summaryrefslogtreecommitdiff
path: root/kernel/events/ring_buffer.c
blob: a0433f37b0243a334a6bf45a95bd08ab527a0008 (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
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
// SPDX-License-Identifier: GPL-2.0
/*
 * Performance events ring-buffer code:
 *
 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
 *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
 *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 */

#include <linux/perf_event.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/circ_buf.h>
#include <linux/poll.h>
#include <linux/nospec.h>

#include "internal.h"

static void perf_output_wakeup(struct perf_output_handle *handle)
{
	atomic_set(&handle->rb->poll, EPOLLIN);

	handle->event->pending_wakeup = 1;
	irq_work_queue(&handle->event->pending_irq);
}

/*
 * We need to ensure a later event_id doesn't publish a head when a former
 * event isn't done writing. However since we need to deal with NMIs we
 * cannot fully serialize things.
 *
 * We only publish the head (and generate a wakeup) when the outer-most
 * event completes.
 */
static void perf_output_get_handle(struct perf_output_handle *handle)
{
	struct perf_buffer *rb = handle->rb;

	preempt_disable();

	/*
	 * Avoid an explicit LOAD/STORE such that architectures with memops
	 * can use them.
	 */
	(*(volatile unsigned int *)&rb->nest)++;
	handle->wakeup = local_read(&rb->wakeup);
}

static void perf_output_put_handle(struct perf_output_handle *handle)
{
	struct perf_buffer *rb = handle->rb;
	unsigned long head;
	unsigned int nest;

	/*
	 * If this isn't the outermost nesting, we don't have to update
	 * @rb->user_page->data_head.
	 */
	nest = READ_ONCE(rb->nest);
	if (nest > 1) {
		WRITE_ONCE(rb->nest, nest - 1);
		goto out;
	}

again:
	/*
	 * In order to avoid publishing a head value that goes backwards,
	 * we must ensure the load of @rb->head happens after we've
	 * incremented @rb->nest.
	 *
	 * Otherwise we can observe a @rb->head value before one published
	 * by an IRQ/NMI happening between the load and the increment.
	 */
	barrier();
	head = local_read(&rb->head);

	/*
	 * IRQ/NMI can happen here and advance @rb->head, causing our
	 * load above to be stale.
	 */

	/*
	 * Since the mmap() consumer (userspace) can run on a different CPU:
	 *
	 *   kernel				user
	 *
	 *   if (LOAD ->data_tail) {		LOAD ->data_head
	 *			(A)		smp_rmb()	(C)
	 *	STORE $data			LOAD $data
	 *	smp_wmb()	(B)		smp_mb()	(D)
	 *	STORE ->data_head		STORE ->data_tail
	 *   }
	 *
	 * Where A pairs with D, and B pairs with C.
	 *
	 * In our case (A) is a control dependency that separates the load of
	 * the ->data_tail and the stores of $data. In case ->data_tail
	 * indicates there is no room in the buffer to store $data we do not.
	 *
	 * D needs to be a full barrier since it separates the data READ
	 * from the tail WRITE.
	 *
	 * For B a WMB is sufficient since it separates two WRITEs, and for C
	 * an RMB is sufficient since it separates two READs.
	 *
	 * See perf_output_begin().
	 */
	smp_wmb(); /* B, matches C */
	WRITE_ONCE(rb->user_page->data_head, head);

	/*
	 * We must publish the head before decrementing the nest count,
	 * otherwise an IRQ/NMI can publish a more recent head value and our
	 * write will (temporarily) publish a stale value.
	 */
	barrier();
	WRITE_ONCE(rb->nest, 0);

	/*
	 * Ensure we decrement @rb->nest before we validate the @rb->head.
	 * Otherwise we cannot be sure we caught the 'last' nested update.
	 */
	barrier();
	if (unlikely(head != local_read(&rb->head))) {
		WRITE_ONCE(rb->nest, 1);
		goto again;
	}

	if (handle->wakeup != local_read(&rb->wakeup))
		perf_output_wakeup(handle);

out:
	preempt_enable();
}

static __always_inline bool
ring_buffer_has_space(unsigned long head, unsigned long tail,
		      unsigned long data_size, unsigned int size,
		      bool backward)
{
	if (!backward)
		return CIRC_SPACE(head, tail, data_size) >= size;
	else
		return CIRC_SPACE(tail, head, data_size) >= size;
}

