summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/task_iter.c
blob: c2a2182ce570219bad9cc5362e15435d4873b6ba (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2020 Facebook */

#include <linux/init.h>
#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/fs.h>
#include <linux/fdtable.h>
#include <linux/filter.h>
#include <linux/btf_ids.h>
#include "mmap_unlock_work.h"

static const char * const iter_task_type_names[] = {
	"ALL",
	"TID",
	"PID",
};

struct bpf_iter_seq_task_common {
	struct pid_namespace *ns;
	enum bpf_iter_task_type	type;
	u32 pid;
	u32 pid_visiting;
};

struct bpf_iter_seq_task_info {
	/* The first field must be struct bpf_iter_seq_task_common.
	 * this is assumed by {init, fini}_seq_pidns() callback functions.
	 */
	struct bpf_iter_seq_task_common common;
	u32 tid;
};

static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_common *common,
						   u32 *tid,
						   bool skip_if_dup_files)
{
	struct task_struct *task, *next_task;
	struct pid *pid;
	u32 saved_tid;

	if (!*tid) {
		/* The first time, the iterator calls this function. */
		pid = find_pid_ns(common->pid, common->ns);
		if (!pid)
			return NULL;

		task = get_pid_task(pid, PIDTYPE_TGID);
		if (!task)
			return NULL;

		*tid = common->pid;
		common->pid_visiting = common->pid;

		return task;
	}

	/* If the control returns to user space and comes back to the
	 * kernel again, *tid and common->pid_visiting should be the
	 * same for task_seq_start() to pick up the correct task.
	 */
	if (*tid == common->pid_visiting) {
		pid = find_pid_ns(common->pid_visiting, common->ns);
		task = get_pid_task(pid, PIDTYPE_PID);

		return task;
	}

	pid = find_pid_ns(common->pid_visiting, common->ns);
	if (!pid)
		return NULL;

	task = get_pid_task(pid, PIDTYPE_PID);
	if (!task)
		return NULL;

retry:
	if (!pid_alive(task)) {
		put_task_struct(task);
		return NULL;
	}

	next_task = next_thread(task);
	put_task_struct(task);
	if (!next_task)
		return NULL;

	saved_tid = *tid;
	*tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns);
	if (!*tid || *tid == common->pid) {
		/* Run out of tasks of a process.  The tasks of a
		 * thread_group are linked as circular linked list.
		 */
		*tid = saved_tid;
		return NULL;
	}

	get_task_struct(next_task);
	common->pid_visiting = *tid;

	if (skip_if_dup_files && task->files == task->group_leader->files) {
		task = next_task;
		goto retry;
	}

	return next_task;
}

static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common,
					     u32 *tid,
					     bool skip_if_dup_files)
{
	struct task_struct *task = NULL;
	struct pid *pid;

	if (common->type == BPF_TASK_ITER_TID) {
		if (*tid && *tid != common->pid)
			return NULL;
		rcu_read_lock();
		pid = find_pid_ns(common->pid, common->ns);
		if (pid) {
			task = get_pid_task(pid, PIDTYPE_TGID);
			*tid = common->pid;
		}
		rcu_read_unlock();

		return task;
	}

	if (common->type == BPF_TASK_ITER_TGID) {
		rcu_read_lock();
		task = task_group_seq_get_next(common, tid, skip_if_dup_files);
		rcu_read_unlock();

		return task;
	}

	rcu_read_lock();
retry:
	pid = find_ge_pid(*tid, common->ns);
	if (pid) {
		*tid = pid_nr_ns(pid, common->ns);
		task = get_pid_task(pid, PIDTYPE_PID);
		if (!task) {
			++*tid;
			goto retry;
		} else if (skip_if_dup_files && !thread_group_leader(task) &&
			   task->files == task->group_leader->files) {
			put_task_struct(task);
			task = NULL;
			++*tid;
			goto retry;
		}
	}
	rcu_read_unlock();

	return task;
}

static void *task_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bpf_iter_seq_task_info *info = seq->private;
	struct task_struct *task;

	task = task_seq_get_next(&info->common, &info->tid, false);
	if (!task)
		return NULL;

	if (*pos == 0)
		++*pos;
	return task;
}

static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bpf_iter_seq_task_info *info = seq->private;
	struct task_struct *task;

