trace.c

/*
 * ring buffer based function tracer
 *
 * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
 * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
 *
 * Originally taken from the RT patch by:
 *    Arnaldo Carvalho de Melo <acme@redhat.com>
 *
 * Based on code from the latency_tracer, that is:
 *  Copyright (C) 2004-2006 Ingo Molnar
 *  Copyright (C) 2004 William Lee Irwin III
 */
#include <linux/ring_buffer.h>
#include <linux/utsrelease.h>
#include <linux/stacktrace.h>
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
#include <linux/pagemap.h>
#include <linux/hardirq.h>
#include <linux/linkage.h>
#include <linux/uaccess.h>
#include <linux/kprobes.h>
#include <linux/ftrace.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/splice.h>
#include <linux/kdebug.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/gfp.h>
#include <linux/fs.h>

#include "trace.h"
#include "trace_output.h"

#define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)

unsigned long __read_mostly	tracing_max_latency;
unsigned long __read_mostly	tracing_thresh;

/*
 * On boot up, the ring buffer is set to the minimum size, so that
 * we do not waste memory on systems that are not using tracing.
 */
static int ring_buffer_expanded;

/*
 * We need to change this state when a selftest is running.
 * A selftest will lurk into the ring-buffer to count the
 * entries inserted during the selftest although some concurrent
 * insertions into the ring-buffer such as trace_printk could occurred
 * at the same time, giving false positive or negative results.
 */
static bool __read_mostly tracing_selftest_running;

/*
 * If a tracer is running, we do not want to run SELFTEST.
 */
static bool __read_mostly tracing_selftest_disabled;

/* For tracers that don't implement custom flags */
static struct tracer_opt dummy_tracer_opt[] = {
	{ }
};

static struct tracer_flags dummy_tracer_flags = {
	.val = 0,
	.opts = dummy_tracer_opt
};

static int dummy_set_flag(u32 old_flags, u32 bit, int set)
{
	return 0;
}

/*
 * Kill all tracing for good (never come back).
 * It is initialized to 1 but will turn to zero if the initialization
 * of the tracer is successful. But that is the only place that sets
 * this back to zero.
 */
static int tracing_disabled = 1;

static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);

static inline void ftrace_disable_cpu(void)
{
	preempt_disable();
	local_inc(&__get_cpu_var(ftrace_cpu_disabled));
}

static inline void ftrace_enable_cpu(void)
{
	local_dec(&__get_cpu_var(ftrace_cpu_disabled));
	preempt_enable();
}

static cpumask_var_t __read_mostly	tracing_buffer_mask;

/* Define which cpu buffers are currently read in trace_pipe */
static cpumask_var_t			tracing_reader_cpumask;

#define for_each_tracing_cpu(cpu)	\
	for_each_cpu(cpu, tracing_buffer_mask)

/*
 * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
 *
 * If there is an oops (or kernel panic) and the ftrace_dump_on_oops
 * is set, then ftrace_dump is called. This will output the contents
 * of the ftrace buffers to the console.  This is very useful for
 * capturing traces that lead to crashes and outputing it to a
 * serial console.
 *
 * It is default off, but you can enable it with either specifying
 * "ftrace_dump_on_oops" in the kernel command line, or setting
 * /proc/sys/kernel/ftrace_dump_on_oops to true.
 */
int ftrace_dump_on_oops;

static int tracing_set_tracer(const char *buf);

#define BOOTUP_TRACER_SIZE		100
static char bootup_tracer_buf[BOOTUP_TRACER_SIZE] __initdata;
static char *default_bootup_tracer;

static int __init set_ftrace(char *str)
{
	strncpy(bootup_tracer_buf, str, BOOTUP_TRACER_SIZE);
	default_bootup_tracer = bootup_tracer_buf;
	/* We are using ftrace early, expand it */
	ring_buffer_expanded = 1;
	return 1;
}
__setup("ftrace=", set_ftrace);

static int __init set_ftrace_dump_on_oops(char *str)
{
	ftrace_dump_on_oops = 1;
	return 1;
}
__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);

long
ns2usecs(cycle_t nsec)
{
	nsec += 500;
	do_div(nsec, 1000);
	return nsec;
}

/*
 * The global_trace is the descriptor that holds the tracing
 * buffers for the live tracing. For each CPU, it contains
 * a link list of pages that will store trace entries. The
 * page descriptor of the pages in the memory is used to hold
 * the link list by linking the lru item in the page descriptor
 * to each of the pages in the buffer per CPU.
 *
 * For each active CPU there is a data field that holds the
 * pages for the buffer for that CPU. Each CPU has the same number
 * of pages allocated for its buffer.
 */
static struct trace_array	global_trace;

static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);

cycle_t ftrace_now(int cpu)
{
	u64 ts;

