From 580f839892d659097459eaf3b52fb1af1a83f358 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:37 -0500
Subject: [PATCH 01/38] drm/radeon: remove unecessary assignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

length_dw field was assigned twice. While at it, move user_ptr
assignment together with all other assignments to p->chunks[i]
structure to make the code more readable.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_cs.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 5407459e56d2..56f9282b3279 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -203,7 +203,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 		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;
 		}
@@ -226,9 +226,6 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 				return -EINVAL;
 		}
 
-		p->chunks[i].length_dw = user_chunk.length_dw;
-		p->chunks[i].user_ptr = (void __user *)(unsigned long)user_chunk.chunk_data;
-
 		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)) {

From d20145043524c4f28d090f5176cf9bf5cc7306c6 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:38 -0500
Subject: [PATCH 02/38] drm/radeon: remove unused prototype from radeon_cs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_cs.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 56f9282b3279..0a23589e3d40 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -29,9 +29,6 @@
 #include "radeon_reg.h"
 #include "radeon.h"
 
-void r100_cs_dump_packet(struct radeon_cs_parser *p,
-			 struct radeon_cs_packet *pkt);
-
 static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 {
 	struct drm_device *ddev = p->rdev->ddev;

From 66b3543ef38216bdaf529a207fb495c500eb98be Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:39 -0500
Subject: [PATCH 03/38] drm/radeon: fix formatting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Preparatory patch: patches to follow will touch a piece of code
that had broken indentication, so fix it before touching it.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r100.c | 45 +++++++++++++++++------------------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 8ff7cac222dc..40c0318b1eef 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2106,31 +2106,30 @@ int r100_cs_parse(struct radeon_cs_parser *p)
 		}
 		p->idx += pkt.count + 2;
 		switch (pkt.type) {
-			case PACKET_TYPE0:
-				if (p->rdev->family >= CHIP_R200)
-					r = r100_cs_parse_packet0(p, &pkt,
-								  p->rdev->config.r100.reg_safe_bm,
-								  p->rdev->config.r100.reg_safe_bm_size,
-								  &r200_packet0_check);
-				else
-					r = r100_cs_parse_packet0(p, &pkt,
-								  p->rdev->config.r100.reg_safe_bm,
-								  p->rdev->config.r100.reg_safe_bm_size,
-								  &r100_packet0_check);
-				break;
-			case PACKET_TYPE2:
-				break;
-			case PACKET_TYPE3:
-				r = r100_packet3_check(p, &pkt);
-				break;
-			default:
-				DRM_ERROR("Unknown packet type %d !\n",
-					  pkt.type);
-				return -EINVAL;
+		case PACKET_TYPE0:
+			if (p->rdev->family >= CHIP_R200)
+				r = r100_cs_parse_packet0(p, &pkt,
+					p->rdev->config.r100.reg_safe_bm,
+					p->rdev->config.r100.reg_safe_bm_size,
+					&r200_packet0_check);
+			else
+				r = r100_cs_parse_packet0(p, &pkt,
+					p->rdev->config.r100.reg_safe_bm,
+					p->rdev->config.r100.reg_safe_bm_size,
+					&r100_packet0_check);
+			break;
+		case PACKET_TYPE2:
+			break;
+		case PACKET_TYPE3:
+			r = r100_packet3_check(p, &pkt);
+			break;
+		default:
+			DRM_ERROR("Unknown packet type %d !\n",
+				  pkt.type);
+			return -EINVAL;
 		}
-		if (r) {
+		if (r)
 			return r;
-		}
 	} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
 	return 0;
 }

From 4db013110cd3da05e4cf7e1119468817709cb9db Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:40 -0500
Subject: [PATCH 04/38] drm/radeon: implement common cs packet parse function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

CS packet parse functions have a lot of in common across
all ASICs. Implement a common function and take care of
small differences between families inside the function.

This patch is a prep for major refactoring and consolidation
of CS parsing code.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_cs.c  | 53 +++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/radeon_reg.h | 11 ++++++
 2 files changed, 64 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 0a23589e3d40..7355a3613e23 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -642,3 +642,56 @@ u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 	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.
+ * @pkt:	where to store packet information
+ *
+ * Assume that chunk_ib_index is properly set. Will return -EINVAL
+ * if packet is bigger than remaining ib size. or if packets is unknown.
+ **/
+int radeon_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];
+	struct radeon_device *rdev = p->rdev;
+	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 = RADEON_CP_PACKET_GET_TYPE(header);
+	pkt->count = RADEON_CP_PACKET_GET_COUNT(header);
+	pkt->one_reg_wr = 0;
+	switch (pkt->type) {
+	case RADEON_PACKET_TYPE0:
+		if (rdev->family < CHIP_R600) {
+			pkt->reg = R100_CP_PACKET0_GET_REG(header);
+			pkt->one_reg_wr =
+				RADEON_CP_PACKET0_GET_ONE_REG_WR(header);
+		} else
+			pkt->reg = R600_CP_PACKET0_GET_REG(header);
+		break;
+	case RADEON_PACKET_TYPE3:
+		pkt->opcode = RADEON_CP_PACKET3_GET_OPCODE(header);
+		break;
+	case RADEON_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;
+}
diff --git a/drivers/gpu/drm/radeon/radeon_reg.h b/drivers/gpu/drm/radeon/radeon_reg.h
index 5d8f735d6aaf..d9e4204430fb 100644
--- a/drivers/gpu/drm/radeon/radeon_reg.h
+++ b/drivers/gpu/drm/radeon/radeon_reg.h
@@ -3706,4 +3706,15 @@
 
 #define RV530_GB_PIPE_SELECT2           0x4124
 
+#define RADEON_CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
+#define RADEON_CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
+#define RADEON_CP_PACKET0_GET_ONE_REG_WR(h) (((h) >> 15) & 1)
+#define RADEON_CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
+#define R100_CP_PACKET0_GET_REG(h) (((h) & 0x1FFF) << 2)
+#define R600_CP_PACKET0_GET_REG(h) (((h) & 0xFFFF) << 2)
+#define RADEON_PACKET_TYPE0 0
+#define RADEON_PACKET_TYPE1 1
+#define RADEON_PACKET_TYPE2 2
+#define RADEON_PACKET_TYPE3 3
+
 #endif

From c38f34b53e74dec4e58fef0c895d9e6df7da1190 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:41 -0500
Subject: [PATCH 05/38] drm/radeon: use common cs packet parse function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We now have a common radeon_cs_packet_parse function
that is good for all ASICs. Hook it up and eliminate
ASIC-specific versions.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 57 +++-----------------------
 drivers/gpu/drm/radeon/r100.c         | 55 ++-----------------------
 drivers/gpu/drm/radeon/r300.c         |  2 +-
 drivers/gpu/drm/radeon/r600_cs.c      | 59 +++------------------------
 drivers/gpu/drm/radeon/radeon.h       |  4 ++
 5 files changed, 20 insertions(+), 157 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 7a445666e71f..1ba4ca38f4f9 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -1008,53 +1008,6 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 	return 0;
 }
 
-/**
- * evergreen_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 evergreen_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;
-}
-
 /**
  * evergreen_cs_packet_next_reloc() - parse next packet which should be reloc packet3
  * @parser:		parser structure holding parsing context.
@@ -1080,7 +1033,7 @@ static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
 	}
 	*cs_reloc = NULL;
 	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
-	r = evergreen_cs_packet_parse(p, &p3reloc, p->idx);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
 	if (r) {
 		return r;
 	}
@@ -1112,7 +1065,7 @@ static bool 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);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
 	if (r) {
 		return false;
 	}
@@ -1150,7 +1103,7 @@ static int evergreen_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	ib = p->ib.ptr;
 
 	/* parse the WAIT_REG_MEM */
-	r = evergreen_cs_packet_parse(p, &wait_reg_mem, p->idx);
+	r = radeon_cs_packet_parse(p, &wait_reg_mem, p->idx);
 	if (r)
 		return r;
 
@@ -1183,7 +1136,7 @@ static int evergreen_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	}
 
 	/* jump over the NOP */
-	r = evergreen_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;
 
@@ -2819,7 +2772,7 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 		p->track = track;
 	}
 	do {
-		r = evergreen_cs_packet_parse(p, &pkt, p->idx);
+		r = radeon_cs_packet_parse(p, &pkt, p->idx);
 		if (r) {
 			kfree(p->track);
 			p->track = NULL;
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 40c0318b1eef..7842447da4fb 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1369,53 +1369,6 @@ void r100_cs_dump_packet(struct radeon_cs_parser *p,
 	}
 }
 
-/**
- * r100_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.
- **/
-int r100_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);
-	switch (pkt->type) {
-	case PACKET_TYPE0:
-		pkt->reg = CP_PACKET0_GET_REG(header);
-		pkt->one_reg_wr = CP_PACKET0_GET_ONE_REG_WR(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;
-}
-
 /**
  * r100_cs_packet_next_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
@@ -1444,7 +1397,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	ib = p->ib.ptr;
 
 	/* parse the wait until */
-	r = r100_cs_packet_parse(p, &waitreloc, p->idx);
+	r = radeon_cs_packet_parse(p, &waitreloc, p->idx);
 	if (r)
 		return r;
 
@@ -1461,7 +1414,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	}
 
 	/* jump over the NOP */
-	r = r100_cs_packet_parse(p, &p3reloc, p->idx + waitreloc.count + 2);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx + waitreloc.count + 2);
 	if (r)
 		return r;
 
@@ -1531,7 +1484,7 @@ int r100_cs_packet_next_reloc(struct radeon_cs_parser *p,
 	}
 	*cs_reloc = NULL;
 	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
-	r = r100_cs_packet_parse(p, &p3reloc, p->idx);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
 	if (r) {
 		return r;
 	}
@@ -2100,7 +2053,7 @@ int r100_cs_parse(struct radeon_cs_parser *p)
 	r100_cs_track_clear(p->rdev, track);
 	p->track = track;
 	do {
-		r = r100_cs_packet_parse(p, &pkt, p->idx);
+		r = radeon_cs_packet_parse(p, &pkt, p->idx);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index d0ba6023a1f8..34ca46e46347 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1257,7 +1257,7 @@ int r300_cs_parse(struct radeon_cs_parser *p)
 	r100_cs_track_clear(p->rdev, track);
 	p->track = track;
 	do {
-		r = r100_cs_packet_parse(p, &pkt, p->idx);
+		r = radeon_cs_packet_parse(p, &pkt, p->idx);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 69ec24ab8d63..3870bf8c1bc7 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -783,53 +783,6 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 	return 0;
 }
 
-/**
- * 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.
@@ -855,7 +808,7 @@ static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
 	}
 	*cs_reloc = NULL;
 	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
 	if (r) {
 		return r;
 	}
@@ -901,7 +854,7 @@ static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
 	}
 	*cs_reloc = NULL;
 	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
 	if (r) {
 		return r;
 	}
@@ -935,7 +888,7 @@ static int r600_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
 	struct radeon_cs_packet p3reloc;
 	int r;
 
-	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
 	if (r) {
 		return 0;
 	}
@@ -973,7 +926,7 @@ 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;
 
@@ -1006,7 +959,7 @@ static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	}
 
 	/* 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;
 
@@ -2410,7 +2363,7 @@ 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;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a08f657329a0..b8d1c5c0c2c6 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1972,6 +1972,10 @@ static inline int radeon_acpi_init(struct radeon_device *rdev) { return 0; }
 static inline void radeon_acpi_fini(struct radeon_device *rdev) { }
 #endif
 
+int radeon_cs_packet_parse(struct radeon_cs_parser *p,
+			   struct radeon_cs_packet *pkt,
+			   unsigned idx);
+
 #include "radeon_object.h"
 
 #endif

From 9ffb7a6dca4fd260db91c808efd4d5c56057600c Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:42 -0500
Subject: [PATCH 06/38] drm/radeon: factor out cs_next_is_pkt3_nop function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Once we factored out radeon_cs_packet_parse function,
evergreen_cs_next_is_pkt3_nop and r600_cs_next_is_pkt3_nop
functions became identical, so they can be factored out
into a common function.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 23 +-------------------
 drivers/gpu/drm/radeon/r600_cs.c      | 30 ++++-----------------------
 drivers/gpu/drm/radeon/radeon.h       |  2 ++
 drivers/gpu/drm/radeon/radeon_cs.c    | 21 +++++++++++++++++++
 drivers/gpu/drm/radeon/radeon_reg.h   |  2 ++
 5 files changed, 30 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 1ba4ca38f4f9..883b9f76a495 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -1054,27 +1054,6 @@ static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
 	return 0;
 }
 
-/**
- * evergreen_cs_packet_next_is_pkt3_nop() - test if the next packet is NOP
- * @p:		structure holding the parser context.
- *
- * Check if the next packet is a relocation packet3.
- **/
-static bool evergreen_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
-{
-	struct radeon_cs_packet p3reloc;
-	int r;
-
-	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
-	if (r) {
-		return false;
-	}
-	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
-		return false;
-	}
-	return true;
-}
-
 /**
  * evergreen_cs_packet_next_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
@@ -2464,7 +2443,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 				if ((tex_dim == SQ_TEX_DIM_2D_MSAA || tex_dim == SQ_TEX_DIM_2D_ARRAY_MSAA) &&
 				    !mip_address &&
-				    !evergreen_cs_packet_next_is_pkt3_nop(p)) {
+				    !radeon_cs_packet_next_is_pkt3_nop(p)) {
 					/* MIP_ADDRESS should point to FMASK for an MSAA texture.
 					 * It should be 0 if FMASK is disabled. */
 					moffset = 0;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 3870bf8c1bc7..6e6fa97043d0 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -876,28 +876,6 @@ static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
 	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)
-{
-	struct radeon_cs_packet p3reloc;
-	int r;
-
-	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
-	if (r) {
-		return 0;
-	}
-	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
-		return 0;
-	}
-	return 1;
-}
-
 /**
  * r600_cs_packet_next_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
@@ -1108,7 +1086,7 @@ 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)) {
+		    radeon_cs_packet_next_is_pkt3_nop(p)) {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
@@ -1209,7 +1187,7 @@ 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)) {
+		     radeon_cs_packet_next_is_pkt3_nop(p)) {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
@@ -1273,7 +1251,7 @@ 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;
@@ -1304,7 +1282,7 @@ 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;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b8d1c5c0c2c6..72c4836162ec 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1975,6 +1975,8 @@ static inline void radeon_acpi_fini(struct radeon_device *rdev) { }
 int radeon_cs_packet_parse(struct radeon_cs_parser *p,
 			   struct radeon_cs_packet *pkt,
 			   unsigned idx);
+bool radeon_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p);
+
 
 #include "radeon_object.h"
 
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 7355a3613e23..56cdb44c3612 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -695,3 +695,24 @@ int radeon_cs_packet_parse(struct radeon_cs_parser *p,
 	}
 	return 0;
 }
+
+/**
+ * radeon_cs_packet_next_is_pkt3_nop() - test if the next packet is P3 NOP
+ * @p:		structure holding the parser context.
+ *
+ * Check if the next packet is NOP relocation packet3.
+ **/
+bool radeon_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
+{
+	struct radeon_cs_packet p3reloc;
+	int r;
+
+	r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
+	if (r)
+		return false;
+	if (p3reloc.type != RADEON_PACKET_TYPE3)
+		return false;
+	if (p3reloc.opcode != RADEON_PACKET3_NOP)
+		return false;
+	return true;
+}
diff --git a/drivers/gpu/drm/radeon/radeon_reg.h b/drivers/gpu/drm/radeon/radeon_reg.h
index d9e4204430fb..ce7e9f29cc89 100644
--- a/drivers/gpu/drm/radeon/radeon_reg.h
+++ b/drivers/gpu/drm/radeon/radeon_reg.h
@@ -3717,4 +3717,6 @@
 #define RADEON_PACKET_TYPE2 2
 #define RADEON_PACKET_TYPE3 3
 
+#define RADEON_PACKET3_NOP 0x10
+
 #endif

From 40592a17b8747903be95338f461573916a71d739 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:43 -0500
Subject: [PATCH 07/38] drm/radeon: refactor vline packet parsing function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vline packet parsing function for R600 and Evergreen+ are
the same, except that they use different registers. Factor
out the algorithm into a common function that uses register
table passed from ASIC-specific caller.

This reduces ASIC-specific function to (trivial) setup
of register table and call into the common function.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 120 +++++---------------------
 drivers/gpu/drm/radeon/r600_cs.c      |  61 +++++++++----
 drivers/gpu/drm/radeon/radeon.h       |   4 +-
 drivers/gpu/drm/radeon/radeon_reg.h   |   2 +
 4 files changed, 70 insertions(+), 117 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 883b9f76a495..26905322d8e7 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -1055,109 +1055,35 @@ static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
 }
 
 /**
- * evergreen_cs_packet_next_vline() - parse userspace VLINE packet
+ * evergreen_cs_packet_parse_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
  *
- * Userspace sends a special sequence for VLINE waits.
- * PACKET0 - VLINE_START_END + value
- * PACKET3 - WAIT_REG_MEM poll vline status reg
- * RELOC (P3) - crtc_id in reloc.
- *
- * 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.
+ * This is an Evergreen(+)-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 evergreen_cs_packet_parse_vline(struct radeon_cs_parser *p)
 {
-	struct drm_mode_object *obj;
-	struct drm_crtc *crtc;
-	struct radeon_crtc *radeon_crtc;
-	struct radeon_cs_packet p3reloc, wait_reg_mem;
-	int crtc_id;
-	int r;
-	uint32_t header, h_idx, reg, wait_reg_mem_info;
-	volatile uint32_t *ib;
-
-	ib = p->ib.ptr;
-
-	/* parse the WAIT_REG_MEM */
-	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 ||
-	    wait_reg_mem.opcode != PACKET3_WAIT_REG_MEM) {
-		DRM_ERROR("vline wait missing WAIT_REG_MEM segment\n");
-		return -EINVAL;
-	}
-
-	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");
-		return -EINVAL;
-	}
-	/* waiting for value to be equal */
-	if ((wait_reg_mem_info & 0x7) != 0x3) {
-		DRM_ERROR("vline WAIT_REG_MEM function not equal\n");
-		return -EINVAL;
-	}
-	if ((radeon_get_ib_value(p, wait_reg_mem.idx + 2) << 2) != EVERGREEN_VLINE_STATUS) {
-		DRM_ERROR("vline WAIT_REG_MEM bad reg\n");
-		return -EINVAL;
-	}
 
-	if (radeon_get_ib_value(p, wait_reg_mem.idx + 5) != EVERGREEN_VLINE_STAT) {
-		DRM_ERROR("vline WAIT_REG_MEM bad bit mask\n");
-		return -EINVAL;
-	}
-
-	/* jump over the NOP */
-	r = radeon_cs_packet_parse(p, &p3reloc, p->idx + wait_reg_mem.count + 2);
-	if (r)
-		return r;
-
-	h_idx = p->idx - 2;
-	p->idx += wait_reg_mem.count + 2;
-	p->idx += p3reloc.count + 2;
-
-	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);
-	obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
-		DRM_ERROR("cannot find crtc %d\n", crtc_id);
-		return -EINVAL;
-	}
-	crtc = obj_to_crtc(obj);
-	radeon_crtc = to_radeon_crtc(crtc);
-	crtc_id = radeon_crtc->crtc_id;
-
-	if (!crtc->enabled) {
-		/* if the 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);
-		ib[h_idx + 5] = PACKET2(0);
-		ib[h_idx + 6] = PACKET2(0);
-		ib[h_idx + 7] = PACKET2(0);
-		ib[h_idx + 8] = PACKET2(0);
-	} else {
-		switch (reg) {
-		case EVERGREEN_VLINE_START_END:
-			header &= ~R600_CP_PACKET0_REG_MASK;
-			header |= (EVERGREEN_VLINE_START_END + radeon_crtc->crtc_offset) >> 2;
-			ib[h_idx] = header;
-			ib[h_idx + 4] = (EVERGREEN_VLINE_STATUS + radeon_crtc->crtc_offset) >> 2;
-			break;
-		default:
-			DRM_ERROR("unknown crtc reloc\n");
-			return -EINVAL;
-		}
-	}
-	return 0;
+	static uint32_t vline_start_end[6] = {
+		EVERGREEN_VLINE_START_END + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		EVERGREEN_VLINE_START_END + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		EVERGREEN_VLINE_START_END + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		EVERGREEN_VLINE_START_END + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		EVERGREEN_VLINE_START_END + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		EVERGREEN_VLINE_START_END + EVERGREEN_CRTC5_REGISTER_OFFSET
+	};
+	static uint32_t vline_status[6] = {
+		EVERGREEN_VLINE_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		EVERGREEN_VLINE_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		EVERGREEN_VLINE_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		EVERGREEN_VLINE_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		EVERGREEN_VLINE_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		EVERGREEN_VLINE_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET
+	};
+
+	return r600_cs_common_vline_parse(p, vline_start_end, vline_status);
 }
 
 static int evergreen_packet0_check(struct radeon_cs_parser *p,
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 6e6fa97043d0..e61a013e63fc 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -877,9 +877,30 @@ static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
 }
 
 /**
- * r600_cs_packet_next_vline() - parse userspace VLINE packet
+ * r600_cs_packet_parse_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
  *
+ * 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)
+{
+	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};
+
+	return r600_cs_common_vline_parse(p, vline_start_end, vline_status);
+}
+
+/**
+ * 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
  * PACKET3 - WAIT_REG_MEM poll vline status reg
@@ -888,9 +909,16 @@ static int r600_cs_packet_next_reloc_nomm(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;
@@ -918,7 +946,7 @@ 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;
 	}
 	/* waiting for value to be equal */
@@ -926,12 +954,12 @@ 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;
 	}
@@ -959,7 +987,7 @@ 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);
@@ -967,20 +995,15 @@ 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;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 72c4836162ec..5caeca38383d 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1976,7 +1976,9 @@ int radeon_cs_packet_parse(struct radeon_cs_parser *p,
 			   struct radeon_cs_packet *pkt,
 			   unsigned idx);
 bool radeon_cs_packet_next_is_pkt3_nop(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);
 
 #include "radeon_object.h"
 
diff --git a/drivers/gpu/drm/radeon/radeon_reg.h b/drivers/gpu/drm/radeon/radeon_reg.h
index ce7e9f29cc89..7e2c2b7cf188 100644
--- a/drivers/gpu/drm/radeon/radeon_reg.h
+++ b/drivers/gpu/drm/radeon/radeon_reg.h
@@ -3719,4 +3719,6 @@
 
 #define RADEON_PACKET3_NOP 0x10
 
+#define RADEON_VLINE_STAT (1 << 12)
+
 #endif

From d6e18a3406d401edeb96a01c7bb9d1689454c41b Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:44 -0500
Subject: [PATCH 08/38] drm/radeon: add a check to wait_reg_mem command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

WAIT_REG_MEM on register does not allow the use of PFP.
Enforce this restriction when checking packets sent from
userland.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 3 +++
 drivers/gpu/drm/radeon/r600_cs.c      | 8 ++++++++
 2 files changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 26905322d8e7..02aeb7fc3778 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2101,6 +2101,9 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 			ib[idx+1] = (ib[idx+1] & 0x3) | (offset & 0xfffffffc);
 			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:
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index e61a013e63fc..9d833728ed00 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -949,6 +949,11 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 		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 */
 	if ((wait_reg_mem_info & 0x7) != 0x3) {
 		DRM_ERROR("vline WAIT_REG_MEM function not equal\n");
@@ -1847,6 +1852,9 @@ 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:

From c3ad63afcdb931159690aa7ba2906079c3b38a13 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:45 -0500
Subject: [PATCH 09/38] drm/radeon: rename r100_cs_dump_packet to
 radeon_cs_dump_packet
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This function is not limited to r100, but it can dump a
(raw) packet for any ASIC. Rename it accordingly and move
its declaration to radeon.h

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r100.c       | 52 +++++++++++------------------
 drivers/gpu/drm/radeon/r100_track.h |  2 --
 drivers/gpu/drm/radeon/r200.c       | 14 ++++----
 drivers/gpu/drm/radeon/r300.c       | 18 +++++-----
 drivers/gpu/drm/radeon/radeon.h     |  2 ++
 drivers/gpu/drm/radeon/radeon_cs.c  | 21 ++++++++++++
 6 files changed, 58 insertions(+), 51 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 7842447da4fb..cf7e35903eae 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1219,7 +1219,7 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
 	if (r) {
 		DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 			  idx, reg);
-		r100_cs_dump_packet(p, pkt);
+		radeon_cs_dump_packet(p, pkt);
 		return r;
 	}
 
@@ -1233,7 +1233,7 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
 		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
 			if (reg == RADEON_SRC_PITCH_OFFSET) {
 				DRM_ERROR("Cannot src blit from microtiled surface\n");
-				r100_cs_dump_packet(p, pkt);
+				radeon_cs_dump_packet(p, pkt);
 				return -EINVAL;
 			}
 			tile_flags |= RADEON_DST_TILE_MICRO;
@@ -1263,7 +1263,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 	if (c > 16) {
 	    DRM_ERROR("Only 16 vertex buffers are allowed %d\n",
 		      pkt->opcode);
-	    r100_cs_dump_packet(p, pkt);
+	    radeon_cs_dump_packet(p, pkt);
 	    return -EINVAL;
 	}
 	track->num_arrays = c;
@@ -1272,7 +1272,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n",
 				  pkt->opcode);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		idx_value = radeon_get_ib_value(p, idx);
@@ -1285,7 +1285,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n",
 				  pkt->opcode);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx+2] = radeon_get_ib_value(p, idx + 2) + ((u32)reloc->lobj.gpu_offset);
@@ -1298,7 +1298,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n",
 					  pkt->opcode);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		idx_value = radeon_get_ib_value(p, idx);
@@ -1355,20 +1355,6 @@ int r100_cs_parse_packet0(struct radeon_cs_parser *p,
 	return 0;
 }
 
-void r100_cs_dump_packet(struct radeon_cs_parser *p,
-			 struct radeon_cs_packet *pkt)
-{
-	volatile uint32_t *ib;
-	unsigned i;
-	unsigned idx;
-
-	ib = p->ib.ptr;
-	idx = pkt->idx;
-	for (i = 0; i <= (pkt->count + 1); i++, idx++) {
-		DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
-	}
-}
-
 /**
  * r100_cs_packet_next_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
@@ -1492,14 +1478,14 @@ int r100_cs_packet_next_reloc(struct radeon_cs_parser *p,
 	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
 		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
 			  p3reloc.idx);
-		r100_cs_dump_packet(p, &p3reloc);
+		radeon_cs_dump_packet(p, &p3reloc);
 		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);
-		r100_cs_dump_packet(p, &p3reloc);
+		radeon_cs_dump_packet(p, &p3reloc);
 		return -EINVAL;
 	}
 	/* FIXME: we assume reloc size is 4 dwords */
@@ -1584,7 +1570,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		break;
@@ -1601,7 +1587,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->zb.robj = reloc->robj;
@@ -1614,7 +1600,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->cb[0].robj = reloc->robj;
@@ -1630,7 +1616,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
@@ -1657,7 +1643,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->textures[0].cube_info[i].offset = idx_value;
@@ -1675,7 +1661,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->textures[1].cube_info[i].offset = idx_value;
@@ -1693,7 +1679,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->textures[2].cube_info[i].offset = idx_value;
@@ -1711,7 +1697,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
@@ -1782,7 +1768,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
@@ -1942,7 +1928,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 		r = r100_cs_packet_next_reloc(p, &reloc);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx+1] = radeon_get_ib_value(p, idx+1) + ((u32)reloc->lobj.gpu_offset);
@@ -1956,7 +1942,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 		r = r100_cs_packet_next_reloc(p, &reloc);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx] = radeon_get_ib_value(p, idx) + ((u32)reloc->lobj.gpu_offset);
diff --git a/drivers/gpu/drm/radeon/r100_track.h b/drivers/gpu/drm/radeon/r100_track.h
index 6a603b378adb..c81b174aaf05 100644
--- a/drivers/gpu/drm/radeon/r100_track.h
+++ b/drivers/gpu/drm/radeon/r100_track.h
@@ -83,8 +83,6 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track);
 int r100_cs_packet_next_reloc(struct radeon_cs_parser *p,
 			      struct radeon_cs_reloc **cs_reloc);
-void r100_cs_dump_packet(struct radeon_cs_parser *p,
-			 struct radeon_cs_packet *pkt);
 
 int r100_cs_packet_parse_vline(struct radeon_cs_parser *p);
 
