1/* 2 * Copyright © 2015 Intel Corporation 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice (including the next 12 * paragraph) shall be included in all copies or substantial portions of the 13 * Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS 21 * IN THE SOFTWARE. 22 */ 23 24#include "util/blob.h" 25#include "util/hash_table.h" 26#include "util/debug.h" 27#include "util/disk_cache.h" 28#include "util/mesa-sha1.h" 29#include "nir/nir_serialize.h" 30#include "anv_private.h" 31#include "nir/nir_xfb_info.h" 32#include "vulkan/util/vk_util.h" 33 34static bool 35anv_shader_bin_serialize(struct vk_pipeline_cache_object *object, 36 struct blob *blob); 37 38struct vk_pipeline_cache_object * 39anv_shader_bin_deserialize(struct vk_device *device, 40 const void *key_data, size_t key_size, 41 struct blob_reader *blob); 42 43static void 44anv_shader_bin_destroy(struct vk_pipeline_cache_object *object) 45{ 46 struct anv_device *device = 47 container_of(object->device, struct anv_device, vk); 48 struct anv_shader_bin *shader = 49 container_of(object, struct anv_shader_bin, base); 50 51 anv_state_pool_free(&device->instruction_state_pool, shader->kernel); 52 vk_pipeline_cache_object_finish(&shader->base); 53 vk_free(&device->vk.alloc, shader); 54} 55 56static const struct vk_pipeline_cache_object_ops anv_shader_bin_ops = { 57 .serialize = anv_shader_bin_serialize, 58 .deserialize = anv_shader_bin_deserialize, 59 .destroy = anv_shader_bin_destroy, 60}; 61 62const struct vk_pipeline_cache_object_ops *const anv_cache_import_ops[2] = { 63 &anv_shader_bin_ops, 64 NULL 65}; 66 67struct anv_shader_bin * 68anv_shader_bin_create(struct anv_device *device, 69 gl_shader_stage stage, 70 const void *key_data, uint32_t key_size, 71 const void *kernel_data, uint32_t kernel_size, 72 const struct brw_stage_prog_data *prog_data_in, 73 uint32_t prog_data_size, 74 const struct brw_compile_stats *stats, uint32_t num_stats, 75 const nir_xfb_info *xfb_info_in, 76 const struct anv_pipeline_bind_map *bind_map) 77{ 78 VK_MULTIALLOC(ma); 79 VK_MULTIALLOC_DECL(&ma, struct anv_shader_bin, shader, 1); 80 VK_MULTIALLOC_DECL_SIZE(&ma, void, obj_key_data, key_size); 81 VK_MULTIALLOC_DECL_SIZE(&ma, struct brw_stage_prog_data, prog_data, 82 prog_data_size); 83 VK_MULTIALLOC_DECL(&ma, struct brw_shader_reloc, prog_data_relocs, 84 prog_data_in->num_relocs); 85 VK_MULTIALLOC_DECL(&ma, uint32_t, prog_data_param, prog_data_in->nr_params); 86 87 VK_MULTIALLOC_DECL_SIZE(&ma, nir_xfb_info, xfb_info, 88 xfb_info_in == NULL ? 0 : 89 nir_xfb_info_size(xfb_info_in->output_count)); 90 91 VK_MULTIALLOC_DECL(&ma, struct anv_pipeline_binding, surface_to_descriptor, 92 bind_map->surface_count); 93 VK_MULTIALLOC_DECL(&ma, struct anv_pipeline_binding, sampler_to_descriptor, 94 bind_map->sampler_count); 95 96 if (!vk_multialloc_alloc(&ma, &device->vk.alloc, 97 VK_SYSTEM_ALLOCATION_SCOPE_DEVICE)) 98 return NULL; 99 100 memcpy(obj_key_data, key_data, key_size); 101 vk_pipeline_cache_object_init(&device->vk, &shader->base, 102 &anv_shader_bin_ops, obj_key_data, key_size); 103 104 shader->stage = stage; 105 106 shader->kernel = 107 anv_state_pool_alloc(&device->instruction_state_pool, kernel_size, 