Linux-libre 4.4-gnupck-4.4-gnu

36 files changed, 454 insertions, 359 deletions

diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 9cd49c584..bd73b4069 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -179,6 +179,7 @@ radeon_dp_aux_transfer_atom(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_WRITE:
 	case DP_AUX_I2C_WRITE:
+	case DP_AUX_I2C_WRITE_STATUS_UPDATE:
 		/* The atom implementation only supports writes with a max payload of
 		 * 12 bytes since it uses 4 bits for the total count (header + payload)
 		 * in the parameter space.  The atom interface supports 16 byte
diff --git a/drivers/gpu/drm/radeon/cayman_blit_shaders.c b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
index 98d009e15..9fec4d09f 100644
--- a/drivers/gpu/drm/radeon/cayman_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
@@ -32,7 +32,7 @@
  * evergreen cards need to use the 3D engine to blit data which requires
  * quite a bit of hw state setup.  Rather than pull the whole 3D driver
  * (which normally generates the 3D state) into the DRM, we opt to use
- * statically generated state tables.  The regsiter state and shaders
+ * statically generated state tables.  The register state and shaders
  * were hand generated to support blitting functionality.  See the 3D
  * driver or documentation for descriptions of the registers and
  * shader instructions.
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index e4959ba1d..62972ef4a 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -4094,11 +4094,7 @@ void cik_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	control |= ib->length_dw | (vm_id << 24);
 
 	radeon_ring_write(ring, header);
-	radeon_ring_write(ring,
-#ifdef __BIG_ENDIAN
-			  (2 << 0) |
-#endif
-			  (ib->gpu_addr & 0xFFFFFFFC));
+	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFFC));
 	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
 	radeon_ring_write(ring, control);
 }
@@ -8393,7 +8389,7 @@ restart_ih:
 	if (queue_dp)
 		schedule_work(&rdev->dp_work);
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_reset) {
 		rdev->needs_reset = true;
 		wake_up_all(&rdev->fence_queue);
@@ -9551,6 +9547,9 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
 		    (rdev->disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+
+		/* Save number of lines the linebuffer leads before the scanout */
+		radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 0acde1949..2ad462896 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1404,44 +1404,20 @@ void dce4_wait_for_vblank(struct radeon_device *rdev, int crtc)
  * @crtc_id: crtc to cleanup pageflip on
  * @crtc_base: new address of the crtc (GPU MC address)
  *
- * Does the actual pageflip (evergreen+).
- * During vblank we take the crtc lock and wait for the update_pending
- * bit to go high, when it does, we release the lock, and allow the
- * double buffered update to take place.
- * Returns the current update pending status.
+ * Triggers the actual pageflip by updating the primary
+ * surface base address (evergreen+).
  */
 void evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
-	u32 tmp = RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset);
-	int i;
-
-	/* Lock the graphics update lock */
-	tmp |= EVERGREEN_GRPH_UPDATE_LOCK;
-	WREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
 
 	/* update the scanout addresses */
-	WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
-	       upper_32_bits(crtc_base));
-	WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
-	       (u32)crtc_base);
-
 	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
 	WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
 	       (u32)crtc_base);
-
-	/* Wait for update_pending to go high. */
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		if (RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING)
-			break;
-		udelay(1);
-	}
-	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
-
-	/* Unlock the lock, so double-buffering can take place inside vblank */
-	tmp &= ~EVERGREEN_GRPH_UPDATE_LOCK;
-	WREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
+	/* post the write */
+	RREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS + radeon_crtc->crtc_offset);
 }
 
 /**
@@ -2396,6 +2372,9 @@ static void evergreen_program_watermarks(struct radeon_device *rdev,
 		c.full = dfixed_div(c, a);
 		priority_b_mark = dfixed_trunc(c);
 		priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+		/* Save number of lines the linebuffer leads before the scanout */
+		radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -5368,7 +5347,7 @@ restart_ih:
 	if (queue_dp)
 		schedule_work(&rdev->dp_work);
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_hdmi)
 		schedule_work(&rdev->audio_work);
 	if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_shaders.c b/drivers/gpu/drm/radeon/evergreen_blit_shaders.c
index d43383470..1a96ddb3e 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_shaders.c
@@ -32,7 +32,7 @@
  * evergreen cards need to use the 3D engine to blit data which requires
  * quite a bit of hw state setup.  Rather than pull the whole 3D driver
  * (which normally generates the 3D state) into the DRM, we opt to use
- * statically generated state tables.  The regsiter state and shaders
+ * statically generated state tables.  The register state and shaders
  * were hand generated to support blitting functionality.  See the 3D
  * driver or documentation for descriptions of the registers and
  * shader instructions.
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index c9e0fbbf7..46f87d4aa 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -34,6 +34,8 @@
 #define MAX(a,b)                   (((a)>(b))?(a):(b))
 #define MIN(a,b)                   (((a)<(b))?(a):(b))
 
+#define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm)
+
 int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
 			   struct radeon_bo_list **cs_reloc);
 struct evergreen_cs_track {
@@ -84,6 +86,7 @@ struct evergreen_cs_track {
 	u32			htile_surface;
 	struct radeon_bo	*htile_bo;
 	unsigned long		indirect_draw_buffer_size;
+	const unsigned		*reg_safe_bm;
 };
 
 static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
@@ -444,7 +447,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
 		 * command stream.
 		 */
 		if (!surf.mode) {
-			volatile u32 *ib = p->ib.ptr;
+			uint32_t *ib = p->ib.ptr;
 			unsigned long tmp, nby, bsize, size, min = 0;
 
 			/* find the height the ddx wants */
@@ -1083,41 +1086,18 @@ static int evergreen_cs_parse_packet0(struct radeon_cs_parser *p,
 }
 
 /**
- * evergreen_cs_check_reg() - check if register is authorized or not
+ * evergreen_cs_handle_reg() - process registers that need special handling.
  * @parser: parser structure holding parsing context
  * @reg: register we are testing
  * @idx: index into the cs buffer
- *
- * This function will test against evergreen_reg_safe_bm and return 0
- * if register is safe. If register is not flag as safe this function
- * will test it against a list of register needind special handling.
  */
-static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
+static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 {
 	struct evergreen_cs_track *track = (struct evergreen_cs_track *)p->track;
 	struct radeon_bo_list *reloc;
-	u32 last_reg;
-	u32 m, i, tmp, *ib;
+	u32 tmp, *ib;
 	int r;
 
-	if (p->rdev->family >= CHIP_CAYMAN)
-		last_reg = ARRAY_SIZE(cayman_reg_safe_bm);
-	else
-		last_reg = ARRAY_SIZE(evergreen_reg_safe_bm);
-
-	i = (reg >> 7);
-	if (i >= last_reg) {
-		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
-		return -EINVAL;
-	}
-	m = 1 << ((reg >> 2) & 31);
-	if (p->rdev->family >= CHIP_CAYMAN) {
-		if (!(cayman_reg_safe_bm[i] & m))
-			return 0;
-	} else {
-		if (!(evergreen_reg_safe_bm[i] & m))
-			return 0;
-	}
 	ib = p->ib.ptr;
 	switch (reg) {
 	/* force following reg to 0 in an attempt to disable out buffer
@@ -1764,29 +1744,27 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	return 0;
 }
 
-static bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
+/**
+ * evergreen_is_safe_reg() - check if register is authorized or not
+ * @parser: parser structure holding parsing context
+ * @reg: register we are testing
+ *
+ * This function will test against reg_safe_bm and return true
+ * if register is safe or false otherwise.
+ */
+static inline bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg)
 {
-	u32 last_reg, m, i;
-
-	if (p->rdev->family >= CHIP_CAYMAN)
-		last_reg = ARRAY_SIZE(cayman_reg_safe_bm);
-	else
-		last_reg = ARRAY_SIZE(evergreen_reg_safe_bm);
+	struct evergreen_cs_track *track = p->track;
+	u32 m, i;
 
 	i = (reg >> 7);
-	if (i >= last_reg) {
-		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+	if (unlikely(i >= REG_SAFE_BM_SIZE)) {
 		return false;
 	}
 	m = 1 << ((reg >> 2) & 31);
-	if (p->rdev->family >= CHIP_CAYMAN) {
-		if (!(cayman_reg_safe_bm[i] & m))
-			return true;
-	} else {
-		if (!(evergreen_reg_safe_bm[i] & m))
-			return true;
-	}
-	dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+	if (!(track->reg_safe_bm[i] & m))
+		return true;
+
 	return false;
 }
 
