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 "drm-uapi/drm_fourcc.h"
27#include "si_pipe.h"
28#include "si_query.h"
29#include "sid.h"
30#include "frontend/drm_driver.h"
31#include "util/format/u_format.h"
32#include "util/os_time.h"
33#include "util/u_log.h"
34#include "util/u_memory.h"
35#include "util/u_pack_color.h"
36#include "util/u_resource.h"
37#include "util/u_surface.h"
38#include "util/u_transfer.h"
39
40#include <errno.h>
41#include <inttypes.h>
42
43#include "amd/addrlib/inc/addrinterface.h"
44
45static enum radeon_surf_mode si_choose_tiling(struct si_screen *sscreen,
46                                              const struct pipe_resource *templ,
47                                              bool tc_compatible_htile);
48
49static bool si_texture_is_aux_plane(const struct pipe_resource *resource);
50
51/* Same as resource_copy_region, except that both upsampling and downsampling are allowed. */
52static void si_copy_region_with_blit(struct pipe_context *pipe, struct pipe_resource *dst,
53                                     unsigned dst_level, unsigned dst_sample, unsigned dstx, unsigned dsty,
54                                     unsigned dstz, struct pipe_resource *src, unsigned src_level,
55                                     const struct pipe_box *src_box)
56{
57   struct pipe_blit_info blit;
58
59   memset(&blit, 0, sizeof(blit));
60   blit.src.resource = src;
61   blit.src.format = src->format;
62   blit.src.level = src_level;
63   blit.src.box = *src_box;
64   blit.dst.resource = dst;
65   blit.dst.format = dst->format;
66   blit.dst.level = dst_level;
67   blit.dst.box.x = dstx;
68   blit.dst.box.y = dsty;
69   blit.dst.box.z = dstz;
70   blit.dst.box.width = src_box->width;
71   blit.dst.box.height = src_box->height;
72   blit.dst.box.depth = src_box->depth;
73   blit.mask = util_format_get_mask(dst->format);
74   blit.filter = PIPE_TEX_FILTER_NEAREST;
75   blit.dst_sample = dst_sample;
76
77   if (blit.mask) {
78      /* Only the gfx blit handles dst_sample. */
79      if (dst_sample)
80         si_gfx_blit(pipe, &blit);
81      else
82         pipe->blit(pipe, &blit);
83   }
84}
85
86/* Copy from a full GPU texture to a transfer's staging one. */
87static void si_copy_to_staging_texture(struct pipe_context *ctx, struct si_transfer *stransfer)
88{
89   struct pipe_transfer *transfer = (struct pipe_transfer *)stransfer;
90   struct pipe_resource *dst = &stransfer->staging->b.b;
91   struct pipe_resource *src = transfer->resource;
92   /* level means sample_index - 1 with MSAA. Used by texture uploads. */
93   unsigned src_level = src->nr_samples > 1 ? 0 : transfer->level;
94
95   if (src->nr_samples > 1 || ((struct si_texture *)src)->is_depth) {
96      si_copy_region_with_blit(ctx, dst, 0, 0, 0, 0, 0, src, src_level, &transfer->box);
97      return;
98   }
99
100   si_resource_copy_region(ctx, dst, 0, 0, 0, 0, src, src_level, &transfer->box);
101}
102
103/* Copy from a transfer's staging texture to a full GPU one. */
104static void si_copy_from_staging_texture(struct pipe_context *ctx, struct si_transfer *stransfer)
105{
106   struct pipe_transfer *transfer = (struct pipe_transfer *)stransfer;
107   struct pipe_resource *dst = transfer->resource;
108   struct pipe_resource *src = &stransfer->staging->b.b;
109   struct pipe_box sbox;
110
111   u_box_3d(0, 0, 0, transfer->box.width, transfer->box.height, transfer->box.depth, &sbox);
112
113   if (dst->nr_samples > 1 || ((struct si_texture *)dst)->is_depth) {
114      unsigned dst_level = dst->nr_samples > 1 ? 0 : transfer->level;
115      unsigned dst_sample = dst->nr_samples > 1 ? transfer->level : 0;
116
117      si_copy_region_with_blit(ctx, dst, dst_level, dst_sample, transfer->box.x, transfer->box.y,
118                               transfer->box.z, src, 0, &sbox);
119      return;
120   }
121
122   if (util_format_is_compressed(dst->format)) {
123      sbox.width = util_format_get_nblocksx(dst->format, sbox.width);
124      sbox.height = util_format_get_nblocksx(dst->format, sbox.height);
125   }
126
127   si_resource_copy_region(ctx, dst, transfer->level, transfer->box.x, transfer->box.y,
128                           transfer->box.z, src, 0, &sbox);
129}
130
131static unsigned si_texture_get_offset(struct si_screen *sscreen, struct si_texture *tex,
132                                      unsigned level, const struct pipe_box *box, unsigned *stride,
133                                      unsigned *layer_stride)
134{
135   if (sscreen->info.gfx_level >= GFX9) {
136      unsigned pitch;
137      if (tex->surface.is_linear) {
138         pitch = tex->surface.u.gfx9.pitch[level];
139      } else {
140         pitch = tex->surface.u.gfx9.surf_pitch;
141      }
142
143      *stride = pitch * tex->surface.bpe;
144      *layer_stride = tex->surface.u.gfx9.surf_slice_size;
145
146      if (!box)
147         return 0;
148
149      /* Each texture is an array of slices. Each slice is an array
150       * of mipmap levels. */
151      return tex->surface.u.gfx9.surf_offset + box->z * tex->surface.u.gfx9.surf_slice_size +
152             tex->surface.u.gfx9.offset[level] +
153             (box->y / tex->surface.blk_h * pitch + box->x / tex->surface.blk_w) *
154             tex->surface.bpe;
155   } else {
156      *stride = tex->surface.u.legacy.level[level].nblk_x * tex->surface.bpe;
157      assert((uint64_t)tex->surface.u.legacy.level[level].slice_size_dw * 4 <= UINT_MAX);
158      *layer_stride = (uint64_t)tex->surface.u.legacy.level[level].slice_size_dw * 4;
159
160      if (!box)
161         return (uint64_t)tex->surface.u.legacy.level[level].offset_256B * 256;
162
163      /* Each texture is an array of mipmap levels. Each level is
164       * an array of slices. */
165      return (uint64_t)tex->surface.u.legacy.level[level].offset_256B * 256 +
166             box->z * (uint64_t)tex->surface.u.legacy.level[level].slice_size_dw * 4 +
167             (box->y / tex->surface.blk_h * tex->surface.u.legacy.level[level].nblk_x +
168              box->x / tex->surface.blk_w) *
169                tex->surface.bpe;
170   }
171}
172
173static int si_init_surface(struct si_screen *sscreen, struct radeon_surf *surface,
174                           const struct pipe_resource *ptex, enum radeon_surf_mode array_mode,
175                           uint64_t modifier, bool is_imported, bool is_scanout,
176                           bool is_flushed_depth, bool tc_compatible_htile)
177{
178   const struct util_format_description *desc = util_format_description(ptex->format);
179   bool is_depth, is_stencil;
180   int r;
181   unsigned bpe;
182   uint64_t flags = 0;
183
184   is_depth = util_format_has_depth(desc);
185   is_stencil = util_format_has_stencil(desc);
186
187   if (!is_flushed_depth && ptex->format == PIPE_FORMAT_Z32_FLOAT_S8X24_UINT) {
188      bpe = 4; /* stencil is allocated separately */
189   } else {
190      bpe = util_format_get_blocksize(ptex->format);
191      assert(util_is_power_of_two_or_zero(bpe));
192   }
193
194   if (!is_flushed_depth && is_depth) {
195      flags |= RADEON_SURF_ZBUFFER;
196
197      if ((sscreen->debug_flags & DBG(NO_HYPERZ)) ||
198          (ptex->bind & PIPE_BIND_SHARED) || is_imported) {
199         flags |= RADEON_SURF_NO_HTILE;
200      } else if (tc_compatible_htile &&
201                 (sscreen->info.gfx_level >= GFX9 || array_mode == RADEON_SURF_MODE_2D)) {
202         /* TC-compatible HTILE only supports Z32_FLOAT.
203          * GFX9 also supports Z16_UNORM.
204          * On GFX8, promote Z16 to Z32. DB->CB copies will convert
205          * the format for transfers.
206          */
207         if (sscreen->info.gfx_level == GFX8)
208            bpe = 4;
209
210         flags |= RADEON_SURF_TC_COMPATIBLE_HTILE;
211      }
212
213      if (is_stencil)
214         flags |= RADEON_SURF_SBUFFER;
215   }
216
217   /* Disable DCC? (it can't be disabled if modifiers are used) */
218   if (sscreen->info.gfx_level >= GFX8 && modifier == DRM_FORMAT_MOD_INVALID && !is_imported) {
219      /* Global options that disable DCC. */
220      if (ptex->flags & SI_RESOURCE_FLAG_DISABLE_DCC)
221         flags |= RADEON_SURF_DISABLE_DCC;
222
223      if (ptex->nr_samples >= 2 && sscreen->debug_flags & DBG(NO_DCC_MSAA))
224         flags |= RADEON_SURF_DISABLE_DCC;
225
226      /* Shared textures must always set up DCC. If it's not present, it will be disabled by
227       * si_get_opaque_metadata later.
228       */
229      if (!is_imported &&
230          (sscreen->debug_flags & DBG(NO_DCC) ||
231           (ptex->bind & PIPE_BIND_SCANOUT && sscreen->debug_flags & DBG(NO_DISPLAY_DCC))))
232         flags |= RADEON_SURF_DISABLE_DCC;
233
234      /* R9G9B9E5 isn't supported for rendering by older generations. */
235      if (sscreen->info.gfx_level < GFX10_3 &&
236          ptex->format == PIPE_FORMAT_R9G9B9E5_FLOAT)
237         flags |= RADEON_SURF_DISABLE_DCC;
238
239      switch (sscreen->info.gfx_level) {
240      case GFX8:
241         /* Stoney: 128bpp MSAA textures randomly fail piglit tests with DCC. */
242         if (sscreen->info.family == CHIP_STONEY && bpe == 16 && ptex->nr_samples >= 2)
243            flags |= RADEON_SURF_DISABLE_DCC;
244
245         /* DCC clear for 4x and 8x MSAA array textures unimplemented. */
246         if (ptex->nr_storage_samples >= 4 && ptex->array_size > 1)
247            flags |= RADEON_SURF_DISABLE_DCC;
248         break;
249
250      case GFX9:
251         /* DCC MSAA fails this on Raven:
252          *    https://www.khronos.org/registry/webgl/sdk/tests/deqp/functional/gles3/fbomultisample.2_samples.html
253          * and this on Picasso:
254          *    https://www.khronos.org/registry/webgl/sdk/tests/deqp/functional/gles3/fbomultisample.4_samples.html
255          */
256         if (sscreen->info.family == CHIP_RAVEN && ptex->nr_storage_samples >= 2 && bpe < 4)
257            flags |= RADEON_SURF_DISABLE_DCC;
258         break;
259
260      case GFX10:
261      case GFX10_3:
262         if (ptex->nr_storage_samples >= 2 && !sscreen->options.dcc_msaa)
263            flags |= RADEON_SURF_DISABLE_DCC;
264         break;
265
266      case GFX11:
267         break;
268
269      default:
270         assert(0);
271      }
272   }
273
274   if (is_scanout) {
275      /* This should catch bugs in gallium users setting incorrect flags. */
276      assert(ptex->nr_samples <= 1 && ptex->array_size == 1 && ptex->depth0 == 1 &&
277             ptex->last_level == 0 && !(flags & RADEON_SURF_Z_OR_SBUFFER));
278
279      flags |= RADEON_SURF_SCANOUT;
280   }
281
282   if (ptex->bind & PIPE_BIND_SHARED)
283      flags |= RADEON_SURF_SHAREABLE;
284   if (is_imported)
285      flags |= RADEON_SURF_IMPORTED | RADEON_SURF_SHAREABLE;
286   if (sscreen->debug_flags & DBG(NO_FMASK))
287      flags |= RADEON_SURF_NO_FMASK;
288
289   if (sscreen->info.gfx_level == GFX9 && (ptex->flags & SI_RESOURCE_FLAG_FORCE_MICRO_TILE_MODE)) {
290      flags |= RADEON_SURF_FORCE_MICRO_TILE_MODE;
291      surface->micro_tile_mode = SI_RESOURCE_FLAG_MICRO_TILE_MODE_GET(ptex->flags);
292   }
293
294   if (ptex->flags & SI_RESOURCE_FLAG_FORCE_MSAA_TILING) {
295      /* GFX11 shouldn't get here because the flag is only used by the CB MSAA resolving
296       * that GFX11 doesn't have.