64); 108 memcpy(shader->kernel.map, kernel_data, kernel_size); 109 shader->kernel_size = kernel_size; 110 111 uint64_t shader_data_addr = INSTRUCTION_STATE_POOL_MIN_ADDRESS + 112 shader->kernel.offset + 113 prog_data_in->const_data_offset; 114 115 int rv_count = 0; 116 struct brw_shader_reloc_value reloc_values[5]; 117 reloc_values[rv_count++] = (struct brw_shader_reloc_value) { 118 .id = BRW_SHADER_RELOC_CONST_DATA_ADDR_LOW, 119 .value = shader_data_addr, 120 }; 121 reloc_values[rv_count++] = (struct brw_shader_reloc_value) { 122 .id = BRW_SHADER_RELOC_CONST_DATA_ADDR_HIGH, 123 .value = shader_data_addr >> 32, 124 }; 125 reloc_values[rv_count++] = (struct brw_shader_reloc_value) { 126 .id = BRW_SHADER_RELOC_SHADER_START_OFFSET, 127 .value = shader->kernel.offset, 128 }; 129 if (brw_shader_stage_is_bindless(stage)) { 130 const struct brw_bs_prog_data *bs_prog_data = 131 brw_bs_prog_data_const(prog_data_in); 132 uint64_t resume_sbt_addr = INSTRUCTION_STATE_POOL_MIN_ADDRESS + 133 shader->kernel.offset + 134 bs_prog_data->resume_sbt_offset; 135 reloc_values[rv_count++] = (struct brw_shader_reloc_value) { 136 .id = BRW_SHADER_RELOC_RESUME_SBT_ADDR_LOW, 137 .value = resume_sbt_addr, 138 }; 139 reloc_values[rv_count++] = (struct brw_shader_reloc_value) { 140 .id = BRW_SHADER_RELOC_RESUME_SBT_ADDR_HIGH, 141 .value = resume_sbt_addr >> 32, 142 }; 143 } 144 145 brw_write_shader_relocs(&device->physical->compiler->isa, 146 shader->kernel.map, prog_data_in, 147 reloc_values, rv_count); 148 149 memcpy(prog_data, prog_data_in, prog_data_size); 150 typed_memcpy(prog_data_relocs, prog_data_in->relocs, 151 prog_data_in->num_relocs); 152 prog_data->relocs = prog_data_relocs; 153 memset(prog_data_param, 0, 154 prog_data->nr_params * sizeof(*prog_data_param)); 155 prog_data->param = prog_data_param; 156 shader->prog_data = prog_data; 157 shader->prog_data_size = prog_data_size; 158 159 assert(num_stats <= ARRAY_SIZE(shader->stats)); 160 typed_memcpy(shader->stats, stats, num_stats); 161 shader->num_stats = num_stats; 162 163 if (xfb_info_in) { 164 *xfb_info = *xfb_info_in; 165 typed_memcpy(xfb_info->outputs, xfb_info_in->outputs, 166 xfb_info_in->output_count); 167 shader->xfb_info = xfb_info; 168 } else { 169 shader->xfb_info = NULL; 170 } 171 172 shader->bind_map = *bind_map; 173 typed_memcpy(surface_to_descriptor, bind_map->surface_to_descriptor, 174 bind_map->surface_count); 175 shader->bind_map.surface_to_descriptor = surface_to_descriptor; 176 typed_memcpy(sampler_to_descriptor, bind_map->sampler_to_descriptor, 177 bind_map->sampler_count); 178 shader->bind_map.sampler_to_descriptor = sampler_to_descriptor; 179 180 return shader; 181} 182 183static bool 184anv_shader_bin_serialize(struct vk_pipeline_cache_object *object, 185 struct blob *blob) 186{ 187 struct anv_shader_bin *shader = 188 container_of(object, struct anv_shader_bin, base); 189 190 blob_write_uint32(blob, shader->stage); 191 192 blob_write_uint32(blob, shader->kernel_size); 193 blob_write_bytes(blob, shader->kernel.map, shader->kernel_size); 194 195 blob_write_uint32(blob, shader->prog_data_size); 196 