	++*pos;
	++info->tid;
	put_task_struct((struct task_struct *)v);
	task = task_seq_get_next(&info->common, &info->tid, false);
	if (!task)
		return NULL;

	return task;
}

struct bpf_iter__task {
	__bpf_md_ptr(struct bpf_iter_meta *, meta);
	__bpf_md_ptr(struct task_struct *, task);
};

DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task)

static int __task_seq_show(struct seq_file *seq, struct task_struct *task,
			   bool in_stop)
{
	struct bpf_iter_meta meta;
	struct bpf_iter__task ctx;
	struct bpf_prog *prog;

	meta.seq = seq;
	prog = bpf_iter_get_info(&meta, in_stop);
	if (!prog)
		return 0;

	ctx.meta = &meta;
	ctx.task = task;
	return bpf_iter_run_prog(prog, &ctx);
}

static int task_seq_show(struct seq_file *seq, void *v)
{
	return __task_seq_show(seq, v, false);
}

static void task_seq_stop(struct seq_file *seq, void *v)
{
	if (!v)
		(void)__task_seq_show(seq, v, true);
	else
		put_task_struct((struct task_struct *)v);
}

static int bpf_iter_attach_task(struct bpf_prog *prog,
				union bpf_iter_link_info *linfo,
				struct bpf_iter_aux_info *aux)
{
	unsigned int flags;
	struct pid *pid;
	pid_t tgid;

	if ((!!linfo->task.tid + !!linfo->task.pid + !!linfo->task.pid_fd) > 1)
		return -EINVAL;

	aux->task.type = BPF_TASK_ITER_ALL;
	if (linfo->task.tid != 0) {
		aux->task.type = BPF_TASK_ITER_TID;
		aux->task.pid = linfo->task.tid;
	}
	if (linfo->task.pid != 0) {
		aux->task.type = BPF_TASK_ITER_TGID;
		aux->task.pid = linfo->task.pid;
	}
	if (linfo->task.pid_fd != 0) {
		aux->task.type = BPF_TASK_ITER_TGID;

		pid = pidfd_get_pid(linfo->task.pid_fd, &flags);
		if (IS_ERR(pid))
			return PTR_ERR(pid);

		tgid = pid_nr_ns(pid, task_active_pid_ns(current));
		aux->task.pid = tgid;
		put_pid(pid);
	}

	return 0;
}

static const struct seq_operations task_seq_ops = {
	.start	= task_seq_start,
	.next	= task_seq_next,
	.stop	= task_seq_stop,
	.show	= task_seq_show,
};

struct bpf_iter_seq_task_file_info {
	/* The first field must be struct bpf_iter_seq_task_common.
	 * this is assumed by {init, fini}_seq_pidns() callback functions.
	 */
	struct bpf_iter_seq_task_common common;
	struct task_struct *task;
	u32 tid;
	u32 fd;
};

static struct file *
task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)
{
	u32 saved_tid = info->tid;
	struct task_struct *curr_task;
	unsigned int curr_fd = info->fd;

	/* If this function returns a non-NULL file object,
	 * it held a reference to the task/file.
	 * Otherwise, it does not hold any reference.
	 */
again:
	if (info->task) {
		curr_task = info->task;
		curr_fd = info->fd;
	} else {
		curr_task = task_seq_get_next(&info->common, &info->tid, true);
                if (!curr_task) {
                        info->task = NULL;
                        return NULL;
                }

		/* set info->task */
		info->task = curr_task;
		if (saved_tid == info->tid)
			curr_fd = info->fd;
		else
			curr_fd = 0;
	}

	rcu_read_lock();
	for (;; curr_fd++) {
		struct file *f;
		f = task_lookup_next_fd_rcu(curr_task, &curr_fd);
		if (!f)
			break;
		if (!get_file_rcu(f))
			continue;

