summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_gem_request.h
blob: d229f47d1028bb615675f846ecbd46a43ae17197 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
/*
 * Copyright © 2008-2015 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 */

#ifndef I915_GEM_REQUEST_H
#define I915_GEM_REQUEST_H

#include <linux/dma-fence.h>

#include "i915_gem.h"
#include "i915_sw_fence.h"

struct drm_file;
struct drm_i915_gem_object;

struct intel_wait {
	struct rb_node node;
	struct task_struct *tsk;
	u32 seqno;
};

struct intel_signal_node {
	struct rb_node node;
	struct intel_wait wait;
};

struct i915_dependency {
	struct i915_priotree *signaler;
	struct list_head signal_link;
	struct list_head wait_link;
	struct list_head dfs_link;
	unsigned long flags;
#define I915_DEPENDENCY_ALLOC BIT(0)
};

/* Requests exist in a complex web of interdependencies. Each request
 * has to wait for some other request to complete before it is ready to be run
 * (e.g. we have to wait until the pixels have been rendering into a texture
 * before we can copy from it). We track the readiness of a request in terms
 * of fences, but we also need to keep the dependency tree for the lifetime
 * of the request (beyond the life of an individual fence). We use the tree
 * at various points to reorder the requests whilst keeping the requests
 * in order with respect to their various dependencies.
 */
struct i915_priotree {
	struct list_head signalers_list; /* those before us, we depend upon */
	struct list_head waiters_list; /* those after us, they depend upon us */
	struct rb_node node;
	int priority;
#define I915_PRIORITY_MAX 1024
#define I915_PRIORITY_MIN (-I915_PRIORITY_MAX)
};

/**
 * Request queue structure.
 *
 * The request queue allows us to note sequence numbers that have been emitted
 * and may be associated with active buffers to be retired.
 *
 * By keeping this list, we can avoid having to do questionable sequence
 * number comparisons on buffer last_read|write_seqno. It also allows an
 * emission time to be associated with the request for tracking how far ahead
 * of the GPU the submission is.
 *
 * When modifying this structure be very aware that we perform a lockless
 * RCU lookup of it that may race against reallocation of the struct
 * from the slab freelist. We intentionally do not zero the structure on
 * allocation so that the lookup can use the dangling pointers (and is
 * cogniscent that those pointers may be wrong). Instead, everything that
 * needs to be initialised must be done so explicitly.
 *
 * The requests are reference counted.
 */
struct drm_i915_gem_request {
	struct dma_fence fence;
	spinlock_t lock;

	/** On Which ring this request was generated */
	struct drm_i915_private *i915;

	/**
	 * Context and ring buffer related to this request
	 * Contexts are refcounted, so when this request is associated with a
	 * context, we must increment the context's refcount, to guarantee that
	 * it persists while any request is linked to it. Requests themselves
	 * are also refcounted, so the request will only be freed when the last
	 * reference to it is dismissed, and the code in
	 * i915_gem_request_free() will then decrement the refcount on the
	 * context.
	 */
	struct i915_gem_context *ctx;
	struct intel_engine_cs *engine;
	struct intel_ring *ring;
	struct intel_timeline *timeline;
	struct intel_signal_node signaling;

	/* Fences for the various phases in the request's lifetime.
	 *
	 * The submit fence is used to await upon all of the request's
	 * dependencies. When it is signaled, the request is ready to run.
	 * It is used by the driver to then queue the request for execution.
	 *
	 * The execute fence is used to signal when the request has been
	 * sent to hardware.
	 *
	 * It is illegal for the submit fence of one request to wait upon the
	 * execute fence of an earlier request. It should be sufficient to
	 * wait upon the submit fence of the earlier request.
	 */
	struct i915_sw_fence submit;
	struct i915_sw_fence execute;
	wait_queue_t submitq;
	wait_queue_t execq;