blob_write_bytes(blob, shader->prog_data, shader->prog_data_size); 197 blob_write_bytes(blob, shader->prog_data->relocs, 198 shader->prog_data->num_relocs * 199 sizeof(shader->prog_data->relocs[0])); 200 201 blob_write_uint32(blob, shader->num_stats); 202 blob_write_bytes(blob, shader->stats, 203 shader->num_stats * sizeof(shader->stats[0])); 204 205 if (shader->xfb_info) { 206 uint32_t xfb_info_size = 207 nir_xfb_info_size(shader->xfb_info->output_count); 208 blob_write_uint32(blob, xfb_info_size); 209 blob_write_bytes(blob, shader->xfb_info, xfb_info_size); 210 } else { 211 blob_write_uint32(blob, 0); 212 } 213 214 blob_write_bytes(blob, shader->bind_map.surface_sha1, 215 sizeof(shader->bind_map.surface_sha1)); 216 blob_write_bytes(blob, shader->bind_map.sampler_sha1, 217 sizeof(shader->bind_map.sampler_sha1)); 218 blob_write_bytes(blob, shader->bind_map.push_sha1, 219 sizeof(shader->bind_map.push_sha1)); 220 blob_write_uint32(blob, shader->bind_map.surface_count); 221 blob_write_uint32(blob, shader->bind_map.sampler_count); 222 blob_write_bytes(blob, shader->bind_map.surface_to_descriptor, 223 shader->bind_map.surface_count * 224 sizeof(*shader->bind_map.surface_to_descriptor)); 225 blob_write_bytes(blob, shader->bind_map.sampler_to_descriptor, 226 shader->bind_map.sampler_count * 227 sizeof(*shader->bind_map.sampler_to_descriptor)); 228 blob_write_bytes(blob, shader->bind_map.push_ranges, 229 sizeof(shader->bind_map.push_ranges)); 230 231 return !blob->out_of_memory; 232} 233 234struct vk_pipeline_cache_object * 235anv_shader_bin_deserialize(struct vk_device *vk_device, 236 const void *key_data, size_t key_size, 237 struct blob_reader *blob) 238{ 239 struct anv_device *device = 240 container_of(vk_device, struct anv_device, vk); 241 242 gl_shader_stage stage = blob_read_uint32(blob); 243 244 uint32_t kernel_size = blob_read_uint32(blob); 245 const void *kernel_data = blob_read_bytes(blob, kernel_size); 246 247 uint32_t prog_data_size = blob_read_uint32(blob); 248 const void *prog_data_bytes = blob_read_bytes(blob, prog_data_size); 249 if (blob->overrun) 250 return NULL; 251 252 union brw_any_prog_data prog_data; 253 memcpy(&prog_data, prog_data_bytes, 254 MIN2(sizeof(prog_data), prog_data_size)); 255 prog_data.base.relocs = 256 blob_read_bytes(blob, prog_data.base.num_relocs * 257 sizeof(prog_data.base.relocs[0])); 258 259 uint32_t num_stats = blob_read_uint32(blob); 260 const struct brw_compile_stats *stats = 261 blob_read_bytes(blob, num_stats * sizeof(stats[0])); 262 263 const nir_xfb_info *xfb_info = NULL; 264 uint32_t xfb_size = blob_read_uint32(blob); 265 if (xfb_size) 266 xfb_info = blob_read_bytes(blob, xfb_size); 267 268 struct anv_pipeline_bind_map bind_map; 269 blob_copy_bytes(blob, bind_map.surface_sha1, sizeof(bind_map.surface_sha1)); 270 blob_copy_bytes(blob, bind_map.sampler_sha1, sizeof(bind_map.sampler_sha1)); 271 blob_copy_bytes(blob, bind_map.push_sha1, sizeof(bind_map.push_sha1)); 272 bind_map.surface_count = blob_read_uint32(blob); 273 bind_map.sampler_count = blob_read_uint32(blob); 274 bind_map.surface_to_descriptor = (void *) 275 blob_read_bytes(blob, bind_map.surface_count * 276 