--- /dev/null
+#ifndef GEN8_MEDIA_H
+#define GEN8_MEDIA_H
+
+#define GEN8_SURFACEFORMAT_R32G32B32A32_FLOAT 0x000
+#define GEN8_SURFACEFORMAT_R32G32B32A32_SINT 0x001
+#define GEN8_SURFACEFORMAT_R32G32B32A32_UINT 0x002
+#define GEN8_SURFACEFORMAT_R32G32B32A32_UNORM 0x003
+#define GEN8_SURFACEFORMAT_R32G32B32A32_SNORM 0x004
+#define GEN8_SURFACEFORMAT_R64G64_FLOAT 0x005
+#define GEN8_SURFACEFORMAT_R32G32B32X32_FLOAT 0x006
+#define GEN8_SURFACEFORMAT_R32G32B32A32_SSCALED 0x007
+#define GEN8_SURFACEFORMAT_R32G32B32A32_USCALED 0x008
+#define GEN8_SURFACEFORMAT_R32G32B32_FLOAT 0x040
+#define GEN8_SURFACEFORMAT_R32G32B32_SINT 0x041
+#define GEN8_SURFACEFORMAT_R32G32B32_UINT 0x042
+#define GEN8_SURFACEFORMAT_R32G32B32_UNORM 0x043
+#define GEN8_SURFACEFORMAT_R32G32B32_SNORM 0x044
+#define GEN8_SURFACEFORMAT_R32G32B32_SSCALED 0x045
+#define GEN8_SURFACEFORMAT_R32G32B32_USCALED 0x046
+#define GEN8_SURFACEFORMAT_R16G16B16A16_UNORM 0x080
+#define GEN8_SURFACEFORMAT_R16G16B16A16_SNORM 0x081
+#define GEN8_SURFACEFORMAT_R16G16B16A16_SINT 0x082
+#define GEN8_SURFACEFORMAT_R16G16B16A16_UINT 0x083
+#define GEN8_SURFACEFORMAT_R16G16B16A16_FLOAT 0x084
+#define GEN8_SURFACEFORMAT_R32G32_FLOAT 0x085
+#define GEN8_SURFACEFORMAT_R32G32_SINT 0x086
+#define GEN8_SURFACEFORMAT_R32G32_UINT 0x087
+#define GEN8_SURFACEFORMAT_R32_FLOAT_X8X24_TYPELESS 0x088
+#define GEN8_SURFACEFORMAT_X32_TYPELESS_G8X24_UINT 0x089
+#define GEN8_SURFACEFORMAT_L32A32_FLOAT 0x08A
+#define GEN8_SURFACEFORMAT_R32G32_UNORM 0x08B
+#define GEN8_SURFACEFORMAT_R32G32_SNORM 0x08C
+#define GEN8_SURFACEFORMAT_R64_FLOAT 0x08D
+#define GEN8_SURFACEFORMAT_R16G16B16X16_UNORM 0x08E
+#define GEN8_SURFACEFORMAT_R16G16B16X16_FLOAT 0x08F
+#define GEN8_SURFACEFORMAT_A32X32_FLOAT 0x090
+#define GEN8_SURFACEFORMAT_L32X32_FLOAT 0x091
+#define GEN8_SURFACEFORMAT_I32X32_FLOAT 0x092
+#define GEN8_SURFACEFORMAT_R16G16B16A16_SSCALED 0x093
+#define GEN8_SURFACEFORMAT_R16G16B16A16_USCALED 0x094
+#define GEN8_SURFACEFORMAT_R32G32_SSCALED 0x095
+#define GEN8_SURFACEFORMAT_R32G32_USCALED 0x096
+#define GEN8_SURFACEFORMAT_B8G8R8A8_UNORM 0x0C0
+#define GEN8_SURFACEFORMAT_B8G8R8A8_UNORM_SRGB 0x0C1
+#define GEN8_SURFACEFORMAT_R10G10B10A2_UNORM 0x0C2
+#define GEN8_SURFACEFORMAT_R10G10B10A2_UNORM_SRGB 0x0C3
+#define GEN8_SURFACEFORMAT_R10G10B10A2_UINT 0x0C4
+#define GEN8_SURFACEFORMAT_R10G10B10_SNORM_A2_UNORM 0x0C5
+#define GEN8_SURFACEFORMAT_R8G8B8A8_UNORM 0x0C7
+#define GEN8_SURFACEFORMAT_R8G8B8A8_UNORM_SRGB 0x0C8
+#define GEN8_SURFACEFORMAT_R8G8B8A8_SNORM 0x0C9
+#define GEN8_SURFACEFORMAT_R8G8B8A8_SINT 0x0CA
+#define GEN8_SURFACEFORMAT_R8G8B8A8_UINT 0x0CB
+#define GEN8_SURFACEFORMAT_R16G16_UNORM 0x0CC
+#define GEN8_SURFACEFORMAT_R16G16_SNORM 0x0CD
