOM_PPLL1)))
+				return ATOM_PPLL1;
+			DRM_ERROR("unable to allocate a PPLL\n");
+			return ATOM_PPLL_INVALID;
+		} else {
+			/* on pre-R5xx asics, the crtc to pll mapping is hardcoded */
+			return radeon_crtc->crtc_id;
+		}
+	}
 }
 
 void radeon_atom_disp_eng_pll_init(struct radeon_device *rdev)
@@ -1588,18 +1756,13 @@ int atombios_crtc_mode_set(struct drm_crtc *crtc,
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *encoder;
+	struct radeon_encoder *radeon_encoder =
+		to_radeon_encoder(radeon_crtc->encoder);
 	bool is_tvcv = false;
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		/* find tv std */
-		if (encoder->crtc == crtc) {
-			struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-			if (radeon_encoder->active_device &
-			    (ATOM_DEVICE_TV_SUPPORT | ATOM_DEVICE_CV_SUPPORT))
-				is_tvcv = true;
-		}
-	}
+	if (radeon_encoder->active_device &
+	    (ATOM_DEVICE_TV_SUPPORT | ATOM_DEVICE_CV_SUPPORT))
+		is_tvcv = true;
 
 	atombios_crtc_set_pll(crtc, adjusted_mode);
 
@@ -1626,8 +1789,34 @@ static bool atombios_crtc_mode_fixup(struct drm_crtc *crtc,
 				     const struct drm_display_mode *mode,
 				     struct drm_display_mode *adjusted_mode)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct drm_encoder *encoder;
+
+	/* assign the encoder to the radeon crtc to avoid repeated lookups later */
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc == crtc) {
+			radeon_crtc->encoder = encoder;
+			radeon_crtc->connector = radeon_get_connector_for_encoder(encoder);
+			break;
+		}
+	}
+	if ((radeon_crtc->encoder == NULL) || (radeon_crtc->connector == NULL)) {
+		radeon_crtc->encoder = NULL;
+		radeon_crtc->connector = NULL;
+		return false;
+	}
 	if (!radeon_crtc_scaling_mode_fixup(crtc, mode, adjusted_mode))
 		return false;
+	if (!atombios_crtc_prepare_pll(crtc, adjusted_mode))
+		return false;
+	/* pick pll */
+	radeon_crtc->pll_id = radeon_atom_pick_pll(crtc);
+	/* if we can't get a PPLL for a non-DP encoder, fail */
+	if ((radeon_crtc->pll_id == ATOM_PPLL_INVALID) &&
+	    !ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder)))
+		return false;
+
 	return true;
 }
 
@@ -1638,8 +1827,6 @@ static void atombios_crtc_prepare(struct drm_crtc *crtc)
 	struct radeon_device *rdev = dev->dev_private;
 
 	radeon_crtc->in_mode_set = true;
-	/* pick pll */
-	radeon_crtc->pll_id = radeon_atom_pick_pll(crtc);
 
 	/* disable crtc pair power gating before programming */
 	if (ASIC_IS_DCE6(rdev))
@@ -1697,7 +1884,10 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 		break;
 	}
 done:
-	radeon_crtc->pll_id = -1;
+	radeon_crtc->pll_id = ATOM_PPLL_INVALID;
+	radeon_crtc->adjusted_clock = 0;
+	radeon_crtc->encoder = NULL;
+	radeon_crtc->connector = NULL;
 }
 
 static const struct drm_crtc_helper_funcs atombios_helper_funcs = {
@@ -1746,6 +1936,9 @@ void radeon_atombios_init_crtc(struct drm_device *dev,
 		else
 			radeon_crtc->crtc_offset = 0;
 	}
-	radeon_crtc->pll_id = -1;
+	radeon_crtc->pll_id = ATOM_PPLL_INVALID;
+	radeon_crtc->adjusted_clock = 0;
+	radeon_crtc->encoder = NULL;
+	radeon_crtc->connector = NULL;
 	drm_crtc_helper_add(&radeon_crtc->base, &atombios_helper_funcs);
 }
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index ea8e2d471c35..d5699fe4f1e8 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -653,9 +653,7 @@ static bool radeon_dp_get_link_status(struct radeon_connector *radeon_connector,
 		return false;
 	}
 
-	DRM_DEBUG_KMS("link status %02x %02x %02x %02x %02x %02x\n",
-		  link_status[0], link_status[1], link_status[2],
-		  link_status[3], link_status[4], link_status[5]);
+	DRM_DEBUG_KMS("link status %*ph\n", 6, link_status);
 	return true;
 }
 
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 8e2ee98e69d2..49cbb3795a10 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -28,9 +28,251 @@
 #include <drm/radeon_drm.h>
 #include "radeon.h"
 #include "atom.h"
+#include <linux/backlight.h>
 
 extern int atom_debug;
 
+static u8
+radeon_atom_get_backlight_level_from_reg(struct radeon_device *rdev)
+{
+	u8 backlight_level;
+	u32 bios_2_scratch;
+
+	if (rdev->family >= CHIP_R600)
+		bios_2_scratch = RREG32(R600_BIOS_2_SCRATCH);
+	else
+		bios_2_scratch = RREG32(RADEON_BIOS_2_SCRATCH);
+
+	backlight_level = ((bios_2_scratch & ATOM_S2_CURRENT_BL_LEVEL_MASK) >>
+			   ATOM_S2_CURRENT_BL_LEVEL_SHIFT);
+
+	return backlight_level;
+}
+
+static void
+radeon_atom_set_backlight_level_to_reg(struct radeon_device *rdev,
+				       u8 backlight_level)
+{
+	u32 bios_2_scratch;
+
+	if (rdev->family >= CHIP_R600)
+		bios_2_scratch = RREG32(R600_BIOS_2_SCRATCH);
+	else
+		bios_2_scratch = RREG32(RADEON_BIOS_2_SCRATCH);
+
+	bios_2_scratch &= ~ATOM_S2_CURRENT_BL_LEVEL_MASK;
+	bios_2_scratch |= ((backlight_level << ATOM_S2_CURRENT_BL_LEVEL_SHIFT) &
+			   ATOM_S2_CURRENT_BL_LEVEL_MASK);
+
+	if (rdev->family >= CHIP_R600)
+		WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch);
+	else
+		WREG32(RADEON_BIOS_2_SCRATCH, bios_2_scratch);
+}
+
+u8
+atombios_get_backlight_level(struct radeon_encoder *radeon_encoder)
+{
+	struct drm_device *dev = radeon_encoder->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
+
+	if (!(rdev->mode_info.firmware_flags & ATOM_BIOS_INFO_BL_CONTROLLED_BY_GPU))
+		return 0;
+
+	return radeon_atom_get_backlight_level_from_reg(rdev);
+}
+
+void
+atombios_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level)
+{
+	struct drm_encoder *encoder = &radeon_encoder->base;
+	struct drm_device *dev = radeon_encoder->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder_atom_dig *dig;
+	DISPLAY_DEVICE_OUTPUT_CONTROL_PS_ALLOCATION args;
+	int index;
+
+	if (!(rdev->mode_info.firmware_flags & ATOM_BIOS_INFO_BL_CONTROLLED_BY_GPU))
+		return;
+
+	if ((radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) &&
+	    radeon_encoder->enc_priv) {
+		dig = radeon_encoder->enc_priv;
+		dig->backlight_level = level;
+		radeon_atom_set_backlight_level_to_reg(rdev, dig->backlight_level);
+
+		switch (radeon_encoder->encoder_id) {
+		case ENCODER_OBJECT_ID_INTERNAL_LVDS:
+		case ENCODER_OBJECT_ID_INTERNAL_LVTM1:
+			index = GetIndexIntoMasterTable(COMMAND, LCD1OutputControl);
+			if (dig->backlight_level == 0) {
+				args.ucAction = ATOM_LCD_BLOFF;
+				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+			} else {
+				args.ucAction = ATOM_LCD_BL_BRIGHTNESS_CONTROL;
+				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+				args.ucAction = ATOM_LCD_BLON;
+				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+			}
+			break;
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
+		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+			if (dig->backlight_level == 0)
+				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0);
+			else {
+				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_BL_BRIGHTNESS_CONTROL, 0, 0);
+				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0);
+			}
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
+
+static u8 radeon_atom_bl_level(struct backlight_device *bd)
+{
+	u8 level;
+
+	/* Convert brightness to hardware level */
+	if (bd->props.brightness < 0)
+		level = 0;
+	else if (bd->props.brightness > RADEON_MAX_BL_LEVEL)
+		level = RADEON_MAX_BL_LEVEL;
+	else
+		level = bd->props.brightness;
+
+	return level;
+}
+
+static int radeon_atom_backlight_update_status(struct backlight_device *bd)
+{
+	struct radeon_backlight_privdata *pdata = bl_get_data(bd);
+	struct radeon_encoder *radeon_encoder = pdata->encoder;
+
+	atombios_set_backlight_level(radeon_encoder, radeon_atom_bl_level(bd));
+
+	return 0;
+}
+
+static int radeon_atom_backlight_get_brightness(struct backlight_device *bd)
+{
+	struct radeon_backlight_privdata *pdata = bl_get_data(bd);
+	struct radeon_encoder *radeon_encoder = pdata->encoder;
+	struct drm_device *dev = radeon_encoder->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
+
+	return radeon_atom_get_backlight_level_from_reg(rdev);
+}
+
+static const struct backlight_ops radeon_atom_backlight_ops = {
+	.get_brightness = radeon_atom_backlight_get_brightness,
+	.update_status	= radeon_atom_backlight_update_status,
+};
+
+void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
+				struct drm_connector *drm_connector)
+{
+	struct drm_device *dev = radeon_encoder->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct backlight_device *bd;
+	struct backlight_properties props;
+	struct radeon_backlight_privdata *pdata;
+	struct radeon_encoder_atom_dig *dig;
+	u8 backlight_level;
+
+	if (!radeon_encoder->enc_priv)
+		return;
+
+	if (!rdev->is_atom_bios)
+		return;
+
+	if (!(rdev->mode_info.firmware_flags & ATOM_BIOS_INFO_BL_CONTROLLED_BY_GPU))
+		return;
+
+	pdata = kmalloc(sizeof(struct radeon_backlight_privdata), GFP_KERNEL);
+	if (!pdata) {
+		DRM_ERROR("Memory allocation failed\n");
+		goto error;
+	}
+
+	memset(&props, 0, sizeof(props));
+	props.max_brightness = RADEON_MAX_BL_LEVEL;
+	props.type = BACKLIGHT_RAW;
+	bd = backlight_device_register("radeon_bl", &drm_connector->kdev,
+				       pdata, &radeon_atom_backlight_ops, &props);
+	if (IS_ERR(bd)) {
+		DRM_ERROR("Backlight registration failed\n");
+		goto error;
+	}
+
+	pdata->encoder = radeon_encoder;
+
+	backlight_level = radeon_atom_get_backlight_level_from_reg(rdev);
+
+	dig = radeon_encoder->enc_priv;
+	dig->bl_dev = bd;
+
+	bd->props.brightness = radeon_atom_backlight_get_brightness(bd);
+	bd->props.power = FB_BLANK_UNBLANK;
+	backlight_update_status(bd);
+
+	DRM_INFO("radeon atom DIG backlight initialized\n");
+
+	return;
+
+error:
+	kfree(pdata);
+	return;
+}
+
+static void radeon_atom_backlight_exit(struct radeon_encoder *radeon_encoder)
+{
+	struct drm_device *dev = radeon_encoder->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct backlight_device *bd = NULL;
+	struct radeon_encoder_atom_dig *dig;
+
+	if (!radeon_encoder->enc_priv)
+		return;
+
+	if (!rdev->is_atom_bios)
+		return;
+
+	if (!(rdev->mode_info.firmware_flags & ATOM_BIOS_INFO_BL_CONTROLLED_BY_GPU))
+		return;
+
+	dig = radeon_encoder->enc_priv;
+	bd = dig->bl_dev;
+	dig->bl_dev = NULL;
+
+	if (bd) {
+		struct radeon_legacy_backlight_privdata *pdata;
+
+		pdata = bl_get_data(bd);
+		backlight_device_unregister(bd);
+		kfree(pdata);
+
+		DRM_INFO("radeon atom LVDS backlight unloaded\n");
+	}
+}
+
+#else /* !CONFIG_BACKLIGHT_CLASS_DEVICE */
+
+void radeon_atom_backlight_init(struct radeon_encoder *encoder)
+{
+}
+
+static void radeon_atom_backlight_exit(struct radeon_encoder *encoder)
+{
+}
+
+#endif
+
 /* evil but including atombios.h is much worse */
 bool radeon_atom_get_tv_timings(struct radeon_device *rdev, int index,
 				struct drm_display_mode *mode);
@@ -209,6 +451,32 @@ atombios_tv_setup(struct drm_encoder *encoder, int action)
 
 }
 
+static u8 radeon_atom_get_bpc(struct drm_encoder *encoder)
+{
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 8;
+
+	if (connector)
+		bpc = radeon_get_monitor_bpc(connector);
+
+	switch (bpc) {
+	case 0:
+		return PANEL_BPC_UNDEFINE;
+	case 6:
+		return PANEL_6BIT_PER_COLOR;
+	case 8:
+	default:
+		return PANEL_8BIT_PER_COLOR;
+	case 10:
+		return PANEL_10BIT_PER_COLOR;
+	case 12:
+		return PANEL_12BIT_PER_COLOR;
+	case 16:
+		return PANEL_16BIT_PER_COLOR;
+	}
+}
+
+
 union dvo_encoder_control {
 	ENABLE_EXTERNAL_TMDS_ENCODER_PS_ALLOCATION ext_tmds;
 	DVO_ENCODER_CONTROL_PS_ALLOCATION dvo;
@@ -406,7 +674,8 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 		return ATOM_ENCODER_MODE_DP;
 
 	/* DVO is always DVO */
-	if (radeon_encoder->encoder_id == ATOM_ENCODER_MODE_DVO)
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_DVO1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1))
 		return ATOM_ENCODER_MODE_DVO;
 
 	connector = radeon_get_connector_for_encoder(encoder);
@@ -535,7 +804,6 @@ atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mo
 	int dp_clock = 0;
 	int dp_lane_count = 0;
 	int hpd_id = RADEON_HPD_NONE;
-	int bpc = 8;
 
 	if (connector) {
 		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
@@ -545,7 +813,6 @@ atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mo
 		dp_clock = dig_connector->dp_clock;
 		dp_lane_count = dig_connector->dp_lane_count;
 		hpd_id = radeon_connector->hpd.hpd;
-		bpc = radeon_get_monitor_bpc(connector);
 	}
 
 	/* no dig encoder assigned */
@@ -612,37 +879,17 @@ atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mo
 			else
 				args.v3.ucEncoderMode = atombios_get_encoder_mode(encoder);
 
-			if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode))
+			if (ENCODER_MODE_IS_DP(args.v3.ucEncoderMode))
 				args.v3.ucLaneNum = dp_lane_count;
 			else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 				args.v3.ucLaneNum = 8;
 			else
 				args.v3.ucLaneNum = 4;
 
-			if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000))
+			if (ENCODER_MODE_IS_DP(args.v3.ucEncoderMode) && (dp_clock == 270000))
 				args.v1.ucConfig |= ATOM_ENCODER_CONFIG_V3_DPLINKRATE_2_70GHZ;
 			args.v3.acConfig.ucDigSel = dig->dig_encoder;
-			switch (bpc) {
-			case 0:
-				args.v3.ucBitPerColor = PANEL_BPC_UNDEFINE;
-				break;
-			case 6:
-				args.v3.ucBitPerColor = PANEL_6BIT_PER_COLOR;
-				break;
-			case 8:
-			default:
-				args.v3.ucBitPerColor = PANEL_8BIT_PER_COLOR;
-				break;
-			case 10:
-				args.v3.ucBitPerColor = PANEL_10BIT_PER_COLOR;
-				break;
-			case 12:
-				args.v3.ucBitPerColor = PANEL_12BIT_PER_COLOR;
-				break;
-			case 16:
-				args.v3.ucBitPerColor = PANEL_16BIT_PER_COLOR;
-				break;
-			}
+			args.v3.ucBitPerColor = radeon_atom_get_bpc(encoder);
 			break;
 		case 4:
 			args.v4.ucAction = action;
@@ -652,41 +899,21 @@ atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mo
 			else
 				args.v4.ucEncoderMode = atombios_get_encoder_mode(encoder);
 
-			if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode))
+			if (ENCODER_MODE_IS_DP(args.v4.ucEncoderMode))
 				args.v4.ucLaneNum = dp_lane_count;
 			else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 				args.v4.ucLaneNum = 8;
 			else
 				args.v4.ucLaneNum = 4;
 
-			if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode)) {
+			if (ENCODER_MODE_IS_DP(args.v4.ucEncoderMode)) {
 				if (dp_clock == 270000)
 					args.v1.ucConfig |= ATOM_ENCODER_CONFIG_V4_DPLINKRATE_2_70GHZ;
 				else if (dp_clock == 540000)
 					args.v1.ucConfig |= ATOM_ENCODER_CONFIG_V4_DPLINKRATE_5_40GHZ;
 			}
 			args.v4.acConfig.ucDigSel = dig->dig_encoder;
-			switch (bpc) {
-			case 0:
-				args.v4.ucBitPerColor = PANEL_BPC_UNDEFINE;
-				break;
-			case 6:
-				args.v4.ucBitPerColor = PANEL_6BIT_PER_COLOR;
-				break;
-			case 8:
-			default:
-				args.v4.ucBitPerColor = PANEL_8BIT_PER_COLOR;
-				break;
-			case 10:
-				args.v4.ucBitPerColor = PANEL_10BIT_PER_COLOR;
-				break;
-			case 12:
-				args.v4.ucBitPerColor = PANEL_12BIT_PER_COLOR;
-				break;
-			case 16:
-				args.v4.ucBitPerColor = PANEL_16BIT_PER_COLOR;
-				break;
-			}
+			args.v4.ucBitPerColor = radeon_atom_get_bpc(encoder);
 			if (hpd_id == RADEON_HPD_NONE)
 				args.v4.ucHPD_ID = 0;
 			else
@@ -799,8 +1026,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 				args.v1.asMode.ucLaneSet = lane_set;
 			} else {
 				if (is_dp)
-					args.v1.usPixelClock =
-						cpu_to_le16(dp_clock / 10);
+					args.v1.usPixelClock = cpu_to_le16(dp_clock / 10);
 				else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 					args.v1.usPixelClock = cpu_to_le16((radeon_encoder->pixel_clock / 2) / 10);
 				else
@@ -857,8 +1083,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 				args.v2.asMode.ucLaneSet = lane_set;
 			} else {
 				if (is_dp)
-					args.v2.usPixelClock =
-						cpu_to_le16(dp_clock / 10);
+					args.v2.usPixelClock = cpu_to_le16(dp_clock / 10);
 				else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 					args.v2.usPixelClock = cpu_to_le16((radeon_encoder->pixel_clock / 2) / 10);
 				else
@@ -900,8 +1125,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 				args.v3.asMode.ucLaneSet = lane_set;
 			} else {
 				if (is_dp)
-					args.v3.usPixelClock =
-						cpu_to_le16(dp_clock / 10);
+					args.v3.usPixelClock = cpu_to_le16(dp_clock / 10);
 				else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 					args.v3.usPixelClock = cpu_to_le16((radeon_encoder->pixel_clock / 2) / 10);
 				else
@@ -960,8 +1184,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 				args.v4.asMode.ucLaneSet = lane_set;
 			} else {
 				if (is_dp)
-					args.v4.usPixelClock =
-						cpu_to_le16(dp_clock / 10);
+					args.v4.usPixelClock = cpu_to_le16(dp_clock / 10);
 				else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 					args.v4.usPixelClock = cpu_to_le16((radeon_encoder->pixel_clock / 2) / 10);
 				else
@@ -1147,7 +1370,6 @@ atombios_external_encoder_setup(struct drm_encoder *encoder,
 	int dp_lane_count = 0;
 	int connector_object_id = 0;
 	u32 ext_enum = (ext_radeon_encoder->encoder_enum & ENUM_ID_MASK) >> ENUM_ID_SHIFT;
-	int bpc = 8;
 
 	if (action == EXTERNAL_ENCODER_ACTION_V3_ENCODER_INIT)
 		connector = radeon_get_connector_for_encoder_init(encoder);
@@ -1163,7 +1385,6 @@ atombios_external_encoder_setup(struct drm_encoder *encoder,
 		dp_lane_count = dig_connector->dp_lane_count;
 		connector_object_id =
 			(radeon_connector->connector_object_id & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-		bpc = radeon_get_monitor_bpc(connector);
 	}
 
 	memset(&args, 0, sizeof(args));
@@ -1221,27 +1442,7 @@ atombios_external_encoder_setup(struct drm_encoder *encoder,
 				args.v3.sExtEncoder.ucConfig |= EXTERNAL_ENCODER_CONFIG_V3_ENCODER3;
 				break;
 			}
-			switch (bpc) {
-			case 0:
-				args.v3.sExtEncoder.ucBitPerColor = PANEL_BPC_UNDEFINE;
-				break;
-			case 6:
-				args.v3.sExtEncoder.ucBitPerColor = PANEL_6BIT_PER_COLOR;
-				break;
-			case 8:
-			default:
-				args.v3.sExtEncoder.ucBitPerColor = PANEL_8BIT_PER_COLOR;
-				break;
-			case 10:
-				args.v3.sExtEncoder.ucBitPerColor = PANEL_10BIT_PER_COLOR;
-				break;
-			case 12:
-				args.v3.sExtEncoder.ucBitPerColor = PANEL_12BIT_PER_COLOR;
-				break;
-			case 16:
-				args.v3.sExtEncoder.ucBitPerColor = PANEL_16BIT_PER_COLOR;
-				break;
-			}
+			args.v3.sExtEncoder.ucBitPerColor = radeon_atom_get_bpc(encoder);
 			break;
 		default:
 			DRM_ERROR("Unknown table version: %d, %d\n", frev, crev);
@@ -2286,6 +2487,8 @@ static const struct drm_encoder_helper_funcs radeon_atom_dac_helper_funcs = {
 void radeon_enc_destroy(struct drm_encoder *encoder)
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
+		radeon_atom_backlight_exit(radeon_encoder);
 	kfree(radeon_encoder->enc_priv);
 	drm_encoder_cleanup(encoder);
 	kfree(radeon_encoder);
@@ -2295,7 +2498,7 @@ static const struct drm_encoder_funcs radeon_atom_enc_funcs = {
 	.destroy = radeon_enc_destroy,
 };
 
-struct radeon_encoder_atom_dac *
+static struct radeon_encoder_atom_dac *
 radeon_atombios_set_dac_info(struct radeon_encoder *radeon_encoder)
 {
 	struct drm_device *dev = radeon_encoder->base.dev;
@@ -2309,7 +2512,7 @@ radeon_atombios_set_dac_info(struct radeon_encoder *radeon_encoder)
 	return dac;
 }
 
-struct radeon_encoder_atom_dig *
+static struct radeon_encoder_atom_dig *
 radeon_atombios_set_dig_info(struct radeon_encoder *radeon_encoder)
 {
 	int encoder_enum = (radeon_encoder->encoder_enum & ENUM_ID_MASK) >> ENUM_ID_SHIFT;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index c548dd75ca8b..a1f49c5fd74b 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -37,6 +37,16 @@
 #define EVERGREEN_PFP_UCODE_SIZE 1120
 #define EVERGREEN_PM4_UCODE_SIZE 1376
 
+static const u32 crtc_offsets[6] =
+{
+	EVERGREEN_CRTC0_REGISTER_OFFSET,
+	EVERGREEN_CRTC1_REGISTER_OFFSET,
+	EVERGREEN_CRTC2_REGISTER_OFFSET,
+	EVERGREEN_CRTC3_REGISTER_OFFSET,
+	EVERGREEN_CRTC4_REGISTER_OFFSET,
+	EVERGREEN_CRTC5_REGISTER_OFFSET
+};
+
 static void evergreen_gpu_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
 void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
@@ -105,17 +115,19 @@ void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev)
  */
 void dce4_wait_for_vblank(struct radeon_device *rdev, int crtc)
 {
-	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc];
 	int i;
 
-	if (RREG32(EVERGREEN_CRTC_CONTROL + radeon_crtc->crtc_offset) & EVERGREEN_CRTC_MASTER_EN) {
+	if (crtc >= rdev->num_crtc)
+		return;
+
+	if (RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[crtc]) & EVERGREEN_CRTC_MASTER_EN) {
 		for (i = 0; i < rdev->usec_timeout; i++) {
-			if (!(RREG32(EVERGREEN_CRTC_STATUS + radeon_crtc->crtc_offset) & EVERGREEN_CRTC_V_BLANK))
+			if (!(RREG32(EVERGREEN_CRTC_STATUS + crtc_offsets[crtc]) & EVERGREEN_CRTC_V_BLANK))
 				break;
 			udelay(1);
 		}
 		for (i = 0; i < rdev->usec_timeout; i++) {
-			if (RREG32(EVERGREEN_CRTC_STATUS + radeon_crtc->crtc_offset) & EVERGREEN_CRTC_V_BLANK)
+			if (RREG32(EVERGREEN_CRTC_STATUS + crtc_offsets[crtc]) & EVERGREEN_CRTC_V_BLANK)
 				break;
 			udelay(1);
 		}
@@ -310,6 +322,64 @@ void sumo_pm_init_profile(struct radeon_device *rdev)
 }
 
 /**
+ * btc_pm_init_profile - Initialize power profiles callback.
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Initialize the power states used in profile mode
+ * (BTC, cayman).
+ * Used for profile mode only.
+ */
+void btc_pm_init_profile(struct radeon_device *rdev)
+{
+	int idx;
+
+	/* default */
+	rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_off_ps_idx = rdev->pm.default_power_state_index;
+	rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_on_ps_idx = rdev->pm.default_power_state_index;
+	rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_on_cm_idx = 2;
+	/* starting with BTC, there is one state that is used for both
+	 * MH and SH.  Difference is that we always use the high clock index for
+	 * mclk.
+	 */
+	if (rdev->flags & RADEON_IS_MOBILITY)
+		idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
+	else
+		idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
+	/* low sh */
+	rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_cm_idx = 0;
+	/* mid sh */
+	rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_cm_idx = 1;
+	/* high sh */
+	rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_cm_idx = 2;
+	/* low mh */
+	rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_cm_idx = 0;
+	/* mid mh */
+	rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_cm_idx = 1;
+	/* high mh */
+	rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_ps_idx = idx;
+	rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_cm_idx = 0;
+	rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_cm_idx = 2;
+}
+
+/**
  * evergreen_pm_misc - set additional pm hw parameters callback.
  *
  * @rdev: radeon_device pointer
@@ -1105,7 +1175,7 @@ void evergreen_pcie_gart_tlb_flush(struct radeon_device *rdev)
 	}
 }
 
-int evergreen_pcie_gart_enable(struct radeon_device *rdev)
+static int evergreen_pcie_gart_enable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int r;
@@ -1164,7 +1234,7 @@ int evergreen_pcie_gart_enable(struct radeon_device *rdev)
 	return 0;
 }
 
-void evergreen_pcie_gart_disable(struct radeon_device *rdev)
+static void evergreen_pcie_gart_disable(struct radeon_device *rdev)
 {
 	u32 tmp;
 
@@ -1189,7 +1259,7 @@ void evergreen_pcie_gart_disable(struct radeon_device *rdev)
 	radeon_gart_table_vram_unpin(rdev);
 }
 
-void evergreen_pcie_gart_fini(struct radeon_device *rdev)
+static void evergreen_pcie_gart_fini(struct radeon_device *rdev)
 {
 	evergreen_pcie_gart_disable(rdev);
 	radeon_gart_table_vram_free(rdev);
@@ -1197,7 +1267,7 @@ void evergreen_pcie_gart_fini(struct radeon_device *rdev)
 }
 
 
-void evergreen_agp_enable(struct radeon_device *rdev)
+static void evergreen_agp_enable(struct radeon_device *rdev)
 {
 	u32 tmp;
 
@@ -1225,116 +1295,103 @@ void evergreen_agp_enable(struct radeon_device *rdev)
 
 void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save)
 {
+	u32 crtc_enabled, tmp, frame_count, blackout;
+	int i, j;
+
 	save->vga_render_control = RREG32(VGA_RENDER_CONTROL);
 	save->vga_hdp_control = RREG32(VGA_HDP_CONTROL);
 
-	/* Stop all video */
+	/* disable VGA render */
 	WREG32(VGA_RENDER_CONTROL, 0);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 1);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 1);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 1);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 1);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 1);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 1);
-	}
-	WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
-	WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
-	}
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
+	/* blank the display controllers */
+	for (i = 0; i < rdev->num_crtc; i++) {
+		crtc_enabled = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]) & EVERGREEN_CRTC_MASTER_EN;
+		if (crtc_enabled) {
+			save->crtc_enabled[i] = true;
+			if (ASIC_IS_DCE6(rdev)) {
+				tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]);
+				if (!(tmp & EVERGREEN_CRTC_BLANK_DATA_EN)) {
+					radeon_wait_for_vblank(rdev, i);
+					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+				}
+			} else {
+				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
+				if (!(tmp & EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE)) {
+					radeon_wait_for_vblank(rdev, i);
+					tmp |= EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+					WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+				}
+			}
+			/* wait for the next frame */
+			frame_count = radeon_get_vblank_counter(rdev, i);
+			for (j = 0; j < rdev->usec_timeout; j++) {
+				if (radeon_get_vblank_counter(rdev, i) != frame_count)
+					break;
+				udelay(1);
+			}
+		}
 	}
 
-	WREG32(D1VGA_CONTROL, 0);
-	WREG32(D2VGA_CONTROL, 0);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_D3VGA_CONTROL, 0);
-		WREG32(EVERGREEN_D4VGA_CONTROL, 0);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_D5VGA_CONTROL, 0);
-		WREG32(EVERGREEN_D6VGA_CONTROL, 0);
+	radeon_mc_wait_for_idle(rdev);
+
+	blackout = RREG32(MC_SHARED_BLACKOUT_CNTL);
+	if ((blackout & BLACKOUT_MODE_MASK) != 1) {
+		/* Block CPU access */
+		WREG32(BIF_FB_EN, 0);
+		/* blackout the MC */
+		blackout &= ~BLACKOUT_MODE_MASK;
+		WREG32(MC_SHARED_BLACKOUT_CNTL, blackout | 1);
 	}
 }
 
 void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save)
 {
-	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC0_REGISTER_OFFSET,
-	       upper_32_bits(rdev->mc.vram_start));
-	WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC0_REGISTER_OFFSET,
-	       upper_32_bits(rdev->mc.vram_start));
-	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + EVERGREEN_CRTC0_REGISTER_OFFSET,
-	       (u32)rdev->mc.vram_start);
-	WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC0_REGISTER_OFFSET,
-	       (u32)rdev->mc.vram_start);
-
-	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC1_REGISTER_OFFSET,
-	       upper_32_bits(rdev->mc.vram_start));
-	WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC1_REGISTER_OFFSET,
-	       upper_32_bits(rdev->mc.vram_start));
-	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + EVERGREEN_CRTC1_REGISTER_OFFSET,
-	       (u32)rdev->mc.vram_start);
-	WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC1_REGISTER_OFFSET,
-	       (u32)rdev->mc.vram_start);
-
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC2_REGISTER_OFFSET,
-		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC2_REGISTER_OFFSET,
-		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + EVERGREEN_CRTC2_REGISTER_OFFSET,
-		       (u32)rdev->mc.vram_start);
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC2_REGISTER_OFFSET,
-		       (u32)rdev->mc.vram_start);
-
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC3_REGISTER_OFFSET,
-		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC3_REGISTER_OFFSET,
-		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + EVERGREEN_CRTC3_REGISTER_OFFSET,
-		       (u32)rdev->mc.vram_start);
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC3_REGISTER_OFFSET,
-		       (u32)rdev->mc.vram_start);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC4_REGISTER_OFFSET,
-		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC4_REGISTER_OFFSET,
-		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + EVERGREEN_CRTC4_REGISTER_OFFSET,
-		       (u32)rdev->mc.vram_start);
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC4_REGISTER_OFFSET,
-		       (u32)rdev->mc.vram_start);
+	u32 tmp, frame_count;
+	int i, j;
 
