ftrace.c 40.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 * Infrastructure for profiling code inserted by 'gcc -pg'.
 *
 * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
 * Copyright (C) 2004-2008 Ingo Molnar <mingo@redhat.com>
 *
 * Originally ported from the -rt patch by:
 *   Copyright (C) 2007 Arnaldo Carvalho de Melo <acme@redhat.com>
 *
 * Based on code in the latency_tracer, that is:
 *
 *  Copyright (C) 2004-2006 Ingo Molnar
 *  Copyright (C) 2004 William Lee Irwin III
 */

16 17 18
#include <linux/stop_machine.h>
#include <linux/clocksource.h>
#include <linux/kallsyms.h>
19 20
#include <linux/seq_file.h>
#include <linux/debugfs.h>
21
#include <linux/hardirq.h>
I
Ingo Molnar 已提交
22
#include <linux/kthread.h>
23
#include <linux/uaccess.h>
24
#include <linux/kprobes.h>
I
Ingo Molnar 已提交
25
#include <linux/ftrace.h>
26
#include <linux/sysctl.h>
27
#include <linux/ctype.h>
I
Ingo Molnar 已提交
28
#include <linux/hash.h>
29 30
#include <linux/list.h>

31 32
#include <asm/ftrace.h>

33
#include "trace.h"
34

35 36 37 38 39 40 41 42 43 44 45 46
#define FTRACE_WARN_ON(cond)			\
	do {					\
		if (WARN_ON(cond))		\
			ftrace_kill();		\
	} while (0)

#define FTRACE_WARN_ON_ONCE(cond)		\
	do {					\
		if (WARN_ON_ONCE(cond))		\
			ftrace_kill();		\
	} while (0)

47 48
/* ftrace_enabled is a method to turn ftrace on or off */
int ftrace_enabled __read_mostly;
49
static int last_ftrace_enabled;
50

51 52 53 54 55 56
/*
 * ftrace_disabled is set when an anomaly is discovered.
 * ftrace_disabled is much stronger than ftrace_enabled.
 */
static int ftrace_disabled __read_mostly;

57
static DEFINE_SPINLOCK(ftrace_lock);
58 59
static DEFINE_MUTEX(ftrace_sysctl_lock);

60 61 62 63 64 65 66 67
static struct ftrace_ops ftrace_list_end __read_mostly =
{
	.func = ftrace_stub,
};

static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;

I
Ingo Molnar 已提交
68
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
69 70 71 72 73 74 75 76 77 78 79 80 81 82 83
{
	struct ftrace_ops *op = ftrace_list;

	/* in case someone actually ports this to alpha! */
	read_barrier_depends();

	while (op != &ftrace_list_end) {
		/* silly alpha */
		read_barrier_depends();
		op->func(ip, parent_ip);
		op = op->next;
	};
}

/**
84
 * clear_ftrace_function - reset the ftrace function
85
 *
86 87
 * This NULLs the ftrace function and in essence stops
 * tracing.  There may be lag
88
 */
89
void clear_ftrace_function(void)
90
{
91 92 93
	ftrace_trace_function = ftrace_stub;
}

I
Ingo Molnar 已提交
94
static int __register_ftrace_function(struct ftrace_ops *ops)
95
{
96
	/* should not be called from interrupt context */
97
	spin_lock(&ftrace_lock);
98 99 100 101 102 103 104 105 106 107

	ops->next = ftrace_list;
	/*
	 * We are entering ops into the ftrace_list but another
	 * CPU might be walking that list. We need to make sure
	 * the ops->next pointer is valid before another CPU sees
	 * the ops pointer included into the ftrace_list.
	 */
	smp_wmb();
	ftrace_list = ops;
108

109 110 111 112 113 114 115 116 117 118
	if (ftrace_enabled) {
		/*
		 * For one func, simply call it directly.
		 * For more than one func, call the chain.
		 */
		if (ops->next == &ftrace_list_end)
			ftrace_trace_function = ops->func;
		else
			ftrace_trace_function = ftrace_list_func;
	}
119 120

	spin_unlock(&ftrace_lock);
121 122 123 124

	return 0;
}

I
Ingo Molnar 已提交
125
static int __unregister_ftrace_function(struct ftrace_ops *ops)
126 127 128 129
{
	struct ftrace_ops **p;
	int ret = 0;

130
	/* should not be called from interrupt context */
131
	spin_lock(&ftrace_lock);
132 133

	/*
134 135
	 * If we are removing the last function, then simply point
	 * to the ftrace_stub.
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
	 */
	if (ftrace_list == ops && ops->next == &ftrace_list_end) {
		ftrace_trace_function = ftrace_stub;
		ftrace_list = &ftrace_list_end;
		goto out;
	}

	for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next)
		if (*p == ops)
			break;

	if (*p != ops) {
		ret = -1;
		goto out;
	}

	*p = (*p)->next;

154 155 156 157 158 159
	if (ftrace_enabled) {
		/* If we only have one func left, then call that directly */
		if (ftrace_list == &ftrace_list_end ||
		    ftrace_list->next == &ftrace_list_end)
			ftrace_trace_function = ftrace_list->func;
	}
160 161

 out:
162 163 164 165 166 167 168
	spin_unlock(&ftrace_lock);

	return ret;
}

#ifdef CONFIG_DYNAMIC_FTRACE

169 170 171 172 173 174 175
#ifndef CONFIG_FTRACE_MCOUNT_RECORD
/*
 * The hash lock is only needed when the recording of the mcount
 * callers are dynamic. That is, by the caller themselves and
 * not recorded via the compilation.
 */
static DEFINE_SPINLOCK(ftrace_hash_lock);
S
Stephen Rothwell 已提交
176
#define ftrace_hash_lock(flags)	  spin_lock_irqsave(&ftrace_hash_lock, flags)
S
Steven Rostedt 已提交
177 178
#define ftrace_hash_unlock(flags) \
			spin_unlock_irqrestore(&ftrace_hash_lock, flags)
179
static void ftrace_release_hash(unsigned long start, unsigned long end);
180 181
#else
/* This is protected via the ftrace_lock with MCOUNT_RECORD. */
I
Ingo Molnar 已提交
182
#define ftrace_hash_lock(flags)   do { (void)(flags); } while (0)
183
#define ftrace_hash_unlock(flags) do { } while(0)
184 185 186
static inline void ftrace_release_hash(unsigned long start, unsigned long end)
{
}
187 188
#endif

189 190 191 192 193 194 195 196
/*
 * Since MCOUNT_ADDR may point to mcount itself, we do not want
 * to get it confused by reading a reference in the code as we
 * are parsing on objcopy output of text. Use a variable for
 * it instead.
 */
static unsigned long mcount_addr = MCOUNT_ADDR;

S
Steven Rostedt 已提交
197 198
static struct task_struct *ftraced_task;

199 200 201 202 203 204 205 206
enum {
	FTRACE_ENABLE_CALLS		= (1 << 0),
	FTRACE_DISABLE_CALLS		= (1 << 1),
	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
	FTRACE_ENABLE_MCOUNT		= (1 << 3),
	FTRACE_DISABLE_MCOUNT		= (1 << 4),
};

207
static int ftrace_filtered;
A
Abhishek Sagar 已提交
208 209
static int tracing_on;
static int frozen_record_count;
210

211 212 213 214 215
static struct hlist_head ftrace_hash[FTRACE_HASHSIZE];

static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu);

static DEFINE_MUTEX(ftraced_lock);
216
static DEFINE_MUTEX(ftrace_regex_lock);
217