297       */
298      assert(sscreen->info.gfx_level <= GFX10_3);
299
300      flags |= RADEON_SURF_FORCE_SWIZZLE_MODE;
301
302      if (sscreen->info.gfx_level >= GFX10)
303         surface->u.gfx9.swizzle_mode = ADDR_SW_64KB_R_X;
304   }
305
306   if (ptex->flags & PIPE_RESOURCE_FLAG_SPARSE) {
307      flags |=
308         RADEON_SURF_PRT |
309         RADEON_SURF_NO_FMASK |
310         RADEON_SURF_NO_HTILE |
311         RADEON_SURF_DISABLE_DCC;
312   }
313
314   surface->modifier = modifier;
315
316   r = sscreen->ws->surface_init(sscreen->ws, ptex, flags, bpe, array_mode, surface);
317   if (r) {
318      return r;
319   }
320
321   return 0;
322}
323
324void si_eliminate_fast_color_clear(struct si_context *sctx, struct si_texture *tex,
325                                   bool *ctx_flushed)
326{
327   struct pipe_context *ctx = &sctx->b;
328
329   unsigned n = sctx->num_decompress_calls;
330   ctx->flush_resource(ctx, &tex->buffer.b.b);
331
332   /* Flush only if any fast clear elimination took place. */
333   bool flushed = false;
334   if (n != sctx->num_decompress_calls)
335   {
336      ctx->flush(ctx, NULL, 0);
337      flushed = true;
338   }
339   if (ctx_flushed)
340      *ctx_flushed = flushed;
341}
342
343void si_texture_discard_cmask(struct si_screen *sscreen, struct si_texture *tex)
344{
345   if (!tex->cmask_buffer)
346      return;
347
348   assert(tex->buffer.b.b.nr_samples <= 1);
349
350   /* Disable CMASK. */
351   tex->cmask_base_address_reg = tex->buffer.gpu_address >> 8;
352   tex->dirty_level_mask = 0;
353
354   tex->cb_color_info &= ~S_028C70_FAST_CLEAR(1);
355
356   if (tex->cmask_buffer != &tex->buffer)
357      si_resource_reference(&tex->cmask_buffer, NULL);
358
359   tex->cmask_buffer = NULL;
360
361   /* Notify all contexts about the change. */
362   p_atomic_inc(&sscreen->dirty_tex_counter);
363   p_atomic_inc(&sscreen->compressed_colortex_counter);
364}
365
366static bool si_can_disable_dcc(struct si_texture *tex)
367{
368   /* We can't disable DCC if it can be written by another process. */
369   return !tex->is_depth &&
370          tex->surface.meta_offset &&
371          (!tex->buffer.b.is_shared ||
372           !(tex->buffer.external_usage & PIPE_HANDLE_USAGE_FRAMEBUFFER_WRITE)) &&
373          !ac_modifier_has_dcc(tex->surface.modifier);
374}
375
376static bool si_texture_discard_dcc(struct si_screen *sscreen, struct si_texture *tex)
377{
378   if (!si_can_disable_dcc(tex))
379      return false;
380
381   /* Disable DCC. */
382   ac_surface_zero_dcc_fields(&tex->surface);
383
384   /* Notify all contexts about the change. */
385   p_atomic_inc(&sscreen->dirty_tex_counter);
386   return true;
387}
388
389/**
390 * Disable DCC for the texture. (first decompress, then discard metadata).
391 *
392 * There is unresolved multi-context synchronization issue between
393 * screen::aux_context and the current context. If applications do this with
394 * multiple contexts, it's already undefined behavior for them and we don't
395 * have to worry about that. The scenario is:
396 *
397 * If context 1 disables DCC and context 2 has queued commands that write
398 * to the texture via CB with DCC enabled, and the order of operations is
399 * as follows:
400 *   context 2 queues draw calls rendering to the texture, but doesn't flush
401 *   context 1 disables DCC and flushes
402 *   context 1 & 2 reset descriptors and FB state
403 *   context 2 flushes (new compressed tiles written by the draw calls)
404 *   context 1 & 2 read garbage, because DCC is disabled, yet there are
405 *   compressed tiled
406 *
407 * \param sctx  the current context if you have one, or sscreen->aux_context
408 *              if you don't.
409 */
410bool si_texture_disable_dcc(struct si_context *sctx, struct si_texture *tex)
411{
412   struct si_screen *sscreen = sctx->screen;
413
414   if (!sctx->has_graphics)
415      return si_texture_discard_dcc(sscreen, tex);
416
417   if (!si_can_disable_dcc(tex))
418      return false;
419
420   /* Decompress DCC. */
421   si_decompress_dcc(sctx, tex);
422   sctx->b.flush(&sctx->b, NULL, 0);
423
424   return si_texture_discard_dcc(sscreen, tex);
425}
426
427static void si_reallocate_texture_inplace(struct si_context *sctx, struct si_texture *tex,
428                                          unsigned new_bind_flag, bool invalidate_storage)
429{
430   struct pipe_screen *screen = sctx->b.screen;
431   struct si_texture *new_tex;
432   struct pipe_resource templ = tex->buffer.b.b;
433   unsigned i;
434
435   templ.bind |= new_bind_flag;
436
437   if (tex->buffer.b.is_shared || tex->num_planes > 1)
438      return;
439
440   if (new_bind_flag == PIPE_BIND_LINEAR) {
441      if (tex->surface.is_linear)
442         return;
443
444      /* This fails with MSAA, depth, and compressed textures. */
445      if (si_choose_tiling(sctx->screen, &templ, false) != RADEON_SURF_MODE_LINEAR_ALIGNED)
446         return;
447   }
448
449   new_tex = (struct si_texture *)screen->resource_create(screen, &templ);
450   if (!new_tex)
451      return;
452
453   /* Copy the pixels to the new texture. */
454   if (!invalidate_storage) {
455      for (i = 0; i <= templ.last_level; i++) {
456         struct pipe_box box;
457
458         u_box_3d(0, 0, 0, u_minify(templ.width0, i), u_minify(templ.height0, i),
459                  util_num_layers(&templ, i), &box);
460
461         si_resource_copy_region(&sctx->b, &new_tex->buffer.b.b,
462                                 i, 0, 0, 0, &tex->buffer.b.b, i, &box);
463      }
464   }
465
466   if (new_bind_flag == PIPE_BIND_LINEAR) {
467      si_texture_discard_cmask(sctx->screen, tex);
468      si_texture_discard_dcc(sctx->screen, tex);
469   }
470
471   /* Replace the structure fields of tex. */
472   tex->buffer.b.b.bind = templ.bind;
473   radeon_bo_reference(sctx->screen->ws, &tex->buffer.buf, new_tex->buffer.buf);
474   tex->buffer.gpu_address = new_tex->buffer.gpu_address;
475   tex->buffer.memory_usage_kb = new_tex->buffer.memory_usage_kb;
476   tex->buffer.bo_size = new_tex->buffer.bo_size;
477   tex->buffer.bo_alignment_log2 = new_tex->buffer.bo_alignment_log2;
478   tex->buffer.domains = new_tex->buffer.domains;
479   tex->buffer.flags = new_tex->buffer.flags;
480
481   tex->surface = new_tex->surface;
482   si_texture_reference(&tex->flushed_depth_texture, new_tex->flushed_depth_texture);
483
484   tex->surface.fmask_offset = new_tex->surface.fmask_offset;
485   tex->surface.cmask_offset = new_tex->surface.cmask_offset;
486   tex->cmask_base_address_reg = new_tex->cmask_base_address_reg;
487
488   if (tex->cmask_buffer == &tex->buffer)
489      tex->cmask_buffer = NULL;
490   else
491      si_resource_reference(&tex->cmask_buffer, NULL);
492
493   if (new_tex->cmask_buffer == &new_tex->buffer)
494      tex->cmask_buffer = &tex->buffer;
495   else
496      si_resource_reference(&tex->cmask_buffer, new_tex->cmask_buffer);
497
498   tex->surface.meta_offset = new_tex->surface.meta_offset;
499   tex->cb_color_info = new_tex->cb_color_info;
500   memcpy(tex->color_clear_value, new_tex->color_clear_value, sizeof(tex->color_clear_value));
501   tex->last_msaa_resolve_target_micro_mode = new_tex->last_msaa_resolve_target_micro_mode;
502
503   memcpy(tex->depth_clear_value, new_tex->depth_clear_value, sizeof(tex->depth_clear_value));
504   tex->dirty_level_mask = new_tex->dirty_level_mask;
505   tex->stencil_dirty_level_mask = new_tex->stencil_dirty_level_mask;
506   tex->db_render_format = new_tex->db_render_format;
507   memcpy(tex->stencil_clear_value, new_tex->stencil_clear_value, sizeof(tex->stencil_clear_value));
508   tex->tc_compatible_htile = new_tex->tc_compatible_htile;
509   tex->depth_cleared_level_mask_once = new_tex->depth_cleared_level_mask_once;
510   tex->stencil_cleared_level_mask_once = new_tex->stencil_cleared_level_mask_once;
511   tex->upgraded_depth = new_tex->upgraded_depth;
512   tex->db_compatible = new_tex->db_compatible;
513   tex->can_sample_z = new_tex->can_sample_z;
514   tex->can_sample_s = new_tex->can_sample_s;
515
516   tex->displayable_dcc_dirty = new_tex->displayable_dcc_dirty;
517
518   if (new_bind_flag == PIPE_BIND_LINEAR) {
519      assert(!tex->surface.meta_offset);
520      assert(!tex->cmask_buffer);
521      assert(!tex->surface.fmask_size);
522      assert(!tex->is_depth);
523   }
524
525   si_texture_reference(&new_tex, NULL);
526
527   p_atomic_inc(&sctx->screen->dirty_tex_counter);
528}
529
530static void si_set_tex_bo_metadata(struct si_screen *sscreen, struct si_texture *tex)
531{
532   struct pipe_resource *res = &tex->buffer.b.b;
533   struct radeon_bo_metadata md;
534
535   memset(&md, 0, sizeof(md));
536
537   assert(tex->surface.fmask_size == 0);
538
539   static const unsigned char swizzle[] = {PIPE_SWIZZLE_X, PIPE_SWIZZLE_Y, PIPE_SWIZZLE_Z,
540                                           PIPE_SWIZZLE_W};
541   bool is_array = util_texture_is_array(res->target);
542   uint32_t desc[8];
543
544   sscreen->make_texture_descriptor(sscreen, tex, true, res->target, res->format, swizzle, 0,
545                                    res->last_level, 0, is_array ? res->array_size - 1 : 0,
546                                    res->width0, res->height0, res->depth0, desc, NULL);
547   si_set_mutable_tex_desc_fields(sscreen, tex, &tex->surface.u.legacy.level[0], 0, 0,
548                                  tex->surface.blk_w, false, 0, desc);
549
550   ac_surface_get_umd_metadata(&sscreen->info, &tex->surface,
551                               tex->buffer.b.b.last_level + 1,
552                               desc, &md.size_metadata, md.metadata);
553   sscreen->ws->buffer_set_metadata(sscreen->ws, tex->buffer.buf, &md, &tex->surface);
554}
555
556static bool si_displayable_dcc_needs_explicit_flush(struct si_texture *tex)
557{
558   struct si_screen *sscreen = (struct si_screen *)tex->buffer.b.b.screen;
559
560   if (sscreen->info.gfx_level <= GFX8)
561      return false;
562
563   /* With modifiers and > 1 planes any applications will know that they
564    * cannot do frontbuffer rendering with the texture. */
565   if (ac_surface_get_nplanes(&tex->surface) > 1)
566      return false;
567
568   return tex->surface.is_displayable && tex->surface.meta_offset;
569}
570
571static bool si_resource_get_param(struct pipe_screen *screen, struct pipe_context *context,
572                                  struct pipe_resource *resource, unsigned plane, unsigned layer,
573                                  unsigned level,
574                                  enum pipe_resource_param param, unsigned handle_usage,
575                                  uint64_t *value)
576{
577   while (plane && resource->next && !si_texture_is_aux_plane(resource->next)) {
578      --plane;
579      resource = resource->next;
580   }
581
582   struct si_screen *sscreen = (struct si_screen *)screen;
583   struct si_texture *tex = (struct si_texture *)resource;
584   struct winsys_handle whandle;
585
586   switch (param) {
587   case PIPE_RESOURCE_PARAM_NPLANES:
588      if (resource->target == PIPE_BUFFER)
589         *value = 1;
590      else if (tex->num_planes > 1)
591         *value = tex->num_planes;
592      else
593         *value = ac_surface_get_nplanes(&tex->surface);
594      return true;
595
596   case PIPE_RESOURCE_PARAM_STRIDE:
597      if (resource->target == PIPE_BUFFER)
598         *value = 0;
599      else
600         *value = ac_surface_get_plane_stride(sscreen->info.gfx_level,
601                                              &tex->surface, plane, level);
602      return true;
603
604   case PIPE_RESOURCE_PARAM_OFFSET:
605      if (resource->target == PIPE_BUFFER) {
606         *value = 0;
607      } else {
608         uint64_t level_offset = tex->surface.is_linear ? tex->surface.u.gfx9.offset[level] : 0;
609         *value = ac_surface_get_plane_offset(sscreen->info.gfx_level,
610                                              &tex->surface, plane, layer)  + level_offset;
611      }
612      return true;
613
614   case PIPE_RESOURCE_PARAM_MODIFIER:
615      *value = tex->surface.modifier;
616      return true;
617
618   case PIPE_RESOURCE_PARAM_HANDLE_TYPE_SHARED:
619   case PIPE_RESOURCE_PARAM_HANDLE_TYPE_KMS:
620   case PIPE_RESOURCE_PARAM_HANDLE_TYPE_FD:
621      memset(&whandle, 0, sizeof(whandle));
622
623      if (param == PIPE_RESOURCE_PARAM_HANDLE_TYPE_SHARED)
624         whandle.type = WINSYS_HANDLE_TYPE_SHARED;
625      else if (param == PIPE_RESOURCE_PARAM_HANDLE_TYPE_KMS)
626         whandle.type = WINSYS_HANDLE_TYPE_KMS;
627      else if (param == PIPE_RESOURCE_PARAM_HANDLE_TYPE_FD)
628         whandle.type = WINSYS_HANDLE_TYPE_FD;
629
630      if (!screen->resource_get_handle(screen, context, resource, &whandle, handle_usage))
631         return false;
632
633      *value = whandle.handle;
634      return true;
635   case PIPE_RESOURCE_PARAM_LAYER_STRIDE:
636      break;
637   }
638   return false;
639}
640
641static void si_texture_get_info(struct pipe_screen *screen, struct pipe_resource *resource,
642                                unsigned *pstride, unsigned *poffset)
643{
644   uint64_t value;
645
646   if (pstride) {
647      si_resource_get_param(screen, NULL, resource, 0, 0, 0, PIPE_RESOURCE_PARAM_STRIDE, 0, &value);
648      *pstride = value;
649   }
650
651   if (poffset) {
652      si_resource_get_param(screen, NULL, resource, 0, 0, 0, PIPE_RESOURCE_PARAM_OFFSET, 0, &value);
653      *poffset = value;
654   }
655}
656
657static bool si_texture_get_handle(struct pipe_screen *screen, struct pipe_context *ctx,
658                                  struct pipe_resource *resource, struct winsys_handle *whandle,
659                                  unsigned usage)
660{
661   struct si_screen *sscreen = (struct si_screen *)screen;
662   struct si_context *sctx;
663   struct si_resource *res = si_resource(resource);
664   struct si_texture *tex = (struct si_texture *)resource;
665   bool update_metadata = false;
666   unsigned stride, offset, slice_size;
667   uint64_t modifier = DRM_FORMAT_MOD_INVALID;
668   bool flush = false;
669
670   ctx = threaded_context_unwrap_sync(ctx);
671   sctx = ctx ? (struct si_context *)ctx : si_get_aux_context(sscreen);
672
673   if (resource->target != PIPE_BUFFER) {
674      unsigned plane = whandle->plane;
675
676      /* Individual planes are chained pipe_resource instances. */
677      while (plane && resource->next && !si_texture_is_aux_plane(resource->next)) {
678         resource = resource->next;
679         --plane;
680      }
681
682      res = si_resource(resource);
683      tex = (struct si_texture *)resource;
684
685      /* This is not supported now, but it might be required for OpenCL
686       * interop in the future.