	/* Early boot up does not have a buffer yet */
	if (!global_trace.buffer)
		return trace_clock_local();

	ts = ring_buffer_time_stamp(global_trace.buffer, cpu);
	ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts);

	return ts;
}

/*
 * The max_tr is used to snapshot the global_trace when a maximum
 * latency is reached. Some tracers will use this to store a maximum
 * trace while it continues examining live traces.
 *
 * The buffers for the max_tr are set up the same as the global_trace.
 * When a snapshot is taken, the link list of the max_tr is swapped
 * with the link list of the global_trace and the buffers are reset for
 * the global_trace so the tracing can continue.
 */
static struct trace_array	max_tr;

static DEFINE_PER_CPU(struct trace_array_cpu, max_data);

/* tracer_enabled is used to toggle activation of a tracer */
static int			tracer_enabled = 1;

/**
 * tracing_is_enabled - return tracer_enabled status
 *
 * This function is used by other tracers to know the status
 * of the tracer_enabled flag.  Tracers may use this function
 * to know if it should enable their features when starting
 * up. See irqsoff tracer for an example (start_irqsoff_tracer).
 */
int tracing_is_enabled(void)
{
	return tracer_enabled;
}

/*
 * trace_buf_size is the size in bytes that is allocated
 * for a buffer. Note, the number of bytes is always rounded
 * to page size.
 *
 * This number is purposely set to a low number of 16384.
 * If the dump on oops happens, it will be much appreciated
 * to not have to wait for all that output. Anyway this can be
 * boot time and run time configurable.
 */
#define TRACE_BUF_SIZE_DEFAULT	1441792UL /* 16384 * 88 (sizeof(entry)) */

static unsigned long		trace_buf_size = TRACE_BUF_SIZE_DEFAULT;

/* trace_types holds a link list of available tracers. */
static struct tracer		*trace_types __read_mostly;

/* current_trace points to the tracer that is currently active */
static struct tracer		*current_trace __read_mostly;

/*
 * max_tracer_type_len is used to simplify the allocating of
 * buffers to read userspace tracer names. We keep track of
 * the longest tracer name registered.
 */
static int			max_tracer_type_len;

/*
 * trace_types_lock is used to protect the trace_types list.
 * This lock is also used to keep user access serialized.
 * Accesses from userspace will grab this lock while userspace
 * activities happen inside the kernel.
 */
static DEFINE_MUTEX(trace_types_lock);

/* trace_wait is a waitqueue for tasks blocked on trace_poll */
static DECLARE_WAIT_QUEUE_HEAD(trace_wait);

/* trace_flags holds trace_options default values */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;

/**
 * trace_wake_up - wake up tasks waiting for trace input
 *
 * Simply wakes up any task that is blocked on the trace_wait
 * queue. These is used with trace_poll for tasks polling the trace.
 */
void trace_wake_up(void)
{
	/*
	 * The runqueue_is_locked() can fail, but this is the best we
	 * have for now:
	 */
	if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked())
		wake_up(&trace_wait);
}

static int __init set_buf_size(char *str)
{
	unsigned long buf_size;
	int ret;

	if (!str)
		return 0;
	ret = strict_strtoul(str, 0, &buf_size);
	/* nr_entries can not be zero */
	if (ret < 0 || buf_size == 0)
		return 0;
	trace_buf_size = buf_size;
	return 1;
}
__setup("trace_buf_size=", set_buf_size);

unsigned long nsecs_to_usecs(unsigned long nsecs)
{
	return nsecs / 1000;
}

/* These must match the bit postions in trace_iterator_flags */
static const char *trace_options[] = {
	"print-parent",
	"sym-offset",
	"sym-addr",
	"verbose",
	"raw",
	"hex",
	"bin",
	"block",
	"stacktrace",
	"sched-tree",
	"trace_printk",
	"ftrace_preempt",
	"branch",
	"annotate",
	"userstacktrace",
	"sym-userobj",
	"printk-msg-only",
	"context-info",
	"latency-format",
	"global-clock",
	"sleep-time",
	NULL
};

