1/*
2 * Copyright 2010 Jerome Glisse <glisse@freedesktop.org>
3 * Copyright 2018 Advanced Micro Devices, Inc.
4 * All Rights Reserved.
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a
7 * copy of this software and associated documentation files (the "Software"),
8 * to deal in the Software without restriction, including without limitation
9 * on the rights to use, copy, modify, merge, publish, distribute, sub
10 * license, and/or sell copies of the Software, and to permit persons to whom
11 * the Software is furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice (including the next
14 * paragraph) shall be included in all copies or substantial portions of the
15 * Software.
16 *
17 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
18 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
19 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
20 * THE AUTHOR(S) AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM,
21 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
22 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
23 * USE OR OTHER DEALINGS IN THE SOFTWARE.
24 */
25
26#include "si_pipe.h"
27
28#include "driver_ddebug/dd_util.h"
29#include "radeon_uvd.h"
30#include "si_compute.h"
31#include "si_public.h"
32#include "si_shader_internal.h"
33#include "sid.h"
34#include "ac_shadowed_regs.h"
35#include "compiler/nir/nir.h"
36#include "util/disk_cache.h"
37#include "util/u_cpu_detect.h"
38#include "util/u_log.h"
39#include "util/u_memory.h"
40#include "util/u_suballoc.h"
41#include "util/u_tests.h"
42#include "util/u_upload_mgr.h"
43#include "util/xmlconfig.h"
44#include "vl/vl_decoder.h"
45
46#include <xf86drm.h>
47
48static struct pipe_context *si_create_context(struct pipe_screen *screen, unsigned flags);
49
50static const struct debug_named_value radeonsi_debug_options[] = {
51   /* Shader logging options: */
52   {"vs", DBG(VS), "Print vertex shaders"},
53   {"ps", DBG(PS), "Print pixel shaders"},
54   {"gs", DBG(GS), "Print geometry shaders"},
55   {"tcs", DBG(TCS), "Print tessellation control shaders"},
56   {"tes", DBG(TES), "Print tessellation evaluation shaders"},
57   {"cs", DBG(CS), "Print compute shaders"},
58   {"noir", DBG(NO_IR), "Don't print the LLVM IR"},
59   {"nonir", DBG(NO_NIR), "Don't print NIR when printing shaders"},
60   {"noasm", DBG(NO_ASM), "Don't print disassembled shaders"},
61   {"preoptir", DBG(PREOPT_IR), "Print the LLVM IR before initial optimizations"},
62
63   /* Shader compiler options the shader cache should be aware of: */
64   {"w32ge", DBG(W32_GE), "Use Wave32 for vertex, tessellation, and geometry shaders."},
65   {"w32ps", DBG(W32_PS), "Use Wave32 for pixel shaders."},
66   {"w32psdiscard", DBG(W32_PS_DISCARD), "Use Wave32 for pixel shaders even if they contain discard and LLVM is buggy."},
67   {"w32cs", DBG(W32_CS), "Use Wave32 for computes shaders."},
68   {"w64ge", DBG(W64_GE), "Use Wave64 for vertex, tessellation, and geometry shaders."},
69   {"w64ps", DBG(W64_PS), "Use Wave64 for pixel shaders."},
70   {"w64cs", DBG(W64_CS), "Use Wave64 for computes shaders."},
71
72   /* Shader compiler options (with no effect on the shader cache): */
73   {"checkir", DBG(CHECK_IR), "Enable additional sanity checks on shader IR"},
74   {"mono", DBG(MONOLITHIC_SHADERS), "Use old-style monolithic shaders compiled on demand"},
75   {"nooptvariant", DBG(NO_OPT_VARIANT), "Disable compiling optimized shader variants."},
76
77   /* Information logging options: */
78   {"info", DBG(INFO), "Print driver information"},
79   {"tex", DBG(TEX), "Print texture info"},
80   {"compute", DBG(COMPUTE), "Print compute info"},
81   {"vm", DBG(VM), "Print virtual addresses when creating resources"},
82   {"cache_stats", DBG(CACHE_STATS), "Print shader cache statistics."},
83   {"ib", DBG(IB), "Print command buffers."},
84
85   /* Driver options: */
86   {"nowc", DBG(NO_WC), "Disable GTT write combining"},
87   {"check_vm", DBG(CHECK_VM), "Check VM faults and dump debug info."},
88   {"reserve_vmid", DBG(RESERVE_VMID), "Force VMID reservation per context."},
89   {"shadowregs", DBG(SHADOW_REGS), "Enable CP register shadowing."},
90   {"nofastdlist", DBG(NO_FAST_DISPLAY_LIST), "Disable fast display lists"},
91
92   /* Multimedia options: */
93   { "noefc", DBG(NO_EFC), "Disable hardware based encoder colour format conversion."},
94
95   /* 3D engine options: */
96   {"nogfx", DBG(NO_GFX), "Disable graphics. Only multimedia compute paths can be used."},
97   {"nongg", DBG(NO_NGG), "Disable NGG and use the legacy pipeline."},
98   {"nggc", DBG(ALWAYS_NGG_CULLING_ALL), "Always use NGG culling even when it can hurt."},
99   {"nonggc", DBG(NO_NGG_CULLING), "Disable NGG culling."},
100   {"switch_on_eop", DBG(SWITCH_ON_EOP), "Program WD/IA to switch on end-of-packet."},
101   {"nooutoforder", DBG(NO_OUT_OF_ORDER), "Disable out-of-order rasterization"},
102   {"nodpbb", DBG(NO_DPBB), "Disable DPBB."},
103   {"dpbb", DBG(DPBB), "Enable DPBB."},
104   {"nohyperz", DBG(NO_HYPERZ), "Disable Hyper-Z"},
105   {"no2d", DBG(NO_2D_TILING), "Disable 2D tiling"},
106   {"notiling", DBG(NO_TILING), "Disable tiling"},
107   {"nodisplaytiling", DBG(NO_DISPLAY_TILING), "Disable display tiling"},
108   {"nodisplaydcc", DBG(NO_DISPLAY_DCC), "Disable display DCC"},
109   {"noexporteddcc", DBG(NO_EXPORTED_DCC), "Disable DCC for all exported buffers (via DMABUF, etc.)"},
110   {"nodcc", DBG(NO_DCC), "Disable DCC."},
111   {"nodccclear", DBG(NO_DCC_CLEAR), "Disable DCC fast clear."},
112   {"nodccstore", DBG(NO_DCC_STORE), "Disable DCC stores"},
113   {"dccstore", DBG(DCC_STORE), "Enable DCC stores"},
114   {"nodccmsaa", DBG(NO_DCC_MSAA), "Disable DCC for MSAA"},
115   {"nofmask", DBG(NO_FMASK), "Disable MSAA compression"},
116   {"nodma", DBG(NO_DMA), "Disable SDMA-copy for DRI_PRIME"},
117
118   {"tmz", DBG(TMZ), "Force allocation of scanout/depth/stencil buffer as encrypted"},
119   {"sqtt", DBG(SQTT), "Enable SQTT"},
120
121   DEBUG_NAMED_VALUE_END /* must be last */
122};
123
124static const struct debug_named_value test_options[] = {
125   /* Tests: */
126   {"imagecopy", DBG(TEST_IMAGE_COPY), "Invoke resource_copy_region tests with images and exit."},
127   {"cbresolve", DBG(TEST_CB_RESOLVE), "Invoke MSAA resolve tests and exit."},
128   {"computeblit", DBG(TEST_COMPUTE_BLIT), "Invoke blits tests and exit."},
129   {"testvmfaultcp", DBG(TEST_VMFAULT_CP), "Invoke a CP VM fault test and exit."},
130   {"testvmfaultshader", DBG(TEST_VMFAULT_SHADER), "Invoke a shader VM fault test and exit."},
131   {"testdmaperf", DBG(TEST_DMA_PERF), "Test DMA performance"},
132   {"testgds", DBG(TEST_GDS), "Test GDS."},
133   {"testgdsmm", DBG(TEST_GDS_MM), "Test GDS memory management."},
134   {"testgdsoamm", DBG(TEST_GDS_OA_MM), "Test GDS OA memory management."},
135
136   DEBUG_NAMED_VALUE_END /* must be last */
137};
138
139bool si_init_compiler(struct si_screen *sscreen, struct ac_llvm_compiler *compiler)
140{
141   /* Only create the less-optimizing version of the compiler on APUs
142    * predating Ryzen (Raven). */
143   bool create_low_opt_compiler =
144      !sscreen->info.has_dedicated_vram && sscreen->info.gfx_level <= GFX8;
145
146   enum ac_target_machine_options tm_options =
147      (sscreen->debug_flags & DBG(CHECK_IR) ? AC_TM_CHECK_IR : 0) |
148      (create_low_opt_compiler ? AC_TM_CREATE_LOW_OPT : 0);
149
150   ac_init_llvm_once();
151
152   if (!ac_init_llvm_compiler(compiler, sscreen->info.family, tm_options))
153      return false;
154
155   compiler->passes = ac_create_llvm_passes(compiler->tm);
156   if (compiler->low_opt_tm)
157      compiler->low_opt_passes = ac_create_llvm_passes(compiler->low_opt_tm);
158
159   return true;
160}
161
162void si_init_aux_async_compute_ctx(struct si_screen *sscreen)
163{
164   assert(!sscreen->async_compute_context);
165   sscreen->async_compute_context = si_create_context(
166      &sscreen->b,
167      SI_CONTEXT_FLAG_AUX |
168         (sscreen->options.aux_debug ? PIPE_CONTEXT_DEBUG : 0) |
169         PIPE_CONTEXT_COMPUTE_ONLY);
170
171   /* Limit the numbers of waves allocated for this context. */
172   if (sscreen->async_compute_context)
173      ((struct si_context*)sscreen->async_compute_context)->cs_max_waves_per_sh = 2;
174}
175
176static void si_destroy_compiler(struct ac_llvm_compiler *compiler)
177{
178   ac_destroy_llvm_compiler(compiler);
179}
180
181
182static void decref_implicit_resource(struct hash_entry *entry)
183{
184   pipe_resource_reference((struct pipe_resource**)&entry->data, NULL);
185}
186
187/*
188 * pipe_context
189 */
190static void si_destroy_context(struct pipe_context *context)
191{
192   struct si_context *sctx = (struct si_context *)context;
193   int i;
194
195   /* Unreference the framebuffer normally to disable related logic
196    * properly.
