Merge tag 'v3.1-rc10' into drm-core-next

There are a number of fixes in mainline required for code in -next,
also there was a few conflicts I'd rather resolve myself.

Signed-off-by: Dave Airlie <airlied@redhat.com>

Conflicts:
	drivers/gpu/drm/radeon/evergreen.c
	drivers/gpu/drm/radeon/r600.c
	drivers/gpu/drm/radeon/radeon_asic.h

19 files changed, 147 insertions, 283 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index b79c6f14fb72..c96b019a3b76 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -67,11 +67,11 @@ module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 MODULE_PARM_DESC(i915_enable_rc6,
 		"Enable power-saving render C-state 6 (default: true)");
 
-unsigned int i915_enable_fbc __read_mostly = 1;
+unsigned int i915_enable_fbc __read_mostly = -1;
 module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
 MODULE_PARM_DESC(i915_enable_fbc,
 		"Enable frame buffer compression for power savings "
-		"(default: false)");
+		"(default: -1 (use per-chip default))");
 
 unsigned int i915_lvds_downclock __read_mostly = 0;
 module_param_named(lvds_downclock, i915_lvds_downclock, int, 0400);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f0e5f9f32aa8..8230cf54cc8d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1800,6 +1800,7 @@ static void intel_update_fbc(struct drm_device *dev)
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 	struct drm_i915_gem_object *obj;
+	int enable_fbc;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -1840,8 +1841,15 @@ static void intel_update_fbc(struct drm_device *dev)
 	intel_fb = to_intel_framebuffer(fb);
 	obj = intel_fb->obj;
 
-	if (!i915_enable_fbc) {
-		DRM_DEBUG_KMS("fbc disabled per module param (default off)\n");
+	enable_fbc = i915_enable_fbc;
+	if (enable_fbc < 0) {
+		DRM_DEBUG_KMS("fbc set to per-chip default\n");
+		enable_fbc = 1;
+		if (INTEL_INFO(dev)->gen <= 5)
+			enable_fbc = 0;
+	}
+	if (!enable_fbc) {
+		DRM_DEBUG_KMS("fbc disabled per module param\n");
 		dev_priv->no_fbc_reason = FBC_MODULE_PARAM;
 		goto out_disable;
 	}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b7e718639b13..98044d626a8d 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -337,9 +337,6 @@ extern void intel_release_load_detect_pipe(struct intel_encoder *intel_encoder,
 					   struct drm_connector *connector,
 					   struct intel_load_detect_pipe *old);
 
-extern struct drm_connector* intel_sdvo_find(struct drm_device *dev, int sdvoB);
-extern int intel_sdvo_supports_hotplug(struct drm_connector *connector);
-extern void intel_sdvo_set_hotplug(struct drm_connector *connector, int enable);
 extern void intelfb_restore(void);
 extern void intel_crtc_fb_gamma_set(struct drm_crtc *crtc, u16 red, u16 green,
 				    u16 blue, int regno);
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index aa94110f0be4..731200243219 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -92,6 +92,11 @@ struct intel_sdvo {
 	*/
 	uint16_t attached_output;
 
+	/*
+	 * Hotplug activation bits for this device
+	 */
+	uint8_t hotplug_active[2];
+
 	/**
 	 * This is used to select the color range of RBG outputs in HDMI mode.
 	 * It is only valid when using TMDS encoding and 8 bit per color mode.
@@ -1208,74 +1213,20 @@ static bool intel_sdvo_get_capabilities(struct intel_sdvo *intel_sdvo, struct in
 	return true;
 }
 
-/* No use! */
-#if 0
-struct drm_connector* intel_sdvo_find(struct drm_device *dev, int sdvoB)
-{
-	struct drm_connector *connector = NULL;
-	struct intel_sdvo *iout = NULL;
-	struct intel_sdvo *sdvo;
-
-	/* find the sdvo connector */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		iout = to_intel_sdvo(connector);
-
-		if (iout->type != INTEL_OUTPUT_SDVO)
-			continue;
-
-		sdvo = iout->dev_priv;
-
-		if (sdvo->sdvo_reg == SDVOB && sdvoB)
-			return connector;
-
-		if (sdvo->sdvo_reg == SDVOC && !sdvoB)
-			return connector;
-
-	}
-
-	return NULL;
-}
-
-int intel_sdvo_supports_hotplug(struct drm_connector *connector)
+static int intel_sdvo_supports_hotplug(struct intel_sdvo *intel_sdvo)
 {
 	u8 response[2];
-	u8 status;
-	struct intel_sdvo *intel_sdvo;
-	DRM_DEBUG_KMS("\n");
-
-	if (!connector)
-		return 0;
-
-	intel_sdvo = to_intel_sdvo(connector);
 
 	return intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_HOT_PLUG_SUPPORT,
 				    &response, 2) && response[0];
 }
 
