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

* 'drm-core-next' of git://people.freedesktop.org/~airlied/linux: (290 commits)
  Revert "drm/ttm: add a way to bo_wait for either the last read or last write"
  Revert "drm/radeon/kms: add a new gem_wait ioctl with read/write flags"
  vmwgfx: Don't pass unused arguments to do_dirty functions
  vmwgfx: Emulate depth 32 framebuffers
  drm/radeon: Lower the severity of the radeon lockup messages.
  drm/i915/dp: Fix eDP on PCH DP on CPT/PPT
  drm/i915/dp: Introduce is_cpu_edp()
  drm/i915: use correct SPD type value
  drm/i915: fix ILK+ infoframe support
  drm/i915: add DP test request handling
  drm/i915: read full receiver capability field during DP hot plug
  drm/i915/dp: Remove eDP special cases from bandwidth checks
  drm/i915/dp: Fix the math in intel_dp_link_required
  drm/i915/panel: Always record the backlight level again (but cleverly)
  i915: Move i915_read/write out of line
  drm/i915: remove transcoder PLL mashing from mode_set per specs
  drm/i915: if transcoder disable fails, say which
  drm/i915: set watermarks for third pipe on IVB
  drm/i915: export a CPT mode set verification function
  drm/i915: fix transcoder PLL select masking
  ...

35 files changed, 869 insertions, 1035 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index c4ffa14fb2f..ed406e8404a 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -39,7 +39,7 @@
 
 static void evergreen_gpu_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
-static void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
+void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
 
 void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev)
 {
@@ -935,6 +935,9 @@ int evergreen_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(VM_CONTEXT1_CNTL, 0);
 
 	evergreen_pcie_gart_tlb_flush(rdev);
+	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
+		 (unsigned)(rdev->mc.gtt_size >> 20),
+		 (unsigned long long)rdev->gart.table_addr);
 	rdev->gart.ready = true;
 	return 0;
 }
@@ -2586,7 +2589,7 @@ int evergreen_irq_set(struct radeon_device *rdev)
 	return 0;
 }
 
-static inline void evergreen_irq_ack(struct radeon_device *rdev)
+static void evergreen_irq_ack(struct radeon_device *rdev)
 {
 	u32 tmp;
 
@@ -2697,7 +2700,7 @@ void evergreen_irq_suspend(struct radeon_device *rdev)
 	r600_rlc_stop(rdev);
 }
 
-static inline u32 evergreen_get_ih_wptr(struct radeon_device *rdev)
+static u32 evergreen_get_ih_wptr(struct radeon_device *rdev)
 {
 	u32 wptr, tmp;
 
@@ -3003,8 +3006,7 @@ static int evergreen_startup(struct radeon_device *rdev)
 	int r;
 
 	/* enable pcie gen2 link */
-	if (!ASIC_IS_DCE5(rdev))
-		evergreen_pcie_gen2_enable(rdev);
+	evergreen_pcie_gen2_enable(rdev);
 
 	if (ASIC_IS_DCE5(rdev)) {
 		if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw || !rdev->mc_fw) {
@@ -3041,7 +3043,7 @@ static int evergreen_startup(struct radeon_device *rdev)
 
 	r = evergreen_blit_init(rdev);
 	if (r) {
-		evergreen_blit_fini(rdev);
+		r600_blit_fini(rdev);
 		rdev->asic->copy = NULL;
 		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
 	}
@@ -3107,45 +3109,14 @@ int evergreen_resume(struct radeon_device *rdev)
 
 int evergreen_suspend(struct radeon_device *rdev)
 {
-	int r;
-
 	/* FIXME: we should wait for ring to be empty */
 	r700_cp_stop(rdev);
 	rdev->cp.ready = false;
 	evergreen_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
 	evergreen_pcie_gart_disable(rdev);
+	r600_blit_suspend(rdev);
 