	/* A list of everyone we wait upon, and everyone who waits upon us.
	 * Even though we will not be submitted to the hardware before the
	 * submit fence is signaled (it waits for all external events as well
	 * as our own requests), the scheduler still needs to know the
	 * dependency tree for the lifetime of the request (from execbuf
	 * to retirement), i.e. bidirectional dependency information for the
	 * request not tied to individual fences.
	 */
	struct i915_priotree priotree;
	struct i915_dependency dep;

	u32 global_seqno;

	/** GEM sequence number associated with the previous request,
	 * when the HWS breadcrumb is equal to this the GPU is processing
	 * this request.
	 */
	u32 previous_seqno;

	/** Position in the ring of the start of the request */
	u32 head;

	/**
	 * Position in the ring of the start of the postfix.
	 * This is required to calculate the maximum available ring space
	 * without overwriting the postfix.
	 */
	u32 postfix;

	/** Position in the ring of the end of the whole request */
	u32 tail;

	/** Position in the ring of the end of any workarounds after the tail */
	u32 wa_tail;

	/** Preallocate space in the ring for the emitting the request */
	u32 reserved_space;

	/**
	 * Context related to the previous request.
	 * As the contexts are accessed by the hardware until the switch is
	 * completed to a new context, the hardware may still be writing
	 * to the context object after the breadcrumb is visible. We must
	 * not unpin/unbind/prune that object whilst still active and so
	 * we keep the previous context pinned until the following (this)
	 * request is retired.
	 */
	struct i915_gem_context *previous_context;

	/** Batch buffer related to this request if any (used for
	 * error state dump only).
	 */
	struct i915_vma *batch;
	struct list_head active_list;

	/** Time at which this request was emitted, in jiffies. */
	unsigned long emitted_jiffies;

	/** engine->request_list entry for this request */
	struct list_head link;

	/** ring->request_list entry for this request */
	struct list_head ring_link;

	struct drm_i915_file_private *file_priv;
	/** file_priv list entry for this request */
	struct list_head client_list;
};

extern const struct dma_fence_ops i915_fence_ops;

static inline bool dma_fence_is_i915(const struct dma_fence *fence)
{
	return fence->ops == &i915_fence_ops;
}

struct drm_i915_gem_request * __must_check
i915_gem_request_alloc(struct intel_engine_cs *engine,
		       struct i915_gem_context *ctx);
int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
				   struct drm_file *file);
void i915_gem_request_retire_upto(struct drm_i915_gem_request *req);

static inline struct drm_i915_gem_request *
to_request(struct dma_fence *fence)
{
	/* We assume that NULL fence/request are interoperable */
	BUILD_BUG_ON(offsetof(struct drm_i915_gem_request, fence) != 0);
	GEM_BUG_ON(fence && !dma_fence_is_i915(fence));
	return container_of(fence, struct drm_i915_gem_request, fence);
}

static inline struct drm_i915_gem_request *
i915_gem_request_get(struct drm_i915_gem_request *req)
{
	return to_request(dma_fence_get(&req->fence));
}

static inline struct drm_i915_gem_request *
i915_gem_request_get_rcu(struct drm_i915_gem_request *req)
{
	return to_request(dma_fence_get_rcu(&req->fence));
}

static inline void
i915_gem_request_put(struct drm_i915_gem_request *req)
{
	dma_fence_put(&req->fence);
}

static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
					   struct drm_i915_gem_request *src)
{
	if (src)
		i915_gem_request_get(src);

	if (*pdst)
		i915_gem_request_put(*pdst);