static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
		    struct perf_sample_data *data,
		    struct perf_event *event, unsigned int size,
		    bool backward)
{
	struct perf_buffer *rb;
	unsigned long tail, offset, head;
	int have_lost, page_shift;
	struct {
		struct perf_event_header header;
		u64			 id;
		u64			 lost;
	} lost_event;

	rcu_read_lock();
	/*
	 * For inherited events we send all the output towards the parent.
	 */
	if (event->parent)
		event = event->parent;

	rb = rcu_dereference(event->rb);
	if (unlikely(!rb))
		goto out;

	if (unlikely(rb->paused)) {
		if (rb->nr_pages) {
			local_inc(&rb->lost);
			atomic64_inc(&event->lost_samples);
		}
		goto out;
	}

	handle->rb    = rb;
	handle->event = event;

	have_lost = local_read(&rb->lost);
	if (unlikely(have_lost)) {
		size += sizeof(lost_event);
		if (event->attr.sample_id_all)
			size += event->id_header_size;
	}

	perf_output_get_handle(handle);

	do {
		tail = READ_ONCE(rb->user_page->data_tail);
		offset = head = local_read(&rb->head);
		if (!rb->overwrite) {
			if (unlikely(!ring_buffer_has_space(head, tail,
							    perf_data_size(rb),
							    size, backward)))
				goto fail;
		}

		/*
		 * The above forms a control dependency barrier separating the
		 * @tail load above from the data stores below. Since the @tail
		 * load is required to compute the branch to fail below.
		 *
		 * A, matches D; the full memory barrier userspace SHOULD issue
		 * after reading the data and before storing the new tail
		 * position.
		 *
		 * See perf_output_put_handle().
		 */

		if (!backward)
			head += size;
		else
			head -= size;
	} while (local_cmpxchg(&rb->head, offset, head) != offset);

	if (backward) {
		offset = head;
		head = (u64)(-head);
	}

	/*
	 * We rely on the implied barrier() by local_cmpxchg() to ensure
	 * none of the data stores below can be lifted up by the compiler.
	 */

	if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
		local_add(rb->watermark, &rb->wakeup);

	page_shift = PAGE_SHIFT + page_order(rb);

	handle->page = (offset >> page_shift) & (rb->nr_pages - 1);
	offset &= (1UL << page_shift) - 1;
	handle->addr = rb->data_pages[handle->page] + offset;
	handle->size = (1UL << page_shift) - offset;

	if (unlikely(have_lost)) {
		lost_event.header.size = sizeof(lost_event);
		lost_event.header.type = PERF_RECORD_LOST;
		lost_event.header.misc = 0;
		lost_event.id          = event->id;
		lost_event.lost        = local_xchg(&rb->lost, 0);

		/* XXX mostly redundant; @data is already fully initializes */
		perf_event_header__init_id(&lost_event.header, data, event);
		perf_output_put(handle, lost_event);
		perf_event__output_id_sample(event, handle, data);
	}

	return 0;

fail:
	local_inc(&rb->lost);
	atomic64_inc(&event->lost_samples);
	perf_output_put_handle(handle);
out:
	rcu_read_unlock();

	return -ENOSPC;
}

int perf_output_begin_forward(struct perf_output_handle *handle,
			      struct perf_sample_data *data,
			      struct perf_event *event, unsigned int size)
{
	return __perf_output_begin(handle, data, event, size, false);
}

int perf_output_begin_backward(struct perf_output_handle *handle,
			       struct perf_sample_data *data,
			       struct perf_event *event, unsigned int size)
{
	return __perf_output_begin(handle, data, event, size, true);
}

int perf_output_begin(struct perf_output_handle *handle,
		      struct perf_sample_data *data,
		      struct perf_event *event, unsigned int size)
{

	return __perf_output_begin(handle, data, event, size,
				   unlikely(is_write_backward(event)));
}

unsigned int perf_output_copy(struct perf_output_handle *handle,
		      const void *buf, unsigned int len)
{
	return __output_copy(handle, buf, len);
}

unsigned int perf_output_skip(struct perf_output_handle *handle,
			      unsigned int len)
{
	return __output_skip(handle, NULL, len);
}

void perf_output_end(struct perf_output_handle *handle)
{
	perf_output_put_handle(handle);
	rcu_read_unlock();
}

static void
ring_buffer_init(struct perf_buffer *rb, long watermark, int flags)
{
	long max_size = perf_data_size(rb);

	if (watermark)
		rb->watermark = min(max_size, watermark);

	if (!rb->watermark)
		rb->watermark = max_size / 2;

	if (flags & RING_BUFFER_WRITABLE)
		rb->overwrite = 0;
	else
		rb->overwrite = 1;

	refcount_set(&rb->refcount, 1);