+#define GEN8_SURFACEFORMAT_R16G16_SINT 0x0CE
+#define GEN8_SURFACEFORMAT_R16G16_UINT 0x0CF
+#define GEN8_SURFACEFORMAT_R16G16_FLOAT 0x0D0
+#define GEN8_SURFACEFORMAT_B10G10R10A2_UNORM 0x0D1
+#define GEN8_SURFACEFORMAT_B10G10R10A2_UNORM_SRGB 0x0D2
+#define GEN8_SURFACEFORMAT_R11G11B10_FLOAT 0x0D3
+#define GEN8_SURFACEFORMAT_R32_SINT 0x0D6
+#define GEN8_SURFACEFORMAT_R32_UINT 0x0D7
+#define GEN8_SURFACEFORMAT_R32_FLOAT 0x0D8
+#define GEN8_SURFACEFORMAT_R24_UNORM_X8_TYPELESS 0x0D9
+#define GEN8_SURFACEFORMAT_X24_TYPELESS_G8_UINT 0x0DA
+#define GEN8_SURFACEFORMAT_L16A16_UNORM 0x0DF
+#define GEN8_SURFACEFORMAT_I24X8_UNORM 0x0E0
+#define GEN8_SURFACEFORMAT_L24X8_UNORM 0x0E1
+#define GEN8_SURFACEFORMAT_A24X8_UNORM 0x0E2
+#define GEN8_SURFACEFORMAT_I32_FLOAT 0x0E3
+#define GEN8_SURFACEFORMAT_L32_FLOAT 0x0E4
+#define GEN8_SURFACEFORMAT_A32_FLOAT 0x0E5
+#define GEN8_SURFACEFORMAT_B8G8R8X8_UNORM 0x0E9
+#define GEN8_SURFACEFORMAT_B8G8R8X8_UNORM_SRGB 0x0EA
+#define GEN8_SURFACEFORMAT_R8G8B8X8_UNORM 0x0EB
+#define GEN8_SURFACEFORMAT_R8G8B8X8_UNORM_SRGB 0x0EC
+#define GEN8_SURFACEFORMAT_R9G9B9E5_SHAREDEXP 0x0ED
+#define GEN8_SURFACEFORMAT_B10G10R10X2_UNORM 0x0EE
+#define GEN8_SURFACEFORMAT_L16A16_FLOAT 0x0F0
+#define GEN8_SURFACEFORMAT_R32_UNORM 0x0F1
+#define GEN8_SURFACEFORMAT_R32_SNORM 0x0F2
+#define GEN8_SURFACEFORMAT_R10G10B10X2_USCALED 0x0F3
+#define GEN8_SURFACEFORMAT_R8G8B8A8_SSCALED 0x0F4
+#define GEN8_SURFACEFORMAT_R8G8B8A8_USCALED 0x0F5
+#define GEN8_SURFACEFORMAT_R16G16_SSCALED 0x0F6
+#define GEN8_SURFACEFORMAT_R16G16_USCALED 0x0F7
+#define GEN8_SURFACEFORMAT_R32_SSCALED 0x0F8
+#define GEN8_SURFACEFORMAT_R32_USCALED 0x0F9
+#define GEN8_SURFACEFORMAT_B5G6R5_UNORM 0x100
+#define GEN8_SURFACEFORMAT_B5G6R5_UNORM_SRGB 0x101
+#define GEN8_SURFACEFORMAT_B5G5R5A1_UNORM 0x102
+#define GEN8_SURFACEFORMAT_B5G5R5A1_UNORM_SRGB 0x103
+#define GEN8_SURFACEFORMAT_B4G4R4A4_UNORM 0x104
+#define GEN8_SURFACEFORMAT_B4G4R4A4_UNORM_SRGB 0x105
+#define GEN8_SURFACEFORMAT_R8G8_UNORM 0x106
+#define GEN8_SURFACEFORMAT_R8G8_SNORM 0x107
+#define GEN8_SURFACEFORMAT_R8G8_SINT 0x108
+#define GEN8_SURFACEFORMAT_R8G8_UINT 0x109
+#define GEN8_SURFACEFORMAT_R16_UNORM 0x10A
+#define GEN8_SURFACEFORMAT_R16_SNORM 0x10B
+#define GEN8_SURFACEFORMAT_R16_SINT 0x10C
+#define GEN8_SURFACEFORMAT_R16_UINT 0x10D
+#define GEN8_SURFACEFORMAT_R16_FLOAT 0x10E
+#define GEN8_SURFACEFORMAT_I16_UNORM 0x111
+#define GEN8_SURFACEFORMAT_L16_UNORM 0x112
+#define GEN8_SURFACEFORMAT_A16_UNORM 0x113
+#define GEN8_SURFACEFORMAT_L8A8_UNORM 0x114
+#define GEN8_SURFACEFORMAT_I16_FLOAT 0x115
+#define GEN8_SURFACEFORMAT_L16_FLOAT 0x116
+#define GEN8_SURFACEFORMAT_A16_FLOAT 0x117
