// SPDX-License-Identifier: GPL-2.0
/*
 * 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/security.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
#include <linux/tracefs.h>
#include <linux/pagemap.h>
#include <linux/hardirq.h>
#include <linux/linkage.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.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/mount.h>
#include <linux/rwsem.h>
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/panic_notifier.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/fs.h>
#include <linux/trace.h>
#include <linux/sched/clock.h>
#include <linux/sched/rt.h>
#include <linux/fsnotify.h>
#include <linux/irq_work.h>
#include <linux/workqueue.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 boot-time tracing including tracers/events via kernel cmdline
 * is running, we do not want to run SELFTEST.
 */
bool __read_mostly tracing_selftest_disabled;

#ifdef CONFIG_FTRACE_STARTUP_TEST
void __init disable_tracing_selftest(const char *reason)
{
        if (!tracing_selftest_disabled) {
                tracing_selftest_disabled = true;
                pr_info("Ftrace startup test is disabled due to %s\n", reason);
        }
}
#endif

/* Pipe tracepoints to printk */
struct trace_iterator *tracepoint_print_iter;
int tracepoint_printk;
static bool tracepoint_printk_stop_on_boot __initdata;
static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key);

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

static int
dummy_set_flag(struct trace_array *tr, 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_taskinfo_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;

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;

/* When set, tracing will stop when a WARN*() is hit */
int __disable_trace_on_warning;

#ifdef CONFIG_TRACE_EVAL_MAP_FILE
/* Map of enums to their values, for "eval_map" file */
struct trace_eval_map_head {
        struct module                   *mod;
        unsigned long                   length;
};

union trace_eval_map_item;

struct trace_eval_map_tail {
        /*
         * "end" is first and points to NULL as it must be different
         * than "mod" or "eval_string"
         */
        union trace_eval_map_item       *next;
        const char                      *end;   /* points to NULL */
};

static DEFINE_MUTEX(trace_eval_mutex);

/*
 * The trace_eval_maps are saved in an array with two extra elements,
 * one at the beginning, and one at the end. The beginning item contains
 * the count of the saved maps (head.length), and the module they
 * belong to if not built in (head.mod). The ending item contains a
 * pointer to the next array of saved eval_map items.
 */
union trace_eval_map_item {
        struct trace_eval_map           map;
        struct trace_eval_map_head      head;
        struct trace_eval_map_tail      tail;
};

static union trace_eval_map_item *trace_eval_maps;
#endif /* CONFIG_TRACE_EVAL_MAP_FILE */

int tracing_set_tracer(struct trace_array *tr, const char *buf);
static void ftrace_trace_userstack(struct trace_array *tr,
                                   struct trace_buffer *buffer,
                                   unsigned int trace_ctx);

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

static bool allocate_snapshot;
static bool snapshot_at_boot;

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 || !strcmp("1", str)) {
                ftrace_dump_on_oops = DUMP_ALL;
                return 1;
        }

        if (!strcmp("orig_cpu", str) || !strcmp("2", str)) {
                ftrace_dump_on_oops = DUMP_ORIG;
                return 1;
        }

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

static int __init stop_trace_on_warning(char *str)
{
        if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
                __disable_trace_on_warning = 1;
        return 1;
}
__setup("traceoff_on_warning", stop_trace_on_warning);

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 int __init boot_snapshot(char *str)
{
        snapshot_at_boot = true;
        boot_alloc_snapshot(str);
        return 1;
}
__setup("ftrace_boot_snapshot", boot_snapshot);


static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;

static int __init set_trace_boot_options(char *str)
{
        strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
        return 1;
}
__setup("trace_options=", set_trace_boot_options);

static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata;
static char *trace_boot_clock __initdata;

static int __init set_trace_boot_clock(char *str)
{
        strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
        trace_boot_clock = trace_boot_clock_buf;
        return 1;
}
__setup("trace_clock=", set_trace_boot_clock);

static int __init set_tracepoint_printk(char *str)
{
        /* Ignore the "tp_printk_stop_on_boot" param */
        if (*str == '_')
                return 0;