	*pdst = src;
}

int
i915_gem_request_await_object(struct drm_i915_gem_request *to,
			      struct drm_i915_gem_object *obj,
			      bool write);
int i915_gem_request_await_dma_fence(struct drm_i915_gem_request *req,
				     struct dma_fence *fence);

void __i915_add_request(struct drm_i915_gem_request *req, bool flush_caches);
#define i915_add_request(req) \
	__i915_add_request(req, true)
#define i915_add_request_no_flush(req) \
	__i915_add_request(req, false)

void __i915_gem_request_submit(struct drm_i915_gem_request *request);
void i915_gem_request_submit(struct drm_i915_gem_request *request);

struct intel_rps_client;
#define NO_WAITBOOST ERR_PTR(-1)
#define IS_RPS_CLIENT(p) (!IS_ERR(p))
#define IS_RPS_USER(p) (!IS_ERR_OR_NULL(p))

long i915_wait_request(struct drm_i915_gem_request *req,
		       unsigned int flags,
		       long timeout)
	__attribute__((nonnull(1)));
#define I915_WAIT_INTERRUPTIBLE	BIT(0)
#define I915_WAIT_LOCKED	BIT(1) /* struct_mutex held, handle GPU reset */
#define I915_WAIT_ALL		BIT(2) /* used by i915_gem_object_wait() */

static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine);

/**
 * Returns true if seq1 is later than seq2.
 */
static inline bool i915_seqno_passed(u32 seq1, u32 seq2)
{
	return (s32)(seq1 - seq2) >= 0;
}

static inline bool
__i915_gem_request_started(const struct drm_i915_gem_request *req)
{
	GEM_BUG_ON(!req->global_seqno);
	return i915_seqno_passed(intel_engine_get_seqno(req->engine),
				 req->previous_seqno);
}

static inline bool
i915_gem_request_started(const struct drm_i915_gem_request *req)
{
	if (!req->global_seqno)
		return false;

	return __i915_gem_request_started(req);
}

static inline bool
__i915_gem_request_completed(const struct drm_i915_gem_request *req)
{
	GEM_BUG_ON(!req->global_seqno);
	return i915_seqno_passed(intel_engine_get_seqno(req->engine),
				 req->global_seqno);
}

static inline bool
i915_gem_request_completed(const struct drm_i915_gem_request *req)
{
	if (!req->global_seqno)
		return false;

	return __i915_gem_request_completed(req);
}

bool __i915_spin_request(const struct drm_i915_gem_request *request,
			 int state, unsigned long timeout_us);
static inline bool i915_spin_request(const struct drm_i915_gem_request *request,
				     int state, unsigned long timeout_us)
{
	return (__i915_gem_request_started(request) &&
		__i915_spin_request(request, state, timeout_us));
}

/* We treat requests as fences. This is not be to confused with our
 * "fence registers" but pipeline synchronisation objects ala GL_ARB_sync.
 * We use the fences to synchronize access from the CPU with activity on the
 * GPU, for example, we should not rewrite an object's PTE whilst the GPU
 * is reading them. We also track fences at a higher level to provide
 * implicit synchronisation around GEM objects, e.g. set-domain will wait
 * for outstanding GPU rendering before marking the object ready for CPU
 * access, or a pageflip will wait until the GPU is complete before showing
 * the frame on the scanout.
 *
 * In order to use a fence, the object must track the fence it needs to
 * serialise with. For example, GEM objects want to track both read and
 * write access so that we can perform concurrent read operations between
 * the CPU and GPU engines, as well as waiting for all rendering to
 * complete, or waiting for the last GPU user of a "fence register". The
 * object then embeds a #i915_gem_active to track the most recent (in
 * retirement order) request relevant for the desired mode of access.
 * The #i915_gem_active is updated with i915_gem_active_set() to track the
 * most recent fence request, typically this is done as part of
 * i915_vma_move_to_active().
 *
 * When the #i915_gem_active completes (is retired), it will
 * signal its completion to the owner through a callback as well as mark
 * itself as idle (i915_gem_active.request == NULL). The owner
 * can then perform any action, such as delayed freeing of an active
 * resource including itself.
 */
struct i915_gem_active;

typedef void (*i915_gem_retire_fn)(struct i915_gem_active *,
				   struct drm_i915_gem_request *);

struct i915_gem_active {
	struct drm_i915_gem_request __rcu *request;
	struct list_head link;
	i915_gem_retire_fn retire;
};

void i915_gem_retire_noop(struct i915_gem_active *,
			  struct drm_i915_gem_request *request);