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC5_REGISTER_OFFSET,
+	/* update crtc base addresses */
+	for (i = 0; i < rdev->num_crtc; i++) {
+		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + crtc_offsets[i],
 		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + crtc_offsets[i],
 		       upper_32_bits(rdev->mc.vram_start));
-		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + crtc_offsets[i],
 		       (u32)rdev->mc.vram_start);
-		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + crtc_offsets[i],
 		       (u32)rdev->mc.vram_start);
 	}
-
 	WREG32(EVERGREEN_VGA_MEMORY_BASE_ADDRESS_HIGH, upper_32_bits(rdev->mc.vram_start));
 	WREG32(EVERGREEN_VGA_MEMORY_BASE_ADDRESS, (u32)rdev->mc.vram_start);
-	/* Unlock host access */
+
+	/* unblackout the MC */
+	tmp = RREG32(MC_SHARED_BLACKOUT_CNTL);
+	tmp &= ~BLACKOUT_MODE_MASK;
+	WREG32(MC_SHARED_BLACKOUT_CNTL, tmp);
+	/* allow CPU access */
+	WREG32(BIF_FB_EN, FB_READ_EN | FB_WRITE_EN);
+
+	for (i = 0; i < rdev->num_crtc; i++) {
+		if (save->crtc_enabled) {
+			if (ASIC_IS_DCE6(rdev)) {
+				tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]);
+				tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+				WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+			} else {
+				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
+				tmp &= ~EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+				WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+			}
+			/* wait for the next frame */
+			frame_count = radeon_get_vblank_counter(rdev, i);
+			for (j = 0; j < rdev->usec_timeout; j++) {
+				if (radeon_get_vblank_counter(rdev, i) != frame_count)
+					break;
+				udelay(1);
+			}
+		}
+	}
+	/* Unlock vga access */
 	WREG32(VGA_HDP_CONTROL, save->vga_hdp_control);
 	mdelay(1);
 	WREG32(VGA_RENDER_CONTROL, save->vga_render_control);
@@ -1553,7 +1610,7 @@ static int evergreen_cp_start(struct radeon_device *rdev)
 	return 0;
 }
 
-int evergreen_cp_resume(struct radeon_device *rdev)
+static int evergreen_cp_resume(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	u32 tmp;
@@ -2329,22 +2386,10 @@ int evergreen_asic_reset(struct radeon_device *rdev)
 
 u32 evergreen_get_vblank_counter(struct radeon_device *rdev, int crtc)
 {
-	switch (crtc) {
-	case 0:
-		return RREG32(CRTC_STATUS_FRAME_COUNT + EVERGREEN_CRTC0_REGISTER_OFFSET);
-	case 1:
-		return RREG32(CRTC_STATUS_FRAME_COUNT + EVERGREEN_CRTC1_REGISTER_OFFSET);
-	case 2:
-		return RREG32(CRTC_STATUS_FRAME_COUNT + EVERGREEN_CRTC2_REGISTER_OFFSET);
-	case 3:
-		return RREG32(CRTC_STATUS_FRAME_COUNT + EVERGREEN_CRTC3_REGISTER_OFFSET);
-	case 4:
-		return RREG32(CRTC_STATUS_FRAME_COUNT + EVERGREEN_CRTC4_REGISTER_OFFSET);
-	case 5:
-		return RREG32(CRTC_STATUS_FRAME_COUNT + EVERGREEN_CRTC5_REGISTER_OFFSET);
-	default:
+	if (crtc >= rdev->num_crtc)
 		return 0;
-	}
+	else
+		return RREG32(CRTC_STATUS_FRAME_COUNT + crtc_offsets[crtc]);
 }
 
 void evergreen_disable_interrupt_state(struct radeon_device *rdev)
@@ -2537,10 +2582,6 @@ int evergreen_irq_set(struct radeon_device *rdev)
 		DRM_DEBUG("evergreen_irq_set: hdmi 5\n");
 		afmt6 |= AFMT_AZ_FORMAT_WTRIG_MASK;
 	}
-	if (rdev->irq.gui_idle) {
-		DRM_DEBUG("gui idle\n");
-		grbm_int_cntl |= GUI_IDLE_INT_ENABLE;
-	}
 
 	if (rdev->family >= CHIP_CAYMAN) {
 		cayman_cp_int_cntl_setup(rdev, 0, cp_int_cntl);
@@ -2722,7 +2763,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 	}
 }
 
-void evergreen_irq_disable(struct radeon_device *rdev)
+static void evergreen_irq_disable(struct radeon_device *rdev)
 {
 	r600_disable_interrupts(rdev);
 	/* Wait and acknowledge irq */
@@ -3075,7 +3116,6 @@ restart_ih:
 			break;
 		case 233: /* GUI IDLE */
 			DRM_DEBUG("IH: GUI idle\n");
-			wake_up(&rdev->irq.idle_queue);
 			break;
 		default:
 			DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 101acd618f67..573ed1bc6cf7 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -846,6 +846,16 @@ static int evergreen_cs_track_validate_texture(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
+	if (!mipmap) {
+		if (llevel) {
+			dev_warn(p->dev, "%s:%i got NULL MIP_ADDRESS relocation\n",
+				 __func__, __LINE__);
+			return -EINVAL;
+		} else {
+			return 0; /* everything's ok */
+		}
+	}
+
 	/* check mipmap size */
 	for (i = 1; i <= llevel; i++) {
 		unsigned w, h, d;
@@ -995,7 +1005,7 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
  * Assume that chunk_ib_index is properly set. Will return -EINVAL
  * if packet is bigger than remaining ib size. or if packets is unknown.
  **/
-int evergreen_cs_packet_parse(struct radeon_cs_parser *p,
+static int evergreen_cs_packet_parse(struct radeon_cs_parser *p,
 			      struct radeon_cs_packet *pkt,
 			      unsigned idx)
 {
@@ -1081,6 +1091,27 @@ static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
 }
 
 /**
+ * evergreen_cs_packet_next_is_pkt3_nop() - test if the next packet is NOP
+ * @p:		structure holding the parser context.
+ *
+ * Check if the next packet is a relocation packet3.
+ **/
+static bool evergreen_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
+{
+	struct radeon_cs_packet p3reloc;
+	int r;
+
+	r = evergreen_cs_packet_parse(p, &p3reloc, p->idx);
+	if (r) {
+		return false;
+	}
+	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
+		return false;
+	}
+	return true;
+}
+
+/**
  * evergreen_cs_packet_next_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
  *
@@ -2330,7 +2361,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		for (i = 0; i < (pkt->count / 8); i++) {
 			struct radeon_bo *texture, *mipmap;
 			u32 toffset, moffset;
-			u32 size, offset;
+			u32 size, offset, mip_address, tex_dim;
 
 			switch (G__SQ_CONSTANT_TYPE(radeon_get_ib_value(p, idx+1+(i*8)+7))) {
 			case SQ_TEX_VTX_VALID_TEXTURE:
@@ -2359,14 +2390,28 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				}
 				texture = reloc->robj;
 				toffset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+
 				/* tex mip base */
-				r = evergreen_cs_packet_next_reloc(p, &reloc);
-				if (r) {
-					DRM_ERROR("bad SET_RESOURCE (tex)\n");
-					return -EINVAL;
+				tex_dim = ib[idx+1+(i*8)+0] & 0x7;
+				mip_address = ib[idx+1+(i*8)+3];
+
+				if ((tex_dim == SQ_TEX_DIM_2D_MSAA || tex_dim == SQ_TEX_DIM_2D_ARRAY_MSAA) &&
+				    !mip_address &&
+				    !evergreen_cs_packet_next_is_pkt3_nop(p)) {
+					/* MIP_ADDRESS should point to FMASK for an MSAA texture.
+					 * It should be 0 if FMASK is disabled. */
+					moffset = 0;
+					mipmap = NULL;
+				} else {
+					r = evergreen_cs_packet_next_reloc(p, &reloc);
+					if (r) {
+						DRM_ERROR("bad SET_RESOURCE (tex)\n");
+						return -EINVAL;
+					}
+					moffset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+					mipmap = reloc->robj;
 				}
-				moffset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
-				mipmap = reloc->robj;
+
 				r = evergreen_cs_track_validate_texture(p, texture, mipmap, idx+1+(i*8));
 				if (r)
 					return r;
diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h
index 8beac1065025..034f4c22e5db 100644
--- a/drivers/gpu/drm/radeon/evergreen_reg.h
+++ b/drivers/gpu/drm/radeon/evergreen_reg.h
@@ -218,6 +218,8 @@
 #define EVERGREEN_CRTC_CONTROL                          0x6e70
 #       define EVERGREEN_CRTC_MASTER_EN                 (1 << 0)
 #       define EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE (1 << 24)
+#define EVERGREEN_CRTC_BLANK_CONTROL                    0x6e74
+#       define EVERGREEN_CRTC_BLANK_DATA_EN             (1 << 8)
 #define EVERGREEN_CRTC_STATUS                           0x6e8c
 #       define EVERGREEN_CRTC_V_BLANK                   (1 << 0)
 #define EVERGREEN_CRTC_STATUS_POSITION                  0x6e90
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 79347855d9bf..df542f1a5dfb 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -87,6 +87,10 @@
 
 #define	CONFIG_MEMSIZE					0x5428
 
+#define	BIF_FB_EN						0x5490
+#define		FB_READ_EN					(1 << 0)
+#define		FB_WRITE_EN					(1 << 1)
+
 #define	CP_COHER_BASE					0x85F8
 #define	CP_STALLED_STAT1			0x8674
 #define	CP_STALLED_STAT2			0x8678
@@ -430,6 +434,9 @@
 #define		NOOFCHAN_MASK					0x00003000
 #define MC_SHARED_CHREMAP					0x2008
 
+#define MC_SHARED_BLACKOUT_CNTL           		0x20ac
+#define		BLACKOUT_MODE_MASK			0x00000007
+
 #define	MC_ARB_RAMCFG					0x2760
 #define		NOOFBANK_SHIFT					0
 #define		NOOFBANK_MASK					0x00000003
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 174462519f15..8bcb554ea0c5 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -726,7 +726,7 @@ void cayman_pcie_gart_tlb_flush(struct radeon_device *rdev)
 	WREG32(VM_INVALIDATE_REQUEST, 1);
 }
 
-int cayman_pcie_gart_enable(struct radeon_device *rdev)
+static int cayman_pcie_gart_enable(struct radeon_device *rdev)
 {
 	int i, r;
 
@@ -782,7 +782,7 @@ int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 0);
 	WREG32(VM_CONTEXT1_CNTL, 0);
-	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
+	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
 
 	cayman_pcie_gart_tlb_flush(rdev);
@@ -793,7 +793,7 @@ int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	return 0;
 }
 
-void cayman_pcie_gart_disable(struct radeon_device *rdev)
+static void cayman_pcie_gart_disable(struct radeon_device *rdev)
 {
 	/* Disable all tables */
 	WREG32(VM_CONTEXT0_CNTL, 0);
@@ -813,7 +813,7 @@ void cayman_pcie_gart_disable(struct radeon_device *rdev)
 	radeon_gart_table_vram_unpin(rdev);
 }
 
-void cayman_pcie_gart_fini(struct radeon_device *rdev)
+static void cayman_pcie_gart_fini(struct radeon_device *rdev)
 {
 	cayman_pcie_gart_disable(rdev);
 	radeon_gart_table_vram_free(rdev);
@@ -879,12 +879,13 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 #endif
 			  (ib->gpu_addr & 0xFFFFFFFC));
 	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFF);
-	radeon_ring_write(ring, ib->length_dw | (ib->vm_id << 24));
+	radeon_ring_write(ring, ib->length_dw | 
+			  (ib->vm ? (ib->vm->id << 24) : 0));
 
 	/* flush read cache over gart for this vmid */
 	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
 	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, ib->vm_id);
+	radeon_ring_write(ring, ib->vm ? ib->vm->id : 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
 	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
 	radeon_ring_write(ring, 0xFFFFFFFF);
@@ -1004,7 +1005,7 @@ static void cayman_cp_fini(struct radeon_device *rdev)
 	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
-int cayman_cp_resume(struct radeon_device *rdev)
+static int cayman_cp_resume(struct radeon_device *rdev)
 {
 	static const int ridx[] = {
 		RADEON_RING_TYPE_GFX_INDEX,
@@ -1496,53 +1497,16 @@ void cayman_vm_fini(struct radeon_device *rdev)
 {
 }
 
-int cayman_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id)
-{
-	WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (id << 2), 0);
-	WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (id << 2), vm->last_pfn);
-	WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (id << 2), vm->pt_gpu_addr >> 12);
-	/* flush hdp cache */
-	WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
-	/* bits 0-7 are the VM contexts0-7 */
-	WREG32(VM_INVALIDATE_REQUEST, 1 << id);
-	return 0;
-}
-
-void cayman_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (vm->id << 2), 0);
-	WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (vm->id << 2), 0);
-	WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2), 0);
-	/* flush hdp cache */
-	WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
-	/* bits 0-7 are the VM contexts0-7 */
-	WREG32(VM_INVALIDATE_REQUEST, 1 << vm->id);
-}
-
-void cayman_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	if (vm->id == -1)
-		return;
-
-	/* flush hdp cache */
-	WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
-	/* bits 0-7 are the VM contexts0-7 */
-	WREG32(VM_INVALIDATE_REQUEST, 1 << vm->id);
-}
-
-#define R600_PTE_VALID     (1 << 0)
+#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,
-			      struct radeon_vm *vm,
-			      uint32_t flags)
+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_PTE_VALID : 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) {
@@ -1552,12 +1516,76 @@ uint32_t cayman_vm_page_flags(struct radeon_device *rdev,
 	return r600_flags;
 }
 
-void cayman_vm_set_page(struct radeon_device *rdev, struct radeon_vm *vm,
-			unsigned pfn, uint64_t addr, uint32_t flags)
+/**
+ * cayman_vm_set_page - update the page tables using the CP
+ *
+ * @rdev: radeon_device pointer
+ * @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-si).
+ */
+void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
+			uint64_t addr, unsigned count,
+			uint32_t incr, uint32_t flags)
+{
+	struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index];
+	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
+	int i;
+
+	radeon_ring_write(ring, PACKET3(PACKET3_ME_WRITE, 1 + count * 2));
+	radeon_ring_write(ring, pe);
+	radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
+	for (i = 0; i < count; ++i) {
+		uint64_t value = 0;
+		if (flags & RADEON_VM_PAGE_SYSTEM) {
+			value = radeon_vm_map_gart(rdev, addr);
+			value &= 0xFFFFFFFFFFFFF000ULL;
+			addr += incr;
+
+		} else if (flags & RADEON_VM_PAGE_VALID) {
+			value = addr;
+			addr += incr;
+		}
+
+		value |= r600_flags;
+		radeon_ring_write(ring, value);
+		radeon_ring_write(ring, upper_32_bits(value));
+	}
+}
+
+/**
+ * cayman_vm_flush - vm flush using the CP
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Update the page table base and flush the VM TLB
+ * using the CP (cayman-si).
+ */
+void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
-	void __iomem *ptr = (void *)vm->pt;
+	struct radeon_ring *ring = &rdev->ring[ridx];
+
+	if (vm == NULL)
+		return;
+
+	radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (vm->id << 2), 0));
+	radeon_ring_write(ring, 0);
+
+	radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (vm->id << 2), 0));
+	radeon_ring_write(ring, vm->last_pfn);
 
-	addr = addr & 0xFFFFFFFFFFFFF000ULL;
-	addr |= flags;
-	writeq(addr, ptr + (pfn * 8));
+	radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2), 0));
+	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+
+	/* flush hdp cache */
+	radeon_ring_write(ring, PACKET0(HDP_MEM_COHERENCY_FLUSH_CNTL, 0));
+	radeon_ring_write(ring, 0x1);
+
+	/* bits 0-7 are the VM contexts0-7 */
+	radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0));
+	radeon_ring_write(ring, 1 << vm->id);
 }
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index 870db340d377..2423d1b5d385 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -585,6 +585,7 @@
 #define	PACKET3_SET_CONTEXT_REG_INDIRECT		0x73
 #define	PACKET3_SET_RESOURCE_INDIRECT			0x74
 #define	PACKET3_SET_APPEND_CNT			        0x75
+#define	PACKET3_ME_WRITE				0x7A
 
 #endif
 
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 3183a815f71c..376884f1bcd2 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -79,10 +79,12 @@ MODULE_FIRMWARE(FIRMWARE_R520);
  */
 void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
 {
-	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc];
 	int i;
 
-	if (radeon_crtc->crtc_id == 0) {
+	if (crtc >= rdev->num_crtc)
+		return;
+
+	if (crtc == 0) {
 		if (RREG32(RADEON_CRTC_GEN_CNTL) & RADEON_CRTC_EN) {
 			for (i = 0; i < rdev->usec_timeout; i++) {
 				if (!(RREG32(RADEON_CRTC_STATUS) & RADEON_CRTC_VBLANK_CUR))
@@ -697,9 +699,6 @@ int r100_irq_set(struct radeon_device *rdev)
 	if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) {
 		tmp |= RADEON_SW_INT_ENABLE;
 	}
-	if (rdev->irq.gui_idle) {
-		tmp |= RADEON_GUI_IDLE_MASK;
-	}
 	if (rdev->irq.crtc_vblank_int[0] ||
 	    atomic_read(&rdev->irq.pflip[0])) {
 		tmp |= RADEON_CRTC_VBLANK_MASK;
@@ -736,12 +735,6 @@ static uint32_t r100_irq_ack(struct radeon_device *rdev)
 		RADEON_CRTC_VBLANK_STAT | RADEON_CRTC2_VBLANK_STAT |
 		RADEON_FP_DETECT_STAT | RADEON_FP2_DETECT_STAT;
 
-	/* the interrupt works, but the status bit is permanently asserted */
-	if (rdev->irq.gui_idle && radeon_gui_idle(rdev)) {
-		if (!rdev->irq.gui_idle_acked)
-			irq_mask |= RADEON_GUI_IDLE_STAT;
-	}
-
 	if (irqs) {
 		WREG32(RADEON_GEN_INT_STATUS, irqs);
 	}
@@ -753,9 +746,6 @@ int r100_irq_process(struct radeon_device *rdev)
 	uint32_t status, msi_rearm;
 	bool queue_hotplug = false;
 
-	/* reset gui idle ack.  the status bit is broken */
-	rdev->irq.gui_idle_acked = false;
-
 	status = r100_irq_ack(rdev);
 	if (!status) {
 		return IRQ_NONE;
@@ -768,11 +758,6 @@ int r100_irq_process(struct radeon_device *rdev)
 		if (status & RADEON_SW_INT_TEST) {
 			radeon_fence_process(rdev, RADEON_RING_TYPE_GFX_INDEX);
 		}
-		/* gui idle interrupt */
-		if (status & RADEON_GUI_IDLE_STAT) {
-			rdev->irq.gui_idle_acked = true;
-			wake_up(&rdev->irq.idle_queue);
-		}
 		/* Vertical blank interrupts */
 		if (status & RADEON_CRTC_VBLANK_STAT) {
 			if (rdev->irq.crtc_vblank_int[0]) {
@@ -802,8 +787,6 @@ int r100_irq_process(struct radeon_device *rdev)
 		}
 		status = r100_irq_ack(rdev);
 	}
-	/* reset gui idle ack.  the status bit is broken */
-	rdev->irq.gui_idle_acked = false;
 	if (queue_hotplug)
 		schedule_work(&rdev->hotplug_work);
 	if (rdev->msi_enabled) {
@@ -2529,7 +2512,7 @@ void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track
 /*
  * Global GPU functions
  */
-void r100_errata(struct radeon_device *rdev)
+static void r100_errata(struct radeon_device *rdev)
 {
 	rdev->pll_errata = 0;
 
@@ -2544,51 +2527,7 @@ void r100_errata(struct radeon_device *rdev)
 	}
 }
 
-/* Wait for vertical sync on primary CRTC */
-void r100_gpu_wait_for_vsync(struct radeon_device *rdev)
-{
-	uint32_t crtc_gen_cntl, tmp;
-	int i;
-
-	crtc_gen_cntl = RREG32(RADEON_CRTC_GEN_CNTL);
-	if ((crtc_gen_cntl & RADEON_CRTC_DISP_REQ_EN_B) ||
-	    !(crtc_gen_cntl & RADEON_CRTC_EN)) {
-		return;
-	}
-	/* Clear the CRTC_VBLANK_SAVE bit */
-	WREG32(RADEON_CRTC_STATUS, RADEON_CRTC_VBLANK_SAVE_CLEAR);
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = RREG32(RADEON_CRTC_STATUS);
-		if (tmp & RADEON_CRTC_VBLANK_SAVE) {
-			return;
-		}
-		DRM_UDELAY(1);
-	}
-}
-
-/* Wait for vertical sync on secondary CRTC */
-void r100_gpu_wait_for_vsync2(struct radeon_device *rdev)
-{
-	uint32_t crtc2_gen_cntl, tmp;
-	int i;
-
-	crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL);
-	if ((crtc2_gen_cntl & RADEON_CRTC2_DISP_REQ_EN_B) ||
-	    !(crtc2_gen_cntl & RADEON_CRTC2_EN))
-		return;
-
-	/* Clear the CRTC_VBLANK_SAVE bit */
-	WREG32(RADEON_CRTC2_STATUS, RADEON_CRTC2_VBLANK_SAVE_CLEAR);
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = RREG32(RADEON_CRTC2_STATUS);
-		if (tmp & RADEON_CRTC2_VBLANK_SAVE) {
-			return;
-		}
-		DRM_UDELAY(1);
-	}
-}
-
-int r100_rbbm_fifo_wait_for_entry(struct radeon_device *rdev, unsigned n)
+static int r100_rbbm_fifo_wait_for_entry(struct radeon_device *rdev, unsigned n)
 {
 	unsigned i;
 	uint32_t tmp;
@@ -2949,7 +2888,7 @@ void r100_vga_set_state(struct radeon_device *rdev, bool state)
 	WREG32(RADEON_CONFIG_CNTL, temp);
 }
 
-void r100_mc_init(struct radeon_device *rdev)
+static void r100_mc_init(struct radeon_device *rdev)
 {
 	u64 base;
 
@@ -3021,7 +2960,7 @@ void r100_pll_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 	r100_pll_errata_after_data(rdev);
 }
 
-void r100_set_safe_registers(struct radeon_device *rdev)
+static void r100_set_safe_registers(struct radeon_device *rdev)
 {
 	if (ASIC_IS_RN50(rdev)) {
 		rdev->config.r100.reg_safe_bm = rn50_reg_safe_bm;
@@ -3816,9 +3755,10 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
-	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, 256);
+	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, NULL, 256);
 	if (r) {
-		return r;
+		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
+		goto free_scratch;
 	}
 	ib.ptr[0] = PACKET0(scratch, 0);
 	ib.ptr[1] = 0xDEADBEEF;
@@ -3831,13 +3771,13 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	ib.length_dw = 8;
 	r = radeon_ib_schedule(rdev, &ib, NULL);
 	if (r) {
-		radeon_scratch_free(rdev, scratch);
-		radeon_ib_free(rdev, &ib);
-		return r;
+		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
+		goto free_ib;
 	}
 	r = radeon_fence_wait(ib.fence, false);
 	if (r) {
-		return r;
+		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+		goto free_ib;
 	}
 	for (i = 0; i < rdev->usec_timeout; i++) {
 		tmp = RREG32(scratch);
@@ -3853,8 +3793,10 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 			  scratch, tmp);
 		r = -EINVAL;
 	}
-	radeon_scratch_free(rdev, scratch);
+free_ib:
 	radeon_ib_free(rdev, &ib);
+free_scratch:
+	radeon_scratch_free(rdev, scratch);
 	return r;
 }
 
@@ -3963,7 +3905,7 @@ static void r100_mc_program(struct radeon_device *rdev)
 	r100_mc_resume(rdev, &save);
 }
 
-void r100_clock_startup(struct radeon_device *rdev)
+static void r100_clock_startup(struct radeon_device *rdev)
 {
 	u32 tmp;
 
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 1e10df214271..d0ba6023a1f8 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -296,7 +296,7 @@ void r300_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
 	radeon_ring_unlock_commit(rdev, ring);
 }
 
-void r300_errata(struct radeon_device *rdev)
+static void r300_errata(struct radeon_device *rdev)
 {
 	rdev->pll_errata = 0;
 
@@ -322,7 +322,7 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-void r300_gpu_init(struct radeon_device *rdev)
+static void r300_gpu_init(struct radeon_device *rdev)
 {
 	uint32_t gb_tile_config, tmp;
 
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index 90703d539e04..f795a4e092cb 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -119,7 +119,7 @@ static void r520_vram_get_type(struct radeon_device *rdev)
 		rdev->mc.vram_width *= 2;
 }
 
-void r520_mc_init(struct radeon_device *rdev)
+static void r520_mc_init(struct radeon_device *rdev)
 {
 
 	r520_vram_get_type(rdev);
@@ -131,7 +131,7 @@ void r520_mc_init(struct radeon_device *rdev)
 	radeon_update_bandwidth_info(rdev);
 }
 
-void r520_mc_program(struct radeon_device *rdev)
+static void r520_mc_program(struct radeon_device *rdev)
 {
 	struct rv515_mc_save save;
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 9f2cafd10f4a..70c800ff6190 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -98,7 +98,7 @@ int r600_debugfs_mc_info_init(struct radeon_device *rdev);
 
 /* r600,rv610,rv630,rv620,rv635,rv670 */
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
-void r600_gpu_init(struct radeon_device *rdev);
+static void r600_gpu_init(struct radeon_device *rdev);
 void r600_fini(struct radeon_device *rdev);
 void r600_irq_disable(struct radeon_device *rdev);
 static void r600_pcie_gen2_enable(struct radeon_device *rdev);
@@ -881,7 +881,7 @@ int r600_pcie_gart_init(struct radeon_device *rdev)
 	return radeon_gart_table_vram_alloc(rdev);
 }
 
-int r600_pcie_gart_enable(struct radeon_device *rdev)
+static int r600_pcie_gart_enable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int r, i;
@@ -938,7 +938,7 @@ int r600_pcie_gart_enable(struct radeon_device *rdev)
 	return 0;
 }
 
-void r600_pcie_gart_disable(struct radeon_device *rdev)
+static void r600_pcie_gart_disable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int i;
@@ -971,14 +971,14 @@ void r600_pcie_gart_disable(struct radeon_device *rdev)
 	radeon_gart_table_vram_unpin(rdev);
 }
 
-void r600_pcie_gart_fini(struct radeon_device *rdev)
+static void r600_pcie_gart_fini(struct radeon_device *rdev)
 {
 	radeon_gart_fini(rdev);
 	r600_pcie_gart_disable(rdev);
 	radeon_gart_table_vram_free(rdev);
 }
 
-void r600_agp_enable(struct radeon_device *rdev)
+static void r600_agp_enable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int i;
@@ -1158,7 +1158,7 @@ static void r600_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc
 	}
 }
 
-int r600_mc_init(struct radeon_device *rdev)
+static int r600_mc_init(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int chansize, numchan;
@@ -1258,7 +1258,7 @@ void r600_vram_scratch_fini(struct radeon_device *rdev)
  * reset, it's up to the caller to determine if the GPU needs one. We
  * might add an helper function to check that.
  */
-int r600_gpu_soft_reset(struct radeon_device *rdev)
+static int r600_gpu_soft_reset(struct radeon_device *rdev)
 {
 	struct rv515_mc_save save;
 	u32 grbm_busy_mask = S_008010_VC_BUSY(1) | S_008010_VGT_BUSY_NO_DMA(1) |
@@ -1433,7 +1433,7 @@ int r600_count_pipe_bits(uint32_t val)
 	return ret;
 }
 
-void r600_gpu_init(struct radeon_device *rdev)
+static void r600_gpu_init(struct radeon_device *rdev)
 {
 	u32 tiling_config;
 	u32 ramcfg;
@@ -2347,7 +2347,7 @@ void r600_clear_surface_reg(struct radeon_device *rdev, int reg)
 	/* FIXME: implement */
 }
 
-int r600_startup(struct radeon_device *rdev)
+static int r600_startup(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
@@ -2635,10 +2635,10 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
-	r = radeon_ib_get(rdev, ring->idx, &ib, 256);
+	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
 	if (r) {
 		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
-		return r;
+		goto free_scratch;
 	}
 	ib.ptr[0] = PACKET3(PACKET3_SET_CONFIG_REG, 1);
 	ib.ptr[1] = ((scratch - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
@@ -2646,15 +2646,13 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	ib.length_dw = 3;
 	r = radeon_ib_schedule(rdev, &ib, NULL);
 	if (r) {
-		radeon_scratch_free(rdev, scratch);
-		radeon_ib_free(rdev, &ib);
 		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
-		return r;
+		goto free_ib;
 	}
 	r = radeon_fence_wait(ib.fence, false);
 	if (r) {
 		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
-		return r;
+		goto free_ib;
 	}
 	for (i = 0; i < rdev->usec_timeout; i++) {
 		tmp = RREG32(scratch);
@@ -2669,8 +2667,10 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 			  scratch, tmp);
 		r = -EINVAL;
 	}
-	radeon_scratch_free(rdev, scratch);
+free_ib:
 	radeon_ib_free(rdev, &ib);
+free_scratch:
+	radeon_scratch_free(rdev, scratch);
 	return r;
 }
 
@@ -3088,10 +3088,6 @@ int r600_irq_set(struct radeon_device *rdev)
 		DRM_DEBUG("r600_irq_set: hdmi 0\n");
 		hdmi1 |= HDMI0_AZ_FORMAT_WTRIG_MASK;
 	}
-	if (rdev->irq.gui_idle) {
-		DRM_DEBUG("gui idle\n");
-		grbm_int_cntl |= GUI_IDLE_INT_ENABLE;
-	}
 
 	WREG32(CP_INT_CNTL, cp_int_cntl);
 	WREG32(DxMODE_INT_MASK, mode_int);
@@ -3475,7 +3471,6 @@ restart_ih:
 			break;
 		case 233: /* GUI IDLE */
 			DRM_DEBUG("IH: GUI idle\n");
-			wake_up(&rdev->irq.idle_queue);
 			break;
 		default:
 			DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/r600_blit.c b/drivers/gpu/drm/radeon/r600_blit.c
index 26ace5623dc7..77da1f9c0b8e 100644
--- a/drivers/gpu/drm/radeon/r600_blit.c
+++ b/drivers/gpu/drm/radeon/r600_blit.c
@@ -488,31 +488,36 @@ set_default_state(drm_radeon_private_t *dev_priv)
 	ADVANCE_RING();
 }
 
-static uint32_t i2f(uint32_t input)
+/* 23 bits of float fractional data */
+#define I2F_FRAC_BITS  23
+#define I2F_MASK ((1 << I2F_FRAC_BITS) - 1)
+
+/*
+ * Converts unsigned integer into 32-bit IEEE floating point representation.
+ * Will be exact from 0 to 2^24.  Above that, we round towards zero
+ * as the fractional bits will not fit in a float.  (It would be better to
+ * round towards even as the fpu does, but that is slower.)
+ */
+__pure uint32_t int2float(uint32_t x)
 {
-	u32 result, i, exponent, fraction;
-
-	if ((input & 0x3fff) == 0)
-		result = 0; /* 0 is a special case */
-	else {
-		exponent = 140; /* exponent biased by 127; */
-		fraction = (input & 0x3fff) << 10; /* cheat and only
-						      handle numbers below 2^^15 */
-		for (i = 0; i < 14; i++) {
-			if (fraction & 0x800000)
-				break;
-			else {
-				fraction = fraction << 1; /* keep
-							     shifting left until top bit = 1 */
-				exponent = exponent - 1;
-			}
-		}
-		result = exponent << 23 | (fraction & 0x7fffff); /* mask
-								    off top bit; assumed 1 */
-	}
-	return result;
-}
+	uint32_t msb, exponent, fraction;
+
+	/* Zero is special */
+	if (!x) return 0;
+
+	/* Get location of the most significant bit */
+	msb = __fls(x);
 
+	/*
+	 * Use a rotate instead of a shift because that works both leftwards
+	 * and rightwards due to the mod(32) behaviour.  This means we don't
+	 * need to check to see if we are above 2^24 or not.
+	 */
+	fraction = ror32(x, (msb - I2F_FRAC_BITS) & 0x1f) & I2F_MASK;
+	exponent = (127 + msb) << I2F_FRAC_BITS;
+
+	return fraction + exponent;
+}
 
 static int r600_nomm_get_vb(struct drm_device *dev)
 {
@@ -631,20 +636,20 @@ r600_blit_copy(struct drm_device *dev,
 				vb = r600_nomm_get_vb_ptr(dev);
 			}
 
-			vb[0] = i2f(dst_x);
+			vb[0] = int2float(dst_x);
 			vb[1] = 0;
-			vb[2] = i2f(src_x);
+			vb[2] = int2float(src_x);
 			vb[3] = 0;
 
-			vb[4] = i2f(dst_x);
-			vb[5] = i2f(h);
-			vb[6] = i2f(src_x);
-			vb[7] = i2f(h);
+			vb[4] = int2float(dst_x);
+			vb[5] = int2float(h);
+			vb[6] = int2float(src_x);
+			vb[7] = int2float(h);
 