@@ -1795,7 +1773,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 {
 	struct radeon_bo_list *reloc;
 	struct evergreen_cs_track *track;
-	volatile u32 *ib;
+	uint32_t *ib;
 	unsigned idx;
 	unsigned i;
 	unsigned start_reg, end_reg, reg;
@@ -2321,9 +2299,10 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
 			return -EINVAL;
 		}
-		for (i = 0; i < pkt->count; i++) {
-			reg = start_reg + (4 * i);
-			r = evergreen_cs_check_reg(p, reg, idx+1+i);
+		for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) {
+			if (evergreen_is_safe_reg(p, reg))
+				continue;
+			r = evergreen_cs_handle_reg(p, reg, idx);
 			if (r)
 				return r;
 		}
@@ -2337,9 +2316,10 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n");
 			return -EINVAL;
 		}
-		for (i = 0; i < pkt->count; i++) {
-			reg = start_reg + (4 * i);
-			r = evergreen_cs_check_reg(p, reg, idx+1+i);
+		for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) {
+			if (evergreen_is_safe_reg(p, reg))
+				continue;
+			r = evergreen_cs_handle_reg(p, reg, idx);
 			if (r)
 				return r;
 		}
@@ -2594,8 +2574,11 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		} else {
 			/* SRC is a reg. */
 			reg = radeon_get_ib_value(p, idx+1) << 2;
-			if (!evergreen_is_safe_reg(p, reg, idx+1))
+			if (!evergreen_is_safe_reg(p, reg)) {
+				dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
+					 reg, idx + 1);
 				return -EINVAL;
+			}
 		}
 		if (idx_value & 0x2) {
 			u64 offset;
@@ -2618,8 +2601,11 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		} else {
 			/* DST is a reg. */
 			reg = radeon_get_ib_value(p, idx+3) << 2;
-			if (!evergreen_is_safe_reg(p, reg, idx+3))
+			if (!evergreen_is_safe_reg(p, reg)) {
+				dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
+					 reg, idx + 3);
 				return -EINVAL;
+			}
 		}
 		break;
 	case PACKET3_NOP:
@@ -2644,11 +2630,15 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 		if (track == NULL)
 			return -ENOMEM;
 		evergreen_cs_track_init(track);
-		if (p->rdev->family >= CHIP_CAYMAN)
+		if (p->rdev->family >= CHIP_CAYMAN) {
 			tmp = p->rdev->config.cayman.tile_config;
-		else
+			track->reg_safe_bm = cayman_reg_safe_bm;
+		} else {
 			tmp = p->rdev->config.evergreen.tile_config;
-
+			track->reg_safe_bm = evergreen_reg_safe_bm;
+		}
+		BUILD_BUG_ON(ARRAY_SIZE(cayman_reg_safe_bm) != REG_SAFE_BM_SIZE);
+		BUILD_BUG_ON(ARRAY_SIZE(evergreen_reg_safe_bm) != REG_SAFE_BM_SIZE);
 		switch (tmp & 0xf) {
 		case 0:
 			track->npipes = 1;
@@ -2757,7 +2747,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 	struct radeon_cs_chunk *ib_chunk = p->chunk_ib;
 	struct radeon_bo_list *src_reloc, *dst_reloc, *dst2_reloc;
 	u32 header, cmd, count, sub_cmd;
-	volatile u32 *ib = p->ib.ptr;
+	uint32_t *ib = p->ib.ptr;
 	u32 idx;
 	u64 src_offset, dst_offset, dst2_offset;
 	int r;
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index e58106620..ede873a5f 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -800,7 +800,7 @@ int r100_irq_process(struct radeon_device *rdev)
 		status = r100_irq_ack(rdev);
 	}
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (rdev->msi_enabled) {
 		switch (rdev->family) {
 		case CHIP_RS400:
@@ -3211,6 +3211,9 @@ void r100_bandwidth_update(struct radeon_device *rdev)
 	uint32_t pixel_bytes1 = 0;
 	uint32_t pixel_bytes2 = 0;
 
+	/* Guess line buffer size to be 8192 pixels */
+	u32 lb_size = 8192;
+
 	if (!rdev->mode_info.mode_config_initialized)
 		return;
 
@@ -3625,6 +3628,13 @@ void r100_bandwidth_update(struct radeon_device *rdev)
 		DRM_DEBUG_KMS("GRPH2_BUFFER_CNTL from to %x\n",
 			  (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL));
 	}
+
+	/* Save number of lines the linebuffer leads before the scanout */
+	if (mode1)
+	    rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+	if (mode2)
+	    rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 int r100_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 98f923b41..2062228b4 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -4228,7 +4228,7 @@ restart_ih:
 		WREG32(IH_RB_RPTR, rptr);
 	}
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_hdmi)
 		schedule_work(&rdev->audio_work);
 	if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/r600_blit_shaders.c b/drivers/gpu/drm/radeon/r600_blit_shaders.c
index 34c8b2340..443cbe59b 100644
--- a/drivers/gpu/drm/radeon/r600_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/r600_blit_shaders.c
@@ -32,7 +32,7 @@
  * R6xx+ cards need to use the 3D engine to blit data which requires
  * quite a bit of hw state setup.  Rather than pull the whole 3D driver
  * (which normally generates the 3D state) into the DRM, we opt to use
- * statically generated state tables.  The regsiter state and shaders
+ * statically generated state tables.  The register state and shaders
  * were hand generated to support blitting functionality.  See the 3D
  * driver or documentation for descriptions of the registers and
  * shader instructions.
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index a692672b9..cdd92eb04 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -1818,7 +1818,7 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
 	SET_RING_HEAD(dev_priv, 0);
 	dev_priv->ring.tail = 0;
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		rptr_addr = dev_priv->ring_rptr->offset
 			- dev->agp->base +
@@ -1844,7 +1844,7 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
 		     dev_priv->ring.size_l2qw);
 #endif
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		/* XXX */
 		radeon_write_agp_base(dev_priv, dev->agp->base);
@@ -1927,7 +1927,7 @@ int r600_do_cleanup_cp(struct drm_device *dev)
 	if (dev->irq_enabled)
 		drm_irq_uninstall(dev);
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		if (dev_priv->cp_ring != NULL) {
 			drm_legacy_ioremapfree(dev_priv->cp_ring, dev);
@@ -2070,7 +2070,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		}
 	}
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	/* XXX */
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		drm_legacy_ioremap_wc(dev_priv->cp_ring, dev);
@@ -2129,7 +2129,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		 * location in the card and on the bus, though we have to
 		 * align it down.
 		 */
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 		/* XXX */
 		if (dev_priv->flags & RADEON_IS_AGP) {
 			base = dev->agp->base;
@@ -2156,7 +2156,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 				 base, dev_priv->gart_vm_start);
 	}
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	/* XXX */
 	if (dev_priv->flags & RADEON_IS_AGP)
 		dev_priv->gart_buffers_offset = (dev->agp_buffer_map->offset
@@ -2193,7 +2193,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 	dev_priv->ring.high_mark = RADEON_RING_HIGH_MARK;
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		/* XXX turn off pcie gart */
 	} else
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b6cbd8165..87db64983 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2414,7 +2414,7 @@ struct radeon_device {
 	struct r600_ih ih; /* r6/700 interrupt ring */
 	struct radeon_rlc rlc;
 	struct radeon_mec mec;
-	struct work_struct hotplug_work;
+	struct delayed_work hotplug_work;
 	struct work_struct dp_work;
 	struct work_struct audio_work;
 	int num_crtc; /* number of crtcs */
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 77e9d07c5..59acd0e5c 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -25,7 +25,6 @@
 #include <linux/acpi.h>
 #include <linux/slab.h>
 #include <linux/power_supply.h>
-#include <linux/vga_switcheroo.h>
 #include <acpi/video.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index a9297b2c3..c77d349c5 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -28,7 +28,7 @@
 #include "radeon.h"
 #include <drm/radeon_drm.h>
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 
 struct radeon_agpmode_quirk {
 	u32 hostbridge_vendor;
@@ -54,6 +54,9 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = {
 	/* Intel 82855PM host bridge / Mobility 9600 M10 RV350 Needs AGPMode 1 (lp #195051) */
 	{ PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4e50,
 		PCI_VENDOR_ID_IBM, 0x0550, 1},
+	/* Intel 82855PM host bridge / RV250/M9 GL [Mobility FireGL 9000/Radeon 9000] needs AGPMode 1 (Thinkpad T40p) */
+	{ PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c66,
+		PCI_VENDOR_ID_IBM, 0x054d, 1},
 	/* Intel 82855PM host bridge / Mobility M7 needs AGPMode 1 */
 	{ PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c57,
 		PCI_VENDOR_ID_IBM, 0x0530, 1},
@@ -123,7 +126,7 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = {
 
