drm/radeon/kms: add initial CS checker support for compute

- Add some new compute regs
- Add new dispatch packets for evergreen/cayman
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/evergreen_cs.c

@@ -856,7 +856,6 @@ static inline int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u3
 	case SQ_PGM_START_PS:
 	case SQ_PGM_START_HS:
 	case SQ_PGM_START_LS:
-	case GDS_ADDR_BASE:
 	case SQ_CONST_MEM_BASE:
 	case SQ_ALU_CONST_CACHE_GS_0:
 	case SQ_ALU_CONST_CACHE_GS_1:
@@ -946,6 +945,34 @@ static inline int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u3
 		}
 		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 		break;
+	case SX_MEMORY_EXPORT_BASE:
+		if (p->rdev->family >= CHIP_CAYMAN) {
+			dev_warn(p->dev, "bad SET_CONFIG_REG "
+				 "0x%04X\n", reg);
+			return -EINVAL;
+		}
+		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONFIG_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		break;
+	case CAYMAN_SX_SCATTER_EXPORT_BASE:
+		if (p->rdev->family < CHIP_CAYMAN) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+				 "0x%04X\n", reg);
+			return -EINVAL;
+		}
+		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		break;
 	default:
 		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 		return -EINVAL;
@@ -1153,6 +1180,34 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			return r;
 		}
 		break;
+	case PACKET3_DISPATCH_DIRECT:
+		if (pkt->count != 3) {
+			DRM_ERROR("bad DISPATCH_DIRECT\n");
+			return -EINVAL;
+		}
+		r = evergreen_cs_track_check(p);
+		if (r) {
+			dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
+			return r;
+		}
+		break;
+	case PACKET3_DISPATCH_INDIRECT:
+		if (pkt->count != 1) {
+			DRM_ERROR("bad DISPATCH_INDIRECT\n");
+			return -EINVAL;
+		}
+		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			DRM_ERROR("bad DISPATCH_INDIRECT\n");
+			return -EINVAL;
+		}
+		ib[idx+0] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
+		r = evergreen_cs_track_check(p);
+		if (r) {
+			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			return r;
+		}
+		break;
 	case PACKET3_WAIT_REG_MEM:
 		if (pkt->count != 5) {
 			DRM_ERROR("bad WAIT_REG_MEM\n");

drivers/gpu/drm/radeon/evergreend.h

@@ -351,6 +351,7 @@
 #define		COLOR_BUFFER_SIZE(x)				((x) << 0)
 #define		POSITION_BUFFER_SIZE(x)				((x) << 8)
 #define		SMX_BUFFER_SIZE(x)				((x) << 16)
+#define	SX_MEMORY_EXPORT_BASE				0x9010
 #define	SX_MISC						0x28350
 
 #define CB_PERF_CTR0_SEL_0				0x9A20
@@ -1122,6 +1123,7 @@
 #define CAYMAN_PA_SC_AA_CONFIG				0x28BE0
 #define         CAYMAN_MSAA_NUM_SAMPLES_SHIFT           0
 #define         CAYMAN_MSAA_NUM_SAMPLES_MASK            0x7
+#define CAYMAN_SX_SCATTER_EXPORT_BASE			0x28358
 /* cayman packet3 addition */
 #define	CAYMAN_PACKET3_DEALLOC_STATE			0x14
 

drivers/gpu/drm/radeon/r600_cs.c

@@ -1200,6 +1200,15 @@ static inline 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);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONFIG_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		break;
 	default:
 		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 		return -EINVAL;

drivers/gpu/drm/radeon/radeon_drv.c

@@ -50,7 +50,7 @@
  *   2.7.0 - fixups for r600 2D tiling support. (no external ABI change), add eg dyn gpr regs
  *   2.8.0 - pageflip support, r500 US_FORMAT regs. r500 ARGB2101010 colorbuf, r300->r500 CMASK, clock crystal query
  *   2.9.0 - r600 tiling (s3tc,rgtc) working, SET_PREDICATION packet 3 on r600 + eg, backend query
- *   2.10.0 - fusion 2D tiling
+ *   2.10.0 - fusion 2D tiling, initial compute support for the CS checker
  */
 #define KMS_DRIVER_MAJOR	2
 #define KMS_DRIVER_MINOR	10

drivers/gpu/drm/radeon/reg_srcs/cayman

@@ -208,6 +208,7 @@ cayman 0x9400
 0x0002834C PA_SC_VPORT_ZMAX_15
 0x00028350 SX_MISC
 0x00028354 SX_SURFACE_SYNC
+0x0002835C SX_SCATTER_EXPORT_SIZE
 0x00028380 SQ_VTX_SEMANTIC_0
 0x00028384 SQ_VTX_SEMANTIC_1
 0x00028388 SQ_VTX_SEMANTIC_2
@@ -432,6 +433,7 @@ cayman 0x9400
 0x00028700 SPI_STACK_MGMT
 0x00028704 SPI_WAVE_MGMT_1
 0x00028708 SPI_WAVE_MGMT_2
+0x00028720 GDS_ADDR_BASE
 0x00028724 GDS_ADDR_SIZE
 0x00028780 CB_BLEND0_CONTROL
 0x00028784 CB_BLEND1_CONTROL

drivers/gpu/drm/radeon/reg_srcs/evergreen

@@ -44,6 +44,7 @@ evergreen 0x9400
 0x00008E28 SQ_STATIC_THREAD_MGMT_3
 0x00008E2C SQ_LDS_RESOURCE_MGMT
 0x00008E48 SQ_EX_ALLOC_TABLE_SLOTS
+0x00009014 SX_MEMORY_EXPORT_SIZE
 0x00009100 SPI_CONFIG_CNTL
 0x0000913C SPI_CONFIG_CNTL_1
 0x00009508 TA_CNTL_AUX
@@ -442,7 +443,9 @@ evergreen 0x9400
 0x000286EC SPI_COMPUTE_NUM_THREAD_X
 0x000286F0 SPI_COMPUTE_NUM_THREAD_Y
 0x000286F4 SPI_COMPUTE_NUM_THREAD_Z
+0x00028720 GDS_ADDR_BASE
 0x00028724 GDS_ADDR_SIZE
+0x00028728 GDS_ORDERED_WAVE_PER_SE
 0x00028780 CB_BLEND0_CONTROL
 0x00028784 CB_BLEND1_CONTROL
 0x00028788 CB_BLEND2_CONTROL

drivers/gpu/drm/radeon/reg_srcs/r600

@@ -429,6 +429,7 @@ r600 0x9400
 0x00028438 SX_ALPHA_REF
 0x00028410 SX_ALPHA_TEST_CONTROL
 0x00028350 SX_MISC
+0x00009014 SX_MEMORY_EXPORT_SIZE
 0x00009604 TC_INVALIDATE
 0x00009400 TD_FILTER4
 0x00009404 TD_FILTER4_1