trace.c

/*
 * ring buffer based function tracer
 *
 * Copyright (C) 2007-2012 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 Nadia Yvette Chambers
 */
#include <linux/ring_buffer.h>
#include <generated/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/string.h>
#include <linux/rwsem.h>
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/fs.h>
#include <linux/sched/rt.h>

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

/*
 * 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.
 */
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.
 */
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;
}

/*
 * To prevent the comm cache from being overwritten when no
 * tracing is active, only save the comm when a trace event
 * occurred.
 */
static DEFINE_PER_CPU(bool, trace_cmdline_save);

/*
 * 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;

DEFINE_PER_CPU(int, ftrace_cpu_disabled);

cpumask_var_t __read_mostly	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
 * Set 1 if you want to dump buffers of all CPUs
 * Set 2 if you want to dump the buffer of the CPU that triggered oops
 */

enum ftrace_dump_mode ftrace_dump_on_oops;

static int tracing_set_tracer(const char *buf);

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

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

static int __init set_ftrace_dump_on_oops(char *str)
{
	if (*str++ != '=' || !*str) {
		ftrace_dump_on_oops = DUMP_ALL;
		return 1;
	}

	if (!strcmp("orig_cpu", str)) {
		ftrace_dump_on_oops = DUMP_ORIG;
                return 1;
        }

        return 0;
}
__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);


static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
static char *trace_boot_options __initdata;

static int __init set_trace_boot_options(char *str)
{
	strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
	trace_boot_options = trace_boot_options_buf;
	return 0;
}
__setup("trace_options=", set_trace_boot_options);

unsigned long 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;

LIST_HEAD(ftrace_trace_arrays);

int filter_current_check_discard(struct ring_buffer *buffer,
				 struct ftrace_event_call *call, void *rec,
				 struct ring_buffer_event *event)
{
	return filter_check_discard(call, rec, buffer, event);
}
EXPORT_SYMBOL_GPL(filter_current_check_discard);

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;

int tracing_is_enabled(void)
{
	return tracing_is_on();
}

/*
 * 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;

/*
 * trace_types_lock is used to protect the trace_types list.
 */
static DEFINE_MUTEX(trace_types_lock);

/*
 * serialize the access of the ring buffer
 *
 * ring buffer serializes readers, but it is low level protection.
 * The validity of the events (which returns by ring_buffer_peek() ..etc)
 * are not protected by ring buffer.
 *
 * The content of events may become garbage if we allow other process consumes
 * these events concurrently:
 *   A) the page of the consumed events may become a normal page
 *      (not reader page) in ring buffer, and this page will be rewrited
 *      by events producer.
 *   B) The page of the consumed events may become a page for splice_read,
 *      and this page will be returned to system.
 *
 * These primitives allow multi process access to different cpu ring buffer
 * concurrently.
 *
 * These primitives don't distinguish read-only and read-consume access.
 * Multi read-only access are also serialized.
 */

#ifdef CONFIG_SMP
static DECLARE_RWSEM(all_cpu_access_lock);
static DEFINE_PER_CPU(struct mutex, cpu_access_lock);

static inline void trace_access_lock(int cpu)
{
	if (cpu == RING_BUFFER_ALL_CPUS) {
		/* gain it for accessing the whole ring buffer. */
		down_write(&all_cpu_access_lock);
	} else {
		/* gain it for accessing a cpu ring buffer. */

		/* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */
		down_read(&all_cpu_access_lock);

		/* Secondly block other access to this @cpu ring buffer. */
		mutex_lock(&per_cpu(cpu_access_lock, cpu));
	}
}

static inline void trace_access_unlock(int cpu)
{
	if (cpu == RING_BUFFER_ALL_CPUS) {
		up_write(&all_cpu_access_lock);
	} else {
		mutex_unlock(&per_cpu(cpu_access_lock, cpu));
		up_read(&all_cpu_access_lock);
	}
}

static inline void trace_access_lock_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		mutex_init(&per_cpu(cpu_access_lock, cpu));
}

#else

static DEFINE_MUTEX(access_lock);

static inline void trace_access_lock(int cpu)
{
	(void)cpu;
	mutex_lock(&access_lock);
}

static inline void trace_access_unlock(int cpu)
{
	(void)cpu;
	mutex_unlock(&access_lock);
}

static inline void trace_access_lock_init(void)
{
}

#endif

/* 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_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS;

