1 /*
2 * SPDX-License-Identifier: MIT
3 *
4 * Copyright © 2011-2012 Intel Corporation
5 */
6
7 /*
8 * This file implements HW context support. On gen5+ a HW context consists of an
9 * opaque GPU object which is referenced at times of context saves and restores.
10 * With RC6 enabled, the context is also referenced as the GPU enters and exists
11 * from RC6 (GPU has it's own internal power context, except on gen5). Though
12 * something like a context does exist for the media ring, the code only
13 * supports contexts for the render ring.
14 *
15 * In software, there is a distinction between contexts created by the user,
16 * and the default HW context. The default HW context is used by GPU clients
17 * that do not request setup of their own hardware context. The default
18 * context's state is never restored to help prevent programming errors. This
19 * would happen if a client ran and piggy-backed off another clients GPU state.
20 * The default context only exists to give the GPU some offset to load as the
21 * current to invoke a save of the context we actually care about. In fact, the
22 * code could likely be constructed, albeit in a more complicated fashion, to
23 * never use the default context, though that limits the driver's ability to
24 * swap out, and/or destroy other contexts.
25 *
26 * All other contexts are created as a request by the GPU client. These contexts
27 * store GPU state, and thus allow GPU clients to not re-emit state (and
28 * potentially query certain state) at any time. The kernel driver makes
29 * certain that the appropriate commands are inserted.
30 *
31 * The context life cycle is semi-complicated in that context BOs may live
32 * longer than the context itself because of the way the hardware, and object
33 * tracking works. Below is a very crude representation of the state machine
34 * describing the context life.
35 * refcount pincount active
36 * S0: initial state 0 0 0
37 * S1: context created 1 0 0
38 * S2: context is currently running 2 1 X
39 * S3: GPU referenced, but not current 2 0 1
40 * S4: context is current, but destroyed 1 1 0
41 * S5: like S3, but destroyed 1 0 1
42 *
43 * The most common (but not all) transitions:
44 * S0->S1: client creates a context
45 * S1->S2: client submits execbuf with context
46 * S2->S3: other clients submits execbuf with context
47 * S3->S1: context object was retired
48 * S3->S2: clients submits another execbuf
49 * S2->S4: context destroy called with current context
50 * S3->S5->S0: destroy path
51 * S4->S5->S0: destroy path on current context
52 *
53 * There are two confusing terms used above:
54 * The "current context" means the context which is currently running on the
55 * GPU. The GPU has loaded its state already and has stored away the gtt
56 * offset of the BO. The GPU is not actively referencing the data at this
57 * offset, but it will on the next context switch. The only way to avoid this
58 * is to do a GPU reset.
59 *
60 * An "active context' is one which was previously the "current context" and is
61 * on the active list waiting for the next context switch to occur. Until this
62 * happens, the object must remain at the same gtt offset. It is therefore
63 * possible to destroy a context, but it is still active.
64 *
65 */
66
67 #include <linux/highmem.h>
68 #include <linux/log2.h>
69 #include <linux/nospec.h>
70
71 #include <drm/drm_cache.h>
72 #include <drm/drm_syncobj.h>
73
74 #include "gt/gen6_ppgtt.h"
75 #include "gt/intel_context.h"
76 #include "gt/intel_context_param.h"
77 #include "gt/intel_engine_heartbeat.h"
78 #include "gt/intel_engine_user.h"
79 #include "gt/intel_gpu_commands.h"
80 #include "gt/intel_ring.h"
81
82 #include "pxp/intel_pxp.h"
83
84 #include "i915_file_private.h"
85 #include "i915_gem_context.h"
86 #include "i915_trace.h"
87 #include "i915_user_extensions.h"
88
89 #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
90
91 static struct kmem_cache *slab_luts;
92
i915_lut_handle_alloc(void)93 struct i915_lut_handle *i915_lut_handle_alloc(void)
94 {
95 return kmem_cache_alloc(slab_luts, GFP_KERNEL);
96 }
97
i915_lut_handle_free(struct i915_lut_handle * lut)98 void i915_lut_handle_free(struct i915_lut_handle *lut)
99 {
100 return kmem_cache_free(slab_luts, lut);
101 }
102
lut_close(struct i915_gem_context * ctx)103 static void lut_close(struct i915_gem_context *ctx)
104 {
105 struct radix_tree_iter iter;
106 void __rcu **slot;
107
108 mutex_lock(&ctx->lut_mutex);
109 rcu_read_lock();
110 radix_tree_for_each_slot(slot, &ctx->handles_vma, &iter, 0) {
111 struct i915_vma *vma = rcu_dereference_raw(*slot);
112 struct drm_i915_gem_object *obj = vma->obj;
113 struct i915_lut_handle *lut;
114
115 if (!kref_get_unless_zero(&obj->base.refcount))
116 continue;
117
118 spin_lock(&obj->lut_lock);
119 list_for_each_entry(lut, &obj->lut_list, obj_link) {
120 if (lut->ctx != ctx)
121 continue;
122
123 if (lut->handle != iter.index)
124 continue;
125
126 list_del(&lut->obj_link);
127 break;
128 }
129 spin_unlock(&obj->lut_lock);
130
131 if (&lut->obj_link != &obj->lut_list) {
132 i915_lut_handle_free(lut);
133 radix_tree_iter_delete(&ctx->handles_vma, &iter, slot);
134 i915_vma_close(vma);
135 i915_gem_object_put(obj);
136 }
137
138 i915_gem_object_put(obj);
139 }
140 rcu_read_unlock();
141 mutex_unlock(&ctx->lut_mutex);
142 }
143
144 static struct intel_context *
lookup_user_engine(struct i915_gem_context * ctx,unsigned long flags,const struct i915_engine_class_instance * ci)145 lookup_user_engine(struct i915_gem_context *ctx,
146 unsigned long flags,
147 const struct i915_engine_class_instance *ci)
148 #define LOOKUP_USER_INDEX BIT(0)
149 {
150 int idx;
151
152 if (!!(flags & LOOKUP_USER_INDEX) != i915_gem_context_user_engines(ctx))
153 return ERR_PTR(-EINVAL);
154
155 if (!i915_gem_context_user_engines(ctx)) {
156 struct intel_engine_cs *engine;
157
158 engine = intel_engine_lookup_user(ctx->i915,
159 ci->engine_class,
160 ci->engine_instance);
161 if (!engine)
162 return ERR_PTR(-EINVAL);
163
164 idx = engine->legacy_idx;
165 } else {
166 idx = ci->engine_instance;
167 }
168
169 return i915_gem_context_get_engine(ctx, idx);
170 }
171
validate_priority(struct drm_i915_private * i915,const struct drm_i915_gem_context_param * args)172 static int validate_priority(struct drm_i915_private *i915,
173 const struct drm_i915_gem_context_param *args)
174 {
175 s64 priority = args->value;
176
177 if (args->size)
178 return -EINVAL;
179
180 if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
181 return -ENODEV;
182
183 if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
184 priority < I915_CONTEXT_MIN_USER_PRIORITY)
185 return -EINVAL;
186
187 if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
188 !capable(CAP_SYS_NICE))
189 return -EPERM;
190
191 return 0;
192 }
193
proto_context_close(struct drm_i915_private * i915,struct i915_gem_proto_context * pc)194 static void proto_context_close(struct drm_i915_private *i915,
195 struct i915_gem_proto_context *pc)
196 {
197 int i;
198
199 if (pc->pxp_wakeref)
200 intel_runtime_pm_put(&i915->runtime_pm, pc->pxp_wakeref);
201 if (pc->vm)
202 i915_vm_put(pc->vm);
203 if (pc->user_engines) {
204 for (i = 0; i < pc->num_user_engines; i++)
205 kfree(pc->user_engines[i].siblings);
206 kfree(pc->user_engines);
207 }
208 kfree(pc);
209 }
210
proto_context_set_persistence(struct drm_i915_private * i915,struct i915_gem_proto_context * pc,bool persist)211 static int proto_context_set_persistence(struct drm_i915_private *i915,
212 struct i915_gem_proto_context *pc,
213 bool persist)
214 {
215 if (persist) {
216 /*
217 * Only contexts that are short-lived [that will expire or be
218 * reset] are allowed to survive past termination. We require
219 * hangcheck to ensure that the persistent requests are healthy.
220 */
221 if (!i915->params.enable_hangcheck)
222 return -EINVAL;
223
224 pc->user_flags |= BIT(UCONTEXT_PERSISTENCE);
225 } else {
226 /* To cancel a context we use "preempt-to-idle" */
227 if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
228 return -ENODEV;
229
230 /*
231 * If the cancel fails, we then need to reset, cleanly!
232 *
233 * If the per-engine reset fails, all hope is lost! We resort
234 * to a full GPU reset in that unlikely case, but realistically
235 * if the engine could not reset, the full reset does not fare
236 * much better. The damage has been done.
237 *
238 * However, if we cannot reset an engine by itself, we cannot
239 * cleanup a hanging persistent context without causing
240 * colateral damage, and we should not pretend we can by
241 * exposing the interface.
242 */
243 if (!intel_has_reset_engine(to_gt(i915)))
244 return -ENODEV;
245
246 pc->user_flags &= ~BIT(UCONTEXT_PERSISTENCE);
247 }
248
249 return 0;
250 }
251
proto_context_set_protected(struct drm_i915_private * i915,struct i915_gem_proto_context * pc,bool protected)252 static int proto_context_set_protected(struct drm_i915_private *i915,
253 struct i915_gem_proto_context *pc,
254 bool protected)
255 {
256 int ret = 0;
257
258 if (!protected) {
259 pc->uses_protected_content = false;
260 } else if (!intel_pxp_is_enabled(i915->pxp)) {
261 ret = -ENODEV;
262 } else if ((pc->user_flags & BIT(UCONTEXT_RECOVERABLE)) ||
263 !(pc->user_flags & BIT(UCONTEXT_BANNABLE))) {
264 ret = -EPERM;
265 } else {
266 pc->uses_protected_content = true;
267
268 /*
269 * protected context usage requires the PXP session to be up,
270 * which in turn requires the device to be active.
