gen7_blorp_emit_urb_config(struct brw_context *brw,
const brw_blorp_params *params)
{
- /* The minimum valid value is 32. See 3DSTATE_URB_VS,
- * Dword 1.15:0 "VS Number of URB Entries".
+ unsigned urb_size = (brw->is_haswell && brw->gt == 3) ? 32 : 16;
+ gen7_emit_push_constant_state(brw,
+ urb_size / 2 /* vs_size */,
+ 0 /* gs_size */,
+ urb_size / 2 /* fs_size */);
+
+ /* The minimum valid number of VS entries is 32. See 3DSTATE_URB_VS, Dword
+ * 1.15:0 "VS Number of URB Entries".
*/
- int num_vs_entries = 32;
- int vs_size = 2;
- int vs_start = 2; /* skip over push constants */
-
- gen7_emit_urb_state(brw, num_vs_entries, vs_size, vs_start);
+ gen7_emit_urb_state(brw,
+ 32 /* num_vs_entries */,
+ 2 /* vs_size */,
+ 2 /* vs_start */,
+ 0 /* num_gs_entries */,
+ 1 /* gs_size */,
+ 2 /* gs_start */);
}
* to divide them by 2 as we do for Gen6 (see
* gen6_blorp_emit_surface_state).
*/
- struct intel_region *region = surface->mt->region;
+ struct intel_mipmap_tree *mt = surface->mt;
uint32_t tile_x, tile_y;
- uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+ const uint8_t mocs = GEN7_MOCS_L3;
uint32_t tiling = surface->map_stencil_as_y_tiled
- ? I915_TILING_Y : region->tiling;
+ ? I915_TILING_Y : mt->tiling;
uint32_t *surf = (uint32_t *)
brw_state_batch(brw, AUB_TRACE_SURFACE_STATE, 8 * 4, 32, &wm_surf_offset);
if (surface->mt->align_w == 8)
surf[0] |= GEN7_SURFACE_HALIGN_8;
- if (surface->array_spacing_lod0)
+ if (surface->array_layout == ALL_SLICES_AT_EACH_LOD)
surf[0] |= GEN7_SURFACE_ARYSPC_LOD0;
else
surf[0] |= GEN7_SURFACE_ARYSPC_FULL;
/* reloc */
surf[1] =
- surface->compute_tile_offsets(&tile_x, &tile_y) + region->bo->offset;
+ surface->compute_tile_offsets(&tile_x, &tile_y) + mt->bo->offset64;
/* Note that the low bits of these fields are missing, so
* there's the possibility of getting in trouble.
surf[2] = SET_FIELD(width - 1, GEN7_SURFACE_WIDTH) |
SET_FIELD(height - 1, GEN7_SURFACE_HEIGHT);
- uint32_t pitch_bytes = region->pitch;
+ uint32_t pitch_bytes = mt->pitch;
if (surface->map_stencil_as_y_tiled)
pitch_bytes *= 2;
surf[3] = pitch_bytes - 1;
/* Emit relocation to surface contents */
drm_intel_bo_emit_reloc(brw->batch.bo,
wm_surf_offset + 4,
- region->bo,
- surf[1] - region->bo->offset,
+ mt->bo,
+ surf[1] - mt->bo->offset64,
read_domains, write_domain);
gen7_check_surface_setup(surf, is_render_target);
}
-/**
- * SAMPLER_STATE. See gen7_update_sampler_state().
