ftrace.c

Kernel code of linux kernel

/*
 * Infrastructure for profiling code inserted by 'gcc -pg'.
 *
 * Copyright (C) 2007-2008 Steven Rostedt <[e-mail]>
 * Copyright (C) 2004-2008 Ingo Molnar <[e-mail]>
 *
 * Originally ported from the -rt patch by:
 *   Copyright (C) 2007 Arnaldo Carvalho de Melo <[e-mail]>
 *
 * Based on code in the latency_tracer, that is:
 *
 *  Copyright (C) 2004-2006 Ingo Molnar
 *  Copyright (C) 2004 William Lee Irwin III
 */

#include <linux/stop_machine.h>
#include <linux/clocksource.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/hardirq.h>
#include <linux/kthread.h>
#include <linux/uaccess.h>
#include <linux/kprobes.h>
#include <linux/ftrace.h>
#include <linux/sysctl.h>
#include <linux/ctype.h>
#include <linux/hash.h>
#include <linux/list.h>

#include <asm/ftrace.h>

#include "trace.h"

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

/*
 * ftrace_disabled is set when an anomaly is discovered.
 * ftrace_disabled is much stronger than ftrace_enabled.
 */
static int ftrace_disabled __read_mostly;

static DEFINE_SPINLOCK(ftrace_lock);
static DEFINE_MUTEX(ftrace_sysctl_lock);

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;

static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
	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;
	};
}

/**
 * clear_ftrace_function - reset the ftrace function
 *
 * This NULLs the ftrace function and in essence stops
 * tracing.  There may be lag
 */
void clear_ftrace_function(void)
{
	ftrace_trace_function = ftrace_stub;
}

static int __register_ftrace_function(struct ftrace_ops *ops)
{
	/* Should never be called by interrupts */
	spin_lock(&ftrace_lock);

	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;

	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;
	}

	spin_unlock(&ftrace_lock);

	return 0;
}

static int __unregister_ftrace_function(struct ftrace_ops *ops)
{
	struct ftrace_ops **p;
	int ret = 0;

	spin_lock(&ftrace_lock);

	/*
	 * If we are removing the last function, then simply point
	 * to the ftrace_stub.
	 */
	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;

	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;
	}

 out:
	spin_unlock(&ftrace_lock);

	return ret;
}

#ifdef CONFIG_DYNAMIC_FTRACE

static struct task_struct *ftraced_task;

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),
};

static int ftrace_filtered;
static int tracing_on;
static int frozen_record_count;

static struct hlist_head ftrace_hash[FTRACE_HASHSIZE];

static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu);

static DEFINE_SPINLOCK(ftrace_shutdown_lock);
static DEFINE_MUTEX(ftraced_lock);
static DEFINE_MUTEX(ftrace_regex_lock);

struct ftrace_page {
	struct ftrace_page	*next;
	unsigned long		index;
	struct dyn_ftrace	records[];
};

#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;

static int ftraced_trigger;
static int ftraced_suspend;
static int ftraced_stop;

static int ftrace_record_suspend;

static struct dyn_ftrace *ftrace_free_records;


#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;
}

static inline int
ftrace_ip_in_hash(unsigned long ip, unsigned long key)
{
	struct dyn_ftrace *p;
	struct hlist_node *t;
	int found = 0;

	hlist_for_each_entry_rcu(p, t, &ftrace_hash[key], node) {
		if (p->ip == ip) {
			found = 1;
			break;
		}
	}

	return found;
}

static inline void
ftrace_add_hash(struct dyn_ftrace *node, unsigned long key)
{
	hlist_add_head_rcu(&node->node, &ftrace_hash[key]);
}

/* called from kstop_machine */
static inline void ftrace_del_hash(struct dyn_ftrace *node)
{
	hlist_del(&node->node);
}

static void ftrace_free_rec(struct dyn_ftrace *rec)
{
	/* no locking, only called from kstop_machine */

	rec->ip = (unsigned long)ftrace_free_records;
	ftrace_free_records = rec;
	rec->flags |= FTRACE_FL_FREE;
}

static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
{
	struct dyn_ftrace *rec;

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

		if (unlikely(!(rec->flags & FTRACE_FL_FREE))) {
			WARN_ON_ONCE(1);
			ftrace_free_records = NULL;
			ftrace_disabled = 1;
			ftrace_enabled = 0;
			return NULL;
		}