687       */
688      if (resource->nr_samples > 1 || tex->is_depth) {
689         if (!ctx)
690            si_put_aux_context_flush(sscreen);
691         return false;
692      }
693
694      whandle->size = tex->buffer.bo_size;
695
696      if (plane) {
697         if (!ctx)
698            si_put_aux_context_flush(sscreen);
699         whandle->offset = ac_surface_get_plane_offset(sscreen->info.gfx_level,
700                                                       &tex->surface, plane, 0);
701         whandle->stride = ac_surface_get_plane_stride(sscreen->info.gfx_level,
702                                                       &tex->surface, plane, 0);
703         whandle->modifier = tex->surface.modifier;
704         return sscreen->ws->buffer_get_handle(sscreen->ws, res->buf, whandle);
705      }
706
707      /* Move a suballocated texture into a non-suballocated allocation. */
708      if (sscreen->ws->buffer_is_suballocated(res->buf) || tex->surface.tile_swizzle ||
709          (tex->buffer.flags & RADEON_FLAG_NO_INTERPROCESS_SHARING &&
710           sscreen->info.has_local_buffers)) {
711         assert(!res->b.is_shared);
712         si_reallocate_texture_inplace(sctx, tex, PIPE_BIND_SHARED, false);
713         flush = true;
714         assert(res->b.b.bind & PIPE_BIND_SHARED);
715         assert(res->flags & RADEON_FLAG_NO_SUBALLOC);
716         assert(!(res->flags & RADEON_FLAG_NO_INTERPROCESS_SHARING));
717         assert(tex->surface.tile_swizzle == 0);
718      }
719
720      /* Since shader image stores don't support DCC on GFX8,
721       * disable it for external clients that want write
722       * access.
723       */
724      if (sscreen->debug_flags & DBG(NO_EXPORTED_DCC) ||
725          (usage & PIPE_HANDLE_USAGE_SHADER_WRITE && !tex->is_depth && tex->surface.meta_offset) ||
726          /* Displayable DCC requires an explicit flush. */
727          (!(usage & PIPE_HANDLE_USAGE_EXPLICIT_FLUSH) &&
728           si_displayable_dcc_needs_explicit_flush(tex))) {
729         if (si_texture_disable_dcc(sctx, tex)) {
730            update_metadata = true;
731            /* si_texture_disable_dcc flushes the context */
732            flush = false;
733         }
734      }
735
736      if (!(usage & PIPE_HANDLE_USAGE_EXPLICIT_FLUSH) &&
737          (tex->cmask_buffer || (!tex->is_depth && tex->surface.meta_offset))) {
738         /* Eliminate fast clear (both CMASK and DCC) */
739         bool flushed;
740         si_eliminate_fast_color_clear(sctx, tex, &flushed);
741         /* eliminate_fast_color_clear sometimes flushes the context */
742         flush = !flushed;
743
744         /* Disable CMASK if flush_resource isn't going
745          * to be called.
746          */
747         if (tex->cmask_buffer)
748            si_texture_discard_cmask(sscreen, tex);
749      }
750
751      /* Set metadata. */
752      if ((!res->b.is_shared || update_metadata) && whandle->offset == 0)
753         si_set_tex_bo_metadata(sscreen, tex);
754
755      if (sscreen->info.gfx_level >= GFX9) {
756         slice_size = tex->surface.u.gfx9.surf_slice_size;
757      } else {
758         slice_size = (uint64_t)tex->surface.u.legacy.level[0].slice_size_dw * 4;
759      }
760
761      modifier = tex->surface.modifier;
762   } else {
763      tc_buffer_disable_cpu_storage(&res->b.b);
764
765      /* Buffer exports are for the OpenCL interop. */
766      /* Move a suballocated buffer into a non-suballocated allocation. */
767      if (sscreen->ws->buffer_is_suballocated(res->buf) ||
768          /* A DMABUF export always fails if the BO is local. */
769          (tex->buffer.flags & RADEON_FLAG_NO_INTERPROCESS_SHARING &&
770           sscreen->info.has_local_buffers)) {
771         assert(!res->b.is_shared);
772
773         /* Allocate a new buffer with PIPE_BIND_SHARED. */
774         struct pipe_resource templ = res->b.b;
775         templ.bind |= PIPE_BIND_SHARED;
776
777         struct pipe_resource *newb = screen->resource_create(screen, &templ);
778         if (!newb) {
779            if (!ctx)
780               si_put_aux_context_flush(sscreen);
781            return false;
782         }
783
784         /* Copy the old buffer contents to the new one. */
785         struct pipe_box box;
786         u_box_1d(0, newb->width0, &box);
787         sctx->b.resource_copy_region(&sctx->b, newb, 0, 0, 0, 0, &res->b.b, 0, &box);
788         flush = true;
789         /* Move the new buffer storage to the old pipe_resource. */
790         si_replace_buffer_storage(&sctx->b, &res->b.b, newb, 0, 0, 0);
791         pipe_resource_reference(&newb, NULL);
792
793         assert(res->b.b.bind & PIPE_BIND_SHARED);
794         assert(res->flags & RADEON_FLAG_NO_SUBALLOC);
795      }
796
797      /* Buffers */
798      slice_size = 0;
799   }
800
801   si_texture_get_info(screen, resource, &stride, &offset);
802
803   if (res->b.is_shared) {
804      /* USAGE_EXPLICIT_FLUSH must be cleared if at least one user
805       * doesn't set it.
806       */
807      res->external_usage |= usage & ~PIPE_HANDLE_USAGE_EXPLICIT_FLUSH;
808      if (!(usage & PIPE_HANDLE_USAGE_EXPLICIT_FLUSH))
809         res->external_usage &= ~PIPE_HANDLE_USAGE_EXPLICIT_FLUSH;
810   } else {
811      res->b.is_shared = true;
812      res->external_usage = usage;
813   }
814
815   if (flush && ctx)
816      sctx->b.flush(&sctx->b, NULL, 0);
817   if (!ctx)
818      si_put_aux_context_flush(sscreen);
819
820   whandle->stride = stride;
821   whandle->offset = offset + slice_size * whandle->layer;
822   whandle->modifier = modifier;
823
824   return sscreen->ws->buffer_get_handle(sscreen->ws, res->buf, whandle);
825}
826
827void si_print_texture_info(struct si_screen *sscreen, struct si_texture *tex,
828                           struct u_log_context *log)
829{
830   int i;
831   FILE *f;
832   char *surf_info = NULL;
833   size_t surf_info_size;
834
835   /* Common parameters. */
836   u_log_printf(log,
837                "  Info: npix_x=%u, npix_y=%u, npix_z=%u, "
838                "array_size=%u, last_level=%u, nsamples=%u",
839                tex->buffer.b.b.width0, tex->buffer.b.b.height0,
840                tex->buffer.b.b.depth0, tex->buffer.b.b.array_size,
841                tex->buffer.b.b.last_level, tex->buffer.b.b.nr_samples);
842
843   if (tex->is_depth && tex->surface.meta_offset)
844      u_log_printf(log, ", tc_compatible_htile=%u", tex->tc_compatible_htile);
845
846   u_log_printf(log, ", %s\n",
847                util_format_short_name(tex->buffer.b.b.format));
848
849   f = open_memstream(&surf_info, &surf_info_size);
850   if (!f)
851      return;
852   ac_surface_print_info(f, &sscreen->info, &tex->surface);
853   fclose(f);
854   u_log_printf(log, "%s", surf_info);
855   free(surf_info);
856
857   if (sscreen->info.gfx_level >= GFX9) {
858      return;
859   }
860
861   if (!tex->is_depth && tex->surface.meta_offset) {
862      for (i = 0; i <= tex->buffer.b.b.last_level; i++)
863         u_log_printf(log,
864                      "    DCCLevel[%i]: enabled=%u, offset=%u, "
865                      "fast_clear_size=%u\n",
866                      i, i < tex->surface.num_meta_levels, tex->surface.u.legacy.color.dcc_level[i].dcc_offset,
867                      tex->surface.u.legacy.color.dcc_level[i].dcc_fast_clear_size);
868   }
869
870   for (i = 0; i <= tex->buffer.b.b.last_level; i++)
871      u_log_printf(log,
872                   "    Level[%i]: offset=%" PRIu64 ", slice_size=%" PRIu64 ", "
873                   "npix_x=%u, npix_y=%u, npix_z=%u, nblk_x=%u, nblk_y=%u, "
874                   "mode=%u, tiling_index = %u\n",
875                   i, (uint64_t)tex->surface.u.legacy.level[i].offset_256B * 256,
876                   (uint64_t)tex->surface.u.legacy.level[i].slice_size_dw * 4,
877                   u_minify(tex->buffer.b.b.width0, i), u_minify(tex->buffer.b.b.height0, i),
878                   u_minify(tex->buffer.b.b.depth0, i), tex->surface.u.legacy.level[i].nblk_x,
879                   tex->surface.u.legacy.level[i].nblk_y, tex->surface.u.legacy.level[i].mode,
880                   tex->surface.u.legacy.tiling_index[i]);
881
882   if (tex->surface.has_stencil) {
883      for (i = 0; i <= tex->buffer.b.b.last_level; i++) {
884         u_log_printf(log,
885                      "    StencilLevel[%i]: offset=%" PRIu64 ", "
886                      "slice_size=%" PRIu64 ", npix_x=%u, "
887                      "npix_y=%u, npix_z=%u, nblk_x=%u, nblk_y=%u, "
888                      "mode=%u, tiling_index = %u\n",
889                      i, (uint64_t)tex->surface.u.legacy.zs.stencil_level[i].offset_256B * 256,
890                      (uint64_t)tex->surface.u.legacy.zs.stencil_level[i].slice_size_dw * 4,
891                      u_minify(tex->buffer.b.b.width0, i), u_minify(tex->buffer.b.b.height0, i),
892                      u_minify(tex->buffer.b.b.depth0, i),
893                      tex->surface.u.legacy.zs.stencil_level[i].nblk_x,
894                      tex->surface.u.legacy.zs.stencil_level[i].nblk_y,
895                      tex->surface.u.legacy.zs.stencil_level[i].mode,
896                      tex->surface.u.legacy.zs.stencil_tiling_index[i]);
897      }
898   }
899}
900
901/**
902 * Common function for si_texture_create and si_texture_from_handle.
903 *
904 * \param screen       screen
905 * \param base         resource template
906 * \param surface      radeon_surf
907 * \param plane0       if a non-zero plane is being created, this is the first plane
908 * \param imported_buf from si_texture_from_handle
909 * \param offset       offset for non-zero planes or imported buffers
910 * \param alloc_size   the size to allocate if plane0 != NULL
911 * \param alignment    alignment for the allocation
912 */
913static struct si_texture *si_texture_create_object(struct pipe_screen *screen,
914                                                   const struct pipe_resource *base,
915                                                   const struct radeon_surf *surface,
916                                                   const struct si_texture *plane0,
917                                                   struct pb_buffer *imported_buf,
918                                                   uint64_t offset, unsigned pitch_in_bytes,
919                                                   uint64_t alloc_size, unsigned alignment)
920{
921   struct si_texture *tex;
922   struct si_resource *resource;
923   struct si_screen *sscreen = (struct si_screen *)screen;
924
925   if (!sscreen->info.has_3d_cube_border_color_mipmap &&
926       (base->last_level > 0 ||
927        base->target == PIPE_TEXTURE_3D ||
928        base->target == PIPE_TEXTURE_CUBE)) {
929      assert(0);
930      return NULL;
931   }
932
933   tex = CALLOC_STRUCT_CL(si_texture);
934   if (!tex)
935      goto error;
936
937   resource = &tex->buffer;
938   resource->b.b = *base;
939   pipe_reference_init(&resource->b.b.reference, 1);
940   resource->b.b.screen = screen;
941
942   /* don't include stencil-only formats which we don't support for rendering */
943   tex->is_depth = util_format_has_depth(util_format_description(tex->buffer.b.b.format));
944   tex->surface = *surface;
945
946   /* Use 1.0 as the default clear value to get optimal ZRANGE_PRECISION if we don't
947    * get a fast clear.