197    */
198   struct pipe_framebuffer_state fb = {};
199   if (context->set_framebuffer_state)
200      context->set_framebuffer_state(context, &fb);
201
202   si_release_all_descriptors(sctx);
203
204   if (sctx->gfx_level >= GFX10 && sctx->has_graphics)
205      gfx10_destroy_query(sctx);
206
207   if (sctx->thread_trace)
208      si_destroy_thread_trace(sctx);
209
210   pipe_resource_reference(&sctx->esgs_ring, NULL);
211   pipe_resource_reference(&sctx->gsvs_ring, NULL);
212   pipe_resource_reference(&sctx->tess_rings, NULL);
213   pipe_resource_reference(&sctx->tess_rings_tmz, NULL);
214   pipe_resource_reference(&sctx->null_const_buf.buffer, NULL);
215   pipe_resource_reference(&sctx->sample_pos_buffer, NULL);
216   si_resource_reference(&sctx->border_color_buffer, NULL);
217   free(sctx->border_color_table);
218   si_resource_reference(&sctx->scratch_buffer, NULL);
219   si_resource_reference(&sctx->compute_scratch_buffer, NULL);
220   si_resource_reference(&sctx->wait_mem_scratch, NULL);
221   si_resource_reference(&sctx->wait_mem_scratch_tmz, NULL);
222   si_resource_reference(&sctx->small_prim_cull_info_buf, NULL);
223   si_resource_reference(&sctx->pipeline_stats_query_buf, NULL);
224
225   if (sctx->cs_preamble_state)
226      si_pm4_free_state(sctx, sctx->cs_preamble_state, ~0);
227   if (sctx->cs_preamble_state_tmz)
228      si_pm4_free_state(sctx, sctx->cs_preamble_state_tmz, ~0);
229
230   for (i = 0; i < ARRAY_SIZE(sctx->vgt_shader_config); i++)
231      si_pm4_free_state(sctx, sctx->vgt_shader_config[i], SI_STATE_IDX(vgt_shader_config));
232
233   if (sctx->fixed_func_tcs_shader_cache) {
234      hash_table_foreach(sctx->fixed_func_tcs_shader_cache, entry) {
235         sctx->b.delete_tcs_state(&sctx->b, entry->data);
236      }
237      _mesa_hash_table_destroy(sctx->fixed_func_tcs_shader_cache, NULL);
238   }
239
240   if (sctx->custom_dsa_flush)
241      sctx->b.delete_depth_stencil_alpha_state(&sctx->b, sctx->custom_dsa_flush);
242   if (sctx->custom_blend_resolve)
243      sctx->b.delete_blend_state(&sctx->b, sctx->custom_blend_resolve);
244   if (sctx->custom_blend_fmask_decompress)
245      sctx->b.delete_blend_state(&sctx->b, sctx->custom_blend_fmask_decompress);
246   if (sctx->custom_blend_eliminate_fastclear)
247      sctx->b.delete_blend_state(&sctx->b, sctx->custom_blend_eliminate_fastclear);
248   if (sctx->custom_blend_dcc_decompress)
249      sctx->b.delete_blend_state(&sctx->b, sctx->custom_blend_dcc_decompress);
250   if (sctx->vs_blit_pos)
251      sctx->b.delete_vs_state(&sctx->b, sctx->vs_blit_pos);
252   if (sctx->vs_blit_pos_layered)
253      sctx->b.delete_vs_state(&sctx->b, sctx->vs_blit_pos_layered);
254   if (sctx->vs_blit_color)
255      sctx->b.delete_vs_state(&sctx->b, sctx->vs_blit_color);
256   if (sctx->vs_blit_color_layered)
257      sctx->b.delete_vs_state(&sctx->b, sctx->vs_blit_color_layered);
258   if (sctx->vs_blit_texcoord)
259      sctx->b.delete_vs_state(&sctx->b, sctx->vs_blit_texcoord);
260   if (sctx->cs_clear_buffer)
261      sctx->b.delete_compute_state(&sctx->b, sctx->cs_clear_buffer);
262   if (sctx->cs_clear_buffer_rmw)
263      sctx->b.delete_compute_state(&sctx->b, sctx->cs_clear_buffer_rmw);
264   if (sctx->cs_copy_buffer)
265      sctx->b.delete_compute_state(&sctx->b, sctx->cs_copy_buffer);
266   for (unsigned i = 0; i < ARRAY_SIZE(sctx->cs_copy_image); i++) {
267      for (unsigned j = 0; j < ARRAY_SIZE(sctx->cs_copy_image[i]); j++) {
268         if (sctx->cs_copy_image[i][j])
269            sctx->b.delete_compute_state(&sctx->b, sctx->cs_copy_image[i][j]);
270      }
271   }
272   if (sctx->cs_clear_render_target)
273      sctx->b.delete_compute_state(&sctx->b, sctx->cs_clear_render_target);
274   if (sctx->cs_clear_render_target_1d_array)
275      sctx->b.delete_compute_state(&sctx->b, sctx->cs_clear_render_target_1d_array);
276   if (sctx->cs_clear_12bytes_buffer)
277      sctx->b.delete_compute_state(&sctx->b, sctx->cs_clear_12bytes_buffer);
278   for (unsigned i = 0; i < ARRAY_SIZE(sctx->cs_dcc_retile); i++) {
279      if (sctx->cs_dcc_retile[i])
280         sctx->b.delete_compute_state(&sctx->b, sctx->cs_dcc_retile[i]);
281   }
282   if (sctx->no_velems_state)
283      sctx->b.delete_vertex_elements_state(&sctx->b, sctx->no_velems_state);
284
285   for (unsigned i = 0; i < ARRAY_SIZE(sctx->cs_fmask_expand); i++) {
286      for (unsigned j = 0; j < ARRAY_SIZE(sctx->cs_fmask_expand[i]); j++) {
287         if (sctx->cs_fmask_expand[i][j]) {
288            sctx->b.delete_compute_state(&sctx->b, sctx->cs_fmask_expand[i][j]);
289         }
290      }
291   }
292
293   for (unsigned i = 0; i < ARRAY_SIZE(sctx->cs_clear_dcc_msaa); i++) {
294      for (unsigned j = 0; j < ARRAY_SIZE(sctx->cs_clear_dcc_msaa[i]); j++) {
295         for (unsigned k = 0; k < ARRAY_SIZE(sctx->cs_clear_dcc_msaa[i][j]); k++) {
296            for (unsigned l = 0; l < ARRAY_SIZE(sctx->cs_clear_dcc_msaa[i][j][k]); l++) {
297               for (unsigned m = 0; m < ARRAY_SIZE(sctx->cs_clear_dcc_msaa[i][j][k][l]); m++) {
298                  if (sctx->cs_clear_dcc_msaa[i][j][k][l][m])
299                     sctx->b.delete_compute_state(&sctx->b, sctx->cs_clear_dcc_msaa[i][j][k][l][m]);
300               }
301            }
302         }
303      }
304   }
305
306   if (sctx->blitter)
307      util_blitter_destroy(sctx->blitter);
308
309   if (sctx->query_result_shader)
310      sctx->b.delete_compute_state(&sctx->b, sctx->query_result_shader);
311   if (sctx->sh_query_result_shader)
312      sctx->b.delete_compute_state(&sctx->b, sctx->sh_query_result_shader);
313
314   sctx->ws->cs_destroy(&sctx->gfx_cs);
315   if (sctx->ctx)
316      sctx->ws->ctx_destroy(sctx->ctx);
317   if (sctx->sdma_cs) {
318      sctx->ws->cs_destroy(sctx->sdma_cs);
319      free(sctx->sdma_cs);
320   }
321
322   if (sctx->dirty_implicit_resources)
323      _mesa_hash_table_destroy(sctx->dirty_implicit_resources,
324                               decref_implicit_resource);
325
326   if (sctx->b.stream_uploader)
327      u_upload_destroy(sctx->b.stream_uploader);
328   if (sctx->b.const_uploader && sctx->b.const_uploader != sctx->b.stream_uploader)
329      u_upload_destroy(sctx->b.const_uploader);
330   if (sctx->cached_gtt_allocator)
331      u_upload_destroy(sctx->cached_gtt_allocator);
332
333   slab_destroy_child(&sctx->pool_transfers);
334   slab_destroy_child(&sctx->pool_transfers_unsync);
335
336   u_suballocator_destroy(&sctx->allocator_zeroed_memory);
337
338   sctx->ws->fence_reference(&sctx->last_gfx_fence, NULL);
339   si_resource_reference(&sctx->eop_bug_scratch, NULL);
340   si_resource_reference(&sctx->eop_bug_scratch_tmz, NULL);
341   si_resource_reference(&sctx->shadowed_regs, NULL);
342
343   si_destroy_compiler(&sctx->compiler);
344
345   si_saved_cs_reference(&sctx->current_saved_cs, NULL);
346
347   _mesa_hash_table_destroy(sctx->tex_handles, NULL);
348   _mesa_hash_table_destroy(sctx->img_handles, NULL);
349
350   util_dynarray_fini(&sctx->resident_tex_handles);
351   util_dynarray_fini(&sctx->resident_img_handles);
352   util_dynarray_fini(&sctx->resident_tex_needs_color_decompress);
353   util_dynarray_fini(&sctx->resident_img_needs_color_decompress);
354   util_dynarray_fini(&sctx->resident_tex_needs_depth_decompress);
355
356   if (!(sctx->context_flags & SI_CONTEXT_FLAG_AUX))
357      p_atomic_dec(&context->screen->num_contexts);
358
359   FREE(sctx);
360}
361
362static enum pipe_reset_status si_get_reset_status(struct pipe_context *ctx)
363{
364   struct si_context *sctx = (struct si_context *)ctx;
365   if (sctx->context_flags & SI_CONTEXT_FLAG_AUX)
366      return PIPE_NO_RESET;
367
368   bool needs_reset;
369   enum pipe_reset_status status = sctx->ws->ctx_query_reset_status(sctx->ctx, false, &needs_reset);
370
371   if (status != PIPE_NO_RESET && needs_reset && !(sctx->context_flags & SI_CONTEXT_FLAG_AUX)) {
372      /* Call the gallium frontend to set a no-op API dispatch. */
373      if (sctx->device_reset_callback.reset) {
374         sctx->device_reset_callback.reset(sctx->device_reset_callback.data, status);
375      }
376   }
377   return status;
378}
379
380static void si_set_device_reset_callback(struct pipe_context *ctx,
381                                         const struct pipe_device_reset_callback *cb)
382{
383   struct si_context *sctx = (struct si_context *)ctx;
384
385   if (cb)
386      sctx->device_reset_callback = *cb;
387   else
388      memset(&sctx->device_reset_callback, 0, sizeof(sctx->device_reset_callback));
389}
390
391/* Apitrace profiling:
392 *   1) qapitrace : Tools -> Profile: Measure CPU & GPU times
393 *   2) In the middle panel, zoom in (mouse wheel) on some bad draw call
394 *      and remember its number.