218 219
struct ftrace_page {
	struct ftrace_page	*next;
220
	unsigned long		index;
221
	struct dyn_ftrace	records[];
222
};
223 224 225 226 227 228 229 230 231 232

#define ENTRIES_PER_PAGE \
  ((PAGE_SIZE - sizeof(struct ftrace_page)) / sizeof(struct dyn_ftrace))

/* estimate from running different kernels */
#define NR_TO_INIT		10000

static struct ftrace_page	*ftrace_pages_start;
static struct ftrace_page	*ftrace_pages;

233 234
static int ftraced_trigger;
static int ftraced_suspend;
235
static int ftraced_stop;
236 237 238

static int ftrace_record_suspend;

239 240
static struct dyn_ftrace *ftrace_free_records;

A
Abhishek Sagar 已提交
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

#ifdef CONFIG_KPROBES
static inline void freeze_record(struct dyn_ftrace *rec)
{
	if (!(rec->flags & FTRACE_FL_FROZEN)) {
		rec->flags |= FTRACE_FL_FROZEN;
		frozen_record_count++;
	}
}

static inline void unfreeze_record(struct dyn_ftrace *rec)
{
	if (rec->flags & FTRACE_FL_FROZEN) {
		rec->flags &= ~FTRACE_FL_FROZEN;
		frozen_record_count--;
	}
}

static inline int record_frozen(struct dyn_ftrace *rec)
{
	return rec->flags & FTRACE_FL_FROZEN;
}
#else
# define freeze_record(rec)			({ 0; })
# define unfreeze_record(rec)			({ 0; })
# define record_frozen(rec)			({ 0; })
#endif /* CONFIG_KPROBES */

int skip_trace(unsigned long ip)
{
	unsigned long fl;
	struct dyn_ftrace *rec;
	struct hlist_node *t;
	struct hlist_head *head;

	if (frozen_record_count == 0)
		return 0;

	head = &ftrace_hash[hash_long(ip, FTRACE_HASHBITS)];
	hlist_for_each_entry_rcu(rec, t, head, node) {
		if (rec->ip == ip) {
			if (record_frozen(rec)) {
				if (rec->flags & FTRACE_FL_FAILED)
					return 1;

				if (!(rec->flags & FTRACE_FL_CONVERTED))
					return 1;

				if (!tracing_on || !ftrace_enabled)
					return 1;

				if (ftrace_filtered) {
					fl = rec->flags & (FTRACE_FL_FILTER |
							   FTRACE_FL_NOTRACE);
					if (!fl || (fl & FTRACE_FL_NOTRACE))
						return 1;
				}
			}
			break;
		}
	}

	return 0;
}

I
Ingo Molnar 已提交
306
static inline int
I
Ingo Molnar 已提交
307
ftrace_ip_in_hash(unsigned long ip, unsigned long key)
308 309 310 311 312
{
	struct dyn_ftrace *p;
	struct hlist_node *t;
	int found = 0;

313
	hlist_for_each_entry_rcu(p, t, &ftrace_hash[key], node) {
314 315 316 317 318 319 320 321 322
		if (p->ip == ip) {
			found = 1;
			break;
		}
	}

	return found;
}

I
Ingo Molnar 已提交
323
static inline void
324 325
ftrace_add_hash(struct dyn_ftrace *node, unsigned long key)
{
326
	hlist_add_head_rcu(&node->node, &ftrace_hash[key]);
327 328
}

329 330 331 332 333 334
/* called from kstop_machine */
static inline void ftrace_del_hash(struct dyn_ftrace *node)
{
	hlist_del(&node->node);
}

I
Ingo Molnar 已提交
335
static void ftrace_free_rec(struct dyn_ftrace *rec)
336 337 338 339 340 341
{
	rec->ip = (unsigned long)ftrace_free_records;
	ftrace_free_records = rec;
	rec->flags |= FTRACE_FL_FREE;
}

342 343 344 345 346 347 348 349
void ftrace_release(void *start, unsigned long size)
{
	struct dyn_ftrace *rec;
	struct ftrace_page *pg;
	unsigned long s = (unsigned long)start;
	unsigned long e = s + size;
	int i;

350
	if (ftrace_disabled || !start)
351 352
		return;

353
	/* should not be called from interrupt context */
354 355 356 357 358 359 360 361 362 363 364 365
	spin_lock(&ftrace_lock);

	for (pg = ftrace_pages_start; pg; pg = pg->next) {
		for (i = 0; i < pg->index; i++) {
			rec = &pg->records[i];

			if ((rec->ip >= s) && (rec->ip < e))
				ftrace_free_rec(rec);
		}
	}
	spin_unlock(&ftrace_lock);

366
	ftrace_release_hash(s, e);
367 368
}

I
Ingo Molnar 已提交
369
static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
370
{
371 372 373 374 375 376 377
	struct dyn_ftrace *rec;

	/* First check for freed records */
	if (ftrace_free_records) {
		rec = ftrace_free_records;

		if (unlikely(!(rec->flags & FTRACE_FL_FREE))) {
378
			FTRACE_WARN_ON_ONCE(1);
379 380 381 382 383 384 385 386 387
			ftrace_free_records = NULL;
			return NULL;
		}

		ftrace_free_records = (void *)rec->ip;
		memset(rec, 0, sizeof(*rec));
		return rec;
	}

388 389 390 391 392 393 394 395 396
	if (ftrace_pages->index == ENTRIES_PER_PAGE) {
		if (!ftrace_pages->next)
			return NULL;
		ftrace_pages = ftrace_pages->next;
	}

	return &ftrace_pages->records[ftrace_pages->index++];
}

I
Ingo Molnar 已提交
397
static void
398
ftrace_record_ip(unsigned long ip)
399 400 401 402 403
{
	struct dyn_ftrace *node;
	unsigned long flags;
	unsigned long key;
	int resched;
404
	int cpu;
405

406
	if (!ftrace_enabled || ftrace_disabled)
407 408
		return;

409 410 411
	resched = need_resched();
	preempt_disable_notrace();

412 413 414 415 416 417 418 419 420
	/*
	 * We simply need to protect against recursion.
	 * Use the the raw version of smp_processor_id and not
	 * __get_cpu_var which can call debug hooks that can
	 * cause a recursive crash here.
	 */
	cpu = raw_smp_processor_id();
	per_cpu(ftrace_shutdown_disable_cpu, cpu)++;
	if (per_cpu(ftrace_shutdown_disable_cpu, cpu) != 1)
421 422 423 424 425 426 427
		goto out;

	if (unlikely(ftrace_record_suspend))
		goto out;

	key = hash_long(ip, FTRACE_HASHBITS);

428
	FTRACE_WARN_ON_ONCE(key >= FTRACE_HASHSIZE);
429 430 431 432

	if (ftrace_ip_in_hash(ip, key))
		goto out;

433
	ftrace_hash_lock(flags);
434 435 436 437 438

	/* This ip may have hit the hash before the lock */
	if (ftrace_ip_in_hash(ip, key))
		goto out_unlock;

439
	node = ftrace_alloc_dyn_node(ip);
440 441 442 443 444 445 446 447 448 449
	if (!node)
		goto out_unlock;

	node->ip = ip;

	ftrace_add_hash(node, key);

	ftraced_trigger = 1;

 out_unlock:
450
	ftrace_hash_unlock(flags);
451
 out:
452
	per_cpu(ftrace_shutdown_disable_cpu, cpu)--;
453 454 455 456 457 458 459 460

