summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/evergreen_cs.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/radeon/evergreen_cs.c')
-rw-r--r--drivers/gpu/drm/radeon/evergreen_cs.c396
1 files changed, 366 insertions, 30 deletions
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 38e1bda73d3..8e8cd85e5c0 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -38,6 +38,7 @@ struct evergreen_cs_track {
u32 group_size;
u32 nbanks;
u32 npipes;
+ u32 row_size;
/* value we track */
u32 nsamples;
u32 cb_color_base_last[12];
@@ -77,6 +78,44 @@ struct evergreen_cs_track {
struct radeon_bo *db_s_write_bo;
};
+static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
+{
+ if (tiling_flags & RADEON_TILING_MACRO)
+ return ARRAY_2D_TILED_THIN1;
+ else if (tiling_flags & RADEON_TILING_MICRO)
+ return ARRAY_1D_TILED_THIN1;
+ else
+ return ARRAY_LINEAR_GENERAL;
+}
+
+static u32 evergreen_cs_get_num_banks(u32 nbanks)
+{
+ switch (nbanks) {
+ case 2:
+ return ADDR_SURF_2_BANK;
+ case 4:
+ return ADDR_SURF_4_BANK;
+ case 8:
+ default:
+ return ADDR_SURF_8_BANK;
+ case 16:
+ return ADDR_SURF_16_BANK;
+ }
+}
+
+static u32 evergreen_cs_get_tile_split(u32 row_size)
+{
+ switch (row_size) {
+ case 1:
+ default:
+ return ADDR_SURF_TILE_SPLIT_1KB;
+ case 2:
+ return ADDR_SURF_TILE_SPLIT_2KB;
+ case 4:
+ return ADDR_SURF_TILE_SPLIT_4KB;
+ }
+}
+
static void evergreen_cs_track_init(struct evergreen_cs_track *track)
{
int i;
@@ -481,7 +520,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
break;
case DB_Z_INFO:
track->db_z_info = radeon_get_ib_value(p, idx);
- if (!p->keep_tiling_flags) {
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
r = evergreen_cs_packet_next_reloc(p, &reloc);
if (r) {
dev_warn(p->dev, "bad SET_CONTEXT_REG "
@@ -490,12 +529,11 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
}
ib[idx] &= ~Z_ARRAY_MODE(0xf);
track->db_z_info &= ~Z_ARRAY_MODE(0xf);
+ ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
- ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- } else {
- ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+ ib[idx] |= DB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ ib[idx] |= DB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
}
}
break;
@@ -611,20 +649,15 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
case CB_COLOR7_INFO:
tmp = (reg - CB_COLOR0_INFO) / 0x3c;
track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
- if (!p->keep_tiling_flags) {
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
r = evergreen_cs_packet_next_reloc(p, &reloc);
if (r) {
dev_warn(p->dev, "bad SET_CONTEXT_REG "
"0x%04X\n", reg);
return -EINVAL;
}
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- } else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- }
+ ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
}
break;
case CB_COLOR8_INFO:
@@ -633,20 +666,15 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
case CB_COLOR11_INFO:
tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
- if (!p->keep_tiling_flags) {
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