395 *   3) In Mesa, enable queries and performance counters around that draw
396 *      call and print the results.
397 *   4) glretrace --benchmark --markers ..
398 */
399static void si_emit_string_marker(struct pipe_context *ctx, const char *string, int len)
400{
401   struct si_context *sctx = (struct si_context *)ctx;
402
403   dd_parse_apitrace_marker(string, len, &sctx->apitrace_call_number);
404
405   if (sctx->thread_trace_enabled)
406      si_write_user_event(sctx, &sctx->gfx_cs, UserEventTrigger, string, len);
407
408   if (sctx->log)
409      u_log_printf(sctx->log, "\nString marker: %*s\n", len, string);
410}
411
412static void si_set_debug_callback(struct pipe_context *ctx, const struct util_debug_callback *cb)
413{
414   struct si_context *sctx = (struct si_context *)ctx;
415   struct si_screen *screen = sctx->screen;
416
417   util_queue_finish(&screen->shader_compiler_queue);
418   util_queue_finish(&screen->shader_compiler_queue_low_priority);
419
420   if (cb)
421      sctx->debug = *cb;
422   else
423      memset(&sctx->debug, 0, sizeof(sctx->debug));
424}
425
426static void si_set_log_context(struct pipe_context *ctx, struct u_log_context *log)
427{
428   struct si_context *sctx = (struct si_context *)ctx;
429   sctx->log = log;
430
431   if (log)
432      u_log_add_auto_logger(log, si_auto_log_cs, sctx);
433}
434
435static void si_set_context_param(struct pipe_context *ctx, enum pipe_context_param param,
436                                 unsigned value)
437{
438   struct radeon_winsys *ws = ((struct si_context *)ctx)->ws;
439
440   switch (param) {
441   case PIPE_CONTEXT_PARAM_PIN_THREADS_TO_L3_CACHE:
442      ws->pin_threads_to_L3_cache(ws, value);
443      break;
444   default:;
445   }
446}
447
448static void si_set_frontend_noop(struct pipe_context *ctx, bool enable)
449{
450   struct si_context *sctx = (struct si_context *)ctx;
451
452   ctx->flush(ctx, NULL, PIPE_FLUSH_ASYNC);
453   sctx->is_noop = enable;
454}
455
456static struct pipe_context *si_create_context(struct pipe_screen *screen, unsigned flags)
457{
458   struct si_screen *sscreen = (struct si_screen *)screen;
459   STATIC_ASSERT(DBG_COUNT <= 64);
460
461   /* Don't create a context if it's not compute-only and hw is compute-only. */
462   if (!sscreen->info.has_graphics && !(flags & PIPE_CONTEXT_COMPUTE_ONLY)) {
463      fprintf(stderr, "radeonsi: can't create a graphics context on a compute chip\n");
464      return NULL;
465   }
466
467   struct si_context *sctx = CALLOC_STRUCT(si_context);
468   struct radeon_winsys *ws = sscreen->ws;
469   int shader, i;
470   bool stop_exec_on_failure = (flags & PIPE_CONTEXT_LOSE_CONTEXT_ON_RESET) != 0;
471   enum radeon_ctx_priority priority;
472
473   if (!sctx) {
474      fprintf(stderr, "radeonsi: can't allocate a context\n");
475      return NULL;
476   }
477
478   sctx->has_graphics = sscreen->info.gfx_level == GFX6 || !(flags & PIPE_CONTEXT_COMPUTE_ONLY);
479
480   if (flags & PIPE_CONTEXT_DEBUG)
481      sscreen->record_llvm_ir = true; /* racy but not critical */
482
483   sctx->b.screen = screen; /* this must be set first */
484   sctx->b.priv = NULL;
485   sctx->b.destroy = si_destroy_context;
486   sctx->screen = sscreen; /* Easy accessing of screen/winsys. */
487   sctx->is_debug = (flags & PIPE_CONTEXT_DEBUG) != 0;
488   sctx->context_flags = flags;
489
490   slab_create_child(&sctx->pool_transfers, &sscreen->pool_transfers);
491   slab_create_child(&sctx->pool_transfers_unsync, &sscreen->pool_transfers);
492
493   sctx->ws = sscreen->ws;
494   sctx->family = sscreen->info.family;
495   sctx->gfx_level = sscreen->info.gfx_level;
496
497   if (sctx->gfx_level == GFX7 || sctx->gfx_level == GFX8 || sctx->gfx_level == GFX9) {
498      sctx->eop_bug_scratch = si_aligned_buffer_create(
499         &sscreen->b, PIPE_RESOURCE_FLAG_UNMAPPABLE | SI_RESOURCE_FLAG_DRIVER_INTERNAL,
500         PIPE_USAGE_DEFAULT, 16 * sscreen->info.max_render_backends, 256);
501      if (!sctx->eop_bug_scratch) {
502         fprintf(stderr, "radeonsi: can't create eop_bug_scratch\n");
503         goto fail;
504      }
505   }
506
507   if (flags & PIPE_CONTEXT_HIGH_PRIORITY) {
508      priority = RADEON_CTX_PRIORITY_HIGH;
509   } else if (flags & PIPE_CONTEXT_LOW_PRIORITY) {
510      priority = RADEON_CTX_PRIORITY_LOW;
511   } else {
512      priority = RADEON_CTX_PRIORITY_MEDIUM;
513   }
514
515   /* Initialize the context handle and the command stream. */
516   sctx->ctx = sctx->ws->ctx_create(sctx->ws, priority);
517   if (!sctx->ctx && priority != RADEON_CTX_PRIORITY_MEDIUM) {
518      /* Context priority should be treated as a hint. If context creation
519       * fails with the requested priority, for example because the caller
520       * lacks CAP_SYS_NICE capability or other system resource constraints,
521       * fallback to normal priority.
522       */
523      priority = RADEON_CTX_PRIORITY_MEDIUM;
524      sctx->ctx = sctx->ws->ctx_create(sctx->ws, priority);
525   }
526   if (!sctx->ctx) {
527      fprintf(stderr, "radeonsi: can't create radeon_winsys_ctx\n");
528      goto fail;
529   }
530
531   ws->cs_create(&sctx->gfx_cs, sctx->ctx, sctx->has_graphics ? AMD_IP_GFX : AMD_IP_COMPUTE,
532                 (void *)si_flush_gfx_cs, sctx, stop_exec_on_failure);
533
534   /* Initialize private allocators. */
535   u_suballocator_init(&sctx->allocator_zeroed_memory, &sctx->b, 128 * 1024, 0,
536                       PIPE_USAGE_DEFAULT,
537                       SI_RESOURCE_FLAG_CLEAR | SI_RESOURCE_FLAG_32BIT, false);
538
539   sctx->cached_gtt_allocator = u_upload_create(&sctx->b, 16 * 1024, 0, PIPE_USAGE_STAGING, 0);
540   if (!sctx->cached_gtt_allocator) {
541      fprintf(stderr, "radeonsi: can't create cached_gtt_allocator\n");
542      goto fail;
543   }
544
545   /* Initialize public allocators. */
546   /* Unify uploaders as follows:
547    * - dGPUs with Smart Access Memory: there is only one uploader instance writing to VRAM.