	/* prevent recursion with scheduler */
	if (resched)
		preempt_enable_no_resched_notrace();
	else
		preempt_enable_notrace();
}

461
#define FTRACE_ADDR ((long)(ftrace_caller))
462

463
static int
464 465 466
__ftrace_replace_code(struct dyn_ftrace *rec,
		      unsigned char *old, unsigned char *new, int enable)
{
467
	unsigned long ip, fl;
468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483

	ip = rec->ip;

	if (ftrace_filtered && enable) {
		/*
		 * If filtering is on:
		 *
		 * If this record is set to be filtered and
		 * is enabled then do nothing.
		 *
		 * If this record is set to be filtered and
		 * it is not enabled, enable it.
		 *
		 * If this record is not set to be filtered
		 * and it is not enabled do nothing.
		 *
484 485 486
		 * If this record is set not to trace then
		 * do nothing.
		 *
487 488 489
		 * If this record is set not to trace and
		 * it is enabled then disable it.
		 *
490 491 492
		 * If this record is not set to be filtered and
		 * it is enabled, disable it.
		 */
493 494 495

		fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE |
				   FTRACE_FL_ENABLED);
496 497

		if ((fl ==  (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) ||
498 499
		    (fl ==  (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) ||
		    !fl || (fl == FTRACE_FL_NOTRACE))
500
			return 0;
501 502 503 504 505

		/*
		 * If it is enabled disable it,
		 * otherwise enable it!
		 */
506
		if (fl & FTRACE_FL_ENABLED) {
507 508 509 510 511 512 513 514 515 516
			/* swap new and old */
			new = old;
			old = ftrace_call_replace(ip, FTRACE_ADDR);
			rec->flags &= ~FTRACE_FL_ENABLED;
		} else {
			new = ftrace_call_replace(ip, FTRACE_ADDR);
			rec->flags |= FTRACE_FL_ENABLED;
		}
	} else {

517 518 519 520 521 522 523
		if (enable) {
			/*
			 * If this record is set not to trace and is
			 * not enabled, do nothing.
			 */
			fl = rec->flags & (FTRACE_FL_NOTRACE | FTRACE_FL_ENABLED);
			if (fl == FTRACE_FL_NOTRACE)
524
				return 0;
525

526
			new = ftrace_call_replace(ip, FTRACE_ADDR);
527
		} else
528 529 530 531
			old = ftrace_call_replace(ip, FTRACE_ADDR);

		if (enable) {
			if (rec->flags & FTRACE_FL_ENABLED)
532
				return 0;
533 534 535
			rec->flags |= FTRACE_FL_ENABLED;
		} else {
			if (!(rec->flags & FTRACE_FL_ENABLED))
536
				return 0;
537 538 539 540
			rec->flags &= ~FTRACE_FL_ENABLED;
		}
	}

541
	return ftrace_modify_code(ip, old, new);
542 543
}

I
Ingo Molnar 已提交
544
static void ftrace_replace_code(int enable)
545
{
546
	int i, failed;
547 548 549 550
	unsigned char *new = NULL, *old = NULL;
	struct dyn_ftrace *rec;
	struct ftrace_page *pg;

551
	if (enable)
552 553 554 555 556 557 558 559 560 561 562 563
		old = ftrace_nop_replace();
	else
		new = ftrace_nop_replace();

	for (pg = ftrace_pages_start; pg; pg = pg->next) {
		for (i = 0; i < pg->index; i++) {
			rec = &pg->records[i];

			/* don't modify code that has already faulted */
			if (rec->flags & FTRACE_FL_FAILED)
				continue;

564
			/* ignore updates to this record's mcount site */
565 566
			if (get_kprobe((void *)rec->ip)) {
				freeze_record(rec);
567
				continue;
568 569 570
			} else {
				unfreeze_record(rec);
			}
571

572 573 574 575
			failed = __ftrace_replace_code(rec, old, new, enable);
			if (failed && (rec->flags & FTRACE_FL_CONVERTED)) {
				rec->flags |= FTRACE_FL_FAILED;
				if ((system_state == SYSTEM_BOOTING) ||
576
				    !core_kernel_text(rec->ip)) {
577 578 579 580
					ftrace_del_hash(rec);
					ftrace_free_rec(rec);
				}
			}
581 582 583 584
		}
	}
}

I
Ingo Molnar 已提交
585
static void ftrace_shutdown_replenish(void)
586 587 588 589 590 591 592
{
	if (ftrace_pages->next)
		return;

	/* allocate another page */
	ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL);
}
593

594 595 596 597 598 599 600 601 602 603
static void print_ip_ins(const char *fmt, unsigned char *p)
{
	int i;

	printk(KERN_CONT "%s", fmt);

	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
}

604
static int
605
ftrace_code_disable(struct dyn_ftrace *rec)
606 607 608
{
	unsigned long ip;
	unsigned char *nop, *call;
609
	int ret;
610 611 612 613

	ip = rec->ip;

	nop = ftrace_nop_replace();
614
	call = ftrace_call_replace(ip, mcount_addr);
615

616 617 618 619
	ret = ftrace_modify_code(ip, call, nop);
	if (ret) {
		switch (ret) {
		case -EFAULT:
620
			FTRACE_WARN_ON_ONCE(1);
621 622 623
			pr_info("ftrace faulted on modifying ");
			print_ip_sym(ip);
			break;
624
		case -EINVAL:
625
			FTRACE_WARN_ON_ONCE(1);
626 627 628 629 630 631 632
			pr_info("ftrace failed to modify ");
			print_ip_sym(ip);
			print_ip_ins(" expected: ", call);
			print_ip_ins(" actual: ", (unsigned char *)ip);
			print_ip_ins(" replace: ", nop);
			printk(KERN_CONT "\n");
			break;
633
		case -EPERM:
634
			FTRACE_WARN_ON_ONCE(1);
635 636 637 638
			pr_info("ftrace faulted on writing ");
			print_ip_sym(ip);
			break;
		default:
639
			FTRACE_WARN_ON_ONCE(1);
640 641
			pr_info("ftrace faulted on unknown error ");
			print_ip_sym(ip);
642 643
		}

644
		rec->flags |= FTRACE_FL_FAILED;
645
		return 0;
646
	}
647
	return 1;
648 649
}

650 651
static int __ftrace_update_code(void *ignore);

I
Ingo Molnar 已提交
652
static int __ftrace_modify_code(void *data)
653
{
654 655 656
	unsigned long addr;
	int *command = data;

657 658 659 660 661 662
	if (*command & FTRACE_ENABLE_CALLS) {
		/*
		 * Update any recorded ips now that we have the
		 * machine stopped
		 */
		__ftrace_update_code(NULL);
663
		ftrace_replace_code(1);
A
Abhishek Sagar 已提交
664 665
		tracing_on = 1;
	} else if (*command & FTRACE_DISABLE_CALLS) {
666
		ftrace_replace_code(0);
A
Abhishek Sagar 已提交
667 668
		tracing_on = 0;
	}
669 670 671 672 673 674 675 676 677 678 679 680 681

	if (*command & FTRACE_UPDATE_TRACE_FUNC)
		ftrace_update_ftrace_func(ftrace_trace_function);

	if (*command & FTRACE_ENABLE_MCOUNT) {
		addr = (unsigned long)ftrace_record_ip;
		ftrace_mcount_set(&addr);
	} else if (*command & FTRACE_DISABLE_MCOUNT) {
		addr = (unsigned long)ftrace_stub;
		ftrace_mcount_set(&addr);
	}

	return 0;
682 683
}

I
Ingo Molnar 已提交
684
static void ftrace_run_update_code(int command)
685
{
R
Rusty Russell 已提交
686
	stop_machine(__ftrace_modify_code, &command, NULL);
687 688
}