+#define GEN8_SURFACEFORMAT_R5G5_SNORM_B6_UNORM 0x119
+#define GEN8_SURFACEFORMAT_B5G5R5X1_UNORM 0x11A
+#define GEN8_SURFACEFORMAT_B5G5R5X1_UNORM_SRGB 0x11B
+#define GEN8_SURFACEFORMAT_R8G8_SSCALED 0x11C
+#define GEN8_SURFACEFORMAT_R8G8_USCALED 0x11D
+#define GEN8_SURFACEFORMAT_R16_SSCALED 0x11E
+#define GEN8_SURFACEFORMAT_R16_USCALED 0x11F
+#define GEN8_SURFACEFORMAT_R8_UNORM 0x140
+#define GEN8_SURFACEFORMAT_R8_SNORM 0x141
+#define GEN8_SURFACEFORMAT_R8_SINT 0x142
+#define GEN8_SURFACEFORMAT_R8_UINT 0x143
+#define GEN8_SURFACEFORMAT_A8_UNORM 0x144
+#define GEN8_SURFACEFORMAT_I8_UNORM 0x145
+#define GEN8_SURFACEFORMAT_L8_UNORM 0x146
+#define GEN8_SURFACEFORMAT_P4A4_UNORM 0x147
+#define GEN8_SURFACEFORMAT_A4P4_UNORM 0x148
+#define GEN8_SURFACEFORMAT_R8_SSCALED 0x149
+#define GEN8_SURFACEFORMAT_R8_USCALED 0x14A
+#define GEN8_SURFACEFORMAT_R1_UINT 0x181
+#define GEN8_SURFACEFORMAT_YCRCB_NORMAL 0x182
+#define GEN8_SURFACEFORMAT_YCRCB_SWAPUVY 0x183
+#define GEN8_SURFACEFORMAT_BC1_UNORM 0x186
+#define GEN8_SURFACEFORMAT_BC2_UNORM 0x187
+#define GEN8_SURFACEFORMAT_BC3_UNORM 0x188
+#define GEN8_SURFACEFORMAT_BC4_UNORM 0x189
+#define GEN8_SURFACEFORMAT_BC5_UNORM 0x18A
+#define GEN8_SURFACEFORMAT_BC1_UNORM_SRGB 0x18B
+#define GEN8_SURFACEFORMAT_BC2_UNORM_SRGB 0x18C
+#define GEN8_SURFACEFORMAT_BC3_UNORM_SRGB 0x18D
+#define GEN8_SURFACEFORMAT_MONO8 0x18E
+#define GEN8_SURFACEFORMAT_YCRCB_SWAPUV 0x18F
+#define GEN8_SURFACEFORMAT_YCRCB_SWAPY 0x190
+#define GEN8_SURFACEFORMAT_DXT1_RGB 0x191
+#define GEN8_SURFACEFORMAT_FXT1 0x192
+#define GEN8_SURFACEFORMAT_R8G8B8_UNORM 0x193
+#define GEN8_SURFACEFORMAT_R8G8B8_SNORM 0x194
+#define GEN8_SURFACEFORMAT_R8G8B8_SSCALED 0x195
+#define GEN8_SURFACEFORMAT_R8G8B8_USCALED 0x196
+#define GEN8_SURFACEFORMAT_R64G64B64A64_FLOAT 0x197
+#define GEN8_SURFACEFORMAT_R64G64B64_FLOAT 0x198
+#define GEN8_SURFACEFORMAT_BC4_SNORM 0x199
+#define GEN8_SURFACEFORMAT_BC5_SNORM 0x19A
+#define GEN8_SURFACEFORMAT_R16G16B16_UNORM 0x19C
+#define GEN8_SURFACEFORMAT_R16G16B16_SNORM 0x19D
+#define GEN8_SURFACEFORMAT_R16G16B16_SSCALED 0x19E
+#define GEN8_SURFACEFORMAT_R16G16B16_USCALED 0x19F
+
+#define GEN8_SURFACERETURNFORMAT_FLOAT32 0
+#define GEN8_SURFACERETURNFORMAT_S1 1
+
+#define GEN8_SURFACE_1D 0
+#define GEN8_SURFACE_2D 1
+#define GEN8_SURFACE_3D 2
+#define GEN8_SURFACE_CUBE 3
+#define GEN8_SURFACE_BUFFER 4
+#define GEN8_SURFACE_NULL 7
+
+#define GEN8_FLOATING_POINT_IEEE_754 0
+#define GEN8_FLOATING_POINT_NON_IEEE_754 1
+
+#define GFXPIPE(Pipeline,Opcode,Subopcode) ((3 << 29) | \
+ ((Pipeline) << 27) | \
+ ((Opcode) << 24) | \
+ ((Subopcode) << 16))
+
+#define GEN8_PIPELINE_SELECT GFXPIPE(1, 1, 4)
+# define PIPELINE_SELECT_3D (0 << 0)
+# define PIPELINE_SELECT_MEDIA (1 << 0)
