1// SPDX-License-Identifier: GPL-2.0-only 2/* 3 * Copyright © 2015 Broadcom 4 */ 5 6/** 7 * DOC: VC4 GEM BO management support 8 * 9 * The VC4 GPU architecture (both scanout and rendering) has direct 10 * access to system memory with no MMU in between. To support it, we 11 * use the GEM CMA helper functions to allocate contiguous ranges of 12 * physical memory for our BOs. 13 * 14 * Since the CMA allocator is very slow, we keep a cache of recently 15 * freed BOs around so that the kernel's allocation of objects for 3D 16 * rendering can return quickly. 17 */ 18 19#include <linux/dma-buf.h> 20 21#include "vc4_drv.h" 22#include "uapi/drm/vc4_drm.h" 23 24static const char * const bo_type_names[] = { 25 "kernel", 26 "V3D", 27 "V3D shader", 28 "dumb", 29 "binner", 30 "RCL", 31 "BCL", 32 "kernel BO cache", 33}; 34 35static bool is_user_label(int label) 36{ 37 return label >= VC4_BO_TYPE_COUNT; 38} 39 40static void vc4_bo_stats_print(struct drm_printer *p, struct vc4_dev *vc4) 41{ 42 int i; 43 44 for (i = 0; i < vc4->num_labels; i++) { 45 if (!vc4->bo_labels[i].num_allocated) 46 continue; 47 48 drm_printf(p, "%30s: %6dkb BOs (%d)\n", 49 vc4->bo_labels[i].name, 50 vc4->bo_labels[i].size_allocated / 1024, 51 vc4->bo_labels[i].num_allocated); 52 } 53 54 mutex_lock(&vc4->purgeable.lock); 55 if (vc4->purgeable.num) 56 drm_printf(p, "%30s: %6zdkb BOs (%d)\n", "userspace BO cache", 57 vc4->purgeable.size / 1024, vc4->purgeable.num); 58 59 if (vc4->purgeable.purged_num) 60 drm_printf(p, "%30s: %6zdkb BOs (%d)\n", "total purged BO", 61 vc4->purgeable.purged_size / 1024, 62 vc4->purgeable.purged_num); 63 mutex_unlock(&vc4->purgeable.lock); 64} 65 66static int vc4_bo_stats_debugfs(struct seq_file *m, void *unused) 67{ 68 struct drm_info_node *node = (struct drm_info_node *)m->private; 69 struct drm_device *dev = node->minor->dev; 70 struct vc4_dev *vc4 = to_vc4_dev(dev); 71 struct drm_printer p = drm_seq_file_printer(m); 72 73 vc4_bo_stats_print(&p, vc4); 74 75 return 0; 76} 77 78/* Takes ownership of *name and returns the appropriate slot for it in 79 * the bo_labels[] array, extending it as necessary. 80 * 81 * This is inefficient and could use a hash table instead of walking 82 * an array and strcmp()ing. However, the assumption is that user 83 * labeling will be infrequent (scanout buffers and other long-lived 84 * objects, or debug driver builds), so we can live with it for now. 85 */ 86static int vc4_get_user_label(struct vc4_dev *vc4, const char *name) 87{ 88 int i; 89 int free_slot = -1; 90 91 for (i = 0; i < vc4->num_labels; i++) { 92 if (!vc4->bo_labels[i].name) { 93 free_slot = i; 94 } else if (strcmp(vc4->bo_labels[i].name, name) == 0) { 95 kfree(name); 96 return i; 97 } 98 } 99 100 if (free_slot != -1) { 101 WARN_ON(vc4->bo_labels[free_slot].num_allocated != 0); 102 vc4->bo_labels[free_slot].name = name; 103 return free_slot; 104 } else { 105 u32 new_label_count = vc4->num_labels + 1; 106 struct vc4_label *new_labels = 107 krealloc(vc4->bo_labels, 108 new_label_count * sizeof(*new_labels), 109 GFP_KERNEL); 110 111 if (!new_labels) { 112 kfree(name); 113 return -1; 114 } 115 116 free_slot = vc4->num_labels; 117 vc4->bo_labels = new_labels; 118 vc4->num_labels = new_label_count; 119 120 vc4->bo_labels[free_slot].name = name; 121 vc4->bo_labels[free_slot].num_allocated = 0; 122 vc4->bo_labels[free_slot].size_allocated = 0; 123 124 return free_slot; 125 } 126} 127 128static void vc4_bo_set_label(struct drm_gem_object *gem_obj, int label) 129{ 130 struct vc4_bo *bo = to_vc4_bo(gem_obj); 131 struct vc4_dev *vc4 = to_vc4_dev(gem_obj->dev); 132 133 lockdep_assert_held(&vc4->bo_lock); 134 135 if (label != -1) { 136 vc4->bo_labels[label].num_allocated++; 137 vc4->bo_labels[label].size_allocated += gem_obj->size; 138 } 139 140 vc4->bo_labels[bo->label].num_allocated--; 141 vc4->bo_labels[bo->label].size_allocated -= gem_obj->size; 142 143 if (vc4->bo_labels[bo->label].num_allocated == 0 && 144 is_user_label(bo->label)) { 145 /* Free user BO label slots on last unreference. 