	INIT_LIST_HEAD(&rb->event_list);
	spin_lock_init(&rb->event_lock);

	/*
	 * perf_output_begin() only checks rb->paused, therefore
	 * rb->paused must be true if we have no pages for output.
	 */
	if (!rb->nr_pages)
		rb->paused = 1;
}

void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)
{
	/*
	 * OVERWRITE is determined by perf_aux_output_end() and can't
	 * be passed in directly.
	 */
	if (WARN_ON_ONCE(flags & PERF_AUX_FLAG_OVERWRITE))
		return;

	handle->aux_flags |= flags;
}
EXPORT_SYMBOL_GPL(perf_aux_output_flag);

/*
 * This is called before hardware starts writing to the AUX area to
 * obtain an output handle and make sure there's room in the buffer.
 * When the capture completes, call perf_aux_output_end() to commit
 * the recorded data to the buffer.
 *
 * The ordering is similar to that of perf_output_{begin,end}, with
 * the exception of (B), which should be taken care of by the pmu
 * driver, since ordering rules will differ depending on hardware.
 *
 * Call this from pmu::start(); see the comment in perf_aux_output_end()
 * about its use in pmu callbacks. Both can also be called from the PMI
 * handler if needed.
 */
void *perf_aux_output_begin(struct perf_output_handle *handle,
			    struct perf_event *event)
{
	struct perf_event *output_event = event;
	unsigned long aux_head, aux_tail;
	struct perf_buffer *rb;
	unsigned int nest;

	if (output_event->parent)
		output_event = output_event->parent;

	/*
	 * Since this will typically be open across pmu::add/pmu::del, we
	 * grab ring_buffer's refcount instead of holding rcu read lock
	 * to make sure it doesn't disappear under us.
	 */
	rb = ring_buffer_get(output_event);
	if (!rb)
		return NULL;

	if (!rb_has_aux(rb))
		goto err;

	/*
	 * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
	 * about to get freed, so we leave immediately.
	 *
	 * Checking rb::aux_mmap_count and rb::refcount has to be done in
	 * the same order, see perf_mmap_close. Otherwise we end up freeing
	 * aux pages in this path, which is a bug, because in_atomic().
	 */
	if (!atomic_read(&rb->aux_mmap_count))
		goto err;

	if (!refcount_inc_not_zero(&rb->aux_refcount))
		goto err;

	nest = READ_ONCE(rb->aux_nest);
	/*
	 * Nesting is not supported for AUX area, make sure nested
	 * writers are caught early
	 */
	if (WARN_ON_ONCE(nest))
		goto err_put;

	WRITE_ONCE(rb->aux_nest, nest + 1);

	aux_head = rb->aux_head;

	handle->rb = rb;
	handle->event = event;
	handle->head = aux_head;
	handle->size = 0;
	handle->aux_flags = 0;

	/*
	 * In overwrite mode, AUX data stores do not depend on aux_tail,
	 * therefore (A) control dependency barrier does not exist. The
	 * (B) <-> (C) ordering is still observed by the pmu driver.
	 */
	if (!rb->aux_overwrite) {
		aux_tail = READ_ONCE(rb->user_page->aux_tail);
		handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
		if (aux_head - aux_tail < perf_aux_size(rb))
			handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb));

		/*
		 * handle->size computation depends on aux_tail load; this forms a
		 * control dependency barrier separating aux_tail load from aux data
		 * store that will be enabled on successful return
		 */
		if (!handle->size) { /* A, matches D */
			event->pending_disable = smp_processor_id();
			perf_output_wakeup(handle);
			WRITE_ONCE(rb->aux_nest, 0);
			goto err_put;
		}
	}

	return handle->rb->aux_priv;

err_put:
	/* can't be last */
	rb_free_aux(rb);

err:
	ring_buffer_put(rb);
	handle->event = NULL;

	return NULL;
}
EXPORT_SYMBOL_GPL(perf_aux_output_begin);

