summaryrefslogtreecommitdiffstats
path: root/kernel/events/hw_breakpoint.c
blob: f32320ac02fd8b79fef8c1333a4e167f27b4200e (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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2007 Alan Stern
 * Copyright (C) IBM Corporation, 2009
 * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
 *
 * Thanks to Ingo Molnar for his many suggestions.
 *
 * Authors: Alan Stern <stern@rowland.harvard.edu>
 *          K.Prasad <prasad@linux.vnet.ibm.com>
 *          Frederic Weisbecker <fweisbec@gmail.com>
 */

/*
 * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
 * using the CPU's debug registers.
 * This file contains the arch-independent routines.
 */

#include <linux/irqflags.h>
#include <linux/kallsyms.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/bug.h>

#include <linux/hw_breakpoint.h>
/*
 * Constraints data
 */
struct bp_cpuinfo {
	/* Number of pinned cpu breakpoints in a cpu */
	unsigned int	cpu_pinned;
	/* tsk_pinned[n] is the number of tasks having n+1 breakpoints */
	unsigned int	*tsk_pinned;
	/* Number of non-pinned cpu/task breakpoints in a cpu */
	unsigned int	flexible; /* XXX: placeholder, see fetch_this_slot() */
};

static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]);
static int nr_slots[TYPE_MAX];

static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
{
	return per_cpu_ptr(bp_cpuinfo + type, cpu);
}

/* Keep track of the breakpoints attached to tasks */
static LIST_HEAD(bp_task_head);

static int constraints_initialized;

/* Gather the number of total pinned and un-pinned bp in a cpuset */
struct bp_busy_slots {
	unsigned int pinned;
	unsigned int flexible;
};

/* Serialize accesses to the above constraints */
static DEFINE_MUTEX(nr_bp_mutex);

__weak int hw_breakpoint_weight(struct perf_event *bp)
{
	return 1;
}

static inline enum bp_type_idx find_slot_idx(u64 bp_type)
{
	if (bp_type & HW_BREAKPOINT_RW)
		return TYPE_DATA;

	return TYPE_INST;
}

/*
 * Report the maximum number of pinned breakpoints a task
 * have in this cpu
 */
static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
{
	unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
	int i;

	for (i = nr_slots[type] - 1; i >= 0; i--) {
		if (tsk_pinned[i] > 0)
			return i + 1;
	}

	return 0;
}

/*
 * Count the number of breakpoints of the same type and same task.
 * The given event must be not on the list.
 */
static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
{
	struct task_struct *tsk = bp->hw.target;
	struct perf_event *iter;
	int count = 0;

	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
		if (iter->hw.target == tsk &&
		    find_slot_idx(iter->attr.bp_type) == type &&
		    (iter->cpu < 0 || cpu == iter->cpu))
			count += hw_breakpoint_weight(iter);
	}

	return count;
}

static const struct cpumask *cpumask_of_bp(struct perf_event *bp)
{
	if (bp->cpu >= 0)
		return cpumask_of(bp->cpu);
	return cpu_possible_mask;
}

/*
 * Report the number of pinned/un-pinned breakpoints we have in
 * a given cpu (cpu > -1) or in all of them (cpu = -1).
 */
static void
fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
		    enum bp_type_idx type)
{
	const struct cpumask *cpumask = cpumask_of_bp(bp);
	int cpu;

	for_each_cpu(cpu, cpumask) {
		struct bp_cpuinfo *info = get_bp_info(cpu, type);
		int nr;

		nr = info->cpu_pinned;
		if (!bp->hw.target)
			nr += max_task_bp_pinned(cpu, type);
		else
			nr += task_bp_pinned(cpu, bp, type);

		if (nr > slots->pinned)
			slots->pinned = nr;

		nr = info->flexible;
		if (nr > slots->flexible)
			slots->flexible = nr;
	}
}

/*
 * For now, continue to consider flexible as pinned, until we can
 * ensure no flexible event can ever be scheduled before a pinned event
 * in a same cpu.
 */
static void
fetch_this_slot(struct bp_busy_slots *slots, int weight)
{
	slots->pinned += weight;
}

/*
 * Add a pinned breakpoint for the given task in our constraint table
 */
static void toggle_bp_task_slot(struct perf_event *bp, int cpu,
				enum bp_type_idx type, int weight)
{
	unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
	int old_idx, new_idx;

	old_idx = task_bp_pinned(cpu, bp, type) - 1;
	new_idx = old_idx + weight;

	if (old_idx >= 0)
		tsk_pinned[old_idx]--;
	if (new_idx >= 0)
		tsk_pinned[new_idx]++;
}

