summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
blob: 38cc42783dfb2f35417fceb3c19fa6366d1b2b07 (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
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2015-2021 Intel Corporation
 */

#include <linux/kthread.h>
#include <trace/events/dma_fence.h>
#include <uapi/linux/sched/types.h>

#include "i915_drv.h"
#include "i915_trace.h"
#include "intel_breadcrumbs.h"
#include "intel_context.h"
#include "intel_engine_pm.h"
#include "intel_gt_pm.h"
#include "intel_gt_requests.h"

static bool irq_enable(struct intel_engine_cs *engine)
{
	if (!engine->irq_enable)
		return false;

	/* Caller disables interrupts */
	spin_lock(&engine->gt->irq_lock);
	engine->irq_enable(engine);
	spin_unlock(&engine->gt->irq_lock);

	return true;
}

static void irq_disable(struct intel_engine_cs *engine)
{
	if (!engine->irq_disable)
		return;

	/* Caller disables interrupts */
	spin_lock(&engine->gt->irq_lock);
	engine->irq_disable(engine);
	spin_unlock(&engine->gt->irq_lock);
}

static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
{
	/*
	 * Since we are waiting on a request, the GPU should be busy
	 * and should have its own rpm reference.
	 */
	if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt)))
		return;

	/*
	 * The breadcrumb irq will be disarmed on the interrupt after the
	 * waiters are signaled. This gives us a single interrupt window in
	 * which we can add a new waiter and avoid the cost of re-enabling
	 * the irq.
	 */
	WRITE_ONCE(b->irq_armed, true);

	/* Requests may have completed before we could enable the interrupt. */
	if (!b->irq_enabled++ && irq_enable(b->irq_engine))
		irq_work_queue(&b->irq_work);
}

static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
{
	if (!b->irq_engine)
		return;

	spin_lock(&b->irq_lock);
	if (!b->irq_armed)
		__intel_breadcrumbs_arm_irq(b);
	spin_unlock(&b->irq_lock);
}

static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
{
	GEM_BUG_ON(!b->irq_enabled);
	if (!--b->irq_enabled)
		irq_disable(b->irq_engine);

	WRITE_ONCE(b->irq_armed, false);
	intel_gt_pm_put_async(b->irq_engine->gt);
}

static void intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
{
	spin_lock(&b->irq_lock);
	if (b->irq_armed)
		__intel_breadcrumbs_disarm_irq(b);
	spin_unlock(&b->irq_lock);
}

static void add_signaling_context(struct intel_breadcrumbs *b,
				  struct intel_context *ce)
{
	lockdep_assert_held(&ce->signal_lock);

	spin_lock(&b->signalers_lock);
	list_add_rcu(&ce->signal_link, &b->signalers);
	spin_unlock(&b->signalers_lock);
}

static bool remove_signaling_context(struct intel_breadcrumbs *b,
				     struct intel_context *ce)
{
	lockdep_assert_held(&ce->signal_lock);

	if (!list_empty(&ce->signals))
		return false;

	spin_lock(&b->signalers_lock);
	list_del_rcu(&ce->signal_link);
	spin_unlock(&b->signalers_lock);

	return true;
}

__maybe_unused static bool
check_signal_order(struct intel_context *ce, struct i915_request *rq)
{
	if (rq->context != ce)
		return false;

	if (!list_is_last(&rq->signal_link, &ce->signals) &&
	    i915_seqno_passed(rq->fence.seqno,
			      list_next_entry(rq, signal_link)->fence.seqno))
		return false;

	if (!list_is_first(&rq->signal_link, &ce->signals) &&
	    i915_seqno_passed(list_prev_entry(rq, signal_link)->fence.seqno,
			      rq->fence.seqno))
		return false;

	return true;
}

static bool
__dma_fence_signal(struct dma_fence *fence)
{
	return !test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
}

static void
__dma_fence_signal__timestamp(struct dma_fence *fence, ktime_t timestamp)
{
	fence->timestamp = timestamp;
	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
	trace_dma_fence_signaled(fence);
}

static void
__dma_fence_signal__notify(struct dma_fence *fence,
			   const struct list_head *list)
{
	struct dma_fence_cb *cur, *tmp;

	lockdep_assert_held(fence->lock);

	list_for_each_entry_safe(cur, tmp, list, node) {
		INIT_LIST_HEAD(&cur->node);
		cur->func(fence, cur);
	}
}

static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
{
	if (b->irq_engine)
		intel_engine_add_retire(b->irq_engine, tl);
}

static struct llist_node *
slist_add(struct llist_node *node, struct llist_node *head)
{
	node->next = head;
	return node;
}

static void signal_irq_work(struct irq_work *work)
{
	struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work);
	const ktime_t timestamp = ktime_get();
	struct llist_node *signal, *sn;
	struct intel_context *ce;

	signal = NULL;
	if (unlikely(!llist_empty(&b->signaled_requests)))
		signal = llist_del_all(&b->signaled_requests);