/*
 * ftrace_max_lock is used to protect the swapping of buffers
 * when taking a max snapshot. The buffers themselves are
 * protected by per_cpu spinlocks. But the action of the swap
 * needs its own lock.
 *
 * This is defined as a raw_spinlock_t in order to help
 * with performance when lockdep debugging is enabled.
 */
static raw_spinlock_t ftrace_max_lock =
	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;

/*
 * Copy the new maximum trace into the separate maximum-trace
 * structure. (this way the maximum trace is permanently saved,
 * for later retrieval via /debugfs/tracing/latency_trace)
 */
static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
	struct trace_array_cpu *data = tr->data[cpu];

	max_tr.cpu = cpu;
	max_tr.time_start = data->preempt_timestamp;

	data = max_tr.data[cpu];
	data->saved_latency = tracing_max_latency;

	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
	data->pid = tsk->pid;
	data->uid = task_uid(tsk);
	data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
	data->policy = tsk->policy;
	data->rt_priority = tsk->rt_priority;

	/* record this tasks comm */
	tracing_record_cmdline(tsk);
}

ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
{
	int len;
	int ret;

	if (!cnt)
		return 0;

	if (s->len <= s->readpos)
		return -EBUSY;

	len = s->len - s->readpos;
	if (cnt > len)
		cnt = len;
	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
	if (ret == cnt)
		return -EFAULT;

	cnt -= ret;

	s->readpos += cnt;
	return cnt;
}

static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
{
	int len;
	void *ret;

	if (s->len <= s->readpos)
		return -EBUSY;

	len = s->len - s->readpos;
	if (cnt > len)
		cnt = len;
	ret = memcpy(buf, s->buffer + s->readpos, cnt);
	if (!ret)
		return -EFAULT;

	s->readpos += cnt;
	return cnt;
}

/**
 * update_max_tr - snapshot all trace buffers from global_trace to max_tr
 * @tr: tracer
 * @tsk: the task with the latency
 * @cpu: The cpu that initiated the trace.
 *
 * Flip the buffers between the @tr and the max_tr and record information
 * about which task was the cause of this latency.
 */
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
	struct ring_buffer *buf = tr->buffer;

	WARN_ON_ONCE(!irqs_disabled());
	__raw_spin_lock(&ftrace_max_lock);

	tr->buffer = max_tr.buffer;
	max_tr.buffer = buf;

	ftrace_disable_cpu();
	ring_buffer_reset(tr->buffer);
	ftrace_enable_cpu();

	__update_max_tr(tr, tsk, cpu);
	__raw_spin_unlock(&ftrace_max_lock);
}

/**
 * update_max_tr_single - only copy one trace over, and reset the rest
 * @tr - tracer
 * @tsk - task with the latency
 * @cpu - the cpu of the buffer to copy.
 *
 * Flip the trace of a single CPU buffer between the @tr and the max_tr.
 */
void
update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
	int ret;

	WARN_ON_ONCE(!irqs_disabled());
	__raw_spin_lock(&ftrace_max_lock);

	ftrace_disable_cpu();

	ring_buffer_reset(max_tr.buffer);
	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);

	ftrace_enable_cpu();

	WARN_ON_ONCE(ret && ret != -EAGAIN);

	__update_max_tr(tr, tsk, cpu);
	__raw_spin_unlock(&ftrace_max_lock);
}

/**
 * register_tracer - register a tracer with the ftrace system.
 * @type - the plugin for the tracer
 *
 * Register a new plugin tracer.
 */
int register_tracer(struct tracer *type)
__releases(kernel_lock)
__acquires(kernel_lock)
{
	struct tracer *t;
	int len;
	int ret = 0;

	if (!type->name) {
		pr_info("Tracer must have a name\n");
		return -1;
	}

	/*
	 * When this gets called we hold the BKL which means that
	 * preemption is disabled. Various trace selftests however
	 * need to disable and enable preemption for successful tests.
	 * So we drop the BKL here and grab it after the tests again.
	 */
	unlock_kernel();
	mutex_lock(&trace_types_lock);

	tracing_selftest_running = true;

	for (t = trace_types; t; t = t->next) {
		if (strcmp(type->name, t->name) == 0) {
			/* already found */
			pr_info("Trace %s already registered\n",
				type->name);
			ret = -1;
			goto out;
		}
	}

	if (!type->set_flag)
		type->set_flag = &dummy_set_flag;
	if (!type->flags)
		type->flags = &dummy_tracer_flags;
	else
		if (!type->flags->opts)
			type->flags->opts = dummy_tracer_opt;
	if (!type->wait_pipe)
		type->wait_pipe = default_wait_pipe;