/**
 * init_request_active - prepares the activity tracker for use
 * @active - the active tracker
 * @func - a callback when then the tracker is retired (becomes idle),
 *         can be NULL
 *
 * init_request_active() prepares the embedded @active struct for use as
 * an activity tracker, that is for tracking the last known active request
 * associated with it. When the last request becomes idle, when it is retired
 * after completion, the optional callback @func is invoked.
 */
static inline void
init_request_active(struct i915_gem_active *active,
		    i915_gem_retire_fn retire)
{
	INIT_LIST_HEAD(&active->link);
	active->retire = retire ?: i915_gem_retire_noop;
}

/**
 * i915_gem_active_set - updates the tracker to watch the current request
 * @active - the active tracker
 * @request - the request to watch
 *
 * i915_gem_active_set() watches the given @request for completion. Whilst
 * that @request is busy, the @active reports busy. When that @request is
 * retired, the @active tracker is updated to report idle.
 */
static inline void
i915_gem_active_set(struct i915_gem_active *active,
		    struct drm_i915_gem_request *request)
{
	list_move(&active->link, &request->active_list);
	rcu_assign_pointer(active->request, request);
}

/**
 * i915_gem_active_set_retire_fn - updates the retirement callback
 * @active - the active tracker
 * @fn - the routine called when the request is retired
 * @mutex - struct_mutex used to guard retirements
 *
 * i915_gem_active_set_retire_fn() updates the function pointer that
 * is called when the final request associated with the @active tracker
 * is retired.
 */
static inline void
i915_gem_active_set_retire_fn(struct i915_gem_active *active,
			      i915_gem_retire_fn fn,
			      struct mutex *mutex)
{
	lockdep_assert_held(mutex);
	active->retire = fn ?: i915_gem_retire_noop;
}

static inline struct drm_i915_gem_request *
__i915_gem_active_peek(const struct i915_gem_active *active)
{
	/* Inside the error capture (running with the driver in an unknown
	 * state), we want to bend the rules slightly (a lot).
	 *
	 * Work is in progress to make it safer, in the meantime this keeps
	 * the known issue from spamming the logs.
	 */
	return rcu_dereference_protected(active->request, 1);
}

/**
 * i915_gem_active_raw - return the active request
 * @active - the active tracker
 *
 * i915_gem_active_raw() returns the current request being tracked, or NULL.
 * It does not obtain a reference on the request for the caller, so the caller
 * must hold struct_mutex.
 */
static inline struct drm_i915_gem_request *
i915_gem_active_raw(const struct i915_gem_active *active, struct mutex *mutex)
{
	return rcu_dereference_protected(active->request,
					 lockdep_is_held(mutex));
}

/**
 * i915_gem_active_peek - report the active request being monitored
 * @active - the active tracker
 *
 * i915_gem_active_peek() returns the current request being tracked if
 * still active, or NULL. It does not obtain a reference on the request
 * for the caller, so the caller must hold struct_mutex.
 */
static inline struct drm_i915_gem_request *
i915_gem_active_peek(const struct i915_gem_active *active, struct mutex *mutex)
{
	struct drm_i915_gem_request *request;

	request = i915_gem_active_raw(active, mutex);
	if (!request || i915_gem_request_completed(request))
		return NULL;

	return request;
}

/**
 * i915_gem_active_get - return a reference to the active request
 * @active - the active tracker
 *
 * i915_gem_active_get() returns a reference to the active request, or NULL
 * if the active tracker is idle. The caller must hold struct_mutex.
 */
static inline struct drm_i915_gem_request *
i915_gem_active_get(const struct i915_gem_active *active, struct mutex *mutex)
{
	return i915_gem_request_get(i915_gem_active_peek(active, mutex));
}