        if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
                tracepoint_printk = 1;
        return 1;
}
__setup("tp_printk", set_tracepoint_printk);

static int __init set_tracepoint_printk_stop(char *str)
{
        tracepoint_printk_stop_on_boot = true;
        return 1;
}
__setup("tp_printk_stop_on_boot", set_tracepoint_printk_stop);

unsigned long long ns2usecs(u64 nsec)
{
        nsec += 500;
        do_div(nsec, 1000);
        return nsec;
}

static void
trace_process_export(struct trace_export *export,
               struct ring_buffer_event *event, int flag)
{
        struct trace_entry *entry;
        unsigned int size = 0;

        if (export->flags & flag) {
                entry = ring_buffer_event_data(event);
                size = ring_buffer_event_length(event);
                export->write(export, entry, size);
        }
}

static DEFINE_MUTEX(ftrace_export_lock);

static struct trace_export __rcu *ftrace_exports_list __read_mostly;

static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled);
static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled);

static inline void ftrace_exports_enable(struct trace_export *export)
{
        if (export->flags & TRACE_EXPORT_FUNCTION)
                static_branch_inc(&trace_function_exports_enabled);

        if (export->flags & TRACE_EXPORT_EVENT)
                static_branch_inc(&trace_event_exports_enabled);

        if (export->flags & TRACE_EXPORT_MARKER)
                static_branch_inc(&trace_marker_exports_enabled);
}

static inline void ftrace_exports_disable(struct trace_export *export)
{
        if (export->flags & TRACE_EXPORT_FUNCTION)
                static_branch_dec(&trace_function_exports_enabled);

        if (export->flags & TRACE_EXPORT_EVENT)
                static_branch_dec(&trace_event_exports_enabled);

        if (export->flags & TRACE_EXPORT_MARKER)
                static_branch_dec(&trace_marker_exports_enabled);
}

static void ftrace_exports(struct ring_buffer_event *event, int flag)
{
        struct trace_export *export;

        preempt_disable_notrace();

        export = rcu_dereference_raw_check(ftrace_exports_list);
        while (export) {
                trace_process_export(export, event, flag);
                export = rcu_dereference_raw_check(export->next);
        }

        preempt_enable_notrace();
}

static inline void
add_trace_export(struct trace_export **list, struct trace_export *export)
{
        rcu_assign_pointer(export->next, *list);
        /*
         * We are entering export into the list but another
         * CPU might be walking that list. We need to make sure
         * the export->next pointer is valid before another CPU sees
         * the export pointer included into the list.
         */
        rcu_assign_pointer(*list, export);
}

static inline int
rm_trace_export(struct trace_export **list, struct trace_export *export)
{
        struct trace_export **p;

        for (p = list; *p != NULL; p = &(*p)->next)
                if (*p == export)
                        break;

        if (*p != export)
                return -1;

        rcu_assign_pointer(*p, (*p)->next);

        return 0;
}

static inline void
add_ftrace_export(struct trace_export **list, struct trace_export *export)
{
        ftrace_exports_enable(export);

        add_trace_export(list, export);
}

static inline int
rm_ftrace_export(struct trace_export **list, struct trace_export *export)
{
        int ret;

        ret = rm_trace_export(list, export);
        ftrace_exports_disable(export);

        return ret;
}

int register_ftrace_export(struct trace_export *export)
{
        if (WARN_ON_ONCE(!export->write))
                return -1;

        mutex_lock(&ftrace_export_lock);

        add_ftrace_export(&ftrace_exports_list, export);

        mutex_unlock(&ftrace_export_lock);

        return 0;
}
EXPORT_SYMBOL_GPL(register_ftrace_export);

int unregister_ftrace_export(struct trace_export *export)
{
        int ret;

        mutex_lock(&ftrace_export_lock);

        ret = rm_ftrace_export(&ftrace_exports_list, export);

        mutex_unlock(&ftrace_export_lock);

        return ret;
}
EXPORT_SYMBOL_GPL(unregister_ftrace_export);