-			vb[8] = i2f(dst_x + cur_size);
-			vb[9] = i2f(h);
-			vb[10] = i2f(src_x + cur_size);
-			vb[11] = i2f(h);
+			vb[8] = int2float(dst_x + cur_size);
+			vb[9] = int2float(h);
+			vb[10] = int2float(src_x + cur_size);
+			vb[11] = int2float(h);
 
 			/* src */
 			set_tex_resource(dev_priv, FMT_8,
@@ -720,20 +725,20 @@ r600_blit_copy(struct drm_device *dev,
 				vb = r600_nomm_get_vb_ptr(dev);
 			}
 
-			vb[0] = i2f(dst_x / 4);
+			vb[0] = int2float(dst_x / 4);
 			vb[1] = 0;
-			vb[2] = i2f(src_x / 4);
+			vb[2] = int2float(src_x / 4);
 			vb[3] = 0;
 
-			vb[4] = i2f(dst_x / 4);
-			vb[5] = i2f(h);
-			vb[6] = i2f(src_x / 4);
-			vb[7] = i2f(h);
+			vb[4] = int2float(dst_x / 4);
+			vb[5] = int2float(h);
+			vb[6] = int2float(src_x / 4);
+			vb[7] = int2float(h);
 
-			vb[8] = i2f((dst_x + cur_size) / 4);
-			vb[9] = i2f(h);
-			vb[10] = i2f((src_x + cur_size) / 4);
-			vb[11] = i2f(h);
+			vb[8] = int2float((dst_x + cur_size) / 4);
+			vb[9] = int2float(h);
+			vb[10] = int2float((src_x + cur_size) / 4);
+			vb[11] = int2float(h);
 
 			/* src */
 			set_tex_resource(dev_priv, FMT_8_8_8_8,
@@ -803,20 +808,20 @@ r600_blit_swap(struct drm_device *dev,
 	dx2 = dx + w;
 	dy2 = dy + h;
 
-	vb[0] = i2f(dx);
-	vb[1] = i2f(dy);
-	vb[2] = i2f(sx);
-	vb[3] = i2f(sy);
+	vb[0] = int2float(dx);
+	vb[1] = int2float(dy);
+	vb[2] = int2float(sx);
+	vb[3] = int2float(sy);
 
-	vb[4] = i2f(dx);
-	vb[5] = i2f(dy2);
-	vb[6] = i2f(sx);
-	vb[7] = i2f(sy2);
+	vb[4] = int2float(dx);
+	vb[5] = int2float(dy2);
+	vb[6] = int2float(sx);
+	vb[7] = int2float(sy2);
 
-	vb[8] = i2f(dx2);
-	vb[9] = i2f(dy2);
-	vb[10] = i2f(sx2);
-	vb[11] = i2f(sy2);
+	vb[8] = int2float(dx2);
+	vb[9] = int2float(dy2);
+	vb[10] = int2float(sx2);
+	vb[11] = int2float(sy2);
 
 	switch(cpp) {
 	case 4:
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index aec8487662c4..e082dca6feee 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -454,46 +454,6 @@ set_default_state(struct radeon_device *rdev)
 	radeon_ring_write(ring, sq_stack_resource_mgmt_2);
 }
 
-#define I2F_MAX_BITS 15
-#define I2F_MAX_INPUT  ((1 << I2F_MAX_BITS) - 1)
-#define I2F_SHIFT (24 - I2F_MAX_BITS)
-
-/*
- * Converts unsigned integer into 32-bit IEEE floating point representation.
- * Conversion is not universal and only works for the range from 0
- * to 2^I2F_MAX_BITS-1. Currently we only use it with inputs between
- * 0 and 16384 (inclusive), so I2F_MAX_BITS=15 is enough. If necessary,
- * I2F_MAX_BITS can be increased, but that will add to the loop iterations
- * and slow us down. Conversion is done by shifting the input and counting
- * down until the first 1 reaches bit position 23. The resulting counter
- * and the shifted input are, respectively, the exponent and the fraction.
- * The sign is always zero.
- */
-static uint32_t i2f(uint32_t input)
-{
-	u32 result, i, exponent, fraction;
-
-	WARN_ON_ONCE(input > I2F_MAX_INPUT);
-
-	if ((input & I2F_MAX_INPUT) == 0)
-		result = 0;
-	else {
-		exponent = 126 + I2F_MAX_BITS;
-		fraction = (input & I2F_MAX_INPUT) << I2F_SHIFT;
-
-		for (i = 0; i < I2F_MAX_BITS; i++) {
-			if (fraction & 0x800000)
-				break;
-			else {
-				fraction = fraction << 1;
-				exponent = exponent - 1;
-			}
-		}
-		result = exponent << 23 | (fraction & 0x7fffff);
-	}
-	return result;
-}
-
 int r600_blit_init(struct radeon_device *rdev)
 {
 	u32 obj_size;
@@ -765,14 +725,14 @@ void r600_kms_blit_copy(struct radeon_device *rdev,
 		vb_cpu_addr[3] = 0;
 
 		vb_cpu_addr[4] = 0;
-		vb_cpu_addr[5] = i2f(h);
+		vb_cpu_addr[5] = int2float(h);
 		vb_cpu_addr[6] = 0;
-		vb_cpu_addr[7] = i2f(h);
+		vb_cpu_addr[7] = int2float(h);
 
-		vb_cpu_addr[8] = i2f(w);
-		vb_cpu_addr[9] = i2f(h);
-		vb_cpu_addr[10] = i2f(w);
-		vb_cpu_addr[11] = i2f(h);
+		vb_cpu_addr[8] = int2float(w);
+		vb_cpu_addr[9] = int2float(h);
+		vb_cpu_addr[10] = int2float(w);
+		vb_cpu_addr[11] = int2float(h);
 
 		rdev->r600_blit.primitives.set_tex_resource(rdev, FMT_8_8_8_8,
 							    w, h, w, src_gpu_addr, size_in_bytes);
diff --git a/drivers/gpu/drm/radeon/r600_blit_shaders.h b/drivers/gpu/drm/radeon/r600_blit_shaders.h
index f437d36dd98c..2f3ce7a75976 100644
--- a/drivers/gpu/drm/radeon/r600_blit_shaders.h
+++ b/drivers/gpu/drm/radeon/r600_blit_shaders.h
@@ -35,4 +35,5 @@ extern const u32 r6xx_default_state[];
 extern const u32 r6xx_ps_size, r6xx_vs_size;
 extern const u32 r6xx_default_size, r7xx_default_size;
 
+__pure uint32_t int2float(uint32_t x);
 #endif
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index cb92646a5e55..211c40252fe0 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -847,7 +847,7 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
  * Assume that chunk_ib_index is properly set. Will return -EINVAL
  * if packet is bigger than remaining ib size. or if packets is unknown.
  **/
-int r600_cs_packet_parse(struct radeon_cs_parser *p,
+static int r600_cs_packet_parse(struct radeon_cs_parser *p,
 			struct radeon_cs_packet *pkt,
 			unsigned idx)
 {
@@ -2180,7 +2180,8 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		}
 		break;
 	case PACKET3_STRMOUT_BASE_UPDATE:
-		if (p->family < CHIP_RV770) {
+		/* RS780 and RS880 also need this */
+		if (p->family < CHIP_RS780) {
 			DRM_ERROR("STRMOUT_BASE_UPDATE only supported on 7xx\n");
 			return -EINVAL;
 		}
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 23be9319c729..ff80efe9cb7d 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -53,7 +53,7 @@ enum r600_hdmi_iec_status_bits {
 	AUDIO_STATUS_LEVEL        = 0x80
 };
 
-struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
+static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
     /*	     32kHz	  44.1kHz	48kHz    */
     /* Clock      N     CTS      N     CTS      N     CTS */
     {  25174,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 59a15315ae9f..b04c06444d8b 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -123,6 +123,7 @@ extern int radeon_lockup_timeout;
 #define CAYMAN_RING_TYPE_CP2_INDEX		2
 
 /* hardcode those limit for now */
+#define RADEON_VA_IB_OFFSET			(1 << 20)
 #define RADEON_VA_RESERVED_SIZE			(8 << 20)
 #define RADEON_IB_VM_MAX_SIZE			(64 << 10)
 
@@ -253,6 +254,22 @@ static inline struct radeon_fence *radeon_fence_later(struct radeon_fence *a,
 	}
 }
 
+static inline bool radeon_fence_is_earlier(struct radeon_fence *a,
+					   struct radeon_fence *b)
+{
+	if (!a) {
+		return false;
+	}
+
+	if (!b) {
+		return true;
+	}
+
+	BUG_ON(a->ring != b->ring);
+
+	return a->seq < b->seq;
+}
+
 /*
  * Tiling registers
  */
@@ -275,18 +292,20 @@ struct radeon_mman {
 
 /* bo virtual address in a specific vm */
 struct radeon_bo_va {
-	/* bo list is protected by bo being reserved */
+	/* protected by bo being reserved */
 	struct list_head		bo_list;
-	/* vm list is protected by vm mutex */
-	struct list_head		vm_list;
-	/* constant after initialization */
-	struct radeon_vm		*vm;
-	struct radeon_bo		*bo;
 	uint64_t			soffset;
 	uint64_t			eoffset;
 	uint32_t			flags;
-	struct radeon_fence		*fence;
 	bool				valid;
+	unsigned			ref_count;
+
+	/* protected by vm mutex */
+	struct list_head		vm_list;
+
+	/* constant after initialization */
+	struct radeon_vm		*vm;
+	struct radeon_bo		*bo;
 };
 
 struct radeon_bo {
@@ -566,9 +585,6 @@ struct radeon_irq {
 	atomic_t			pflip[RADEON_MAX_CRTCS];
 	wait_queue_head_t		vblank_queue;
 	bool				hpd[RADEON_MAX_HPD_PINS];
-	bool				gui_idle;
-	bool				gui_idle_acked;
-	wait_queue_head_t		idle_queue;
 	bool				afmt[RADEON_MAX_AFMT_BLOCKS];
 	union radeon_irq_stat_regs	stat_regs;
 };
@@ -583,7 +599,6 @@ void radeon_irq_kms_enable_afmt(struct radeon_device *rdev, int block);
 void radeon_irq_kms_disable_afmt(struct radeon_device *rdev, int block);
 void radeon_irq_kms_enable_hpd(struct radeon_device *rdev, unsigned hpd_mask);
 void radeon_irq_kms_disable_hpd(struct radeon_device *rdev, unsigned hpd_mask);
-int radeon_irq_kms_wait_gui_idle(struct radeon_device *rdev);
 
 /*
  * CP & rings.
@@ -596,7 +611,7 @@ struct radeon_ib {
 	uint32_t			*ptr;
 	int				ring;
 	struct radeon_fence		*fence;
-	unsigned			vm_id;
+	struct radeon_vm		*vm;
 	bool				is_const_ib;
 	struct radeon_fence		*sync_to[RADEON_NUM_RINGS];
 	struct radeon_semaphore		*semaphore;
@@ -632,41 +647,38 @@ struct radeon_ring {
 /*
  * VM
  */
+
+/* maximum number of VMIDs */
+#define RADEON_NUM_VM	16
+
+/* defines number of bits in page table versus page directory,
+ * a page is 4KB so we have 12 bits offset, 9 bits in the page
+ * table and the remaining 19 bits are in the page directory */
+#define RADEON_VM_BLOCK_SIZE   9
+
+/* number of entries in page table */
+#define RADEON_VM_PTE_COUNT (1 << RADEON_VM_BLOCK_SIZE)
+
 struct radeon_vm {
 	struct list_head		list;
 	struct list_head		va;
-	int				id;
+	unsigned			id;
 	unsigned			last_pfn;
-	u64				pt_gpu_addr;
-	u64				*pt;
+	u64				pd_gpu_addr;
 	struct radeon_sa_bo		*sa_bo;
 	struct mutex			mutex;
 	/* last fence for cs using this vm */
 	struct radeon_fence		*fence;
-};
-
-struct radeon_vm_funcs {
-	int (*init)(struct radeon_device *rdev);
-	void (*fini)(struct radeon_device *rdev);
-	/* cs mutex must be lock for schedule_ib */
-	int (*bind)(struct radeon_device *rdev, struct radeon_vm *vm, int id);
-	void (*unbind)(struct radeon_device *rdev, struct radeon_vm *vm);
-	void (*tlb_flush)(struct radeon_device *rdev, struct radeon_vm *vm);
-	uint32_t (*page_flags)(struct radeon_device *rdev,
-			       struct radeon_vm *vm,
-			       uint32_t flags);
-	void (*set_page)(struct radeon_device *rdev, struct radeon_vm *vm,
-			unsigned pfn, uint64_t addr, uint32_t flags);
+	/* last flush or NULL if we still need to flush */
+	struct radeon_fence		*last_flush;
 };
 
 struct radeon_vm_manager {
 	struct mutex			lock;
 	struct list_head		lru_vm;
-	uint32_t			use_bitmap;
+	struct radeon_fence		*active[RADEON_NUM_VM];
 	struct radeon_sa_manager	sa_manager;
 	uint32_t			max_pfn;
-	/* fields constant after init */
-	const struct radeon_vm_funcs	*funcs;
 	/* number of VMIDs */
 	unsigned			nvm;
 	/* vram base address for page table entry  */
@@ -738,7 +750,8 @@ struct si_rlc {
 };
 
 int radeon_ib_get(struct radeon_device *rdev, int ring,
-		  struct radeon_ib *ib, unsigned size);
+		  struct radeon_ib *ib, struct radeon_vm *vm,
+		  unsigned size);
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 		       struct radeon_ib *const_ib);
@@ -1131,6 +1144,15 @@ struct radeon_asic {
 		void (*tlb_flush)(struct radeon_device *rdev);
 		int (*set_page)(struct radeon_device *rdev, int i, uint64_t addr);
 	} gart;
+	struct {
+		int (*init)(struct radeon_device *rdev);
+		void (*fini)(struct radeon_device *rdev);
+
+		u32 pt_ring_index;
+		void (*set_page)(struct radeon_device *rdev, uint64_t pe,
+				 uint64_t addr, unsigned count,
+				 uint32_t incr, uint32_t flags);
+	} vm;
 	/* ring specific callbacks */
 	struct {
 		void (*ib_execute)(struct radeon_device *rdev, struct radeon_ib *ib);
@@ -1143,6 +1165,7 @@ struct radeon_asic {
 		int (*ring_test)(struct radeon_device *rdev, struct radeon_ring *cp);
 		int (*ib_test)(struct radeon_device *rdev, struct radeon_ring *cp);
 		bool (*is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
+		void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 	} ring[RADEON_NUM_RINGS];
 	/* irqs */
 	struct {
@@ -1157,6 +1180,10 @@ struct radeon_asic {
 		u32 (*get_vblank_counter)(struct radeon_device *rdev, int crtc);
 		/* wait for vblank */
 		void (*wait_for_vblank)(struct radeon_device *rdev, int crtc);
+		/* set backlight level */
+		void (*set_backlight_level)(struct radeon_encoder *radeon_encoder, u8 level);
+		/* get backlight level */
+		u8 (*get_backlight_level)(struct radeon_encoder *radeon_encoder);
 	} display;
 	/* copy functions for bo handling */
 	struct {
@@ -1428,6 +1455,56 @@ struct r600_vram_scratch {
 	u64				gpu_addr;
 };
 
+/*
+ * ACPI
+ */
+struct radeon_atif_notification_cfg {
+	bool enabled;
+	int command_code;
+};
+
+struct radeon_atif_notifications {
+	bool display_switch;
+	bool expansion_mode_change;
+	bool thermal_state;
+	bool forced_power_state;
+	bool system_power_state;
+	bool display_conf_change;
+	bool px_gfx_switch;
+	bool brightness_change;
+	bool dgpu_display_event;
+};
+
+struct radeon_atif_functions {
+	bool system_params;
+	bool sbios_requests;
+	bool select_active_disp;
+	bool lid_state;
+	bool get_tv_standard;
+	bool set_tv_standard;
+	bool get_panel_expansion_mode;
+	bool set_panel_expansion_mode;
+	bool temperature_change;
+	bool graphics_device_types;
+};
+
+struct radeon_atif {
+	struct radeon_atif_notifications notifications;
+	struct radeon_atif_functions functions;
+	struct radeon_atif_notification_cfg notification_cfg;
+	struct radeon_encoder *encoder_for_bl;
+};
+
+struct radeon_atcs_functions {
+	bool get_ext_state;
+	bool pcie_perf_req;
+	bool pcie_dev_rdy;
+	bool pcie_bus_width;
+};
+
+struct radeon_atcs {
+	struct radeon_atcs_functions functions;
+};
 
 /*
  * Core structure, functions and helpers.
@@ -1520,6 +1597,9 @@ struct radeon_device {
 	/* virtual memory */
 	struct radeon_vm_manager	vm_manager;
 	struct mutex			gpu_clock_mutex;
+	/* ACPI interface */
+	struct radeon_atif		atif;
+	struct radeon_atcs		atcs;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -1683,15 +1763,21 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
 #define radeon_gart_set_page(rdev, i, p) (rdev)->asic->gart.set_page((rdev), (i), (p))
+#define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
+#define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
+#define radeon_asic_vm_set_page(rdev, pe, addr, count, incr, flags) ((rdev)->asic->vm.set_page((rdev), (pe), (addr), (count), (incr), (flags)))
 #define radeon_ring_start(rdev, r, cp) (rdev)->asic->ring[(r)].ring_start((rdev), (cp))
 #define radeon_ring_test(rdev, r, cp) (rdev)->asic->ring[(r)].ring_test((rdev), (cp))
 #define radeon_ib_test(rdev, r, cp) (rdev)->asic->ring[(r)].ib_test((rdev), (cp))
 #define radeon_ring_ib_execute(rdev, r, ib) (rdev)->asic->ring[(r)].ib_execute((rdev), (ib))
 #define radeon_ring_ib_parse(rdev, r, ib) (rdev)->asic->ring[(r)].ib_parse((rdev), (ib))
 #define radeon_ring_is_lockup(rdev, r, cp) (rdev)->asic->ring[(r)].is_lockup((rdev), (cp))
+#define radeon_ring_vm_flush(rdev, r, vm) (rdev)->asic->ring[(r)].vm_flush((rdev), (r), (vm))
 #define radeon_irq_set(rdev) (rdev)->asic->irq.set((rdev))
 #define radeon_irq_process(rdev) (rdev)->asic->irq.process((rdev))
 #define radeon_get_vblank_counter(rdev, crtc) (rdev)->asic->display.get_vblank_counter((rdev), (crtc))
+#define radeon_set_backlight_level(rdev, e, l) (rdev)->asic->display.set_backlight_level((e), (l))
+#define radeon_get_backlight_level(rdev, e) (rdev)->asic->display.get_backlight_level((e))
 #define radeon_fence_ring_emit(rdev, r, fence) (rdev)->asic->ring[(r)].emit_fence((rdev), (fence))
 #define radeon_semaphore_ring_emit(rdev, r, cp, semaphore, emit_wait) (rdev)->asic->ring[(r)].emit_semaphore((rdev), (cp), (semaphore), (emit_wait))
 #define radeon_copy_blit(rdev, s, d, np, f) (rdev)->asic->copy.blit((rdev), (s), (d), (np), (f))
@@ -1759,22 +1845,30 @@ int radeon_vm_manager_init(struct radeon_device *rdev);
 void radeon_vm_manager_fini(struct radeon_device *rdev);
 int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm);
 void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm);
-int radeon_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm);
-void radeon_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
+int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm);
+struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev,
+				       struct radeon_vm *vm, int ring);
+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);
 void radeon_vm_bo_invalidate(struct radeon_device *rdev,
 			     struct radeon_bo *bo);
-int radeon_vm_bo_add(struct radeon_device *rdev,
-		     struct radeon_vm *vm,
-		     struct radeon_bo *bo,
-		     uint64_t offset,
-		     uint32_t flags);
+struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
+				       struct radeon_bo *bo);
+struct radeon_bo_va *radeon_vm_bo_add(struct radeon_device *rdev,
+				      struct radeon_vm *vm,
+				      struct radeon_bo *bo);
+int radeon_vm_bo_set_addr(struct radeon_device *rdev,
+			  struct radeon_bo_va *bo_va,
+			  uint64_t offset,
+			  uint32_t flags);
 int radeon_vm_bo_rmv(struct radeon_device *rdev,
-		     struct radeon_vm *vm,
-		     struct radeon_bo *bo);
+		     struct radeon_bo_va *bo_va);
 
 /* audio */
 void r600_audio_update_hdmi(struct work_struct *work);
@@ -1832,12 +1926,14 @@ extern void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_displ
 extern int ni_init_microcode(struct radeon_device *rdev);
 extern int ni_mc_load_microcode(struct radeon_device *rdev);
 
-/* radeon_acpi.c */ 
-#if defined(CONFIG_ACPI) 
-extern int radeon_acpi_init(struct radeon_device *rdev); 
-#else 
-static inline int radeon_acpi_init(struct radeon_device *rdev) { return 0; } 
-#endif 
+/* radeon_acpi.c */
+#if defined(CONFIG_ACPI)
+extern int radeon_acpi_init(struct radeon_device *rdev);
+extern void radeon_acpi_fini(struct radeon_device *rdev);
+#else
+static inline int radeon_acpi_init(struct radeon_device *rdev) { return 0; }
+static inline void radeon_acpi_fini(struct radeon_device *rdev) { }
+#endif
 
 #include "radeon_object.h"
 
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 215063e1a292..b0a5688c67f8 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -1,33 +1,118 @@
+/*
+ * Copyright 2012 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
+#include <linux/power_supply.h>
 #include <acpi/acpi_drivers.h>
 #include <acpi/acpi_bus.h>
+#include <acpi/video.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include "radeon.h"
+#include "radeon_acpi.h"
+#include "atom.h"
 
 #include <linux/vga_switcheroo.h>
 
+#define ACPI_AC_CLASS           "ac_adapter"
+
+extern void radeon_pm_acpi_event_handler(struct radeon_device *rdev);
+
+struct atif_verify_interface {
+	u16 size;		/* structure size in bytes (includes size field) */
+	u16 version;		/* version */
+	u32 notification_mask;	/* supported notifications mask */
+	u32 function_bits;	/* supported functions bit vector */
+} __packed;
+
+struct atif_system_params {
+	u16 size;		/* structure size in bytes (includes size field) */
+	u32 valid_mask;		/* valid flags mask */
+	u32 flags;		/* flags */
+	u8 command_code;	/* notify command code */
+} __packed;
+
+struct atif_sbios_requests {
+	u16 size;		/* structure size in bytes (includes size field) */
+	u32 pending;		/* pending sbios requests */
+	u8 panel_exp_mode;	/* panel expansion mode */
+	u8 thermal_gfx;		/* thermal state: target gfx controller */
+	u8 thermal_state;	/* thermal state: state id (0: exit state, non-0: state) */
+	u8 forced_power_gfx;	/* forced power state: target gfx controller */
+	u8 forced_power_state;	/* forced power state: state id */
+	u8 system_power_src;	/* system power source */
+	u8 backlight_level;	/* panel backlight level (0-255) */
+} __packed;
+
+#define ATIF_NOTIFY_MASK	0x3
+#define ATIF_NOTIFY_NONE	0
+#define ATIF_NOTIFY_81		1
+#define ATIF_NOTIFY_N		2
+
+struct atcs_verify_interface {
+	u16 size;		/* structure size in bytes (includes size field) */
+	u16 version;		/* version */
+	u32 function_bits;	/* supported functions bit vector */
+} __packed;
+
 /* Call the ATIF method
+ */
+/**
+ * radeon_atif_call - call an ATIF method
  *
- * Note: currently we discard the output
+ * @handle: acpi handle
+ * @function: the ATIF function to execute
+ * @params: ATIF function params
+ *
+ * Executes the requested ATIF function (all asics).
+ * Returns a pointer to the acpi output buffer.
  */
-static int radeon_atif_call(acpi_handle handle)
+static union acpi_object *radeon_atif_call(acpi_handle handle, int function,
+		struct acpi_buffer *params)
 {
 	acpi_status status;
 	union acpi_object atif_arg_elements[2];
 	struct acpi_object_list atif_arg;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 
 	atif_arg.count = 2;
 	atif_arg.pointer = &atif_arg_elements[0];
 
 	atif_arg_elements[0].type = ACPI_TYPE_INTEGER;
-	atif_arg_elements[0].integer.value = 0;
-	atif_arg_elements[1].type = ACPI_TYPE_INTEGER;
-	atif_arg_elements[1].integer.value = 0;
+	atif_arg_elements[0].integer.value = function;
+
+	if (params) {
+		atif_arg_elements[1].type = ACPI_TYPE_BUFFER;
+		atif_arg_elements[1].buffer.length = params->length;
+		atif_arg_elements[1].buffer.pointer = params->pointer;
+	} else {
+		/* We need a second fake parameter */
+		atif_arg_elements[1].type = ACPI_TYPE_INTEGER;
+		atif_arg_elements[1].integer.value = 0;
+	}
 
 	status = acpi_evaluate_object(handle, "ATIF", &atif_arg, &buffer);
 
@@ -36,17 +121,434 @@ static int radeon_atif_call(acpi_handle handle)
 		DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
 				 acpi_format_exception(status));
 		kfree(buffer.pointer);
-		return 1;
+		return NULL;
 	}
 