r = evergreen_cs_packet_next_reloc(p, &reloc);
if (r) {
dev_warn(p->dev, "bad SET_CONTEXT_REG "
"0x%04X\n", reg);
return -EINVAL;
}
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- } else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- }
+ ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
}
break;
case CB_COLOR0_PITCH:
@@ -701,6 +729,16 @@ 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);
+ if (r) {
+ dev_warn(p->dev, "bad SET_CONTEXT_REG "
+ "0x%04X\n", reg);
+ return -EINVAL;
+ }
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ ib[idx] |= CB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+ }
break;
case CB_COLOR0_DIM:
case CB_COLOR1_DIM:
@@ -1317,11 +1355,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
return -EINVAL;
}
ib[idx+1+(i*8)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
- if (!p->keep_tiling_flags) {
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+ if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+ ib[idx+1+(i*8)+1] |=
+ TEX_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx+1+(i*8)+6] |=
+ TEX_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+ ib[idx+1+(i*8)+7] |=
+ TEX_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ }
}
texture = reloc->robj;
/* tex mip base */
@@ -1422,6 +1464,7 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
{
struct radeon_cs_packet pkt;
struct evergreen_cs_track *track;
+ u32 tmp;
int r;
if (p->track == NULL) {
@@ -1430,9 +1473,63 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
if (track == NULL)
return -ENOMEM;
evergreen_cs_track_init(track);
- track->npipes = p->rdev->config.evergreen.tiling_npipes;
- track->nbanks = p->rdev->config.evergreen.tiling_nbanks;
- track->group_size = p->rdev->config.evergreen.tiling_group_size;
+ if (p->rdev->family >= CHIP_CAYMAN)
+ tmp = p->rdev->config.cayman.tile_config;
+ else
+ tmp = p->rdev->config.evergreen.tile_config;
+
+ switch (tmp & 0xf) {
+ case 0:
+ track->npipes = 1;
+ break;
+ case 1:
+ default:
+ track->npipes = 2;
+ break;
+ case 2:
+ track->npipes = 4;
+ break;
+ case 3:
+ track->npipes = 8;
+ break;
+ }
+
+ switch ((tmp & 0xf0) >> 4) {
+ case 0:
+ track->nbanks = 4;
+ break;
+ case 1:
+ default:
+ track->nbanks = 8;
+ break;
+ case 2:
+ track->nbanks = 16;
+ break;
+ }
+
+ switch ((tmp & 0xf00) >> 8) {
+ case 0:
+ track->group_size = 256;
+ break;
+ case 1:
+ default:
+ track->group_size = 512;
+ break;
+ }
+
+ switch ((tmp & 0xf000) >> 12) {
+ case 0:
+ track->row_size = 1;
+ break;
+ case 1:
+ default:
+ track->row_size = 2;
+ break;
+ case 2:
+ track->row_size = 4;
+ break;
+ }
+
p->track = track;
}
do {
@@ -1475,3 +1572,242 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
return 0;
}
+/* vm parser */
+static bool evergreen_vm_reg_valid(u32 reg)
+{
+ /* context regs are fine */
+ if (reg >= 0x28000)
+ return true;
+
+ /* check config regs */
+ switch (reg) {
+ case GRBM_GFX_INDEX:
+ case VGT_VTX_VECT_EJECT_REG:
+ case VGT_CACHE_INVALIDATION:
+ case VGT_GS_VERTEX_REUSE:
+ case VGT_PRIMITIVE_TYPE:
+ case VGT_INDEX_TYPE:
+ case VGT_NUM_INDICES:
+ case VGT_NUM_INSTANCES:
+ case VGT_COMPUTE_DIM_X:
+ case VGT_COMPUTE_DIM_Y:
+ case VGT_COMPUTE_DIM_Z:
+ case VGT_COMPUTE_START_X:
+ case VGT_COMPUTE_START_Y:
+ case VGT_COMPUTE_START_Z:
+ case VGT_COMPUTE_INDEX:
+ case VGT_COMPUTE_THREAD_GROUP_SIZE:
+ case VGT_HS_OFFCHIP_PARAM:
+ case PA_CL_ENHANCE:
+ case PA_SU_LINE_STIPPLE_VALUE:
+ case PA_SC_LINE_STIPPLE_STATE:
+ case PA_SC_ENHANCE:
+ case SQ_DYN_GPR_CNTL_PS_FLUSH_REQ:
+ case SQ_DYN_GPR_SIMD_LOCK_EN:
+ case SQ_CONFIG:
+ case SQ_GPR_RESOURCE_MGMT_1:
+ case SQ_GLOBAL_GPR_RESOURCE_MGMT_1:
+ case SQ_GLOBAL_GPR_RESOURCE_MGMT_2:
+ case SQ_CONST_MEM_BASE:
+ case SQ_STATIC_THREAD_MGMT_1:
+ case SQ_STATIC_THREAD_MGMT_2:
+ case SQ_STATIC_THREAD_MGMT_3:
+ case SPI_CONFIG_CNTL:
+ case SPI_CONFIG_CNTL_1:
+ case TA_CNTL_AUX:
+ case DB_DEBUG:
+ case DB_DEBUG2:
+ case DB_DEBUG3:
+ case DB_DEBUG4:
+ case DB_WATERMARKS:
+ case TD_PS_BORDER_COLOR_INDEX:
+ case TD_PS_BORDER_COLOR_RED:
+ case TD_PS_BORDER_COLOR_GREEN:
+ case TD_PS_BORDER_COLOR_BLUE:
+ case TD_PS_BORDER_COLOR_ALPHA:
+ case TD_VS_BORDER_COLOR_INDEX:
+ case TD_VS_BORDER_COLOR_RED:
+ case TD_VS_BORDER_COLOR_GREEN:
+ case TD_VS_BORDER_COLOR_BLUE:
+ case TD_VS_BORDER_COLOR_ALPHA:
+ case TD_GS_BORDER_COLOR_INDEX:
+ case TD_GS_BORDER_COLOR_RED:
+ case TD_GS_BORDER_COLOR_GREEN:
+ case TD_GS_BORDER_COLOR_BLUE:
+ case TD_GS_BORDER_COLOR_ALPHA:
+ case TD_HS_BORDER_COLOR_INDEX:
+ case TD_HS_BORDER_COLOR_RED:
+ case TD_HS_BORDER_COLOR_GREEN:
+ case TD_HS_BORDER_COLOR_BLUE:
+ case TD_HS_BORDER_COLOR_ALPHA:
+ case TD_LS_BORDER_COLOR_INDEX:
+ case TD_LS_BORDER_COLOR_RED:
+ case TD_LS_BORDER_COLOR_GREEN:
+ case TD_LS_BORDER_COLOR_BLUE:
+ case TD_LS_BORDER_COLOR_ALPHA:
+ case TD_CS_BORDER_COLOR_INDEX:
+ case TD_CS_BORDER_COLOR_RED:
+ case TD_CS_BORDER_COLOR_GREEN:
+ case TD_CS_BORDER_COLOR_BLUE:
+ case TD_CS_BORDER_COLOR_ALPHA:
+ case SQ_ESGS_RING_SIZE:
+ case SQ_GSVS_RING_SIZE:
+ case SQ_ESTMP_RING_SIZE:
+ case SQ_GSTMP_RING_SIZE:
+ case SQ_HSTMP_RING_SIZE:
+ case SQ_LSTMP_RING_SIZE:
+ case SQ_PSTMP_RING_SIZE:
+ case SQ_VSTMP_RING_SIZE:
+ case SQ_ESGS_RING_ITEMSIZE:
+ case SQ_ESTMP_RING_ITEMSIZE:
+ case SQ_GSTMP_RING_ITEMSIZE:
+ case SQ_GSVS_RING_ITEMSIZE:
+ case SQ_GS_VERT_ITEMSIZE:
+ case SQ_GS_VERT_ITEMSIZE_1:
+ case SQ_GS_VERT_ITEMSIZE_2:
+ case SQ_GS_VERT_ITEMSIZE_3:
+ case SQ_GSVS_RING_OFFSET_1:
+ case SQ_GSVS_RING_OFFSET_2:
+ case SQ_GSVS_RING_OFFSET_3:
+ case SQ_HSTMP_RING_ITEMSIZE:
+ case SQ_LSTMP_RING_ITEMSIZE:
+ case SQ_PSTMP_RING_ITEMSIZE:
+ case SQ_VSTMP_RING_ITEMSIZE:
+ case VGT_TF_RING_SIZE:
+ case SQ_ESGS_RING_BASE:
+ case SQ_GSVS_RING_BASE:
+ case SQ_ESTMP_RING_BASE:
+ case SQ_GSTMP_RING_BASE:
+ case SQ_HSTMP_RING_BASE:
+ case SQ_LSTMP_RING_BASE:
+ case SQ_PSTMP_RING_BASE:
+ case SQ_VSTMP_RING_BASE:
+ case CAYMAN_VGT_OFFCHIP_LDS_BASE:
+ case CAYMAN_SQ_EX_ALLOC_TABLE_SLOTS:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static int evergreen_vm_packet3_check(struct radeon_device *rdev,
+ u32 *ib, struct radeon_cs_packet *pkt)
+{
+ u32 idx = pkt->idx + 1;
+ u32 idx_value = ib[idx];