-void intel_sdvo_set_hotplug(struct drm_connector *connector, int on)
+static void intel_sdvo_enable_hotplug(struct intel_encoder *encoder)
 {
-	u8 response[2];
-	u8 status;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(connector);
-
-	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG, NULL, 0);
-	intel_sdvo_read_response(intel_sdvo, &response, 2);
-
-	if (on) {
-		intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_GET_HOT_PLUG_SUPPORT, NULL, 0);
-		status = intel_sdvo_read_response(intel_sdvo, &response, 2);
-
-		intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG, &response, 2);
-	} else {
-		response[0] = 0;
-		response[1] = 0;
-		intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG, &response, 2);
-	}
+	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
 
-	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG, NULL, 0);
-	intel_sdvo_read_response(intel_sdvo, &response, 2);
+	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG, &intel_sdvo->hotplug_active, 2);
 }
-#endif
 
 static bool
 intel_sdvo_multifunc_encoder(struct intel_sdvo *intel_sdvo)
@@ -2045,6 +1996,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 {
 	struct drm_encoder *encoder = &intel_sdvo->base.base;
 	struct drm_connector *connector;
+	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
 	struct intel_connector *intel_connector;
 	struct intel_sdvo_connector *intel_sdvo_connector;
 
@@ -2062,7 +2014,17 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 
 	intel_connector = &intel_sdvo_connector->base;
 	connector = &intel_connector->base;
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
+	if (intel_sdvo_supports_hotplug(intel_sdvo) & (1 << device)) {
+		connector->polled = DRM_CONNECTOR_POLL_HPD;
+		intel_sdvo->hotplug_active[0] |= 1 << device;
+		/* Some SDVO devices have one-shot hotplug interrupts.
+		 * Ensure that they get re-enabled when an interrupt happens.
+		 */
+		intel_encoder->hot_plug = intel_sdvo_enable_hotplug;
+		intel_sdvo_enable_hotplug(intel_encoder);
+	}
+	else
+		connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 	encoder->encoder_type = DRM_MODE_ENCODER_TMDS;
 	connector->connector_type = DRM_MODE_CONNECTOR_DVID;
 
@@ -2569,6 +2531,14 @@ bool intel_sdvo_init(struct drm_device *dev, int sdvo_reg)
 	if (!intel_sdvo_get_capabilities(intel_sdvo, &intel_sdvo->caps))
 		goto err;
 
+	/* Set up hotplug command - note paranoia about contents of reply.
+	 * We assume that the hardware is in a sane state, and only touch
+	 * the bits we think we understand.
+	 */
+	intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG,
+			     &intel_sdvo->hotplug_active, 2);
+	intel_sdvo->hotplug_active[0] &= ~0x3;
+
 	if (intel_sdvo_output_setup(intel_sdvo,
 				    intel_sdvo->caps.output_flags) != true) {
 		DRM_DEBUG_KMS("SDVO output failed to setup on SDVO%c\n",
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 7ad43c6b1db7..79e8ebc05307 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -115,6 +115,7 @@ static int radeon_dp_aux_native_write(struct radeon_connector *radeon_connector,
 	u8 msg[20];
 	int msg_bytes = send_bytes + 4;
 	u8 ack;
+	unsigned retry;
 
 	if (send_bytes > 16)
 		return -1;
@@ -125,20 +126,22 @@ static int radeon_dp_aux_native_write(struct radeon_connector *radeon_connector,
 	msg[3] = (msg_bytes << 4) | (send_bytes - 1);
 	memcpy(&msg[4], send, send_bytes);
 
-	while (1) {
+	for (retry = 0; retry < 4; retry++) {
 		ret = radeon_process_aux_ch(dig_connector->dp_i2c_bus,
 					    msg, msg_bytes, NULL, 0, delay, &ack);
-		if (ret < 0)
+		if (ret == -EBUSY)
+			continue;
+		else if (ret < 0)
 			return ret;
 		if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK)
-			break;
+			return send_bytes;
 		else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER)
 			udelay(400);
 		else
 			return -EIO;
 	}
 
-	return send_bytes;
+	return -EIO;
 }
 
 static int radeon_dp_aux_native_read(struct radeon_connector *radeon_connector,
@@ -149,26 +152,31 @@ static int radeon_dp_aux_native_read(struct radeon_connector *radeon_connector,
 	int msg_bytes = 4;
 	u8 ack;
 	int ret;
+	unsigned retry;
 
 	msg[0] = address;
 	msg[1] = address >> 8;
 	msg[2] = AUX_NATIVE_READ << 4;
 	msg[3] = (msg_bytes << 4) | (recv_bytes - 1);
 