-	kfree(buffer.pointer);
-	return 0;
+	return buffer.pointer;
+}
+
+/**
+ * radeon_atif_parse_notification - parse supported notifications
+ *
+ * @n: supported notifications struct
+ * @mask: supported notifications mask from ATIF
+ *
+ * Use the supported notifications mask from ATIF function
+ * ATIF_FUNCTION_VERIFY_INTERFACE to determine what notifications
+ * are supported (all asics).
+ */
+static void radeon_atif_parse_notification(struct radeon_atif_notifications *n, u32 mask)
+{
+	n->display_switch = mask & ATIF_DISPLAY_SWITCH_REQUEST_SUPPORTED;
+	n->expansion_mode_change = mask & ATIF_EXPANSION_MODE_CHANGE_REQUEST_SUPPORTED;
+	n->thermal_state = mask & ATIF_THERMAL_STATE_CHANGE_REQUEST_SUPPORTED;
+	n->forced_power_state = mask & ATIF_FORCED_POWER_STATE_CHANGE_REQUEST_SUPPORTED;
+	n->system_power_state = mask & ATIF_SYSTEM_POWER_SOURCE_CHANGE_REQUEST_SUPPORTED;
+	n->display_conf_change = mask & ATIF_DISPLAY_CONF_CHANGE_REQUEST_SUPPORTED;
+	n->px_gfx_switch = mask & ATIF_PX_GFX_SWITCH_REQUEST_SUPPORTED;
+	n->brightness_change = mask & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST_SUPPORTED;
+	n->dgpu_display_event = mask & ATIF_DGPU_DISPLAY_EVENT_SUPPORTED;
+}
+
+/**
+ * radeon_atif_parse_functions - parse supported functions
+ *
+ * @f: supported functions struct
+ * @mask: supported functions mask from ATIF
+ *
+ * Use the supported functions mask from ATIF function
+ * ATIF_FUNCTION_VERIFY_INTERFACE to determine what functions
+ * are supported (all asics).
+ */
+static void radeon_atif_parse_functions(struct radeon_atif_functions *f, u32 mask)
+{
+	f->system_params = mask & ATIF_GET_SYSTEM_PARAMETERS_SUPPORTED;
+	f->sbios_requests = mask & ATIF_GET_SYSTEM_BIOS_REQUESTS_SUPPORTED;
+	f->select_active_disp = mask & ATIF_SELECT_ACTIVE_DISPLAYS_SUPPORTED;
+	f->lid_state = mask & ATIF_GET_LID_STATE_SUPPORTED;
+	f->get_tv_standard = mask & ATIF_GET_TV_STANDARD_FROM_CMOS_SUPPORTED;
+	f->set_tv_standard = mask & ATIF_SET_TV_STANDARD_IN_CMOS_SUPPORTED;
+	f->get_panel_expansion_mode = mask & ATIF_GET_PANEL_EXPANSION_MODE_FROM_CMOS_SUPPORTED;
+	f->set_panel_expansion_mode = mask & ATIF_SET_PANEL_EXPANSION_MODE_IN_CMOS_SUPPORTED;
+	f->temperature_change = mask & ATIF_TEMPERATURE_CHANGE_NOTIFICATION_SUPPORTED;
+	f->graphics_device_types = mask & ATIF_GET_GRAPHICS_DEVICE_TYPES_SUPPORTED;
+}
+
+/**
+ * radeon_atif_verify_interface - verify ATIF
+ *
+ * @handle: acpi handle
+ * @atif: radeon atif struct
+ *
+ * Execute the ATIF_FUNCTION_VERIFY_INTERFACE ATIF function
+ * to initialize ATIF and determine what features are supported
+ * (all asics).
+ * returns 0 on success, error on failure.
+ */
+static int radeon_atif_verify_interface(acpi_handle handle,
+		struct radeon_atif *atif)
+{
+	union acpi_object *info;
+	struct atif_verify_interface output;
+	size_t size;
+	int err = 0;
+
+	info = radeon_atif_call(handle, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
+	if (!info)
+		return -EIO;
+
+	memset(&output, 0, sizeof(output));
+
+	size = *(u16 *) info->buffer.pointer;
+	if (size < 12) {
+		DRM_INFO("ATIF buffer is too small: %lu\n", size);
+		err = -EINVAL;
+		goto out;
+	}
+	size = min(sizeof(output), size);
+
+	memcpy(&output, info->buffer.pointer, size);
+
+	/* TODO: check version? */
+	DRM_DEBUG_DRIVER("ATIF version %u\n", output.version);
+
+	radeon_atif_parse_notification(&atif->notifications, output.notification_mask);
+	radeon_atif_parse_functions(&atif->functions, output.function_bits);
+
+out:
+	kfree(info);
+	return err;
+}
+
+/**
+ * radeon_atif_get_notification_params - determine notify configuration
+ *
+ * @handle: acpi handle
+ * @n: atif notification configuration struct
+ *
+ * Execute the ATIF_FUNCTION_GET_SYSTEM_PARAMETERS ATIF function
+ * to determine if a notifier is used and if so which one
+ * (all asics).  This is either Notify(VGA, 0x81) or Notify(VGA, n)
+ * where n is specified in the result if a notifier is used.
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atif_get_notification_params(acpi_handle handle,
+		struct radeon_atif_notification_cfg *n)
+{
+	union acpi_object *info;
+	struct atif_system_params params;
+	size_t size;
+	int err = 0;
+
+	info = radeon_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS, NULL);
+	if (!info) {
+		err = -EIO;
+		goto out;
+	}
+
+	size = *(u16 *) info->buffer.pointer;
+	if (size < 10) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	memset(&params, 0, sizeof(params));
+	size = min(sizeof(params), size);
+	memcpy(&params, info->buffer.pointer, size);
+
+	DRM_DEBUG_DRIVER("SYSTEM_PARAMS: mask = %#x, flags = %#x\n",
+			params.flags, params.valid_mask);
+	params.flags = params.flags & params.valid_mask;
+
+	if ((params.flags & ATIF_NOTIFY_MASK) == ATIF_NOTIFY_NONE) {
+		n->enabled = false;
+		n->command_code = 0;
+	} else if ((params.flags & ATIF_NOTIFY_MASK) == ATIF_NOTIFY_81) {
+		n->enabled = true;
+		n->command_code = 0x81;
+	} else {
+		if (size < 11) {
+			err = -EINVAL;
+			goto out;
+		}
+		n->enabled = true;
+		n->command_code = params.command_code;
+	}
+
+out:
+	DRM_DEBUG_DRIVER("Notification %s, command code = %#x\n",
+			(n->enabled ? "enabled" : "disabled"),
+			n->command_code);
+	kfree(info);
+	return err;
+}
+
+/**
+ * radeon_atif_get_sbios_requests - get requested sbios event
+ *
+ * @handle: acpi handle
+ * @req: atif sbios request struct
+ *
+ * Execute the ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS ATIF function
+ * to determine what requests the sbios is making to the driver
+ * (all asics).
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atif_get_sbios_requests(acpi_handle handle,
+		struct atif_sbios_requests *req)
+{
+	union acpi_object *info;
+	size_t size;
+	int count = 0;
+
+	info = radeon_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS, NULL);
+	if (!info)
+		return -EIO;
+
+	size = *(u16 *)info->buffer.pointer;
+	if (size < 0xd) {
+		count = -EINVAL;
+		goto out;
+	}
+	memset(req, 0, sizeof(*req));
+
+	size = min(sizeof(*req), size);
+	memcpy(req, info->buffer.pointer, size);
+	DRM_DEBUG_DRIVER("SBIOS pending requests: %#x\n", req->pending);
+
+	count = hweight32(req->pending);
+
+out:
+	kfree(info);
+	return count;
+}
+
+/**
+ * radeon_atif_handler - handle ATIF notify requests
+ *
+ * @rdev: radeon_device pointer
+ * @event: atif sbios request struct
+ *
+ * Checks the acpi event and if it matches an atif event,
+ * handles it.
+ * Returns NOTIFY code
+ */
+int radeon_atif_handler(struct radeon_device *rdev,
+		struct acpi_bus_event *event)
+{
+	struct radeon_atif *atif = &rdev->atif;
+	struct atif_sbios_requests req;
+	acpi_handle handle;
+	int count;
+
+	DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
+			event->device_class, event->type);
+
+	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
+		return NOTIFY_DONE;
+
+	if (!atif->notification_cfg.enabled ||
+			event->type != atif->notification_cfg.command_code)
+		/* Not our event */
+		return NOTIFY_DONE;
+
+	/* Check pending SBIOS requests */
+	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	count = radeon_atif_get_sbios_requests(handle, &req);
+
+	if (count <= 0)
+		return NOTIFY_DONE;
+
+	DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
+
+	if (req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) {
+		struct radeon_encoder *enc = atif->encoder_for_bl;
+
+		if (enc) {
+			DRM_DEBUG_DRIVER("Changing brightness to %d\n",
+					req.backlight_level);
+
+			radeon_set_backlight_level(rdev, enc, req.backlight_level);
+
+			if (rdev->is_atom_bios) {
+				struct radeon_encoder_atom_dig *dig = enc->enc_priv;
+				backlight_force_update(dig->bl_dev,
+						       BACKLIGHT_UPDATE_HOTKEY);
+			} else {
+				struct radeon_encoder_lvds *dig = enc->enc_priv;
+				backlight_force_update(dig->bl_dev,
+						       BACKLIGHT_UPDATE_HOTKEY);
+			}
+		}
+	}
+	/* TODO: check other events */
+
+	/* We've handled the event, stop the notifier chain. The ACPI interface
+	 * overloads ACPI_VIDEO_NOTIFY_PROBE, we don't want to send that to
+	 * userspace if the event was generated only to signal a SBIOS
+	 * request.
+	 */
+	return NOTIFY_BAD;
+}
+
+/* Call the ATCS method
+ */
+/**
+ * radeon_atcs_call - call an ATCS method
+ *
+ * @handle: acpi handle
+ * @function: the ATCS function to execute
+ * @params: ATCS function params
+ *
+ * Executes the requested ATCS function (all asics).
+ * Returns a pointer to the acpi output buffer.
+ */
+static union acpi_object *radeon_atcs_call(acpi_handle handle, int function,
+					   struct acpi_buffer *params)
+{
+	acpi_status status;
+	union acpi_object atcs_arg_elements[2];
+	struct acpi_object_list atcs_arg;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+
+	atcs_arg.count = 2;
+	atcs_arg.pointer = &atcs_arg_elements[0];
+
+	atcs_arg_elements[0].type = ACPI_TYPE_INTEGER;
+	atcs_arg_elements[0].integer.value = function;
+
+	if (params) {
+		atcs_arg_elements[1].type = ACPI_TYPE_BUFFER;
+		atcs_arg_elements[1].buffer.length = params->length;
+		atcs_arg_elements[1].buffer.pointer = params->pointer;
+	} else {
+		/* We need a second fake parameter */
+		atcs_arg_elements[1].type = ACPI_TYPE_INTEGER;
+		atcs_arg_elements[1].integer.value = 0;
+	}
+
+	status = acpi_evaluate_object(handle, "ATCS", &atcs_arg, &buffer);
+
+	/* Fail only if calling the method fails and ATIF is supported */
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		DRM_DEBUG_DRIVER("failed to evaluate ATCS got %s\n",
+				 acpi_format_exception(status));
+		kfree(buffer.pointer);
+		return NULL;
+	}
+
+	return buffer.pointer;
+}
+
+/**
+ * radeon_atcs_parse_functions - parse supported functions
+ *
+ * @f: supported functions struct
+ * @mask: supported functions mask from ATCS
+ *
+ * Use the supported functions mask from ATCS function
+ * ATCS_FUNCTION_VERIFY_INTERFACE to determine what functions
+ * are supported (all asics).
+ */
+static void radeon_atcs_parse_functions(struct radeon_atcs_functions *f, u32 mask)
+{
+	f->get_ext_state = mask & ATCS_GET_EXTERNAL_STATE_SUPPORTED;
+	f->pcie_perf_req = mask & ATCS_PCIE_PERFORMANCE_REQUEST_SUPPORTED;
+	f->pcie_dev_rdy = mask & ATCS_PCIE_DEVICE_READY_NOTIFICATION_SUPPORTED;
+	f->pcie_bus_width = mask & ATCS_SET_PCIE_BUS_WIDTH_SUPPORTED;
+}
+
+/**
+ * radeon_atcs_verify_interface - verify ATCS
+ *
+ * @handle: acpi handle
+ * @atcs: radeon atcs struct
+ *
+ * Execute the ATCS_FUNCTION_VERIFY_INTERFACE ATCS function
+ * to initialize ATCS and determine what features are supported
+ * (all asics).
+ * returns 0 on success, error on failure.
+ */
+static int radeon_atcs_verify_interface(acpi_handle handle,
+					struct radeon_atcs *atcs)
+{
+	union acpi_object *info;
+	struct atcs_verify_interface output;
+	size_t size;
+	int err = 0;
+
+	info = radeon_atcs_call(handle, ATCS_FUNCTION_VERIFY_INTERFACE, NULL);
+	if (!info)
+		return -EIO;
+
+	memset(&output, 0, sizeof(output));
+
+	size = *(u16 *) info->buffer.pointer;
+	if (size < 8) {
+		DRM_INFO("ATCS buffer is too small: %lu\n", size);
+		err = -EINVAL;
+		goto out;
+	}
+	size = min(sizeof(output), size);
+
+	memcpy(&output, info->buffer.pointer, size);
+
+	/* TODO: check version? */
+	DRM_DEBUG_DRIVER("ATCS version %u\n", output.version);
+
+	radeon_atcs_parse_functions(&atcs->functions, output.function_bits);
+
+out:
+	kfree(info);
+	return err;
+}
+
+/**
+ * radeon_acpi_event - handle notify events
+ *
+ * @nb: notifier block
+ * @val: val
+ * @data: acpi event
+ *
+ * Calls relevant radeon functions in response to various
+ * acpi events.
+ * Returns NOTIFY code
+ */
+static int radeon_acpi_event(struct notifier_block *nb,
+			     unsigned long val,
+			     void *data)
+{
+	struct radeon_device *rdev = container_of(nb, struct radeon_device, acpi_nb);
+	struct acpi_bus_event *entry = (struct acpi_bus_event *)data;
+
+	if (strcmp(entry->device_class, ACPI_AC_CLASS) == 0) {
+		if (power_supply_is_system_supplied() > 0)
+			DRM_DEBUG_DRIVER("pm: AC\n");
+		else
+			DRM_DEBUG_DRIVER("pm: DC\n");
+
+		radeon_pm_acpi_event_handler(rdev);
+	}
+
+	/* Check for pending SBIOS requests */
+	return radeon_atif_handler(rdev, entry);
 }
 
 /* Call all ACPI methods here */
+/**
+ * radeon_acpi_init - init driver acpi support
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Verifies the AMD ACPI interfaces and registers with the acpi
+ * notifier chain (all asics).
+ * Returns 0 on success, error on failure.
+ */
 int radeon_acpi_init(struct radeon_device *rdev)
 {
 	acpi_handle handle;
+	struct radeon_atif *atif = &rdev->atif;
+	struct radeon_atcs *atcs = &rdev->atcs;
 	int ret;
 
 	/* Get the device handle */
@@ -56,11 +558,90 @@ int radeon_acpi_init(struct radeon_device *rdev)
 	if (!ASIC_IS_AVIVO(rdev) || !rdev->bios || !handle)
 		return 0;
 
+	/* Call the ATCS method */
+	ret = radeon_atcs_verify_interface(handle, atcs);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Call to ATCS verify_interface failed: %d\n", ret);
+	}
+
 	/* Call the ATIF method */
-	ret = radeon_atif_call(handle);
-	if (ret)
-		return ret;
+	ret = radeon_atif_verify_interface(handle, atif);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Call to ATIF verify_interface failed: %d\n", ret);
+		goto out;
+	}
+
+	if (atif->notifications.brightness_change) {
+		struct drm_encoder *tmp;
+		struct radeon_encoder *target = NULL;
+
+		/* Find the encoder controlling the brightness */
+		list_for_each_entry(tmp, &rdev->ddev->mode_config.encoder_list,
+				head) {
+			struct radeon_encoder *enc = to_radeon_encoder(tmp);
+
+			if ((enc->devices & (ATOM_DEVICE_LCD_SUPPORT)) &&
+			    enc->enc_priv) {
+				if (rdev->is_atom_bios) {
+					struct radeon_encoder_atom_dig *dig = enc->enc_priv;
+					if (dig->bl_dev) {
+						target = enc;
+						break;
+					}
+				} else {
+					struct radeon_encoder_lvds *dig = enc->enc_priv;
+					if (dig->bl_dev) {
+						target = enc;
+						break;
+					}
+				}
+			}
+		}
+
+		atif->encoder_for_bl = target;
+		if (!target) {
+			/* Brightness change notification is enabled, but we
+			 * didn't find a backlight controller, this should
+			 * never happen.
+			 */
+			DRM_ERROR("Cannot find a backlight controller\n");
+		}
+	}
 
-	return 0;
+	if (atif->functions.sbios_requests && !atif->functions.system_params) {
+		/* XXX check this workraround, if sbios request function is
+		 * present we have to see how it's configured in the system
+		 * params
+		 */
+		atif->functions.system_params = true;
+	}
+
+	if (atif->functions.system_params) {
+		ret = radeon_atif_get_notification_params(handle,
+				&atif->notification_cfg);
+		if (ret) {
+			DRM_DEBUG_DRIVER("Call to GET_SYSTEM_PARAMS failed: %d\n",
+					ret);
+			/* Disable notification */
+			atif->notification_cfg.enabled = false;
+		}
+	}
+
+out:
+	rdev->acpi_nb.notifier_call = radeon_acpi_event;
+	register_acpi_notifier(&rdev->acpi_nb);
+
+	return ret;
 }
 
+/**
+ * radeon_acpi_fini - tear down driver acpi support
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Unregisters with the acpi notifier chain (all asics).
+ */
+void radeon_acpi_fini(struct radeon_device *rdev)
+{
+	unregister_acpi_notifier(&rdev->acpi_nb);
+}
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.h b/drivers/gpu/drm/radeon/radeon_acpi.h
new file mode 100644
index 000000000000..be4af76f213d
--- /dev/null
+++ b/drivers/gpu/drm/radeon/radeon_acpi.h
@@ -0,0 +1,445 @@
+/*
+ * Copyright 2012 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef RADEON_ACPI_H
+#define RADEON_ACPI_H
+
+struct radeon_device;
+struct acpi_bus_event;
+
+int radeon_atif_handler(struct radeon_device *rdev,
+		struct acpi_bus_event *event);
+
+/* AMD hw uses four ACPI control methods:
+ * 1. ATIF
+ * ARG0: (ACPI_INTEGER) function code
+ * ARG1: (ACPI_BUFFER) parameter buffer, 256 bytes
+ * OUTPUT: (ACPI_BUFFER) output buffer, 256 bytes
+ * ATIF provides an entry point for the gfx driver to interact with the sbios.
+ * The AMD ACPI notification mechanism uses Notify (VGA, 0x81) or a custom
+ * notification. Which notification is used as indicated by the ATIF Control
+ * Method GET_SYSTEM_PARAMETERS. When the driver receives Notify (VGA, 0x81) or
+ * a custom notification it invokes ATIF Control Method GET_SYSTEM_BIOS_REQUESTS
+ * to identify pending System BIOS requests and associated parameters. For
+ * example, if one of the pending requests is DISPLAY_SWITCH_REQUEST, the driver
+ * will perform display device detection and invoke ATIF Control Method
+ * SELECT_ACTIVE_DISPLAYS.
+ *
+ * 2. ATPX
+ * ARG0: (ACPI_INTEGER) function code
+ * ARG1: (ACPI_BUFFER) parameter buffer, 256 bytes
+ * OUTPUT: (ACPI_BUFFER) output buffer, 256 bytes
+ * ATPX methods are used on PowerXpress systems to handle mux switching and
+ * discrete GPU power control.
+ *
+ * 3. ATRM
+ * ARG0: (ACPI_INTEGER) offset of vbios rom data
+ * ARG1: (ACPI_BUFFER) size of the buffer to fill (up to 4K).
+ * OUTPUT: (ACPI_BUFFER) output buffer
+ * ATRM provides an interfacess to access the discrete GPU vbios image on
+ * PowerXpress systems with multiple GPUs.
+ *
+ * 4. ATCS
+ * ARG0: (ACPI_INTEGER) function code
+ * ARG1: (ACPI_BUFFER) parameter buffer, 256 bytes
+ * OUTPUT: (ACPI_BUFFER) output buffer, 256 bytes
+ * ATCS provides an interface to AMD chipset specific functionality.
+ *
+ */
+/* ATIF */
+#define ATIF_FUNCTION_VERIFY_INTERFACE                             0x0
+/* ARG0: ATIF_FUNCTION_VERIFY_INTERFACE
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - version
+ * DWORD - supported notifications mask
+ * DWORD - supported functions bit vector
+ */
+/* Notifications mask */
+#       define ATIF_DISPLAY_SWITCH_REQUEST_SUPPORTED               (1 << 0)
+#       define ATIF_EXPANSION_MODE_CHANGE_REQUEST_SUPPORTED        (1 << 1)
+#       define ATIF_THERMAL_STATE_CHANGE_REQUEST_SUPPORTED         (1 << 2)
+#       define ATIF_FORCED_POWER_STATE_CHANGE_REQUEST_SUPPORTED    (1 << 3)
+#       define ATIF_SYSTEM_POWER_SOURCE_CHANGE_REQUEST_SUPPORTED   (1 << 4)
+#       define ATIF_DISPLAY_CONF_CHANGE_REQUEST_SUPPORTED          (1 << 5)
+#       define ATIF_PX_GFX_SWITCH_REQUEST_SUPPORTED                (1 << 6)
+#       define ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST_SUPPORTED      (1 << 7)
+#       define ATIF_DGPU_DISPLAY_EVENT_SUPPORTED                   (1 << 8)
+/* supported functions vector */
+#       define ATIF_GET_SYSTEM_PARAMETERS_SUPPORTED               (1 << 0)
+#       define ATIF_GET_SYSTEM_BIOS_REQUESTS_SUPPORTED            (1 << 1)
+#       define ATIF_SELECT_ACTIVE_DISPLAYS_SUPPORTED              (1 << 2)
+#       define ATIF_GET_LID_STATE_SUPPORTED                       (1 << 3)
+#       define ATIF_GET_TV_STANDARD_FROM_CMOS_SUPPORTED           (1 << 4)
+#       define ATIF_SET_TV_STANDARD_IN_CMOS_SUPPORTED             (1 << 5)
+#       define ATIF_GET_PANEL_EXPANSION_MODE_FROM_CMOS_SUPPORTED  (1 << 6)
+#       define ATIF_SET_PANEL_EXPANSION_MODE_IN_CMOS_SUPPORTED    (1 << 7)
+#       define ATIF_TEMPERATURE_CHANGE_NOTIFICATION_SUPPORTED     (1 << 12)
+#       define ATIF_GET_GRAPHICS_DEVICE_TYPES_SUPPORTED           (1 << 14)
+#define ATIF_FUNCTION_GET_SYSTEM_PARAMETERS                        0x1
+/* ARG0: ATIF_FUNCTION_GET_SYSTEM_PARAMETERS
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * DWORD - valid flags mask
+ * DWORD - flags
+ *
+ * OR
+ *
+ * WORD  - structure size in bytes (includes size field)
+ * DWORD - valid flags mask
+ * DWORD - flags
+ * BYTE  - notify command code
+ *
+ * flags
+ * bits 1:0:
+ * 0 - Notify(VGA, 0x81) is not used for notification
+ * 1 - Notify(VGA, 0x81) is used for notification
+ * 2 - Notify(VGA, n) is used for notification where
+ * n (0xd0-0xd9) is specified in notify command code.
+ * bit 2:
+ * 1 - lid changes not reported though int10
+ */
+#define ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS                     0x2
+/* ARG0: ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * DWORD - pending sbios requests
+ * BYTE  - panel expansion mode
+ * BYTE  - thermal state: target gfx controller
+ * BYTE  - thermal state: state id (0: exit state, non-0: state)
+ * BYTE  - forced power state: target gfx controller
+ * BYTE  - forced power state: state id
+ * BYTE  - system power source
+ * BYTE  - panel backlight level (0-255)
+ */
+/* pending sbios requests */
+#       define ATIF_DISPLAY_SWITCH_REQUEST                         (1 << 0)
+#       define ATIF_EXPANSION_MODE_CHANGE_REQUEST                  (1 << 1)
+#       define ATIF_THERMAL_STATE_CHANGE_REQUEST                   (1 << 2)
+#       define ATIF_FORCED_POWER_STATE_CHANGE_REQUEST              (1 << 3)
+#       define ATIF_SYSTEM_POWER_SOURCE_CHANGE_REQUEST             (1 << 4)
+#       define ATIF_DISPLAY_CONF_CHANGE_REQUEST                    (1 << 5)
+#       define ATIF_PX_GFX_SWITCH_REQUEST                          (1 << 6)
+#       define ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST                (1 << 7)
+#       define ATIF_DGPU_DISPLAY_EVENT                             (1 << 8)
+/* panel expansion mode */
+#       define ATIF_PANEL_EXPANSION_DISABLE                        0
+#       define ATIF_PANEL_EXPANSION_FULL                           1
+#       define ATIF_PANEL_EXPANSION_ASPECT                         2
+/* target gfx controller */
+#       define ATIF_TARGET_GFX_SINGLE                              0
+#       define ATIF_TARGET_GFX_PX_IGPU                             1
+#       define ATIF_TARGET_GFX_PX_DGPU                             2
+/* system power source */
+#       define ATIF_POWER_SOURCE_AC                                1
+#       define ATIF_POWER_SOURCE_DC                                2
+#       define ATIF_POWER_SOURCE_RESTRICTED_AC_1                   3
+#       define ATIF_POWER_SOURCE_RESTRICTED_AC_2                   4
+#define ATIF_FUNCTION_SELECT_ACTIVE_DISPLAYS                       0x3
+/* ARG0: ATIF_FUNCTION_SELECT_ACTIVE_DISPLAYS
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - selected displays
+ * WORD  - connected displays
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - selected displays
+ */
+#       define ATIF_LCD1                                           (1 << 0)
+#       define ATIF_CRT1                                           (1 << 1)
+#       define ATIF_TV                                             (1 << 2)
+#       define ATIF_DFP1                                           (1 << 3)
+#       define ATIF_CRT2                                           (1 << 4)
+#       define ATIF_LCD2                                           (1 << 5)
+#       define ATIF_DFP2                                           (1 << 7)
+#       define ATIF_CV                                             (1 << 8)
+#       define ATIF_DFP3                                           (1 << 9)
+#       define ATIF_DFP4                                           (1 << 10)
+#       define ATIF_DFP5                                           (1 << 11)
+#       define ATIF_DFP6                                           (1 << 12)
+#define ATIF_FUNCTION_GET_LID_STATE                                0x4
+/* ARG0: ATIF_FUNCTION_GET_LID_STATE
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - lid state (0: open, 1: closed)
+ *
+ * GET_LID_STATE only works at boot and resume, for general lid
+ * status, use the kernel provided status
+ */
+#define ATIF_FUNCTION_GET_TV_STANDARD_FROM_CMOS                    0x5
+/* ARG0: ATIF_FUNCTION_GET_TV_STANDARD_FROM_CMOS
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - 0
+ * BYTE  - TV standard
+ */
+#       define ATIF_TV_STD_NTSC                                    0
+#       define ATIF_TV_STD_PAL                                     1
+#       define ATIF_TV_STD_PALM                                    2
+#       define ATIF_TV_STD_PAL60                                   3
+#       define ATIF_TV_STD_NTSCJ                                   4
+#       define ATIF_TV_STD_PALCN                                   5
+#       define ATIF_TV_STD_PALN                                    6
+#       define ATIF_TV_STD_SCART_RGB                               9
+#define ATIF_FUNCTION_SET_TV_STANDARD_IN_CMOS                      0x6
+/* ARG0: ATIF_FUNCTION_SET_TV_STANDARD_IN_CMOS
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - 0
+ * BYTE  - TV standard
+ * OUTPUT: none
+ */
+#define ATIF_FUNCTION_GET_PANEL_EXPANSION_MODE_FROM_CMOS           0x7
+/* ARG0: ATIF_FUNCTION_GET_PANEL_EXPANSION_MODE_FROM_CMOS
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - panel expansion mode
+ */
+#define ATIF_FUNCTION_SET_PANEL_EXPANSION_MODE_IN_CMOS             0x8
+/* ARG0: ATIF_FUNCTION_SET_PANEL_EXPANSION_MODE_IN_CMOS
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - panel expansion mode
+ * OUTPUT: none
+ */
+#define ATIF_FUNCTION_TEMPERATURE_CHANGE_NOTIFICATION              0xD
+/* ARG0: ATIF_FUNCTION_TEMPERATURE_CHANGE_NOTIFICATION
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - gfx controller id
+ * BYTE  - current temperature (degress Celsius)
+ * OUTPUT: none
+ */
+#define ATIF_FUNCTION_GET_GRAPHICS_DEVICE_TYPES                    0xF
+/* ARG0: ATIF_FUNCTION_GET_GRAPHICS_DEVICE_TYPES
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - number of gfx devices
+ * WORD  - device structure size in bytes (excludes device size field)
+ * DWORD - flags         \
+ * WORD  - bus number     } repeated structure
+ * WORD  - device number /
+ */
+/* flags */
+#       define ATIF_PX_REMOVABLE_GRAPHICS_DEVICE                   (1 << 0)
+#       define ATIF_XGP_PORT                                       (1 << 1)
+#       define ATIF_VGA_ENABLED_GRAPHICS_DEVICE                    (1 << 2)
+#       define ATIF_XGP_PORT_IN_DOCK                               (1 << 3)
+
+/* ATPX */
+#define ATPX_FUNCTION_VERIFY_INTERFACE                             0x0
+/* ARG0: ATPX_FUNCTION_VERIFY_INTERFACE
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - version
+ * DWORD - supported functions bit vector
+ */
+/* supported functions vector */
+#       define ATPX_GET_PX_PARAMETERS_SUPPORTED                    (1 << 0)
+#       define ATPX_POWER_CONTROL_SUPPORTED                        (1 << 1)
+#       define ATPX_DISPLAY_MUX_CONTROL_SUPPORTED                  (1 << 2)
+#       define ATPX_I2C_MUX_CONTROL_SUPPORTED                      (1 << 3)
+#       define ATPX_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION_SUPPORTED (1 << 4)
+#       define ATPX_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION_SUPPORTED   (1 << 5)
+#       define ATPX_GET_DISPLAY_CONNECTORS_MAPPING_SUPPORTED       (1 << 7)
+#       define ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED          (1 << 8)
+#define ATPX_FUNCTION_GET_PX_PARAMETERS                            0x1
+/* ARG0: ATPX_FUNCTION_GET_PX_PARAMETERS
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * DWORD - valid flags mask
+ * DWORD - flags
+ */
+/* flags */
+#       define ATPX_LVDS_I2C_AVAILABLE_TO_BOTH_GPUS                (1 << 0)
+#       define ATPX_CRT1_I2C_AVAILABLE_TO_BOTH_GPUS                (1 << 1)
+#       define ATPX_DVI1_I2C_AVAILABLE_TO_BOTH_GPUS                (1 << 2)
+#       define ATPX_CRT1_RGB_SIGNAL_MUXED                          (1 << 3)
+#       define ATPX_TV_SIGNAL_MUXED                                (1 << 4)
+#       define ATPX_DFP_SIGNAL_MUXED                               (1 << 5)
+#       define ATPX_SEPARATE_MUX_FOR_I2C                           (1 << 6)
+#       define ATPX_DYNAMIC_PX_SUPPORTED                           (1 << 7)
+#       define ATPX_ACF_NOT_SUPPORTED                              (1 << 8)
+#       define ATPX_FIXED_NOT_SUPPORTED                            (1 << 9)
+#       define ATPX_DYNAMIC_DGPU_POWER_OFF_SUPPORTED               (1 << 10)
+#       define ATPX_DGPU_REQ_POWER_FOR_DISPLAYS                    (1 << 11)
+#define ATPX_FUNCTION_POWER_CONTROL                                0x2
+/* ARG0: ATPX_FUNCTION_POWER_CONTROL
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - dGPU power state (0: power off, 1: power on)
+ * OUTPUT: none
+ */
+#define ATPX_FUNCTION_DISPLAY_MUX_CONTROL                          0x3
+/* ARG0: ATPX_FUNCTION_DISPLAY_MUX_CONTROL
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - display mux control (0: iGPU, 1: dGPU)
+ * OUTPUT: none
+ */
+#       define ATPX_INTEGRATED_GPU                                 0
+#       define ATPX_DISCRETE_GPU                                   1
+#define ATPX_FUNCTION_I2C_MUX_CONTROL                              0x4
+/* ARG0: ATPX_FUNCTION_I2C_MUX_CONTROL
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - i2c/aux/hpd mux control (0: iGPU, 1: dGPU)
+ * OUTPUT: none
+ */
+#define ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION    0x5
+/* ARG0: ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - target gpu (0: iGPU, 1: dGPU)
+ * OUTPUT: none
+ */
+#define ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION      0x6
+/* ARG0: ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - target gpu (0: iGPU, 1: dGPU)
+ * OUTPUT: none
+ */
+#define ATPX_FUNCTION_GET_DISPLAY_CONNECTORS_MAPPING               0x8
+/* ARG0: ATPX_FUNCTION_GET_DISPLAY_CONNECTORS_MAPPING
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - number of display connectors
+ * WORD  - connector structure size in bytes (excludes connector size field)
+ * BYTE  - flags                                                     \
+ * BYTE  - ATIF display vector bit position                           } repeated
+ * BYTE  - adapter id (0: iGPU, 1-n: dGPU ordered by pcie bus number) } structure
+ * WORD  - connector ACPI id                                         /
+ */
+/* flags */
+#       define ATPX_DISPLAY_OUTPUT_SUPPORTED_BY_ADAPTER_ID_DEVICE  (1 << 0)
+#       define ATPX_DISPLAY_HPD_SUPPORTED_BY_ADAPTER_ID_DEVICE     (1 << 1)
+#       define ATPX_DISPLAY_I2C_SUPPORTED_BY_ADAPTER_ID_DEVICE     (1 << 2)
+#define ATPX_FUNCTION_GET_DISPLAY_DETECTION_PORTS                  0x9
+/* ARG0: ATPX_FUNCTION_GET_DISPLAY_DETECTION_PORTS
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - number of HPD/DDC ports
+ * WORD  - port structure size in bytes (excludes port size field)
+ * BYTE  - ATIF display vector bit position \
+ * BYTE  - hpd id                            } reapeated structure
+ * BYTE  - ddc id                           /
+ *
+ * available on A+A systems only
+ */
+/* hpd id */
+#       define ATPX_HPD_NONE                                       0
+#       define ATPX_HPD1                                           1
+#       define ATPX_HPD2                                           2
+#       define ATPX_HPD3                                           3
+#       define ATPX_HPD4                                           4
+#       define ATPX_HPD5                                           5
+#       define ATPX_HPD6                                           6
+/* ddc id */
+#       define ATPX_DDC_NONE                                       0
+#       define ATPX_DDC1                                           1
+#       define ATPX_DDC2                                           2
+#       define ATPX_DDC3                                           3
+#       define ATPX_DDC4                                           4
+#       define ATPX_DDC5                                           5
+#       define ATPX_DDC6                                           6
+#       define ATPX_DDC7                                           7
+#       define ATPX_DDC8                                           8
+
+/* ATCS */
+#define ATCS_FUNCTION_VERIFY_INTERFACE                             0x0
+/* ARG0: ATCS_FUNCTION_VERIFY_INTERFACE
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - version
+ * DWORD - supported functions bit vector
+ */
+/* supported functions vector */
+#       define ATCS_GET_EXTERNAL_STATE_SUPPORTED                   (1 << 0)
+#       define ATCS_PCIE_PERFORMANCE_REQUEST_SUPPORTED             (1 << 1)
+#       define ATCS_PCIE_DEVICE_READY_NOTIFICATION_SUPPORTED       (1 << 2)
+#       define ATCS_SET_PCIE_BUS_WIDTH_SUPPORTED                   (1 << 3)
+#define ATCS_FUNCTION_GET_EXTERNAL_STATE                           0x1
+/* ARG0: ATCS_FUNCTION_GET_EXTERNAL_STATE
+ * ARG1: none
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * DWORD - valid flags mask
+ * DWORD - flags (0: undocked, 1: docked)
+ */
+/* flags */
+#       define ATCS_DOCKED                                         (1 << 0)
+#define ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST                     0x2
+/* ARG0: ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - client id (bit 2-0: func num, 7-3: dev num, 15-8: bus num)
+ * WORD  - valid flags mask
+ * WORD  - flags
+ * BYTE  - request type
+ * BYTE  - performance request
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - return value
+ */
+/* flags */
+#       define ATCS_ADVERTISE_CAPS                                 (1 << 0)
+#       define ATCS_WAIT_FOR_COMPLETION                            (1 << 1)
+/* request type */
+#       define ATCS_PCIE_LINK_SPEED                                1
+/* performance request */
+#       define ATCS_REMOVE                                         0
+#       define ATCS_FORCE_LOW_POWER                                1
+#       define ATCS_PERF_LEVEL_1                                   2 /* PCIE Gen 1 */
+#       define ATCS_PERF_LEVEL_2                                   3 /* PCIE Gen 2 */
+#       define ATCS_PERF_LEVEL_3                                   4 /* PCIE Gen 3 */
+/* return value */
+#       define ATCS_REQUEST_REFUSED                                1
+#       define ATCS_REQUEST_COMPLETE                               2
+#       define ATCS_REQUEST_IN_PROGRESS                            3
+#define ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION               0x3
+/* ARG0: ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION
+ * ARG1: none
+ * OUTPUT: none
+ */
+#define ATCS_FUNCTION_SET_PCIE_BUS_WIDTH                           0x4
+/* ARG0: ATCS_FUNCTION_SET_PCIE_BUS_WIDTH
+ * ARG1:
+ * WORD  - structure size in bytes (includes size field)
+ * WORD  - client id (bit 2-0: func num, 7-3: dev num, 15-8: bus num)
+ * BYTE  - number of active lanes
+ * OUTPUT:
+ * WORD  - structure size in bytes (includes size field)
+ * BYTE  - number of active lanes
+ */
+
+#endif
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 973417c4b014..654520b95ab7 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -198,6 +198,8 @@ static struct radeon_asic r100_asic = {
 		.bandwidth_update = &r100_bandwidth_update,
 		.get_vblank_counter = &r100_get_vblank_counter,
 		.wait_for_vblank = &r100_wait_for_vblank,
+		.set_backlight_level = &radeon_legacy_set_backlight_level,
+		.get_backlight_level = &radeon_legacy_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -272,6 +274,8 @@ static struct radeon_asic r200_asic = {
 		.bandwidth_update = &r100_bandwidth_update,
 		.get_vblank_counter = &r100_get_vblank_counter,
 		.wait_for_vblank = &r100_wait_for_vblank,
+		.set_backlight_level = &radeon_legacy_set_backlight_level,
+		.get_backlight_level = &radeon_legacy_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -346,6 +350,8 @@ static struct radeon_asic r300_asic = {
 		.bandwidth_update = &r100_bandwidth_update,
 		.get_vblank_counter = &r100_get_vblank_counter,
 		.wait_for_vblank = &r100_wait_for_vblank,
+		.set_backlight_level = &radeon_legacy_set_backlight_level,
+		.get_backlight_level = &radeon_legacy_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -420,6 +426,8 @@ static struct radeon_asic r300_asic_pcie = {
 		.bandwidth_update = &r100_bandwidth_update,
 		.get_vblank_counter = &r100_get_vblank_counter,
 		.wait_for_vblank = &r100_wait_for_vblank,
+		.set_backlight_level = &radeon_legacy_set_backlight_level,
+		.get_backlight_level = &radeon_legacy_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -494,6 +502,8 @@ static struct radeon_asic r420_asic = {
 		.bandwidth_update = &r100_bandwidth_update,
 		.get_vblank_counter = &r100_get_vblank_counter,
 		.wait_for_vblank = &r100_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -568,6 +578,8 @@ static struct radeon_asic rs400_asic = {
 		.bandwidth_update = &r100_bandwidth_update,
 		.get_vblank_counter = &r100_get_vblank_counter,
 		.wait_for_vblank = &r100_wait_for_vblank,
+		.set_backlight_level = &radeon_legacy_set_backlight_level,
+		.get_backlight_level = &radeon_legacy_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -642,6 +654,8 @@ static struct radeon_asic rs600_asic = {
 		.bandwidth_update = &rs600_bandwidth_update,
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -716,6 +730,8 @@ static struct radeon_asic rs690_asic = {
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.bandwidth_update = &rs690_bandwidth_update,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -790,6 +806,8 @@ static struct radeon_asic rv515_asic = {
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.bandwidth_update = &rv515_bandwidth_update,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -864,6 +882,8 @@ static struct radeon_asic r520_asic = {
 		.bandwidth_update = &rv515_bandwidth_update,
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r100_copy_blit,
@@ -937,6 +957,8 @@ static struct radeon_asic r600_asic = {
 		.bandwidth_update = &rv515_bandwidth_update,
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1010,6 +1032,8 @@ static struct radeon_asic rs780_asic = {
 		.bandwidth_update = &rs690_bandwidth_update,
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1083,6 +1107,8 @@ static struct radeon_asic rv770_asic = {
 		.bandwidth_update = &rv515_bandwidth_update,
 		.get_vblank_counter = &rs600_get_vblank_counter,
 		.wait_for_vblank = &avivo_wait_for_vblank,
+		.set_backlight_level = &atombios_set_backlight_level,
+		.get_backlight_level = &atombios_get_backlight_level,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1156,6 +1182,8 @@ static struct radeon_asic evergreen_asic = {
 		.bandwidth_update = &evergreen_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,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1229,6 +1257,8 @@ static struct radeon_asic sumo_asic = {
 		.bandwidth_update = &evergreen_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,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1302,6 +1332,8 @@ static struct radeon_asic btc_asic = {
 		.bandwidth_update = &evergreen_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,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1325,7 +1357,7 @@ static struct radeon_asic btc_asic = {
 		.misc = &evergreen_pm_misc,
 		.prepare = &evergreen_pm_prepare,
 		.finish = &evergreen_pm_finish,
-		.init_profile = &r600_pm_init_profile,
+		.init_profile = &btc_pm_init_profile,
 		.get_dynpm_state = &r600_pm_get_dynpm_state,
 		.get_engine_clock = &radeon_atom_get_engine_clock,
 		.set_engine_clock = &radeon_atom_set_engine_clock,
@@ -1342,16 +1374,6 @@ static struct radeon_asic btc_asic = {
 	},
 };
 