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index 98143a5c5b73..07ea6f4a9903 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -162,7 +162,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		break;
@@ -179,7 +179,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->zb.robj = reloc->robj;
@@ -192,7 +192,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->cb[0].robj = reloc->robj;
@@ -211,7 +211,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
@@ -264,7 +264,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->textures[i].cube_info[face - 1].offset = idx_value;
@@ -282,7 +282,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 
@@ -359,7 +359,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 34ca46e46347..47bfca14cec8 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -615,7 +615,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		break;
@@ -634,7 +634,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->cb[i].robj = reloc->robj;
@@ -647,7 +647,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->zb.robj = reloc->robj;
@@ -676,7 +676,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 
@@ -749,7 +749,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			if (r) {
 				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					  idx, reg);
-				r100_cs_dump_packet(p, pkt);
+				radeon_cs_dump_packet(p, pkt);
 				return r;
 			}
 
@@ -834,7 +834,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			if (r) {
 				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					  idx, reg);
-				r100_cs_dump_packet(p, pkt);
+				radeon_cs_dump_packet(p, pkt);
 				return r;
 			}
 
@@ -1049,7 +1049,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
@@ -1091,7 +1091,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		track->aa.robj = reloc->robj;
@@ -1159,7 +1159,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p,
 		r = r100_cs_packet_next_reloc(p, &reloc);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
-			r100_cs_dump_packet(p, pkt);
+			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
 		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 5caeca38383d..5f964309ba68 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1976,6 +1976,8 @@ int radeon_cs_packet_parse(struct radeon_cs_parser *p,
 			   struct radeon_cs_packet *pkt,
 			   unsigned idx);
 bool radeon_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p);
+void radeon_cs_dump_packet(struct radeon_cs_parser *p,
+			   struct radeon_cs_packet *pkt);
 int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 			       uint32_t *vline_start_end,
 			       uint32_t *vline_status);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 56cdb44c3612..7f48d46a757d 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -716,3 +716,24 @@ bool radeon_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
 		return false;
 	return true;
 }
+
+/**
+ * radeon_cs_dump_packet() - dump raw packet context
+ * @p:		structure holding the parser context.
+ * @pkt:	structure holding the packet.
+ *
+ * Used mostly for debugging and error reporting.
+ **/
+void radeon_cs_dump_packet(struct radeon_cs_parser *p,
+			   struct radeon_cs_packet *pkt)
+{
+	volatile uint32_t *ib;
+	unsigned i;
+	unsigned idx;
+
+	ib = p->ib.ptr;
+	idx = pkt->idx;
+	for (i = 0; i <= (pkt->count + 1); i++, idx++)
+		DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
+}
+

From e97169930941c4326dd563578369590a52aec707 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:46 -0500
Subject: [PATCH 10/38] drm/radeon: pull out common next_reloc function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

next_reloc function does the same thing in all ASICs with
the exception of R600 which has a special case in legacy mode.
Pull out the common function in preparation for refactoring.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon.h    |  3 ++
 drivers/gpu/drm/radeon/radeon_cs.c | 54 ++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 5f964309ba68..fa17ce026aba 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1978,6 +1978,9 @@ int radeon_cs_packet_parse(struct radeon_cs_parser *p,
 bool radeon_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p);
 void radeon_cs_dump_packet(struct radeon_cs_parser *p,
 			   struct radeon_cs_packet *pkt);
+int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p,
+				struct radeon_cs_reloc **cs_reloc,
+				int nomm);
 int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 			       uint32_t *vline_start_end,
 			       uint32_t *vline_status);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 7f48d46a757d..1d214b66650f 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -737,3 +737,57 @@ void radeon_cs_dump_packet(struct radeon_cs_parser *p,
 		DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
 }
 
+/**
+ * radeon_cs_packet_next_reloc() - parse next (should be reloc) 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 if next packet is relocation packet3, do bo validation and compute
+ * GPU offset using the provided start.
+ **/
+int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p,
+				struct radeon_cs_reloc **cs_reloc,
+				int nomm)
+{
+	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 = radeon_cs_packet_parse(p, &p3reloc, p->idx);
+	if (r)
+		return r;
+	p->idx += p3reloc.count + 2;
+	if (p3reloc.type != RADEON_PACKET_TYPE3 ||
+	    p3reloc.opcode != RADEON_PACKET3_NOP) {
+		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
+			  p3reloc.idx);
+		radeon_cs_dump_packet(p, &p3reloc);
+		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);
+		radeon_cs_dump_packet(p, &p3reloc);
+		return -EINVAL;
+	}
+	/* FIXME: we assume reloc size is 4 dwords */
+	if (nomm) {
+		*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];
+	} else
+		*cs_reloc = p->relocs_ptr[(idx / 4)];
+	return 0;
+}

From 012e976d42d2819c79bdd4ef2843515bdd44e408 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:47 -0500
Subject: [PATCH 11/38] drm/radeon: use common next_reloc function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch eliminates ASIC-specific ***_cs_packet_next_reloc
functions and hooks up the new common function.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 129 +++++++--------------
 drivers/gpu/drm/radeon/r100.c         |  76 +++----------
 drivers/gpu/drm/radeon/r100_track.h   |   2 -
 drivers/gpu/drm/radeon/r200.c         |  12 +-
 drivers/gpu/drm/radeon/r300.c         |  16 +--
 drivers/gpu/drm/radeon/r600_cs.c      | 158 +++++---------------------
 6 files changed, 98 insertions(+), 295 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 02aeb7fc3778..211b50956153 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -36,9 +36,6 @@
 
 int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
 			   struct radeon_cs_reloc **cs_reloc);
-static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
-					  struct radeon_cs_reloc **cs_reloc);
-
 struct evergreen_cs_track {
 	u32			group_size;
 	u32			nbanks;
@@ -1008,52 +1005,6 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 	return 0;
 }
 
-/**
- * evergreen_cs_packet_next_reloc() - 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 evergreen_cs_packet_next_reloc(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 = radeon_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;
-}
-
 /**
  * evergreen_cs_packet_parse_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
@@ -1205,7 +1156,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_LSTMP_RING_BASE:
 	case SQ_PSTMP_RING_BASE:
 	case SQ_VSTMP_RING_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1234,7 +1185,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_Z_INFO:
 		track->db_z_info = radeon_get_ib_value(p, idx);
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
 						"0x%04X\n", reg);
@@ -1276,7 +1227,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_Z_READ_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1288,7 +1239,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_Z_WRITE_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1300,7 +1251,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_STENCIL_READ_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1312,7 +1263,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_STENCIL_WRITE_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1335,7 +1286,7 @@ static int evergreen_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 = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1357,7 +1308,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->streamout_dirty = true;
 		break;
 	case CP_COHER_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "missing reloc for CP_COHER_BASE "
 					"0x%04X\n", reg);
@@ -1421,7 +1372,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		tmp = (reg - CB_COLOR0_INFO) / 0x3c;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
 						"0x%04X\n", reg);
@@ -1439,7 +1390,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
 						"0x%04X\n", reg);
@@ -1500,7 +1451,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR5_ATTRIB:
 	case CB_COLOR6_ATTRIB:
 	case CB_COLOR7_ATTRIB:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1528,7 +1479,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR9_ATTRIB:
 	case CB_COLOR10_ATTRIB:
 	case CB_COLOR11_ATTRIB:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1561,7 +1512,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR6_FMASK:
 	case CB_COLOR7_FMASK:
 		tmp = (reg - CB_COLOR0_FMASK) / 0x3c;
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 			return -EINVAL;
@@ -1578,7 +1529,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR6_CMASK:
 	case CB_COLOR7_CMASK:
 		tmp = (reg - CB_COLOR0_CMASK) / 0x3c;
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 			return -EINVAL;
@@ -1616,7 +1567,7 @@ static int evergreen_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 = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1632,7 +1583,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR9_BASE:
 	case CB_COLOR10_BASE:
 	case CB_COLOR11_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1645,7 +1596,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->cb_dirty = true;
 		break;
 	case DB_HTILE_DATA_BASE:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1763,7 +1714,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_ALU_CONST_CACHE_LS_13:
 	case SQ_ALU_CONST_CACHE_LS_14:
 	case SQ_ALU_CONST_CACHE_LS_15:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1777,7 +1728,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 				 "0x%04X\n", reg);
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONFIG_REG "
 					"0x%04X\n", reg);
@@ -1791,7 +1742,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 				 "0x%04X\n", reg);
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			dev_warn(p->dev, "bad SET_CONTEXT_REG "
 					"0x%04X\n", reg);
@@ -1876,7 +1827,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			return -EINVAL;
 		}
 
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad SET PREDICATION\n");
 			return -EINVAL;
@@ -1922,7 +1873,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad INDEX_BASE\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad INDEX_BASE\n");
 			return -EINVAL;
@@ -1949,7 +1900,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad DRAW_INDEX\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad DRAW_INDEX\n");
 			return -EINVAL;
@@ -1977,7 +1928,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad DRAW_INDEX_2\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad DRAW_INDEX_2\n");
 			return -EINVAL;
@@ -2068,7 +2019,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad DISPATCH_INDIRECT\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad DISPATCH_INDIRECT\n");
 			return -EINVAL;
@@ -2089,7 +2040,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if (idx_value & 0x10) {
 			uint64_t offset;
 
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad WAIT_REG_MEM\n");
 				return -EINVAL;
@@ -2143,7 +2094,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			}
 			/* src address space is memory */
 			if (((info & 0x60000000) >> 29) == 0) {
-				r = evergreen_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
 					DRM_ERROR("bad CP DMA SRC\n");
 					return -EINVAL;
@@ -2181,7 +2132,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				return -EINVAL;
 			}
 			if (((info & 0x00300000) >> 20) == 0) {
-				r = evergreen_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
 					DRM_ERROR("bad CP DMA DST\n");
 					return -EINVAL;
@@ -2215,7 +2166,7 @@ static int evergreen_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 = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad SURFACE_SYNC\n");
 				return -EINVAL;
@@ -2231,7 +2182,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if (pkt->count) {
 			uint64_t offset;
 
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad EVENT_WRITE\n");
 				return -EINVAL;
@@ -2252,7 +2203,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad EVENT_WRITE_EOP\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad EVENT_WRITE_EOP\n");
 			return -EINVAL;
@@ -2274,7 +2225,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad EVENT_WRITE_EOS\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad EVENT_WRITE_EOS\n");
 			return -EINVAL;
@@ -2341,7 +2292,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			switch (G__SQ_CONSTANT_TYPE(radeon_get_ib_value(p, idx+1+(i*8)+7))) {
 			case SQ_TEX_VTX_VALID_TEXTURE:
 				/* tex base */
-				r = evergreen_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
 					DRM_ERROR("bad SET_RESOURCE (tex)\n");
 					return -EINVAL;
@@ -2378,7 +2329,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 					moffset = 0;
 					mipmap = NULL;
 				} else {
-					r = evergreen_cs_packet_next_reloc(p, &reloc);
+					r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 					if (r) {
 						DRM_ERROR("bad SET_RESOURCE (tex)\n");
 						return -EINVAL;
@@ -2397,7 +2348,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			{
 				uint64_t offset64;
 				/* vtx base */
-				r = evergreen_cs_packet_next_reloc(p, &reloc);
+				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
 					DRM_ERROR("bad SET_RESOURCE (vtx)\n");
 					return -EINVAL;
@@ -2479,7 +2430,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		/* Updating memory at DST_ADDRESS. */
 		if (idx_value & 0x1) {
 			u64 offset;
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n");
 				return -EINVAL;
@@ -2498,7 +2449,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		/* Reading data from SRC_ADDRESS. */
 		if (((idx_value >> 1) & 0x3) == 2) {
 			u64 offset;
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n");
 				return -EINVAL;
@@ -2523,7 +2474,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			DRM_ERROR("bad MEM_WRITE (invalid count)\n");
 			return -EINVAL;
 		}
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("bad MEM_WRITE (missing reloc)\n");
 			return -EINVAL;
@@ -2552,7 +2503,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if (idx_value & 0x1) {
 			u64 offset;
 			/* SRC is memory. */
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad COPY_DW (missing src reloc)\n");
 				return -EINVAL;
@@ -2576,7 +2527,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if (idx_value & 0x2) {
 			u64 offset;
 			/* DST is memory. */
-			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("bad COPY_DW (missing dst reloc)\n");
 				return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index cf7e35903eae..846960764a05 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1215,7 +1215,7 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
 	struct radeon_cs_reloc *reloc;
 	u32 value;
 
-	r = r100_cs_packet_next_reloc(p, &reloc);
+	r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 	if (r) {
 		DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 			  idx, reg);
@@ -1268,7 +1268,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 	}
 	track->num_arrays = c;
 	for (i = 0; i < (c - 1); i+=2, idx+=3) {
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n",
 				  pkt->opcode);
@@ -1281,7 +1281,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 		track->arrays[i + 0].esize = idx_value >> 8;
 		track->arrays[i + 0].robj = reloc->robj;
 		track->arrays[i + 0].esize &= 0x7F;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n",
 				  pkt->opcode);
@@ -1294,7 +1294,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 		track->arrays[i + 1].esize &= 0x7F;
 	}
 	if (c & 1) {
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n",
 					  pkt->opcode);
@@ -1445,54 +1445,6 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	return 0;
 }
 
-/**
- * r100_cs_packet_next_reloc() - 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.
- **/
-int r100_cs_packet_next_reloc(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 = radeon_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);
-		radeon_cs_dump_packet(p, &p3reloc);
-		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);
-		radeon_cs_dump_packet(p, &p3reloc);
-		return -EINVAL;
-	}
-	/* FIXME: we assume reloc size is 4 dwords */
-	*cs_reloc = p->relocs_ptr[(idx / 4)];
-	return 0;
-}
-
 static int r100_get_vtx_size(uint32_t vtx_fmt)
 {
 	int vtx_size;
@@ -1583,7 +1535,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			return r;
 		break;
 	case RADEON_RB3D_DEPTHOFFSET:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1596,7 +1548,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
 		break;
 	case RADEON_RB3D_COLOROFFSET:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1612,7 +1564,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_PP_TXOFFSET_1:
 	case RADEON_PP_TXOFFSET_2:
 		i = (reg - RADEON_PP_TXOFFSET_0) / 24;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1639,7 +1591,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_PP_CUBIC_OFFSET_T0_3:
 	case RADEON_PP_CUBIC_OFFSET_T0_4:
 		i = (reg - RADEON_PP_CUBIC_OFFSET_T0_0) / 4;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1657,7 +1609,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_PP_CUBIC_OFFSET_T1_3:
 	case RADEON_PP_CUBIC_OFFSET_T1_4:
 		i = (reg - RADEON_PP_CUBIC_OFFSET_T1_0) / 4;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1675,7 +1627,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_PP_CUBIC_OFFSET_T2_3:
 	case RADEON_PP_CUBIC_OFFSET_T2_4:
 		i = (reg - RADEON_PP_CUBIC_OFFSET_T2_0) / 4;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1693,7 +1645,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		track->zb_dirty = true;
 		break;
 	case RADEON_RB3D_COLORPITCH:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1764,7 +1716,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		track->zb_dirty = true;
 		break;
 	case RADEON_RB3D_ZPASS_ADDR:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1925,7 +1877,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 			return r;
 		break;
 	case PACKET3_INDX_BUFFER:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
@@ -1939,7 +1891,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case 0x23:
 		/* 3D_RNDR_GEN_INDX_PRIM on r100/r200 */
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
diff --git a/drivers/gpu/drm/radeon/r100_track.h b/drivers/gpu/drm/radeon/r100_track.h
index c81b174aaf05..eb40888bdfcc 100644
--- a/drivers/gpu/drm/radeon/r100_track.h
+++ b/drivers/gpu/drm/radeon/r100_track.h
@@ -81,8 +81,6 @@ struct r100_cs_track {
 
 int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track);
 void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track);
-int r100_cs_packet_next_reloc(struct radeon_cs_parser *p,
-			      struct radeon_cs_reloc **cs_reloc);
 
 int r100_cs_packet_parse_vline(struct radeon_cs_parser *p);
 
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index 07ea6f4a9903..b3807edb1936 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -175,7 +175,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 			return r;
 		break;
 	case RADEON_RB3D_DEPTHOFFSET:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -188,7 +188,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
 		break;
 	case RADEON_RB3D_COLOROFFSET:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -207,7 +207,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case R200_PP_TXOFFSET_4:
 	case R200_PP_TXOFFSET_5:
 		i = (reg - R200_PP_TXOFFSET_0) / 24;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -260,7 +260,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case R200_PP_CUBIC_OFFSET_F5_5:
 		i = (reg - R200_PP_TXOFFSET_0) / 24;
 		face = (reg - ((i * 24) + R200_PP_TXOFFSET_0)) / 4;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -278,7 +278,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		track->zb_dirty = true;
 		break;
 	case RADEON_RB3D_COLORPITCH:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -355,7 +355,7 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		track->zb_dirty = true;
 		break;
 	case RADEON_RB3D_ZPASS_ADDR:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 47bfca14cec8..98f723c7ef66 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -630,7 +630,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case R300_RB3D_COLOROFFSET2:
 	case R300_RB3D_COLOROFFSET3:
 		i = (reg - R300_RB3D_COLOROFFSET0) >> 2;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
@@ -643,7 +643,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
 		break;
 	case R300_ZB_DEPTHOFFSET:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
@@ -672,7 +672,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case R300_TX_OFFSET_0+56:
 	case R300_TX_OFFSET_0+60:
 		i = (reg - R300_TX_OFFSET_0) >> 2;
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
@@ -745,7 +745,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		/* RB3D_COLORPITCH2 */
 		/* RB3D_COLORPITCH3 */
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			r = r100_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					  idx, reg);
@@ -830,7 +830,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case 0x4F24:
 		/* ZB_DEPTHPITCH */
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			r = r100_cs_packet_next_reloc(p, &reloc);
+			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
 				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					  idx, reg);
@@ -1045,7 +1045,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		track->tex_dirty = true;
 		break;
 	case R300_ZB_ZPASS_ADDR:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 					idx, reg);
@@ -1087,7 +1087,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		track->cb_dirty = true;
 		break;
 	case R300_RB3D_AARESOLVE_OFFSET:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
@@ -1156,7 +1156,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p,
 			return r;
 		break;
 	case PACKET3_INDX_BUFFER:
-		r = r100_cs_packet_next_reloc(p, &reloc);
+		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
 			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 9d833728ed00..f8fe50cb4726 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);
 
 
@@ -783,99 +778,6 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 	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 = radeon_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
- * @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 = radeon_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_parse_vline() - parse userspace VLINE packet
  * @parser:		parser structure holding parsing context.
@@ -1115,7 +1017,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_028010_DB_DEPTH_INFO:
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS) &&
 		    radeon_cs_packet_next_is_pkt3_nop(p)) {
-			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);
@@ -1157,7 +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);
@@ -1180,7 +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);
@@ -1216,7 +1118,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_0280BC_CB_COLOR7_INFO:
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS) &&
 		     radeon_cs_packet_next_is_pkt3_nop(p)) {
-			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;
@@ -1288,7 +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;
@@ -1319,7 +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;
@@ -1354,7 +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);
@@ -1369,7 +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);
@@ -1382,7 +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);
@@ -1452,7 +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);
@@ -1461,7 +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);
@@ -1747,7 +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;
@@ -1788,7 +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;
@@ -1840,7 +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;
@@ -1877,7 +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;
@@ -1907,7 +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;
@@ -1937,7 +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;
@@ -1953,7 +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;
@@ -1974,7 +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;
@@ -2040,7 +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;
@@ -2054,7 +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;
@@ -2075,7 +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;
@@ -2176,7 +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;
@@ -2220,7 +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;
@@ -2239,7 +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;
@@ -2264,7 +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;
@@ -2293,7 +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;
@@ -2317,7 +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;
@@ -2505,7 +2407,7 @@ 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;
 }
 
 /*

From 4e872ae2bbb9de838212680c52dcbb85be1e4419 Mon Sep 17 00:00:00 2001
From: Ilija Hadzic <ihadzic@research.bell-labs.com>
Date: Wed, 2 Jan 2013 18:27:48 -0500
Subject: [PATCH 12/38] drm/radeon: consolidate redundant macros and constants
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After refactoring the _cs logic, we ended up with many
macros and constants that #define the same thing.
Clean'em up.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 18 +++++++++---------
 drivers/gpu/drm/radeon/evergreend.h   | 13 ++-----------
 drivers/gpu/drm/radeon/nid.h          | 13 ++-----------
 drivers/gpu/drm/radeon/r100.c         |  8 ++++----
 drivers/gpu/drm/radeon/r100d.h        | 11 -----------
 drivers/gpu/drm/radeon/r300.c         |  6 +++---
 drivers/gpu/drm/radeon/r300d.h        | 11 -----------
 drivers/gpu/drm/radeon/r600_cs.c      | 10 +++++-----
 drivers/gpu/drm/radeon/r600d.h        | 13 ++-----------
 drivers/gpu/drm/radeon/rv515d.h       | 11 -----------
 drivers/gpu/drm/radeon/si.c           | 12 ++++++------
 drivers/gpu/drm/radeon/sid.h          | 13 ++-----------
 12 files changed, 35 insertions(+), 104 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 211b50956153..4a9760ab8774 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2639,12 +2639,12 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 		}
 		p->idx += pkt.count + 2;
 		switch (pkt.type) {
-		case PACKET_TYPE0:
+		case RADEON_PACKET_TYPE0:
 			r = evergreen_cs_parse_packet0(p, &pkt);
 			break;
-		case PACKET_TYPE2:
+		case RADEON_PACKET_TYPE2:
 			break;
-		case PACKET_TYPE3:
+		case RADEON_PACKET_TYPE3:
 			r = evergreen_packet3_check(p, &pkt);
 			break;
 		default:
@@ -3395,19 +3395,19 @@ int evergreen_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 
 	do {
 		pkt.idx = idx;
-		pkt.type = CP_PACKET_GET_TYPE(ib->ptr[idx]);
-		pkt.count = CP_PACKET_GET_COUNT(ib->ptr[idx]);
+		pkt.type = RADEON_CP_PACKET_GET_TYPE(ib->ptr[idx]);
+		pkt.count = RADEON_CP_PACKET_GET_COUNT(ib->ptr[idx]);
 		pkt.one_reg_wr = 0;
 		switch (pkt.type) {
-		case PACKET_TYPE0:
+		case RADEON_PACKET_TYPE0:
 			dev_err(rdev->dev, "Packet0 not allowed!\n");
 			ret = -EINVAL;
 			break;
-		case PACKET_TYPE2:
+		case RADEON_PACKET_TYPE2:
 			idx += 1;
 			break;
-		case PACKET_TYPE3:
-			pkt.opcode = CP_PACKET3_GET_OPCODE(ib->ptr[idx]);
+		case RADEON_PACKET_TYPE3:
+			pkt.opcode = RADEON_CP_PACKET3_GET_OPCODE(ib->ptr[idx]);
 			ret = evergreen_vm_packet3_check(rdev, ib->ptr, &pkt);
 			idx += pkt.count + 2;
 			break;
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 0bfd0e9e469b..70388fe4ee59 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -980,16 +980,7 @@
 /*
  * PM4
  */
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0xFFFF) << 2)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-#define PACKET0(reg, n)	((PACKET_TYPE0 << 30) |				\
+#define PACKET0(reg, n)	((RADEON_PACKET_TYPE0 << 30) |			\
 			 (((reg) >> 2) & 0xFFFF) |			\
 			 ((n) & 0x3FFF) << 16)
 #define CP_PACKET2			0x80000000
@@ -998,7 +989,7 @@
 
 #define PACKET2(v)	(CP_PACKET2 | REG_SET(PACKET2_PAD, (v)))
 
-#define PACKET3(op, n)	((PACKET_TYPE3 << 30) |				\
+#define PACKET3(op, n)	((RADEON_PACKET_TYPE3 << 30) |			\
 			 (((op) & 0xFF) << 8) |				\
 			 ((n) & 0x3FFF) << 16)
 
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index 48e5022ee921..c4b84c5a9ab7 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -474,16 +474,7 @@
 /*
  * PM4
  */
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0xFFFF) << 2)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-#define PACKET0(reg, n)	((PACKET_TYPE0 << 30) |				\
+#define PACKET0(reg, n)	((RADEON_PACKET_TYPE0 << 30) |			\
 			 (((reg) >> 2) & 0xFFFF) |			\
 			 ((n) & 0x3FFF) << 16)
 #define CP_PACKET2			0x80000000
@@ -492,7 +483,7 @@
 
 #define PACKET2(v)	(CP_PACKET2 | REG_SET(PACKET2_PAD, (v)))
 
-#define PACKET3(op, n)	((PACKET_TYPE3 << 30) |				\
+#define PACKET3(op, n)	((RADEON_PACKET_TYPE3 << 30) |			\
 			 (((op) & 0xFF) << 8) |				\
 			 ((n) & 0x3FFF) << 16)
 
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 846960764a05..9db58530be37 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1410,7 +1410,7 @@ int r100_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 + 5);
-	reg = CP_PACKET0_GET_REG(header);
+	reg = R100_CP_PACKET0_GET_REG(header);
 	obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
 	if (!obj) {
 		DRM_ERROR("cannot find crtc %d\n", crtc_id);
@@ -1997,7 +1997,7 @@ int r100_cs_parse(struct radeon_cs_parser *p)
 		}
 		p->idx += pkt.count + 2;
 		switch (pkt.type) {
-		case PACKET_TYPE0:
+		case RADEON_PACKET_TYPE0:
 			if (p->rdev->family >= CHIP_R200)
 				r = r100_cs_parse_packet0(p, &pkt,
 					p->rdev->config.r100.reg_safe_bm,
@@ -2009,9 +2009,9 @@ int r100_cs_parse(struct radeon_cs_parser *p)
 					p->rdev->config.r100.reg_safe_bm_size,
 					&r100_packet0_check);
 			break;
-		case PACKET_TYPE2:
+		case RADEON_PACKET_TYPE2:
 			break;
-		case PACKET_TYPE3:
+		case RADEON_PACKET_TYPE3:
 			r = r100_packet3_check(p, &pkt);
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/r100d.h b/drivers/gpu/drm/radeon/r100d.h
index eab91760fae0..f0f8ee69f480 100644
--- a/drivers/gpu/drm/radeon/r100d.h
+++ b/drivers/gpu/drm/radeon/r100d.h
@@ -64,17 +64,6 @@
 			 REG_SET(PACKET3_IT_OPCODE, (op)) |		\
 			 REG_SET(PACKET3_COUNT, (n)))
 