271 */
272 pc->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm);
273
274 if (!intel_pxp_is_active(i915->pxp))
275 ret = intel_pxp_start(i915->pxp);
276 }
277
278 return ret;
279 }
280
281 static struct i915_gem_proto_context *
proto_context_create(struct drm_i915_private * i915,unsigned int flags)282 proto_context_create(struct drm_i915_private *i915, unsigned int flags)
283 {
284 struct i915_gem_proto_context *pc, *err;
285
286 pc = kzalloc(sizeof(*pc), GFP_KERNEL);
287 if (!pc)
288 return ERR_PTR(-ENOMEM);
289
290 pc->num_user_engines = -1;
291 pc->user_engines = NULL;
292 pc->user_flags = BIT(UCONTEXT_BANNABLE) |
293 BIT(UCONTEXT_RECOVERABLE);
294 if (i915->params.enable_hangcheck)
295 pc->user_flags |= BIT(UCONTEXT_PERSISTENCE);
296 pc->sched.priority = I915_PRIORITY_NORMAL;
297
298 if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE) {
299 if (!HAS_EXECLISTS(i915)) {
300 err = ERR_PTR(-EINVAL);
301 goto proto_close;
302 }
303 pc->single_timeline = true;
304 }
305
306 return pc;
307
308 proto_close:
309 proto_context_close(i915, pc);
310 return err;
311 }
312
proto_context_register_locked(struct drm_i915_file_private * fpriv,struct i915_gem_proto_context * pc,u32 * id)313 static int proto_context_register_locked(struct drm_i915_file_private *fpriv,
314 struct i915_gem_proto_context *pc,
315 u32 *id)
316 {
317 int ret;
318 void *old;
319
320 lockdep_assert_held(&fpriv->proto_context_lock);
321
322 ret = xa_alloc(&fpriv->context_xa, id, NULL, xa_limit_32b, GFP_KERNEL);
323 if (ret)
324 return ret;
325
326 old = xa_store(&fpriv->proto_context_xa, *id, pc, GFP_KERNEL);
327 if (xa_is_err(old)) {
328 xa_erase(&fpriv->context_xa, *id);
329 return xa_err(old);
330 }
331 WARN_ON(old);
332
333 return 0;
334 }
335
proto_context_register(struct drm_i915_file_private * fpriv,struct i915_gem_proto_context * pc,u32 * id)336 static int proto_context_register(struct drm_i915_file_private *fpriv,
337 struct i915_gem_proto_context *pc,
338 u32 *id)
339 {
340 int ret;
341
342 mutex_lock(&fpriv->proto_context_lock);
343 ret = proto_context_register_locked(fpriv, pc, id);
344 mutex_unlock(&fpriv->proto_context_lock);
345
346 return ret;
347 }
348
349 static struct i915_address_space *
i915_gem_vm_lookup(struct drm_i915_file_private * file_priv,u32 id)350 i915_gem_vm_lookup(struct drm_i915_file_private *file_priv, u32 id)
351 {
352 struct i915_address_space *vm;
353
354 xa_lock(&file_priv->vm_xa);
355 vm = xa_load(&file_priv->vm_xa, id);
356 if (vm)
357 kref_get(&vm->ref);
358 xa_unlock(&file_priv->vm_xa);
359
360 return vm;
361 }
362
set_proto_ctx_vm(struct drm_i915_file_private * fpriv,struct i915_gem_proto_context * pc,const struct drm_i915_gem_context_param * args)363 static int set_proto_ctx_vm(struct drm_i915_file_private *fpriv,
364 struct i915_gem_proto_context *pc,
365 const struct drm_i915_gem_context_param *args)
366 {
367 struct drm_i915_private *i915 = fpriv->dev_priv;
368 struct i915_address_space *vm;
369
370 if (args->size)
371 return -EINVAL;
372
373 if (!HAS_FULL_PPGTT(i915))
374 return -ENODEV;
375
376 if (upper_32_bits(args->value))
377 return -ENOENT;
378
379 vm = i915_gem_vm_lookup(fpriv, args->value);
380 if (!vm)
381 return -ENOENT;
382
383 if (pc->vm)
384 i915_vm_put(pc->vm);
385 pc->vm = vm;
386
387 return 0;
388 }
389
390 struct set_proto_ctx_engines {
391 struct drm_i915_private *i915;
392 unsigned num_engines;
393 struct i915_gem_proto_engine *engines;
394 };
395
396 static int
set_proto_ctx_engines_balance(struct i915_user_extension __user * base,void * data)397 set_proto_ctx_engines_balance(struct i915_user_extension __user *base,
398 void *data)
399 {
400 struct i915_context_engines_load_balance __user *ext =
401 container_of_user(base, typeof(*ext), base);
402 const struct set_proto_ctx_engines *set = data;
403 struct drm_i915_private *i915 = set->i915;
404 struct intel_engine_cs **siblings;
405 u16 num_siblings, idx;
406 unsigned int n;
407 int err;
408
409 if (!HAS_EXECLISTS(i915))
410 return -ENODEV;
411
412 if (get_user(idx, &ext->engine_index))
413 return -EFAULT;
414
415 if (idx >= set->num_engines) {
416 drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
417 idx, set->num_engines);
418 return -EINVAL;
419 }
420
421 idx = array_index_nospec(idx, set->num_engines);
422 if (set->engines[idx].type != I915_GEM_ENGINE_TYPE_INVALID) {
423 drm_dbg(&i915->drm,
424 "Invalid placement[%d], already occupied\n", idx);
425 return -EEXIST;
426 }
427
428 if (get_user(num_siblings, &ext->num_siblings))
429 return -EFAULT;
430
431 err = check_user_mbz(&ext->flags);
432 if (err)
433 return err;
434
435 err = check_user_mbz(&ext->mbz64);
436 if (err)
437 return err;
438
439 if (num_siblings == 0)
440 return 0;
441
442 siblings = kmalloc_array(num_siblings, sizeof(*siblings), GFP_KERNEL);
443 if (!siblings)
444 return -ENOMEM;
445
446 for (n = 0; n < num_siblings; n++) {
447 struct i915_engine_class_instance ci;
448
449 if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
450 err = -EFAULT;
451 goto err_siblings;
452 }
453
454 siblings[n] = intel_engine_lookup_user(i915,
455 ci.engine_class,
456 ci.engine_instance);
457 if (!siblings[n]) {
458 drm_dbg(&i915->drm,
459 "Invalid sibling[%d]: { class:%d, inst:%d }\n",
460 n, ci.engine_class, ci.engine_instance);
461 err = -EINVAL;
462 goto err_siblings;
463 }
464 }
465
466 if (num_siblings == 1) {
467 set->engines[idx].type = I915_GEM_ENGINE_TYPE_PHYSICAL;
468 set->engines[idx].engine = siblings[0];
469 kfree(siblings);
470 } else {
471 set->engines[idx].type = I915_GEM_ENGINE_TYPE_BALANCED;
472 set->engines[idx].num_siblings = num_siblings;
473 set->engines[idx].siblings = siblings;
474 }
475
476 return 0;
477
478 err_siblings:
479 kfree(siblings);
480
481 return err;
482 }
483
484 static int
set_proto_ctx_engines_bond(struct i915_user_extension __user * base,void * data)485 set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
486 {
487 struct i915_context_engines_bond __user *ext =
488 container_of_user(base, typeof(*ext), base);
489 const struct set_proto_ctx_engines *set = data;
490 struct drm_i915_private *i915 = set->i915;
491 struct i915_engine_class_instance ci;
492 struct intel_engine_cs *master;
493 u16 idx, num_bonds;
494 int err, n;
495
496 if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915) &&
497 !IS_ROCKETLAKE(i915) && !IS_ALDERLAKE_S(i915)) {
498 drm_dbg(&i915->drm,
499 "Bonding not supported on this platform\n");
500 return -ENODEV;
501 }
502
503 if (get_user(idx, &ext->virtual_index))
504 return -EFAULT;
505
506 if (idx >= set->num_engines) {
507 drm_dbg(&i915->drm,
508 "Invalid index for virtual engine: %d >= %d\n",
509 idx, set->num_engines);
510 return -EINVAL;
511 }
512
513 idx = array_index_nospec(idx, set->num_engines);
514 if (set->engines[idx].type == I915_GEM_ENGINE_TYPE_INVALID) {
515 drm_dbg(&i915->drm, "Invalid engine at %d\n", idx);
516 return -EINVAL;
517 }
518
519 if (set->engines[idx].type != I915_GEM_ENGINE_TYPE_PHYSICAL) {
520 drm_dbg(&i915->drm,
521 "Bonding with virtual engines not allowed\n");
522 return -EINVAL;
523 }
524
525 err = check_user_mbz(&ext->flags);
526 if (err)
527 return err;
528
529 for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
530 err = check_user_mbz(&ext->mbz64[n]);
531 if (err)
532 return err;
533 }
534
535 if (copy_from_user(&ci, &ext->master, sizeof(ci)))
536 return -EFAULT;
537
538 master = intel_engine_lookup_user(i915,
539 ci.engine_class,
540 ci.engine_instance);
541 if (!master) {
542 drm_dbg(&i915->drm,
543 "Unrecognised master engine: { class:%u, instance:%u }\n",
544 ci.engine_class, ci.engine_instance);
545 return -EINVAL;
546 }
547
548 if (intel_engine_uses_guc(master)) {
549 drm_dbg(&i915->drm, "bonding extension not supported with GuC submission");
550 return -ENODEV;
551 }
552
553 if (get_user(num_bonds, &ext->num_bonds))
554 return -EFAULT;
555
556 for (n = 0; n < num_bonds; n++) {
557 struct intel_engine_cs *bond;
558
559 if (copy_from_user(&ci, &ext->engines[n], sizeof(ci)))
560 return -EFAULT;
561
562 bond = intel_engine_lookup_user(i915,
563 ci.engine_class,
564 ci.engine_instance);
565 if (!bond) {
566 drm_dbg(&i915->drm,
567 "Unrecognised engine[%d] for bonding: { class:%d, instance: %d }\n",
568 n, ci.engine_class, ci.engine_instance);
569 return -EINVAL;
570 }
571 }
572
573 return 0;
574 }
575
576 static int
set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user * base,void * data)577 set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
578 void *data)
579 {
580 struct i915_context_engines_parallel_submit __user *ext =
581 container_of_user(base, typeof(*ext), base);
582 const struct set_proto_ctx_engines *set = data;
583 struct drm_i915_private *i915 = set->i915;
584 struct i915_engine_class_instance prev_engine;
585 u64 flags;
586 int err = 0, n, i, j;
587 u16 slot, width, num_siblings;
588 struct intel_engine_cs **siblings = NULL;
589 intel_engine_mask_t prev_mask;
590
591 if (get_user(slot, &ext->engine_index))
592 return -EFAULT;
593
594 if (get_user(width, &ext->width))
595 return -EFAULT;
596
597 if (get_user(num_siblings, &ext->num_siblings))
598 return -EFAULT;
599
600 if (!intel_uc_uses_guc_submission(&to_gt(i915)->uc) &&
601 num_siblings != 1) {
602 drm_dbg(&i915->drm, "Only 1 sibling (%d) supported in non-GuC mode\n",
603 num_siblings);
604 return -EINVAL;
605 }
606
607 if (slot >= set->num_engines) {
608 drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
609 slot, set->num_engines);
610 return -EINVAL;
611 }
612
613 if (set->engines[slot].type != I915_GEM_ENGINE_TYPE_INVALID) {
614 drm_dbg(&i915->drm,
615 "Invalid placement[%d], already occupied\n", slot);
616 return -EINVAL;
617 }
618
619 if (get_user(flags, &ext->flags))
620 return -EFAULT;
621
622 if (flags) {
623 drm_dbg(&i915->drm, "Unknown flags 0x%02llx", flags);
624 return -EINVAL;
625 }
626
627 for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