-	/* unpin shaders bo */
-	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-	if (likely(r == 0)) {
-		radeon_bo_unpin(rdev->r600_blit.shader_obj);
-		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-	}
-
-	return 0;
-}
-
-int evergreen_copy_blit(struct radeon_device *rdev,
-			uint64_t src_offset,
-			uint64_t dst_offset,
-			unsigned num_gpu_pages,
-			struct radeon_fence *fence)
-{
-	int r;
-
-	mutex_lock(&rdev->r600_blit.mutex);
-	rdev->r600_blit.vb_ib = NULL;
-	r = evergreen_blit_prepare_copy(rdev, num_gpu_pages * RADEON_GPU_PAGE_SIZE);
-	if (r) {
-		if (rdev->r600_blit.vb_ib)
-			radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
-		mutex_unlock(&rdev->r600_blit.mutex);
-		return r;
-	}
-	evergreen_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages * RADEON_GPU_PAGE_SIZE);
-	evergreen_blit_done_copy(rdev, fence);
-	mutex_unlock(&rdev->r600_blit.mutex);
 	return 0;
 }
 
@@ -3257,7 +3228,7 @@ int evergreen_init(struct radeon_device *rdev)
 
 void evergreen_fini(struct radeon_device *rdev)
 {
-	evergreen_blit_fini(rdev);
+	r600_blit_fini(rdev);
 	r700_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
@@ -3273,7 +3244,7 @@ void evergreen_fini(struct radeon_device *rdev)
 	rdev->bios = NULL;
 }
 
-static void evergreen_pcie_gen2_enable(struct radeon_device *rdev)
+void evergreen_pcie_gen2_enable(struct radeon_device *rdev)
 {
 	u32 link_width_cntl, speed_cntl;
 
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index 2eb251858e7..dcf11bbc06d 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -56,7 +56,9 @@ set_render_target(struct radeon_device *rdev, int format,
 	if (h < 8)
 		h = 8;
 
-	cb_color_info = ((format << 2) | (1 << 24) | (1 << 8));
+	cb_color_info = CB_FORMAT(format) |
+		CB_SOURCE_FORMAT(CB_SF_EXPORT_NORM) |
+		CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
 	pitch = (w / 8) - 1;
 	slice = ((w * h) / 64) - 1;
 
@@ -67,7 +69,7 @@ set_render_target(struct radeon_device *rdev, int format,
 	radeon_ring_write(rdev, slice);
 	radeon_ring_write(rdev, 0);
 	radeon_ring_write(rdev, cb_color_info);
-	radeon_ring_write(rdev, (1 << 4));
+	radeon_ring_write(rdev, 0);
 	radeon_ring_write(rdev, (w - 1) | ((h - 1) << 16));
 	radeon_ring_write(rdev, 0);
 	radeon_ring_write(rdev, 0);
@@ -133,12 +135,16 @@ set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr)
 	u32 sq_vtx_constant_word2, sq_vtx_constant_word3;
 
 	/* high addr, stride */
-	sq_vtx_constant_word2 = ((upper_32_bits(gpu_addr) & 0xff) | (16 << 8));
+	sq_vtx_constant_word2 = SQ_VTXC_BASE_ADDR_HI(upper_32_bits(gpu_addr) & 0xff) |
+		SQ_VTXC_STRIDE(16);
 #ifdef __BIG_ENDIAN
-	sq_vtx_constant_word2 |= (2 << 30);
+	sq_vtx_constant_word2 |= SQ_VTXC_ENDIAN_SWAP(SQ_ENDIAN_8IN32);
 #endif
 	/* xyzw swizzles */
-	sq_vtx_constant_word3 = (0 << 3) | (1 << 6) | (2 << 9) | (3 << 12);
+	sq_vtx_constant_word3 = SQ_VTCX_SEL_X(SQ_SEL_X) |
+		SQ_VTCX_SEL_Y(SQ_SEL_Y) |
+		SQ_VTCX_SEL_Z(SQ_SEL_Z) |
+		SQ_VTCX_SEL_W(SQ_SEL_W);
 