		/* set info->fd */
		info->fd = curr_fd;
		rcu_read_unlock();
		return f;
	}

	/* the current task is done, go to the next task */
	rcu_read_unlock();
	put_task_struct(curr_task);

	if (info->common.type == BPF_TASK_ITER_TID) {
		info->task = NULL;
		return NULL;
	}

	info->task = NULL;
	info->fd = 0;
	saved_tid = ++(info->tid);
	goto again;
}

static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bpf_iter_seq_task_file_info *info = seq->private;
	struct file *file;

	info->task = NULL;
	file = task_file_seq_get_next(info);
	if (file && *pos == 0)
		++*pos;

	return file;
}

static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bpf_iter_seq_task_file_info *info = seq->private;

	++*pos;
	++info->fd;
	fput((struct file *)v);
	return task_file_seq_get_next(info);
}

struct bpf_iter__task_file {
	__bpf_md_ptr(struct bpf_iter_meta *, meta);
	__bpf_md_ptr(struct task_struct *, task);
	u32 fd __aligned(8);
	__bpf_md_ptr(struct file *, file);
};

DEFINE_BPF_ITER_FUNC(task_file, struct bpf_iter_meta *meta,
		     struct task_struct *task, u32 fd,
		     struct file *file)

static int __task_file_seq_show(struct seq_file *seq, struct file *file,
				bool in_stop)
{
	struct bpf_iter_seq_task_file_info *info = seq->private;
	struct bpf_iter__task_file ctx;
	struct bpf_iter_meta meta;
	struct bpf_prog *prog;

	meta.seq = seq;
	prog = bpf_iter_get_info(&meta, in_stop);
	if (!prog)
		return 0;

	ctx.meta = &meta;
	ctx.task = info->task;
	ctx.fd = info->fd;
	ctx.file = file;
	return bpf_iter_run_prog(prog, &ctx);
}

static int task_file_seq_show(struct seq_file *seq, void *v)
{
	return __task_file_seq_show(seq, v, false);
}

static void task_file_seq_stop(struct seq_file *seq, void *v)
{
	struct bpf_iter_seq_task_file_info *info = seq->private;

	if (!v) {
		(void)__task_file_seq_show(seq, v, true);
	} else {
		fput((struct file *)v);
		put_task_struct(info->task);
		info->task = NULL;
	}
}

static int init_seq_pidns(void *priv_data, struct bpf_iter_aux_info *aux)
{
	struct bpf_iter_seq_task_common *common = priv_data;

	common->ns = get_pid_ns(task_active_pid_ns(current));
	common->type = aux->task.type;
	common->pid = aux->task.pid;

	return 0;
}

static void fini_seq_pidns(void *priv_data)
{
	struct bpf_iter_seq_task_common *common = priv_data;

	put_pid_ns(common->ns);
}

static const struct seq_operations task_file_seq_ops = {
	.start	= task_file_seq_start,
	.next	= task_file_seq_next,
	.stop	= task_file_seq_stop,
	.show	= task_file_seq_show,
};

struct bpf_iter_seq_task_vma_info {
	/* The first field must be struct bpf_iter_seq_task_common.
	 * this is assumed by {init, fini}_seq_pidns() callback functions.
	 */
	struct bpf_iter_seq_task_common common;
	struct task_struct *task;
	struct vm_area_struct *vma;
	u32 tid;
	unsigned long prev_vm_start;
	unsigned long prev_vm_end;
};

enum bpf_task_vma_iter_find_op {
	task_vma_iter_first_vma,   /* use find_vma() with addr 0 */
	task_vma_iter_next_vma,    /* use vma_next() with curr_vma */
	task_vma_iter_find_vma,    /* use find_vma() to find next vma */
};

static struct vm_area_struct *
task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
{
	enum bpf_task_vma_iter_find_op op;
	struct vm_area_struct *curr_vma;
	struct task_struct *curr_task;
	u32 saved_tid = info->tid;