628 err = check_user_mbz(&ext->mbz64[n]);
629 if (err)
630 return err;
631 }
632
633 if (width < 2) {
634 drm_dbg(&i915->drm, "Width (%d) < 2\n", width);
635 return -EINVAL;
636 }
637
638 if (num_siblings < 1) {
639 drm_dbg(&i915->drm, "Number siblings (%d) < 1\n",
640 num_siblings);
641 return -EINVAL;
642 }
643
644 siblings = kmalloc_array(num_siblings * width,
645 sizeof(*siblings),
646 GFP_KERNEL);
647 if (!siblings)
648 return -ENOMEM;
649
650 /* Create contexts / engines */
651 for (i = 0; i < width; ++i) {
652 intel_engine_mask_t current_mask = 0;
653
654 for (j = 0; j < num_siblings; ++j) {
655 struct i915_engine_class_instance ci;
656
657 n = i * num_siblings + j;
658 if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
659 err = -EFAULT;
660 goto out_err;
661 }
662
663 siblings[n] =
664 intel_engine_lookup_user(i915, ci.engine_class,
665 ci.engine_instance);
666 if (!siblings[n]) {
667 drm_dbg(&i915->drm,
668 "Invalid sibling[%d]: { class:%d, inst:%d }\n",
669 n, ci.engine_class, ci.engine_instance);
670 err = -EINVAL;
671 goto out_err;
672 }
673
674 /*
675 * We don't support breadcrumb handshake on these
676 * classes
677 */
678 if (siblings[n]->class == RENDER_CLASS ||
679 siblings[n]->class == COMPUTE_CLASS) {
680 err = -EINVAL;
681 goto out_err;
682 }
683
684 if (n) {
685 if (prev_engine.engine_class !=
686 ci.engine_class) {
687 drm_dbg(&i915->drm,
688 "Mismatched class %d, %d\n",
689 prev_engine.engine_class,
690 ci.engine_class);
691 err = -EINVAL;
692 goto out_err;
693 }
694 }
695
696 prev_engine = ci;
697 current_mask |= siblings[n]->logical_mask;
698 }
699
700 if (i > 0) {
701 if (current_mask != prev_mask << 1) {
702 drm_dbg(&i915->drm,
703 "Non contiguous logical mask 0x%x, 0x%x\n",
704 prev_mask, current_mask);
705 err = -EINVAL;
706 goto out_err;
707 }
708 }
709 prev_mask = current_mask;
710 }
711
712 set->engines[slot].type = I915_GEM_ENGINE_TYPE_PARALLEL;
713 set->engines[slot].num_siblings = num_siblings;
714 set->engines[slot].width = width;
715 set->engines[slot].siblings = siblings;
716
717 return 0;
718
719 out_err:
720 kfree(siblings);
721
722 return err;
723 }
724
725 static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = {
726 [I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance,
727 [I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond,
728 [I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT] =
729 set_proto_ctx_engines_parallel_submit,
730 };
731
set_proto_ctx_engines(struct drm_i915_file_private * fpriv,struct i915_gem_proto_context * pc,const struct drm_i915_gem_context_param * args)732 static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv,
733 struct i915_gem_proto_context *pc,
734 const struct drm_i915_gem_context_param *args)
735 {
736 struct drm_i915_private *i915 = fpriv->dev_priv;
737 struct set_proto_ctx_engines set = { .i915 = i915 };
738 struct i915_context_param_engines __user *user =
739 u64_to_user_ptr(args->value);
740 unsigned int n;
741 u64 extensions;
742 int err;
743
744 if (pc->num_user_engines >= 0) {
745 drm_dbg(&i915->drm, "Cannot set engines twice");
746 return -EINVAL;
747 }
748
749 if (args->size < sizeof(*user) ||
750 !IS_ALIGNED(args->size - sizeof(*user), sizeof(*user->engines))) {
751 drm_dbg(&i915->drm, "Invalid size for engine array: %d\n",
752 args->size);
753 return -EINVAL;
754 }
755
756 set.num_engines = (args->size - sizeof(*user)) / sizeof(*user->engines);
757 /* RING_MASK has no shift so we can use it directly here */
758 if (set.num_engines > I915_EXEC_RING_MASK + 1)
759 return -EINVAL;
760
761 set.engines = kmalloc_array(set.num_engines, sizeof(*set.engines), GFP_KERNEL);
762 if (!set.engines)
763 return -ENOMEM;
764
765 for (n = 0; n < set.num_engines; n++) {
766 struct i915_engine_class_instance ci;
767 struct intel_engine_cs *engine;
768
769 if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) {
770 kfree(set.engines);
771 return -EFAULT;
772 }
773
774 memset(&set.engines[n], 0, sizeof(set.engines[n]));
775
776 if (ci.engine_class == (u16)I915_ENGINE_CLASS_INVALID &&
777 ci.engine_instance == (u16)I915_ENGINE_CLASS_INVALID_NONE)
778 continue;
779
780 engine = intel_engine_lookup_user(i915,
781 ci.engine_class,
782 ci.engine_instance);
783 if (!engine) {
784 drm_dbg(&i915->drm,
785 "Invalid engine[%d]: { class:%d, instance:%d }\n",
786 n, ci.engine_class, ci.engine_instance);
787 kfree(set.engines);
788 return -ENOENT;
789 }
790
791 set.engines[n].type = I915_GEM_ENGINE_TYPE_PHYSICAL;
792 set.engines[n].engine = engine;
793 }
794
795 err = -EFAULT;
796 if (!get_user(extensions, &user->extensions))
797 err = i915_user_extensions(u64_to_user_ptr(extensions),
798 set_proto_ctx_engines_extensions,
799 ARRAY_SIZE(set_proto_ctx_engines_extensions),
800 &set);
801 if (err) {
802 kfree(set.engines);
803 return err;
804 }
805
806 pc->num_user_engines = set.num_engines;
807 pc->user_engines = set.engines;
808
809 return 0;
810 }
811
set_proto_ctx_sseu(struct drm_i915_file_private * fpriv,struct i915_gem_proto_context * pc,struct drm_i915_gem_context_param * args)812 static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv,
813 struct i915_gem_proto_context *pc,
814 struct drm_i915_gem_context_param *args)
815 {
816 struct drm_i915_private *i915 = fpriv->dev_priv;
817 struct drm_i915_gem_context_param_sseu user_sseu;
818 struct intel_sseu *sseu;
819 int ret;
820
821 if (args->size < sizeof(user_sseu))
822 return -EINVAL;
823
824 if (GRAPHICS_VER(i915) != 11)
825 return -ENODEV;
826
827 if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
828 sizeof(user_sseu)))
829 return -EFAULT;
830
831 if (user_sseu.rsvd)
832 return -EINVAL;
833
834 if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
835 return -EINVAL;
836
837 if (!!(user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX) != (pc->num_user_engines >= 0))
838 return -EINVAL;
839
840 if (pc->num_user_engines >= 0) {
841 int idx = user_sseu.engine.engine_instance;
842 struct i915_gem_proto_engine *pe;
843
844 if (idx >= pc->num_user_engines)
845 return -EINVAL;
846
847 pe = &pc->user_engines[idx];
848
849 /* Only render engine supports RPCS configuration. */
850 if (pe->engine->class != RENDER_CLASS)
851 return -EINVAL;
852
853 sseu = &pe->sseu;
854 } else {
855 /* Only render engine supports RPCS configuration. */
856 if (user_sseu.engine.engine_class != I915_ENGINE_CLASS_RENDER)
857 return -EINVAL;
858
859 /* There is only one render engine */
860 if (user_sseu.engine.engine_instance != 0)
861 return -EINVAL;
862
863 sseu = &pc->legacy_rcs_sseu;
864 }
865
866 ret = i915_gem_user_to_context_sseu(to_gt(i915), &user_sseu, sseu);
867 if (ret)
868 return ret;
869
870 args->size = sizeof(user_sseu);
871
872 return 0;
873 }
874
set_proto_ctx_param(struct drm_i915_file_private * fpriv,struct i915_gem_proto_context * pc,struct drm_i915_gem_context_param * args)875 static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
876 struct i915_gem_proto_context *pc,
877 struct drm_i915_gem_context_param *args)
878 {
879 int ret = 0;
880
881 switch (args->param) {
882 case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
883 if (args->size)
884 ret = -EINVAL;
885 else if (args->value)
886 pc->user_flags |= BIT(UCONTEXT_NO_ERROR_CAPTURE);
887 else
888 pc->user_flags &= ~BIT(UCONTEXT_NO_ERROR_CAPTURE);
889 break;
890
891 case I915_CONTEXT_PARAM_BANNABLE:
892 if (args->size)
893 ret = -EINVAL;
894 else if (!capable(CAP_SYS_ADMIN) && !args->value)
895 ret = -EPERM;
896 else if (args->value)
897 pc->user_flags |= BIT(UCONTEXT_BANNABLE);
898 else if (pc->uses_protected_content)
899 ret = -EPERM;
900 else
901 pc->user_flags &= ~BIT(UCONTEXT_BANNABLE);
902 break;
903
904 case I915_CONTEXT_PARAM_RECOVERABLE:
905 if (args->size)
906 ret = -EINVAL;
907 else if (!args->value)
908 pc->user_flags &= ~BIT(UCONTEXT_RECOVERABLE);
909 else if (pc->uses_protected_content)
910 ret = -EPERM;
911 else
912 pc->user_flags |= BIT(UCONTEXT_RECOVERABLE);
913 break;
914
915 case I915_CONTEXT_PARAM_PRIORITY:
916 ret = validate_priority(fpriv->dev_priv, args);
917 if (!ret)
918 pc->sched.priority = args->value;
919 break;
920
921 case I915_CONTEXT_PARAM_SSEU:
922 ret = set_proto_ctx_sseu(fpriv, pc, args);
923 break;
924
925 case I915_CONTEXT_PARAM_VM:
926 ret = set_proto_ctx_vm(fpriv, pc, args);
927 break;
928
929 case I915_CONTEXT_PARAM_ENGINES:
930 ret = set_proto_ctx_engines(fpriv, pc, args);
931 break;
932
933 case I915_CONTEXT_PARAM_PERSISTENCE:
934 if (args->size)
935 ret = -EINVAL;
936 else
937 ret = proto_context_set_persistence(fpriv->dev_priv, pc,
938 args->value);
939 break;
940
941 case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
942 ret = proto_context_set_protected(fpriv->dev_priv, pc,
943 args->value);
944 break;
945
946 case I915_CONTEXT_PARAM_NO_ZEROMAP:
947 case I915_CONTEXT_PARAM_BAN_PERIOD:
948 case I915_CONTEXT_PARAM_RINGSIZE:
949 default:
950 ret = -EINVAL;
951 break;
952 }
953
954 return ret;
955 }
956
intel_context_set_gem(struct intel_context * ce,struct i915_gem_context * ctx,struct intel_sseu sseu)957 static int intel_context_set_gem(struct intel_context *ce,
958 struct i915_gem_context *ctx,
959 struct intel_sseu sseu)
960 {
961 int ret = 0;
962
963 GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
964 RCU_INIT_POINTER(ce->gem_context, ctx);
965
966 GEM_BUG_ON(intel_context_is_pinned(ce));
967 ce->ring_size = SZ_16K;
968
969 i915_vm_put(ce->vm);
970 ce->vm = i915_gem_context_get_eb_vm(ctx);
971
972 if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
973 intel_engine_has_timeslices(ce->engine) &&
974 intel_engine_has_semaphores(ce->engine))
975 __set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
976
977 if (CONFIG_DRM_I915_REQUEST_TIMEOUT &&
978 ctx->i915->params.request_timeout_ms) {
979 unsigned int timeout_ms = ctx->i915->params.request_timeout_ms;
980
981 intel_context_set_watchdog_us(ce, (u64)timeout_ms * 1000);
