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

Pull drm merge from Dave Airlie:
 "Highlights:

   - TI LCD controller KMS driver

   - TI OMAP KMS driver merged from staging

   - drop gma500 stub driver

   - the fbcon locking fixes

   - the vgacon dirty like zebra fix.

   - open firmware videomode and hdmi common code helpers

   - major locking rework for kms object handling - pageflip/cursor
     won't block on polling anymore!

   - fbcon helper and prime helper cleanups

   - i915: all over the map, haswell power well enhancements, valleyview
     macro horrors cleaned up, killing lots of legacy GTT code,

   - radeon: CS ioctl unification, deprecated UMS support, gpu reset
     rework, VM fixes

   - nouveau: reworked thermal code, external dp/tmds encoder support
     (anx9805), fences sleep instead of polling,

   - exynos: all over the driver fixes."

Lovely conflict in radeon/evergreen_cs.c between commit de0babd60d8d
("drm/radeon: enforce use of radeon_get_ib_value when reading user cmd")
and the new changes that modified that evergreen_dma_cs_parse()
function.

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (508 commits)
  drm/tilcdc: only build on arm
  drm/i915: Revert hdmi HDP pin checks
  drm/tegra: Add list of framebuffers to debugfs
  drm/tegra: Fix color expansion
  drm/tegra: Split DC_CMD_STATE_CONTROL register write
  drm/tegra: Implement page-flipping support
  drm/tegra: Implement VBLANK support
  drm/tegra: Implement .mode_set_base()
  drm/tegra: Add plane support
  drm/tegra: Remove bogus tegra_framebuffer structure
  drm: Add consistency check for page-flipping
  drm/radeon: Use generic HDMI infoframe helpers
  drm/tegra: Use generic HDMI infoframe helpers
  drm: Add EDID helper documentation
  drm: Add HDMI infoframe helpers
  video: Add generic HDMI infoframe helpers
  drm: Add some missing forward declarations
  drm: Move mode tables to drm_edid.c
  drm: Remove duplicate drm_mode_cea_vic()
  gma500: Fix n, m1 and m2 clock limits for sdvo and lvds
  ...

1 files changed, 100 insertions, 232 deletions

diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 9b2512bf1a46..01a3ec83f284 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -31,12 +31,7 @@
 #include "r600d.h"
 #include "r600_reg_safe.h"
 
-static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
-					struct radeon_cs_reloc **cs_reloc);
-static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
-					struct radeon_cs_reloc **cs_reloc);
-typedef int (*next_reloc_t)(struct radeon_cs_parser*, struct radeon_cs_reloc**);
-static next_reloc_t r600_cs_packet_next_reloc = &r600_cs_packet_next_reloc_mm;
+static int r600_nomm;
 extern void r600_cs_legacy_get_tiling_conf(struct drm_device *dev, u32 *npipes, u32 *nbanks, u32 *group_size);
 