static __always_inline bool rb_need_aux_wakeup(struct perf_buffer *rb)
{
	if (rb->aux_overwrite)
		return false;

	if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
		rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
		return true;
	}

	return false;
}

/*
 * Commit the data written by hardware into the ring buffer by adjusting
 * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
 * pmu driver's responsibility to observe ordering rules of the hardware,
 * so that all the data is externally visible before this is called.
 *
 * Note: this has to be called from pmu::stop() callback, as the assumption
 * of the AUX buffer management code is that after pmu::stop(), the AUX
 * transaction must be stopped and therefore drop the AUX reference count.
 */
void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
{
	bool wakeup = !!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED);
	struct perf_buffer *rb = handle->rb;
	unsigned long aux_head;

	/* in overwrite mode, driver provides aux_head via handle */
	if (rb->aux_overwrite) {
		handle->aux_flags |= PERF_AUX_FLAG_OVERWRITE;

		aux_head = handle->head;
		rb->aux_head = aux_head;
	} else {
		handle->aux_flags &= ~PERF_AUX_FLAG_OVERWRITE;

		aux_head = rb->aux_head;
		rb->aux_head += size;
	}

	/*
	 * Only send RECORD_AUX if we have something useful to communicate
	 *
	 * Note: the OVERWRITE records by themselves are not considered
	 * useful, as they don't communicate any *new* information,
	 * aside from the short-lived offset, that becomes history at
	 * the next event sched-in and therefore isn't useful.
	 * The userspace that needs to copy out AUX data in overwrite
	 * mode should know to use user_page::aux_head for the actual
	 * offset. So, from now on we don't output AUX records that
	 * have *only* OVERWRITE flag set.
	 */
	if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
		perf_event_aux_event(handle->event, aux_head, size,
				     handle->aux_flags);

	WRITE_ONCE(rb->user_page->aux_head, rb->aux_head);
	if (rb_need_aux_wakeup(rb))
		wakeup = true;

	if (wakeup) {
		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
			handle->event->pending_disable = smp_processor_id();
		perf_output_wakeup(handle);
	}

	handle->event = NULL;

	WRITE_ONCE(rb->aux_nest, 0);
	/* can't be last */
	rb_free_aux(rb);
	ring_buffer_put(rb);
}
EXPORT_SYMBOL_GPL(perf_aux_output_end);

/*
 * Skip over a given number of bytes in the AUX buffer, due to, for example,
 * hardware's alignment constraints.
 */
int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
{
	struct perf_buffer *rb = handle->rb;

	if (size > handle->size)
		return -ENOSPC;

	rb->aux_head += size;

	WRITE_ONCE(rb->user_page->aux_head, rb->aux_head);
	if (rb_need_aux_wakeup(rb)) {
		perf_output_wakeup(handle);
		handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
	}

	handle->head = rb->aux_head;
	handle->size -= size;

	return 0;
}
EXPORT_SYMBOL_GPL(perf_aux_output_skip);

void *perf_get_aux(struct perf_output_handle *handle)
{
	/* this is only valid between perf_aux_output_begin and *_end */
	if (!handle->event)
		return NULL;

	return handle->rb->aux_priv;
}
EXPORT_SYMBOL_GPL(perf_get_aux);

/*
 * Copy out AUX data from an AUX handle.
 */
long perf_output_copy_aux(struct perf_output_handle *aux_handle,
			  struct perf_output_handle *handle,
			  unsigned long from, unsigned long to)
{
	struct perf_buffer *rb = aux_handle->rb;
	unsigned long tocopy, remainder, len = 0;
	void *addr;

	from &= (rb->aux_nr_pages << PAGE_SHIFT) - 1;
	to &= (rb->aux_nr_pages << PAGE_SHIFT) - 1;

	do {
		tocopy = PAGE_SIZE - offset_in_page(from);
		if (to > from)
			tocopy = min(tocopy, to - from);
		if (!tocopy)
			break;

		addr = rb->aux_pages[from >> PAGE_SHIFT];
		addr += offset_in_page(from);

		remainder = perf_output_copy(handle, addr, tocopy);
		if (remainder)
			return -EFAULT;

		len += tocopy;
		from += tocopy;
		from &= (rb->aux_nr_pages << PAGE_SHIFT) - 1;
	} while (to != from);

	return len;
}

#define PERF_AUX_GFP	(GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY)