146 * Slots are just where we track the stats for a given 147 * name, and once a name is unused we can reuse that 148 * slot. 149 */ 150 kfree(vc4->bo_labels[bo->label].name); 151 vc4->bo_labels[bo->label].name = NULL; 152 } 153 154 bo->label = label; 155} 156 157static uint32_t bo_page_index(size_t size) 158{ 159 return (size / PAGE_SIZE) - 1; 160} 161 162static void vc4_bo_destroy(struct vc4_bo *bo) 163{ 164 struct drm_gem_object *obj = &bo->base.base; 165 struct vc4_dev *vc4 = to_vc4_dev(obj->dev); 166 167 lockdep_assert_held(&vc4->bo_lock); 168 169 vc4_bo_set_label(obj, -1); 170 171 if (bo->validated_shader) { 172 kfree(bo->validated_shader->uniform_addr_offsets); 173 kfree(bo->validated_shader->texture_samples); 174 kfree(bo->validated_shader); 175 bo->validated_shader = NULL; 176 } 177 178 drm_gem_cma_free_object(obj); 179} 180 181static void vc4_bo_remove_from_cache(struct vc4_bo *bo) 182{ 183 struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev); 184 185 lockdep_assert_held(&vc4->bo_lock); 186 list_del(&bo->unref_head); 187 list_del(&bo->size_head); 188} 189 190static struct list_head *vc4_get_cache_list_for_size(struct drm_device *dev, 191 size_t size) 192{ 193 struct vc4_dev *vc4 = to_vc4_dev(dev); 194 uint32_t page_index = bo_page_index(size); 195 196 if (vc4->bo_cache.size_list_size <= page_index) { 197 uint32_t new_size = max(vc4->bo_cache.size_list_size * 2, 198 page_index + 1); 199 struct list_head *new_list; 200 uint32_t i; 201 202 new_list = kmalloc_array(new_size, sizeof(struct list_head), 203 GFP_KERNEL); 204 if (!new_list) 205 return NULL; 206 207 /* Rebase the old cached BO lists to their new list 208 * head locations. 209 */ 210 for (i = 0; i < vc4->bo_cache.size_list_size; i++) { 211 struct list_head *old_list = 212 &vc4->bo_cache.size_list[i]; 213 214 if (list_empty(old_list)) 215 INIT_LIST_HEAD(&new_list[i]); 216 else 217 list_replace(old_list, &new_list[i]); 218 } 219 /* And initialize the brand new BO list heads. */ 220 for (i = vc4->bo_cache.size_list_size; i < new_size; i++) 221 INIT_LIST_HEAD(&new_list[i]); 222 223 kfree(vc4->bo_cache.size_list); 224 vc4->bo_cache.size_list = new_list; 225 vc4->bo_cache.size_list_size = new_size; 226 } 227 228 return &vc4->bo_cache.size_list[page_index]; 229} 230 231static void vc4_bo_cache_purge(struct drm_device *dev) 232{ 233 struct vc4_dev *vc4 = to_vc4_dev(dev); 234 235 mutex_lock(&vc4->bo_lock); 236 while (!list_empty(&vc4->bo_cache.time_list)) { 237 struct vc4_bo *bo = list_last_entry(&vc4->bo_cache.time_list, 238 struct vc4_bo, unref_head); 239 vc4_bo_remove_from_cache(bo); 240 vc4_bo_destroy(bo); 241 } 242 mutex_unlock(&vc4->bo_lock); 243} 244 245void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo) 246{ 247 struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev); 248 249 mutex_lock(&vc4->purgeable.lock); 250 list_add_tail(&bo->size_head, &vc4->purgeable.list); 251 vc4->purgeable.num++; 252 vc4->purgeable.size += bo->base.base.size; 253 mutex_unlock(&vc4->purgeable.lock); 254} 255 256static void vc4_bo_remove_from_purgeable_pool_locked(struct vc4_bo *bo) 257{ 258 struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev); 259 260 /* list_del_init() is used here because the caller might release 261 * the purgeable lock in order to acquire the madv one and update the 262 * madv status. 263 * During this short period of time a user might decide to mark 264 * the BO as unpurgeable, and if bo->madv is set to 265 * VC4_MADV_DONTNEED it will try to remove the BO from the 266 * purgeable list which will fail if the ->next/prev fields 267 * are set to LIST_POISON1/LIST_POISON2 (which is what 268 * list_del() does). 