982 }
983
984 /* A valid SSEU has no zero fields */
985 if (sseu.slice_mask && !WARN_ON(ce->engine->class != RENDER_CLASS))
986 ret = intel_context_reconfigure_sseu(ce, sseu);
987
988 return ret;
989 }
990
__unpin_engines(struct i915_gem_engines * e,unsigned int count)991 static void __unpin_engines(struct i915_gem_engines *e, unsigned int count)
992 {
993 while (count--) {
994 struct intel_context *ce = e->engines[count], *child;
995
996 if (!ce || !test_bit(CONTEXT_PERMA_PIN, &ce->flags))
997 continue;
998
999 for_each_child(ce, child)
1000 intel_context_unpin(child);
1001 intel_context_unpin(ce);
1002 }
1003 }
1004
unpin_engines(struct i915_gem_engines * e)1005 static void unpin_engines(struct i915_gem_engines *e)
1006 {
1007 __unpin_engines(e, e->num_engines);
1008 }
1009
__free_engines(struct i915_gem_engines * e,unsigned int count)1010 static void __free_engines(struct i915_gem_engines *e, unsigned int count)
1011 {
1012 while (count--) {
1013 if (!e->engines[count])
1014 continue;
1015
1016 intel_context_put(e->engines[count]);
1017 }
1018 kfree(e);
1019 }
1020
free_engines(struct i915_gem_engines * e)1021 static void free_engines(struct i915_gem_engines *e)
1022 {
1023 __free_engines(e, e->num_engines);
1024 }
1025
free_engines_rcu(struct rcu_head * rcu)1026 static void free_engines_rcu(struct rcu_head *rcu)
1027 {
1028 struct i915_gem_engines *engines =
1029 container_of(rcu, struct i915_gem_engines, rcu);
1030
1031 i915_sw_fence_fini(&engines->fence);
1032 free_engines(engines);
1033 }
1034
accumulate_runtime(struct i915_drm_client * client,struct i915_gem_engines * engines)1035 static void accumulate_runtime(struct i915_drm_client *client,
1036 struct i915_gem_engines *engines)
1037 {
1038 struct i915_gem_engines_iter it;
1039 struct intel_context *ce;
1040
1041 if (!client)
1042 return;
1043
1044 /* Transfer accumulated runtime to the parent GEM context. */
1045 for_each_gem_engine(ce, engines, it) {
1046 unsigned int class = ce->engine->uabi_class;
1047
1048 GEM_BUG_ON(class >= ARRAY_SIZE(client->past_runtime));
1049 atomic64_add(intel_context_get_total_runtime_ns(ce),
1050 &client->past_runtime[class]);
1051 }
1052 }
1053
1054 static int
engines_notify(struct i915_sw_fence * fence,enum i915_sw_fence_notify state)1055 engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
1056 {
1057 struct i915_gem_engines *engines =
1058 container_of(fence, typeof(*engines), fence);
1059 struct i915_gem_context *ctx = engines->ctx;
1060
1061 switch (state) {
1062 case FENCE_COMPLETE:
1063 if (!list_empty(&engines->link)) {
1064 unsigned long flags;
1065
1066 spin_lock_irqsave(&ctx->stale.lock, flags);
1067 list_del(&engines->link);
1068 spin_unlock_irqrestore(&ctx->stale.lock, flags);
1069 }
1070 accumulate_runtime(ctx->client, engines);
1071 i915_gem_context_put(ctx);
1072
1073 break;
1074
1075 case FENCE_FREE:
1076 init_rcu_head(&engines->rcu);
1077 call_rcu(&engines->rcu, free_engines_rcu);
1078 break;
1079 }
1080
1081 return NOTIFY_DONE;
1082 }
1083
alloc_engines(unsigned int count)1084 static struct i915_gem_engines *alloc_engines(unsigned int count)
1085 {
1086 struct i915_gem_engines *e;
1087
1088 e = kzalloc(struct_size(e, engines, count), GFP_KERNEL);
1089 if (!e)
1090 return NULL;
1091
1092 i915_sw_fence_init(&e->fence, engines_notify);
1093 return e;
1094 }
1095
default_engines(struct i915_gem_context * ctx,struct intel_sseu rcs_sseu)1096 static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
1097 struct intel_sseu rcs_sseu)
1098 {
1099 const unsigned int max = I915_NUM_ENGINES;
1100 struct intel_engine_cs *engine;
1101 struct i915_gem_engines *e, *err;
1102
1103 e = alloc_engines(max);
1104 if (!e)
1105 return ERR_PTR(-ENOMEM);
1106
1107 for_each_uabi_engine(engine, ctx->i915) {
1108 struct intel_context *ce;
1109 struct intel_sseu sseu = {};
1110 int ret;
1111
1112 if (engine->legacy_idx == INVALID_ENGINE)
1113 continue;
1114
1115 GEM_BUG_ON(engine->legacy_idx >= max);
1116 GEM_BUG_ON(e->engines[engine->legacy_idx]);
1117
1118 ce = intel_context_create(engine);
1119 if (IS_ERR(ce)) {
1120 err = ERR_CAST(ce);
1121 goto free_engines;
1122 }
1123
1124 e->engines[engine->legacy_idx] = ce;
1125 e->num_engines = max(e->num_engines, engine->legacy_idx + 1);
1126
1127 if (engine->class == RENDER_CLASS)
1128 sseu = rcs_sseu;
1129
1130 ret = intel_context_set_gem(ce, ctx, sseu);
1131 if (ret) {
1132 err = ERR_PTR(ret);
1133 goto free_engines;
1134 }
1135
1136 }
1137
1138 return e;
1139
1140 free_engines:
1141 free_engines(e);
1142 return err;
1143 }
1144
perma_pin_contexts(struct intel_context * ce)1145 static int perma_pin_contexts(struct intel_context *ce)
1146 {
1147 struct intel_context *child;
1148 int i = 0, j = 0, ret;
1149
1150 GEM_BUG_ON(!intel_context_is_parent(ce));
1151
1152 ret = intel_context_pin(ce);
1153 if (unlikely(ret))
1154 return ret;
1155
1156 for_each_child(ce, child) {
1157 ret = intel_context_pin(child);
1158 if (unlikely(ret))
1159 goto unwind;
1160 ++i;
1161 }
1162
1163 set_bit(CONTEXT_PERMA_PIN, &ce->flags);
1164
1165 return 0;
1166
1167 unwind:
1168 intel_context_unpin(ce);
1169 for_each_child(ce, child) {
1170 if (j++ < i)
1171 intel_context_unpin(child);
1172 else
1173 break;
1174 }
1175
1176 return ret;
1177 }
1178
user_engines(struct i915_gem_context * ctx,unsigned int num_engines,struct i915_gem_proto_engine * pe)1179 static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
1180 unsigned int num_engines,
1181 struct i915_gem_proto_engine *pe)
1182 {
1183 struct i915_gem_engines *e, *err;
1184 unsigned int n;
1185
1186 e = alloc_engines(num_engines);
1187 if (!e)
1188 return ERR_PTR(-ENOMEM);
1189 e->num_engines = num_engines;
1190
1191 for (n = 0; n < num_engines; n++) {
1192 struct intel_context *ce, *child;
1193 int ret;
1194
1195 switch (pe[n].type) {
1196 case I915_GEM_ENGINE_TYPE_PHYSICAL:
1197 ce = intel_context_create(pe[n].engine);
1198 break;
1199
1200 case I915_GEM_ENGINE_TYPE_BALANCED:
1201 ce = intel_engine_create_virtual(pe[n].siblings,
1202 pe[n].num_siblings, 0);
1203 break;
1204
1205 case I915_GEM_ENGINE_TYPE_PARALLEL:
1206 ce = intel_engine_create_parallel(pe[n].siblings,
1207 pe[n].num_siblings,
1208 pe[n].width);
1209 break;
1210
1211 case I915_GEM_ENGINE_TYPE_INVALID:
1212 default:
1213 GEM_WARN_ON(pe[n].type != I915_GEM_ENGINE_TYPE_INVALID);
1214 continue;
1215 }
1216
1217 if (IS_ERR(ce)) {
1218 err = ERR_CAST(ce);
1219 goto free_engines;
1220 }
1221
1222 e->engines[n] = ce;
1223
1224 ret = intel_context_set_gem(ce, ctx, pe->sseu);
1225 if (ret) {
1226 err = ERR_PTR(ret);
1227 goto free_engines;
1228 }
1229 for_each_child(ce, child) {
1230 ret = intel_context_set_gem(child, ctx, pe->sseu);
1231 if (ret) {
1232 err = ERR_PTR(ret);
1233 goto free_engines;
1234 }
1235 }
1236
1237 /*
1238 * XXX: Must be done after calling intel_context_set_gem as that
1239 * function changes the ring size. The ring is allocated when
1240 * the context is pinned. If the ring size is changed after
1241 * allocation we have a mismatch of the ring size and will cause
1242 * the context to hang. Presumably with a bit of reordering we
1243 * could move the perma-pin step to the backend function
1244 * intel_engine_create_parallel.
1245 */
1246 if (pe[n].type == I915_GEM_ENGINE_TYPE_PARALLEL) {
1247 ret = perma_pin_contexts(ce);
1248 if (ret) {
1249 err = ERR_PTR(ret);
1250 goto free_engines;
1251 }
1252 }
1253 }
1254
1255 return e;
1256
1257 free_engines:
1258 free_engines(e);
1259 return err;
1260 }
1261
i915_gem_context_release_work(struct work_struct * work)1262 static void i915_gem_context_release_work(struct work_struct *work)
1263 {
1264 struct i915_gem_context *ctx = container_of(work, typeof(*ctx),
1265 release_work);
1266 struct i915_address_space *vm;
1267
1268 trace_i915_context_free(ctx);
1269 GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
1270
1271 spin_lock(&ctx->i915->gem.contexts.lock);
1272 list_del(&ctx->link);
1273 spin_unlock(&ctx->i915->gem.contexts.lock);
1274
1275 if (ctx->syncobj)
1276 drm_syncobj_put(ctx->syncobj);
1277
1278 vm = ctx->vm;
1279 if (vm)
1280 i915_vm_put(vm);
1281
1282 if (ctx->pxp_wakeref)
1283 intel_runtime_pm_put(&ctx->i915->runtime_pm, ctx->pxp_wakeref);
1284
1285 if (ctx->client)
1286 i915_drm_client_put(ctx->client);
1287
1288 mutex_destroy(&ctx->engines_mutex);
1289 mutex_destroy(&ctx->lut_mutex);
1290
1291 put_pid(ctx->pid);
1292 mutex_destroy(&ctx->mutex);
1293
1294 kfree_rcu(ctx, rcu);
1295 }
1296
i915_gem_context_release(struct kref * ref)1297 void i915_gem_context_release(struct kref *ref)
1298 {
1299 struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
1300
1301 queue_work(ctx->i915->wq, &ctx->release_work);
1302 }
1303
1304 static inline struct i915_gem_engines *
__context_engines_static(const struct i915_gem_context * ctx)1305 __context_engines_static(const struct i915_gem_context *ctx)
1306 {
1307 return rcu_dereference_protected(ctx->engines, true);
1308 }
1309
__reset_context(struct i915_gem_context * ctx,struct intel_engine_cs * engine)1310 static void __reset_context(struct i915_gem_context *ctx,
1311 struct intel_engine_cs *engine)
1312 {
1313 intel_gt_handle_error(engine->gt, engine->mask, 0,
1314 "context closure in %s", ctx->name);
1315 }
1316
__cancel_engine(struct intel_engine_cs * engine)1317 static bool __cancel_engine(struct intel_engine_cs *engine)
1318 {
1319 /*
1320 * Send a "high priority pulse" down the engine to cause the
1321 * current request to be momentarily preempted. (If it fails to
1322 * be preempted, it will be reset). As we have marked our context
1323 * as banned, any incomplete request, including any running, will
1324 * be skipped following the preemption.
1325 *
1326 * If there is no hangchecking (one of the reasons why we try to
1327 * cancel the context) and no forced preemption, there may be no
1328 * means by which we reset the GPU and evict the persistent hog.