 
@@ -784,170 +779,29 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 }
 
 /**
- * r600_cs_packet_parse() - parse cp packet and point ib index to next packet
- * @parser:	parser structure holding parsing context.
- * @pkt:	where to store packet informations
- *
- * Assume that chunk_ib_index is properly set. Will return -EINVAL
- * if packet is bigger than remaining ib size. or if packets is unknown.
- **/
-static int r600_cs_packet_parse(struct radeon_cs_parser *p,
-			struct radeon_cs_packet *pkt,
-			unsigned idx)
-{
-	struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx];
-	uint32_t header;
-
-	if (idx >= ib_chunk->length_dw) {
-		DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
-			  idx, ib_chunk->length_dw);
-		return -EINVAL;
-	}
-	header = radeon_get_ib_value(p, idx);
-	pkt->idx = idx;
-	pkt->type = CP_PACKET_GET_TYPE(header);
-	pkt->count = CP_PACKET_GET_COUNT(header);
-	pkt->one_reg_wr = 0;
-	switch (pkt->type) {
-	case PACKET_TYPE0:
-		pkt->reg = CP_PACKET0_GET_REG(header);
-		break;
-	case PACKET_TYPE3:
-		pkt->opcode = CP_PACKET3_GET_OPCODE(header);
-		break;
-	case PACKET_TYPE2:
-		pkt->count = -1;
-		break;
-	default:
-		DRM_ERROR("Unknown packet type %d at %d !\n", pkt->type, idx);
-		return -EINVAL;
-	}
-	if ((pkt->count + 1 + pkt->idx) >= ib_chunk->length_dw) {
-		DRM_ERROR("Packet (%d:%d:%d) end after CS buffer (%d) !\n",
-			  pkt->idx, pkt->type, pkt->count, ib_chunk->length_dw);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-/**
- * r600_cs_packet_next_reloc_mm() - parse next packet which should be reloc packet3
- * @parser:		parser structure holding parsing context.
- * @data:		pointer to relocation data
- * @offset_start:	starting offset
- * @offset_mask:	offset mask (to align start offset on)
- * @reloc:		reloc informations
- *
- * Check next packet is relocation packet3, do bo validation and compute
- * GPU offset using the provided start.
- **/
-static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
-					struct radeon_cs_reloc **cs_reloc)
-{
-	struct radeon_cs_chunk *relocs_chunk;
-	struct radeon_cs_packet p3reloc;
-	unsigned idx;
-	int r;
-
-	if (p->chunk_relocs_idx == -1) {
-		DRM_ERROR("No relocation chunk !\n");
-		return -EINVAL;
-	}
-	*cs_reloc = NULL;
-	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
-	if (r) {
-		return r;
-	}
-	p->idx += p3reloc.count + 2;
-	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
-		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
-			  p3reloc.idx);
-		return -EINVAL;
-	}
-	idx = radeon_get_ib_value(p, p3reloc.idx + 1);
-	if (idx >= relocs_chunk->length_dw) {
-		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
-			  idx, relocs_chunk->length_dw);
-		return -EINVAL;
-	}
-	/* FIXME: we assume reloc size is 4 dwords */
-	*cs_reloc = p->relocs_ptr[(idx / 4)];
-	return 0;
-}
-
-/**
- * r600_cs_packet_next_reloc_nomm() - parse next packet which should be reloc packet3
+ * r600_cs_packet_parse_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
- * @data:		pointer to relocation data
- * @offset_start:	starting offset
- * @offset_mask:	offset mask (to align start offset on)
- * @reloc:		reloc informations
  *
- * Check next packet is relocation packet3, do bo validation and compute
- * GPU offset using the provided start.
- **/
-static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
-					struct radeon_cs_reloc **cs_reloc)
-{
-	struct radeon_cs_chunk *relocs_chunk;
-	struct radeon_cs_packet p3reloc;
-	unsigned idx;
-	int r;
-
-	if (p->chunk_relocs_idx == -1) {
-		DRM_ERROR("No relocation chunk !\n");
-		return -EINVAL;
-	}
-	*cs_reloc = NULL;
-	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
-	if (r) {
-		return r;
-	}
-	p->idx += p3reloc.count + 2;
-	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
-		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
-			  p3reloc.idx);
-		return -EINVAL;
-	}
-	idx = radeon_get_ib_value(p, p3reloc.idx + 1);
-	if (idx >= relocs_chunk->length_dw) {
-		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
-			  idx, relocs_chunk->length_dw);
-		return -EINVAL;
-	}
-	*cs_reloc = p->relocs;
-	(*cs_reloc)->lobj.gpu_offset = (u64)relocs_chunk->kdata[idx + 3] << 32;
-	(*cs_reloc)->lobj.gpu_offset |= relocs_chunk->kdata[idx + 0];
-	return 0;
-}
-
-/**
- * r600_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 int r600_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
+ * This is an R600-specific function for parsing VLINE packets.
+ * Real work is done by r600_cs_common_vline_parse function.
+ * Here we just set up ASIC-specific register table and call
+ * the common implementation function.
+ */
+static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 {
-	struct radeon_cs_packet p3reloc;
-	int r;
+	static uint32_t vline_start_end[2] = {AVIVO_D1MODE_VLINE_START_END,
+					      AVIVO_D2MODE_VLINE_START_END};
+	static uint32_t vline_status[2] = {AVIVO_D1MODE_VLINE_STATUS,
+					   AVIVO_D2MODE_VLINE_STATUS};
 