/**
 * tracing_on - enable tracing buffers
 *
 * This function enables tracing buffers that may have been
 * disabled with tracing_off.
 */
void tracing_on(void)
{
	if (global_trace.buffer)
		ring_buffer_record_on(global_trace.buffer);
	/*
	 * This flag is only looked at when buffers haven't been
	 * allocated yet. We don't really care about the race
	 * between setting this flag and actually turning
	 * on the buffer.
	 */
	global_trace.buffer_disabled = 0;
}
EXPORT_SYMBOL_GPL(tracing_on);

/**
 * tracing_off - turn off tracing buffers
 *
 * This function stops the tracing buffers from recording data.
 * It does not disable any overhead the tracers themselves may
 * be causing. This function simply causes all recording to
 * the ring buffers to fail.
 */
void tracing_off(void)
{
	if (global_trace.buffer)
		ring_buffer_record_off(global_trace.buffer);
	/*
	 * This flag is only looked at when buffers haven't been
	 * allocated yet. We don't really care about the race
	 * between setting this flag and actually turning
	 * on the buffer.
	 */
	global_trace.buffer_disabled = 1;
}
EXPORT_SYMBOL_GPL(tracing_off);

/**
 * tracing_is_on - show state of ring buffers enabled
 */
int tracing_is_on(void)
{
	if (global_trace.buffer)
		return ring_buffer_record_is_on(global_trace.buffer);
	return !global_trace.buffer_disabled;
}
EXPORT_SYMBOL_GPL(tracing_is_on);

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

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

static int __init set_tracing_thresh(char *str)
{
	unsigned long threshold;
	int ret;

	if (!str)
		return 0;
	ret = kstrtoul(str, 0, &threshold);
	if (ret < 0)
		return 0;
	tracing_thresh = threshold * 1000;
	return 1;
}
__setup("tracing_thresh=", set_tracing_thresh);

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",
	"trace_printk",
	"ftrace_preempt",
	"branch",
	"annotate",
	"userstacktrace",
	"sym-userobj",
	"printk-msg-only",
	"context-info",
	"latency-format",
	"sleep-time",
	"graph-time",
	"record-cmd",
	"overwrite",
	"disable_on_free",
	"irq-info",
	"markers",
	NULL
};

static struct {
	u64 (*func)(void);
	const char *name;
	int in_ns;		/* is this clock in nanoseconds? */
} trace_clocks[] = {
	{ trace_clock_local,	"local",	1 },
	{ trace_clock_global,	"global",	1 },
	{ trace_clock_counter,	"counter",	0 },
	ARCH_TRACE_CLOCKS
};

int trace_clock_id;

/*
 * trace_parser_get_init - gets the buffer for trace parser
 */
int trace_parser_get_init(struct trace_parser *parser, int size)
{
	memset(parser, 0, sizeof(*parser));

	parser->buffer = kmalloc(size, GFP_KERNEL);
	if (!parser->buffer)
		return 1;

	parser->size = size;
	return 0;
}

/*
 * trace_parser_put - frees the buffer for trace parser
 */
void trace_parser_put(struct trace_parser *parser)
{
	kfree(parser->buffer);
}

/*
 * trace_get_user - reads the user input string separated by  space
 * (matched by isspace(ch))
 *
 * For each string found the 'struct trace_parser' is updated,
 * and the function returns.
 *
 * Returns number of bytes read.
 *
 * See kernel/trace/trace.h for 'struct trace_parser' details.
 */
int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
	size_t cnt, loff_t *ppos)
{
	char ch;
	size_t read = 0;
	ssize_t ret;

	if (!*ppos)
		trace_parser_clear(parser);

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

	read++;
	cnt--;

	/*
	 * The parser is not finished with the last write,
	 * continue reading the user input without skipping spaces.
	 */
	if (!parser->cont) {
		/* skip white space */
		while (cnt && isspace(ch)) {
			ret = get_user(ch, ubuf++);
			if (ret)
				goto out;
			read++;
			cnt--;
		}

		/* only spaces were written */
		if (isspace(ch)) {
			*ppos += read;
			ret = read;
			goto out;
		}

		parser->idx = 0;
	}

	/* read the non-space input */
	while (cnt && !isspace(ch)) {
		if (parser->idx < parser->size - 1)
			parser->buffer[parser->idx++] = ch;
		else {
			ret = -EINVAL;
			goto out;
		}
		ret = get_user(ch, ubuf++);
		if (ret)
			goto out;
		read++;
		cnt--;
	}