1329 * Ergo if we are unable to inject a preemptive pulse that can
1330 * kill the banned context, we fallback to doing a local reset
1331 * instead.
1332 */
1333 return intel_engine_pulse(engine) == 0;
1334 }
1335
active_engine(struct intel_context * ce)1336 static struct intel_engine_cs *active_engine(struct intel_context *ce)
1337 {
1338 struct intel_engine_cs *engine = NULL;
1339 struct i915_request *rq;
1340
1341 if (intel_context_has_inflight(ce))
1342 return intel_context_inflight(ce);
1343
1344 if (!ce->timeline)
1345 return NULL;
1346
1347 /*
1348 * rq->link is only SLAB_TYPESAFE_BY_RCU, we need to hold a reference
1349 * to the request to prevent it being transferred to a new timeline
1350 * (and onto a new timeline->requests list).
1351 */
1352 rcu_read_lock();
1353 list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
1354 bool found;
1355
1356 /* timeline is already completed upto this point? */
1357 if (!i915_request_get_rcu(rq))
1358 break;
1359
1360 /* Check with the backend if the request is inflight */
1361 found = true;
1362 if (likely(rcu_access_pointer(rq->timeline) == ce->timeline))
1363 found = i915_request_active_engine(rq, &engine);
1364
1365 i915_request_put(rq);
1366 if (found)
1367 break;
1368 }
1369 rcu_read_unlock();
1370
1371 return engine;
1372 }
1373
1374 static void
kill_engines(struct i915_gem_engines * engines,bool exit,bool persistent)1375 kill_engines(struct i915_gem_engines *engines, bool exit, bool persistent)
1376 {
1377 struct i915_gem_engines_iter it;
1378 struct intel_context *ce;
1379
1380 /*
1381 * Map the user's engine back to the actual engines; one virtual
1382 * engine will be mapped to multiple engines, and using ctx->engine[]
1383 * the same engine may be have multiple instances in the user's map.
1384 * However, we only care about pending requests, so only include
1385 * engines on which there are incomplete requests.
1386 */
1387 for_each_gem_engine(ce, engines, it) {
1388 struct intel_engine_cs *engine;
1389
1390 if ((exit || !persistent) && intel_context_revoke(ce))
1391 continue; /* Already marked. */
1392
1393 /*
1394 * Check the current active state of this context; if we
1395 * are currently executing on the GPU we need to evict
1396 * ourselves. On the other hand, if we haven't yet been
1397 * submitted to the GPU or if everything is complete,
1398 * we have nothing to do.
1399 */
1400 engine = active_engine(ce);
1401
1402 /* First attempt to gracefully cancel the context */
1403 if (engine && !__cancel_engine(engine) && (exit || !persistent))
1404 /*
1405 * If we are unable to send a preemptive pulse to bump
1406 * the context from the GPU, we have to resort to a full
1407 * reset. We hope the collateral damage is worth it.
1408 */
1409 __reset_context(engines->ctx, engine);
1410 }
1411 }
1412
kill_context(struct i915_gem_context * ctx)1413 static void kill_context(struct i915_gem_context *ctx)
1414 {
1415 struct i915_gem_engines *pos, *next;
1416
1417 spin_lock_irq(&ctx->stale.lock);
1418 GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
1419 list_for_each_entry_safe(pos, next, &ctx->stale.engines, link) {
1420 if (!i915_sw_fence_await(&pos->fence)) {
1421 list_del_init(&pos->link);
1422 continue;
1423 }
1424
1425 spin_unlock_irq(&ctx->stale.lock);
1426
1427 kill_engines(pos, !ctx->i915->params.enable_hangcheck,
1428 i915_gem_context_is_persistent(ctx));
1429
1430 spin_lock_irq(&ctx->stale.lock);
1431 GEM_BUG_ON(i915_sw_fence_signaled(&pos->fence));
1432 list_safe_reset_next(pos, next, link);
1433 list_del_init(&pos->link); /* decouple from FENCE_COMPLETE */
1434
1435 i915_sw_fence_complete(&pos->fence);
1436 }
1437 spin_unlock_irq(&ctx->stale.lock);
1438 }
1439
engines_idle_release(struct i915_gem_context * ctx,struct i915_gem_engines * engines)1440 static void engines_idle_release(struct i915_gem_context *ctx,
1441 struct i915_gem_engines *engines)
1442 {
1443 struct i915_gem_engines_iter it;
1444 struct intel_context *ce;
1445
1446 INIT_LIST_HEAD(&engines->link);
1447
1448 engines->ctx = i915_gem_context_get(ctx);
1449
1450 for_each_gem_engine(ce, engines, it) {
1451 int err;
1452
1453 /* serialises with execbuf */
1454 intel_context_close(ce);
1455 if (!intel_context_pin_if_active(ce))
1456 continue;
1457
1458 /* Wait until context is finally scheduled out and retired */
1459 err = i915_sw_fence_await_active(&engines->fence,
1460 &ce->active,
1461 I915_ACTIVE_AWAIT_BARRIER);
1462 intel_context_unpin(ce);
1463 if (err)
1464 goto kill;
1465 }
1466
1467 spin_lock_irq(&ctx->stale.lock);
1468 if (!i915_gem_context_is_closed(ctx))
1469 list_add_tail(&engines->link, &ctx->stale.engines);
1470 spin_unlock_irq(&ctx->stale.lock);
1471
1472 kill:
1473 if (list_empty(&engines->link)) /* raced, already closed */
1474 kill_engines(engines, true,
1475 i915_gem_context_is_persistent(ctx));
1476
1477 i915_sw_fence_commit(&engines->fence);
1478 }
1479
set_closed_name(struct i915_gem_context * ctx)1480 static void set_closed_name(struct i915_gem_context *ctx)
1481 {
1482 char *s;
1483
1484 /* Replace '[]' with '<>' to indicate closed in debug prints */
1485
1486 s = strrchr(ctx->name, '[');
1487 if (!s)
1488 return;
1489
1490 *s = '<';
1491
1492 s = strchr(s + 1, ']');
1493 if (s)
1494 *s = '>';
1495 }
1496
context_close(struct i915_gem_context * ctx)1497 static void context_close(struct i915_gem_context *ctx)
1498 {
1499 struct i915_drm_client *client;
1500
1501 /* Flush any concurrent set_engines() */
1502 mutex_lock(&ctx->engines_mutex);
1503 unpin_engines(__context_engines_static(ctx));
1504 engines_idle_release(ctx, rcu_replace_pointer(ctx->engines, NULL, 1));
1505 i915_gem_context_set_closed(ctx);
1506 mutex_unlock(&ctx->engines_mutex);
1507
1508 mutex_lock(&ctx->mutex);
1509
1510 set_closed_name(ctx);
1511
1512 /*
1513 * The LUT uses the VMA as a backpointer to unref the object,
1514 * so we need to clear the LUT before we close all the VMA (inside
1515 * the ppgtt).
1516 */
1517 lut_close(ctx);
1518
1519 ctx->file_priv = ERR_PTR(-EBADF);
1520
1521 client = ctx->client;
1522 if (client) {
1523 spin_lock(&client->ctx_lock);
1524 list_del_rcu(&ctx->client_link);
1525 spin_unlock(&client->ctx_lock);
1526 }
1527
1528 mutex_unlock(&ctx->mutex);
1529
1530 /*
1531 * If the user has disabled hangchecking, we can not be sure that
1532 * the batches will ever complete after the context is closed,
1533 * keeping the context and all resources pinned forever. So in this
1534 * case we opt to forcibly kill off all remaining requests on
1535 * context close.
1536 */
1537 kill_context(ctx);
1538
1539 i915_gem_context_put(ctx);
1540 }
1541
__context_set_persistence(struct i915_gem_context * ctx,bool state)1542 static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
1543 {
1544 if (i915_gem_context_is_persistent(ctx) == state)
1545 return 0;
1546
1547 if (state) {
1548 /*
1549 * Only contexts that are short-lived [that will expire or be
1550 * reset] are allowed to survive past termination. We require
1551 * hangcheck to ensure that the persistent requests are healthy.
1552 */
1553 if (!ctx->i915->params.enable_hangcheck)
1554 return -EINVAL;
1555
1556 i915_gem_context_set_persistence(ctx);
1557 } else {
1558 /* To cancel a context we use "preempt-to-idle" */
1559 if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
1560 return -ENODEV;
1561
1562 /*
1563 * If the cancel fails, we then need to reset, cleanly!
1564 *
1565 * If the per-engine reset fails, all hope is lost! We resort
1566 * to a full GPU reset in that unlikely case, but realistically
1567 * if the engine could not reset, the full reset does not fare
1568 * much better. The damage has been done.
1569 *
1570 * However, if we cannot reset an engine by itself, we cannot
1571 * cleanup a hanging persistent context without causing
1572 * colateral damage, and we should not pretend we can by
1573 * exposing the interface.
1574 */
1575 if (!intel_has_reset_engine(to_gt(ctx->i915)))
1576 return -ENODEV;
1577
1578 i915_gem_context_clear_persistence(ctx);
1579 }
1580
1581 return 0;
1582 }
1583
1584 static struct i915_gem_context *
i915_gem_create_context(struct drm_i915_private * i915,const struct i915_gem_proto_context * pc)1585 i915_gem_create_context(struct drm_i915_private *i915,
1586 const struct i915_gem_proto_context *pc)
1587 {
1588 struct i915_gem_context *ctx;
1589 struct i915_address_space *vm = NULL;
1590 struct i915_gem_engines *e;
1591 int err;
1592 int i;
1593
1594 ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
1595 if (!ctx)
1596 return ERR_PTR(-ENOMEM);
1597
1598 kref_init(&ctx->ref);
1599 ctx->i915 = i915;
1600 ctx->sched = pc->sched;
1601 mutex_init(&ctx->mutex);
1602 INIT_LIST_HEAD(&ctx->link);
1603 INIT_WORK(&ctx->release_work, i915_gem_context_release_work);
1604
1605 spin_lock_init(&ctx->stale.lock);
1606 INIT_LIST_HEAD(&ctx->stale.engines);
1607
1608 if (pc->vm) {
1609 vm = i915_vm_get(pc->vm);
1610 } else if (HAS_FULL_PPGTT(i915)) {
1611 struct i915_ppgtt *ppgtt;
1612
1613 ppgtt = i915_ppgtt_create(to_gt(i915), 0);
1614 if (IS_ERR(ppgtt)) {
1615 drm_dbg(&i915->drm, "PPGTT setup failed (%ld)\n",
1616 PTR_ERR(ppgtt));
1617 err = PTR_ERR(ppgtt);
1618 goto err_ctx;
1619 }
1620 vm = &ppgtt->vm;
1621 }
1622 if (vm)
1623 ctx->vm = vm;
1624
1625 mutex_init(&ctx->engines_mutex);
1626 if (pc->num_user_engines >= 0) {
1627 i915_gem_context_set_user_engines(ctx);
1628 e = user_engines(ctx, pc->num_user_engines, pc->user_engines);
1629 } else {
1630 i915_gem_context_clear_user_engines(ctx);
1631 e = default_engines(ctx, pc->legacy_rcs_sseu);
1632 }
1633 if (IS_ERR(e)) {
1634 err = PTR_ERR(e);
1635 goto err_vm;
1636 }
1637 RCU_INIT_POINTER(ctx->engines, e);
1638
1639 INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
1640 mutex_init(&ctx->lut_mutex);
1641
1642 /* NB: Mark all slices as needing a remap so that when the context first
1643 * loads it will restore whatever remap state already exists. If there
1644 * is no remap info, it will be a NOP. */
1645 ctx->remap_slice = ALL_L3_SLICES(i915);
1646
1647 ctx->user_flags = pc->user_flags;
1648
1649 for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
1650 ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
1651
1652 if (pc->single_timeline) {
1653 err = drm_syncobj_create(&ctx->syncobj,
1654 DRM_SYNCOBJ_CREATE_SIGNALED,
1655 NULL);
1656 if (err)
1657 goto err_engines;
1658 }
1659
1660 if (pc->uses_protected_content) {
1661 ctx->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm);
1662 ctx->uses_protected_content = true;
1663 }
1664
1665 trace_i915_context_create(ctx);
1666
1667 return ctx;
1668
1669 err_engines:
1670 free_engines(e);
1671 err_vm:
1672 if (ctx->vm)
1673 i915_vm_put(ctx->vm);
1674 err_ctx:
1675 kfree(ctx);
1676 return ERR_PTR(err);
1677 }
1678
init_contexts(struct i915_gem_contexts * gc)1679 static void init_contexts(struct i915_gem_contexts *gc)
1680 {
1681 spin_lock_init(&gc->lock);
1682 INIT_LIST_HEAD(&gc->list);
1683 }
1684
i915_gem_init__contexts(struct drm_i915_private * i915)1685 void i915_gem_init__contexts(struct drm_i915_private *i915)
1686 {
1687 init_contexts(&i915->gem.contexts);
1688 }
1689
1690 /*
1691 * Note that this implicitly consumes the ctx reference, by placing
1692 * the ctx in the context_xa.