static struct page *rb_alloc_aux_page(int node, int order)
{
	struct page *page;

	if (order > MAX_ORDER)
		order = MAX_ORDER;

	do {
		page = alloc_pages_node(node, PERF_AUX_GFP, order);
	} while (!page && order--);

	if (page && order) {
		/*
		 * Communicate the allocation size to the driver:
		 * if we managed to secure a high-order allocation,
		 * set its first page's private to this order;
		 * !PagePrivate(page) means it's just a normal page.
		 */
		split_page(page, order);
		SetPagePrivate(page);
		set_page_private(page, order);
	}

	return page;
}

static void rb_free_aux_page(struct perf_buffer *rb, int idx)
{
	struct page *page = virt_to_page(rb->aux_pages[idx]);

	ClearPagePrivate(page);
	page->mapping = NULL;
	__free_page(page);
}

static void __rb_free_aux(struct perf_buffer *rb)
{
	int pg;

	/*
	 * Should never happen, the last reference should be dropped from
	 * perf_mmap_close() path, which first stops aux transactions (which
	 * in turn are the atomic holders of aux_refcount) and then does the
	 * last rb_free_aux().
	 */
	WARN_ON_ONCE(in_atomic());

	if (rb->aux_priv) {
		rb->free_aux(rb->aux_priv);
		rb->free_aux = NULL;
		rb->aux_priv = NULL;
	}

	if (rb->aux_nr_pages) {
		for (pg = 0; pg < rb->aux_nr_pages; pg++)
			rb_free_aux_page(rb, pg);

		kfree(rb->aux_pages);
		rb->aux_nr_pages = 0;
	}
}

int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
		 pgoff_t pgoff, int nr_pages, long watermark, int flags)
{
	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
	int ret = -ENOMEM, max_order;

	if (!has_aux(event))
		return -EOPNOTSUPP;

	if (!overwrite) {
		/*
		 * Watermark defaults to half the buffer, and so does the
		 * max_order, to aid PMU drivers in double buffering.
		 */
		if (!watermark)
			watermark = nr_pages << (PAGE_SHIFT - 1);

		/*
		 * Use aux_watermark as the basis for chunking to
		 * help PMU drivers honor the watermark.
		 */
		max_order = get_order(watermark);
	} else {
		/*
		 * We need to start with the max_order that fits in nr_pages,
		 * not the other way around, hence ilog2() and not get_order.
		 */
		max_order = ilog2(nr_pages);
		watermark = 0;
	}

	rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
				     node);
	if (!rb->aux_pages)
		return -ENOMEM;

	rb->free_aux = event->pmu->free_aux;
	for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;) {
		struct page *page;
		int last, order;

		order = min(max_order, ilog2(nr_pages - rb->aux_nr_pages));
		page = rb_alloc_aux_page(node, order);
		if (!page)
			goto out;

		for (last = rb->aux_nr_pages + (1 << page_private(page));
		     last > rb->aux_nr_pages; rb->aux_nr_pages++)
			rb->aux_pages[rb->aux_nr_pages] = page_address(page++);
	}

	/*
	 * In overwrite mode, PMUs that don't support SG may not handle more
	 * than one contiguous allocation, since they rely on PMI to do double
	 * buffering. In this case, the entire buffer has to be one contiguous
	 * chunk.
	 */
	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) &&
	    overwrite) {
		struct page *page = virt_to_page(rb->aux_pages[0]);

		if (page_private(page) != max_order)
			goto out;
	}

	rb->aux_priv = event->pmu->setup_aux(event, rb->aux_pages, nr_pages,
					     overwrite);
	if (!rb->aux_priv)
		goto out;

	ret = 0;

	/*
	 * aux_pages (and pmu driver's private data, aux_priv) will be
	 * referenced in both producer's and consumer's contexts, thus
	 * we keep a refcount here to make sure either of the two can
	 * reference them safely.
	 */
	refcount_set(&rb->aux_refcount, 1);

	rb->aux_overwrite = overwrite;
	rb->aux_watermark = watermark;

out:
	if (!ret)
		rb->aux_pgoff = pgoff;
	else
		__rb_free_aux(rb);

	return ret;
}

void rb_free_aux(struct perf_buffer *rb)
{
	if (refcount_dec_and_test(&rb->aux_refcount))
		__rb_free_aux(rb);
}