 	radeon_ring_write(rdev, PACKET3(PACKET3_SET_RESOURCE, 8));
 	radeon_ring_write(rdev, 0x580);
@@ -149,7 +155,7 @@ set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr)
 	radeon_ring_write(rdev, 0);
 	radeon_ring_write(rdev, 0);
 	radeon_ring_write(rdev, 0);
-	radeon_ring_write(rdev, SQ_TEX_VTX_VALID_BUFFER << 30);
+	radeon_ring_write(rdev, S__SQ_CONSTANT_TYPE(SQ_TEX_VTX_VALID_BUFFER));
 
 	if ((rdev->family == CHIP_CEDAR) ||
 	    (rdev->family == CHIP_PALM) ||
@@ -176,14 +182,19 @@ set_tex_resource(struct radeon_device *rdev,
 	if (h < 1)
 		h = 1;
 
-	sq_tex_resource_word0 = (1 << 0); /* 2D */
+	sq_tex_resource_word0 = TEX_DIM(SQ_TEX_DIM_2D);
 	sq_tex_resource_word0 |= ((((pitch >> 3) - 1) << 6) |
 				  ((w - 1) << 18));
-	sq_tex_resource_word1 = ((h - 1) << 0) | (1 << 28);
+	sq_tex_resource_word1 = ((h - 1) << 0) |
+				TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
 	/* xyzw swizzles */
-	sq_tex_resource_word4 = (0 << 16) | (1 << 19) | (2 << 22) | (3 << 25);
+	sq_tex_resource_word4 = TEX_DST_SEL_X(SQ_SEL_X) |
+				TEX_DST_SEL_Y(SQ_SEL_Y) |
+				TEX_DST_SEL_Z(SQ_SEL_Z) |
+				TEX_DST_SEL_W(SQ_SEL_W);
 
-	sq_tex_resource_word7 = format | (SQ_TEX_VTX_VALID_TEXTURE << 30);
+	sq_tex_resource_word7 = format |
+		S__SQ_CONSTANT_TYPE(SQ_TEX_VTX_VALID_TEXTURE);
 
 	radeon_ring_write(rdev, PACKET3(PACKET3_SET_RESOURCE, 8));
 	radeon_ring_write(rdev, 0);
@@ -584,31 +595,6 @@ set_default_state(struct radeon_device *rdev)
 
 }
 
-static inline uint32_t i2f(uint32_t input)
-{
-	u32 result, i, exponent, fraction;
-
-	if ((input & 0x3fff) == 0)
-		result = 0; /* 0 is a special case */
-	else {
-		exponent = 140; /* exponent biased by 127; */
-		fraction = (input & 0x3fff) << 10; /* cheat and only
-						      handle numbers below 2^^15 */
-		for (i = 0; i < 14; i++) {
-			if (fraction & 0x800000)
-				break;
-			else {
-				fraction = fraction << 1; /* keep
-							     shifting left until top bit = 1 */
-				exponent = exponent - 1;
-			}
-		}
-		result = exponent << 23 | (fraction & 0x7fffff); /* mask
-								    off top bit; assumed 1 */
-	}
-	return result;
-}
-
 int evergreen_blit_init(struct radeon_device *rdev)
 {
 	u32 obj_size;
@@ -617,6 +603,24 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	u32 packet2s[16];
 	int num_packet2s = 0;
 