/* trace_flags holds trace_options default values */
#define TRACE_DEFAULT_FLAGS                                             \
        (FUNCTION_DEFAULT_FLAGS |                                       \
         TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |                  \
         TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO |                \
         TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |                 \
         TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS |                     \
         TRACE_ITER_HASH_PTR)

/* trace_options that are only supported by global_trace */
#define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK |                      \
               TRACE_ITER_PRINTK_MSGONLY | TRACE_ITER_RECORD_CMD)

/* trace_flags that are default zero for instances */
#define ZEROED_TRACE_FLAGS \
        (TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK)

/*
 * The global_trace is the descriptor that holds the top-level tracing
 * buffers for the live tracing.
 */
static struct trace_array global_trace = {
        .trace_flags = TRACE_DEFAULT_FLAGS,
};

LIST_HEAD(ftrace_trace_arrays);

int trace_array_get(struct trace_array *this_tr)
{
        struct trace_array *tr;
        int ret = -ENODEV;

        mutex_lock(&trace_types_lock);
        list_for_each_entry(tr, &ftrace_trace_arrays, list) {
                if (tr == this_tr) {
                        tr->ref++;
                        ret = 0;
                        break;
                }
        }
        mutex_unlock(&trace_types_lock);

        return ret;
}

static void __trace_array_put(struct trace_array *this_tr)
{
        WARN_ON(!this_tr->ref);
        this_tr->ref--;
}

/**
 * trace_array_put - Decrement the reference counter for this trace array.
 * @this_tr : pointer to the trace array
 *
 * NOTE: Use this when we no longer need the trace array returned by
 * trace_array_get_by_name(). This ensures the trace array can be later
 * destroyed.
 *
 */
void trace_array_put(struct trace_array *this_tr)
{
        if (!this_tr)
                return;

        mutex_lock(&trace_types_lock);
        __trace_array_put(this_tr);
        mutex_unlock(&trace_types_lock);
}
EXPORT_SYMBOL_GPL(trace_array_put);

int tracing_check_open_get_tr(struct trace_array *tr)
{
        int ret;

        ret = security_locked_down(LOCKDOWN_TRACEFS);
        if (ret)
                return ret;

        if (tracing_disabled)
                return -ENODEV;

        if (tr && trace_array_get(tr) < 0)
                return -ENODEV;

        return 0;
}

int call_filter_check_discard(struct trace_event_call *call, void *rec,
                              struct trace_buffer *buffer,
                              struct ring_buffer_event *event)
{
        if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
            !filter_match_preds(call->filter, rec)) {
                __trace_event_discard_commit(buffer, event);
                return 1;
        }

        return 0;
}

/**
 * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
 * @filtered_pids: The list of pids to check
 * @search_pid: The PID to find in @filtered_pids
 *
 * Returns true if @search_pid is found in @filtered_pids, and false otherwise.
 */
bool
trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
{
        return trace_pid_list_is_set(filtered_pids, search_pid);
}

/**
 * trace_ignore_this_task - should a task be ignored for tracing
 * @filtered_pids: The list of pids to check
 * @filtered_no_pids: The list of pids not to be traced
 * @task: The task that should be ignored if not filtered
 *
 * Checks if @task should be traced or not from @filtered_pids.
 * Returns true if @task should *NOT* be traced.
 * Returns false if @task should be traced.
 */
bool
trace_ignore_this_task(struct trace_pid_list *filtered_pids,
                       struct trace_pid_list *filtered_no_pids,
                       struct task_struct *task)
{
        /*
         * If filtered_no_pids is not empty, and the task's pid is listed
         * in filtered_no_pids, then return true.
         * Otherwise, if filtered_pids is empty, that means we can
         * trace all tasks. If it has content, then only trace pids
         * within filtered_pids.
         */

        return (filtered_pids &&
                !trace_find_filtered_pid(filtered_pids, task->pid)) ||
                (filtered_no_pids &&
                 trace_find_filtered_pid(filtered_no_pids, task->pid));
}