#ifdef CONFIG_FTRACE_STARTUP_TEST
	if (type->selftest && !tracing_selftest_disabled) {
		struct tracer *saved_tracer = current_trace;
		struct trace_array *tr = &global_trace;
		int i;

		/*
		 * Run a selftest on this tracer.
		 * Here we reset the trace buffer, and set the current
		 * tracer to be this tracer. The tracer can then run some
		 * internal tracing to verify that everything is in order.
		 * If we fail, we do not register this tracer.
		 */
		for_each_tracing_cpu(i)
			tracing_reset(tr, i);

		current_trace = type;
		/* the test is responsible for initializing and enabling */
		pr_info("Testing tracer %s: ", type->name);
		ret = type->selftest(type, tr);
		/* the test is responsible for resetting too */
		current_trace = saved_tracer;
		if (ret) {
			printk(KERN_CONT "FAILED!\n");
			goto out;
		}
		/* Only reset on passing, to avoid touching corrupted buffers */
		for_each_tracing_cpu(i)
			tracing_reset(tr, i);

		printk(KERN_CONT "PASSED\n");
	}
#endif

	type->next = trace_types;
	trace_types = type;
	len = strlen(type->name);
	if (len > max_tracer_type_len)
		max_tracer_type_len = len;

 out:
	tracing_selftest_running = false;
	mutex_unlock(&trace_types_lock);

	if (ret || !default_bootup_tracer)
		goto out_unlock;

	if (strncmp(default_bootup_tracer, type->name, BOOTUP_TRACER_SIZE))
		goto out_unlock;

	printk(KERN_INFO "Starting tracer '%s'\n", type->name);
	/* Do we want this tracer to start on bootup? */
	tracing_set_tracer(type->name);
	default_bootup_tracer = NULL;
	/* disable other selftests, since this will break it. */
	tracing_selftest_disabled = 1;
#ifdef CONFIG_FTRACE_STARTUP_TEST
	printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n",
	       type->name);
#endif

 out_unlock:
	lock_kernel();
	return ret;
}

void unregister_tracer(struct tracer *type)
{
	struct tracer **t;
	int len;

	mutex_lock(&trace_types_lock);
	for (t = &trace_types; *t; t = &(*t)->next) {
		if (*t == type)
			goto found;
	}
	pr_info("Trace %s not registered\n", type->name);
	goto out;

 found:
	*t = (*t)->next;

	if (type == current_trace && tracer_enabled) {
		tracer_enabled = 0;
		tracing_stop();
		if (current_trace->stop)
			current_trace->stop(&global_trace);
		current_trace = &nop_trace;
	}

	if (strlen(type->name) != max_tracer_type_len)
		goto out;

	max_tracer_type_len = 0;
	for (t = &trace_types; *t; t = &(*t)->next) {
		len = strlen((*t)->name);
		if (len > max_tracer_type_len)
			max_tracer_type_len = len;
	}
 out:
	mutex_unlock(&trace_types_lock);
}

void tracing_reset(struct trace_array *tr, int cpu)
{
	ftrace_disable_cpu();
	ring_buffer_reset_cpu(tr->buffer, cpu);
	ftrace_enable_cpu();
}

void tracing_reset_online_cpus(struct trace_array *tr)
{
	int cpu;

	tr->time_start = ftrace_now(tr->cpu);

	for_each_online_cpu(cpu)
		tracing_reset(tr, cpu);
}

#define SAVED_CMDLINES 128
#define NO_CMDLINE_MAP UINT_MAX
static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
static int cmdline_idx;
static raw_spinlock_t trace_cmdline_lock = __RAW_SPIN_LOCK_UNLOCKED;

/* temporary disable recording */
static atomic_t trace_record_cmdline_disabled __read_mostly;

static void trace_init_cmdlines(void)
{
	memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
	memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
	cmdline_idx = 0;
}

static int trace_stop_count;
static DEFINE_SPINLOCK(tracing_start_lock);