+	rdev->r600_blit.primitives.set_render_target = set_render_target;
+	rdev->r600_blit.primitives.cp_set_surface_sync = cp_set_surface_sync;
+	rdev->r600_blit.primitives.set_shaders = set_shaders;
+	rdev->r600_blit.primitives.set_vtx_resource = set_vtx_resource;
+	rdev->r600_blit.primitives.set_tex_resource = set_tex_resource;
+	rdev->r600_blit.primitives.set_scissors = set_scissors;
+	rdev->r600_blit.primitives.draw_auto = draw_auto;
+	rdev->r600_blit.primitives.set_default_state = set_default_state;
+
+	rdev->r600_blit.ring_size_common = 55; /* shaders + def state */
+	rdev->r600_blit.ring_size_common += 10; /* fence emit for VB IB */
+	rdev->r600_blit.ring_size_common += 5; /* done copy */
+	rdev->r600_blit.ring_size_common += 10; /* fence emit for done copy */
+
+	rdev->r600_blit.ring_size_per_loop = 74;
+
+	rdev->r600_blit.max_dim = 16384;
+
 	/* pin copy shader into vram if already initialized */
 	if (rdev->r600_blit.shader_obj)
 		goto done;
@@ -712,277 +716,3 @@ done:
 	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
 	return 0;
 }
-
-void evergreen_blit_fini(struct radeon_device *rdev)
-{
-	int r;
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
-	if (rdev->r600_blit.shader_obj == NULL)
-		return;
-	/* If we can't reserve the bo, unref should be enough to destroy
-	 * it when it becomes idle.
-	 */
-	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-	if (!r) {
-		radeon_bo_unpin(rdev->r600_blit.shader_obj);
-		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-	}
-	radeon_bo_unref(&rdev->r600_blit.shader_obj);
-}
-
-static int evergreen_vb_ib_get(struct radeon_device *rdev)
-{
-	int r;
-	r = radeon_ib_get(rdev, &rdev->r600_blit.vb_ib);
-	if (r) {
-		DRM_ERROR("failed to get IB for vertex buffer\n");
-		return r;
-	}
-
-	rdev->r600_blit.vb_total = 64*1024;
-	rdev->r600_blit.vb_used = 0;
-	return 0;
-}
-
-static void evergreen_vb_ib_put(struct radeon_device *rdev)
-{
-	radeon_fence_emit(rdev, rdev->r600_blit.vb_ib->fence);
-	radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
-}
-
-int evergreen_blit_prepare_copy(struct radeon_device *rdev, int size_bytes)
-{
-	int r;
-	int ring_size, line_size;
-	int max_size;
-	/* loops of emits + fence emit possible */
-	int dwords_per_loop = 74, num_loops;
-
-	r = evergreen_vb_ib_get(rdev);
-	if (r)
-		return r;
-
-	/* 8 bpp vs 32 bpp for xfer unit */
-	if (size_bytes & 3)
-		line_size = 8192;
-	else
-		line_size = 8192 * 4;
-
-	max_size = 8192 * line_size;
-
-	/* major loops cover the max size transfer */
-	num_loops = ((size_bytes + max_size) / max_size);
-	/* minor loops cover the extra non aligned bits */
-	num_loops += ((size_bytes % line_size) ? 1 : 0);
-	/* calculate number of loops correctly */
-	ring_size = num_loops * dwords_per_loop;
-	/* set default  + shaders */
-	ring_size += 55; /* shaders + def state */
-	ring_size += 10; /* fence emit for VB IB */
-	ring_size += 5; /* done copy */
-	ring_size += 10; /* fence emit for done copy */
-	r = radeon_ring_lock(rdev, ring_size);
-	if (r)
-		return r;
-
-	set_default_state(rdev); /* 36 */
-	set_shaders(rdev); /* 16 */
-	return 0;
-}
-
-void evergreen_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence)
-{
-	int r;
-
-	if (rdev->r600_blit.vb_ib)
-		evergreen_vb_ib_put(rdev);
-
-	if (fence)
-		r = radeon_fence_emit(rdev, fence);
-
-	radeon_ring_unlock_commit(rdev);
-}
-
-void evergreen_kms_blit_copy(struct radeon_device *rdev,
-			     u64 src_gpu_addr, u64 dst_gpu_addr,
-			     int size_bytes)
-{
-	int max_bytes;
-	u64 vb_gpu_addr;
-	u32 *vb;
-
-	DRM_DEBUG("emitting copy %16llx %16llx %d %d\n", src_gpu_addr, dst_gpu_addr,
-		  size_bytes, rdev->r600_blit.vb_used);
-	vb = (u32 *)(rdev->r600_blit.vb_ib->ptr + rdev->r600_blit.vb_used);
-	if ((size_bytes & 3) || (src_gpu_addr & 3) || (dst_gpu_addr & 3)) {
-		max_bytes = 8192;
-
-		while (size_bytes) {
-			int cur_size = size_bytes;
-			int src_x = src_gpu_addr & 255;
-			int dst_x = dst_gpu_addr & 255;
-			int h = 1;
-			src_gpu_addr = src_gpu_addr & ~255ULL;
-			dst_gpu_addr = dst_gpu_addr & ~255ULL;