/**
 * trace_filter_add_remove_task - Add or remove a task from a pid_list
 * @pid_list: The list to modify
 * @self: The current task for fork or NULL for exit
 * @task: The task to add or remove
 *
 * If adding a task, if @self is defined, the task is only added if @self
 * is also included in @pid_list. This happens on fork and tasks should
 * only be added when the parent is listed. If @self is NULL, then the
 * @task pid will be removed from the list, which would happen on exit
 * of a task.
 */
void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
                                  struct task_struct *self,
                                  struct task_struct *task)
{
        if (!pid_list)
                return;

        /* For forks, we only add if the forking task is listed */
        if (self) {
                if (!trace_find_filtered_pid(pid_list, self->pid))
                        return;
        }

        /* "self" is set for forks, and NULL for exits */
        if (self)
                trace_pid_list_set(pid_list, task->pid);
        else
                trace_pid_list_clear(pid_list, task->pid);
}

/**
 * trace_pid_next - Used for seq_file to get to the next pid of a pid_list
 * @pid_list: The pid list to show
 * @v: The last pid that was shown (+1 the actual pid to let zero be displayed)
 * @pos: The position of the file
 *
 * This is used by the seq_file "next" operation to iterate the pids
 * listed in a trace_pid_list structure.
 *
 * Returns the pid+1 as we want to display pid of zero, but NULL would
 * stop the iteration.
 */
void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
{
        long pid = (unsigned long)v;
        unsigned int next;

        (*pos)++;

        /* pid already is +1 of the actual previous bit */
        if (trace_pid_list_next(pid_list, pid, &next) < 0)
                return NULL;

        pid = next;

        /* Return pid + 1 to allow zero to be represented */
        return (void *)(pid + 1);
}

/**
 * trace_pid_start - Used for seq_file to start reading pid lists
 * @pid_list: The pid list to show
 * @pos: The position of the file
 *
 * This is used by seq_file "start" operation to start the iteration
 * of listing pids.
 *
 * Returns the pid+1 as we want to display pid of zero, but NULL would
 * stop the iteration.
 */
void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos)
{
        unsigned long pid;
        unsigned int first;
        loff_t l = 0;

        if (trace_pid_list_first(pid_list, &first) < 0)
                return NULL;

        pid = first;

        /* Return pid + 1 so that zero can be the exit value */
        for (pid++; pid && l < *pos;
             pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l))
                ;
        return (void *)pid;
}

/**
 * trace_pid_show - show the current pid in seq_file processing
 * @m: The seq_file structure to write into
 * @v: A void pointer of the pid (+1) value to display
 *
 * Can be directly used by seq_file operations to display the current
 * pid value.
 */
int trace_pid_show(struct seq_file *m, void *v)
{
        unsigned long pid = (unsigned long)v - 1;

        seq_printf(m, "%lu\n", pid);
        return 0;
}

/* 128 should be much more than enough */
#define PID_BUF_SIZE            127

int trace_pid_write(struct trace_pid_list *filtered_pids,
                    struct trace_pid_list **new_pid_list,
                    const char __user *ubuf, size_t cnt)
{
        struct trace_pid_list *pid_list;
        struct trace_parser parser;
        unsigned long val;
        int nr_pids = 0;
        ssize_t read = 0;
        ssize_t ret;
        loff_t pos;
        pid_t pid;

        if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1))
                return -ENOMEM;

        /*
         * Always recreate a new array. The write is an all or nothing
         * operation. Always create a new array when adding new pids by
         * the user. If the operation fails, then the current list is
         * not modified.
         */
        pid_list = trace_pid_list_alloc();
        if (!pid_list) {
                trace_parser_put(&parser);
                return -ENOMEM;
        }

        if (filtered_pids) {
                /* copy the current bits to the new max */
                ret = trace_pid_list_first(filtered_pids, &pid);
                while (!ret) {
                        trace_pid_list_set(pid_list, pid);
                        ret = trace_pid_list_next(filtered_pids, pid + 1, &pid);
                        nr_pids++;
                }
        }