948    */
949   for (unsigned i = 0; i < ARRAY_SIZE(tex->depth_clear_value); i++)
950      tex->depth_clear_value[i] = 1.0;
951
952   /* On GFX8, HTILE uses different tiling depending on the TC_COMPATIBLE_HTILE
953    * setting, so we have to enable it if we enabled it at allocation.
954    *
955    * GFX9 and later use the same tiling for both, so TC-compatible HTILE can be
956    * enabled on demand.
957    */
958   tex->tc_compatible_htile = (sscreen->info.gfx_level == GFX8 &&
959                               tex->surface.flags & RADEON_SURF_TC_COMPATIBLE_HTILE) ||
960                              /* Mipmapping always starts TC-compatible. */
961                              (sscreen->info.gfx_level >= GFX8 &&
962                               tex->surface.flags & RADEON_SURF_TC_COMPATIBLE_HTILE &&
963                               tex->buffer.b.b.last_level > 0);
964
965   /* TC-compatible HTILE:
966    * - GFX8 only supports Z32_FLOAT.
967    * - GFX9 only supports Z32_FLOAT and Z16_UNORM. */
968   if (tex->surface.flags & RADEON_SURF_TC_COMPATIBLE_HTILE) {
969      if (sscreen->info.gfx_level >= GFX9 && base->format == PIPE_FORMAT_Z16_UNORM)
970         tex->db_render_format = base->format;
971      else {
972         tex->db_render_format = PIPE_FORMAT_Z32_FLOAT;
973         tex->upgraded_depth = base->format != PIPE_FORMAT_Z32_FLOAT &&
974                               base->format != PIPE_FORMAT_Z32_FLOAT_S8X24_UINT;
975      }
976   } else {
977      tex->db_render_format = base->format;
978   }
979
980   /* Applies to GCN. */
981   tex->last_msaa_resolve_target_micro_mode = tex->surface.micro_tile_mode;
982
983   if (!ac_surface_override_offset_stride(&sscreen->info, &tex->surface,
984                                     tex->buffer.b.b.last_level + 1,
985                                          offset, pitch_in_bytes / tex->surface.bpe))
986      goto error;
987
988   if (tex->is_depth) {
989      tex->htile_stencil_disabled = !tex->surface.has_stencil;
990
991      if (sscreen->info.gfx_level >= GFX9) {
992         tex->can_sample_z = true;
993         tex->can_sample_s = true;
994
995         /* Stencil texturing with HTILE doesn't work
996          * with mipmapping on Navi10-14. */
997         if (sscreen->info.gfx_level == GFX10 && base->last_level > 0)
998            tex->htile_stencil_disabled = true;
999      } else {
1000         tex->can_sample_z = !tex->surface.u.legacy.depth_adjusted;
1001         tex->can_sample_s = !tex->surface.u.legacy.stencil_adjusted;
1002
1003         /* GFX8 must keep stencil enabled because it can't use Z-only TC-compatible
1004          * HTILE because of a hw bug. This has only a small effect on performance
1005          * because we lose a little bit of Z precision in order to make space for
1006          * stencil in HTILE.
1007          */
1008         if (sscreen->info.gfx_level == GFX8 &&
1009             tex->surface.flags & RADEON_SURF_TC_COMPATIBLE_HTILE)
1010            tex->htile_stencil_disabled = false;
1011      }
1012
1013      tex->db_compatible = surface->flags & RADEON_SURF_ZBUFFER;
1014   } else {
1015      if (tex->surface.cmask_offset) {
1016         assert(sscreen->info.gfx_level < GFX11);
1017         tex->cb_color_info |= S_028C70_FAST_CLEAR(1);
1018         tex->cmask_buffer = &tex->buffer;
1019      }
1020   }
1021
1022   if (plane0) {
1023      /* The buffer is shared with the first plane. */
1024      resource->bo_size = plane0->buffer.bo_size;
1025      resource->bo_alignment_log2 = plane0->buffer.bo_alignment_log2;
1026      resource->flags = plane0->buffer.flags;
1027      resource->domains = plane0->buffer.domains;
1028      resource->memory_usage_kb = plane0->buffer.memory_usage_kb;
1029
1030      radeon_bo_reference(sscreen->ws, &resource->buf, plane0->buffer.buf);
1031      resource->gpu_address = plane0->buffer.gpu_address;
1032   } else if (!(surface->flags & RADEON_SURF_IMPORTED)) {
1033      if (base->flags & PIPE_RESOURCE_FLAG_SPARSE)
1034         resource->b.b.flags |= PIPE_RESOURCE_FLAG_UNMAPPABLE;
1035      if (base->bind & PIPE_BIND_PRIME_BLIT_DST)
1036         resource->b.b.flags |= SI_RESOURCE_FLAG_GL2_BYPASS;
1037
1038      /* Create the backing buffer. */
1039      si_init_resource_fields(sscreen, resource, alloc_size, alignment);
1040
1041      if (!si_alloc_resource(sscreen, resource))
1042         goto error;
1043   } else {
1044      resource->buf = imported_buf;
1045      resource->gpu_address = sscreen->ws->buffer_get_virtual_address(resource->buf);
1046      resource->bo_size = imported_buf->size;
1047      resource->bo_alignment_log2 = imported_buf->alignment_log2;
1048      resource->domains = sscreen->ws->buffer_get_initial_domain(resource->buf);
1049      resource->memory_usage_kb = MAX2(1, resource->bo_size / 1024);
1050      if (sscreen->ws->buffer_get_flags)
1051         resource->flags = sscreen->ws->buffer_get_flags(resource->buf);
1052   }
1053
1054   /* Prepare metadata clears.  */
1055   struct si_clear_info clears[4];
1056   unsigned num_clears = 0;
1057
1058   if (tex->cmask_buffer) {
1059      /* Initialize the cmask to 0xCC (= compressed state). */
1060      assert(num_clears < ARRAY_SIZE(clears));
1061      si_init_buffer_clear(&clears[num_clears++], &tex->cmask_buffer->b.b,
1062                           tex->surface.cmask_offset, tex->surface.cmask_size,
1063                           0xCCCCCCCC);
1064   }
1065   if (tex->is_depth && tex->surface.meta_offset) {
1066      uint32_t clear_value = 0;
1067
1068      if (sscreen->info.gfx_level >= GFX9 || tex->tc_compatible_htile)
1069         clear_value = 0x0000030F;
1070
1071      assert(num_clears < ARRAY_SIZE(clears));
1072      si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.meta_offset,
1073                           tex->surface.meta_size, clear_value);
1074   }
1075
1076   /* Initialize DCC only if the texture is not being imported. */
1077   if (!(surface->flags & RADEON_SURF_IMPORTED) && !tex->is_depth && tex->surface.meta_offset) {
1078      /* Clear DCC to black for all tiles with DCC enabled.
1079       *
1080       * This fixes corruption in 3DMark Slingshot Extreme, which
1081       * uses uninitialized textures, causing corruption.
1082       */
1083      if (tex->surface.num_meta_levels == tex->buffer.b.b.last_level + 1 &&
1084          tex->buffer.b.b.nr_samples <= 2) {
1085         /* Simple case - all tiles have DCC enabled. */
1086         assert(num_clears < ARRAY_SIZE(clears));
1087         si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.meta_offset,
1088                              tex->surface.meta_size, DCC_CLEAR_0000);
1089      } else if (sscreen->info.gfx_level >= GFX9) {
1090         /* Clear to uncompressed. Clearing this to black is complicated. */
1091         assert(num_clears < ARRAY_SIZE(clears));
1092         si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.meta_offset,
1093                              tex->surface.meta_size, DCC_UNCOMPRESSED);
1094      } else {
1095         /* GFX8: Initialize mipmap levels and multisamples separately. */
1096         if (tex->buffer.b.b.nr_samples >= 2) {
1097            /* Clearing this to black is complicated. */
1098            assert(num_clears < ARRAY_SIZE(clears));
1099            si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.meta_offset,
1100                                 tex->surface.meta_size, DCC_UNCOMPRESSED);
1101         } else {
1102            /* Clear the enabled mipmap levels to black. */
1103            unsigned size = 0;
1104
1105            for (unsigned i = 0; i < tex->surface.num_meta_levels; i++) {
1106               if (!tex->surface.u.legacy.color.dcc_level[i].dcc_fast_clear_size)
1107                  break;
1108
1109               size = tex->surface.u.legacy.color.dcc_level[i].dcc_offset +
1110                      tex->surface.u.legacy.color.dcc_level[i].dcc_fast_clear_size;
1111            }
1112
1113            /* Mipmap levels with DCC. */
1114            if (size) {
1115               assert(num_clears < ARRAY_SIZE(clears));
1116               si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.meta_offset, size,
1117                                    DCC_CLEAR_0000);
1118            }
1119            /* Mipmap levels without DCC. */
1120            if (size != tex->surface.meta_size) {
1121               assert(num_clears < ARRAY_SIZE(clears));
1122               si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.meta_offset + size,
1123                                    tex->surface.meta_size - size, DCC_UNCOMPRESSED);
1124            }
1125         }
1126      }
1127   }
1128
1129   /* Initialize displayable DCC that requires the retile blit. */
1130   if (tex->surface.display_dcc_offset && !(surface->flags & RADEON_SURF_IMPORTED)) {
1131      /* Uninitialized DCC can hang the display hw.
1132       * Clear to white to indicate that. */
1133      assert(num_clears < ARRAY_SIZE(clears));
1134      si_init_buffer_clear(&clears[num_clears++], &tex->buffer.b.b, tex->surface.display_dcc_offset,
1135                           tex->surface.u.gfx9.color.display_dcc_size,
1136                           sscreen->info.gfx_level >= GFX11 ? GFX11_DCC_CLEAR_1111_UNORM
1137                                                             : GFX8_DCC_CLEAR_1111);
1138   }
1139
1140   /* Execute the clears. */
1141   if (num_clears) {
1142      si_execute_clears(si_get_aux_context(sscreen), clears, num_clears, 0);
1143      si_put_aux_context_flush(sscreen);
1144   }
1145
1146   /* Initialize the CMASK base register value. */
1147   tex->cmask_base_address_reg = (tex->buffer.gpu_address + tex->surface.cmask_offset) >> 8;
1148
1149   if (sscreen->debug_flags & DBG(VM)) {
1150      fprintf(stderr,
1151              "VM start=0x%" PRIX64 "  end=0x%" PRIX64
1152              " | Texture %ix%ix%i, %i levels, %i samples, %s\n",
1153              tex->buffer.gpu_address, tex->buffer.gpu_address + tex->buffer.buf->size,
1154              base->width0, base->height0, util_num_layers(base, 0), base->last_level + 1,
1155              base->nr_samples ? base->nr_samples : 1, util_format_short_name(base->format));
1156   }
1157
1158   if (sscreen->debug_flags & DBG(TEX)) {
1159      puts("Texture:");
1160      struct u_log_context log;
1161      u_log_context_init(&log);
1162      si_print_texture_info(sscreen, tex, &log);
1163      u_log_new_page_print(&log, stdout);
1164      fflush(stdout);
1165      u_log_context_destroy(&log);
1166   }
1167
1168   return tex;
1169
1170error:
1171   FREE_CL(tex);
1172   return NULL;
1173}
1174
1175static enum radeon_surf_mode si_choose_tiling(struct si_screen *sscreen,
1176                                              const struct pipe_resource *templ,
1177                                              bool tc_compatible_htile)
1178{
1179   const struct util_format_description *desc = util_format_description(templ->format);
1180   bool force_tiling = templ->flags & SI_RESOURCE_FLAG_FORCE_MSAA_TILING;
1181   bool is_depth_stencil = util_format_is_depth_or_stencil(templ->format) &&
1182                           !(templ->flags & SI_RESOURCE_FLAG_FLUSHED_DEPTH);
1183
1184   /* MSAA resources must be 2D tiled. */
1185   if (templ->nr_samples > 1)
1186      return RADEON_SURF_MODE_2D;
1187
1188   /* Transfer resources should be linear. */
1189   if (templ->flags & SI_RESOURCE_FLAG_FORCE_LINEAR)
1190      return RADEON_SURF_MODE_LINEAR_ALIGNED;
1191
1192   /* Avoid Z/S decompress blits by forcing TC-compatible HTILE on GFX8,
1193    * which requires 2D tiling.
1194    */
1195   if (sscreen->info.gfx_level == GFX8 && tc_compatible_htile)
1196      return RADEON_SURF_MODE_2D;
1197
1198   /* Handle common candidates for the linear mode.
1199    * Compressed textures and DB surfaces must always be tiled.
1200    */
1201   if (!force_tiling && !is_depth_stencil && !util_format_is_compressed(templ->format)) {
1202      if (sscreen->debug_flags & DBG(NO_TILING) ||
1203          (templ->bind & PIPE_BIND_SCANOUT && sscreen->debug_flags & DBG(NO_DISPLAY_TILING)))
1204         return RADEON_SURF_MODE_LINEAR_ALIGNED;
1205
1206      /* Tiling doesn't work with the 422 (SUBSAMPLED) formats. */
1207      if (desc->layout == UTIL_FORMAT_LAYOUT_SUBSAMPLED)
1208         return RADEON_SURF_MODE_LINEAR_ALIGNED;
1209
1210      /* Cursors are linear on AMD GCN.