269 * Re-initializing the list element guarantees that list_del() 270 * will work correctly even if it's a NOP. 271 */ 272 list_del_init(&bo->size_head); 273 vc4->purgeable.num--; 274 vc4->purgeable.size -= bo->base.base.size; 275} 276 277void vc4_bo_remove_from_purgeable_pool(struct vc4_bo *bo) 278{ 279 struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev); 280 281 mutex_lock(&vc4->purgeable.lock); 282 vc4_bo_remove_from_purgeable_pool_locked(bo); 283 mutex_unlock(&vc4->purgeable.lock); 284} 285 286static void vc4_bo_purge(struct drm_gem_object *obj) 287{ 288 struct vc4_bo *bo = to_vc4_bo(obj); 289 struct drm_device *dev = obj->dev; 290 291 WARN_ON(!mutex_is_locked(&bo->madv_lock)); 292 WARN_ON(bo->madv != VC4_MADV_DONTNEED); 293 294 drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping); 295 296 dma_free_wc(dev->dev, obj->size, bo->base.vaddr, bo->base.paddr); 297 bo->base.vaddr = NULL; 298 bo->madv = __VC4_MADV_PURGED; 299} 300 301static void vc4_bo_userspace_cache_purge(struct drm_device *dev) 302{ 303 struct vc4_dev *vc4 = to_vc4_dev(dev); 304 305 mutex_lock(&vc4->purgeable.lock); 306 while (!list_empty(&vc4->purgeable.list)) { 307 struct vc4_bo *bo = list_first_entry(&vc4->purgeable.list, 308 struct vc4_bo, size_head); 309 struct drm_gem_object *obj = &bo->base.base; 310 size_t purged_size = 0; 311 312 vc4_bo_remove_from_purgeable_pool_locked(bo); 313 314 /* Release the purgeable lock while we're purging the BO so 315 * that other people can continue inserting things in the 316 * purgeable pool without having to wait for all BOs to be 317 * purged. 318 */ 319 mutex_unlock(&vc4->purgeable.lock); 320 mutex_lock(&bo->madv_lock); 321 322 /* Since we released the purgeable pool lock before acquiring 323 * the BO madv one, the user may have marked the BO as WILLNEED 324 * and re-used it in the meantime. 325 * Before purging the BO we need to make sure 326 * - it is still marked as DONTNEED 327 * - it has not been re-inserted in the purgeable list 328 * - it is not used by HW blocks 329 * If one of these conditions is not met, just skip the entry. 330 */ 331 if (bo->madv == VC4_MADV_DONTNEED && 332 list_empty(&bo->size_head) && 333 !refcount_read(&bo->usecnt)) { 334 purged_size = bo->base.base.size; 335 vc4_bo_purge(obj); 336 } 337 mutex_unlock(&bo->madv_lock); 338 mutex_lock(&vc4->purgeable.lock); 339 340 if (purged_size) { 341 vc4->purgeable.purged_size += purged_size; 342 vc4->purgeable.purged_num++; 343 } 344 } 345 mutex_unlock(&vc4->purgeable.lock); 346} 347 348static struct vc4_bo *vc4_bo_get_from_cache(struct drm_device *dev, 349 uint32_t size, 350 enum vc4_kernel_bo_type type) 351{ 352 struct vc4_dev *vc4 = to_vc4_dev(dev); 353 uint32_t page_index = bo_page_index(size); 354 struct vc4_bo *bo = NULL; 355 356 size = roundup(size, PAGE_SIZE); 357 358 mutex_lock(&vc4->bo_lock); 359 if (page_index >= vc4->bo_cache.size_list_size) 360 goto out; 361 362 if (list_empty(&vc4->bo_cache.size_list[page_index])) 363 goto out; 364 365 bo = list_first_entry(&vc4->bo_cache.size_list[page_index], 366 struct vc4_bo, size_head); 367 vc4_bo_remove_from_cache(bo); 368 kref_init(&bo->base.base.refcount); 369 370out: 371 if (bo) 372 vc4_bo_set_label(&bo->base.base, type); 373 mutex_unlock(&vc4->bo_lock); 374 return bo; 375} 376 377/** 378 * vc4_gem_create_object - Implementation of driver->gem_create_object. 379 * @dev: DRM device 380 * @size: Size in bytes of the memory the object will reference 381 * 382 * This lets the CMA helpers allocate object structs for us, and keep 383 * our BO stats correct. 