689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
void ftrace_disable_daemon(void)
{
	/* Stop the daemon from calling kstop_machine */
	mutex_lock(&ftraced_lock);
	ftraced_stop = 1;
	mutex_unlock(&ftraced_lock);

	ftrace_force_update();
}

void ftrace_enable_daemon(void)
{
	mutex_lock(&ftraced_lock);
	ftraced_stop = 0;
	mutex_unlock(&ftraced_lock);

	ftrace_force_update();
}

708 709
static ftrace_func_t saved_ftrace_func;

I
Ingo Molnar 已提交
710
static void ftrace_startup(void)
711
{
712 713
	int command = 0;

714 715 716
	if (unlikely(ftrace_disabled))
		return;

717 718
	mutex_lock(&ftraced_lock);
	ftraced_suspend++;
719 720 721 722 723 724 725 726 727
	if (ftraced_suspend == 1)
		command |= FTRACE_ENABLE_CALLS;

	if (saved_ftrace_func != ftrace_trace_function) {
		saved_ftrace_func = ftrace_trace_function;
		command |= FTRACE_UPDATE_TRACE_FUNC;
	}

	if (!command || !ftrace_enabled)
728 729
		goto out;

730
	ftrace_run_update_code(command);
731 732 733 734
 out:
	mutex_unlock(&ftraced_lock);
}

I
Ingo Molnar 已提交
735
static void ftrace_shutdown(void)
736
{
737 738
	int command = 0;

739 740 741
	if (unlikely(ftrace_disabled))
		return;

742 743
	mutex_lock(&ftraced_lock);
	ftraced_suspend--;
744 745
	if (!ftraced_suspend)
		command |= FTRACE_DISABLE_CALLS;
746

747 748 749 750
	if (saved_ftrace_func != ftrace_trace_function) {
		saved_ftrace_func = ftrace_trace_function;
		command |= FTRACE_UPDATE_TRACE_FUNC;
	}
751

752 753 754 755
	if (!command || !ftrace_enabled)
		goto out;

	ftrace_run_update_code(command);
756 757 758 759
 out:
	mutex_unlock(&ftraced_lock);
}

I
Ingo Molnar 已提交
760
static void ftrace_startup_sysctl(void)
761
{
762 763
	int command = FTRACE_ENABLE_MCOUNT;

764 765 766
	if (unlikely(ftrace_disabled))
		return;

767
	mutex_lock(&ftraced_lock);
768 769
	/* Force update next time */
	saved_ftrace_func = NULL;
770 771
	/* ftraced_suspend is true if we want ftrace running */
	if (ftraced_suspend)
772 773 774
		command |= FTRACE_ENABLE_CALLS;

	ftrace_run_update_code(command);
775 776 777
	mutex_unlock(&ftraced_lock);
}

I
Ingo Molnar 已提交
778
static void ftrace_shutdown_sysctl(void)
779
{
780 781
	int command = FTRACE_DISABLE_MCOUNT;

782 783 784
	if (unlikely(ftrace_disabled))
		return;

785 786 787
	mutex_lock(&ftraced_lock);
	/* ftraced_suspend is true if ftrace is running */
	if (ftraced_suspend)
788 789 790
		command |= FTRACE_DISABLE_CALLS;

	ftrace_run_update_code(command);
791 792 793
	mutex_unlock(&ftraced_lock);
}

794 795 796 797
static cycle_t		ftrace_update_time;
static unsigned long	ftrace_update_cnt;
unsigned long		ftrace_update_tot_cnt;

I
Ingo Molnar 已提交
798
static int __ftrace_update_code(void *ignore)
799
{
800 801
	int i, save_ftrace_enabled;
	cycle_t start, stop;
802
	struct dyn_ftrace *p;
803
	struct hlist_node *t, *n;
804
	struct hlist_head *head, temp_list;
805

806
	/* Don't be recording funcs now */
807
	ftrace_record_suspend++;
808 809
	save_ftrace_enabled = ftrace_enabled;
	ftrace_enabled = 0;
810

I
Ingo Molnar 已提交
811
	start = ftrace_now(raw_smp_processor_id());
812 813 814 815
	ftrace_update_cnt = 0;

	/* No locks needed, the machine is stopped! */
	for (i = 0; i < FTRACE_HASHSIZE; i++) {
816 817 818
		INIT_HLIST_HEAD(&temp_list);
		head = &ftrace_hash[i];

819
		/* all CPUS are stopped, we are safe to modify code */
820
		hlist_for_each_entry_safe(p, t, n, head, node) {
821 822 823 824
			/* Skip over failed records which have not been
			 * freed. */
			if (p->flags & FTRACE_FL_FAILED)
				continue;
825

826 827 828 829 830 831 832
			/* Unconverted records are always at the head of the
			 * hash bucket. Once we encounter a converted record,
			 * simply skip over to the next bucket. Saves ftraced
			 * some processor cycles (ftrace does its bid for
			 * global warming :-p ). */
			if (p->flags & (FTRACE_FL_CONVERTED))
				break;
833

834 835 836 837 838 839 840 841 842
			/* Ignore updates to this record's mcount site.
			 * Reintroduce this record at the head of this
			 * bucket to attempt to "convert" it again if
			 * the kprobe on it is unregistered before the
			 * next run. */
			if (get_kprobe((void *)p->ip)) {
				ftrace_del_hash(p);
				INIT_HLIST_NODE(&p->node);
				hlist_add_head(&p->node, &temp_list);
843
				freeze_record(p);
844
				continue;
845 846
			} else {
				unfreeze_record(p);
847 848 849
			}

			/* convert record (i.e, patch mcount-call with NOP) */
850 851
			if (ftrace_code_disable(p)) {
				p->flags |= FTRACE_FL_CONVERTED;
852
				ftrace_update_cnt++;
853 854
			} else {
				if ((system_state == SYSTEM_BOOTING) ||
855
				    !core_kernel_text(p->ip)) {
856 857 858 859
					ftrace_del_hash(p);
					ftrace_free_rec(p);
				}
			}
860
		}
861 862 863 864 865 866

		hlist_for_each_entry_safe(p, t, n, &temp_list, node) {
			hlist_del(&p->node);
			INIT_HLIST_NODE(&p->node);
			hlist_add_head(&p->node, head);
		}
867 868
	}

I
Ingo Molnar 已提交
869
	stop = ftrace_now(raw_smp_processor_id());
870 871
	ftrace_update_time = stop - start;
	ftrace_update_tot_cnt += ftrace_update_cnt;
872
	ftraced_trigger = 0;
873

874
	ftrace_enabled = save_ftrace_enabled;
875
	ftrace_record_suspend--;
876 877 878 879

	return 0;
}

880
static int ftrace_update_code(void)
881
{
882 883 884
	if (unlikely(ftrace_disabled) ||
	    !ftrace_enabled || !ftraced_trigger)
		return 0;
885

R
Rusty Russell 已提交
886
	stop_machine(__ftrace_update_code, NULL, NULL);
887 888

	return 1;
889 890
}

891
static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
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
{
	struct ftrace_page *pg;
	int cnt;
	int i;

