/*
 * 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.
 */
bool 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 bool allocate_snapshot;

static int __init set_cmdline_ftrace(char *str)
{
        strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
        default_bootup_tracer = bootup_tracer_buf;
        /* We are using ftrace early, expand it */
        ring_buffer_expanded = true;
        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 int __init boot_alloc_snapshot(char *str)
{
        allocate_snapshot = true;
        /* We also need the main ring buffer expanded */
        ring_buffer_expanded = true;
        return 1;
}
__setup("alloc_snapshot", boot_alloc_snapshot);


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)
{
        strlcpy(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.trace_buffer.buffer)
                return trace_clock_local();

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

        return ts;
}

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 | TRACE_ITER_FUNCTION;

/**
 * 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.trace_buffer.buffer)
                ring_buffer_record_on(global_trace.trace_buffer.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);

/**
 * __trace_puts - write a constant string into the trace buffer.
 * @ip:    The address of the caller
 * @str:   The constant string to write
 * @size:  The size of the string.
 */
int __trace_puts(unsigned long ip, const char *str, int size)
{
        struct ring_buffer_event *event;
        struct ring_buffer *buffer;
        struct print_entry *entry;
        unsigned long irq_flags;
        int alloc;

        alloc = sizeof(*entry) + size + 2; /* possible \n added */

        local_save_flags(irq_flags);
        buffer = global_trace.trace_buffer.buffer;
        event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
                                          irq_flags, preempt_count());
        if (!event)
                return 0;

        entry = ring_buffer_event_data(event);
        entry->ip = ip;

        memcpy(&entry->buf, str, size);

        /* Add a newline if necessary */
        if (entry->buf[size - 1] != '\n') {
                entry->buf[size] = '\n';
                entry->buf[size + 1] = '\0';
        } else
                entry->buf[size] = '\0';

        __buffer_unlock_commit(buffer, event);

        return size;
}
EXPORT_SYMBOL_GPL(__trace_puts);

/**
 * __trace_bputs - write the pointer to a constant string into trace buffer
 * @ip:    The address of the caller
 * @str:   The constant string to write to the buffer to
 */
int __trace_bputs(unsigned long ip, const char *str)
{
        struct ring_buffer_event *event;
        struct ring_buffer *buffer;
        struct bputs_entry *entry;
        unsigned long irq_flags;
        int size = sizeof(struct bputs_entry);

        local_save_flags(irq_flags);
        buffer = global_trace.trace_buffer.buffer;
        event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
                                          irq_flags, preempt_count());
        if (!event)
                return 0;

        entry = ring_buffer_event_data(event);
        entry->ip                       = ip;
        entry->str                      = str;

        __buffer_unlock_commit(buffer, event);

        return 1;
}
EXPORT_SYMBOL_GPL(__trace_bputs);

#ifdef CONFIG_TRACER_SNAPSHOT
/**
 * trace_snapshot - take a snapshot of the current buffer.
 *
 * This causes a swap between the snapshot buffer and the current live
 * tracing buffer. You can use this to take snapshots of the live
 * trace when some condition is triggered, but continue to trace.
 *
 * Note, make sure to allocate the snapshot with either
 * a tracing_snapshot_alloc(), or by doing it manually
 * with: echo 1 > /sys/kernel/debug/tracing/snapshot
 *
 * If the snapshot buffer is not allocated, it will stop tracing.
 * Basically making a permanent snapshot.
 */
void tracing_snapshot(void)
{
        struct trace_array *tr = &global_trace;
        struct tracer *tracer = tr->current_trace;
        unsigned long flags;

        if (in_nmi()) {
                internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n");
                internal_trace_puts("*** snapshot is being ignored        ***\n");
                return;
        }

        if (!tr->allocated_snapshot) {
                internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n");
                internal_trace_puts("*** stopping trace here!   ***\n");
                tracing_off();
                return;
        }

        /* Note, snapshot can not be used when the tracer uses it */
        if (tracer->use_max_tr) {
                internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n");
                internal_trace_puts("*** Can not use snapshot (sorry) ***\n");
                return;
        }

        local_irq_save(flags);
        update_max_tr(tr, current, smp_processor_id());
        local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(tracing_snapshot);

static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
                                        struct trace_buffer *size_buf, int cpu_id);
static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);

static int alloc_snapshot(struct trace_array *tr)
{
        int ret;

        if (!tr->allocated_snapshot) {

                /* allocate spare buffer */
                ret = resize_buffer_duplicate_size(&tr->max_buffer,
                                   &tr->trace_buffer, RING_BUFFER_ALL_CPUS);
                if (ret < 0)
                        return ret;

                tr->allocated_snapshot = true;
        }

        return 0;
}

void free_snapshot(struct trace_array *tr)
{
        /*
         * We don't free the ring buffer. instead, resize it because
         * The max_tr ring buffer has some state (e.g. ring->clock) and
         * we want preserve it.
         */
        ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
        set_buffer_entries(&tr->max_buffer, 1);
        tracing_reset_online_cpus(&tr->max_buffer);
        tr->allocated_snapshot = false;
}

/**
 * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
 *
 * This is similar to trace_snapshot(), but it will allocate the
 * snapshot buffer if it isn't already allocated. Use this only
 * where it is safe to sleep, as the allocation may sleep.
 *
 * This causes a swap between the snapshot buffer and the current live
 * tracing buffer. You can use this to take snapshots of the live
 * trace when some condition is triggered, but continue to trace.
 */
void tracing_snapshot_alloc(void)
{
        struct trace_array *tr = &global_trace;
        int ret;

        ret = alloc_snapshot(tr);
        if (WARN_ON(ret < 0))
                return;

        tracing_snapshot();
}
EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
#else
void tracing_snapshot(void)
{
        WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
}
EXPORT_SYMBOL_GPL(tracing_snapshot);
void tracing_snapshot_alloc(void)
{
        /* Give warning */
        tracing_snapshot();
}
EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
#endif /* CONFIG_TRACER_SNAPSHOT */

/**
 * 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.trace_buffer.buffer)
                ring_buffer_record_off(global_trace.trace_buffer.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.trace_buffer.buffer)
                return ring_buffer_record_is_on(global_trace.trace_buffer.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",
        "function-trace",
        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 },
        { trace_clock_jiffies,  "uptime",       1 },
        { trace_clock,          "perf",         1 },
        ARCH_TRACE_CLOCKS
};

/*
 * 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_buffer *trace_buf = &tr->trace_buffer;
        struct trace_buffer *max_buf = &tr->max_buffer;
        struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu);
        struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu);

        max_buf->cpu = cpu;
        max_buf->time_start = data->preempt_timestamp;

        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;
        /*
         * If tsk == current, then use current_uid(), as that does not use
         * RCU. The irq tracer can be called out of RCU scope.
         */
        if (tsk == current)
                max_data->uid = current_uid();
        else
                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->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->trace_buffer.buffer;
        tr->trace_buffer.buffer = tr->max_buffer.buffer;
        tr->max_buffer.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 (!tr->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);

        ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.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_buf(tr->max_buffer.buffer, _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->trace_buffer->buffer, iter->cpu_file);
}

#ifdef CONFIG_FTRACE_STARTUP_TEST
static int run_tracer_selftest(struct tracer *type)
{
        struct trace_array *tr = &global_trace;
        struct tracer *saved_tracer = tr->current_trace;
        int ret;

        if (!type->selftest || tracing_selftest_disabled)
                return 0;

        /*
         * 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->trace_buffer);

        tr->current_trace = type;

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

        /* 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);
                return -1;
        }
        /* Only reset on passing, to avoid touching corrupted buffers */
        tracing_reset_online_cpus(&tr->trace_buffer);

#ifdef CONFIG_TRACER_MAX_TRACE
        if (type->use_max_tr) {
                tr->allocated_snapshot = false;

                /* Shrink the max buffer again */
                if (ring_buffer_expanded)

                        ring_buffer_resize(tr->max_buffer.buffer, 1,
                                           RING_BUFFER_ALL_CPUS);
        }
#endif

        printk(KERN_CONT "PASSED\n");
        return 0;
}
#else
static inline int run_tracer_selftest(struct tracer *type)
{
        return 0;
}
#endif /* CONFIG_FTRACE_STARTUP_TEST */

/**
 * 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;

        ret = run_tracer_selftest(type);
        if (ret < 0)
                goto out;

        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 = true;
#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_buffer *buf, int cpu)
{
        struct ring_buffer *buffer = buf->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_buffer *buf)
{
        struct ring_buffer *buffer = buf->buffer;
        int cpu;

        if (!buffer)
                return;

        ring_buffer_record_disable(buffer);

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

        buf->time_start = ftrace_now(buf->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.trace_buffer, 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->trace_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
                tracing_reset_online_cpus(&tr->max_buffer);
#endif
        }
        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.trace_buffer.buffer;
        if (buffer)
                ring_buffer_record_enable(buffer);

#ifdef CONFIG_TRACER_MAX_TRACE
        buffer = global_trace.max_buffer.buffer;
        if (buffer)
                ring_buffer_record_enable(buffer);
#endif

        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->trace_buffer.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.trace_buffer.buffer;
        if (buffer)
                ring_buffer_record_disable(buffer);

#ifdef CONFIG_TRACER_MAX_TRACE
        buffer = global_trace.max_buffer.buffer;
        if (buffer)
                ring_buffer_record_disable(buffer);
#endif