	/*
	 * Keep the irq armed until the interrupt after all listeners are gone.
	 *
	 * Enabling/disabling the interrupt is rather costly, roughly a couple
	 * of hundred microseconds. If we are proactive and enable/disable
	 * the interrupt around every request that wants a breadcrumb, we
	 * quickly drown in the extra orders of magnitude of latency imposed
	 * on request submission.
	 *
	 * So we try to be lazy, and keep the interrupts enabled until no
	 * more listeners appear within a breadcrumb interrupt interval (that
	 * is until a request completes that no one cares about). The
	 * observation is that listeners come in batches, and will often
	 * listen to a bunch of requests in succession. Though note on icl+,
	 * interrupts are always enabled due to concerns with rc6 being
	 * dysfunctional with per-engine interrupt masking.
	 *
	 * We also try to avoid raising too many interrupts, as they may
	 * be generated by userspace batches and it is unfortunately rather
	 * too easy to drown the CPU under a flood of GPU interrupts. Thus
	 * whenever no one appears to be listening, we turn off the interrupts.
	 * Fewer interrupts should conserve power -- at the very least, fewer
	 * interrupt draw less ire from other users of the system and tools
	 * like powertop.
	 */
	if (!signal && READ_ONCE(b->irq_armed) && list_empty(&b->signalers))
		intel_breadcrumbs_disarm_irq(b);

	rcu_read_lock();
	atomic_inc(&b->signaler_active);
	list_for_each_entry_rcu(ce, &b->signalers, signal_link) {
		struct i915_request *rq;

		list_for_each_entry_rcu(rq, &ce->signals, signal_link) {
			bool release;

			if (!__i915_request_is_complete(rq))
				break;

			if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL,
						&rq->fence.flags))
				break;

			/*
			 * Queue for execution after dropping the signaling
			 * spinlock as the callback chain may end up adding
			 * more signalers to the same context or engine.
			 */
			spin_lock(&ce->signal_lock);
			list_del_rcu(&rq->signal_link);
			release = remove_signaling_context(b, ce);
			spin_unlock(&ce->signal_lock);
			if (release) {
				if (intel_timeline_is_last(ce->timeline, rq))
					add_retire(b, ce->timeline);
				intel_context_put(ce);
			}

			if (__dma_fence_signal(&rq->fence))
				/* We own signal_node now, xfer to local list */
				signal = slist_add(&rq->signal_node, signal);
			else
				i915_request_put(rq);
		}
	}
	atomic_dec(&b->signaler_active);
	rcu_read_unlock();

	llist_for_each_safe(signal, sn, signal) {
		struct i915_request *rq =
			llist_entry(signal, typeof(*rq), signal_node);
		struct list_head cb_list;

		spin_lock(&rq->lock);
		list_replace(&rq->fence.cb_list, &cb_list);
		__dma_fence_signal__timestamp(&rq->fence, timestamp);
		__dma_fence_signal__notify(&rq->fence, &cb_list);
		spin_unlock(&rq->lock);

		i915_request_put(rq);
	}

	if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers))
		intel_breadcrumbs_arm_irq(b);
}

struct intel_breadcrumbs *
intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
{
	struct intel_breadcrumbs *b;

	b = kzalloc(sizeof(*b), GFP_KERNEL);
	if (!b)
		return NULL;

	b->irq_engine = irq_engine;

	spin_lock_init(&b->signalers_lock);
	INIT_LIST_HEAD(&b->signalers);
	init_llist_head(&b->signaled_requests);

	spin_lock_init(&b->irq_lock);
	init_irq_work(&b->irq_work, signal_irq_work);

	return b;
}

void intel_breadcrumbs_reset(struct intel_breadcrumbs *b)
{
	unsigned long flags;

	if (!b->irq_engine)
		return;

	spin_lock_irqsave(&b->irq_lock, flags);

	if (b->irq_enabled)
		irq_enable(b->irq_engine);
	else
		irq_disable(b->irq_engine);

	spin_unlock_irqrestore(&b->irq_lock, flags);
}

void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
{
	if (!READ_ONCE(b->irq_armed))
		return;

	/* Kick the work once more to drain the signalers, and disarm the irq */
	irq_work_sync(&b->irq_work);
	while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) {
		local_irq_disable();
		signal_irq_work(&b->irq_work);
		local_irq_enable();
		cond_resched();
	}
}

void intel_breadcrumbs_free(struct intel_breadcrumbs *b)
{
	irq_work_sync(&b->irq_work);
	GEM_BUG_ON(!list_empty(&b->signalers));
	GEM_BUG_ON(b->irq_armed);
	kfree(b);
}

static void irq_signal_request(struct i915_request *rq,
			       struct intel_breadcrumbs *b)
{
	if (!__dma_fence_signal(&rq->fence))
		return;

	i915_request_get(rq);
	if (llist_add(&rq->signal_node, &b->signaled_requests))
		irq_work_queue(&b->irq_work);
}

static void insert_breadcrumb(struct i915_request *rq)
{
	struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs;
	struct intel_context *ce = rq->context;
	struct list_head *pos;

	if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
		return;