-
-			if (!src_x && !dst_x) {
-				h = (cur_size / max_bytes);
-				if (h > 8192)
-					h = 8192;
-				if (h == 0)
-					h = 1;
-				else
-					cur_size = max_bytes;
-			} else {
-				if (cur_size > max_bytes)
-					cur_size = max_bytes;
-				if (cur_size > (max_bytes - dst_x))
-					cur_size = (max_bytes - dst_x);
-				if (cur_size > (max_bytes - src_x))
-					cur_size = (max_bytes - src_x);
-			}
-
-			if ((rdev->r600_blit.vb_used + 48) > rdev->r600_blit.vb_total) {
-				WARN_ON(1);
-			}
-
-			vb[0] = i2f(dst_x);
-			vb[1] = 0;
-			vb[2] = i2f(src_x);
-			vb[3] = 0;
-
-			vb[4] = i2f(dst_x);
-			vb[5] = i2f(h);
-			vb[6] = i2f(src_x);
-			vb[7] = i2f(h);
-
-			vb[8] = i2f(dst_x + cur_size);
-			vb[9] = i2f(h);
-			vb[10] = i2f(src_x + cur_size);
-			vb[11] = i2f(h);
-
-			/* src 10 */
-			set_tex_resource(rdev, FMT_8,
-					 src_x + cur_size, h, src_x + cur_size,
-					 src_gpu_addr);
-
-			/* 5 */
-			cp_set_surface_sync(rdev,
-					    PACKET3_TC_ACTION_ENA, (src_x + cur_size * h), src_gpu_addr);
-
-
-			/* dst 17 */
-			set_render_target(rdev, COLOR_8,
-					  dst_x + cur_size, h,
-					  dst_gpu_addr);
-
-			/* scissors 12 */
-			set_scissors(rdev, dst_x, 0, dst_x + cur_size, h);
-
-			/* 15 */
-			vb_gpu_addr = rdev->r600_blit.vb_ib->gpu_addr + rdev->r600_blit.vb_used;
-			set_vtx_resource(rdev, vb_gpu_addr);
-
-			/* draw 10 */
-			draw_auto(rdev);
-
-			/* 5 */
-			cp_set_surface_sync(rdev,
-					    PACKET3_CB_ACTION_ENA | PACKET3_CB0_DEST_BASE_ENA,
-					    cur_size * h, dst_gpu_addr);
-
-			vb += 12;
-			rdev->r600_blit.vb_used += 12 * 4;
-
-			src_gpu_addr += cur_size * h;
-			dst_gpu_addr += cur_size * h;
-			size_bytes -= cur_size * h;
-		}
-	} else {
-		max_bytes = 8192 * 4;
-
-		while (size_bytes) {
-			int cur_size = size_bytes;
-			int src_x = (src_gpu_addr & 255);
-			int dst_x = (dst_gpu_addr & 255);
-			int h = 1;
-			src_gpu_addr = src_gpu_addr & ~255ULL;
-			dst_gpu_addr = dst_gpu_addr & ~255ULL;
-
-			if (!src_x && !dst_x) {
-				h = (cur_size / max_bytes);
-				if (h > 8192)
-					h = 8192;
-				if (h == 0)
-					h = 1;
-				else
-					cur_size = max_bytes;
-			} else {
-				if (cur_size > max_bytes)
-					cur_size = max_bytes;
-				if (cur_size > (max_bytes - dst_x))
-					cur_size = (max_bytes - dst_x);
-				if (cur_size > (max_bytes - src_x))
-					cur_size = (max_bytes - src_x);
-			}
-
-			if ((rdev->r600_blit.vb_used + 48) > rdev->r600_blit.vb_total) {
-				WARN_ON(1);
-			}
-
-			vb[0] = i2f(dst_x / 4);
-			vb[1] = 0;
-			vb[2] = i2f(src_x / 4);
-			vb[3] = 0;
-
-			vb[4] = i2f(dst_x / 4);
-			vb[5] = i2f(h);
-			vb[6] = i2f(src_x / 4);
-			vb[7] = i2f(h);
-
-			vb[8] = i2f((dst_x + cur_size) / 4);
-			vb[9] = i2f(h);
-			vb[10] = i2f((src_x + cur_size) / 4);
-			vb[11] = i2f(h);
-
-			/* src 10 */
-			set_tex_resource(rdev, FMT_8_8_8_8,
-					 (src_x + cur_size) / 4,
-					 h, (src_x + cur_size) / 4,
-					 src_gpu_addr);
-			/* 5 */
-			cp_set_surface_sync(rdev,
-					    PACKET3_TC_ACTION_ENA, (src_x + cur_size * h), src_gpu_addr);
-
-			/* dst 17 */
-			set_render_target(rdev, COLOR_8_8_8_8,
-					  (dst_x + cur_size) / 4, h,
-					  dst_gpu_addr);
-
-			/* scissors 12  */
-			set_scissors(rdev, (dst_x / 4), 0, (dst_x + cur_size / 4), h);
-
-			/* Vertex buffer setup 15 */
-			vb_gpu_addr = rdev->r600_blit.vb_ib->gpu_addr + rdev->r600_blit.vb_used;
-			set_vtx_resource(rdev, vb_gpu_addr);
-
-			/* draw 10 */
-			draw_auto(rdev);
-
-			/* 5 */
-			cp_set_surface_sync(rdev,
-					    PACKET3_CB_ACTION_ENA | PACKET3_CB0_DEST_BASE_ENA,
-					    cur_size * h, dst_gpu_addr);
-
-			/* 74 ring dwords per loop */
-			vb += 12;
-			rdev->r600_blit.vb_used += 12 * 4;
-
-			src_gpu_addr += cur_size * h;
-			dst_gpu_addr += cur_size * h;
-			size_bytes -= cur_size * h;
-		}
-	}
-}
-
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index a134790903d..7fdfa8ea757 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -122,12 +122,6 @@ static void evergreen_cs_track_init(struct evergreen_cs_track *track)
 	track->db_s_write_bo = NULL;
 }
 