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0x1FFF) << 2)
-#define CP_PACKET0_GET_ONE_REG_WR(h) (((h) >> 15) & 1)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-
 /* Registers */
 #define R_0000F0_RBBM_SOFT_RESET                     0x0000F0
 #define   S_0000F0_SOFT_RESET_CP(x)                    (((x) & 0x1) << 0)
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 98f723c7ef66..c60350e6872d 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1263,15 +1263,15 @@ int r300_cs_parse(struct radeon_cs_parser *p)
 		}
 		p->idx += pkt.count + 2;
 		switch (pkt.type) {
-		case PACKET_TYPE0:
+		case RADEON_PACKET_TYPE0:
 			r = r100_cs_parse_packet0(p, &pkt,
 						  p->rdev->config.r300.reg_safe_bm,
 						  p->rdev->config.r300.reg_safe_bm_size,
 						  &r300_packet0_check);
 			break;
-		case PACKET_TYPE2:
+		case RADEON_PACKET_TYPE2:
 			break;
-		case PACKET_TYPE3:
+		case RADEON_PACKET_TYPE3:
 			r = r300_packet3_check(p, &pkt);
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/r300d.h b/drivers/gpu/drm/radeon/r300d.h
index 1f519a5ffb8c..ff229a00d273 100644
--- a/drivers/gpu/drm/radeon/r300d.h
+++ b/drivers/gpu/drm/radeon/r300d.h
@@ -65,17 +65,6 @@
 			 REG_SET(PACKET3_IT_OPCODE, (op)) |		\
 			 REG_SET(PACKET3_COUNT, (n)))
 
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0x1FFF) << 2)
-#define CP_PACKET0_GET_ONE_REG_WR(h) (((h) >> 15) & 1)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-
 /* Registers */
 #define R_000148_MC_FB_LOCATION                      0x000148
 #define   S_000148_MC_FB_START(x)                      (((x) & 0xFFFF) << 0)
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index f8fe50cb4726..0d210164cdba 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -839,7 +839,7 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 		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;
@@ -882,7 +882,7 @@ int r600_cs_common_vline_parse(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) {
@@ -2282,12 +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:
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 4a53402b1852..62423b0eb2b9 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1143,19 +1143,10 @@
 /*
  * PM4
  */
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0xFFFF) << 2)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-#define PACKET0(reg, n)	((PACKET_TYPE0 << 30) |				\
+#define PACKET0(reg, n)	((RADEON_PACKET_TYPE0 << 30) |			\
 			 (((reg) >> 2) & 0xFFFF) |			\
 			 ((n) & 0x3FFF) << 16)
-#define PACKET3(op, n)	((PACKET_TYPE3 << 30) |				\
+#define PACKET3(op, n)	((RADEON_PACKET_TYPE3 << 30) |			\
 			 (((op) & 0xFF) << 8) |				\
 			 ((n) & 0x3FFF) << 16)
 
diff --git a/drivers/gpu/drm/radeon/rv515d.h b/drivers/gpu/drm/radeon/rv515d.h
index 590309a710b1..6927a200daf4 100644
--- a/drivers/gpu/drm/radeon/rv515d.h
+++ b/drivers/gpu/drm/radeon/rv515d.h
@@ -205,17 +205,6 @@
 			 REG_SET(PACKET3_IT_OPCODE, (op)) |		\
 			 REG_SET(PACKET3_COUNT, (n)))
 
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0x1FFF) << 2)
-#define CP_PACKET0_GET_ONE_REG_WR(h) (((h) >> 15) & 1)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-
 /* Registers */
 #define R_0000F0_RBBM_SOFT_RESET                     0x0000F0
 #define   S_0000F0_SOFT_RESET_CP(x)                    (((x) & 0x1) << 0)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ae8b48205a6c..f06072f5e5da 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2855,19 +2855,19 @@ int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 
 	do {
 		pkt.idx = idx;
-		pkt.type = CP_PACKET_GET_TYPE(ib->ptr[idx]);
-		pkt.count = CP_PACKET_GET_COUNT(ib->ptr[idx]);
+		pkt.type = RADEON_CP_PACKET_GET_TYPE(ib->ptr[idx]);
+		pkt.count = RADEON_CP_PACKET_GET_COUNT(ib->ptr[idx]);
 		pkt.one_reg_wr = 0;
 		switch (pkt.type) {
-		case PACKET_TYPE0:
+		case RADEON_PACKET_TYPE0:
 			dev_err(rdev->dev, "Packet0 not allowed!\n");
 			ret = -EINVAL;
 			break;
-		case PACKET_TYPE2:
+		case RADEON_PACKET_TYPE2:
 			idx += 1;
 			break;
-		case PACKET_TYPE3:
-			pkt.opcode = CP_PACKET3_GET_OPCODE(ib->ptr[idx]);
+		case RADEON_PACKET_TYPE3:
+			pkt.opcode = RADEON_CP_PACKET3_GET_OPCODE(ib->ptr[idx]);
 			if (ib->is_const_ib)
 				ret = si_vm_packet3_ce_check(rdev, ib->ptr, &pkt);
 			else {
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index c056aae814f0..76b5911585f1 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -783,16 +783,7 @@
 /*
  * PM4
  */
-#define	PACKET_TYPE0	0
-#define	PACKET_TYPE1	1
-#define	PACKET_TYPE2	2
-#define	PACKET_TYPE3	3
-
-#define CP_PACKET_GET_TYPE(h) (((h) >> 30) & 3)
-#define CP_PACKET_GET_COUNT(h) (((h) >> 16) & 0x3FFF)
-#define CP_PACKET0_GET_REG(h) (((h) & 0xFFFF) << 2)
-#define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
-#define PACKET0(reg, n)	((PACKET_TYPE0 << 30) |				\
+#define PACKET0(reg, n)	((RADEON_PACKET_TYPE0 << 30) |			\
 			 (((reg) >> 2) & 0xFFFF) |			\
 			 ((n) & 0x3FFF) << 16)
 #define CP_PACKET2			0x80000000
@@ -801,7 +792,7 @@
 
 #define PACKET2(v)	(CP_PACKET2 | REG_SET(PACKET2_PAD, (v)))
 
-#define PACKET3(op, n)	((PACKET_TYPE3 << 30) |				\
+#define PACKET3(op, n)	((RADEON_PACKET_TYPE3 << 30) |			\
 			 (((op) & 0xFF) << 8) |				\
 			 ((n) & 0x3FFF) << 16)
 

From 0fcb6155cb5c146b57a8c50e35afb9b7cfbde394 Mon Sep 17 00:00:00 2001
From: Jerome Glisse <jglisse@redhat.com>
Date: Mon, 14 Jan 2013 11:32:27 -0500
Subject: [PATCH 13/38] radeon/kms: cleanup async dma packet checking

This simplify and cleanup the async dma checking.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c    |  16 +-
 drivers/gpu/drm/radeon/evergreen_cs.c | 807 +++++++++++++-------------
 drivers/gpu/drm/radeon/evergreend.h   |  29 +-
 3 files changed, 417 insertions(+), 435 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index a2d478e8692a..a1e12bf2d0f7 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3280,14 +3280,14 @@ void evergreen_dma_fence_ring_emit(struct radeon_device *rdev,
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
 	/* write the fence */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0, 0));
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0));
 	radeon_ring_write(ring, addr & 0xfffffffc);
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff));
 	radeon_ring_write(ring, fence->seq);
 	/* generate an interrupt */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0, 0));
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0));
 	/* flush HDP */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0));
 	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
 	radeon_ring_write(ring, 1);
 }
@@ -3310,7 +3310,7 @@ void evergreen_dma_ring_ib_execute(struct radeon_device *rdev,
 		while ((next_rptr & 7) != 5)
 			next_rptr++;
 		next_rptr += 3;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 1));
 		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
 		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
 		radeon_ring_write(ring, next_rptr);
@@ -3320,8 +3320,8 @@ void evergreen_dma_ring_ib_execute(struct radeon_device *rdev,
 	 * Pad as necessary with NOPs.
 	 */
 	while ((ring->wptr & 7) != 5)
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0, 0));
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0));
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0));
 	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
 	radeon_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
 
@@ -3380,7 +3380,7 @@ int evergreen_copy_dma(struct radeon_device *rdev,
 		if (cur_size_in_dw > 0xFFFFF)
 			cur_size_in_dw = 0xFFFFF;
 		size_in_dw -= cur_size_in_dw;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, cur_size_in_dw));
 		radeon_ring_write(ring, dst_offset & 0xfffffffc);
 		radeon_ring_write(ring, src_offset & 0xfffffffc);
 		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
@@ -3488,7 +3488,7 @@ static int evergreen_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     DMA_RB_RPTR, DMA_RB_WPTR,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0));
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 4a9760ab8774..d8f5d5fcd303 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2670,16 +2670,6 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 	return 0;
 }
 
-/*
- *  DMA
- */
-
-#define GET_DMA_CMD(h) (((h) & 0xf0000000) >> 28)
-#define GET_DMA_COUNT(h) ((h) & 0x000fffff)
-#define GET_DMA_T(h) (((h) & 0x00800000) >> 23)
-#define GET_DMA_NEW(h) (((h) & 0x04000000) >> 26)
-#define GET_DMA_MISC(h) (((h) & 0x0700000) >> 20)
-
 /**
  * evergreen_dma_cs_parse() - parse the DMA IB
  * @p:		parser structure holding parsing context.
@@ -2693,9 +2683,9 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 {
 	struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx];
 	struct radeon_cs_reloc *src_reloc, *dst_reloc, *dst2_reloc;
-	u32 header, cmd, count, tiled, new_cmd, misc;
+	u32 header, cmd, count, sub_cmd;
 	volatile u32 *ib = p->ib.ptr;
-	u32 idx, idx_value;
+	u32 idx;
 	u64 src_offset, dst_offset, dst2_offset;
 	int r;
 
@@ -2709,9 +2699,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 		header = radeon_get_ib_value(p, idx);
 		cmd = GET_DMA_CMD(header);
 		count = GET_DMA_COUNT(header);
-		tiled = GET_DMA_T(header);
-		new_cmd = GET_DMA_NEW(header);
-		misc = GET_DMA_MISC(header);
+		sub_cmd = GET_DMA_SUB_CMD(header);
 
 		switch (cmd) {
 		case DMA_PACKET_WRITE:
@@ -2720,19 +2708,27 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				DRM_ERROR("bad DMA_PACKET_WRITE\n");
 				return -EINVAL;
 			}
-			if (tiled) {
+			switch (sub_cmd) {
+			/* tiled */
+			case 8:
 				dst_offset = ib[idx+1];
 				dst_offset <<= 8;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				p->idx += count + 7;
-			} else {
+				break;
+			/* linear */
+			case 0:
 				dst_offset = ib[idx+1];
 				dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 				p->idx += count + 3;
+				break;
+			default:
+				DRM_ERROR("bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, ib[idx+0]);
+				return -EINVAL;
 			}
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
 				dev_warn(p->dev, "DMA write buffer too small (%llu %lu)\n",
@@ -2751,338 +2747,330 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				DRM_ERROR("bad DMA_PACKET_COPY\n");
 				return -EINVAL;
 			}
-			if (tiled) {
-				idx_value = radeon_get_ib_value(p, idx + 2);
-				if (new_cmd) {
-					switch (misc) {
-					case 0:
-						/* L2T, frame to fields */
-						if (idx_value & (1 << 31)) {
-							DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						r = r600_dma_cs_next_reloc(p, &dst2_reloc);
-						if (r) {
-							DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						dst_offset = ib[idx+1];
-						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
-						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
-						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n",
-								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
-								 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
-								 dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
-						ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-						ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-						p->idx += 10;
-						break;
-					case 1:
-						/* L2T, T2L partial */
-						if (p->family < CHIP_CAYMAN) {
-							DRM_ERROR("L2T, T2L Partial is cayman only !\n");
-							return -EINVAL;
-						}
-						/* detile bit */
-						if (idx_value & (1 << 31)) {
-							/* tiled src, linear dst */
-							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
-
-							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-						} else {
-							/* linear src, tiled dst */
-							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-
-							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						}
-						p->idx += 12;
-						break;
-					case 3:
-						/* L2T, broadcast */
-						if (idx_value & (1 << 31)) {
-							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						r = r600_dma_cs_next_reloc(p, &dst2_reloc);
-						if (r) {
-							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						dst_offset = ib[idx+1];
-						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
-						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
-						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
-								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
-								 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
-								 dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
-						ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-						ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-						p->idx += 10;
-						break;
-					case 4:
-						/* L2T, T2L */
-						/* detile bit */
-						if (idx_value & (1 << 31)) {
-							/* tiled src, linear dst */
-							src_offset = ib[idx+1];
-							src_offset <<= 8;
-							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
-
-							dst_offset = ib[idx+7];
-							dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
-							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-						} else {
-							/* linear src, tiled dst */
-							src_offset = ib[idx+7];
-							src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
-							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-
-							dst_offset = ib[idx+1];
-							dst_offset <<= 8;
-							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						}
-						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n",
-								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, T2L dst buffer too small (%llu %lu)\n",
-								 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						p->idx += 9;
-						break;
-					case 5:
-						/* T2T partial */
-						if (p->family < CHIP_CAYMAN) {
-							DRM_ERROR("L2T, T2L Partial is cayman only !\n");
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
-						ib[idx+4] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						p->idx += 13;
-						break;
-					case 7:
-						/* L2T, broadcast */
-						if (idx_value & (1 << 31)) {
-							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						r = r600_dma_cs_next_reloc(p, &dst2_reloc);
-						if (r) {
-							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						dst_offset = ib[idx+1];
-						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
-						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
-						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
-								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
-								 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
-								 dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
-						ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-						ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-						p->idx += 10;
-						break;
-					default:
-						DRM_ERROR("bad DMA_PACKET_COPY misc %u\n", misc);
-						return -EINVAL;
-					}
+			switch (sub_cmd) {
+			/* Copy L2L, DW aligned */
+			case 0x00:
+				/* L2L, dw */
+				src_offset = ib[idx+2];
+				src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
+				dst_offset = ib[idx+1];
+				dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, dw dst buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				p->idx += 5;
+				break;
+			/* Copy L2T/T2L */
+			case 0x08:
+				/* detile bit */
+				if (ib[idx + 2] & (1 << 31)) {
+					/* tiled src, linear dst */
+					src_offset = ib[idx+1];
+					src_offset <<= 8;
+					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+
+					dst_offset = radeon_get_ib_value(p, idx + 7);
+					dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+					ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 				} else {
-					switch (misc) {
-					case 0:
-						/* detile bit */
-						if (idx_value & (1 << 31)) {
-							/* tiled src, linear dst */
-							src_offset = ib[idx+1];
-							src_offset <<= 8;
-							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
-
-							dst_offset = ib[idx+7];
-							dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
-							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-						} else {
-							/* linear src, tiled dst */
-							src_offset = ib[idx+7];
-							src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
-							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-
-							dst_offset = ib[idx+1];
-							dst_offset <<= 8;
-							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-						}
-						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
-								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
-								 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						p->idx += 9;
-						break;
-					default:
-						DRM_ERROR("bad DMA_PACKET_COPY misc %u\n", misc);
-						return -EINVAL;
-					}
+					/* linear src, tiled dst */
+					src_offset = ib[idx+7];
+					src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+					ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+
+					dst_offset = ib[idx+1];
+					dst_offset <<= 8;
+					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				}
-			} else {
-				if (new_cmd) {
-					switch (misc) {
-					case 0:
-						/* L2L, byte */
-						src_offset = ib[idx+2];
-						src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-						dst_offset = ib[idx+1];
-						dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
-						if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n",
-								 src_offset + count, radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + count) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2L, byte dst buffer too small (%llu %lu)\n",
-								 dst_offset + count, radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xffffffff);
-						ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xffffffff);
-						ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-						ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-						p->idx += 5;
-						break;
-					case 1:
-						/* L2L, partial */
-						if (p->family < CHIP_CAYMAN) {
-							DRM_ERROR("L2L Partial is cayman only !\n");
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset & 0xffffffff);
-						ib[idx+2] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-						ib[idx+4] += (u32)(dst_reloc->lobj.gpu_offset & 0xffffffff);
-						ib[idx+5] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-
-						p->idx += 9;
-						break;
-					case 4:
-						/* L2L, dw, broadcast */
-						r = r600_dma_cs_next_reloc(p, &dst2_reloc);
-						if (r) {
-							DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n");
-							return -EINVAL;
-						}
-						dst_offset = ib[idx+1];
-						dst_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-						dst2_offset = ib[idx+2];
-						dst2_offset |= ((u64)(ib[idx+5] & 0xff)) << 32;
-						src_offset = ib[idx+3];
-						src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
-						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n",
-								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2L, dw, broadcast dst buffer too small (%llu %lu)\n",
-								 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-							return -EINVAL;
-						}
-						if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-							dev_warn(p->dev, "DMA L2L, dw, broadcast dst2 buffer too small (%llu %lu)\n",
-								 dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
-							return -EINVAL;
-						}
-						ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-						ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset & 0xfffffffc);
-						ib[idx+3] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-						ib[idx+4] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-						ib[idx+5] += upper_32_bits(dst2_reloc->lobj.gpu_offset) & 0xff;
-						ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-						p->idx += 7;
-						break;
-					default:
-						DRM_ERROR("bad DMA_PACKET_COPY misc %u\n", misc);
-						return -EINVAL;
-					}
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, dst buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				p->idx += 9;
+				break;
+			/* Copy L2L, byte aligned */
+			case 0x40:
+				/* L2L, byte */
+				src_offset = ib[idx+2];
+				src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
+				dst_offset = ib[idx+1];
+				dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+				if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n",
+							src_offset + count, radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + count) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, byte dst buffer too small (%llu %lu)\n",
+							dst_offset + count, radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xffffffff);
+				ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xffffffff);
+				ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				p->idx += 5;
+				break;
+			/* Copy L2L, partial */
+			case 0x41:
+				/* L2L, partial */
+				if (p->family < CHIP_CAYMAN) {
+					DRM_ERROR("L2L Partial is cayman only !\n");
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset & 0xffffffff);
+				ib[idx+2] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+4] += (u32)(dst_reloc->lobj.gpu_offset & 0xffffffff);
+				ib[idx+5] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+
+				p->idx += 9;
+				break;
+			/* Copy L2L, DW aligned, broadcast */
+			case 0x44:
+				/* L2L, dw, broadcast */
+				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
+				if (r) {
+					DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				dst_offset = ib[idx+1];
+				dst_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
+				dst2_offset = ib[idx+2];
+				dst2_offset |= ((u64)(ib[idx+5] & 0xff)) << 32;
+				src_offset = ib[idx+3];
+				src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, dw, broadcast dst buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2L, dw, broadcast dst2 buffer too small (%llu %lu)\n",
+							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+3] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+4] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+5] += upper_32_bits(dst2_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				p->idx += 7;
+				break;
+			/* Copy L2T Frame to Field */
+			case 0x48:
+				if (ib[idx + 2] & (1 << 31)) {
+					DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
+				if (r) {
+					DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				dst_offset = ib[idx+1];
+				dst_offset <<= 8;
+				dst2_offset = ib[idx+2];
+				dst2_offset <<= 8;
+				src_offset = ib[idx+8];
+				src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
+							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
+				ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				p->idx += 10;
+				break;
+			/* Copy L2T/T2L, partial */
+			case 0x49:
+				/* L2T, T2L partial */
+				if (p->family < CHIP_CAYMAN) {
+					DRM_ERROR("L2T, T2L Partial is cayman only !\n");
+					return -EINVAL;
+				}
+				/* detile bit */
+				if (ib[idx + 2 ] & (1 << 31)) {
+					/* tiled src, linear dst */
+					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+
+					ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				} else {
+					/* linear src, tiled dst */
+					ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+
+					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				}
+				p->idx += 12;
+				break;
+			/* Copy L2T broadcast */
+			case 0x4b:
+				/* L2T, broadcast */
+				if (ib[idx + 2] & (1 << 31)) {
+					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
+				if (r) {
+					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				dst_offset = ib[idx+1];
+				dst_offset <<= 8;
+				dst2_offset = ib[idx+2];
+				dst2_offset <<= 8;
+				src_offset = ib[idx+8];
+				src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
+							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
+				ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				p->idx += 10;
+				break;
+			/* Copy L2T/T2L (tile units) */
+			case 0x4c:
+				/* L2T, T2L */
+				/* detile bit */
+				if (ib[idx + 2] & (1 << 31)) {
+					/* tiled src, linear dst */
+					src_offset = ib[idx+1];
+					src_offset <<= 8;
+					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+
+					dst_offset = ib[idx+7];
+					dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+					ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 				} else {
-					/* L2L, dw */
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
+					/* linear src, tiled dst */
+					src_offset = ib[idx+7];
+					src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+					ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+
 					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
-					if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-						dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n",
-							 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
-						return -EINVAL;
-					}
-					if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-						dev_warn(p->dev, "DMA L2L, dw dst buffer too small (%llu %lu)\n",
-							 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
-						return -EINVAL;
-					}
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-					ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-					p->idx += 5;
+					dst_offset <<= 8;
+					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				}
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, T2L dst buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				p->idx += 9;
+				break;
+			/* Copy T2T, partial (tile units) */
+			case 0x4d:
+				/* T2T partial */
+				if (p->family < CHIP_CAYMAN) {
+					DRM_ERROR("L2T, T2L Partial is cayman only !\n");
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+				ib[idx+4] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				p->idx += 13;
+				break;
+			/* Copy L2T broadcast (tile units) */
+			case 0x4f:
+				/* L2T, broadcast */
+				if (ib[idx + 2] & (1 << 31)) {
+					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
+				if (r) {
+					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					return -EINVAL;
+				}
+				dst_offset = ib[idx+1];
+				dst_offset <<= 8;
+				dst2_offset = ib[idx+2];
+				dst2_offset <<= 8;
+				src_offset = ib[idx+8];
+				src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
+							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
+							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					return -EINVAL;
+				}
+				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
+					dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
+							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					return -EINVAL;
+				}
+				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
+				ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
+				ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				p->idx += 10;
+				break;
+			default:
+				DRM_ERROR("bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, ib[idx+0]);
+				return -EINVAL;
 			}
 			break;
 		case DMA_PACKET_CONSTANT_FILL:
@@ -3435,88 +3423,79 @@ 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)
 {
 	u32 idx = 0;
-	u32 header, cmd, count, tiled, new_cmd, misc;
+	u32 header, cmd, count, sub_cmd;
 
 	do {
 		header = ib->ptr[idx];
 		cmd = GET_DMA_CMD(header);
 		count = GET_DMA_COUNT(header);
-		tiled = GET_DMA_T(header);
-		new_cmd = GET_DMA_NEW(header);
-		misc = GET_DMA_MISC(header);
+		sub_cmd = GET_DMA_SUB_CMD(header);
 
 		switch (cmd) {
 		case DMA_PACKET_WRITE:
-			if (tiled)
+			switch (sub_cmd) {
+			/* tiled */
+			case 8:
 				idx += count + 7;
-			else
+				break;
+			/* linear */
+			case 0:
 				idx += count + 3;
+				break;
+			default:
+				DRM_ERROR("bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, ib->ptr[idx]);
+				return -EINVAL;
+			}
 			break;
 		case DMA_PACKET_COPY:
-			if (tiled) {
-				if (new_cmd) {
-					switch (misc) {
-					case 0:
-						/* L2T, frame to fields */
-						idx += 10;
-						break;
-					case 1:
-						/* L2T, T2L partial */
-						idx += 12;
-						break;
-					case 3:
-						/* L2T, broadcast */
-						idx += 10;
-						break;
-					case 4:
-						/* L2T, T2L */
-						idx += 9;
-						break;
-					case 5:
-						/* T2T partial */
-						idx += 13;
-						break;
-					case 7:
-						/* L2T, broadcast */
-						idx += 10;
-						break;
-					default:
-						DRM_ERROR("bad DMA_PACKET_COPY misc %u\n", misc);
-						return -EINVAL;
-					}
-				} else {
-					switch (misc) {
-					case 0:
-						idx += 9;
-						break;
-					default:
-						DRM_ERROR("bad DMA_PACKET_COPY misc %u\n", misc);
-						return -EINVAL;
-					}
-				}
-			} else {
-				if (new_cmd) {
-					switch (misc) {
-					case 0:
-						/* L2L, byte */
-						idx += 5;
-						break;
-					case 1:
-						/* L2L, partial */
-						idx += 9;
-						break;
-					case 4:
-						/* L2L, dw, broadcast */
-						idx += 7;
-						break;
-					default:
-						DRM_ERROR("bad DMA_PACKET_COPY misc %u\n", misc);
-						return -EINVAL;
-					}
-				} else {
-					/* L2L, dw */
-					idx += 5;
-				}
+			switch (sub_cmd) {
+			/* Copy L2L, DW aligned */
+			case 0x00:
+				idx += 5;
+				break;
+			/* Copy L2T/T2L */
+			case 0x08:
+				idx += 9;
+				break;
+			/* Copy L2L, byte aligned */
+			case 0x40:
+				idx += 5;
+				break;
+			/* Copy L2L, partial */
+			case 0x41:
+				idx += 9;
+				break;
+			/* Copy L2L, DW aligned, broadcast */
+			case 0x44:
+				idx += 7;
+				break;
+			/* Copy L2T Frame to Field */
+			case 0x48:
+				idx += 10;
+				break;
+			/* Copy L2T/T2L, partial */
+			case 0x49:
+				idx += 12;
+				break;
+			/* Copy L2T broadcast */
+			case 0x4b:
+				idx += 10;
+				break;
+			/* Copy L2T/T2L (tile units) */
+			case 0x4c:
+				idx += 9;
+				break;
+			/* Copy T2T, partial (tile units) */
+			case 0x4d:
+				idx += 13;
+				break;
+			/* Copy L2T broadcast (tile units) */
+			case 0x4f:
+				idx += 10;
+				break;
+			default:
+				DRM_ERROR("bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, ib->ptr[idx]);
+				return -EINVAL;
 			}
 			break;
 		case DMA_PACKET_CONSTANT_FILL:
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 70388fe4ee59..5ad29f3fc722 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -924,20 +924,23 @@
 #define CAYMAN_DMA1_CNTL                                  0xd82c
 
 /* async DMA packets */
-#define DMA_PACKET(cmd, t, s, n)	((((cmd) & 0xF) << 28) |	\
-					 (((t) & 0x1) << 23) |		\
-					 (((s) & 0x1) << 22) |		\
-					 (((n) & 0xFFFFF) << 0))
+#define DMA_PACKET(cmd, sub_cmd, n) ((((cmd) & 0xF) << 28) |    \
+                                    (((sub_cmd) & 0xFF) << 20) |\
+                                    (((n) & 0xFFFFF) << 0))
+#define GET_DMA_CMD(h) (((h) & 0xf0000000) >> 28)
+#define GET_DMA_COUNT(h) ((h) & 0x000fffff)
+#define GET_DMA_SUB_CMD(h) (((h) & 0x0ff00000) >> 20)
+
 /* async DMA Packet types */
-#define	DMA_PACKET_WRITE				  0x2
-#define	DMA_PACKET_COPY					  0x3
-#define	DMA_PACKET_INDIRECT_BUFFER			  0x4
-#define	DMA_PACKET_SEMAPHORE				  0x5
-#define	DMA_PACKET_FENCE				  0x6
-#define	DMA_PACKET_TRAP					  0x7
-#define	DMA_PACKET_SRBM_WRITE				  0x9
-#define	DMA_PACKET_CONSTANT_FILL			  0xd
-#define	DMA_PACKET_NOP					  0xf
+#define	DMA_PACKET_WRITE                        0x2
+#define	DMA_PACKET_COPY                         0x3
+#define	DMA_PACKET_INDIRECT_BUFFER              0x4
+#define	DMA_PACKET_SEMAPHORE                    0x5
+#define	DMA_PACKET_FENCE                        0x6
+#define	DMA_PACKET_TRAP                         0x7
+#define	DMA_PACKET_SRBM_WRITE                   0x9
+#define	DMA_PACKET_CONSTANT_FILL                0xd
+#define	DMA_PACKET_NOP                          0xf
 
 /* PCIE link stuff */
 #define PCIE_LC_TRAINING_CNTL                             0xa1 /* PCIE_P */

From 14adc89298f894816ea2f3aef4d8d2d6ede18575 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Mon, 21 Jan 2013 13:58:46 +0100
Subject: [PATCH 14/38] drm/radeon: Deprecate UMS support v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

KMS support is out and stable for a couple of years now and
the userspace code has deprecated or abandoned the old UMS interface.

