diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index bf87f6d435f8..86d9ee08b13f 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1753,7 +1753,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				if (pll != ATOM_PPLL_INVALID)
 					return pll;
 			}
-		} else {
+		} else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */
 			/* use the same PPLL for all monitors with the same clock */
 			pll = radeon_get_shared_nondp_ppll(crtc);
 			if (pll != ATOM_PPLL_INVALID)
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 28e2dc48e015..eb3ba60a2e92 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1644,19 +1644,11 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
 			/* enable the transmitter */
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		} else {
 			/* setup and enable the encoder and transmitter */
 			atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-			/* some dce3.x boards have a bug in their transmitter control table.
-			 * ACTION_ENABLE_OUTPUT can probably be dropped since ACTION_ENABLE
-			 * does the same thing and more.
-			 */
-			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) &&
-			    (rdev->family != CHIP_RS880))
-				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
 			if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
@@ -1674,16 +1666,11 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+		if (ASIC_IS_DCE4(rdev)) {
 			/* disable the transmitter */
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-		} else if (ASIC_IS_DCE4(rdev)) {
-			/* disable the transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
 		} else {
 			/* disable the encoder and transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
 			atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0);
 		}
@@ -2392,6 +2379,15 @@ static void radeon_atom_encoder_prepare(struct drm_encoder *encoder)
 
 	/* this is needed for the pll/ss setup to work correctly in some cases */
 	atombios_set_encoder_crtc_source(encoder);
+	/* set up the FMT blocks */
+	if (ASIC_IS_DCE8(rdev))
+		dce8_program_fmt(encoder);
+	else if (ASIC_IS_DCE4(rdev))
+		dce4_program_fmt(encoder);
+	else if (ASIC_IS_DCE3(rdev))
+		dce3_program_fmt(encoder);
+	else if (ASIC_IS_AVIVO(rdev))
+		avivo_program_fmt(encoder);
 }
 
 static void radeon_atom_encoder_commit(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index d02fd1c045d5..2e48f902e3b5 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -67,11 +67,6 @@ extern void si_init_uvd_internal_cg(struct radeon_device *rdev);
 extern int cik_sdma_resume(struct radeon_device *rdev);
 extern void cik_sdma_enable(struct radeon_device *rdev, bool enable);
 extern void cik_sdma_fini(struct radeon_device *rdev);
-extern void cik_sdma_vm_set_page(struct radeon_device *rdev,
-				 struct radeon_ib *ib,
-				 uint64_t pe,
-				 uint64_t addr, unsigned count,
-				 uint32_t incr, uint32_t flags);
 static void cik_rlc_stop(struct radeon_device *rdev);
 static void cik_pcie_gen3_enable(struct radeon_device *rdev);
 static void cik_program_aspm(struct radeon_device *rdev);
@@ -3094,6 +3089,85 @@ void cik_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | sel);
 }
 
+/**
+ * cik_copy_cpdma - copy pages using the CP DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the CP DMA engine (CIK+).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int cik_copy_cpdma(struct radeon_device *rdev,
+		   uint64_t src_offset, uint64_t dst_offset,
+		   unsigned num_gpu_pages,
+		   struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.blit_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_bytes, cur_size_in_bytes, control;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
+	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);
+	r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_bytes = size_in_bytes;
+		if (cur_size_in_bytes > 0x1fffff)
+			cur_size_in_bytes = 0x1fffff;
+		size_in_bytes -= cur_size_in_bytes;
+		control = 0;
+		if (size_in_bytes == 0)
+			control |= PACKET3_DMA_DATA_CP_SYNC;
+		radeon_ring_write(ring, PACKET3(PACKET3_DMA_DATA, 5));
+		radeon_ring_write(ring, control);
+		radeon_ring_write(ring, lower_32_bits(src_offset));
+		radeon_ring_write(ring, upper_32_bits(src_offset));
+		radeon_ring_write(ring, lower_32_bits(dst_offset));
+		radeon_ring_write(ring, upper_32_bits(dst_offset));
+		radeon_ring_write(ring, cur_size_in_bytes);
+		src_offset += cur_size_in_bytes;
+		dst_offset += cur_size_in_bytes;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
+
 /*
  * IB stuff
  */
@@ -4824,62 +4898,6 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	}
 }
 
-/**
- * cik_vm_set_page - update the page tables using sDMA
- *
- * @rdev: radeon_device pointer
- * @ib: indirect buffer to fill with commands
- * @pe: addr of the page entry
- * @addr: dst addr to write into pe
- * @count: number of page entries to update
- * @incr: increase next addr by incr bytes
- * @flags: access flags
- *
- * Update the page tables using CP or sDMA (CIK).
- */
-void cik_vm_set_page(struct radeon_device *rdev,
-		     struct radeon_ib *ib,
-		     uint64_t pe,
-		     uint64_t addr, unsigned count,
-		     uint32_t incr, uint32_t flags)
-{
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	uint64_t value;
-	unsigned ndw;
-
-	if (rdev->asic->vm.pt_ring_index == RADEON_RING_TYPE_GFX_INDEX) {
-		/* CP */
-		while (count) {
-			ndw = 2 + count * 2;
-			if (ndw > 0x3FFE)
-				ndw = 0x3FFE;
-
-			ib->ptr[ib->length_dw++] = PACKET3(PACKET3_WRITE_DATA, ndw);
-			ib->ptr[ib->length_dw++] = (WRITE_DATA_ENGINE_SEL(0) |
-						    WRITE_DATA_DST_SEL(1));
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-			for (; ndw > 2; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= r600_flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		/* DMA */
-		cik_sdma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
-	}
-}
-
 /*
  * RLC
  * The RLC is a multi-purpose microengine that handles a
@@ -5546,7 +5564,7 @@ void cik_init_cp_pg_table(struct radeon_device *rdev)
 		}
 
 		for (i = 0; i < CP_ME_TABLE_SIZE; i ++) {
-			dst_ptr[bo_offset + i] = be32_to_cpu(fw_data[table_offset + i]);
+			dst_ptr[bo_offset + i] = cpu_to_le32(be32_to_cpu(fw_data[table_offset + i]));
 		}
 		bo_offset += CP_ME_TABLE_SIZE;
 	}
@@ -5768,52 +5786,53 @@ void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
 	if (buffer == NULL)
 		return;
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_BEGIN_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_BEGIN_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CONTEXT_CONTROL, 1);
-	buffer[count++] = 0x80000000;
-	buffer[count++] = 0x80000000;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CONTEXT_CONTROL, 1));
+	buffer[count++] = cpu_to_le32(0x80000000);
+	buffer[count++] = cpu_to_le32(0x80000000);
 
 	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
 		for (ext = sect->section; ext->extent != NULL; ++ext) {
 			if (sect->id == SECT_CONTEXT) {
-				buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count);
-				buffer[count++] = ext->reg_index - 0xa000;
+				buffer[count++] =
+					cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count));
+				buffer[count++] = cpu_to_le32(ext->reg_index - 0xa000);
 				for (i = 0; i < ext->reg_count; i++)
-					buffer[count++] = ext->extent[i];
+					buffer[count++] = cpu_to_le32(ext->extent[i]);
 			} else {
 				return;
 			}
 		}
 	}
 
-	buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, 2);
-	buffer[count++] = PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, 2));
+	buffer[count++] = cpu_to_le32(PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
-		buffer[count++] = 0x16000012;
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x16000012);
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	case CHIP_KAVERI:
-		buffer[count++] = 0x00000000; /* XXX */
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000); /* XXX */
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	case CHIP_KABINI:
-		buffer[count++] = 0x00000000; /* XXX */
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000); /* XXX */
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	default:
-		buffer[count++] = 0x00000000;
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000);
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	}
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_END_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CLEAR_STATE, 0);
-	buffer[count++] = 0;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CLEAR_STATE, 0));
+	buffer[count++] = cpu_to_le32(0);
 }
 
 static void cik_init_pg(struct radeon_device *rdev)
@@ -7108,7 +7127,7 @@ static int cik_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     CP_RB0_RPTR, CP_RB0_WPTR,
-			     RADEON_CP_PACKET2);
+			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
 
@@ -7418,6 +7437,70 @@ void cik_fini(struct radeon_device *rdev)
 	rdev->bios = NULL;
 }
 
+void dce8_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS/eDP FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	/* not needed for analog */
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2))
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH(0));
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH(0));
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_RGB_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH(1));
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH(1));
+		break;
+	case 10:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_RGB_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH(2));
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH(2));
+		break;
+	default:
+		/* not needed */
+		break;
+	}
+
+	WREG32(FMT_BIT_DEPTH_CONTROL + radeon_crtc->crtc_offset, tmp);
+}
+
 /* display watermark setup */
 /**
  * dce8_line_buffer_adjust - Set up the line buffer
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index b6286068e111..8d84ebe2b6fa 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -25,6 +25,7 @@
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
+#include "radeon_trace.h"
 #include "cikd.h"
 
 /* sdma */
@@ -653,11 +654,12 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			  uint64_t addr, unsigned count,
 			  uint32_t incr, uint32_t flags)
 {
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
 
-	if (flags & RADEON_VM_PAGE_SYSTEM) {
+	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
+
+	if (flags & R600_PTE_SYSTEM) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -669,16 +671,10 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
 			ib->ptr[ib->length_dw++] = ndw;
 			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
 				addr += incr;
-				value |= r600_flags;
+				value |= flags;
 				ib->ptr[ib->length_dw++] = value;
 				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
@@ -689,7 +685,7 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			if (ndw > 0x7FFFF)
 				ndw = 0x7FFFF;
 
-			if (flags & RADEON_VM_PAGE_VALID)
+			if (flags & R600_PTE_VALID)
 				value = addr;
 			else
 				value = 0;
@@ -697,7 +693,7 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_GENERATE_PTE_PDE, 0, 0);
 			ib->ptr[ib->length_dw++] = pe; /* dst addr */
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = flags; /* mask */
 			ib->ptr[ib->length_dw++] = 0;
 			ib->ptr[ib->length_dw++] = value; /* value */
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 203d2a09a1f5..380cea311a2b 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -906,6 +906,39 @@
 #define DPG_PIPE_STUTTER_CONTROL                          0x6cd4
 #       define STUTTER_ENABLE                             (1 << 0)
 
+/* DCE8 FMT blocks */
+#define FMT_DYNAMIC_EXP_CNTL                 0x6fb4
+#       define FMT_DYNAMIC_EXP_EN            (1 << 0)
+#       define FMT_DYNAMIC_EXP_MODE          (1 << 4)
+        /* 0 = 10bit -> 12bit, 1 = 8bit -> 12bit */
+#define FMT_CONTROL                          0x6fb8
+#       define FMT_PIXEL_ENCODING            (1 << 16)
+        /* 0 = RGB 4:4:4 or YCbCr 4:4:4, 1 = YCbCr 4:2:2 */
+#define FMT_BIT_DEPTH_CONTROL                0x6fc8
+#       define FMT_TRUNCATE_EN               (1 << 0)
+#       define FMT_TRUNCATE_MODE             (1 << 1)
+#       define FMT_TRUNCATE_DEPTH(x)         ((x) << 4) /* 0 - 18bpp, 1 - 24bpp, 2 - 30bpp */
+#       define FMT_SPATIAL_DITHER_EN         (1 << 8)
+#       define FMT_SPATIAL_DITHER_MODE(x)    ((x) << 9)
+#       define FMT_SPATIAL_DITHER_DEPTH(x)   ((x) << 11) /* 0 - 18bpp, 1 - 24bpp, 2 - 30bpp */
+#       define FMT_FRAME_RANDOM_ENABLE       (1 << 13)
+#       define FMT_RGB_RANDOM_ENABLE         (1 << 14)
+#       define FMT_HIGHPASS_RANDOM_ENABLE    (1 << 15)
+#       define FMT_TEMPORAL_DITHER_EN        (1 << 16)
+#       define FMT_TEMPORAL_DITHER_DEPTH(x)  ((x) << 17) /* 0 - 18bpp, 1 - 24bpp, 2 - 30bpp */
+#       define FMT_TEMPORAL_DITHER_OFFSET(x) ((x) << 21)
+#       define FMT_TEMPORAL_LEVEL            (1 << 24)
+#       define FMT_TEMPORAL_DITHER_RESET     (1 << 25)
+#       define FMT_25FRC_SEL(x)              ((x) << 26)
+#       define FMT_50FRC_SEL(x)              ((x) << 28)
+#       define FMT_75FRC_SEL(x)              ((x) << 30)
+#define FMT_CLAMP_CONTROL                    0x6fe4
+#       define FMT_CLAMP_DATA_EN             (1 << 0)
+#       define FMT_CLAMP_COLOR_FORMAT(x)     ((x) << 16)
+#       define FMT_CLAMP_6BPC                0
+#       define FMT_CLAMP_8BPC                1
+#       define FMT_CLAMP_10BPC               2
+
 #define	GRBM_CNTL					0x8000
 #define		GRBM_READ_TIMEOUT(x)				((x) << 0)
 
@@ -1714,6 +1747,68 @@
 #              define PACKET3_PREAMBLE_BEGIN_CLEAR_STATE     (2 << 28)
 #              define PACKET3_PREAMBLE_END_CLEAR_STATE       (3 << 28)
 #define	PACKET3_DMA_DATA				0x50
+/* 1. header
+ * 2. CONTROL
+ * 3. SRC_ADDR_LO or DATA [31:0]
+ * 4. SRC_ADDR_HI [31:0]
+ * 5. DST_ADDR_LO [31:0]
+ * 6. DST_ADDR_HI [7:0]
+ * 7. COMMAND [30:21] | BYTE_COUNT [20:0]
+ */
+/* CONTROL */
+#              define PACKET3_DMA_DATA_ENGINE(x)     ((x) << 0)
+                /* 0 - ME
+		 * 1 - PFP
+		 */
+#              define PACKET3_DMA_DATA_SRC_CACHE_POLICY(x) ((x) << 13)
+                /* 0 - LRU
+		 * 1 - Stream
+		 * 2 - Bypass
+		 */
+#              define PACKET3_DMA_DATA_SRC_VOLATILE (1 << 15)
+#              define PACKET3_DMA_DATA_DST_SEL(x)  ((x) << 20)
+                /* 0 - DST_ADDR using DAS
+		 * 1 - GDS
+		 * 3 - DST_ADDR using L2
+		 */
+#              define PACKET3_DMA_DATA_DST_CACHE_POLICY(x) ((x) << 25)
+                /* 0 - LRU
+		 * 1 - Stream
+		 * 2 - Bypass
+		 */
+#              define PACKET3_DMA_DATA_DST_VOLATILE (1 << 27)
+#              define PACKET3_DMA_DATA_SRC_SEL(x)  ((x) << 29)
+                /* 0 - SRC_ADDR using SAS
+		 * 1 - GDS
+		 * 2 - DATA
+		 * 3 - SRC_ADDR using L2
+		 */
+#              define PACKET3_DMA_DATA_CP_SYNC     (1 << 31)
+/* COMMAND */
+#              define PACKET3_DMA_DATA_DIS_WC      (1 << 21)
+#              define PACKET3_DMA_DATA_CMD_SRC_SWAP(x) ((x) << 22)
+                /* 0 - none
+		 * 1 - 8 in 16
+		 * 2 - 8 in 32
+		 * 3 - 8 in 64
+		 */
+#              define PACKET3_DMA_DATA_CMD_DST_SWAP(x) ((x) << 24)
+                /* 0 - none
+		 * 1 - 8 in 16
+		 * 2 - 8 in 32
+		 * 3 - 8 in 64
+		 */
+#              define PACKET3_DMA_DATA_CMD_SAS     (1 << 26)
+                /* 0 - memory
+		 * 1 - register
+		 */
+#              define PACKET3_DMA_DATA_CMD_DAS     (1 << 27)
+                /* 0 - memory
+		 * 1 - register
+		 */
+#              define PACKET3_DMA_DATA_CMD_SAIC    (1 << 28)
+#              define PACKET3_DMA_DATA_CMD_DAIC    (1 << 29)
+#              define PACKET3_DMA_DATA_CMD_RAW_WAIT  (1 << 30)
 #define	PACKET3_AQUIRE_MEM				0x58
 #define	PACKET3_REWIND					0x59
 #define	PACKET3_LOAD_UCONFIG_REG			0x5E
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 85a69d2ea3d2..5929056beca6 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -102,6 +102,49 @@ void dce6_afmt_select_pin(struct drm_encoder *encoder)
 	       AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id));
 }
 