	/* allocate a few pages */
	ftrace_pages_start = (void *)get_zeroed_page(GFP_KERNEL);
	if (!ftrace_pages_start)
		return -1;

	/*
	 * Allocate a few more pages.
	 *
	 * TODO: have some parser search vmlinux before
	 *   final linking to find all calls to ftrace.
	 *   Then we can:
	 *    a) know how many pages to allocate.
	 *     and/or
	 *    b) set up the table then.
	 *
	 *  The dynamic code is still necessary for
	 *  modules.
	 */

	pg = ftrace_pages = ftrace_pages_start;

918 919 920
	cnt = num_to_init / ENTRIES_PER_PAGE;
	pr_info("ftrace: allocating %ld hash entries in %d pages\n",
		num_to_init, cnt);
921 922 923 924 925 926 927 928 929 930 931 932 933 934

	for (i = 0; i < cnt; i++) {
		pg->next = (void *)get_zeroed_page(GFP_KERNEL);

		/* If we fail, we'll try later anyway */
		if (!pg->next)
			break;

		pg = pg->next;
	}

	return 0;
}

935 936 937
enum {
	FTRACE_ITER_FILTER	= (1 << 0),
	FTRACE_ITER_CONT	= (1 << 1),
938
	FTRACE_ITER_NOTRACE	= (1 << 2),
939
	FTRACE_ITER_FAILURES	= (1 << 3),
940 941 942 943 944 945 946 947 948 949 950 951 952 953
};

#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */

struct ftrace_iterator {
	loff_t			pos;
	struct ftrace_page	*pg;
	unsigned		idx;
	unsigned		flags;
	unsigned char		buffer[FTRACE_BUFF_MAX+1];
	unsigned		buffer_idx;
	unsigned		filtered;
};

I
Ingo Molnar 已提交
954
static void *
955 956 957 958 959 960 961
t_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct ftrace_iterator *iter = m->private;
	struct dyn_ftrace *rec = NULL;

	(*pos)++;

962 963
	/* should not be called from interrupt context */
	spin_lock(&ftrace_lock);
964 965 966 967 968 969 970 971 972
 retry:
	if (iter->idx >= iter->pg->index) {
		if (iter->pg->next) {
			iter->pg = iter->pg->next;
			iter->idx = 0;
			goto retry;
		}
	} else {
		rec = &iter->pg->records[iter->idx++];
973 974 975
		if ((rec->flags & FTRACE_FL_FREE) ||

		    (!(iter->flags & FTRACE_ITER_FAILURES) &&
976 977 978
		     (rec->flags & FTRACE_FL_FAILED)) ||

		    ((iter->flags & FTRACE_ITER_FAILURES) &&
979
		     !(rec->flags & FTRACE_FL_FAILED)) ||
980

981 982
		    ((iter->flags & FTRACE_ITER_NOTRACE) &&
		     !(rec->flags & FTRACE_FL_NOTRACE))) {
983 984 985 986
			rec = NULL;
			goto retry;
		}
	}
987
	spin_unlock(&ftrace_lock);
988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036

	iter->pos = *pos;

	return rec;
}

static void *t_start(struct seq_file *m, loff_t *pos)
{
	struct ftrace_iterator *iter = m->private;
	void *p = NULL;
	loff_t l = -1;

	if (*pos != iter->pos) {
		for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l))
			;
	} else {
		l = *pos;
		p = t_next(m, p, &l);
	}

	return p;
}

static void t_stop(struct seq_file *m, void *p)
{
}

static int t_show(struct seq_file *m, void *v)
{
	struct dyn_ftrace *rec = v;
	char str[KSYM_SYMBOL_LEN];

	if (!rec)
		return 0;

	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);

	seq_printf(m, "%s\n", str);

	return 0;
}

static struct seq_operations show_ftrace_seq_ops = {
	.start = t_start,
	.next = t_next,
	.stop = t_stop,
	.show = t_show,
};

I
Ingo Molnar 已提交
1037
static int
1038 1039 1040 1041 1042
ftrace_avail_open(struct inode *inode, struct file *file)
{
	struct ftrace_iterator *iter;
	int ret;

1043 1044 1045
	if (unlikely(ftrace_disabled))
		return -ENODEV;

1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return -ENOMEM;

	iter->pg = ftrace_pages_start;
	iter->pos = -1;

	ret = seq_open(file, &show_ftrace_seq_ops);
	if (!ret) {
		struct seq_file *m = file->private_data;
I
Ingo Molnar 已提交
1056

1057
		m->private = iter;
I
Ingo Molnar 已提交
1058
	} else {
1059
		kfree(iter);
I
Ingo Molnar 已提交
1060
	}
1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071

	return ret;
}

int ftrace_avail_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = (struct seq_file *)file->private_data;
	struct ftrace_iterator *iter = m->private;

	seq_release(inode, file);
	kfree(iter);
I
Ingo Molnar 已提交
1072

1073 1074 1075
	return 0;
}

1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093
static int
ftrace_failures_open(struct inode *inode, struct file *file)
{
	int ret;
	struct seq_file *m;
	struct ftrace_iterator *iter;

	ret = ftrace_avail_open(inode, file);
	if (!ret) {
		m = (struct seq_file *)file->private_data;
		iter = (struct ftrace_iterator *)m->private;
		iter->flags = FTRACE_ITER_FAILURES;
	}

	return ret;
}


1094
static void ftrace_filter_reset(int enable)
1095 1096 1097
{
	struct ftrace_page *pg;
	struct dyn_ftrace *rec;
1098
	unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
1099 1100
	unsigned i;

1101 1102
	/* should not be called from interrupt context */
	spin_lock(&ftrace_lock);
1103 1104
	if (enable)
		ftrace_filtered = 0;
1105 1106 1107 1108 1109 1110
	pg = ftrace_pages_start;
	while (pg) {
		for (i = 0; i < pg->index; i++) {
			rec = &pg->records[i];
			if (rec->flags & FTRACE_FL_FAILED)
				continue;
1111
			rec->flags &= ~type;
1112 1113 1114
		}
		pg = pg->next;
	}
1115
	spin_unlock(&ftrace_lock);
1116 1117
}

I
Ingo Molnar 已提交
1118
static int
1119
ftrace_regex_open(struct inode *inode, struct file *file, int enable)
1120 1121 1122 1123
{
	struct ftrace_iterator *iter;
	int ret = 0;

1124 1125 1126
	if (unlikely(ftrace_disabled))
		return -ENODEV;

1127 1128 1129 1130
	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return -ENOMEM;

1131
	mutex_lock(&ftrace_regex_lock);
1132 1133
	if ((file->f_mode & FMODE_WRITE) &&
	    !(file->f_flags & O_APPEND))
1134
		ftrace_filter_reset(enable);
1135 1136 1137 1138

	if (file->f_mode & FMODE_READ) {
		iter->pg = ftrace_pages_start;
		iter->pos = -1;
1139 1140
		iter->flags = enable ? FTRACE_ITER_FILTER :
			FTRACE_ITER_NOTRACE;
1141 1142 1143 1144 1145 1146 1147 1148 1149

		ret = seq_open(file, &show_ftrace_seq_ops);
		if (!ret) {
			struct seq_file *m = file->private_data;
			m->private = iter;
		} else
			kfree(iter);
	} else
		file->private_data = iter;
1150
	mutex_unlock(&ftrace_regex_lock);
1151 1152 1153 1154

	return ret;
}

1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166
static int
ftrace_filter_open(struct inode *inode, struct file *file)
{
	return ftrace_regex_open(inode, file, 1);
}

static int
ftrace_notrace_open(struct inode *inode, struct file *file)
{
	return ftrace_regex_open(inode, file, 0);
}