548    * - APUs: There is only one uploader instance writing to RAM. VRAM has the same perf on APUs.
549    * - Other chips: The const uploader writes to VRAM and the stream uploader writes to RAM.
550    */
551   bool smart_access_memory = sscreen->info.smart_access_memory;
552   bool is_apu = !sscreen->info.has_dedicated_vram;
553   sctx->b.stream_uploader =
554      u_upload_create(&sctx->b, 1024 * 1024, 0,
555                      smart_access_memory && !is_apu ? PIPE_USAGE_DEFAULT : PIPE_USAGE_STREAM,
556                      SI_RESOURCE_FLAG_32BIT); /* same flags as const_uploader */
557   if (!sctx->b.stream_uploader) {
558      fprintf(stderr, "radeonsi: can't create stream_uploader\n");
559      goto fail;
560   }
561
562   if (smart_access_memory || is_apu) {
563      sctx->b.const_uploader = sctx->b.stream_uploader;
564   } else {
565      sctx->b.const_uploader =
566         u_upload_create(&sctx->b, 256 * 1024, 0, PIPE_USAGE_DEFAULT,
567                         SI_RESOURCE_FLAG_32BIT);
568      if (!sctx->b.const_uploader) {
569         fprintf(stderr, "radeonsi: can't create const_uploader\n");
570         goto fail;
571      }
572   }
573
574   /* Border colors. */
575   if (sscreen->info.has_3d_cube_border_color_mipmap) {
576      sctx->border_color_table = malloc(SI_MAX_BORDER_COLORS * sizeof(*sctx->border_color_table));
577      if (!sctx->border_color_table) {
578         fprintf(stderr, "radeonsi: can't create border_color_table\n");
579         goto fail;
580      }
581
582      sctx->border_color_buffer = si_resource(pipe_buffer_create(
583         screen, 0, PIPE_USAGE_DEFAULT, SI_MAX_BORDER_COLORS * sizeof(*sctx->border_color_table)));
584      if (!sctx->border_color_buffer) {
585         fprintf(stderr, "radeonsi: can't create border_color_buffer\n");
586         goto fail;
587      }
588
589      sctx->border_color_map =
590         ws->buffer_map(ws, sctx->border_color_buffer->buf, NULL, PIPE_MAP_WRITE);
591      if (!sctx->border_color_map) {
592         fprintf(stderr, "radeonsi: can't map border_color_buffer\n");
593         goto fail;
594      }
595   }
596
597   sctx->ngg = sscreen->use_ngg;
598   si_shader_change_notify(sctx);
599
600   /* Initialize context functions used by graphics and compute. */
601   if (sctx->gfx_level >= GFX10)
602      sctx->emit_cache_flush = gfx10_emit_cache_flush;
603   else
604      sctx->emit_cache_flush = si_emit_cache_flush;
605
606   sctx->b.emit_string_marker = si_emit_string_marker;
607   sctx->b.set_debug_callback = si_set_debug_callback;
608   sctx->b.set_log_context = si_set_log_context;
609   sctx->b.set_context_param = si_set_context_param;
610   sctx->b.get_device_reset_status = si_get_reset_status;
611   sctx->b.set_device_reset_callback = si_set_device_reset_callback;
612   sctx->b.set_frontend_noop = si_set_frontend_noop;
613
614   si_init_all_descriptors(sctx);
615   si_init_buffer_functions(sctx);
616   si_init_clear_functions(sctx);
617   si_init_blit_functions(sctx);
618   si_init_compute_functions(sctx);
619   si_init_compute_blit_functions(sctx);
620   si_init_debug_functions(sctx);
621   si_init_fence_functions(sctx);
622   si_init_query_functions(sctx);
623   si_init_state_compute_functions(sctx);
624   si_init_context_texture_functions(sctx);
625
626   /* Initialize graphics-only context functions. */
627   if (sctx->has_graphics) {
628      if (sctx->gfx_level >= GFX10)
629         gfx10_init_query(sctx);
630      si_init_msaa_functions(sctx);
631      si_init_shader_functions(sctx);
632      si_init_state_functions(sctx);
633      si_init_streamout_functions(sctx);
634      si_init_viewport_functions(sctx);
635      si_init_spi_map_functions(sctx);
636
637      sctx->blitter = util_blitter_create(&sctx->b);
638      if (sctx->blitter == NULL) {
639         fprintf(stderr, "radeonsi: can't create blitter\n");
640         goto fail;
641      }
642      sctx->blitter->skip_viewport_restore = true;
643
644      /* Some states are expected to be always non-NULL. */
645      sctx->noop_blend = util_blitter_get_noop_blend_state(sctx->blitter);
646      sctx->queued.named.blend = sctx->noop_blend;
647
648      sctx->noop_dsa = util_blitter_get_noop_dsa_state(sctx->blitter);
649      sctx->queued.named.dsa = sctx->noop_dsa;
650
651      sctx->no_velems_state = sctx->b.create_vertex_elements_state(&sctx->b, 0, NULL);
652      sctx->vertex_elements = sctx->no_velems_state;
653
654      sctx->discard_rasterizer_state = util_blitter_get_discard_rasterizer_state(sctx->blitter);
655      sctx->queued.named.rasterizer = sctx->discard_rasterizer_state;
656
657      switch (sctx->gfx_level) {
658      case GFX6:
659         si_init_draw_functions_GFX6(sctx);
660         break;
661      case GFX7:
662         si_init_draw_functions_GFX7(sctx);
663         break;
664      case GFX8:
665         si_init_draw_functions_GFX8(sctx);
666         break;
667      case GFX9:
668         si_init_draw_functions_GFX9(sctx);
669         break;
670      case GFX10:
671         si_init_draw_functions_GFX10(sctx);
672         break;
673      case GFX10_3:
674         si_init_draw_functions_GFX10_3(sctx);
675         break;
676      case GFX11:
677         si_init_draw_functions_GFX11(sctx);
678         break;
679      default:
680         unreachable("unhandled gfx level");
681      }
682   }
683
684   sctx->sample_mask = 0xffff;
685
686   /* Initialize multimedia functions. */
687   if (sscreen->info.ip[AMD_IP_UVD].num_queues || sscreen->info.has_video_hw.vcn_decode ||
688       sscreen->info.ip[AMD_IP_VCN_JPEG].num_queues || sscreen->info.ip[AMD_IP_VCE].num_queues ||
689       sscreen->info.ip[AMD_IP_UVD_ENC].num_queues || sscreen->info.ip[AMD_IP_VCN_ENC].num_queues) {
690      sctx->b.create_video_codec = si_uvd_create_decoder;
691      sctx->b.create_video_buffer = si_video_buffer_create;
692      if (screen->resource_create_with_modifiers)
693         sctx->b.create_video_buffer_with_modifiers = si_video_buffer_create_with_modifiers;
694   } else {
695      sctx->b.create_video_codec = vl_create_decoder;
696      sctx->b.create_video_buffer = vl_video_buffer_create;
697   }
698
699   /* GFX7 cannot unbind a constant buffer (S_BUFFER_LOAD doesn't skip loads
700    * if NUM_RECORDS == 0). We need to use a dummy buffer instead. */
701   if (sctx->gfx_level == GFX7) {
702      sctx->null_const_buf.buffer =
703         pipe_aligned_buffer_create(screen,
704                                    PIPE_RESOURCE_FLAG_UNMAPPABLE | SI_RESOURCE_FLAG_32BIT |
705                                    SI_RESOURCE_FLAG_DRIVER_INTERNAL,
706                                    PIPE_USAGE_DEFAULT, 16,
707                                    sctx->screen->info.tcc_cache_line_size);
708      if (!sctx->null_const_buf.buffer) {
709         fprintf(stderr, "radeonsi: can't create null_const_buf\n");
710         goto fail;
711      }
712      sctx->null_const_buf.buffer_size = sctx->null_const_buf.buffer->width0;
713
714      unsigned start_shader = sctx->has_graphics ? 0 : PIPE_SHADER_COMPUTE;
715      for (shader = start_shader; shader < SI_NUM_SHADERS; shader++) {
716         for (i = 0; i < SI_NUM_CONST_BUFFERS; i++) {
717            sctx->b.set_constant_buffer(&sctx->b, shader, i, false, &sctx->null_const_buf);
718         }
719      }
720
721      si_set_internal_const_buffer(sctx, SI_HS_CONST_DEFAULT_TESS_LEVELS, &sctx->null_const_buf);
722      si_set_internal_const_buffer(sctx, SI_VS_CONST_INSTANCE_DIVISORS, &sctx->null_const_buf);
723      si_set_internal_const_buffer(sctx, SI_VS_CONST_CLIP_PLANES, &sctx->null_const_buf);
724      si_set_internal_const_buffer(sctx, SI_PS_CONST_POLY_STIPPLE, &sctx->null_const_buf);
725      si_set_internal_const_buffer(sctx, SI_PS_CONST_SAMPLE_POSITIONS, &sctx->null_const_buf);
726   }
727
728   /* Bindless handles. */
729   sctx->tex_handles = _mesa_hash_table_create(NULL, _mesa_hash_pointer, _mesa_key_pointer_equal);
730   sctx->img_handles = _mesa_hash_table_create(NULL, _mesa_hash_pointer, _mesa_key_pointer_equal);
731
732   util_dynarray_init(&sctx->resident_tex_handles, NULL);
733   util_dynarray_init(&sctx->resident_img_handles, NULL);
734   util_dynarray_init(&sctx->resident_tex_needs_color_decompress, NULL);
735   util_dynarray_init(&sctx->resident_img_needs_color_decompress, NULL);
736   util_dynarray_init(&sctx->resident_tex_needs_depth_decompress, NULL);
737
738   sctx->dirty_implicit_resources = _mesa_pointer_hash_table_create(NULL);
739   if (!sctx->dirty_implicit_resources) {
740      fprintf(stderr, "radeonsi: can't create dirty_implicit_resources\n");
741      goto fail;
742   }
743
744   /* The remainder of this function initializes the gfx CS and must be last. */
745   assert(sctx->gfx_cs.current.cdw == 0);
746
747   if (sctx->has_graphics) {
748      si_init_cp_reg_shadowing(sctx);
749   }
750
751   /* Set immutable fields of shader keys. */
752   if (sctx->gfx_level >= GFX9) {
753      /* The LS output / HS input layout can be communicated
754       * directly instead of via user SGPRs for merged LS-HS.