1693 */
gem_context_register(struct i915_gem_context * ctx,struct drm_i915_file_private * fpriv,u32 id)1694 static void gem_context_register(struct i915_gem_context *ctx,
1695 struct drm_i915_file_private *fpriv,
1696 u32 id)
1697 {
1698 struct drm_i915_private *i915 = ctx->i915;
1699 void *old;
1700
1701 ctx->file_priv = fpriv;
1702
1703 ctx->pid = get_task_pid(current, PIDTYPE_PID);
1704 ctx->client = i915_drm_client_get(fpriv->client);
1705
1706 snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
1707 current->comm, pid_nr(ctx->pid));
1708
1709 spin_lock(&ctx->client->ctx_lock);
1710 list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
1711 spin_unlock(&ctx->client->ctx_lock);
1712
1713 spin_lock(&i915->gem.contexts.lock);
1714 list_add_tail(&ctx->link, &i915->gem.contexts.list);
1715 spin_unlock(&i915->gem.contexts.lock);
1716
1717 /* And finally expose ourselves to userspace via the idr */
1718 old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
1719 WARN_ON(old);
1720 }
1721
i915_gem_context_open(struct drm_i915_private * i915,struct drm_file * file)1722 int i915_gem_context_open(struct drm_i915_private *i915,
1723 struct drm_file *file)
1724 {
1725 struct drm_i915_file_private *file_priv = file->driver_priv;
1726 struct i915_gem_proto_context *pc;
1727 struct i915_gem_context *ctx;
1728 int err;
1729
1730 mutex_init(&file_priv->proto_context_lock);
1731 xa_init_flags(&file_priv->proto_context_xa, XA_FLAGS_ALLOC);
1732
1733 /* 0 reserved for the default context */
1734 xa_init_flags(&file_priv->context_xa, XA_FLAGS_ALLOC1);
1735
1736 /* 0 reserved for invalid/unassigned ppgtt */
1737 xa_init_flags(&file_priv->vm_xa, XA_FLAGS_ALLOC1);
1738
1739 pc = proto_context_create(i915, 0);
1740 if (IS_ERR(pc)) {
1741 err = PTR_ERR(pc);
1742 goto err;
1743 }
1744
1745 ctx = i915_gem_create_context(i915, pc);
1746 proto_context_close(i915, pc);
1747 if (IS_ERR(ctx)) {
1748 err = PTR_ERR(ctx);
1749 goto err;
1750 }
1751
1752 gem_context_register(ctx, file_priv, 0);
1753
1754 return 0;
1755
1756 err:
1757 xa_destroy(&file_priv->vm_xa);
1758 xa_destroy(&file_priv->context_xa);
1759 xa_destroy(&file_priv->proto_context_xa);
1760 mutex_destroy(&file_priv->proto_context_lock);
1761 return err;
1762 }
1763
i915_gem_context_close(struct drm_file * file)1764 void i915_gem_context_close(struct drm_file *file)
1765 {
1766 struct drm_i915_file_private *file_priv = file->driver_priv;
1767 struct i915_gem_proto_context *pc;
1768 struct i915_address_space *vm;
1769 struct i915_gem_context *ctx;
1770 unsigned long idx;
1771
1772 xa_for_each(&file_priv->proto_context_xa, idx, pc)
1773 proto_context_close(file_priv->dev_priv, pc);
1774 xa_destroy(&file_priv->proto_context_xa);
1775 mutex_destroy(&file_priv->proto_context_lock);
1776
1777 xa_for_each(&file_priv->context_xa, idx, ctx)
1778 context_close(ctx);
1779 xa_destroy(&file_priv->context_xa);
1780
1781 xa_for_each(&file_priv->vm_xa, idx, vm)
1782 i915_vm_put(vm);
1783 xa_destroy(&file_priv->vm_xa);
1784 }
1785
i915_gem_vm_create_ioctl(struct drm_device * dev,void * data,struct drm_file * file)1786 int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
1787 struct drm_file *file)
1788 {
1789 struct drm_i915_private *i915 = to_i915(dev);
1790 struct drm_i915_gem_vm_control *args = data;
1791 struct drm_i915_file_private *file_priv = file->driver_priv;
1792 struct i915_ppgtt *ppgtt;
1793 u32 id;
1794 int err;
1795
1796 if (!HAS_FULL_PPGTT(i915))
1797 return -ENODEV;
1798
1799 if (args->flags)
1800 return -EINVAL;
1801
1802 ppgtt = i915_ppgtt_create(to_gt(i915), 0);
1803 if (IS_ERR(ppgtt))
1804 return PTR_ERR(ppgtt);
1805
1806 if (args->extensions) {
1807 err = i915_user_extensions(u64_to_user_ptr(args->extensions),
1808 NULL, 0,
1809 ppgtt);
1810 if (err)
1811 goto err_put;
1812 }
1813
1814 err = xa_alloc(&file_priv->vm_xa, &id, &ppgtt->vm,
1815 xa_limit_32b, GFP_KERNEL);
1816 if (err)
1817 goto err_put;
1818
1819 GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
1820 args->vm_id = id;
1821 return 0;
1822
1823 err_put:
1824 i915_vm_put(&ppgtt->vm);
1825 return err;
1826 }
1827
i915_gem_vm_destroy_ioctl(struct drm_device * dev,void * data,struct drm_file * file)1828 int i915_gem_vm_destroy_ioctl(struct drm_device *dev, void *data,
1829 struct drm_file *file)
1830 {
1831 struct drm_i915_file_private *file_priv = file->driver_priv;
1832 struct drm_i915_gem_vm_control *args = data;
1833 struct i915_address_space *vm;
1834
1835 if (args->flags)
1836 return -EINVAL;
1837
1838 if (args->extensions)
1839 return -EINVAL;
1840
1841 vm = xa_erase(&file_priv->vm_xa, args->vm_id);
1842 if (!vm)
1843 return -ENOENT;
1844
1845 i915_vm_put(vm);
1846 return 0;
1847 }
1848
get_ppgtt(struct drm_i915_file_private * file_priv,struct i915_gem_context * ctx,struct drm_i915_gem_context_param * args)1849 static int get_ppgtt(struct drm_i915_file_private *file_priv,
1850 struct i915_gem_context *ctx,
1851 struct drm_i915_gem_context_param *args)
1852 {
1853 struct i915_address_space *vm;
1854 int err;
1855 u32 id;
1856
1857 if (!i915_gem_context_has_full_ppgtt(ctx))
1858 return -ENODEV;
1859
1860 vm = ctx->vm;
1861 GEM_BUG_ON(!vm);
1862
1863 /*
1864 * Get a reference for the allocated handle. Once the handle is
1865 * visible in the vm_xa table, userspace could try to close it
1866 * from under our feet, so we need to hold the extra reference
1867 * first.
1868 */
1869 i915_vm_get(vm);
1870
1871 err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL);
1872 if (err) {
1873 i915_vm_put(vm);
1874 return err;
1875 }
1876
1877 GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
1878 args->value = id;
1879 args->size = 0;
1880
1881 return err;
1882 }
1883
1884 int
i915_gem_user_to_context_sseu(struct intel_gt * gt,const struct drm_i915_gem_context_param_sseu * user,struct intel_sseu * context)1885 i915_gem_user_to_context_sseu(struct intel_gt *gt,
1886 const struct drm_i915_gem_context_param_sseu *user,
1887 struct intel_sseu *context)
1888 {
1889 const struct sseu_dev_info *device = >->info.sseu;
1890 struct drm_i915_private *i915 = gt->i915;
1891 unsigned int dev_subslice_mask = intel_sseu_get_hsw_subslices(device, 0);
1892
1893 /* No zeros in any field. */
1894 if (!user->slice_mask || !user->subslice_mask ||
1895 !user->min_eus_per_subslice || !user->max_eus_per_subslice)
1896 return -EINVAL;
1897
1898 /* Max > min. */
1899 if (user->max_eus_per_subslice < user->min_eus_per_subslice)
1900 return -EINVAL;
1901
1902 /*
1903 * Some future proofing on the types since the uAPI is wider than the
1904 * current internal implementation.
1905 */
1906 if (overflows_type(user->slice_mask, context->slice_mask) ||
1907 overflows_type(user->subslice_mask, context->subslice_mask) ||
1908 overflows_type(user->min_eus_per_subslice,
1909 context->min_eus_per_subslice) ||
1910 overflows_type(user->max_eus_per_subslice,
1911 context->max_eus_per_subslice))
1912 return -EINVAL;
1913
1914 /* Check validity against hardware. */
1915 if (user->slice_mask & ~device->slice_mask)
1916 return -EINVAL;
1917
1918 if (user->subslice_mask & ~dev_subslice_mask)
1919 return -EINVAL;
1920
1921 if (user->max_eus_per_subslice > device->max_eus_per_subslice)
1922 return -EINVAL;
1923
1924 context->slice_mask = user->slice_mask;
1925 context->subslice_mask = user->subslice_mask;
1926 context->min_eus_per_subslice = user->min_eus_per_subslice;
1927 context->max_eus_per_subslice = user->max_eus_per_subslice;
1928
1929 /* Part specific restrictions. */
1930 if (GRAPHICS_VER(i915) == 11) {
1931 unsigned int hw_s = hweight8(device->slice_mask);
1932 unsigned int hw_ss_per_s = hweight8(dev_subslice_mask);
1933 unsigned int req_s = hweight8(context->slice_mask);
1934 unsigned int req_ss = hweight8(context->subslice_mask);
1935
1936 /*
1937 * Only full subslice enablement is possible if more than one
1938 * slice is turned on.
1939 */
1940 if (req_s > 1 && req_ss != hw_ss_per_s)
1941 return -EINVAL;
1942
1943 /*
1944 * If more than four (SScount bitfield limit) subslices are
1945 * requested then the number has to be even.
1946 */
1947 if (req_ss > 4 && (req_ss & 1))
1948 return -EINVAL;
1949
1950 /*
1951 * If only one slice is enabled and subslice count is below the
1952 * device full enablement, it must be at most half of the all
1953 * available subslices.