I
Ingo Molnar 已提交
1167
static ssize_t
1168
ftrace_regex_read(struct file *file, char __user *ubuf,
1169 1170 1171 1172 1173 1174 1175 1176
		       size_t cnt, loff_t *ppos)
{
	if (file->f_mode & FMODE_READ)
		return seq_read(file, ubuf, cnt, ppos);
	else
		return -EPERM;
}

I
Ingo Molnar 已提交
1177
static loff_t
1178
ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196
{
	loff_t ret;

	if (file->f_mode & FMODE_READ)
		ret = seq_lseek(file, offset, origin);
	else
		file->f_pos = ret = 1;

	return ret;
}

enum {
	MATCH_FULL,
	MATCH_FRONT_ONLY,
	MATCH_MIDDLE_ONLY,
	MATCH_END_ONLY,
};

I
Ingo Molnar 已提交
1197
static void
1198
ftrace_match(unsigned char *buff, int len, int enable)
1199 1200 1201 1202 1203 1204
{
	char str[KSYM_SYMBOL_LEN];
	char *search = NULL;
	struct ftrace_page *pg;
	struct dyn_ftrace *rec;
	int type = MATCH_FULL;
1205
	unsigned long flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
	unsigned i, match = 0, search_len = 0;

	for (i = 0; i < len; i++) {
		if (buff[i] == '*') {
			if (!i) {
				search = buff + i + 1;
				type = MATCH_END_ONLY;
				search_len = len - (i + 1);
			} else {
				if (type == MATCH_END_ONLY) {
					type = MATCH_MIDDLE_ONLY;
				} else {
					match = i;
					type = MATCH_FRONT_ONLY;
				}
				buff[i] = 0;
				break;
			}
		}
	}

1227 1228
	/* should not be called from interrupt context */
	spin_lock(&ftrace_lock);
1229 1230
	if (enable)
		ftrace_filtered = 1;
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
	pg = ftrace_pages_start;
	while (pg) {
		for (i = 0; i < pg->index; i++) {
			int matched = 0;
			char *ptr;

			rec = &pg->records[i];
			if (rec->flags & FTRACE_FL_FAILED)
				continue;
			kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
			switch (type) {
			case MATCH_FULL:
				if (strcmp(str, buff) == 0)
					matched = 1;
				break;
			case MATCH_FRONT_ONLY:
				if (memcmp(str, buff, match) == 0)
					matched = 1;
				break;
			case MATCH_MIDDLE_ONLY:
				if (strstr(str, search))
					matched = 1;
				break;
			case MATCH_END_ONLY:
				ptr = strstr(str, search);
				if (ptr && (ptr[search_len] == 0))
					matched = 1;
				break;
			}
			if (matched)
1261
				rec->flags |= flag;
1262 1263 1264
		}
		pg = pg->next;
	}
1265
	spin_unlock(&ftrace_lock);
1266 1267
}

I
Ingo Molnar 已提交
1268
static ssize_t
1269 1270
ftrace_regex_write(struct file *file, const char __user *ubuf,
		   size_t cnt, loff_t *ppos, int enable)
1271 1272 1273 1274 1275 1276 1277 1278 1279
{
	struct ftrace_iterator *iter;
	char ch;
	size_t read = 0;
	ssize_t ret;

	if (!cnt || cnt < 0)
		return 0;

1280
	mutex_lock(&ftrace_regex_lock);
1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334

	if (file->f_mode & FMODE_READ) {
		struct seq_file *m = file->private_data;
		iter = m->private;
	} else
		iter = file->private_data;

	if (!*ppos) {
		iter->flags &= ~FTRACE_ITER_CONT;
		iter->buffer_idx = 0;
	}

	ret = get_user(ch, ubuf++);
	if (ret)
		goto out;
	read++;
	cnt--;

	if (!(iter->flags & ~FTRACE_ITER_CONT)) {
		/* skip white space */
		while (cnt && isspace(ch)) {
			ret = get_user(ch, ubuf++);
			if (ret)
				goto out;
			read++;
			cnt--;
		}

		if (isspace(ch)) {
			file->f_pos += read;
			ret = read;
			goto out;
		}

		iter->buffer_idx = 0;
	}

	while (cnt && !isspace(ch)) {
		if (iter->buffer_idx < FTRACE_BUFF_MAX)
			iter->buffer[iter->buffer_idx++] = ch;
		else {
			ret = -EINVAL;
			goto out;
		}
		ret = get_user(ch, ubuf++);
		if (ret)
			goto out;
		read++;
		cnt--;
	}

	if (isspace(ch)) {
		iter->filtered++;
		iter->buffer[iter->buffer_idx] = 0;
1335
		ftrace_match(iter->buffer, iter->buffer_idx, enable);
1336 1337 1338 1339 1340 1341 1342 1343 1344
		iter->buffer_idx = 0;
	} else
		iter->flags |= FTRACE_ITER_CONT;


	file->f_pos += read;

	ret = read;
 out:
1345
	mutex_unlock(&ftrace_regex_lock);
1346 1347 1348 1349

	return ret;
}

1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377
static ssize_t
ftrace_filter_write(struct file *file, const char __user *ubuf,
		    size_t cnt, loff_t *ppos)
{
	return ftrace_regex_write(file, ubuf, cnt, ppos, 1);
}

static ssize_t
ftrace_notrace_write(struct file *file, const char __user *ubuf,
		     size_t cnt, loff_t *ppos)
{
	return ftrace_regex_write(file, ubuf, cnt, ppos, 0);
}

static void
ftrace_set_regex(unsigned char *buf, int len, int reset, int enable)
{
	if (unlikely(ftrace_disabled))
		return;

	mutex_lock(&ftrace_regex_lock);
	if (reset)
		ftrace_filter_reset(enable);
	if (buf)
		ftrace_match(buf, len, enable);
	mutex_unlock(&ftrace_regex_lock);
}

1378 1379 1380 1381 1382 1383 1384 1385 1386
/**
 * ftrace_set_filter - set a function to filter on in ftrace
 * @buf - the string that holds the function filter text.
 * @len - the length of the string.
 * @reset - non zero to reset all filters before applying this filter.
 *
 * Filters denote which functions should be enabled when tracing is enabled.
 * If @buf is NULL and reset is set, all functions will be enabled for tracing.
 */
I
Ingo Molnar 已提交
1387
void ftrace_set_filter(unsigned char *buf, int len, int reset)
1388
{
1389 1390
	ftrace_set_regex(buf, len, reset, 1);
}
1391

1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404
/**
 * ftrace_set_notrace - set a function to not trace in ftrace
 * @buf - the string that holds the function notrace text.
 * @len - the length of the string.
 * @reset - non zero to reset all filters before applying this filter.
 *
 * Notrace Filters denote which functions should not be enabled when tracing
 * is enabled. If @buf is NULL and reset is set, all functions will be enabled
 * for tracing.
 */
void ftrace_set_notrace(unsigned char *buf, int len, int reset)
{
	ftrace_set_regex(buf, len, reset, 0);
1405 1406
}

I
Ingo Molnar 已提交
1407
static int
1408
ftrace_regex_release(struct inode *inode, struct file *file, int enable)
1409 1410 1411 1412
{
	struct seq_file *m = (struct seq_file *)file->private_data;
	struct ftrace_iterator *iter;