+
+#define GEN8_STATE_BASE_ADDRESS GFXPIPE(0, 1, 1)
+# define BASE_ADDRESS_MODIFY (1 << 0)
+
+#define GEN8_MEDIA_VFE_STATE GFXPIPE(2, 0, 0)
+#define GEN8_MEDIA_CURBE_LOAD GFXPIPE(2, 0, 1)
+#define GEN8_MEDIA_INTERFACE_DESCRIPTOR_LOAD GFXPIPE(2, 0, 2)
+#define GEN8_MEDIA_STATE_FLUSH GFXPIPE(2, 0, 4)
+#define GEN8_MEDIA_OBJECT GFXPIPE(2, 1, 0)
+
+struct gen8_interface_descriptor_data
+{
+ struct {
+ uint32_t pad0:6;
+ uint32_t kernel_start_pointer:26;
+ } desc0;
+
+ struct {
+ uint32_t kernel_start_pointer_high:16;
+ uint32_t pad0:16;
+ } desc1;
+
+ struct {
+ uint32_t pad0:7;
+ uint32_t software_exception_enable:1;
+ uint32_t pad1:3;
+ uint32_t maskstack_exception_enable:1;
+ uint32_t pad2:1;
+ uint32_t illegal_opcode_exception_enable:1;
+ uint32_t pad3:2;
+ uint32_t floating_point_mode:1;
+ uint32_t thread_priority:1;
+ uint32_t single_program_flow:1;
+ uint32_t denorm_mode:1;
+ uint32_t pad4:12;
+ } desc2;
+
+ struct {
+ uint32_t pad0:2;
+ uint32_t sampler_count:3;
+ uint32_t sampler_state_pointer:27;
+ } desc3;
+
+ struct {
+ uint32_t binding_table_entry_count:5;
+ uint32_t binding_table_pointer:11;
+ uint32_t pad0: 16;
+ } desc4;
+
+ struct {
+ uint32_t constant_urb_entry_read_offset:16;
+ uint32_t constant_urb_entry_read_length:16;
+ } desc5;
+
+ struct {
+ uint32_t num_threads_in_tg:10;
+ uint32_t pad0:5;
+ uint32_t global_barrier_enable:1;
+ uint32_t shared_local_memory_size:5;
+ uint32_t barrier_enable:1;
+ uint32_t rounding_mode:2;
+ uint32_t pad1:8;
+ } desc6;
+
+ struct {
+ uint32_t cross_thread_constant_data_read_length:8;
+ uint32_t pad0:24;
+ } desc7;
+};
+
+struct gen8_surface_state
+{
+ struct {
+ uint32_t cube_pos_z:1;
+ uint32_t cube_neg_z:1;
+ uint32_t cube_pos_y:1;
+ uint32_t cube_neg_y:1;
+ uint32_t cube_pos_x:1;
+ uint32_t cube_neg_x:1;
+ uint32_t media_boundary_pixel_mode:2;
+ uint32_t render_cache_read_write:1;
+ uint32_t sampler_l2_bypass_disable:1;
+ uint32_t vert_line_stride_ofs:1;
+ uint32_t vert_line_stride:1;
+ uint32_t tiled_mode:2;
+ uint32_t horizontal_alignment:2;
+ uint32_t vertical_alignment:2;
+ uint32_t surface_format:9; /**< BRW_SURFACEFORMAT_x */
+ uint32_t pad0:1;
+ uint32_t is_array:1;
+ uint32_t surface_type:3; /**< BRW_SURFACE_1D/2D/3D/CUBE */
+ } ss0;
+
+ struct {
+ uint32_t qpitch:15;
+ uint32_t pad1:4;
+ uint32_t base_mip_level:5;
+ uint32_t memory_object_control:7;
+ uint32_t pad0:1;
+ } ss1;
+
+ struct {
+ uint32_t width:14;
+ uint32_t pad1:2;
+ uint32_t height:14;
+ uint32_t pad0:2;
+ } ss2;
+
+ struct {
+ uint32_t pitch:18;
+ uint32_t pad:3;
+ uint32_t depth:11;
+ } ss3;
+
+ struct {
+ uint32_t multisample_position_palette_index:3;
+ uint32_t num_multisamples:3;
+ uint32_t multisampled_surface_storage_format:1;