 int radeon_agp_init(struct radeon_device *rdev)
 {
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	struct radeon_agpmode_quirk *p = radeon_agpmode_quirk_list;
 	struct drm_agp_mode mode;
 	struct drm_agp_info info;
@@ -257,7 +260,7 @@ int radeon_agp_init(struct radeon_device *rdev)
 
 void radeon_agp_resume(struct radeon_device *rdev)
 {
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	int r;
 	if (rdev->flags & RADEON_IS_AGP) {
 		r = radeon_agp_init(rdev);
@@ -269,7 +272,7 @@ void radeon_agp_resume(struct radeon_device *rdev)
 
 void radeon_agp_fini(struct radeon_device *rdev)
 {
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (rdev->ddev->agp && rdev->ddev->agp->acquired) {
 		drm_agp_release(rdev->ddev);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index f2421bc3e..1d4d4520a 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -31,7 +31,6 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/radeon_drm.h>
 #include <linux/vgaarb.h>
-#include <linux/vga_switcheroo.h>
 #include "radeon_reg.h"
 #include "radeon.h"
 #include "radeon_asic.h"
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 8bc7d0bbd..c4b4f298a 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -499,7 +499,7 @@ static int radeon_atpx_get_client_id(struct pci_dev *pdev)
 		return VGA_SWITCHEROO_DIS;
 }
 
-static struct vga_switcheroo_handler radeon_atpx_handler = {
+static const struct vga_switcheroo_handler radeon_atpx_handler = {
 	.switchto = radeon_atpx_switchto,
 	.power_state = radeon_atpx_power_state,
 	.init = radeon_atpx_init,
@@ -535,7 +535,7 @@ static bool radeon_atpx_detect(void)
 
 	if (has_atpx && vga_count == 2) {
 		acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
-		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
+		printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		radeon_atpx_priv.atpx_detected = true;
 		return true;
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index d27e4ccb8..21b673242 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -30,7 +30,6 @@
 #include "radeon.h"
 #include "atom.h"
 
-#include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 5a2cafb4f..340f3f549 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1234,13 +1234,32 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	if (r < 0)
 		return connector_status_disconnected;
 
+	if (radeon_connector->detected_hpd_without_ddc) {
+		force = true;
+		radeon_connector->detected_hpd_without_ddc = false;
+	}
+
 	if (!force && radeon_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
 		goto exit;
 	}
 
-	if (radeon_connector->ddc_bus)
+	if (radeon_connector->ddc_bus) {
 		dret = radeon_ddc_probe(radeon_connector, false);
+
+		/* Sometimes the pins required for the DDC probe on DVI
+		 * connectors don't make contact at the same time that the ones
+		 * for HPD do. If the DDC probe fails even though we had an HPD
+		 * signal, try again later */
+		if (!dret && !force &&
+		    connector->status != connector_status_connected) {
+			DRM_DEBUG_KMS("hpd detected without ddc, retrying in 1 second\n");
+			radeon_connector->detected_hpd_without_ddc = true;
+			schedule_delayed_work(&rdev->hotplug_work,
+					      msecs_to_jiffies(1000));
+			goto exit;
+		}
+	}
 	if (dret) {
 		radeon_connector->detected_by_load = false;
 		radeon_connector_free_edid(connector);
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index c1203e05b..1a59e294b 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -756,7 +756,7 @@ static void radeon_cp_init_ring_buffer(struct drm_device * dev,
 			     ((dev_priv->gart_vm_start - 1) & 0xffff0000)
 			     | (dev_priv->fb_location >> 16));
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		radeon_write_agp_base(dev_priv, dev->agp->base);
 
@@ -785,7 +785,7 @@ static void radeon_cp_init_ring_buffer(struct drm_device * dev,
 	SET_RING_HEAD(dev_priv, cur_read_ptr);
 	dev_priv->ring.tail = cur_read_ptr;
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		RADEON_WRITE(RADEON_CP_RB_RPTR_ADDR,
 			     dev_priv->ring_rptr->offset
@@ -1329,7 +1329,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		}
 	}
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		drm_legacy_ioremap_wc(dev_priv->cp_ring, dev);
 		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
@@ -1388,7 +1388,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		 * location in the card and on the bus, though we have to
 		 * align it down.
 		 */
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 		if (dev_priv->flags & RADEON_IS_AGP) {
 			base = dev->agp->base;
 			/* Check if valid */
@@ -1418,7 +1418,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 			RADEON_READ(RADEON_CONFIG_APER_SIZE);
 	}
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP)
 		dev_priv->gart_buffers_offset = (dev->agp_buffer_map->offset
 						 - dev->agp->base
@@ -1449,7 +1449,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 	dev_priv->ring.high_mark = RADEON_RING_HIGH_MARK;
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		/* Turn off PCI GART */
 		radeon_set_pcigart(dev_priv, 0);
@@ -1560,7 +1560,7 @@ static int radeon_do_cleanup_cp(struct drm_device * dev)
 	if (dev->irq_enabled)
 		drm_irq_uninstall(dev);
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		if (dev_priv->cp_ring != NULL) {
 			drm_legacy_ioremapfree(dev_priv->cp_ring, dev);
@@ -1619,7 +1619,7 @@ static int radeon_do_resume_cp(struct drm_device *dev, struct drm_file *file_pri
 
 	DRM_DEBUG("Starting radeon_do_resume_cp()\n");
 
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		/* Turn off PCI GART */
 		radeon_set_pcigart(dev_priv, 0);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index f3f562f6d..c566993a2 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1197,7 +1197,7 @@ static void radeon_check_arguments(struct radeon_device *rdev)
  * radeon_switcheroo_set_state - set switcheroo state
  *
  * @pdev: pci dev pointer
- * @state: vga switcheroo state
+ * @state: vga_switcheroo state
  *
  * Callback for the switcheroo driver.  Suspends or resumes the
  * the asics before or after it is powered up using ACPI methods.
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 6743174ac..1eca0acac 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -322,8 +322,11 @@ void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id)
 	 * to complete in this vblank?
 	 */
 	if (update_pending &&
-	    (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id, 0,
-							       &vpos, &hpos, NULL, NULL)) &&
+	    (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev,
+							       crtc_id,
+							       USE_REAL_VBLANKSTART,
+							       &vpos, &hpos, NULL, NULL,
+							       &rdev->mode_info.crtcs[crtc_id]->base.hwmode)) &&
 	    ((vpos >= (99 * rdev->mode_info.crtcs[crtc_id]->base.hwmode.crtc_vdisplay)/100) ||
 	     (vpos < 0 && !ASIC_IS_AVIVO(rdev)))) {
 		/* crtc didn't flip in this target vblank interval,
@@ -400,6 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	struct drm_crtc *crtc = &radeon_crtc->base;
 	unsigned long flags;
 	int r;
+	int vpos, hpos, stat, min_udelay;
+	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         down_read(&rdev->exclusive_lock);
 	if (work->fence) {
@@ -436,6 +441,41 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	/* set the proper interrupt */
 	radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id);
 