-static inline int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
-{
-	/* XXX fill in */
-	return 0;
-}
-
 static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 {
 	struct evergreen_cs_track *track = p->track;
@@ -236,28 +230,6 @@ static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
 }
 
 /**
- * evergreen_cs_packet_next_is_pkt3_nop() - test if next packet is packet3 nop for reloc
- * @parser:		parser structure holding parsing context.
- *
- * Check next packet is relocation packet3, do bo validation and compute
- * GPU offset using the provided start.
- **/
-static inline int evergreen_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
-{
-	struct radeon_cs_packet p3reloc;
-	int r;
-
-	r = evergreen_cs_packet_parse(p, &p3reloc, p->idx);
-	if (r) {
-		return 0;
-	}
-	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
-		return 0;
-	}
-	return 1;
-}
-
-/**
  * evergreen_cs_packet_next_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
  *
@@ -414,7 +386,7 @@ static int evergreen_cs_parse_packet0(struct radeon_cs_parser *p,
  * if register is safe. If register is not flag as safe this function
  * will test it against a list of register needind special handling.
  */
-static inline int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
+static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 {
 	struct evergreen_cs_track *track = (struct evergreen_cs_track *)p->track;
 	struct radeon_cs_reloc *reloc;
@@ -990,7 +962,7 @@ static inline int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u3
  * This function will check that the resource has valid field and that
  * the texture and mipmap bo object are big enough to cover this resource.
  */
-static inline int evergreen_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
+static int evergreen_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 						   struct radeon_bo *texture,
 						   struct radeon_bo *mipmap)
 {
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 7363d9dec90..b937c49054d 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -941,11 +941,15 @@
 #define	CB_COLOR0_SLICE					0x28c68
 #define	CB_COLOR0_VIEW					0x28c6c
 #define	CB_COLOR0_INFO					0x28c70
+#	define CB_FORMAT(x)				((x) << 2)
 #       define CB_ARRAY_MODE(x)                         ((x) << 8)
 #       define ARRAY_LINEAR_GENERAL                     0
 #       define ARRAY_LINEAR_ALIGNED                     1
 #       define ARRAY_1D_TILED_THIN1                     2
 #       define ARRAY_2D_TILED_THIN1                     4
+#	define CB_SOURCE_FORMAT(x)			((x) << 24)
+#	define CB_SF_EXPORT_FULL			0
+#	define CB_SF_EXPORT_NORM			1
 #define	CB_COLOR0_ATTRIB				0x28c74
 #define	CB_COLOR0_DIM					0x28c78
 /* only CB0-7 blocks have these regs */
@@ -1107,15 +1111,53 @@
 #define	CB_COLOR7_CLEAR_WORD3				0x28e3c
 