	/*
	 * If the request is already completed, we can transfer it
	 * straight onto a signaled list, and queue the irq worker for
	 * its signal completion.
	 */
	if (__i915_request_is_complete(rq)) {
		irq_signal_request(rq, b);
		return;
	}

	if (list_empty(&ce->signals)) {
		intel_context_get(ce);
		add_signaling_context(b, ce);
		pos = &ce->signals;
	} else {
		/*
		 * We keep the seqno in retirement order, so we can break
		 * inside intel_engine_signal_breadcrumbs as soon as we've
		 * passed the last completed request (or seen a request that
		 * hasn't event started). We could walk the timeline->requests,
		 * but keeping a separate signalers_list has the advantage of
		 * hopefully being much smaller than the full list and so
		 * provides faster iteration and detection when there are no
		 * more interrupts required for this context.
		 *
		 * We typically expect to add new signalers in order, so we
		 * start looking for our insertion point from the tail of
		 * the list.
		 */
		list_for_each_prev(pos, &ce->signals) {
			struct i915_request *it =
				list_entry(pos, typeof(*it), signal_link);

			if (i915_seqno_passed(rq->fence.seqno, it->fence.seqno))
				break;
		}
	}

	i915_request_get(rq);
	list_add_rcu(&rq->signal_link, pos);
	GEM_BUG_ON(!check_signal_order(ce, rq));
	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags));
	set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);

	/*
	 * Defer enabling the interrupt to after HW submission and recheck
	 * the request as it may have completed and raised the interrupt as
	 * we were attaching it into the lists.
	 */
	irq_work_queue(&b->irq_work);
}

bool i915_request_enable_breadcrumb(struct i915_request *rq)
{
	struct intel_context *ce = rq->context;

	/* Serialises with i915_request_retire() using rq->lock */
	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
		return true;

	/*
	 * Peek at i915_request_submit()/i915_request_unsubmit() status.
	 *
	 * If the request is not yet active (and not signaled), we will
	 * attach the breadcrumb later.
	 */
	if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
		return true;

	spin_lock(&ce->signal_lock);
	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
		insert_breadcrumb(rq);
	spin_unlock(&ce->signal_lock);

	return true;
}

void i915_request_cancel_breadcrumb(struct i915_request *rq)
{
	struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs;
	struct intel_context *ce = rq->context;
	bool release;

	spin_lock(&ce->signal_lock);
	if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) {
		spin_unlock(&ce->signal_lock);
		return;
	}

	list_del_rcu(&rq->signal_link);
	release = remove_signaling_context(b, ce);
	spin_unlock(&ce->signal_lock);
	if (release)
		intel_context_put(ce);

	if (__i915_request_is_complete(rq))
		irq_signal_request(rq, b);

	i915_request_put(rq);
}

void intel_context_remove_breadcrumbs(struct intel_context *ce,
				      struct intel_breadcrumbs *b)
{
	struct i915_request *rq, *rn;
	bool release = false;
	unsigned long flags;

	spin_lock_irqsave(&ce->signal_lock, flags);

	if (list_empty(&ce->signals))
		goto unlock;

	list_for_each_entry_safe(rq, rn, &ce->signals, signal_link) {
		GEM_BUG_ON(!__i915_request_is_complete(rq));
		if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL,
					&rq->fence.flags))
			continue;

		list_del_rcu(&rq->signal_link);
		irq_signal_request(rq, b);
		i915_request_put(rq);
	}
	release = remove_signaling_context(b, ce);

unlock:
	spin_unlock_irqrestore(&ce->signal_lock, flags);
	if (release)
		intel_context_put(ce);

	while (atomic_read(&b->signaler_active))
		cpu_relax();
}

static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p)
{
	struct intel_context *ce;
	struct i915_request *rq;

	drm_printf(p, "Signals:\n");

	rcu_read_lock();
	list_for_each_entry_rcu(ce, &b->signalers, signal_link) {
		list_for_each_entry_rcu(rq, &ce->signals, signal_link)
			drm_printf(p, "\t[%llx:%llx%s] @ %dms\n",
				   rq->fence.context, rq->fence.seqno,
				   __i915_request_is_complete(rq) ? "!" :
				   __i915_request_has_started(rq) ? "*" :
				   "",
				   jiffies_to_msecs(jiffies - rq->emitted_jiffies));
	}
	rcu_read_unlock();
}

void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
				    struct drm_printer *p)
{
	struct intel_breadcrumbs *b;

	b = engine->breadcrumbs;
	if (!b)
		return;

	drm_printf(p, "IRQ: %s\n", enableddisabled(b->irq_armed));
	if (!list_empty(&b->signalers))
		print_signals(b, p);
}