        ret = 0;
        while (cnt > 0) {

                pos = 0;

                ret = trace_get_user(&parser, ubuf, cnt, &pos);
                if (ret < 0)
                        break;

                read += ret;
                ubuf += ret;
                cnt -= ret;

                if (!trace_parser_loaded(&parser))
                        break;

                ret = -EINVAL;
                if (kstrtoul(parser.buffer, 0, &val))
                        break;

                pid = (pid_t)val;

                if (trace_pid_list_set(pid_list, pid) < 0) {
                        ret = -1;
                        break;
                }
                nr_pids++;

                trace_parser_clear(&parser);
                ret = 0;
        }
        trace_parser_put(&parser);

        if (ret < 0) {
                trace_pid_list_free(pid_list);
                return ret;
        }

        if (!nr_pids) {
                /* Cleared the list of pids */
                trace_pid_list_free(pid_list);
                pid_list = NULL;
        }

        *new_pid_list = pid_list;

        return read;
}

static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu)
{
        u64 ts;

        /* Early boot up does not have a buffer yet */
        if (!buf->buffer)
                return trace_clock_local();

        ts = ring_buffer_time_stamp(buf->buffer);
        ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts);

        return ts;
}

u64 ftrace_now(int cpu)
{
        return buffer_ftrace_now(&global_trace.array_buffer, cpu);
}

/**
 * tracing_is_enabled - Show if global_trace has been enabled
 *
 * Shows if the global trace has been enabled or not. It uses the
 * mirror flag "buffer_disabled" to be used in fast paths such as for
 * the irqsoff tracer. But it may be inaccurate due to races. If you
 * need to know the accurate state, use tracing_is_on() which is a little
 * slower, but accurate.
 */
int tracing_is_enabled(void)
{
        /*
         * For quick access (irqsoff uses this in fast path), just
         * return the mirror variable of the state of the ring buffer.
         * It's a little racy, but we don't really care.
         */
        smp_rmb();
        return !global_trace.buffer_disabled;
}

/*
 * 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.
 */
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 rewritten
 *      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

#ifdef CONFIG_STACKTRACE
static void __ftrace_trace_stack(struct trace_buffer *buffer,
                                 unsigned int trace_ctx,
                                 int skip, struct pt_regs *regs);
static inline void ftrace_trace_stack(struct trace_array *tr,
                                      struct trace_buffer *buffer,
                                      unsigned int trace_ctx,
                                      int skip, struct pt_regs *regs);

#else
static inline void __ftrace_trace_stack(struct trace_buffer *buffer,
                                        unsigned int trace_ctx,
                                        int skip, struct pt_regs *regs)
{
}
static inline void ftrace_trace_stack(struct trace_array *tr,
                                      struct trace_buffer *buffer,
                                      unsigned long trace_ctx,
                                      int skip, struct pt_regs *regs)
{
}

#endif

static __always_inline void
trace_event_setup(struct ring_buffer_event *event,
                  int type, unsigned int trace_ctx)
{
        struct trace_entry *ent = ring_buffer_event_data(event);

        tracing_generic_entry_update(ent, type, trace_ctx);
}

static __always_inline struct ring_buffer_event *
__trace_buffer_lock_reserve(struct trace_buffer *buffer,
                          int type,
                          unsigned long len,
                          unsigned int trace_ctx)
{
        struct ring_buffer_event *event;

        event = ring_buffer_lock_reserve(buffer, len);
        if (event != NULL)
                trace_event_setup(event, type, trace_ctx);

        return event;
}

void tracer_tracing_on(struct trace_array *tr)
{
        if (tr->array_buffer.buffer)
                ring_buffer_record_on(tr->array_buffer.buffer);
        /*
         * This flag is looked at when buffers haven't been allocated
         * yet, or by some tracers (like irqsoff), that just want to
         * know if the ring buffer has been disabled, but it can handle
         * races of where it gets disabled but we still do a record.
         * As the check is in the fast path of the tracers, it is more
         * important to be fast than accurate.
         */
        tr->buffer_disabled = 0;
        /* Make the flag seen by readers */
        smp_wmb();
}