1413
	mutex_lock(&ftrace_regex_lock);
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423
	if (file->f_mode & FMODE_READ) {
		iter = m->private;

		seq_release(inode, file);
	} else
		iter = file->private_data;

	if (iter->buffer_idx) {
		iter->filtered++;
		iter->buffer[iter->buffer_idx] = 0;
1424
		ftrace_match(iter->buffer, iter->buffer_idx, enable);
1425 1426 1427 1428 1429 1430 1431 1432 1433 1434
	}

	mutex_lock(&ftrace_sysctl_lock);
	mutex_lock(&ftraced_lock);
	if (iter->filtered && ftraced_suspend && ftrace_enabled)
		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
	mutex_unlock(&ftraced_lock);
	mutex_unlock(&ftrace_sysctl_lock);

	kfree(iter);
1435
	mutex_unlock(&ftrace_regex_lock);
1436 1437 1438
	return 0;
}

1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450
static int
ftrace_filter_release(struct inode *inode, struct file *file)
{
	return ftrace_regex_release(inode, file, 1);
}

static int
ftrace_notrace_release(struct inode *inode, struct file *file)
{
	return ftrace_regex_release(inode, file, 0);
}

1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499
static ssize_t
ftraced_read(struct file *filp, char __user *ubuf,
		     size_t cnt, loff_t *ppos)
{
	/* don't worry about races */
	char *buf = ftraced_stop ? "disabled\n" : "enabled\n";
	int r = strlen(buf);

	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

static ssize_t
ftraced_write(struct file *filp, const char __user *ubuf,
		      size_t cnt, loff_t *ppos)
{
	char buf[64];
	long val;
	int ret;

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	if (strncmp(buf, "enable", 6) == 0)
		val = 1;
	else if (strncmp(buf, "disable", 7) == 0)
		val = 0;
	else {
		buf[cnt] = 0;

		ret = strict_strtoul(buf, 10, &val);
		if (ret < 0)
			return ret;

		val = !!val;
	}

	if (val)
		ftrace_enable_daemon();
	else
		ftrace_disable_daemon();

	filp->f_pos += cnt;

	return cnt;
}

1500 1501 1502 1503 1504 1505 1506
static struct file_operations ftrace_avail_fops = {
	.open = ftrace_avail_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = ftrace_avail_release,
};

1507 1508 1509 1510 1511 1512 1513
static struct file_operations ftrace_failures_fops = {
	.open = ftrace_failures_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = ftrace_avail_release,
};

1514 1515
static struct file_operations ftrace_filter_fops = {
	.open = ftrace_filter_open,
1516
	.read = ftrace_regex_read,
1517
	.write = ftrace_filter_write,
1518
	.llseek = ftrace_regex_lseek,
1519 1520 1521
	.release = ftrace_filter_release,
};

1522 1523 1524 1525 1526 1527 1528 1529
static struct file_operations ftrace_notrace_fops = {
	.open = ftrace_notrace_open,
	.read = ftrace_regex_read,
	.write = ftrace_notrace_write,
	.llseek = ftrace_regex_lseek,
	.release = ftrace_notrace_release,
};

1530 1531 1532 1533 1534 1535
static struct file_operations ftraced_fops = {
	.open = tracing_open_generic,
	.read = ftraced_read,
	.write = ftraced_write,
};

S
Steven Rostedt 已提交
1536 1537 1538 1539 1540 1541 1542
/**
 * ftrace_force_update - force an update to all recording ftrace functions
 */
int ftrace_force_update(void)
{
	int ret = 0;

1543
	if (unlikely(ftrace_disabled))
S
Steven Rostedt 已提交
1544 1545
		return -ENODEV;

1546
	mutex_lock(&ftrace_sysctl_lock);
S
Steven Rostedt 已提交
1547 1548
	mutex_lock(&ftraced_lock);

1549 1550 1551 1552 1553 1554
	/*
	 * If ftraced_trigger is not set, then there is nothing
	 * to update.
	 */
	if (ftraced_trigger && !ftrace_update_code())
		ret = -EBUSY;
S
Steven Rostedt 已提交
1555 1556

	mutex_unlock(&ftraced_lock);
1557
	mutex_unlock(&ftrace_sysctl_lock);
S
Steven Rostedt 已提交
1558 1559 1560 1561

	return ret;
}

1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574
static __init int ftrace_init_debugfs(void)
{
	struct dentry *d_tracer;
	struct dentry *entry;

	d_tracer = tracing_init_dentry();

	entry = debugfs_create_file("available_filter_functions", 0444,
				    d_tracer, NULL, &ftrace_avail_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'available_filter_functions' entry\n");

1575 1576 1577 1578 1579
	entry = debugfs_create_file("failures", 0444,
				    d_tracer, NULL, &ftrace_failures_fops);
	if (!entry)
		pr_warning("Could not create debugfs 'failures' entry\n");

1580 1581 1582 1583 1584
	entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer,
				    NULL, &ftrace_filter_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'set_ftrace_filter' entry\n");
1585 1586 1587 1588 1589 1590

	entry = debugfs_create_file("set_ftrace_notrace", 0644, d_tracer,
				    NULL, &ftrace_notrace_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'set_ftrace_notrace' entry\n");
1591 1592 1593 1594 1595 1596

	entry = debugfs_create_file("ftraced_enabled", 0644, d_tracer,
				    NULL, &ftraced_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'ftraced_enabled' entry\n");
1597 1598 1599 1600 1601
	return 0;
}

fs_initcall(ftrace_init_debugfs);

1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
static int ftrace_convert_nops(unsigned long *start,
			       unsigned long *end)
{
	unsigned long *p;
	unsigned long addr;
	unsigned long flags;

	p = start;
	while (p < end) {
		addr = ftrace_call_adjust(*p++);
1613
		/* should not be called from interrupt context */
1614
		spin_lock(&ftrace_lock);
1615
		ftrace_record_ip(addr);
1616
		spin_unlock(&ftrace_lock);
1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627
		ftrace_shutdown_replenish();
	}

	/* p is ignored */
	local_irq_save(flags);
	__ftrace_update_code(p);
	local_irq_restore(flags);

	return 0;
}

1628 1629
void ftrace_init_module(unsigned long *start, unsigned long *end)
{
1630
	if (ftrace_disabled || start == end)
1631
		return;
1632 1633 1634
	ftrace_convert_nops(start, end);
}

1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669
extern unsigned long __start_mcount_loc[];
extern unsigned long __stop_mcount_loc[];

void __init ftrace_init(void)
{
	unsigned long count, addr, flags;
	int ret;

	/* Keep the ftrace pointer to the stub */
	addr = (unsigned long)ftrace_stub;

	local_irq_save(flags);
	ftrace_dyn_arch_init(&addr);
	local_irq_restore(flags);

	/* ftrace_dyn_arch_init places the return code in addr */
	if (addr)
		goto failed;

	count = __stop_mcount_loc - __start_mcount_loc;

	ret = ftrace_dyn_table_alloc(count);
	if (ret)
		goto failed;

	last_ftrace_enabled = ftrace_enabled = 1;

	ret = ftrace_convert_nops(__start_mcount_loc,
				  __stop_mcount_loc);

	return;
 failed:
	ftrace_disabled = 1;
}
#else /* CONFIG_FTRACE_MCOUNT_RECORD */
1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707

static void ftrace_release_hash(unsigned long start, unsigned long end)
{
	struct dyn_ftrace *rec;
	struct hlist_node *t, *n;
	struct hlist_head *head, temp_list;
	unsigned long flags;
	int i, cpu;

	preempt_disable_notrace();