1954 */
1955 if (req_s == 1 && req_ss < hw_ss_per_s &&
1956 req_ss > (hw_ss_per_s / 2))
1957 return -EINVAL;
1958
1959 /* ABI restriction - VME use case only. */
1960
1961 /* All slices or one slice only. */
1962 if (req_s != 1 && req_s != hw_s)
1963 return -EINVAL;
1964
1965 /*
1966 * Half subslices or full enablement only when one slice is
1967 * enabled.
1968 */
1969 if (req_s == 1 &&
1970 (req_ss != hw_ss_per_s && req_ss != (hw_ss_per_s / 2)))
1971 return -EINVAL;
1972
1973 /* No EU configuration changes. */
1974 if ((user->min_eus_per_subslice !=
1975 device->max_eus_per_subslice) ||
1976 (user->max_eus_per_subslice !=
1977 device->max_eus_per_subslice))
1978 return -EINVAL;
1979 }
1980
1981 return 0;
1982 }
1983
set_sseu(struct i915_gem_context * ctx,struct drm_i915_gem_context_param * args)1984 static int set_sseu(struct i915_gem_context *ctx,
1985 struct drm_i915_gem_context_param *args)
1986 {
1987 struct drm_i915_private *i915 = ctx->i915;
1988 struct drm_i915_gem_context_param_sseu user_sseu;
1989 struct intel_context *ce;
1990 struct intel_sseu sseu;
1991 unsigned long lookup;
1992 int ret;
1993
1994 if (args->size < sizeof(user_sseu))
1995 return -EINVAL;
1996
1997 if (GRAPHICS_VER(i915) != 11)
1998 return -ENODEV;
1999
2000 if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
2001 sizeof(user_sseu)))
2002 return -EFAULT;
2003
2004 if (user_sseu.rsvd)
2005 return -EINVAL;
2006
2007 if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
2008 return -EINVAL;
2009
2010 lookup = 0;
2011 if (user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX)
2012 lookup |= LOOKUP_USER_INDEX;
2013
2014 ce = lookup_user_engine(ctx, lookup, &user_sseu.engine);
2015 if (IS_ERR(ce))
2016 return PTR_ERR(ce);
2017
2018 /* Only render engine supports RPCS configuration. */
2019 if (ce->engine->class != RENDER_CLASS) {
2020 ret = -ENODEV;
2021 goto out_ce;
2022 }
2023
2024 ret = i915_gem_user_to_context_sseu(ce->engine->gt, &user_sseu, &sseu);
2025 if (ret)
2026 goto out_ce;
2027
2028 ret = intel_context_reconfigure_sseu(ce, sseu);
2029 if (ret)
2030 goto out_ce;
2031
2032 args->size = sizeof(user_sseu);
2033
2034 out_ce:
2035 intel_context_put(ce);
2036 return ret;
2037 }
2038
2039 static int
set_persistence(struct i915_gem_context * ctx,const struct drm_i915_gem_context_param * args)2040 set_persistence(struct i915_gem_context *ctx,
2041 const struct drm_i915_gem_context_param *args)
2042 {
2043 if (args->size)
2044 return -EINVAL;
2045
2046 return __context_set_persistence(ctx, args->value);
2047 }
2048
set_priority(struct i915_gem_context * ctx,const struct drm_i915_gem_context_param * args)2049 static int set_priority(struct i915_gem_context *ctx,
2050 const struct drm_i915_gem_context_param *args)
2051 {
2052 struct i915_gem_engines_iter it;
2053 struct intel_context *ce;
2054 int err;
2055
2056 err = validate_priority(ctx->i915, args);
2057 if (err)
2058 return err;
2059
2060 ctx->sched.priority = args->value;
2061
2062 for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
2063 if (!intel_engine_has_timeslices(ce->engine))
2064 continue;
2065
2066 if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
2067 intel_engine_has_semaphores(ce->engine))
2068 intel_context_set_use_semaphores(ce);
2069 else
2070 intel_context_clear_use_semaphores(ce);
2071 }
2072 i915_gem_context_unlock_engines(ctx);
2073
2074 return 0;
2075 }
2076
get_protected(struct i915_gem_context * ctx,struct drm_i915_gem_context_param * args)2077 static int get_protected(struct i915_gem_context *ctx,
2078 struct drm_i915_gem_context_param *args)
2079 {
2080 args->size = 0;
2081 args->value = i915_gem_context_uses_protected_content(ctx);
2082
2083 return 0;
2084 }
2085
ctx_setparam(struct drm_i915_file_private * fpriv,struct i915_gem_context * ctx,struct drm_i915_gem_context_param * args)2086 static int ctx_setparam(struct drm_i915_file_private *fpriv,
2087 struct i915_gem_context *ctx,
2088 struct drm_i915_gem_context_param *args)
2089 {
2090 int ret = 0;
2091
2092 switch (args->param) {
2093 case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
2094 if (args->size)
2095 ret = -EINVAL;
2096 else if (args->value)
2097 i915_gem_context_set_no_error_capture(ctx);
2098 else
2099 i915_gem_context_clear_no_error_capture(ctx);
2100 break;
2101
2102 case I915_CONTEXT_PARAM_BANNABLE:
2103 if (args->size)
2104 ret = -EINVAL;
2105 else if (!capable(CAP_SYS_ADMIN) && !args->value)
2106 ret = -EPERM;
2107 else if (args->value)
2108 i915_gem_context_set_bannable(ctx);
2109 else if (i915_gem_context_uses_protected_content(ctx))
2110 ret = -EPERM; /* can't clear this for protected contexts */
2111 else
2112 i915_gem_context_clear_bannable(ctx);
2113 break;
2114
2115 case I915_CONTEXT_PARAM_RECOVERABLE:
2116 if (args->size)
2117 ret = -EINVAL;
2118 else if (!args->value)
2119 i915_gem_context_clear_recoverable(ctx);
2120 else if (i915_gem_context_uses_protected_content(ctx))
2121 ret = -EPERM; /* can't set this for protected contexts */
2122 else
2123 i915_gem_context_set_recoverable(ctx);
2124 break;
2125
2126 case I915_CONTEXT_PARAM_PRIORITY:
2127 ret = set_priority(ctx, args);
2128 break;
2129
2130 case I915_CONTEXT_PARAM_SSEU:
2131 ret = set_sseu(ctx, args);
2132 break;
2133
2134 case I915_CONTEXT_PARAM_PERSISTENCE:
2135 ret = set_persistence(ctx, args);
2136 break;
2137
2138 case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
2139 case I915_CONTEXT_PARAM_NO_ZEROMAP:
2140 case I915_CONTEXT_PARAM_BAN_PERIOD:
2141 case I915_CONTEXT_PARAM_RINGSIZE:
2142 case I915_CONTEXT_PARAM_VM:
2143 case I915_CONTEXT_PARAM_ENGINES:
2144 default:
2145 ret = -EINVAL;
2146 break;
2147 }
2148
2149 return ret;
2150 }
2151
2152 struct create_ext {
2153 struct i915_gem_proto_context *pc;
2154 struct drm_i915_file_private *fpriv;
2155 };
2156
create_setparam(struct i915_user_extension __user * ext,void * data)2157 static int create_setparam(struct i915_user_extension __user *ext, void *data)
2158 {
2159 struct drm_i915_gem_context_create_ext_setparam local;
2160 const struct create_ext *arg = data;
2161
2162 if (copy_from_user(&local, ext, sizeof(local)))
2163 return -EFAULT;
2164
2165 if (local.param.ctx_id)
2166 return -EINVAL;
2167
2168 return set_proto_ctx_param(arg->fpriv, arg->pc, &local.param);
2169 }
2170
invalid_ext(struct i915_user_extension __user * ext,void * data)2171 static int invalid_ext(struct i915_user_extension __user *ext, void *data)
2172 {
2173 return -EINVAL;
2174 }
2175
2176 static const i915_user_extension_fn create_extensions[] = {
2177 [I915_CONTEXT_CREATE_EXT_SETPARAM] = create_setparam,
2178 [I915_CONTEXT_CREATE_EXT_CLONE] = invalid_ext,
2179 };
2180
client_is_banned(struct drm_i915_file_private * file_priv)2181 static bool client_is_banned(struct drm_i915_file_private *file_priv)
2182 {
2183 return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
2184 }
2185
2186 static inline struct i915_gem_context *
__context_lookup(struct drm_i915_file_private * file_priv,u32 id)2187 __context_lookup(struct drm_i915_file_private *file_priv, u32 id)
2188 {
2189 struct i915_gem_context *ctx;
2190
2191 rcu_read_lock();
2192 ctx = xa_load(&file_priv->context_xa, id);
2193 if (ctx && !kref_get_unless_zero(&ctx->ref))
2194 ctx = NULL;
2195 rcu_read_unlock();
2196
2197 return ctx;
2198 }
2199
2200 static struct i915_gem_context *
finalize_create_context_locked(struct drm_i915_file_private * file_priv,struct i915_gem_proto_context * pc,u32 id)2201 finalize_create_context_locked(struct drm_i915_file_private *file_priv,
2202 struct i915_gem_proto_context *pc, u32 id)
2203 {
2204 struct i915_gem_context *ctx;
2205 void *old;
2206
2207 lockdep_assert_held(&file_priv->proto_context_lock);
2208
2209 ctx = i915_gem_create_context(file_priv->dev_priv, pc);
2210 if (IS_ERR(ctx))
2211 return ctx;
2212
2213 /*
2214 * One for the xarray and one for the caller. We need to grab
2215 * the reference *prior* to making the ctx visble to userspace
2216 * in gem_context_register(), as at any point after that
2217 * userspace can try to race us with another thread destroying
2218 * the context under our feet.