	/* If this function returns a non-NULL vma, it holds a reference to
	 * the task_struct, and holds read lock on vma->mm->mmap_lock.
	 * If this function returns NULL, it does not hold any reference or
	 * lock.
	 */
	if (info->task) {
		curr_task = info->task;
		curr_vma = info->vma;
		/* In case of lock contention, drop mmap_lock to unblock
		 * the writer.
		 *
		 * After relock, call find(mm, prev_vm_end - 1) to find
		 * new vma to process.
		 *
		 *   +------+------+-----------+
		 *   | VMA1 | VMA2 | VMA3      |
		 *   +------+------+-----------+
		 *   |      |      |           |
		 *  4k     8k     16k         400k
		 *
		 * For example, curr_vma == VMA2. Before unlock, we set
		 *
		 *    prev_vm_start = 8k
		 *    prev_vm_end   = 16k
		 *
		 * There are a few cases:
		 *
		 * 1) VMA2 is freed, but VMA3 exists.
		 *
		 *    find_vma() will return VMA3, just process VMA3.
		 *
		 * 2) VMA2 still exists.
		 *
		 *    find_vma() will return VMA2, process VMA2->next.
		 *
		 * 3) no more vma in this mm.
		 *
		 *    Process the next task.
		 *
		 * 4) find_vma() returns a different vma, VMA2'.
		 *
		 *    4.1) If VMA2 covers same range as VMA2', skip VMA2',
		 *         because we already covered the range;
		 *    4.2) VMA2 and VMA2' covers different ranges, process
		 *         VMA2'.
		 */
		if (mmap_lock_is_contended(curr_task->mm)) {
			info->prev_vm_start = curr_vma->vm_start;
			info->prev_vm_end = curr_vma->vm_end;
			op = task_vma_iter_find_vma;
			mmap_read_unlock(curr_task->mm);
			if (mmap_read_lock_killable(curr_task->mm))
				goto finish;
		} else {
			op = task_vma_iter_next_vma;
		}
	} else {
again:
		curr_task = task_seq_get_next(&info->common, &info->tid, true);
		if (!curr_task) {
			info->tid++;
			goto finish;
		}

		if (saved_tid != info->tid) {
			/* new task, process the first vma */
			op = task_vma_iter_first_vma;
		} else {
			/* Found the same tid, which means the user space
			 * finished data in previous buffer and read more.
			 * We dropped mmap_lock before returning to user
			 * space, so it is necessary to use find_vma() to
			 * find the next vma to process.
			 */
			op = task_vma_iter_find_vma;
		}

		if (!curr_task->mm)
			goto next_task;

		if (mmap_read_lock_killable(curr_task->mm))
			goto finish;
	}

	switch (op) {
	case task_vma_iter_first_vma:
		curr_vma = find_vma(curr_task->mm, 0);
		break;
	case task_vma_iter_next_vma:
		curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
		break;
	case task_vma_iter_find_vma:
		/* We dropped mmap_lock so it is necessary to use find_vma
		 * to find the next vma. This is similar to the  mechanism
		 * in show_smaps_rollup().
		 */
		curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
		/* case 1) and 4.2) above just use curr_vma */

		/* check for case 2) or case 4.1) above */
		if (curr_vma &&
		    curr_vma->vm_start == info->prev_vm_start &&
		    curr_vma->vm_end == info->prev_vm_end)
			curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
		break;
	}
	if (!curr_vma) {
		/* case 3) above, or case 2) 4.1) with vma->next == NULL */
		mmap_read_unlock(curr_task->mm);
		goto next_task;
	}
	info->task = curr_task;
	info->vma = curr_vma;
	return curr_vma;

next_task:
	if (info->common.type == BPF_TASK_ITER_TID)
		goto finish;

	put_task_struct(curr_task);
	info->task = NULL;
	info->tid++;
	goto again;

finish:
	if (curr_task)
		put_task_struct(curr_task);
	info->task = NULL;
	info->vma = NULL;
	return NULL;
}

static void *task_vma_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bpf_iter_seq_task_vma_info *info = seq->private;
	struct vm_area_struct *vma;

	vma = task_vma_seq_get_next(info);
	if (vma && *pos == 0)
		++*pos;

	return vma;
}

static void *task_vma_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bpf_iter_seq_task_vma_info *info = seq->private;