- */
-static uint32_t
-gen7_blorp_emit_sampler_state(struct brw_context *brw,
- const brw_blorp_params *params)
-{
- uint32_t sampler_offset;
-
- struct gen7_sampler_state *sampler = (struct gen7_sampler_state *)
- brw_state_batch(brw, AUB_TRACE_SAMPLER_STATE,
- sizeof(struct gen7_sampler_state),
- 32, &sampler_offset);
- memset(sampler, 0, sizeof(*sampler));
-
- sampler->ss0.min_filter = BRW_MAPFILTER_LINEAR;
- sampler->ss0.mip_filter = BRW_MIPFILTER_NONE;
- sampler->ss0.mag_filter = BRW_MAPFILTER_LINEAR;
-
- sampler->ss3.r_wrap_mode = BRW_TEXCOORDMODE_CLAMP;
- sampler->ss3.s_wrap_mode = BRW_TEXCOORDMODE_CLAMP;
- sampler->ss3.t_wrap_mode = BRW_TEXCOORDMODE_CLAMP;
-
- // sampler->ss0.min_mag_neq = 1;
-
- /* Set LOD bias:
- */
- sampler->ss0.lod_bias = 0;
-
- sampler->ss0.lod_preclamp = 1; /* OpenGL mode */
- sampler->ss0.default_color_mode = 0; /* OpenGL/DX10 mode */
-
- /* Set BaseMipLevel, MaxLOD, MinLOD:
- *
- * XXX: I don't think that using firstLevel, lastLevel works,
- * because we always setup the surface state as if firstLevel ==
- * level zero. Probably have to subtract firstLevel from each of
- * these:
- */
- sampler->ss0.base_level = U_FIXED(0, 1);
-
- sampler->ss1.max_lod = U_FIXED(0, 8);
- sampler->ss1.min_lod = U_FIXED(0, 8);
-
- sampler->ss3.non_normalized_coord = 1;
-
- sampler->ss3.address_round |= BRW_ADDRESS_ROUNDING_ENABLE_U_MIN |
- BRW_ADDRESS_ROUNDING_ENABLE_V_MIN |
- BRW_ADDRESS_ROUNDING_ENABLE_R_MIN;
- sampler->ss3.address_round |= BRW_ADDRESS_ROUNDING_ENABLE_U_MAG |
- BRW_ADDRESS_ROUNDING_ENABLE_V_MAG |
- BRW_ADDRESS_ROUNDING_ENABLE_R_MAG;
-
- return sampler_offset;
-}
-
-
/* 3DSTATE_VS
*
* Disable vertex shader.
OUT_BATCH(0);
ADVANCE_BATCH();
+ /**
+ * From Graphics BSpec: 3D-Media-GPGPU Engine > 3D Pipeline Stages >
+ * Geometry > Geometry Shader > State:
+ *
+ * "Note: Because of corruption in IVB:GT2, software needs to flush the
+ * whole fixed function pipeline when the GS enable changes value in
+ * the 3DSTATE_GS."
+ *
+ * The hardware architects have clarified that in this context "flush the
+ * whole fixed function pipeline" means to emit a PIPE_CONTROL with the "CS
+ * Stall" bit set.
+ */
+ if (!brw->is_haswell && brw->gt == 2 && brw->gs.enabled)
+ gen7_emit_cs_stall_flush(brw);
+
BEGIN_BATCH(7);
OUT_BATCH(_3DSTATE_GS << 16 | (7 - 2));
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
ADVANCE_BATCH();
+ brw->gs.enabled = false;
}
/* 3DSTATE_STREAMOUT
OUT_BATCH(_3DSTATE_SF << 16 | (7 - 2));
OUT_BATCH(params->depth_format <<
GEN7_SF_DEPTH_BUFFER_SURFACE_FORMAT_SHIFT);
- OUT_BATCH(params->num_samples > 1 ? GEN6_SF_MSRAST_ON_PATTERN : 0);
+ OUT_BATCH(params->dst.num_samples > 1 ? GEN6_SF_MSRAST_ON_PATTERN : 0);
OUT_BATCH(0);
OUT_BATCH(0);
OUT_BATCH(0);
case GEN6_HIZ_OP_NONE:
break;
default:
- assert(0);
- break;
+ unreachable("not reached");
}
dw1 |= GEN7_WM_LINE_AA_WIDTH_1_0;
dw1 |= GEN7_WM_LINE_END_CAP_AA_WIDTH_0_5;
dw1 |= GEN7_WM_DISPATCH_ENABLE; /* We are rendering */
}
- if (params->num_samples > 1) {
+ if (params->dst.num_samples > 1) {
dw1 |= GEN7_WM_MSRAST_ON_PATTERN;
if (prog_data && prog_data->persample_msaa_dispatch)
dw2 |= GEN7_WM_MSDISPMODE_PERSAMPLE;
const brw_blorp_params *params,
uint32_t wm_push_const_offset)
{
- uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+ const uint8_t mocs = GEN7_MOCS_L3;
/* Make sure the push constants fill an exact integer number of
* registers.