+ uint32_t render_target_view_extent:11;
+ uint32_t min_array_elt:11;
+ uint32_t rotation:2;
+ uint32_t force_ncmp_reduce_type:1;
+ } ss4;
+
+ struct {
+ uint32_t mip_count:4;
+ uint32_t min_lod:4;
+ uint32_t pad3:6;
+ uint32_t coherency_type:1;
+ uint32_t pad2:5;
+ uint32_t ewa_disable_for_cube:1;
+ uint32_t y_offset:3;
+ uint32_t pad0:1;
+ uint32_t x_offset:7;
+ } ss5;
+
+ struct {
+ uint32_t pad; /* Multisample Control Surface stuff */
+ } ss6;
+
+ struct {
+ uint32_t resource_min_lod:12;
+
+ /* Only on Haswell */
+ uint32_t pad0:4;
+ uint32_t shader_chanel_select_a:3;
+ uint32_t shader_chanel_select_b:3;
+ uint32_t shader_chanel_select_g:3;
+ uint32_t shader_chanel_select_r:3;
+
+ uint32_t alpha_clear_color:1;
+ uint32_t blue_clear_color:1;
+ uint32_t green_clear_color:1;
+ uint32_t red_clear_color:1;
+ } ss7;
+
+ struct {
+ uint32_t base_addr;
+ } ss8;
+
+ struct {
+ uint32_t base_addr_hi:16;
+ uint32_t pad0:16;
+ } ss9;
+
+ struct {
+ uint32_t pad0:12;
+ uint32_t aux_base_addr:20;
+ } ss10;
+
+ struct {
+ uint32_t aux_base_addr_hi:16;
+ uint32_t pad:16;
+ } ss11;
+
+ struct {
+ uint32_t hiz_depth_clear_value;
+ } ss12;
+
+ struct {
+ uint32_t reserved;
+ } ss13;
+
+ struct {
+ uint32_t reserved;
+ } ss14;
+
+ struct {
+ uint32_t reserved;
+ } ss15;
+};
+
+#endif /* GEN8_MEDIA_H */
--- /dev/null
+#include "media_fill.h"
+#include "gen8_media.h"
+
+#include <assert.h>
+
+#define ALIGN(x, y) (((x) + (y)-1) & ~((y)-1))
+
+static const uint32_t media_kernel[][4] = {
+ { 0x00400001, 0x20202288, 0x00000020, 0x00000000 },
+ { 0x00600001, 0x20800208, 0x008d0000, 0x00000000 },
+ { 0x00200001, 0x20800208, 0x00450040, 0x00000000 },
+ { 0x00000001, 0x20880608, 0x00000000, 0x000f000f },
+ { 0x00800001, 0x20a00208, 0x00000020, 0x00000000 },
+ { 0x00800001, 0x20e00208, 0x00000020, 0x00000000 },
+ { 0x00800001, 0x21200208, 0x00000020, 0x00000000 },
+ { 0x00800001, 0x21600208, 0x00000020, 0x00000000 },
+ { 0x0c800031, 0x24000a40, 0x0e000080, 0x120a8000 },
+ { 0x00600001, 0x2e000208, 0x008d0000, 0x00000000 },
+ { 0x07800031, 0x20000a40, 0x0e000e00, 0x82000010 },
+};
+
+static uint32_t
+batch_used(struct intel_batchbuffer *batch)
+{
+ return batch->ptr - batch->buffer;
+}
+
+static uint32_t
+batch_align(struct intel_batchbuffer *batch, uint32_t align)
+{
+ uint32_t offset = batch_used(batch);
+ offset = ALIGN(offset, align);
+ batch->ptr = batch->buffer + offset;
+ return offset;
+}
+
+static void *
+batch_alloc(struct intel_batchbuffer *batch, uint32_t size, uint32_t align)
+{
+ uint32_t offset = batch_align(batch, align);
+ batch->ptr += size;
+ return memset(batch->buffer + offset, 0, size);
+}
+
+static uint32_t