	/* We either got finished input or we have to wait for another call. */
	if (isspace(ch)) {
		parser->buffer[parser->idx] = 0;
		parser->cont = false;
	} else {
		parser->cont = true;
		parser->buffer[parser->idx++] = ch;
	}

	*ppos += read;
	ret = read;

out:
	return ret;
}

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;

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

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

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

/*
 * 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 arch_spinlock_t in order to help
 * with performance when lockdep debugging is enabled.
 *
 * It is also used in other places outside the update_max_tr
 * so it needs to be defined outside of the
 * CONFIG_TRACER_MAX_TRACE.
 */
static arch_spinlock_t ftrace_max_lock =
	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;

unsigned long __read_mostly	tracing_thresh;

#ifdef CONFIG_TRACER_MAX_TRACE
unsigned long __read_mostly	tracing_max_latency;

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

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

	max_data = per_cpu_ptr(max_tr.data, cpu);
	max_data->saved_latency = tracing_max_latency;
	max_data->critical_start = data->critical_start;
	max_data->critical_end = data->critical_end;

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

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

/**
 * 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;

	if (tr->stop_count)
		return;

	WARN_ON_ONCE(!irqs_disabled());

	if (!tr->current_trace->allocated_snapshot) {
		/* Only the nop tracer should hit this when disabling */
		WARN_ON_ONCE(tr->current_trace != &nop_trace);
		return;
	}

	arch_spin_lock(&ftrace_max_lock);

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

	__update_max_tr(tr, tsk, cpu);
	arch_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;

	if (tr->stop_count)
		return;

	WARN_ON_ONCE(!irqs_disabled());
	if (WARN_ON_ONCE(!tr->current_trace->allocated_snapshot))
		return;

	arch_spin_lock(&ftrace_max_lock);

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

	if (ret == -EBUSY) {
		/*
		 * We failed to swap the buffer due to a commit taking
		 * place on this CPU. We fail to record, but we reset
		 * the max trace buffer (no one writes directly to it)
		 * and flag that it failed.
		 */
		trace_array_printk(&max_tr, _THIS_IP_,
			"Failed to swap buffers due to commit in progress\n");
	}

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

	__update_max_tr(tr, tsk, cpu);
	arch_spin_unlock(&ftrace_max_lock);
}
#endif /* CONFIG_TRACER_MAX_TRACE */

static void default_wait_pipe(struct trace_iterator *iter)
{
	/* Iterators are static, they should be filled or empty */
	if (trace_buffer_iter(iter, iter->cpu_file))
		return;

	ring_buffer_wait(iter->tr->buffer, iter->cpu_file);
}

/**
 * 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)
{
	struct tracer *t;
	int ret = 0;

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

	if (strlen(type->name) >= MAX_TRACER_SIZE) {
		pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
		return -1;
	}

	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("Tracer %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 trace_array *tr = &global_trace;
		struct tracer *saved_tracer = tr->current_trace;

		/*
		 * 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.
		 */
		tracing_reset_online_cpus(tr);

		tr->current_trace = type;

		if (type->use_max_tr) {
			/* If we expanded the buffers, make sure the max is expanded too */
			if (ring_buffer_expanded)
				ring_buffer_resize(max_tr.buffer, trace_buf_size,
						   RING_BUFFER_ALL_CPUS);
			type->allocated_snapshot = true;
		}

		/* 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 */
		tr->current_trace = saved_tracer;
		if (ret) {
			printk(KERN_CONT "FAILED!\n");
			/* Add the warning after printing 'FAILED' */
			WARN_ON(1);
			goto out;
		}
		/* Only reset on passing, to avoid touching corrupted buffers */
		tracing_reset_online_cpus(tr);

		if (type->use_max_tr) {
			type->allocated_snapshot = false;

			/* Shrink the max buffer again */
			if (ring_buffer_expanded)
				ring_buffer_resize(max_tr.buffer, 1,
						   RING_BUFFER_ALL_CPUS);
		}

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

	type->next = trace_types;
	trace_types = type;

 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, MAX_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:
	return ret;
}

void tracing_reset(struct trace_array *tr, int cpu)
{
	struct ring_buffer *buffer = tr->buffer;

	if (!buffer)
		return;

	ring_buffer_record_disable(buffer);