-	while (1) {
+	for (retry = 0; retry < 4; retry++) {
 		ret = radeon_process_aux_ch(dig_connector->dp_i2c_bus,
 					    msg, msg_bytes, recv, recv_bytes, delay, &ack);
-		if (ret == 0)
-			return -EPROTO;
-		if (ret < 0)
+		if (ret == -EBUSY)
+			continue;
+		else if (ret < 0)
 			return ret;
 		if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK)
 			return ret;
 		else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER)
 			udelay(400);
+		else if (ret == 0)
+			return -EPROTO;
 		else
 			return -EIO;
 	}
+
+	return -EIO;
 }
 
 static void radeon_write_dpcd_reg(struct radeon_connector *radeon_connector,
@@ -232,7 +240,9 @@ int radeon_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 	for (retry = 0; retry < 4; retry++) {
 		ret = radeon_process_aux_ch(auxch,
 					    msg, msg_bytes, reply, reply_bytes, 0, &ack);
-		if (ret < 0) {
+		if (ret == -EBUSY)
+			continue;
+		else if (ret < 0) {
 			DRM_DEBUG_KMS("aux_ch failed %d\n", ret);
 			return ret;
 		}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 35b5673d432d..ed406e8404a3 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1407,7 +1407,8 @@ int evergreen_cp_resume(struct radeon_device *rdev)
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32(CP_RB_CNTL, tmp | RB_RPTR_WR_ENA);
 	WREG32(CP_RB_RPTR_WR, 0);
-	WREG32(CP_RB_WPTR, 0);
+	rdev->cp.wptr = 0;
+	WREG32(CP_RB_WPTR, rdev->cp.wptr);
 
 	/* set the wb address wether it's enabled or not */
 	WREG32(CP_RB_RPTR_ADDR,
@@ -1429,7 +1430,6 @@ int evergreen_cp_resume(struct radeon_device *rdev)
 	WREG32(CP_DEBUG, (1 << 27) | (1 << 28));
 
 	rdev->cp.rptr = RREG32(CP_RB_RPTR);
-	rdev->cp.wptr = RREG32(CP_RB_WPTR);
 
 	evergreen_cp_start(rdev);
 	rdev->cp.ready = true;
@@ -1593,48 +1593,6 @@ static u32 evergreen_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	return backend_map;
 }
 
-static void evergreen_program_channel_remap(struct radeon_device *rdev)
-{
-	u32 tcp_chan_steer_lo, tcp_chan_steer_hi, mc_shared_chremap, tmp;
-
-	tmp = RREG32(MC_SHARED_CHMAP);
-	switch ((tmp & NOOFCHAN_MASK) >> NOOFCHAN_SHIFT) {
-	case 0:
-	case 1:
-	case 2:
-	case 3:
-	default:
-		/* default mapping */
-		mc_shared_chremap = 0x00fac688;
-		break;
-	}
-
-	switch (rdev->family) {
-	case CHIP_HEMLOCK:
-	case CHIP_CYPRESS:
-	case CHIP_BARTS:
-		tcp_chan_steer_lo = 0x54763210;
-		tcp_chan_steer_hi = 0x0000ba98;
-		break;
-	case CHIP_JUNIPER:
-	case CHIP_REDWOOD:
-	case CHIP_CEDAR:
-	case CHIP_PALM:
-	case CHIP_SUMO:
-	case CHIP_SUMO2:
-	case CHIP_TURKS:
-	case CHIP_CAICOS:
-	default:
-		tcp_chan_steer_lo = 0x76543210;
-		tcp_chan_steer_hi = 0x0000ba98;
-		break;
-	}
-
-	WREG32(TCP_CHAN_STEER_LO, tcp_chan_steer_lo);
-	WREG32(TCP_CHAN_STEER_HI, tcp_chan_steer_hi);
-	WREG32(MC_SHARED_CHREMAP, mc_shared_chremap);
-}
-
 static void evergreen_gpu_init(struct radeon_device *rdev)
 {
 	u32 cc_rb_backend_disable = 0;
@@ -2081,8 +2039,6 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 
-	evergreen_program_channel_remap(rdev);
-
 	num_shader_engines = ((RREG32(GB_ADDR_CONFIG) & NUM_SHADER_ENGINES(3)) >> 12) + 1;
 	grbm_gfx_index = INSTANCE_BROADCAST_WRITES;
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 770cc2ab088a..556b7bc3418b 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -570,36 +570,6 @@ static u32 cayman_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	return backend_map;
 }
 