So make the KMS interface the default and deprecate the UMS interface
in the kernel as well.

v2: rebased on alex/drm-next-3.9-wip

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/Kconfig                |  1 +
 drivers/gpu/drm/radeon/Kconfig         | 33 ++----------
 drivers/gpu/drm/radeon/Makefile        | 10 ++--
 drivers/gpu/drm/radeon/r300_cmdbuf.c   |  2 +
 drivers/gpu/drm/radeon/r600_blit.c     | 33 +-----------
 drivers/gpu/drm/radeon/r600_blit_kms.c | 31 ++++++++++++
 drivers/gpu/drm/radeon/r600_cp.c       |  2 +
 drivers/gpu/drm/radeon/r600_cs.c       | 26 ++++++----
 drivers/gpu/drm/radeon/radeon_cp.c     |  2 +
 drivers/gpu/drm/radeon/radeon_drv.c    | 70 ++++++++++++++------------
 drivers/gpu/drm/radeon/radeon_drv.h    | 16 ++----
 drivers/gpu/drm/radeon/radeon_irq.c    |  2 +
 drivers/gpu/drm/radeon/radeon_mem.c    |  2 +
 drivers/gpu/drm/radeon/radeon_state.c  |  2 +
 14 files changed, 115 insertions(+), 117 deletions(-)

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 983201b450f1..3399b209260a 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -96,6 +96,7 @@ config DRM_RADEON
         select DRM_TTM
 	select POWER_SUPPLY
 	select HWMON
+	select BACKLIGHT_CLASS_DEVICE
 	help
 	  Choose this option if you have an ATI Radeon graphics card.  There
 	  are both PCI and AGP versions.  You don't need to choose this to
diff --git a/drivers/gpu/drm/radeon/Kconfig b/drivers/gpu/drm/radeon/Kconfig
index ea92bbe3ed37..970f8e92dbb7 100644
--- a/drivers/gpu/drm/radeon/Kconfig
+++ b/drivers/gpu/drm/radeon/Kconfig
@@ -1,31 +1,8 @@
-config DRM_RADEON_KMS
-	bool "Enable modesetting on radeon by default - NEW DRIVER"
+config DRM_RADEON_UMS
+	bool "Enable userspace modesetting on radeon (DEPRECATED)"
 	depends on DRM_RADEON
-	select BACKLIGHT_CLASS_DEVICE
 	help
-	  Choose this option if you want kernel modesetting enabled by default.
+	  Choose this option if you still need userspace modesetting.
 
-	  This is a completely new driver. It's only part of the existing drm
-	  for compatibility reasons. It requires an entirely different graphics
-	  stack above it and works very differently from the old drm stack.
-	  i.e. don't enable this unless you know what you are doing it may
-	  cause issues or bugs compared to the previous userspace driver stack.
-
-	  When kernel modesetting is enabled the IOCTL of radeon/drm
-	  driver are considered as invalid and an error message is printed
-	  in the log and they return failure.
-
-	  KMS enabled userspace will use new API to talk with the radeon/drm
-	  driver. The new API provide functions to create/destroy/share/mmap
-	  buffer object which are then managed by the kernel memory manager
-	  (here TTM). In order to submit command to the GPU the userspace
-	  provide a buffer holding the command stream, along this buffer
-	  userspace have to provide a list of buffer object used by the
-	  command stream. The kernel radeon driver will then place buffer
-	  in GPU accessible memory and will update command stream to reflect
-	  the position of the different buffers.
-
-	  The kernel will also perform security check on command stream
-	  provided by the user, we want to catch and forbid any illegal use
-	  of the GPU such as DMA into random system memory or into memory
-	  not owned by the process supplying the command stream.
+	  Userspace modesetting is deprecated for quite some time now, so
+	  enable this only if you have ancient versions of the DDX drivers.
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index a6598fd66423..bf172522ea68 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -56,8 +56,12 @@ $(obj)/r600_cs.o: $(obj)/r600_reg_safe.h
 
 $(obj)/evergreen_cs.o: $(obj)/evergreen_reg_safe.h $(obj)/cayman_reg_safe.h
 
-radeon-y := radeon_drv.o radeon_cp.o radeon_state.o radeon_mem.o \
-	radeon_irq.o r300_cmdbuf.o r600_cp.o
+radeon-y := radeon_drv.o
+
+# add UMS driver
+radeon-$(CONFIG_DRM_RADEON_UMS)+= radeon_cp.o radeon_state.o radeon_mem.o \
+	radeon_irq.o r300_cmdbuf.o r600_cp.o r600_blit.o
+
 # add KMS driver
 radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	radeon_atombios.o radeon_agp.o atombios_crtc.o radeon_combios.o \
@@ -67,7 +71,7 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	radeon_clocks.o radeon_fb.o radeon_gem.o radeon_ring.o radeon_irq_kms.o \
 	radeon_cs.o radeon_bios.o radeon_benchmark.o r100.o r300.o r420.o \
 	rs400.o rs600.o rs690.o rv515.o r520.o r600.o rv770.o radeon_test.o \
-	r200.o radeon_legacy_tv.o r600_cs.o r600_blit.o r600_blit_shaders.o \
+	r200.o radeon_legacy_tv.o r600_cs.o r600_blit_shaders.o \
 	r600_blit_kms.o radeon_pm.o atombios_dp.o r600_audio.o r600_hdmi.o \
 	evergreen.o evergreen_cs.o evergreen_blit_shaders.o evergreen_blit_kms.o \
 	evergreen_hdmi.o radeon_trace_points.o ni.o cayman_blit_shaders.o \
diff --git a/drivers/gpu/drm/radeon/r300_cmdbuf.c b/drivers/gpu/drm/radeon/r300_cmdbuf.c
index 002ab038d2ab..865e2c9980db 100644
--- a/drivers/gpu/drm/radeon/r300_cmdbuf.c
+++ b/drivers/gpu/drm/radeon/r300_cmdbuf.c
@@ -29,6 +29,8 @@
  *
  * Authors:
  *    Nicolai Haehnle <prefect_@gmx.net>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/radeon/r600_blit.c b/drivers/gpu/drm/radeon/r600_blit.c
index 77da1f9c0b8e..f651881eb0ae 100644
--- a/drivers/gpu/drm/radeon/r600_blit.c
+++ b/drivers/gpu/drm/radeon/r600_blit.c
@@ -22,6 +22,8 @@
  *
  * Authors:
  *     Alex Deucher <alexander.deucher@amd.com>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
@@ -488,37 +490,6 @@ set_default_state(drm_radeon_private_t *dev_priv)
 	ADVANCE_RING();
 }
 
-/* 23 bits of float fractional data */
-#define I2F_FRAC_BITS  23
-#define I2F_MASK ((1 << I2F_FRAC_BITS) - 1)
-
-/*
- * Converts unsigned integer into 32-bit IEEE floating point representation.
- * Will be exact from 0 to 2^24.  Above that, we round towards zero
- * as the fractional bits will not fit in a float.  (It would be better to
- * round towards even as the fpu does, but that is slower.)
- */
-__pure uint32_t int2float(uint32_t x)
-{
-	uint32_t msb, exponent, fraction;
-
-	/* Zero is special */
-	if (!x) return 0;
-
-	/* Get location of the most significant bit */
-	msb = __fls(x);
-
-	/*
-	 * Use a rotate instead of a shift because that works both leftwards
-	 * and rightwards due to the mod(32) behaviour.  This means we don't
-	 * need to check to see if we are above 2^24 or not.
-	 */
-	fraction = ror32(x, (msb - I2F_FRAC_BITS) & 0x1f) & I2F_MASK;
-	exponent = (127 + msb) << I2F_FRAC_BITS;
-
-	return fraction + exponent;
-}
-
 static int r600_nomm_get_vb(struct drm_device *dev)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index e082dca6feee..9fb5780a552f 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -31,6 +31,37 @@
 #include "r600_blit_shaders.h"
 #include "radeon_blit_common.h"
 
+/* 23 bits of float fractional data */
+#define I2F_FRAC_BITS  23
+#define I2F_MASK ((1 << I2F_FRAC_BITS) - 1)
+
+/*
+ * Converts unsigned integer into 32-bit IEEE floating point representation.
+ * Will be exact from 0 to 2^24.  Above that, we round towards zero
+ * as the fractional bits will not fit in a float.  (It would be better to
+ * round towards even as the fpu does, but that is slower.)
+ */
+__pure uint32_t int2float(uint32_t x)
+{
+	uint32_t msb, exponent, fraction;
+
+	/* Zero is special */
+	if (!x) return 0;
+
+	/* Get location of the most significant bit */
+	msb = __fls(x);
+
+	/*
+	 * Use a rotate instead of a shift because that works both leftwards
+	 * and rightwards due to the mod(32) behaviour.  This means we don't
+	 * need to check to see if we are above 2^24 or not.
+	 */
+	fraction = ror32(x, (msb - I2F_FRAC_BITS) & 0x1f) & I2F_MASK;
+	exponent = (127 + msb) << I2F_FRAC_BITS;
+
+	return fraction + exponent;
+}
+
 /* emits 21 on rv770+, 23 on r600 */
 static void
 set_render_target(struct radeon_device *rdev, int format,
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index be85f75aedda..1c51c08b1fde 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -24,6 +24,8 @@
  * Authors:
  *     Dave Airlie <airlied@redhat.com>
  *     Alex Deucher <alexander.deucher@amd.com>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 
 #include <linux/module.h>
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 0d210164cdba..931a70289033 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -2313,17 +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
@@ -2349,6 +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)
 {
@@ -2410,6 +2412,8 @@ void r600_cs_legacy_init(void)
 	r600_nomm = 1;
 }
 
+#endif
+
 /*
  *  DMA
  */
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index 9143fc45e35b..efc4f6441ef4 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -27,6 +27,8 @@
  * Authors:
  *    Kevin E. Martin <martin@valinux.com>
  *    Gareth Hughes <gareth@valinux.com>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 
 #include <linux/module.h>
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d9bf96ee299a..833484da12d9 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -123,15 +123,25 @@ struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
 					int flags);
 struct drm_gem_object *radeon_gem_prime_import(struct drm_device *dev,
 					       struct dma_buf *dma_buf);
+extern long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd,
+				    unsigned long arg);
 
 #if defined(CONFIG_DEBUG_FS)
 int radeon_debugfs_init(struct drm_minor *minor);
 void radeon_debugfs_cleanup(struct drm_minor *minor);
 #endif
 
+/* atpx handler */
+#if defined(CONFIG_VGA_SWITCHEROO)
+void radeon_register_atpx_handler(void);
+void radeon_unregister_atpx_handler(void);
+#else
+static inline void radeon_register_atpx_handler(void) {}
+static inline void radeon_unregister_atpx_handler(void) {}
+#endif
 
 int radeon_no_wb;
-int radeon_modeset = -1;
+int radeon_modeset = 1;
 int radeon_dynclks = -1;
 int radeon_r4xx_atom = 0;
 int radeon_agpmode = 0;
@@ -199,6 +209,14 @@ module_param_named(msi, radeon_msi, int, 0444);
 MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (defaul 10000 = 10 seconds, 0 = disable)");
 module_param_named(lockup_timeout, radeon_lockup_timeout, int, 0444);
 
+static struct pci_device_id pciidlist[] = {
+	radeon_PCI_IDS
+};
+
+MODULE_DEVICE_TABLE(pci, pciidlist);
+
+#ifdef CONFIG_DRM_RADEON_UMS
+
 static int radeon_suspend(struct drm_device *dev, pm_message_t state)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
@@ -227,14 +245,6 @@ static int radeon_resume(struct drm_device *dev)
 	return 0;
 }
 
-static struct pci_device_id pciidlist[] = {
-	radeon_PCI_IDS
-};
-
-#if defined(CONFIG_DRM_RADEON_KMS)
-MODULE_DEVICE_TABLE(pci, pciidlist);
-#endif
-
 static const struct file_operations radeon_driver_old_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -284,6 +294,8 @@ static struct drm_driver driver_old = {
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
 
+#endif
+
 static struct drm_driver kms_driver;
 
 static int radeon_kick_out_firmware_fb(struct pci_dev *pdev)
@@ -411,10 +423,12 @@ static struct drm_driver kms_driver = {
 static struct drm_driver *driver;
 static struct pci_driver *pdriver;
 
+#ifdef CONFIG_DRM_RADEON_UMS
 static struct pci_driver radeon_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
 };
+#endif
 
 static struct pci_driver radeon_kms_pci_driver = {
 	.name = DRIVER_NAME,
@@ -427,28 +441,6 @@ static struct pci_driver radeon_kms_pci_driver = {
 
 static int __init radeon_init(void)
 {
-	driver = &driver_old;
-	pdriver = &radeon_pci_driver;
-	driver->num_ioctls = radeon_max_ioctl;
-#ifdef CONFIG_VGA_CONSOLE
-	if (vgacon_text_force() && radeon_modeset == -1) {
-		DRM_INFO("VGACON disable radeon kernel modesetting.\n");
-		driver = &driver_old;
-		pdriver = &radeon_pci_driver;
-		driver->driver_features &= ~DRIVER_MODESET;
-		radeon_modeset = 0;
-	}
-#endif
-	/* if enabled by default */
-	if (radeon_modeset == -1) {
-#ifdef CONFIG_DRM_RADEON_KMS
-		DRM_INFO("radeon defaulting to kernel modesetting.\n");
-		radeon_modeset = 1;
-#else
-		DRM_INFO("radeon defaulting to userspace modesetting.\n");
-		radeon_modeset = 0;
-#endif
-	}
 	if (radeon_modeset == 1) {
 		DRM_INFO("radeon kernel modesetting enabled.\n");
 		driver = &kms_driver;
@@ -456,9 +448,21 @@ static int __init radeon_init(void)
 		driver->driver_features |= DRIVER_MODESET;
 		driver->num_ioctls = radeon_max_kms_ioctl;
 		radeon_register_atpx_handler();
+
+	} else {
+#ifdef CONFIG_DRM_RADEON_UMS
+		DRM_INFO("radeon userspace modesetting enabled.\n");
+		driver = &driver_old;
+		pdriver = &radeon_pci_driver;
+		driver->driver_features &= ~DRIVER_MODESET;
+		driver->num_ioctls = radeon_max_ioctl;
+#else
+		DRM_ERROR("No UMS support in radeon module!\n");
+		return -EINVAL;
+#endif
 	}
-	/* if the vga console setting is enabled still
-	 * let modprobe override it */
+
+	/* let modprobe override vga console setting */
 	return drm_pci_init(driver, pdriver);
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index e7fdf163a8ca..b369d42f7de5 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
 
+/* The rest of the file is DEPRECATED! */
+#ifdef CONFIG_DRM_RADEON_UMS
+
 enum radeon_cp_microcode_version {
 	UCODE_R100,
 	UCODE_R200,
@@ -418,8 +421,6 @@ extern int radeon_driver_open(struct drm_device *dev,
 			      struct drm_file *file_priv);
 extern long radeon_compat_ioctl(struct file *filp, unsigned int cmd,
 				unsigned long arg);
-extern long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd,
-				    unsigned long arg);
 
 extern int radeon_master_create(struct drm_device *dev, struct drm_master *master);
 extern void radeon_master_destroy(struct drm_device *dev, struct drm_master *master);
@@ -462,15 +463,6 @@ extern void r600_blit_swap(struct drm_device *dev,
 			   int sx, int sy, int dx, int dy,
 			   int w, int h, int src_pitch, int dst_pitch, int cpp);
 
-/* atpx handler */
-#if defined(CONFIG_VGA_SWITCHEROO)
-void radeon_register_atpx_handler(void);
-void radeon_unregister_atpx_handler(void);
-#else
-static inline void radeon_register_atpx_handler(void) {}
-static inline void radeon_unregister_atpx_handler(void) {}
-#endif
-
 /* Flags for stats.boxes
  */
 #define RADEON_BOX_DMA_IDLE      0x1
@@ -2167,4 +2159,6 @@ extern void radeon_commit_ring(drm_radeon_private_t *dev_priv);
 } while (0)
 
 
+#endif				/* CONFIG_DRM_RADEON_UMS */
+
 #endif				/* __RADEON_DRV_H__ */
diff --git a/drivers/gpu/drm/radeon/radeon_irq.c b/drivers/gpu/drm/radeon/radeon_irq.c
index e7710339a6a7..8d68e972789a 100644
--- a/drivers/gpu/drm/radeon/radeon_irq.c
+++ b/drivers/gpu/drm/radeon/radeon_irq.c
@@ -28,6 +28,8 @@
  * Authors:
  *    Keith Whitwell <keith@tungstengraphics.com>
  *    Michel D�zer <michel@daenzer.net>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/radeon/radeon_mem.c b/drivers/gpu/drm/radeon/radeon_mem.c
index b9f067241633..d54d2d7c9031 100644
--- a/drivers/gpu/drm/radeon/radeon_mem.c
+++ b/drivers/gpu/drm/radeon/radeon_mem.c
@@ -27,6 +27,8 @@
  *
  * Authors:
  *    Keith Whitwell <keith@tungstengraphics.com>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 8e9057b6a365..4d20910899d4 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -25,6 +25,8 @@
  * Authors:
  *    Gareth Hughes <gareth@valinux.com>
  *    Kevin E. Martin <martin@valinux.com>
+ *
+ * ------------------------ This file is DEPRECATED! -------------------------
  */
 
 #include <drm/drmP.h>

From 9ff0744c6d7745c331a484a937160f4c2c056923 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 12:18:17 -0500
Subject: [PATCH 15/38] drm/radeon: add additional reset flags

This adds further flags for fine grained reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index fa17ce026aba..ec3b739ffd79 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -136,6 +136,15 @@ extern int radeon_lockup_timeout;
 #define RADEON_RESET_GFX			(1 << 0)
 #define RADEON_RESET_COMPUTE			(1 << 1)
 #define RADEON_RESET_DMA			(1 << 2)
+#define RADEON_RESET_CP				(1 << 3)
+#define RADEON_RESET_GRBM			(1 << 4)
+#define RADEON_RESET_DMA1			(1 << 5)
+#define RADEON_RESET_RLC			(1 << 6)
+#define RADEON_RESET_SEM			(1 << 7)
+#define RADEON_RESET_IH				(1 << 8)
+#define RADEON_RESET_VMC			(1 << 9)
+#define RADEON_RESET_MC				(1 << 10)
+#define RADEON_RESET_DISPLAY			(1 << 11)
 
 /*
  * Errata workarounds.

From 410a3418a88cc1273a281d347687f736fc39dd86 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 13:05:39 -0500
Subject: [PATCH 16/38] drm/radeon: add a bios scratch asic hung helper

Used by all asic families from r600+.
Flag for the vbios and later instances of the driver
that the GPU is hung.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c |  5 +++++
 drivers/gpu/drm/radeon/ni.c        |  5 +++++
 drivers/gpu/drm/radeon/r600.c      | 17 +++++++++++++++++
 drivers/gpu/drm/radeon/radeon.h    |  1 +
 drivers/gpu/drm/radeon/si.c        |  5 +++++
 5 files changed, 33 insertions(+)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index a1e12bf2d0f7..dd1d188376bf 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2433,6 +2433,8 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
+	r600_set_bios_scratch_engine_hung(rdev, true);
+
 	evergreen_mc_stop(rdev, &save);
 	if (evergreen_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
@@ -2448,6 +2450,9 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	udelay(50);
 
 	evergreen_mc_resume(rdev, &save);
+
+	r600_set_bios_scratch_engine_hung(rdev, false);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 835992d8d067..af9e86d2fc07 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1422,6 +1422,8 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	if (reset_mask == 0)
 		return 0;
 
+	r600_set_bios_scratch_engine_hung(rdev, true);
+
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
 	dev_info(rdev->dev, "  VM_CONTEXT0_PROTECTION_FAULT_ADDR   0x%08X\n",
@@ -1448,6 +1450,9 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	udelay(50);
 
 	evergreen_mc_resume(rdev, &save);
+
+	r600_set_bios_scratch_engine_hung(rdev, false);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index becb03e8b32f..a6208178a6f2 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1254,6 +1254,18 @@ void r600_vram_scratch_fini(struct radeon_device *rdev)
 	radeon_bo_unref(&rdev->vram_scratch.robj);
 }
 
+void r600_set_bios_scratch_engine_hung(struct radeon_device *rdev, bool hung)
+{
+	u32 tmp = RREG32(R600_BIOS_3_SCRATCH);
+
+	if (hung)
+		tmp |= ATOM_S3_ASIC_GUI_ENGINE_HUNG;
+	else
+		tmp &= ~ATOM_S3_ASIC_GUI_ENGINE_HUNG;
+
+	WREG32(R600_BIOS_3_SCRATCH, tmp);
+}
+
 /* We doesn't check that the GPU really needs a reset we simply do the
  * reset, it's up to the caller to determine if the GPU needs one. We
  * might add an helper function to check that.
@@ -1389,6 +1401,8 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
+	r600_set_bios_scratch_engine_hung(rdev, true);
+
 	rv515_mc_stop(rdev, &save);
 	if (r600_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
@@ -1404,6 +1418,9 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	mdelay(1);
 
 	rv515_mc_resume(rdev, &save);
+
+	r600_set_bios_scratch_engine_hung(rdev, false);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index ec3b739ffd79..6539d6cb4bc7 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1860,6 +1860,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 /* Common functions */
 /* AGP */
 extern int radeon_gpu_reset(struct radeon_device *rdev);
+extern void r600_set_bios_scratch_engine_hung(struct radeon_device *rdev, bool hung);
 extern void radeon_agp_disable(struct radeon_device *rdev);
 extern int radeon_modeset_init(struct radeon_device *rdev);
 extern void radeon_modeset_fini(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index f06072f5e5da..1fc0e5545694 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2231,6 +2231,8 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	r600_set_bios_scratch_engine_hung(rdev, true);
+
 	evergreen_mc_stop(rdev, &save);
 	if (radeon_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
@@ -2246,6 +2248,9 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	udelay(50);
 
 	evergreen_mc_resume(rdev, &save);
+
+	r600_set_bios_scratch_engine_hung(rdev, false);
+
 	return 0;
 }
 

From d3cb781e83b39561f717358e95d357e53a0da720 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 13:53:37 -0500
Subject: [PATCH 17/38] drm/radeon: rework GPU reset on r6xx/r7xx

Update the code to better match the recommended
programming sequence for soft reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r600.c  | 249 +++++++++++++++++----------------
 drivers/gpu/drm/radeon/r600d.h |   2 +
 2 files changed, 129 insertions(+), 122 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index a6208178a6f2..083eeb0b4fd1 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1266,122 +1266,22 @@ void r600_set_bios_scratch_engine_hung(struct radeon_device *rdev, bool hung)
 	WREG32(R600_BIOS_3_SCRATCH, tmp);
 }
 
-/* We doesn't check that the GPU really needs a reset we simply do the
- * reset, it's up to the caller to determine if the GPU needs one. We
- * might add an helper function to check that.
- */
-static void r600_gpu_soft_reset_gfx(struct radeon_device *rdev)
+static void r600_print_gpu_status_regs(struct radeon_device *rdev)
 {
-	u32 grbm_busy_mask = S_008010_VC_BUSY(1) | S_008010_VGT_BUSY_NO_DMA(1) |
-				S_008010_VGT_BUSY(1) | S_008010_TA03_BUSY(1) |
-				S_008010_TC_BUSY(1) | S_008010_SX_BUSY(1) |
-				S_008010_SH_BUSY(1) | S_008010_SPI03_BUSY(1) |
-				S_008010_SMX_BUSY(1) | S_008010_SC_BUSY(1) |
-				S_008010_PA_BUSY(1) | S_008010_DB03_BUSY(1) |
-				S_008010_CR_BUSY(1) | S_008010_CB03_BUSY(1) |
-				S_008010_GUI_ACTIVE(1);
-	u32 grbm2_busy_mask = S_008014_SPI0_BUSY(1) | S_008014_SPI1_BUSY(1) |
-			S_008014_SPI2_BUSY(1) | S_008014_SPI3_BUSY(1) |
-			S_008014_TA0_BUSY(1) | S_008014_TA1_BUSY(1) |
-			S_008014_TA2_BUSY(1) | S_008014_TA3_BUSY(1) |
-			S_008014_DB0_BUSY(1) | S_008014_DB1_BUSY(1) |
-			S_008014_DB2_BUSY(1) | S_008014_DB3_BUSY(1) |
-			S_008014_CB0_BUSY(1) | S_008014_CB1_BUSY(1) |
-			S_008014_CB2_BUSY(1) | S_008014_CB3_BUSY(1);
-	u32 tmp;
-
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		return;
-
-	dev_info(rdev->dev, "  R_008010_GRBM_STATUS      = 0x%08X\n",
-		RREG32(R_008010_GRBM_STATUS));
-	dev_info(rdev->dev, "  R_008014_GRBM_STATUS2     = 0x%08X\n",
-		RREG32(R_008014_GRBM_STATUS2));
-	dev_info(rdev->dev, "  R_000E50_SRBM_STATUS      = 0x%08X\n",
-		RREG32(R_000E50_SRBM_STATUS));
-	dev_info(rdev->dev, "  R_008674_CP_STALLED_STAT1 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT1));
-	dev_info(rdev->dev, "  R_008678_CP_STALLED_STAT2 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT2));
-	dev_info(rdev->dev, "  R_00867C_CP_BUSY_STAT     = 0x%08X\n",
-		RREG32(CP_BUSY_STAT));
-	dev_info(rdev->dev, "  R_008680_CP_STAT          = 0x%08X\n",
-		RREG32(CP_STAT));
-
-	/* Disable CP parsing/prefetching */
-	WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1));
-
-	/* Check if any of the rendering block is busy and reset it */
-	if ((RREG32(R_008010_GRBM_STATUS) & grbm_busy_mask) ||
-	    (RREG32(R_008014_GRBM_STATUS2) & grbm2_busy_mask)) {
-		tmp = S_008020_SOFT_RESET_CR(1) |
-			S_008020_SOFT_RESET_DB(1) |
-			S_008020_SOFT_RESET_CB(1) |
-			S_008020_SOFT_RESET_PA(1) |
-			S_008020_SOFT_RESET_SC(1) |
-			S_008020_SOFT_RESET_SMX(1) |
-			S_008020_SOFT_RESET_SPI(1) |
-			S_008020_SOFT_RESET_SX(1) |
-			S_008020_SOFT_RESET_SH(1) |
-			S_008020_SOFT_RESET_TC(1) |
-			S_008020_SOFT_RESET_TA(1) |
-			S_008020_SOFT_RESET_VC(1) |
-			S_008020_SOFT_RESET_VGT(1);
-		dev_info(rdev->dev, "  R_008020_GRBM_SOFT_RESET=0x%08X\n", tmp);
-		WREG32(R_008020_GRBM_SOFT_RESET, tmp);
-		RREG32(R_008020_GRBM_SOFT_RESET);
-		mdelay(15);
-		WREG32(R_008020_GRBM_SOFT_RESET, 0);
-	}
-	/* Reset CP (we always reset CP) */
-	tmp = S_008020_SOFT_RESET_CP(1);
-	dev_info(rdev->dev, "R_008020_GRBM_SOFT_RESET=0x%08X\n", tmp);
-	WREG32(R_008020_GRBM_SOFT_RESET, tmp);
-	RREG32(R_008020_GRBM_SOFT_RESET);
-	mdelay(15);
-	WREG32(R_008020_GRBM_SOFT_RESET, 0);
-
 	dev_info(rdev->dev, "  R_008010_GRBM_STATUS      = 0x%08X\n",
-		RREG32(R_008010_GRBM_STATUS));
+		 RREG32(R_008010_GRBM_STATUS));
 	dev_info(rdev->dev, "  R_008014_GRBM_STATUS2     = 0x%08X\n",
-		RREG32(R_008014_GRBM_STATUS2));
+		 RREG32(R_008014_GRBM_STATUS2));
 	dev_info(rdev->dev, "  R_000E50_SRBM_STATUS      = 0x%08X\n",
-		RREG32(R_000E50_SRBM_STATUS));
+		 RREG32(R_000E50_SRBM_STATUS));
 	dev_info(rdev->dev, "  R_008674_CP_STALLED_STAT1 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT1));
+		 RREG32(CP_STALLED_STAT1));
 	dev_info(rdev->dev, "  R_008678_CP_STALLED_STAT2 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT2));
+		 RREG32(CP_STALLED_STAT2));
 	dev_info(rdev->dev, "  R_00867C_CP_BUSY_STAT     = 0x%08X\n",
-		RREG32(CP_BUSY_STAT));
+		 RREG32(CP_BUSY_STAT));
 	dev_info(rdev->dev, "  R_008680_CP_STAT          = 0x%08X\n",
-		RREG32(CP_STAT));
-
-}
-
-static void r600_gpu_soft_reset_dma(struct radeon_device *rdev)
-{
-	u32 tmp;
-
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		return;
-
-	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
-		RREG32(DMA_STATUS_REG));
-
-	/* Disable DMA */
-	tmp = RREG32(DMA_RB_CNTL);
-	tmp &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL, tmp);
-
-	/* Reset dma */
-	if (rdev->family >= CHIP_RV770)
-		WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA);
-	else
-		WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
+		 RREG32(CP_STAT));
 	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
 		RREG32(DMA_STATUS_REG));
 }
@@ -1389,9 +1289,12 @@ static void r600_gpu_soft_reset_dma(struct radeon_device *rdev)
 static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct rv515_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
+	int ret = 0;
 