384 */ 385struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size) 386{ 387 struct vc4_dev *vc4 = to_vc4_dev(dev); 388 struct vc4_bo *bo; 389 390 bo = kzalloc(sizeof(*bo), GFP_KERNEL); 391 if (!bo) 392 return NULL; 393 394 bo->madv = VC4_MADV_WILLNEED; 395 refcount_set(&bo->usecnt, 0); 396 mutex_init(&bo->madv_lock); 397 mutex_lock(&vc4->bo_lock); 398 bo->label = VC4_BO_TYPE_KERNEL; 399 vc4->bo_labels[VC4_BO_TYPE_KERNEL].num_allocated++; 400 vc4->bo_labels[VC4_BO_TYPE_KERNEL].size_allocated += size; 401 mutex_unlock(&vc4->bo_lock); 402 403 return &bo->base.base; 404} 405 406struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size, 407 bool allow_unzeroed, enum vc4_kernel_bo_type type) 408{ 409 size_t size = roundup(unaligned_size, PAGE_SIZE); 410 struct vc4_dev *vc4 = to_vc4_dev(dev); 411 struct drm_gem_cma_object *cma_obj; 412 struct vc4_bo *bo; 413 414 if (size == 0) 415 return ERR_PTR(-EINVAL); 416 417 /* First, try to get a vc4_bo from the kernel BO cache. */ 418 bo = vc4_bo_get_from_cache(dev, size, type); 419 if (bo) { 420 if (!allow_unzeroed) 421 memset(bo->base.vaddr, 0, bo->base.base.size); 422 return bo; 423 } 424 425 cma_obj = drm_gem_cma_create(dev, size); 426 if (IS_ERR(cma_obj)) { 427 /* 428 * If we've run out of CMA memory, kill the cache of 429 * CMA allocations we've got laying around and try again. 430 */ 431 vc4_bo_cache_purge(dev); 432 cma_obj = drm_gem_cma_create(dev, size); 433 } 434 435 if (IS_ERR(cma_obj)) { 436 /* 437 * Still not enough CMA memory, purge the userspace BO 438 * cache and retry. 439 * This is sub-optimal since we purge the whole userspace 440 * BO cache which forces user that want to re-use the BO to 441 * restore its initial content. 442 * Ideally, we should purge entries one by one and retry 443 * after each to see if CMA allocation succeeds. Or even 444 * better, try to find an entry with at least the same 445 * size. 446 */ 447 vc4_bo_userspace_cache_purge(dev); 448 cma_obj = drm_gem_cma_create(dev, size); 449 } 450 451 if (IS_ERR(cma_obj)) { 452 struct drm_printer p = drm_info_printer(vc4->base.dev); 453 DRM_ERROR("Failed to allocate from CMA:\n"); 454 vc4_bo_stats_print(&p, vc4); 455 return ERR_PTR(-ENOMEM); 456 } 457 bo = to_vc4_bo(&cma_obj->base); 458 459 /* By default, BOs do not support the MADV ioctl. This will be enabled 460 * only on BOs that are exposed to userspace (V3D, V3D_SHADER and DUMB 461 * BOs). 462 */ 463 bo->madv = __VC4_MADV_NOTSUPP; 464 465 mutex_lock(&vc4->bo_lock); 466 vc4_bo_set_label(&cma_obj->base, type); 467 mutex_unlock(&vc4->bo_lock); 468 469 return bo; 470} 471 472int vc4_dumb_create(struct drm_file *file_priv, 473 struct drm_device *dev, 474 struct drm_mode_create_dumb *args) 475{ 476 int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8); 477 struct vc4_bo *bo = NULL; 478 int ret; 479 480 if (args->pitch < min_pitch) 481 args->pitch = min_pitch; 482 483 if (args->size < args->pitch * args->height) 484 args->size = args->pitch * args->height; 485 486 bo = vc4_bo_create(dev, args->size, false, VC4_BO_TYPE_DUMB); 487 if (IS_ERR(bo)) 488 return PTR_ERR(bo); 489 490 bo->madv = VC4_MADV_WILLNEED; 491 492 ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); 493 drm_gem_object_put(&bo->base.base); 494 495 return ret; 496} 497 498static void vc4_bo_cache_free_old(struct drm_device *dev) 499{ 500 struct vc4_dev *vc4 = to_vc4_dev(dev); 501 unsigned long expire_time = jiffies - msecs_to_jiffies(1000); 502 503 lockdep_assert_held(&vc4->bo_lock); 504 505 while (!list_empty(&vc4->bo_cache.time_list)) { 506 struct vc4_bo *bo = list_last_entry(&vc4->bo_cache.time_list, 507 struct vc4_bo, unref_head); 508 if (time_before(expire_time, bo->free_time)) { 509 mod_timer(&vc4->bo_cache.time_timer, 510 round_jiffies_up(jiffies + 511 msecs_to_jiffies(1000))); 512 return; 513 } 514 515 vc4_bo_remove_from_cache(bo); 516 vc4_bo_destroy(bo); 517 } 518} 519 520/* Called on the last userspace/kernel unreference of the BO. Returns 521 * it to the BO cache if possible, otherwise frees it. 522 */ 523void vc4_free_object(struct drm_gem_object *gem_bo) 524{ 525 struct drm_device *dev = gem_bo->dev; 526 struct vc4_dev *vc4 = to_vc4_dev(dev); 527 struct vc4_bo *bo = to_vc4_bo(gem_bo); 528 struct list_head *cache_list; 529 