-static void cayman_program_channel_remap(struct radeon_device *rdev)
-{
-	u32 tcp_chan_steer_lo, tcp_chan_steer_hi, mc_shared_chremap, tmp;
-
-	tmp = RREG32(MC_SHARED_CHMAP);
-	switch ((tmp & NOOFCHAN_MASK) >> NOOFCHAN_SHIFT) {
-	case 0:
-	case 1:
-	case 2:
-	case 3:
-	default:
-		/* default mapping */
-		mc_shared_chremap = 0x00fac688;
-		break;
-	}
-
-	switch (rdev->family) {
-	case CHIP_CAYMAN:
-	default:
-		//tcp_chan_steer_lo = 0x54763210
-		tcp_chan_steer_lo = 0x76543210;
-		tcp_chan_steer_hi = 0x0000ba98;
-		break;
-	}
-
-	WREG32(TCP_CHAN_STEER_LO, tcp_chan_steer_lo);
-	WREG32(TCP_CHAN_STEER_HI, tcp_chan_steer_hi);
-	WREG32(MC_SHARED_CHREMAP, mc_shared_chremap);
-}
-
 static u32 cayman_get_disable_mask_per_asic(struct radeon_device *rdev,
 					    u32 disable_mask_per_se,
 					    u32 max_disable_mask_per_se,
@@ -843,8 +813,6 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 	WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 
-	cayman_program_channel_remap(rdev);
-
 	/* primary versions */
 	WREG32(CC_RB_BACKEND_DISABLE, cc_rb_backend_disable);
 	WREG32(CC_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
@@ -1191,7 +1159,8 @@ int cayman_cp_resume(struct radeon_device *rdev)
 
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32(CP_RB0_CNTL, tmp | RB_RPTR_WR_ENA);
-	WREG32(CP_RB0_WPTR, 0);
+	rdev->cp.wptr = 0;
+	WREG32(CP_RB0_WPTR, rdev->cp.wptr);
 
 	/* set the wb address wether it's enabled or not */
 	WREG32(CP_RB0_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC);
@@ -1211,7 +1180,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
 	WREG32(CP_RB0_BASE, rdev->cp.gpu_addr >> 8);
 
 	rdev->cp.rptr = RREG32(CP_RB0_RPTR);
-	rdev->cp.wptr = RREG32(CP_RB0_WPTR);
 
 	/* ring1  - compute only */
 	/* Set ring buffer size */
@@ -1224,7 +1192,8 @@ int cayman_cp_resume(struct radeon_device *rdev)
 
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32(CP_RB1_CNTL, tmp | RB_RPTR_WR_ENA);
-	WREG32(CP_RB1_WPTR, 0);
+	rdev->cp1.wptr = 0;
+	WREG32(CP_RB1_WPTR, rdev->cp1.wptr);
 
 	/* set the wb address wether it's enabled or not */
 	WREG32(CP_RB1_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP1_RPTR_OFFSET) & 0xFFFFFFFC);
@@ -1236,7 +1205,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
 	WREG32(CP_RB1_BASE, rdev->cp1.gpu_addr >> 8);
 
 	rdev->cp1.rptr = RREG32(CP_RB1_RPTR);
-	rdev->cp1.wptr = RREG32(CP_RB1_WPTR);
 
 	/* ring2 - compute only */
 	/* Set ring buffer size */
@@ -1249,7 +1217,8 @@ int cayman_cp_resume(struct radeon_device *rdev)
 
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32(CP_RB2_CNTL, tmp | RB_RPTR_WR_ENA);
-	WREG32(CP_RB2_WPTR, 0);
+	rdev->cp2.wptr = 0;
+	WREG32(CP_RB2_WPTR, rdev->cp2.wptr);
 
 	/* set the wb address wether it's enabled or not */
 	WREG32(CP_RB2_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP2_RPTR_OFFSET) & 0xFFFFFFFC);
@@ -1261,7 +1230,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
 	WREG32(CP_RB2_BASE, rdev->cp2.gpu_addr >> 8);
 
 	rdev->cp2.rptr = RREG32(CP_RB2_RPTR);
-	rdev->cp2.wptr = RREG32(CP_RB2_WPTR);
 
 	/* start the rings */
 	cayman_cp_start(rdev);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index e108f265882a..8f8b8fa14357 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -826,11 +826,11 @@ void r100_fence_ring_emit(struct radeon_device *rdev,
 int r100_copy_blit(struct radeon_device *rdev,
 		   uint64_t src_offset,
 		   uint64_t dst_offset,
-		   unsigned num_pages,
+		   unsigned num_gpu_pages,
 		   struct radeon_fence *fence)
 {
 	uint32_t cur_pages;
-	uint32_t stride_bytes = PAGE_SIZE;
+	uint32_t stride_bytes = RADEON_GPU_PAGE_SIZE;
 	uint32_t pitch;
 	uint32_t stride_pixels;
 	unsigned ndw;
@@ -842,7 +842,7 @@ int r100_copy_blit(struct radeon_device *rdev,
 	/* radeon pitch is /64 */
 	pitch = stride_bytes / 64;
 	stride_pixels = stride_bytes / 4;
-	num_loops = DIV_ROUND_UP(num_pages, 8191);
+	num_loops = DIV_ROUND_UP(num_gpu_pages, 8191);
 