-static const struct radeon_vm_funcs cayman_vm_funcs = {
-	.init = &cayman_vm_init,
-	.fini = &cayman_vm_fini,
-	.bind = &cayman_vm_bind,
-	.unbind = &cayman_vm_unbind,
-	.tlb_flush = &cayman_vm_tlb_flush,
-	.page_flags = &cayman_vm_page_flags,
-	.set_page = &cayman_vm_set_page,
-};
-
 static struct radeon_asic cayman_asic = {
 	.init = &cayman_init,
 	.fini = &cayman_fini,
@@ -1366,6 +1388,12 @@ static struct radeon_asic cayman_asic = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
 		.set_page = &rs600_gart_set_page,
 	},
+	.vm = {
+		.init = &cayman_vm_init,
+		.fini = &cayman_vm_fini,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.set_page = &cayman_vm_set_page,
+	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1376,6 +1404,7 @@ static struct radeon_asic cayman_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &evergreen_gpu_is_lockup,
+			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1386,6 +1415,7 @@ static struct radeon_asic cayman_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &evergreen_gpu_is_lockup,
+			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1396,6 +1426,7 @@ static struct radeon_asic cayman_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &evergreen_gpu_is_lockup,
+			.vm_flush = &cayman_vm_flush,
 		}
 	},
 	.irq = {
@@ -1406,6 +1437,8 @@ static struct radeon_asic cayman_asic = {
 		.bandwidth_update = &evergreen_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,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1429,7 +1462,7 @@ static struct radeon_asic cayman_asic = {
 		.misc = &evergreen_pm_misc,
 		.prepare = &evergreen_pm_prepare,
 		.finish = &evergreen_pm_finish,
-		.init_profile = &r600_pm_init_profile,
+		.init_profile = &btc_pm_init_profile,
 		.get_dynpm_state = &r600_pm_get_dynpm_state,
 		.get_engine_clock = &radeon_atom_get_engine_clock,
 		.set_engine_clock = &radeon_atom_set_engine_clock,
@@ -1460,6 +1493,12 @@ static struct radeon_asic trinity_asic = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
 		.set_page = &rs600_gart_set_page,
 	},
+	.vm = {
+		.init = &cayman_vm_init,
+		.fini = &cayman_vm_fini,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.set_page = &cayman_vm_set_page,
+	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1470,6 +1509,7 @@ static struct radeon_asic trinity_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &evergreen_gpu_is_lockup,
+			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1480,6 +1520,7 @@ static struct radeon_asic trinity_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &evergreen_gpu_is_lockup,
+			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1490,6 +1531,7 @@ static struct radeon_asic trinity_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &evergreen_gpu_is_lockup,
+			.vm_flush = &cayman_vm_flush,
 		}
 	},
 	.irq = {
@@ -1500,6 +1542,8 @@ static struct radeon_asic trinity_asic = {
 		.bandwidth_update = &dce6_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,
 	},
 	.copy = {
 		.blit = &r600_copy_blit,
@@ -1540,16 +1584,6 @@ static struct radeon_asic trinity_asic = {
 	},
 };
 
-static const struct radeon_vm_funcs si_vm_funcs = {
-	.init = &si_vm_init,
-	.fini = &si_vm_fini,
-	.bind = &si_vm_bind,
-	.unbind = &si_vm_unbind,
-	.tlb_flush = &si_vm_tlb_flush,
-	.page_flags = &cayman_vm_page_flags,
-	.set_page = &cayman_vm_set_page,
-};
-
 static struct radeon_asic si_asic = {
 	.init = &si_init,
 	.fini = &si_fini,
@@ -1564,6 +1598,12 @@ static struct radeon_asic si_asic = {
 		.tlb_flush = &si_pcie_gart_tlb_flush,
 		.set_page = &rs600_gart_set_page,
 	},
+	.vm = {
+		.init = &si_vm_init,
+		.fini = &si_vm_fini,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.set_page = &si_vm_set_page,
+	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = {
 			.ib_execute = &si_ring_ib_execute,
@@ -1574,6 +1614,7 @@ static struct radeon_asic si_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &si_gpu_is_lockup,
+			.vm_flush = &si_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &si_ring_ib_execute,
@@ -1584,6 +1625,7 @@ static struct radeon_asic si_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &si_gpu_is_lockup,
+			.vm_flush = &si_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &si_ring_ib_execute,
@@ -1594,6 +1636,7 @@ static struct radeon_asic si_asic = {
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
 			.is_lockup = &si_gpu_is_lockup,
+			.vm_flush = &si_vm_flush,
 		}
 	},
 	.irq = {
@@ -1604,6 +1647,8 @@ static struct radeon_asic si_asic = {
 		.bandwidth_update = &dce6_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,
 	},
 	.copy = {
 		.blit = NULL,
@@ -1697,6 +1742,7 @@ int radeon_asic_init(struct radeon_device *rdev)
 			rdev->asic->pm.set_engine_clock = &radeon_legacy_set_engine_clock;
 			rdev->asic->pm.get_memory_clock = &radeon_legacy_get_memory_clock;
 			rdev->asic->pm.set_memory_clock = NULL;
+			rdev->asic->display.set_backlight_level = &radeon_legacy_set_backlight_level;
 		}
 		break;
 	case CHIP_RS400:
@@ -1769,13 +1815,11 @@ int radeon_asic_init(struct radeon_device *rdev)
 		rdev->asic = &cayman_asic;
 		/* set num crtcs */
 		rdev->num_crtc = 6;
-		rdev->vm_manager.funcs = &cayman_vm_funcs;
 		break;
 	case CHIP_ARUBA:
 		rdev->asic = &trinity_asic;
 		/* set num crtcs */
 		rdev->num_crtc = 4;
-		rdev->vm_manager.funcs = &cayman_vm_funcs;
 		break;
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
@@ -1783,7 +1827,6 @@ int radeon_asic_init(struct radeon_device *rdev)
 		rdev->asic = &si_asic;
 		/* set num crtcs */
 		rdev->num_crtc = 6;
-		rdev->vm_manager.funcs = &si_vm_funcs;
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 18c38d14c8cd..5e3a0e5c6be1 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -42,6 +42,12 @@ uint32_t radeon_atom_get_memory_clock(struct radeon_device *rdev);
 void radeon_atom_set_memory_clock(struct radeon_device *rdev, uint32_t mem_clock);
 void radeon_atom_set_clock_gating(struct radeon_device *rdev, int enable);
 
+void atombios_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level);
+u8 atombios_get_backlight_level(struct radeon_encoder *radeon_encoder);
+void radeon_legacy_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level);
+u8 radeon_legacy_get_backlight_level(struct radeon_encoder *radeon_encoder);
+
+
 /*
  * r100,rv100,rs100,rv200,rs200
  */
@@ -389,6 +395,7 @@ void r700_cp_fini(struct radeon_device *rdev);
 struct evergreen_mc_save {
 	u32 vga_render_control;
 	u32 vga_hdp_control;
+	bool crtc_enabled[RADEON_MAX_CRTCS];
 };
 
 void evergreen_pcie_gart_tlb_flush(struct radeon_device *rdev);
@@ -413,6 +420,7 @@ extern void evergreen_pm_misc(struct radeon_device *rdev);
 extern void evergreen_pm_prepare(struct radeon_device *rdev);
 extern void evergreen_pm_finish(struct radeon_device *rdev);
 extern void sumo_pm_init_profile(struct radeon_device *rdev);
+extern void btc_pm_init_profile(struct radeon_device *rdev);
 extern void evergreen_pre_page_flip(struct radeon_device *rdev, int crtc);
 extern u32 evergreen_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
 extern void evergreen_post_page_flip(struct radeon_device *rdev, int crtc);
@@ -435,14 +443,11 @@ int cayman_asic_reset(struct radeon_device *rdev);
 void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int cayman_vm_init(struct radeon_device *rdev);
 void cayman_vm_fini(struct radeon_device *rdev);
-int cayman_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id);
-void cayman_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
-void cayman_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm);
-uint32_t cayman_vm_page_flags(struct radeon_device *rdev,
-			      struct radeon_vm *vm,
-			      uint32_t flags);
-void cayman_vm_set_page(struct radeon_device *rdev, struct radeon_vm *vm,
-			unsigned pfn, uint64_t addr, uint32_t flags);
+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, 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);
 
 /* DCE6 - SI */
@@ -465,9 +470,10 @@ 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);
-int si_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id);
-void si_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
-void si_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm);
+void si_vm_set_page(struct radeon_device *rdev, 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);
 uint64_t si_get_gpu_clock(struct radeon_device *rdev);
 
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index c4b5d0542ee2..f22eb5713528 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1254,6 +1254,10 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 		if (rdev->clock.max_pixel_clock == 0)
 			rdev->clock.max_pixel_clock = 40000;
 
+		/* not technically a clock, but... */
+		rdev->mode_info.firmware_flags =
+			le16_to_cpu(firmware_info->info.usFirmwareCapability.susAccess);
+
 		return true;
 	}
 
@@ -2005,7 +2009,8 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
 	power_info = (union power_info *)(mode_info->atom_context->bios + data_offset);
 
 	/* add the i2c bus for thermal/fan chip */
-	if (power_info->info.ucOverdriveThermalController > 0) {
+	if ((power_info->info.ucOverdriveThermalController > 0) &&
+	    (power_info->info.ucOverdriveThermalController < ARRAY_SIZE(thermal_controller_names))) {
 		DRM_INFO("Possible %s thermal controller at 0x%02x\n",
 			 thermal_controller_names[power_info->info.ucOverdriveThermalController],
 			 power_info->info.ucOverdriveControllerAddress >> 1);
@@ -2209,7 +2214,7 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r
 			   (controller->ucType ==
 			    ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL)) {
 			DRM_INFO("Special thermal controller config\n");
-		} else {
+		} else if (controller->ucType < ARRAY_SIZE(pp_lib_thermal_controller_names)) {
 			DRM_INFO("Possible %s thermal controller at 0x%02x %s fan control\n",
 				 pp_lib_thermal_controller_names[controller->ucType],
 				 controller->ucI2cAddress >> 1,
@@ -2224,6 +2229,12 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r
 				strlcpy(info.type, name, sizeof(info.type));
 				i2c_new_device(&rdev->pm.i2c_bus->adapter, &info);
 			}
+		} else {
+			DRM_INFO("Unknown thermal controller type %d at 0x%02x %s fan control\n",
+				 controller->ucType,
+				 controller->ucI2cAddress >> 1,
+				 (controller->ucFanParameters &
+				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
 		}
 	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 2a2cf0b88a28..582e99449c12 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -12,30 +12,62 @@
 #include <acpi/acpi_bus.h>
 #include <linux/pci.h>
 
-#define ATPX_VERSION 0
-#define ATPX_GPU_PWR 2
-#define ATPX_MUX_SELECT 3
-#define ATPX_I2C_MUX_SELECT 4
-#define ATPX_SWITCH_START 5
-#define ATPX_SWITCH_END 6
-
-#define ATPX_INTEGRATED 0
-#define ATPX_DISCRETE 1
+#include "radeon_acpi.h"
+
+struct radeon_atpx_functions {
+	bool px_params;
+	bool power_cntl;
+	bool disp_mux_cntl;
+	bool i2c_mux_cntl;
+	bool switch_start;
+	bool switch_end;
+	bool disp_connectors_mapping;
+	bool disp_detetion_ports;
+};
 
-#define ATPX_MUX_IGD 0
-#define ATPX_MUX_DISCRETE 1
+struct radeon_atpx {
+	acpi_handle handle;
+	struct radeon_atpx_functions functions;
+};
 
 static struct radeon_atpx_priv {
 	bool atpx_detected;
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
-	acpi_handle atpx_handle;
+	struct radeon_atpx atpx;
 } radeon_atpx_priv;
 
-static int radeon_atpx_get_version(acpi_handle handle)
+struct atpx_verify_interface {
+	u16 size;		/* structure size in bytes (includes size field) */
+	u16 version;		/* version */
+	u32 function_bits;	/* supported functions bit vector */
+} __packed;
+
+struct atpx_power_control {
+	u16 size;
+	u8 dgpu_state;
+} __packed;
+
+struct atpx_mux {
+	u16 size;
+	u16 mux;
+} __packed;
+
+/**
+ * radeon_atpx_call - call an ATPX method
+ *
+ * @handle: acpi handle
+ * @function: the ATPX function to execute
+ * @params: ATPX function params
+ *
+ * Executes the requested ATPX function (all asics).
+ * Returns a pointer to the acpi output buffer.
+ */
+static union acpi_object *radeon_atpx_call(acpi_handle handle, int function,
+					   struct acpi_buffer *params)
 {
 	acpi_status status;
-	union acpi_object atpx_arg_elements[2], *obj;
+	union acpi_object atpx_arg_elements[2];
 	struct acpi_object_list atpx_arg;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 
@@ -43,99 +75,292 @@ static int radeon_atpx_get_version(acpi_handle handle)
 	atpx_arg.pointer = &atpx_arg_elements[0];
 
 	atpx_arg_elements[0].type = ACPI_TYPE_INTEGER;
-	atpx_arg_elements[0].integer.value = ATPX_VERSION;
+	atpx_arg_elements[0].integer.value = function;
+
+	if (params) {
+		atpx_arg_elements[1].type = ACPI_TYPE_BUFFER;
+		atpx_arg_elements[1].buffer.length = params->length;
+		atpx_arg_elements[1].buffer.pointer = params->pointer;
+	} else {
+		/* We need a second fake parameter */
+		atpx_arg_elements[1].type = ACPI_TYPE_INTEGER;
+		atpx_arg_elements[1].integer.value = 0;
+	}
 
-	atpx_arg_elements[1].type = ACPI_TYPE_INTEGER;
-	atpx_arg_elements[1].integer.value = ATPX_VERSION;
+	status = acpi_evaluate_object(handle, "ATPX", &atpx_arg, &buffer);
 
-	status = acpi_evaluate_object(handle, NULL, &atpx_arg, &buffer);
-	if (ACPI_FAILURE(status)) {
-		printk("%s: failed to call ATPX: %s\n", __func__, acpi_format_exception(status));
-		return -ENOSYS;
+	/* Fail only if calling the method fails and ATPX is supported */
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		printk("failed to evaluate ATPX got %s\n",
+		       acpi_format_exception(status));
+		kfree(buffer.pointer);
+		return NULL;
 	}
-	obj = (union acpi_object *)buffer.pointer;
-	if (obj && (obj->type == ACPI_TYPE_BUFFER))
-		printk(KERN_INFO "radeon atpx: version is %d\n", *((u8 *)(obj->buffer.pointer) + 2));
-	kfree(buffer.pointer);
-	return 0;
+
+	return buffer.pointer;
 }
 
-static int radeon_atpx_execute(acpi_handle handle, int cmd_id, u16 value)
+/**
+ * radeon_atpx_parse_functions - parse supported functions
+ *
+ * @f: supported functions struct
+ * @mask: supported functions mask from ATPX
+ *
+ * Use the supported functions mask from ATPX function
+ * ATPX_FUNCTION_VERIFY_INTERFACE to determine what functions
+ * are supported (all asics).
+ */
+static void radeon_atpx_parse_functions(struct radeon_atpx_functions *f, u32 mask)
 {
-	acpi_status status;
-	union acpi_object atpx_arg_elements[2];
-	struct acpi_object_list atpx_arg;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	uint8_t buf[4] = {0};
-
-	if (!handle)
-		return -EINVAL;
-
-	atpx_arg.count = 2;
-	atpx_arg.pointer = &atpx_arg_elements[0];
+	f->px_params = mask & ATPX_GET_PX_PARAMETERS_SUPPORTED;
+	f->power_cntl = mask & ATPX_POWER_CONTROL_SUPPORTED;
+	f->disp_mux_cntl = mask & ATPX_DISPLAY_MUX_CONTROL_SUPPORTED;
+	f->i2c_mux_cntl = mask & ATPX_I2C_MUX_CONTROL_SUPPORTED;
+	f->switch_start = mask & ATPX_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION_SUPPORTED;
+	f->switch_end = mask & ATPX_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION_SUPPORTED;
+	f->disp_connectors_mapping = mask & ATPX_GET_DISPLAY_CONNECTORS_MAPPING_SUPPORTED;
+	f->disp_detetion_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
+}
 
-	atpx_arg_elements[0].type = ACPI_TYPE_INTEGER;
-	atpx_arg_elements[0].integer.value = cmd_id;
+/**
+ * radeon_atpx_verify_interface - verify ATPX
+ *
+ * @handle: acpi handle
+ * @atpx: radeon atpx struct
+ *
+ * Execute the ATPX_FUNCTION_VERIFY_INTERFACE ATPX function
+ * to initialize ATPX and determine what features are supported
+ * (all asics).
+ * returns 0 on success, error on failure.
+ */
+static int radeon_atpx_verify_interface(struct radeon_atpx *atpx)
+{
+	union acpi_object *info;
+	struct atpx_verify_interface output;
+	size_t size;
+	int err = 0;
+
+	info = radeon_atpx_call(atpx->handle, ATPX_FUNCTION_VERIFY_INTERFACE, NULL);
+	if (!info)
+		return -EIO;
+
+	memset(&output, 0, sizeof(output));
+
+	size = *(u16 *) info->buffer.pointer;
+	if (size < 8) {
+		printk("ATPX buffer is too small: %lu\n", size);
+		err = -EINVAL;
+		goto out;
+	}
+	size = min(sizeof(output), size);
 
-	buf[2] = value & 0xff;
-	buf[3] = (value >> 8) & 0xff;
+	memcpy(&output, info->buffer.pointer, size);
 
-	atpx_arg_elements[1].type = ACPI_TYPE_BUFFER;
-	atpx_arg_elements[1].buffer.length = 4;
-	atpx_arg_elements[1].buffer.pointer = buf;
+	/* TODO: check version? */
+	printk("ATPX version %u\n", output.version);
 
-	status = acpi_evaluate_object(handle, NULL, &atpx_arg, &buffer);
-	if (ACPI_FAILURE(status)) {
-		printk("%s: failed to call ATPX: %s\n", __func__, acpi_format_exception(status));
-		return -ENOSYS;
-	}
-	kfree(buffer.pointer);
+	radeon_atpx_parse_functions(&atpx->functions, output.function_bits);
 
-	return 0;
+out:
+	kfree(info);
+	return err;
 }
 
-static int radeon_atpx_set_discrete_state(acpi_handle handle, int state)
+/**
+ * radeon_atpx_set_discrete_state - power up/down discrete GPU
+ *
+ * @atpx: atpx info struct
+ * @state: discrete GPU state (0 = power down, 1 = power up)
+ *
+ * Execute the ATPX_FUNCTION_POWER_CONTROL ATPX function to
+ * power down/up the discrete GPU (all asics).
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atpx_set_discrete_state(struct radeon_atpx *atpx, u8 state)
 {
-	return radeon_atpx_execute(handle, ATPX_GPU_PWR, state);
+	struct acpi_buffer params;
+	union acpi_object *info;
+	struct atpx_power_control input;
+
+	if (atpx->functions.power_cntl) {
+		input.size = 3;
+		input.dgpu_state = state;
+		params.length = input.size;
+		params.pointer = &input;
+		info = radeon_atpx_call(atpx->handle,
+					ATPX_FUNCTION_POWER_CONTROL,
+					&params);
+		if (!info)
+			return -EIO;
+		kfree(info);
+	}
+	return 0;
 }
 
-static int radeon_atpx_switch_mux(acpi_handle handle, int mux_id)
+/**
+ * radeon_atpx_switch_disp_mux - switch display mux
+ *
+ * @atpx: atpx info struct
+ * @mux_id: mux state (0 = integrated GPU, 1 = discrete GPU)
+ *
+ * Execute the ATPX_FUNCTION_DISPLAY_MUX_CONTROL ATPX function to
+ * switch the display mux between the discrete GPU and integrated GPU
+ * (all asics).
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atpx_switch_disp_mux(struct radeon_atpx *atpx, u16 mux_id)
 {
-	return radeon_atpx_execute(handle, ATPX_MUX_SELECT, mux_id);
+	struct acpi_buffer params;
+	union acpi_object *info;
+	struct atpx_mux input;
+
+	if (atpx->functions.disp_mux_cntl) {
+		input.size = 4;
+		input.mux = mux_id;
+		params.length = input.size;
+		params.pointer = &input;
+		info = radeon_atpx_call(atpx->handle,
+					ATPX_FUNCTION_DISPLAY_MUX_CONTROL,
+					&params);
+		if (!info)
+			return -EIO;
+		kfree(info);
+	}
+	return 0;
 }
 
-static int radeon_atpx_switch_i2c_mux(acpi_handle handle, int mux_id)
+/**
+ * radeon_atpx_switch_i2c_mux - switch i2c/hpd mux
+ *
+ * @atpx: atpx info struct
+ * @mux_id: mux state (0 = integrated GPU, 1 = discrete GPU)
+ *
+ * Execute the ATPX_FUNCTION_I2C_MUX_CONTROL ATPX function to
+ * switch the i2c/hpd mux between the discrete GPU and integrated GPU
+ * (all asics).
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atpx_switch_i2c_mux(struct radeon_atpx *atpx, u16 mux_id)
 {
-	return radeon_atpx_execute(handle, ATPX_I2C_MUX_SELECT, mux_id);
+	struct acpi_buffer params;
+	union acpi_object *info;
+	struct atpx_mux input;
+
+	if (atpx->functions.i2c_mux_cntl) {
+		input.size = 4;
+		input.mux = mux_id;
+		params.length = input.size;
+		params.pointer = &input;
+		info = radeon_atpx_call(atpx->handle,
+					ATPX_FUNCTION_I2C_MUX_CONTROL,
+					&params);
+		if (!info)
+			return -EIO;
+		kfree(info);
+	}
+	return 0;
 }
 
-static int radeon_atpx_switch_start(acpi_handle handle, int gpu_id)
+/**
+ * radeon_atpx_switch_start - notify the sbios of a GPU switch
+ *
+ * @atpx: atpx info struct
+ * @mux_id: mux state (0 = integrated GPU, 1 = discrete GPU)
+ *
+ * Execute the ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION ATPX
+ * function to notify the sbios that a switch between the discrete GPU and
+ * integrated GPU has begun (all asics).
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atpx_switch_start(struct radeon_atpx *atpx, u16 mux_id)
 {
-	return radeon_atpx_execute(handle, ATPX_SWITCH_START, gpu_id);
+	struct acpi_buffer params;
+	union acpi_object *info;
+	struct atpx_mux input;
+
+	if (atpx->functions.switch_start) {
+		input.size = 4;
+		input.mux = mux_id;
+		params.length = input.size;
+		params.pointer = &input;
+		info = radeon_atpx_call(atpx->handle,
+					ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION,
+					&params);
+		if (!info)
+			return -EIO;
+		kfree(info);
+	}
+	return 0;
 }
 
-static int radeon_atpx_switch_end(acpi_handle handle, int gpu_id)
+/**
+ * radeon_atpx_switch_end - notify the sbios of a GPU switch
+ *
+ * @atpx: atpx info struct
+ * @mux_id: mux state (0 = integrated GPU, 1 = discrete GPU)
+ *
+ * Execute the ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION ATPX
+ * function to notify the sbios that a switch between the discrete GPU and
+ * integrated GPU has ended (all asics).
+ * Returns 0 on success, error on failure.
+ */
+static int radeon_atpx_switch_end(struct radeon_atpx *atpx, u16 mux_id)
 {
-	return radeon_atpx_execute(handle, ATPX_SWITCH_END, gpu_id);
+	struct acpi_buffer params;
+	union acpi_object *info;
+	struct atpx_mux input;
+
+	if (atpx->functions.switch_end) {
+		input.size = 4;
+		input.mux = mux_id;
+		params.length = input.size;
+		params.pointer = &input;
+		info = radeon_atpx_call(atpx->handle,
+					ATPX_FUNCTION_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION,
+					&params);
+		if (!info)
+			return -EIO;
+		kfree(info);
+	}
+	return 0;
 }
 
+/**
+ * radeon_atpx_switchto - switch to the requested GPU
+ *
+ * @id: GPU to switch to
+ *
+ * Execute the necessary ATPX functions to switch between the discrete GPU and
+ * integrated GPU (all asics).
+ * Returns 0 on success, error on failure.
+ */
 static int radeon_atpx_switchto(enum vga_switcheroo_client_id id)
 {
-	int gpu_id;
+	u16 gpu_id;
 
 	if (id == VGA_SWITCHEROO_IGD)
-		gpu_id = ATPX_INTEGRATED;
+		gpu_id = ATPX_INTEGRATED_GPU;
 	else
-		gpu_id = ATPX_DISCRETE;
+		gpu_id = ATPX_DISCRETE_GPU;
 
-	radeon_atpx_switch_start(radeon_atpx_priv.atpx_handle, gpu_id);
-	radeon_atpx_switch_mux(radeon_atpx_priv.atpx_handle, gpu_id);
-	radeon_atpx_switch_i2c_mux(radeon_atpx_priv.atpx_handle, gpu_id);
-	radeon_atpx_switch_end(radeon_atpx_priv.atpx_handle, gpu_id);
+	radeon_atpx_switch_start(&radeon_atpx_priv.atpx, gpu_id);
+	radeon_atpx_switch_disp_mux(&radeon_atpx_priv.atpx, gpu_id);
+	radeon_atpx_switch_i2c_mux(&radeon_atpx_priv.atpx, gpu_id);
+	radeon_atpx_switch_end(&radeon_atpx_priv.atpx, gpu_id);
 
 	return 0;
 }
 
+/**
+ * radeon_atpx_switchto - switch to the requested GPU
+ *
+ * @id: GPU to switch to
+ * @state: requested power state (0 = off, 1 = on)
+ *
+ * Execute the necessary ATPX function to power down/up the discrete GPU
+ * (all asics).
+ * Returns 0 on success, error on failure.
+ */
 static int radeon_atpx_power_state(enum vga_switcheroo_client_id id,
 				   enum vga_switcheroo_state state)
 {
@@ -143,10 +368,18 @@ static int radeon_atpx_power_state(enum vga_switcheroo_client_id id,
 	if (id == VGA_SWITCHEROO_IGD)
 		return 0;
 
-	radeon_atpx_set_discrete_state(radeon_atpx_priv.atpx_handle, state);
+	radeon_atpx_set_discrete_state(&radeon_atpx_priv.atpx, state);
 	return 0;
 }
 
+/**
+ * radeon_atpx_pci_probe_handle - look up the ATRM and ATPX handles
+ *
+ * @pdev: pci device
+ *
+ * Look up the ATPX and ATRM handles (all asics).
+ * Returns true if the handles are found, false if not.
+ */
 static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 {
 	acpi_handle dhandle, atpx_handle;
@@ -161,18 +394,30 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 		return false;
 
 	radeon_atpx_priv.dhandle = dhandle;
-	radeon_atpx_priv.atpx_handle = atpx_handle;
+	radeon_atpx_priv.atpx.handle = atpx_handle;
 	return true;
 }
 
+/**
+ * radeon_atpx_init - verify the ATPX interface
+ *
+ * Verify the ATPX interface (all asics).
+ * Returns 0 on success, error on failure.
+ */
 static int radeon_atpx_init(void)
 {
 	/* set up the ATPX handle */
-
-	radeon_atpx_get_version(radeon_atpx_priv.atpx_handle);
-	return 0;
+	return radeon_atpx_verify_interface(&radeon_atpx_priv.atpx);
 }
 
+/**
+ * radeon_atpx_get_client_id - get the client id
+ *
+ * @pdev: pci device
+ *
+ * look up whether we are the integrated or discrete GPU (all asics).
+ * Returns the client id.
+ */
 static int radeon_atpx_get_client_id(struct pci_dev *pdev)
 {
 	if (radeon_atpx_priv.dhandle == DEVICE_ACPI_HANDLE(&pdev->dev))
@@ -188,6 +433,12 @@ static struct vga_switcheroo_handler radeon_atpx_handler = {
 	.get_client_id = radeon_atpx_get_client_id,
 };
 
+/**
+ * radeon_atpx_detect - detect whether we have PX
+ *
+ * Check if we have a PX system (all asics).
+ * Returns true if we have a PX system, false if not.
+ */
 static bool radeon_atpx_detect(void)
 {
 	char acpi_method_name[255] = { 0 };
@@ -203,7 +454,7 @@ static bool radeon_atpx_detect(void)
 	}
 
 	if (has_atpx && vga_count == 2) {
-		acpi_get_name(radeon_atpx_priv.atpx_handle, ACPI_FULL_PATHNAME, &buffer);
+		acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		radeon_atpx_priv.atpx_detected = true;
@@ -212,6 +463,11 @@ static bool radeon_atpx_detect(void)
 	return false;
 }
 
+/**
+ * radeon_register_atpx_handler - register with vga_switcheroo
+ *
+ * Register the PX callbacks with vga_switcheroo (all asics).
+ */
 void radeon_register_atpx_handler(void)
 {
 	bool r;
@@ -224,6 +480,11 @@ void radeon_register_atpx_handler(void)
 	vga_switcheroo_register_handler(&radeon_atpx_handler);
 }
 
+/**
+ * radeon_unregister_atpx_handler - unregister with vga_switcheroo
+ *
+ * Unregister the PX callbacks with vga_switcheroo (all asics).
+ */
 void radeon_unregister_atpx_handler(void)
 {
 	vga_switcheroo_unregister_handler();
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index a3900e7bd77b..45b660b27cfc 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -3319,15 +3319,6 @@ static void combios_write_ram_size(struct drm_device *dev)
 	WREG32(RADEON_CONFIG_MEMSIZE, mem_size);
 }
 