#ifndef CONFIG_PERF_USE_VMALLOC

/*
 * Back perf_mmap() with regular GFP_KERNEL-0 pages.
 */

static struct page *
__perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff)
{
	if (pgoff > rb->nr_pages)
		return NULL;

	if (pgoff == 0)
		return virt_to_page(rb->user_page);

	return virt_to_page(rb->data_pages[pgoff - 1]);
}

static void *perf_mmap_alloc_page(int cpu)
{
	struct page *page;
	int node;

	node = (cpu == -1) ? cpu : cpu_to_node(cpu);
	page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
	if (!page)
		return NULL;

	return page_address(page);
}

static void perf_mmap_free_page(void *addr)
{
	struct page *page = virt_to_page(addr);

	page->mapping = NULL;
	__free_page(page);
}

struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
{
	struct perf_buffer *rb;
	unsigned long size;
	int i, node;

	size = sizeof(struct perf_buffer);
	size += nr_pages * sizeof(void *);

	if (order_base_2(size) > PAGE_SHIFT+MAX_ORDER)
		goto fail;

	node = (cpu == -1) ? cpu : cpu_to_node(cpu);
	rb = kzalloc_node(size, GFP_KERNEL, node);
	if (!rb)
		goto fail;

	rb->user_page = perf_mmap_alloc_page(cpu);
	if (!rb->user_page)
		goto fail_user_page;

	for (i = 0; i < nr_pages; i++) {
		rb->data_pages[i] = perf_mmap_alloc_page(cpu);
		if (!rb->data_pages[i])
			goto fail_data_pages;
	}

	rb->nr_pages = nr_pages;

	ring_buffer_init(rb, watermark, flags);

	return rb;

fail_data_pages:
	for (i--; i >= 0; i--)
		perf_mmap_free_page(rb->data_pages[i]);

	perf_mmap_free_page(rb->user_page);

fail_user_page:
	kfree(rb);

fail:
	return NULL;
}

void rb_free(struct perf_buffer *rb)
{
	int i;

	perf_mmap_free_page(rb->user_page);
	for (i = 0; i < rb->nr_pages; i++)
		perf_mmap_free_page(rb->data_pages[i]);
	kfree(rb);
}

#else
static struct page *
__perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff)
{
	/* The '>' counts in the user page. */
	if (pgoff > data_page_nr(rb))
		return NULL;

	return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE);
}

static void perf_mmap_unmark_page(void *addr)
{
	struct page *page = vmalloc_to_page(addr);

	page->mapping = NULL;
}

static void rb_free_work(struct work_struct *work)
{
	struct perf_buffer *rb;
	void *base;
	int i, nr;

	rb = container_of(work, struct perf_buffer, work);
	nr = data_page_nr(rb);

	base = rb->user_page;
	/* The '<=' counts in the user page. */
	for (i = 0; i <= nr; i++)
		perf_mmap_unmark_page(base + (i * PAGE_SIZE));

	vfree(base);
	kfree(rb);
}

void rb_free(struct perf_buffer *rb)
{
	schedule_work(&rb->work);
}

struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
{
	struct perf_buffer *rb;
	unsigned long size;
	void *all_buf;
	int node;

	size = sizeof(struct perf_buffer);
	size += sizeof(void *);

	node = (cpu == -1) ? cpu : cpu_to_node(cpu);
	rb = kzalloc_node(size, GFP_KERNEL, node);
	if (!rb)
		goto fail;

	INIT_WORK(&rb->work, rb_free_work);

	all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE);
	if (!all_buf)
		goto fail_all_buf;

	rb->user_page = all_buf;
	rb->data_pages[0] = all_buf + PAGE_SIZE;
	if (nr_pages) {
		rb->nr_pages = 1;
		rb->page_order = ilog2(nr_pages);
	}

	ring_buffer_init(rb, watermark, flags);

	return rb;

fail_all_buf:
	kfree(rb);

fail:
	return NULL;
}

#endif

struct page *
perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff)
{
	if (rb->aux_nr_pages) {
		/* above AUX space */
		if (pgoff > rb->aux_pgoff + rb->aux_nr_pages)
			return NULL;

		/* AUX space */
		if (pgoff >= rb->aux_pgoff) {
			int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages);
			return virt_to_page(rb->aux_pages[aux_pgoff]);
		}
	}

	return __perf_mmap_to_page(rb, pgoff);
}