 	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
 
 	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
 		reset_mask &= ~RADEON_RESET_DMA;
@@ -1401,6 +1304,8 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
+	r600_print_gpu_status_regs(rdev);
+
 	r600_set_bios_scratch_engine_hung(rdev, true);
 
 	rv515_mc_stop(rdev, &save);
@@ -1408,20 +1313,127 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
 
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE))
-		r600_gpu_soft_reset_gfx(rdev);
+	/* Disable CP parsing/prefetching */
+	if (rdev->family >= CHIP_RV770)
+		WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1) | S_0086D8_CP_PFP_HALT(1));
+	else
+		WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1));
+
+	/* disable the RLC */
+	WREG32(RLC_CNTL, 0);
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		/* Disable DMA */
+		tmp = RREG32(DMA_RB_CNTL);
+		tmp &= ~DMA_RB_ENABLE;
+		WREG32(DMA_RB_CNTL, tmp);
+	}
+
+	mdelay(50);
+
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE)) {
+		if (rdev->family >= CHIP_RV770)
+			grbm_soft_reset |= S_008020_SOFT_RESET_DB(1) |
+				S_008020_SOFT_RESET_CB(1) |
+				S_008020_SOFT_RESET_PA(1) |
+				S_008020_SOFT_RESET_SC(1) |
+				S_008020_SOFT_RESET_SPI(1) |
+				S_008020_SOFT_RESET_SX(1) |
+				S_008020_SOFT_RESET_SH(1) |
+				S_008020_SOFT_RESET_TC(1) |
+				S_008020_SOFT_RESET_TA(1) |
+				S_008020_SOFT_RESET_VC(1) |
+				S_008020_SOFT_RESET_VGT(1);
+		else
+			grbm_soft_reset |= S_008020_SOFT_RESET_CR(1) |
+				S_008020_SOFT_RESET_DB(1) |
+				S_008020_SOFT_RESET_CB(1) |
+				S_008020_SOFT_RESET_PA(1) |
+				S_008020_SOFT_RESET_SC(1) |
+				S_008020_SOFT_RESET_SMX(1) |
+				S_008020_SOFT_RESET_SPI(1) |
+				S_008020_SOFT_RESET_SX(1) |
+				S_008020_SOFT_RESET_SH(1) |
+				S_008020_SOFT_RESET_TC(1) |
+				S_008020_SOFT_RESET_TA(1) |
+				S_008020_SOFT_RESET_VC(1) |
+				S_008020_SOFT_RESET_VGT(1);
+	}
+
+	if (reset_mask & RADEON_RESET_CP) {
+		grbm_soft_reset |= S_008020_SOFT_RESET_CP(1) |
+			S_008020_SOFT_RESET_VGT(1);
 
-	if (reset_mask & RADEON_RESET_DMA)
-		r600_gpu_soft_reset_dma(rdev);
+		srbm_soft_reset |= S_000E60_SOFT_RESET_GRBM(1);
+	}
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		if (rdev->family >= CHIP_RV770)
+			srbm_soft_reset |= RV770_SOFT_RESET_DMA;
+		else
+			srbm_soft_reset |= SOFT_RESET_DMA;
+	}
+
+	if (grbm_soft_reset) {
+		tmp = RREG32(R_008020_GRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(rdev->dev, "R_008020_GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(R_008020_GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(R_008020_GRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~grbm_soft_reset;
+		WREG32(R_008020_GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(R_008020_GRBM_SOFT_RESET);
+	}
+
+	if (srbm_soft_reset) {
+		tmp = RREG32(SRBM_SOFT_RESET);
+		tmp |= srbm_soft_reset;
+		dev_info(rdev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~srbm_soft_reset;
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+	}
 
 	/* Wait a little for things to settle down */
 	mdelay(1);
 
 	rv515_mc_resume(rdev, &save);
+	udelay(50);
 
-	r600_set_bios_scratch_engine_hung(rdev, false);
+#if 0
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
+		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
+			ret = -EAGAIN;
+	}
 
-	return 0;
+	if (reset_mask & RADEON_RESET_DMA) {
+		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
+			ret = -EAGAIN;
+	}
+#endif
+
+	if (!ret)
+		r600_set_bios_scratch_engine_hung(rdev, false);
+
+	r600_print_gpu_status_regs(rdev);
+
+	return ret;
+}
+
+int r600_asic_reset(struct radeon_device *rdev)
+{
+	return r600_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
+					  RADEON_RESET_COMPUTE |
+					  RADEON_RESET_DMA |
+					  RADEON_RESET_CP));
 }
 
 bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
@@ -1465,13 +1477,6 @@ bool r600_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-int r600_asic_reset(struct radeon_device *rdev)
-{
-	return r600_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
-					  RADEON_RESET_COMPUTE |
-					  RADEON_RESET_DMA));
-}
-
 u32 r6xx_remap_render_backend(struct radeon_device *rdev,
 			      u32 tiling_pipe_num,
 			      u32 max_rb_num,
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 62423b0eb2b9..494ef768966f 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -182,6 +182,8 @@
 #define	CP_COHER_BASE					0x85F8
 #define	CP_DEBUG					0xC1FC
 #define	R_0086D8_CP_ME_CNTL			0x86D8
+#define		S_0086D8_CP_PFP_HALT(x)			(((x) & 1)<<26)
+#define		C_0086D8_CP_PFP_HALT(x)			((x) & 0xFBFFFFFF)
 #define		S_0086D8_CP_ME_HALT(x)			(((x) & 1)<<28)
 #define		C_0086D8_CP_ME_HALT(x)			((x) & 0xEFFFFFFF)
 #define	CP_ME_RAM_DATA					0xC160

From b7630473def7dad61728c68b4f23d0f2294405bc Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 14:28:41 -0500
Subject: [PATCH 18/38] drm/radeon: rework GPU reset on evergreen

Update the code to better match the recommended
programming sequence for soft reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c | 161 +++++++++++++++--------------
 1 file changed, 85 insertions(+), 76 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index dd1d188376bf..903cc544cedf 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2327,54 +2327,8 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-static void evergreen_gpu_soft_reset_gfx(struct radeon_device *rdev)
+static void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
 {
-	u32 grbm_reset = 0;
-
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		return;
-
-	dev_info(rdev->dev, "  GRBM_STATUS               = 0x%08X\n",
-		RREG32(GRBM_STATUS));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE0           = 0x%08X\n",
-		RREG32(GRBM_STATUS_SE0));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE1           = 0x%08X\n",
-		RREG32(GRBM_STATUS_SE1));
-	dev_info(rdev->dev, "  SRBM_STATUS               = 0x%08X\n",
-		RREG32(SRBM_STATUS));
-	dev_info(rdev->dev, "  R_008674_CP_STALLED_STAT1 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT1));
-	dev_info(rdev->dev, "  R_008678_CP_STALLED_STAT2 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT2));
-	dev_info(rdev->dev, "  R_00867C_CP_BUSY_STAT     = 0x%08X\n",
-		RREG32(CP_BUSY_STAT));
-	dev_info(rdev->dev, "  R_008680_CP_STAT          = 0x%08X\n",
-		RREG32(CP_STAT));
-
-	/* Disable CP parsing/prefetching */
-	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT);
-
-	/* reset all the gfx blocks */
-	grbm_reset = (SOFT_RESET_CP |
-		      SOFT_RESET_CB |
-		      SOFT_RESET_DB |
-		      SOFT_RESET_PA |
-		      SOFT_RESET_SC |
-		      SOFT_RESET_SPI |
-		      SOFT_RESET_SH |
-		      SOFT_RESET_SX |
-		      SOFT_RESET_TC |
-		      SOFT_RESET_TA |
-		      SOFT_RESET_VC |
-		      SOFT_RESET_VGT);
-
-	dev_info(rdev->dev, "  GRBM_SOFT_RESET=0x%08X\n", grbm_reset);
-	WREG32(GRBM_SOFT_RESET, grbm_reset);
-	(void)RREG32(GRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(GRBM_SOFT_RESET, 0);
-	(void)RREG32(GRBM_SOFT_RESET);
-
 	dev_info(rdev->dev, "  GRBM_STATUS               = 0x%08X\n",
 		RREG32(GRBM_STATUS));
 	dev_info(rdev->dev, "  GRBM_STATUS_SE0           = 0x%08X\n",
@@ -2391,29 +2345,6 @@ static void evergreen_gpu_soft_reset_gfx(struct radeon_device *rdev)
 		RREG32(CP_BUSY_STAT));
 	dev_info(rdev->dev, "  R_008680_CP_STAT          = 0x%08X\n",
 		RREG32(CP_STAT));
-}
-
-static void evergreen_gpu_soft_reset_dma(struct radeon_device *rdev)
-{
-	u32 tmp;
-
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		return;
-
-	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
-		RREG32(DMA_STATUS_REG));
-
-	/* Disable DMA */
-	tmp = RREG32(DMA_RB_CNTL);
-	tmp &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL, tmp);
-
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
 	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
 		RREG32(DMA_STATUS_REG));
 }
@@ -2421,9 +2352,12 @@ static void evergreen_gpu_soft_reset_dma(struct radeon_device *rdev)
 static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct evergreen_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
+	int ret = 0;
 
 	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
 
 	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
 		reset_mask &= ~RADEON_RESET_DMA;
@@ -2433,6 +2367,8 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
+	evergreen_print_gpu_status_regs(rdev);
+
 	r600_set_bios_scratch_engine_hung(rdev, true);
 
 	evergreen_mc_stop(rdev, &save);
@@ -2440,18 +2376,90 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
 
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE))
-		evergreen_gpu_soft_reset_gfx(rdev);
+	/* Disable CP parsing/prefetching */
+	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT);
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		/* Disable DMA */
+		tmp = RREG32(DMA_RB_CNTL);
+		tmp &= ~DMA_RB_ENABLE;
+		WREG32(DMA_RB_CNTL, tmp);
+	}
+
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE)) {
+		grbm_soft_reset |= SOFT_RESET_DB |
+			SOFT_RESET_CB |
+			SOFT_RESET_PA |
+			SOFT_RESET_SC |
+			SOFT_RESET_SPI |
+			SOFT_RESET_SX |
+			SOFT_RESET_SH |
+			SOFT_RESET_TC |
+			SOFT_RESET_TA |
+			SOFT_RESET_VC |
+			SOFT_RESET_VGT;
+	}
+
+	if (reset_mask & RADEON_RESET_CP) {
+		grbm_soft_reset |= SOFT_RESET_CP |
+			SOFT_RESET_VGT;
+
+		srbm_soft_reset |= SOFT_RESET_GRBM;
+	}
 
 	if (reset_mask & RADEON_RESET_DMA)
-		evergreen_gpu_soft_reset_dma(rdev);
+		srbm_soft_reset |= SOFT_RESET_DMA;
+
+	if (grbm_soft_reset) {
+		tmp = RREG32(GRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(rdev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(GRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~grbm_soft_reset;
+		WREG32(GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(GRBM_SOFT_RESET);
+	}
+
+	if (srbm_soft_reset) {
+		tmp = RREG32(SRBM_SOFT_RESET);
+		tmp |= srbm_soft_reset;
+		dev_info(rdev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~srbm_soft_reset;
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+	}
 
 	/* Wait a little for things to settle down */
 	udelay(50);
 
 	evergreen_mc_resume(rdev, &save);
+	udelay(50);
+
+#if 0
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
+		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
+			ret = -EAGAIN;
+	}
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
+			ret = -EAGAIN;
+	}
+#endif
+
+	if (!ret)
+		r600_set_bios_scratch_engine_hung(rdev, false);
 
-	r600_set_bios_scratch_engine_hung(rdev, false);
+	evergreen_print_gpu_status_regs(rdev);
 
 	return 0;
 }
@@ -2460,7 +2468,8 @@ int evergreen_asic_reset(struct radeon_device *rdev)
 {
 	return evergreen_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
 					       RADEON_RESET_COMPUTE |
-					       RADEON_RESET_DMA));
+					       RADEON_RESET_DMA |
+						RADEON_RESET_CP));
 }
 
 /* Interrupts */

From 187e359311ac101c3a0c5078e161d64789ef16e0 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 14:51:38 -0500
Subject: [PATCH 19/38] drm/radeon: rework GPU reset on cayman/TN

Update the code to better match the recommended
programming sequence for soft reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c |   2 +-
 drivers/gpu/drm/radeon/ni.c        | 198 +++++++++++++----------------
 2 files changed, 92 insertions(+), 108 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 903cc544cedf..48967a967890 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2327,7 +2327,7 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-static void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
+void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
 {
 	dev_info(rdev->dev, "  GRBM_STATUS               = 0x%08X\n",
 		RREG32(GRBM_STATUS));
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index af9e86d2fc07..88f6fbbe4be6 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -34,6 +34,7 @@
 #include "ni_reg.h"
 #include "cayman_blit_shaders.h"
 
+extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
 extern void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern int evergreen_mc_wait_for_idle(struct radeon_device *rdev);
@@ -1310,111 +1311,15 @@ void cayman_dma_fini(struct radeon_device *rdev)
 	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
 }
 
-static void cayman_gpu_soft_reset_gfx(struct radeon_device *rdev)
-{
-	u32 grbm_reset = 0;
-
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		return;
-
-	dev_info(rdev->dev, "  GRBM_STATUS               = 0x%08X\n",
-		RREG32(GRBM_STATUS));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE0           = 0x%08X\n",
-		RREG32(GRBM_STATUS_SE0));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE1           = 0x%08X\n",
-		RREG32(GRBM_STATUS_SE1));
-	dev_info(rdev->dev, "  SRBM_STATUS               = 0x%08X\n",
-		RREG32(SRBM_STATUS));
-	dev_info(rdev->dev, "  R_008674_CP_STALLED_STAT1 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT1));
-	dev_info(rdev->dev, "  R_008678_CP_STALLED_STAT2 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT2));
-	dev_info(rdev->dev, "  R_00867C_CP_BUSY_STAT     = 0x%08X\n",
-		RREG32(CP_BUSY_STAT));
-	dev_info(rdev->dev, "  R_008680_CP_STAT          = 0x%08X\n",
-		RREG32(CP_STAT));
-
-	/* Disable CP parsing/prefetching */
-	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT);
-
-	/* reset all the gfx blocks */
-	grbm_reset = (SOFT_RESET_CP |
-		      SOFT_RESET_CB |
-		      SOFT_RESET_DB |
-		      SOFT_RESET_GDS |
-		      SOFT_RESET_PA |
-		      SOFT_RESET_SC |
-		      SOFT_RESET_SPI |
-		      SOFT_RESET_SH |
-		      SOFT_RESET_SX |
-		      SOFT_RESET_TC |
-		      SOFT_RESET_TA |
-		      SOFT_RESET_VGT |
-		      SOFT_RESET_IA);
-
-	dev_info(rdev->dev, "  GRBM_SOFT_RESET=0x%08X\n", grbm_reset);
-	WREG32(GRBM_SOFT_RESET, grbm_reset);
-	(void)RREG32(GRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(GRBM_SOFT_RESET, 0);
-	(void)RREG32(GRBM_SOFT_RESET);
-
-	dev_info(rdev->dev, "  GRBM_STATUS               = 0x%08X\n",
-		RREG32(GRBM_STATUS));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE0           = 0x%08X\n",
-		RREG32(GRBM_STATUS_SE0));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE1           = 0x%08X\n",
-		RREG32(GRBM_STATUS_SE1));
-	dev_info(rdev->dev, "  SRBM_STATUS               = 0x%08X\n",
-		RREG32(SRBM_STATUS));
-	dev_info(rdev->dev, "  R_008674_CP_STALLED_STAT1 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT1));
-	dev_info(rdev->dev, "  R_008678_CP_STALLED_STAT2 = 0x%08X\n",
-		RREG32(CP_STALLED_STAT2));
-	dev_info(rdev->dev, "  R_00867C_CP_BUSY_STAT     = 0x%08X\n",
-		RREG32(CP_BUSY_STAT));
-	dev_info(rdev->dev, "  R_008680_CP_STAT          = 0x%08X\n",
-		RREG32(CP_STAT));
-
-}
-
-static void cayman_gpu_soft_reset_dma(struct radeon_device *rdev)
-{
-	u32 tmp;
-
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		return;
-
-	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
-		RREG32(DMA_STATUS_REG));
-
-	/* dma0 */
-	tmp = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
-	tmp &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, tmp);
-
-	/* dma1 */
-	tmp = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
-	tmp &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, tmp);
-
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
-	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
-		RREG32(DMA_STATUS_REG));
-
-}
-
 static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct evergreen_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
+	int ret = 0;
 
 	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
 
 	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
 		reset_mask &= ~RADEON_RESET_DMA;
@@ -1422,10 +1327,9 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	if (reset_mask == 0)
 		return 0;
 
-	r600_set_bios_scratch_engine_hung(rdev, true);
-
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
+	evergreen_print_gpu_status_regs(rdev);
 	dev_info(rdev->dev, "  VM_CONTEXT0_PROTECTION_FAULT_ADDR   0x%08X\n",
 		 RREG32(0x14F8));
 	dev_info(rdev->dev, "  VM_CONTEXT0_PROTECTION_FAULT_STATUS 0x%08X\n",
@@ -1435,23 +1339,102 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(0x14DC));
 
+	r600_set_bios_scratch_engine_hung(rdev, true);
+
 	evergreen_mc_stop(rdev, &save);
 	if (evergreen_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
 
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE))
-		cayman_gpu_soft_reset_gfx(rdev);
+	/* Disable CP parsing/prefetching */
+	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT);
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		/* dma0 */
+		tmp = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
+		tmp &= ~DMA_RB_ENABLE;
+		WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, tmp);
+
+		/* dma1 */
+		tmp = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
+		tmp &= ~DMA_RB_ENABLE;
+		WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, tmp);
+	}
+
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE)) {
+		grbm_soft_reset = SOFT_RESET_CB |
+			SOFT_RESET_DB |
+			SOFT_RESET_GDS |
+			SOFT_RESET_PA |
+			SOFT_RESET_SC |
+			SOFT_RESET_SPI |
+			SOFT_RESET_SH |
+			SOFT_RESET_SX |
+			SOFT_RESET_TC |
+			SOFT_RESET_TA |
+			SOFT_RESET_VGT |
+			SOFT_RESET_IA;
+	}
+
+	if (reset_mask & RADEON_RESET_CP) {
+		grbm_soft_reset |= SOFT_RESET_CP | SOFT_RESET_VGT;
+
+		srbm_soft_reset |= SOFT_RESET_GRBM;
+	}
 
 	if (reset_mask & RADEON_RESET_DMA)
-		cayman_gpu_soft_reset_dma(rdev);
+		srbm_soft_reset |= SOFT_RESET_DMA | SOFT_RESET_DMA1;
+
+	if (grbm_soft_reset) {
+		tmp = RREG32(GRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(rdev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(GRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~grbm_soft_reset;
+		WREG32(GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(GRBM_SOFT_RESET);
+	}
+
+	if (srbm_soft_reset) {
+		tmp = RREG32(SRBM_SOFT_RESET);
+		tmp |= srbm_soft_reset;
+		dev_info(rdev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~srbm_soft_reset;
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+	}
 
 	/* Wait a little for things to settle down */
 	udelay(50);
 
 	evergreen_mc_resume(rdev, &save);
+	udelay(50);
+
+#if 0
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
+		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
+			ret = -EAGAIN;
+	}
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
+			ret = -EAGAIN;
+	}
+#endif
+
+	if (!ret)
+		r600_set_bios_scratch_engine_hung(rdev, false);
 
-	r600_set_bios_scratch_engine_hung(rdev, false);
+	evergreen_print_gpu_status_regs(rdev);
 
 	return 0;
 }
@@ -1460,7 +1443,8 @@ int cayman_asic_reset(struct radeon_device *rdev)
 {
 	return cayman_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
 					    RADEON_RESET_COMPUTE |
-					    RADEON_RESET_DMA));
+					    RADEON_RESET_DMA |
+					    RADEON_RESET_CP));
 }
 
 /**

From 1c53467144c3af58f5dbccb13ff48466c2de0496 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 15:08:38 -0500
Subject: [PATCH 20/38] drm/radeon: rework GPU reset on cayman/TN

Update the code to better match the recommended
programming sequence for soft reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/si.c | 182 ++++++++++++++++++------------------
 1 file changed, 90 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1fc0e5545694..64841553f9ef 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -61,6 +61,7 @@ extern void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev);
 extern void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern u32 evergreen_get_number_of_dram_channels(struct radeon_device *rdev);
+extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
 
 /* get temperature in millidegrees */
 int si_get_temp(struct radeon_device *rdev)
@@ -2126,97 +2127,15 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-static void si_gpu_soft_reset_gfx(struct radeon_device *rdev)
-{
-	u32 grbm_reset = 0;
-
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		return;
-
-	dev_info(rdev->dev, "  GRBM_STATUS=0x%08X\n",
-		RREG32(GRBM_STATUS));
-	dev_info(rdev->dev, "  GRBM_STATUS2=0x%08X\n",
-		RREG32(GRBM_STATUS2));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE0=0x%08X\n",
-		RREG32(GRBM_STATUS_SE0));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE1=0x%08X\n",
-		RREG32(GRBM_STATUS_SE1));
-	dev_info(rdev->dev, "  SRBM_STATUS=0x%08X\n",
-		RREG32(SRBM_STATUS));
-
-	/* Disable CP parsing/prefetching */
-	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT | CP_CE_HALT);
-
-	/* reset all the gfx blocks */
-	grbm_reset = (SOFT_RESET_CP |
-		      SOFT_RESET_CB |
-		      SOFT_RESET_DB |
-		      SOFT_RESET_GDS |
-		      SOFT_RESET_PA |
-		      SOFT_RESET_SC |
-		      SOFT_RESET_BCI |
-		      SOFT_RESET_SPI |
-		      SOFT_RESET_SX |
-		      SOFT_RESET_TC |
-		      SOFT_RESET_TA |
-		      SOFT_RESET_VGT |
-		      SOFT_RESET_IA);
-
-	dev_info(rdev->dev, "  GRBM_SOFT_RESET=0x%08X\n", grbm_reset);
-	WREG32(GRBM_SOFT_RESET, grbm_reset);
-	(void)RREG32(GRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(GRBM_SOFT_RESET, 0);
-	(void)RREG32(GRBM_SOFT_RESET);
-
-	dev_info(rdev->dev, "  GRBM_STATUS=0x%08X\n",
-		RREG32(GRBM_STATUS));
-	dev_info(rdev->dev, "  GRBM_STATUS2=0x%08X\n",
-		RREG32(GRBM_STATUS2));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE0=0x%08X\n",
-		RREG32(GRBM_STATUS_SE0));
-	dev_info(rdev->dev, "  GRBM_STATUS_SE1=0x%08X\n",
-		RREG32(GRBM_STATUS_SE1));
-	dev_info(rdev->dev, "  SRBM_STATUS=0x%08X\n",
-		RREG32(SRBM_STATUS));
-}
-
-static void si_gpu_soft_reset_dma(struct radeon_device *rdev)
-{
-	u32 tmp;
-
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		return;
-
-	dev_info(rdev->dev, "  DMA_STATUS_REG   = 0x%08X\n",
-		RREG32(DMA_STATUS_REG));
-
-	/* dma0 */
-	tmp = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
-	tmp &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, tmp);
-
-	/* dma1 */
-	tmp = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
-	tmp &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, tmp);
-
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
-	dev_info(rdev->dev, "  DMA_STATUS_REG   = 0x%08X\n",
-		RREG32(DMA_STATUS_REG));
-}
-
 static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 {
 	struct evergreen_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
+	int ret = 0;
 
 	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE);
+		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
 
 	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
 		reset_mask &= ~RADEON_RESET_DMA;
@@ -2226,6 +2145,7 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
+	evergreen_print_gpu_status_regs(rdev);
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR));
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
@@ -2234,22 +2154,99 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	r600_set_bios_scratch_engine_hung(rdev, true);
 
 	evergreen_mc_stop(rdev, &save);
-	if (radeon_mc_wait_for_idle(rdev)) {
+	if (evergreen_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
 
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE))
-		si_gpu_soft_reset_gfx(rdev);
+	/* Disable CP parsing/prefetching */
+	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT | CP_CE_HALT);
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		/* dma0 */
+		tmp = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
+		tmp &= ~DMA_RB_ENABLE;
+		WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, tmp);
+
+		/* dma1 */
+		tmp = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
+		tmp &= ~DMA_RB_ENABLE;
+		WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, tmp);
+	}
+
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
+		grbm_soft_reset = SOFT_RESET_CB |
+			SOFT_RESET_DB |
+			SOFT_RESET_GDS |
+			SOFT_RESET_PA |
+			SOFT_RESET_SC |
+			SOFT_RESET_BCI |
+			SOFT_RESET_SPI |
+			SOFT_RESET_SX |
+			SOFT_RESET_TC |
+			SOFT_RESET_TA |
+			SOFT_RESET_VGT |
+			SOFT_RESET_IA;
+	}
+
+	if (reset_mask & RADEON_RESET_CP) {
+		grbm_soft_reset |= SOFT_RESET_CP | SOFT_RESET_VGT;
+
+		srbm_soft_reset |= SOFT_RESET_GRBM;
+	}
 
 	if (reset_mask & RADEON_RESET_DMA)
-		si_gpu_soft_reset_dma(rdev);
+		srbm_soft_reset |= SOFT_RESET_DMA | SOFT_RESET_DMA1;
+
+	if (grbm_soft_reset) {
+		tmp = RREG32(GRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(rdev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(GRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~grbm_soft_reset;
+		WREG32(GRBM_SOFT_RESET, tmp);
+		tmp = RREG32(GRBM_SOFT_RESET);
+	}
+
+	if (srbm_soft_reset) {
+		tmp = RREG32(SRBM_SOFT_RESET);
+		tmp |= srbm_soft_reset;
+		dev_info(rdev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+
+		udelay(50);
+
+		tmp &= ~srbm_soft_reset;
+		WREG32(SRBM_SOFT_RESET, tmp);
+		tmp = RREG32(SRBM_SOFT_RESET);
+	}
 