1211       * (XXX double-check, maybe also use RADEON_SURF_SCANOUT) */
1212      if (templ->bind & PIPE_BIND_CURSOR)
1213         return RADEON_SURF_MODE_LINEAR_ALIGNED;
1214
1215      if (templ->bind & PIPE_BIND_LINEAR)
1216         return RADEON_SURF_MODE_LINEAR_ALIGNED;
1217
1218      /* Textures with a very small height are recommended to be linear. */
1219      if (templ->target == PIPE_TEXTURE_1D || templ->target == PIPE_TEXTURE_1D_ARRAY ||
1220          /* Only very thin and long 2D textures should benefit from
1221           * linear_aligned. */
1222          templ->height0 <= 2)
1223         return RADEON_SURF_MODE_LINEAR_ALIGNED;
1224
1225      /* Textures likely to be mapped often. */
1226      if (templ->usage == PIPE_USAGE_STAGING || templ->usage == PIPE_USAGE_STREAM)
1227         return RADEON_SURF_MODE_LINEAR_ALIGNED;
1228   }
1229
1230   /* Make small textures 1D tiled. */
1231   if (templ->width0 <= 16 || templ->height0 <= 16 || (sscreen->debug_flags & DBG(NO_2D_TILING)))
1232      return RADEON_SURF_MODE_1D;
1233
1234   /* The allocator will switch to 1D if needed. */
1235   return RADEON_SURF_MODE_2D;
1236}
1237
1238static struct pipe_resource *
1239si_texture_create_with_modifier(struct pipe_screen *screen,
1240                                const struct pipe_resource *templ,
1241                                uint64_t modifier)
1242{
1243   struct si_screen *sscreen = (struct si_screen *)screen;
1244   bool is_zs = util_format_is_depth_or_stencil(templ->format);
1245
1246   if (templ->nr_samples >= 2) {
1247      /* This is hackish (overwriting the const pipe_resource template),
1248       * but should be harmless and gallium frontends can also see
1249       * the overriden number of samples in the created pipe_resource.
1250       */
1251      if (is_zs && sscreen->eqaa_force_z_samples) {
1252         ((struct pipe_resource *)templ)->nr_samples =
1253            ((struct pipe_resource *)templ)->nr_storage_samples = sscreen->eqaa_force_z_samples;
1254      } else if (!is_zs && sscreen->eqaa_force_color_samples) {
1255         ((struct pipe_resource *)templ)->nr_samples = sscreen->eqaa_force_coverage_samples;
1256         ((struct pipe_resource *)templ)->nr_storage_samples = sscreen->eqaa_force_color_samples;
1257      }
1258   }
1259
1260   bool is_flushed_depth = templ->flags & SI_RESOURCE_FLAG_FLUSHED_DEPTH ||
1261                           templ->flags & SI_RESOURCE_FLAG_FORCE_LINEAR;
1262   bool tc_compatible_htile =
1263      sscreen->info.gfx_level >= GFX8 &&
1264      /* There are issues with TC-compatible HTILE on Tonga (and
1265       * Iceland is the same design), and documented bug workarounds
1266       * don't help. For example, this fails:
1267       *   piglit/bin/tex-miplevel-selection 'texture()' 2DShadow -auto
1268       */
1269      sscreen->info.family != CHIP_TONGA && sscreen->info.family != CHIP_ICELAND &&
1270      (templ->flags & PIPE_RESOURCE_FLAG_TEXTURING_MORE_LIKELY) &&
1271      !(sscreen->debug_flags & DBG(NO_HYPERZ)) && !is_flushed_depth &&
1272      is_zs;
1273   enum radeon_surf_mode tile_mode = si_choose_tiling(sscreen, templ, tc_compatible_htile);
1274
1275   /* This allocates textures with multiple planes like NV12 in 1 buffer. */
1276   enum
1277   {
1278      SI_TEXTURE_MAX_PLANES = 3
1279   };
1280   struct radeon_surf surface[SI_TEXTURE_MAX_PLANES] = {};
1281   struct pipe_resource plane_templ[SI_TEXTURE_MAX_PLANES];
1282   uint64_t plane_offset[SI_TEXTURE_MAX_PLANES] = {};
1283   uint64_t total_size = 0;
1284   unsigned max_alignment = 0;
1285   unsigned num_planes = util_format_get_num_planes(templ->format);
1286   assert(num_planes <= SI_TEXTURE_MAX_PLANES);
1287
1288   /* Compute texture or plane layouts and offsets. */
1289   for (unsigned i = 0; i < num_planes; i++) {
1290      plane_templ[i] = *templ;
1291      plane_templ[i].format = util_format_get_plane_format(templ->format, i);
1292      plane_templ[i].width0 = util_format_get_plane_width(templ->format, i, templ->width0);
1293      plane_templ[i].height0 = util_format_get_plane_height(templ->format, i, templ->height0);
1294
1295      /* Multi-plane allocations need PIPE_BIND_SHARED, because we can't
1296       * reallocate the storage to add PIPE_BIND_SHARED, because it's
1297       * shared by 3 pipe_resources.
1298       */
1299      if (num_planes > 1)
1300         plane_templ[i].bind |= PIPE_BIND_SHARED;
1301
1302      if (si_init_surface(sscreen, &surface[i], &plane_templ[i], tile_mode, modifier,
1303                          false, plane_templ[i].bind & PIPE_BIND_SCANOUT,
1304                          is_flushed_depth, tc_compatible_htile))
1305         return NULL;
1306
1307      plane_templ[i].nr_sparse_levels = surface[i].first_mip_tail_level;
1308
1309      plane_offset[i] = align64(total_size, 1 << surface[i].surf_alignment_log2);
1310      total_size = plane_offset[i] + surface[i].total_size;
1311      max_alignment = MAX2(max_alignment, 1 << surface[i].surf_alignment_log2);
1312   }
1313
1314   struct si_texture *plane0 = NULL, *last_plane = NULL;
1315
1316   for (unsigned i = 0; i < num_planes; i++) {
1317      struct si_texture *tex =
1318         si_texture_create_object(screen, &plane_templ[i], &surface[i], plane0, NULL,
1319                                  plane_offset[i], 0, total_size, max_alignment);
1320      if (!tex) {
1321         si_texture_reference(&plane0, NULL);
1322         return NULL;
1323      }
1324
1325      tex->plane_index = i;
1326      tex->num_planes = num_planes;
1327
1328      if (!plane0) {
1329         plane0 = last_plane = tex;
1330      } else {
1331         last_plane->buffer.b.b.next = &tex->buffer.b.b;
1332         last_plane = tex;
1333      }
1334   }
1335
1336   return (struct pipe_resource *)plane0;
1337}
1338
1339struct pipe_resource *si_texture_create(struct pipe_screen *screen,
1340                                        const struct pipe_resource *templ)
1341{
1342   return si_texture_create_with_modifier(screen, templ, DRM_FORMAT_MOD_INVALID);
1343}
1344
1345bool si_texture_commit(struct si_context *ctx, struct si_resource *res, unsigned level,
1346                       struct pipe_box *box, bool commit)
1347{
1348   struct si_texture *tex = (struct si_texture *)res;
1349   struct radeon_surf *surface = &tex->surface;
1350   enum pipe_format format = res->b.b.format;
1351   unsigned blks = util_format_get_blocksize(format);
1352   unsigned samples = MAX2(1, res->b.b.nr_samples);
1353
1354   assert(ctx->gfx_level >= GFX9);
1355
1356   unsigned row_pitch = surface->u.gfx9.prt_level_pitch[level] *
1357      surface->prt_tile_height * surface->prt_tile_depth * blks * samples;
1358   unsigned depth_pitch = surface->u.gfx9.surf_slice_size * surface->prt_tile_depth;
1359
1360   unsigned x = box->x / surface->prt_tile_width;
1361   unsigned y = box->y / surface->prt_tile_height;
1362   unsigned z = box->z / surface->prt_tile_depth;
1363
1364   unsigned w = DIV_ROUND_UP(box->width, surface->prt_tile_width);
1365   unsigned h = DIV_ROUND_UP(box->height, surface->prt_tile_height);
1366   unsigned d = DIV_ROUND_UP(box->depth, surface->prt_tile_depth);
1367
1368   /* Align to tile block base, for levels in mip tail whose offset is inside
1369    * a tile block.
1370    */
1371   unsigned level_base = ROUND_DOWN_TO(surface->u.gfx9.prt_level_offset[level],
1372                                       RADEON_SPARSE_PAGE_SIZE);
1373   unsigned commit_base = level_base +
1374      x * RADEON_SPARSE_PAGE_SIZE + y * row_pitch + z * depth_pitch;
1375
1376   unsigned size = w * RADEON_SPARSE_PAGE_SIZE;
1377   for (int i = 0; i < d; i++) {
1378      unsigned base = commit_base + i * depth_pitch;
1379      for (int j = 0; j < h; j++) {
1380         unsigned offset = base + j * row_pitch;
1381         if (!ctx->ws->buffer_commit(ctx->ws, res->buf, offset, size, commit))
1382            return false;
1383      }
1384   }
1385
1386   return true;
1387}
1388
1389static void si_query_dmabuf_modifiers(struct pipe_screen *screen,
1390                                      enum pipe_format format,
1391                                      int max,
1392                                      uint64_t *modifiers,
1393                                      unsigned int *external_only,
1394                                      int *count)
1395{
1396   struct si_screen *sscreen = (struct si_screen *)screen;
1397
1398   unsigned ac_mod_count = max;
1399   ac_get_supported_modifiers(&sscreen->info, &(struct ac_modifier_options) {
1400         .dcc = !(sscreen->debug_flags & DBG(NO_DCC)),
1401         /* Do not support DCC with retiling yet. This needs explicit
1402          * resource flushes, but the app has no way to promise doing
1403          * flushes with modifiers. */
1404         .dcc_retile = !(sscreen->debug_flags & DBG(NO_DCC)),
1405      }, format, &ac_mod_count,  max ? modifiers : NULL);
1406   if (max && external_only) {
1407      for (unsigned i = 0; i < ac_mod_count; ++i)
1408         external_only[i] = util_format_is_yuv(format);
1409   }
1410   *count = ac_mod_count;
1411}
1412
1413static bool
1414si_is_dmabuf_modifier_supported(struct pipe_screen *screen,
1415                               uint64_t modifier,
1416                               enum pipe_format format,
1417                               bool *external_only)
1418{
1419   int allowed_mod_count;
1420   si_query_dmabuf_modifiers(screen, format, 0, NULL, NULL, &allowed_mod_count);
1421
1422   uint64_t *allowed_modifiers = (uint64_t *)calloc(allowed_mod_count, sizeof(uint64_t));
1423   if (!allowed_modifiers)
1424      return false;
1425
1426   unsigned *external_array = NULL;
1427   if (external_only) {
1428      external_array = (unsigned *)calloc(allowed_mod_count, sizeof(unsigned));
1429      if (!external_array) {
1430         free(allowed_modifiers);
1431         return false;
1432      }
1433   }
1434
1435   si_query_dmabuf_modifiers(screen, format, allowed_mod_count, allowed_modifiers,
1436                            external_array, &allowed_mod_count);
1437
1438   bool supported = false;
1439   for (int i = 0; i < allowed_mod_count && !supported; ++i) {
1440      if (allowed_modifiers[i] != modifier)
1441         continue;
1442
1443      supported = true;
1444      if (external_only)
1445         *external_only = external_array[i];
1446   }
1447
1448   free(allowed_modifiers);
1449   free(external_array);
1450   return supported;
1451}
1452
1453static unsigned
1454si_get_dmabuf_modifier_planes(struct pipe_screen *pscreen, uint64_t modifier,
1455                             enum pipe_format format)
1456{
1457   unsigned planes = util_format_get_num_planes(format);
1458
1459   if (IS_AMD_FMT_MOD(modifier) && planes == 1) {
1460      if (AMD_FMT_MOD_GET(DCC_RETILE, modifier))
1461         return 3;
1462      else if (AMD_FMT_MOD_GET(DCC, modifier))
1463         return 2;
1464      else
1465         return 1;
1466   }
1467
1468   return planes;
1469}
1470
1471static bool
1472si_modifier_supports_resource(struct pipe_screen *screen,
1473                              uint64_t modifier,
1474                              const struct pipe_resource *templ)
1475{
1476   struct si_screen *sscreen = (struct si_screen *)screen;
1477   uint32_t max_width, max_height;
1478
1479   ac_modifier_max_extent(&sscreen->info, modifier, &max_width, &max_height);
1480   return templ->width0 <= max_width && templ->height0 <= max_height;
1481}
1482
1483static struct pipe_resource *
1484si_texture_create_with_modifiers(struct pipe_screen *screen,
1485                                 const struct pipe_resource *templ,
1486                                 const uint64_t *modifiers,
1487                                 int modifier_count)
1488{
1489   /* Buffers with modifiers make zero sense. */
1490   assert(templ->target != PIPE_BUFFER);
1491
1492   /* Select modifier. */
1493   int allowed_mod_count;
1494   si_query_dmabuf_modifiers(screen, templ->format, 0, NULL, NULL, &allowed_mod_count);
1495
1496   uint64_t *allowed_modifiers = (uint64_t *)calloc(allowed_mod_count, sizeof(uint64_t));
1497   if (!allowed_modifiers) {
1498      return NULL;
1499   }
1500
1501   /* This does not take external_only into account. We assume it is the same for all modifiers. */
1502   si_query_dmabuf_modifiers(screen, templ->format, allowed_mod_count, allowed_modifiers, NULL, &allowed_mod_count);
1503
1504   uint64_t modifier = DRM_FORMAT_MOD_INVALID;
1505
1506   /* Try to find the first allowed modifier that is in the application provided
1507    * list. We assume that the allowed modifiers are ordered in descending
1508    * preference in the list provided by si_query_dmabuf_modifiers. */
1509   for (int i = 0; i < allowed_mod_count; ++i) {
1510      bool found = false;
1511      for (int j = 0; j < modifier_count && !found; ++j)
1512         if (modifiers[j] == allowed_modifiers[i] && si_modifier_supports_resource(screen, modifiers[j], templ))
1513            found = true;
1514
1515      if (found) {
1516         modifier = allowed_modifiers[i];
1517         break;
1518      }
1519   }
1520
1521   free(allowed_modifiers);
1522
1523   if (modifier == DRM_FORMAT_MOD_INVALID) {
1524      return NULL;
1525   }
1526   return si_texture_create_with_modifier(screen, templ, modifier);
1527}
1528
1529static bool si_texture_is_aux_plane(const struct pipe_resource *resource)
1530{
1531   return resource->flags & SI_RESOURCE_AUX_PLANE;
1532}
1533
1534static struct pipe_resource *si_texture_from_winsys_buffer(struct si_screen *sscreen,
1535                                                           const struct pipe_resource *templ,
1536                                                           struct pb_buffer *buf, unsigned stride,
1537                                                           uint64_t offset, uint64_t modifier,
1538                                                           unsigned usage, bool dedicated)
1539{
1540   struct radeon_surf surface = {};
1541   struct radeon_bo_metadata metadata = {};
1542   struct si_texture *tex;
1543   int r;
1544
1545   /* Ignore metadata for non-zero planes. */
1546   if (offset != 0)
1547      dedicated = false;
1548
1549   if (dedicated) {
1550      sscreen->ws->buffer_get_metadata(sscreen->ws, buf, &metadata, &surface);
1551   } else {
1552      /**
1553       * The bo metadata is unset for un-dedicated images. So we fall
1554       * back to linear. See answer to question 5 of the
1555       * VK_KHX_external_memory spec for some details.