530 /* Remove the BO from the purgeable list. */ 531 mutex_lock(&bo->madv_lock); 532 if (bo->madv == VC4_MADV_DONTNEED && !refcount_read(&bo->usecnt)) 533 vc4_bo_remove_from_purgeable_pool(bo); 534 mutex_unlock(&bo->madv_lock); 535 536 mutex_lock(&vc4->bo_lock); 537 /* If the object references someone else's memory, we can't cache it. 538 */ 539 if (gem_bo->import_attach) { 540 vc4_bo_destroy(bo); 541 goto out; 542 } 543 544 /* Don't cache if it was publicly named. */ 545 if (gem_bo->name) { 546 vc4_bo_destroy(bo); 547 goto out; 548 } 549 550 /* If this object was partially constructed but CMA allocation 551 * had failed, just free it. Can also happen when the BO has been 552 * purged. 553 */ 554 if (!bo->base.vaddr) { 555 vc4_bo_destroy(bo); 556 goto out; 557 } 558 559 cache_list = vc4_get_cache_list_for_size(dev, gem_bo->size); 560 if (!cache_list) { 561 vc4_bo_destroy(bo); 562 goto out; 563 } 564 565 if (bo->validated_shader) { 566 kfree(bo->validated_shader->uniform_addr_offsets); 567 kfree(bo->validated_shader->texture_samples); 568 kfree(bo->validated_shader); 569 bo->validated_shader = NULL; 570 } 571 572 /* Reset madv and usecnt before adding the BO to the cache. */ 573 bo->madv = __VC4_MADV_NOTSUPP; 574 refcount_set(&bo->usecnt, 0); 575 576 bo->t_format = false; 577 bo->free_time = jiffies; 578 list_add(&bo->size_head, cache_list); 579 list_add(&bo->unref_head, &vc4->bo_cache.time_list); 580 581 vc4_bo_set_label(&bo->base.base, VC4_BO_TYPE_KERNEL_CACHE); 582 583 vc4_bo_cache_free_old(dev); 584 585out: 586 mutex_unlock(&vc4->bo_lock); 587} 588 589static void vc4_bo_cache_time_work(struct work_struct *work) 590{ 591 struct vc4_dev *vc4 = 592 container_of(work, struct vc4_dev, bo_cache.time_work); 593 struct drm_device *dev = &vc4->base; 594 595 mutex_lock(&vc4->bo_lock); 596 vc4_bo_cache_free_old(dev); 597 mutex_unlock(&vc4->bo_lock); 598} 599 600int vc4_bo_inc_usecnt(struct vc4_bo *bo) 601{ 602 int ret; 603 604 /* Fast path: if the BO is already retained by someone, no need to 605 * check the madv status. 606 */ 607 if (refcount_inc_not_zero(&bo->usecnt)) 608 return 0; 609 610 mutex_lock(&bo->madv_lock); 611 switch (bo->madv) { 612 case VC4_MADV_WILLNEED: 613 if (!refcount_inc_not_zero(&bo->usecnt)) 614 refcount_set(&bo->usecnt, 1); 615 ret = 0; 616 break; 617 case VC4_MADV_DONTNEED: 618 /* We shouldn't use a BO marked as purgeable if at least 619 * someone else retained its content by incrementing usecnt. 620 * Luckily the BO hasn't been purged yet, but something wrong 621 * is happening here. Just throw an error instead of 622 * authorizing this use case. 623 */ 624 case __VC4_MADV_PURGED: 625 /* We can't use a purged BO. */ 626 default: 627 /* Invalid madv value. */ 628 ret = -EINVAL; 629 break; 630 } 631 mutex_unlock(&bo->madv_lock); 632 633 return ret; 634} 635 636void vc4_bo_dec_usecnt(struct vc4_bo *bo) 637{ 638 /* Fast path: if the BO is still retained by someone, no need to test 639 * the madv value. 640 */ 641 if (refcount_dec_not_one(&bo->usecnt)) 642 return; 643 644 mutex_lock(&bo->madv_lock); 645 if (refcount_dec_and_test(&bo->usecnt) && 646 bo->madv == VC4_MADV_DONTNEED) 647 vc4_bo_add_to_purgeable_pool(bo); 648 mutex_unlock(&bo->madv_lock); 649} 650 651static void vc4_bo_cache_time_timer(struct timer_list *t) 652{ 653 struct vc4_dev *vc4 = from_timer(vc4, t, bo_cache.time_timer); 654 655 schedule_work(&vc4->bo_cache.time_work); 656} 657 658struct dma_buf * vc4_prime_export(struct drm_gem_object *obj, int flags) 659{ 660 struct vc4_bo *bo = to_vc4_bo(obj); 661 struct dma_buf *dmabuf; 662 int ret; 663 664 if (bo->validated_shader) { 665 DRM_DEBUG("Attempting to export shader BO\n"); 666 return ERR_PTR(-EINVAL); 667 } 668 669 /* Note: as soon as the BO is exported it becomes unpurgeable, because 670 * noone ever decrements the usecnt even if the reference held by the 671 * exported BO is released. This shouldn't be a problem since we don't 672 * expect exported BOs to be marked as purgeable. 