755       * This also enables jumping over the VS prolog for HS-only waves.
756       *
757       * When the LS VGPR fix is needed, monolithic shaders can:
758       *  - avoid initializing EXEC in both the LS prolog
759       *    and the LS main part when !vs_needs_prolog
760       *  - remove the fixup for unused input VGPRs
761       */
762      sctx->shader.tcs.key.ge.opt.prefer_mono = 1;
763
764      /* This enables jumping over the VS prolog for GS-only waves. */
765      sctx->shader.gs.key.ge.opt.prefer_mono = 1;
766   }
767
768   si_begin_new_gfx_cs(sctx, true);
769   assert(sctx->gfx_cs.current.cdw == sctx->initial_gfx_cs_size);
770
771   if (sctx->gfx_level >= GFX9 && sctx->gfx_level < GFX11) {
772      sctx->wait_mem_scratch =
773           si_aligned_buffer_create(screen,
774                                    PIPE_RESOURCE_FLAG_UNMAPPABLE |
775                                    SI_RESOURCE_FLAG_DRIVER_INTERNAL,
776                                    PIPE_USAGE_DEFAULT, 4,
777                                    sscreen->info.tcc_cache_line_size);
778      if (!sctx->wait_mem_scratch) {
779         fprintf(stderr, "radeonsi: can't create wait_mem_scratch\n");
780         goto fail;
781      }
782
783      si_cp_write_data(sctx, sctx->wait_mem_scratch, 0, 4, V_370_MEM, V_370_ME,
784                       &sctx->wait_mem_number);
785   }
786
787   if (sctx->gfx_level == GFX7) {
788      /* Clear the NULL constant buffer, because loads should return zeros.
789       * Note that this forces CP DMA to be used, because clover deadlocks
790       * for some reason when the compute codepath is used.
791       */
792      uint32_t clear_value = 0;
793      si_clear_buffer(sctx, sctx->null_const_buf.buffer, 0, sctx->null_const_buf.buffer->width0,
794                      &clear_value, 4, SI_OP_SYNC_AFTER, SI_COHERENCY_SHADER,
795                      SI_CP_DMA_CLEAR_METHOD);
796   }
797
798   if (!(flags & SI_CONTEXT_FLAG_AUX)) {
799      p_atomic_inc(&screen->num_contexts);
800
801      /* Check if the aux_context needs to be recreated */
802      struct si_context *saux = si_get_aux_context(sscreen);
803
804      enum pipe_reset_status status = sctx->ws->ctx_query_reset_status(
805         saux->ctx, true, NULL);
806      if (status != PIPE_NO_RESET) {
807         /* We lost the aux_context, create a new one */
808         struct u_log_context *aux_log = (saux)->log;
809         saux->b.set_log_context(&saux->b, NULL);
810         saux->b.destroy(&saux->b);
811
812         saux = (struct si_context *)si_create_context(
813            &sscreen->b, SI_CONTEXT_FLAG_AUX |
814                         (sscreen->options.aux_debug ? PIPE_CONTEXT_DEBUG : 0) |
815                         (sscreen->info.has_graphics ? 0 : PIPE_CONTEXT_COMPUTE_ONLY));
816         saux->b.set_log_context(&saux->b, aux_log);
817         sscreen->aux_context = saux;
818      }
819      si_put_aux_context_flush(sscreen);
820
821      simple_mtx_lock(&sscreen->async_compute_context_lock);
822      if (status != PIPE_NO_RESET && sscreen->async_compute_context) {
823         sscreen->async_compute_context->destroy(sscreen->async_compute_context);
824         sscreen->async_compute_context = NULL;
825      }
826      simple_mtx_unlock(&sscreen->async_compute_context_lock);
827   }
828
829   sctx->initial_gfx_cs_size = sctx->gfx_cs.current.cdw;
830   return &sctx->b;
831fail:
832   fprintf(stderr, "radeonsi: Failed to create a context.\n");
833   si_destroy_context(&sctx->b);
834   return NULL;
835}
836
837static bool si_is_resource_busy(struct pipe_screen *screen, struct pipe_resource *resource,
838                                unsigned usage)
839{
840   struct radeon_winsys *ws = ((struct si_screen *)screen)->ws;
841
842   return !ws->buffer_wait(ws, si_resource(resource)->buf, 0,
843                           /* If mapping for write, we need to wait for all reads and writes.
844                            * If mapping for read, we only need to wait for writes.
845                            */
846                           usage & PIPE_MAP_WRITE ? RADEON_USAGE_READWRITE : RADEON_USAGE_WRITE);
847}
848
849static struct pipe_context *si_pipe_create_context(struct pipe_screen *screen, void *priv,
850                                                   unsigned flags)
851{
852   struct si_screen *sscreen = (struct si_screen *)screen;
853   struct pipe_context *ctx;
854
855   if (sscreen->debug_flags & DBG(CHECK_VM))
856      flags |= PIPE_CONTEXT_DEBUG;
857
858   ctx = si_create_context(screen, flags);
859
860   if (ctx && sscreen->info.gfx_level >= GFX9 && sscreen->debug_flags & DBG(SQTT)) {
861      if (ac_check_profile_state(&sscreen->info)) {
862         fprintf(stderr, "radeonsi: Canceling RGP trace request as a hang condition has been "
863                         "detected. Force the GPU into a profiling mode with e.g. "
864                         "\"echo profile_peak  > "
865                         "/sys/class/drm/card0/device/power_dpm_force_performance_level\"\n");
866      } else if (!si_init_thread_trace((struct si_context *)ctx)) {
867         FREE(ctx);
868         return NULL;
869      }
870   }
871
872   if (!(flags & PIPE_CONTEXT_PREFER_THREADED))
873      return ctx;
874
875   /* Clover (compute-only) is unsupported. */
876   if (flags & PIPE_CONTEXT_COMPUTE_ONLY)
877      return ctx;
878
879   /* When shaders are logged to stderr, asynchronous compilation is
880    * disabled too. */
881   if (sscreen->debug_flags & DBG_ALL_SHADERS)
882      return ctx;
883
884   /* Use asynchronous flushes only on amdgpu, since the radeon
885    * implementation for fence_server_sync is incomplete. */
886   struct pipe_context *tc =
887      threaded_context_create(ctx, &sscreen->pool_transfers,
888                              si_replace_buffer_storage,
889                              &(struct threaded_context_options){
890                                 .create_fence = sscreen->info.is_amdgpu ?