-void radeon_combios_dyn_clk_setup(struct drm_device *dev, int enable)
-{
-	uint16_t dyn_clk_info =
-	    combios_get_table_offset(dev, COMBIOS_DYN_CLK_1_TABLE);
-
-	if (dyn_clk_info)
-		combios_parse_pll_table(dev, dyn_clk_info);
-}
-
 void radeon_combios_asic_init(struct drm_device *dev)
 {
 	struct radeon_device *rdev = dev->dev_private;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 3bc22e341719..67cfc1795ecd 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -40,10 +40,6 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector,
 				       struct drm_encoder *encoder,
 				       bool connected);
 
-extern void
-radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
-			     struct drm_connector *drm_connector);
-
 void radeon_connector_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
@@ -198,7 +194,7 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 	}
 }
 
-struct drm_encoder *radeon_find_encoder(struct drm_connector *connector, int encoder_type)
+static struct drm_encoder *radeon_find_encoder(struct drm_connector *connector, int encoder_type)
 {
 	struct drm_mode_object *obj;
 	struct drm_encoder *encoder;
@@ -219,7 +215,7 @@ struct drm_encoder *radeon_find_encoder(struct drm_connector *connector, int enc
 	return NULL;
 }
 
-struct drm_encoder *radeon_best_single_encoder(struct drm_connector *connector)
+static struct drm_encoder *radeon_best_single_encoder(struct drm_connector *connector)
 {
 	int enc_id = connector->encoder_ids[0];
 	struct drm_mode_object *obj;
@@ -370,7 +366,7 @@ static void radeon_add_common_modes(struct drm_encoder *encoder, struct drm_conn
 	}
 }
 
-int radeon_connector_set_property(struct drm_connector *connector, struct drm_property *property,
+static int radeon_connector_set_property(struct drm_connector *connector, struct drm_property *property,
 				  uint64_t val)
 {
 	struct drm_device *dev = connector->dev;
@@ -691,13 +687,13 @@ static int radeon_lvds_set_property(struct drm_connector *connector,
 }
 
 
-struct drm_connector_helper_funcs radeon_lvds_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs radeon_lvds_connector_helper_funcs = {
 	.get_modes = radeon_lvds_get_modes,
 	.mode_valid = radeon_lvds_mode_valid,
 	.best_encoder = radeon_best_single_encoder,
 };
 
-struct drm_connector_funcs radeon_lvds_connector_funcs = {
+static const struct drm_connector_funcs radeon_lvds_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = radeon_lvds_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
@@ -809,13 +805,13 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	return ret;
 }
 
-struct drm_connector_helper_funcs radeon_vga_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs radeon_vga_connector_helper_funcs = {
 	.get_modes = radeon_vga_get_modes,
 	.mode_valid = radeon_vga_mode_valid,
 	.best_encoder = radeon_best_single_encoder,
 };
 
-struct drm_connector_funcs radeon_vga_connector_funcs = {
+static const struct drm_connector_funcs radeon_vga_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = radeon_vga_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
@@ -879,13 +875,13 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	return ret;
 }
 
-struct drm_connector_helper_funcs radeon_tv_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs radeon_tv_connector_helper_funcs = {
 	.get_modes = radeon_tv_get_modes,
 	.mode_valid = radeon_tv_mode_valid,
 	.best_encoder = radeon_best_single_encoder,
 };
 
-struct drm_connector_funcs radeon_tv_connector_funcs = {
+static const struct drm_connector_funcs radeon_tv_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = radeon_tv_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
@@ -1089,7 +1085,7 @@ out:
 }
 
 /* okay need to be smart in here about which encoder to pick */
-struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
+static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 {
 	int enc_id = connector->encoder_ids[0];
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
@@ -1179,13 +1175,13 @@ static int radeon_dvi_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-struct drm_connector_helper_funcs radeon_dvi_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs radeon_dvi_connector_helper_funcs = {
 	.get_modes = radeon_dvi_get_modes,
 	.mode_valid = radeon_dvi_mode_valid,
 	.best_encoder = radeon_dvi_encoder,
 };
 
-struct drm_connector_funcs radeon_dvi_connector_funcs = {
+static const struct drm_connector_funcs radeon_dvi_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = radeon_dvi_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
@@ -1462,13 +1458,13 @@ static int radeon_dp_mode_valid(struct drm_connector *connector,
 	}
 }
 
-struct drm_connector_helper_funcs radeon_dp_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs radeon_dp_connector_helper_funcs = {
 	.get_modes = radeon_dp_get_modes,
 	.mode_valid = radeon_dp_mode_valid,
 	.best_encoder = radeon_dvi_encoder,
 };
 
-struct drm_connector_funcs radeon_dp_connector_funcs = {
+static const struct drm_connector_funcs radeon_dp_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = radeon_dp_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
@@ -2008,15 +2004,4 @@ radeon_add_legacy_connector(struct drm_device *dev,
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 	connector->display_info.subpixel_order = subpixel_order;
 	drm_sysfs_connector_add(connector);
-	if (connector_type == DRM_MODE_CONNECTOR_LVDS) {
-		struct drm_encoder *drm_encoder;
-
-		list_for_each_entry(drm_encoder, &dev->mode_config.encoder_list, head) {
-			struct radeon_encoder *radeon_encoder;
-
-			radeon_encoder = to_radeon_encoder(drm_encoder);
-			if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_LVDS)
-				radeon_legacy_backlight_init(radeon_encoder, connector);
-		}
-	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 891fff52ab65..cb7b7c062fef 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -32,7 +32,7 @@
 void r100_cs_dump_packet(struct radeon_cs_parser *p,
 			 struct radeon_cs_packet *pkt);
 
-int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
+static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 {
 	struct drm_device *ddev = p->rdev->ddev;
 	struct radeon_cs_chunk *chunk;
@@ -115,19 +115,27 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 	return 0;
 }
 
+static void radeon_cs_sync_to(struct radeon_cs_parser *p,
+			      struct radeon_fence *fence)
+{
+	struct radeon_fence *other;
+
+	if (!fence)
+		return;
+
+	other = p->ib.sync_to[fence->ring];
+	p->ib.sync_to[fence->ring] = radeon_fence_later(fence, other);
+}
+
 static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 {
 	int i;
 
 	for (i = 0; i < p->nrelocs; i++) {
-		struct radeon_fence *a, *b;
-
-		if (!p->relocs[i].robj || !p->relocs[i].robj->tbo.sync_obj)
+		if (!p->relocs[i].robj)
 			continue;
 
-		a = p->relocs[i].robj->tbo.sync_obj;
-		b = p->ib.sync_to[a->ring];
-		p->ib.sync_to[a->ring] = radeon_fence_later(a, b);
+		radeon_cs_sync_to(p, p->relocs[i].robj->tbo.sync_obj);
 	}
 }
 
@@ -278,30 +286,6 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 	return 0;
 }
 
-static void radeon_bo_vm_fence_va(struct radeon_cs_parser *parser,
-				  struct radeon_fence *fence)
-{
-	struct radeon_fpriv *fpriv = parser->filp->driver_priv;
-	struct radeon_vm *vm = &fpriv->vm;
-	struct radeon_bo_list *lobj;
-
-	if (parser->chunk_ib_idx == -1) {
-		return;
-	}
-	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0) {
-		return;
-	}
-
-	list_for_each_entry(lobj, &parser->validated, tv.head) {
-		struct radeon_bo_va *bo_va;
-		struct radeon_bo *rbo = lobj->bo;
-
-		bo_va = radeon_bo_va(rbo, vm);
-		radeon_fence_unref(&bo_va->fence);
-		bo_va->fence = radeon_fence_ref(fence);
-	}
-}
-
 /**
  * cs_parser_fini() - clean parser states
  * @parser:	parser structure holding parsing context.
@@ -315,8 +299,6 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 	unsigned i;
 
 	if (!error) {
-		/* fence all bo va before ttm_eu_fence_buffer_objects so bo are still reserved */
-		radeon_bo_vm_fence_va(parser, parser->ib.fence);
 		ttm_eu_fence_buffer_objects(&parser->validated,
 					    parser->ib.fence);
 	} else {
@@ -363,7 +345,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 	 * uncached).
 	 */
 	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
-			   ib_chunk->length_dw * 4);
+			   NULL, ib_chunk->length_dw * 4);
 	if (r) {
 		DRM_ERROR("Failed to get ib !\n");
 		return r;
@@ -380,7 +362,6 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 		return r;
 	}
 	radeon_cs_sync_rings(parser);
-	parser->ib.vm_id = 0;
 	r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	if (r) {
 		DRM_ERROR("Failed to schedule IB !\n");
@@ -391,10 +372,15 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
 				   struct radeon_vm *vm)
 {
+	struct radeon_device *rdev = parser->rdev;
 	struct radeon_bo_list *lobj;
 	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);
+	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);
@@ -426,7 +412,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 			return -EINVAL;
 		}
 		r =  radeon_ib_get(rdev, parser->ring, &parser->const_ib,
-				   ib_chunk->length_dw * 4);
+				   vm, ib_chunk->length_dw * 4);
 		if (r) {
 			DRM_ERROR("Failed to get const ib !\n");
 			return r;
@@ -450,7 +436,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		return -EINVAL;
 	}
 	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
-			   ib_chunk->length_dw * 4);
+			   vm, ib_chunk->length_dw * 4);
 	if (r) {
 		DRM_ERROR("Failed to get ib !\n");
 		return r;
@@ -468,7 +454,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
-	r = radeon_vm_bind(rdev, vm);
+	r = radeon_vm_alloc_pt(rdev, vm);
 	if (r) {
 		goto out;
 	}
@@ -477,32 +463,21 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		goto out;
 	}
 	radeon_cs_sync_rings(parser);
-
-	parser->ib.vm_id = vm->id;
-	/* ib pool is bind at 0 in virtual address space,
-	 * so gpu_addr is the offset inside the pool bo
-	 */
-	parser->ib.gpu_addr = parser->ib.sa_bo->soffset;
+	radeon_cs_sync_to(parser, vm->fence);
+	radeon_cs_sync_to(parser, radeon_vm_grab_id(rdev, vm, parser->ring));
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
-		parser->const_ib.vm_id = vm->id;
-		/* ib pool is bind at 0 in virtual address space,
-		 * so gpu_addr is the offset inside the pool bo
-		 */
-		parser->const_ib.gpu_addr = parser->const_ib.sa_bo->soffset;
 		r = radeon_ib_schedule(rdev, &parser->ib, &parser->const_ib);
 	} else {
 		r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	}
 
-out:
 	if (!r) {
-		if (vm->fence) {
-			radeon_fence_unref(&vm->fence);
-		}
-		vm->fence = radeon_fence_ref(parser->ib.fence);
+		radeon_vm_fence(rdev, vm, parser->ib.fence);
 	}
+
+out:
 	mutex_unlock(&vm->mutex);
 	mutex_unlock(&rdev->vm_manager.lock);
 	return r;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 7a3daebd732d..64a42647f08a 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -842,7 +842,7 @@ static unsigned int radeon_vga_set_decode(void *cookie, bool state)
  * Validates certain module parameters and updates
  * the associated values used by the driver (all asics).
  */
-void radeon_check_arguments(struct radeon_device *rdev)
+static void radeon_check_arguments(struct radeon_device *rdev)
 {
 	/* vramlimit must be a power of two */
 	switch (radeon_vram_limit) {
@@ -1013,13 +1013,11 @@ int radeon_device_init(struct radeon_device *rdev,
 	init_rwsem(&rdev->pm.mclk_lock);
 	init_rwsem(&rdev->exclusive_lock);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
-	init_waitqueue_head(&rdev->irq.idle_queue);
 	r = radeon_gem_init(rdev);
 	if (r)
 		return r;
 	/* initialize vm here */
 	mutex_init(&rdev->vm_manager.lock);
-	rdev->vm_manager.use_bitmap = 1;
 	rdev->vm_manager.max_pfn = 1 << 20;
 	INIT_LIST_HEAD(&rdev->vm_manager.lru_vm);
 
@@ -1284,6 +1282,13 @@ int radeon_resume_kms(struct drm_device *dev)
 	if (rdev->is_atom_bios) {
 		radeon_atom_encoder_init(rdev);
 		radeon_atom_disp_eng_pll_init(rdev);
+		/* turn on the BL */
+		if (rdev->mode_info.bl_encoder) {
+			u8 bl_level = radeon_get_backlight_level(rdev,
+								 rdev->mode_info.bl_encoder);
+			radeon_set_backlight_level(rdev, rdev->mode_info.bl_encoder,
+						   bl_level);
+		}
 	}
 	/* reset hpd state */
 	radeon_hpd_init(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 97f3fe7dd040..07eb84e8a8a4 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -63,9 +63,11 @@
  *   2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query
  *   2.21.0 - r600-r700: FMASK and CMASK
  *   2.22.0 - r600 only: RESOLVE_BOX allowed
+ *   2.23.0 - allow STRMOUT_BASE_UPDATE on RS780 and RS880
+ *   2.24.0 - eg only: allow MIP_ADDRESS=0 for MSAA textures
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	22
+#define KMS_DRIVER_MINOR	24
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 5a1bae3a2426..bd4959ca23aa 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -29,6 +29,14 @@
 #include "radeon.h"
 #include "atom.h"
 
+extern void
+radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
+			     struct drm_connector *drm_connector);
+extern void
+radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
+			   struct drm_connector *drm_connector);
+
+
 static uint32_t radeon_encoder_clones(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
@@ -153,6 +161,7 @@ radeon_get_encoder_enum(struct drm_device *dev, uint32_t supported_device, uint8
 void
 radeon_link_encoder_connector(struct drm_device *dev)
 {
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_connector *connector;
 	struct radeon_connector *radeon_connector;
 	struct drm_encoder *encoder;
@@ -163,8 +172,16 @@ radeon_link_encoder_connector(struct drm_device *dev)
 		radeon_connector = to_radeon_connector(connector);
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			radeon_encoder = to_radeon_encoder(encoder);
-			if (radeon_encoder->devices & radeon_connector->devices)
+			if (radeon_encoder->devices & radeon_connector->devices) {
 				drm_mode_connector_attach_encoder(connector, encoder);
+				if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+					if (rdev->is_atom_bios)
+						radeon_atom_backlight_init(radeon_encoder, connector);
+					else
+						radeon_legacy_backlight_init(radeon_encoder, connector);
+					rdev->mode_info.bl_encoder = radeon_encoder;
+				}
+			}
 		}
 	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index fae493710ebf..cc8489d8c6d1 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -315,22 +315,6 @@ static int radeon_fb_find_or_create_single(struct drm_fb_helper *helper,
 	return new_fb;
 }
 
-static char *mode_option;
-int radeon_parse_options(char *options)
-{
-	char *this_opt;
-
-	if (!options || !*options)
-		return 0;
-
-	while ((this_opt = strsep(&options, ",")) != NULL) {
-		if (!*this_opt)
-			continue;
-		mode_option = this_opt;
-	}
-	return 0;
-}
-
 void radeon_fb_output_poll_changed(struct radeon_device *rdev)
 {
 	drm_fb_helper_hotplug_event(&rdev->mode_info.rfbdev->helper);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 5cd47ff03e48..22bd6c2c2740 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -398,7 +398,7 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 	return 0;
 }
 
-bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
+static bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
 {
 	unsigned i;
 
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 33cc03e310fd..f0c06d196b75 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -423,6 +423,18 @@ void radeon_gart_fini(struct radeon_device *rdev)
  */
 
 /**
+ * radeon_vm_directory_size - returns the size of the page directory in bytes
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Calculate the size of the page directory in bytes (cayman+).
+ */
+static unsigned radeon_vm_directory_size(struct radeon_device *rdev)
+{
+	return (rdev->vm_manager.max_pfn >> RADEON_VM_BLOCK_SIZE) * 8;
+}
+
+/**
  * radeon_vm_manager_init - init the vm manager
  *
  * @rdev: radeon_device pointer
@@ -435,12 +447,15 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 	struct radeon_vm *vm;
 	struct radeon_bo_va *bo_va;
 	int r;
+	unsigned size;
 
 	if (!rdev->vm_manager.enabled) {
-		/* mark first vm as always in use, it's the system one */
 		/* allocate enough for 2 full VM pts */
+		size = RADEON_GPU_PAGE_ALIGN(radeon_vm_directory_size(rdev));
+		size += RADEON_GPU_PAGE_ALIGN(rdev->vm_manager.max_pfn * 8);
+		size *= 2;
 		r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
-					      rdev->vm_manager.max_pfn * 8 * 2,
+					      size,
 					      RADEON_GEM_DOMAIN_VRAM);
 		if (r) {
 			dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n",
@@ -448,10 +463,10 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 			return r;
 		}
 
-		r = rdev->vm_manager.funcs->init(rdev);
+		r = radeon_asic_vm_init(rdev);
 		if (r)
 			return r;
-	
+
 		rdev->vm_manager.enabled = true;
 
 		r = radeon_sa_bo_manager_start(rdev, &rdev->vm_manager.sa_manager);
@@ -461,73 +476,36 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 
 	/* restore page table */
 	list_for_each_entry(vm, &rdev->vm_manager.lru_vm, list) {
-		if (vm->id == -1)
+		if (vm->sa_bo == NULL)
 			continue;
 
 		list_for_each_entry(bo_va, &vm->va, vm_list) {
-			struct ttm_mem_reg *mem = NULL;
-			if (bo_va->valid)
-				mem = &bo_va->bo->tbo.mem;
-
 			bo_va->valid = false;
-			r = radeon_vm_bo_update_pte(rdev, vm, bo_va->bo, mem);
-			if (r) {
-				DRM_ERROR("Failed to update pte for vm %d!\n", vm->id);
-			}
-		}
-
-		r = rdev->vm_manager.funcs->bind(rdev, vm, vm->id);
-		if (r) {
-			DRM_ERROR("Failed to bind vm %d!\n", vm->id);
 		}
 	}
 	return 0;
 }
 
-/* global mutex must be lock */
 /**
- * radeon_vm_unbind_locked - unbind a specific vm
+ * radeon_vm_free_pt - free the page table for a specific vm
  *
  * @rdev: radeon_device pointer
  * @vm: vm to unbind
  *
- * Unbind the requested vm (cayman+).
- * Wait for use of the VM to finish, then unbind the page table,
- * and free the page table memory.
+ * Free the page table of a specific vm (cayman+).
+ *
+ * Global and local mutex must be lock!
  */
-static void radeon_vm_unbind_locked(struct radeon_device *rdev,
+static void radeon_vm_free_pt(struct radeon_device *rdev,
 				    struct radeon_vm *vm)
 {
 	struct radeon_bo_va *bo_va;
 
-	if (vm->id == -1) {
+	if (!vm->sa_bo)
 		return;
-	}
 
-	/* wait for vm use to end */
-	while (vm->fence) {
-		int r;
-		r = radeon_fence_wait(vm->fence, false);
-		if (r)
-			DRM_ERROR("error while waiting for fence: %d\n", r);
-		if (r == -EDEADLK) {
-			mutex_unlock(&rdev->vm_manager.lock);
-			r = radeon_gpu_reset(rdev);
-			mutex_lock(&rdev->vm_manager.lock);
-			if (!r)
-				continue;
-		}
-		break;
-	}
-	radeon_fence_unref(&vm->fence);
-
-	/* hw unbind */
-	rdev->vm_manager.funcs->unbind(rdev, vm);
-	rdev->vm_manager.use_bitmap &= ~(1 << vm->id);
 	list_del_init(&vm->list);
-	vm->id = -1;
-	radeon_sa_bo_free(rdev, &vm->sa_bo, NULL);
-	vm->pt = NULL;
+	radeon_sa_bo_free(rdev, &vm->sa_bo, vm->fence);
 
 	list_for_each_entry(bo_va, &vm->va, vm_list) {
 		bo_va->valid = false;
@@ -544,16 +522,22 @@ static void radeon_vm_unbind_locked(struct radeon_device *rdev,
 void radeon_vm_manager_fini(struct radeon_device *rdev)
 {
 	struct radeon_vm *vm, *tmp;
+	int i;
 
 	if (!rdev->vm_manager.enabled)
 		return;
 
 	mutex_lock(&rdev->vm_manager.lock);
-	/* unbind all active vm */
+	/* free all allocated page tables */
 	list_for_each_entry_safe(vm, tmp, &rdev->vm_manager.lru_vm, list) {
-		radeon_vm_unbind_locked(rdev, vm);
+		mutex_lock(&vm->mutex);
+		radeon_vm_free_pt(rdev, vm);
+		mutex_unlock(&vm->mutex);
 	}
-	rdev->vm_manager.funcs->fini(rdev);
+	for (i = 0; i < RADEON_NUM_VM; ++i) {
+		radeon_fence_unref(&rdev->vm_manager.active[i]);
+	}
+	radeon_asic_vm_fini(rdev);
 	mutex_unlock(&rdev->vm_manager.lock);
 
 	radeon_sa_bo_manager_suspend(rdev, &rdev->vm_manager.sa_manager);
@@ -561,46 +545,34 @@ void radeon_vm_manager_fini(struct radeon_device *rdev)
 	rdev->vm_manager.enabled = false;
 }
 
-/* global mutex must be locked */
 /**
- * radeon_vm_unbind - locked version of unbind
- *
- * @rdev: radeon_device pointer
- * @vm: vm to unbind
- *
- * Locked version that wraps radeon_vm_unbind_locked (cayman+).
- */
-void radeon_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	mutex_lock(&vm->mutex);
-	radeon_vm_unbind_locked(rdev, vm);
-	mutex_unlock(&vm->mutex);
-}
-
-/* global and local mutex must be locked */
-/**
- * radeon_vm_bind - bind a page table to a VMID
+ * radeon_vm_alloc_pt - allocates a page table for a VM
  *
  * @rdev: radeon_device pointer
  * @vm: vm to bind
  *
- * Bind the requested vm (cayman+).
- * Suballocate memory for the page table, allocate a VMID
- * and bind the page table to it, and finally start to populate
- * the page table.
+ * Allocate a page table for the requested vm (cayman+).
+ * Also starts to populate the page table.
  * Returns 0 for success, error for failure.
+ *
+ * Global and local mutex must be locked!
  */
-int radeon_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm)
+int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 {
 	struct radeon_vm *vm_evict;
-	unsigned i;
-	int id = -1, r;
+	int r;
+	u64 *pd_addr;
+	int tables_size;
 
 	if (vm == NULL) {
 		return -EINVAL;
 	}
 
-	if (vm->id != -1) {
+	/* allocate enough to cover the current VM size */
+	tables_size = RADEON_GPU_PAGE_ALIGN(radeon_vm_directory_size(rdev));
+	tables_size += RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8);
+
+	if (vm->sa_bo != NULL) {
 		/* update lru */
 		list_del_init(&vm->list);
 		list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
@@ -609,98 +581,215 @@ int radeon_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm)
 
 retry:
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, &vm->sa_bo,
-			     RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8),
-			     RADEON_GPU_PAGE_SIZE, false);
-	if (r) {
+			     tables_size, RADEON_GPU_PAGE_SIZE, false);
+	if (r == -ENOMEM) {
 		if (list_empty(&rdev->vm_manager.lru_vm)) {
 			return r;
 		}
 		vm_evict = list_first_entry(&rdev->vm_manager.lru_vm, struct radeon_vm, list);
-		radeon_vm_unbind(rdev, vm_evict);
+		mutex_lock(&vm_evict->mutex);
+		radeon_vm_free_pt(rdev, vm_evict);
+		mutex_unlock(&vm_evict->mutex);
 		goto retry;
+
+	} else if (r) {
+		return r;
 	}
-	vm->pt = radeon_sa_bo_cpu_addr(vm->sa_bo);
-	vm->pt_gpu_addr = radeon_sa_bo_gpu_addr(vm->sa_bo);
-	memset(vm->pt, 0, RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8));
 
-retry_id:
-	/* search for free vm */
-	for (i = 0; i < rdev->vm_manager.nvm; i++) {
-		if (!(rdev->vm_manager.use_bitmap & (1 << i))) {
-			id = i;
-			break;
+	pd_addr = radeon_sa_bo_cpu_addr(vm->sa_bo);
+	vm->pd_gpu_addr = radeon_sa_bo_gpu_addr(vm->sa_bo);
+	memset(pd_addr, 0, tables_size);
+
+	list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
+	return radeon_vm_bo_update_pte(rdev, vm, rdev->ring_tmp_bo.bo,
+				       &rdev->ring_tmp_bo.bo->tbo.mem);
+}
+
+/**
+ * radeon_vm_grab_id - allocate the next free VMID
+ *
+ * @rdev: radeon_device pointer
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ *
+ * Allocate an id for the vm (cayman+).
+ * Returns the fence we need to sync to (if any).
+ *
+ * Global and local mutex must be locked!
+ */
+struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev,
+				       struct radeon_vm *vm, int ring)
+{
+	struct radeon_fence *best[RADEON_NUM_RINGS] = {};
+	unsigned choices[2] = {};
+	unsigned i;
+
+	/* check if the id is still valid */
+	if (vm->fence && vm->fence == rdev->vm_manager.active[vm->id])
+		return NULL;
+
+	/* we definately need to flush */
+	radeon_fence_unref(&vm->last_flush);
+
+	/* skip over VMID 0, since it is the system VM */
+	for (i = 1; i < rdev->vm_manager.nvm; ++i) {
+		struct radeon_fence *fence = rdev->vm_manager.active[i];
+
+		if (fence == NULL) {
+			/* found a free one */
+			vm->id = i;
+			return NULL;
+		}
+
+		if (radeon_fence_is_earlier(fence, best[fence->ring])) {
+			best[fence->ring] = fence;
+			choices[fence->ring == ring ? 0 : 1] = i;
 		}
 	}
-	/* evict vm if necessary */
-	if (id == -1) {
-		vm_evict = list_first_entry(&rdev->vm_manager.lru_vm, struct radeon_vm, list);
-		radeon_vm_unbind(rdev, vm_evict);
-		goto retry_id;
+
+	for (i = 0; i < 2; ++i) {
+		if (choices[i]) {
+			vm->id = choices[i];
+			return rdev->vm_manager.active[choices[i]];
+		}
 	}
 
-	/* do hw bind */
-	r = rdev->vm_manager.funcs->bind(rdev, vm, id);
-	if (r) {
-		radeon_sa_bo_free(rdev, &vm->sa_bo, NULL);
-		return r;
+	/* should never happen */
+	BUG();
+	return NULL;
+}
+
+/**
+ * radeon_vm_fence - remember fence for vm
+ *
+ * @rdev: radeon_device pointer
+ * @vm: vm we want to fence
+ * @fence: fence to remember
+ *
+ * Fence the vm (cayman+).
+ * Set the fence used to protect page table and id.
+ *
+ * Global and local mutex must be locked!
+ */
+void radeon_vm_fence(struct radeon_device *rdev,
+		     struct radeon_vm *vm,
+		     struct radeon_fence *fence)
+{
+	radeon_fence_unref(&rdev->vm_manager.active[vm->id]);
+	rdev->vm_manager.active[vm->id] = radeon_fence_ref(fence);
+
+	radeon_fence_unref(&vm->fence);
+	vm->fence = radeon_fence_ref(fence);
+}
+
+/**
+ * radeon_vm_bo_find - find the bo_va for a specific vm & bo
+ *
+ * @vm: requested vm
+ * @bo: requested buffer object
+ *
+ * Find @bo inside the requested vm (cayman+).
+ * Search inside the @bos vm list for the requested vm
+ * Returns the found bo_va or NULL if none is found
+ *
+ * Object has to be reserved!
+ */
+struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
+				       struct radeon_bo *bo)
+{
+	struct radeon_bo_va *bo_va;
+
+	list_for_each_entry(bo_va, &bo->va, bo_list) {
+		if (bo_va->vm == vm) {
+			return bo_va;
+		}
 	}
-	rdev->vm_manager.use_bitmap |= 1 << id;
-	vm->id = id;
-	list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
-	return radeon_vm_bo_update_pte(rdev, vm, rdev->ring_tmp_bo.bo,
-				       &rdev->ring_tmp_bo.bo->tbo.mem);
+	return NULL;
 }
 
-/* object have to be reserved */
 /**
  * radeon_vm_bo_add - add a bo to a specific vm
  *
  * @rdev: radeon_device pointer
  * @vm: requested vm
  * @bo: radeon buffer object
- * @offset: requested offset of the buffer in the VM address space
- * @flags: attributes of pages (read/write/valid/etc.)
  *
  * Add @bo into the requested vm (cayman+).
- * Add @bo to the list of bos associated with the vm and validate
- * the offset requested within the vm address space.
- * Returns 0 for success, error for failure.
+ * Add @bo to the list of bos associated with the vm
+ * Returns newly added bo_va or NULL for failure
+ *
+ * Object has to be reserved!
  */
-int radeon_vm_bo_add(struct radeon_device *rdev,
-		     struct radeon_vm *vm,
-		     struct radeon_bo *bo,
-		     uint64_t offset,
-		     uint32_t flags)
+struct radeon_bo_va *radeon_vm_bo_add(struct radeon_device *rdev,
+				      struct radeon_vm *vm,
+				      struct radeon_bo *bo)
 {
-	struct radeon_bo_va *bo_va, *tmp;
-	struct list_head *head;
-	uint64_t size = radeon_bo_size(bo), last_offset = 0;
-	unsigned last_pfn;
+	struct radeon_bo_va *bo_va;
 
 	bo_va = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
 	if (bo_va == NULL) {
-		return -ENOMEM;
+		return NULL;
 	}
 	bo_va->vm = vm;
 	bo_va->bo = bo;
-	bo_va->soffset = offset;
-	bo_va->eoffset = offset + size;
-	bo_va->flags = flags;
+	bo_va->soffset = 0;
+	bo_va->eoffset = 0;
+	bo_va->flags = 0;
 	bo_va->valid = false;
+	bo_va->ref_count = 1;
 	INIT_LIST_HEAD(&bo_va->bo_list);
 	INIT_LIST_HEAD(&bo_va->vm_list);
-	/* make sure object fit at this offset */
-	if (bo_va->soffset >= bo_va->eoffset) {
-		kfree(bo_va);
-		return -EINVAL;
-	}
 
-	last_pfn = bo_va->eoffset / RADEON_GPU_PAGE_SIZE;
-	if (last_pfn > rdev->vm_manager.max_pfn) {
-		kfree(bo_va);
-		dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n",
-			last_pfn, rdev->vm_manager.max_pfn);
-		return -EINVAL;
+	mutex_lock(&vm->mutex);
+	list_add(&bo_va->vm_list, &vm->va);
+	list_add_tail(&bo_va->bo_list, &bo->va);
+	mutex_unlock(&vm->mutex);
+
+	return bo_va;
+}
+
+/**
+ * radeon_vm_bo_set_addr - set bos virtual address inside a vm
+ *
+ * @rdev: radeon_device pointer
+ * @bo_va: bo_va to store the address
+ * @soffset: requested offset of the buffer in the VM address space
+ * @flags: attributes of pages (read/write/valid/etc.)
+ *
+ * Set offset of @bo_va (cayman+).
+ * Validate and set the offset requested within the vm address space.
+ * Returns 0 for success, error for failure.
+ *
+ * Object has to be reserved!
+ */
+int radeon_vm_bo_set_addr(struct radeon_device *rdev,
+			  struct radeon_bo_va *bo_va,
+			  uint64_t soffset,
+			  uint32_t flags)
+{
+	uint64_t size = radeon_bo_size(bo_va->bo);
+	uint64_t eoffset, last_offset = 0;
+	struct radeon_vm *vm = bo_va->vm;
+	struct radeon_bo_va *tmp;
+	struct list_head *head;
+	unsigned last_pfn;
+
+	if (soffset) {
+		/* make sure object fit at this offset */
+		eoffset = soffset + size;
+		if (soffset >= eoffset) {
+			return -EINVAL;
+		}
+
+		last_pfn = eoffset / RADEON_GPU_PAGE_SIZE;
+		if (last_pfn > rdev->vm_manager.max_pfn) {
+			dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n",
+				last_pfn, rdev->vm_manager.max_pfn);
+			return -EINVAL;
+		}
+
+	} else {
+		eoffset = last_pfn = 0;
 	}
 
 	mutex_lock(&vm->mutex);
@@ -713,7 +802,7 @@ int radeon_vm_bo_add(struct radeon_device *rdev,
 		if (last_pfn > vm->last_pfn) {
 			/* grow va space 32M by 32M */
 			unsigned align = ((32 << 20) >> 12) - 1;
-			radeon_vm_unbind_locked(rdev, vm);
+			radeon_vm_free_pt(rdev, vm);
 			vm->last_pfn = (last_pfn + align) & ~align;
 		}
 		mutex_unlock(&rdev->vm_manager.lock);
@@ -721,68 +810,60 @@ int radeon_vm_bo_add(struct radeon_device *rdev,
 	head = &vm->va;
 	last_offset = 0;
 	list_for_each_entry(tmp, &vm->va, vm_list) {
-		if (bo_va->soffset >= last_offset && bo_va->eoffset < tmp->soffset) {
+		if (bo_va == tmp) {
+			/* skip over currently modified bo */
+			continue;
+		}
+
+		if (soffset >= last_offset && eoffset <= tmp->soffset) {
 			/* bo can be added before this one */
 			break;
 		}
-		if (bo_va->soffset >= tmp->soffset && bo_va->soffset < tmp->eoffset) {
+		if (eoffset > tmp->soffset && soffset < tmp->eoffset) {
 			/* bo and tmp overlap, invalid offset */
 			dev_err(rdev->dev, "bo %p va 0x%08X conflict with (bo %p 0x%08X 0x%08X)\n",
-				bo, (unsigned)bo_va->soffset, tmp->bo,
+				bo_va->bo, (unsigned)bo_va->soffset, tmp->bo,
 				(unsigned)tmp->soffset, (unsigned)tmp->eoffset);
-			kfree(bo_va);
 			mutex_unlock(&vm->mutex);
 			return -EINVAL;
 		}
 		last_offset = tmp->eoffset;
 		head = &tmp->vm_list;
 	}
-	list_add(&bo_va->vm_list, head);
-	list_add_tail(&bo_va->bo_list, &bo->va);
+
+	bo_va->soffset = soffset;
+	bo_va->eoffset = eoffset;
+	bo_va->flags = flags;
+	bo_va->valid = false;
+	list_move(&bo_va->vm_list, head);
+
 	mutex_unlock(&vm->mutex);
 	return 0;
 }
 