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
-	if (r) {
-		return 0;
-	}
-	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
-		return 0;
-	}
-	return 1;
+	return r600_cs_common_vline_parse(p, vline_start_end, vline_status);
 }
 
 /**
- * r600_cs_packet_next_vline() - parse userspace VLINE packet
+ * r600_cs_common_vline_parse() - common vline parser
  * @parser:		parser structure holding parsing context.
+ * @vline_start_end:    table of vline_start_end registers
+ * @vline_status:       table of vline_status registers
  *
  * Userspace sends a special sequence for VLINE waits.
  * PACKET0 - VLINE_START_END + value
@@ -957,9 +811,16 @@ static int r600_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
  * This function parses this and relocates the VLINE START END
  * and WAIT_REG_MEM packets to the correct crtc.
  * It also detects a switched off crtc and nulls out the
- * wait in that case.
+ * wait in that case. This function is common for all ASICs that
+ * are R600 and newer. The parsing algorithm is the same, and only
+ * differs in which registers are used.
+ *
+ * Caller is the ASIC-specific function which passes the parser
+ * context and ASIC-specific register table
  */
-static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
+int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
+			       uint32_t *vline_start_end,
+			       uint32_t *vline_status)
 {
 	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
@@ -973,12 +834,12 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	ib = p->ib.ptr;
 
 	/* parse the WAIT_REG_MEM */
-	r = r600_cs_packet_parse(p, &wait_reg_mem, p->idx);
+	r = radeon_cs_packet_parse(p, &wait_reg_mem, p->idx);
 	if (r)
 		return r;
 
 	/* check its a WAIT_REG_MEM */
-	if (wait_reg_mem.type != PACKET_TYPE3 ||
+	if (wait_reg_mem.type != RADEON_PACKET_TYPE3 ||
 	    wait_reg_mem.opcode != PACKET3_WAIT_REG_MEM) {
 		DRM_ERROR("vline wait missing WAIT_REG_MEM segment\n");
 		return -EINVAL;
@@ -987,7 +848,12 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	wait_reg_mem_info = radeon_get_ib_value(p, wait_reg_mem.idx + 1);
 	/* bit 4 is reg (0) or mem (1) */
 	if (wait_reg_mem_info & 0x10) {
-		DRM_ERROR("vline WAIT_REG_MEM waiting on MEM rather than REG\n");
+		DRM_ERROR("vline WAIT_REG_MEM waiting on MEM instead of REG\n");
+		return -EINVAL;
+	}
+	/* bit 8 is me (0) or pfp (1) */
+	if (wait_reg_mem_info & 0x100) {
+		DRM_ERROR("vline WAIT_REG_MEM waiting on PFP instead of ME\n");
 		return -EINVAL;
 	}
 	/* waiting for value to be equal */
@@ -995,18 +861,18 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 		DRM_ERROR("vline WAIT_REG_MEM function not equal\n");
 		return -EINVAL;
 	}
-	if ((radeon_get_ib_value(p, wait_reg_mem.idx + 2) << 2) != AVIVO_D1MODE_VLINE_STATUS) {
+	if ((radeon_get_ib_value(p, wait_reg_mem.idx + 2) << 2) != vline_status[0]) {
 		DRM_ERROR("vline WAIT_REG_MEM bad reg\n");
 		return -EINVAL;
 	}
 
-	if (radeon_get_ib_value(p, wait_reg_mem.idx + 5) != AVIVO_D1MODE_VLINE_STAT) {
+	if (radeon_get_ib_value(p, wait_reg_mem.idx + 5) != RADEON_VLINE_STAT) {
 		DRM_ERROR("vline WAIT_REG_MEM bad bit mask\n");
 		return -EINVAL;
 	}
 