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

	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++];
}

static void
ftrace_record_ip(unsigned long ip)
{
	struct dyn_ftrace *node;
	unsigned long flags;
	unsigned long key;
	int resched;
	int atomic;
	int cpu;

	if (!ftrace_enabled || ftrace_disabled)
		return;

	resched = need_resched();
	preempt_disable_notrace();

	/*
	 * 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)
		goto out;

	if (unlikely(ftrace_record_suspend))
		goto out;

	key = hash_long(ip, FTRACE_HASHBITS);

	WARN_ON_ONCE(key >= FTRACE_HASHSIZE);

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

	atomic = irqs_disabled();

	spin_lock_irqsave(&ftrace_shutdown_lock, flags);

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

	node = ftrace_alloc_dyn_node(ip);
	if (!node)
		goto out_unlock;

	node->ip = ip;

	ftrace_add_hash(node, key);

	ftraced_trigger = 1;

 out_unlock:
	spin_unlock_irqrestore(&ftrace_shutdown_lock, flags);
 out:
	per_cpu(ftrace_shutdown_disable_cpu, cpu)--;

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

#define FTRACE_ADDR ((long)(ftrace_caller))

static int
__ftrace_replace_code(struct dyn_ftrace *rec,
		      unsigned char *old, unsigned char *new, int enable)
{
	unsigned long ip, fl;

	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.
		 *
		 * If this record is set not to trace then
		 * do nothing.
		 *
		 * If this record is set not to trace and
		 * it is enabled then disable it.
		 *
		 * If this record is not set to be filtered and
		 * it is enabled, disable it.
		 */

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

		if ((fl ==  (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) ||
		    (fl ==  (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) ||
		    !fl || (fl == FTRACE_FL_NOTRACE))
			return 0;

		/*
		 * If it is enabled disable it,
		 * otherwise enable it!
		 */
		if (fl & FTRACE_FL_ENABLED) {
			/* 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 {

		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)
				return 0;

			new = ftrace_call_replace(ip, FTRACE_ADDR);
		} else
			old = ftrace_call_replace(ip, FTRACE_ADDR);

		if (enable) {
			if (rec->flags & FTRACE_FL_ENABLED)
				return 0;
			rec->flags |= FTRACE_FL_ENABLED;
		} else {
			if (!(rec->flags & FTRACE_FL_ENABLED))
				return 0;
			rec->flags &= ~FTRACE_FL_ENABLED;
		}
	}

	return ftrace_modify_code(ip, old, new);
}

static void ftrace_replace_code(int enable)
{
	int i, failed;
	unsigned char *new = NULL, *old = NULL;
	struct dyn_ftrace *rec;
	struct ftrace_page *pg;

	if (enable)
		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;

			/* ignore updates to this record's mcount site */
			if (get_kprobe((void *)rec->ip)) {
				freeze_record(rec);
				continue;
			} else {
				unfreeze_record(rec);
			}

			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) ||
				    !core_kernel_text(rec->ip)) {
					ftrace_del_hash(rec);
					ftrace_free_rec(rec);
				}
			}
		}
	}
}

static void ftrace_shutdown_replenish(void)
{
	if (ftrace_pages->next)
		return;

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

static int
ftrace_code_disable(struct dyn_ftrace *rec)
{
	unsigned long ip;
	unsigned char *nop, *call;
	int failed;

	ip = rec->ip;

	nop = ftrace_nop_replace();
	call = ftrace_call_replace(ip, MCOUNT_ADDR);

	failed = ftrace_modify_code(ip, call, nop);
	if (failed) {
		rec->flags |= FTRACE_FL_FAILED;
		return 0;
	}
	return 1;
}

static int __ftrace_update_code(void *ignore);

static int __ftrace_modify_code(void *data)
{
	unsigned long addr;
	int *command = data;

	if (*command & FTRACE_ENABLE_CALLS) {
		/*
		 * Update any recorded ips now that we have the
		 * machine stopped
		 */
		__ftrace_update_code(NULL);
		ftrace_replace_code(1);
		tracing_on = 1;
	} else if (*command & FTRACE_DISABLE_CALLS) {
		ftrace_replace_code(0);
		tracing_on = 0;
	}

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