	++*pos;
	return task_vma_seq_get_next(info);
}

struct bpf_iter__task_vma {
	__bpf_md_ptr(struct bpf_iter_meta *, meta);
	__bpf_md_ptr(struct task_struct *, task);
	__bpf_md_ptr(struct vm_area_struct *, vma);
};

DEFINE_BPF_ITER_FUNC(task_vma, struct bpf_iter_meta *meta,
		     struct task_struct *task, struct vm_area_struct *vma)

static int __task_vma_seq_show(struct seq_file *seq, bool in_stop)
{
	struct bpf_iter_seq_task_vma_info *info = seq->private;
	struct bpf_iter__task_vma ctx;
	struct bpf_iter_meta meta;
	struct bpf_prog *prog;

	meta.seq = seq;
	prog = bpf_iter_get_info(&meta, in_stop);
	if (!prog)
		return 0;

	ctx.meta = &meta;
	ctx.task = info->task;
	ctx.vma = info->vma;
	return bpf_iter_run_prog(prog, &ctx);
}

static int task_vma_seq_show(struct seq_file *seq, void *v)
{
	return __task_vma_seq_show(seq, false);
}

static void task_vma_seq_stop(struct seq_file *seq, void *v)
{
	struct bpf_iter_seq_task_vma_info *info = seq->private;

	if (!v) {
		(void)__task_vma_seq_show(seq, true);
	} else {
		/* info->vma has not been seen by the BPF program. If the
		 * user space reads more, task_vma_seq_get_next should
		 * return this vma again. Set prev_vm_start to ~0UL,
		 * so that we don't skip the vma returned by the next
		 * find_vma() (case task_vma_iter_find_vma in
		 * task_vma_seq_get_next()).
		 */
		info->prev_vm_start = ~0UL;
		info->prev_vm_end = info->vma->vm_end;
		mmap_read_unlock(info->task->mm);
		put_task_struct(info->task);
		info->task = NULL;
	}
}

static const struct seq_operations task_vma_seq_ops = {
	.start	= task_vma_seq_start,
	.next	= task_vma_seq_next,
	.stop	= task_vma_seq_stop,
	.show	= task_vma_seq_show,
};

static const struct bpf_iter_seq_info task_seq_info = {
	.seq_ops		= &task_seq_ops,
	.init_seq_private	= init_seq_pidns,
	.fini_seq_private	= fini_seq_pidns,
	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_info),
};

static int bpf_iter_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info)
{
	switch (aux->task.type) {
	case BPF_TASK_ITER_TID:
		info->iter.task.tid = aux->task.pid;
		break;
	case BPF_TASK_ITER_TGID:
		info->iter.task.pid = aux->task.pid;
		break;
	default:
		break;
	}
	return 0;
}

static void bpf_iter_task_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq)
{
	seq_printf(seq, "task_type:\t%s\n", iter_task_type_names[aux->task.type]);
	if (aux->task.type == BPF_TASK_ITER_TID)
		seq_printf(seq, "tid:\t%u\n", aux->task.pid);
	else if (aux->task.type == BPF_TASK_ITER_TGID)
		seq_printf(seq, "pid:\t%u\n", aux->task.pid);
}

static struct bpf_iter_reg task_reg_info = {
	.target			= "task",
	.attach_target		= bpf_iter_attach_task,
	.feature		= BPF_ITER_RESCHED,
	.ctx_arg_info_size	= 1,
	.ctx_arg_info		= {
		{ offsetof(struct bpf_iter__task, task),
		  PTR_TO_BTF_ID_OR_NULL },
	},
	.seq_info		= &task_seq_info,
	.fill_link_info		= bpf_iter_fill_link_info,
	.show_fdinfo		= bpf_iter_task_show_fdinfo,
};

