summaryrefslogtreecommitdiffstats
path: root/kernel/hw_breakpoint.c
blob: dd3fb4a999d346116461445d14e19ae633262183 (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
/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * 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/smp.h>

#include <linux/hw_breakpoint.h>

/*
 * Constraints data
 */

/* Number of pinned cpu breakpoints in a cpu */
static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);

/* Number of pinned task breakpoints in a cpu */
static DEFINE_PER_CPU(unsigned int, task_bp_pinned[HBP_NUM]);

/* Number of non-pinned cpu/task breakpoints in a cpu */
static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);

/* 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);

/*
 * Report the maximum number of pinned breakpoints a task
 * have in this cpu
 */
static unsigned int max_task_bp_pinned(int cpu)
{
	int i;
	unsigned int *tsk_pinned = per_cpu(task_bp_pinned, cpu);

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

	return 0;
}

/*
 * 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, int cpu)
{
	if (cpu >= 0) {
		slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
		slots->pinned += max_task_bp_pinned(cpu);
		slots->flexible = per_cpu(nr_bp_flexible, cpu);

		return;
	}

	for_each_online_cpu(cpu) {
		unsigned int nr;

		nr = per_cpu(nr_cpu_bp_pinned, cpu);
		nr += max_task_bp_pinned(cpu);

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

		nr = per_cpu(nr_bp_flexible, cpu);

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

/*
 * Add a pinned breakpoint for the given task in our constraint table
 */
static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
{
	int count = 0;
	struct perf_event *bp;
	struct perf_event_context *ctx = tsk->perf_event_ctxp;
	unsigned int *task_bp_pinned;
	struct list_head *list;
	unsigned long flags;

	if (WARN_ONCE(!ctx, "No perf context for this task"))
		return;

	list = &ctx->event_list;

	spin_lock_irqsave(&ctx->lock, flags);

	/*
	 * The current breakpoint counter is not included in the list
	 * at the open() callback time
	 */
	list_for_each_entry(bp, list, event_entry) {
		if (bp->attr.type == PERF_TYPE_BREAKPOINT)
			count++;
	}

	spin_unlock_irqrestore(&ctx->lock, flags);

	if (WARN_ONCE(count < 0, "No breakpoint counter found in the counter list"))
		return;

	task_bp_pinned = per_cpu(task_bp_pinned, cpu);
	if (enable) {
		task_bp_pinned[count]++;
		if (count > 0)
			task_bp_pinned[count-1]--;
	} else {
		task_bp_pinned[count]--;
		if (count > 0)
			task_bp_pinned[count-1]++;
	}
}

/*
 * Add/remove the given breakpoint in our constraint table
 */
static void toggle_bp_slot(struct perf_event *bp, bool enable)
{
	int cpu = bp->cpu;
	struct task_struct *tsk = bp->ctx->task;

	/* Pinned counter task profiling */
	if (tsk) {
		if (cpu >= 0) {
			toggle_bp_task_slot(tsk, cpu, enable);
			return;
		}

		for_each_online_cpu(cpu)
			toggle_bp_task_slot(tsk, cpu, enable);
		return;
	}

	/* Pinned counter cpu profiling */
	if (enable)
		per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
	else
		per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
}

/*
 * Contraints 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(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
 *           + max(per_cpu(task_bp_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(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
 *           + max(per_cpu(task_bp_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(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
 *            + max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
 *
 *       -> Same checks as before. But now the nr_bp_flexible, if any, must keep
 *          one register at least (or they will never be fed).
 *
 *   - If attached to every cpus, check:
 *
 *       ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
 *            + max(per_cpu(task_bp_pinned, *))) < HBP_NUM
 */
int reserve_bp_slot(struct perf_event *bp)
{
	struct bp_busy_slots slots = {0};
	int ret = 0;

	mutex_lock(&nr_bp_mutex);

	fetch_bp_busy_slots(&slots, bp->cpu);

	/* Flexible counters need to keep at least one slot */
	if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
		ret = -ENOSPC;
		goto end;
	}

	toggle_bp_slot(bp, true);

end:
	mutex_unlock(&nr_bp_mutex);

	return ret;
}

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

	toggle_bp_slot(bp, false);

	mutex_unlock(&nr_bp_mutex);
}


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

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

	/*
	 * Ptrace breakpoints can be temporary perf events only
	 * meant to reserve a slot. In this case, it is created disabled and
	 * we don't want to check the params right now (as we put a null addr)
	 * But perf tools create events as disabled and we want to check
	 * the params for them.
	 * This is a quick hack that will be removed soon, once we remove
	 * the tmp breakpoints from ptrace
	 */
	if (!bp->attr.disabled || bp->callback == perf_bp_event)
		ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);

	return ret;
}

int register_perf_hw_breakpoint(struct perf_event *bp)
{
	bp->callback = perf_bp_event;

	return __register_perf_hw_breakpoint(bp);
}

/*
 * Register a breakpoint bound to a task and a given cpu.
 * If cpu is -1, the breakpoint is active for the task in every cpu
 * If the task is -1, the breakpoint is active for every tasks in the given
 * cpu.
 */
static struct perf_event *
register_user_hw_breakpoint_cpu(unsigned long addr,
				int len,
				int type,
				perf_callback_t triggered,
				pid_t pid,
				int cpu,
				bool active)
{
	struct perf_event_attr *attr;
	struct perf_event *bp;