	/* disable incase we call something that calls mcount */
	cpu = raw_smp_processor_id();
	per_cpu(ftrace_shutdown_disable_cpu, cpu)++;

	ftrace_hash_lock(flags);

	for (i = 0; i < FTRACE_HASHSIZE; i++) {
		INIT_HLIST_HEAD(&temp_list);
		head = &ftrace_hash[i];

		/* all CPUS are stopped, we are safe to modify code */
		hlist_for_each_entry_safe(rec, t, n, head, node) {
			if (rec->flags & FTRACE_FL_FREE)
				continue;

			if ((rec->ip >= start) && (rec->ip < end))
				ftrace_free_rec(rec);
		}
	}

	ftrace_hash_unlock(flags);

	per_cpu(ftrace_shutdown_disable_cpu, cpu)--;
	preempt_enable_notrace();

}

1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734
static int ftraced(void *ignore)
{
	unsigned long usecs;

	while (!kthread_should_stop()) {

		set_current_state(TASK_INTERRUPTIBLE);

		/* check once a second */
		schedule_timeout(HZ);

		if (unlikely(ftrace_disabled))
			continue;

		mutex_lock(&ftrace_sysctl_lock);
		mutex_lock(&ftraced_lock);
		if (!ftraced_suspend && !ftraced_stop &&
		    ftrace_update_code()) {
			usecs = nsecs_to_usecs(ftrace_update_time);
			if (ftrace_update_tot_cnt > 100000) {
				ftrace_update_tot_cnt = 0;
				pr_info("hm, dftrace overflow: %lu change%s"
					" (%lu total) in %lu usec%s\n",
					ftrace_update_cnt,
					ftrace_update_cnt != 1 ? "s" : "",
					ftrace_update_tot_cnt,
					usecs, usecs != 1 ? "s" : "");
1735
				FTRACE_WARN_ON_ONCE(1);
1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746
			}
		}
		mutex_unlock(&ftraced_lock);
		mutex_unlock(&ftrace_sysctl_lock);

		ftrace_shutdown_replenish();
	}
	__set_current_state(TASK_RUNNING);
	return 0;
}

I
Ingo Molnar 已提交
1747
static int __init ftrace_dynamic_init(void)
1748 1749
{
	struct task_struct *p;
1750
	unsigned long addr;
1751 1752
	int ret;

1753
	addr = (unsigned long)ftrace_record_ip;
I
Ingo Molnar 已提交
1754

R
Rusty Russell 已提交
1755
	stop_machine(ftrace_dyn_arch_init, &addr, NULL);
1756 1757

	/* ftrace_dyn_arch_init places the return code in addr */
1758 1759 1760 1761
	if (addr) {
		ret = (int)addr;
		goto failed;
	}
1762

1763
	ret = ftrace_dyn_table_alloc(NR_TO_INIT);
1764
	if (ret)
1765
		goto failed;
1766 1767

	p = kthread_run(ftraced, NULL, "ftraced");
1768 1769 1770 1771
	if (IS_ERR(p)) {
		ret = -1;
		goto failed;
	}
1772

1773
	last_ftrace_enabled = ftrace_enabled = 1;
S
Steven Rostedt 已提交
1774
	ftraced_task = p;
1775 1776

	return 0;
1777 1778 1779 1780

 failed:
	ftrace_disabled = 1;
	return ret;
1781 1782
}

1783
core_initcall(ftrace_dynamic_init);
1784 1785
#endif /* CONFIG_FTRACE_MCOUNT_RECORD */

1786
#else
I
Ingo Molnar 已提交
1787 1788 1789 1790
# define ftrace_startup()		do { } while (0)
# define ftrace_shutdown()		do { } while (0)
# define ftrace_startup_sysctl()	do { } while (0)
# define ftrace_shutdown_sysctl()	do { } while (0)
1791 1792
#endif /* CONFIG_DYNAMIC_FTRACE */

S
Steven Rostedt 已提交
1793
/**
1794
 * ftrace_kill - kill ftrace
S
Steven Rostedt 已提交
1795 1796 1797 1798 1799
 *
 * This function should be used by panic code. It stops ftrace
 * but in a not so nice way. If you need to simply kill ftrace
 * from a non-atomic section, use ftrace_kill.
 */
1800
void ftrace_kill(void)
S
Steven Rostedt 已提交
1801 1802 1803
{
	ftrace_disabled = 1;
	ftrace_enabled = 0;
1804
#ifdef CONFIG_DYNAMIC_FTRACE
S
Steven Rostedt 已提交
1805
	ftraced_suspend = -1;
1806
#endif
S
Steven Rostedt 已提交
1807 1808 1809
	clear_ftrace_function();
}

1810
/**
1811 1812
 * register_ftrace_function - register a function for profiling
 * @ops - ops structure that holds the function for profiling.
1813
 *
1814 1815 1816 1817 1818 1819
 * Register a function to be called by all functions in the
 * kernel.
 *
 * Note: @ops->func and all the functions it calls must be labeled
 *       with "notrace", otherwise it will go into a
 *       recursive loop.
1820
 */
1821
int register_ftrace_function(struct ftrace_ops *ops)
1822
{
1823 1824
	int ret;

1825 1826 1827
	if (unlikely(ftrace_disabled))
		return -1;

1828 1829
	mutex_lock(&ftrace_sysctl_lock);
	ret = __register_ftrace_function(ops);
1830
	ftrace_startup();
1831 1832 1833
	mutex_unlock(&ftrace_sysctl_lock);

	return ret;
1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845
}

/**
 * unregister_ftrace_function - unresgister a function for profiling.
 * @ops - ops structure that holds the function to unregister
 *
 * Unregister a function that was added to be called by ftrace profiling.
 */
int unregister_ftrace_function(struct ftrace_ops *ops)
{
	int ret;

1846
	mutex_lock(&ftrace_sysctl_lock);
1847
	ret = __unregister_ftrace_function(ops);
1848
	ftrace_shutdown();
1849 1850 1851 1852 1853
	mutex_unlock(&ftrace_sysctl_lock);

	return ret;
}

I
Ingo Molnar 已提交
1854
int
1855
ftrace_enable_sysctl(struct ctl_table *table, int write,
1856
		     struct file *file, void __user *buffer, size_t *lenp,
1857 1858 1859 1860
		     loff_t *ppos)
{
	int ret;

1861 1862 1863
	if (unlikely(ftrace_disabled))
		return -ENODEV;

1864 1865
	mutex_lock(&ftrace_sysctl_lock);

1866
	ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893

	if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
		goto out;

	last_ftrace_enabled = ftrace_enabled;

	if (ftrace_enabled) {

		ftrace_startup_sysctl();

		/* we are starting ftrace again */
		if (ftrace_list != &ftrace_list_end) {
			if (ftrace_list->next == &ftrace_list_end)
				ftrace_trace_function = ftrace_list->func;
			else
				ftrace_trace_function = ftrace_list_func;
		}

	} else {
		/* stopping ftrace calls (just send to ftrace_stub) */
		ftrace_trace_function = ftrace_stub;

		ftrace_shutdown_sysctl();
	}

 out:
	mutex_unlock(&ftrace_sysctl_lock);
1894
	return ret;
1895
}