+	/* If this happens to execute within the "virtually extended" vblank
+	 * interval before the start of the real vblank interval then it needs
+	 * to delay programming the mmio flip until the real vblank is entered.
+	 * This prevents completing a flip too early due to the way we fudge
+	 * our vblank counter and vblank timestamps in order to work around the
+	 * problem that the hw fires vblank interrupts before actual start of
+	 * vblank (when line buffer refilling is done for a frame). It
+	 * complements the fudging logic in radeon_get_crtc_scanoutpos() for
+	 * timestamping and radeon_get_vblank_counter_kms() for vblank counts.
+	 *
+	 * In practice this won't execute very often unless on very fast
+	 * machines because the time window for this to happen is very small.
+	 */
+	for (;;) {
+		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+		 * start in hpos, and to the "fudged earlier" vblank start in
+		 * vpos.
+		 */
+		stat = radeon_get_crtc_scanoutpos(rdev->ddev, work->crtc_id,
+						  GET_DISTANCE_TO_VBLANKSTART,
+						  &vpos, &hpos, NULL, NULL,
+						  &crtc->hwmode);
+
+		if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+		    !(vpos >= 0 && hpos <= 0))
+			break;
+
+		/* Sleep at least until estimated real start of hw vblank */
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		usleep_range(min_udelay, 2 * min_udelay);
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+	};
+
 	/* do the flip (mmio) */
 	radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
 
@@ -1767,6 +1807,15 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param crtc Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -1788,8 +1837,10 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * unknown small number of scanlines wrt. real scanout position.
  *
  */
-int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int flags,
-			       int *vpos, int *hpos, ktime_t *stime, ktime_t *etime)
+int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
+			       unsigned int flags, int *vpos, int *hpos,
+			       ktime_t *stime, ktime_t *etime,
+			       const struct drm_display_mode *mode)
 {
 	u32 stat_crtc = 0, vbl = 0, position = 0;
 	int vbl_start, vbl_end, vtotal, ret = 0;
@@ -1804,42 +1855,42 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 		*stime = ktime_get();
 
 	if (ASIC_IS_DCE4(rdev)) {
-		if (crtc == 0) {
+		if (pipe == 0) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
 				     EVERGREEN_CRTC0_REGISTER_OFFSET);
 			position = RREG32(EVERGREEN_CRTC_STATUS_POSITION +
 					  EVERGREEN_CRTC0_REGISTER_OFFSET);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 1) {
+		if (pipe == 1) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
 				     EVERGREEN_CRTC1_REGISTER_OFFSET);
 			position = RREG32(EVERGREEN_CRTC_STATUS_POSITION +
 					  EVERGREEN_CRTC1_REGISTER_OFFSET);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 2) {
+		if (pipe == 2) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
 				     EVERGREEN_CRTC2_REGISTER_OFFSET);
 			position = RREG32(EVERGREEN_CRTC_STATUS_POSITION +
 					  EVERGREEN_CRTC2_REGISTER_OFFSET);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 3) {
+		if (pipe == 3) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
 				     EVERGREEN_CRTC3_REGISTER_OFFSET);
 			position = RREG32(EVERGREEN_CRTC_STATUS_POSITION +
 					  EVERGREEN_CRTC3_REGISTER_OFFSET);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 4) {
+		if (pipe == 4) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
 				     EVERGREEN_CRTC4_REGISTER_OFFSET);
 			position = RREG32(EVERGREEN_CRTC_STATUS_POSITION +
 					  EVERGREEN_CRTC4_REGISTER_OFFSET);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 5) {
+		if (pipe == 5) {
 			vbl = RREG32(EVERGREEN_CRTC_V_BLANK_START_END +
 				     EVERGREEN_CRTC5_REGISTER_OFFSET);
 			position = RREG32(EVERGREEN_CRTC_STATUS_POSITION +
@@ -1847,19 +1898,19 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
 	} else if (ASIC_IS_AVIVO(rdev)) {
-		if (crtc == 0) {
+		if (pipe == 0) {
 			vbl = RREG32(AVIVO_D1CRTC_V_BLANK_START_END);
 			position = RREG32(AVIVO_D1CRTC_STATUS_POSITION);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 1) {
+		if (pipe == 1) {
 			vbl = RREG32(AVIVO_D2CRTC_V_BLANK_START_END);
 			position = RREG32(AVIVO_D2CRTC_STATUS_POSITION);
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
 	} else {
 		/* Pre-AVIVO: Different encoding of scanout pos and vblank interval. */
-		if (crtc == 0) {
+		if (pipe == 0) {
 			/* Assume vbl_end == 0, get vbl_start from
 			 * upper 16 bits.
 			 */
@@ -1873,7 +1924,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 
 			ret |= DRM_SCANOUTPOS_VALID;
 		}
-		if (crtc == 1) {
+		if (pipe == 1) {
 			vbl = (RREG32(RADEON_CRTC2_V_TOTAL_DISP) &
 				RADEON_CRTC_V_DISP) >> RADEON_CRTC_V_DISP_SHIFT;
 			position = (RREG32(RADEON_CRTC2_VLINE_CRNT_VLINE) >> 16) & RADEON_CRTC_V_TOTAL;
@@ -1904,14 +1955,44 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 	}
 	else {
 		/* No: Fake something reasonable which gives at least ok results. */
-		vbl_start = rdev->mode_info.crtcs[crtc]->base.hwmode.crtc_vdisplay;
+		vbl_start = mode->crtc_vdisplay;
 		vbl_end = 0;
 	}
 
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+	    /* Caller wants distance from real vbl_start in *hpos */
+	    *hpos = *vpos - vbl_start;
+	}
+
+	/* Fudge vblank to start a few scanlines earlier to handle the
+	 * problem that vblank irqs fire a few scanlines before start
+	 * of vblank. Some driver internal callers need the true vblank
+	 * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+	 *
+	 * The cause of the "early" vblank irq is that the irq is triggered
+	 * by the line buffer logic when the line buffer read position enters
+	 * the vblank, whereas our crtc scanout position naturally lags the
+	 * line buffer read position.
+	 */
+	if (!(flags & USE_REAL_VBLANKSTART))
+		vbl_start -= rdev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
 	/* Test scanout position against vblank region. */
 	if ((*vpos < vbl_start) && (*vpos >= vbl_end))
 		in_vbl = false;
 
+	/* In vblank? */
+	if (in_vbl)
+	    ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+		/* Caller wants distance from fudged earlier vbl_start */
+		*vpos -= vbl_start;
+		return ret;
+	}
+
 	/* Check if inside vblank area and apply corrective offsets:
 	 * vpos will then be >=0 in video scanout area, but negative
 	 * within vblank area, counting down the number of lines until
@@ -1920,38 +2001,12 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 
 	/* Inside "upper part" of vblank area? Apply corrective offset if so: */
 	if (in_vbl && (*vpos >= vbl_start)) {
-		vtotal = rdev->mode_info.crtcs[crtc]->base.hwmode.crtc_vtotal;
+		vtotal = mode->crtc_vtotal;
 		*vpos = *vpos - vtotal;
 	}
 
 	/* Correct for shifted end of vbl at vbl_end. */
 	*vpos = *vpos - vbl_end;
 
-	/* In vblank? */
-	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-	/* Is vpos outside nominal vblank area, but less than
-	 * 1/100 of a frame height away from start of vblank?
-	 * If so, assume this isn't a massively delayed vblank
-	 * interrupt, but a vblank interrupt that fired a few
-	 * microseconds before true start of vblank. Compensate
-	 * by adding a full frame duration to the final timestamp.
-	 * Happens, e.g., on ATI R500, R600.
-	 *
-	 * We only do this if DRM_CALLED_FROM_VBLIRQ.
-	 */
-	if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-		vbl_start = rdev->mode_info.crtcs[crtc]->base.hwmode.crtc_vdisplay;
-		vtotal = rdev->mode_info.crtcs[crtc]->base.hwmode.crtc_vtotal;
-
-		if (vbl_start - *vpos < vtotal / 100) {
-			*vpos -= vtotal;
-
-			/* Signal this correction as "applied". */
-			ret |= 0x8;
-		}
-	}
-
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 575144667..5b6a6f5b3 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -105,10 +105,10 @@ void radeon_driver_preclose_kms(struct drm_device *dev,
 				struct drm_file *file_priv);
 int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon);
 int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
-u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc);
-int radeon_enable_vblank_kms(struct drm_device *dev, int crtc);
-void radeon_disable_vblank_kms(struct drm_device *dev, int crtc);
-int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc,
+u32 radeon_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe);
+int radeon_enable_vblank_kms(struct drm_device *dev, unsigned int pipe);
+void radeon_disable_vblank_kms(struct drm_device *dev, unsigned int pipe);
+int radeon_get_vblank_timestamp_kms(struct drm_device *dev, unsigned int pipe,
 				    int *max_error,
 				    struct timeval *vblank_time,
 				    unsigned flags);
@@ -124,10 +124,10 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
 					struct drm_gem_object *gobj,
 					int flags);
-extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
-				      unsigned int flags,
-				      int *vpos, int *hpos, ktime_t *stime,
-				      ktime_t *etime);
+extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int crtc,
+				      unsigned int flags, int *vpos, int *hpos,
+				      ktime_t *stime, ktime_t *etime,
+				      const struct drm_display_mode *mode);
 extern bool radeon_is_px(struct drm_device *dev);
 extern const struct drm_ioctl_desc radeon_ioctls_kms[];
 extern int radeon_max_kms_ioctl;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index 46bd39382..0caafc7a6 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -404,9 +404,9 @@ extern int radeon_irq_emit(struct drm_device *dev, void *data, struct drm_file *
 extern int radeon_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_priv);
 