        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->trace_buffer.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);

struct ring_buffer_event *
trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
                          struct ftrace_event_file *ftrace_file,
                          int type, unsigned long len,
                          unsigned long flags, int pc)
{
        *current_rb = ftrace_file->tr->trace_buffer.buffer;
        return trace_buffer_lock_reserve(*current_rb,
                                         type, len, flags, pc);
}
EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);

struct ring_buffer_event *
trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
                                  int type, unsigned long len,
                                  unsigned long flags, int pc)
{
        *current_rb = global_trace.trace_buffer.buffer;
        return trace_buffer_lock_reserve(*current_rb,
                                         type, len, flags, pc);
}
EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);

void trace_current_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_current_buffer_unlock_commit);

void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
                                     struct ring_buffer_event *event,
                                     unsigned long flags, int pc,
                                     struct pt_regs *regs)
{
        __buffer_unlock_commit(buffer, event);

        ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
        ftrace_trace_userstack(buffer, flags, pc);
}
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);

void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
                                         struct ring_buffer_event *event)
{
        ring_buffer_discard_commit(buffer, event);
}
EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);

void
trace_function(struct trace_array *tr,
               unsigned long ip, unsigned long parent_ip, unsigned long flags,
               int pc)
{
        struct ftrace_event_call *call = &event_function;
        struct ring_buffer *buffer = tr->trace_buffer.buffer;
        struct ring_buffer_event *event;
        struct ftrace_entry *entry;

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

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

        if (!filter_check_discard(call, entry, buffer, event))
                __buffer_unlock_commit(buffer, event);
}

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);
}

#ifdef CONFIG_STACKTRACE

#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
struct ftrace_stack {
        unsigned long           calls[FTRACE_STACK_MAX_ENTRIES];
};

static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
static DEFINE_PER_CPU(int, ftrace_stack_reserve);

static void __ftrace_trace_stack(struct ring_buffer *buffer,
                                 unsigned long flags,
                                 int skip, int pc, struct pt_regs *regs)
{
        struct ftrace_event_call *call = &event_kernel_stack;
        struct ring_buffer_event *event;
        struct stack_entry *entry;
        struct stack_trace trace;
        int use_stack;
        int size = FTRACE_STACK_ENTRIES;

        trace.nr_entries        = 0;
        trace.skip              = skip;

        /*
         * Since events can happen in NMIs there's no safe way to
         * use the per cpu ftrace_stacks. We reserve it and if an interrupt
         * or NMI comes in, it will just have to use the default
         * FTRACE_STACK_SIZE.
         */
        preempt_disable_notrace();

        use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
        /*
         * We don't need any atomic variables, just a barrier.
         * If an interrupt comes in, we don't care, because it would
         * have exited and put the counter back to what we want.
         * We just need a barrier to keep gcc from moving things
         * around.
         */
        barrier();
        if (use_stack == 1) {
                trace.entries           = &__get_cpu_var(ftrace_stack).calls[0];
                trace.max_entries       = FTRACE_STACK_MAX_ENTRIES;

                if (regs)
                        save_stack_trace_regs(regs, &trace);
                else
                        save_stack_trace(&trace);

                if (trace.nr_entries > size)
                        size = trace.nr_entries;
        } else
                /* From now on, use_stack is a boolean */
                use_stack = 0;

        size *= sizeof(unsigned long);

        event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
                                          sizeof(*entry) + size, flags, pc);
        if (!event)
                goto out;
        entry = ring_buffer_event_data(event);

        memset(&entry->caller, 0, size);

        if (use_stack)
                memcpy(&entry->caller, trace.entries,
                       trace.nr_entries * sizeof(unsigned long));
        else {
                trace.max_entries       = FTRACE_STACK_ENTRIES;
                trace.entries           = entry->caller;
                if (regs)
                        save_stack_trace_regs(regs, &trace);
                else
                        save_stack_trace(&trace);
        }

        entry->size = trace.nr_entries;

        if (!filter_check_discard(call, entry, buffer, event))
                __buffer_unlock_commit(buffer, event);

 out:
        /* Again, don't let gcc optimize things here */
        barrier();
        __this_cpu_dec(ftrace_stack_reserve);
        preempt_enable_notrace();

}

void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
                             int skip, int pc, struct pt_regs *regs)
{
        if (!(trace_flags & TRACE_ITER_STACKTRACE))
                return;

        __ftrace_trace_stack(buffer, flags, skip, pc, regs);
}

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

        __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
}

void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
                   int pc)
{
        __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL);
}

/**
 * trace_dump_stack - record a stack back trace in the trace buffer
 * @skip: Number of functions to skip (helper handlers)
 */
void trace_dump_stack(int skip)
{
        unsigned long flags;

        if (tracing_disabled || tracing_selftest_running)
                return;

        local_save_flags(flags);

        /*
         * Skip 3 more, seems to get us at the caller of
         * this function.
         */
        skip += 3;
        __ftrace_trace_stack(global_trace.trace_buffer.buffer,
                             flags, skip, preempt_count(), NULL);
}

static DEFINE_PER_CPU(int, user_stack_count);

void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
        struct ftrace_event_call *call = &event_user_stack;
        struct ring_buffer_event *event;
        struct userstack_entry *entry;
        struct stack_trace trace;

        if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
                return;

        /*
         * NMIs can not handle page faults, even with fix ups.
         * The save user stack can (and often does) fault.
         */
        if (unlikely(in_nmi()))
                return;

        /*
         * prevent recursion, since the user stack tracing may
         * trigger other kernel events.
         */
        preempt_disable();
        if (__this_cpu_read(user_stack_count))
                goto out;

        __this_cpu_inc(user_stack_count);

        event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
                                          sizeof(*entry), flags, pc);
        if (!event)
                goto out_drop_count;
        entry   = ring_buffer_event_data(event);

        entry->tgid             = current->tgid;
        memset(&entry->caller, 0, sizeof(entry->caller));

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

        save_stack_trace_user(&trace);
        if (!filter_check_discard(call, entry, buffer, event))
                __buffer_unlock_commit(buffer, event);

 out_drop_count:
        __this_cpu_dec(user_stack_count);
 out:
        preempt_enable();
}

#ifdef UNUSED
static void __trace_userstack(struct trace_array *tr, unsigned long flags)
{
        ftrace_trace_userstack(tr, flags, preempt_count());
}
#endif /* UNUSED */

#endif /* CONFIG_STACKTRACE */

/* created for use with alloc_percpu */
struct trace_buffer_struct {
        char buffer[TRACE_BUF_SIZE];
};

static struct trace_buffer_struct *trace_percpu_buffer;
static struct trace_buffer_struct *trace_percpu_sirq_buffer;
static struct trace_buffer_struct *trace_percpu_irq_buffer;
static struct trace_buffer_struct *trace_percpu_nmi_buffer;

/*
 * The buffer used is dependent on the context. There is a per cpu
 * buffer for normal context, softirq contex, hard irq context and
 * for NMI context. Thise allows for lockless recording.
 *
 * Note, if the buffers failed to be allocated, then this returns NULL
 */
static char *get_trace_buf(void)
{
        struct trace_buffer_struct *percpu_buffer;

        /*
         * If we have allocated per cpu buffers, then we do not
         * need to do any locking.
         */
        if (in_nmi())
                percpu_buffer = trace_percpu_nmi_buffer;
        else if (in_irq())
                percpu_buffer = trace_percpu_irq_buffer;
        else if (in_softirq())
                percpu_buffer = trace_percpu_sirq_buffer;
        else
                percpu_buffer = trace_percpu_buffer;

        if (!percpu_buffer)
                return NULL;

        return this_cpu_ptr(&percpu_buffer->buffer[0]);
}

static int alloc_percpu_trace_buffer(void)
{
        struct trace_buffer_struct *buffers;
        struct trace_buffer_struct *sirq_buffers;
        struct trace_buffer_struct *irq_buffers;
        struct trace_buffer_struct *nmi_buffers;

        buffers = alloc_percpu(struct trace_buffer_struct);
        if (!buffers)
                goto err_warn;

        sirq_buffers = alloc_percpu(struct trace_buffer_struct);
        if (!sirq_buffers)
                goto err_sirq;

        irq_buffers = alloc_percpu(struct trace_buffer_struct);
        if (!irq_buffers)
                goto err_irq;

        nmi_buffers = alloc_percpu(struct trace_buffer_struct);
        if (!nmi_buffers)
                goto err_nmi;

        trace_percpu_buffer = buffers;
        trace_percpu_sirq_buffer = sirq_buffers;
        trace_percpu_irq_buffer = irq_buffers;
        trace_percpu_nmi_buffer = nmi_buffers;

        return 0;

 err_nmi:
        free_percpu(irq_buffers);
 err_irq:
        free_percpu(sirq_buffers);
 err_sirq:
        free_percpu(buffers);
 err_warn:
        WARN(1, "Could not allocate percpu trace_printk buffer");
        return -ENOMEM;
}

static int buffers_allocated;

void trace_printk_init_buffers(void)
{
        if (buffers_allocated)
                return;

        if (alloc_percpu_trace_buffer())
                return;

        pr_info("ftrace: Allocated trace_printk buffers\n");

        /* Expand the buffers to set size */
        tracing_update_buffers();

        buffers_allocated = 1;