static const struct bpf_iter_seq_info task_file_seq_info = {
	.seq_ops		= &task_file_seq_ops,
	.init_seq_private	= init_seq_pidns,
	.fini_seq_private	= fini_seq_pidns,
	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_file_info),
};

static struct bpf_iter_reg task_file_reg_info = {
	.target			= "task_file",
	.attach_target		= bpf_iter_attach_task,
	.feature		= BPF_ITER_RESCHED,
	.ctx_arg_info_size	= 2,
	.ctx_arg_info		= {
		{ offsetof(struct bpf_iter__task_file, task),
		  PTR_TO_BTF_ID_OR_NULL },
		{ offsetof(struct bpf_iter__task_file, file),
		  PTR_TO_BTF_ID_OR_NULL },
	},
	.seq_info		= &task_file_seq_info,
	.fill_link_info		= bpf_iter_fill_link_info,
	.show_fdinfo		= bpf_iter_task_show_fdinfo,
};

static const struct bpf_iter_seq_info task_vma_seq_info = {
	.seq_ops		= &task_vma_seq_ops,
	.init_seq_private	= init_seq_pidns,
	.fini_seq_private	= fini_seq_pidns,
	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_vma_info),
};

static struct bpf_iter_reg task_vma_reg_info = {
	.target			= "task_vma",
	.attach_target		= bpf_iter_attach_task,
	.feature		= BPF_ITER_RESCHED,
	.ctx_arg_info_size	= 2,
	.ctx_arg_info		= {
		{ offsetof(struct bpf_iter__task_vma, task),
		  PTR_TO_BTF_ID_OR_NULL },
		{ offsetof(struct bpf_iter__task_vma, vma),
		  PTR_TO_BTF_ID_OR_NULL },
	},
	.seq_info		= &task_vma_seq_info,
	.fill_link_info		= bpf_iter_fill_link_info,
	.show_fdinfo		= bpf_iter_task_show_fdinfo,
};

BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
	   bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags)
{
	struct mmap_unlock_irq_work *work = NULL;
	struct vm_area_struct *vma;
	bool irq_work_busy = false;
	struct mm_struct *mm;
	int ret = -ENOENT;

	if (flags)
		return -EINVAL;

	if (!task)
		return -ENOENT;

	mm = task->mm;
	if (!mm)
		return -ENOENT;

	irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);

	if (irq_work_busy || !mmap_read_trylock(mm))
		return -EBUSY;

	vma = find_vma(mm, start);

	if (vma && vma->vm_start <= start && vma->vm_end > start) {
		callback_fn((u64)(long)task, (u64)(long)vma,
			    (u64)(long)callback_ctx, 0, 0);
		ret = 0;
	}
	bpf_mmap_unlock_mm(work, mm);
	return ret;
}

const struct bpf_func_proto bpf_find_vma_proto = {
	.func		= bpf_find_vma,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_BTF_ID,
	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
	.arg2_type	= ARG_ANYTHING,
	.arg3_type	= ARG_PTR_TO_FUNC,
	.arg4_type	= ARG_PTR_TO_STACK_OR_NULL,
	.arg5_type	= ARG_ANYTHING,
};

DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);

static void do_mmap_read_unlock(struct irq_work *entry)
{
	struct mmap_unlock_irq_work *work;

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

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

static int __init task_iter_init(void)
{
	struct mmap_unlock_irq_work *work;
	int ret, cpu;

	for_each_possible_cpu(cpu) {
		work = per_cpu_ptr(&mmap_unlock_work, cpu);
		init_irq_work(&work->irq_work, do_mmap_read_unlock);
	}

	task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
	ret = bpf_iter_reg_target(&task_reg_info);
	if (ret)
		return ret;

	task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
	task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE];
	ret =  bpf_iter_reg_target(&task_file_reg_info);
	if (ret)
		return ret;

	task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
	return bpf_iter_reg_target(&task_vma_reg_info);
}
late_initcall(task_iter_init);