/**
 * tracing_on - enable tracing buffers
 *
 * This function enables tracing buffers that may have been
 * disabled with tracing_off.
 */
void tracing_on(void)
{
        tracer_tracing_on(&global_trace);
}
EXPORT_SYMBOL_GPL(tracing_on);


static __always_inline void
__buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event)
{
        __this_cpu_write(trace_taskinfo_save, true);

        /* If this is the temp buffer, we need to commit fully */
        if (this_cpu_read(trace_buffered_event) == event) {
                /* Length is in event->array[0] */
                ring_buffer_write(buffer, event->array[0], &event->array[1]);
                /* Release the temp buffer */
                this_cpu_dec(trace_buffered_event_cnt);
                /* ring_buffer_unlock_commit() enables preemption */
                preempt_enable_notrace();

        } else
                ring_buffer_unlock_commit(buffer, event);
}

/**
 * __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 trace_buffer *buffer;
        struct print_entry *entry;
        unsigned int trace_ctx;
        int alloc;

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

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

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

        trace_ctx = tracing_gen_ctx();
        buffer = global_trace.array_buffer.buffer;
        ring_buffer_nest_start(buffer);
        event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
                                            trace_ctx);
        if (!event) {
                size = 0;
                goto out;
        }

        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);
        ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL);
 out:
        ring_buffer_nest_end(buffer);
        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 trace_buffer *buffer;
        struct bputs_entry *entry;
        unsigned int trace_ctx;
        int size = sizeof(struct bputs_entry);
        int ret = 0;

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

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

        trace_ctx = tracing_gen_ctx();
        buffer = global_trace.array_buffer.buffer;

        ring_buffer_nest_start(buffer);
        event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
                                            trace_ctx);
        if (!event)
                goto out;

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

        __buffer_unlock_commit(buffer, event);
        ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL);

        ret = 1;
 out:
        ring_buffer_nest_end(buffer);
        return ret;
}
EXPORT_SYMBOL_GPL(__trace_bputs);

#ifdef CONFIG_TRACER_SNAPSHOT
static void tracing_snapshot_instance_cond(struct trace_array *tr,
                                           void *cond_data)
{
        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(), cond_data);
        local_irq_restore(flags);
}

void tracing_snapshot_instance(struct trace_array *tr)
{
        tracing_snapshot_instance_cond(tr, NULL);
}

/**
 * tracing_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;

        tracing_snapshot_instance(tr);
}
EXPORT_SYMBOL_GPL(tracing_snapshot);

/**
 * tracing_snapshot_cond - conditionally take a snapshot of the current buffer.
 * @tr:         The tracing instance to snapshot
 * @cond_data:  The data to be tested conditionally, and possibly saved
 *
 * This is the same as tracing_snapshot() except that the snapshot is
 * conditional - the snapshot will only happen if the
 * cond_snapshot.update() implementation receiving the cond_data
 * returns true, which means that the trace array's cond_snapshot
 * update() operation used the cond_data to determine whether the
 * snapshot should be taken, and if it was, presumably saved it along
 * with the snapshot.
 */
void tracing_snapshot_cond(struct trace_array *tr, void *cond_data)
{
        tracing_snapshot_instance_cond(tr, cond_data);
}
EXPORT_SYMBOL_GPL(tracing_snapshot_cond);

/**
 * tracing_cond_snapshot_data - get the user data associated with a snapshot
 * @tr:         The tracing instance
 *
 * When the user enables a conditional snapshot using
 * tracing_snapshot_cond_enable(), the user-defined cond_data is saved
 * with the snapshot.  This accessor is used to retrieve it.
 *
 * Should not be called from cond_snapshot.update(), since it takes
 * the tr->max_lock lock, which the code calling
 * cond_snapshot.update() has already done.
 *
 * Returns the cond_data associated with the trace array's snapshot.
 */
void *tracing_cond_snapshot_data(struct trace_array *tr)
{
        void *cond_data = NULL;

        arch_spin_lock(&tr->max_lock);

        if (tr->cond_snapshot)
                cond_data = tr->cond_snapshot->cond_data;

        arch_spin_unlock(&tr->max_lock);

        return cond_data;
}
EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data);