 	/* Ask for enough room for blit + flush + fence */
 	ndw = 64 + (10 * num_loops);
@@ -851,12 +851,12 @@ int r100_copy_blit(struct radeon_device *rdev,
 		DRM_ERROR("radeon: moving bo (%d) asking for %u dw.\n", r, ndw);
 		return -EINVAL;
 	}
-	while (num_pages > 0) {
-		cur_pages = num_pages;
+	while (num_gpu_pages > 0) {
+		cur_pages = num_gpu_pages;
 		if (cur_pages > 8191) {
 			cur_pages = 8191;
 		}
-		num_pages -= cur_pages;
+		num_gpu_pages -= cur_pages;
 
 		/* pages are in Y direction - height
 		   page width in X direction - width */
@@ -878,8 +878,8 @@ int r100_copy_blit(struct radeon_device *rdev,
 		radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
 		radeon_ring_write(rdev, 0);
 		radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
-		radeon_ring_write(rdev, num_pages);
-		radeon_ring_write(rdev, num_pages);
+		radeon_ring_write(rdev, num_gpu_pages);
+		radeon_ring_write(rdev, num_gpu_pages);
 		radeon_ring_write(rdev, cur_pages | (stride_pixels << 16));
 	}
 	radeon_ring_write(rdev, PACKET0(RADEON_DSTCACHE_CTLSTAT, 0));
@@ -1095,7 +1095,8 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 	/* Force read & write ptr to 0 */
 	WREG32(RADEON_CP_RB_CNTL, tmp | RADEON_RB_RPTR_WR_ENA | RADEON_RB_NO_UPDATE);
 	WREG32(RADEON_CP_RB_RPTR_WR, 0);
-	WREG32(RADEON_CP_RB_WPTR, 0);
+	rdev->cp.wptr = 0;
+	WREG32(RADEON_CP_RB_WPTR, rdev->cp.wptr);
 
 	/* set the wb address whether it's enabled or not */
 	WREG32(R_00070C_CP_RB_RPTR_ADDR,
@@ -1112,9 +1113,6 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 	WREG32(RADEON_CP_RB_CNTL, tmp);
 	udelay(10);
 	rdev->cp.rptr = RREG32(RADEON_CP_RB_RPTR);
-	rdev->cp.wptr = RREG32(RADEON_CP_RB_WPTR);
-	/* protect against crazy HW on resume */
-	rdev->cp.wptr &= rdev->cp.ptr_mask;
 	/* Set cp mode to bus mastering & enable cp*/
 	WREG32(RADEON_CP_CSQ_MODE,
 	       REG_SET(RADEON_INDIRECT2_START, indirect2_start) |
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index f24058300413..a1f3ba063c2d 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -84,7 +84,7 @@ static int r200_get_vtx_size_0(uint32_t vtx_fmt_0)
 int r200_copy_dma(struct radeon_device *rdev,
 		  uint64_t src_offset,
 		  uint64_t dst_offset,
-		  unsigned num_pages,
+		  unsigned num_gpu_pages,
 		  struct radeon_fence *fence)
 {
 	uint32_t size;
@@ -93,7 +93,7 @@ int r200_copy_dma(struct radeon_device *rdev,
 	int r = 0;
 
 	/* radeon pitch is /64 */
-	size = num_pages << PAGE_SHIFT;
+	size = num_gpu_pages << RADEON_GPU_PAGE_SHIFT;
 	num_loops = DIV_ROUND_UP(size, 0x1FFFFF);
 	r = radeon_ring_lock(rdev, num_loops * 4 + 64);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index e87f5662a104..12470b090ddf 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2212,7 +2212,8 @@ int r600_cp_resume(struct radeon_device *rdev)
 	/* Initialize the ring buffer's read and write pointers */
 	WREG32(CP_RB_CNTL, tmp | RB_RPTR_WR_ENA);
 	WREG32(CP_RB_RPTR_WR, 0);
-	WREG32(CP_RB_WPTR, 0);
+	rdev->cp.wptr = 0;
+	WREG32(CP_RB_WPTR, rdev->cp.wptr);
 