	/* Make sure all commits have finished */
	synchronize_sched();
	ring_buffer_reset_cpu(buffer, cpu);

	ring_buffer_record_enable(buffer);
}

void tracing_reset_online_cpus(struct trace_array *tr)
{
	struct ring_buffer *buffer = tr->buffer;
	int cpu;

	if (!buffer)
		return;

	ring_buffer_record_disable(buffer);

	/* Make sure all commits have finished */
	synchronize_sched();

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

	for_each_online_cpu(cpu)
		ring_buffer_reset_cpu(buffer, cpu);

	ring_buffer_record_enable(buffer);
}

void tracing_reset_current(int cpu)
{
	tracing_reset(&global_trace, cpu);
}

void tracing_reset_all_online_cpus(void)
{
	struct trace_array *tr;

	mutex_lock(&trace_types_lock);
	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
		tracing_reset_online_cpus(tr);
	}
	mutex_unlock(&trace_types_lock);
}

#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 arch_spinlock_t trace_cmdline_lock = __ARCH_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;
}

int is_tracing_stopped(void)
{
	return global_trace.stop_count;
}

/**
 * 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;

	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
	if (--global_trace.stop_count) {
		if (global_trace.stop_count < 0) {
			/* Someone screwed up their debugging */
			WARN_ON_ONCE(1);
			global_trace.stop_count = 0;
		}
		goto out;
	}

	/* Prevent the buffers from switching */
	arch_spin_lock(&ftrace_max_lock);

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

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

	arch_spin_unlock(&ftrace_max_lock);

	ftrace_start();
 out:
	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
}

static void tracing_start_tr(struct trace_array *tr)
{
	struct ring_buffer *buffer;
	unsigned long flags;

	if (tracing_disabled)
		return;

	/* If global, we need to also start the max tracer */
	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
		return tracing_start();

	raw_spin_lock_irqsave(&tr->start_lock, flags);

	if (--tr->stop_count) {
		if (tr->stop_count < 0) {
			/* Someone screwed up their debugging */
			WARN_ON_ONCE(1);
			tr->stop_count = 0;
		}
		goto out;
	}

	buffer = tr->buffer;
	if (buffer)
		ring_buffer_record_enable(buffer);

 out:
	raw_spin_unlock_irqrestore(&tr->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();
	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
	if (global_trace.stop_count++)
		goto out;

	/* Prevent the buffers from switching */
	arch_spin_lock(&ftrace_max_lock);

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

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

	arch_spin_unlock(&ftrace_max_lock);

 out:
	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
}

static void tracing_stop_tr(struct trace_array *tr)
{
	struct ring_buffer *buffer;
	unsigned long flags;

	/* If global, we need to also stop the max tracer */
	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
		return tracing_stop();

	raw_spin_lock_irqsave(&tr->start_lock, flags);
	if (tr->stop_count++)
		goto out;

	buffer = tr->buffer;
	if (buffer)
		ring_buffer_record_disable(buffer);

 out:
	raw_spin_unlock_irqrestore(&tr->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 (!arch_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);

	arch_spin_unlock(&trace_cmdline_lock);
}

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

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

	if (WARN_ON_ONCE(pid < 0)) {
		strcpy(comm, "<XXX>");
		return;
	}

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

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

	arch_spin_unlock(&trace_cmdline_lock);
	preempt_enable();
}

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

	if (!__this_cpu_read(trace_cmdline_save))
		return;

	__this_cpu_write(trace_cmdline_save, false);

	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->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);
}
EXPORT_SYMBOL_GPL(tracing_generic_entry_update);

struct ring_buffer_event *
trace_buffer_lock_reserve(struct ring_buffer *buffer,
			  int type,
			  unsigned long len,
			  unsigned long flags, int pc)
{
	struct ring_buffer_event *event;

	event = ring_buffer_lock_reserve(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;
}

void
__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
{
	__this_cpu_write(trace_cmdline_save, true);
	ring_buffer_unlock_commit(buffer, event);
}

static inline void
__trace_buffer_unlock_commit(struct ring_buffer *buffer,
			     struct ring_buffer_event *event,
			     unsigned long flags, int pc)
{
	__buffer_unlock_commit(buffer, event);

	ftrace_trace_stack(buffer, flags, 6, pc);
	ftrace_trace_userstack(buffer, flags, pc);
}

void trace_buffer_unlock_commit(struct ring_buffer *buffer,
				struct ring_buffer_event *event,
				unsigned long flags, int pc)
{
	__trace_buffer_unlock_commit(buffer, event, flags, pc);
}
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);