/**
 * __i915_gem_active_get_rcu - return a reference to the active request
 * @active - the active tracker
 *
 * __i915_gem_active_get() returns a reference to the active request, or NULL
 * if the active tracker is idle. The caller must hold the RCU read lock, but
 * the returned pointer is safe to use outside of RCU.
 */
static inline struct drm_i915_gem_request *
__i915_gem_active_get_rcu(const struct i915_gem_active *active)
{
	/* Performing a lockless retrieval of the active request is super
	 * tricky. SLAB_DESTROY_BY_RCU merely guarantees that the backing
	 * slab of request objects will not be freed whilst we hold the
	 * RCU read lock. It does not guarantee that the request itself
	 * will not be freed and then *reused*. Viz,
	 *
	 * Thread A			Thread B
	 *
	 * req = active.request
	 *				retire(req) -> free(req);
	 *				(req is now first on the slab freelist)
	 *				active.request = NULL
	 *
	 *				req = new submission on a new object
	 * ref(req)
	 *
	 * To prevent the request from being reused whilst the caller
	 * uses it, we take a reference like normal. Whilst acquiring
	 * the reference we check that it is not in a destroyed state
	 * (refcnt == 0). That prevents the request being reallocated
	 * whilst the caller holds on to it. To check that the request
	 * was not reallocated as we acquired the reference we have to
	 * check that our request remains the active request across
	 * the lookup, in the same manner as a seqlock. The visibility
	 * of the pointer versus the reference counting is controlled
	 * by using RCU barriers (rcu_dereference and rcu_assign_pointer).
	 *
	 * In the middle of all that, we inspect whether the request is
	 * complete. Retiring is lazy so the request may be completed long
	 * before the active tracker is updated. Querying whether the
	 * request is complete is far cheaper (as it involves no locked
	 * instructions setting cachelines to exclusive) than acquiring
	 * the reference, so we do it first. The RCU read lock ensures the
	 * pointer dereference is valid, but does not ensure that the
	 * seqno nor HWS is the right one! However, if the request was
	 * reallocated, that means the active tracker's request was complete.
	 * If the new request is also complete, then both are and we can
	 * just report the active tracker is idle. If the new request is
	 * incomplete, then we acquire a reference on it and check that
	 * it remained the active request.
	 *
	 * It is then imperative that we do not zero the request on
	 * reallocation, so that we can chase the dangling pointers!
	 * See i915_gem_request_alloc().
	 */
	do {
		struct drm_i915_gem_request *request;

		request = rcu_dereference(active->request);
		if (!request || i915_gem_request_completed(request))
			return NULL;

		/* An especially silly compiler could decide to recompute the
		 * result of i915_gem_request_completed, more specifically
		 * re-emit the load for request->fence.seqno. A race would catch
		 * a later seqno value, which could flip the result from true to
		 * false. Which means part of the instructions below might not
		 * be executed, while later on instructions are executed. Due to
		 * barriers within the refcounting the inconsistency can't reach
		 * past the call to i915_gem_request_get_rcu, but not executing
		 * that while still executing i915_gem_request_put() creates
		 * havoc enough.  Prevent this with a compiler barrier.
		 */
		barrier();

		request = i915_gem_request_get_rcu(request);

		/* What stops the following rcu_access_pointer() from occurring
		 * before the above i915_gem_request_get_rcu()? If we were
		 * to read the value before pausing to get the reference to
		 * the request, we may not notice a change in the active
		 * tracker.
		 *
		 * The rcu_access_pointer() is a mere compiler barrier, which
		 * means both the CPU and compiler are free to perform the
		 * memory read without constraint. The compiler only has to
		 * ensure that any operations after the rcu_access_pointer()
		 * occur afterwards in program order. This means the read may
		 * be performed earlier by an out-of-order CPU, or adventurous
		 * compiler.
		 *
		 * The atomic operation at the heart of
		 * i915_gem_request_get_rcu(), see dma_fence_get_rcu(), is
		 * atomic_inc_not_zero() which is only a full memory barrier
		 * when successful. That is, if i915_gem_request_get_rcu()
		 * returns the request (and so with the reference counted
		 * incremented) then the following read for rcu_access_pointer()
		 * must occur after the atomic operation and so confirm
		 * that this request is the one currently being tracked.
		 *
		 * The corresponding write barrier is part of
		 * rcu_assign_pointer().
		 */
		if (!request || request == rcu_access_pointer(active->request))
			return rcu_pointer_handoff(request);