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

int tracing_alloc_snapshot_instance(struct trace_array *tr)
{
        int ret;

        if (!tr->allocated_snapshot) {

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

                tr->allocated_snapshot = true;
        }

        return 0;
}

static 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;
}

/**
 * tracing_alloc_snapshot - allocate snapshot buffer.
 *
 * This only allocates the snapshot buffer if it isn't already
 * allocated - it doesn't also take a snapshot.
 *
 * This is meant to be used in cases where the snapshot buffer needs
 * to be set up for events that can't sleep but need to be able to
 * trigger a snapshot.
 */
int tracing_alloc_snapshot(void)
{
        struct trace_array *tr = &global_trace;
        int ret;

        ret = tracing_alloc_snapshot_instance(tr);
        WARN_ON(ret < 0);

        return ret;
}
EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);

/**
 * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer.
 *
 * This is similar to tracing_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)
{
        int ret;

        ret = tracing_alloc_snapshot();
        if (ret < 0)
                return;

        tracing_snapshot();
}
EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);

/**
 * tracing_snapshot_cond_enable - enable conditional snapshot for an instance
 * @tr:         The tracing instance
 * @cond_data:  User data to associate with the snapshot
 * @update:     Implementation of the cond_snapshot update function
 *
 * Check whether the conditional snapshot for the given instance has
 * already been enabled, or if the current tracer is already using a
 * snapshot; if so, return -EBUSY, else create a cond_snapshot and
 * save the cond_data and update function inside.
 *
 * Returns 0 if successful, error otherwise.
 */
int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data,
                                 cond_update_fn_t update)
{
        struct cond_snapshot *cond_snapshot;
        int ret = 0;

        cond_snapshot = kzalloc(sizeof(*cond_snapshot), GFP_KERNEL);
        if (!cond_snapshot)
                return -ENOMEM;

        cond_snapshot->cond_data = cond_data;
        cond_snapshot->update = update;

        mutex_lock(&trace_types_lock);

        ret = tracing_alloc_snapshot_instance(tr);
        if (ret)
                goto fail_unlock;

        if (tr->current_trace->use_max_tr) {
                ret = -EBUSY;
                goto fail_unlock;
        }

        /*
         * The cond_snapshot can only change to NULL without the
         * trace_types_lock. We don't care if we race with it going
         * to NULL, but we want to make sure that it's not set to
         * something other than NULL when we get here, which we can
         * do safely with only holding the trace_types_lock and not
         * having to take the max_lock.
         */
        if (tr->cond_snapshot) {
                ret = -EBUSY;
                goto fail_unlock;
        }

        arch_spin_lock(&tr->max_lock);
        tr->cond_snapshot = cond_snapshot;
        arch_spin_unlock(&tr->max_lock);

        mutex_unlock(&trace_types_lock);

        return ret;

 fail_unlock:
        mutex_unlock(&trace_types_lock);
        kfree(cond_snapshot);
        return ret;
}
EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable);

/**
 * tracing_snapshot_cond_disable - disable conditional snapshot for an instance
 * @tr:         The tracing instance
 *
 * Check whether the conditional snapshot for the given instance is
 * enabled; if so, free the cond_snapshot associated with it,
 * otherwise return -EINVAL.
 *
 * Returns 0 if successful, error otherwise.
 */
int tracing_snapshot_cond_disable(struct trace_array *tr)
{
        int ret = 0;

        arch_spin_lock(&tr->max_lock);

        if (!tr->cond_snapshot)
                ret = -EINVAL;
        else {
                kfree(tr->cond_snapshot);
                tr->cond_snapshot = NULL;
        }

        arch_spin_unlock(&tr->max_lock);