 extern void radeon_do_release(struct drm_device * dev);
-extern u32 radeon_get_vblank_counter(struct drm_device *dev, int crtc);
-extern int radeon_enable_vblank(struct drm_device *dev, int crtc);
-extern void radeon_disable_vblank(struct drm_device *dev, int crtc);
+extern u32 radeon_get_vblank_counter(struct drm_device *dev, unsigned int pipe);
+extern int radeon_enable_vblank(struct drm_device *dev, unsigned int pipe);
+extern void radeon_disable_vblank(struct drm_device *dev, unsigned int pipe);
 extern irqreturn_t radeon_driver_irq_handler(int irq, void *arg);
 extern void radeon_driver_irq_preinstall(struct drm_device * dev);
 extern int radeon_driver_irq_postinstall(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_irq.c b/drivers/gpu/drm/radeon/radeon_irq.c
index 244b19bab..688afb62f 100644
--- a/drivers/gpu/drm/radeon/radeon_irq.c
+++ b/drivers/gpu/drm/radeon/radeon_irq.c
@@ -62,12 +62,12 @@ static void r500_vbl_irq_set_state(struct drm_device *dev, u32 mask, int state)
 		RADEON_WRITE(R500_DxMODE_INT_MASK, dev_priv->r500_disp_irq_reg);
 }
 
-int radeon_enable_vblank(struct drm_device *dev, int crtc)
+int radeon_enable_vblank(struct drm_device *dev, unsigned int pipe)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
 
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS600) {
-		switch (crtc) {
+		switch (pipe) {
 		case 0:
 			r500_vbl_irq_set_state(dev, R500_D1MODE_INT_MASK, 1);
 			break;
@@ -75,12 +75,12 @@ int radeon_enable_vblank(struct drm_device *dev, int crtc)
 			r500_vbl_irq_set_state(dev, R500_D2MODE_INT_MASK, 1);
 			break;
 		default:
-			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
-				  crtc);
+			DRM_ERROR("tried to enable vblank on non-existent crtc %u\n",
+				  pipe);
 			return -EINVAL;
 		}
 	} else {
-		switch (crtc) {
+		switch (pipe) {
 		case 0:
 			radeon_irq_set_state(dev, RADEON_CRTC_VBLANK_MASK, 1);
 			break;
@@ -88,8 +88,8 @@ int radeon_enable_vblank(struct drm_device *dev, int crtc)
 			radeon_irq_set_state(dev, RADEON_CRTC2_VBLANK_MASK, 1);
 			break;
 		default:
-			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
-				  crtc);
+			DRM_ERROR("tried to enable vblank on non-existent crtc %u\n",
+				  pipe);
 			return -EINVAL;
 		}
 	}
@@ -97,12 +97,12 @@ int radeon_enable_vblank(struct drm_device *dev, int crtc)
 	return 0;
 }
 
-void radeon_disable_vblank(struct drm_device *dev, int crtc)
+void radeon_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
 
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS600) {
-		switch (crtc) {
+		switch (pipe) {
 		case 0:
 			r500_vbl_irq_set_state(dev, R500_D1MODE_INT_MASK, 0);
 			break;
@@ -110,12 +110,12 @@ void radeon_disable_vblank(struct drm_device *dev, int crtc)
 			r500_vbl_irq_set_state(dev, R500_D2MODE_INT_MASK, 0);
 			break;
 		default:
-			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
-				  crtc);
+			DRM_ERROR("tried to enable vblank on non-existent crtc %u\n",
+				  pipe);
 			break;
 		}
 	} else {
-		switch (crtc) {
+		switch (pipe) {
 		case 0:
 			radeon_irq_set_state(dev, RADEON_CRTC_VBLANK_MASK, 0);
 			break;
@@ -123,8 +123,8 @@ void radeon_disable_vblank(struct drm_device *dev, int crtc)
 			radeon_irq_set_state(dev, RADEON_CRTC2_VBLANK_MASK, 0);
 			break;
 		default:
-			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
-				  crtc);
+			DRM_ERROR("tried to enable vblank on non-existent crtc %u\n",
+				  pipe);
 			break;
 		}
 	}
@@ -255,7 +255,7 @@ static int radeon_wait_irq(struct drm_device * dev, int swi_nr)
 	return ret;
 }
 
-u32 radeon_get_vblank_counter(struct drm_device *dev, int crtc)
+u32 radeon_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
 
@@ -264,18 +264,18 @@ u32 radeon_get_vblank_counter(struct drm_device *dev, int crtc)
 		return -EINVAL;
 	}
 
-	if (crtc < 0 || crtc > 1) {
-		DRM_ERROR("Invalid crtc %d\n", crtc);
+	if (pipe > 1) {
+		DRM_ERROR("Invalid crtc %u\n", pipe);
 		return -EINVAL;
 	}
 
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS600) {
-		if (crtc == 0)
+		if (pipe == 0)
 			return RADEON_READ(R500_D1CRTC_FRAME_COUNT);
 		else
 			return RADEON_READ(R500_D2CRTC_FRAME_COUNT);
 	} else {
-		if (crtc == 0)
+		if (pipe == 0)
 			return RADEON_READ(RADEON_CRTC_CRNT_FRAME);
 		else
 			return RADEON_READ(RADEON_CRTC2_CRNT_FRAME);
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 171d3e43c..979f3bf65 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -74,7 +74,7 @@ irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg)
 static void radeon_hotplug_work_func(struct work_struct *work)
 {
 	struct radeon_device *rdev = container_of(work, struct radeon_device,
-						  hotplug_work);
+						  hotplug_work.work);
 	struct drm_device *dev = rdev->ddev;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
@@ -302,7 +302,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 		}
 	}
 
-	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+	INIT_DELAYED_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
 	INIT_WORK(&rdev->dp_work, radeon_dp_work_func);
 	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
 
@@ -310,7 +310,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 	r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq);
 	if (r) {
 		rdev->irq.installed = false;
-		flush_work(&rdev->hotplug_work);
+		flush_delayed_work(&rdev->hotplug_work);
 		return r;
 	}
 
@@ -333,7 +333,7 @@ void radeon_irq_kms_fini(struct radeon_device *rdev)
 		rdev->irq.installed = false;
 		if (rdev->msi_enabled)
 			pci_disable_msi(rdev->pdev);
-		flush_work(&rdev->hotplug_work);
+		flush_delayed_work(&rdev->hotplug_work);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0e932bf93..d290a8a09 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -181,7 +181,9 @@ static void radeon_set_filp_rights(struct drm_device *dev,
 				   struct drm_file *applier,
 				   uint32_t *value)
 {
-	mutex_lock(&dev->struct_mutex);
+	struct radeon_device *rdev = dev->dev_private;
+
+	mutex_lock(&rdev->gem.mutex);
 	if (*value == 1) {
 		/* wants rights */
 		if (!*owner)
@@ -192,7 +194,7 @@ static void radeon_set_filp_rights(struct drm_device *dev,
 			*owner = NULL;
 	}
 	*value = *owner == applier ? 1 : 0;
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&rdev->gem.mutex);
 }
 
