summaryrefslogtreecommitdiff
path: root/kernel/bpf/stackmap.c
blob: 09a3fd97d329ea2b3ecdad1f1c5e85dbff0478ca (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 Facebook
 */
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/kernel.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include <linux/irq_work.h>
#include <linux/btf_ids.h>
#include <linux/buildid.h>
#include "percpu_freelist.h"

#define STACK_CREATE_FLAG_MASK					\
	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\
	 BPF_F_STACK_BUILD_ID)

struct stack_map_bucket {
	struct pcpu_freelist_node fnode;
	u32 hash;
	u32 nr;
	u64 data[];
};

struct bpf_stack_map {
	struct bpf_map map;
	void *elems;
	struct pcpu_freelist freelist;
	u32 n_buckets;
	struct stack_map_bucket *buckets[];
};

/* irq_work to run up_read() for build_id lookup in nmi context */
struct stack_map_irq_work {
	struct irq_work irq_work;
	struct mm_struct *mm;
};

static void do_up_read(struct irq_work *entry)
{
	struct stack_map_irq_work *work;

	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
		return;

	work = container_of(entry, struct stack_map_irq_work, irq_work);
	mmap_read_unlock_non_owner(work->mm);
}

static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);

static inline bool stack_map_use_build_id(struct bpf_map *map)
{
	return (map->map_flags & BPF_F_STACK_BUILD_ID);
}

static inline int stack_map_data_size(struct bpf_map *map)
{
	return stack_map_use_build_id(map) ?
		sizeof(struct bpf_stack_build_id) : sizeof(u64);
}

static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
{
	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
	int err;

	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,
					 smap->map.numa_node);
	if (!smap->elems)
		return -ENOMEM;

	err = pcpu_freelist_init(&smap->freelist);
	if (err)
		goto free_elems;

	pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
			       smap->map.max_entries);
	return 0;

free_elems:
	bpf_map_area_free(smap->elems);
	return err;
}

/* Called from syscall */
static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
{
	u32 value_size = attr->value_size;
	struct bpf_stack_map *smap;
	u64 cost, n_buckets;
	int err;

	if (!bpf_capable())
		return ERR_PTR(-EPERM);

	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
		return ERR_PTR(-EINVAL);

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    value_size < 8 || value_size % 8)
		return ERR_PTR(-EINVAL);

	BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64));
	if (attr->map_flags & BPF_F_STACK_BUILD_ID) {
		if (value_size % sizeof(struct bpf_stack_build_id) ||
		    value_size / sizeof(struct bpf_stack_build_id)
		    > sysctl_perf_event_max_stack)
			return ERR_PTR(-EINVAL);
	} else if (value_size / 8 > sysctl_perf_event_max_stack)
		return ERR_PTR(-EINVAL);

	/* hash table size must be power of 2 */
	n_buckets = roundup_pow_of_two(attr->max_entries);
	if (!n_buckets)
		return ERR_PTR(-E2BIG);

	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
	if (!smap)
		return ERR_PTR(-ENOMEM);

	bpf_map_init_from_attr(&smap->map, attr);
	smap->map.value_size = value_size;
	smap->n_buckets = n_buckets;

	err = get_callchain_buffers(sysctl_perf_event_max_stack);
	if (err)
		goto free_smap;

	err = prealloc_elems_and_freelist(smap);
	if (err)
		goto put_buffers;

	return &smap->map;

put_buffers:
	put_callchain_buffers();
free_smap:
	bpf_map_area_free(smap);
	return ERR_PTR(err);
}

static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
					  u64 *ips, u32 trace_nr, bool user)
{
	int i;
	struct vm_area_struct *vma;
	bool irq_work_busy = false;
	struct stack_map_irq_work *work = NULL;

	if (irqs_disabled()) {
		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
			work = this_cpu_ptr(&up_read_work);
			if (irq_work_is_busy(&work->irq_work)) {
				/* cannot queue more up_read, fallback */
				irq_work_busy = true;
			}
		} else {
			/*
			 * PREEMPT_RT does not allow to trylock mmap sem in
			 * interrupt disabled context. Force the fallback code.
			 */
			irq_work_busy = true;
		}
	}