 	/* jump over the NOP */
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx + wait_reg_mem.count + 2);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx + wait_reg_mem.count + 2);
 	if (r)
 		return r;
 
@@ -1016,7 +882,7 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 
 	header = radeon_get_ib_value(p, h_idx);
 	crtc_id = radeon_get_ib_value(p, h_idx + 2 + 7 + 1);
-	reg = CP_PACKET0_GET_REG(header);
+	reg = R600_CP_PACKET0_GET_REG(header);
 
 	obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
 	if (!obj) {
@@ -1028,7 +894,7 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	crtc_id = radeon_crtc->crtc_id;
 
 	if (!crtc->enabled) {
-		/* if the CRTC isn't enabled - we need to nop out the WAIT_REG_MEM */
+		/* CRTC isn't enabled - we need to nop out the WAIT_REG_MEM */
 		ib[h_idx + 2] = PACKET2(0);
 		ib[h_idx + 3] = PACKET2(0);
 		ib[h_idx + 4] = PACKET2(0);
@@ -1036,20 +902,15 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 		ib[h_idx + 6] = PACKET2(0);
 		ib[h_idx + 7] = PACKET2(0);
 		ib[h_idx + 8] = PACKET2(0);
-	} else if (crtc_id == 1) {
-		switch (reg) {
-		case AVIVO_D1MODE_VLINE_START_END:
-			header &= ~R600_CP_PACKET0_REG_MASK;
-			header |= AVIVO_D2MODE_VLINE_START_END >> 2;
-			break;
-		default:
-			DRM_ERROR("unknown crtc reloc\n");
-			return -EINVAL;
-		}
+	} else if (reg == vline_start_end[0]) {
+		header &= ~R600_CP_PACKET0_REG_MASK;
+		header |= vline_start_end[crtc_id] >> 2;
 		ib[h_idx] = header;
-		ib[h_idx + 4] = AVIVO_D2MODE_VLINE_STATUS >> 2;
+		ib[h_idx + 4] = vline_status[crtc_id] >> 2;
+	} else {
+		DRM_ERROR("unknown crtc reloc\n");
+		return -EINVAL;
 	}
-
 	return 0;
 }
 
@@ -1155,8 +1016,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		break;
 	case R_028010_DB_DEPTH_INFO:
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS) &&
-		    r600_cs_packet_next_is_pkt3_nop(p)) {
-			r = r600_cs_packet_next_reloc(p, &reloc);
+		    radeon_cs_packet_next_is_pkt3_nop(p)) {
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					 "0x%04X\n", reg);
@@ -1198,7 +1059,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case VGT_STRMOUT_BUFFER_BASE_1:
 	case VGT_STRMOUT_BUFFER_BASE_2:
 	case VGT_STRMOUT_BUFFER_BASE_3:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1221,7 +1082,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->streamout_dirty = true;
 		break;
 	case CP_COHER_BASE:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "missing reloc for CP_COHER_BASE "
 					"0x%04X\n", reg);
@@ -1256,8 +1117,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_0280B8_CB_COLOR6_INFO:
 	case R_0280BC_CB_COLOR7_INFO:
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS) &&
-		     r600_cs_packet_next_is_pkt3_nop(p)) {
-			r = r600_cs_packet_next_reloc(p, &reloc);
+		     radeon_cs_packet_next_is_pkt3_nop(p)) {
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
@@ -1320,7 +1181,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_0280F8_CB_COLOR6_FRAG:
 	case R_0280FC_CB_COLOR7_FRAG:
 		tmp = (reg - R_0280E0_CB_COLOR0_FRAG) / 4;
-		if (!r600_cs_packet_next_is_pkt3_nop(p)) {
+		if (!radeon_cs_packet_next_is_pkt3_nop(p)) {
 			if (!track->cb_color_base_last[tmp]) {
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
@@ -1329,7 +1190,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 			track->cb_color_frag_offset[tmp] = track->cb_color_bo_offset[tmp];
 			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
@@ -1351,7 +1212,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_0280D8_CB_COLOR6_TILE:
 	case R_0280DC_CB_COLOR7_TILE:
 		tmp = (reg - R_0280C0_CB_COLOR0_TILE) / 4;
-		if (!r600_cs_packet_next_is_pkt3_nop(p)) {
+		if (!radeon_cs_packet_next_is_pkt3_nop(p)) {
 			if (!track->cb_color_base_last[tmp]) {
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
@@ -1360,7 +1221,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 			track->cb_color_tile_offset[tmp] = track->cb_color_bo_offset[tmp];
 			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
@@ -1395,7 +1256,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR5_BASE:
 	case CB_COLOR6_BASE:
 	case CB_COLOR7_BASE:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1410,7 +1271,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->cb_dirty = true;
 		break;
 	case DB_DEPTH_BASE:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1423,7 +1284,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_HTILE_DATA_BASE:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1493,7 +1354,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_ALU_CONST_CACHE_VS_13:
 	case SQ_ALU_CONST_CACHE_VS_14:
 	case SQ_ALU_CONST_CACHE_VS_15:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1502,7 +1363,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SX_MEMORY_EXPORT_BASE:
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONFIG_REG "
 					"0x%04X\n", reg);
@@ -1788,7 +1649,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			return -EINVAL;
 		}
 