/**
 * ftrace_off_permanent - disable all ftrace code permanently
 *
 * This should only be called when a serious anomally has
 * been detected.  This will turn off the function tracing,
 * ring buffers, and other tracing utilites. It takes no
 * locks and can be called from any context.
 */
void ftrace_off_permanent(void)
{
	tracing_disabled = 1;
	ftrace_stop();
	tracing_off_permanent();
}

/**
 * tracing_start - quick start of the tracer
 *
 * If tracing is enabled but was stopped by tracing_stop,
 * this will start the tracer back up.
 */
void tracing_start(void)
{
	struct ring_buffer *buffer;
	unsigned long flags;

	if (tracing_disabled)
		return;

	spin_lock_irqsave(&tracing_start_lock, flags);
	if (--trace_stop_count) {
		if (trace_stop_count < 0) {
			/* Someone screwed up their debugging */
			WARN_ON_ONCE(1);
			trace_stop_count = 0;
		}
		goto out;
	}


	buffer = global_trace.buffer;
	if (buffer)
		ring_buffer_record_enable(buffer);

	buffer = max_tr.buffer;
	if (buffer)
		ring_buffer_record_enable(buffer);

	ftrace_start();
 out:
	spin_unlock_irqrestore(&tracing_start_lock, flags);
}

/**
 * tracing_stop - quick stop of the tracer
 *
 * Light weight way to stop tracing. Use in conjunction with
 * tracing_start.
 */
void tracing_stop(void)
{
	struct ring_buffer *buffer;
	unsigned long flags;

	ftrace_stop();
	spin_lock_irqsave(&tracing_start_lock, flags);
	if (trace_stop_count++)
		goto out;

	buffer = global_trace.buffer;
	if (buffer)
		ring_buffer_record_disable(buffer);

	buffer = max_tr.buffer;
	if (buffer)
		ring_buffer_record_disable(buffer);

 out:
	spin_unlock_irqrestore(&tracing_start_lock, flags);
}

void trace_stop_cmdline_recording(void);

static void trace_save_cmdline(struct task_struct *tsk)
{
	unsigned pid, idx;

	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
		return;

	/*
	 * It's not the end of the world if we don't get
	 * the lock, but we also don't want to spin
	 * nor do we want to disable interrupts,
	 * so if we miss here, then better luck next time.
	 */
	if (!__raw_spin_trylock(&trace_cmdline_lock))
		return;

	idx = map_pid_to_cmdline[tsk->pid];
	if (idx == NO_CMDLINE_MAP) {
		idx = (cmdline_idx + 1) % SAVED_CMDLINES;

		/*
		 * Check whether the cmdline buffer at idx has a pid
		 * mapped. We are going to overwrite that entry so we
		 * need to clear the map_pid_to_cmdline. Otherwise we
		 * would read the new comm for the old pid.
		 */
		pid = map_cmdline_to_pid[idx];
		if (pid != NO_CMDLINE_MAP)
			map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;

		map_cmdline_to_pid[idx] = tsk->pid;
		map_pid_to_cmdline[tsk->pid] = idx;

		cmdline_idx = idx;
	}

	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);

	__raw_spin_unlock(&trace_cmdline_lock);
}

void trace_find_cmdline(int pid, char comm[])
{
	unsigned map;

	if (!pid) {
		strcpy(comm, "<idle>");
		return;
	}

	if (pid > PID_MAX_DEFAULT) {
		strcpy(comm, "<...>");
		return;
	}

	__raw_spin_lock(&trace_cmdline_lock);
	map = map_pid_to_cmdline[pid];
	if (map != NO_CMDLINE_MAP)
		strcpy(comm, saved_cmdlines[map]);
	else
		strcpy(comm, "<...>");

	__raw_spin_unlock(&trace_cmdline_lock);
}

void tracing_record_cmdline(struct task_struct *tsk)
{
	if (atomic_read(&trace_record_cmdline_disabled) || !tracer_enabled ||
	    !tracing_is_on())
		return;

	trace_save_cmdline(tsk);
}

void
tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
			     int pc)
{
	struct task_struct *tsk = current;

	entry->preempt_count		= pc & 0xff;
	entry->pid			= (tsk) ? tsk->pid : 0;
	entry->tgid			= (tsk) ? tsk->tgid : 0;
	entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
#else
		TRACE_FLAG_IRQS_NOSUPPORT |
#endif
		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
		(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
}

struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
						    unsigned char type,
						    unsigned long len,
						    unsigned long flags, int pc)
{
	struct ring_buffer_event *event;