 	/* Wait a little for things to settle down */
 	udelay(50);
 
 	evergreen_mc_resume(rdev, &save);
+	udelay(50);
+
+#if 0
+	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
+		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
+			ret = -EAGAIN;
+	}
+
+	if (reset_mask & RADEON_RESET_DMA) {
+		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
+			ret = -EAGAIN;
+	}
+#endif
+
+	if (!ret)
+		r600_set_bios_scratch_engine_hung(rdev, false);
 
-	r600_set_bios_scratch_engine_hung(rdev, false);
+	evergreen_print_gpu_status_regs(rdev);
 
 	return 0;
 }
@@ -2258,7 +2255,8 @@ int si_asic_reset(struct radeon_device *rdev)
 {
 	return si_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
 					RADEON_RESET_COMPUTE |
-					RADEON_RESET_DMA));
+					RADEON_RESET_DMA |
+					RADEON_RESET_CP));
 }
 
 /* MC */

From f13f7731a20ad2ceee8fa8a940b5a68abc733e06 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 18:12:22 -0500
Subject: [PATCH 21/38] drm/radeon: use status regs to determine what to reset
 (6xx/7xx)

When we attempt the reset the GPU, look at the status registers
to determine what blocks need to be reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r500_reg.h |   1 +
 drivers/gpu/drm/radeon/r600.c     | 165 ++++++++++++++++++++++++------
 drivers/gpu/drm/radeon/r600d.h    |   2 +
 3 files changed, 136 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r500_reg.h b/drivers/gpu/drm/radeon/r500_reg.h
index ec576aaafb73..c0dc8d3ba0bb 100644
--- a/drivers/gpu/drm/radeon/r500_reg.h
+++ b/drivers/gpu/drm/radeon/r500_reg.h
@@ -355,6 +355,7 @@
 #       define AVIVO_D1CRTC_V_BLANK                             (1 << 0)
 #define AVIVO_D1CRTC_STATUS_POSITION                            0x60a0
 #define AVIVO_D1CRTC_FRAME_COUNT                                0x60a4
+#define AVIVO_D1CRTC_STATUS_HV_COUNT                            0x60ac
 #define AVIVO_D1CRTC_STEREO_CONTROL                             0x60c4
 
 #define AVIVO_D1MODE_MASTER_UPDATE_MODE                         0x60e4
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 083eeb0b4fd1..997707b2a33e 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -94,6 +94,12 @@ MODULE_FIRMWARE("radeon/SUMO_me.bin");
 MODULE_FIRMWARE("radeon/SUMO2_pfp.bin");
 MODULE_FIRMWARE("radeon/SUMO2_me.bin");
 
+static const u32 crtc_offsets[2] =
+{
+	0,
+	AVIVO_D2CRTC_H_TOTAL - AVIVO_D1CRTC_H_TOTAL
+};
+
 int r600_debugfs_mc_info_init(struct radeon_device *rdev);
 
 /* r600,rv610,rv630,rv620,rv635,rv670 */
@@ -1286,28 +1292,111 @@ static void r600_print_gpu_status_regs(struct radeon_device *rdev)
 		RREG32(DMA_STATUS_REG));
 }
 
-static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+static bool r600_is_display_hung(struct radeon_device *rdev)
 {
-	struct rv515_mc_save save;
-	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 crtc_hung = 0;
+	u32 crtc_status[2];
+	u32 i, j, tmp;
+
+	for (i = 0; i < rdev->num_crtc; i++) {
+		if (RREG32(AVIVO_D1CRTC_CONTROL + crtc_offsets[i]) & AVIVO_CRTC_EN) {
+			crtc_status[i] = RREG32(AVIVO_D1CRTC_STATUS_HV_COUNT + crtc_offsets[i]);
+			crtc_hung |= (1 << i);
+		}
+	}
+
+	for (j = 0; j < 10; j++) {
+		for (i = 0; i < rdev->num_crtc; i++) {
+			if (crtc_hung & (1 << i)) {
+				tmp = RREG32(AVIVO_D1CRTC_STATUS_HV_COUNT + crtc_offsets[i]);
+				if (tmp != crtc_status[i])
+					crtc_hung &= ~(1 << i);
+			}
+		}
+		if (crtc_hung == 0)
+			return false;
+		udelay(100);
+	}
+
+	return true;
+}
+
+static u32 r600_gpu_check_soft_reset(struct radeon_device *rdev)
+{
+	u32 reset_mask = 0;
 	u32 tmp;
-	int ret = 0;
 
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
+	/* GRBM_STATUS */
+	tmp = RREG32(R_008010_GRBM_STATUS);
+	if (rdev->family >= CHIP_RV770) {
+		if (G_008010_PA_BUSY(tmp) | G_008010_SC_BUSY(tmp) |
+		    G_008010_SH_BUSY(tmp) | G_008010_SX_BUSY(tmp) |
+		    G_008010_TA_BUSY(tmp) | G_008010_VGT_BUSY(tmp) |
+		    G_008010_DB03_BUSY(tmp) | G_008010_CB03_BUSY(tmp) |
+		    G_008010_SPI03_BUSY(tmp) | G_008010_VGT_BUSY_NO_DMA(tmp))
+			reset_mask |= RADEON_RESET_GFX;
+	} else {
+		if (G_008010_PA_BUSY(tmp) | G_008010_SC_BUSY(tmp) |
+		    G_008010_SH_BUSY(tmp) | G_008010_SX_BUSY(tmp) |
+		    G_008010_TA03_BUSY(tmp) | G_008010_VGT_BUSY(tmp) |
+		    G_008010_DB03_BUSY(tmp) | G_008010_CB03_BUSY(tmp) |
+		    G_008010_SPI03_BUSY(tmp) | G_008010_VGT_BUSY_NO_DMA(tmp))
+			reset_mask |= RADEON_RESET_GFX;
+	}
+
+	if (G_008010_CF_RQ_PENDING(tmp) | G_008010_PF_RQ_PENDING(tmp) |
+	    G_008010_CP_BUSY(tmp) | G_008010_CP_COHERENCY_BUSY(tmp))
+		reset_mask |= RADEON_RESET_CP;
+
+	if (G_008010_GRBM_EE_BUSY(tmp))
+		reset_mask |= RADEON_RESET_GRBM | RADEON_RESET_GFX | RADEON_RESET_CP;
+
+	/* DMA_STATUS_REG */
+	tmp = RREG32(DMA_STATUS_REG);
+	if (!(tmp & DMA_IDLE))
+		reset_mask |= RADEON_RESET_DMA;
+
+	/* SRBM_STATUS */
+	tmp = RREG32(R_000E50_SRBM_STATUS);
+	if (G_000E50_RLC_RQ_PENDING(tmp) | G_000E50_RLC_BUSY(tmp))
+		reset_mask |= RADEON_RESET_RLC;
+
+	if (G_000E50_IH_BUSY(tmp))
+		reset_mask |= RADEON_RESET_IH;
 
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		reset_mask &= ~RADEON_RESET_DMA;
+	if (G_000E50_SEM_BUSY(tmp))
+		reset_mask |= RADEON_RESET_SEM;
+
+	if (G_000E50_GRBM_RQ_PENDING(tmp))
+		reset_mask |= RADEON_RESET_GRBM;
+
+	if (G_000E50_VMC_BUSY(tmp))
+		reset_mask |= RADEON_RESET_VMC;
+
+	if (G_000E50_MCB_BUSY(tmp) | G_000E50_MCDZ_BUSY(tmp) |
+	    G_000E50_MCDY_BUSY(tmp) | G_000E50_MCDX_BUSY(tmp) |
+	    G_000E50_MCDW_BUSY(tmp))
+		reset_mask |= RADEON_RESET_MC;
+
+	if (r600_is_display_hung(rdev))
+		reset_mask |= RADEON_RESET_DISPLAY;
+
+	return reset_mask;
+}
+
+static void r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+{
+	struct rv515_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
 
 	if (reset_mask == 0)
-		return 0;
+		return;
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
 	r600_print_gpu_status_regs(rdev);
 
-	r600_set_bios_scratch_engine_hung(rdev, true);
-
 	rv515_mc_stop(rdev, &save);
 	if (r600_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
@@ -1374,6 +1463,24 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 			srbm_soft_reset |= SOFT_RESET_DMA;
 	}
 
+	if (reset_mask & RADEON_RESET_RLC)
+		srbm_soft_reset |= S_000E60_SOFT_RESET_RLC(1);
+
+	if (reset_mask & RADEON_RESET_SEM)
+		srbm_soft_reset |= S_000E60_SOFT_RESET_SEM(1);
+
+	if (reset_mask & RADEON_RESET_IH)
+		srbm_soft_reset |= S_000E60_SOFT_RESET_IH(1);
+
+	if (reset_mask & RADEON_RESET_GRBM)
+		srbm_soft_reset |= S_000E60_SOFT_RESET_GRBM(1);
+
+	if (reset_mask & RADEON_RESET_MC)
+		srbm_soft_reset |= S_000E60_SOFT_RESET_MC(1);
+
+	if (reset_mask & RADEON_RESET_VMC)
+		srbm_soft_reset |= S_000E60_SOFT_RESET_VMC(1);
+
 	if (grbm_soft_reset) {
 		tmp = RREG32(R_008020_GRBM_SOFT_RESET);
 		tmp |= grbm_soft_reset;
@@ -1408,32 +1515,26 @@ static int r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	rv515_mc_resume(rdev, &save);
 	udelay(50);
 
-#if 0
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
-		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
-			ret = -EAGAIN;
-	}
-
-	if (reset_mask & RADEON_RESET_DMA) {
-		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
-			ret = -EAGAIN;
-	}
-#endif
-
-	if (!ret)
-		r600_set_bios_scratch_engine_hung(rdev, false);
-
 	r600_print_gpu_status_regs(rdev);
-
-	return ret;
 }
 
 int r600_asic_reset(struct radeon_device *rdev)
 {
-	return r600_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
-					  RADEON_RESET_COMPUTE |
-					  RADEON_RESET_DMA |
-					  RADEON_RESET_CP));
+	u32 reset_mask;
+
+	reset_mask = r600_gpu_check_soft_reset(rdev);
+
+	if (reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, true);
+
+	r600_gpu_soft_reset(rdev, reset_mask);
+
+	reset_mask = r600_gpu_check_soft_reset(rdev);
+
+	if (!reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, false);
+
+	return 0;
 }
 
 bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 494ef768966f..a42ba11a3bed 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1321,6 +1321,7 @@
 #define		G_008010_VC_BUSY(x)			(((x) >> 11) & 1)
 #define		G_008010_DB03_CLEAN(x)			(((x) >> 12) & 1)
 #define		G_008010_CB03_CLEAN(x)			(((x) >> 13) & 1)
+#define		G_008010_TA_BUSY(x)			(((x) >> 14) & 1)
 #define		G_008010_VGT_BUSY_NO_DMA(x)		(((x) >> 16) & 1)
 #define		G_008010_VGT_BUSY(x)			(((x) >> 17) & 1)
 #define		G_008010_TA03_BUSY(x)			(((x) >> 18) & 1)
@@ -1388,6 +1389,7 @@
 #define		G_000E50_MCDW_BUSY(x)			(((x) >> 13) & 1)
 #define		G_000E50_SEM_BUSY(x)			(((x) >> 14) & 1)
 #define		G_000E50_RLC_BUSY(x)			(((x) >> 15) & 1)
+#define		G_000E50_IH_BUSY(x)			(((x) >> 17) & 1)
 #define		G_000E50_BIF_BUSY(x)			(((x) >> 29) & 1)
 #define	R_000E60_SRBM_SOFT_RESET			0x0E60
 #define		S_000E60_SOFT_RESET_BIF(x)		(((x) & 1) << 1)

From a65a4369f7a69281b65ed42b7fa2a8e8d6ff585f Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 18:55:54 -0500
Subject: [PATCH 22/38] drm/radeon: use status regs to determine what to reset
 (evergreen)

When we attempt the reset the GPU, look at the status registers
to determine what blocks need to be reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c     | 164 ++++++++++++++++++++-----
 drivers/gpu/drm/radeon/evergreen_reg.h |   1 +
 drivers/gpu/drm/radeon/evergreend.h    |  12 ++
 3 files changed, 145 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 48967a967890..8b73743b0b3f 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2337,6 +2337,8 @@ void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
 		RREG32(GRBM_STATUS_SE1));
 	dev_info(rdev->dev, "  SRBM_STATUS               = 0x%08X\n",
 		RREG32(SRBM_STATUS));
+	dev_info(rdev->dev, "  SRBM_STATUS2              = 0x%08X\n",
+		RREG32(SRBM_STATUS2));
 	dev_info(rdev->dev, "  R_008674_CP_STALLED_STAT1 = 0x%08X\n",
 		RREG32(CP_STALLED_STAT1));
 	dev_info(rdev->dev, "  R_008678_CP_STALLED_STAT2 = 0x%08X\n",
@@ -2349,28 +2351,111 @@ void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
 		RREG32(DMA_STATUS_REG));
 }
 
-static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+static bool evergreen_is_display_hung(struct radeon_device *rdev)
 {
-	struct evergreen_mc_save save;
-	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 crtc_hung = 0;
+	u32 crtc_status[6];
+	u32 i, j, tmp;
+
+	for (i = 0; i < rdev->num_crtc; i++) {
+		if (RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]) & EVERGREEN_CRTC_MASTER_EN) {
+			crtc_status[i] = RREG32(EVERGREEN_CRTC_STATUS_HV_COUNT + crtc_offsets[i]);
+			crtc_hung |= (1 << i);
+		}
+	}
+
+	for (j = 0; j < 10; j++) {
+		for (i = 0; i < rdev->num_crtc; i++) {
+			if (crtc_hung & (1 << i)) {
+				tmp = RREG32(EVERGREEN_CRTC_STATUS_HV_COUNT + crtc_offsets[i]);
+				if (tmp != crtc_status[i])
+					crtc_hung &= ~(1 << i);
+			}
+		}
+		if (crtc_hung == 0)
+			return false;
+		udelay(100);
+	}
+
+	return true;
+}
+
+static u32 evergreen_gpu_check_soft_reset(struct radeon_device *rdev)
+{
+	u32 reset_mask = 0;
 	u32 tmp;
-	int ret = 0;
 
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
+	/* GRBM_STATUS */
+	tmp = RREG32(GRBM_STATUS);
+	if (tmp & (PA_BUSY | SC_BUSY |
+		   SH_BUSY | SX_BUSY |
+		   TA_BUSY | VGT_BUSY |
+		   DB_BUSY | CB_BUSY |
+		   SPI_BUSY | VGT_BUSY_NO_DMA))
+		reset_mask |= RADEON_RESET_GFX;
+
+	if (tmp & (CF_RQ_PENDING | PF_RQ_PENDING |
+		   CP_BUSY | CP_COHERENCY_BUSY))
+		reset_mask |= RADEON_RESET_CP;
+
+	if (tmp & GRBM_EE_BUSY)
+		reset_mask |= RADEON_RESET_GRBM | RADEON_RESET_GFX | RADEON_RESET_CP;
 
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		reset_mask &= ~RADEON_RESET_DMA;
+	/* DMA_STATUS_REG */
+	tmp = RREG32(DMA_STATUS_REG);
+	if (!(tmp & DMA_IDLE))
+		reset_mask |= RADEON_RESET_DMA;
+
+	/* SRBM_STATUS2 */
+	tmp = RREG32(SRBM_STATUS2);
+	if (tmp & DMA_BUSY)
+		reset_mask |= RADEON_RESET_DMA;
+
+	/* SRBM_STATUS */
+	tmp = RREG32(SRBM_STATUS);
+	if (tmp & (RLC_RQ_PENDING | RLC_BUSY))
+		reset_mask |= RADEON_RESET_RLC;
+
+	if (tmp & IH_BUSY)
+		reset_mask |= RADEON_RESET_IH;
+
+	if (tmp & SEM_BUSY)
+		reset_mask |= RADEON_RESET_SEM;
+
+	if (tmp & GRBM_RQ_PENDING)
+		reset_mask |= RADEON_RESET_GRBM;
+
+	if (tmp & VMC_BUSY)
+		reset_mask |= RADEON_RESET_VMC;
+
+	if (tmp & (MCB_BUSY | MCB_NON_DISPLAY_BUSY |
+		   MCC_BUSY | MCD_BUSY))
+		reset_mask |= RADEON_RESET_MC;
+
+	if (evergreen_is_display_hung(rdev))
+		reset_mask |= RADEON_RESET_DISPLAY;
+
+	/* VM_L2_STATUS */
+	tmp = RREG32(VM_L2_STATUS);
+	if (tmp & L2_BUSY)
+		reset_mask |= RADEON_RESET_VMC;
+
+	return reset_mask;
+}
+
+static void evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+{
+	struct evergreen_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
 
 	if (reset_mask == 0)
-		return 0;
+		return;
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
 	evergreen_print_gpu_status_regs(rdev);
 
-	r600_set_bios_scratch_engine_hung(rdev, true);
-
 	evergreen_mc_stop(rdev, &save);
 	if (evergreen_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
@@ -2410,6 +2495,27 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	if (reset_mask & RADEON_RESET_DMA)
 		srbm_soft_reset |= SOFT_RESET_DMA;
 
+	if (reset_mask & RADEON_RESET_DISPLAY)
+		srbm_soft_reset |= SOFT_RESET_DC;
+
+	if (reset_mask & RADEON_RESET_RLC)
+		srbm_soft_reset |= SOFT_RESET_RLC;
+
+	if (reset_mask & RADEON_RESET_SEM)
+		srbm_soft_reset |= SOFT_RESET_SEM;
+
+	if (reset_mask & RADEON_RESET_IH)
+		srbm_soft_reset |= SOFT_RESET_IH;
+
+	if (reset_mask & RADEON_RESET_GRBM)
+		srbm_soft_reset |= SOFT_RESET_GRBM;
+
+	if (reset_mask & RADEON_RESET_VMC)
+		srbm_soft_reset |= SOFT_RESET_VMC;
+
+	if (reset_mask & RADEON_RESET_MC)
+		srbm_soft_reset |= SOFT_RESET_MC;
+
 	if (grbm_soft_reset) {
 		tmp = RREG32(GRBM_SOFT_RESET);
 		tmp |= grbm_soft_reset;
@@ -2444,32 +2550,26 @@ static int evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	evergreen_mc_resume(rdev, &save);
 	udelay(50);
 
-#if 0
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
-		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
-			ret = -EAGAIN;
-	}
-
-	if (reset_mask & RADEON_RESET_DMA) {
-		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
-			ret = -EAGAIN;
-	}
-#endif
-
-	if (!ret)
-		r600_set_bios_scratch_engine_hung(rdev, false);
-
 	evergreen_print_gpu_status_regs(rdev);
-
-	return 0;
 }
 
 int evergreen_asic_reset(struct radeon_device *rdev)
 {
-	return evergreen_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
-					       RADEON_RESET_COMPUTE |
-					       RADEON_RESET_DMA |
-						RADEON_RESET_CP));
+	u32 reset_mask;
+
+	reset_mask = evergreen_gpu_check_soft_reset(rdev);
+
+	if (reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, true);
+
+	evergreen_gpu_soft_reset(rdev, reset_mask);
+
+	reset_mask = evergreen_gpu_check_soft_reset(rdev);
+
+	if (!reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, false);
+
+	return 0;
 }
 
 /* Interrupts */
diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h
index 034f4c22e5db..f585be16e2d5 100644
--- a/drivers/gpu/drm/radeon/evergreen_reg.h
+++ b/drivers/gpu/drm/radeon/evergreen_reg.h
@@ -223,6 +223,7 @@
 #define EVERGREEN_CRTC_STATUS                           0x6e8c
 #       define EVERGREEN_CRTC_V_BLANK                   (1 << 0)
 #define EVERGREEN_CRTC_STATUS_POSITION                  0x6e90
+#define EVERGREEN_CRTC_STATUS_HV_COUNT                  0x6ea0
 #define EVERGREEN_MASTER_UPDATE_MODE                    0x6ef8
 #define EVERGREEN_CRTC_UPDATE_LOCK                      0x6ed4
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 5ad29f3fc722..982d25ad9af3 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -729,6 +729,18 @@
 #define	WAIT_UNTIL					0x8040
 
 #define	SRBM_STATUS				        0x0E50
+#define		RLC_RQ_PENDING 				(1 << 3)
+#define		GRBM_RQ_PENDING 			(1 << 5)
+#define		VMC_BUSY 				(1 << 8)
+#define		MCB_BUSY 				(1 << 9)
+#define		MCB_NON_DISPLAY_BUSY 			(1 << 10)
+#define		MCC_BUSY 				(1 << 11)
+#define		MCD_BUSY 				(1 << 12)
+#define		SEM_BUSY 				(1 << 14)
+#define		RLC_BUSY 				(1 << 15)
+#define		IH_BUSY 				(1 << 17)
+#define	SRBM_STATUS2				        0x0EC4
+#define		DMA_BUSY 				(1 << 5)
 #define	SRBM_SOFT_RESET				        0x0E60
 #define		SRBM_SOFT_RESET_ALL_MASK    	       	0x00FEEFA6
 #define		SOFT_RESET_BIF				(1 << 1)

From 168757ea854b7dd8eac3962753ed75a542ebca92 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 19:17:22 -0500
Subject: [PATCH 23/38] drm/radeon: use status regs to determine what to reset
 (cayman)

When we attempt the reset the GPU, look at the status registers
to determine what blocks need to be reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c |   6 +-
 drivers/gpu/drm/radeon/ni.c        | 148 +++++++++++++++++++++++------
 drivers/gpu/drm/radeon/nid.h       |  14 +++
 3 files changed, 136 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 8b73743b0b3f..fd5e0025b656 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2349,9 +2349,13 @@ void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
 		RREG32(CP_STAT));
 	dev_info(rdev->dev, "  R_00D034_DMA_STATUS_REG   = 0x%08X\n",
 		RREG32(DMA_STATUS_REG));
+	if (rdev->family >= CHIP_CAYMAN) {
+		dev_info(rdev->dev, "  R_00D834_DMA_STATUS_REG   = 0x%08X\n",
+			 RREG32(DMA_STATUS_REG + 0x800));
+	}
 }
 
-static bool evergreen_is_display_hung(struct radeon_device *rdev)
+bool evergreen_is_display_hung(struct radeon_device *rdev)
 {
 	u32 crtc_hung = 0;
 	u32 crtc_status[6];
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 88f6fbbe4be6..eee013f5699a 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -34,6 +34,7 @@
 #include "ni_reg.h"
 #include "cayman_blit_shaders.h"
 
+extern bool evergreen_is_display_hung(struct radeon_device *rdev);
 extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
 extern void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save);
@@ -1311,21 +1312,86 @@ void cayman_dma_fini(struct radeon_device *rdev)
 	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
 }
 
-static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+static u32 cayman_gpu_check_soft_reset(struct radeon_device *rdev)
 {
-	struct evergreen_mc_save save;
-	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 reset_mask = 0;
 	u32 tmp;
-	int ret = 0;
 
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
+	/* GRBM_STATUS */
+	tmp = RREG32(GRBM_STATUS);
+	if (tmp & (PA_BUSY | SC_BUSY |
+		   SH_BUSY | SX_BUSY |
+		   TA_BUSY | VGT_BUSY |
+		   DB_BUSY | CB_BUSY |
+		   GDS_BUSY | SPI_BUSY |
+		   IA_BUSY | IA_BUSY_NO_DMA))
+		reset_mask |= RADEON_RESET_GFX;
+
+	if (tmp & (CF_RQ_PENDING | PF_RQ_PENDING |
+		   CP_BUSY | CP_COHERENCY_BUSY))
+		reset_mask |= RADEON_RESET_CP;
+
+	if (tmp & GRBM_EE_BUSY)
+		reset_mask |= RADEON_RESET_GRBM | RADEON_RESET_GFX | RADEON_RESET_CP;
+
+	/* DMA_STATUS_REG 0 */
+	tmp = RREG32(DMA_STATUS_REG + DMA0_REGISTER_OFFSET);
+	if (!(tmp & DMA_IDLE))
+		reset_mask |= RADEON_RESET_DMA;
+
+	/* DMA_STATUS_REG 1 */
+	tmp = RREG32(DMA_STATUS_REG + DMA1_REGISTER_OFFSET);
+	if (!(tmp & DMA_IDLE))
+		reset_mask |= RADEON_RESET_DMA1;
+
+	/* SRBM_STATUS2 */
+	tmp = RREG32(SRBM_STATUS2);
+	if (tmp & DMA_BUSY)
+		reset_mask |= RADEON_RESET_DMA;
+
+	if (tmp & DMA1_BUSY)
+		reset_mask |= RADEON_RESET_DMA1;
+
+	/* SRBM_STATUS */
+	tmp = RREG32(SRBM_STATUS);
+	if (tmp & (RLC_RQ_PENDING | RLC_BUSY))
+		reset_mask |= RADEON_RESET_RLC;
+
+	if (tmp & IH_BUSY)
+		reset_mask |= RADEON_RESET_IH;
+
+	if (tmp & SEM_BUSY)
+		reset_mask |= RADEON_RESET_SEM;
+
+	if (tmp & GRBM_RQ_PENDING)
+		reset_mask |= RADEON_RESET_GRBM;
+
+	if (tmp & VMC_BUSY)
+		reset_mask |= RADEON_RESET_VMC;
 
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		reset_mask &= ~RADEON_RESET_DMA;
+	if (tmp & (MCB_BUSY | MCB_NON_DISPLAY_BUSY |
+		   MCC_BUSY | MCD_BUSY))
+		reset_mask |= RADEON_RESET_MC;
+
+	if (evergreen_is_display_hung(rdev))
+		reset_mask |= RADEON_RESET_DISPLAY;
+
+	/* VM_L2_STATUS */
+	tmp = RREG32(VM_L2_STATUS);
+	if (tmp & L2_BUSY)
+		reset_mask |= RADEON_RESET_VMC;
+
+	return reset_mask;
+}
+
+static void cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+{
+	struct evergreen_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
 
 	if (reset_mask == 0)
-		return 0;
+		return;
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
@@ -1354,7 +1420,9 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		tmp = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
 		tmp &= ~DMA_RB_ENABLE;
 		WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, tmp);
+	}
 
+	if (reset_mask & RADEON_RESET_DMA1) {
 		/* dma1 */
 		tmp = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
 		tmp &= ~DMA_RB_ENABLE;
@@ -1383,7 +1451,31 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	}
 
 	if (reset_mask & RADEON_RESET_DMA)
-		srbm_soft_reset |= SOFT_RESET_DMA | SOFT_RESET_DMA1;
+		srbm_soft_reset |= SOFT_RESET_DMA;
+
+	if (reset_mask & RADEON_RESET_DMA1)
+		srbm_soft_reset |= SOFT_RESET_DMA1;
+
+	if (reset_mask & RADEON_RESET_DISPLAY)
+		srbm_soft_reset |= SOFT_RESET_DC;
+
+	if (reset_mask & RADEON_RESET_RLC)
+		srbm_soft_reset |= SOFT_RESET_RLC;
+
+	if (reset_mask & RADEON_RESET_SEM)
+		srbm_soft_reset |= SOFT_RESET_SEM;
+
+	if (reset_mask & RADEON_RESET_IH)
+		srbm_soft_reset |= SOFT_RESET_IH;
+
+	if (reset_mask & RADEON_RESET_GRBM)
+		srbm_soft_reset |= SOFT_RESET_GRBM;
+
+	if (reset_mask & RADEON_RESET_VMC)
+		srbm_soft_reset |= SOFT_RESET_VMC;
+
+	if (reset_mask & RADEON_RESET_MC)
+		srbm_soft_reset |= SOFT_RESET_MC;
 
 	if (grbm_soft_reset) {
 		tmp = RREG32(GRBM_SOFT_RESET);
@@ -1419,32 +1511,26 @@ static int cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	evergreen_mc_resume(rdev, &save);
 	udelay(50);
 