+void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
+				    struct drm_display_mode *mode)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp = 0, offset;
+
+	if (!dig->afmt->pin)
+		return;
+
+	offset = dig->afmt->pin->offset;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		if (connector->latency_present[1])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
+				AUDIO_LIPSYNC(connector->audio_latency[1]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	} else {
+		if (connector->latency_present[0])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[0]) |
+				AUDIO_LIPSYNC(connector->audio_latency[0]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	}
+	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
+}
+
 void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 555164e270a7..7a84d0cdeda7 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1193,6 +1193,62 @@ void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev)
 	}
 }
 
+void dce4_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS/eDP FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	/* not needed for analog */
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2))
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN);
+		else
+			tmp |= FMT_TRUNCATE_EN;
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_FRAME_RANDOM_ENABLE | FMT_HIGHPASS_RANDOM_ENABLE |
+				FMT_RGB_RANDOM_ENABLE |
+				FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH);
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH);
+		break;
+	case 10:
+	default:
+		/* not needed */
+		break;
+	}
+
+	WREG32(FMT_BIT_DEPTH_CONTROL + radeon_crtc->crtc_offset, tmp);
+}
+
 static bool dce4_is_in_vblank(struct radeon_device *rdev, int crtc)
 {
 	if (RREG32(EVERGREEN_CRTC_STATUS + crtc_offsets[crtc]) & EVERGREEN_CRTC_V_BLANK)
@@ -3963,7 +4019,7 @@ int sumo_rlc_init(struct radeon_device *rdev)
 		if (rdev->family >= CHIP_TAHITI) {
 			/* SI */
 			for (i = 0; i < rdev->rlc.reg_list_size; i++)
-				dst_ptr[i] = src_ptr[i];
+				dst_ptr[i] = cpu_to_le32(src_ptr[i]);
 		} else {
 			/* ON/LN/TN */
 			/* format:
@@ -3977,10 +4033,10 @@ int sumo_rlc_init(struct radeon_device *rdev)
 				if (i < dws)
 					data |= (src_ptr[i] >> 2) << 16;
 				j = (((i - 1) * 3) / 2);
-				dst_ptr[j] = data;
+				dst_ptr[j] = cpu_to_le32(data);
 			}
 			j = ((i * 3) / 2);
-			dst_ptr[j] = RLC_SAVE_RESTORE_LIST_END_MARKER;
+			dst_ptr[j] = cpu_to_le32(RLC_SAVE_RESTORE_LIST_END_MARKER);
 		}
 		radeon_bo_kunmap(rdev->rlc.save_restore_obj);
 		radeon_bo_unreserve(rdev->rlc.save_restore_obj);
@@ -4042,40 +4098,40 @@ int sumo_rlc_init(struct radeon_device *rdev)
 			cik_get_csb_buffer(rdev, dst_ptr);
 		} else if (rdev->family >= CHIP_TAHITI) {
 			reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + 256;
-			dst_ptr[0] = upper_32_bits(reg_list_mc_addr);
-			dst_ptr[1] = lower_32_bits(reg_list_mc_addr);
-			dst_ptr[2] = rdev->rlc.clear_state_size;
+			dst_ptr[0] = cpu_to_le32(upper_32_bits(reg_list_mc_addr));
+			dst_ptr[1] = cpu_to_le32(lower_32_bits(reg_list_mc_addr));
+			dst_ptr[2] = cpu_to_le32(rdev->rlc.clear_state_size);
 			si_get_csb_buffer(rdev, &dst_ptr[(256/4)]);
 		} else {
 			reg_list_hdr_blk_index = 0;
 			reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + (reg_list_blk_index * 4);
 			data = upper_32_bits(reg_list_mc_addr);
-			dst_ptr[reg_list_hdr_blk_index] = data;
+			dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 			reg_list_hdr_blk_index++;
 			for (i = 0; cs_data[i].section != NULL; i++) {
 				for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
 					reg_num = cs_data[i].section[j].reg_count;
 					data = reg_list_mc_addr & 0xffffffff;
-					dst_ptr[reg_list_hdr_blk_index] = data;
+					dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 					reg_list_hdr_blk_index++;
 
 					data = (cs_data[i].section[j].reg_index * 4) & 0xffffffff;
-					dst_ptr[reg_list_hdr_blk_index] = data;
+					dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 					reg_list_hdr_blk_index++;
 
 					data = 0x08000000 | (reg_num * 4);
-					dst_ptr[reg_list_hdr_blk_index] = data;
+					dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(data);
 					reg_list_hdr_blk_index++;
 
 					for (k = 0; k < reg_num; k++) {
 						data = cs_data[i].section[j].extent[k];
-						dst_ptr[reg_list_blk_index + k] = data;
+						dst_ptr[reg_list_blk_index + k] = cpu_to_le32(data);
 					}
 					reg_list_mc_addr += reg_num * 4;
 					reg_list_blk_index += reg_num;
 				}
 			}
-			dst_ptr[reg_list_hdr_blk_index] = RLC_CLEAR_STATE_END_MARKER;
+			dst_ptr[reg_list_hdr_blk_index] = cpu_to_le32(RLC_CLEAR_STATE_END_MARKER);
 		}
 		radeon_bo_kunmap(rdev->rlc.clear_state_obj);
 		radeon_bo_unreserve(rdev->rlc.clear_state_obj);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index f71ce390aebe..678736542ed8 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -35,6 +35,8 @@
 extern void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder);
 extern void dce6_afmt_write_sad_regs(struct drm_encoder *encoder);
 extern void dce6_afmt_select_pin(struct drm_encoder *encoder);
+extern void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
+					   struct drm_display_mode *mode);
 
 /*
  * update the N and CTS parameters for a given pixel clock rate
@@ -58,6 +60,42 @@ static void evergreen_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t cloc
 	WREG32(HDMI_ACR_48_1 + offset, acr.n_48khz);
 }
 
+static void dce4_afmt_write_latency_fields(struct drm_encoder *encoder,
+					   struct drm_display_mode *mode)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp = 0;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		if (connector->latency_present[1])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
+				AUDIO_LIPSYNC(connector->audio_latency[1]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	} else {
+		if (connector->latency_present[0])
+			tmp = VIDEO_LIPSYNC(connector->video_latency[0]) |
+				AUDIO_LIPSYNC(connector->audio_latency[0]);
+		else
+			tmp = VIDEO_LIPSYNC(255) | AUDIO_LIPSYNC(255);
+	}
+	WREG32(AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_LIPSYNC, tmp);
+}
+
 static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
@@ -68,8 +106,10 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	int sad_count;
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -121,8 +161,10 @@ static void evergreen_hdmi_write_sad_regs(struct drm_encoder *encoder)
 	};
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -321,8 +363,10 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	if (ASIC_IS_DCE6(rdev)) {
 		dce6_afmt_select_pin(encoder);
 		dce6_afmt_write_sad_regs(encoder);
+		dce6_afmt_write_latency_fields(encoder, mode);
 	} else {
 		evergreen_hdmi_write_sad_regs(encoder);
+		dce4_afmt_write_latency_fields(encoder, mode);
 	}
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 8768fd6a1e27..11e002a47b55 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -750,6 +750,44 @@
  * bit6 = 192 kHz
  */
 
+#define AZ_CHANNEL_COUNT_CONTROL                          0x5fe4
+#       define HBR_CHANNEL_COUNT(x)                       (((x) & 0x7) << 0)
+#       define COMPRESSED_CHANNEL_COUNT(x)                (((x) & 0x7) << 4)
+/* HBR_CHANNEL_COUNT, COMPRESSED_CHANNEL_COUNT
+ * 0   = use stream header
+ * 1-7 = channel count - 1
+ */
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_LIPSYNC         0x5fe8
+#       define VIDEO_LIPSYNC(x)                           (((x) & 0xff) << 0)
+#       define AUDIO_LIPSYNC(x)                           (((x) & 0xff) << 8)
+/* VIDEO_LIPSYNC, AUDIO_LIPSYNC
+ * 0   = invalid
+ * x   = legal delay value
+ * 255 = sync not supported
+ */
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_HBR             0x5fec
+#       define HBR_CAPABLE                                (1 << 0) /* enabled by default */
+
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_AV_ASSOCIATION0 0x5ff4
+#       define DISPLAY0_TYPE(x)                           (((x) & 0x3) << 0)
+#       define DISPLAY_TYPE_NONE                   0
+#       define DISPLAY_TYPE_HDMI                   1
+#       define DISPLAY_TYPE_DP                     2
+#       define DISPLAY0_ID(x)                             (((x) & 0x3f) << 2)
+#       define DISPLAY1_TYPE(x)                           (((x) & 0x3) << 8)
+#       define DISPLAY1_ID(x)                             (((x) & 0x3f) << 10)
+#       define DISPLAY2_TYPE(x)                           (((x) & 0x3) << 16)
+#       define DISPLAY2_ID(x)                             (((x) & 0x3f) << 18)
+#       define DISPLAY3_TYPE(x)                           (((x) & 0x3) << 24)
+#       define DISPLAY3_ID(x)                             (((x) & 0x3f) << 26)
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_AV_ASSOCIATION1 0x5ff8
+#       define DISPLAY4_TYPE(x)                           (((x) & 0x3) << 0)
+#       define DISPLAY4_ID(x)                             (((x) & 0x3f) << 2)
+#       define DISPLAY5_TYPE(x)                           (((x) & 0x3) << 8)
+#       define DISPLAY5_ID(x)                             (((x) & 0x3f) << 10)
+#define AZ_F0_CODEC_PIN0_CONTROL_RESPONSE_AV_NUMBER       0x5ffc
+#       define NUMBER_OF_DISPLAY_ID(x)                    (((x) & 0x7) << 0)
+
 #define AZ_HOT_PLUG_CONTROL                               0x5e78
 #       define AZ_FORCE_CODEC_WAKE                        (1 << 0)
 #       define PIN0_JACK_DETECTION_ENABLE                 (1 << 4)
@@ -1312,6 +1350,38 @@
 #       define DC_HPDx_RX_INT_TIMER(x)                    ((x) << 16)
 #       define DC_HPDx_EN                                 (1 << 28)
 
+/* DCE4/5/6 FMT blocks */
+#define FMT_DYNAMIC_EXP_CNTL                 0x6fb4
+#       define FMT_DYNAMIC_EXP_EN            (1 << 0)
+#       define FMT_DYNAMIC_EXP_MODE          (1 << 4)
+        /* 0 = 10bit -> 12bit, 1 = 8bit -> 12bit */
+#define FMT_CONTROL                          0x6fb8
+#       define FMT_PIXEL_ENCODING            (1 << 16)
+        /* 0 = RGB 4:4:4 or YCbCr 4:4:4, 1 = YCbCr 4:2:2 */
+#define FMT_BIT_DEPTH_CONTROL                0x6fc8
+#       define FMT_TRUNCATE_EN               (1 << 0)
+#       define FMT_TRUNCATE_DEPTH            (1 << 4)
+#       define FMT_SPATIAL_DITHER_EN         (1 << 8)
+#       define FMT_SPATIAL_DITHER_MODE(x)    ((x) << 9)
+#       define FMT_SPATIAL_DITHER_DEPTH      (1 << 12)
+#       define FMT_FRAME_RANDOM_ENABLE       (1 << 13)
+#       define FMT_RGB_RANDOM_ENABLE         (1 << 14)
+#       define FMT_HIGHPASS_RANDOM_ENABLE    (1 << 15)
+#       define FMT_TEMPORAL_DITHER_EN        (1 << 16)
+#       define FMT_TEMPORAL_DITHER_DEPTH     (1 << 20)
+#       define FMT_TEMPORAL_DITHER_OFFSET(x) ((x) << 21)
+#       define FMT_TEMPORAL_LEVEL            (1 << 24)
+#       define FMT_TEMPORAL_DITHER_RESET     (1 << 25)
+#       define FMT_25FRC_SEL(x)              ((x) << 26)
+#       define FMT_50FRC_SEL(x)              ((x) << 28)
+#       define FMT_75FRC_SEL(x)              ((x) << 30)
+#define FMT_CLAMP_CONTROL                    0x6fe4
+#       define FMT_CLAMP_DATA_EN             (1 << 0)
+#       define FMT_CLAMP_COLOR_FORMAT(x)     ((x) << 16)
+#       define FMT_CLAMP_6BPC                0
+#       define FMT_CLAMP_8BPC                1
+#       define FMT_CLAMP_10BPC               2
+
 /* ASYNC DMA */
 #define DMA_RB_RPTR                                       0xd008
 #define DMA_RB_WPTR                                       0xd00c
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 93c1f9ef5da9..e299a38e683a 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -174,11 +174,6 @@ extern void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
 extern void evergreen_program_aspm(struct radeon_device *rdev);
 extern void sumo_rlc_fini(struct radeon_device *rdev);
 extern int sumo_rlc_init(struct radeon_device *rdev);
-extern void cayman_dma_vm_set_page(struct radeon_device *rdev,
-				   struct radeon_ib *ib,
-				   uint64_t pe,
-				   uint64_t addr, unsigned count,
-				   uint32_t incr, uint32_t flags);
 
 /* Firmware Names */
 MODULE_FIRMWARE("radeon/BARTS_pfp.bin");
@@ -2399,77 +2394,6 @@ void cayman_vm_decode_fault(struct radeon_device *rdev,
 	       block, mc_id);
 }
 
-#define R600_ENTRY_VALID   (1 << 0)
-#define R600_PTE_SYSTEM    (1 << 1)
-#define R600_PTE_SNOOPED   (1 << 2)
-#define R600_PTE_READABLE  (1 << 5)
-#define R600_PTE_WRITEABLE (1 << 6)
-
-uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags)
-{
-	uint32_t r600_flags = 0;
-	r600_flags |= (flags & RADEON_VM_PAGE_VALID) ? R600_ENTRY_VALID : 0;
-	r600_flags |= (flags & RADEON_VM_PAGE_READABLE) ? R600_PTE_READABLE : 0;
-	r600_flags |= (flags & RADEON_VM_PAGE_WRITEABLE) ? R600_PTE_WRITEABLE : 0;
-	if (flags & RADEON_VM_PAGE_SYSTEM) {
-		r600_flags |= R600_PTE_SYSTEM;
-		r600_flags |= (flags & RADEON_VM_PAGE_SNOOPED) ? R600_PTE_SNOOPED : 0;
-	}
-	return r600_flags;
-}
-
-/**
- * cayman_vm_set_page - update the page tables using the CP
- *
- * @rdev: radeon_device pointer
- * @ib: indirect buffer to fill with commands
- * @pe: addr of the page entry
- * @addr: dst addr to write into pe
- * @count: number of page entries to update
- * @incr: increase next addr by incr bytes
- * @flags: access flags
- *
- * Update the page tables using the CP (cayman/TN).
- */
-void cayman_vm_set_page(struct radeon_device *rdev,
-			struct radeon_ib *ib,
-			uint64_t pe,
-			uint64_t addr, unsigned count,
-			uint32_t incr, uint32_t flags)
-{
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	uint64_t value;
-	unsigned ndw;
-
-	if (rdev->asic->vm.pt_ring_index == RADEON_RING_TYPE_GFX_INDEX) {
-		while (count) {
-			ndw = 1 + count * 2;
-			if (ndw > 0x3FFF)
-				ndw = 0x3FFF;
-
-			ib->ptr[ib->length_dw++] = PACKET3(PACKET3_ME_WRITE, ndw);
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			for (; ndw > 1; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= r600_flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		cayman_dma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
-	}
-}
-
 /**
  * cayman_vm_flush - vm flush using the CP
  *
diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
index dd6e9688fbef..bdeb65ed3658 100644
--- a/drivers/gpu/drm/radeon/ni_dma.c
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -24,6 +24,7 @@
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
+#include "radeon_trace.h"
 #include "nid.h"
 
 u32 cayman_gpu_check_soft_reset(struct radeon_device *rdev);
@@ -245,8 +246,7 @@ bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
  * @addr: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
- * @flags: access flags
- * @r600_flags: hw access flags 
+ * @flags: hw access flags 
  *
  * Update the page tables using the DMA (cayman/TN).
  */
@@ -256,11 +256,12 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			    uint64_t addr, unsigned count,
 			    uint32_t incr, uint32_t flags)
 {
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
 