	event = ring_buffer_lock_reserve(tr->buffer, len);
	if (event != NULL) {
		struct trace_entry *ent = ring_buffer_event_data(event);

		tracing_generic_entry_update(ent, flags, pc);
		ent->type = type;
	}

	return event;
}
static void ftrace_trace_stack(struct trace_array *tr,
			       unsigned long flags, int skip, int pc);
static void ftrace_trace_userstack(struct trace_array *tr,
				   unsigned long flags, int pc);

void trace_buffer_unlock_commit(struct trace_array *tr,
				struct ring_buffer_event *event,
				unsigned long flags, int pc)
{
	ring_buffer_unlock_commit(tr->buffer, event);

	ftrace_trace_stack(tr, flags, 6, pc);
	ftrace_trace_userstack(tr, flags, pc);
	trace_wake_up();
}

struct ring_buffer_event *
trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
				  unsigned long flags, int pc)
{
	return trace_buffer_lock_reserve(&global_trace,
					 type, len, flags, pc);
}

void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
					unsigned long flags, int pc)
{
	return trace_buffer_unlock_commit(&global_trace, event, flags, pc);
}

void
trace_function(struct trace_array *tr,
	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
	       int pc)
{
	struct ring_buffer_event *event;
	struct ftrace_entry *entry;

	/* If we are reading the ring buffer, don't trace */
	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
		return;

	event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry),
					  flags, pc);
	if (!event)
		return;
	entry	= ring_buffer_event_data(event);
	entry->ip			= ip;
	entry->parent_ip		= parent_ip;
	ring_buffer_unlock_commit(tr->buffer, event);
}

#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static void __trace_graph_entry(struct trace_array *tr,
				struct ftrace_graph_ent *trace,
				unsigned long flags,
				int pc)
{
	struct ring_buffer_event *event;
	struct ftrace_graph_ent_entry *entry;

	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
		return;

	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
					  sizeof(*entry), flags, pc);
	if (!event)
		return;
	entry	= ring_buffer_event_data(event);
	entry->graph_ent			= *trace;
	ring_buffer_unlock_commit(global_trace.buffer, event);
}

static void __trace_graph_return(struct trace_array *tr,
				struct ftrace_graph_ret *trace,
				unsigned long flags,
				int pc)
{
	struct ring_buffer_event *event;
	struct ftrace_graph_ret_entry *entry;

	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
		return;

	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET,
					  sizeof(*entry), flags, pc);
	if (!event)
		return;
	entry	= ring_buffer_event_data(event);
	entry->ret				= *trace;
	ring_buffer_unlock_commit(global_trace.buffer, event);
}
#endif

void
ftrace(struct trace_array *tr, struct trace_array_cpu *data,
       unsigned long ip, unsigned long parent_ip, unsigned long flags,
       int pc)
{
	if (likely(!atomic_read(&data->disabled)))
		trace_function(tr, ip, parent_ip, flags, pc);
}

static void __ftrace_trace_stack(struct trace_array *tr,
				 unsigned long flags,
				 int skip, int pc)
{
#ifdef CONFIG_STACKTRACE
	struct ring_buffer_event *event;
	struct stack_entry *entry;
	struct stack_trace trace;

	event = trace_buffer_lock_reserve(tr, TRACE_STACK,
					  sizeof(*entry), flags, pc);
	if (!event)
		return;
	entry	= ring_buffer_event_data(event);
	memset(&entry->caller, 0, sizeof(entry->caller));

	trace.nr_entries	= 0;
	trace.max_entries	= FTRACE_STACK_ENTRIES;
	trace.skip		= skip;
	trace.entries		= entry->caller;

	save_stack_trace(&trace);
	ring_buffer_unlock_commit(tr->buffer, event);
#endif
}

static void ftrace_trace_stack(struct trace_array *tr,
			       unsigned long flags,
			       int skip, int pc)
{
	if (!(trace_flags & TRACE_ITER_STACKTRACE))
		return;

	__ftrace_trace_stack(tr, flags, skip, pc);
}

void __trace_stack(struct trace_array *tr,
		   unsigned long flags,
		   int skip, int pc)
{
	__ftrace_trace_stack(tr, flags, skip, pc);
}

static void ftrace_trace_userstack(struct trace_array *tr,
				   unsigned long flags, int pc)
{
#ifdef CONFIG_STACKTRACE
	struct ring_buffer_event *event;
	struct userstack_entry *entry;
	struct stack_trace trace;