-#if 0
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
-		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
-			ret = -EAGAIN;
-	}
-
-	if (reset_mask & RADEON_RESET_DMA) {
-		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
-			ret = -EAGAIN;
-	}
-#endif
-
-	if (!ret)
-		r600_set_bios_scratch_engine_hung(rdev, false);
-
 	evergreen_print_gpu_status_regs(rdev);
-
-	return 0;
 }
 
 int cayman_asic_reset(struct radeon_device *rdev)
 {
-	return cayman_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
-					    RADEON_RESET_COMPUTE |
-					    RADEON_RESET_DMA |
-					    RADEON_RESET_CP));
+	u32 reset_mask;
+
+	reset_mask = cayman_gpu_check_soft_reset(rdev);
+
+	if (reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, true);
+
+	cayman_gpu_soft_reset(rdev, reset_mask);
+
+	reset_mask = cayman_gpu_check_soft_reset(rdev);
+
+	if (!reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, false);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index c4b84c5a9ab7..079dee202a9e 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -49,6 +49,16 @@
 #define		RINGID(x)					(((x) & 0x3) << 0)
 #define		VMID(x)						(((x) & 0x7) << 0)
 #define	SRBM_STATUS				        0x0E50
+#define		RLC_RQ_PENDING 				(1 << 3)
+#define		GRBM_RQ_PENDING 			(1 << 5)
+#define		VMC_BUSY 				(1 << 8)
+#define		MCB_BUSY 				(1 << 9)
+#define		MCB_NON_DISPLAY_BUSY 			(1 << 10)
+#define		MCC_BUSY 				(1 << 11)
+#define		MCD_BUSY 				(1 << 12)
+#define		SEM_BUSY 				(1 << 14)
+#define		RLC_BUSY 				(1 << 15)
+#define		IH_BUSY 				(1 << 17)
 
 #define	SRBM_SOFT_RESET				        0x0E60
 #define		SOFT_RESET_BIF				(1 << 1)
@@ -68,6 +78,10 @@
 #define		SOFT_RESET_REGBB			(1 << 22)
 #define		SOFT_RESET_ORB				(1 << 23)
 
+#define	SRBM_STATUS2				        0x0EC4
+#define		DMA_BUSY 				(1 << 5)
+#define		DMA1_BUSY 				(1 << 6)
+
 #define VM_CONTEXT0_REQUEST_RESPONSE			0x1470
 #define		REQUEST_TYPE(x)					(((x) & 0xf) << 0)
 #define		RESPONSE_TYPE_MASK				0x000000F0

From 014bb209214d8dce9698efea71c68d20ba477abc Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jan 2013 19:36:20 -0500
Subject: [PATCH 24/38] drm/radeon: use status regs to determine what to reset
 (si)

When we attempt the reset the GPU, look at the status registers
to determine what blocks need to be reset.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/si.c  | 154 +++++++++++++++++++++++++++--------
 drivers/gpu/drm/radeon/sid.h |  12 +++
 2 files changed, 132 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 64841553f9ef..7a8ca728f36f 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -62,6 +62,7 @@ extern void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_sa
 extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save);
 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);
 
 /* get temperature in millidegrees */
 int si_get_temp(struct radeon_device *rdev)
@@ -2127,21 +2128,89 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+static u32 si_gpu_check_soft_reset(struct radeon_device *rdev)
 {
-	struct evergreen_mc_save save;
-	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 reset_mask = 0;
 	u32 tmp;
-	int ret = 0;
 
-	if (!(RREG32(GRBM_STATUS) & GUI_ACTIVE))
-		reset_mask &= ~(RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP);
+	/* GRBM_STATUS */
+	tmp = RREG32(GRBM_STATUS);
+	if (tmp & (PA_BUSY | SC_BUSY |
+		   BCI_BUSY | SX_BUSY |
+		   TA_BUSY | VGT_BUSY |
+		   DB_BUSY | CB_BUSY |
+		   GDS_BUSY | SPI_BUSY |
+		   IA_BUSY | IA_BUSY_NO_DMA))
+		reset_mask |= RADEON_RESET_GFX;
+
+	if (tmp & (CF_RQ_PENDING | PF_RQ_PENDING |
+		   CP_BUSY | CP_COHERENCY_BUSY))
+		reset_mask |= RADEON_RESET_CP;
+
+	if (tmp & GRBM_EE_BUSY)
+		reset_mask |= RADEON_RESET_GRBM | RADEON_RESET_GFX | RADEON_RESET_CP;
+
+	/* GRBM_STATUS2 */
+	tmp = RREG32(GRBM_STATUS2);
+	if (tmp & (RLC_RQ_PENDING | RLC_BUSY))
+		reset_mask |= RADEON_RESET_RLC;
+
+	/* DMA_STATUS_REG 0 */
+	tmp = RREG32(DMA_STATUS_REG + DMA0_REGISTER_OFFSET);
+	if (!(tmp & DMA_IDLE))
+		reset_mask |= RADEON_RESET_DMA;
+
+	/* DMA_STATUS_REG 1 */
+	tmp = RREG32(DMA_STATUS_REG + DMA1_REGISTER_OFFSET);
+	if (!(tmp & DMA_IDLE))
+		reset_mask |= RADEON_RESET_DMA1;
+
+	/* SRBM_STATUS2 */
+	tmp = RREG32(SRBM_STATUS2);
+	if (tmp & DMA_BUSY)
+		reset_mask |= RADEON_RESET_DMA;
+
+	if (tmp & DMA1_BUSY)
+		reset_mask |= RADEON_RESET_DMA1;
+
+	/* SRBM_STATUS */
+	tmp = RREG32(SRBM_STATUS);
+
+	if (tmp & IH_BUSY)
+		reset_mask |= RADEON_RESET_IH;
+
+	if (tmp & SEM_BUSY)
+		reset_mask |= RADEON_RESET_SEM;
+
+	if (tmp & GRBM_RQ_PENDING)
+		reset_mask |= RADEON_RESET_GRBM;
+
+	if (tmp & VMC_BUSY)
+		reset_mask |= RADEON_RESET_VMC;
 
-	if (RREG32(DMA_STATUS_REG) & DMA_IDLE)
-		reset_mask &= ~RADEON_RESET_DMA;
+	if (tmp & (MCB_BUSY | MCB_NON_DISPLAY_BUSY |
+		   MCC_BUSY | MCD_BUSY))
+		reset_mask |= RADEON_RESET_MC;
+
+	if (evergreen_is_display_hung(rdev))
+		reset_mask |= RADEON_RESET_DISPLAY;
+
+	/* VM_L2_STATUS */
+	tmp = RREG32(VM_L2_STATUS);
+	if (tmp & L2_BUSY)
+		reset_mask |= RADEON_RESET_VMC;
+
+	return reset_mask;
+}
+
+static void si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
+{
+	struct evergreen_mc_save save;
+	u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
+	u32 tmp;
 
 	if (reset_mask == 0)
-		return 0;
+		return;
 
 	dev_info(rdev->dev, "GPU softreset: 0x%08X\n", reset_mask);
 
@@ -2151,8 +2220,6 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
-	r600_set_bios_scratch_engine_hung(rdev, true);
-
 	evergreen_mc_stop(rdev, &save);
 	if (evergreen_mc_wait_for_idle(rdev)) {
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
@@ -2166,7 +2233,8 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		tmp = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
 		tmp &= ~DMA_RB_ENABLE;
 		WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, tmp);
-
+	}
+	if (reset_mask & RADEON_RESET_DMA1) {
 		/* dma1 */
 		tmp = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
 		tmp &= ~DMA_RB_ENABLE;
@@ -2195,7 +2263,31 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	}
 
 	if (reset_mask & RADEON_RESET_DMA)
-		srbm_soft_reset |= SOFT_RESET_DMA | SOFT_RESET_DMA1;
+		srbm_soft_reset |= SOFT_RESET_DMA;
+
+	if (reset_mask & RADEON_RESET_DMA1)
+		srbm_soft_reset |= SOFT_RESET_DMA1;
+
+	if (reset_mask & RADEON_RESET_DISPLAY)
+		srbm_soft_reset |= SOFT_RESET_DC;
+
+	if (reset_mask & RADEON_RESET_RLC)
+		grbm_soft_reset |= SOFT_RESET_RLC;
+
+	if (reset_mask & RADEON_RESET_SEM)
+		srbm_soft_reset |= SOFT_RESET_SEM;
+
+	if (reset_mask & RADEON_RESET_IH)
+		srbm_soft_reset |= SOFT_RESET_IH;
+
+	if (reset_mask & RADEON_RESET_GRBM)
+		srbm_soft_reset |= SOFT_RESET_GRBM;
+
+	if (reset_mask & RADEON_RESET_VMC)
+		srbm_soft_reset |= SOFT_RESET_VMC;
+
+	if (reset_mask & RADEON_RESET_MC)
+		srbm_soft_reset |= SOFT_RESET_MC;
 
 	if (grbm_soft_reset) {
 		tmp = RREG32(GRBM_SOFT_RESET);
@@ -2231,32 +2323,26 @@ static int si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	evergreen_mc_resume(rdev, &save);
 	udelay(50);
 
-#if 0
-	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
-		if (RREG32(GRBM_STATUS) & GUI_ACTIVE)
-			ret = -EAGAIN;
-	}
-
-	if (reset_mask & RADEON_RESET_DMA) {
-		if (!(RREG32(DMA_STATUS_REG) & DMA_IDLE))
-			ret = -EAGAIN;
-	}
-#endif
-
-	if (!ret)
-		r600_set_bios_scratch_engine_hung(rdev, false);
-
 	evergreen_print_gpu_status_regs(rdev);
-
-	return 0;
 }
 
 int si_asic_reset(struct radeon_device *rdev)
 {
-	return si_gpu_soft_reset(rdev, (RADEON_RESET_GFX |
-					RADEON_RESET_COMPUTE |
-					RADEON_RESET_DMA |
-					RADEON_RESET_CP));
+	u32 reset_mask;
+
+	reset_mask = si_gpu_check_soft_reset(rdev);
+
+	if (reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, true);
+
+	si_gpu_soft_reset(rdev, reset_mask);
+
+	reset_mask = si_gpu_check_soft_reset(rdev);
+
+	if (!reset_mask)
+		r600_set_bios_scratch_engine_hung(rdev, false);
+
+	return 0;
 }
 
 /* MC */
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 76b5911585f1..07fc455e35ae 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -61,6 +61,14 @@
 #define DMIF_ADDR_CONFIG  				0xBD4
 
 #define	SRBM_STATUS				        0xE50
+#define		GRBM_RQ_PENDING 			(1 << 5)
+#define		VMC_BUSY 				(1 << 8)
+#define		MCB_BUSY 				(1 << 9)
+#define		MCB_NON_DISPLAY_BUSY 			(1 << 10)
+#define		MCC_BUSY 				(1 << 11)
+#define		MCD_BUSY 				(1 << 12)
+#define		SEM_BUSY 				(1 << 14)
+#define		IH_BUSY 				(1 << 17)
 
 #define	SRBM_SOFT_RESET				        0x0E60
 #define		SOFT_RESET_BIF				(1 << 1)
@@ -81,6 +89,10 @@
 #define	CC_SYS_RB_BACKEND_DISABLE			0xe80
 #define	GC_USER_SYS_RB_BACKEND_DISABLE			0xe84
 
+#define	SRBM_STATUS2				        0x0EC4
+#define		DMA_BUSY 				(1 << 5)
+#define		DMA1_BUSY 				(1 << 6)
+
 #define VM_L2_CNTL					0x1400
 #define		ENABLE_L2_CACHE					(1 << 0)
 #define		ENABLE_L2_FRAGMENT_PROCESSING			(1 << 1)

From ca57802e521de54341efc8a56f70571f79ffac72 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 23 Jan 2013 18:56:08 -0500
Subject: [PATCH 25/38] drm/radeon: halt engines before disabling MC (6xx/7xx)

It's better to halt the engines before we disable the MC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r600.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 997707b2a33e..abb143c0bdca 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1397,11 +1397,6 @@ static void r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	r600_print_gpu_status_regs(rdev);
 
-	rv515_mc_stop(rdev, &save);
-	if (r600_mc_wait_for_idle(rdev)) {
-		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
-	}
-
 	/* Disable CP parsing/prefetching */
 	if (rdev->family >= CHIP_RV770)
 		WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1) | S_0086D8_CP_PFP_HALT(1));
@@ -1420,6 +1415,11 @@ static void r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	mdelay(50);
 
+	rv515_mc_stop(rdev, &save);
+	if (r600_mc_wait_for_idle(rdev)) {
+		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
+	}
+
 	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE)) {
 		if (rdev->family >= CHIP_RV770)
 			grbm_soft_reset |= S_008020_SOFT_RESET_DB(1) |

From b21b6e7aab9d0ee97f6d3cf3654fda4348b3b7ea Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 23 Jan 2013 18:57:56 -0500
Subject: [PATCH 26/38] drm/radeon: halt engines before disabling MC
 (evergreen)

It's better to halt the engines before we disable the MC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index fd5e0025b656..f77e33262274 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2460,11 +2460,6 @@ static void evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 
 	evergreen_print_gpu_status_regs(rdev);
 
-	evergreen_mc_stop(rdev, &save);
-	if (evergreen_mc_wait_for_idle(rdev)) {
-		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
-	}
-
 	/* Disable CP parsing/prefetching */
 	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT);
 
@@ -2475,6 +2470,13 @@ static void evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		WREG32(DMA_RB_CNTL, tmp);
 	}
 
+	udelay(50);
+
+	evergreen_mc_stop(rdev, &save);
+	if (evergreen_mc_wait_for_idle(rdev)) {
+		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
+	}
+
 	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE)) {
 		grbm_soft_reset |= SOFT_RESET_DB |
 			SOFT_RESET_CB |

From 90fb87791a698ae16af374aaaa9540fde37f6195 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 23 Jan 2013 18:59:17 -0500
Subject: [PATCH 27/38] drm/radeon: halt engines before disabling MC
 (cayman/TN)

It's better to halt the engines before we disable the MC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/ni.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index eee013f5699a..4784c4e5056f 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1405,13 +1405,6 @@ static void cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(0x14DC));
 
-	r600_set_bios_scratch_engine_hung(rdev, true);
-
-	evergreen_mc_stop(rdev, &save);
-	if (evergreen_mc_wait_for_idle(rdev)) {
-		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
-	}
-
 	/* Disable CP parsing/prefetching */
 	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT);
 
@@ -1429,6 +1422,13 @@ static void cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, tmp);
 	}
 
+	udelay(50);
+
+	evergreen_mc_stop(rdev, &save);
+	if (evergreen_mc_wait_for_idle(rdev)) {
+		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
+	}
+
 	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE)) {
 		grbm_soft_reset = SOFT_RESET_CB |
 			SOFT_RESET_DB |

From f770d78ac159a96071e3c4e4ab97c262e79506d3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 23 Jan 2013 19:00:25 -0500
Subject: [PATCH 28/38] drm/radeon: halt engines before disabling MC (si)

It's better to halt the engines before we disable the MC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/si.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 7a8ca728f36f..89b564ec3d34 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2220,11 +2220,6 @@ static void si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
-	evergreen_mc_stop(rdev, &save);
-	if (evergreen_mc_wait_for_idle(rdev)) {
-		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
-	}
-
 	/* Disable CP parsing/prefetching */
 	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT | CP_CE_HALT);
 
@@ -2241,6 +2236,13 @@ static void si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 		WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, tmp);
 	}
 
+	udelay(50);
+
+	evergreen_mc_stop(rdev, &save);
+	if (evergreen_mc_wait_for_idle(rdev)) {
+		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
+	}
+
 	if (reset_mask & (RADEON_RESET_GFX | RADEON_RESET_COMPUTE | RADEON_RESET_CP)) {
 		grbm_soft_reset = SOFT_RESET_CB |
 			SOFT_RESET_DB |

From 123bc1832c33218dfa677a88c2c54bc1a48a9e72 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 24 Jan 2013 11:37:19 -0500
Subject: [PATCH 29/38] drm/radeon: use the reset mask to determine if rings
 are hung

fetch the reset mask and check if the relevant ring flags
are set to determine whether the ring is hung or not.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c   | 65 +++++++++++++++++--------
 drivers/gpu/drm/radeon/ni.c          | 36 ++++++++++++--
 drivers/gpu/drm/radeon/r600.c        | 31 +++++++-----
 drivers/gpu/drm/radeon/radeon_asic.c | 40 ++++++++--------
 drivers/gpu/drm/radeon/radeon_asic.h |  9 ++--
 drivers/gpu/drm/radeon/si.c          | 72 ++++++++++++++++++++--------
 6 files changed, 173 insertions(+), 80 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index f77e33262274..045955d5f337 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2308,25 +2308,6 @@ int evergreen_mc_init(struct radeon_device *rdev)
 	return 0;
 }
 
-bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 srbm_status;
-	u32 grbm_status;
-	u32 grbm_status_se0, grbm_status_se1;
-
-	srbm_status = RREG32(SRBM_STATUS);
-	grbm_status = RREG32(GRBM_STATUS);
-	grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
-	grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
-	if (!(grbm_status & GUI_ACTIVE)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force CP activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 void evergreen_print_gpu_status_regs(struct radeon_device *rdev)
 {
 	dev_info(rdev->dev, "  GRBM_STATUS               = 0x%08X\n",
@@ -2578,6 +2559,52 @@ int evergreen_asic_reset(struct radeon_device *rdev)
 	return 0;
 }
 
+/**
+ * evergreen_gfx_is_lockup - Check if the GFX engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the GFX engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool evergreen_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = evergreen_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & (RADEON_RESET_GFX |
+			    RADEON_RESET_COMPUTE |
+			    RADEON_RESET_CP))) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force CP activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+/**
+ * evergreen_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool evergreen_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = evergreen_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & RADEON_RESET_DMA)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
 /* Interrupts */
 
 u32 evergreen_get_vblank_counter(struct radeon_device *rdev, int crtc)
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 4784c4e5056f..b6e80550ed90 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1533,24 +1533,50 @@ int cayman_asic_reset(struct radeon_device *rdev)
 	return 0;
 }
 
+/**
+ * cayman_gfx_is_lockup - Check if the GFX engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the GFX engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool cayman_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = cayman_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & (RADEON_RESET_GFX |
+			    RADEON_RESET_COMPUTE |
+			    RADEON_RESET_CP))) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force CP activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
 /**
  * cayman_dma_is_lockup - Check if the DMA engine is locked up
  *
  * @rdev: radeon_device pointer
  * @ring: radeon_ring structure holding ring information
  *
- * Check if the async DMA engine is locked up (cayman-SI).
+ * Check if the async DMA engine is locked up.
  * Returns true if the engine appears to be locked up, false if not.
  */
 bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	u32 dma_status_reg;
+	u32 reset_mask = cayman_gpu_check_soft_reset(rdev);
+	u32 mask;
 
 	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
-		dma_status_reg = RREG32(DMA_STATUS_REG + DMA0_REGISTER_OFFSET);
+		mask = RADEON_RESET_DMA;
 	else
-		dma_status_reg = RREG32(DMA_STATUS_REG + DMA1_REGISTER_OFFSET);
-	if (dma_status_reg & DMA_IDLE) {
+		mask = RADEON_RESET_DMA1;
+
+	if (!(reset_mask & mask)) {
 		radeon_ring_lockup_update(ring);
 		return false;
 	}
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index abb143c0bdca..3f292765aea8 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1537,16 +1537,22 @@ int r600_asic_reset(struct radeon_device *rdev)
 	return 0;
 }
 
-bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+/**
+ * r600_gfx_is_lockup - Check if the GFX engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the GFX engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool r600_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	u32 srbm_status;
-	u32 grbm_status;
-	u32 grbm_status2;
-
-	srbm_status = RREG32(R_000E50_SRBM_STATUS);
-	grbm_status = RREG32(R_008010_GRBM_STATUS);
-	grbm_status2 = RREG32(R_008014_GRBM_STATUS2);
-	if (!G_008010_GUI_ACTIVE(grbm_status)) {
+	u32 reset_mask = r600_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & (RADEON_RESET_GFX |
+			    RADEON_RESET_COMPUTE |
+			    RADEON_RESET_CP))) {
 		radeon_ring_lockup_update(ring);
 		return false;
 	}
@@ -1561,15 +1567,14 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
  * @rdev: radeon_device pointer
  * @ring: radeon_ring structure holding ring information
  *
- * Check if the async DMA engine is locked up (r6xx-evergreen).
+ * Check if the async DMA engine is locked up.
  * Returns true if the engine appears to be locked up, false if not.
  */
 bool r600_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	u32 dma_status_reg;
+	u32 reset_mask = r600_gpu_check_soft_reset(rdev);
 
-	dma_status_reg = RREG32(DMA_STATUS_REG);
-	if (dma_status_reg & DMA_IDLE) {
+	if (!(reset_mask & RADEON_RESET_DMA)) {
 		radeon_ring_lockup_update(ring);
 		return false;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 0b202c07fe50..82b5ef043b0e 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -946,7 +946,7 @@ static struct radeon_asic r600_asic = {
 			.cs_parse = &r600_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gpu_is_lockup,
+			.is_lockup = &r600_gfx_is_lockup,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
 			.ib_execute = &r600_dma_ring_ib_execute,
@@ -1030,7 +1030,7 @@ static struct radeon_asic rs780_asic = {
 			.cs_parse = &r600_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gpu_is_lockup,
+			.is_lockup = &r600_gfx_is_lockup,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
 			.ib_execute = &r600_dma_ring_ib_execute,
@@ -1114,7 +1114,7 @@ static struct radeon_asic rv770_asic = {
 			.cs_parse = &r600_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gpu_is_lockup,
+			.is_lockup = &r600_gfx_is_lockup,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
 			.ib_execute = &r600_dma_ring_ib_execute,
@@ -1198,7 +1198,7 @@ static struct radeon_asic evergreen_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &evergreen_gfx_is_lockup,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
 			.ib_execute = &evergreen_dma_ring_ib_execute,
@@ -1207,7 +1207,7 @@ static struct radeon_asic evergreen_asic = {
 			.cs_parse = &evergreen_dma_cs_parse,
 			.ring_test = &r600_dma_ring_test,
 			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
+			.is_lockup = &evergreen_dma_is_lockup,
 		}
 	},
 	.irq = {
@@ -1282,7 +1282,7 @@ static struct radeon_asic sumo_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &evergreen_gfx_is_lockup,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
 			.ib_execute = &evergreen_dma_ring_ib_execute,
@@ -1291,7 +1291,7 @@ static struct radeon_asic sumo_asic = {
 			.cs_parse = &evergreen_dma_cs_parse,
 			.ring_test = &r600_dma_ring_test,
 			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
+			.is_lockup = &evergreen_dma_is_lockup,
 		}
 	},
 	.irq = {
@@ -1366,7 +1366,7 @@ static struct radeon_asic btc_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &evergreen_gfx_is_lockup,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
 			.ib_execute = &evergreen_dma_ring_ib_execute,
@@ -1375,7 +1375,7 @@ static struct radeon_asic btc_asic = {
 			.cs_parse = &evergreen_dma_cs_parse,
 			.ring_test = &r600_dma_ring_test,
 			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
+			.is_lockup = &evergreen_dma_is_lockup,
 		}
 	},
 	.irq = {
@@ -1457,7 +1457,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &cayman_gfx_is_lockup,
 			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
@@ -1468,7 +1468,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &cayman_gfx_is_lockup,
 			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
@@ -1479,7 +1479,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &cayman_gfx_is_lockup,
 			.vm_flush = &cayman_vm_flush,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
@@ -1584,7 +1584,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &cayman_gfx_is_lockup,
 			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
@@ -1595,7 +1595,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &cayman_gfx_is_lockup,
 			.vm_flush = &cayman_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
@@ -1606,7 +1606,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gpu_is_lockup,
+			.is_lockup = &cayman_gfx_is_lockup,
 			.vm_flush = &cayman_vm_flush,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
@@ -1711,7 +1711,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &si_gpu_is_lockup,
+			.is_lockup = &si_gfx_is_lockup,
 			.vm_flush = &si_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
@@ -1722,7 +1722,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &si_gpu_is_lockup,
+			.is_lockup = &si_gfx_is_lockup,
 			.vm_flush = &si_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
@@ -1733,7 +1733,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &si_gpu_is_lockup,
+			.is_lockup = &si_gfx_is_lockup,
 			.vm_flush = &si_vm_flush,
 		},
 		[R600_RING_TYPE_DMA_INDEX] = {
@@ -1744,7 +1744,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_dma_ring_test,
 			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &cayman_dma_is_lockup,
+			.is_lockup = &si_dma_is_lockup,
 			.vm_flush = &si_dma_vm_flush,
 		},
 		[CAYMAN_RING_TYPE_DMA1_INDEX] = {
@@ -1755,7 +1755,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_dma_ring_test,
 			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &cayman_dma_is_lockup,
+			.is_lockup = &si_dma_is_lockup,
 			.vm_flush = &si_dma_vm_flush,
 		}
 	},
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 15d70e613076..e429e2574cae 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -319,7 +319,7 @@ void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
 				  bool emit_wait);
 void r600_dma_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 bool r600_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
-bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
+bool r600_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 int r600_asic_reset(struct radeon_device *rdev);
 int r600_set_surface_reg(struct radeon_device *rdev, int reg,
 			 uint32_t tiling_flags, uint32_t pitch,
@@ -422,7 +422,8 @@ int evergreen_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
 int evergreen_suspend(struct radeon_device *rdev);
 int evergreen_resume(struct radeon_device *rdev);
-bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
+bool evergreen_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
+bool evergreen_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 int evergreen_asic_reset(struct radeon_device *rdev);
 void evergreen_bandwidth_update(struct radeon_device *rdev);
 void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
@@ -480,6 +481,7 @@ 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_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 
@@ -496,7 +498,8 @@ int si_init(struct radeon_device *rdev);
 void si_fini(struct radeon_device *rdev);
 int si_suspend(struct radeon_device *rdev);
 int si_resume(struct radeon_device *rdev);
-bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
+bool si_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
+bool si_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 int si_asic_reset(struct radeon_device *rdev);
 void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int si_irq_set(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 89b564ec3d34..cd83bc5bd235 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2108,26 +2108,6 @@ static int si_cp_resume(struct radeon_device *rdev)
 	return 0;
 }
 
-bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 srbm_status;
-	u32 grbm_status, grbm_status2;
-	u32 grbm_status_se0, grbm_status_se1;
-
-	srbm_status = RREG32(SRBM_STATUS);
-	grbm_status = RREG32(GRBM_STATUS);
-	grbm_status2 = RREG32(GRBM_STATUS2);
-	grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
-	grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
-	if (!(grbm_status & GUI_ACTIVE)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force CP activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 static u32 si_gpu_check_soft_reset(struct radeon_device *rdev)
 {
 	u32 reset_mask = 0;
@@ -2347,6 +2327,58 @@ int si_asic_reset(struct radeon_device *rdev)
 	return 0;
 }
 
+/**
+ * si_gfx_is_lockup - Check if the GFX engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the GFX engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool si_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = si_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & (RADEON_RESET_GFX |
+			    RADEON_RESET_COMPUTE |
+			    RADEON_RESET_CP))) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force CP activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+/**
+ * si_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool si_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = si_gpu_check_soft_reset(rdev);
+	u32 mask;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		mask = RADEON_RESET_DMA;
+	else
+		mask = RADEON_RESET_DMA1;
+
+	if (!(reset_mask & mask)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
 /* MC */
 static void si_mc_program(struct radeon_device *rdev)
 {