 	/* set the wb address whether it's enabled or not */
 	WREG32(CP_RB_RPTR_ADDR,
@@ -2234,7 +2235,6 @@ int r600_cp_resume(struct radeon_device *rdev)
 	WREG32(CP_DEBUG, (1 << 27) | (1 << 28));
 
 	rdev->cp.rptr = RREG32(CP_RB_RPTR);
-	rdev->cp.wptr = RREG32(CP_RB_WPTR);
 
 	r600_cp_start(rdev);
 	rdev->cp.ready = true;
@@ -2356,21 +2356,23 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 }
 
 int r600_copy_blit(struct radeon_device *rdev,
-		   uint64_t src_offset, uint64_t dst_offset,
-		   unsigned num_pages, struct radeon_fence *fence)
+		   uint64_t src_offset,
+		   uint64_t dst_offset,
+		   unsigned num_gpu_pages,
+		   struct radeon_fence *fence)
 {
 	int r;
 
 	mutex_lock(&rdev->r600_blit.mutex);
 	rdev->r600_blit.vb_ib = NULL;
-	r = r600_blit_prepare_copy(rdev, num_pages);
+	r = r600_blit_prepare_copy(rdev, num_gpu_pages);
 	if (r) {
 		if (rdev->r600_blit.vb_ib)
 			radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
 		mutex_unlock(&rdev->r600_blit.mutex);
 		return r;
 	}
-	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_pages);
+	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages);
 	r600_blit_done_copy(rdev, fence);
 	mutex_unlock(&rdev->r600_blit.mutex);
 	return 0;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 3cf983c5243f..156b8b7e028e 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -322,6 +322,7 @@ union radeon_gart_table {
 
 #define RADEON_GPU_PAGE_SIZE 4096
 #define RADEON_GPU_PAGE_MASK (RADEON_GPU_PAGE_SIZE - 1)
+#define RADEON_GPU_PAGE_SHIFT 12
 
 struct radeon_gart {
 	dma_addr_t			table_addr;
@@ -912,17 +913,17 @@ struct radeon_asic {
 	int (*copy_blit)(struct radeon_device *rdev,
 			 uint64_t src_offset,
 			 uint64_t dst_offset,
-			 unsigned num_pages,
+			 unsigned num_gpu_pages,
 			 struct radeon_fence *fence);
 	int (*copy_dma)(struct radeon_device *rdev,
 			uint64_t src_offset,
 			uint64_t dst_offset,
-			unsigned num_pages,
+			unsigned num_gpu_pages,
 			struct radeon_fence *fence);
 	int (*copy)(struct radeon_device *rdev,
 		    uint64_t src_offset,
 		    uint64_t dst_offset,
-		    unsigned num_pages,
+		    unsigned num_gpu_pages,
 		    struct radeon_fence *fence);
 	uint32_t (*get_engine_clock)(struct radeon_device *rdev);
 	void (*set_engine_clock)(struct radeon_device *rdev, uint32_t eng_clock);
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index e040de3e8cc7..85f14f0337e4 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -75,7 +75,7 @@ uint32_t r100_pll_rreg(struct radeon_device *rdev, uint32_t reg);
 int r100_copy_blit(struct radeon_device *rdev,
 		   uint64_t src_offset,
 		   uint64_t dst_offset,
-		   unsigned num_pages,
+		   unsigned num_gpu_pages,
 		   struct radeon_fence *fence);
 int r100_set_surface_reg(struct radeon_device *rdev, int reg,
 			 uint32_t tiling_flags, uint32_t pitch,
@@ -143,7 +143,7 @@ extern void r100_post_page_flip(struct radeon_device *rdev, int crtc);
 extern int r200_copy_dma(struct radeon_device *rdev,
 			 uint64_t src_offset,
 			 uint64_t dst_offset,
-			 unsigned num_pages,
+			 unsigned num_gpu_pages,
 			 struct radeon_fence *fence);
 void r200_set_safe_registers(struct radeon_device *rdev);
 
@@ -311,7 +311,7 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int r600_ring_test(struct radeon_device *rdev);
 int r600_copy_blit(struct radeon_device *rdev,
 		   uint64_t src_offset, uint64_t dst_offset,
-		   unsigned num_pages, struct radeon_fence *fence);
+		   unsigned num_gpu_pages, struct radeon_fence *fence);
 void r600_hpd_init(struct radeon_device *rdev);
 void r600_hpd_fini(struct radeon_device *rdev);
 bool r600_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 9b5b3e4d2386..dec6cbe6a0a6 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -68,11 +68,11 @@ void radeon_connector_hotplug(struct drm_connector *connector)
 	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
 		int saved_dpms = connector->dpms;
 