-	if ((flags & RADEON_VM_PAGE_SYSTEM) || (count == 1)) {
+	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
+
+	if ((flags & R600_PTE_SYSTEM) || (count == 1)) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -271,16 +272,16 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = pe;
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
 			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
+				if (flags & R600_PTE_SYSTEM) {
 					value = radeon_vm_map_gart(rdev, addr);
 					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
+				} else if (flags & R600_PTE_VALID) {
 					value = addr;
 				} else {
 					value = 0;
 				}
 				addr += incr;
-				value |= r600_flags;
+				value |= flags;
 				ib->ptr[ib->length_dw++] = value;
 				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
@@ -291,7 +292,7 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			if (ndw > 0xFFFFE)
 				ndw = 0xFFFFE;
 
-			if (flags & RADEON_VM_PAGE_VALID)
+			if (flags & R600_PTE_VALID)
 				value = addr;
 			else
 				value = 0;
@@ -299,7 +300,7 @@ void cayman_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
 			ib->ptr[ib->length_dw++] = pe; /* dst addr */
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = flags; /* mask */
 			ib->ptr[ib->length_dw++] = 0;
 			ib->ptr[ib->length_dw++] = value; /* value */
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 2a1b1876b431..af922e297a12 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -124,6 +124,59 @@ int r600_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 	return 0;
 }
 
+void dce3_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	/* not needed for analog */
+	if ((radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) ||
+	    (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2))
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= FMT_SPATIAL_DITHER_EN;
+		else
+			tmp |= FMT_TRUNCATE_EN;
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (FMT_SPATIAL_DITHER_EN | FMT_SPATIAL_DITHER_DEPTH);
+		else
+			tmp |= (FMT_TRUNCATE_EN | FMT_TRUNCATE_DEPTH);
+		break;
+	case 10:
+	default:
+		/* not needed */
+		break;
+	}
+
+	WREG32(FMT_BIT_DEPTH_CONTROL + radeon_crtc->crtc_offset, tmp);
+}
+
 /* get temperature in millidegrees */
 int rv6xx_get_temp(struct radeon_device *rdev)
 {
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 01a3ec83f284..1abaa2be460d 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -2328,13 +2328,8 @@ static void r600_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 	unsigned i;
 
 	kfree(parser->relocs);
-	for (i = 0; i < parser->nchunks; i++) {
-		kfree(parser->chunks[i].kdata);
-		if (parser->rdev && (parser->rdev->flags & RADEON_IS_AGP)) {
-			kfree(parser->chunks[i].kpage[0]);
-			kfree(parser->chunks[i].kpage[1]);
-		}
-	}
+	for (i = 0; i < parser->nchunks; i++)
+		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
 	kfree(parser->chunks_array);
 }
@@ -2391,13 +2386,12 @@ int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp,
 	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
 	parser.ib.length_dw = ib_chunk->length_dw;
 	*l = parser.ib.length_dw;
-	r = r600_cs_parse(&parser);
-	if (r) {
-		DRM_ERROR("Invalid command stream !\n");
+	if (DRM_COPY_FROM_USER(ib, ib_chunk->user_ptr, ib_chunk->length_dw * 4)) {
+		r = -EFAULT;
 		r600_cs_parser_fini(&parser, r);
 		return r;
 	}
-	r = radeon_cs_finish_pages(&parser);
+	r = r600_cs_parse(&parser);
 	if (r) {
 		DRM_ERROR("Invalid command stream !\n");
 		r600_cs_parser_fini(&parser, r);
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index b0fa6002af3e..21f2b74e20e6 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -303,8 +303,10 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	int sad_count;
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
@@ -356,8 +358,10 @@ static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
 	};
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder)
+		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
 	}
 
 	if (!radeon_connector) {
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index e673fe26ea84..8e01b126aaeb 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1199,6 +1199,34 @@
 #       define AFMT_AZ_FORMAT_WTRIG_ACK      (1 << 29)
 #       define AFMT_AZ_AUDIO_ENABLE_CHG_ACK  (1 << 30)
 
+/* DCE3 FMT blocks */
+#define FMT_CONTROL                          0x6700
+#       define FMT_PIXEL_ENCODING            (1 << 16)
+        /* 0 = RGB 4:4:4 or YCbCr 4:4:4, 1 = YCbCr 4:2:2 */
+#define FMT_BIT_DEPTH_CONTROL                0x6710
+#       define FMT_TRUNCATE_EN               (1 << 0)
+#       define FMT_TRUNCATE_DEPTH            (1 << 4)
+#       define FMT_SPATIAL_DITHER_EN         (1 << 8)
+#       define FMT_SPATIAL_DITHER_MODE(x)    ((x) << 9)
+#       define FMT_SPATIAL_DITHER_DEPTH      (1 << 12)
+#       define FMT_FRAME_RANDOM_ENABLE       (1 << 13)
+#       define FMT_RGB_RANDOM_ENABLE         (1 << 14)
+#       define FMT_HIGHPASS_RANDOM_ENABLE    (1 << 15)
+#       define FMT_TEMPORAL_DITHER_EN        (1 << 16)
+#       define FMT_TEMPORAL_DITHER_DEPTH     (1 << 20)
+#       define FMT_TEMPORAL_DITHER_OFFSET(x) ((x) << 21)
+#       define FMT_TEMPORAL_LEVEL            (1 << 24)
+#       define FMT_TEMPORAL_DITHER_RESET     (1 << 25)
+#       define FMT_25FRC_SEL(x)              ((x) << 26)
+#       define FMT_50FRC_SEL(x)              ((x) << 28)
+#       define FMT_75FRC_SEL(x)              ((x) << 30)
+#define FMT_CLAMP_CONTROL                    0x672c
+#       define FMT_CLAMP_DATA_EN             (1 << 0)
+#       define FMT_CLAMP_COLOR_FORMAT(x)     ((x) << 16)
+#       define FMT_CLAMP_6BPC                0
+#       define FMT_CLAMP_8BPC                1
+#       define FMT_CLAMP_10BPC               2
+
 /* Power management */
 #define CG_SPLL_FUNC_CNTL                                 0x600
 #       define SPLL_RESET                                (1 << 0)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a400ac1c4147..b264af6e8b9c 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -98,6 +98,7 @@ extern int radeon_lockup_timeout;
 extern int radeon_fastfb;
 extern int radeon_dpm;
 extern int radeon_aspm;
+extern int radeon_runtime_pm;
 
 /*
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
@@ -327,7 +328,6 @@ struct radeon_fence_driver {
 	/* sync_seq is protected by ring emission lock */
 	uint64_t			sync_seq[RADEON_NUM_RINGS];
 	atomic64_t			last_seq;
-	unsigned long			last_activity;
 	bool				initialized;
 };
 
@@ -832,6 +832,12 @@ struct radeon_mec {
 #define RADEON_VM_PTB_ALIGN_MASK (RADEON_VM_PTB_ALIGN_SIZE - 1)
 #define RADEON_VM_PTB_ALIGN(a) (((a) + RADEON_VM_PTB_ALIGN_MASK) & ~RADEON_VM_PTB_ALIGN_MASK)
 
+#define R600_PTE_VALID		(1 << 0)
+#define R600_PTE_SYSTEM		(1 << 1)
+#define R600_PTE_SNOOPED	(1 << 2)
+#define R600_PTE_READABLE	(1 << 5)
+#define R600_PTE_WRITEABLE	(1 << 6)
+
 struct radeon_vm {
 	struct list_head		list;
 	struct list_head		va;
@@ -967,12 +973,8 @@ struct radeon_cs_reloc {
 struct radeon_cs_chunk {
 	uint32_t		chunk_id;
 	uint32_t		length_dw;
-	int			kpage_idx[2];
-	uint32_t		*kpage[2];
 	uint32_t		*kdata;
 	void __user		*user_ptr;
-	int			last_copied_page;
-	int			last_page_index;
 };
 
 struct radeon_cs_parser {
@@ -1007,8 +1009,15 @@ struct radeon_cs_parser {
 	struct ww_acquire_ctx	ticket;
 };
 
-extern int radeon_cs_finish_pages(struct radeon_cs_parser *p);
-extern u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx);
+static inline u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
+{
+	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
+
+	if (ibc->kdata)
+		return ibc->kdata[idx];
+	return p->ib.ptr[idx];
+}
+
 
 struct radeon_cs_packet {
 	unsigned	idx;
@@ -1675,8 +1684,6 @@ struct radeon_asic {
 	struct {
 		int (*init)(struct radeon_device *rdev);
 		void (*fini)(struct radeon_device *rdev);
-
-		u32 pt_ring_index;
 		void (*set_page)(struct radeon_device *rdev,
 				 struct radeon_ib *ib,
 				 uint64_t pe,
@@ -2170,6 +2177,7 @@ struct radeon_device {
 	bool				need_dma32;
 	bool				accel_working;
 	bool				fastfb_working; /* IGP feature*/
+	bool				needs_reset;
 	struct radeon_surface_reg surface_regs[RADEON_GEM_MAX_SURFACES];
 	const struct firmware *me_fw;	/* all family ME firmware */
 	const struct firmware *pfp_fw;	/* r6/700 PFP firmware */
@@ -2212,6 +2220,9 @@ struct radeon_device {
 	/* clock, powergating flags */
 	u32 cg_flags;
 	u32 pg_flags;
+
+	struct dev_pm_domain vga_pm_domain;
+	bool have_disp_power_ref;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -2673,8 +2684,8 @@ extern void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain);
 extern bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo);
 extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base);
 extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
-extern int radeon_resume_kms(struct drm_device *dev);
-extern int radeon_suspend_kms(struct drm_device *dev, pm_message_t state);
+extern int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
+extern int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon);
 extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size);
 extern void radeon_program_register_sequence(struct radeon_device *rdev,
 					     const u32 *registers,
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 8f7e04538fd6..d4b91675671d 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1622,8 +1622,7 @@ static struct radeon_asic cayman_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cayman_vm_set_page,
+		.set_page = &cayman_dma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &cayman_gfx_ring,
@@ -1723,8 +1722,7 @@ static struct radeon_asic trinity_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cayman_vm_set_page,
+		.set_page = &cayman_dma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &cayman_gfx_ring,
@@ -1854,8 +1852,7 @@ static struct radeon_asic si_asic = {
 	.vm = {
 		.init = &si_vm_init,
 		.fini = &si_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &si_vm_set_page,
+		.set_page = &si_dma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &si_gfx_ring,
@@ -1879,7 +1876,7 @@ static struct radeon_asic si_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = NULL,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &si_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2000,8 +1997,7 @@ static struct radeon_asic ci_asic = {
 	.vm = {
 		.init = &cik_vm_init,
 		.fini = &cik_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cik_vm_set_page,
+		.set_page = &cik_sdma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &ci_gfx_ring,
@@ -2100,8 +2096,7 @@ static struct radeon_asic kv_asic = {
 	.vm = {
 		.init = &cik_vm_init,
 		.fini = &cik_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.set_page = &cik_vm_set_page,
+		.set_page = &cik_sdma_vm_set_page,
 	},
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &ci_gfx_ring,
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 70c29d5e080d..f2833ee3a613 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -581,17 +581,18 @@ int cayman_vm_init(struct radeon_device *rdev);
 void cayman_vm_fini(struct radeon_device *rdev);
 void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags);
-void cayman_vm_set_page(struct radeon_device *rdev,
-			struct radeon_ib *ib,
-			uint64_t pe,
-			uint64_t addr, unsigned count,
-			uint32_t incr, uint32_t flags);
 int evergreen_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 void cayman_dma_ring_ib_execute(struct radeon_device *rdev,
 				struct radeon_ib *ib);
 bool cayman_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
 bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
+void cayman_dma_vm_set_page(struct radeon_device *rdev,
+			    struct radeon_ib *ib,
+			    uint64_t pe,
+			    uint64_t addr, unsigned count,
+			    uint32_t incr, uint32_t flags);
+
 void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 
 int ni_dpm_init(struct radeon_device *rdev);
@@ -653,17 +654,17 @@ int si_irq_set(struct radeon_device *rdev);
 int si_irq_process(struct radeon_device *rdev);
 int si_vm_init(struct radeon_device *rdev);
 void si_vm_fini(struct radeon_device *rdev);
-void si_vm_set_page(struct radeon_device *rdev,
-		    struct radeon_ib *ib,
-		    uint64_t pe,
-		    uint64_t addr, unsigned count,
-		    uint32_t incr, uint32_t flags);
 void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 int si_copy_dma(struct radeon_device *rdev,
 		uint64_t src_offset, uint64_t dst_offset,
 		unsigned num_gpu_pages,
 		struct radeon_fence **fence);
+void si_dma_vm_set_page(struct radeon_device *rdev,
+			struct radeon_ib *ib,
+			uint64_t pe,
+			uint64_t addr, unsigned count,
+			uint32_t incr, uint32_t flags);
 void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 u32 si_get_xclk(struct radeon_device *rdev);
 uint64_t si_get_gpu_clock_counter(struct radeon_device *rdev);
@@ -705,6 +706,10 @@ int cik_copy_dma(struct radeon_device *rdev,
 		 uint64_t src_offset, uint64_t dst_offset,
 		 unsigned num_gpu_pages,
 		 struct radeon_fence **fence);
+int cik_copy_cpdma(struct radeon_device *rdev,
+		   uint64_t src_offset, uint64_t dst_offset,
+		   unsigned num_gpu_pages,
+		   struct radeon_fence **fence);
 int cik_sdma_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
 int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 bool cik_sdma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
@@ -731,11 +736,11 @@ int cik_irq_process(struct radeon_device *rdev);
 int cik_vm_init(struct radeon_device *rdev);
 void cik_vm_fini(struct radeon_device *rdev);
 void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
-void cik_vm_set_page(struct radeon_device *rdev,
-		     struct radeon_ib *ib,
-		     uint64_t pe,
-		     uint64_t addr, unsigned count,
-		     uint32_t incr, uint32_t flags);
+void cik_sdma_vm_set_page(struct radeon_device *rdev,
+			  struct radeon_ib *ib,
+			  uint64_t pe,
+			  uint64_t addr, unsigned count,
+			  uint32_t incr, uint32_t flags);
 void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 int cik_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
 u32 cik_compute_ring_get_rptr(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index d96070bf8388..6153ec18943a 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -59,6 +59,10 @@ struct atpx_mux {
 	u16 mux;
 } __packed;
 
+bool radeon_is_px(void) {
+	return radeon_atpx_priv.atpx_detected;
+}
+
 /**
  * radeon_atpx_call - call an ATPX method
  *
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 79159b5da05b..e972143e5a36 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -31,6 +31,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+#include <linux/pm_runtime.h>
+
 extern void
 radeon_combios_connected_scratch_regs(struct drm_connector *connector,
 				      struct drm_encoder *encoder,
@@ -411,6 +413,21 @@ static int radeon_connector_set_property(struct drm_connector *connector, struct
 		}
 	}
 
+	if (property == rdev->mode_info.dither_property) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		/* need to find digital encoder on connector */
+		encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS);
+		if (!encoder)
+			return 0;
+
+		radeon_encoder = to_radeon_encoder(encoder);
+
+		if (radeon_connector->dither != val) {
+			radeon_connector->dither = val;
+			radeon_property_change_mode(&radeon_encoder->base);
+		}
+	}
+
 	if (property == rdev->mode_info.underscan_property) {
 		/* need to find digital encoder on connector */
 		encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS);
@@ -626,6 +643,11 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
 	enum drm_connector_status ret = connector_status_disconnected;
+	int r;
+
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
 
 	if (encoder) {
 		struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
@@ -651,6 +673,8 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 	/* check acpi lid status ??? */
 
 	radeon_connector_update_scratch_regs(connector, ret);
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
 	return ret;
 }
 