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			DRM_ERROR("bad SET PREDICATION\n");
 			return -EINVAL;
@@ -1829,7 +1690,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad DRAW_INDEX\n");
 			return -EINVAL;
 		}
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			DRM_ERROR("bad DRAW_INDEX\n");
 			return -EINVAL;
@@ -1881,7 +1742,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if (idx_value & 0x10) {
 			uint64_t offset;
 
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad WAIT_REG_MEM\n");
 				return -EINVAL;
@@ -1893,6 +1754,9 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 
 			ib[idx+1] = (ib[idx+1] & 0x3) | (offset & 0xfffffff0);
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
+		} else if (idx_value & 0x100) {
+			DRM_ERROR("cannot use PFP on REG wait\n");
+			return -EINVAL;
 		}
 		break;
 	case PACKET3_CP_DMA:
@@ -1915,7 +1779,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 				return -EINVAL;
 			}
 			/* src address space is memory */
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad CP DMA SRC\n");
 				return -EINVAL;
@@ -1945,7 +1809,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 				DRM_ERROR("CP DMA DAIC only supported for registers\n");
 				return -EINVAL;
 			}
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad CP DMA DST\n");
 				return -EINVAL;
@@ -1975,7 +1839,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		/* 0xffffffff/0x0 is flush all cache flag */
 		if (radeon_get_ib_value(p, idx + 1) != 0xffffffff ||
 		    radeon_get_ib_value(p, idx + 2) != 0) {
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad SURFACE_SYNC\n");
 				return -EINVAL;
@@ -1991,7 +1855,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if (pkt->count) {
 			uint64_t offset;
 
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad EVENT_WRITE\n");
 				return -EINVAL;
@@ -2012,7 +1876,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad EVENT_WRITE_EOP\n");
 			return -EINVAL;
 		}
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			DRM_ERROR("bad EVENT_WRITE\n");
 			return -EINVAL;
@@ -2078,7 +1942,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			switch (G__SQ_VTX_CONSTANT_TYPE(radeon_get_ib_value(p, idx+(i*7)+6+1))) {
 			case SQ_TEX_VTX_VALID_TEXTURE:
 				/* tex base */
-				r = r600_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 				if (r) {
 					DRM_ERROR("bad SET_RESOURCE\n");
 					return -EINVAL;
@@ -2092,7 +1956,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 				}
 				texture = reloc->robj;
 				/* tex mip base */
-				r = r600_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 				if (r) {
 					DRM_ERROR("bad SET_RESOURCE\n");
 					return -EINVAL;
@@ -2113,7 +1977,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			{
 				uint64_t offset64;
 				/* vtx base */
-				r = r600_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 				if (r) {
 					DRM_ERROR("bad SET_RESOURCE\n");
 					return -EINVAL;
@@ -2214,7 +2078,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		{
 			u64 offset;
 