sizeof(*bind_map.surface_to_descriptor)); 277 bind_map.sampler_to_descriptor = (void *) 278 blob_read_bytes(blob, bind_map.sampler_count * 279 sizeof(*bind_map.sampler_to_descriptor)); 280 blob_copy_bytes(blob, bind_map.push_ranges, sizeof(bind_map.push_ranges)); 281 282 if (blob->overrun) 283 return NULL; 284 285 struct anv_shader_bin *shader = 286 anv_shader_bin_create(device, stage, 287 key_data, key_size, 288 kernel_data, kernel_size, 289 &prog_data.base, prog_data_size, 290 stats, num_stats, xfb_info, &bind_map); 291 if (shader == NULL) 292 return NULL; 293 294 return &shader->base; 295} 296 297struct anv_shader_bin * 298anv_device_search_for_kernel(struct anv_device *device, 299 struct vk_pipeline_cache *cache, 300 const void *key_data, uint32_t key_size, 301 bool *user_cache_hit) 302{ 303 /* Use the default pipeline cache if none is specified */ 304 if (cache == NULL) 305 cache = device->default_pipeline_cache; 306 307 bool cache_hit = false; 308 struct vk_pipeline_cache_object *object = 309 vk_pipeline_cache_lookup_object(cache, key_data, key_size, 310 &anv_shader_bin_ops, &cache_hit); 311 if (user_cache_hit != NULL) { 312 *user_cache_hit = object != NULL && cache_hit && 313 cache != device->default_pipeline_cache; 314 } 315 if (object == NULL) 316 return NULL; 317 318 return container_of(object, struct anv_shader_bin, base); 319} 320 321struct anv_shader_bin * 322anv_device_upload_kernel(struct anv_device *device, 323 struct vk_pipeline_cache *cache, 324 gl_shader_stage stage, 325 const void *key_data, uint32_t key_size, 326 const void *kernel_data, uint32_t kernel_size, 327 const struct brw_stage_prog_data *prog_data, 328 uint32_t prog_data_size, 329 const struct brw_compile_stats *stats, 330 uint32_t num_stats, 331 const nir_xfb_info *xfb_info, 332 const struct anv_pipeline_bind_map *bind_map) 333{ 334 /* Use the default pipeline cache if none is specified */ 335 if (cache == NULL) 336 cache = device->default_pipeline_cache; 337 338 struct anv_shader_bin *shader = 339 anv_shader_bin_create(device, stage, 340 key_data, key_size, 341 kernel_data, kernel_size, 342 prog_data, prog_data_size, 343 stats, num_stats, 344 xfb_info, bind_map); 345 if (shader == NULL) 346 return NULL; 347 348 struct vk_pipeline_cache_object *cached = 349 vk_pipeline_cache_add_object(cache, &shader->base); 350 351 return container_of(cached, struct anv_shader_bin, base); 352} 353 354#define SHA1_KEY_SIZE 20 355 356struct nir_shader * 357anv_device_search_for_nir(struct anv_device *device, 358 struct vk_pipeline_cache *cache, 359 const nir_shader_compiler_options *nir_options, 360 unsigned char sha1_key[SHA1_KEY_SIZE], 361 void *mem_ctx) 362{ 363 if (cache == NULL) 364 cache = device->default_pipeline_cache; 365 366 return vk_pipeline_cache_lookup_nir(cache, sha1_key, SHA1_KEY_SIZE, 367 nir_options, NULL, mem_ctx); 368} 369 370void 371anv_device_upload_nir(struct anv_device *device, 372 struct vk_pipeline_cache *cache, 373 const struct nir_shader *nir, 374 unsigned char sha1_key[SHA1_KEY_SIZE]) 375{ 376 if (cache == NULL) 377 cache = device->default_pipeline_cache; 378 379 vk_pipeline_cache_add_nir(cache, sha1_key, SHA1_KEY_SIZE, nir); 380} 381