@@ -750,6 +774,11 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder_helper_funcs *encoder_funcs;
 	bool dret = false;
 	enum drm_connector_status ret = connector_status_disconnected;
+	int r;
+
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
 
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)
@@ -790,9 +819,8 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 			 * detected a monitor via load.
 			 */
 			if (radeon_connector->detected_by_load)
-				return connector->status;
-			else
-				return ret;
+				ret = connector->status;
+			goto out;
 		}
 
 		if (radeon_connector->dac_load_detect && encoder) {
@@ -817,6 +845,11 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	}
 
 	radeon_connector_update_scratch_regs(connector, ret);
+
+out:
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
 	return ret;
 }
 
@@ -873,10 +906,15 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	enum drm_connector_status ret = connector_status_disconnected;
+	int r;
 
 	if (!radeon_connector->dac_load_detect)
 		return ret;
 
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
+
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)
 		ret = connector_status_disconnected;
@@ -887,6 +925,8 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	if (ret == connector_status_connected)
 		ret = radeon_connector_analog_encoder_conflict_solve(connector, encoder, ret, false);
 	radeon_connector_update_scratch_regs(connector, ret);
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
 	return ret;
 }
 
@@ -954,12 +994,18 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder *encoder = NULL;
 	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct drm_mode_object *obj;
-	int i;
+	int i, r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	if (!force && radeon_check_hpd_status_unchanged(connector))
-		return connector->status;
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
+
+	if (!force && radeon_check_hpd_status_unchanged(connector)) {
+		ret = connector->status;
+		goto exit;
+	}
 
 	if (radeon_connector->ddc_bus)
 		dret = radeon_ddc_probe(radeon_connector, false);
@@ -1110,6 +1156,11 @@ out:
 
 	/* updated in get modes as well since we need to know if it's analog or digital */
 	radeon_connector_update_scratch_regs(connector, ret);
+
+exit:
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
 	return ret;
 }
 
@@ -1377,9 +1428,16 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
 	struct drm_encoder *encoder = radeon_best_single_encoder(connector);
+	int r;
 
-	if (!force && radeon_check_hpd_status_unchanged(connector))
-		return connector->status;
+	r = pm_runtime_get_sync(connector->dev->dev);
+	if (r < 0)
+		return connector_status_disconnected;
+
+	if (!force && radeon_check_hpd_status_unchanged(connector)) {
+		ret = connector->status;
+		goto out;
+	}
 
 	if (radeon_connector->edid) {
 		kfree(radeon_connector->edid);
@@ -1443,6 +1501,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	}
 
 	radeon_connector_update_scratch_regs(connector, ret);
+out:
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
 	return ret;
 }
 
@@ -1660,7 +1722,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 						      0);
 			drm_object_attach_property(&radeon_connector->base.base,
 						   rdev->mode_info.audio_property,
-						   RADEON_AUDIO_DISABLE);
+						   RADEON_AUDIO_AUTO);
+			drm_object_attach_property(&radeon_connector->base.base,
+						   rdev->mode_info.dither_property,
+						   RADEON_FMT_DITHER_DISABLE);
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
 			if (connector_type == DRM_MODE_CONNECTOR_HDMIB)
@@ -1757,7 +1822,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 			if (ASIC_IS_DCE2(rdev)) {
 				drm_object_attach_property(&radeon_connector->base.base,
 							      rdev->mode_info.audio_property,
-							      RADEON_AUDIO_DISABLE);
+							      RADEON_AUDIO_AUTO);
+			}
+			if (ASIC_IS_AVIVO(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.dither_property,
+							   RADEON_FMT_DITHER_DISABLE);
 			}
 			if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 				radeon_connector->dac_load_detect = true;
@@ -1802,7 +1872,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 			if (ASIC_IS_DCE2(rdev)) {
 				drm_object_attach_property(&radeon_connector->base.base,
 							      rdev->mode_info.audio_property,
-							      RADEON_AUDIO_DISABLE);
+							      RADEON_AUDIO_AUTO);
+			}
+			if (ASIC_IS_AVIVO(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.dither_property,
+							   RADEON_FMT_DITHER_DISABLE);
 			}
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
@@ -1846,7 +1921,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 			if (ASIC_IS_DCE2(rdev)) {
 				drm_object_attach_property(&radeon_connector->base.base,
 							      rdev->mode_info.audio_property,
-							      RADEON_AUDIO_DISABLE);
+							      RADEON_AUDIO_AUTO);
+			}
+			if (ASIC_IS_AVIVO(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							   rdev->mode_info.dither_property,
+							   RADEON_FMT_DITHER_DISABLE);
 			}
 			connector->interlace_allowed = true;
 			/* in theory with a DP to VGA converter... */
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 66c222836631..c8ab019a980e 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -213,9 +213,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			return -EFAULT;
 		}
 		p->chunks[i].length_dw = user_chunk.length_dw;
-		p->chunks[i].kdata = NULL;
 		p->chunks[i].chunk_id = user_chunk.chunk_id;
-		p->chunks[i].user_ptr = (void __user *)(unsigned long)user_chunk.chunk_data;
 		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_RELOCS) {
 			p->chunk_relocs_idx = i;
 		}
@@ -238,25 +236,31 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 				return -EINVAL;
 		}
 
-		cdata = (uint32_t *)(unsigned long)user_chunk.chunk_data;
-		if ((p->chunks[i].chunk_id == RADEON_CHUNK_ID_RELOCS) ||
-		    (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS)) {
-			size = p->chunks[i].length_dw * sizeof(uint32_t);
-			p->chunks[i].kdata = kmalloc(size, GFP_KERNEL);
-			if (p->chunks[i].kdata == NULL) {
-				return -ENOMEM;
-			}
-			if (DRM_COPY_FROM_USER(p->chunks[i].kdata,
-					       p->chunks[i].user_ptr, size)) {
-				return -EFAULT;
-			}
-			if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
-				p->cs_flags = p->chunks[i].kdata[0];
-				if (p->chunks[i].length_dw > 1)
-					ring = p->chunks[i].kdata[1];
-				if (p->chunks[i].length_dw > 2)
-					priority = (s32)p->chunks[i].kdata[2];
-			}
+		size = p->chunks[i].length_dw;
+		cdata = (void __user *)(unsigned long)user_chunk.chunk_data;
+		p->chunks[i].user_ptr = cdata;
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_CONST_IB)
+			continue;
+
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_IB) {
+			if (!p->rdev || !(p->rdev->flags & RADEON_IS_AGP))
+				continue;
+		}
+
+		p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t));
+		size *= sizeof(uint32_t);
+		if (p->chunks[i].kdata == NULL) {
+			return -ENOMEM;
+		}
+		if (DRM_COPY_FROM_USER(p->chunks[i].kdata, cdata, size)) {
+			return -EFAULT;
+		}
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
+			p->cs_flags = p->chunks[i].kdata[0];
+			if (p->chunks[i].length_dw > 1)
+				ring = p->chunks[i].kdata[1];
+			if (p->chunks[i].length_dw > 2)
+				priority = (s32)p->chunks[i].kdata[2];
 		}
 	}
 
@@ -279,34 +283,6 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 		}
 	}
 
-	/* deal with non-vm */
-	if ((p->chunk_ib_idx != -1) &&
-	    ((p->cs_flags & RADEON_CS_USE_VM) == 0) &&
-	    (p->chunks[p->chunk_ib_idx].chunk_id == RADEON_CHUNK_ID_IB)) {
-		if (p->chunks[p->chunk_ib_idx].length_dw > (16 * 1024)) {
-			DRM_ERROR("cs IB too big: %d\n",
-				  p->chunks[p->chunk_ib_idx].length_dw);
-			return -EINVAL;
-		}
-		if (p->rdev && (p->rdev->flags & RADEON_IS_AGP)) {
-			p->chunks[p->chunk_ib_idx].kpage[0] = kmalloc(PAGE_SIZE, GFP_KERNEL);
-			p->chunks[p->chunk_ib_idx].kpage[1] = kmalloc(PAGE_SIZE, GFP_KERNEL);
-			if (p->chunks[p->chunk_ib_idx].kpage[0] == NULL ||
-			    p->chunks[p->chunk_ib_idx].kpage[1] == NULL) {
-				kfree(p->chunks[p->chunk_ib_idx].kpage[0]);
-				kfree(p->chunks[p->chunk_ib_idx].kpage[1]);
-				p->chunks[p->chunk_ib_idx].kpage[0] = NULL;
-				p->chunks[p->chunk_ib_idx].kpage[1] = NULL;
-				return -ENOMEM;
-			}
-		}
-		p->chunks[p->chunk_ib_idx].kpage_idx[0] = -1;
-		p->chunks[p->chunk_ib_idx].kpage_idx[1] = -1;
-		p->chunks[p->chunk_ib_idx].last_copied_page = -1;
-		p->chunks[p->chunk_ib_idx].last_page_index =
-			((p->chunks[p->chunk_ib_idx].length_dw * 4) - 1) / PAGE_SIZE;
-	}
-
 	return 0;
 }
 
@@ -340,13 +316,8 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
 	kfree(parser->track);
 	kfree(parser->relocs);
 	kfree(parser->relocs_ptr);
-	for (i = 0; i < parser->nchunks; i++) {
-		kfree(parser->chunks[i].kdata);
-		if ((parser->rdev->flags & RADEON_IS_AGP)) {
-			kfree(parser->chunks[i].kpage[0]);
-			kfree(parser->chunks[i].kpage[1]);
-		}
-	}
+	for (i = 0; i < parser->nchunks; i++)
+		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
 	kfree(parser->chunks_array);
 	radeon_ib_free(parser->rdev, &parser->ib);
@@ -356,7 +327,6 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
 static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 			      struct radeon_cs_parser *parser)
 {
-	struct radeon_cs_chunk *ib_chunk;
 	int r;
 
 	if (parser->chunk_ib_idx == -1)
@@ -365,28 +335,11 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 	if (parser->cs_flags & RADEON_CS_USE_VM)
 		return 0;
 
-	ib_chunk = &parser->chunks[parser->chunk_ib_idx];
-	/* Copy the packet into the IB, the parser will read from the
-	 * input memory (cached) and write to the IB (which can be
-	 * uncached).
-	 */
-	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
-			   NULL, ib_chunk->length_dw * 4);
-	if (r) {
-		DRM_ERROR("Failed to get ib !\n");
-		return r;
-	}
-	parser->ib.length_dw = ib_chunk->length_dw;
 	r = radeon_cs_parse(rdev, parser->ring, parser);
 	if (r || parser->parser_error) {
 		DRM_ERROR("Invalid command stream !\n");
 		return r;
 	}
-	r = radeon_cs_finish_pages(parser);
-	if (r) {
-		DRM_ERROR("Invalid command stream !\n");
-		return r;
-	}
 
 	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
 		radeon_uvd_note_usage(rdev);
@@ -424,7 +377,6 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
 static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 				 struct radeon_cs_parser *parser)
 {
-	struct radeon_cs_chunk *ib_chunk;
 	struct radeon_fpriv *fpriv = parser->filp->driver_priv;
 	struct radeon_vm *vm = &fpriv->vm;
 	int r;
@@ -434,49 +386,13 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0)
 		return 0;
 
-	if ((rdev->family >= CHIP_TAHITI) &&
-	    (parser->chunk_const_ib_idx != -1)) {
-		ib_chunk = &parser->chunks[parser->chunk_const_ib_idx];
-		if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
-			DRM_ERROR("cs IB CONST too big: %d\n", ib_chunk->length_dw);
-			return -EINVAL;
-		}
-		r =  radeon_ib_get(rdev, parser->ring, &parser->const_ib,
-				   vm, ib_chunk->length_dw * 4);
-		if (r) {
-			DRM_ERROR("Failed to get const ib !\n");
-			return r;
-		}
-		parser->const_ib.is_const_ib = true;
-		parser->const_ib.length_dw = ib_chunk->length_dw;
-		/* Copy the packet into the IB */
-		if (DRM_COPY_FROM_USER(parser->const_ib.ptr, ib_chunk->user_ptr,
-				       ib_chunk->length_dw * 4)) {
-			return -EFAULT;
-		}
+	if (parser->const_ib.length_dw) {
 		r = radeon_ring_ib_parse(rdev, parser->ring, &parser->const_ib);
 		if (r) {
 			return r;
 		}
 	}
 
-	ib_chunk = &parser->chunks[parser->chunk_ib_idx];
-	if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
-		DRM_ERROR("cs IB too big: %d\n", ib_chunk->length_dw);
-		return -EINVAL;
-	}
-	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
-			   vm, ib_chunk->length_dw * 4);
-	if (r) {
-		DRM_ERROR("Failed to get ib !\n");
-		return r;
-	}
-	parser->ib.length_dw = ib_chunk->length_dw;
-	/* Copy the packet into the IB */
-	if (DRM_COPY_FROM_USER(parser->ib.ptr, ib_chunk->user_ptr,
-			       ib_chunk->length_dw * 4)) {
-		return -EFAULT;
-	}
 	r = radeon_ring_ib_parse(rdev, parser->ring, &parser->ib);
 	if (r) {
 		return r;
@@ -528,6 +444,62 @@ static int radeon_cs_handle_lockup(struct radeon_device *rdev, int r)
 	return r;
 }
 
+static int radeon_cs_ib_fill(struct radeon_device *rdev, struct radeon_cs_parser *parser)
+{
+	struct radeon_cs_chunk *ib_chunk;
+	struct radeon_vm *vm = NULL;
+	int r;
+
+	if (parser->chunk_ib_idx == -1)
+		return 0;
+
+	if (parser->cs_flags & RADEON_CS_USE_VM) {
+		struct radeon_fpriv *fpriv = parser->filp->driver_priv;
+		vm = &fpriv->vm;
+
+		if ((rdev->family >= CHIP_TAHITI) &&
+		    (parser->chunk_const_ib_idx != -1)) {
+			ib_chunk = &parser->chunks[parser->chunk_const_ib_idx];
+			if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
+				DRM_ERROR("cs IB CONST too big: %d\n", ib_chunk->length_dw);
+				return -EINVAL;
+			}
+			r =  radeon_ib_get(rdev, parser->ring, &parser->const_ib,
+					   vm, ib_chunk->length_dw * 4);
+			if (r) {
+				DRM_ERROR("Failed to get const ib !\n");
+				return r;
+			}
+			parser->const_ib.is_const_ib = true;
+			parser->const_ib.length_dw = ib_chunk->length_dw;
+			if (DRM_COPY_FROM_USER(parser->const_ib.ptr,
+					       ib_chunk->user_ptr,
+					       ib_chunk->length_dw * 4))
+				return -EFAULT;
+		}
+
+		ib_chunk = &parser->chunks[parser->chunk_ib_idx];
+		if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) {
+			DRM_ERROR("cs IB too big: %d\n", ib_chunk->length_dw);
+			return -EINVAL;
+		}
+	}
+	ib_chunk = &parser->chunks[parser->chunk_ib_idx];
+
+	r =  radeon_ib_get(rdev, parser->ring, &parser->ib,
+			   vm, ib_chunk->length_dw * 4);
+	if (r) {
+		DRM_ERROR("Failed to get ib !\n");
+		return r;
+	}
+	parser->ib.length_dw = ib_chunk->length_dw;
+	if (ib_chunk->kdata)
+		memcpy(parser->ib.ptr, ib_chunk->kdata, ib_chunk->length_dw * 4);
+	else if (DRM_COPY_FROM_USER(parser->ib.ptr, ib_chunk->user_ptr, ib_chunk->length_dw * 4))
+		return -EFAULT;
+	return 0;
+}
+
 int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct radeon_device *rdev = dev->dev_private;
@@ -553,10 +525,15 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		r = radeon_cs_handle_lockup(rdev, r);
 		return r;
 	}
-	r = radeon_cs_parser_relocs(&parser);
-	if (r) {
-		if (r != -ERESTARTSYS)
+
+	r = radeon_cs_ib_fill(rdev, &parser);
+	if (!r) {
+		r = radeon_cs_parser_relocs(&parser);
+		if (r && r != -ERESTARTSYS)
 			DRM_ERROR("Failed to parse relocation %d!\n", r);
+	}
+
+	if (r) {
 		radeon_cs_parser_fini(&parser, r, false);
 		up_read(&rdev->exclusive_lock);
 		r = radeon_cs_handle_lockup(rdev, r);
@@ -580,97 +557,6 @@ out:
 	return r;
 }
 