From 24178ec42b0985d485886bc43b97e54ff173627e Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 24 Jan 2013 15:00:17 -0500
Subject: [PATCH 30/38] drm/radeon: don't reset the MC on IGPs/APUs

The MC isn't part of the GPU per se.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c | 6 ++++--
 drivers/gpu/drm/radeon/ni.c        | 6 ++++--
 drivers/gpu/drm/radeon/r600.c      | 6 ++++--
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 045955d5f337..2916de896a60 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2500,8 +2500,10 @@ static void evergreen_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	if (reset_mask & RADEON_RESET_VMC)
 		srbm_soft_reset |= SOFT_RESET_VMC;
 
-	if (reset_mask & RADEON_RESET_MC)
-		srbm_soft_reset |= SOFT_RESET_MC;
+	if (!(rdev->flags & RADEON_IS_IGP)) {
+		if (reset_mask & RADEON_RESET_MC)
+			srbm_soft_reset |= SOFT_RESET_MC;
+	}
 
 	if (grbm_soft_reset) {
 		tmp = RREG32(GRBM_SOFT_RESET);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index b6e80550ed90..170bd03d4dd8 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1474,8 +1474,10 @@ static void cayman_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	if (reset_mask & RADEON_RESET_VMC)
 		srbm_soft_reset |= SOFT_RESET_VMC;
 
-	if (reset_mask & RADEON_RESET_MC)
-		srbm_soft_reset |= SOFT_RESET_MC;
+	if (!(rdev->flags & RADEON_IS_IGP)) {
+		if (reset_mask & RADEON_RESET_MC)
+			srbm_soft_reset |= SOFT_RESET_MC;
+	}
 
 	if (grbm_soft_reset) {
 		tmp = RREG32(GRBM_SOFT_RESET);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 3f292765aea8..dbcb0752f083 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1475,8 +1475,10 @@ static void r600_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	if (reset_mask & RADEON_RESET_GRBM)
 		srbm_soft_reset |= S_000E60_SOFT_RESET_GRBM(1);
 
-	if (reset_mask & RADEON_RESET_MC)
-		srbm_soft_reset |= S_000E60_SOFT_RESET_MC(1);
+	if (!(rdev->flags & RADEON_IS_IGP)) {
+		if (reset_mask & RADEON_RESET_MC)
+			srbm_soft_reset |= S_000E60_SOFT_RESET_MC(1);
+	}
 
 	if (reset_mask & RADEON_RESET_VMC)
 		srbm_soft_reset |= S_000E60_SOFT_RESET_VMC(1);

From 43f1214aa094e46efdfc0255d9601be0e5ea0f62 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 1 Feb 2013 17:32:42 +0100
Subject: [PATCH 31/38] drm/radeon: use IBs for VM page table updates v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For very large page table updates, we can exceed the
size of the ring.  To avoid this, use an IB to perform
the page table update.

v2(ck): cleanup the IB infrastructure and the use it instead
        of filling the struct ourself.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/radeon/ni.c          | 30 ++++++++------
 drivers/gpu/drm/radeon/radeon.h      |  7 +++-
 drivers/gpu/drm/radeon/radeon_asic.h |  8 +++-
 drivers/gpu/drm/radeon/radeon_cs.c   | 19 ++-------
 drivers/gpu/drm/radeon/radeon_gart.c | 60 +++++++++++-----------------
 drivers/gpu/drm/radeon/radeon_ring.c | 19 +++++++++
 drivers/gpu/drm/radeon/si.c          | 52 +++++++++++++-----------
 7 files changed, 103 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 170bd03d4dd8..7cead763be9e 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1946,19 +1946,21 @@ uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t 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-si).
+ * Update the page tables using the CP (cayman/TN).
  */
-void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
+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)
 {
-	struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index];
 	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
@@ -1969,9 +1971,9 @@ void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 			if (ndw > 0x3FFF)
 				ndw = 0x3FFF;
 
-			radeon_ring_write(ring, PACKET3(PACKET3_ME_WRITE, ndw));
-			radeon_ring_write(ring, pe);
-			radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
+			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);
@@ -1983,8 +1985,8 @@ void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 				}
 				addr += incr;
 				value |= r600_flags;
-				radeon_ring_write(ring, value);
-				radeon_ring_write(ring, upper_32_bits(value));
+				ib->ptr[ib->length_dw++] = value;
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
 		}
 	} else {
@@ -1994,9 +1996,9 @@ void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 				ndw = 0xFFFFE;
 
 			/* for non-physically contiguous pages (system) */
-			radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, ndw));
-			radeon_ring_write(ring, pe);
-			radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
+			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, ndw);
+			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);
@@ -2008,10 +2010,12 @@ void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 				}
 				addr += incr;
 				value |= r600_flags;
-				radeon_ring_write(ring, value);
-				radeon_ring_write(ring, upper_32_bits(value));
+				ib->ptr[ib->length_dw++] = value;
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
 		}
+		while (ib->length_dw & 0x7)
+			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 6539d6cb4bc7..307d681b3443 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -780,6 +780,7 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib *ib, struct radeon_vm *vm,
 		  unsigned size);
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
+void radeon_ib_sync_to(struct radeon_ib *ib, struct radeon_fence *fence);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 		       struct radeon_ib *const_ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);
@@ -1188,7 +1189,9 @@ struct radeon_asic {
 		void (*fini)(struct radeon_device *rdev);
 
 		u32 pt_ring_index;
-		void (*set_page)(struct radeon_device *rdev, uint64_t pe,
+		void (*set_page)(struct radeon_device *rdev,
+				 struct radeon_ib *ib,
+				 uint64_t pe,
 				 uint64_t addr, unsigned count,
 				 uint32_t incr, uint32_t flags);
 	} vm;
@@ -1810,7 +1813,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_gart_set_page(rdev, i, p) (rdev)->asic->gart.set_page((rdev), (i), (p))
 #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
 #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
-#define radeon_asic_vm_set_page(rdev, pe, addr, count, incr, flags) ((rdev)->asic->vm.set_page((rdev), (pe), (addr), (count), (incr), (flags)))
+#define radeon_asic_vm_set_page(rdev, ib, pe, addr, count, incr, flags) ((rdev)->asic->vm.set_page((rdev), (ib), (pe), (addr), (count), (incr), (flags)))
 #define radeon_ring_start(rdev, r, cp) (rdev)->asic->ring[(r)].ring_start((rdev), (cp))
 #define radeon_ring_test(rdev, r, cp) (rdev)->asic->ring[(r)].ring_test((rdev), (cp))
 #define radeon_ib_test(rdev, r, cp) (rdev)->asic->ring[(r)].ib_test((rdev), (cp))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index e429e2574cae..f4134a823958 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -474,7 +474,9 @@ 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, uint64_t pe,
+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);
@@ -506,7 +508,9 @@ 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, uint64_t pe,
+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);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 1d214b66650f..70d38241b083 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -125,18 +125,6 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 	return 0;
 }
 
-static void radeon_cs_sync_to(struct radeon_cs_parser *p,
-			      struct radeon_fence *fence)
-{
-	struct radeon_fence *other;
-
-	if (!fence)
-		return;
-
-	other = p->ib.sync_to[fence->ring];
-	p->ib.sync_to[fence->ring] = radeon_fence_later(fence, other);
-}
-
 static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 {
 	int i;
@@ -145,7 +133,7 @@ static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 		if (!p->relocs[i].robj)
 			continue;
 
-		radeon_cs_sync_to(p, p->relocs[i].robj->tbo.sync_obj);
+		radeon_ib_sync_to(&p->ib, p->relocs[i].robj->tbo.sync_obj);
 	}
 }
 
@@ -472,8 +460,9 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		goto out;
 	}
 	radeon_cs_sync_rings(parser);
-	radeon_cs_sync_to(parser, vm->fence);
-	radeon_cs_sync_to(parser, radeon_vm_grab_id(rdev, vm, parser->ring));
+	radeon_ib_sync_to(&parser->ib, vm->fence);
+	radeon_ib_sync_to(&parser->ib, radeon_vm_grab_id(
+		rdev, vm, parser->ring));
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 6e24f84755b5..2c1341f63dc5 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -929,6 +929,7 @@ uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr)
  */
 static int radeon_vm_update_pdes(struct radeon_device *rdev,
 				 struct radeon_vm *vm,
+				 struct radeon_ib *ib,
 				 uint64_t start, uint64_t end)
 {
 	static const uint32_t incr = RADEON_VM_PTE_COUNT * 8;
@@ -971,7 +972,7 @@ static int radeon_vm_update_pdes(struct radeon_device *rdev,
 		    ((last_pt + incr * count) != pt)) {
 
 			if (count) {
-				radeon_asic_vm_set_page(rdev, last_pde,
+				radeon_asic_vm_set_page(rdev, ib, last_pde,
 							last_pt, count, incr,
 							RADEON_VM_PAGE_VALID);
 			}
@@ -985,7 +986,7 @@ static int radeon_vm_update_pdes(struct radeon_device *rdev,
 	}
 
 	if (count) {
-		radeon_asic_vm_set_page(rdev, last_pde, last_pt, count,
+		radeon_asic_vm_set_page(rdev, ib, last_pde, last_pt, count,
 					incr, RADEON_VM_PAGE_VALID);
 
 	}
@@ -1009,6 +1010,7 @@ static int radeon_vm_update_pdes(struct radeon_device *rdev,
  */
 static void radeon_vm_update_ptes(struct radeon_device *rdev,
 				  struct radeon_vm *vm,
+				  struct radeon_ib *ib,
 				  uint64_t start, uint64_t end,
 				  uint64_t dst, uint32_t flags)
 {
@@ -1038,7 +1040,7 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 		if ((last_pte + 8 * count) != pte) {
 
 			if (count) {
-				radeon_asic_vm_set_page(rdev, last_pte,
+				radeon_asic_vm_set_page(rdev, ib, last_pte,
 							last_dst, count,
 							RADEON_GPU_PAGE_SIZE,
 							flags);
@@ -1056,7 +1058,8 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 	}
 
 	if (count) {
-		radeon_asic_vm_set_page(rdev, last_pte,	last_dst, count,
+		radeon_asic_vm_set_page(rdev, ib, last_pte,
+					last_dst, count,
 					RADEON_GPU_PAGE_SIZE, flags);
 	}
 }
@@ -1080,8 +1083,7 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 			    struct ttm_mem_reg *mem)
 {
 	unsigned ridx = rdev->asic->vm.pt_ring_index;
-	struct radeon_ring *ring = &rdev->ring[ridx];
-	struct radeon_semaphore *sem = NULL;
+	struct radeon_ib ib;
 	struct radeon_bo_va *bo_va;
 	unsigned nptes, npdes, ndw;
 	uint64_t addr;
@@ -1124,25 +1126,13 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 		bo_va->valid = false;
 	}
 
-	if (vm->fence && radeon_fence_signaled(vm->fence)) {
-		radeon_fence_unref(&vm->fence);
-	}
-
-	if (vm->fence && vm->fence->ring != ridx) {
-		r = radeon_semaphore_create(rdev, &sem);
-		if (r) {
-			return r;
-		}
-	}
-
 	nptes = radeon_bo_ngpu_pages(bo);
 
 	/* assume two extra pdes in case the mapping overlaps the borders */
 	npdes = (nptes >> RADEON_VM_BLOCK_SIZE) + 2;
 
-	/* estimate number of dw needed */
-	/* semaphore, fence and padding */
-	ndw = 32;
+	/* padding, etc. */
+	ndw = 64;
 
 	if (RADEON_VM_BLOCK_SIZE > 11)
 		/* reserve space for one header for every 2k dwords */
@@ -1161,33 +1151,31 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 	/* reserve space for pde addresses */
 	ndw += npdes * 2;
 
-	r = radeon_ring_lock(rdev, ring, ndw);
-	if (r) {
-		return r;
-	}
+	/* update too big for an IB */
+	if (ndw > 0xfffff)
+		return -ENOMEM;
 
-	if (sem && radeon_fence_need_sync(vm->fence, ridx)) {
-		radeon_semaphore_sync_rings(rdev, sem, vm->fence->ring, ridx);
-		radeon_fence_note_sync(vm->fence, ridx);
-	}
+	r = radeon_ib_get(rdev, ridx, &ib, NULL, ndw * 4);
+	ib.length_dw = 0;
 
-	r = radeon_vm_update_pdes(rdev, vm, bo_va->soffset, bo_va->eoffset);
+	r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
 	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
+		radeon_ib_free(rdev, &ib);
 		return r;
 	}
 
-	radeon_vm_update_ptes(rdev, vm, bo_va->soffset, bo_va->eoffset,
+	radeon_vm_update_ptes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset,
 			      addr, bo_va->flags);
 
-	radeon_fence_unref(&vm->fence);
-	r = radeon_fence_emit(rdev, &vm->fence, ridx);
+	radeon_ib_sync_to(&ib, vm->fence);
+	r = radeon_ib_schedule(rdev, &ib, NULL);
 	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
+		radeon_ib_free(rdev, &ib);
 		return r;
 	}
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_semaphore_free(rdev, &sem, vm->fence);
+	radeon_fence_unref(&vm->fence);
+	vm->fence = radeon_fence_ref(ib.fence);
+	radeon_ib_free(rdev, &ib);
 	radeon_fence_unref(&vm->last_flush);
 
 	return 0;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index cd72062d5a91..8d58e268ff6d 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -108,6 +108,25 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 	radeon_fence_unref(&ib->fence);
 }
 
+/**
+ * radeon_ib_sync_to - sync to fence before executing the IB
+ *
+ * @ib: IB object to add fence to
+ * @fence: fence to sync to
+ *
+ * Sync to the fence before executing the IB
+ */
+void radeon_ib_sync_to(struct radeon_ib *ib, struct radeon_fence *fence)
+{
+	struct radeon_fence *other;
+
+	if (!fence)
+		return;
+
+	other = ib->sync_to[fence->ring];
+	ib->sync_to[fence->ring] = radeon_fence_later(fence, other);
+}
+
 /**
  * radeon_ib_schedule - schedule an IB (Indirect Buffer) on the ring
  *
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index cd83bc5bd235..a910cb92cfd0 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -3043,19 +3043,21 @@ void si_vm_fini(struct radeon_device *rdev)
  * 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 (cayman-si).
+ * Update the page tables using the CP (SI).
  */
-void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
+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)
 {
-	struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index];
 	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
 	uint64_t value;
 	unsigned ndw;
@@ -3066,11 +3068,11 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 			if (ndw > 0x3FFE)
 				ndw = 0x3FFE;
 
-			radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, ndw));
-			radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
-						 WRITE_DATA_DST_SEL(1)));
-			radeon_ring_write(ring, pe);
-			radeon_ring_write(ring, upper_32_bits(pe));
+			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);
@@ -3082,8 +3084,8 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 				}
 				addr += incr;
 				value |= r600_flags;
-				radeon_ring_write(ring, value);
-				radeon_ring_write(ring, upper_32_bits(value));
+				ib->ptr[ib->length_dw++] = value;
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
 			}
 		}
 	} else {
@@ -3095,9 +3097,9 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 					ndw = 0xFFFFE;
 
 				/* for non-physically contiguous pages (system) */
-				radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 0, ndw));
-				radeon_ring_write(ring, pe);
-				radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
+				ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 0, ndw);
+				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);
@@ -3109,8 +3111,8 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 					}
 					addr += incr;
 					value |= r600_flags;
-					radeon_ring_write(ring, value);
-					radeon_ring_write(ring, upper_32_bits(value));
+					ib->ptr[ib->length_dw++] = value;
+					ib->ptr[ib->length_dw++] = upper_32_bits(value);
 				}
 			}
 		} else {
@@ -3124,20 +3126,22 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 				else
 					value = 0;
 				/* for physically contiguous pages (vram) */
-				radeon_ring_write(ring, DMA_PTE_PDE_PACKET(ndw));
-				radeon_ring_write(ring, pe); /* dst addr */
-				radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
-				radeon_ring_write(ring, r600_flags); /* mask */
-				radeon_ring_write(ring, 0);
-				radeon_ring_write(ring, value); /* value */
-				radeon_ring_write(ring, upper_32_bits(value));
-				radeon_ring_write(ring, incr); /* increment size */
-				radeon_ring_write(ring, 0);
+				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++] = 0;
+				ib->ptr[ib->length_dw++] = value; /* value */
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
+				ib->ptr[ib->length_dw++] = incr; /* increment size */
+				ib->ptr[ib->length_dw++] = 0;
 				pe += ndw * 4;
 				addr += (ndw / 2) * incr;
 				count -= ndw / 2;
 			}
 		}
+		while (ib->length_dw & 0x7)
+			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0);
 	}
 }
 

From df16004447fe55dcd6f05f6bb47bf8eaeddb160c Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 31 Jan 2013 16:26:02 -0500
Subject: [PATCH 32/38] drm/radeon: switch back to using the DMA ring for VM PT
 updates

Now that we have switched to using IBs for page table updates,
we can switch back the using the DMA ring.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_asic.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 82b5ef043b0e..60edad7e4311 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1445,7 +1445,7 @@ static struct radeon_asic cayman_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1572,7 +1572,7 @@ static struct radeon_asic trinity_asic = {
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1699,7 +1699,7 @@ static struct radeon_asic si_asic = {
 	.vm = {
 		.init = &si_vm_init,
 		.fini = &si_vm_fini,
-		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
 		.set_page = &si_vm_set_page,
 	},
 	.ring = {

From 624d35242a90cb508064c11c1ff3beb54f08a6a5 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 18 Dec 2012 17:01:35 -0500
Subject: [PATCH 33/38] drm/radeon: add Oland chip family

Oland is a new asic in the SI family.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon.h        | 1 +
 drivers/gpu/drm/radeon/radeon_device.c | 1 +
 drivers/gpu/drm/radeon/radeon_family.h | 1 +
 3 files changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 307d681b3443..59bfbd3868c9 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1769,6 +1769,7 @@ void r100_pll_errata_after_index(struct radeon_device *rdev);
 #define ASIC_IS_DCE6(rdev) ((rdev->family >= CHIP_ARUBA))
 #define ASIC_IS_DCE61(rdev) ((rdev->family >= CHIP_ARUBA) && \
 			     (rdev->flags & RADEON_IS_IGP))
+#define ASIC_IS_DCE64(rdev) ((rdev->family == CHIP_OLAND))
 
 /*
  * BIOS helpers.
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index edfc54e41842..6a36f4b67680 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -93,6 +93,7 @@ static const char radeon_family_name[][16] = {
 	"TAHITI",
 	"PITCAIRN",
 	"VERDE",
+	"OLAND",
 	"LAST",
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index d1fafeabea09..2d91123f2759 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -91,6 +91,7 @@ enum radeon_family {
 	CHIP_TAHITI,
 	CHIP_PITCAIRN,
 	CHIP_VERDE,
+	CHIP_OLAND,
 	CHIP_LAST,
 };
 

From d0ae7fccb3bae2f3749aa70636c537aa16f37bb7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 26 Jul 2012 17:42:25 -0400
Subject: [PATCH 34/38] drm/radeon: fill in gpu init for Oland

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/si.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index a910cb92cfd0..ec62110f22f5 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1127,7 +1127,8 @@ static void si_tiling_mode_table_init(struct radeon_device *rdev)
 			}
 			WREG32(GB_TILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
-	} else if (rdev->family == CHIP_VERDE) {
+	} else if ((rdev->family == CHIP_VERDE) ||
+		   (rdev->family == CHIP_OLAND)) {
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
 			case 0:  /* non-AA compressed depth or any compressed stencil */
@@ -1566,6 +1567,23 @@ static void si_gpu_init(struct radeon_device *rdev)
 		rdev->config.si.max_gs_threads = 32;
 		rdev->config.si.max_hw_contexts = 8;
 
+		rdev->config.si.sc_prim_fifo_size_frontend = 0x20;
+		rdev->config.si.sc_prim_fifo_size_backend = 0x40;
+		rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = VERDE_GB_ADDR_CONFIG_GOLDEN;
+		break;
+	case CHIP_OLAND:
+		rdev->config.si.max_shader_engines = 1;
+		rdev->config.si.max_tile_pipes = 4;
+		rdev->config.si.max_cu_per_sh = 6;
+		rdev->config.si.max_sh_per_se = 1;
+		rdev->config.si.max_backends_per_se = 2;
+		rdev->config.si.max_texture_channel_caches = 4;
+		rdev->config.si.max_gprs = 256;
+		rdev->config.si.max_gs_threads = 16;
+		rdev->config.si.max_hw_contexts = 8;
+
 		rdev->config.si.sc_prim_fifo_size_frontend = 0x20;
 		rdev->config.si.sc_prim_fifo_size_backend = 0x40;
 		rdev->config.si.sc_hiz_tile_fifo_size = 0x30;

From bcc7f5d24dddfbe75893e25d84ebf9d7579c34c1 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 26 Jul 2012 18:36:28 -0400
Subject: [PATCH 35/38] drm/radeon: add ucode loading support for Oland

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/si.c | 59 +++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ec62110f22f5..719f03e061db 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -38,6 +38,7 @@
 #define SI_CE_UCODE_SIZE 2144
 #define SI_RLC_UCODE_SIZE 2048
 #define SI_MC_UCODE_SIZE 7769
+#define OLAND_MC_UCODE_SIZE 7863
 
 MODULE_FIRMWARE("radeon/TAHITI_pfp.bin");
 MODULE_FIRMWARE("radeon/TAHITI_me.bin");
@@ -54,6 +55,11 @@ MODULE_FIRMWARE("radeon/VERDE_me.bin");
 MODULE_FIRMWARE("radeon/VERDE_ce.bin");
 MODULE_FIRMWARE("radeon/VERDE_mc.bin");
 MODULE_FIRMWARE("radeon/VERDE_rlc.bin");
+MODULE_FIRMWARE("radeon/OLAND_pfp.bin");
+MODULE_FIRMWARE("radeon/OLAND_me.bin");
+MODULE_FIRMWARE("radeon/OLAND_ce.bin");
+MODULE_FIRMWARE("radeon/OLAND_mc.bin");
+MODULE_FIRMWARE("radeon/OLAND_rlc.bin");
 
 extern int r600_ih_ring_alloc(struct radeon_device *rdev);
 extern void r600_ih_ring_fini(struct radeon_device *rdev);
@@ -202,6 +208,45 @@ static const u32 verde_io_mc_regs[TAHITI_IO_MC_REGS_SIZE][2] = {
 	{0x0000009f, 0x00a37400}
 };
 
+static const u32 oland_io_mc_regs[TAHITI_IO_MC_REGS_SIZE][2] = {
+	{0x0000006f, 0x03044000},
+	{0x00000070, 0x0480c018},
+	{0x00000071, 0x00000040},
+	{0x00000072, 0x01000000},
+	{0x00000074, 0x000000ff},
+	{0x00000075, 0x00143400},
+	{0x00000076, 0x08ec0800},
+	{0x00000077, 0x040000cc},
+	{0x00000079, 0x00000000},
+	{0x0000007a, 0x21000409},
+	{0x0000007c, 0x00000000},
+	{0x0000007d, 0xe8000000},
+	{0x0000007e, 0x044408a8},
+	{0x0000007f, 0x00000003},
+	{0x00000080, 0x00000000},
+	{0x00000081, 0x01000000},
+	{0x00000082, 0x02000000},
+	{0x00000083, 0x00000000},
+	{0x00000084, 0xe3f3e4f4},
+	{0x00000085, 0x00052024},
+	{0x00000087, 0x00000000},
+	{0x00000088, 0x66036603},
+	{0x00000089, 0x01000000},
+	{0x0000008b, 0x1c0a0000},
+	{0x0000008c, 0xff010000},
+	{0x0000008e, 0xffffefff},
+	{0x0000008f, 0xfff3efff},
+	{0x00000090, 0xfff3efbf},
+	{0x00000094, 0x00101101},
+	{0x00000095, 0x00000fff},
+	{0x00000096, 0x00116fff},
+	{0x00000097, 0x60010000},
+	{0x00000098, 0x10010000},
+	{0x00000099, 0x00006000},
+	{0x0000009a, 0x00001000},
+	{0x0000009f, 0x00a17730}
+};
+
 /* ucode loading */
 static int si_mc_load_microcode(struct radeon_device *rdev)
 {
@@ -230,6 +275,11 @@ static int si_mc_load_microcode(struct radeon_device *rdev)
 		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
+	case CHIP_OLAND:
+		io_mc_regs = (u32 *)&oland_io_mc_regs;
+		ucode_size = OLAND_MC_UCODE_SIZE;
+		regs_size = TAHITI_IO_MC_REGS_SIZE;
+		break;
 	}
 
 	running = RREG32(MC_SEQ_SUP_CNTL) & RUN_MASK;
@@ -324,6 +374,15 @@ static int si_init_microcode(struct radeon_device *rdev)
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
 		break;
+	case CHIP_OLAND:
+		chip_name = "OLAND";
+		rlc_chip_name = "OLAND";
+		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
+		me_req_size = SI_PM4_UCODE_SIZE * 4;
+		ce_req_size = SI_CE_UCODE_SIZE * 4;
+		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
+		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
+		break;
 	default: BUG();
 	}
 

From e737a14cd1f30a0bca753ae32ebada10adf93c3b Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 30 Aug 2012 14:00:03 -0400
Subject: [PATCH 36/38] drm/radeon: radeon-asic updates for Oland

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_asic.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 60edad7e4311..67f008febec7 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1944,9 +1944,13 @@ int radeon_asic_init(struct radeon_device *rdev)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
+	case CHIP_OLAND:
 		rdev->asic = &si_asic;
 		/* set num crtcs */
-		rdev->num_crtc = 6;
+		if (rdev->family == CHIP_OLAND)
+			rdev->num_crtc = 2;
+		else
+			rdev->num_crtc = 6;
 		break;
 	default:
 		/* FIXME: not supported yet */

From 7271c7f999609787c4617c51750d39e447859e7d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 26 Jul 2012 18:48:01 -0400
Subject: [PATCH 37/38] drm/radeon: add Oland pci ids

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/drm/drm_pciids.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index c5c35e629426..a386b0b654cc 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -139,6 +139,19 @@
 	{0x1002, 0x5e4c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5e4d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5e4f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6600, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6620, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6700, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6701, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6702, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \

From 0e3d50bfcbd338254795a700dcff429a96cba1a6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 5 Feb 2013 11:47:09 -0500
Subject: [PATCH 38/38] drm/radeon/dce6: fix display powergating

Only enable it when we disable the display rather than
at DPMS time since enabling it requires a full modeset
to restore the display state.  Fixes blank screens in
certain cases.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/atombios_crtc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 9175615bbd8a..21a892c6ab9c 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -252,8 +252,6 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 		radeon_crtc->enabled = true;
 		/* adjust pm to dpms changes BEFORE enabling crtcs */
 		radeon_pm_compute_clocks(rdev);
-		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set)
-			atombios_powergate_crtc(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_ENABLE);
 		if (ASIC_IS_DCE3(rdev) && !ASIC_IS_DCE6(rdev))
 			atombios_enable_crtc_memreq(crtc, ATOM_ENABLE);
@@ -271,8 +269,6 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 			atombios_enable_crtc_memreq(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_DISABLE);
 		radeon_crtc->enabled = false;
-		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set)
-			atombios_powergate_crtc(crtc, ATOM_ENABLE);
 		/* adjust pm to dpms changes AFTER disabling crtcs */
 		radeon_pm_compute_clocks(rdev);
 		break;
@@ -1844,6 +1840,8 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	int i;
 
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	if (ASIC_IS_DCE6(rdev))
+		atombios_powergate_crtc(crtc, ATOM_ENABLE);
 
 	for (i = 0; i < rdev->num_crtc; i++) {
 		if (rdev->mode_info.crtcs[i] &&