/*
 * Add/remove the given breakpoint in our constraint table
 */
static void
toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
	       int weight)
{
	const struct cpumask *cpumask = cpumask_of_bp(bp);
	int cpu;

	if (!enable)
		weight = -weight;

	/* Pinned counter cpu profiling */
	if (!bp->hw.target) {
		get_bp_info(bp->cpu, type)->cpu_pinned += weight;
		return;
	}

	/* Pinned counter task profiling */
	for_each_cpu(cpu, cpumask)
		toggle_bp_task_slot(bp, cpu, type, weight);

	if (enable)
		list_add_tail(&bp->hw.bp_list, &bp_task_head);
	else
		list_del(&bp->hw.bp_list);
}

__weak int arch_reserve_bp_slot(struct perf_event *bp)
{
	return 0;
}

__weak void arch_release_bp_slot(struct perf_event *bp)
{
}

/*
 * Function to perform processor-specific cleanup during unregistration
 */
__weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
{
	/*
	 * A weak stub function here for those archs that don't define
	 * it inside arch/.../kernel/hw_breakpoint.c
	 */
}

/*
 * Constraints to check before allowing this new breakpoint counter:
 *
 *  == Non-pinned counter == (Considered as pinned for now)
 *
 *   - If attached to a single cpu, check:
 *
 *       (per_cpu(info->flexible, cpu) || (per_cpu(info->cpu_pinned, cpu)
 *           + max(per_cpu(info->tsk_pinned, cpu)))) < HBP_NUM
 *
 *       -> If there are already non-pinned counters in this cpu, it means
 *          there is already a free slot for them.
 *          Otherwise, we check that the maximum number of per task
 *          breakpoints (for this cpu) plus the number of per cpu breakpoint
 *          (for this cpu) doesn't cover every registers.
 *
 *   - If attached to every cpus, check:
 *
 *       (per_cpu(info->flexible, *) || (max(per_cpu(info->cpu_pinned, *))
 *           + max(per_cpu(info->tsk_pinned, *)))) < HBP_NUM
 *
 *       -> This is roughly the same, except we check the number of per cpu
 *          bp for every cpu and we keep the max one. Same for the per tasks
 *          breakpoints.
 *
 *
 * == Pinned counter ==
 *
 *   - If attached to a single cpu, check:
 *
 *       ((per_cpu(info->flexible, cpu) > 1) + per_cpu(info->cpu_pinned, cpu)
 *            + max(per_cpu(info->tsk_pinned, cpu))) < HBP_NUM
 *
 *       -> Same checks as before. But now the info->flexible, if any, must keep
 *          one register at least (or they will never be fed).
 *
 *   - If attached to every cpus, check:
 *
 *       ((per_cpu(info->flexible, *) > 1) + max(per_cpu(info->cpu_pinned, *))
 *            + max(per_cpu(info->tsk_pinned, *))) < HBP_NUM
 */
static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
{
	struct bp_busy_slots slots = {0};
	enum bp_type_idx type;
	int weight;
	int ret;

	/* We couldn't initialize breakpoint constraints on boot */
	if (!constraints_initialized)
		return -ENOMEM;

	/* Basic checks */
	if (bp_type == HW_BREAKPOINT_EMPTY ||
	    bp_type == HW_BREAKPOINT_INVALID)
		return -EINVAL;

	type = find_slot_idx(bp_type);
	weight = hw_breakpoint_weight(bp);

	fetch_bp_busy_slots(&slots, bp, type);
	/*
	 * Simulate the addition of this breakpoint to the constraints
	 * and see the result.
	 */
	fetch_this_slot(&slots, weight);

	/* Flexible counters need to keep at least one slot */
	if (slots.pinned + (!!slots.flexible) > nr_slots[type])
		return -ENOSPC;

	ret = arch_reserve_bp_slot(bp);
	if (ret)
		return ret;

	toggle_bp_slot(bp, true, type, weight);

	return 0;
}

int reserve_bp_slot(struct perf_event *bp)
{
	int ret;

	mutex_lock(&nr_bp_mutex);

	ret = __reserve_bp_slot(bp, bp->attr.bp_type);

	mutex_unlock(&nr_bp_mutex);

	return ret;
}

static void __release_bp_slot(struct perf_event *bp, u64 bp_type)
{
	enum bp_type_idx type;
	int weight;

	arch_release_bp_slot(bp);

	type = find_slot_idx(bp_type);
	weight = hw_breakpoint_weight(bp);
	toggle_bp_slot(bp, false, type, weight);
}

void release_bp_slot(struct perf_event *bp)
{
	mutex_lock(&nr_bp_mutex);

	arch_unregister_hw_breakpoint(bp);
	__release_bp_slot(bp, bp->attr.bp_type);

	mutex_unlock(&nr_bp_mutex);
}

static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
	int err;