        /*
         * trace_printk_init_buffers() can be called by modules.
         * If that happens, then we need to start cmdline recording
         * directly here. If the global_trace.buffer is already
         * allocated here, then this was called by module code.
         */
        if (global_trace.trace_buffer.buffer)
                tracing_start_cmdline_record();
}

void trace_printk_start_comm(void)
{
        /* Start tracing comms if trace printk is set */
        if (!buffers_allocated)
                return;
        tracing_start_cmdline_record();
}

static void trace_printk_start_stop_comm(int enabled)
{
        if (!buffers_allocated)
                return;

        if (enabled)
                tracing_start_cmdline_record();
        else
                tracing_stop_cmdline_record();
}

/**
 * trace_vbprintk - write binary msg to tracing buffer
 *
 */
int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
{
        struct ftrace_event_call *call = &event_bprint;
        struct ring_buffer_event *event;
        struct ring_buffer *buffer;
        struct trace_array *tr = &global_trace;
        struct bprint_entry *entry;
        unsigned long flags;
        char *tbuffer;
        int len = 0, size, pc;

        if (unlikely(tracing_selftest_running || tracing_disabled))
                return 0;

        /* Don't pollute graph traces with trace_vprintk internals */
        pause_graph_tracing();

        pc = preempt_count();
        preempt_disable_notrace();

        tbuffer = get_trace_buf();
        if (!tbuffer) {
                len = 0;
                goto out;
        }

        len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args);

        if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0)
                goto out;

        local_save_flags(flags);
        size = sizeof(*entry) + sizeof(u32) * len;
        buffer = tr->trace_buffer.buffer;
        event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
                                          flags, pc);
        if (!event)
                goto out;
        entry = ring_buffer_event_data(event);
        entry->ip                       = ip;
        entry->fmt                      = fmt;

        memcpy(entry->buf, tbuffer, sizeof(u32) * len);
        if (!filter_check_discard(call, entry, buffer, event)) {
                __buffer_unlock_commit(buffer, event);
                ftrace_trace_stack(buffer, flags, 6, pc);
        }

out:
        preempt_enable_notrace();
        unpause_graph_tracing();

        return len;
}
EXPORT_SYMBOL_GPL(trace_vbprintk);

static int
__trace_array_vprintk(struct ring_buffer *buffer,
                      unsigned long ip, const char *fmt, va_list args)
{
        struct ftrace_event_call *call = &event_print;
        struct ring_buffer_event *event;
        int len = 0, size, pc;
        struct print_entry *entry;
        unsigned long flags;
        char *tbuffer;

        if (tracing_disabled || tracing_selftest_running)
                return 0;

        /* Don't pollute graph traces with trace_vprintk internals */
        pause_graph_tracing();

        pc = preempt_count();
        preempt_disable_notrace();


        tbuffer = get_trace_buf();
        if (!tbuffer) {
                len = 0;
                goto out;
        }

        len = vsnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
        if (len > TRACE_BUF_SIZE)
                goto out;

        local_save_flags(flags);
        size = sizeof(*entry) + len + 1;
        event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
                                          flags, pc);
        if (!event)
                goto out;
        entry = ring_buffer_event_data(event);
        entry->ip = ip;

        memcpy(&entry->buf, tbuffer, len);
        entry->buf[len] = '\0';
        if (!filter_check_discard(call, entry, buffer, event)) {
                __buffer_unlock_commit(buffer, event);
                ftrace_trace_stack(buffer, flags, 6, pc);
        }
 out:
        preempt_enable_notrace();
        unpause_graph_tracing();

        return len;
}

int trace_array_vprintk(struct trace_array *tr,
                        unsigned long ip, const char *fmt, va_list args)
{
        return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
}

int trace_array_printk(struct trace_array *tr,
                       unsigned long ip, const char *fmt, ...)
{
        int ret;
        va_list ap;

        if (!(trace_flags & TRACE_ITER_PRINTK))
                return 0;

        va_start(ap, fmt);
        ret = trace_array_vprintk(tr, ip, fmt, ap);
        va_end(ap);
        return ret;
}

int trace_array_printk_buf(struct ring_buffer *buffer,
                           unsigned long ip, const char *fmt, ...)
{
        int ret;
        va_list ap;

        if (!(trace_flags & TRACE_ITER_PRINTK))
                return 0;

        va_start(ap, fmt);
        ret = __trace_array_vprintk(buffer, ip, fmt, ap);
        va_end(ap);
        return ret;
}

int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
        return trace_array_vprintk(&global_trace, ip, fmt, args);
}
EXPORT_SYMBOL_GPL(trace_vprintk);

static void trace_iterator_increment(struct trace_iterator *iter)
{
        struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu);

        iter->idx++;
        if (buf_iter)
                ring_buffer_read(buf_iter, NULL);
}

static struct trace_entry *
peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
                unsigned long *lost_events)
{
        struct ring_buffer_event *event;
        struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu);

        if (buf_iter)
                event = ring_buffer_iter_peek(buf_iter, ts);
        else
                event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts,
                                         lost_events);

        if (event) {
                iter->ent_size = ring_buffer_event_length(event);
                return ring_buffer_event_data(event);
        }
        iter->ent_size = 0;
        return NULL;
}

static struct trace_entry *
__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
                  unsigned long *missing_events, u64 *ent_ts)
{
        struct ring_buffer *buffer = iter->trace_buffer->buffer;
        struct trace_entry *ent, *next = NULL;
        unsigned long lost_events = 0, next_lost = 0;
        int cpu_file = iter->cpu_file;
        u64 next_ts = 0, ts;
        int next_cpu = -1;
        int next_size = 0;
        int cpu;

        /*
         * If we are in a per_cpu trace file, don't bother by iterating over
         * all cpu and peek directly.
         */
        if (cpu_file > RING_BUFFER_ALL_CPUS) {
                if (ring_buffer_empty_cpu(buffer, cpu_file))
                        return NULL;
                ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
                if (ent_cpu)
                        *ent_cpu = cpu_file;

                return ent;
        }

        for_each_tracing_cpu(cpu) {

                if (ring_buffer_empty_cpu(buffer, cpu))
                        continue;

                ent = peek_next_entry(iter, cpu, &ts, &lost_events);

                /*
                 * Pick the entry with the smallest timestamp:
                 */
                if (ent && (!next || ts < next_ts)) {
                        next = ent;
                        next_cpu = cpu;
                        next_ts = ts;
                        next_lost = lost_events;
                        next_size = iter->ent_size;
                }
        }

        iter->ent_size = next_size;

        if (ent_cpu)
                *ent_cpu = next_cpu;

        if (ent_ts)
                *ent_ts = next_ts;

        if (missing_events)
                *missing_events = next_lost;

        return next;
}

/* Find the next real entry, without updating the iterator itself */
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
                                          int *ent_cpu, u64 *ent_ts)
{
        return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
}

/* Find the next real entry, and increment the iterator to the next entry */
void *trace_find_next_entry_inc(struct trace_iterator *iter)
{
        iter->ent = __find_next_entry(iter, &iter->cpu,
                                      &iter->lost_events, &iter->ts);

        if (iter->ent)
                trace_iterator_increment(iter);

        return iter->ent ? iter : NULL;
}

static void trace_consume(struct trace_iterator *iter)
{
        ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts,
                            &iter->lost_events);
}

static void *s_next(struct seq_file *m, void *v, loff_t *pos)
{
        struct trace_iterator *iter = m->private;
        int i = (int)*pos;
        void *ent;

        WARN_ON_ONCE(iter->leftover);

        (*pos)++;

        /* can't go backwards */
        if (iter->idx > i)
                return NULL;

        if (iter->idx < 0)
                ent = trace_find_next_entry_inc(iter);
        else
                ent = iter;

        while (ent && iter->idx < i)
                ent = trace_find_next_entry_inc(iter);

        iter->pos = *pos;

        return ent;
}

void tracing_iter_reset(struct trace_iterator *iter, int cpu)
{
        struct ring_buffer_event *event;
        struct ring_buffer_iter *buf_iter;
        unsigned long entries = 0;
        u64 ts;

        per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0;

        buf_iter = trace_buffer_iter(iter, cpu);
        if (!buf_iter)
                return;

        ring_buffer_iter_reset(buf_iter);

        /*
         * We could have the case with the max latency tracers
         * that a reset never took place on a cpu. This is evident
         * by the timestamp being before the start of the buffer.
         */
        while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
                if (ts >= iter->trace_buffer->time_start)
                        break;
                entries++;
                ring_buffer_read(buf_iter, NULL);
        }

        per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries;
}

/*
 * The current tracer is copied to avoid a global locking
 * all around.
 */
static void *s_start(struct seq_file *m, loff_t *pos)
{
        struct trace_iterator *iter = m->private;
        struct trace_array *tr = iter->tr;
        int cpu_file = iter->cpu_file;
        void *p = NULL;
        loff_t l = 0;
        int cpu;

        /*
         * copy the tracer to avoid using a global lock all around.
         * iter->trace is a copy of current_trace, the pointer to the
         * name may be used instead of a strcmp(), as iter->trace->name
         * will point to the same string as current_trace->name.
         */
        mutex_lock(&trace_types_lock);
        if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name))
                *iter->trace = *tr->current_trace;
        mutex_unlock(&trace_types_lock);