 /**
- * radeon_vm_get_addr - get the physical address of the page
+ * radeon_vm_map_gart - get the physical address of a gart page
  *
  * @rdev: radeon_device pointer
- * @mem: ttm mem
- * @pfn: pfn
+ * @addr: the unmapped addr
  *
  * Look up the physical address of the page that the pte resolves
  * to (cayman+).
  * Returns the physical address of the page.
  */
-static u64 radeon_vm_get_addr(struct radeon_device *rdev,
-			      struct ttm_mem_reg *mem,
-			      unsigned pfn)
+uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr)
 {
-	u64 addr = 0;
-
-	switch (mem->mem_type) {
-	case TTM_PL_VRAM:
-		addr = (mem->start << PAGE_SHIFT);
-		addr += pfn * RADEON_GPU_PAGE_SIZE;
-		addr += rdev->vm_manager.vram_base_offset;
-		break;
-	case TTM_PL_TT:
-		/* offset inside page table */
-		addr = mem->start << PAGE_SHIFT;
-		addr += pfn * RADEON_GPU_PAGE_SIZE;
-		addr = addr >> PAGE_SHIFT;
-		/* page table offset */
-		addr = rdev->gart.pages_addr[addr];
-		/* in case cpu page size != gpu page size*/
-		addr += (pfn * RADEON_GPU_PAGE_SIZE) & (~PAGE_MASK);
-		break;
-	default:
-		break;
-	}
-	return addr;
+	uint64_t result;
+
+	/* page table offset */
+	result = rdev->gart.pages_addr[addr >> PAGE_SHIFT];
+
+	/* in case cpu page size != gpu page size*/
+	result |= addr & (~PAGE_MASK);
+
+	return result;
 }
 
-/* object have to be reserved & global and local mutex must be locked */
 /**
  * radeon_vm_bo_update_pte - map a bo into the vm page table
  *
@@ -793,103 +874,160 @@ static u64 radeon_vm_get_addr(struct radeon_device *rdev,
  *
  * Fill in the page table entries for @bo (cayman+).
  * Returns 0 for success, -EINVAL for failure.
+ *
+ * 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)
 {
+	unsigned ridx = rdev->asic->vm.pt_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ridx];
+	struct radeon_semaphore *sem = NULL;
 	struct radeon_bo_va *bo_va;
-	unsigned ngpu_pages, i;
-	uint64_t addr = 0, pfn;
-	uint32_t flags;
+	unsigned nptes, npdes, ndw;
+	uint64_t pe, addr;
+	uint64_t pfn;
+	int r;
 
 	/* nothing to do if vm isn't bound */
-	if (vm->id == -1)
+	if (vm->sa_bo == NULL)
 		return 0;
 
-	bo_va = radeon_bo_va(bo, vm);
+	bo_va = radeon_vm_bo_find(vm, bo);
 	if (bo_va == NULL) {
 		dev_err(rdev->dev, "bo %p not in vm %p\n", bo, vm);
 		return -EINVAL;
 	}
 
-	if (bo_va->valid && mem)
+	if (!bo_va->soffset) {
+		dev_err(rdev->dev, "bo %p don't has a mapping in vm %p\n",
+			bo, vm);
+		return -EINVAL;
+	}
+
+	if ((bo_va->valid && mem) || (!bo_va->valid && mem == NULL))
 		return 0;
 
-	ngpu_pages = radeon_bo_ngpu_pages(bo);
 	bo_va->flags &= ~RADEON_VM_PAGE_VALID;
 	bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM;
 	if (mem) {
+		addr = mem->start << PAGE_SHIFT;
 		if (mem->mem_type != TTM_PL_SYSTEM) {
 			bo_va->flags |= RADEON_VM_PAGE_VALID;
 			bo_va->valid = true;
 		}
 		if (mem->mem_type == TTM_PL_TT) {
 			bo_va->flags |= RADEON_VM_PAGE_SYSTEM;
+		} else {
+			addr += rdev->vm_manager.vram_base_offset;
 		}
+	} else {
+		addr = 0;
+		bo_va->valid = false;
 	}
-	pfn = bo_va->soffset / RADEON_GPU_PAGE_SIZE;
-	flags = rdev->vm_manager.funcs->page_flags(rdev, bo_va->vm, bo_va->flags);
-	for (i = 0, addr = 0; i < ngpu_pages; i++) {
-		if (mem && bo_va->valid) {
-			addr = radeon_vm_get_addr(rdev, mem, i);
+
+	if (vm->fence && radeon_fence_signaled(vm->fence)) {
+		radeon_fence_unref(&vm->fence);
+	}
+
+	if (vm->fence && vm->fence->ring != ridx) {
+		r = radeon_semaphore_create(rdev, &sem);
+		if (r) {
+			return r;
 		}
-		rdev->vm_manager.funcs->set_page(rdev, bo_va->vm, i + pfn, addr, flags);
 	}
-	rdev->vm_manager.funcs->tlb_flush(rdev, bo_va->vm);
+
+	/* estimate number of dw needed */
+	/* reserve space for 32-bit padding */
+	ndw = 32;
+
+	nptes = radeon_bo_ngpu_pages(bo);
+
+	pfn = (bo_va->soffset / RADEON_GPU_PAGE_SIZE);
+
+	/* handle cases where a bo spans several pdes  */
+	npdes = (ALIGN(pfn + nptes, RADEON_VM_PTE_COUNT) -
+		 (pfn & ~(RADEON_VM_PTE_COUNT - 1))) >> RADEON_VM_BLOCK_SIZE;
+
+	/* reserve space for one header for every 2k dwords */
+	ndw += (nptes >> 11) * 3;
+	/* reserve space for pte addresses */
+	ndw += nptes * 2;
+
+	/* reserve space for one header for every 2k dwords */
+	ndw += (npdes >> 11) * 3;
+	/* reserve space for pde addresses */
+	ndw += npdes * 2;
+
+	r = radeon_ring_lock(rdev, ring, ndw);
+	if (r) {
+		return r;
+	}
+
+	if (sem && radeon_fence_need_sync(vm->fence, ridx)) {
+		radeon_semaphore_sync_rings(rdev, sem, vm->fence->ring, ridx);
+		radeon_fence_note_sync(vm->fence, ridx);
+	}
+
+	/* update page table entries */
+	pe = vm->pd_gpu_addr;
+	pe += radeon_vm_directory_size(rdev);
+	pe += (bo_va->soffset / RADEON_GPU_PAGE_SIZE) * 8;
+
+	radeon_asic_vm_set_page(rdev, pe, addr, nptes,
+				RADEON_GPU_PAGE_SIZE, bo_va->flags);
+
+	/* update page directory entries */
+	addr = pe;
+
+	pe = vm->pd_gpu_addr;
+	pe += ((bo_va->soffset / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE) * 8;
+
+	radeon_asic_vm_set_page(rdev, pe, addr, npdes,
+				RADEON_VM_PTE_COUNT * 8, RADEON_VM_PAGE_VALID);
+
+	radeon_fence_unref(&vm->fence);
+	r = radeon_fence_emit(rdev, &vm->fence, ridx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, vm->fence);
+	radeon_fence_unref(&vm->last_flush);
 	return 0;
 }
 
-/* object have to be reserved */
 /**
  * radeon_vm_bo_rmv - remove a bo to a specific vm
  *
  * @rdev: radeon_device pointer
- * @vm: requested vm
- * @bo: radeon buffer object
+ * @bo_va: requested bo_va
  *
- * Remove @bo from the requested vm (cayman+).
- * Remove @bo from the list of bos associated with the vm and
- * remove the ptes for @bo in the page table.
+ * Remove @bo_va->bo from the requested vm (cayman+).
+ * Remove @bo_va->bo from the list of bos associated with the bo_va->vm and
+ * remove the ptes for @bo_va in the page table.
  * Returns 0 for success.
+ *
+ * Object have to be reserved!
  */
 int radeon_vm_bo_rmv(struct radeon_device *rdev,
-		     struct radeon_vm *vm,
-		     struct radeon_bo *bo)
+		     struct radeon_bo_va *bo_va)
 {
-	struct radeon_bo_va *bo_va;
 	int r;
 
-	bo_va = radeon_bo_va(bo, vm);
-	if (bo_va == NULL)
-		return 0;
-
-	/* wait for va use to end */
-	while (bo_va->fence) {
-		r = radeon_fence_wait(bo_va->fence, false);
-		if (r) {
-			DRM_ERROR("error while waiting for fence: %d\n", r);
-		}
-		if (r == -EDEADLK) {
-			r = radeon_gpu_reset(rdev);
-			if (!r)
-				continue;
-		}
-		break;
-	}
-	radeon_fence_unref(&bo_va->fence);
-
 	mutex_lock(&rdev->vm_manager.lock);
-	mutex_lock(&vm->mutex);
-	radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
+	mutex_lock(&bo_va->vm->mutex);
+	r = radeon_vm_bo_update_pte(rdev, bo_va->vm, bo_va->bo, NULL);
 	mutex_unlock(&rdev->vm_manager.lock);
 	list_del(&bo_va->vm_list);
-	mutex_unlock(&vm->mutex);
+	mutex_unlock(&bo_va->vm->mutex);
 	list_del(&bo_va->bo_list);
 
 	kfree(bo_va);
-	return 0;
+	return r;
 }
 
 /**
@@ -925,27 +1063,23 @@ void radeon_vm_bo_invalidate(struct radeon_device *rdev,
  */
 int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 {
+	struct radeon_bo_va *bo_va;
 	int r;
 
-	vm->id = -1;
+	vm->id = 0;
 	vm->fence = NULL;
+	vm->last_pfn = 0;
 	mutex_init(&vm->mutex);
 	INIT_LIST_HEAD(&vm->list);
 	INIT_LIST_HEAD(&vm->va);
-	/* SI requires equal sized PTs for all VMs, so always set
-	 * last_pfn to max_pfn.  cayman allows variable sized
-	 * pts so we can grow then as needed.  Once we switch
-	 * to two level pts we can unify this again.
-	 */
-	if (rdev->family >= CHIP_TAHITI)
-		vm->last_pfn = rdev->vm_manager.max_pfn;
-	else
-		vm->last_pfn = 0;
+
 	/* map the ib pool buffer at 0 in virtual address space, set
 	 * read only
 	 */
-	r = radeon_vm_bo_add(rdev, vm, rdev->ring_tmp_bo.bo, 0,
-			     RADEON_VM_PAGE_READABLE | RADEON_VM_PAGE_SNOOPED);
+	bo_va = radeon_vm_bo_add(rdev, vm, rdev->ring_tmp_bo.bo);
+	r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
+				  RADEON_VM_PAGE_READABLE |
+				  RADEON_VM_PAGE_SNOOPED);
 	return r;
 }
 
@@ -965,7 +1099,7 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
-	radeon_vm_unbind_locked(rdev, vm);
+	radeon_vm_free_pt(rdev, vm);
 	mutex_unlock(&rdev->vm_manager.lock);
 
 	/* remove all bo at this point non are busy any more because unbind
@@ -973,10 +1107,9 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 	 */
 	r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 	if (!r) {
-		bo_va = radeon_bo_va(rdev->ring_tmp_bo.bo, vm);
+		bo_va = radeon_vm_bo_find(vm, rdev->ring_tmp_bo.bo);
 		list_del_init(&bo_va->bo_list);
 		list_del_init(&bo_va->vm_list);
-		radeon_fence_unref(&bo_va->fence);
 		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		kfree(bo_va);
 	}
@@ -988,10 +1121,11 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 		r = radeon_bo_reserve(bo_va->bo, false);
 		if (!r) {
 			list_del_init(&bo_va->bo_list);
-			radeon_fence_unref(&bo_va->fence);
 			radeon_bo_unreserve(bo_va->bo);
 			kfree(bo_va);
 		}
 	}
+	radeon_fence_unref(&vm->fence);
+	radeon_fence_unref(&vm->last_flush);
 	mutex_unlock(&vm->mutex);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 04c212da6f65..f38fbcc46935 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -123,6 +123,30 @@ void radeon_gem_fini(struct radeon_device *rdev)
  */
 int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv)
 {
+	struct radeon_bo *rbo = gem_to_radeon_bo(obj);
+	struct radeon_device *rdev = rbo->rdev;
+	struct radeon_fpriv *fpriv = file_priv->driver_priv;
+	struct radeon_vm *vm = &fpriv->vm;
+	struct radeon_bo_va *bo_va;
+	int r;
+
+	if (rdev->family < CHIP_CAYMAN) {
+		return 0;
+	}
+
+	r = radeon_bo_reserve(rbo, false);
+	if (r) {
+		return r;
+	}
+
+	bo_va = radeon_vm_bo_find(vm, rbo);
+	if (!bo_va) {
+		bo_va = radeon_vm_bo_add(rdev, vm, rbo);
+	} else {
+		++bo_va->ref_count;
+	}
+	radeon_bo_unreserve(rbo);
+
 	return 0;
 }
 
@@ -133,16 +157,25 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 	struct radeon_device *rdev = rbo->rdev;
 	struct radeon_fpriv *fpriv = file_priv->driver_priv;
 	struct radeon_vm *vm = &fpriv->vm;
+	struct radeon_bo_va *bo_va;
+	int r;
 
 	if (rdev->family < CHIP_CAYMAN) {
 		return;
 	}
 
-	if (radeon_bo_reserve(rbo, false)) {
-		dev_err(rdev->dev, "leaking bo va because we fail to reserve bo\n");
+	r = radeon_bo_reserve(rbo, true);
+	if (r) {
+		dev_err(rdev->dev, "leaking bo va because "
+			"we fail to reserve bo (%d)\n", r);
 		return;
 	}
-	radeon_vm_bo_rmv(rdev, vm, rbo);
+	bo_va = radeon_vm_bo_find(vm, rbo);
+	if (bo_va) {
+		if (--bo_va->ref_count == 0) {
+			radeon_vm_bo_rmv(rdev, bo_va);
+		}
+	}
 	radeon_bo_unreserve(rbo);
 }
 
@@ -458,19 +491,24 @@ int radeon_gem_va_ioctl(struct drm_device *dev, void *data,
 		drm_gem_object_unreference_unlocked(gobj);
 		return r;
 	}
+	bo_va = radeon_vm_bo_find(&fpriv->vm, rbo);
+	if (!bo_va) {
+		args->operation = RADEON_VA_RESULT_ERROR;
+		drm_gem_object_unreference_unlocked(gobj);
+		return -ENOENT;
+	}
+
 	switch (args->operation) {
 	case RADEON_VA_MAP:
-		bo_va = radeon_bo_va(rbo, &fpriv->vm);
-		if (bo_va) {
+		if (bo_va->soffset) {
 			args->operation = RADEON_VA_RESULT_VA_EXIST;
 			args->offset = bo_va->soffset;
 			goto out;
 		}
-		r = radeon_vm_bo_add(rdev, &fpriv->vm, rbo,
-				     args->offset, args->flags);
+		r = radeon_vm_bo_set_addr(rdev, bo_va, args->offset, args->flags);
 		break;
 	case RADEON_VA_UNMAP:
-		r = radeon_vm_bo_rmv(rdev, &fpriv->vm, rbo);
+		r = radeon_vm_bo_set_addr(rdev, bo_va, 0, 0);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/radeon/radeon_ioc32.c b/drivers/gpu/drm/radeon/radeon_ioc32.c
index 8fc81a26438a..c180df8e84db 100644
--- a/drivers/gpu/drm/radeon/radeon_ioc32.c
+++ b/drivers/gpu/drm/radeon/radeon_ioc32.c
@@ -368,7 +368,7 @@ static int compat_radeon_cp_setparam(struct file *file, unsigned int cmd,
 #define compat_radeon_cp_setparam NULL
 #endif /* X86_64 || IA64 */
 
-drm_ioctl_compat_t *radeon_compat_ioctls[] = {
+static drm_ioctl_compat_t *radeon_compat_ioctls[] = {
 	[DRM_RADEON_CP_INIT] = compat_radeon_cp_init,
 	[DRM_RADEON_CLEAR] = compat_radeon_cp_clear,
 	[DRM_RADEON_STIPPLE] = compat_radeon_cp_stipple,
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 9201992cee12..90374dd77960 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -99,7 +99,6 @@ void radeon_driver_irq_preinstall_kms(struct drm_device *dev)
 	/* Disable *all* interrupts */
 	for (i = 0; i < RADEON_NUM_RINGS; i++)
 		atomic_set(&rdev->irq.ring_int[i], 0);
-	rdev->irq.gui_idle = false;
 	for (i = 0; i < RADEON_MAX_HPD_PINS; i++)
 		rdev->irq.hpd[i] = false;
 	for (i = 0; i < RADEON_MAX_CRTCS; i++) {
@@ -147,7 +146,6 @@ void radeon_driver_irq_uninstall_kms(struct drm_device *dev)
 	/* Disable *all* interrupts */
 	for (i = 0; i < RADEON_NUM_RINGS; i++)
 		atomic_set(&rdev->irq.ring_int[i], 0);
-	rdev->irq.gui_idle = false;
 	for (i = 0; i < RADEON_MAX_HPD_PINS; i++)
 		rdev->irq.hpd[i] = false;
 	for (i = 0; i < RADEON_MAX_CRTCS; i++) {
@@ -204,6 +202,16 @@ static bool radeon_msi_ok(struct radeon_device *rdev)
 	    (rdev->pdev->subsystem_device == 0x01fd))
 		return true;
 
+	/* Gateway RS690 only seems to work with MSIs. */
+	if ((rdev->pdev->device == 0x791f) &&
+	    (rdev->pdev->subsystem_vendor == 0x107b) &&
+	    (rdev->pdev->subsystem_device == 0x0185))
+		return true;
+
+	/* try and enable MSIs by default on all RS690s */
+	if (rdev->family == CHIP_RS690)
+		return true;
+
 	/* RV515 seems to have MSI issues where it loses
 	 * MSI rearms occasionally. This leads to lockups and freezes.
 	 * disable it by default.
@@ -457,34 +465,3 @@ void radeon_irq_kms_disable_hpd(struct radeon_device *rdev, unsigned hpd_mask)
 	spin_unlock_irqrestore(&rdev->irq.lock, irqflags);
 }
 
-/**
- * radeon_irq_kms_wait_gui_idle - waits for drawing engine to be idle
- *
- * @rdev: radeon device pointer
- *
- * Enabled the GUI idle interrupt and waits for it to fire (r6xx+).
- * This is currently used to make sure the 3D engine is idle for power
- * management, but should be replaces with proper fence waits.
- * GUI idle interrupts don't work very well on pre-r6xx hw and it also
- * does not take into account other aspects of the chip that may be busy.
- * DO NOT USE GOING FORWARD.
- */
-int radeon_irq_kms_wait_gui_idle(struct radeon_device *rdev)
-{
-	unsigned long irqflags;
-	int r;
-
-	spin_lock_irqsave(&rdev->irq.lock, irqflags);
-	rdev->irq.gui_idle = true;
-	radeon_irq_set(rdev);
-	spin_unlock_irqrestore(&rdev->irq.lock, irqflags);
-
-	r = wait_event_timeout(rdev->irq.idle_queue, radeon_gui_idle(rdev),
-			       msecs_to_jiffies(RADEON_WAIT_IDLE_TIMEOUT));
-
-	spin_lock_irqsave(&rdev->irq.lock, irqflags);
-	rdev->irq.gui_idle = false;
-	radeon_irq_set(rdev);
-	spin_unlock_irqrestore(&rdev->irq.lock, irqflags);
-	return r;
-}
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 8a7f87f17c13..83b8d8aa71c0 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -50,6 +50,7 @@ int radeon_driver_unload_kms(struct drm_device *dev)
 
 	if (rdev == NULL)
 		return 0;
+	radeon_acpi_fini(rdev);
 	radeon_modeset_fini(rdev);
 	radeon_device_fini(rdev);
 	kfree(rdev);
@@ -102,11 +103,6 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		goto out;
 	}
 
-	/* Call ACPI methods */
-	acpi_status = radeon_acpi_init(rdev);
-	if (acpi_status)
-		dev_dbg(&dev->pdev->dev, "Error during ACPI methods call\n");
-
 	/* Again modeset_init should fail only on fatal error
 	 * otherwise it should provide enough functionalities
 	 * for shadowfb to run
@@ -114,6 +110,17 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	r = radeon_modeset_init(rdev);
 	if (r)
 		dev_err(&dev->pdev->dev, "Fatal error during modeset init\n");
+
+	/* Call ACPI methods: require modeset init
+	 * but failure is not fatal
+	 */
+	if (!r) {
+		acpi_status = radeon_acpi_init(rdev);
+		if (acpi_status)
+		dev_dbg(&dev->pdev->dev,
+				"Error during ACPI methods call\n");
+	}
+
 out:
 	if (r)
 		radeon_driver_unload_kms(dev);
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 94b4a1c12893..5677a424b585 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -206,11 +206,6 @@ static void radeon_legacy_rmx_mode_set(struct drm_crtc *crtc,
 	WREG32(RADEON_FP_CRTC_V_TOTAL_DISP, fp_crtc_v_total_disp);
 }
 
-void radeon_restore_common_regs(struct drm_device *dev)
-{
-	/* don't need this yet */
-}
-
 static void radeon_pll_wait_for_read_update_complete(struct drm_device *dev)
 {
 	struct radeon_device *rdev = dev->dev_private;
@@ -295,7 +290,7 @@ static uint8_t radeon_compute_pll_gain(uint16_t ref_freq, uint16_t ref_div,
 		return 1;
 }
 
-void radeon_crtc_dpms(struct drm_crtc *crtc, int mode)
+static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index 757b08f07195..92487e614778 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -271,13 +271,6 @@ static const struct drm_encoder_helper_funcs radeon_legacy_lvds_helper_funcs = {
 
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 
-#define MAX_RADEON_LEVEL 0xFF
-
-struct radeon_backlight_privdata {
-	struct radeon_encoder *encoder;
-	uint8_t negative;
-};
-
 static uint8_t radeon_legacy_lvds_level(struct backlight_device *bd)
 {
 	struct radeon_backlight_privdata *pdata = bl_get_data(bd);
@@ -286,21 +279,33 @@ static uint8_t radeon_legacy_lvds_level(struct backlight_device *bd)
 	/* Convert brightness to hardware level */
 	if (bd->props.brightness < 0)
 		level = 0;
-	else if (bd->props.brightness > MAX_RADEON_LEVEL)
-		level = MAX_RADEON_LEVEL;
+	else if (bd->props.brightness > RADEON_MAX_BL_LEVEL)
+		level = RADEON_MAX_BL_LEVEL;
 	else
 		level = bd->props.brightness;
 
 	if (pdata->negative)
-		level = MAX_RADEON_LEVEL - level;
+		level = RADEON_MAX_BL_LEVEL - level;
 
 	return level;
 }
 
-static int radeon_legacy_backlight_update_status(struct backlight_device *bd)
+u8
+radeon_legacy_get_backlight_level(struct radeon_encoder *radeon_encoder)
+{
+	struct drm_device *dev = radeon_encoder->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
+	u8 backlight_level;
+
+	backlight_level = (RREG32(RADEON_LVDS_GEN_CNTL) >>
+			   RADEON_LVDS_BL_MOD_LEVEL_SHIFT) & 0xff;
+
+	return backlight_level;
+}
+
+void
+radeon_legacy_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level)
 {
-	struct radeon_backlight_privdata *pdata = bl_get_data(bd);
-	struct radeon_encoder *radeon_encoder = pdata->encoder;
 	struct drm_device *dev = radeon_encoder->base.dev;
 	struct radeon_device *rdev = dev->dev_private;
 	int dpms_mode = DRM_MODE_DPMS_ON;
@@ -308,19 +313,31 @@ static int radeon_legacy_backlight_update_status(struct backlight_device *bd)
 	if (radeon_encoder->enc_priv) {
 		if (rdev->is_atom_bios) {
 			struct radeon_encoder_atom_dig *lvds = radeon_encoder->enc_priv;
-			dpms_mode = lvds->dpms_mode;
-			lvds->backlight_level = radeon_legacy_lvds_level(bd);
+			if (lvds->backlight_level > 0)
+				dpms_mode = lvds->dpms_mode;
+			else
+				dpms_mode = DRM_MODE_DPMS_OFF;
+			lvds->backlight_level = level;
 		} else {
 			struct radeon_encoder_lvds *lvds = radeon_encoder->enc_priv;
-			dpms_mode = lvds->dpms_mode;
-			lvds->backlight_level = radeon_legacy_lvds_level(bd);
+			if (lvds->backlight_level > 0)
+				dpms_mode = lvds->dpms_mode;
+			else
+				dpms_mode = DRM_MODE_DPMS_OFF;
+			lvds->backlight_level = level;
 		}
 	}
 
-	if (bd->props.brightness > 0)
-		radeon_legacy_lvds_update(&radeon_encoder->base, dpms_mode);
-	else
-		radeon_legacy_lvds_update(&radeon_encoder->base, DRM_MODE_DPMS_OFF);
+	radeon_legacy_lvds_update(&radeon_encoder->base, dpms_mode);
+}
+
+static int radeon_legacy_backlight_update_status(struct backlight_device *bd)
+{
+	struct radeon_backlight_privdata *pdata = bl_get_data(bd);
+	struct radeon_encoder *radeon_encoder = pdata->encoder;
+
+	radeon_legacy_set_backlight_level(radeon_encoder,
+					  radeon_legacy_lvds_level(bd));
 
 	return 0;
 }
@@ -336,7 +353,7 @@ static int radeon_legacy_backlight_get_brightness(struct backlight_device *bd)
 	backlight_level = (RREG32(RADEON_LVDS_GEN_CNTL) >>
 			   RADEON_LVDS_BL_MOD_LEVEL_SHIFT) & 0xff;
 
-	return pdata->negative ? MAX_RADEON_LEVEL - backlight_level : backlight_level;
+	return pdata->negative ? RADEON_MAX_BL_LEVEL - backlight_level : backlight_level;
 }
 
 static const struct backlight_ops radeon_backlight_ops = {
@@ -370,7 +387,7 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
 	}
 
 	memset(&props, 0, sizeof(props));
-	props.max_brightness = MAX_RADEON_LEVEL;
+	props.max_brightness = RADEON_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
 	bd = backlight_device_register("radeon_bl", &drm_connector->kdev,
 				       pdata, &radeon_backlight_ops, &props);
@@ -449,7 +466,7 @@ static void radeon_legacy_backlight_exit(struct radeon_encoder *radeon_encoder)
 	}
 
 	if (bd) {
-		struct radeon_legacy_backlight_privdata *pdata;
+		struct radeon_backlight_privdata *pdata;
 
 		pdata = bl_get_data(bd);
 		backlight_device_unregister(bd);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 0c28ca3964b1..92c5f473cf08 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -251,8 +251,23 @@ struct radeon_mode_info {
 
 	/* pointer to fbdev info structure */
 	struct radeon_fbdev *rfbdev;
+	/* firmware flags */
+	u16 firmware_flags;
+	/* pointer to backlight encoder */
+	struct radeon_encoder *bl_encoder;
 };
 
+#define RADEON_MAX_BL_LEVEL 0xFF
+
+#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
+
+struct radeon_backlight_privdata {
+	struct radeon_encoder *encoder;
+	uint8_t negative;
+};
+
+#endif
+
 #define MAX_H_CODE_TIMING_LEN 32
 #define MAX_V_CODE_TIMING_LEN 32
 
@@ -268,6 +283,18 @@ struct radeon_tv_regs {
 	uint16_t v_code_timing[MAX_V_CODE_TIMING_LEN];
 };
 
+struct radeon_atom_ss {
+	uint16_t percentage;
+	uint8_t type;
+	uint16_t step;
+	uint8_t delay;
+	uint8_t range;
+	uint8_t refdiv;
+	/* asic_ss */
+	uint16_t rate;
+	uint16_t amount;
+};
+
 struct radeon_crtc {
 	struct drm_crtc base;
 	int crtc_id;
@@ -292,6 +319,16 @@ struct radeon_crtc {
 	/* page flipping */
 	struct radeon_unpin_work *unpin_work;
 	int deferred_flip_completion;
+	/* pll sharing */
+	struct radeon_atom_ss ss;
+	bool ss_enabled;
+	u32 adjusted_clock;
+	int bpc;
+	u32 pll_reference_div;
+	u32 pll_post_div;
+	u32 pll_flags;
+	struct drm_encoder *encoder;
+	struct drm_connector *connector;
 };
 
 struct radeon_encoder_primary_dac {
@@ -345,18 +382,6 @@ struct radeon_encoder_ext_tmds {
 };
 
 /* spread spectrum */
-struct radeon_atom_ss {
-	uint16_t percentage;
-	uint8_t type;
-	uint16_t step;
-	uint8_t delay;
-	uint8_t range;
-	uint8_t refdiv;
-	/* asic_ss */
-	uint16_t rate;
-	uint16_t amount;
-};
-
 struct radeon_encoder_atom_dig {
 	bool linkb;
 	/* atom dig */
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 56ed724b398d..8b27dd6e3144 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -52,7 +52,7 @@ void radeon_bo_clear_va(struct radeon_bo *bo)
 
 	list_for_each_entry_safe(bo_va, tmp, &bo->va, bo_list) {
 		/* remove from all vm address space */
-		radeon_vm_bo_rmv(bo->rdev, bo_va->vm, bo);
+		radeon_vm_bo_rmv(bo->rdev, bo_va);
 	}
 }
 
@@ -627,18 +627,17 @@ int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
 /**
  * radeon_bo_reserve - reserve bo
  * @bo:		bo structure
- * @no_wait:		don't sleep while trying to reserve (return -EBUSY)
+ * @no_intr:	don't return -ERESTARTSYS on pending signal
  *
  * Returns:
- * -EBUSY: buffer is busy and @no_wait is true
  * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by
  * a signal. Release all buffer reservations and return to user-space.
  */
-int radeon_bo_reserve(struct radeon_bo *bo, bool no_wait)
+int radeon_bo_reserve(struct radeon_bo *bo, bool no_intr)
 {
 	int r;
 
-	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, 0);
+	r = ttm_bo_reserve(&bo->tbo, !no_intr, false, false, 0);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			dev_err(bo->rdev->dev, "%p reserve failed\n", bo);
@@ -646,16 +645,3 @@ int radeon_bo_reserve(struct radeon_bo *bo, bool no_wait)
 	}
 	return 0;
 }
-
-/* object have to be reserved */
-struct radeon_bo_va *radeon_bo_va(struct radeon_bo *rbo, struct radeon_vm *vm)
-{
-	struct radeon_bo_va *bo_va;
-
-	list_for_each_entry(bo_va, &rbo->va, bo_list) {
-		if (bo_va->vm == vm) {
-			return bo_va;
-		}
-	}
-	return NULL;
-}
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 17fb99f177cf..93cd491fff2e 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -52,7 +52,7 @@ static inline unsigned radeon_mem_type_to_domain(u32 mem_type)
 	return 0;
 }
 
-int radeon_bo_reserve(struct radeon_bo *bo, bool no_wait);
+int radeon_bo_reserve(struct radeon_bo *bo, bool no_intr);
 
 static inline void radeon_bo_unreserve(struct radeon_bo *bo)
 {
@@ -141,8 +141,6 @@ extern void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 					struct ttm_mem_reg *mem);
 extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 extern int radeon_bo_get_surface_reg(struct radeon_bo *bo);
-extern struct radeon_bo_va *radeon_bo_va(struct radeon_bo *rbo,
-					 struct radeon_vm *vm);
 