673 */ 674 ret = vc4_bo_inc_usecnt(bo); 675 if (ret) { 676 DRM_ERROR("Failed to increment BO usecnt\n"); 677 return ERR_PTR(ret); 678 } 679 680 dmabuf = drm_gem_prime_export(obj, flags); 681 if (IS_ERR(dmabuf)) 682 vc4_bo_dec_usecnt(bo); 683 684 return dmabuf; 685} 686 687vm_fault_t vc4_fault(struct vm_fault *vmf) 688{ 689 struct vm_area_struct *vma = vmf->vma; 690 struct drm_gem_object *obj = vma->vm_private_data; 691 struct vc4_bo *bo = to_vc4_bo(obj); 692 693 /* The only reason we would end up here is when user-space accesses 694 * BO's memory after it's been purged. 695 */ 696 mutex_lock(&bo->madv_lock); 697 WARN_ON(bo->madv != __VC4_MADV_PURGED); 698 mutex_unlock(&bo->madv_lock); 699 700 return VM_FAULT_SIGBUS; 701} 702 703int vc4_mmap(struct file *filp, struct vm_area_struct *vma) 704{ 705 struct drm_gem_object *gem_obj; 706 unsigned long vm_pgoff; 707 struct vc4_bo *bo; 708 int ret; 709 710 ret = drm_gem_mmap(filp, vma); 711 if (ret) 712 return ret; 713 714 gem_obj = vma->vm_private_data; 715 bo = to_vc4_bo(gem_obj); 716 717 if (bo->validated_shader && (vma->vm_flags & VM_WRITE)) { 718 DRM_DEBUG("mmaping of shader BOs for writing not allowed.\n"); 719 return -EINVAL; 720 } 721 722 if (bo->madv != VC4_MADV_WILLNEED) { 723 DRM_DEBUG("mmaping of %s BO not allowed\n", 724 bo->madv == VC4_MADV_DONTNEED ? 725 "purgeable" : "purged"); 726 return -EINVAL; 727 } 728 729 /* 730 * Clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the 731 * vm_pgoff (used as a fake buffer offset by DRM) to 0 as we want to map 732 * the whole buffer. 733 */ 734 vma->vm_flags &= ~VM_PFNMAP; 735 736 /* This ->vm_pgoff dance is needed to make all parties happy: 737 * - dma_mmap_wc() uses ->vm_pgoff as an offset within the allocated 738 * mem-region, hence the need to set it to zero (the value set by 739 * the DRM core is a virtual offset encoding the GEM object-id) 740 * - the mmap() core logic needs ->vm_pgoff to be restored to its 741 * initial value before returning from this function because it 742 * encodes the offset of this GEM in the dev->anon_inode pseudo-file 743 * and this information will be used when we invalidate userspace 744 * mappings with drm_vma_node_unmap() (called from vc4_gem_purge()). 745 */ 746 vm_pgoff = vma->vm_pgoff; 747 vma->vm_pgoff = 0; 748 ret = dma_mmap_wc(bo->base.base.dev->dev, vma, bo->base.vaddr, 749 bo->base.paddr, vma->vm_end - vma->vm_start); 750 vma->vm_pgoff = vm_pgoff; 751 752 if (ret) 753 drm_gem_vm_close(vma); 754 755 return ret; 756} 757 758int vc4_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) 759{ 760 struct vc4_bo *bo = to_vc4_bo(obj); 761 762 if (bo->validated_shader && (vma->vm_flags & VM_WRITE)) { 763 DRM_DEBUG("mmaping of shader BOs for writing not allowed.\n"); 764 return -EINVAL; 765 } 766 767 return drm_gem_cma_prime_mmap(obj, vma); 768} 769 770void *vc4_prime_vmap(struct drm_gem_object *obj) 771{ 772 struct vc4_bo *bo = to_vc4_bo(obj); 773 774 if (bo->validated_shader) { 775 DRM_DEBUG("mmaping of shader BOs not allowed.\n"); 776 return ERR_PTR(-EINVAL); 777 } 778 779 return drm_gem_cma_prime_vmap(obj); 780} 781 782struct drm_gem_object * 783vc4_prime_import_sg_table(struct drm_device *dev, 784 struct dma_buf_attachment *attach, 785 struct sg_table *sgt) 786{ 787 struct drm_gem_object *obj; 788 789 obj = drm_gem_cma_prime_import_sg_table(dev, attach, sgt); 790 if (IS_ERR(obj)) 791 return obj; 792 793 return obj; 794} 795 796static int vc4_grab_bin_bo(struct vc4_dev *vc4, struct vc4_file *vc4file) 797{ 798 int ret; 799 800 if (!vc4->v3d) 801 return -ENODEV; 802 803 if (vc4file->bin_bo_used) 804 return 0; 805 806 ret = vc4_v3d_bin_bo_get(vc4, &vc4file->bin_bo_used); 807 if (ret) 808 return ret; 809 810 return 0; 811} 812 813int vc4_create_bo_ioctl(struct drm_device *dev, void *data, 814 struct drm_file *file_priv) 815{ 816 struct drm_vc4_create_bo *args = data; 817 struct vc4_file *vc4file = file_priv->driver_priv; 818 struct vc4_dev *vc4 = to_vc4_dev(dev); 819 struct vc4_bo *bo = NULL; 820 int ret; 821 822 ret = vc4_grab_bin_bo(vc4, vc4file); 823 if (ret) 824 return ret; 825 826 /* 827 * We can't allocate from the BO cache, because the BOs don't 828 * get zeroed, and that might leak data between users. 