-int radeon_cs_finish_pages(struct radeon_cs_parser *p)
-{
-	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
-	int i;
-	int size = PAGE_SIZE;
-
-	for (i = ibc->last_copied_page + 1; i <= ibc->last_page_index; i++) {
-		if (i == ibc->last_page_index) {
-			size = (ibc->length_dw * 4) % PAGE_SIZE;
-			if (size == 0)
-				size = PAGE_SIZE;
-		}
-		
-		if (DRM_COPY_FROM_USER(p->ib.ptr + (i * (PAGE_SIZE/4)),
-				       ibc->user_ptr + (i * PAGE_SIZE),
-				       size))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-static int radeon_cs_update_pages(struct radeon_cs_parser *p, int pg_idx)
-{
-	int new_page;
-	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
-	int i;
-	int size = PAGE_SIZE;
-	bool copy1 = (p->rdev && (p->rdev->flags & RADEON_IS_AGP)) ?
-		false : true;
-
-	for (i = ibc->last_copied_page + 1; i < pg_idx; i++) {
-		if (DRM_COPY_FROM_USER(p->ib.ptr + (i * (PAGE_SIZE/4)),
-				       ibc->user_ptr + (i * PAGE_SIZE),
-				       PAGE_SIZE)) {
-			p->parser_error = -EFAULT;
-			return 0;
-		}
-	}
-
-	if (pg_idx == ibc->last_page_index) {
-		size = (ibc->length_dw * 4) % PAGE_SIZE;
-		if (size == 0)
-			size = PAGE_SIZE;
-	}
-
-	new_page = ibc->kpage_idx[0] < ibc->kpage_idx[1] ? 0 : 1;
-	if (copy1)
-		ibc->kpage[new_page] = p->ib.ptr + (pg_idx * (PAGE_SIZE / 4));
-
-	if (DRM_COPY_FROM_USER(ibc->kpage[new_page],
-			       ibc->user_ptr + (pg_idx * PAGE_SIZE),
-			       size)) {
-		p->parser_error = -EFAULT;
-		return 0;
-	}
-
-	/* copy to IB for non single case */
-	if (!copy1)
-		memcpy((void *)(p->ib.ptr+(pg_idx*(PAGE_SIZE/4))), ibc->kpage[new_page], size);
-
-	ibc->last_copied_page = pg_idx;
-	ibc->kpage_idx[new_page] = pg_idx;
-
-	return new_page;
-}
-
-u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
-{
-	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
-	u32 pg_idx, pg_offset;
-	u32 idx_value = 0;
-	int new_page;
-
-	pg_idx = (idx * 4) / PAGE_SIZE;
-	pg_offset = (idx * 4) % PAGE_SIZE;
-
-	if (ibc->kpage_idx[0] == pg_idx)
-		return ibc->kpage[0][pg_offset/4];
-	if (ibc->kpage_idx[1] == pg_idx)
-		return ibc->kpage[1][pg_offset/4];
-
-	new_page = radeon_cs_update_pages(p, pg_idx);
-	if (new_page < 0) {
-		p->parser_error = new_page;
-		return 0;
-	}
-
-	idx_value = ibc->kpage[new_page][pg_offset/4];
-	return idx_value;
-}
-
 /**
  * radeon_cs_packet_parse() - parse cp packet and point ib index to next packet
  * @parser:	parser structure holding parsing context.
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 841d0e09be3e..61dbdd938133 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -101,6 +101,12 @@ static const char radeon_family_name[][16] = {
 	"LAST",
 };
 
+#if defined(CONFIG_VGA_SWITCHEROO)
+bool radeon_is_px(void);
+#else
+static inline bool radeon_is_px(void) { return false; }
+#endif
+
 /**
  * radeon_program_register_sequence - program an array of registers.
  *
@@ -1076,7 +1082,10 @@ static bool radeon_switcheroo_quirk_long_wakeup(struct pci_dev *pdev)
 static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
+
+	if (radeon_is_px() && state == VGA_SWITCHEROO_OFF)
+		return;
+
 	if (state == VGA_SWITCHEROO_ON) {
 		unsigned d3_delay = dev->pdev->d3_delay;
 
@@ -1087,7 +1096,7 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		if (d3_delay < 20 && radeon_switcheroo_quirk_long_wakeup(pdev))
 			dev->pdev->d3_delay = 20;
 
-		radeon_resume_kms(dev);
+		radeon_resume_kms(dev, true, true);
 
 		dev->pdev->d3_delay = d3_delay;
 
@@ -1097,7 +1106,7 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		printk(KERN_INFO "radeon: switched off\n");
 		drm_kms_helper_poll_disable(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		radeon_suspend_kms(dev, pmm);
+		radeon_suspend_kms(dev, true, true);
 		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
 	}
 }
@@ -1147,6 +1156,7 @@ int radeon_device_init(struct radeon_device *rdev,
 {
 	int r, i;
 	int dma_bits;
+	bool runtime = false;
 
 	rdev->shutdown = false;
 	rdev->dev = &pdev->dev;
@@ -1293,7 +1303,14 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
 	vga_client_register(rdev->pdev, rdev, NULL, radeon_vga_set_decode);
-	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, false);
+
+	if (radeon_runtime_pm == 1)
+		runtime = true;
+	if ((radeon_runtime_pm == -1) && radeon_is_px())
+		runtime = true;
+	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, runtime);
+	if (runtime)
+		vga_switcheroo_init_domain_pm_ops(rdev->dev, &rdev->vga_pm_domain);
 
 	r = radeon_init(rdev);
 	if (r)
@@ -1383,7 +1400,7 @@ void radeon_device_fini(struct radeon_device *rdev)
  * Returns 0 for success or an error on failure.
  * Called at driver suspend.
  */
-int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
+int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 {
 	struct radeon_device *rdev;
 	struct drm_crtc *crtc;
@@ -1394,9 +1411,7 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	if (dev == NULL || dev->dev_private == NULL) {
 		return -ENODEV;
 	}
-	if (state.event == PM_EVENT_PRETHAW) {
-		return 0;
-	}
+
 	rdev = dev->dev_private;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
@@ -1455,14 +1470,17 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	radeon_agp_suspend(rdev);
 
 	pci_save_state(dev->pdev);
-	if (state.event == PM_EVENT_SUSPEND) {
+	if (suspend) {
 		/* Shut down the device */
 		pci_disable_device(dev->pdev);
 		pci_set_power_state(dev->pdev, PCI_D3hot);
 	}
-	console_lock();
-	radeon_fbdev_set_suspend(rdev, 1);
-	console_unlock();
+
+	if (fbcon) {
+		console_lock();
+		radeon_fbdev_set_suspend(rdev, 1);
+		console_unlock();
+	}
 	return 0;
 }
 
@@ -1475,7 +1493,7 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
  * Returns 0 for success or an error on failure.
  * Called at driver resume.
  */
-int radeon_resume_kms(struct drm_device *dev)
+int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 {
 	struct drm_connector *connector;
 	struct radeon_device *rdev = dev->dev_private;
@@ -1484,12 +1502,17 @@ int radeon_resume_kms(struct drm_device *dev)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	console_lock();
-	pci_set_power_state(dev->pdev, PCI_D0);
-	pci_restore_state(dev->pdev);
-	if (pci_enable_device(dev->pdev)) {
-		console_unlock();
-		return -1;
+	if (fbcon) {
+		console_lock();
+	}
+	if (resume) {
+		pci_set_power_state(dev->pdev, PCI_D0);
+		pci_restore_state(dev->pdev);
+		if (pci_enable_device(dev->pdev)) {
+			if (fbcon)
+				console_unlock();
+			return -1;
+		}
 	}
 	/* resume AGP if in use */
 	radeon_agp_resume(rdev);
@@ -1502,9 +1525,11 @@ int radeon_resume_kms(struct drm_device *dev)
 	radeon_pm_resume(rdev);
 	radeon_restore_bios_scratch_regs(rdev);
 
-	radeon_fbdev_set_suspend(rdev, 0);
-	console_unlock();
-
+	if (fbcon) {
+		radeon_fbdev_set_suspend(rdev, 0);
+		console_unlock();
+	}
+       
 	/* init dig PHYs, disp eng pll */
 	if (rdev->is_atom_bios) {
 		radeon_atom_encoder_init(rdev);
@@ -1549,6 +1574,14 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	int resched;
 
 	down_write(&rdev->exclusive_lock);
+
+	if (!rdev->needs_reset) {
+		up_write(&rdev->exclusive_lock);
+		return 0;
+	}
+
+	rdev->needs_reset = false;
+
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 0d1aa050d41d..0e52cc532c26 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -30,6 +30,7 @@
 #include "atom.h"
 #include <asm/div64.h>
 
+#include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
 
@@ -494,11 +495,55 @@ unlock_free:
 	return r;
 }
 
+static int
+radeon_crtc_set_config(struct drm_mode_set *set)
+{
+	struct drm_device *dev;
+	struct radeon_device *rdev;
+	struct drm_crtc *crtc;
+	bool active = false;
+	int ret;
+
+	if (!set || !set->crtc)
+		return -EINVAL;
+
+	dev = set->crtc->dev;
+
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_crtc_helper_set_config(set);
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+		if (crtc->enabled)
+			active = true;
+
+	pm_runtime_mark_last_busy(dev->dev);
+
+	rdev = dev->dev_private;
+	/* if we have active crtcs and we don't have a power ref,
+	   take the current one */
+	if (active && !rdev->have_disp_power_ref) {
+		rdev->have_disp_power_ref = true;
+		return ret;
+	}
+	/* if we have no active crtcs, then drop the power ref
+	   we got before */
+	if (!active && rdev->have_disp_power_ref) {
+		pm_runtime_put_autosuspend(dev->dev);
+		rdev->have_disp_power_ref = false;
+	}
+
+	/* drop the power reference we got coming in here */
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
 static const struct drm_crtc_funcs radeon_crtc_funcs = {
 	.cursor_set = radeon_crtc_cursor_set,
 	.cursor_move = radeon_crtc_cursor_move,
 	.gamma_set = radeon_crtc_gamma_set,
-	.set_config = drm_crtc_helper_set_config,
+	.set_config = radeon_crtc_set_config,
 	.destroy = radeon_crtc_destroy,
 	.page_flip = radeon_crtc_page_flip,
 };
@@ -1178,6 +1223,12 @@ static struct drm_prop_enum_list radeon_audio_enum_list[] =
 	{ RADEON_AUDIO_AUTO, "auto" },
 };
 
+/* XXX support different dither options? spatial, temporal, both, etc. */
+static struct drm_prop_enum_list radeon_dither_enum_list[] =
+{	{ RADEON_FMT_DITHER_DISABLE, "off" },
+	{ RADEON_FMT_DITHER_ENABLE, "on" },
+};
+
 static int radeon_modeset_create_props(struct radeon_device *rdev)
 {
 	int sz;
@@ -1234,6 +1285,12 @@ static int radeon_modeset_create_props(struct radeon_device *rdev)
 					 "audio",
 					 radeon_audio_enum_list, sz);
 
+	sz = ARRAY_SIZE(radeon_dither_enum_list);
+	rdev->mode_info.dither_property =
+		drm_property_create_enum(rdev->ddev, 0,
+					 "dither",
+					 radeon_dither_enum_list, sz);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 22f685827b7e..dfd4149a43b6 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -36,8 +36,9 @@
 #include <drm/drm_pciids.h>
 #include <linux/console.h>
 #include <linux/module.h>
-
-
+#include <linux/pm_runtime.h>
+#include <linux/vga_switcheroo.h>
+#include "drm_crtc_helper.h"
 /*
  * KMS wrapper.
  * - 2.0.0 - initial interface
@@ -87,8 +88,8 @@ void radeon_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv);
 void radeon_driver_preclose_kms(struct drm_device *dev,
 				struct drm_file *file_priv);
-int radeon_suspend_kms(struct drm_device *dev, pm_message_t state);
-int radeon_resume_kms(struct drm_device *dev);
+int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon);
+int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
 u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc);
 int radeon_enable_vblank_kms(struct drm_device *dev, int crtc);
 void radeon_disable_vblank_kms(struct drm_device *dev, int crtc);
@@ -136,9 +137,11 @@ void radeon_debugfs_cleanup(struct drm_minor *minor);
 #if defined(CONFIG_VGA_SWITCHEROO)
 void radeon_register_atpx_handler(void);
 void radeon_unregister_atpx_handler(void);
+bool radeon_is_px(void);
 #else
 static inline void radeon_register_atpx_handler(void) {}
 static inline void radeon_unregister_atpx_handler(void) {}
+static inline bool radeon_is_px(void) { return false; }
 #endif
 
 int radeon_no_wb;
@@ -161,6 +164,7 @@ int radeon_lockup_timeout = 10000;
 int radeon_fastfb = 0;
 int radeon_dpm = -1;
 int radeon_aspm = -1;
+int radeon_runtime_pm = -1;
 
 MODULE_PARM_DESC(no_wb, "Disable AGP writeback for scratch registers");
 module_param_named(no_wb, radeon_no_wb, int, 0444);
@@ -222,6 +226,9 @@ module_param_named(dpm, radeon_dpm, int, 0444);
 MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(aspm, radeon_aspm, int, 0444);
 
+MODULE_PARM_DESC(runpm, "PX runtime pm (1 = force enable, 0 = disable, -1 = PX only default)");
+module_param_named(runpm, radeon_runtime_pm, int, 0444);
+
 static struct pci_device_id pciidlist[] = {
 	radeon_PCI_IDS
 };
@@ -258,6 +265,7 @@ static int radeon_resume(struct drm_device *dev)
 	return 0;
 }
 
+
 static const struct file_operations radeon_driver_old_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -352,25 +360,144 @@ radeon_pci_remove(struct pci_dev *pdev)
 	drm_put_dev(dev);
 }
 
-static int
-radeon_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+static int radeon_pmops_suspend(struct device *dev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
-	return radeon_suspend_kms(dev, state);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_suspend_kms(drm_dev, true, true);
 }
 
-static int
-radeon_pci_resume(struct pci_dev *pdev)
+static int radeon_pmops_resume(struct device *dev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
-	return radeon_resume_kms(dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_resume_kms(drm_dev, true, true);
 }
 
+static int radeon_pmops_freeze(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_suspend_kms(drm_dev, false, true);
+}
+
+static int radeon_pmops_thaw(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	return radeon_resume_kms(drm_dev, false, true);
+}
+
+static int radeon_pmops_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
+
+	if (radeon_runtime_pm == 0)
+		return -EINVAL;
+
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+	drm_kms_helper_poll_disable(drm_dev);
+	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
+
+	ret = radeon_suspend_kms(drm_dev, false, false);
+	pci_save_state(pdev);
+	pci_disable_device(pdev);
+	pci_set_power_state(pdev, PCI_D3cold);
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+
+	return 0;
+}
+
+static int radeon_pmops_runtime_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
+
+	if (radeon_runtime_pm == 0)
+		return -EINVAL;
+
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+	pci_set_master(pdev);
+
+	ret = radeon_resume_kms(drm_dev, false, false);
+	drm_kms_helper_poll_enable(drm_dev);
+	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
+	return 0;
+}
+
+static int radeon_pmops_runtime_idle(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct drm_crtc *crtc;
+
+	if (radeon_runtime_pm == 0)
+		return -EBUSY;
+
+	/* are we PX enabled? */
+	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
+		DRM_DEBUG_DRIVER("failing to power off - not px\n");
+		return -EBUSY;
+	}
+
+	list_for_each_entry(crtc, &drm_dev->mode_config.crtc_list, head) {
+		if (crtc->enabled) {
+			DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
+			return -EBUSY;
+		}
+	}
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_autosuspend(dev);
+	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
+	return 1;
+}
+
+long radeon_drm_ioctl(struct file *filp,
+		      unsigned int cmd, unsigned long arg)
+{
+	struct drm_file *file_priv = filp->private_data;
+	struct drm_device *dev;
+	long ret;
+	dev = file_priv->minor->dev;
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_ioctl(filp, cmd, arg);
+	
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
+
+static const struct dev_pm_ops radeon_pm_ops = {
+	.suspend = radeon_pmops_suspend,
+	.resume = radeon_pmops_resume,
+	.freeze = radeon_pmops_freeze,
+	.thaw = radeon_pmops_thaw,
+	.poweroff = radeon_pmops_freeze,
+	.restore = radeon_pmops_resume,
+	.runtime_suspend = radeon_pmops_runtime_suspend,
+	.runtime_resume = radeon_pmops_runtime_resume,
+	.runtime_idle = radeon_pmops_runtime_idle,
+};
+
 static const struct file_operations radeon_driver_kms_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.release = drm_release,
-	.unlocked_ioctl = drm_ioctl,
+	.unlocked_ioctl = radeon_drm_ioctl,
 	.mmap = radeon_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
@@ -379,6 +506,15 @@ static const struct file_operations radeon_driver_kms_fops = {
 #endif
 };
 