891                                       si_create_fence : NULL,
892                                 .is_resource_busy = si_is_resource_busy,
893                                 .driver_calls_flush_notify = true,
894                              },
895                              &((struct si_context *)ctx)->tc);
896
897   if (tc && tc != ctx)
898      threaded_context_init_bytes_mapped_limit((struct threaded_context *)tc, 4);
899
900   return tc;
901}
902
903/*
904 * pipe_screen
905 */
906static void si_destroy_screen(struct pipe_screen *pscreen)
907{
908   struct si_screen *sscreen = (struct si_screen *)pscreen;
909   struct si_shader_part *parts[] = {sscreen->vs_prologs, sscreen->tcs_epilogs,
910                                     sscreen->ps_prologs, sscreen->ps_epilogs};
911   unsigned i;
912
913   if (!sscreen->ws->unref(sscreen->ws))
914      return;
915
916   if (sscreen->debug_flags & DBG(CACHE_STATS)) {
917      printf("live shader cache:   hits = %u, misses = %u\n", sscreen->live_shader_cache.hits,
918             sscreen->live_shader_cache.misses);
919      printf("memory shader cache: hits = %u, misses = %u\n", sscreen->num_memory_shader_cache_hits,
920             sscreen->num_memory_shader_cache_misses);
921      printf("disk shader cache:   hits = %u, misses = %u\n", sscreen->num_disk_shader_cache_hits,
922             sscreen->num_disk_shader_cache_misses);
923   }
924
925   si_resource_reference(&sscreen->attribute_ring, NULL);
926
927   if (sscreen->aux_context) {
928      struct si_context *saux = si_get_aux_context(sscreen);
929      struct u_log_context *aux_log = saux->log;
930      if (aux_log) {
931         saux->b.set_log_context(&saux->b, NULL);
932         u_log_context_destroy(aux_log);
933         FREE(aux_log);
934      }
935
936      saux->b.destroy(&saux->b);
937      mtx_unlock(&sscreen->aux_context_lock);
938   }
939   mtx_destroy(&sscreen->aux_context_lock);
940
941   simple_mtx_destroy(&sscreen->async_compute_context_lock);
942   if (sscreen->async_compute_context) {
943      sscreen->async_compute_context->destroy(sscreen->async_compute_context);
944   }
945
946   util_queue_destroy(&sscreen->shader_compiler_queue);
947   util_queue_destroy(&sscreen->shader_compiler_queue_low_priority);
948
949   /* Release the reference on glsl types of the compiler threads. */
950   glsl_type_singleton_decref();
951
952   for (i = 0; i < ARRAY_SIZE(sscreen->compiler); i++)
953      si_destroy_compiler(&sscreen->compiler[i]);
954
955   for (i = 0; i < ARRAY_SIZE(sscreen->compiler_lowp); i++)
956      si_destroy_compiler(&sscreen->compiler_lowp[i]);
957
958   /* Free shader parts. */
959   for (i = 0; i < ARRAY_SIZE(parts); i++) {
960      while (parts[i]) {
961         struct si_shader_part *part = parts[i];
962
963         parts[i] = part->next;
964         si_shader_binary_clean(&part->binary);
965         FREE(part);
966      }
967   }
968   simple_mtx_destroy(&sscreen->shader_parts_mutex);
969   si_destroy_shader_cache(sscreen);
970
971   si_destroy_perfcounters(sscreen);
972   si_gpu_load_kill_thread(sscreen);
973
974   simple_mtx_destroy(&sscreen->gpu_load_mutex);
975   simple_mtx_destroy(&sscreen->gds_mutex);
976
977   radeon_bo_reference(sscreen->ws, &sscreen->gds, NULL);
978   radeon_bo_reference(sscreen->ws, &sscreen->gds_oa, NULL);
979
980   slab_destroy_parent(&sscreen->pool_transfers);
981
982   disk_cache_destroy(sscreen->disk_shader_cache);
983   util_live_shader_cache_deinit(&sscreen->live_shader_cache);
984   util_idalloc_mt_fini(&sscreen->buffer_ids);
985   util_vertex_state_cache_deinit(&sscreen->vertex_state_cache);
986
987   sscreen->ws->destroy(sscreen->ws);
988   FREE(sscreen);
989}
990
991static void si_init_gs_info(struct si_screen *sscreen)
992{
993   sscreen->gs_table_depth = ac_get_gs_table_depth(sscreen->info.gfx_level, sscreen->info.family);
994}
995
996static void si_test_vmfault(struct si_screen *sscreen, uint64_t test_flags)
997{
998   struct pipe_context *ctx = sscreen->aux_context;
999   struct si_context *sctx = (struct si_context *)ctx;
1000   struct pipe_resource *buf = pipe_buffer_create_const0(&sscreen->b, 0, PIPE_USAGE_DEFAULT, 64);
1001
1002   if (!buf) {
1003      puts("Buffer allocation failed.");
1004      exit(1);
1005   }
1006
1007   si_resource(buf)->gpu_address = 0; /* cause a VM fault */
1008
1009   if (test_flags & DBG(TEST_VMFAULT_CP)) {
1010      si_cp_dma_copy_buffer(sctx, buf, buf, 0, 4, 4, SI_OP_SYNC_BEFORE_AFTER,
1011                            SI_COHERENCY_NONE, L2_BYPASS);
1012      ctx->flush(ctx, NULL, 0);
1013      puts("VM fault test: CP - done.");
1014   }
1015   if (test_flags & DBG(TEST_VMFAULT_SHADER)) {
1016      util_test_constant_buffer(ctx, buf);
1017      puts("VM fault test: Shader - done.");
1018   }
1019   exit(0);
1020}
1021
1022static void si_test_gds_memory_management(struct si_context *sctx, unsigned alloc_size,
1023                                          unsigned alignment, enum radeon_bo_domain domain)
1024{
1025   struct radeon_winsys *ws = sctx->ws;
1026   struct radeon_cmdbuf cs[8];
1027   struct pb_buffer *gds_bo[ARRAY_SIZE(cs)];
1028
1029   for (unsigned i = 0; i < ARRAY_SIZE(cs); i++) {
1030      ws->cs_create(&cs[i], sctx->ctx, AMD_IP_COMPUTE, NULL, NULL, false);
1031      gds_bo[i] = ws->buffer_create(ws, alloc_size, alignment, domain, 0);
1032      assert(gds_bo[i]);
1033   }
1034
1035   for (unsigned iterations = 0; iterations < 20000; iterations++) {
1036      for (unsigned i = 0; i < ARRAY_SIZE(cs); i++) {
1037         /* This clears GDS with CP DMA.
1038          *
1039          * We don't care if GDS is present. Just add some packet
1040          * to make the GPU busy for a moment.
1041          */
1042         si_cp_dma_clear_buffer(
1043            sctx, &cs[i], NULL, 0, alloc_size, 0,
1044            SI_OP_CPDMA_SKIP_CHECK_CS_SPACE, 0,
1045            0);
1046
1047         ws->cs_add_buffer(&cs[i], gds_bo[i], RADEON_USAGE_READWRITE, domain);
1048         ws->cs_flush(&cs[i], PIPE_FLUSH_ASYNC, NULL);
1049      }
1050   }
1051   exit(0);
1052}
1053
1054static void si_disk_cache_create(struct si_screen *sscreen)
1055{
1056   /* Don't use the cache if shader dumping is enabled. */
1057   if (sscreen->debug_flags & DBG_ALL_SHADERS)
1058      return;
1059
1060   struct mesa_sha1 ctx;
1061   unsigned char sha1[20];
1062   char cache_id[20 * 2 + 1];
1063
1064   _mesa_sha1_init(&ctx);
1065
1066   if (!disk_cache_get_function_identifier(si_disk_cache_create, &ctx) ||
1067       !disk_cache_get_function_identifier(LLVMInitializeAMDGPUTargetInfo, &ctx))
1068      return;
1069
1070   _mesa_sha1_final(&ctx, sha1);
1071   disk_cache_format_hex_id(cache_id, sha1, 20 * 2);
1072
1073   sscreen->disk_shader_cache = disk_cache_create(sscreen->info.name, cache_id,
1074                                                  sscreen->info.address32_hi);
1075}
1076
1077static void si_set_max_shader_compiler_threads(struct pipe_screen *screen, unsigned max_threads)
1078{
1079   struct si_screen *sscreen = (struct si_screen *)screen;
1080
1081   /* This function doesn't allow a greater number of threads than
1082    * the queue had at its creation. */
1083   util_queue_adjust_num_threads(&sscreen->shader_compiler_queue, max_threads);
1084   /* Don't change the number of threads on the low priority queue. */
1085}
1086
1087static bool si_is_parallel_shader_compilation_finished(struct pipe_screen *screen, void *shader,
1088                                                       enum pipe_shader_type shader_type)
1089{
1090   struct si_shader_selector *sel = (struct si_shader_selector *)shader;
1091
1092   return util_queue_fence_is_signalled(&sel->ready);
1093}
1094
1095static struct pipe_screen *radeonsi_screen_create_impl(struct radeon_winsys *ws,
1096                                                       const struct pipe_screen_config *config)
1097{
1098   struct si_screen *sscreen = CALLOC_STRUCT(si_screen);
1099   unsigned hw_threads, num_comp_hi_threads, num_comp_lo_threads;
1100   uint64_t test_flags;
1101
1102   if (!sscreen) {
1103      return NULL;
1104   }
1105
1106   {
1107#define OPT_BOOL(name, dflt, description)                                                          \
1108   sscreen->options.name = driQueryOptionb(config->options, "radeonsi_" #name);
1109#define OPT_INT(name, dflt, description)                                                           \
1110   sscreen->options.name = driQueryOptioni(config->options, "radeonsi_" #name);
1111#include "si_debug_options.h"
1112   }
1113
1114   sscreen->ws = ws;
1115   ws->query_info(ws, &sscreen->info,
1116                  sscreen->options.enable_sam,
1117                  sscreen->options.disable_sam);
1118
1119   if (sscreen->info.gfx_level >= GFX9) {
1120      sscreen->se_tile_repeat = 32 * sscreen->info.max_se;
1121   } else {
1122      ac_get_raster_config(&sscreen->info, &sscreen->pa_sc_raster_config,
1123                           &sscreen->pa_sc_raster_config_1, &sscreen->se_tile_repeat);
1124   }
1125
1126   sscreen->debug_flags = debug_get_flags_option("R600_DEBUG", radeonsi_debug_options, 0);
1127   sscreen->debug_flags |= debug_get_flags_option("AMD_DEBUG", radeonsi_debug_options, 0);
1128   test_flags = debug_get_flags_option("AMD_TEST", test_options, 0);
1129
1130   if (sscreen->debug_flags & DBG(NO_GFX))
1131      sscreen->info.has_graphics = false;
1132
1133   if ((sscreen->debug_flags & DBG(TMZ)) &&
1134       !sscreen->info.has_tmz_support) {
1135      fprintf(stderr, "radeonsi: requesting TMZ features but TMZ is not supported\n");
1136      FREE(sscreen);
1137      return NULL;
1138   }
1139
1140   /* Initialize just one compiler instance to check for errors. The other compiler instances are
1141    * initialized on demand.