	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
	if (!attr)
		return ERR_PTR(-ENOMEM);

	attr->type = PERF_TYPE_BREAKPOINT;
	attr->size = sizeof(*attr);
	attr->bp_addr = addr;
	attr->bp_len = len;
	attr->bp_type = type;
	/*
	 * Such breakpoints are used by debuggers to trigger signals when
	 * we hit the excepted memory op. We can't miss such events, they
	 * must be pinned.
	 */
	attr->pinned = 1;

	if (!active)
		attr->disabled = 1;

	bp = perf_event_create_kernel_counter(attr, cpu, pid, triggered);
	kfree(attr);

	return bp;
}

/**
 * register_user_hw_breakpoint - register a hardware breakpoint for user space
 * @addr: is the memory address that triggers the breakpoint
 * @len: the length of the access to the memory (1 byte, 2 bytes etc...)
 * @type: the type of the access to the memory (read/write/exec)
 * @triggered: callback to trigger when we hit the breakpoint
 * @tsk: pointer to 'task_struct' of the process to which the address belongs
 * @active: should we activate it while registering it
 *
 */
struct perf_event *
register_user_hw_breakpoint(unsigned long addr,
			    int len,
			    int type,
			    perf_callback_t triggered,
			    struct task_struct *tsk,
			    bool active)
{
	return register_user_hw_breakpoint_cpu(addr, len, type, triggered,
					       tsk->pid, -1, active);
}
EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);

/**
 * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
 * @bp: the breakpoint structure to modify
 * @addr: is the memory address that triggers the breakpoint
 * @len: the length of the access to the memory (1 byte, 2 bytes etc...)
 * @type: the type of the access to the memory (read/write/exec)
 * @triggered: callback to trigger when we hit the breakpoint
 * @tsk: pointer to 'task_struct' of the process to which the address belongs
 * @active: should we activate it while registering it
 */
struct perf_event *
modify_user_hw_breakpoint(struct perf_event *bp,
			  unsigned long addr,
			  int len,
			  int type,
			  perf_callback_t triggered,
			  struct task_struct *tsk,
			  bool active)
{
	/*
	 * FIXME: do it without unregistering
	 * - We don't want to lose our slot
	 * - If the new bp is incorrect, don't lose the older one
	 */
	unregister_hw_breakpoint(bp);

	return register_user_hw_breakpoint(addr, len, type, triggered,
					   tsk, active);
}
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);

static struct perf_event *
register_kernel_hw_breakpoint_cpu(unsigned long addr,
				  int len,
				  int type,
				  perf_callback_t triggered,
				  int cpu,
				  bool active)
{
	return register_user_hw_breakpoint_cpu(addr, len, type, triggered,
					       -1, cpu, active);
}

/**
 * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
 * @addr: is the memory address that triggers the breakpoint
 * @len: the length of the access to the memory (1 byte, 2 bytes etc...)
 * @type: the type of the access to the memory (read/write/exec)
 * @triggered: callback to trigger when we hit the breakpoint
 * @active: should we activate it while registering it
 *
 * @return a set of per_cpu pointers to perf events
 */
struct perf_event **
register_wide_hw_breakpoint(unsigned long addr,
			    int len,
			    int type,
			    perf_callback_t triggered,
			    bool active)
{
	struct perf_event **cpu_events, **pevent, *bp;
	long err;
	int cpu;

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

	for_each_possible_cpu(cpu) {
		pevent = per_cpu_ptr(cpu_events, cpu);
		bp = register_kernel_hw_breakpoint_cpu(addr, len, type,
					triggered, cpu, active);

		*pevent = bp;

		if (IS_ERR(bp)) {
			err = PTR_ERR(bp);
			goto fail;
		}
	}

	return cpu_events;

fail:
	for_each_possible_cpu(cpu) {
		pevent = per_cpu_ptr(cpu_events, cpu);
		if (IS_ERR(*pevent))
			break;
		unregister_hw_breakpoint(*pevent);
	}
	free_percpu(cpu_events);
	/* return the error if any */
	return 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 **cpu_events)
{
	int cpu;
	struct perf_event **pevent;

	for_each_possible_cpu(cpu) {
		pevent = per_cpu_ptr(cpu_events, cpu);
		unregister_hw_breakpoint(*pevent);
	}
	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 int __init init_hw_breakpoint(void)
{
	return register_die_notifier(&hw_breakpoint_exceptions_nb);
}
core_initcall(init_hw_breakpoint);


struct pmu perf_ops_bp = {
	.enable		= arch_install_hw_breakpoint,
	.disable	= arch_uninstall_hw_breakpoint,
	.read		= hw_breakpoint_pmu_read,
	.unthrottle	= hw_breakpoint_pmu_unthrottle
};