 /*
@@ -602,7 +604,7 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
  *
  * @dev: drm dev pointer
  *
- * Switch vga switcheroo state after last close (all asics).
+ * Switch vga_switcheroo state after last close (all asics).
  */
 void radeon_driver_lastclose_kms(struct drm_device *dev)
 {
@@ -727,10 +729,14 @@ void radeon_driver_preclose_kms(struct drm_device *dev,
 				struct drm_file *file_priv)
 {
 	struct radeon_device *rdev = dev->dev_private;
+
+	mutex_lock(&rdev->gem.mutex);
 	if (rdev->hyperz_filp == file_priv)
 		rdev->hyperz_filp = NULL;
 	if (rdev->cmask_filp == file_priv)
 		rdev->cmask_filp = NULL;
+	mutex_unlock(&rdev->gem.mutex);
+
 	radeon_uvd_free_handles(rdev, file_priv);
 	radeon_vce_free_handles(rdev, file_priv);
 }
@@ -749,6 +755,8 @@ void radeon_driver_preclose_kms(struct drm_device *dev,
  */
 u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
 {
+	int vpos, hpos, stat;
+	u32 count;
 	struct radeon_device *rdev = dev->dev_private;
 
 	if (crtc < 0 || crtc >= rdev->num_crtc) {
@@ -756,7 +764,53 @@ u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
 		return -EINVAL;
 	}
 
-	return radeon_get_vblank_counter(rdev, crtc);
+	/* The hw increments its frame counter at start of vsync, not at start
+	 * of vblank, as is required by DRM core vblank counter handling.
+	 * Cook the hw count here to make it appear to the caller as if it
+	 * incremented at start of vblank. We measure distance to start of
+	 * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+	 * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+	 * result by 1 to give the proper appearance to caller.
+	 */
+	if (rdev->mode_info.crtcs[crtc]) {
+		/* Repeat readout if needed to provide stable result if
+		 * we cross start of vsync during the queries.
+		 */
+		do {
+			count = radeon_get_vblank_counter(rdev, crtc);
+			/* Ask radeon_get_crtc_scanoutpos to return vpos as
+			 * distance to start of vblank, instead of regular
+			 * vertical scanout pos.
+			 */
+			stat = radeon_get_crtc_scanoutpos(
+				dev, crtc, GET_DISTANCE_TO_VBLANKSTART,
+				&vpos, &hpos, NULL, NULL,
+				&rdev->mode_info.crtcs[crtc]->base.hwmode);
+		} while (count != radeon_get_vblank_counter(rdev, crtc));
+
+		if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+			DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+		}
+		else {
+			DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+				      crtc, vpos);
+
+			/* Bump counter if we are at >= leading edge of vblank,
+			 * but before vsync where vpos would turn negative and
+			 * the hw counter really increments.
+			 */
+			if (vpos >= 0)
+				count++;
+		}
+	}
+	else {
+	    /* Fallback to use value as is. */
+	    count = radeon_get_vblank_counter(rdev, crtc);
+	    DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+	}
+
+	return count;
 }
 
 /**
@@ -844,92 +898,52 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc,
 	/* Helper routine in DRM core does all the work: */
 	return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error,
 						     vblank_time, flags,
-						     drmcrtc, &drmcrtc->hwmode);
-}
-
-#define KMS_INVALID_IOCTL(name)						\
-static int name(struct drm_device *dev, void *data, struct drm_file	\
-		*file_priv)						\
-{									\
-	DRM_ERROR("invalid ioctl with kms %s\n", __func__);		\
-	return -EINVAL;							\
+						     &drmcrtc->hwmode);
 }
 
-/*
- * All these ioctls are invalid in kms world.
- */
-KMS_INVALID_IOCTL(radeon_cp_init_kms)
-KMS_INVALID_IOCTL(radeon_cp_start_kms)
-KMS_INVALID_IOCTL(radeon_cp_stop_kms)
-KMS_INVALID_IOCTL(radeon_cp_reset_kms)
-KMS_INVALID_IOCTL(radeon_cp_idle_kms)
-KMS_INVALID_IOCTL(radeon_cp_resume_kms)
-KMS_INVALID_IOCTL(radeon_engine_reset_kms)
-KMS_INVALID_IOCTL(radeon_fullscreen_kms)
-KMS_INVALID_IOCTL(radeon_cp_swap_kms)
-KMS_INVALID_IOCTL(radeon_cp_clear_kms)
-KMS_INVALID_IOCTL(radeon_cp_vertex_kms)
-KMS_INVALID_IOCTL(radeon_cp_indices_kms)
-KMS_INVALID_IOCTL(radeon_cp_texture_kms)
-KMS_INVALID_IOCTL(radeon_cp_stipple_kms)
-KMS_INVALID_IOCTL(radeon_cp_indirect_kms)
-KMS_INVALID_IOCTL(radeon_cp_vertex2_kms)
-KMS_INVALID_IOCTL(radeon_cp_cmdbuf_kms)
-KMS_INVALID_IOCTL(radeon_cp_getparam_kms)
-KMS_INVALID_IOCTL(radeon_cp_flip_kms)
-KMS_INVALID_IOCTL(radeon_mem_alloc_kms)
-KMS_INVALID_IOCTL(radeon_mem_free_kms)
-KMS_INVALID_IOCTL(radeon_mem_init_heap_kms)
-KMS_INVALID_IOCTL(radeon_irq_emit_kms)
-KMS_INVALID_IOCTL(radeon_irq_wait_kms)
-KMS_INVALID_IOCTL(radeon_cp_setparam_kms)
-KMS_INVALID_IOCTL(radeon_surface_alloc_kms)
-KMS_INVALID_IOCTL(radeon_surface_free_kms)
-
-
 const struct drm_ioctl_desc radeon_ioctls_kms[] = {
-	DRM_IOCTL_DEF_DRV(RADEON_CP_INIT, radeon_cp_init_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(RADEON_CP_START, radeon_cp_start_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(RADEON_CP_STOP, radeon_cp_stop_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(RADEON_CP_RESET, radeon_cp_reset_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(RADEON_CP_IDLE, radeon_cp_idle_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_CP_RESUME, radeon_cp_resume_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_RESET, radeon_engine_reset_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_FULLSCREEN, radeon_fullscreen_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_SWAP, radeon_cp_swap_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_CLEAR, radeon_cp_clear_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_VERTEX, radeon_cp_vertex_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_INDICES, radeon_cp_indices_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_TEXTURE, radeon_cp_texture_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_STIPPLE, radeon_cp_stipple_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_INDIRECT, radeon_cp_indirect_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(RADEON_VERTEX2, radeon_cp_vertex2_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_CMDBUF, radeon_cp_cmdbuf_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_GETPARAM, radeon_cp_getparam_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_FLIP, radeon_cp_flip_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_ALLOC, radeon_mem_alloc_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_FREE, radeon_mem_free_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_INIT_HEAP, radeon_mem_init_heap_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(RADEON_IRQ_EMIT, radeon_irq_emit_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_IRQ_WAIT, radeon_irq_wait_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_SETPARAM, radeon_cp_setparam_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_SURF_ALLOC, radeon_surface_alloc_kms, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(RADEON_SURF_FREE, radeon_surface_free_kms, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_CP_INIT, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(RADEON_CP_START, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(RADEON_CP_STOP, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(RADEON_CP_RESET, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(RADEON_CP_IDLE, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_CP_RESUME, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_RESET, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_FULLSCREEN, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_SWAP, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_CLEAR, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_VERTEX, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_INDICES, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_TEXTURE, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_STIPPLE, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_INDIRECT, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(RADEON_VERTEX2, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_CMDBUF, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_GETPARAM, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_FLIP, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_ALLOC, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_FREE, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_INIT_HEAP, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(RADEON_IRQ_EMIT, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_IRQ_WAIT, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_SETPARAM, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_SURF_ALLOC, drm_invalid_op, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_SURF_FREE, drm_invalid_op, DRM_AUTH),
 	/* KMS */
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_INFO, radeon_gem_info_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_CREATE, radeon_gem_create_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_MMAP, radeon_gem_mmap_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_DOMAIN, radeon_gem_set_domain_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_PREAD, radeon_gem_pread_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_PWRITE, radeon_gem_pwrite_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_WAIT_IDLE, radeon_gem_wait_idle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_CS, radeon_cs_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_INFO, radeon_info_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_TILING, radeon_gem_set_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_GET_TILING, radeon_gem_get_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_OP, radeon_gem_op_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_USERPTR, radeon_gem_userptr_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_INFO, radeon_gem_info_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_CREATE, radeon_gem_create_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_MMAP, radeon_gem_mmap_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_DOMAIN, radeon_gem_set_domain_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_PREAD, radeon_gem_pread_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_PWRITE, radeon_gem_pwrite_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_WAIT_IDLE, radeon_gem_wait_idle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_CS, radeon_cs_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_INFO, radeon_info_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_TILING, radeon_gem_set_tiling_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_GET_TILING, radeon_gem_get_tiling_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_OP, radeon_gem_op_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_USERPTR, radeon_gem_userptr_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 };
 int radeon_max_kms_ioctl = ARRAY_SIZE(radeon_ioctls_kms);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 457b026a0..bba112628 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -367,6 +367,7 @@ struct radeon_crtc {
 	u32 line_time;
 	u32 wm_low;
 	u32 wm_high;
+	u32 lb_vblank_lead_lines;
 	struct drm_display_mode hw_mode;
 	enum radeon_output_csc output_csc;
 };
@@ -553,6 +554,7 @@ struct radeon_connector {
 	void *con_priv;
 	bool dac_load_detect;
 	bool detected_by_load; /* if the connection status was determined by load */
+	bool detected_hpd_without_ddc; /* if an HPD signal was detected on DVI, but ddc probing failed */
 	uint16_t connector_object_id;
 	struct radeon_hpd hpd;
 	struct radeon_router router;
@@ -686,6 +688,9 @@ struct atom_voltage_table
 	struct atom_voltage_table_entry entries[MAX_VOLTAGE_ENTRIES];
 };
 