829 */ 830 bo = vc4_bo_create(dev, args->size, false, VC4_BO_TYPE_V3D); 831 if (IS_ERR(bo)) 832 return PTR_ERR(bo); 833 834 bo->madv = VC4_MADV_WILLNEED; 835 836 ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); 837 drm_gem_object_put(&bo->base.base); 838 839 return ret; 840} 841 842int vc4_mmap_bo_ioctl(struct drm_device *dev, void *data, 843 struct drm_file *file_priv) 844{ 845 struct drm_vc4_mmap_bo *args = data; 846 struct drm_gem_object *gem_obj; 847 848 gem_obj = drm_gem_object_lookup(file_priv, args->handle); 849 if (!gem_obj) { 850 DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle); 851 return -EINVAL; 852 } 853 854 /* The mmap offset was set up at BO allocation time. */ 855 args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node); 856 857 drm_gem_object_put(gem_obj); 858 return 0; 859} 860 861int 862vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data, 863 struct drm_file *file_priv) 864{ 865 struct drm_vc4_create_shader_bo *args = data; 866 struct vc4_file *vc4file = file_priv->driver_priv; 867 struct vc4_dev *vc4 = to_vc4_dev(dev); 868 struct vc4_bo *bo = NULL; 869 int ret; 870 871 if (args->size == 0) 872 return -EINVAL; 873 874 if (args->size % sizeof(u64) != 0) 875 return -EINVAL; 876 877 if (args->flags != 0) { 878 DRM_INFO("Unknown flags set: 0x%08x\n", args->flags); 879 return -EINVAL; 880 } 881 882 if (args->pad != 0) { 883 DRM_INFO("Pad set: 0x%08x\n", args->pad); 884 return -EINVAL; 885 } 886 887 ret = vc4_grab_bin_bo(vc4, vc4file); 888 if (ret) 889 return ret; 890 891 bo = vc4_bo_create(dev, args->size, true, VC4_BO_TYPE_V3D_SHADER); 892 if (IS_ERR(bo)) 893 return PTR_ERR(bo); 894 895 bo->madv = VC4_MADV_WILLNEED; 896 897 if (copy_from_user(bo->base.vaddr, 898 (void __user *)(uintptr_t)args->data, 899 args->size)) { 900 ret = -EFAULT; 901 goto fail; 902 } 903 /* Clear the rest of the memory from allocating from the BO 904 * cache. 905 */ 906 memset(bo->base.vaddr + args->size, 0, 907 bo->base.base.size - args->size); 908 909 bo->validated_shader = vc4_validate_shader(&bo->base); 910 if (!bo->validated_shader) { 911 ret = -EINVAL; 912 goto fail; 913 } 914 915 /* We have to create the handle after validation, to avoid 916 * races for users to do doing things like mmap the shader BO. 917 */ 918 ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); 919 920fail: 921 drm_gem_object_put(&bo->base.base); 922 923 return ret; 924} 925 926/** 927 * vc4_set_tiling_ioctl() - Sets the tiling modifier for a BO. 928 * @dev: DRM device 929 * @data: ioctl argument 930 * @file_priv: DRM file for this fd 931 * 932 * The tiling state of the BO decides the default modifier of an fb if 933 * no specific modifier was set by userspace, and the return value of 934 * vc4_get_tiling_ioctl() (so that userspace can treat a BO it 935 * received from dmabuf as the same tiling format as the producer 936 * used). 937 */ 938int vc4_set_tiling_ioctl(struct drm_device *dev, void *data, 939 struct drm_file *file_priv) 940{ 941 struct drm_vc4_set_tiling *args = data; 942 struct drm_gem_object *gem_obj; 943 struct vc4_bo *bo; 944 bool t_format; 945 946 if (args->flags != 0) 947 return -EINVAL; 948 949 switch (args->modifier) { 950 case DRM_FORMAT_MOD_NONE: 951 t_format = false; 952 break; 953 case DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED: 954 t_format = true; 955 break; 956 default: 957 return -EINVAL; 958 } 959 960 gem_obj = drm_gem_object_lookup(file_priv, args->handle); 961 if (!gem_obj) { 962 DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle); 963 return -ENOENT; 964 } 965 bo = to_vc4_bo(gem_obj); 966 bo->t_format = t_format; 967 968 drm_gem_object_put(gem_obj); 969 970 return 0; 971} 972 973/** 974 * vc4_get_tiling_ioctl() - Gets the tiling modifier for a BO. 975 * @dev: DRM device 976 * @data: ioctl argument 977 * @file_priv: DRM file for this fd 978 * 979 * Returns the tiling modifier for a BO as set by vc4_set_tiling_ioctl(). 