+batch_offset(struct intel_batchbuffer *batch, void *ptr)
+{
+ return (uint8_t *)ptr - batch->buffer;
+}
+
+static uint32_t
+batch_copy(struct intel_batchbuffer *batch, const void *ptr, uint32_t size, uint32_t align)
+{
+ return batch_offset(batch, memcpy(batch_alloc(batch, size, align), ptr, size));
+}
+
+static void
+gen8_render_flush(struct intel_batchbuffer *batch, uint32_t batch_end)
+{
+ int ret;
+
+ ret = drm_intel_bo_subdata(batch->bo, 0, 4096, batch->buffer);
+ if (ret == 0)
+ ret = drm_intel_bo_mrb_exec(batch->bo, batch_end,
+ NULL, 0, 0, 0);
+ assert(ret == 0);
+}
+
+static uint32_t
+gen8_fill_curbe_buffer_data(struct intel_batchbuffer *batch,
+ uint8_t color)
+{
+ uint8_t *curbe_buffer;
+ uint32_t offset;
+
+ curbe_buffer = batch_alloc(batch, sizeof(uint32_t) * 8, 64);
+ offset = batch_offset(batch, curbe_buffer);
+ *curbe_buffer = color;
+
+ return offset;
+}
+
+static uint32_t
+gen8_fill_surface_state(struct intel_batchbuffer *batch,
+ struct scratch_buf *buf,
+ uint32_t format,
+ int is_dst)
+{
+ struct gen8_surface_state *ss;
+ uint32_t write_domain, read_domain, offset;
+ int ret;
+
+ if (is_dst) {
+ write_domain = read_domain = I915_GEM_DOMAIN_RENDER;
+ } else {
+ write_domain = 0;
+ read_domain = I915_GEM_DOMAIN_SAMPLER;
+ }
+
+ ss = batch_alloc(batch, sizeof(*ss), 64);
+ offset = batch_offset(batch, ss);
+
+ ss->ss0.surface_type = GEN8_SURFACE_2D;
+ ss->ss0.surface_format = format;
+ ss->ss0.render_cache_read_write = 1;
+ ss->ss0.vertical_alignment = 1; /* align 4 */
+ ss->ss0.horizontal_alignment = 1; /* align 4 */
+
+ if (buf->tiling == I915_TILING_X)
+ ss->ss0.tiled_mode = 2;
+ else if (buf->tiling == I915_TILING_Y)
+ ss->ss0.tiled_mode = 3;
+
+ ss->ss8.base_addr = buf->bo->offset;
+
+ ret = drm_intel_bo_emit_reloc(batch->bo,
+ batch_offset(batch, ss) + 8 * 4,
+ buf->bo, 0,
+ read_domain, write_domain);
+ assert(ret == 0);
+
+ ss->ss2.height = buf_height(buf) - 1;
+ ss->ss2.width = buf_width(buf) - 1;
+ ss->ss3.pitch = buf->stride - 1;
+
+ ss->ss7.shader_chanel_select_r = 4;
+ ss->ss7.shader_chanel_select_g = 5;
+ ss->ss7.shader_chanel_select_b = 6;
+ ss->ss7.shader_chanel_select_a = 7;
+
+ return offset;
+}
+
+static uint32_t
+gen8_fill_binding_table(struct intel_batchbuffer *batch,
+ struct scratch_buf *dst)
+{
+ uint32_t *binding_table, offset;
+
+ binding_table = batch_alloc(batch, 32, 64);
+ offset = batch_offset(batch, binding_table);
+
+ binding_table[0] = gen8_fill_surface_state(batch, dst, GEN8_SURFACEFORMAT_R8_UNORM, 1);
+
+ return offset;
+}
+
+static uint32_t
+gen8_fill_media_kernel(struct intel_batchbuffer *batch,
+ const uint32_t kernel[][4],
+ size_t size)
+{
+ uint32_t offset;
+
+ offset = batch_copy(batch, kernel, size, 64);
+