+
+static void
+radeon_pci_shutdown(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+
+	radeon_driver_unload_kms(dev);
+}
+
 static struct drm_driver kms_driver = {
 	.driver_features =
 	    DRIVER_USE_AGP |
@@ -391,8 +527,6 @@ static struct drm_driver kms_driver = {
 	.postclose = radeon_driver_postclose_kms,
 	.lastclose = radeon_driver_lastclose_kms,
 	.unload = radeon_driver_unload_kms,
-	.suspend = radeon_suspend_kms,
-	.resume = radeon_resume_kms,
 	.get_vblank_counter = radeon_get_vblank_counter_kms,
 	.enable_vblank = radeon_enable_vblank_kms,
 	.disable_vblank = radeon_disable_vblank_kms,
@@ -449,8 +583,8 @@ static struct pci_driver radeon_kms_pci_driver = {
 	.id_table = pciidlist,
 	.probe = radeon_pci_probe,
 	.remove = radeon_pci_remove,
-	.suspend = radeon_pci_suspend,
-	.resume = radeon_pci_resume,
+	.driver.pm = &radeon_pm_ops,
+	.shutdown = radeon_pci_shutdown,
 };
 
 static int __init radeon_init(void)
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index b369d42f7de5..543dcfae7e6f 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -113,6 +113,9 @@
 #define DRIVER_MINOR		33
 #define DRIVER_PATCHLEVEL	0
 
+long radeon_drm_ioctl(struct file *filp,
+		      unsigned int cmd, unsigned long arg);
+
 /* The rest of the file is DEPRECATED! */
 #ifdef CONFIG_DRM_RADEON_UMS
 
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index ddb8f8e04eb5..b8f68b2c47d4 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -190,10 +190,8 @@ void radeon_fence_process(struct radeon_device *rdev, int ring)
 		}
 	} while (atomic64_xchg(&rdev->fence_drv[ring].last_seq, seq) > seq);
 
-	if (wake) {
-		rdev->fence_drv[ring].last_activity = jiffies;
+	if (wake)
 		wake_up_all(&rdev->fence_queue);
-	}
 }
 
 /**
@@ -212,13 +210,13 @@ static void radeon_fence_destroy(struct kref *kref)
 }
 
 /**
- * radeon_fence_seq_signaled - check if a fence sequeuce number has signaled
+ * radeon_fence_seq_signaled - check if a fence sequence number has signaled
  *
  * @rdev: radeon device pointer
  * @seq: sequence number
  * @ring: ring index the fence is associated with
  *
- * Check if the last singled fence sequnce number is >= the requested
+ * Check if the last signaled fence sequnce number is >= the requested
  * sequence number (all asics).
  * Returns true if the fence has signaled (current fence value
  * is >= requested value) or false if it has not (current fence
@@ -263,113 +261,131 @@ bool radeon_fence_signaled(struct radeon_fence *fence)
 }
 
 /**
- * radeon_fence_wait_seq - wait for a specific sequence number
+ * radeon_fence_any_seq_signaled - check if any sequence number is signaled
  *
  * @rdev: radeon device pointer
- * @target_seq: sequence number we want to wait for
- * @ring: ring index the fence is associated with
+ * @seq: sequence numbers
+ *
+ * Check if the last signaled fence sequnce number is >= the requested
+ * sequence number (all asics).
+ * Returns true if any has signaled (current value is >= requested value)
+ * or false if it has not. Helper function for radeon_fence_wait_seq.
+ */
+static bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
+{
+	unsigned i;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (seq[i] && radeon_fence_seq_signaled(rdev, seq[i], i))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * radeon_fence_wait_seq - wait for a specific sequence numbers
+ *
+ * @rdev: radeon device pointer
+ * @target_seq: sequence number(s) we want to wait for
  * @intr: use interruptable sleep
  * @lock_ring: whether the ring should be locked or not
  *
- * Wait for the requested sequence number to be written (all asics).
+ * Wait for the requested sequence number(s) to be written by any ring
+ * (all asics).  Sequnce number array is indexed by ring id.
  * @intr selects whether to use interruptable (true) or non-interruptable
  * (false) sleep when waiting for the sequence number.  Helper function
- * for radeon_fence_wait(), et al.
+ * for radeon_fence_wait_*().
  * Returns 0 if the sequence number has passed, error for all other cases.
- * -EDEADLK is returned when a GPU lockup has been detected and the ring is
- * marked as not ready so no further jobs get scheduled until a successful
- * reset.
+ * -EDEADLK is returned when a GPU lockup has been detected.
  */
-static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 target_seq,
-				 unsigned ring, bool intr, bool lock_ring)
+static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 *target_seq,
+				 bool intr, bool lock_ring)
 {
-	unsigned long timeout, last_activity;
-	uint64_t seq;
-	unsigned i;
+	uint64_t last_seq[RADEON_NUM_RINGS];
 	bool signaled;
-	int r;
+	int i, r;
 
-	while (target_seq > atomic64_read(&rdev->fence_drv[ring].last_seq)) {
-		if (!rdev->ring[ring].ready) {
-			return -EBUSY;
+	while (!radeon_fence_any_seq_signaled(rdev, target_seq)) {
+
+		/* Save current sequence values, used to check for GPU lockups */
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			if (!target_seq[i])
+				continue;
+
+			last_seq[i] = atomic64_read(&rdev->fence_drv[i].last_seq);
+			trace_radeon_fence_wait_begin(rdev->ddev, target_seq[i]);
+			radeon_irq_kms_sw_irq_get(rdev, i);
 		}
 
-		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
-		if (time_after(rdev->fence_drv[ring].last_activity, timeout)) {
-			/* the normal case, timeout is somewhere before last_activity */
-			timeout = rdev->fence_drv[ring].last_activity - timeout;
-		} else {
-			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
-			 * anyway we will just wait for the minimum amount and then check for a lockup
-			 */
-			timeout = 1;
-		}
-		seq = atomic64_read(&rdev->fence_drv[ring].last_seq);
-		/* Save current last activity valuee, used to check for GPU lockups */
-		last_activity = rdev->fence_drv[ring].last_activity;
-
-		trace_radeon_fence_wait_begin(rdev->ddev, seq);
-		radeon_irq_kms_sw_irq_get(rdev, ring);
 		if (intr) {
-			r = wait_event_interruptible_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_seq_signaled(rdev, target_seq, ring)),
-				timeout);
-                } else {
-			r = wait_event_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_seq_signaled(rdev, target_seq, ring)),
-				timeout);
+			r = wait_event_interruptible_timeout(rdev->fence_queue, (
+				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq))
+				 || rdev->needs_reset), RADEON_FENCE_JIFFIES_TIMEOUT);
+		} else {
+			r = wait_event_timeout(rdev->fence_queue, (
+				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq))
+				 || rdev->needs_reset), RADEON_FENCE_JIFFIES_TIMEOUT);
 		}
-		radeon_irq_kms_sw_irq_put(rdev, ring);
-		if (unlikely(r < 0)) {
+
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			if (!target_seq[i])
+				continue;
+
+			radeon_irq_kms_sw_irq_put(rdev, i);
+			trace_radeon_fence_wait_end(rdev->ddev, target_seq[i]);
+		}
+
+		if (unlikely(r < 0))
 			return r;
-		}
-		trace_radeon_fence_wait_end(rdev->ddev, seq);
 
 		if (unlikely(!signaled)) {
+			if (rdev->needs_reset)
+				return -EDEADLK;
+
 			/* we were interrupted for some reason and fence
 			 * isn't signaled yet, resume waiting */
-			if (r) {
+			if (r)
 				continue;
+
+			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+				if (!target_seq[i])
+					continue;
+
+				if (last_seq[i] != atomic64_read(&rdev->fence_drv[i].last_seq))
+					break;
 			}
 
-			/* check if sequence value has changed since last_activity */
-			if (seq != atomic64_read(&rdev->fence_drv[ring].last_seq)) {
+			if (i != RADEON_NUM_RINGS)
 				continue;
-			}
 
-			if (lock_ring) {
+			if (lock_ring)
 				mutex_lock(&rdev->ring_lock);
+
+			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+				if (!target_seq[i])
+					continue;
+
+				if (radeon_ring_is_lockup(rdev, i, &rdev->ring[i]))
+					break;
 			}
 
-			/* test if somebody else has already decided that this is a lockup */
-			if (last_activity != rdev->fence_drv[ring].last_activity) {
-				if (lock_ring) {
-					mutex_unlock(&rdev->ring_lock);
-				}
-				continue;
-			}
-
-			if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
+			if (i < RADEON_NUM_RINGS) {
 				/* good news we believe it's a lockup */
-				dev_warn(rdev->dev, "GPU lockup (waiting for 0x%016llx last fence id 0x%016llx)\n",
-					 target_seq, seq);
+				dev_warn(rdev->dev, "GPU lockup (waiting for "
+					 "0x%016llx last fence id 0x%016llx on"
+					 " ring %d)\n",
+					 target_seq[i], last_seq[i], i);
 
-				/* change last activity so nobody else think there is a lockup */
-				for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-					rdev->fence_drv[i].last_activity = jiffies;
-				}
-
-				/* mark the ring as not ready any more */
-				rdev->ring[ring].ready = false;
-				if (lock_ring) {
+				/* remember that we need an reset */
+				rdev->needs_reset = true;
+				if (lock_ring)
 					mutex_unlock(&rdev->ring_lock);
-				}
+				wake_up_all(&rdev->fence_queue);
 				return -EDEADLK;
 			}
 
-			if (lock_ring) {
+			if (lock_ring)
 				mutex_unlock(&rdev->ring_lock);
-			}
 		}
 	}
 	return 0;
@@ -388,6 +404,7 @@ static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 target_seq,
  */
 int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 {
+	uint64_t seq[RADEON_NUM_RINGS] = {};
 	int r;
 
 	if (fence == NULL) {
@@ -395,150 +412,18 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 		return -EINVAL;
 	}
 
-	r = radeon_fence_wait_seq(fence->rdev, fence->seq,
-				  fence->ring, intr, true);
-	if (r) {
+	seq[fence->ring] = fence->seq;
+	if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
+		return 0;
+
+	r = radeon_fence_wait_seq(fence->rdev, seq, intr, true);
+	if (r)
 		return r;
-	}
+
 	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
 	return 0;
 }
 
-static bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
-{
-	unsigned i;
-
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (seq[i] && radeon_fence_seq_signaled(rdev, seq[i], i)) {
-			return true;
-		}
-	}
-	return false;
-}
-
-/**
- * radeon_fence_wait_any_seq - wait for a sequence number on any ring
- *
- * @rdev: radeon device pointer
- * @target_seq: sequence number(s) we want to wait for
- * @intr: use interruptable sleep
- *
- * Wait for the requested sequence number(s) to be written by any ring
- * (all asics).  Sequnce number array is indexed by ring id.
- * @intr selects whether to use interruptable (true) or non-interruptable
- * (false) sleep when waiting for the sequence number.  Helper function
- * for radeon_fence_wait_any(), et al.
- * Returns 0 if the sequence number has passed, error for all other cases.
- */
-static int radeon_fence_wait_any_seq(struct radeon_device *rdev,
-				     u64 *target_seq, bool intr)
-{
-	unsigned long timeout, last_activity, tmp;
-	unsigned i, ring = RADEON_NUM_RINGS;
-	bool signaled;
-	int r;
-
-	for (i = 0, last_activity = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (!target_seq[i]) {
-			continue;
-		}
-
-		/* use the most recent one as indicator */
-		if (time_after(rdev->fence_drv[i].last_activity, last_activity)) {
-			last_activity = rdev->fence_drv[i].last_activity;
-		}
-
-		/* For lockup detection just pick the lowest ring we are
-		 * actively waiting for
-		 */
-		if (i < ring) {
-			ring = i;
-		}
-	}
-
-	/* nothing to wait for ? */
-	if (ring == RADEON_NUM_RINGS) {
-		return -ENOENT;
-	}
-
-	while (!radeon_fence_any_seq_signaled(rdev, target_seq)) {
-		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
-		if (time_after(last_activity, timeout)) {
-			/* the normal case, timeout is somewhere before last_activity */
-			timeout = last_activity - timeout;
-		} else {
-			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
-			 * anyway we will just wait for the minimum amount and then check for a lockup
-			 */
-			timeout = 1;
-		}
-
-		trace_radeon_fence_wait_begin(rdev->ddev, target_seq[ring]);
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			if (target_seq[i]) {
-				radeon_irq_kms_sw_irq_get(rdev, i);
-			}
-		}
-		if (intr) {
-			r = wait_event_interruptible_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq)),
-				timeout);
-		} else {
-			r = wait_event_timeout(rdev->fence_queue,
-				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq)),
-				timeout);
-		}
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			if (target_seq[i]) {
-				radeon_irq_kms_sw_irq_put(rdev, i);
-			}
-		}
-		if (unlikely(r < 0)) {
-			return r;
-		}
-		trace_radeon_fence_wait_end(rdev->ddev, target_seq[ring]);
-
-		if (unlikely(!signaled)) {
-			/* we were interrupted for some reason and fence
-			 * isn't signaled yet, resume waiting */
-			if (r) {
-				continue;
-			}
-
-			mutex_lock(&rdev->ring_lock);
-			for (i = 0, tmp = 0; i < RADEON_NUM_RINGS; ++i) {
-				if (time_after(rdev->fence_drv[i].last_activity, tmp)) {
-					tmp = rdev->fence_drv[i].last_activity;
-				}
-			}
-			/* test if somebody else has already decided that this is a lockup */
-			if (last_activity != tmp) {
-				last_activity = tmp;
-				mutex_unlock(&rdev->ring_lock);
-				continue;
-			}
-
-			if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
-				/* good news we believe it's a lockup */
-				dev_warn(rdev->dev, "GPU lockup (waiting for 0x%016llx)\n",
-					 target_seq[ring]);
-
-				/* change last activity so nobody else think there is a lockup */
-				for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-					rdev->fence_drv[i].last_activity = jiffies;
-				}
-
-				/* mark the ring as not ready any more */
-				rdev->ring[ring].ready = false;
-				mutex_unlock(&rdev->ring_lock);
-				return -EDEADLK;
-			}
-			mutex_unlock(&rdev->ring_lock);
-		}
-	}
-	return 0;
-}
-
 /**
  * radeon_fence_wait_any - wait for a fence to signal on any ring
  *
@@ -557,7 +442,7 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 			  bool intr)
 {
 	uint64_t seq[RADEON_NUM_RINGS];
-	unsigned i;
+	unsigned i, num_rings = 0;
 	int r;
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -567,15 +452,19 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 			continue;
 		}
 
-		if (fences[i]->seq == RADEON_FENCE_SIGNALED_SEQ) {
-			/* something was allready signaled */
-			return 0;
-		}
-
 		seq[i] = fences[i]->seq;
+		++num_rings;
+
+		/* test if something was allready signaled */
+		if (seq[i] == RADEON_FENCE_SIGNALED_SEQ)
+			return 0;
 	}
 
-	r = radeon_fence_wait_any_seq(rdev, seq, intr);
+	/* nothing to wait for ? */
+	if (num_rings == 0)
+		return -ENOENT;
+
+	r = radeon_fence_wait_seq(rdev, seq, intr, true);
 	if (r) {
 		return r;
 	}
@@ -594,15 +483,15 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
  */
 int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring)
 {
-	uint64_t seq;
+	uint64_t seq[RADEON_NUM_RINGS] = {};
 