1556       *
1557       * It is possible that this case isn't going to work if the
1558       * surface pitch isn't correctly aligned by default.
1559       *
1560       * In order to support it correctly we require multi-image
1561       * metadata to be synchronized between radv and radeonsi. The
1562       * semantics of associating multiple image metadata to a memory
1563       * object on the vulkan export side are not concretely defined
1564       * either.
1565       *
1566       * All the use cases we are aware of at the moment for memory
1567       * objects use dedicated allocations. So lets keep the initial
1568       * implementation simple.
1569       *
1570       * A possible alternative is to attempt to reconstruct the
1571       * tiling information when the TexParameter TEXTURE_TILING_EXT
1572       * is set.
1573       */
1574      metadata.mode = RADEON_SURF_MODE_LINEAR_ALIGNED;
1575   }
1576
1577   r = si_init_surface(sscreen, &surface, templ, metadata.mode, modifier, true,
1578                       surface.flags & RADEON_SURF_SCANOUT, false, false);
1579   if (r)
1580      return NULL;
1581
1582   tex = si_texture_create_object(&sscreen->b, templ, &surface, NULL, buf,
1583                                  offset, stride, 0, 0);
1584   if (!tex)
1585      return NULL;
1586
1587   tex->buffer.b.is_shared = true;
1588   tex->buffer.external_usage = usage;
1589   tex->num_planes = 1;
1590   if (tex->buffer.flags & RADEON_FLAG_ENCRYPTED)
1591      tex->buffer.b.b.bind |= PIPE_BIND_PROTECTED;
1592
1593   /* Account for multiple planes with lowered yuv import. */
1594   struct pipe_resource *next_plane = tex->buffer.b.b.next;
1595   while (next_plane && !si_texture_is_aux_plane(next_plane)) {
1596      struct si_texture *next_tex = (struct si_texture *)next_plane;
1597      ++next_tex->num_planes;
1598      ++tex->num_planes;
1599      next_plane = next_plane->next;
1600   }
1601
1602   unsigned nplanes = ac_surface_get_nplanes(&tex->surface);
1603   unsigned plane = 1;
1604   while (next_plane) {
1605      struct si_auxiliary_texture *ptex = (struct si_auxiliary_texture *)next_plane;
1606      if (plane >= nplanes || ptex->buffer != tex->buffer.buf ||
1607          ptex->offset != ac_surface_get_plane_offset(sscreen->info.gfx_level,
1608                                                      &tex->surface, plane, 0) ||
1609          ptex->stride != ac_surface_get_plane_stride(sscreen->info.gfx_level,
1610                                                      &tex->surface, plane, 0)) {
1611         si_texture_reference(&tex, NULL);
1612         return NULL;
1613      }
1614      ++plane;
1615      next_plane = next_plane->next;
1616   }
1617
1618   if (plane != nplanes && tex->num_planes == 1) {
1619      si_texture_reference(&tex, NULL);
1620      return NULL;
1621   }
1622
1623   if (!ac_surface_set_umd_metadata(&sscreen->info, &tex->surface,
1624                                    tex->buffer.b.b.nr_storage_samples,
1625                                    tex->buffer.b.b.last_level + 1,
1626                                    metadata.size_metadata,
1627                                    metadata.metadata)) {
1628      si_texture_reference(&tex, NULL);
1629      return NULL;
1630   }
1631
1632   if (ac_surface_get_plane_offset(sscreen->info.gfx_level, &tex->surface, 0, 0) +
1633        tex->surface.total_size > buf->size ||
1634       buf->alignment_log2 < tex->surface.alignment_log2) {
1635      si_texture_reference(&tex, NULL);
1636      return NULL;
1637   }
1638
1639   /* Displayable DCC requires an explicit flush. */
1640   if (dedicated && offset == 0 && !(usage & PIPE_HANDLE_USAGE_EXPLICIT_FLUSH) &&
1641       si_displayable_dcc_needs_explicit_flush(tex)) {
1642      /* TODO: do we need to decompress DCC? */
1643      if (si_texture_discard_dcc(sscreen, tex)) {
1644         /* Update BO metadata after disabling DCC. */
1645         si_set_tex_bo_metadata(sscreen, tex);
1646      }
1647   }
1648
1649   assert(tex->surface.tile_swizzle == 0);
1650   return &tex->buffer.b.b;
1651}
1652
1653static struct pipe_resource *si_texture_from_handle(struct pipe_screen *screen,
1654                                                    const struct pipe_resource *templ,
1655                                                    struct winsys_handle *whandle, unsigned usage)
1656{
1657   struct si_screen *sscreen = (struct si_screen *)screen;
1658   struct pb_buffer *buf = NULL;
1659
1660   /* Support only 2D textures without mipmaps */
1661   if ((templ->target != PIPE_TEXTURE_2D && templ->target != PIPE_TEXTURE_RECT &&
1662        templ->target != PIPE_TEXTURE_2D_ARRAY) ||
1663       templ->last_level != 0)
1664      return NULL;
1665
1666   buf = sscreen->ws->buffer_from_handle(sscreen->ws, whandle,
1667                                         sscreen->info.max_alignment,
1668                                         templ->bind & PIPE_BIND_PRIME_BLIT_DST);
1669   if (!buf)
1670      return NULL;
1671
1672   if (whandle->plane >= util_format_get_num_planes(whandle->format)) {
1673      struct si_auxiliary_texture *tex = CALLOC_STRUCT_CL(si_auxiliary_texture);
1674      if (!tex)
1675         return NULL;
1676      tex->b.b = *templ;
1677      tex->b.b.flags |= SI_RESOURCE_AUX_PLANE;
1678      tex->stride = whandle->stride;
1679      tex->offset = whandle->offset;
1680      tex->buffer = buf;
1681      pipe_reference_init(&tex->b.b.reference, 1);
1682      tex->b.b.screen = screen;
1683
1684      return &tex->b.b;
1685   }
1686
1687   return si_texture_from_winsys_buffer(sscreen, templ, buf, whandle->stride, whandle->offset,
1688                                        whandle->modifier, usage, true);
1689}
1690
1691bool si_init_flushed_depth_texture(struct pipe_context *ctx, struct pipe_resource *texture)
1692{
1693   struct si_texture *tex = (struct si_texture *)texture;
1694   struct pipe_resource resource;
1695   enum pipe_format pipe_format = texture->format;
1696
1697   assert(!tex->flushed_depth_texture);
1698
1699   if (!tex->can_sample_z && tex->can_sample_s) {
1700      switch (pipe_format) {
1701      case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
1702         /* Save memory by not allocating the S plane. */
1703         pipe_format = PIPE_FORMAT_Z32_FLOAT;
1704         break;
1705      case PIPE_FORMAT_Z24_UNORM_S8_UINT:
1706      case PIPE_FORMAT_S8_UINT_Z24_UNORM:
1707         /* Save memory bandwidth by not copying the
1708          * stencil part during flush.
1709          *
1710          * This potentially increases memory bandwidth
1711          * if an application uses both Z and S texturing
1712          * simultaneously (a flushed Z24S8 texture
1713          * would be stored compactly), but how often
1714          * does that really happen?
1715          */
1716         pipe_format = PIPE_FORMAT_Z24X8_UNORM;
1717         break;
1718      default:;
1719      }
1720   } else if (!tex->can_sample_s && tex->can_sample_z) {
1721      assert(util_format_has_stencil(util_format_description(pipe_format)));
1722
1723      /* DB->CB copies to an 8bpp surface don't work. */
1724      pipe_format = PIPE_FORMAT_X24S8_UINT;
1725   }
1726
1727   memset(&resource, 0, sizeof(resource));
1728   resource.target = texture->target;
1729   resource.format = pipe_format;
1730   resource.width0 = texture->width0;
1731   resource.height0 = texture->height0;
1732   resource.depth0 = texture->depth0;
1733   resource.array_size = texture->array_size;
1734   resource.last_level = texture->last_level;
1735   resource.nr_samples = texture->nr_samples;
1736   resource.nr_storage_samples = texture->nr_storage_samples;
1737   resource.usage = PIPE_USAGE_DEFAULT;
1738   resource.bind = texture->bind & ~PIPE_BIND_DEPTH_STENCIL;
1739   resource.flags = texture->flags | SI_RESOURCE_FLAG_FLUSHED_DEPTH;
1740
1741   tex->flushed_depth_texture =
1742      (struct si_texture *)ctx->screen->resource_create(ctx->screen, &resource);
1743   if (!tex->flushed_depth_texture) {
1744      PRINT_ERR("failed to create temporary texture to hold flushed depth\n");
1745      return false;
1746   }
1747   return true;
1748}
1749
1750/**
1751 * Initialize the pipe_resource descriptor to be of the same size as the box,
1752 * which is supposed to hold a subregion of the texture "orig" at the given
1753 * mipmap level.
1754 */
1755static void si_init_temp_resource_from_box(struct pipe_resource *res, struct pipe_resource *orig,
1756                                           const struct pipe_box *box, unsigned level,
1757                                           unsigned usage, unsigned flags)
1758{
1759   memset(res, 0, sizeof(*res));
1760   res->format = orig->format;
1761   res->width0 = box->width;
1762   res->height0 = box->height;
1763   res->depth0 = 1;
1764   res->array_size = 1;
1765   res->usage = usage;
1766   res->flags = flags;
1767
1768   if (flags & SI_RESOURCE_FLAG_FORCE_LINEAR && util_format_is_compressed(orig->format)) {
1769      /* Transfer resources are allocated with linear tiling, which is
1770       * not supported for compressed formats.