gen7_blorp_emit_depth_stencil_config(struct brw_context *brw,
const brw_blorp_params *params)
{
- uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+ const uint8_t mocs = GEN7_MOCS_L3;
uint32_t surfwidth, surfheight;
uint32_t surftype;
unsigned int depth = MAX2(params->depth.mt->logical_depth0, 1);
surfwidth = params->depth.width;
surfheight = params->depth.height;
} else {
- surfwidth = params->depth.mt->physical_width0;
- surfheight = params->depth.mt->physical_height0;
+ surfwidth = params->depth.mt->logical_width0;
+ surfheight = params->depth.mt->logical_height0;
}
/* 3DSTATE_DEPTH_BUFFER */
BEGIN_BATCH(7);
OUT_BATCH(GEN7_3DSTATE_DEPTH_BUFFER << 16 | (7 - 2));
- OUT_BATCH((params->depth.mt->region->pitch - 1) |
+ OUT_BATCH((params->depth.mt->pitch - 1) |
params->depth_format << 18 |
1 << 22 | /* hiz enable */
1 << 28 | /* depth write */
surftype << 29);
- OUT_RELOC(params->depth.mt->region->bo,
+ OUT_RELOC(params->depth.mt->bo,
I915_GEM_DOMAIN_RENDER, I915_GEM_DOMAIN_RENDER,
0);
OUT_BATCH((surfwidth - 1) << 4 |
/* 3DSTATE_HIER_DEPTH_BUFFER */
{
- struct intel_region *hiz_region = params->depth.mt->hiz_mt->region;
+ struct intel_miptree_aux_buffer *hiz_buf = params->depth.mt->hiz_buf;
BEGIN_BATCH(3);
OUT_BATCH((GEN7_3DSTATE_HIER_DEPTH_BUFFER << 16) | (3 - 2));
OUT_BATCH((mocs << 25) |
- (hiz_region->pitch - 1));
- OUT_RELOC(hiz_region->bo,
+ (hiz_buf->pitch - 1));
+ OUT_RELOC(hiz_buf->bo,
I915_GEM_DOMAIN_RENDER, I915_GEM_DOMAIN_RENDER,
0);
ADVANCE_BATCH();
OUT_BATCH(0);
OUT_BATCH(0);
ADVANCE_BATCH();
+
+ BEGIN_BATCH(3);
+ OUT_BATCH(GEN7_3DSTATE_HIER_DEPTH_BUFFER << 16 | (3 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+
+ BEGIN_BATCH(3);
+ OUT_BATCH(GEN7_3DSTATE_STENCIL_BUFFER << 16 | (3 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
}
gen7_blorp_exec(struct brw_context *brw,
const brw_blorp_params *params)
{
+ if (brw->gen >= 8)
+ return;
+
brw_blorp_prog_data *prog_data = NULL;
uint32_t cc_blend_state_offset = 0;
uint32_t cc_state_offset = 0;
uint32_t sampler_offset = 0;
uint32_t prog_offset = params->get_wm_prog(brw, &prog_data);
- gen6_blorp_emit_batch_head(brw, params);
- gen6_emit_3dstate_multisample(brw, params->num_samples);
- gen6_emit_3dstate_sample_mask(brw, params->num_samples, 1.0, false, ~0u);
+ gen6_emit_3dstate_multisample(brw, params->dst.num_samples);
+ gen6_emit_3dstate_sample_mask(brw,
+ params->dst.num_samples > 1 ?
+ (1 << params->dst.num_samples) - 1 : 1);
gen6_blorp_emit_state_base_address(brw, params);
gen6_blorp_emit_vertices(brw, params);
gen7_blorp_emit_urb_config(brw, params);
gen6_blorp_emit_binding_table(brw, params,
wm_surf_offset_renderbuffer,
wm_surf_offset_texture);
- sampler_offset = gen7_blorp_emit_sampler_state(brw, params);
+ sampler_offset = gen6_blorp_emit_sampler_state(brw, params);
}
gen7_blorp_emit_vs_disable(brw, params);
gen7_blorp_emit_hs_disable(brw, params);