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad STRMOUT_BASE_UPDATE reloc\n");
 				return -EINVAL;
@@ -2258,7 +2122,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		/* Updating memory at DST_ADDRESS. */
 		if (idx_value & 0x1) {
 			u64 offset;
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n");
 				return -EINVAL;
@@ -2277,7 +2141,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		/* Reading data from SRC_ADDRESS. */
 		if (((idx_value >> 1) & 0x3) == 2) {
 			u64 offset;
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n");
 				return -EINVAL;
@@ -2302,7 +2166,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad MEM_WRITE (invalid count)\n");
 			return -EINVAL;
 		}
-		r = r600_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
 			DRM_ERROR("bad MEM_WRITE (missing reloc)\n");
 			return -EINVAL;
@@ -2331,7 +2195,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if (idx_value & 0x1) {
 			u64 offset;
 			/* SRC is memory. */
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad COPY_DW (missing src reloc)\n");
 				return -EINVAL;
@@ -2355,7 +2219,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if (idx_value & 0x2) {
 			u64 offset;
 			/* DST is memory. */
-			r = r600_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
 				DRM_ERROR("bad COPY_DW (missing dst reloc)\n");
 				return -EINVAL;
@@ -2410,7 +2274,7 @@ int r600_cs_parse(struct radeon_cs_parser *p)
 		p->track = track;
 	}
 	do {
-		r = r600_cs_packet_parse(p, &pkt, p->idx);
+		r = radeon_cs_packet_parse(p, &pkt, p->idx);
 		if (r) {
 			kfree(p->track);
 			p->track = NULL;
@@ -2418,12 +2282,12 @@ int r600_cs_parse(struct radeon_cs_parser *p)
 		}
 		p->idx += pkt.count + 2;
 		switch (pkt.type) {
-		case PACKET_TYPE0:
+		case RADEON_PACKET_TYPE0:
 			r = r600_cs_parse_packet0(p, &pkt);
 			break;
-		case PACKET_TYPE2:
+		case RADEON_PACKET_TYPE2:
 			break;
-		case PACKET_TYPE3:
+		case RADEON_PACKET_TYPE3:
 			r = r600_packet3_check(p, &pkt);
 			break;
 		default:
@@ -2449,17 +2313,7 @@ int r600_cs_parse(struct radeon_cs_parser *p)
 	return 0;
 }
 
-static int r600_cs_parser_relocs_legacy(struct radeon_cs_parser *p)
-{
-	if (p->chunk_relocs_idx == -1) {
-		return 0;
-	}
-	p->relocs = kzalloc(sizeof(struct radeon_cs_reloc), GFP_KERNEL);
-	if (p->relocs == NULL) {
-		return -ENOMEM;
-	}
-	return 0;
-}
+#ifdef CONFIG_DRM_RADEON_UMS
 
 /**
  * cs_parser_fini() - clean parser states
@@ -2485,6 +2339,18 @@ static void r600_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 	kfree(parser->chunks_array);
 }
 
+static int r600_cs_parser_relocs_legacy(struct radeon_cs_parser *p)
+{
+	if (p->chunk_relocs_idx == -1) {
+		return 0;
+	}
+	p->relocs = kzalloc(sizeof(struct radeon_cs_reloc), GFP_KERNEL);
+	if (p->relocs == NULL) {
+		return -ENOMEM;
+	}
+	return 0;
+}
+
 int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp,
 			unsigned family, u32 *ib, int *l)
 {
@@ -2543,9 +2409,11 @@ int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp,
 
 void r600_cs_legacy_init(void)
 {
-	r600_cs_packet_next_reloc = &r600_cs_packet_next_reloc_nomm;
+	r600_nomm = 1;
 }
 
+#endif
+
 /*
  *  DMA
  */