-		if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd) &&
-		    radeon_dp_needs_link_train(radeon_connector))
-			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
-		else
+		/* Only turn off the display it it's physically disconnected */
+		if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd))
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+		else if (radeon_dp_needs_link_train(radeon_connector))
+			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		connector->dpms = saved_dpms;
 	}
 }
@@ -1325,23 +1325,14 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 		/* get the DPCD from the bridge */
 		radeon_dp_getdpcd(radeon_connector);
 
-		if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd))
-			ret = connector_status_connected;
-		else {
-			/* need to setup ddc on the bridge */
-			if (encoder)
-				radeon_atom_ext_encoder_setup_ddc(encoder);
+		if (encoder) {
+			/* setup ddc on the bridge */
+			radeon_atom_ext_encoder_setup_ddc(encoder);
 			if (radeon_ddc_probe(radeon_connector,
-					     radeon_connector->requires_extended_probe))
+					     radeon_connector->requires_extended_probe)) /* try DDC */
 				ret = connector_status_connected;
-		}
-
-		if ((ret == connector_status_disconnected) &&
-		    radeon_connector->dac_load_detect) {
-			struct drm_encoder *encoder = radeon_best_single_encoder(connector);
-			struct drm_encoder_helper_funcs *encoder_funcs;
-			if (encoder) {
-				encoder_funcs = encoder->helper_private;
+			else if (radeon_connector->dac_load_detect) { /* try load detection */
+				struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private;
 				ret = encoder_funcs->detect(encoder, connector);
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 3189a7efb2e9..fde25c0d65a0 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -208,23 +208,25 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 	int xorigin = 0, yorigin = 0;
 	int w = radeon_crtc->cursor_width;
 
-	if (x < 0)
-		xorigin = -x + 1;
-	if (y < 0)
-		yorigin = -y + 1;
-	if (xorigin >= CURSOR_WIDTH)
-		xorigin = CURSOR_WIDTH - 1;
-	if (yorigin >= CURSOR_HEIGHT)
-		yorigin = CURSOR_HEIGHT - 1;
-
 	if (ASIC_IS_AVIVO(rdev)) {
-		int i = 0;
-		struct drm_crtc *crtc_p;
-
 		/* avivo cursor are offset into the total surface */
 		x += crtc->x;
 		y += crtc->y;
-		DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
+	}
+	DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
+
+	if (x < 0) {
+		xorigin = min(-x, CURSOR_WIDTH - 1);
+		x = 0;
+	}
+	if (y < 0) {
+		yorigin = min(-y, CURSOR_HEIGHT - 1);
+		y = 0;
+	}
+
+	if (ASIC_IS_AVIVO(rdev)) {
+		int i = 0;
+		struct drm_crtc *crtc_p;
 
 		/* avivo cursor image can't end on 128 pixel boundary or
 		 * go past the end of the frame if both crtcs are enabled
@@ -253,16 +255,12 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 
 	radeon_lock_cursor(crtc, true);
 	if (ASIC_IS_DCE4(rdev)) {
-		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset,
-		       ((xorigin ? 0 : x) << 16) |
-		       (yorigin ? 0 : y));
+		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset, (x << 16) | y);
 		WREG32(EVERGREEN_CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
 		WREG32(EVERGREEN_CUR_SIZE + radeon_crtc->crtc_offset,
 		       ((w - 1) << 16) | (radeon_crtc->cursor_height - 1));
 	} else if (ASIC_IS_AVIVO(rdev)) {
-		WREG32(AVIVO_D1CUR_POSITION + radeon_crtc->crtc_offset,
-			     ((xorigin ? 0 : x) << 16) |
-			     (yorigin ? 0 : y));
+		WREG32(AVIVO_D1CUR_POSITION + radeon_crtc->crtc_offset, (x << 16) | y);
 		WREG32(AVIVO_D1CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
 		WREG32(AVIVO_D1CUR_SIZE + radeon_crtc->crtc_offset,
 		       ((w - 1) << 16) | (radeon_crtc->cursor_height - 1));
@@ -276,8 +274,8 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 			| yorigin));
 		WREG32(RADEON_CUR_HORZ_VERT_POSN + radeon_crtc->crtc_offset,
 		       (RADEON_CUR_LOCK
-			| ((xorigin ? 0 : x) << 16)
-			| (yorigin ? 0 : y)));
+			| (x << 16)
+			| y));
 		/* offset is from DISP(2)_BASE_ADDRESS */
 		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, (radeon_crtc->legacy_cursor_offset +
 								      (yorigin * 256)));
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 6cc17fb96a57..6adb3e58affd 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -473,8 +473,8 @@ pflip_cleanup:
 	spin_lock_irqsave(&dev->event_lock, flags);
 	radeon_crtc->unpin_work = NULL;
 unlock_free:
-	drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
+	drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
 	radeon_fence_unref(&work->fence);
 	kfree(work);
 