		i915_gem_request_put(request);
	} while (1);
}

/**
 * i915_gem_active_get_unlocked - return a reference to the active request
 * @active - the active tracker
 *
 * i915_gem_active_get_unlocked() returns a reference to the active request,
 * or NULL if the active tracker is idle. The reference is obtained under RCU,
 * so no locking is required by the caller.
 *
 * The reference should be freed with i915_gem_request_put().
 */
static inline struct drm_i915_gem_request *
i915_gem_active_get_unlocked(const struct i915_gem_active *active)
{
	struct drm_i915_gem_request *request;

	rcu_read_lock();
	request = __i915_gem_active_get_rcu(active);
	rcu_read_unlock();

	return request;
}

/**
 * i915_gem_active_isset - report whether the active tracker is assigned
 * @active - the active tracker
 *
 * i915_gem_active_isset() returns true if the active tracker is currently
 * assigned to a request. Due to the lazy retiring, that request may be idle
 * and this may report stale information.
 */
static inline bool
i915_gem_active_isset(const struct i915_gem_active *active)
{
	return rcu_access_pointer(active->request);
}

/**
 * i915_gem_active_wait - waits until the request is completed
 * @active - the active request on which to wait
 * @flags - how to wait
 * @timeout - how long to wait at most
 * @rps - userspace client to charge for a waitboost
 *
 * i915_gem_active_wait() waits until the request is completed before
 * returning, without requiring any locks to be held. Note that it does not
 * retire any requests before returning.
 *
 * This function relies on RCU in order to acquire the reference to the active
 * request without holding any locks. See __i915_gem_active_get_rcu() for the
 * glory details on how that is managed. Once the reference is acquired, we
 * can then wait upon the request, and afterwards release our reference,
 * free of any locking.
 *
 * This function wraps i915_wait_request(), see it for the full details on
 * the arguments.
 *
 * Returns 0 if successful, or a negative error code.
 */
static inline int
i915_gem_active_wait(const struct i915_gem_active *active, unsigned int flags)
{
	struct drm_i915_gem_request *request;
	long ret = 0;

	request = i915_gem_active_get_unlocked(active);
	if (request) {
		ret = i915_wait_request(request, flags, MAX_SCHEDULE_TIMEOUT);
		i915_gem_request_put(request);
	}

	return ret < 0 ? ret : 0;
}

/**
 * i915_gem_active_retire - waits until the request is retired
 * @active - the active request on which to wait
 *
 * i915_gem_active_retire() waits until the request is completed,
 * and then ensures that at least the retirement handler for this
 * @active tracker is called before returning. If the @active
 * tracker is idle, the function returns immediately.
 */
static inline int __must_check
i915_gem_active_retire(struct i915_gem_active *active,
		       struct mutex *mutex)
{
	struct drm_i915_gem_request *request;
	long ret;

	request = i915_gem_active_raw(active, mutex);
	if (!request)
		return 0;

	ret = i915_wait_request(request,
				I915_WAIT_INTERRUPTIBLE | I915_WAIT_LOCKED,
				MAX_SCHEDULE_TIMEOUT);
	if (ret < 0)
		return ret;

	list_del_init(&active->link);
	RCU_INIT_POINTER(active->request, NULL);

	active->retire(active, request);

	return 0;
}

#define for_each_active(mask, idx) \
	for (; mask ? idx = ffs(mask) - 1, 1 : 0; mask &= ~BIT(idx))

#endif /* I915_GEM_REQUEST_H */