-	seq = atomic64_read(&rdev->fence_drv[ring].last_seq) + 1ULL;
-	if (seq >= rdev->fence_drv[ring].sync_seq[ring]) {
+	seq[ring] = atomic64_read(&rdev->fence_drv[ring].last_seq) + 1ULL;
+	if (seq[ring] >= rdev->fence_drv[ring].sync_seq[ring]) {
 		/* nothing to wait for, last_seq is
 		   already the last emited fence */
 		return -ENOENT;
 	}
-	return radeon_fence_wait_seq(rdev, seq, ring, false, false);
+	return radeon_fence_wait_seq(rdev, seq, false, false);
 }
 
 /**
@@ -617,14 +506,15 @@ int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring)
  */
 int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring)
 {
-	uint64_t seq = rdev->fence_drv[ring].sync_seq[ring];
+	uint64_t seq[RADEON_NUM_RINGS] = {};
 	int r;
 
-	r = radeon_fence_wait_seq(rdev, seq, ring, false, false);
+	seq[ring] = rdev->fence_drv[ring].sync_seq[ring];
+	r = radeon_fence_wait_seq(rdev, seq, false, false);
 	if (r) {
-		if (r == -EDEADLK) {
+		if (r == -EDEADLK)
 			return -EDEADLK;
-		}
+
 		dev_err(rdev->dev, "error waiting for ring[%d] to become idle (%d)\n",
 			ring, r);
 	}
@@ -826,7 +716,6 @@ static void radeon_fence_driver_init_ring(struct radeon_device *rdev, int ring)
 	for (i = 0; i < RADEON_NUM_RINGS; ++i)
 		rdev->fence_drv[ring].sync_seq[i] = 0;
 	atomic64_set(&rdev->fence_drv[ring].last_seq, 0);
-	rdev->fence_drv[ring].last_activity = jiffies;
 	rdev->fence_drv[ring].initialized = false;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index b990b1a2bd50..8a83b89d4709 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -607,8 +607,8 @@ static int radeon_vm_evict(struct radeon_device *rdev, struct radeon_vm *vm)
  */
 int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 {
-	unsigned pd_size, pts_size;
-	u64 *pd_addr;
+	unsigned pd_size, pd_entries, pts_size;
+	struct radeon_ib ib;
 	int r;
 
 	if (vm == NULL) {
@@ -619,8 +619,10 @@ int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 		return 0;
 	}
 
-retry:
 	pd_size = radeon_vm_directory_size(rdev);
+	pd_entries = radeon_vm_num_pdes(rdev);
+
+retry:
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
 			     &vm->page_directory, pd_size,
 			     RADEON_VM_PTB_ALIGN_SIZE, false);
@@ -637,9 +639,31 @@ retry:
 	vm->pd_gpu_addr = radeon_sa_bo_gpu_addr(vm->page_directory);
 
 	/* Initially clear the page directory */
-	pd_addr = radeon_sa_bo_cpu_addr(vm->page_directory);
-	memset(pd_addr, 0, pd_size);
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib,
+			  NULL, pd_entries * 2 + 64);
+	if (r) {
+		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
+		return r;
+	}
 
+	ib.length_dw = 0;
+
+	radeon_asic_vm_set_page(rdev, &ib, vm->pd_gpu_addr,
+				0, pd_entries, 0, 0);
+
+	radeon_ib_sync_to(&ib, vm->fence);
+	r = radeon_ib_schedule(rdev, &ib, NULL);
+	if (r) {
+		radeon_ib_free(rdev, &ib);
+		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
+		return r;
+	}
+	radeon_fence_unref(&vm->fence);
+	vm->fence = radeon_fence_ref(ib.fence);
+	radeon_ib_free(rdev, &ib);
+	radeon_fence_unref(&vm->last_flush);
+
+	/* allocate page table array */
 	pts_size = radeon_vm_num_pdes(rdev) * sizeof(struct radeon_sa_bo *);
 	vm->page_tables = kzalloc(pts_size, GFP_KERNEL);
 
@@ -913,6 +937,26 @@ uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr)
 	return result;
 }
 
+/**
+ * radeon_vm_page_flags - translate page flags to what the hw uses
+ *
+ * @flags: flags comming from userspace
+ *
+ * Translate the flags the userspace ABI uses to hw flags.
+ */
+static uint32_t radeon_vm_page_flags(uint32_t flags)
+{
+        uint32_t hw_flags = 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_VALID) ? R600_PTE_VALID : 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_READABLE) ? R600_PTE_READABLE : 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_WRITEABLE) ? R600_PTE_WRITEABLE : 0;
+        if (flags & RADEON_VM_PAGE_SYSTEM) {
+                hw_flags |= R600_PTE_SYSTEM;
+                hw_flags |= (flags & RADEON_VM_PAGE_SNOOPED) ? R600_PTE_SNOOPED : 0;
+        }
+        return hw_flags;
+}
+
 /**
  * radeon_vm_update_pdes - make sure that page directory is valid
  *
@@ -974,7 +1018,11 @@ retry:
 			if (count) {
 				radeon_asic_vm_set_page(rdev, ib, last_pde,
 							last_pt, count, incr,
-							RADEON_VM_PAGE_VALID);
+							R600_PTE_VALID);
+
+				count *= RADEON_VM_PTE_COUNT;
+				radeon_asic_vm_set_page(rdev, ib, last_pt, 0,
+							count, 0, 0);
 			}
 
 			count = 1;
@@ -987,8 +1035,11 @@ retry:
 
 	if (count) {
 		radeon_asic_vm_set_page(rdev, ib, last_pde, last_pt, count,
-					incr, RADEON_VM_PAGE_VALID);
+					incr, R600_PTE_VALID);
 
+		count *= RADEON_VM_PTE_COUNT;
+		radeon_asic_vm_set_page(rdev, ib, last_pt, 0,
+					count, 0, 0);
 	}
 
 	return 0;
@@ -1082,7 +1133,6 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 			    struct radeon_bo *bo,
 			    struct ttm_mem_reg *mem)
 {
-	unsigned ridx = rdev->asic->vm.pt_ring_index;
 	struct radeon_ib ib;
 	struct radeon_bo_va *bo_va;
 	unsigned nptes, npdes, ndw;
@@ -1151,11 +1201,14 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 	/* reserve space for pde addresses */
 	ndw += npdes * 2;
 
+	/* reserve space for clearing new page tables */
+	ndw += npdes * 2 * RADEON_VM_PTE_COUNT;
+
 	/* update too big for an IB */
 	if (ndw > 0xfffff)
 		return -ENOMEM;
 
-	r = radeon_ib_get(rdev, ridx, &ib, NULL, ndw * 4);
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib, NULL, ndw * 4);
 	ib.length_dw = 0;
 
 	r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
@@ -1165,7 +1218,7 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 	}
 
 	radeon_vm_update_ptes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset,
-			      addr, bo_va->flags);
+			      addr, radeon_vm_page_flags(bo_va->flags));
 
 	radeon_ib_sync_to(&ib, vm->fence);
 	r = radeon_ib_schedule(rdev, &ib, NULL);
diff --git a/drivers/gpu/drm/radeon/radeon_ioc32.c b/drivers/gpu/drm/radeon/radeon_ioc32.c
index c180df8e84db..bdb0f93e73bc 100644
--- a/drivers/gpu/drm/radeon/radeon_ioc32.c
+++ b/drivers/gpu/drm/radeon/radeon_ioc32.c
@@ -418,7 +418,7 @@ long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long
 	if (nr < DRM_COMMAND_BASE)
 		return drm_compat_ioctl(filp, cmd, arg);
 
-	ret = drm_ioctl(filp, cmd, arg);
+	ret = radeon_drm_ioctl(filp, cmd, arg);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index cc9e8482cf30..ec6240b00469 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -32,6 +32,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+#include <linux/pm_runtime.h>
+
 #define RADEON_WAIT_IDLE_TIMEOUT 200
 
 /**
@@ -47,8 +49,12 @@ irqreturn_t radeon_driver_irq_handler_kms(DRM_IRQ_ARGS)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	struct radeon_device *rdev = dev->dev_private;
+	irqreturn_t ret;
 
-	return radeon_irq_process(rdev);
+	ret = radeon_irq_process(rdev);
+	if (ret == IRQ_HANDLED)
+		pm_runtime_mark_last_busy(dev->dev);
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index d6b36766e8c9..bb8710531a1b 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -32,7 +32,7 @@
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
-
+#include <linux/pm_runtime.h>
 /**
  * radeon_driver_unload_kms - Main unload function for KMS.
  *
@@ -50,9 +50,14 @@ int radeon_driver_unload_kms(struct drm_device *dev)
 
 	if (rdev == NULL)
 		return 0;
+
 	if (rdev->rmmio == NULL)
 		goto done_free;
+
+	pm_runtime_get_sync(dev->dev);
+
 	radeon_acpi_fini(rdev);
+	
 	radeon_modeset_fini(rdev);
 	radeon_device_fini(rdev);
 
@@ -125,9 +130,20 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 				"Error during ACPI methods call\n");
 	}
 
+	if (radeon_runtime_pm != 0) {
+		pm_runtime_use_autosuspend(dev->dev);
+		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
+		pm_runtime_set_active(dev->dev);
+		pm_runtime_allow(dev->dev);
+		pm_runtime_mark_last_busy(dev->dev);
+		pm_runtime_put_autosuspend(dev->dev);
+	}
+
 out:
 	if (r)
 		radeon_driver_unload_kms(dev);
+
+
 	return r;
 }
 
@@ -475,9 +491,14 @@ void radeon_driver_lastclose_kms(struct drm_device *dev)
 int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 {
 	struct radeon_device *rdev = dev->dev_private;
+	int r;
 
 	file_priv->driver_priv = NULL;
 
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
+
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN) {
 		struct radeon_fpriv *fpriv;
@@ -506,6 +527,9 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 		file_priv->driver_priv = fpriv;
 	}
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index ef63d3f00b2f..8b4e712c1e5c 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -249,6 +249,8 @@ struct radeon_mode_info {
 	struct drm_property *underscan_vborder_property;
 	/* audio */
 	struct drm_property *audio_property;
+	/* FMT dithering */
+	struct drm_property *dither_property;
 	/* hardcoded DFP edid from BIOS */
 	struct edid *bios_hardcoded_edid;
 	int bios_hardcoded_edid_size;
@@ -479,6 +481,11 @@ enum radeon_connector_audio {
 	RADEON_AUDIO_AUTO = 2
 };
 
+enum radeon_connector_dither {
+	RADEON_FMT_DITHER_DISABLE = 0,
+	RADEON_FMT_DITHER_ENABLE = 1,
+};
+
 struct radeon_connector {
 	struct drm_connector base;
 	uint32_t connector_id;
@@ -498,6 +505,7 @@ struct radeon_connector {
 	struct radeon_router router;
 	struct radeon_i2c_chan *router_bus;
 	enum radeon_connector_audio audio;
+	enum radeon_connector_dither dither;
 };
 
 struct radeon_framebuffer {
@@ -850,6 +858,12 @@ void radeon_legacy_tv_mode_set(struct drm_encoder *encoder,
 			       struct drm_display_mode *mode,
 			       struct drm_display_mode *adjusted_mode);
 
+/* fmt blocks */
+void avivo_program_fmt(struct drm_encoder *encoder);
+void dce3_program_fmt(struct drm_encoder *encoder);
+void dce4_program_fmt(struct drm_encoder *encoder);
+void dce8_program_fmt(struct drm_encoder *encoder);
+
 /* fbdev layer */
 int radeon_fbdev_init(struct radeon_device *rdev);
 void radeon_fbdev_fini(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index ac07ad1d4f8c..2baa0fa75e36 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -508,17 +508,21 @@ static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev,
 	} else if (strncmp("auto", buf, strlen("auto")) == 0) {
 		level = RADEON_DPM_FORCED_LEVEL_AUTO;
 	} else {
-		mutex_unlock(&rdev->pm.mutex);
 		count = -EINVAL;
 		goto fail;
 	}
 	if (rdev->asic->dpm.force_performance_level) {
+		if (rdev->pm.dpm.thermal_active) {
+			count = -EINVAL;
+			goto fail;
+		}
 		ret = radeon_dpm_force_performance_level(rdev, level);
 		if (ret)
 			count = -EINVAL;
 	}
-	mutex_unlock(&rdev->pm.mutex);
 fail:
+	mutex_unlock(&rdev->pm.mutex);
+
 	return count;
 }
 
@@ -881,11 +885,12 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 		}
 	}
 
-	printk("switching from power state:\n");
-	radeon_dpm_print_power_state(rdev, rdev->pm.dpm.current_ps);
-	printk("switching to power state:\n");
-	radeon_dpm_print_power_state(rdev, rdev->pm.dpm.requested_ps);
-
+	if (radeon_dpm == 1) {
+		printk("switching from power state:\n");
+		radeon_dpm_print_power_state(rdev, rdev->pm.dpm.current_ps);
+		printk("switching to power state:\n");
+		radeon_dpm_print_power_state(rdev, rdev->pm.dpm.requested_ps);
+	}
 	mutex_lock(&rdev->ddev->struct_mutex);
 	down_write(&rdev->pm.mclk_lock);
 	mutex_lock(&rdev->ring_lock);
@@ -918,12 +923,16 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 	radeon_dpm_post_set_power_state(rdev);
 
 	if (rdev->asic->dpm.force_performance_level) {
-		if (rdev->pm.dpm.thermal_active)
+		if (rdev->pm.dpm.thermal_active) {
+			enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
 			/* force low perf level for thermal */
 			radeon_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_LOW);
-		else
-			/* otherwise, enable auto */
-			radeon_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
+			/* save the user's level */
+			rdev->pm.dpm.forced_level = level;
+		} else {
+			/* otherwise, user selected level */
+			radeon_dpm_force_performance_level(rdev, rdev->pm.dpm.forced_level);
+		}
 	}
 
 done:
@@ -1176,7 +1185,8 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev)
 	mutex_lock(&rdev->pm.mutex);
 	radeon_dpm_init(rdev);
 	rdev->pm.dpm.current_ps = rdev->pm.dpm.requested_ps = rdev->pm.dpm.boot_ps;
-	radeon_dpm_print_power_states(rdev);
+	if (radeon_dpm == 1)
+		radeon_dpm_print_power_states(rdev);
 	radeon_dpm_setup_asic(rdev);
 	ret = radeon_dpm_enable(rdev);
 	mutex_unlock(&rdev->pm.mutex);
@@ -1238,6 +1248,23 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_RV670:
 	case CHIP_RS780:
 	case CHIP_RS880:
+	case CHIP_CAYMAN:
+	case CHIP_ARUBA:
+	case CHIP_BONAIRE:
+	case CHIP_KABINI:
+	case CHIP_KAVERI:
+		/* DPM requires the RLC, RV770+ dGPU requires SMC */
+		if (!rdev->rlc_fw)
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if ((rdev->family >= CHIP_RV770) &&
+			 (!(rdev->flags & RADEON_IS_IGP)) &&
+			 (!rdev->smc_fw))
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if (radeon_dpm == 1)
+			rdev->pm.pm_method = PM_METHOD_DPM;
+		else
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		break;
 	case CHIP_RV770:
 	case CHIP_RV730:
 	case CHIP_RV710:
@@ -1253,16 +1280,11 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_BARTS:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
-	case CHIP_CAYMAN:
-	case CHIP_ARUBA:
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
 	case CHIP_HAINAN:
-	case CHIP_BONAIRE:
-	case CHIP_KABINI:
-	case CHIP_KAVERI:
 		/* DPM requires the RLC, RV770+ dGPU requires SMC */
 		if (!rdev->rlc_fw)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
@@ -1270,10 +1292,10 @@ int radeon_pm_init(struct radeon_device *rdev)
 			 (!(rdev->flags & RADEON_IS_IGP)) &&
 			 (!rdev->smc_fw))
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
-		else if (radeon_dpm == 1)
-			rdev->pm.pm_method = PM_METHOD_DPM;
-		else
+		else if (radeon_dpm == 0)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else
+			rdev->pm.pm_method = PM_METHOD_DPM;
 		break;
 	default:
 		/* default to profile method */
diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h
index f7e367815964..811bca691b36 100644
--- a/drivers/gpu/drm/radeon/radeon_trace.h
+++ b/drivers/gpu/drm/radeon/radeon_trace.h
@@ -47,6 +47,30 @@ TRACE_EVENT(radeon_cs,
 		      __entry->fences)
 );
 