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 319d85d7e759..8a171b21b453 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -1507,7 +1507,14 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
 		switch (mode) {
 		case DRM_MODE_DPMS_ON:
 			args.ucAction = ATOM_ENABLE;
-			atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+			/* workaround for DVOOutputControl on some RS690 systems */
+			if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_DDI) {
+				u32 reg = RREG32(RADEON_BIOS_3_SCRATCH);
+				WREG32(RADEON_BIOS_3_SCRATCH, reg & ~ATOM_S3_DFP2I_ACTIVE);
+				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+				WREG32(RADEON_BIOS_3_SCRATCH, reg);
+			} else
+				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 			if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
 				args.ucAction = ATOM_LCD_BLON;
 				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
@@ -1748,9 +1755,12 @@ static int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder)
 	/* DCE4/5 */
 	if (ASIC_IS_DCE4(rdev)) {
 		dig = radeon_encoder->enc_priv;
-		if (ASIC_IS_DCE41(rdev))
-			return radeon_crtc->crtc_id;
-		else {
+		if (ASIC_IS_DCE41(rdev)) {
+			if (dig->linkb)
+				return 1;
+			else
+				return 0;
+		} else {
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
 				if (dig->linkb)
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 9b86fb0e4122..0b5468bfaf54 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -277,7 +277,12 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 		DRM_ERROR("Trying to move memory with CP turned off.\n");
 		return -EINVAL;
 	}
-	r = radeon_copy(rdev, old_start, new_start, new_mem->num_pages, fence);
+
+	BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);
+
+	r = radeon_copy(rdev, old_start, new_start,
+			new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE), /* GPU pages */
+			fence);
 	/* FIXME: handle copy error */
 	r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL,
 				      evict, no_wait_reserve, no_wait_gpu, new_mem);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 298feaec6d56..87cc1feee3ac 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -539,55 +539,6 @@ static u32 r700_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	return backend_map;
 }
 
-static void rv770_program_channel_remap(struct radeon_device *rdev)
-{
-	u32 tcp_chan_steer, mc_shared_chremap, tmp;
-	bool force_no_swizzle;
-
-	switch (rdev->family) {
-	case CHIP_RV770:
-	case CHIP_RV730:
-		force_no_swizzle = false;
-		break;
-	case CHIP_RV710:
-	case CHIP_RV740:
-	default:
-		force_no_swizzle = true;
-		break;
-	}
-
-	tmp = RREG32(MC_SHARED_CHMAP);
-	switch ((tmp & NOOFCHAN_MASK) >> NOOFCHAN_SHIFT) {
-	case 0:
-	case 1:
-	default:
-		/* default mapping */
-		mc_shared_chremap = 0x00fac688;
-		break;
-	case 2:
-	case 3:
-		if (force_no_swizzle)
-			mc_shared_chremap = 0x00fac688;
-		else
-			mc_shared_chremap = 0x00bbc298;
-		break;
-	}
-
-	if (rdev->family == CHIP_RV740)
-		tcp_chan_steer = 0x00ef2a60;
-	else
-		tcp_chan_steer = 0x00fac688;
-
-	/* RV770 CE has special chremap setup */
-	if (rdev->pdev->device == 0x944e) {
-		tcp_chan_steer = 0x00b08b08;
-		mc_shared_chremap = 0x00b08b08;
-	}
-
-	WREG32(TCP_CHAN_STEER, tcp_chan_steer);
-	WREG32(MC_SHARED_CHREMAP, mc_shared_chremap);
-}
-
 static void rv770_gpu_init(struct radeon_device *rdev)
 {
 	int i, j, num_qd_pipes;
@@ -788,8 +739,6 @@ static void rv770_gpu_init(struct radeon_device *rdev)
 	WREG32(DCP_TILING_CONFIG, (gb_tiling_config & 0xffff));
 	WREG32(HDP_TILING_CONFIG, (gb_tiling_config & 0xffff));
 
-	rv770_program_channel_remap(rdev);
-
 	WREG32(CC_RB_BACKEND_DISABLE,      cc_rb_backend_disable);
 	WREG32(CC_GC_SHADER_PIPE_CONFIG,   cc_gc_shader_pipe_config);
 	WREG32(GC_USER_SHADER_PIPE_CONFIG, cc_gc_shader_pipe_config);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 6e96c85b70da..50fc8e4c9a31 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -394,7 +394,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	if (!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) {
 		if (bo->ttm == NULL) {
-			ret = ttm_bo_add_ttm(bo, false);
+			bool zero = !(old_man->flags & TTM_MEMTYPE_FLAG_FIXED);
+			ret = ttm_bo_add_ttm(bo, zero);
 			if (ret)
 				goto out_err;
 		}