980 */ 981int vc4_get_tiling_ioctl(struct drm_device *dev, void *data, 982 struct drm_file *file_priv) 983{ 984 struct drm_vc4_get_tiling *args = data; 985 struct drm_gem_object *gem_obj; 986 struct vc4_bo *bo; 987 988 if (args->flags != 0 || args->modifier != 0) 989 return -EINVAL; 990 991 gem_obj = drm_gem_object_lookup(file_priv, args->handle); 992 if (!gem_obj) { 993 DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle); 994 return -ENOENT; 995 } 996 bo = to_vc4_bo(gem_obj); 997 998 if (bo->t_format) 999 args->modifier = DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED; 1000 else 1001 args->modifier = DRM_FORMAT_MOD_NONE; 1002 1003 drm_gem_object_put(gem_obj); 1004 1005 return 0; 1006} 1007 1008static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused); 1009int vc4_bo_cache_init(struct drm_device *dev) 1010{ 1011 struct vc4_dev *vc4 = to_vc4_dev(dev); 1012 int i; 1013 1014 /* Create the initial set of BO labels that the kernel will 1015 * use. This lets us avoid a bunch of string reallocation in 1016 * the kernel's draw and BO allocation paths. 1017 */ 1018 vc4->bo_labels = kcalloc(VC4_BO_TYPE_COUNT, sizeof(*vc4->bo_labels), 1019 GFP_KERNEL); 1020 if (!vc4->bo_labels) 1021 return -ENOMEM; 1022 vc4->num_labels = VC4_BO_TYPE_COUNT; 1023 1024 BUILD_BUG_ON(ARRAY_SIZE(bo_type_names) != VC4_BO_TYPE_COUNT); 1025 for (i = 0; i < VC4_BO_TYPE_COUNT; i++) 1026 vc4->bo_labels[i].name = bo_type_names[i]; 1027 1028 mutex_init(&vc4->bo_lock); 1029 1030 vc4_debugfs_add_file(dev, "bo_stats", vc4_bo_stats_debugfs, NULL); 1031 1032 INIT_LIST_HEAD(&vc4->bo_cache.time_list); 1033 1034 INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work); 1035 timer_setup(&vc4->bo_cache.time_timer, vc4_bo_cache_time_timer, 0); 1036 1037 return drmm_add_action_or_reset(dev, vc4_bo_cache_destroy, NULL); 1038} 1039 1040static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused) 1041{ 1042 struct vc4_dev *vc4 = to_vc4_dev(dev); 1043 int i; 1044 1045 del_timer(&vc4->bo_cache.time_timer); 1046 cancel_work_sync(&vc4->bo_cache.time_work); 1047 1048 vc4_bo_cache_purge(dev); 1049 1050 for (i = 0; i < vc4->num_labels; i++) { 1051 if (vc4->bo_labels[i].num_allocated) { 1052 DRM_ERROR("Destroying BO cache with %d %s " 1053 "BOs still allocated\n", 1054 vc4->bo_labels[i].num_allocated, 1055 vc4->bo_labels[i].name); 1056 } 1057 1058 if (is_user_label(i)) 1059 kfree(vc4->bo_labels[i].name); 1060 } 1061 kfree(vc4->bo_labels); 1062} 1063 1064int vc4_label_bo_ioctl(struct drm_device *dev, void *data, 1065 struct drm_file *file_priv) 1066{ 1067 struct vc4_dev *vc4 = to_vc4_dev(dev); 1068 struct drm_vc4_label_bo *args = data; 1069 char *name; 1070 struct drm_gem_object *gem_obj; 1071 int ret = 0, label; 1072 1073 if (!args->len) 1074 return -EINVAL; 1075 1076 name = strndup_user(u64_to_user_ptr(args->name), args->len + 1); 1077 if (IS_ERR(name)) 1078 return PTR_ERR(name); 1079 1080 gem_obj = drm_gem_object_lookup(file_priv, args->handle); 1081 if (!gem_obj) { 1082 DRM_ERROR("Failed to look up GEM BO %d\n", args->handle); 1083 kfree(name); 1084 return -ENOENT; 1085 } 1086 1087 mutex_lock(&vc4->bo_lock); 1088 label = vc4_get_user_label(vc4, name); 1089 if (label != -1) 1090 vc4_bo_set_label(gem_obj, label); 1091 else 1092 ret = -ENOMEM; 1093 mutex_unlock(&vc4->bo_lock); 1094 1095 drm_gem_object_put(gem_obj); 1096 1097 return ret; 1098} 1099