+ u32 start_reg, end_reg, reg, i;
+
+ switch (pkt->opcode) {
+ case PACKET3_NOP:
+ case PACKET3_SET_BASE:
+ case PACKET3_CLEAR_STATE:
+ case PACKET3_INDEX_BUFFER_SIZE:
+ case PACKET3_DISPATCH_DIRECT:
+ case PACKET3_DISPATCH_INDIRECT:
+ case PACKET3_MODE_CONTROL:
+ case PACKET3_SET_PREDICATION:
+ case PACKET3_COND_EXEC:
+ case PACKET3_PRED_EXEC:
+ case PACKET3_DRAW_INDIRECT:
+ case PACKET3_DRAW_INDEX_INDIRECT:
+ case PACKET3_INDEX_BASE:
+ case PACKET3_DRAW_INDEX_2:
+ case PACKET3_CONTEXT_CONTROL:
+ case PACKET3_DRAW_INDEX_OFFSET:
+ case PACKET3_INDEX_TYPE:
+ case PACKET3_DRAW_INDEX:
+ case PACKET3_DRAW_INDEX_AUTO:
+ case PACKET3_DRAW_INDEX_IMMD:
+ case PACKET3_NUM_INSTANCES:
+ case PACKET3_DRAW_INDEX_MULTI_AUTO:
+ case PACKET3_STRMOUT_BUFFER_UPDATE:
+ case PACKET3_DRAW_INDEX_OFFSET_2:
+ case PACKET3_DRAW_INDEX_MULTI_ELEMENT:
+ case PACKET3_MPEG_INDEX:
+ case PACKET3_WAIT_REG_MEM:
+ case PACKET3_MEM_WRITE:
+ case PACKET3_SURFACE_SYNC:
+ case PACKET3_EVENT_WRITE:
+ case PACKET3_EVENT_WRITE_EOP:
+ case PACKET3_EVENT_WRITE_EOS:
+ case PACKET3_SET_CONTEXT_REG:
+ case PACKET3_SET_BOOL_CONST:
+ case PACKET3_SET_LOOP_CONST:
+ case PACKET3_SET_RESOURCE:
+ case PACKET3_SET_SAMPLER:
+ case PACKET3_SET_CTL_CONST:
+ case PACKET3_SET_RESOURCE_OFFSET:
+ case PACKET3_SET_CONTEXT_REG_INDIRECT:
+ case PACKET3_SET_RESOURCE_INDIRECT:
+ case CAYMAN_PACKET3_DEALLOC_STATE:
+ break;
+ case PACKET3_COND_WRITE:
+ if (idx_value & 0x100) {
+ reg = ib[idx + 5] * 4;
+ if (!evergreen_vm_reg_valid(reg))
+ return -EINVAL;
+ }
+ break;
+ case PACKET3_COPY_DW:
+ if (idx_value & 0x2) {
+ reg = ib[idx + 3] * 4;
+ if (!evergreen_vm_reg_valid(reg))
+ return -EINVAL;
+ }
+ break;
+ case PACKET3_SET_CONFIG_REG:
+ start_reg = (idx_value << 2) + PACKET3_SET_CONFIG_REG_START;
+ end_reg = 4 * pkt->count + start_reg - 4;
+ if ((start_reg < PACKET3_SET_CONFIG_REG_START) ||
+ (start_reg >= PACKET3_SET_CONFIG_REG_END) ||
+ (end_reg >= PACKET3_SET_CONFIG_REG_END)) {
+ DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
+ return -EINVAL;
+ }
+ for (i = 0; i < pkt->count; i++) {
+ reg = start_reg + (4 * i);
+ if (!evergreen_vm_reg_valid(reg))
+ return -EINVAL;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+int evergreen_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
+{
+ int ret = 0;
+ u32 idx = 0;
+ struct radeon_cs_packet pkt;
+
+ do {
+ pkt.idx = idx;
+ pkt.type = CP_PACKET_GET_TYPE(ib->ptr[idx]);
+ pkt.count = CP_PACKET_GET_COUNT(ib->ptr[idx]);
+ pkt.one_reg_wr = 0;
+ switch (pkt.type) {
+ case PACKET_TYPE0:
+ dev_err(rdev->dev, "Packet0 not allowed!\n");
+ ret = -EINVAL;
+ break;
+ case PACKET_TYPE2:
+ idx += 1;
+ break;
+ case PACKET_TYPE3:
+ pkt.opcode = CP_PACKET3_GET_OPCODE(ib->ptr[idx]);
+ ret = evergreen_vm_packet3_check(rdev, ib->ptr, &pkt);
+ idx += pkt.count + 2;
+ break;
+ default:
+ dev_err(rdev->dev, "Unknown packet type %d !\n", pkt.type);
+ ret = -EINVAL;
+ break;
+ }
+ if (ret)
+ break;
+ } while (idx < ib->length_dw);
+
+ return ret;
+}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-28 03:21:50 +0000