+/* Driver internal use only flags of radeon_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART 		(1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART	(1 << 31)
 
 extern void
 radeon_add_atom_connector(struct drm_device *dev,
@@ -874,10 +879,10 @@ extern int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 				   int x, int y);
 extern void radeon_cursor_reset(struct drm_crtc *crtc);
 
-extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
-				      unsigned int flags,
-				      int *vpos, int *hpos, ktime_t *stime,
-				      ktime_t *etime);
+extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
+				      unsigned int flags, int *vpos, int *hpos,
+				      ktime_t *stime, ktime_t *etime,
+				      const struct drm_display_mode *mode);
 
 extern bool radeon_combios_check_hardcoded_edid(struct radeon_device *rdev);
 extern struct edid *
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index d3024883b..84d45633d 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -221,11 +221,17 @@ int radeon_bo_create(struct radeon_device *rdev,
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 
+	/* Write-combined CPU mappings of GTT cause GPU hangs with RV6xx
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=91268
+	 */
+	if (rdev->family >= CHIP_RV610 && rdev->family <= CHIP_RV635)
+		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
+
 #ifdef CONFIG_X86_32
 	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
 	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
-	bo->flags &= ~RADEON_GEM_GTT_WC;
+	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 #elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
 	/* Don't try to enable write-combining when it can't work, or things
 	 * may be slow
@@ -235,9 +241,10 @@ int radeon_bo_create(struct radeon_device *rdev,
 #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
 	 thanks to write-combining
 
-	DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
-		      "better performance thanks to write-combining\n");
-	bo->flags &= ~RADEON_GEM_GTT_WC;
+	if (bo->flags & RADEON_GEM_GTT_WC)
+		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+			      "better performance thanks to write-combining\n");
+	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 #endif
 
 	radeon_ttm_placement_from_domain(bo, domain);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 5feee3b4c..59abebd6b 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1542,8 +1542,7 @@ int radeon_pm_late_init(struct radeon_device *rdev)
 				ret = device_create_file(rdev->dev, &dev_attr_power_method);
 				if (ret)
 					DRM_ERROR("failed to create device file for power method\n");
-				if (!ret)
-					rdev->pm.sysfs_initialized = true;
+				rdev->pm.sysfs_initialized = true;
 			}
 
 			mutex_lock(&rdev->pm.mutex);
@@ -1757,7 +1756,11 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
 	 */
 	for (crtc = 0; (crtc < rdev->num_crtc) && in_vbl; crtc++) {
 		if (rdev->pm.active_crtcs & (1 << crtc)) {
-			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0, &vpos, &hpos, NULL, NULL);
+			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev,
+								crtc,
+								USE_REAL_VBLANKSTART,
+								&vpos, &hpos, NULL, NULL,
+								&rdev->mode_info.crtcs[crtc]->base.hwmode);
 			if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
 			    !(vbl_status & DRM_SCANOUTPOS_IN_VBLANK))
 				in_vbl = false;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 06ac59fe3..e34307459 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -144,7 +144,7 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		man->available_caching = TTM_PL_MASK_CACHING;
 		man->default_caching = TTM_PL_FLAG_CACHED;
 		man->flags = TTM_MEMTYPE_FLAG_MAPPABLE | TTM_MEMTYPE_FLAG_CMA;
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 		if (rdev->flags & RADEON_IS_AGP) {
 			if (!rdev->ddev->agp) {
 				DRM_ERROR("AGP is not enabled for memory type %u\n",
@@ -461,7 +461,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_
 		/* system memory */
 		return 0;
 	case TTM_PL_TT:
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 		if (rdev->flags & RADEON_IS_AGP) {
 			/* RADEON_IS_AGP is set only if AGP is active */
 			mem->bus.offset = mem->start << PAGE_SHIFT;
@@ -680,7 +680,7 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 	struct radeon_ttm_tt *gtt;
 
 	rdev = radeon_get_rdev(bdev);
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
 		return ttm_agp_tt_create(bdev, rdev->ddev->agp->bridge,
 					 size, page_flags, dummy_read_page);
@@ -736,7 +736,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 	}
 
 	rdev = radeon_get_rdev(ttm->bdev);
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
 		return ttm_agp_tt_populate(ttm);
 	}
@@ -787,7 +787,7 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 		return;
 
 	rdev = radeon_get_rdev(ttm->bdev);
-#if __OS_HAS_AGP
+#if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
 		ttm_agp_tt_unpopulate(ttm);
 		return;
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 722ce75a5..5a8f7fbea 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -360,31 +360,31 @@ int radeon_vce_get_create_msg(struct radeon_device *rdev, int ring,
 
 	/* stitch together an VCE create msg */
 	ib.length_dw = 0;
-	ib.ptr[ib.length_dw++] = 0x0000000c; /* len */
-	ib.ptr[ib.length_dw++] = 0x00000001; /* session cmd */
-	ib.ptr[ib.length_dw++] = handle;
-
-	ib.ptr[ib.length_dw++] = 0x00000030; /* len */
-	ib.ptr[ib.length_dw++] = 0x01000001; /* create cmd */
-	ib.ptr[ib.length_dw++] = 0x00000000;
-	ib.ptr[ib.length_dw++] = 0x00000042;
-	ib.ptr[ib.length_dw++] = 0x0000000a;
-	ib.ptr[ib.length_dw++] = 0x00000001;
-	ib.ptr[ib.length_dw++] = 0x00000080;
-	ib.ptr[ib.length_dw++] = 0x00000060;
-	ib.ptr[ib.length_dw++] = 0x00000100;
-	ib.ptr[ib.length_dw++] = 0x00000100;
-	ib.ptr[ib.length_dw++] = 0x0000000c;
-	ib.ptr[ib.length_dw++] = 0x00000000;
-
-	ib.ptr[ib.length_dw++] = 0x00000014; /* len */
-	ib.ptr[ib.length_dw++] = 0x05000005; /* feedback buffer */
-	ib.ptr[ib.length_dw++] = upper_32_bits(dummy);
-	ib.ptr[ib.length_dw++] = dummy;
-	ib.ptr[ib.length_dw++] = 0x00000001;
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); /* len */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); /* session cmd */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(handle);
+
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000030); /* len */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x01000001); /* create cmd */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000000);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000042);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000a);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000080);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000060);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000100);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000100);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000000);
+
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000014); /* len */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x05000005); /* feedback buffer */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(upper_32_bits(dummy));
+	ib.ptr[ib.length_dw++] = cpu_to_le32(dummy);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001);
 
 	for (i = ib.length_dw; i < ib_size_dw; ++i)
-		ib.ptr[i] = 0x0;
+		ib.ptr[i] = cpu_to_le32(0x0);
 
 	r = radeon_ib_schedule(rdev, &ib, NULL, false);
 	if (r) {
@@ -427,21 +427,21 @@ int radeon_vce_get_destroy_msg(struct radeon_device *rdev, int ring,
 