1771       */
1772      unsigned blocksize = util_format_get_blocksize(orig->format);
1773
1774      if (blocksize == 8) {
1775         res->format = PIPE_FORMAT_R16G16B16A16_UINT;
1776      } else {
1777         assert(blocksize == 16);
1778         res->format = PIPE_FORMAT_R32G32B32A32_UINT;
1779      }
1780
1781      res->width0 = util_format_get_nblocksx(orig->format, box->width);
1782      res->height0 = util_format_get_nblocksy(orig->format, box->height);
1783   }
1784
1785   /* We must set the correct texture target and dimensions for a 3D box. */
1786   if (box->depth > 1 && util_max_layer(orig, level) > 0) {
1787      res->target = PIPE_TEXTURE_2D_ARRAY;
1788      res->array_size = box->depth;
1789   } else {
1790      res->target = PIPE_TEXTURE_2D;
1791   }
1792}
1793
1794static bool si_can_invalidate_texture(struct si_screen *sscreen, struct si_texture *tex,
1795                                      unsigned transfer_usage, const struct pipe_box *box)
1796{
1797   return !tex->buffer.b.is_shared && !(tex->surface.flags & RADEON_SURF_IMPORTED) &&
1798          !(transfer_usage & PIPE_MAP_READ) && tex->buffer.b.b.last_level == 0 &&
1799          util_texrange_covers_whole_level(&tex->buffer.b.b, 0, box->x, box->y, box->z, box->width,
1800                                           box->height, box->depth);
1801}
1802
1803static void si_texture_invalidate_storage(struct si_context *sctx, struct si_texture *tex)
1804{
1805   struct si_screen *sscreen = sctx->screen;
1806
1807   /* There is no point in discarding depth and tiled buffers. */
1808   assert(!tex->is_depth);
1809   assert(tex->surface.is_linear);
1810
1811   /* Reallocate the buffer in the same pipe_resource. */
1812   si_alloc_resource(sscreen, &tex->buffer);
1813
1814   /* Initialize the CMASK base address (needed even without CMASK). */
1815   tex->cmask_base_address_reg = (tex->buffer.gpu_address + tex->surface.cmask_offset) >> 8;
1816
1817   p_atomic_inc(&sscreen->dirty_tex_counter);
1818
1819   sctx->num_alloc_tex_transfer_bytes += tex->surface.total_size;
1820}
1821
1822static void *si_texture_transfer_map(struct pipe_context *ctx, struct pipe_resource *texture,
1823                                     unsigned level, unsigned usage, const struct pipe_box *box,
1824                                     struct pipe_transfer **ptransfer)
1825{
1826   struct si_context *sctx = (struct si_context *)ctx;
1827   struct si_texture *tex = (struct si_texture *)texture;
1828   struct si_transfer *trans;
1829   struct si_resource *buf;
1830   unsigned offset = 0;
1831   char *map;
1832   bool use_staging_texture = tex->buffer.flags & RADEON_FLAG_ENCRYPTED;
1833   unsigned real_level = texture->nr_samples > 1 ? 0 : level;
1834
1835   assert(texture->target != PIPE_BUFFER);
1836   assert(!(texture->flags & SI_RESOURCE_FLAG_FORCE_LINEAR));
1837   assert(box->width && box->height && box->depth);
1838
1839   if (tex->buffer.b.b.flags & SI_RESOURCE_AUX_PLANE)
1840      return NULL;
1841
1842   if ((tex->buffer.flags & RADEON_FLAG_ENCRYPTED) && usage & PIPE_MAP_READ)
1843      return NULL;
1844
1845   if (tex->is_depth || tex->buffer.flags & RADEON_FLAG_SPARSE) {
1846      /* Depth and sparse textures use staging unconditionally. */
1847      use_staging_texture = true;
1848   } else {
1849      /* Degrade the tile mode if we get too many transfers on APUs.
1850       * On dGPUs, the staging texture is always faster.
1851       * Only count uploads that are at least 4x4 pixels large.
1852       */
1853      if (!sctx->screen->info.has_dedicated_vram && real_level == 0 && box->width >= 4 &&
1854          box->height >= 4 && p_atomic_inc_return(&tex->num_level0_transfers) == 10) {
1855         bool can_invalidate = si_can_invalidate_texture(sctx->screen, tex, usage, box);
1856
1857         si_reallocate_texture_inplace(sctx, tex, PIPE_BIND_LINEAR, can_invalidate);
1858      }
1859
1860      /* Tiled textures need to be converted into a linear texture for CPU
1861       * access. The staging texture is always linear and is placed in GART.
1862       *
1863       * dGPU use a staging texture for VRAM, so that we don't map it and
1864       * don't relocate it to GTT.
1865       *
1866       * Reading from VRAM or GTT WC is slow, always use the staging
1867       * texture in this case.
1868       *
1869       * Use the staging texture for uploads if the underlying BO
1870       * is busy.
1871       */
1872      if (!tex->surface.is_linear || (tex->buffer.flags & RADEON_FLAG_ENCRYPTED) ||
1873          (tex->buffer.domains & RADEON_DOMAIN_VRAM && sctx->screen->info.has_dedicated_vram &&
1874           !sctx->screen->info.smart_access_memory))
1875         use_staging_texture = true;
1876      else if (usage & PIPE_MAP_READ)
1877         use_staging_texture =
1878            tex->buffer.domains & RADEON_DOMAIN_VRAM || tex->buffer.flags & RADEON_FLAG_GTT_WC;
1879      /* Write & linear only: */
1880      else if (si_cs_is_buffer_referenced(sctx, tex->buffer.buf, RADEON_USAGE_READWRITE) ||
1881               !sctx->ws->buffer_wait(sctx->ws, tex->buffer.buf, 0, RADEON_USAGE_READWRITE)) {
1882         /* It's busy. */
1883         if (si_can_invalidate_texture(sctx->screen, tex, usage, box))
1884            si_texture_invalidate_storage(sctx, tex);
1885         else
1886            use_staging_texture = true;
1887      }
1888   }
1889
1890   trans = CALLOC_STRUCT(si_transfer);
1891   if (!trans)
1892      return NULL;
1893   pipe_resource_reference(&trans->b.b.resource, texture);
1894   trans->b.b.level = level;
1895   trans->b.b.usage = usage;
1896   trans->b.b.box = *box;
1897
1898   if (use_staging_texture) {
1899      struct pipe_resource resource;
1900      struct si_texture *staging;
1901      unsigned bo_usage = usage & PIPE_MAP_READ ? PIPE_USAGE_STAGING : PIPE_USAGE_STREAM;
1902      unsigned bo_flags = SI_RESOURCE_FLAG_FORCE_LINEAR | SI_RESOURCE_FLAG_DRIVER_INTERNAL;
1903
1904      si_init_temp_resource_from_box(&resource, texture, box, real_level, bo_usage,
1905                                     bo_flags);
1906
1907      /* Since depth-stencil textures don't support linear tiling,
1908       * blit from ZS to color and vice versa. u_blitter will do
1909       * the packing for these formats.
1910       */
1911      if (tex->is_depth)
1912         resource.format = util_blitter_get_color_format_for_zs(resource.format);
1913
1914      /* Create the temporary texture. */
1915      staging = (struct si_texture *)ctx->screen->resource_create(ctx->screen, &resource);
1916      if (!staging) {
1917         PRINT_ERR("failed to create temporary texture to hold untiled copy\n");
1918         goto fail_trans;
1919      }
1920      trans->staging = &staging->buffer;
1921
1922      /* Just get the strides. */
1923      si_texture_get_offset(sctx->screen, staging, 0, NULL, &trans->b.b.stride,
1924                            &trans->b.b.layer_stride);
1925
1926      if (usage & PIPE_MAP_READ)
1927         si_copy_to_staging_texture(ctx, trans);
1928      else
1929         usage |= PIPE_MAP_UNSYNCHRONIZED;
1930
1931      buf = trans->staging;
1932   } else {
1933      /* the resource is mapped directly */
1934      offset = si_texture_get_offset(sctx->screen, tex, real_level, box, &trans->b.b.stride,
1935                                     &trans->b.b.layer_stride);
1936      buf = &tex->buffer;
1937   }
1938
1939   /* Always unmap texture CPU mappings on 32-bit architectures, so that
1940    * we don't run out of the CPU address space.
1941    */
1942   if (sizeof(void *) == 4)
1943      usage |= RADEON_MAP_TEMPORARY;
1944
1945   if (!(map = si_buffer_map(sctx, buf, usage)))
1946      goto fail_trans;
1947
1948   *ptransfer = &trans->b.b;
1949   return map + offset;
1950
1951fail_trans:
1952   si_resource_reference(&trans->staging, NULL);
1953   pipe_resource_reference(&trans->b.b.resource, NULL);
1954   FREE(trans);
1955   return NULL;
1956}
1957
1958static void si_texture_transfer_unmap(struct pipe_context *ctx, struct pipe_transfer *transfer)
1959{
1960   struct si_context *sctx = (struct si_context *)ctx;
1961   struct si_transfer *stransfer = (struct si_transfer *)transfer;
1962   struct pipe_resource *texture = transfer->resource;
1963   struct si_texture *tex = (struct si_texture *)texture;
1964
1965   /* Always unmap texture CPU mappings on 32-bit architectures, so that
1966    * we don't run out of the CPU address space.
1967    */
1968   if (sizeof(void *) == 4) {
1969      struct si_resource *buf = stransfer->staging ? stransfer->staging : &tex->buffer;
1970
1971      sctx->ws->buffer_unmap(sctx->ws, buf->buf);
1972   }
1973
1974   if ((transfer->usage & PIPE_MAP_WRITE) && stransfer->staging)
1975      si_copy_from_staging_texture(ctx, stransfer);
1976
1977   if (stransfer->staging) {
1978      sctx->num_alloc_tex_transfer_bytes += stransfer->staging->buf->size;
1979      si_resource_reference(&stransfer->staging, NULL);
1980   }
1981
1982   /* Heuristic for {upload, draw, upload, draw, ..}:
1983    *
1984    * Flush the gfx IB if we've allocated too much texture storage.
1985    *
1986    * The idea is that we don't want to build IBs that use too much
1987    * memory and put pressure on the kernel memory manager and we also
1988    * want to make temporary and invalidated buffers go idle ASAP to
1989    * decrease the total memory usage or make them reusable. The memory
1990    * usage will be slightly higher than given here because of the buffer
1991    * cache in the winsys.
1992    *
1993    * The result is that the kernel memory manager is never a bottleneck.
1994    */
1995   if (sctx->num_alloc_tex_transfer_bytes > (uint64_t)sctx->screen->info.gart_size_kb * 1024 / 4) {
1996      si_flush_gfx_cs(sctx, RADEON_FLUSH_ASYNC_START_NEXT_GFX_IB_NOW, NULL);
1997      sctx->num_alloc_tex_transfer_bytes = 0;
1998   }
1999
2000   pipe_resource_reference(&transfer->resource, NULL);
2001   FREE(transfer);
2002}
2003
2004/* Return if it's allowed to reinterpret one format as another with DCC enabled.
2005 */
2006bool vi_dcc_formats_compatible(struct si_screen *sscreen, enum pipe_format format1,
2007                               enum pipe_format format2)
2008{
2009   const struct util_format_description *desc1, *desc2;
2010
2011   /* All formats are compatible on GFX11. */
2012   if (sscreen->info.gfx_level >= GFX11)
2013      return true;
2014
2015   /* No format change - exit early. */
2016   if (format1 == format2)
2017      return true;
2018
2019   format1 = si_simplify_cb_format(format1);
2020   format2 = si_simplify_cb_format(format2);
2021
2022   /* Check again after format adjustments. */
2023   if (format1 == format2)
2024      return true;
2025
2026   desc1 = util_format_description(format1);
2027   desc2 = util_format_description(format2);
2028
2029   if (desc1->layout != UTIL_FORMAT_LAYOUT_PLAIN || desc2->layout != UTIL_FORMAT_LAYOUT_PLAIN)
2030      return false;
2031
2032   /* Float and non-float are totally incompatible. */
2033   if ((desc1->channel[0].type == UTIL_FORMAT_TYPE_FLOAT) !=
2034       (desc2->channel[0].type == UTIL_FORMAT_TYPE_FLOAT))
2035      return false;
2036
2037   /* Channel sizes must match across DCC formats.
2038    * Comparing just the first 2 channels should be enough.
2039    */
2040   if (desc1->channel[0].size != desc2->channel[0].size ||
2041       (desc1->nr_channels >= 2 && desc1->channel[1].size != desc2->channel[1].size))
2042      return false;
2043
2044   /* Everything below is not needed if the driver never uses the DCC
2045    * clear code with the value of 1.
2046    */
2047
2048   /* If the clear values are all 1 or all 0, this constraint can be
2049    * ignored. */
2050   if (vi_alpha_is_on_msb(sscreen, format1) != vi_alpha_is_on_msb(sscreen, format2))
2051      return false;
2052
2053   /* Channel types must match if the clear value of 1 is used.
2054    * The type categories are only float, signed, unsigned.
2055    * NORM and INT are always compatible.