	__release_bp_slot(bp, old_type);

	err = __reserve_bp_slot(bp, new_type);
	if (err) {
		/*
		 * Reserve the old_type slot back in case
		 * there's no space for the new type.
		 *
		 * This must succeed, because we just released
		 * the old_type slot in the __release_bp_slot
		 * call above. If not, something is broken.
		 */
		WARN_ON(__reserve_bp_slot(bp, old_type));
	}

	return err;
}

static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
{
	int ret;

	mutex_lock(&nr_bp_mutex);
	ret = __modify_bp_slot(bp, old_type, new_type);
	mutex_unlock(&nr_bp_mutex);
	return ret;
}

/*
 * Allow the kernel debugger to reserve breakpoint slots without
 * taking a lock using the dbg_* variant of for the reserve and
 * release breakpoint slots.
 */
int dbg_reserve_bp_slot(struct perf_event *bp)
{
	if (mutex_is_locked(&nr_bp_mutex))
		return -1;

	return __reserve_bp_slot(bp, bp->attr.bp_type);
}

int dbg_release_bp_slot(struct perf_event *bp)
{
	if (mutex_is_locked(&nr_bp_mutex))
		return -1;

	__release_bp_slot(bp, bp->attr.bp_type);

	return 0;
}

static int hw_breakpoint_parse(struct perf_event *bp,
			       const struct perf_event_attr *attr,
			       struct arch_hw_breakpoint *hw)
{
	int err;

	err = hw_breakpoint_arch_parse(bp, attr, hw);
	if (err)
		return err;

	if (arch_check_bp_in_kernelspace(hw)) {
		if (attr->exclude_kernel)
			return -EINVAL;
		/*
		 * Don't let unprivileged users set a breakpoint in the trap
		 * path to avoid trap recursion attacks.
		 */
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;
	}

	return 0;
}

int register_perf_hw_breakpoint(struct perf_event *bp)
{
	struct arch_hw_breakpoint hw = { };
	int err;

	err = reserve_bp_slot(bp);
	if (err)
		return err;

	err = hw_breakpoint_parse(bp, &bp->attr, &hw);
	if (err) {
		release_bp_slot(bp);
		return err;
	}

	bp->hw.info = hw;

	return 0;
}

/**
 * register_user_hw_breakpoint - register a hardware breakpoint for user space
 * @attr: breakpoint attributes
 * @triggered: callback to trigger when we hit the breakpoint
 * @context: context data could be used in the triggered callback
 * @tsk: pointer to 'task_struct' of the process to which the address belongs
 */
struct perf_event *
register_user_hw_breakpoint(struct perf_event_attr *attr,
			    perf_overflow_handler_t triggered,
			    void *context,
			    struct task_struct *tsk)
{
	return perf_event_create_kernel_counter(attr, -1, tsk, triggered,
						context);
}
EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);

static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
				    struct perf_event_attr *from)
{
	to->bp_addr = from->bp_addr;
	to->bp_type = from->bp_type;
	to->bp_len  = from->bp_len;
	to->disabled = from->disabled;
}

int
modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
			        bool check)
{
	struct arch_hw_breakpoint hw = { };
	int err;

	err = hw_breakpoint_parse(bp, attr, &hw);
	if (err)
		return err;

	if (check) {
		struct perf_event_attr old_attr;

		old_attr = bp->attr;
		hw_breakpoint_copy_attr(&old_attr, attr);
		if (memcmp(&old_attr, attr, sizeof(*attr)))
			return -EINVAL;
	}

	if (bp->attr.bp_type != attr->bp_type) {
		err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
		if (err)
			return err;
	}

	hw_breakpoint_copy_attr(&bp->attr, attr);
	bp->hw.info = hw;

	return 0;
}

/**
 * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
 * @bp: the breakpoint structure to modify
 * @attr: new breakpoint attributes
 */
int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
{
	int err;

	/*
	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
	 * will not be possible to raise IPIs that invoke __perf_event_disable.
	 * So call the function directly after making sure we are targeting the
	 * current task.
	 */
	if (irqs_disabled() && bp->ctx && bp->ctx->task == current)
		perf_event_disable_local(bp);
	else
		perf_event_disable(bp);

	err = modify_user_hw_breakpoint_check(bp, attr, false);

	if (!bp->attr.disabled)
		perf_event_enable(bp);

	return err;
}
EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);