#ifdef CONFIG_TRACER_MAX_TRACE
        if (iter->snapshot && iter->trace->use_max_tr)
                return ERR_PTR(-EBUSY);
#endif

        if (!iter->snapshot)
                atomic_inc(&trace_record_cmdline_disabled);

        if (*pos != iter->pos) {
                iter->ent = NULL;
                iter->cpu = 0;
                iter->idx = -1;

                if (cpu_file == RING_BUFFER_ALL_CPUS) {
                        for_each_tracing_cpu(cpu)
                                tracing_iter_reset(iter, cpu);
                } else
                        tracing_iter_reset(iter, cpu_file);

                iter->leftover = 0;
                for (p = iter; p && l < *pos; p = s_next(m, p, &l))
                        ;

        } else {
                /*
                 * If we overflowed the seq_file before, then we want
                 * to just reuse the trace_seq buffer again.
                 */
                if (iter->leftover)
                        p = iter;
                else {
                        l = *pos - 1;
                        p = s_next(m, p, &l);
                }
        }

        trace_event_read_lock();
        trace_access_lock(cpu_file);
        return p;
}

static void s_stop(struct seq_file *m, void *p)
{
        struct trace_iterator *iter = m->private;

#ifdef CONFIG_TRACER_MAX_TRACE
        if (iter->snapshot && iter->trace->use_max_tr)
                return;
#endif

        if (!iter->snapshot)
                atomic_dec(&trace_record_cmdline_disabled);

        trace_access_unlock(iter->cpu_file);
        trace_event_read_unlock();
}

static void
get_total_entries(struct trace_buffer *buf,
                  unsigned long *total, unsigned long *entries)
{
        unsigned long count;
        int cpu;

        *total = 0;
        *entries = 0;

        for_each_tracing_cpu(cpu) {
                count = ring_buffer_entries_cpu(buf->buffer, cpu);
                /*
                 * If this buffer has skipped entries, then we hold all
                 * entries for the trace and we need to ignore the
                 * ones before the time stamp.
                 */
                if (per_cpu_ptr(buf->data, cpu)->skipped_entries) {
                        count -= per_cpu_ptr(buf->data, cpu)->skipped_entries;
                        /* total is the same as the entries */
                        *total += count;
                } else
                        *total += count +
                                ring_buffer_overrun_cpu(buf->buffer, cpu);
                *entries += count;
        }
}

static void print_lat_help_header(struct seq_file *m)
{
        seq_puts(m, "#                  _------=> CPU#            \n");
        seq_puts(m, "#                 / _-----=> irqs-off        \n");
        seq_puts(m, "#                | / _----=> need-resched    \n");
        seq_puts(m, "#                || / _---=> hardirq/softirq \n");
        seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
        seq_puts(m, "#                |||| /     delay             \n");
        seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
        seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
}

static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
{
        unsigned long total;
        unsigned long entries;

        get_total_entries(buf, &total, &entries);
        seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu   #P:%d\n",
                   entries, total, num_online_cpus());
        seq_puts(m, "#\n");
}

static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
{
        print_event_info(buf, m);
        seq_puts(m, "#           TASK-PID   CPU#      TIMESTAMP  FUNCTION\n");
        seq_puts(m, "#              | |       |          |         |\n");
}

static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
{
        print_event_info(buf, m);
        seq_puts(m, "#                              _-----=> irqs-off\n");
        seq_puts(m, "#                             / _----=> need-resched\n");
        seq_puts(m, "#                            | / _---=> hardirq/softirq\n");
        seq_puts(m, "#                            || / _--=> preempt-depth\n");
        seq_puts(m, "#                            ||| /     delay\n");
        seq_puts(m, "#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION\n");
        seq_puts(m, "#              | |       |   ||||       |         |\n");
}

void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
        unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
        struct trace_buffer *buf = iter->trace_buffer;
        struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu);
        struct tracer *type = iter->trace;
        unsigned long entries;
        unsigned long total;
        const char *name = "preemption";

        name = type->name;

        get_total_entries(buf, &total, &entries);

        seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
                   name, UTS_RELEASE);
        seq_puts(m, "# -----------------------------------"
                 "---------------------------------\n");
        seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |"
                   " (M:%s VP:%d, KP:%d, SP:%d HP:%d",
                   nsecs_to_usecs(data->saved_latency),
                   entries,
                   total,
                   buf->cpu,
#if defined(CONFIG_PREEMPT_NONE)
                   "server",
#elif defined(CONFIG_PREEMPT_VOLUNTARY)
                   "desktop",
#elif defined(CONFIG_PREEMPT)
                   "preempt",
#else
                   "unknown",
#endif
                   /* These are reserved for later use */
                   0, 0, 0, 0);
#ifdef CONFIG_SMP
        seq_printf(m, " #P:%d)\n", num_online_cpus());
#else
        seq_puts(m, ")\n");
#endif
        seq_puts(m, "#    -----------------\n");
        seq_printf(m, "#    | task: %.16s-%d "
                   "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n",
                   data->comm, data->pid,
                   from_kuid_munged(seq_user_ns(m), data->uid), data->nice,
                   data->policy, data->rt_priority);
        seq_puts(m, "#    -----------------\n");

        if (data->critical_start) {
                seq_puts(m, "#  => started at: ");
                seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags);
                trace_print_seq(m, &iter->seq);
                seq_puts(m, "\n#  => ended at:   ");
                seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
                trace_print_seq(m, &iter->seq);
                seq_puts(m, "\n#\n");
        }

        seq_puts(m, "#\n");
}

static void test_cpu_buff_start(struct trace_iterator *iter)
{
        struct trace_seq *s = &iter->seq;

        if (!(trace_flags & TRACE_ITER_ANNOTATE))
                return;

        if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
                return;

        if (cpumask_test_cpu(iter->cpu, iter->started))
                return;

        if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
                return;

        cpumask_set_cpu(iter->cpu, iter->started);

        /* Don't print started cpu buffer for the first entry of the trace */
        if (iter->idx > 1)
                trace_seq_printf(s, "##### CPU %u buffer started ####\n",
                                iter->cpu);
}

static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
{
        struct trace_seq *s = &iter->seq;
        unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
        struct trace_entry *entry;
        struct trace_event *event;

        entry = iter->ent;

        test_cpu_buff_start(iter);

        event = ftrace_find_event(entry->type);

        if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
                if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
                        if (!trace_print_lat_context(iter))
                                goto partial;
                } else {
                        if (!trace_print_context(iter))
                                goto partial;
                }
        }

        if (event)
                return event->funcs->trace(iter, sym_flags, event);

        if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
                goto partial;

        return TRACE_TYPE_HANDLED;
partial:
        return TRACE_TYPE_PARTIAL_LINE;
}

static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
{
        struct trace_seq *s = &iter->seq;
        struct trace_entry *entry;
        struct trace_event *event;

        entry = iter->ent;

        if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
                if (!trace_seq_printf(s, "%d %d %llu ",
                                      entry->pid, iter->cpu, iter->ts))
                        goto partial;
        }

        event = ftrace_find_event(entry->type);
        if (event)
                return event->funcs->raw(iter, 0, event);

        if (!trace_seq_printf(s, "%d ?\n", entry->type))
                goto partial;

        return TRACE_TYPE_HANDLED;
partial:
        return TRACE_TYPE_PARTIAL_LINE;
}

static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
{
        struct trace_seq *s = &iter->seq;
        unsigned char newline = '\n';
        struct trace_entry *entry;
        struct trace_event *event;

        entry = iter->ent;

        if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
                SEQ_PUT_HEX_FIELD_RET(s, entry->pid);
                SEQ_PUT_HEX_FIELD_RET(s, iter->cpu);
                SEQ_PUT_HEX_FIELD_RET(s, iter->ts);
        }

        event = ftrace_find_event(entry->type);
        if (event) {
                enum print_line_t ret = event->funcs->hex(iter, 0, event);
                if (ret != TRACE_TYPE_HANDLED)
                        return ret;
        }

        SEQ_PUT_FIELD_RET(s, newline);

        return TRACE_TYPE_HANDLED;
}

static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
{
        struct trace_seq *s = &iter->seq;
        struct trace_entry *entry;
        struct trace_event *event;

        entry = iter->ent;

        if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
                SEQ_PUT_FIELD_RET(s, entry->pid);
                SEQ_PUT_FIELD_RET(s, iter->cpu);
                SEQ_PUT_FIELD_RET(s, iter->ts);
        }

        event = ftrace_find_event(entry->type);
        return event ? event->funcs->binary(iter, 0, event) :
                TRACE_TYPE_HANDLED;
}

int trace_empty(struct trace_iterator *iter)
{
        struct ring_buffer_iter *buf_iter;
        int cpu;