+ return offset;
+}
+
+static uint32_t
+gen8_fill_interface_descriptor(struct intel_batchbuffer *batch, struct scratch_buf *dst)
+{
+ struct gen8_interface_descriptor_data *idd;
+ uint32_t offset;
+ uint32_t binding_table_offset, kernel_offset;
+
+ binding_table_offset = gen8_fill_binding_table(batch, dst);
+ kernel_offset = gen8_fill_media_kernel(batch, media_kernel, sizeof(media_kernel));
+
+ idd = batch_alloc(batch, sizeof(*idd), 64);
+ offset = batch_offset(batch, idd);
+
+ idd->desc0.kernel_start_pointer = (kernel_offset >> 6);
+
+ idd->desc2.single_program_flow = 1;
+ idd->desc2.floating_point_mode = GEN8_FLOATING_POINT_IEEE_754;
+
+ idd->desc3.sampler_count = 0; /* 0 samplers used */
+ idd->desc3.sampler_state_pointer = 0;
+
+ idd->desc4.binding_table_entry_count = 0;
+ idd->desc4.binding_table_pointer = (binding_table_offset >> 5);
+
+ idd->desc5.constant_urb_entry_read_offset = 0;
+ idd->desc5.constant_urb_entry_read_length = 1; /* grf 1 */
+
+ return offset;
+}
+
+static void
+gen8_emit_state_base_address(struct intel_batchbuffer *batch)
+{
+ OUT_BATCH(GEN8_STATE_BASE_ADDRESS | (16 - 2));
+
+ /* general */
+ OUT_BATCH(0 | BASE_ADDRESS_MODIFY);
+ OUT_BATCH(0);
+
+ /* stateless data port */
+ OUT_BATCH(0 | BASE_ADDRESS_MODIFY);
+
+ /* surface */
+ OUT_RELOC(batch->bo, I915_GEM_DOMAIN_SAMPLER, 0, BASE_ADDRESS_MODIFY);
+ OUT_BATCH(0);
+
+ /* dynamic */
+ OUT_RELOC(batch->bo, I915_GEM_DOMAIN_RENDER | I915_GEM_DOMAIN_INSTRUCTION,
+ 0, BASE_ADDRESS_MODIFY);
+ OUT_BATCH(0);
+
+ /* indirect */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+
+ /* instruction */
+ OUT_RELOC(batch->bo, I915_GEM_DOMAIN_INSTRUCTION, 0, BASE_ADDRESS_MODIFY);
+ OUT_BATCH(0);
+
+ /* general state buffer size */
+ OUT_BATCH(0xfffff000 | 1);
+ /* dynamic state buffer size */
+ OUT_BATCH(1 << 12 | 1);
+ /* indirect object buffer size */
+ OUT_BATCH(0xfffff000 | 1);
+ /* intruction buffer size, must set modify enable bit, otherwise it may result in GPU hang */
+ OUT_BATCH(1 << 12 | 1);
+}
+
+static void
+gen8_emit_vfe_state(struct intel_batchbuffer *batch)
+{
+ OUT_BATCH(GEN8_MEDIA_VFE_STATE | (9 - 2));
+
+ /* scratch buffer */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+
+ /* number of threads & urb entries */
+ OUT_BATCH(1 << 16 |
+ 2 << 8);
+
+ OUT_BATCH(0);
+
+ /* urb entry size & curbe size */
+ OUT_BATCH(2 << 16 |
+ 2);
+
+ /* scoreboard */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+}
+
+static void
+gen8_emit_curbe_load(struct intel_batchbuffer *batch, uint32_t curbe_buffer)
+{
+ OUT_BATCH(GEN8_MEDIA_CURBE_LOAD | (4 - 2));
+ OUT_BATCH(0);
+ /* curbe total data length */
+ OUT_BATCH(64);
+ /* curbe data start address, is relative to the dynamics base address */