	/*
	 * We cannot do up_read() when the irq is disabled, because of
	 * risk to deadlock with rq_lock. To do build_id lookup when the
	 * irqs are disabled, we need to run up_read() in irq_work. We use
	 * a percpu variable to do the irq_work. If the irq_work is
	 * already used by another lookup, we fall back to report ips.
	 *
	 * Same fallback is used for kernel stack (!user) on a stackmap
	 * with build_id.
	 */
	if (!user || !current || !current->mm || irq_work_busy ||
	    !mmap_read_trylock(current->mm)) {
		/* cannot access current->mm, fall back to ips */
		for (i = 0; i < trace_nr; i++) {
			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
			id_offs[i].ip = ips[i];
			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
		}
		return;
	}

	for (i = 0; i < trace_nr; i++) {
		vma = find_vma(current->mm, ips[i]);
		if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) {
			/* per entry fall back to ips */
			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
			id_offs[i].ip = ips[i];
			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
			continue;
		}
		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
			- vma->vm_start;
		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
	}

	if (!work) {
		mmap_read_unlock(current->mm);
	} else {
		work->mm = current->mm;

		/* The lock will be released once we're out of interrupt
		 * context. Tell lockdep that we've released it now so
		 * it doesn't complain that we forgot to release it.
		 */
		rwsem_release(&current->mm->mmap_lock.dep_map, _RET_IP_);
		irq_work_queue(&work->irq_work);
	}
}

static struct perf_callchain_entry *
get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
{
#ifdef CONFIG_STACKTRACE
	struct perf_callchain_entry *entry;
	int rctx;

	entry = get_callchain_entry(&rctx);

	if (!entry)
		return NULL;

	entry->nr = init_nr +
		stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
				     sysctl_perf_event_max_stack - init_nr, 0);

	/* stack_trace_save_tsk() works on unsigned long array, while
	 * perf_callchain_entry uses u64 array. For 32-bit systems, it is
	 * necessary to fix this mismatch.
	 */
	if (__BITS_PER_LONG != 64) {
		unsigned long *from = (unsigned long *) entry->ip;
		u64 *to = entry->ip;
		int i;

		/* copy data from the end to avoid using extra buffer */
		for (i = entry->nr - 1; i >= (int)init_nr; i--)
			to[i] = (u64)(from[i]);
	}

	put_callchain_entry(rctx);

	return entry;
#else /* CONFIG_STACKTRACE */
	return NULL;
#endif
}

static long __bpf_get_stackid(struct bpf_map *map,
			      struct perf_callchain_entry *trace, u64 flags)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
	u32 max_depth = map->value_size / stack_map_data_size(map);
	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
	u32 hash, id, trace_nr, trace_len;
	bool user = flags & BPF_F_USER_STACK;
	u64 *ips;
	bool hash_matches;

	/* get_perf_callchain() guarantees that trace->nr >= init_nr
	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
	 */
	trace_nr = trace->nr - init_nr;

	if (trace_nr <= skip)
		/* skipping more than usable stack trace */
		return -EFAULT;

	trace_nr -= skip;
	trace_len = trace_nr * sizeof(u64);
	ips = trace->ip + skip + init_nr;
	hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
	id = hash & (smap->n_buckets - 1);
	bucket = READ_ONCE(smap->buckets[id]);

	hash_matches = bucket && bucket->hash == hash;
	/* fast cmp */
	if (hash_matches && flags & BPF_F_FAST_STACK_CMP)
		return id;

	if (stack_map_use_build_id(map)) {
		/* for build_id+offset, pop a bucket before slow cmp */
		new_bucket = (struct stack_map_bucket *)
			pcpu_freelist_pop(&smap->freelist);
		if (unlikely(!new_bucket))
			return -ENOMEM;
		new_bucket->nr = trace_nr;
		stack_map_get_build_id_offset(
			(struct bpf_stack_build_id *)new_bucket->data,
			ips, trace_nr, user);
		trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
		if (hash_matches && bucket->nr == trace_nr &&
		    memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
			pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
			return id;
		}
		if (bucket && !(flags & BPF_F_REUSE_STACKID)) {
			pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
			return -EEXIST;
		}
	} else {
		if (hash_matches && bucket->nr == trace_nr &&
		    memcmp(bucket->data, ips, trace_len) == 0)
			return id;
		if (bucket && !(flags & BPF_F_REUSE_STACKID))
			return -EEXIST;

		new_bucket = (struct stack_map_bucket *)
			pcpu_freelist_pop(&smap->freelist);
		if (unlikely(!new_bucket))
			return -ENOMEM;
		memcpy(new_bucket->data, ips, trace_len);
	}

	new_bucket->hash = hash;
	new_bucket->nr = trace_nr;

	old_bucket = xchg(&smap->buckets[id], new_bucket);
	if (old_bucket)
		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
	return id;
}

BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
	   u64, flags)
{
	u32 max_depth = map->value_size / stack_map_data_size(map);
	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
	bool user = flags & BPF_F_USER_STACK;
	struct perf_callchain_entry *trace;
	bool kernel = !user;

	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
		return -EINVAL;

	trace = get_perf_callchain(regs, init_nr, kernel, user,
				   sysctl_perf_event_max_stack, false, false);

	if (unlikely(!trace))
		/* couldn't fetch the stack trace */
		return -EFAULT;

	return __bpf_get_stackid(map, trace, flags);
}

const struct bpf_func_proto bpf_get_stackid_proto = {
	.func		= bpf_get_stackid,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

static __u64 count_kernel_ip(struct perf_callchain_entry *trace)
{
	__u64 nr_kernel = 0;

	while (nr_kernel < trace->nr) {
		if (trace->ip[nr_kernel] == PERF_CONTEXT_USER)
			break;
		nr_kernel++;
	}
	return nr_kernel;
}

BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
	   struct bpf_map *, map, u64, flags)
{
	struct perf_event *event = ctx->event;
	struct perf_callchain_entry *trace;
	bool kernel, user;
	__u64 nr_kernel;
	int ret;

	/* perf_sample_data doesn't have callchain, use bpf_get_stackid */
	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
		return bpf_get_stackid((unsigned long)(ctx->regs),
				       (unsigned long) map, flags, 0, 0);

	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
		return -EINVAL;

	user = flags & BPF_F_USER_STACK;
	kernel = !user;

	trace = ctx->data->callchain;
	if (unlikely(!trace))
		return -EFAULT;

	nr_kernel = count_kernel_ip(trace);

	if (kernel) {
		__u64 nr = trace->nr;

		trace->nr = nr_kernel;
		ret = __bpf_get_stackid(map, trace, flags);

		/* restore nr */
		trace->nr = nr;
	} else { /* user */
		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;

		skip += nr_kernel;
		if (skip > BPF_F_SKIP_FIELD_MASK)
			return -EFAULT;

		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
		ret = __bpf_get_stackid(map, trace, flags);
	}
	return ret;
}

const struct bpf_func_proto bpf_get_stackid_proto_pe = {
	.func		= bpf_get_stackid_pe,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
			    struct perf_callchain_entry *trace_in,
			    void *buf, u32 size, u64 flags)
{
	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
	bool user = flags & BPF_F_USER_STACK;
	struct perf_callchain_entry *trace;
	bool kernel = !user;
	int err = -EINVAL;
	u64 *ips;

	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
			       BPF_F_USER_BUILD_ID)))
		goto clear;
	if (kernel && user_build_id)
		goto clear;

	elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
					    : sizeof(u64);
	if (unlikely(size % elem_size))
		goto clear;

	/* cannot get valid user stack for task without user_mode regs */
	if (task && user && !user_mode(regs))
		goto err_fault;

	num_elem = size / elem_size;
	if (sysctl_perf_event_max_stack < num_elem)
		init_nr = 0;
	else
		init_nr = sysctl_perf_event_max_stack - num_elem;

	if (trace_in)
		trace = trace_in;
	else if (kernel && task)
		trace = get_callchain_entry_for_task(task, init_nr);
	else
		trace = get_perf_callchain(regs, init_nr, kernel, user,
					   sysctl_perf_event_max_stack,
					   false, false);
	if (unlikely(!trace))
		goto err_fault;

	trace_nr = trace->nr - init_nr;
	if (trace_nr < skip)
		goto err_fault;

	trace_nr -= skip;
	trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
	copy_len = trace_nr * elem_size;
	ips = trace->ip + skip + init_nr;
	if (user && user_build_id)
		stack_map_get_build_id_offset(buf, ips, trace_nr, user);
	else
		memcpy(buf, ips, copy_len);

	if (size > copy_len)
		memset(buf + copy_len, 0, size - copy_len);
	return copy_len;

err_fault:
	err = -EFAULT;
clear:
	memset(buf, 0, size);
	return err;
}

BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
	   u64, flags)
{
	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
}

const struct bpf_func_proto bpf_get_stack_proto = {
	.func		= bpf_get_stack,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg4_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
	   u32, size, u64, flags)
{
	struct pt_regs *regs;
	long res;

	if (!try_get_task_stack(task))
		return -EFAULT;

	regs = task_pt_regs(task);
	res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
	put_task_stack(task);

	return res;
}

const struct bpf_func_proto bpf_get_task_stack_proto = {
	.func		= bpf_get_task_stack,
	.gpl_only	= false,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_BTF_ID,
	.arg1_btf_id	= &btf_task_struct_ids[0],
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg4_type	= ARG_ANYTHING,
};

BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
	   void *, buf, u32, size, u64, flags)
{
	struct pt_regs *regs = (struct pt_regs *)(ctx->regs);
	struct perf_event *event = ctx->event;
	struct perf_callchain_entry *trace;
	bool kernel, user;
	int err = -EINVAL;
	__u64 nr_kernel;

	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);

	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
			       BPF_F_USER_BUILD_ID)))
		goto clear;

	user = flags & BPF_F_USER_STACK;
	kernel = !user;

	err = -EFAULT;
	trace = ctx->data->callchain;
	if (unlikely(!trace))
		goto clear;

	nr_kernel = count_kernel_ip(trace);

	if (kernel) {
		__u64 nr = trace->nr;

		trace->nr = nr_kernel;
		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);

		/* restore nr */
		trace->nr = nr;
	} else { /* user */
		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;

		skip += nr_kernel;
		if (skip > BPF_F_SKIP_FIELD_MASK)
			goto clear;

		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
	}
	return err;

clear:
	memset(buf, 0, size);
	return err;

}

const struct bpf_func_proto bpf_get_stack_proto_pe = {
	.func		= bpf_get_stack_pe,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
	.arg4_type	= ARG_ANYTHING,
};

/* Called from eBPF program */
static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
{
	return ERR_PTR(-EOPNOTSUPP);
}

/* Called from syscall */
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
	struct stack_map_bucket *bucket, *old_bucket;
	u32 id = *(u32 *)key, trace_len;

	if (unlikely(id >= smap->n_buckets))
		return -ENOENT;

	bucket = xchg(&smap->buckets[id], NULL);
	if (!bucket)
		return -ENOENT;

	trace_len = bucket->nr * stack_map_data_size(map);
	memcpy(value, bucket->data, trace_len);
	memset(value + trace_len, 0, map->value_size - trace_len);

	old_bucket = xchg(&smap->buckets[id], bucket);
	if (old_bucket)
		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
	return 0;
}

static int stack_map_get_next_key(struct bpf_map *map, void *key,
				  void *next_key)
{
	struct bpf_stack_map *smap = container_of(map,
						  struct bpf_stack_map, map);
	u32 id;

	WARN_ON_ONCE(!rcu_read_lock_held());

	if (!key) {
		id = 0;
	} else {
		id = *(u32 *)key;
		if (id >= smap->n_buckets || !smap->buckets[id])
			id = 0;
		else
			id++;
	}

	while (id < smap->n_buckets && !smap->buckets[id])
		id++;

	if (id >= smap->n_buckets)
		return -ENOENT;

	*(u32 *)next_key = id;
	return 0;
}

static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
				 u64 map_flags)
{
	return -EINVAL;
}

/* Called from syscall or from eBPF program */
static int stack_map_delete_elem(struct bpf_map *map, void *key)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
	struct stack_map_bucket *old_bucket;
	u32 id = *(u32 *)key;

	if (unlikely(id >= smap->n_buckets))
		return -E2BIG;

	old_bucket = xchg(&smap->buckets[id], NULL);
	if (old_bucket) {
		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
		return 0;
	} else {
		return -ENOENT;
	}
}

/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void stack_map_free(struct bpf_map *map)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);

	bpf_map_area_free(smap->elems);
	pcpu_freelist_destroy(&smap->freelist);
	bpf_map_area_free(smap);
	put_callchain_buffers();
}

static int stack_trace_map_btf_id;
const struct bpf_map_ops stack_trace_map_ops = {
	.map_meta_equal = bpf_map_meta_equal,
	.map_alloc = stack_map_alloc,
	.map_free = stack_map_free,
	.map_get_next_key = stack_map_get_next_key,
	.map_lookup_elem = stack_map_lookup_elem,
	.map_update_elem = stack_map_update_elem,
	.map_delete_elem = stack_map_delete_elem,
	.map_check_btf = map_check_no_btf,
	.map_btf_name = "bpf_stack_map",
	.map_btf_id = &stack_trace_map_btf_id,
};

static int __init stack_map_init(void)
{
	int cpu;
	struct stack_map_irq_work *work;

	for_each_possible_cpu(cpu) {
		work = per_cpu_ptr(&up_read_work, cpu);
		init_irq_work(&work->irq_work, do_up_read);
	}
	return 0;
}
subsys_initcall(stack_map_init);