 	/* stitch together an VCE destroy msg */
 	ib.length_dw = 0;
-	ib.ptr[ib.length_dw++] = 0x0000000c; /* len */
-	ib.ptr[ib.length_dw++] = 0x00000001; /* session cmd */
-	ib.ptr[ib.length_dw++] = handle;
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); /* len */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); /* session cmd */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(handle);
 
-	ib.ptr[ib.length_dw++] = 0x00000014; /* len */
-	ib.ptr[ib.length_dw++] = 0x05000005; /* feedback buffer */
-	ib.ptr[ib.length_dw++] = upper_32_bits(dummy);
-	ib.ptr[ib.length_dw++] = dummy;
-	ib.ptr[ib.length_dw++] = 0x00000001;
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000014); /* len */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x05000005); /* feedback buffer */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(upper_32_bits(dummy));
+	ib.ptr[ib.length_dw++] = cpu_to_le32(dummy);
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001);
 
-	ib.ptr[ib.length_dw++] = 0x00000008; /* len */
-	ib.ptr[ib.length_dw++] = 0x02000001; /* destroy cmd */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000008); /* len */
+	ib.ptr[ib.length_dw++] = cpu_to_le32(0x02000001); /* destroy cmd */
 
 	for (i = ib.length_dw; i < ib_size_dw; ++i)
-		ib.ptr[i] = 0x0;
+		ib.ptr[i] = cpu_to_le32(0x0);
 
 	r = radeon_ib_schedule(rdev, &ib, NULL, false);
 	if (r) {
@@ -698,12 +698,12 @@ bool radeon_vce_semaphore_emit(struct radeon_device *rdev,
 {
 	uint64_t addr = semaphore->gpu_addr;
 
-	radeon_ring_write(ring, VCE_CMD_SEMAPHORE);
-	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-	radeon_ring_write(ring, 0x01003000 | (emit_wait ? 1 : 0));
+	radeon_ring_write(ring, cpu_to_le32(VCE_CMD_SEMAPHORE));
+	radeon_ring_write(ring, cpu_to_le32((addr >> 3) & 0x000FFFFF));
+	radeon_ring_write(ring, cpu_to_le32((addr >> 23) & 0x000FFFFF));
+	radeon_ring_write(ring, cpu_to_le32(0x01003000 | (emit_wait ? 1 : 0)));
 	if (!emit_wait)
-		radeon_ring_write(ring, VCE_CMD_END);
+		radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END));
 
 	return true;
 }
@@ -718,10 +718,10 @@ bool radeon_vce_semaphore_emit(struct radeon_device *rdev,
 void radeon_vce_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
-	radeon_ring_write(ring, VCE_CMD_IB);
-	radeon_ring_write(ring, ib->gpu_addr);
-	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr));
-	radeon_ring_write(ring, ib->length_dw);
+	radeon_ring_write(ring, cpu_to_le32(VCE_CMD_IB));
+	radeon_ring_write(ring, cpu_to_le32(ib->gpu_addr));
+	radeon_ring_write(ring, cpu_to_le32(upper_32_bits(ib->gpu_addr)));
+	radeon_ring_write(ring, cpu_to_le32(ib->length_dw));
 }
 
 /**
@@ -737,12 +737,12 @@ void radeon_vce_fence_emit(struct radeon_device *rdev,
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
 
-	radeon_ring_write(ring, VCE_CMD_FENCE);
-	radeon_ring_write(ring, addr);
-	radeon_ring_write(ring, upper_32_bits(addr));
-	radeon_ring_write(ring, fence->seq);
-	radeon_ring_write(ring, VCE_CMD_TRAP);
-	radeon_ring_write(ring, VCE_CMD_END);
+	radeon_ring_write(ring, cpu_to_le32(VCE_CMD_FENCE));
+	radeon_ring_write(ring, cpu_to_le32(addr));
+	radeon_ring_write(ring, cpu_to_le32(upper_32_bits(addr)));
+	radeon_ring_write(ring, cpu_to_le32(fence->seq));
+	radeon_ring_write(ring, cpu_to_le32(VCE_CMD_TRAP));
+	radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END));
 }
 
 /**
@@ -764,7 +764,7 @@ int radeon_vce_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
 			  ring->idx, r);
 		return r;
 	}
-	radeon_ring_write(ring, VCE_CMD_END);
+	radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END));
 	radeon_ring_unlock_commit(rdev, ring, false);
 
 	for (i = 0; i < rdev->usec_timeout; i++) {
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 97a904835..6244f4e44 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -813,7 +813,7 @@ int rs600_irq_process(struct radeon_device *rdev)
 		status = rs600_irq_ack(rdev);
 	}
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_hdmi)
 		schedule_work(&rdev->audio_work);
 	if (rdev->msi_enabled) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 516ca27cf..6bc44c24e 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -207,6 +207,9 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
 {
 	u32 tmp;
 
+	/* Guess line buffer size to be 8192 pixels */
+	u32 lb_size = 8192;
+
 	/*
 	 * Line Buffer Setup
 	 * There is a single line buffer shared by both display controllers.
@@ -243,6 +246,13 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
 		tmp |= V_006520_DC_LB_MEMORY_SPLIT_D1_1Q_D2_3Q;
 	}
 	WREG32(R_006520_DC_LB_MEMORY_SPLIT, tmp);
+
+	/* Save number of lines the linebuffer leads before the scanout */
+	if (mode1)
+		rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+	if (mode2)
+		rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 struct rs690_watermark {
diff --git a/drivers/gpu/drm/radeon/rv730_dpm.c b/drivers/gpu/drm/radeon/rv730_dpm.c
index 3f5e1cf13..d37ba2cb8 100644
--- a/drivers/gpu/drm/radeon/rv730_dpm.c
+++ b/drivers/gpu/drm/radeon/rv730_dpm.c
@@ -464,7 +464,7 @@ void rv730_stop_dpm(struct radeon_device *rdev)
 	result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
 	if (result != PPSMC_Result_OK)
-		DRM_ERROR("Could not force DPM to low\n");
+		DRM_DEBUG("Could not force DPM to low\n");
 
 	WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index b9c770745..e830c8935 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -193,7 +193,7 @@ void rv770_stop_dpm(struct radeon_device *rdev)
 	result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
 	if (result != PPSMC_Result_OK)
-		DRM_ERROR("Could not force DPM to low.\n");
+		DRM_DEBUG("Could not force DPM to low.\n");
 
 	WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
@@ -1418,7 +1418,7 @@ int rv770_resume_smc(struct radeon_device *rdev)
 int rv770_set_sw_state(struct radeon_device *rdev)
 {
 	if (rv770_send_msg_to_smc(rdev, PPSMC_MSG_SwitchToSwState) != PPSMC_Result_OK)
-		return -EINVAL;
+		DRM_DEBUG("rv770_set_sw_state failed\n");
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 6936e275f..f7b997eee 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2303,6 +2303,9 @@ static void dce6_program_watermarks(struct radeon_device *rdev,
 		c.full = dfixed_div(c, a);
 		priority_b_mark = dfixed_trunc(c);
 		priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+		/* Save number of lines the linebuffer leads before the scanout */
+		radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -6775,7 +6778,7 @@ restart_ih:
 	if (queue_dp)
 		schedule_work(&rdev->dp_work);
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_thermal && rdev->pm.dpm_enabled)
 		schedule_work(&rdev->pm.dpm.thermal.work);
 	rdev->ih.rptr = rptr;
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index e72bf4604..a82b891ae 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2927,7 +2927,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
-	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 },
 	{ 0, 0, 0, 0 },
 };