        /* If we are looking at one CPU buffer, only check that one */
        if (iter->cpu_file != RING_BUFFER_ALL_CPUS) {
                cpu = iter->cpu_file;
                buf_iter = trace_buffer_iter(iter, cpu);
                if (buf_iter) {
                        if (!ring_buffer_iter_empty(buf_iter))
                                return 0;
                } else {
                        if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu))
                                return 0;
                }
                return 1;
        }

        for_each_tracing_cpu(cpu) {
                buf_iter = trace_buffer_iter(iter, cpu);
                if (buf_iter) {
                        if (!ring_buffer_iter_empty(buf_iter))
                                return 0;
                } else {
                        if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu))
                                return 0;
                }
        }

        return 1;
}

/*  Called with trace_event_read_lock() held. */
enum print_line_t print_trace_line(struct trace_iterator *iter)
{
        enum print_line_t ret;

        if (iter->lost_events &&
            !trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
                                 iter->cpu, iter->lost_events))
                return TRACE_TYPE_PARTIAL_LINE;

        if (iter->trace && iter->trace->print_line) {
                ret = iter->trace->print_line(iter);
                if (ret != TRACE_TYPE_UNHANDLED)
                        return ret;
        }

        if (iter->ent->type == TRACE_BPUTS &&
                        trace_flags & TRACE_ITER_PRINTK &&
                        trace_flags & TRACE_ITER_PRINTK_MSGONLY)
                return trace_print_bputs_msg_only(iter);

        if (iter->ent->type == TRACE_BPRINT &&
                        trace_flags & TRACE_ITER_PRINTK &&
                        trace_flags & TRACE_ITER_PRINTK_MSGONLY)
                return trace_print_bprintk_msg_only(iter);

        if (iter->ent->type == TRACE_PRINT &&
                        trace_flags & TRACE_ITER_PRINTK &&
                        trace_flags & TRACE_ITER_PRINTK_MSGONLY)
                return trace_print_printk_msg_only(iter);

        if (trace_flags & TRACE_ITER_BIN)
                return print_bin_fmt(iter);

        if (trace_flags & TRACE_ITER_HEX)
                return print_hex_fmt(iter);

        if (trace_flags & TRACE_ITER_RAW)
                return print_raw_fmt(iter);

        return print_trace_fmt(iter);
}

void trace_latency_header(struct seq_file *m)
{
        struct trace_iterator *iter = m->private;

        /* print nothing if the buffers are empty */
        if (trace_empty(iter))
                return;

        if (iter->iter_flags & TRACE_FILE_LAT_FMT)
                print_trace_header(m, iter);

        if (!(trace_flags & TRACE_ITER_VERBOSE))
                print_lat_help_header(m);
}

void trace_default_header(struct seq_file *m)
{
        struct trace_iterator *iter = m->private;

        if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
                return;

        if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
                /* print nothing if the buffers are empty */
                if (trace_empty(iter))
                        return;
                print_trace_header(m, iter);
                if (!(trace_flags & TRACE_ITER_VERBOSE))
                        print_lat_help_header(m);
        } else {
                if (!(trace_flags & TRACE_ITER_VERBOSE)) {
                        if (trace_flags & TRACE_ITER_IRQ_INFO)
                                print_func_help_header_irq(iter->trace_buffer, m);
                        else
                                print_func_help_header(iter->trace_buffer, m);
                }
        }
}

static void test_ftrace_alive(struct seq_file *m)
{
        if (!ftrace_is_dead())
                return;
        seq_printf(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n");
        seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
}

#ifdef CONFIG_TRACER_MAX_TRACE
static void show_snapshot_main_help(struct seq_file *m)
{
        seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
        seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
        seq_printf(m, "#                      Takes a snapshot of the main buffer.\n");
        seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
        seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
        seq_printf(m, "#                       is not a '0' or '1')\n");
}

static void show_snapshot_percpu_help(struct seq_file *m)
{
        seq_printf(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n");
#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
        seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
        seq_printf(m, "#                      Takes a snapshot of the main buffer for this cpu.\n");
#else
        seq_printf(m, "# echo 1 > snapshot : Not supported with this kernel.\n");
        seq_printf(m, "#                     Must use main snapshot file to allocate.\n");
#endif
        seq_printf(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n");
        seq_printf(m, "#                      (Doesn't have to be '2' works with any number that\n");
        seq_printf(m, "#                       is not a '0' or '1')\n");
}

static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter)
{
        if (iter->tr->allocated_snapshot)
                seq_printf(m, "#\n# * Snapshot is allocated *\n#\n");
        else
                seq_printf(m, "#\n# * Snapshot is freed *\n#\n");

        seq_printf(m, "# Snapshot commands:\n");
        if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
                show_snapshot_main_help(m);
        else
                show_snapshot_percpu_help(m);
}
#else
/* Should never be called */
static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { }
#endif

static int s_show(struct seq_file *m, void *v)
{
        struct trace_iterator *iter = v;
        int ret;

        if (iter->ent == NULL) {
                if (iter->tr) {
                        seq_printf(m, "# tracer: %s\n", iter->trace->name);
                        seq_puts(m, "#\n");
                        test_ftrace_alive(m);
                }
                if (iter->snapshot && trace_empty(iter))
                        print_snapshot_help(m, iter);
                else if (iter->trace && iter->trace->print_header)
                        iter->trace->print_header(m);
                else
                        trace_default_header(m);

        } else if (iter->leftover) {
                /*
                 * If we filled the seq_file buffer earlier, we
                 * want to just show it now.
                 */
                ret = trace_print_seq(m, &iter->seq);

                /* ret should this time be zero, but you never know */
                iter->leftover = ret;

        } else {
                print_trace_line(iter);
                ret = trace_print_seq(m, &iter->seq);
                /*
                 * If we overflow the seq_file buffer, then it will
                 * ask us for this data again at start up.
                 * Use that instead.
                 *  ret is 0 if seq_file write succeeded.
                 *        -1 otherwise.
                 */
                iter->leftover = ret;
        }

        return 0;
}

static const struct seq_operations tracer_seq_ops = {
        .start          = s_start,
        .next           = s_next,
        .stop           = s_stop,
        .show           = s_show,
};

static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, bool snapshot)
{
        struct trace_cpu *tc = inode->i_private;
        struct trace_array *tr = tc->tr;
        struct trace_iterator *iter;
        int cpu;

        if (tracing_disabled)
                return ERR_PTR(-ENODEV);

        iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter));
        if (!iter)
                return ERR_PTR(-ENOMEM);

        iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(),
                                    GFP_KERNEL);
        if (!iter->buffer_iter)
                goto release;

        /*
         * We make a copy of the current tracer to avoid concurrent
         * changes on it while we are reading.
         */
        mutex_lock(&trace_types_lock);
        iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL);
        if (!iter->trace)
                goto fail;

        *iter->trace = *tr->current_trace;

        if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
                goto fail;

        iter->tr = tr;

#ifdef CONFIG_TRACER_MAX_TRACE
        /* Currently only the top directory has a snapshot */
        if (tr->current_trace->print_max || snapshot)
                iter->trace_buffer = &tr->max_buffer;
        else
#endif
                iter->trace_buffer = &tr->trace_buffer;
        iter->snapshot = snapshot;
        iter->pos = -1;
        mutex_init(&iter->mutex);
        iter->cpu_file = tc->cpu;

        /* Notify the tracer early; before we stop tracing. */
        if (iter->trace && iter->trace->open)
                iter->trace->open(iter);

        /* Annotate start of buffers if we had overruns */
        if (ring_buffer_overruns(iter->trace_buffer->buffer))
                iter->iter_flags |= TRACE_FILE_ANNOTATE;

        /* Output in nanoseconds only if we are using a clock in nanoseconds. */
        if (trace_clocks[tr->clock_id].in_ns)
                iter->iter_flags |= TRACE_FILE_TIME_IN_NS;

        /* stop the trace while dumping if we are not opening "snapshot" */
        if (!iter->snapshot)
                tracing_stop_tr(tr);

        if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
                for_each_tracing_cpu(cpu) {
                        iter->buffer_iter[cpu] =
                                ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
                }
                ring_buffer_read_prepare_sync();
                for_each_tracing_cpu(cpu) {
                        ring_buffer_read_start(iter->buffer_iter[cpu]);
                        tracing_iter_reset(iter, cpu);
                }
        } else {
                cpu = iter->cpu_file;
                iter->buffer_iter[cpu] =
                        ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
                ring_buffer_read_prepare_sync();
                ring_buffer_read_start(iter->buffer_iter[cpu]);
                tracing_iter_reset(iter, cpu);
        }

        tr->ref++;

        mutex_unlock(&trace_types_lock);

        return iter;

 fail:
        mutex_unlock(&trace_types_lock);
        kfree(iter->trace);
        kfree(iter->buffer_iter);
release:
        seq_release_private(inode, file);
        return ERR_PTR(-ENOMEM);
}

int tracing_open_generic(struct inode *inode, struct file *filp)
{
        if (tracing_disabled)
                return -ENODEV;

        filp->private_data = inode->i_private;
        return 0;
}

static int tracing_release(struct inode *inode, struct file *file)
{
        struct seq_file *m = file->private_data;
        struct trace_iterator *iter;
        struct trace_array *tr;
        int cpu;

        if (!(file->f_mode & FMODE_READ))
                return 0;

        iter = m->private;
        tr = iter->tr;

        mutex_lock(&trace_types_lock);

        WARN_ON(!tr->ref);
        tr->ref--;

        for_each_tracing_cpu(cpu) {
                if (iter->buffer_iter[cpu])
                        ring_buffer_read_finish(iter->buffer_iter[cpu]);
        }

        if (iter->trace && iter->trace->close)
                iter->trace->close(iter);

        if (!iter->snapshot)
                /* reenable tracing if it was previously enabled */
                tracing_start_tr(tr);
        mutex_unlock(&trace_types_lock);

        mutex_destroy(&iter->mutex);
        free_cpumask_var(iter->started);
        kfree(iter->trace);
        kfree(iter->buffer_iter);
        seq_release_private(inode, file);
        return 0;
}

static int tracing_open(struct inode *inode, struct file *file)
{
        struct trace_iterator *iter;
        int ret = 0;