/**
 * unregister_hw_breakpoint - unregister a user-space hardware breakpoint
 * @bp: the breakpoint structure to unregister
 */
void unregister_hw_breakpoint(struct perf_event *bp)
{
	if (!bp)
		return;
	perf_event_release_kernel(bp);
}
EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);

/**
 * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
 * @attr: breakpoint attributes
 * @triggered: callback to trigger when we hit the breakpoint
 * @context: context data could be used in the triggered callback
 *
 * @return a set of per_cpu pointers to perf events
 */
struct perf_event * __percpu *
register_wide_hw_breakpoint(struct perf_event_attr *attr,
			    perf_overflow_handler_t triggered,
			    void *context)
{
	struct perf_event * __percpu *cpu_events, *bp;
	long err = 0;
	int cpu;

	cpu_events = alloc_percpu(typeof(*cpu_events));
	if (!cpu_events)
		return (void __percpu __force *)ERR_PTR(-ENOMEM);

	cpus_read_lock();
	for_each_online_cpu(cpu) {
		bp = perf_event_create_kernel_counter(attr, cpu, NULL,
						      triggered, context);
		if (IS_ERR(bp)) {
			err = PTR_ERR(bp);
			break;
		}

		per_cpu(*cpu_events, cpu) = bp;
	}
	cpus_read_unlock();

	if (likely(!err))
		return cpu_events;

	unregister_wide_hw_breakpoint(cpu_events);
	return (void __percpu __force *)ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);

/**
 * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
 * @cpu_events: the per cpu set of events to unregister
 */
void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
{
	int cpu;

	for_each_possible_cpu(cpu)
		unregister_hw_breakpoint(per_cpu(*cpu_events, cpu));

	free_percpu(cpu_events);
}
EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);

static struct notifier_block hw_breakpoint_exceptions_nb = {
	.notifier_call = hw_breakpoint_exceptions_notify,
	/* we need to be notified first */
	.priority = 0x7fffffff
};

static void bp_perf_event_destroy(struct perf_event *event)
{
	release_bp_slot(event);
}

static int hw_breakpoint_event_init(struct perf_event *bp)
{
	int err;

	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
		return -ENOENT;

	/*
	 * no branch sampling for breakpoint events
	 */
	if (has_branch_stack(bp))
		return -EOPNOTSUPP;

	err = register_perf_hw_breakpoint(bp);
	if (err)
		return err;

	bp->destroy = bp_perf_event_destroy;

	return 0;
}

static int hw_breakpoint_add(struct perf_event *bp, int flags)
{
	if (!(flags & PERF_EF_START))
		bp->hw.state = PERF_HES_STOPPED;

	if (is_sampling_event(bp)) {
		bp->hw.last_period = bp->hw.sample_period;
		perf_swevent_set_period(bp);
	}

	return arch_install_hw_breakpoint(bp);
}

static void hw_breakpoint_del(struct perf_event *bp, int flags)
{
	arch_uninstall_hw_breakpoint(bp);
}

static void hw_breakpoint_start(struct perf_event *bp, int flags)
{
	bp->hw.state = 0;
}

static void hw_breakpoint_stop(struct perf_event *bp, int flags)
{
	bp->hw.state = PERF_HES_STOPPED;
}

static struct pmu perf_breakpoint = {
	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */

	.event_init	= hw_breakpoint_event_init,
	.add		= hw_breakpoint_add,
	.del		= hw_breakpoint_del,
	.start		= hw_breakpoint_start,
	.stop		= hw_breakpoint_stop,
	.read		= hw_breakpoint_pmu_read,
};

int __init init_hw_breakpoint(void)
{
	int cpu, err_cpu;
	int i;

	for (i = 0; i < TYPE_MAX; i++)
		nr_slots[i] = hw_breakpoint_slots(i);

	for_each_possible_cpu(cpu) {
		for (i = 0; i < TYPE_MAX; i++) {
			struct bp_cpuinfo *info = get_bp_info(cpu, i);

			info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
							GFP_KERNEL);
			if (!info->tsk_pinned)
				goto err_alloc;
		}
	}

	constraints_initialized = 1;

	perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);

	return register_die_notifier(&hw_breakpoint_exceptions_nb);

 err_alloc:
	for_each_possible_cpu(err_cpu) {
		for (i = 0; i < TYPE_MAX; i++)
			kfree(get_bp_info(err_cpu, i)->tsk_pinned);
		if (err_cpu == cpu)
			break;
	}

	return -ENOMEM;
}