+TRACE_EVENT(radeon_vm_set_page,
+	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
+		     uint32_t incr, uint32_t flags),
+	    TP_ARGS(pe, addr, count, incr, flags),
+	    TP_STRUCT__entry(
+			     __field(u64, pe)
+			     __field(u64, addr)
+			     __field(u32, count)
+			     __field(u32, incr)
+			     __field(u32, flags)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pe = pe;
+			   __entry->addr = addr;
+			   __entry->count = count;
+			   __entry->incr = incr;
+			   __entry->flags = flags;
+			   ),
+	    TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%08x, count=%u",
+		      __entry->pe, __entry->addr, __entry->incr,
+		      __entry->flags, __entry->count)
+);
+
 DECLARE_EVENT_CLASS(radeon_fence_request,
 
 	    TP_PROTO(struct drm_device *dev, u32 seqno),
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index a0f11856ddde..234b2a3b8add 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -240,6 +240,8 @@ void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)
 		if (handle != 0 && rdev->uvd.filp[i] == filp) {
 			struct radeon_fence *fence;
 
+			radeon_uvd_note_usage(rdev);
+
 			r = radeon_uvd_get_destroy_msg(rdev,
 				R600_RING_TYPE_UVD_INDEX, handle, &fence);
 			if (r) {
@@ -619,7 +621,7 @@ static int radeon_uvd_send_msg(struct radeon_device *rdev,
 	if (r) 
 		goto err;
 
-	r = radeon_ib_get(rdev, ring, &ib, NULL, 16);
+	r = radeon_ib_get(rdev, ring, &ib, NULL, 64);
 	if (r)
 		goto err;
 
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 6acba8017b9a..76cc8d3aafec 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -153,6 +153,70 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	return RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING;
 }
 
+void avivo_program_fmt(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int bpc = 0;
+	u32 tmp = 0;
+	enum radeon_connector_dither dither = RADEON_FMT_DITHER_DISABLE;
+
+	if (connector) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		bpc = radeon_get_monitor_bpc(connector);
+		dither = radeon_connector->dither;
+	}
+
+	/* LVDS FMT is set up by atom */
+	if (radeon_encoder->devices & ATOM_DEVICE_LCD_SUPPORT)
+		return;
+
+	if (bpc == 0)
+		return;
+
+	switch (bpc) {
+	case 6:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= AVIVO_TMDS_BIT_DEPTH_CONTROL_SPATIAL_DITHER_EN;
+		else
+			tmp |= AVIVO_TMDS_BIT_DEPTH_CONTROL_TRUNCATE_EN;
+		break;
+	case 8:
+		if (dither == RADEON_FMT_DITHER_ENABLE)
+			/* XXX sort out optimal dither settings */
+			tmp |= (AVIVO_TMDS_BIT_DEPTH_CONTROL_SPATIAL_DITHER_EN |
+				AVIVO_TMDS_BIT_DEPTH_CONTROL_SPATIAL_DITHER_DEPTH);
+		else
+			tmp |= (AVIVO_TMDS_BIT_DEPTH_CONTROL_TRUNCATE_EN |
+				AVIVO_TMDS_BIT_DEPTH_CONTROL_TRUNCATE_DEPTH);
+		break;
+	case 10:
+	default:
+		/* not needed */
+		break;
+	}
+
+	switch (radeon_encoder->encoder_id) {
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1:
+		WREG32(AVIVO_TMDSA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	case ENCODER_OBJECT_ID_INTERNAL_LVTM1:
+		WREG32(AVIVO_LVTMA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
+		WREG32(AVIVO_DVOA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	case ENCODER_OBJECT_ID_INTERNAL_DDI:
+		WREG32(AVIVO_DDIA_BIT_DEPTH_CONTROL, tmp);
+		break;
+	default:
+		break;
+	}
+}
+
 void rs600_pm_misc(struct radeon_device *rdev)
 {
 	int requested_index = rdev->pm.requested_power_state_index;
diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c
index 5811d277a36a..26633a025252 100644
--- a/drivers/gpu/drm/radeon/rv6xx_dpm.c
+++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c
@@ -407,9 +407,9 @@ static void rv6xx_enable_engine_feedback_and_reference_sync(struct radeon_device
 	WREG32_P(SPLL_CNTL_MODE, SPLL_DIV_SYNC, ~SPLL_DIV_SYNC);
 }
 
-static u64 rv6xx_clocks_per_unit(u32 unit)
+static u32 rv6xx_clocks_per_unit(u32 unit)
 {
-	u64 tmp = 1 << (2 * unit);
+	u32 tmp = 1 << (2 * unit);
 
 	return tmp;
 }
@@ -417,7 +417,7 @@ static u64 rv6xx_clocks_per_unit(u32 unit)
 static u32 rv6xx_scale_count_given_unit(struct radeon_device *rdev,
 					u32 unscaled_count, u32 unit)
 {
-	u32 count_per_unit = (u32)rv6xx_clocks_per_unit(unit);
+	u32 count_per_unit = rv6xx_clocks_per_unit(unit);
 
 	return (unscaled_count + count_per_unit - 1) / count_per_unit;
 }
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index c354c1094967..2acfe561796f 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -78,11 +78,6 @@ extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_
 extern u32 evergreen_get_number_of_dram_channels(struct radeon_device *rdev);
 extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
 extern bool evergreen_is_display_hung(struct radeon_device *rdev);
-extern void si_dma_vm_set_page(struct radeon_device *rdev,
-			       struct radeon_ib *ib,
-			       uint64_t pe,
-			       uint64_t addr, unsigned count,
-			       uint32_t incr, uint32_t flags);
 static void si_enable_gui_idle_interrupt(struct radeon_device *rdev,
 					 bool enable);
 
@@ -4662,61 +4657,6 @@ static void si_vm_decode_fault(struct radeon_device *rdev,
 	       block, mc_id);
 }
 
-/**
- * si_vm_set_page - update the page tables using the CP
- *
- * @rdev: radeon_device pointer
- * @ib: indirect buffer to fill with commands
- * @pe: addr of the page entry
- * @addr: dst addr to write into pe
- * @count: number of page entries to update
- * @incr: increase next addr by incr bytes
- * @flags: access flags
- *
- * Update the page tables using the CP (SI).
- */
-void si_vm_set_page(struct radeon_device *rdev,
-		    struct radeon_ib *ib,
-		    uint64_t pe,
-		    uint64_t addr, unsigned count,
-		    uint32_t incr, uint32_t flags)
-{
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	uint64_t value;
-	unsigned ndw;
-
-	if (rdev->asic->vm.pt_ring_index == RADEON_RING_TYPE_GFX_INDEX) {
-		while (count) {
-			ndw = 2 + count * 2;
-			if (ndw > 0x3FFE)
-				ndw = 0x3FFE;
-
-			ib->ptr[ib->length_dw++] = PACKET3(PACKET3_WRITE_DATA, ndw);
-			ib->ptr[ib->length_dw++] = (WRITE_DATA_ENGINE_SEL(0) |
-					WRITE_DATA_DST_SEL(1));
-			ib->ptr[ib->length_dw++] = pe;
-			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-			for (; ndw > 2; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
-				addr += incr;
-				value |= r600_flags;
-				ib->ptr[ib->length_dw++] = value;
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-			}
-		}
-	} else {
-		/* DMA */
-		si_dma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
-	}
-}
-
 void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
 	struct radeon_ring *ring = &rdev->ring[ridx];
@@ -5361,52 +5301,53 @@ void si_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
 	if (buffer == NULL)
 		return;
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_BEGIN_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_BEGIN_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CONTEXT_CONTROL, 1);
-	buffer[count++] = 0x80000000;
-	buffer[count++] = 0x80000000;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CONTEXT_CONTROL, 1));
+	buffer[count++] = cpu_to_le32(0x80000000);
+	buffer[count++] = cpu_to_le32(0x80000000);
 
 	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
 		for (ext = sect->section; ext->extent != NULL; ++ext) {
 			if (sect->id == SECT_CONTEXT) {
-				buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count);
-				buffer[count++] = ext->reg_index - 0xa000;
+				buffer[count++] =
+					cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count));
+				buffer[count++] = cpu_to_le32(ext->reg_index - 0xa000);
 				for (i = 0; i < ext->reg_count; i++)
-					buffer[count++] = ext->extent[i];
+					buffer[count++] = cpu_to_le32(ext->extent[i]);
 			} else {
 				return;
 			}
 		}
 	}
 
-	buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, 1);
-	buffer[count++] = PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, 1));
+	buffer[count++] = cpu_to_le32(PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
-		buffer[count++] = 0x2a00126a;
+		buffer[count++] = cpu_to_le32(0x2a00126a);
 		break;
 	case CHIP_VERDE:
-		buffer[count++] = 0x0000124a;
+		buffer[count++] = cpu_to_le32(0x0000124a);
 		break;
 	case CHIP_OLAND:
-		buffer[count++] = 0x00000082;
+		buffer[count++] = cpu_to_le32(0x00000082);
 		break;
 	case CHIP_HAINAN:
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	default:
-		buffer[count++] = 0x00000000;
+		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	}
 
-	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
-	buffer[count++] = PACKET3_PREAMBLE_END_CLEAR_STATE;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
+	buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE);
 
-	buffer[count++] = PACKET3(PACKET3_CLEAR_STATE, 0);
-	buffer[count++] = 0;
+	buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CLEAR_STATE, 0));
+	buffer[count++] = cpu_to_le32(0);
 }
 
 static void si_init_pg(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index 49909d23dfce..8e8f46133532 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -24,6 +24,7 @@
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
+#include "radeon_trace.h"
 #include "sid.h"
 
 u32 si_gpu_check_soft_reset(struct radeon_device *rdev);
@@ -75,11 +76,12 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			uint64_t addr, unsigned count,
 			uint32_t incr, uint32_t flags)
 {
-	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
 
-	if (flags & RADEON_VM_PAGE_SYSTEM) {
+	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
+
+	if (flags & R600_PTE_SYSTEM) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -90,16 +92,10 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = pe;
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
 			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-				if (flags & RADEON_VM_PAGE_SYSTEM) {
-					value = radeon_vm_map_gart(rdev, addr);
-					value &= 0xFFFFFFFFFFFFF000ULL;
-				} else if (flags & RADEON_VM_PAGE_VALID) {
-					value = addr;
-				} else {
-					value = 0;
-				}
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
 				addr += incr;
-				value |= r600_flags;
+				value |= flags;
 				ib->ptr[ib->length_dw++] = value;
 				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
@@ -110,7 +106,7 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			if (ndw > 0xFFFFE)
 				ndw = 0xFFFFE;
 
-			if (flags & RADEON_VM_PAGE_VALID)
+			if (flags & R600_PTE_VALID)
 				value = addr;
 			else
 				value = 0;
@@ -118,7 +114,7 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
 			ib->ptr[ib->length_dw++] = pe; /* dst addr */
 			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = flags; /* mask */
 			ib->ptr[ib->length_dw++] = 0;
 			ib->ptr[ib->length_dw++] = value; /* value */
 			ib->ptr[ib->length_dw++] = upper_32_bits(value);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 9ace28702c76..a24ada406046 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3589,7 +3589,12 @@ static void si_program_display_gap(struct radeon_device *rdev)
 		WREG32(DCCG_DISP_SLOW_SELECT_REG, tmp);
 	}
 
-	si_notify_smc_display_change(rdev, rdev->pm.dpm.new_active_crtc_count > 0);
+	/* Setting this to false forces the performance state to low if the crtcs are disabled.
+	 * This can be a problem on PowerXpress systems or if you want to use the card
+	 * for offscreen rendering or compute if there are no crtcs enabled.  Set it to
+	 * true for now so that performance scales even if the displays are off.
+	 */
+	si_notify_smc_display_change(rdev, true /*rdev->pm.dpm.new_active_crtc_count > 0*/);
 }
 
 static void si_enable_spread_spectrum(struct radeon_device *rdev, bool enable)
@@ -4553,7 +4558,7 @@ static int si_init_smc_table(struct radeon_device *rdev)
 		table->systemFlags |= PPSMC_SYSTEMFLAG_GDDR5;
 
 	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_REVERT_GPIO5_POLARITY)
-		table->systemFlags |= PPSMC_EXTRAFLAGS_AC2DC_GPIO5_POLARITY_HIGH;
+		table->extraFlags |= PPSMC_EXTRAFLAGS_AC2DC_GPIO5_POLARITY_HIGH;
 
 	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_VRHOT_GPIO_CONFIGURABLE) {
 		table->systemFlags |= PPSMC_SYSTEMFLAG_REGULATOR_HOT_PROG_GPIO;
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 52d2ab6b67a0..5691a7c30686 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -478,7 +478,7 @@
 #define		STATE3_MASK				(0x1f << 15)
 #define		STATE3_SHIFT				15
 
-#define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x2808
+#define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x28e8
 #define		TRAIN_DONE_D0      			(1 << 30)
 #define		TRAIN_DONE_D1      			(1 << 31)
 
@@ -683,6 +683,51 @@
  * bit5 = 176.4 kHz
  * bit6 = 192 kHz
  */
+
+#define AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC         0x37
+#       define VIDEO_LIPSYNC(x)                           (((x) & 0xff) << 0)
+#       define AUDIO_LIPSYNC(x)                           (((x) & 0xff) << 8)
+/* VIDEO_LIPSYNC, AUDIO_LIPSYNC
+ * 0   = invalid
+ * x   = legal delay value
+ * 255 = sync not supported
+ */
+#define AZ_F0_CODEC_PIN_CONTROL_RESPONSE_HBR             0x38
+#       define HBR_CAPABLE                                (1 << 0) /* enabled by default */
+
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO0               0x3a
+#       define MANUFACTURER_ID(x)                        (((x) & 0xffff) << 0)
+#       define PRODUCT_ID(x)                             (((x) & 0xffff) << 16)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO1               0x3b
+#       define SINK_DESCRIPTION_LEN(x)                   (((x) & 0xff) << 0)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO2               0x3c
+#       define PORT_ID0(x)                               (((x) & 0xffffffff) << 0)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO3               0x3d
+#       define PORT_ID1(x)                               (((x) & 0xffffffff) << 0)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO4               0x3e
+#       define DESCRIPTION0(x)                           (((x) & 0xff) << 0)
+#       define DESCRIPTION1(x)                           (((x) & 0xff) << 8)
+#       define DESCRIPTION2(x)                           (((x) & 0xff) << 16)
+#       define DESCRIPTION3(x)                           (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO5               0x3f
+#       define DESCRIPTION4(x)                           (((x) & 0xff) << 0)
+#       define DESCRIPTION5(x)                           (((x) & 0xff) << 8)
+#       define DESCRIPTION6(x)                           (((x) & 0xff) << 16)
+#       define DESCRIPTION7(x)                           (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO6               0x40
+#       define DESCRIPTION8(x)                           (((x) & 0xff) << 0)
+#       define DESCRIPTION9(x)                           (((x) & 0xff) << 8)
+#       define DESCRIPTION10(x)                          (((x) & 0xff) << 16)
+#       define DESCRIPTION11(x)                          (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO7               0x41
+#       define DESCRIPTION12(x)                          (((x) & 0xff) << 0)
+#       define DESCRIPTION13(x)                          (((x) & 0xff) << 8)
+#       define DESCRIPTION14(x)                          (((x) & 0xff) << 16)
+#       define DESCRIPTION15(x)                          (((x) & 0xff) << 24)
+#define AZ_F0_CODEC_PIN_CONTROL_SINK_INFO8               0x42
+#       define DESCRIPTION16(x)                          (((x) & 0xff) << 0)
+#       define DESCRIPTION17(x)                          (((x) & 0xff) << 8)
+
 #define AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL          0x54
 #       define AUDIO_ENABLED                             (1 << 31)