1142    */
1143   if (!si_init_compiler(sscreen, &sscreen->compiler[0])) {
1144      /* The callee prints the error message. */
1145      FREE(sscreen);
1146      return NULL;
1147   }
1148
1149   util_idalloc_mt_init_tc(&sscreen->buffer_ids);
1150
1151   /* Set functions first. */
1152   sscreen->b.context_create = si_pipe_create_context;
1153   sscreen->b.destroy = si_destroy_screen;
1154   sscreen->b.set_max_shader_compiler_threads = si_set_max_shader_compiler_threads;
1155   sscreen->b.is_parallel_shader_compilation_finished = si_is_parallel_shader_compilation_finished;
1156   sscreen->b.finalize_nir = si_finalize_nir;
1157
1158   si_init_screen_get_functions(sscreen);
1159   si_init_screen_buffer_functions(sscreen);
1160   si_init_screen_fence_functions(sscreen);
1161   si_init_screen_state_functions(sscreen);
1162   si_init_screen_texture_functions(sscreen);
1163   si_init_screen_query_functions(sscreen);
1164   si_init_screen_live_shader_cache(sscreen);
1165
1166   sscreen->max_texel_buffer_elements = sscreen->b.get_param(
1167      &sscreen->b, PIPE_CAP_MAX_TEXEL_BUFFER_ELEMENTS_UINT);
1168
1169   /* Set these flags in debug_flags early, so that the shader cache takes
1170    * them into account.
1171    *
1172    * Enable FS_CORRECT_DERIVS_AFTER_KILL by default if LLVM is >= 13. This makes
1173    * nir_opt_move_discards_to_top more effective.
1174    */
1175   if (driQueryOptionb(config->options, "glsl_correct_derivatives_after_discard") ||
1176       LLVM_VERSION_MAJOR >= 13)
1177      sscreen->debug_flags |= DBG(FS_CORRECT_DERIVS_AFTER_KILL);
1178
1179   if (sscreen->debug_flags & DBG(INFO))
1180      ac_print_gpu_info(&sscreen->info, stdout);
1181
1182   slab_create_parent(&sscreen->pool_transfers, sizeof(struct si_transfer), 64);
1183
1184   sscreen->force_aniso = MIN2(16, debug_get_num_option("R600_TEX_ANISO", -1));
1185   if (sscreen->force_aniso == -1) {
1186      sscreen->force_aniso = MIN2(16, debug_get_num_option("AMD_TEX_ANISO", -1));
1187   }
1188
1189   if (sscreen->force_aniso >= 0) {
1190      printf("radeonsi: Forcing anisotropy filter to %ix\n",
1191             /* round down to a power of two */
1192             1 << util_logbase2(sscreen->force_aniso));
1193   }
1194
1195   (void)mtx_init(&sscreen->aux_context_lock, mtx_recursive);
1196   (void)simple_mtx_init(&sscreen->async_compute_context_lock, mtx_plain);
1197   (void)simple_mtx_init(&sscreen->gpu_load_mutex, mtx_plain);
1198   (void)simple_mtx_init(&sscreen->gds_mutex, mtx_plain);
1199
1200   si_init_gs_info(sscreen);
1201   if (!si_init_shader_cache(sscreen)) {
1202      FREE(sscreen);
1203      return NULL;
1204   }
1205
1206   if (sscreen->info.gfx_level < GFX10_3)
1207      sscreen->options.vrs2x2 = false;
1208
1209   si_disk_cache_create(sscreen);
1210
1211   /* Determine the number of shader compiler threads. */
1212   const struct util_cpu_caps_t *caps = util_get_cpu_caps();
1213   hw_threads = caps->nr_cpus;
1214
1215   if (hw_threads >= 12) {
1216      num_comp_hi_threads = hw_threads * 3 / 4;
1217      num_comp_lo_threads = hw_threads / 3;
1218   } else if (hw_threads >= 6) {
1219      num_comp_hi_threads = hw_threads - 2;
1220      num_comp_lo_threads = hw_threads / 2;
1221   } else if (hw_threads >= 2) {
1222      num_comp_hi_threads = hw_threads - 1;
1223      num_comp_lo_threads = hw_threads / 2;
1224   } else {
1225      num_comp_hi_threads = 1;
1226      num_comp_lo_threads = 1;
1227   }
1228
1229#ifndef NDEBUG
1230   nir_process_debug_variable();
1231
1232   /* Use a single compilation thread if NIR printing is enabled to avoid
1233    * multiple shaders being printed at the same time.
1234    */
1235   if (NIR_DEBUG(PRINT)) {
1236      num_comp_hi_threads = 1;
1237      num_comp_lo_threads = 1;
1238   }
1239#endif
1240
1241   num_comp_hi_threads = MIN2(num_comp_hi_threads, ARRAY_SIZE(sscreen->compiler));
1242   num_comp_lo_threads = MIN2(num_comp_lo_threads, ARRAY_SIZE(sscreen->compiler_lowp));
1243
1244   /* Take a reference on the glsl types for the compiler threads. */
1245   glsl_type_singleton_init_or_ref();
1246
1247   /* Start with a single thread and a single slot.
1248    * Each time we'll hit the "all slots are in use" case, the number of threads and
1249    * slots will be increased.
1250    */
1251   int num_slots = num_comp_hi_threads == 1 ? 64 : 1;
1252   if (!util_queue_init(&sscreen->shader_compiler_queue, "sh", num_slots,
1253                        num_comp_hi_threads,
1254                        UTIL_QUEUE_INIT_RESIZE_IF_FULL |
1255                           UTIL_QUEUE_INIT_SCALE_THREADS |
1256                           UTIL_QUEUE_INIT_SET_FULL_THREAD_AFFINITY, NULL)) {
1257      si_destroy_shader_cache(sscreen);
1258      FREE(sscreen);
1259      glsl_type_singleton_decref();
1260      return NULL;
1261   }
1262
1263   if (!util_queue_init(&sscreen->shader_compiler_queue_low_priority, "shlo", num_slots,
1264                        num_comp_lo_threads,
1265                        UTIL_QUEUE_INIT_RESIZE_IF_FULL |
1266                           UTIL_QUEUE_INIT_SCALE_THREADS |
1267                           UTIL_QUEUE_INIT_SET_FULL_THREAD_AFFINITY |
1268                           UTIL_QUEUE_INIT_USE_MINIMUM_PRIORITY, NULL)) {
1269      si_destroy_shader_cache(sscreen);
1270      FREE(sscreen);
1271      glsl_type_singleton_decref();
1272      return NULL;
1273   }
1274
1275   if (!debug_get_bool_option("RADEON_DISABLE_PERFCOUNTERS", false))
1276      si_init_perfcounters(sscreen);
1277
1278   sscreen->max_memory_usage_kb = sscreen->info.vram_size_kb + sscreen->info.gart_size_kb / 4 * 3;
1279
1280   ac_get_hs_info(&sscreen->info, &sscreen->hs);
1281
1282   sscreen->has_draw_indirect_multi =
1283      (sscreen->info.family >= CHIP_POLARIS10) ||
1284      (sscreen->info.gfx_level == GFX8 && sscreen->info.pfp_fw_version >= 121 &&
1285       sscreen->info.me_fw_version >= 87) ||
1286      (sscreen->info.gfx_level == GFX7 && sscreen->info.pfp_fw_version >= 211 &&
1287       sscreen->info.me_fw_version >= 173) ||
1288      (sscreen->info.gfx_level == GFX6 && sscreen->info.pfp_fw_version >= 79 &&
1289       sscreen->info.me_fw_version >= 142);
1290
1291   sscreen->has_out_of_order_rast =
1292      sscreen->info.has_out_of_order_rast && !(sscreen->debug_flags & DBG(NO_OUT_OF_ORDER));
1293
1294   if (sscreen->info.gfx_level >= GFX11) {
1295      sscreen->use_ngg = true;
1296      sscreen->use_ngg_streamout = true;
1297      /* TODO: Disable for now. Investigate if it helps.  */
1298      sscreen->use_ngg_culling = (sscreen->debug_flags & DBG(ALWAYS_NGG_CULLING_ALL)) &&
1299                                 !(sscreen->debug_flags & DBG(NO_NGG_CULLING));
1300   } else {
1301      sscreen->use_ngg = !(sscreen->debug_flags & DBG(NO_NGG)) &&
1302                         sscreen->info.gfx_level >= GFX10 &&
1303                         (sscreen->info.family != CHIP_NAVI14 ||
1304                          sscreen->info.is_pro_graphics);
1305      sscreen->use_ngg_streamout = false;
1306      sscreen->use_ngg_culling = sscreen->use_ngg &&
1307                                 sscreen->info.max_render_backends >= 2 &&
1308                                 !(sscreen->debug_flags & DBG(NO_NGG_CULLING)) &&
1309                                 LLVM_VERSION_MAJOR >= 12; /* hangs on 11, see #4874 */
1310   }
1311
1312   /* Only set this for the cases that are known to work, which are:
1313    * - GFX9 if bpp >= 4 (in bytes)
1314    */
1315   if (sscreen->info.gfx_level >= GFX10) {
1316      memset(sscreen->allow_dcc_msaa_clear_to_reg_for_bpp, true,
1317             sizeof(sscreen->allow_dcc_msaa_clear_to_reg_for_bpp));
1318   } else if (sscreen->info.gfx_level == GFX9) {
1319      for (unsigned bpp_log2 = util_logbase2(1); bpp_log2 <= util_logbase2(16); bpp_log2++)
1320         sscreen->allow_dcc_msaa_clear_to_reg_for_bpp[bpp_log2] = true;
1321   }
1322
1323   /* DCC stores have 50% performance of uncompressed stores and sometimes
1324    * even less than that. It's risky to enable on dGPUs.