 #define SQ_TEX_RESOURCE_WORD0_0                         0x30000
+#	define TEX_DIM(x)				((x) << 0)
+#	define SQ_TEX_DIM_1D				0
+#	define SQ_TEX_DIM_2D				1
+#	define SQ_TEX_DIM_3D				2
+#	define SQ_TEX_DIM_CUBEMAP			3
+#	define SQ_TEX_DIM_1D_ARRAY			4
+#	define SQ_TEX_DIM_2D_ARRAY			5
+#	define SQ_TEX_DIM_2D_MSAA			6
+#	define SQ_TEX_DIM_2D_ARRAY_MSAA			7
 #define SQ_TEX_RESOURCE_WORD1_0                         0x30004
 #       define TEX_ARRAY_MODE(x)                        ((x) << 28)
 #define SQ_TEX_RESOURCE_WORD2_0                         0x30008
 #define SQ_TEX_RESOURCE_WORD3_0                         0x3000C
 #define SQ_TEX_RESOURCE_WORD4_0                         0x30010
+#	define TEX_DST_SEL_X(x)				((x) << 16)
+#	define TEX_DST_SEL_Y(x)				((x) << 19)
+#	define TEX_DST_SEL_Z(x)				((x) << 22)
+#	define TEX_DST_SEL_W(x)				((x) << 25)
+#	define SQ_SEL_X					0
+#	define SQ_SEL_Y					1
+#	define SQ_SEL_Z					2
+#	define SQ_SEL_W					3
+#	define SQ_SEL_0					4
+#	define SQ_SEL_1					5
 #define SQ_TEX_RESOURCE_WORD5_0                         0x30014
 #define SQ_TEX_RESOURCE_WORD6_0                         0x30018
 #define SQ_TEX_RESOURCE_WORD7_0                         0x3001c
 