+ OUT_BATCH(curbe_buffer);
+}
+
+static void
+gen8_emit_interface_descriptor_load(struct intel_batchbuffer *batch, uint32_t interface_descriptor)
+{
+ OUT_BATCH(GEN8_MEDIA_INTERFACE_DESCRIPTOR_LOAD | (4 - 2));
+ OUT_BATCH(0);
+ /* interface descriptor data length */
+ OUT_BATCH(sizeof(struct gen8_interface_descriptor_data));
+ /* interface descriptor address, is relative to the dynamics base address */
+ OUT_BATCH(interface_descriptor);
+}
+
+static void
+gen8_emit_media_state_flush(struct intel_batchbuffer *batch)
+{
+ OUT_BATCH(GEN8_MEDIA_STATE_FLUSH | (2 - 2));
+ OUT_BATCH(0);
+}
+
+static void
+gen8_emit_media_objects(struct intel_batchbuffer *batch,
+ unsigned x, unsigned y,
+ unsigned width, unsigned height)
+{
+ int i, j;
+
+ for (i = 0; i < width / 16; i++) {
+ for (j = 0; j < height / 16; j++) {
+ OUT_BATCH(GEN8_MEDIA_OBJECT | (8 - 2));
+
+ /* interface descriptor offset */
+ OUT_BATCH(0);
+
+ /* without indirect data */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+
+ /* scoreboard */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+
+ /* inline data (xoffset, yoffset) */
+ OUT_BATCH(x + i * 16);
+ OUT_BATCH(y + j * 16);
+ gen8_emit_media_state_flush(batch);
+ }
+ }
+}
+
+/*
+ * This sets up the media pipeline,
+ *
+ * +---------------+ <---- 4096
+ * | ^ |
+ * | | |
+ * | various |
+ * | state |
+ * | | |
+ * |_______|_______| <---- 2048 + ?
+ * | ^ |
+ * | | |
+ * | batch |
+ * | commands |
+ * | | |
+ * | | |
+ * +---------------+ <---- 0 + ?
+ *
+ */
+
+#define BATCH_STATE_SPLIT 2048
+
+void
+gen8_media_fillfunc(struct intel_batchbuffer *batch,
+ struct scratch_buf *dst,
+ unsigned x, unsigned y,
+ unsigned width, unsigned height,
+ uint8_t color)
+{
+ uint32_t curbe_buffer, interface_descriptor;
+ uint32_t batch_end;
+
+ intel_batchbuffer_flush(batch);
+
+ /* setup states */
+ batch->ptr = &batch->buffer[BATCH_STATE_SPLIT];
+
+ curbe_buffer = gen8_fill_curbe_buffer_data(batch, color);
+ interface_descriptor = gen8_fill_interface_descriptor(batch, dst);
+ assert(batch->ptr < &batch->buffer[4095]);
+
+ /* media pipeline */
+ batch->ptr = batch->buffer;
+ OUT_BATCH(GEN8_PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
+ gen8_emit_state_base_address(batch);
+
+ gen8_emit_vfe_state(batch);
+
+ gen8_emit_curbe_load(batch, curbe_buffer);
+
+ gen8_emit_interface_descriptor_load(batch, interface_descriptor);
+
+ gen8_emit_media_objects(batch, x, y, width, height);
+
+ OUT_BATCH(MI_BATCH_BUFFER_END);
+
+ batch_end = batch_align(batch, 8);
+ assert(batch_end < BATCH_STATE_SPLIT);
+
+ gen8_render_flush(batch, batch_end);
+ intel_batchbuffer_reset(batch);
+}
projects / profile / extras / intel-gpu-tools.git / commitdiff