 /*
  * sub allocation
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 3ef0319981d3..aa14dbb7e4fb 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -24,9 +24,6 @@
 #include "radeon.h"
 #include "avivod.h"
 #include "atom.h"
-#ifdef CONFIG_ACPI
-#include <linux/acpi.h>
-#endif
 #include <linux/power_supply.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
@@ -36,7 +33,7 @@
 #define RADEON_WAIT_VBLANK_TIMEOUT 200
 
 static const char *radeon_pm_state_type_name[5] = {
-	"Default",
+	"",
 	"Powersave",
 	"Battery",
 	"Balanced",
@@ -50,8 +47,6 @@ static bool radeon_pm_debug_check_in_vbl(struct radeon_device *rdev, bool finish
 static void radeon_pm_update_profile(struct radeon_device *rdev);
 static void radeon_pm_set_clocks(struct radeon_device *rdev);
 
-#define ACPI_AC_CLASS           "ac_adapter"
-
 int radeon_pm_get_type_index(struct radeon_device *rdev,
 			     enum radeon_pm_state_type ps_type,
 			     int instance)
@@ -70,33 +65,17 @@ int radeon_pm_get_type_index(struct radeon_device *rdev,
 	return rdev->pm.default_power_state_index;
 }
 
-#ifdef CONFIG_ACPI
-static int radeon_acpi_event(struct notifier_block *nb,
-			     unsigned long val,
-			     void *data)
+void radeon_pm_acpi_event_handler(struct radeon_device *rdev)
 {
-	struct radeon_device *rdev = container_of(nb, struct radeon_device, acpi_nb);
-	struct acpi_bus_event *entry = (struct acpi_bus_event *)data;
-
-	if (strcmp(entry->device_class, ACPI_AC_CLASS) == 0) {
-		if (power_supply_is_system_supplied() > 0)
-			DRM_DEBUG_DRIVER("pm: AC\n");
-		else
-			DRM_DEBUG_DRIVER("pm: DC\n");
-
-		if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
-			if (rdev->pm.profile == PM_PROFILE_AUTO) {
-				mutex_lock(&rdev->pm.mutex);
-				radeon_pm_update_profile(rdev);
-				radeon_pm_set_clocks(rdev);
-				mutex_unlock(&rdev->pm.mutex);
-			}
+	if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
+		if (rdev->pm.profile == PM_PROFILE_AUTO) {
+			mutex_lock(&rdev->pm.mutex);
+			radeon_pm_update_profile(rdev);
+			radeon_pm_set_clocks(rdev);
+			mutex_unlock(&rdev->pm.mutex);
 		}
 	}
-
-	return NOTIFY_OK;
 }
-#endif
 
 static void radeon_pm_update_profile(struct radeon_device *rdev)
 {
@@ -188,8 +167,21 @@ static void radeon_set_power_state(struct radeon_device *rdev)
 		if (sclk > rdev->pm.default_sclk)
 			sclk = rdev->pm.default_sclk;
 
-		mclk = rdev->pm.power_state[rdev->pm.requested_power_state_index].
-			clock_info[rdev->pm.requested_clock_mode_index].mclk;
+		/* starting with BTC, there is one state that is used for both
+		 * MH and SH.  Difference is that we always use the high clock index for
+		 * mclk.
+		 */
+		if ((rdev->pm.pm_method == PM_METHOD_PROFILE) &&
+		    (rdev->family >= CHIP_BARTS) &&
+		    rdev->pm.active_crtc_count &&
+		    ((rdev->pm.profile_index == PM_PROFILE_MID_MH_IDX) ||
+		     (rdev->pm.profile_index == PM_PROFILE_LOW_MH_IDX)))
+			mclk = rdev->pm.power_state[rdev->pm.requested_power_state_index].
+				clock_info[rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_cm_idx].mclk;
+		else
+			mclk = rdev->pm.power_state[rdev->pm.requested_power_state_index].
+				clock_info[rdev->pm.requested_clock_mode_index].mclk;
+
 		if (mclk > rdev->pm.default_mclk)
 			mclk = rdev->pm.default_mclk;
 
@@ -253,18 +245,13 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev)
 	down_write(&rdev->pm.mclk_lock);
 	mutex_lock(&rdev->ring_lock);
 
-	/* gui idle int has issues on older chips it seems */
-	if (rdev->family >= CHIP_R600) {
-		if (rdev->irq.installed) {
-			/* wait for GPU to become idle */
-			radeon_irq_kms_wait_gui_idle(rdev);
-		}
-	} else {
-		struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-		if (ring->ready) {
-			radeon_fence_wait_empty_locked(rdev, RADEON_RING_TYPE_GFX_INDEX);
-		}
+	/* wait for the rings to drain */
+	for (i = 0; i < RADEON_NUM_RINGS; i++) {
+		struct radeon_ring *ring = &rdev->ring[i];
+		if (ring->ready)
+			radeon_fence_wait_empty_locked(rdev, i);
 	}
+
 	radeon_unmap_vram_bos(rdev);
 
 	if (rdev->irq.installed) {
@@ -320,17 +307,15 @@ static void radeon_pm_print_states(struct radeon_device *rdev)
 		for (j = 0; j < power_state->num_clock_modes; j++) {
 			clock_info = &(power_state->clock_info[j]);
 			if (rdev->flags & RADEON_IS_IGP)
-				DRM_DEBUG_DRIVER("\t\t%d e: %d%s\n",
-					j,
-					clock_info->sclk * 10,
-					clock_info->flags & RADEON_PM_MODE_NO_DISPLAY ? "\tNo display only" : "");
+				DRM_DEBUG_DRIVER("\t\t%d e: %d\n",
+						 j,
+						 clock_info->sclk * 10);
 			else
-				DRM_DEBUG_DRIVER("\t\t%d e: %d\tm: %d\tv: %d%s\n",
-					j,
-					clock_info->sclk * 10,
-					clock_info->mclk * 10,
-					clock_info->voltage.voltage,
-					clock_info->flags & RADEON_PM_MODE_NO_DISPLAY ? "\tNo display only" : "");
+				DRM_DEBUG_DRIVER("\t\t%d e: %d\tm: %d\tv: %d\n",
+						 j,
+						 clock_info->sclk * 10,
+						 clock_info->mclk * 10,
+						 clock_info->voltage.voltage);
 		}
 	}
 }
@@ -547,7 +532,9 @@ void radeon_pm_suspend(struct radeon_device *rdev)
 void radeon_pm_resume(struct radeon_device *rdev)
 {
 	/* set up the default clocks if the MC ucode is loaded */
-	if (ASIC_IS_DCE5(rdev) && rdev->mc_fw) {
+	if ((rdev->family >= CHIP_BARTS) &&
+	    (rdev->family <= CHIP_CAYMAN) &&
+	    rdev->mc_fw) {
 		if (rdev->pm.default_vddc)
 			radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
 						SET_VOLTAGE_TYPE_ASIC_VDDC);
@@ -602,7 +589,9 @@ int radeon_pm_init(struct radeon_device *rdev)
 		radeon_pm_print_states(rdev);
 		radeon_pm_init_profile(rdev);
 		/* set up the default clocks if the MC ucode is loaded */
-		if (ASIC_IS_DCE5(rdev) && rdev->mc_fw) {
+		if ((rdev->family >= CHIP_BARTS) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
+		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
 							SET_VOLTAGE_TYPE_ASIC_VDDC);
@@ -632,10 +621,6 @@ int radeon_pm_init(struct radeon_device *rdev)
 		if (ret)
 			DRM_ERROR("failed to create device file for power method\n");
 
-#ifdef CONFIG_ACPI
-		rdev->acpi_nb.notifier_call = radeon_acpi_event;
-		register_acpi_notifier(&rdev->acpi_nb);
-#endif
 		if (radeon_debugfs_pm_init(rdev)) {
 			DRM_ERROR("Failed to register debugfs file for PM!\n");
 		}
@@ -666,9 +651,6 @@ void radeon_pm_fini(struct radeon_device *rdev)
 
 		device_remove_file(rdev->dev, &dev_attr_power_profile);
 		device_remove_file(rdev->dev, &dev_attr_power_method);
-#ifdef CONFIG_ACPI
-		unregister_acpi_notifier(&rdev->acpi_nb);
-#endif
 	}
 
 	if (rdev->pm.power_state)
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index fc209c8b8666..bba66902c83b 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -43,7 +43,7 @@
  * produce command buffers which are send to the kernel and
  * put in IBs for execution by the requested ring.
  */
-int radeon_debugfs_sa_init(struct radeon_device *rdev);
+static int radeon_debugfs_sa_init(struct radeon_device *rdev);
 
 /**
  * radeon_ib_get - request an IB (Indirect Buffer)
@@ -58,7 +58,8 @@ int radeon_debugfs_sa_init(struct radeon_device *rdev);
  * Returns 0 on success, error on failure.
  */
 int radeon_ib_get(struct radeon_device *rdev, int ring,
-		  struct radeon_ib *ib, unsigned size)
+		  struct radeon_ib *ib, struct radeon_vm *vm,
+		  unsigned size)
 {
 	int i, r;
 
@@ -76,8 +77,15 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 	ib->ring = ring;
 	ib->fence = NULL;
 	ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo);
-	ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
-	ib->vm_id = 0;
+	ib->vm = vm;
+	if (vm) {
+		/* ib pool is bound at RADEON_VA_IB_OFFSET in virtual address
+		 * space and soffset is the offset inside the pool bo
+		 */
+		ib->gpu_addr = ib->sa_bo->soffset + RADEON_VA_IB_OFFSET;
+	} else {
+		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;
@@ -152,6 +160,10 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 	if (!need_sync) {
 		radeon_semaphore_free(rdev, &ib->semaphore, NULL);
 	}
+	/* if we can't remember our last VM flush then flush now! */
+	if (ib->vm && !ib->vm->last_flush) {
+		radeon_ring_vm_flush(rdev, ib->ring, ib->vm);
+	}
 	if (const_ib) {
 		radeon_ring_ib_execute(rdev, const_ib->ring, const_ib);
 		radeon_semaphore_free(rdev, &const_ib->semaphore, NULL);
@@ -166,6 +178,10 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 	if (const_ib) {
 		const_ib->fence = radeon_fence_ref(ib->fence);
 	}
+	/* we just flushed the VM, remember that */
+	if (ib->vm && !ib->vm->last_flush) {
+		ib->vm->last_flush = radeon_fence_ref(ib->fence);
+	}
 	radeon_ring_unlock_commit(rdev, ring);
 	return 0;
 }
@@ -275,7 +291,7 @@ int radeon_ib_ring_tests(struct radeon_device *rdev)
  * wptr.  The GPU then starts fetching commands and executes
  * them until the pointers are equal again.
  */
-int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
+static int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
 
 /**
  * radeon_ring_write - write a value to the ring
@@ -803,7 +819,7 @@ static struct drm_info_list radeon_debugfs_sa_list[] = {
 
 #endif
 
-int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring)
+static int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 #if defined(CONFIG_DEBUG_FS)
 	unsigned i;
@@ -823,7 +839,7 @@ int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *rin
 	return 0;
 }
 
-int radeon_debugfs_sa_init(struct radeon_device *rdev)
+static int radeon_debugfs_sa_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
 	return radeon_debugfs_add_files(rdev, radeon_debugfs_sa_list, 1);
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 83e889b9420b..cb800995d4f9 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -315,7 +315,7 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 {
 	struct radeon_fence *fences[RADEON_NUM_RINGS];
 	unsigned tries[RADEON_NUM_RINGS];
-	int i, r = -ENOMEM;
+	int i, r;
 
 	BUG_ON(align > RADEON_GPU_PAGE_SIZE);
 	BUG_ON(size > sa_manager->size);
@@ -330,7 +330,7 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 	INIT_LIST_HEAD(&(*sa_bo)->flist);
 
 	spin_lock(&sa_manager->wq.lock);
-	while(1) {
+	do {
 		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
 			fences[i] = NULL;
 			tries[i] = 0;
@@ -348,26 +348,22 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 			/* see if we can skip over some allocations */
 		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
 
-		if (!block) {
-			break;
-		}
-
 		spin_unlock(&sa_manager->wq.lock);
 		r = radeon_fence_wait_any(rdev, fences, false);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
-		if (r == -ENOENT) {
+		if (r == -ENOENT && block) {
 			r = wait_event_interruptible_locked(
 				sa_manager->wq, 
 				radeon_sa_event(sa_manager, size, align)
 			);
+
+		} else if (r == -ENOENT) {
+			r = -ENOMEM;
 		}
-		if (r) {
-			goto out_err;
-		}
-	};
 
-out_err:
+	} while (!r);
+
 	spin_unlock(&sa_manager->wq.lock);
 	kfree(*sa_bo);
 	*sa_bo = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 7c16540c10ff..587c09a00ba2 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -313,7 +313,7 @@ out_cleanup:
 		printk(KERN_WARNING "Error while testing ring sync (%d).\n", r);
 }
 
-void radeon_test_ring_sync2(struct radeon_device *rdev,
+static void radeon_test_ring_sync2(struct radeon_device *rdev,
 			    struct radeon_ring *ringA,
 			    struct radeon_ring *ringB,
 			    struct radeon_ring *ringC)
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 5b71c716d83f..5ebe1b3e5db2 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -549,7 +549,7 @@ static struct ttm_backend_func radeon_backend_func = {
 	.destroy = &radeon_ttm_backend_destroy,
 };
 
-struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
+static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 				    unsigned long size, uint32_t page_flags,
 				    struct page *dummy_read_page)
 {
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 2752f7f78237..73051ce3121e 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -242,7 +242,7 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-void rs400_gpu_init(struct radeon_device *rdev)
+static void rs400_gpu_init(struct radeon_device *rdev)
 {
 	/* FIXME: is this correct ? */
 	r420_pipes_init(rdev);
@@ -252,7 +252,7 @@ void rs400_gpu_init(struct radeon_device *rdev)
 	}
 }
 
-void rs400_mc_init(struct radeon_device *rdev)
+static void rs400_mc_init(struct radeon_device *rdev)
 {
 	u64 base;
 
@@ -370,7 +370,7 @@ static int rs400_debugfs_pcie_gart_info_init(struct radeon_device *rdev)
 #endif
 }
 
-void rs400_mc_program(struct radeon_device *rdev)
+static void rs400_mc_program(struct radeon_device *rdev)
 {
 	struct r100_mc_save save;
 
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 6590cc128f36..5a0fc74c2ba6 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -43,22 +43,30 @@
 
 #include "rs600_reg_safe.h"
 
-void rs600_gpu_init(struct radeon_device *rdev);
+static void rs600_gpu_init(struct radeon_device *rdev);
 int rs600_mc_wait_for_idle(struct radeon_device *rdev);
 
+static const u32 crtc_offsets[2] =
+{
+	0,
+	AVIVO_D2CRTC_H_TOTAL - AVIVO_D1CRTC_H_TOTAL
+};
+
 void avivo_wait_for_vblank(struct radeon_device *rdev, int crtc)
 {
-	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc];
 	int i;
 
-	if (RREG32(AVIVO_D1CRTC_CONTROL + radeon_crtc->crtc_offset) & AVIVO_CRTC_EN) {
+	if (crtc >= rdev->num_crtc)
+		return;
+
+	if (RREG32(AVIVO_D1CRTC_CONTROL + crtc_offsets[crtc]) & AVIVO_CRTC_EN) {
 		for (i = 0; i < rdev->usec_timeout; i++) {
-			if (!(RREG32(AVIVO_D1CRTC_STATUS + radeon_crtc->crtc_offset) & AVIVO_D1CRTC_V_BLANK))
+			if (!(RREG32(AVIVO_D1CRTC_STATUS + crtc_offsets[crtc]) & AVIVO_D1CRTC_V_BLANK))
 				break;
 			udelay(1);
 		}
 		for (i = 0; i < rdev->usec_timeout; i++) {
-			if (RREG32(AVIVO_D1CRTC_STATUS + radeon_crtc->crtc_offset) & AVIVO_D1CRTC_V_BLANK)
+			if (RREG32(AVIVO_D1CRTC_STATUS + crtc_offsets[crtc]) & AVIVO_D1CRTC_V_BLANK)
 				break;
 			udelay(1);
 		}
@@ -424,7 +432,7 @@ void rs600_gart_tlb_flush(struct radeon_device *rdev)
 	tmp = RREG32_MC(R_000100_MC_PT0_CNTL);
 }
 
-int rs600_gart_init(struct radeon_device *rdev)
+static int rs600_gart_init(struct radeon_device *rdev)
 {
 	int r;
 
@@ -506,7 +514,7 @@ static int rs600_gart_enable(struct radeon_device *rdev)
 	return 0;
 }
 
-void rs600_gart_disable(struct radeon_device *rdev)
+static void rs600_gart_disable(struct radeon_device *rdev)
 {
 	u32 tmp;
 
@@ -517,7 +525,7 @@ void rs600_gart_disable(struct radeon_device *rdev)
 	radeon_gart_table_vram_unpin(rdev);
 }
 
-void rs600_gart_fini(struct radeon_device *rdev)
+static void rs600_gart_fini(struct radeon_device *rdev)
 {
 	radeon_gart_fini(rdev);
 	rs600_gart_disable(rdev);
@@ -567,9 +575,6 @@ int rs600_irq_set(struct radeon_device *rdev)
 	if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) {
 		tmp |= S_000040_SW_INT_EN(1);
 	}
-	if (rdev->irq.gui_idle) {
-		tmp |= S_000040_GUI_IDLE(1);
-	}
 	if (rdev->irq.crtc_vblank_int[0] ||
 	    atomic_read(&rdev->irq.pflip[0])) {
 		mode_int |= S_006540_D1MODE_VBLANK_INT_MASK(1);
@@ -602,12 +607,6 @@ static inline u32 rs600_irq_ack(struct radeon_device *rdev)
 	uint32_t irq_mask = S_000044_SW_INT(1);
 	u32 tmp;
 
-	/* the interrupt works, but the status bit is permanently asserted */
-	if (rdev->irq.gui_idle && radeon_gui_idle(rdev)) {
-		if (!rdev->irq.gui_idle_acked)
-			irq_mask |= S_000044_GUI_IDLE_STAT(1);
-	}
-
 	if (G_000044_DISPLAY_INT_STAT(irqs)) {
 		rdev->irq.stat_regs.r500.disp_int = RREG32(R_007EDC_DISP_INTERRUPT_STATUS);
 		if (G_007EDC_LB_D1_VBLANK_INTERRUPT(rdev->irq.stat_regs.r500.disp_int)) {
@@ -667,9 +666,6 @@ int rs600_irq_process(struct radeon_device *rdev)
 	bool queue_hotplug = false;
 	bool queue_hdmi = false;
 
-	/* reset gui idle ack.  the status bit is broken */
-	rdev->irq.gui_idle_acked = false;
-
 	status = rs600_irq_ack(rdev);
 	if (!status &&
 	    !rdev->irq.stat_regs.r500.disp_int &&
@@ -683,11 +679,6 @@ int rs600_irq_process(struct radeon_device *rdev)
 		if (G_000044_SW_INT(status)) {
 			radeon_fence_process(rdev, RADEON_RING_TYPE_GFX_INDEX);
 		}
-		/* GUI idle */
-		if (G_000040_GUI_IDLE(status)) {
-			rdev->irq.gui_idle_acked = true;
-			wake_up(&rdev->irq.idle_queue);
-		}
 		/* Vertical blank interrupts */
 		if (G_007EDC_LB_D1_VBLANK_INTERRUPT(rdev->irq.stat_regs.r500.disp_int)) {
 			if (rdev->irq.crtc_vblank_int[0]) {
@@ -721,8 +712,6 @@ int rs600_irq_process(struct radeon_device *rdev)
 		}
 		status = rs600_irq_ack(rdev);
 	}
-	/* reset gui idle ack.  the status bit is broken */
-	rdev->irq.gui_idle_acked = false;
 	if (queue_hotplug)
 		schedule_work(&rdev->hotplug_work);
 	if (queue_hdmi)
@@ -764,7 +753,7 @@ int rs600_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-void rs600_gpu_init(struct radeon_device *rdev)
+static void rs600_gpu_init(struct radeon_device *rdev)
 {
 	r420_pipes_init(rdev);
 	/* Wait for mc idle */
@@ -772,7 +761,7 @@ void rs600_gpu_init(struct radeon_device *rdev)
 		dev_warn(rdev->dev, "Wait MC idle timeout before updating MC.\n");
 }
 
-void rs600_mc_init(struct radeon_device *rdev)
+static void rs600_mc_init(struct radeon_device *rdev)
 {
 	u64 base;
 
@@ -834,7 +823,7 @@ void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 	WREG32(R_000074_MC_IND_DATA, v);
 }
 
-void rs600_debugfs(struct radeon_device *rdev)
+static void rs600_debugfs(struct radeon_device *rdev)
 {
 	if (r100_debugfs_rbbm_init(rdev))
 		DRM_ERROR("Failed to register debugfs file for RBBM !\n");
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index dfb9f0fe6f38..5706d2ac75ab 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -145,7 +145,7 @@ void rs690_pm_info(struct radeon_device *rdev)
 	rdev->pm.sideport_bandwidth.full = dfixed_div(rdev->pm.sideport_bandwidth, tmp);
 }
 
-void rs690_mc_init(struct radeon_device *rdev)
+static void rs690_mc_init(struct radeon_device *rdev)
 {
 	u64 base;
 
@@ -224,7 +224,7 @@ struct rs690_watermark {
 	fixed20_12 sclk;
 };
 
-void rs690_crtc_bandwidth_compute(struct radeon_device *rdev,
+static void rs690_crtc_bandwidth_compute(struct radeon_device *rdev,
 				  struct radeon_crtc *crtc,
 				  struct rs690_watermark *wm)
 {
@@ -581,7 +581,7 @@ void rs690_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 	WREG32(R_000078_MC_INDEX, 0x7F);
 }
 
-void rs690_mc_program(struct radeon_device *rdev)
+static void rs690_mc_program(struct radeon_device *rdev)
 {
 	struct rv515_mc_save save;
 
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index ae4f93e2f135..785d09590b24 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -35,9 +35,9 @@
 #include "rv515_reg_safe.h"
 
 /* This files gather functions specifics to: rv515 */
-int rv515_debugfs_pipes_info_init(struct radeon_device *rdev);
-int rv515_debugfs_ga_info_init(struct radeon_device *rdev);
-void rv515_gpu_init(struct radeon_device *rdev);
+static int rv515_debugfs_pipes_info_init(struct radeon_device *rdev);
+static int rv515_debugfs_ga_info_init(struct radeon_device *rdev);
+static void rv515_gpu_init(struct radeon_device *rdev);
 int rv515_mc_wait_for_idle(struct radeon_device *rdev);
 
 void rv515_debugfs(struct radeon_device *rdev)
@@ -143,7 +143,7 @@ void rv515_vga_render_disable(struct radeon_device *rdev)
 		RREG32(R_000300_VGA_RENDER_CONTROL) & C_000300_VGA_VSTATUS_CNTL);
 }
 
-void rv515_gpu_init(struct radeon_device *rdev)
+static void rv515_gpu_init(struct radeon_device *rdev)
 {
 	unsigned pipe_select_current, gb_pipe_select, tmp;
 
@@ -189,7 +189,7 @@ static void rv515_vram_get_type(struct radeon_device *rdev)
 	}
 }
 
-void rv515_mc_init(struct radeon_device *rdev)
+static void rv515_mc_init(struct radeon_device *rdev)
 {
 
 	rv515_vram_get_type(rdev);
@@ -261,7 +261,7 @@ static struct drm_info_list rv515_ga_info_list[] = {
 };
 #endif
 
-int rv515_debugfs_pipes_info_init(struct radeon_device *rdev)
+static int rv515_debugfs_pipes_info_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
 	return radeon_debugfs_add_files(rdev, rv515_pipes_info_list, 1);
@@ -270,7 +270,7 @@ int rv515_debugfs_pipes_info_init(struct radeon_device *rdev)
 #endif
 }
 
-int rv515_debugfs_ga_info_init(struct radeon_device *rdev)
+static int rv515_debugfs_ga_info_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
 	return radeon_debugfs_add_files(rdev, rv515_ga_info_list, 1);
@@ -310,7 +310,7 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
 	WREG32(R_000300_VGA_RENDER_CONTROL, save->vga_render_control);
 }
 
-void rv515_mc_program(struct radeon_device *rdev)
+static void rv515_mc_program(struct radeon_device *rdev)
 {
 	struct rv515_mc_save save;
 
@@ -787,7 +787,7 @@ struct rv515_watermark {
 	fixed20_12 sclk;
 };
 
-void rv515_crtc_bandwidth_compute(struct radeon_device *rdev,
+static void rv515_crtc_bandwidth_compute(struct radeon_device *rdev,
 				  struct radeon_crtc *crtc,
 				  struct rv515_watermark *wm)
 {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 35a4152bb1ad..79814a08c8e5 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -124,7 +124,7 @@ void rv770_pm_misc(struct radeon_device *rdev)
 /*
  * GART
  */
-int rv770_pcie_gart_enable(struct radeon_device *rdev)
+static int rv770_pcie_gart_enable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int r, i;
@@ -175,7 +175,7 @@ int rv770_pcie_gart_enable(struct radeon_device *rdev)
 	return 0;
 }
 
-void rv770_pcie_gart_disable(struct radeon_device *rdev)
+static void rv770_pcie_gart_disable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int i;
@@ -201,7 +201,7 @@ void rv770_pcie_gart_disable(struct radeon_device *rdev)
 	radeon_gart_table_vram_unpin(rdev);
 }
 
-void rv770_pcie_gart_fini(struct radeon_device *rdev)
+static void rv770_pcie_gart_fini(struct radeon_device *rdev)
 {
 	radeon_gart_fini(rdev);
 	rv770_pcie_gart_disable(rdev);
@@ -209,7 +209,7 @@ void rv770_pcie_gart_fini(struct radeon_device *rdev)
 }
 
 
-void rv770_agp_enable(struct radeon_device *rdev)
+static void rv770_agp_enable(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int i;
@@ -839,7 +839,7 @@ void r700_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc)
 	}
 }
 
-int rv770_mc_init(struct radeon_device *rdev)
+static int rv770_mc_init(struct radeon_device *rdev)
 {
 	u32 tmp;
 	int chansize, numchan;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index d883cae56378..f79633a036c3 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1806,13 +1806,14 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 #endif
 			  (ib->gpu_addr & 0xFFFFFFFC));
 	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
-	radeon_ring_write(ring, ib->length_dw | (ib->vm_id << 24));
+	radeon_ring_write(ring, ib->length_dw |
+			  (ib->vm ? (ib->vm->id << 24) : 0));
 
 	if (!ib->is_const_ib) {
 		/* flush read cache over gart for this vmid */
 		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
 		radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-		radeon_ring_write(ring, ib->vm_id);
+		radeon_ring_write(ring, ib->vm ? ib->vm->id : 0);
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
 		radeon_ring_write(ring, PACKET3_TCL1_ACTION_ENA |
 				  PACKET3_TC_ACTION_ENA |
@@ -2363,7 +2364,7 @@ void si_pcie_gart_tlb_flush(struct radeon_device *rdev)
 	WREG32(VM_INVALIDATE_REQUEST, 1);
 }
 
-int si_pcie_gart_enable(struct radeon_device *rdev)
+static int si_pcie_gart_enable(struct radeon_device *rdev)
 {
 	int r, i;
 
@@ -2425,7 +2426,7 @@ int si_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(VM_CONTEXT1_PROTECTION_FAULT_DEFAULT_ADDR,
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 0);
-	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
+	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
 
 	si_pcie_gart_tlb_flush(rdev);
@@ -2436,7 +2437,7 @@ int si_pcie_gart_enable(struct radeon_device *rdev)
 	return 0;
 }
 
-void si_pcie_gart_disable(struct radeon_device *rdev)
+static void si_pcie_gart_disable(struct radeon_device *rdev)
 {
 	/* Disable all tables */
 	WREG32(VM_CONTEXT0_CNTL, 0);
@@ -2455,7 +2456,7 @@ void si_pcie_gart_disable(struct radeon_device *rdev)
 	radeon_gart_table_vram_unpin(rdev);
 }
 
-void si_pcie_gart_fini(struct radeon_device *rdev)
+static void si_pcie_gart_fini(struct radeon_device *rdev)
 {
 	si_pcie_gart_disable(rdev);
 	radeon_gart_table_vram_free(rdev);
@@ -2788,41 +2789,84 @@ void si_vm_fini(struct radeon_device *rdev)
 {
 }
 
-int si_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id)
+/**
+ * si_vm_set_page - update the page tables using the CP
+ *
+ * @rdev: radeon_device pointer
+ * @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-si).
+ */
+void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
+		    uint64_t addr, unsigned count,
+		    uint32_t incr, uint32_t flags)
 {
-	if (id < 8)
-		WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (id << 2), vm->pt_gpu_addr >> 12);
-	else
-		WREG32(VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((id - 8) << 2),
-		       vm->pt_gpu_addr >> 12);
-	/* flush hdp cache */
-	WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
-	/* bits 0-15 are the VM contexts0-15 */
-	WREG32(VM_INVALIDATE_REQUEST, 1 << id);
-	return 0;
+	struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index];
+	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
+	int i;
+	uint64_t value;
+
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 2 + count * 2));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(1)));
+	radeon_ring_write(ring, pe);
+	radeon_ring_write(ring, upper_32_bits(pe));
+	for (i = 0; i < count; ++i) {
+		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;
+		radeon_ring_write(ring, value);
+		radeon_ring_write(ring, upper_32_bits(value));
+	}
 }
 
-void si_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm)
+void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
-	if (vm->id < 8)
-		WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2), 0);
-	else
-		WREG32(VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2), 0);
-	/* flush hdp cache */
-	WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
-	/* bits 0-15 are the VM contexts0-15 */
-	WREG32(VM_INVALIDATE_REQUEST, 1 << vm->id);
-}
+	struct radeon_ring *ring = &rdev->ring[ridx];
 
-void si_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	if (vm->id == -1)
+	if (vm == NULL)
 		return;
 
+	/* write new base address */
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(0)));
+
+	if (vm->id < 8) {
+		radeon_ring_write(ring,
+				  (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
+	} else {
+		radeon_ring_write(ring,
+				  (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
+	}
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+
 	/* flush hdp cache */
-	WREG32(HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1);
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(0)));
+	radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, 0x1);
+
 	/* bits 0-15 are the VM contexts0-15 */
-	WREG32(VM_INVALIDATE_REQUEST, 1 << vm->id);
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(0)));
+	radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, 1 << vm->id);
 }
 
 /*
@@ -3199,10 +3243,6 @@ int si_irq_set(struct radeon_device *rdev)
 		DRM_DEBUG("si_irq_set: hpd 6\n");
 		hpd6 |= DC_HPDx_INT_EN;
 	}
-	if (rdev->irq.gui_idle) {
-		DRM_DEBUG("gui idle\n");
-		grbm_int_cntl |= GUI_IDLE_INT_ENABLE;
-	}
 
 	WREG32(CP_INT_CNTL_RING0, cp_int_cntl);
 	WREG32(CP_INT_CNTL_RING1, cp_int_cntl1);
@@ -3658,7 +3698,6 @@ restart_ih:
 			break;
 		case 233: /* GUI IDLE */
 			DRM_DEBUG("IH: GUI idle\n");
-			wake_up(&rdev->irq.idle_queue);
 			break;
 		default:
 			DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index ef4815c27b1c..7d2a20e56577 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -812,6 +812,21 @@
 #define	PACKET3_DRAW_INDEX_OFFSET_2			0x35
 #define	PACKET3_DRAW_INDEX_MULTI_ELEMENT		0x36
 #define	PACKET3_WRITE_DATA				0x37
+#define		WRITE_DATA_DST_SEL(x)                   ((x) << 8)
+                /* 0 - register
+		 * 1 - memory (sync - via GRBM)
+		 * 2 - tc/l2
+		 * 3 - gds
+		 * 4 - reserved
+		 * 5 - memory (async - direct)
+		 */
+#define		WR_ONE_ADDR                             (1 << 16)
+#define		WR_CONFIRM                              (1 << 20)
+#define		WRITE_DATA_ENGINE_SEL(x)                ((x) << 30)
+                /* 0 - me
+		 * 1 - pfp
+		 * 2 - ce
+		 */
 #define	PACKET3_DRAW_INDEX_INDIRECT_MULTI		0x38
 #define	PACKET3_MEM_SEMAPHORE				0x39
 #define	PACKET3_MPEG_INDEX				0x3A