        /* If this file was open for write, then erase contents */
        if ((file->f_mode & FMODE_WRITE) &&
            (file->f_flags & O_TRUNC)) {
                struct trace_cpu *tc = inode->i_private;
                struct trace_array *tr = tc->tr;

                if (tc->cpu == RING_BUFFER_ALL_CPUS)
                        tracing_reset_online_cpus(&tr->trace_buffer);
                else
                        tracing_reset(&tr->trace_buffer, tc->cpu);
        }

        if (file->f_mode & FMODE_READ) {
                iter = __tracing_open(inode, file, false);
                if (IS_ERR(iter))
                        ret = PTR_ERR(iter);
                else if (trace_flags & TRACE_ITER_LATENCY_FMT)
                        iter->iter_flags |= TRACE_FILE_LAT_FMT;
        }
        return ret;
}

static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
        struct tracer *t = v;

        (*pos)++;

        if (t)
                t = t->next;

        return t;
}

static void *t_start(struct seq_file *m, loff_t *pos)
{
        struct tracer *t;
        loff_t l = 0;

        mutex_lock(&trace_types_lock);
        for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
                ;

        return t;
}

static void t_stop(struct seq_file *m, void *p)
{
        mutex_unlock(&trace_types_lock);
}

static int t_show(struct seq_file *m, void *v)
{
        struct tracer *t = v;

        if (!t)
                return 0;

        seq_printf(m, "%s", t->name);
        if (t->next)
                seq_putc(m, ' ');
        else
                seq_putc(m, '\n');

        return 0;
}

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

static int show_traces_open(struct inode *inode, struct file *file)
{
        if (tracing_disabled)
                return -ENODEV;

        return seq_open(file, &show_traces_seq_ops);
}

static ssize_t
tracing_write_stub(struct file *filp, const char __user *ubuf,
                   size_t count, loff_t *ppos)
{
        return count;
}

static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
{
        if (file->f_mode & FMODE_READ)
                return seq_lseek(file, offset, origin);
        else
                return 0;
}

static const struct file_operations tracing_fops = {
        .open           = tracing_open,
        .read           = seq_read,
        .write          = tracing_write_stub,
        .llseek         = tracing_seek,
        .release        = tracing_release,
};

static const struct file_operations show_traces_fops = {
        .open           = show_traces_open,
        .read           = seq_read,
        .release        = seq_release,
        .llseek         = seq_lseek,
};

/*
 * Only trace on a CPU if the bitmask is set:
 */
static cpumask_var_t tracing_cpumask;

/*
 * The tracer itself will not take this lock, but still we want
 * to provide a consistent cpumask to user-space:
 */
static DEFINE_MUTEX(tracing_cpumask_update_lock);

/*
 * Temporary storage for the character representation of the
 * CPU bitmask (and one more byte for the newline):
 */
static char mask_str[NR_CPUS + 1];

static ssize_t
tracing_cpumask_read(struct file *filp, char __user *ubuf,
                     size_t count, loff_t *ppos)
{
        int len;

        mutex_lock(&tracing_cpumask_update_lock);

        len = cpumask_scnprintf(mask_str, count, tracing_cpumask);
        if (count - len < 2) {
                count = -EINVAL;
                goto out_err;
        }
        len += sprintf(mask_str + len, "\n");
        count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);

out_err:
        mutex_unlock(&tracing_cpumask_update_lock);

        return count;
}

static ssize_t
tracing_cpumask_write(struct file *filp, const char __user *ubuf,
                      size_t count, loff_t *ppos)
{
        struct trace_array *tr = filp->private_data;
        cpumask_var_t tracing_cpumask_new;
        int err, cpu;

        if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
                return -ENOMEM;

        err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
        if (err)
                goto err_unlock;

        mutex_lock(&tracing_cpumask_update_lock);

        local_irq_disable();
        arch_spin_lock(&ftrace_max_lock);
        for_each_tracing_cpu(cpu) {
                /*
                 * Increase/decrease the disabled counter if we are
                 * about to flip a bit in the cpumask:
                 */
                if (cpumask_test_cpu(cpu, tracing_cpumask) &&
                                !cpumask_test_cpu(cpu, tracing_cpumask_new)) {
                        atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
                        ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu);
                }
                if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
                                cpumask_test_cpu(cpu, tracing_cpumask_new)) {
                        atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
                        ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
                }
        }
        arch_spin_unlock(&ftrace_max_lock);
        local_irq_enable();

        cpumask_copy(tracing_cpumask, tracing_cpumask_new);

        mutex_unlock(&tracing_cpumask_update_lock);
        free_cpumask_var(tracing_cpumask_new);

        return count;

err_unlock:
        free_cpumask_var(tracing_cpumask_new);

        return err;
}

static const struct file_operations tracing_cpumask_fops = {
        .open           = tracing_open_generic,
        .read           = tracing_cpumask_read,
        .write          = tracing_cpumask_write,
        .llseek         = generic_file_llseek,
};

static int tracing_trace_options_show(struct seq_file *m, void *v)
{
        struct tracer_opt *trace_opts;
        struct trace_array *tr = m->private;
        u32 tracer_flags;
        int i;

        mutex_lock(&trace_types_lock);
        tracer_flags = tr->current_trace->flags->val;
        trace_opts = tr->current_trace->flags->opts;

        for (i = 0; trace_options[i]; i++) {
                if (trace_flags & (1 << i))
                        seq_printf(m, "%s\n", trace_options[i]);
                else
                        seq_printf(m, "no%s\n", trace_options[i]);
        }

        for (i = 0; trace_opts[i].name; i++) {
                if (tracer_flags & trace_opts[i].bit)
                        seq_printf(m, "%s\n", trace_opts[i].name);
                else
                        seq_printf(m, "no%s\n", trace_opts[i].name);
        }
        mutex_unlock(&trace_types_lock);

        return 0;
}

static int __set_tracer_option(struct tracer *trace,
                               struct tracer_flags *tracer_flags,
                               struct tracer_opt *opts, int neg)
{
        int ret;

        ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
        if (ret)
                return ret;

        if (neg)
                tracer_flags->val &= ~opts->bit;
        else
                tracer_flags->val |= opts->bit;
        return 0;
}

/* Try to assign a tracer specific option */
static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
{
        struct tracer_flags *tracer_flags = trace->flags;
        struct tracer_opt *opts = NULL;
        int i;

        for (i = 0; tracer_flags->opts[i].name; i++) {
                opts = &tracer_flags->opts[i];

                if (strcmp(cmp, opts->name) == 0)
                        return __set_tracer_option(trace, trace->flags,
                                                   opts, neg);
        }

        return -EINVAL;
}

/* Some tracers require overwrite to stay enabled */
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
{
        if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
                return -1;

        return 0;
}

int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
{
        /* do nothing if flag is already set */
        if (!!(trace_flags & mask) == !!enabled)
                return 0;

        /* Give the tracer a chance to approve the change */
        if (tr->current_trace->flag_changed)
                if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled))
                        return -EINVAL;

        if (enabled)
                trace_flags |= mask;
        else
                trace_flags &= ~mask;

        if (mask == TRACE_ITER_RECORD_CMD)
                trace_event_enable_cmd_record(enabled);

        if (mask == TRACE_ITER_OVERWRITE) {
                ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
#ifdef CONFIG_TRACER_MAX_TRACE
                ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled);
#endif
        }

        if (mask == TRACE_ITER_PRINTK)
                trace_printk_start_stop_comm(enabled);

        return 0;
}

static int trace_set_options(struct trace_array *tr, char *option)
{
        char *cmp;
        int neg = 0;
        int ret = -ENODEV;
        int i;

        cmp = strstrip(option);

        if (strncmp(cmp, "no", 2) == 0) {
                neg = 1;
                cmp += 2;
        }

        mutex_lock(&trace_types_lock);

        for (i = 0; trace_options[i]; i++) {
                if (strcmp(cmp, trace_options[i]) == 0) {
                        ret = set_tracer_flag(tr, 1 << i, !neg);
                        break;
                }
        }

        /* If no option could be set, test the specific tracer options */
        if (!trace_options[i])
                ret = set_tracer_option(tr->current_trace, cmp, neg);

        mutex_unlock(&trace_types_lock);

        return ret;
}

static ssize_t
tracing_trace_options_write(struct file *filp, const char __user *ubuf,
                        size_t cnt, loff_t *ppos)
{
        struct seq_file *m = filp->private_data;
        struct trace_array *tr = m->private;
        char buf[64];
        int ret;

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

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

        buf[cnt] = 0;

        ret = trace_set_options(tr, buf);
        if (ret < 0)
                return ret;