2056    */
2057   if (desc1->channel[0].type != desc2->channel[0].type ||
2058       (desc1->nr_channels >= 2 && desc1->channel[1].type != desc2->channel[1].type))
2059      return false;
2060
2061   return true;
2062}
2063
2064bool vi_dcc_formats_are_incompatible(struct pipe_resource *tex, unsigned level,
2065                                     enum pipe_format view_format)
2066{
2067   struct si_texture *stex = (struct si_texture *)tex;
2068
2069   return vi_dcc_enabled(stex, level) &&
2070          !vi_dcc_formats_compatible((struct si_screen *)tex->screen, tex->format, view_format);
2071}
2072
2073/* This can't be merged with the above function, because
2074 * vi_dcc_formats_compatible should be called only when DCC is enabled. */
2075void vi_disable_dcc_if_incompatible_format(struct si_context *sctx, struct pipe_resource *tex,
2076                                           unsigned level, enum pipe_format view_format)
2077{
2078   struct si_texture *stex = (struct si_texture *)tex;
2079
2080   if (vi_dcc_formats_are_incompatible(tex, level, view_format))
2081      if (!si_texture_disable_dcc(sctx, stex))
2082         si_decompress_dcc(sctx, stex);
2083}
2084
2085static struct pipe_surface *si_create_surface(struct pipe_context *pipe, struct pipe_resource *tex,
2086                                              const struct pipe_surface *templ)
2087{
2088   unsigned level = templ->u.tex.level;
2089   unsigned width = u_minify(tex->width0, level);
2090   unsigned height = u_minify(tex->height0, level);
2091   unsigned width0 = tex->width0;
2092   unsigned height0 = tex->height0;
2093
2094   if (tex->target != PIPE_BUFFER && templ->format != tex->format) {
2095      const struct util_format_description *tex_desc = util_format_description(tex->format);
2096      const struct util_format_description *templ_desc = util_format_description(templ->format);
2097
2098      assert(tex_desc->block.bits == templ_desc->block.bits);
2099
2100      /* Adjust size of surface if and only if the block width or
2101       * height is changed. */
2102      if (tex_desc->block.width != templ_desc->block.width ||
2103          tex_desc->block.height != templ_desc->block.height) {
2104         unsigned nblks_x = util_format_get_nblocksx(tex->format, width);
2105         unsigned nblks_y = util_format_get_nblocksy(tex->format, height);
2106
2107         width = nblks_x * templ_desc->block.width;
2108         height = nblks_y * templ_desc->block.height;
2109
2110         width0 = util_format_get_nblocksx(tex->format, width0);
2111         height0 = util_format_get_nblocksy(tex->format, height0);
2112      }
2113   }
2114
2115   struct si_surface *surface = CALLOC_STRUCT(si_surface);
2116
2117   if (!surface)
2118      return NULL;
2119
2120   assert(templ->u.tex.first_layer <= util_max_layer(tex, templ->u.tex.level));
2121   assert(templ->u.tex.last_layer <= util_max_layer(tex, templ->u.tex.level));
2122
2123   pipe_reference_init(&surface->base.reference, 1);
2124   pipe_resource_reference(&surface->base.texture, tex);
2125   surface->base.context = pipe;
2126   surface->base.format = templ->format;
2127   surface->base.width = width;
2128   surface->base.height = height;
2129   surface->base.u = templ->u;
2130
2131   surface->width0 = width0;
2132   surface->height0 = height0;
2133
2134   surface->dcc_incompatible =
2135      tex->target != PIPE_BUFFER &&
2136      vi_dcc_formats_are_incompatible(tex, templ->u.tex.level, templ->format);
2137   return &surface->base;
2138}
2139
2140static void si_surface_destroy(struct pipe_context *pipe, struct pipe_surface *surface)
2141{
2142   pipe_resource_reference(&surface->texture, NULL);
2143   FREE(surface);
2144}
2145
2146unsigned si_translate_colorswap(enum amd_gfx_level gfx_level, enum pipe_format format,
2147                                bool do_endian_swap)
2148{
2149   const struct util_format_description *desc = util_format_description(format);
2150
2151#define HAS_SWIZZLE(chan, swz) (desc->swizzle[chan] == PIPE_SWIZZLE_##swz)
2152
2153   if (format == PIPE_FORMAT_R11G11B10_FLOAT) /* isn't plain */
2154      return V_028C70_SWAP_STD;
2155
2156   if (gfx_level >= GFX10_3 &&
2157       format == PIPE_FORMAT_R9G9B9E5_FLOAT) /* isn't plain */
2158      return V_028C70_SWAP_STD;
2159
2160   if (desc->layout != UTIL_FORMAT_LAYOUT_PLAIN)
2161      return ~0U;
2162
2163   switch (desc->nr_channels) {
2164   case 1:
2165      if (HAS_SWIZZLE(0, X))
2166         return V_028C70_SWAP_STD; /* X___ */
2167      else if (HAS_SWIZZLE(3, X))
2168         return V_028C70_SWAP_ALT_REV; /* ___X */
2169      break;
2170   case 2:
2171      if ((HAS_SWIZZLE(0, X) && HAS_SWIZZLE(1, Y)) || (HAS_SWIZZLE(0, X) && HAS_SWIZZLE(1, NONE)) ||
2172          (HAS_SWIZZLE(0, NONE) && HAS_SWIZZLE(1, Y)))
2173         return V_028C70_SWAP_STD; /* XY__ */
2174      else if ((HAS_SWIZZLE(0, Y) && HAS_SWIZZLE(1, X)) ||
2175               (HAS_SWIZZLE(0, Y) && HAS_SWIZZLE(1, NONE)) ||
2176               (HAS_SWIZZLE(0, NONE) && HAS_SWIZZLE(1, X)))
2177         /* YX__ */
2178         return (do_endian_swap ? V_028C70_SWAP_STD : V_028C70_SWAP_STD_REV);
2179      else if (HAS_SWIZZLE(0, X) && HAS_SWIZZLE(3, Y))
2180         return V_028C70_SWAP_ALT; /* X__Y */
2181      else if (HAS_SWIZZLE(0, Y) && HAS_SWIZZLE(3, X))
2182         return V_028C70_SWAP_ALT_REV; /* Y__X */
2183      break;
2184   case 3:
2185      if (HAS_SWIZZLE(0, X))
2186         return (do_endian_swap ? V_028C70_SWAP_STD_REV : V_028C70_SWAP_STD);
2187      else if (HAS_SWIZZLE(0, Z))
2188         return V_028C70_SWAP_STD_REV; /* ZYX */
2189      break;
2190   case 4:
2191      /* check the middle channels, the 1st and 4th channel can be NONE */
2192      if (HAS_SWIZZLE(1, Y) && HAS_SWIZZLE(2, Z)) {
2193         return V_028C70_SWAP_STD; /* XYZW */
2194      } else if (HAS_SWIZZLE(1, Z) && HAS_SWIZZLE(2, Y)) {
2195         return V_028C70_SWAP_STD_REV; /* WZYX */
2196      } else if (HAS_SWIZZLE(1, Y) && HAS_SWIZZLE(2, X)) {
2197         return V_028C70_SWAP_ALT; /* ZYXW */
2198      } else if (HAS_SWIZZLE(1, Z) && HAS_SWIZZLE(2, W)) {
2199         /* YZWX */
2200         if (desc->is_array)
2201            return V_028C70_SWAP_ALT_REV;
2202         else
2203            return (do_endian_swap ? V_028C70_SWAP_ALT : V_028C70_SWAP_ALT_REV);
2204      }
2205      break;
2206   }
2207   return ~0U;
2208}
2209
2210static struct pipe_memory_object *
2211si_memobj_from_handle(struct pipe_screen *screen, struct winsys_handle *whandle, bool dedicated)
2212{
2213   struct si_screen *sscreen = (struct si_screen *)screen;
2214   struct si_memory_object *memobj = CALLOC_STRUCT(si_memory_object);
2215   struct pb_buffer *buf = NULL;
2216
2217   if (!memobj)
2218      return NULL;
2219
2220   buf = sscreen->ws->buffer_from_handle(sscreen->ws, whandle, sscreen->info.max_alignment, false);
2221   if (!buf) {
2222      free(memobj);
2223      return NULL;
2224   }
2225
2226   memobj->b.dedicated = dedicated;
2227   memobj->buf = buf;
2228   memobj->stride = whandle->stride;
2229
2230   return (struct pipe_memory_object *)memobj;
2231}
2232
2233static void si_memobj_destroy(struct pipe_screen *screen, struct pipe_memory_object *_memobj)
2234{
2235   struct si_memory_object *memobj = (struct si_memory_object *)_memobj;
2236
2237   radeon_bo_reference(((struct si_screen*)screen)->ws, &memobj->buf, NULL);
2238   free(memobj);
2239}
2240
2241static struct pipe_resource *si_resource_from_memobj(struct pipe_screen *screen,
2242                                                    const struct pipe_resource *templ,
2243                                                    struct pipe_memory_object *_memobj,
2244                                                    uint64_t offset)
2245{
2246   struct si_screen *sscreen = (struct si_screen *)screen;
2247   struct si_memory_object *memobj = (struct si_memory_object *)_memobj;
2248   struct pipe_resource *res;
2249
2250   if (templ->target == PIPE_BUFFER)
2251      res = si_buffer_from_winsys_buffer(screen, templ, memobj->buf, offset);
2252   else
2253      res = si_texture_from_winsys_buffer(sscreen, templ, memobj->buf,
2254                                          memobj->stride,
2255                                          offset, DRM_FORMAT_MOD_INVALID,
2256                                          PIPE_HANDLE_USAGE_FRAMEBUFFER_WRITE | PIPE_HANDLE_USAGE_SHADER_WRITE,
2257                                          memobj->b.dedicated);
2258
2259   if (!res)
2260      return NULL;
2261
2262   /* si_texture_from_winsys_buffer doesn't increment refcount of
2263    * memobj->buf, so increment it here.
2264    */
2265   struct pb_buffer *buf = NULL;
2266   radeon_bo_reference(sscreen->ws, &buf, memobj->buf);
2267   return res;
2268}
2269
2270static bool si_check_resource_capability(struct pipe_screen *screen, struct pipe_resource *resource,
2271                                         unsigned bind)
2272{
2273   struct si_texture *tex = (struct si_texture *)resource;
2274
2275   /* Buffers only support the linear flag. */
2276   if (resource->target == PIPE_BUFFER)
2277      return (bind & ~PIPE_BIND_LINEAR) == 0;
2278
2279   if (bind & PIPE_BIND_LINEAR && !tex->surface.is_linear)
2280      return false;
2281
2282   if (bind & PIPE_BIND_SCANOUT && !tex->surface.is_displayable)
2283      return false;
2284
2285   /* TODO: PIPE_BIND_CURSOR - do we care? */
2286   return true;
2287}
2288
2289static int si_get_sparse_texture_virtual_page_size(struct pipe_screen *screen,
2290                                                   enum pipe_texture_target target,
2291                                                   bool multi_sample,
2292                                                   enum pipe_format format,
2293                                                   unsigned offset, unsigned size,
2294                                                   int *x, int *y, int *z)
2295{
2296   struct si_screen *sscreen = (struct si_screen *)screen;
2297
2298   /* Only support one type of page size. */
2299   if (offset != 0)
2300      return 0;
2301
2302   static const int page_size_2d[][3] = {
2303      { 256, 256, 1 }, /* 8bpp   */
2304      { 256, 128, 1 }, /* 16bpp  */
2305      { 128, 128, 1 }, /* 32bpp  */
2306      { 128, 64,  1 }, /* 64bpp  */
2307      { 64,  64,  1 }, /* 128bpp */
2308   };
2309   static const int page_size_3d[][3] = {
2310      { 64,  32,  32 }, /* 8bpp   */
2311      { 32,  32,  32 }, /* 16bpp  */
2312      { 32,  32,  16 }, /* 32bpp  */
2313      { 32,  16,  16 }, /* 64bpp  */
2314      { 16,  16,  16 }, /* 128bpp */
2315   };
2316
2317   const int (*page_sizes)[3];
2318
2319   /* Supported targets. */
2320   switch (target) {
2321   case PIPE_TEXTURE_2D:
2322   case PIPE_TEXTURE_CUBE:
2323   case PIPE_TEXTURE_RECT:
2324   case PIPE_TEXTURE_2D_ARRAY:
2325   case PIPE_TEXTURE_CUBE_ARRAY:
2326      page_sizes = page_size_2d;
2327      break;
2328   case PIPE_TEXTURE_3D:
2329      page_sizes = page_size_3d;
2330      break;
2331   default:
2332      return 0;
2333   }
2334
2335   /* ARB_sparse_texture2 need to query supported virtual page x/y/z without
2336    * knowing the actual sample count. So we need to return a fixed virtual page
2337    * x/y/z for all sample count which means the virtual page size can not be fixed
2338    * to 64KB.
2339    *
2340    * Only enabled for GFX9. GFX10+ removed MS texture support. By specification
2341    * ARB_sparse_texture2 need MS texture support, but we relax it by just return
2342    * no page size for GFX10+ to keep shader query capbility.
2343    */
2344   if (multi_sample && sscreen->info.gfx_level != GFX9)
2345      return 0;
2346
2347   /* Unsupport formats. */
2348   /* TODO: support these formats. */
2349   if (util_format_is_depth_or_stencil(format) ||
2350       util_format_get_num_planes(format) > 1 ||
2351       util_format_is_compressed(format))
2352      return 0;
2353
2354   int blk_size = util_format_get_blocksize(format);
2355   /* We don't support any non-power-of-two bpp formats, so
2356    * pipe_screen->is_format_supported() should already filter out these formats.
2357    */
2358   assert(util_is_power_of_two_nonzero(blk_size));
2359
2360   if (size) {
2361      unsigned index = util_logbase2(blk_size);
2362      if (x) *x = page_sizes[index][0];
2363      if (y) *y = page_sizes[index][1];
2364      if (z) *z = page_sizes[index][2];
2365   }
2366
2367   return 1;
2368}
2369
2370void si_init_screen_texture_functions(struct si_screen *sscreen)
2371{
2372   sscreen->b.resource_from_handle = si_texture_from_handle;
2373   sscreen->b.resource_get_handle = si_texture_get_handle;
2374   sscreen->b.resource_get_param = si_resource_get_param;
2375   sscreen->b.resource_get_info = si_texture_get_info;
2376   sscreen->b.resource_from_memobj = si_resource_from_memobj;
2377   sscreen->b.memobj_create_from_handle = si_memobj_from_handle;
2378   sscreen->b.memobj_destroy = si_memobj_destroy;
2379   sscreen->b.check_resource_capability = si_check_resource_capability;
2380   sscreen->b.get_sparse_texture_virtual_page_size =
2381      si_get_sparse_texture_virtual_page_size;
2382
2383   /* By not setting it the frontend will fall back to non-modifier create,
2384    * which works around some applications using modifiers that are not
2385    * allowed in combination with lack of error reporting in
2386    * gbm_dri_surface_create */
2387   if (sscreen->info.gfx_level >= GFX9 && sscreen->info.kernel_has_modifiers) {
2388      sscreen->b.resource_create_with_modifiers = si_texture_create_with_modifiers;
2389      sscreen->b.query_dmabuf_modifiers = si_query_dmabuf_modifiers;
2390      sscreen->b.is_dmabuf_modifier_supported = si_is_dmabuf_modifier_supported;
2391      sscreen->b.get_dmabuf_modifier_planes = si_get_dmabuf_modifier_planes;
2392   }
2393}
2394
2395void si_init_context_texture_functions(struct si_context *sctx)
2396{
2397   sctx->b.texture_map = si_texture_transfer_map;
2398   sctx->b.texture_unmap = si_texture_transfer_unmap;
2399   sctx->b.create_surface = si_create_surface;
2400   sctx->b.surface_destroy = si_surface_destroy;
2401}
2402