1325    */
1326   sscreen->always_allow_dcc_stores = !(sscreen->debug_flags & DBG(NO_DCC_STORE)) &&
1327                                      (sscreen->debug_flags & DBG(DCC_STORE) ||
1328                                       sscreen->info.gfx_level >= GFX11 || /* always enabled on gfx11 */
1329                                       (sscreen->info.gfx_level >= GFX10_3 &&
1330                                        !sscreen->info.has_dedicated_vram));
1331
1332   sscreen->dpbb_allowed = !(sscreen->debug_flags & DBG(NO_DPBB)) &&
1333                           (sscreen->info.gfx_level >= GFX10 ||
1334                            /* Only enable primitive binning on gfx9 APUs by default. */
1335                            (sscreen->info.gfx_level == GFX9 && !sscreen->info.has_dedicated_vram) ||
1336                            sscreen->debug_flags & DBG(DPBB));
1337
1338   if (sscreen->dpbb_allowed) {
1339      if (sscreen->info.has_dedicated_vram) {
1340         if (sscreen->info.max_render_backends > 4) {
1341            sscreen->pbb_context_states_per_bin = 1;
1342            sscreen->pbb_persistent_states_per_bin = 1;
1343         } else {
1344            sscreen->pbb_context_states_per_bin = 3;
1345            sscreen->pbb_persistent_states_per_bin = 8;
1346         }
1347      } else {
1348         /* This is a workaround for:
1349          *    https://bugs.freedesktop.org/show_bug.cgi?id=110214
1350          * (an alternative is to insert manual BATCH_BREAK event when
1351          *  a context_roll is detected). */
1352         sscreen->pbb_context_states_per_bin = sscreen->info.has_gfx9_scissor_bug ? 1 : 6;
1353         /* Using 32 here can cause GPU hangs on RAVEN1 */
1354         sscreen->pbb_persistent_states_per_bin = 16;
1355      }
1356
1357      assert(sscreen->pbb_context_states_per_bin >= 1 &&
1358             sscreen->pbb_context_states_per_bin <= 6);
1359      assert(sscreen->pbb_persistent_states_per_bin >= 1 &&
1360             sscreen->pbb_persistent_states_per_bin <= 32);
1361   }
1362
1363   (void)simple_mtx_init(&sscreen->shader_parts_mutex, mtx_plain);
1364   sscreen->use_monolithic_shaders = (sscreen->debug_flags & DBG(MONOLITHIC_SHADERS)) != 0;
1365
1366   sscreen->barrier_flags.cp_to_L2 = SI_CONTEXT_INV_SCACHE | SI_CONTEXT_INV_VCACHE;
1367   if (sscreen->info.gfx_level <= GFX8) {
1368      sscreen->barrier_flags.cp_to_L2 |= SI_CONTEXT_INV_L2;
1369      sscreen->barrier_flags.L2_to_cp |= SI_CONTEXT_WB_L2;
1370   }
1371
1372   if (debug_get_bool_option("RADEON_DUMP_SHADERS", false))
1373      sscreen->debug_flags |= DBG_ALL_SHADERS;
1374
1375   /* Syntax:
1376    *     EQAA=s,z,c
1377    * Example:
1378    *     EQAA=8,4,2
1379
1380    * That means 8 coverage samples, 4 Z/S samples, and 2 color samples.
1381    * Constraints:
1382    *     s >= z >= c (ignoring this only wastes memory)
1383    *     s = [2..16]
1384    *     z = [2..8]
1385    *     c = [2..8]
1386    *
1387    * Only MSAA color and depth buffers are overriden.
1388    */
1389   if (sscreen->info.has_eqaa_surface_allocator) {
1390      const char *eqaa = debug_get_option("EQAA", NULL);
1391      unsigned s, z, f;
1392
1393      if (eqaa && sscanf(eqaa, "%u,%u,%u", &s, &z, &f) == 3 && s && z && f) {
1394         sscreen->eqaa_force_coverage_samples = s;
1395         sscreen->eqaa_force_z_samples = z;
1396         sscreen->eqaa_force_color_samples = f;
1397      }
1398   }
1399
1400   sscreen->ngg_subgroup_size = 128;
1401
1402   if (sscreen->info.gfx_level >= GFX11) {
1403      /* TODO: tweak this */
1404      unsigned attr_ring_size_per_se = align(1400000, 64 * 1024);
1405      unsigned attr_ring_size = attr_ring_size_per_se * sscreen->info.max_se;
1406      assert(attr_ring_size <= 16 * 1024 * 1024); /* maximum size */
1407      sscreen->attribute_ring = si_aligned_buffer_create(&sscreen->b,
1408                                                         PIPE_RESOURCE_FLAG_UNMAPPABLE |
1409                                                         SI_RESOURCE_FLAG_32BIT |
1410                                                         SI_RESOURCE_FLAG_DRIVER_INTERNAL |
1411                                                         SI_RESOURCE_FLAG_DISCARDABLE,
1412                                                         PIPE_USAGE_DEFAULT,
1413                                                         attr_ring_size, 2 * 1024 * 1024);
1414   }
1415
1416   /* Create the auxiliary context. This must be done last. */
1417   sscreen->aux_context = si_create_context(
1418      &sscreen->b,
1419      SI_CONTEXT_FLAG_AUX |
1420      (sscreen->options.aux_debug ? PIPE_CONTEXT_DEBUG : 0) |
1421      (sscreen->info.has_graphics ? 0 : PIPE_CONTEXT_COMPUTE_ONLY));
1422
1423   if (sscreen->options.aux_debug) {
1424      struct u_log_context *log = CALLOC_STRUCT(u_log_context);
1425      u_log_context_init(log);
1426      si_get_aux_context(sscreen)->b.set_log_context(sscreen->aux_context, log);
1427      si_put_aux_context_flush(sscreen);
1428   }
1429
1430   if (test_flags & DBG(TEST_IMAGE_COPY))
1431      si_test_image_copy_region(sscreen);
1432
1433   if (test_flags & (DBG(TEST_CB_RESOLVE) | DBG(TEST_COMPUTE_BLIT)))
1434      si_test_blit(sscreen, test_flags);
1435
1436   if (test_flags & DBG(TEST_DMA_PERF)) {
1437      si_test_dma_perf(sscreen);
1438   }
1439
1440   if (test_flags & (DBG(TEST_VMFAULT_CP) | DBG(TEST_VMFAULT_SHADER)))
1441      si_test_vmfault(sscreen, test_flags);
1442
1443   if (test_flags & DBG(TEST_GDS))
1444      si_test_gds((struct si_context *)sscreen->aux_context);
1445
1446   if (test_flags & DBG(TEST_GDS_MM)) {
1447      si_test_gds_memory_management((struct si_context *)sscreen->aux_context, 32 * 1024, 4,
1448                                    RADEON_DOMAIN_GDS);
1449   }
1450   if (test_flags & DBG(TEST_GDS_OA_MM)) {
1451      si_test_gds_memory_management((struct si_context *)sscreen->aux_context, 4, 1,
1452                                    RADEON_DOMAIN_OA);
1453   }
1454
1455   ac_print_shadowed_regs(&sscreen->info);
1456
1457   STATIC_ASSERT(sizeof(union si_vgt_stages_key) == 1);
1458   return &sscreen->b;
1459}
1460
1461struct pipe_screen *radeonsi_screen_create(int fd, const struct pipe_screen_config *config)
1462{
1463   drmVersionPtr version = drmGetVersion(fd);
1464   struct radeon_winsys *rw = NULL;
1465
1466   driParseConfigFiles(config->options, config->options_info, 0, "radeonsi",
1467                       NULL, NULL, NULL, 0, NULL, 0);
1468
1469   switch (version->version_major) {
1470   case 2:
1471      rw = radeon_drm_winsys_create(fd, config, radeonsi_screen_create_impl);
1472      break;
1473   case 3:
1474      rw = amdgpu_winsys_create(fd, config, radeonsi_screen_create_impl);
1475      break;
1476   }
1477
1478   drmFreeVersion(version);
1479   return rw ? rw->screen : NULL;
1480}
1481
1482struct si_context* si_get_aux_context(struct si_screen *sscreen)
1483{
1484   mtx_lock(&sscreen->aux_context_lock);
1485   return (struct si_context*)sscreen->aux_context;
1486}
1487
1488void si_put_aux_context_flush(struct si_screen *sscreen)
1489{
1490   struct pipe_context *c = &((struct si_context*)sscreen->aux_context)->b;
1491   c->flush(c, NULL, 0);
1492   mtx_unlock(&sscreen->aux_context_lock);
1493}
1494