        *ppos += cnt;

        return cnt;
}

static int tracing_trace_options_open(struct inode *inode, struct file *file)
{
        if (tracing_disabled)
                return -ENODEV;

        return single_open(file, tracing_trace_options_show, inode->i_private);
}

static const struct file_operations tracing_iter_fops = {
        .open           = tracing_trace_options_open,
        .read           = seq_read,
        .llseek         = seq_lseek,
        .release        = single_release,
        .write          = tracing_trace_options_write,
};

static const char readme_msg[] =
        "tracing mini-HOWTO:\n\n"
        "# echo 0 > tracing_on : quick way to disable tracing\n"
        "# echo 1 > tracing_on : quick way to re-enable tracing\n\n"
        " Important files:\n"
        "  trace\t\t\t- The static contents of the buffer\n"
        "\t\t\t  To clear the buffer write into this file: echo > trace\n"
        "  trace_pipe\t\t- A consuming read to see the contents of the buffer\n"
        "  current_tracer\t- function and latency tracers\n"
        "  available_tracers\t- list of configured tracers for current_tracer\n"
        "  buffer_size_kb\t- view and modify size of per cpu buffer\n"
        "  buffer_total_size_kb  - view total size of all cpu buffers\n\n"
        "  trace_clock\t\t-change the clock used to order events\n"
        "       local:   Per cpu clock but may not be synced across CPUs\n"
        "      global:   Synced across CPUs but slows tracing down.\n"
        "     counter:   Not a clock, but just an increment\n"
        "      uptime:   Jiffy counter from time of boot\n"
        "        perf:   Same clock that perf events use\n"
#ifdef CONFIG_X86_64
        "     x86-tsc:   TSC cycle counter\n"
#endif
        "\n  trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
        "  tracing_cpumask\t- Limit which CPUs to trace\n"
        "  instances\t\t- Make sub-buffers with: mkdir instances/foo\n"
        "\t\t\t  Remove sub-buffer with rmdir\n"
        "  trace_options\t\t- Set format or modify how tracing happens\n"
        "\t\t\t  Disable an option by adding a suffix 'no' to the option name\n"
#ifdef CONFIG_DYNAMIC_FTRACE
        "\n  available_filter_functions - list of functions that can be filtered on\n"
        "  set_ftrace_filter\t- echo function name in here to only trace these functions\n"
        "            accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
        "            modules: Can select a group via module\n"
        "             Format: :mod:<module-name>\n"
        "             example: echo :mod:ext3 > set_ftrace_filter\n"
        "            triggers: a command to perform when function is hit\n"
        "              Format: <function>:<trigger>[:count]\n"
        "             trigger: traceon, traceoff\n"
        "                      enable_event:<system>:<event>\n"
        "                      disable_event:<system>:<event>\n"
#ifdef CONFIG_STACKTRACE
        "                      stacktrace\n"
#endif
#ifdef CONFIG_TRACER_SNAPSHOT
        "                      snapshot\n"
#endif
        "             example: echo do_fault:traceoff > set_ftrace_filter\n"
        "                      echo do_trap:traceoff:3 > set_ftrace_filter\n"
        "             The first one will disable tracing every time do_fault is hit\n"
        "             The second will disable tracing at most 3 times when do_trap is hit\n"
        "               The first time do trap is hit and it disables tracing, the counter\n"
        "               will decrement to 2. If tracing is already disabled, the counter\n"
        "               will not decrement. It only decrements when the trigger did work\n"
        "             To remove trigger without count:\n"
        "               echo '!<function>:<trigger> > set_ftrace_filter\n"
        "             To remove trigger with a count:\n"
        "               echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
        "  set_ftrace_notrace\t- echo function name in here to never trace.\n"
        "            accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
        "            modules: Can select a group via module command :mod:\n"
        "            Does not accept triggers\n"
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_TRACER
        "  set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n"
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
        "  set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
        "  max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n"
#endif
#ifdef CONFIG_TRACER_SNAPSHOT
        "\n  snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
        "\t\t\t  Read the contents for more information\n"
#endif
#ifdef CONFIG_STACKTRACE
        "  stack_trace\t\t- Shows the max stack trace when active\n"
        "  stack_max_size\t- Shows current max stack size that was traced\n"
        "\t\t\t  Write into this file to reset the max size (trigger a new trace)\n"
#ifdef CONFIG_DYNAMIC_FTRACE
        "  stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
#endif
#endif /* CONFIG_STACKTRACE */
;

static ssize_t
tracing_readme_read(struct file *filp, char __user *ubuf,
                       size_t cnt, loff_t *ppos)
{
        return simple_read_from_buffer(ubuf, cnt, ppos,
                                        readme_msg, strlen(readme_msg));
}

static const struct file_operations tracing_readme_fops = {
        .open           = tracing_open_generic,
        .read           = tracing_readme_read,
        .llseek         = generic_file_llseek,
};

static ssize_t
tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
                                size_t cnt, loff_t *ppos)
{
        char *buf_comm;
        char *file_buf;
        char *buf;
        int len = 0;
        int pid;
        int i;

        file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
        if (!file_buf)
                return -ENOMEM;

        buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
        if (!buf_comm) {
                kfree(file_buf);
                return -ENOMEM;
        }

        buf = file_buf;

        for (i = 0; i < SAVED_CMDLINES; i++) {
                int r;

                pid = map_cmdline_to_pid[i];
                if (pid == -1 || pid == NO_CMDLINE_MAP)
                        continue;

                trace_find_cmdline(pid, buf_comm);
                r = sprintf(buf, "%d %s\n", pid, buf_comm);
                buf += r;
                len += r;
        }

        len = simple_read_from_buffer(ubuf, cnt, ppos,
                                      file_buf, len);

        kfree(file_buf);
        kfree(buf_comm);

        return len;
}

static const struct file_operations tracing_saved_cmdlines_fops = {
    .open       = tracing_open_generic,
    .read       = tracing_saved_cmdlines_read,
    .llseek     = generic_file_llseek,
};

static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
                       size_t cnt, loff_t *ppos)
{
        struct trace_array *tr = filp->private_data;
        char buf[MAX_TRACER_SIZE+2];
        int r;

        mutex_lock(&trace_types_lock);
        r = sprintf(buf, "%s\n", tr->current_trace->name);
        mutex_unlock(&trace_types_lock);

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

int tracer_init(struct tracer *t, struct trace_array *tr)
{
        tracing_reset_online_cpus(&tr->trace_buffer);
        return t->init(tr);
}

static void set_buffer_entries(struct trace_buffer *buf, unsigned long val)
{
        int cpu;

        for_each_tracing_cpu(cpu)
                per_cpu_ptr(buf->data, cpu)->entries = val;
}

#ifdef CONFIG_TRACER_MAX_TRACE
/* resize @tr's buffer to the size of @size_tr's entries */
static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
                                        struct trace_buffer *size_buf, int cpu_id)
{
        int cpu, ret = 0;

        if (cpu_id == RING_BUFFER_ALL_CPUS) {
                for_each_tracing_cpu(cpu) {
                        ret = ring_buffer_resize(trace_buf->buffer,
                                 per_cpu_ptr(size_buf->data, cpu)->entries, cpu);
                        if (ret < 0)
                                break;
                        per_cpu_ptr(trace_buf->data, cpu)->entries =
                                per_cpu_ptr(size_buf->data, cpu)->entries;
                }
        } else {
                ret = ring_buffer_resize(trace_buf->buffer,
                                 per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id);
                if (ret == 0)
                        per_cpu_ptr(trace_buf->data, cpu_id)->entries =
                                per_cpu_ptr(size_buf->data, cpu_id)->entries;
        }

        return ret;
}
#endif /* CONFIG_TRACER_MAX_TRACE */

static int __tracing_resize_ring_buffer(struct trace_array *tr,
                                        unsigned long size, int cpu)
{
        int ret;

        /*
         * If kernel or user changes the size of the ring buffer
         * we use the size that was given, and we can forget about
         * expanding it later.
         */
        ring_buffer_expanded = true;

        /* May be called before buffers are initialized */
        if (!tr->trace_buffer.buffer)
                return 0;

        ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu);
        if (ret < 0)
                return ret;

#ifdef CONFIG_TRACER_MAX_TRACE
        if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
            !tr->current_trace->use_max_tr)
                goto out;

        ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
        if (ret < 0) {
                int r = resize_buffer_duplicate_size(&tr->trace_buffer,
                                                     &tr->trace_buffer, cpu);
                if (r < 0) {
                        /*
                         * AARGH! We are left with different
                         * size max buffer!!!!
                         * The max buffer is our "snapshot" buffer.
                         * When a tracer needs a snapshot (one of the
                         * latency tracers), it swaps the max buffer
                         * with the saved snap shot. We succeeded to
                         * update the size of the main buffer, but failed to
                         * update the size of the max buffer. But when we tried
                         * to reset the main buffer to the original size, we
                         * failed there too. This is very unlikely to
                         * happen, but if it does, warn and kill all
                         * tracing.
                         */
                        WARN_ON(1);
                        tracing_disabled = 1;
                }
                return ret;
        }

        if (cpu == RING_BUFFER_ALL_CPUS)
                set_buffer_entries(&tr->max_buffer, size);
        else
                per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size;

 out:
#endif /* CONFIG_TRACER_MAX_TRACE */

        if (cpu == RING_BUFFER_ALL_CPUS)
                set_buffer_entries(&tr->trace_buffer, size);
        else
                per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size;

        return ret;
}

static ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
                                          unsigned long size, int cpu_id)
{
        int ret = size;

        mutex_lock(&trace_types_lock);

        if (cpu_id != RING_BUFFER_ALL_CPUS) {
                /* make sure, this cpu is enabled in the mask */
                if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) {
                        ret = -EINVAL;
                        goto out;
                }
        }

        ret = __tracing_resize_ring_buffer(tr, size, cpu_id);
        if (ret < 0)
                ret = -ENOMEM;

out:
        mutex_unlock(&trace_types_lock);

        return ret;
}


/**
 * tracing_update_buffers - used by tracing facility to expand ring buffers
 *
 * To save on memory when the tracing is never used on a system with it
 * configured in. The ring buffers are set to a minimum size. But once
 * a user starts to use the tracing facility, then they need to grow
 * to their default size.
 *
 * This function is to be called when a tracer is about to be used.
 */
int tracing_update_buffers(void)
{
        int ret = 0;

        mutex_lock(&trace_types_lock);
        if (!ring_buffer_expanded)
                ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size,
                                                RING_BUFFER_ALL_CPUS);
        mutex_unlock(&trace_types_lock);

        return ret;
}

struct trace_option_dentry;

static struct trace_option_dentry *
create_trace_option_files(struct trace_array *tr, struct tracer *tracer);

static void
destroy_trace_option_files(struct trace_option_dentry *topts);

static int tracing_set_tracer(const char *buf)
{
        static struct trace_option_dentry *topts;
        struct trace_array *tr = &global_trace;
        struct tracer *t;
#ifdef CONFIG_TRACER_MAX_TRACE
        bool had_max_tr;
#endif
        int ret = 0;

        mutex_lock(&trace_types_lock);

        if (!ring_buffer_expanded) {
                ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
                                                RING_BUFFER_ALL_CPUS);
                if (ret < 0)
                        goto out;
                ret = 0;
        }

        for (t = trace_types; t; t = t->next) {
                if (strcmp(t->name, buf) == 0)
                        break;
        }
        if (!t) {
                ret = -EINVAL;
                goto out;
        }
        if (t == tr->current_trace)
                goto out;

        trace_branch_disable();

        tr->current_trace->enabled = false;

        if (tr->current_trace->reset)
                tr->current_trace->reset(tr);