+#define SQ_VTX_CONSTANT_WORD0_0				0x30000
+#define SQ_VTX_CONSTANT_WORD1_0				0x30004
+#define SQ_VTX_CONSTANT_WORD2_0				0x30008
+#	define SQ_VTXC_BASE_ADDR_HI(x)			((x) << 0)
+#	define SQ_VTXC_STRIDE(x)			((x) << 8)
+#	define SQ_VTXC_ENDIAN_SWAP(x)			((x) << 30)
+#	define SQ_ENDIAN_NONE				0
+#	define SQ_ENDIAN_8IN16				1
+#	define SQ_ENDIAN_8IN32				2
+#define SQ_VTX_CONSTANT_WORD3_0				0x3000C
+#	define SQ_VTCX_SEL_X(x)				((x) << 3)
+#	define SQ_VTCX_SEL_Y(x)				((x) << 6)
+#	define SQ_VTCX_SEL_Z(x)				((x) << 9)
+#	define SQ_VTCX_SEL_W(x)				((x) << 12)
+#define SQ_VTX_CONSTANT_WORD4_0				0x30010
+#define SQ_VTX_CONSTANT_WORD5_0                         0x30014
+#define SQ_VTX_CONSTANT_WORD6_0                         0x30018
+#define SQ_VTX_CONSTANT_WORD7_0                         0x3001c
+
 /* cayman 3D regs */
 #define CAYMAN_VGT_OFFCHIP_LDS_BASE			0x89B0
 #define CAYMAN_DB_EQAA					0x28804
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8c79ca97753..556b7bc3418 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -40,6 +40,7 @@ extern void evergreen_mc_program(struct radeon_device *rdev);
 extern void evergreen_irq_suspend(struct radeon_device *rdev);
 extern int evergreen_mc_init(struct radeon_device *rdev);
 extern void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev);
+extern void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
 
 #define EVERGREEN_PFP_UCODE_SIZE 1120
 #define EVERGREEN_PM4_UCODE_SIZE 1376
@@ -967,6 +968,9 @@ int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(VM_CONTEXT1_CNTL, 0);
 
 	cayman_pcie_gart_tlb_flush(rdev);
+	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
+		 (unsigned)(rdev->mc.gtt_size >> 20),
+		 (unsigned long long)rdev->gart.table_addr);
 	rdev->gart.ready = true;
 	return 0;
 }
@@ -1341,6 +1345,9 @@ static int cayman_startup(struct radeon_device *rdev)
 {
 	int r;
 
+	/* enable pcie gen2 link */
+	evergreen_pcie_gen2_enable(rdev);
+
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw || !rdev->mc_fw) {
 		r = ni_init_microcode(rdev);
 		if (r) {
@@ -1362,7 +1369,7 @@ static int cayman_startup(struct radeon_device *rdev)
 
 	r = evergreen_blit_init(rdev);
 	if (r) {
-		evergreen_blit_fini(rdev);
+		r600_blit_fini(rdev);
 		rdev->asic->copy = NULL;
 		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
 	}
@@ -1423,21 +1430,13 @@ int cayman_resume(struct radeon_device *rdev)
 
 int cayman_suspend(struct radeon_device *rdev)
 {
-	int r;
-
 	/* FIXME: we should wait for ring to be empty */
 	cayman_cp_enable(rdev, false);
 	rdev->cp.ready = false;
 	evergreen_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
 	cayman_pcie_gart_disable(rdev);
-
-	/* unpin shaders bo */
-	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-	if (likely(r == 0)) {
-		radeon_bo_unpin(rdev->r600_blit.shader_obj);
-		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-	}
+	r600_blit_suspend(rdev);
 
 	return 0;
 }
@@ -1550,7 +1549,7 @@ int cayman_init(struct radeon_device *rdev)
 
 void cayman_fini(struct radeon_device *rdev)
 {
-	evergreen_blit_fini(rdev);
+	r600_blit_fini(rdev);
 	cayman_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 7fcdbbbf297..8f8b8fa1435 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -68,6 +68,108 @@ MODULE_FIRMWARE(FIRMWA