2219 */
2220 i915_gem_context_get(ctx);
2221
2222 gem_context_register(ctx, file_priv, id);
2223
2224 old = xa_erase(&file_priv->proto_context_xa, id);
2225 GEM_BUG_ON(old != pc);
2226 proto_context_close(file_priv->dev_priv, pc);
2227
2228 return ctx;
2229 }
2230
2231 struct i915_gem_context *
i915_gem_context_lookup(struct drm_i915_file_private * file_priv,u32 id)2232 i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
2233 {
2234 struct i915_gem_proto_context *pc;
2235 struct i915_gem_context *ctx;
2236
2237 ctx = __context_lookup(file_priv, id);
2238 if (ctx)
2239 return ctx;
2240
2241 mutex_lock(&file_priv->proto_context_lock);
2242 /* Try one more time under the lock */
2243 ctx = __context_lookup(file_priv, id);
2244 if (!ctx) {
2245 pc = xa_load(&file_priv->proto_context_xa, id);
2246 if (!pc)
2247 ctx = ERR_PTR(-ENOENT);
2248 else
2249 ctx = finalize_create_context_locked(file_priv, pc, id);
2250 }
2251 mutex_unlock(&file_priv->proto_context_lock);
2252
2253 return ctx;
2254 }
2255
i915_gem_context_create_ioctl(struct drm_device * dev,void * data,struct drm_file * file)2256 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
2257 struct drm_file *file)
2258 {
2259 struct drm_i915_private *i915 = to_i915(dev);
2260 struct drm_i915_gem_context_create_ext *args = data;
2261 struct create_ext ext_data;
2262 int ret;
2263 u32 id;
2264
2265 if (!DRIVER_CAPS(i915)->has_logical_contexts)
2266 return -ENODEV;
2267
2268 if (args->flags & I915_CONTEXT_CREATE_FLAGS_UNKNOWN)
2269 return -EINVAL;
2270
2271 ret = intel_gt_terminally_wedged(to_gt(i915));
2272 if (ret)
2273 return ret;
2274
2275 ext_data.fpriv = file->driver_priv;
2276 if (client_is_banned(ext_data.fpriv)) {
2277 drm_dbg(&i915->drm,
2278 "client %s[%d] banned from creating ctx\n",
2279 current->comm, task_pid_nr(current));
2280 return -EIO;
2281 }
2282
2283 ext_data.pc = proto_context_create(i915, args->flags);
2284 if (IS_ERR(ext_data.pc))
2285 return PTR_ERR(ext_data.pc);
2286
2287 if (args->flags & I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS) {
2288 ret = i915_user_extensions(u64_to_user_ptr(args->extensions),
2289 create_extensions,
2290 ARRAY_SIZE(create_extensions),
2291 &ext_data);
2292 if (ret)
2293 goto err_pc;
2294 }
2295
2296 if (GRAPHICS_VER(i915) > 12) {
2297 struct i915_gem_context *ctx;
2298
2299 /* Get ourselves a context ID */
2300 ret = xa_alloc(&ext_data.fpriv->context_xa, &id, NULL,
2301 xa_limit_32b, GFP_KERNEL);
2302 if (ret)
2303 goto err_pc;
2304
2305 ctx = i915_gem_create_context(i915, ext_data.pc);
2306 if (IS_ERR(ctx)) {
2307 ret = PTR_ERR(ctx);
2308 goto err_pc;
2309 }
2310
2311 proto_context_close(i915, ext_data.pc);
2312 gem_context_register(ctx, ext_data.fpriv, id);
2313 } else {
2314 ret = proto_context_register(ext_data.fpriv, ext_data.pc, &id);
2315 if (ret < 0)
2316 goto err_pc;
2317 }
2318
2319 args->ctx_id = id;
2320
2321 return 0;
2322
2323 err_pc:
2324 proto_context_close(i915, ext_data.pc);
2325 return ret;
2326 }
2327
i915_gem_context_destroy_ioctl(struct drm_device * dev,void * data,struct drm_file * file)2328 int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
2329 struct drm_file *file)
2330 {
2331 struct drm_i915_gem_context_destroy *args = data;
2332 struct drm_i915_file_private *file_priv = file->driver_priv;
2333 struct i915_gem_proto_context *pc;
2334 struct i915_gem_context *ctx;
2335
2336 if (args->pad != 0)
2337 return -EINVAL;
2338
2339 if (!args->ctx_id)
2340 return -ENOENT;
2341
2342 /* We need to hold the proto-context lock here to prevent races
2343 * with finalize_create_context_locked().
2344 */
2345 mutex_lock(&file_priv->proto_context_lock);
2346 ctx = xa_erase(&file_priv->context_xa, args->ctx_id);
2347 pc = xa_erase(&file_priv->proto_context_xa, args->ctx_id);
2348 mutex_unlock(&file_priv->proto_context_lock);
2349
2350 if (!ctx && !pc)
2351 return -ENOENT;
2352 GEM_WARN_ON(ctx && pc);
2353
2354 if (pc)
2355 proto_context_close(file_priv->dev_priv, pc);
2356
2357 if (ctx)
2358 context_close(ctx);
2359
2360 return 0;
2361 }
2362
get_sseu(struct i915_gem_context * ctx,struct drm_i915_gem_context_param * args)2363 static int get_sseu(struct i915_gem_context *ctx,
2364 struct drm_i915_gem_context_param *args)
2365 {
2366 struct drm_i915_gem_context_param_sseu user_sseu;
2367 struct intel_context *ce;
2368 unsigned long lookup;
2369 int err;
2370
2371 if (args->size == 0)
2372 goto out;
2373 else if (args->size < sizeof(user_sseu))
2374 return -EINVAL;
2375
2376 if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
2377 sizeof(user_sseu)))
2378 return -EFAULT;
2379
2380 if (user_sseu.rsvd)
2381 return -EINVAL;
2382
2383 if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
2384 return -EINVAL;
2385
2386 lookup = 0;
2387 if (user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX)
2388 lookup |= LOOKUP_USER_INDEX;
2389
2390 ce = lookup_user_engine(ctx, lookup, &user_sseu.engine);
2391 if (IS_ERR(ce))
2392 return PTR_ERR(ce);
2393
2394 err = intel_context_lock_pinned(ce); /* serialises with set_sseu */
2395 if (err) {
2396 intel_context_put(ce);
2397 return err;
2398 }
2399
2400 user_sseu.slice_mask = ce->sseu.slice_mask;
2401 user_sseu.subslice_mask = ce->sseu.subslice_mask;
2402 user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice;
2403 user_sseu.max_eus_per_subslice = ce->sseu.max_eus_per_subslice;
2404
2405 intel_context_unlock_pinned(ce);
2406 intel_context_put(ce);
2407
2408 if (copy_to_user(u64_to_user_ptr(args->value), &user_sseu,
2409 sizeof(user_sseu)))
2410 return -EFAULT;
2411
2412 out:
2413 args->size = sizeof(user_sseu);
2414
2415 return 0;
2416 }
2417
i915_gem_context_getparam_ioctl(struct drm_device * dev,void * data,struct drm_file * file)2418 int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
2419 struct drm_file *file)
2420 {
2421 struct drm_i915_file_private *file_priv = file->driver_priv;
2422 struct drm_i915_gem_context_param *args = data;
2423 struct i915_gem_context *ctx;
2424 struct i915_address_space *vm;
2425 int ret = 0;
2426
2427 ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
2428 if (IS_ERR(ctx))
2429 return PTR_ERR(ctx);
2430
2431 switch (args->param) {
2432 case I915_CONTEXT_PARAM_GTT_SIZE:
2433 args->size = 0;
2434 vm = i915_gem_context_get_eb_vm(ctx);
2435 args->value = vm->total;
2436 i915_vm_put(vm);
2437
2438 break;
2439
2440 case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
2441 args->size = 0;
2442 args->value = i915_gem_context_no_error_capture(ctx);
2443 break;
2444
2445 case I915_CONTEXT_PARAM_BANNABLE:
2446 args->size = 0;
2447 args->value = i915_gem_context_is_bannable(ctx);
2448 break;
2449
2450 case I915_CONTEXT_PARAM_RECOVERABLE:
2451 args->size = 0;
2452 args->value = i915_gem_context_is_recoverable(ctx);
2453 break;
2454
2455 case I915_CONTEXT_PARAM_PRIORITY:
2456 args->size = 0;
2457 args->value = ctx->sched.priority;
2458 break;
2459
2460 case I915_CONTEXT_PARAM_SSEU:
2461 ret = get_sseu(ctx, args);
2462 break;
2463
2464 case I915_CONTEXT_PARAM_VM:
2465 ret = get_ppgtt(file_priv, ctx, args);
2466 break;
2467
2468 case I915_CONTEXT_PARAM_PERSISTENCE:
2469 args->size = 0;
2470 args->value = i915_gem_context_is_persistent(ctx);
2471 break;
2472
2473 case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
2474 ret = get_protected(ctx, args);
2475 break;
2476
2477 case I915_CONTEXT_PARAM_NO_ZEROMAP:
2478 case I915_CONTEXT_PARAM_BAN_PERIOD:
2479 case I915_CONTEXT_PARAM_ENGINES:
2480 case I915_CONTEXT_PARAM_RINGSIZE:
2481 default:
2482 ret = -EINVAL;
2483 break;
2484 }
2485
2486 i915_gem_context_put(ctx);
2487 return ret;
2488 }
2489
i915_gem_context_setparam_ioctl(struct drm_device * dev,void * data,struct drm_file * file)2490 int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
2491 struct drm_file *file)
2492 {
2493 struct drm_i915_file_private *file_priv = file->driver_priv;
2494 struct drm_i915_gem_context_param *args = data;
2495 struct i915_gem_proto_context *pc;
2496 struct i915_gem_context *ctx;
2497 int ret = 0;
2498
2499 mutex_lock(&file_priv->proto_context_lock);
2500 ctx = __context_lookup(file_priv, args->ctx_id);
2501 if (!ctx) {
2502 pc = xa_load(&file_priv->proto_context_xa, args->ctx_id);
2503 if (pc) {
2504 /* Contexts should be finalized inside
2505 * GEM_CONTEXT_CREATE starting with graphics
2506 * version 13.
2507 */
2508 WARN_ON(GRAPHICS_VER(file_priv->dev_priv) > 12);
2509 ret = set_proto_ctx_param(file_priv, pc, args);
2510 } else {
2511 ret = -ENOENT;
2512 }
2513 }
2514 mutex_unlock(&file_priv->proto_context_lock);
2515
2516 if (ctx) {
2517 ret = ctx_setparam(file_priv, ctx, args);
2518 i915_gem_context_put(ctx);
2519 }
2520
2521 return ret;
2522 }
2523
i915_gem_context_reset_stats_ioctl(struct drm_device * dev,void * data,struct drm_file * file)2524 int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
2525 void *data, struct drm_file *file)
2526 {
2527 struct drm_i915_private *i915 = to_i915(dev);
2528 struct drm_i915_reset_stats *args = data;
2529 struct i915_gem_context *ctx;
2530
2531 if (args->flags || args->pad)
2532 return -EINVAL;
2533
2534 ctx = i915_gem_context_lookup(file->driver_priv, args->ctx_id);
2535 if (IS_ERR(ctx))
2536 return PTR_ERR(ctx);
2537
2538 /*
2539 * We opt for unserialised reads here. This may result in tearing
2540 * in the extremely unlikely event of a GPU hang on this context
2541 * as we are querying them. If we need that extra layer of protection,
2542 * we should wrap the hangstats with a seqlock.
2543 */
2544
2545 if (capable(CAP_SYS_ADMIN))
2546 args->reset_count = i915_reset_count(&i915->gpu_error);
2547 else
2548 args->reset_count = 0;
2549
2550 args->batch_active = atomic_read(&ctx->guilty_count);
2551 args->batch_pending = atomic_read(&ctx->active_count);
2552
2553 i915_gem_context_put(ctx);
2554 return 0;
2555 }
2556
2557 /* GEM context-engines iterator: for_each_gem_engine() */
2558 struct intel_context *
i915_gem_engines_iter_next(struct i915_gem_engines_iter * it)2559 i915_gem_engines_iter_next(struct i915_gem_engines_iter *it)
2560 {
2561 const struct i915_gem_engines *e = it->engines;
2562 struct intel_context *ctx;
2563
2564 if (unlikely(!e))
2565 return NULL;
2566
2567 do {
2568 if (it->idx >= e->num_engines)
2569 return NULL;
2570
2571 ctx = e->engines[it->idx++];
2572 } while (!ctx);
2573
2574 return ctx;
2575 }
2576
2577 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
2578 #include "selftests/mock_context.c"
2579 #include "selftests/i915_gem_context.c"
2580 #endif
2581
i915_gem_context_module_exit(void)2582 void i915_gem_context_module_exit(void)
2583 {
2584 kmem_cache_destroy(slab_luts);
2585 }
2586
i915_gem_context_module_init(void)2587 int __init i915_gem_context_module_init(void)
2588 {
2589 slab_luts = KMEM_CACHE(i915_lut_handle, 0);
2590 if (!slab_luts)
2591 return -ENOMEM;
2592
2593 return 0;
2594 }
2595