        /* Current trace needs to be nop_trace before synchronize_sched */
        tr->current_trace = &nop_trace;

#ifdef CONFIG_TRACER_MAX_TRACE
        had_max_tr = tr->allocated_snapshot;

        if (had_max_tr && !t->use_max_tr) {
                /*
                 * We need to make sure that the update_max_tr sees that
                 * current_trace changed to nop_trace to keep it from
                 * swapping the buffers after we resize it.
                 * The update_max_tr is called from interrupts disabled
                 * so a synchronized_sched() is sufficient.
                 */
                synchronize_sched();
                free_snapshot(tr);
        }
#endif
        destroy_trace_option_files(topts);

        topts = create_trace_option_files(tr, t);

#ifdef CONFIG_TRACER_MAX_TRACE
        if (t->use_max_tr && !had_max_tr) {
                ret = alloc_snapshot(tr);
                if (ret < 0)
                        goto out;
        }
#endif

        if (t->init) {
                ret = tracer_init(t, tr);
                if (ret)
                        goto out;
        }

        tr->current_trace = t;
        tr->current_trace->enabled = true;
        trace_branch_enable(tr);
 out:
        mutex_unlock(&trace_types_lock);

        return ret;
}

static ssize_t
tracing_set_trace_write(struct file *filp, const char __user *ubuf,
                        size_t cnt, loff_t *ppos)
{
        char buf[MAX_TRACER_SIZE+1];
        int i;
        size_t ret;
        int err;

        ret = cnt;

        if (cnt > MAX_TRACER_SIZE)
                cnt = MAX_TRACER_SIZE;

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

        buf[cnt] = 0;

        /* strip ending whitespace. */
        for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
                buf[i] = 0;

        err = tracing_set_tracer(buf);
        if (err)
                return err;

        *ppos += ret;

        return ret;
}

static ssize_t
tracing_max_lat_read(struct file *filp, char __user *ubuf,
                     size_t cnt, loff_t *ppos)
{
        unsigned long *ptr = filp->private_data;
        char buf[64];
        int r;

        r = snprintf(buf, sizeof(buf), "%ld\n",
                     *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
        if (r > sizeof(buf))
                r = sizeof(buf);
        return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

static ssize_t
tracing_max_lat_write(struct file *filp, const char __user *ubuf,
                      size_t cnt, loff_t *ppos)
{
        unsigned long *ptr = filp->private_data;
        unsigned long val;
        int ret;

        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
        if (ret)
                return ret;

        *ptr = val * 1000;

        return cnt;
}

static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
        struct trace_cpu *tc = inode->i_private;
        struct trace_array *tr = tc->tr;
        struct trace_iterator *iter;
        int ret = 0;

        if (tracing_disabled)
                return -ENODEV;

        mutex_lock(&trace_types_lock);

        /* create a buffer to store the information to pass to userspace */
        iter = kzalloc(sizeof(*iter), GFP_KERNEL);
        if (!iter) {
                ret = -ENOMEM;
                goto out;
        }

        /*
         * We make a copy of the current tracer to avoid concurrent
         * changes on it while we are reading.
         */
        iter->trace = kmalloc(sizeof(*iter->trace), GFP_KERNEL);
        if (!iter->trace) {
                ret = -ENOMEM;
                goto fail;
        }
        *iter->trace = *tr->current_trace;

        if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
                ret = -ENOMEM;
                goto fail;
        }

        /* trace pipe does not show start of buffer */
        cpumask_setall(iter->started);

        if (trace_flags & TRACE_ITER_LATENCY_FMT)
                iter->iter_flags |= TRACE_FILE_LAT_FMT;

        /* Output in nanoseconds only if we are using a clock in nanoseconds. */
        if (trace_clocks[tr->clock_id].in_ns)
                iter->iter_flags |= TRACE_FILE_TIME_IN_NS;

        iter->cpu_file = tc->cpu;
        iter->tr = tc->tr;
        iter->trace_buffer = &tc->tr->trace_buffer;
        mutex_init(&iter->mutex);
        filp->private_data = iter;

        if (iter->trace->pipe_open)
                iter->trace->pipe_open(iter);

        nonseekable_open(inode, filp);
out:
        mutex_unlock(&trace_types_lock);
        return ret;

fail:
        kfree(iter->trace);
        kfree(iter);
        mutex_unlock(&trace_types_lock);
        return ret;
}

static int tracing_release_pipe(struct inode *inode, struct file *file)
{
        struct trace_iterator *iter = file->private_data;

        mutex_lock(&trace_types_lock);

        if (iter->trace->pipe_close)
                iter->trace->pipe_close(iter);

        mutex_unlock(&trace_types_lock);

        free_cpumask_var(iter->started);
        mutex_destroy(&iter->mutex);
        kfree(iter->trace);
        kfree(iter);

        return 0;
}

static unsigned int
trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table)
{
        /* Iterators are static, they should be filled or empty */
        if (trace_buffer_iter(iter, iter->cpu_file))
                return POLLIN | POLLRDNORM;

        if (trace_flags & TRACE_ITER_BLOCK)
                /*
                 * Always select as readable when in blocking mode
                 */
                return POLLIN | POLLRDNORM;
        else
                return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file,
                                             filp, poll_table);
}

static unsigned int
tracing_poll_pipe(struct file *filp, poll_table *poll_table)
{
        struct trace_iterator *iter = filp->private_data;

        return trace_poll(iter, filp, poll_table);
}

/*
 * This is a make-shift waitqueue.
 * A tracer might use this callback on some rare cases:
 *
 *  1) the current tracer might hold the runqueue lock when it wakes up
 *     a reader, hence a deadlock (sched, function, and function graph tracers)
 *  2) the function tracers, trace all functions, we don't want
 *     the overhead of calling wake_up and friends
 *     (and tracing them too)
 *
 *     Anyway, this is really very primitive wakeup.
 */
void poll_wait_pipe(struct trace_iterator *iter)
{
        set_current_state(TASK_INTERRUPTIBLE);
        /* sleep for 100 msecs, and try again. */
        schedule_timeout(HZ / 10);
}

/* Must be called with trace_types_lock mutex held. */
static int tracing_wait_pipe(struct file *filp)
{
        struct trace_iterator *iter = filp->private_data;

        while (trace_empty(iter)) {

                if ((filp->f_flags & O_NONBLOCK)) {
                        return -EAGAIN;
                }

                mutex_unlock(&iter->mutex);

                iter->trace->wait_pipe(iter);

                mutex_lock(&iter->mutex);

                if (signal_pending(current))
                        return -EINTR;

                /*
                 * We block until we read something and tracing is disabled.
                 * We still block if tracing is disabled, but we have never
                 * read anything. This allows a user to cat this file, and
                 * then enable tracing. But after we have read something,
                 * we give an EOF when tracing is again disabled.
                 *
                 * iter->pos will be 0 if we haven't read anything.
                 */
                if (!tracing_is_enabled() && iter->pos)
                        break;
        }

        return 1;
}

/*
 * Consumer reader.
 */
static ssize_t
tracing_read_pipe(struct file *filp, char __user *ubuf,
                  size_t cnt, loff_t *ppos)
{
        struct trace_iterator *iter = filp->private_data;
        struct trace_array *tr = iter->tr;
        ssize_t sret;

        /* return any leftover data */
        sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
        if (sret != -EBUSY)
                return sret;

        trace_seq_init(&iter->seq);

        /* copy the tracer to avoid using a global lock all around */
        mutex_lock(&trace_types_lock);
        if (unlikely(iter->trace->name != tr->current_trace->name))
                *iter->trace = *tr->current_trace;
        mutex_unlock(&trace_types_lock);

        /*
         * Avoid more than one consumer on a single file descriptor
         * This is just a matter of traces coherency, the ring buffer itself
         * is protected.
         */
        mutex_lock(&iter->mutex);
        if (iter->trace->read) {
                sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
                if (sret)
                        goto out;
        }

waitagain:
        sret = tracing_wait_pipe(filp);
        if (sret <= 0)
                goto out;

        /* stop when tracing is finished */
        if (trace_empty(iter)) {
                sret = 0;
                goto out;
        }

        if (cnt >= PAGE_SIZE)
                cnt = PAGE_SIZE - 1;

        /* reset all but tr, trace, and overruns */
        memset(&iter->seq, 0,