        return ret;
}
EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable);
#else
void tracing_snapshot(void)
{
        WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
}
EXPORT_SYMBOL_GPL(tracing_snapshot);
void tracing_snapshot_cond(struct trace_array *tr, void *cond_data)
{
        WARN_ONCE(1, "Snapshot feature not enabled, but internal conditional snapshot used");
}
EXPORT_SYMBOL_GPL(tracing_snapshot_cond);
int tracing_alloc_snapshot(void)
{
        WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used");
        return -ENODEV;
}
EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
void tracing_snapshot_alloc(void)
{
        /* Give warning */
        tracing_snapshot();
}
EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
void *tracing_cond_snapshot_data(struct trace_array *tr)
{
        return NULL;
}
EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data);
int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update)
{
        return -ENODEV;
}
EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable);
int tracing_snapshot_cond_disable(struct trace_array *tr)
{
        return false;
}
EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable);
#endif /* CONFIG_TRACER_SNAPSHOT */

void tracer_tracing_off(struct trace_array *tr)
{
        if (tr->array_buffer.buffer)
                ring_buffer_record_off(tr->array_buffer.buffer);
        /*
         * This flag is looked at when buffers haven't been allocated
         * yet, or by some tracers (like irqsoff), that just want to
         * know if the ring buffer has been disabled, but it can handle
         * races of where it gets disabled but we still do a record.
         * As the check is in the fast path of the tracers, it is more
         * important to be fast than accurate.
         */
        tr->buffer_disabled = 1;
        /* Make the flag seen by readers */
        smp_wmb();
}

/**
 * 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)
{
        tracer_tracing_off(&global_trace);
}
EXPORT_SYMBOL_GPL(tracing_off);

void disable_trace_on_warning(void)
{
        if (__disable_trace_on_warning) {
                trace_array_printk_buf(global_trace.array_buffer.buffer, _THIS_IP_,
                        "Disabling tracing due to warning\n");
                tracing_off();
        }
}

/**
 * tracer_tracing_is_on - show real state of ring buffer enabled
 * @tr : the trace array to know if ring buffer is enabled
 *
 * Shows real state of the ring buffer if it is enabled or not.
 */
bool tracer_tracing_is_on(struct trace_array *tr)
{
        if (tr->array_buffer.buffer)
                return ring_buffer_record_is_on(tr->array_buffer.buffer);
        return !tr->buffer_disabled;
}

/**
 * tracing_is_on - show state of ring buffers enabled
 */
int tracing_is_on(void)
{
        return tracer_tracing_is_on(&global_trace);
}
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 and the startup
         * tests require some buffer space. Therefore
         * ensure we have at least 4096 bytes of buffer.
         */
        trace_buf_size = max(4096UL, 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;
}

/*
 * TRACE_FLAGS is defined as a tuple matching bit masks with strings.
 * It uses C(a, b) where 'a' is the eval (enum) name and 'b' is the string that
 * matches it. By defining "C(a, b) b", TRACE_FLAGS becomes a list
 * of strings in the order that the evals (enum) were defined.
 */
#undef C
#define C(a, b) b

/* These must match the bit positions in trace_iterator_flags */
static const char *trace_options[] = {
        TRACE_FLAGS
        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",       0 },
        { trace_clock,                  "perf",         1 },
        { ktime_get_mono_fast_ns,       "mono",         1 },
        { ktime_get_raw_fast_ns,        "mono_raw",     1 },
        { ktime_get_boot_fast_ns,       "boot",         1 },
        { ktime_get_tai_fast_ns,        "tai",          1 },
        ARCH_TRACE_CLOCKS
};

bool trace_clock_in_ns(struct trace_array *tr)
{
        if (trace_clocks[tr->clock_id].in_ns)
                return true;

        return false;
}

/*
 * 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);
        parser->buffer = NULL;
}

/*
 * 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--;
                }

                parser->idx = 0;

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

        /* read the non-space input */
        while (cnt && !isspace(ch) && 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) || !ch) {
                parser->buffer[parser->idx] = 0;
                parser->cont = false;
        } else if (parser->idx < parser->size - 1) {
                parser->cont = true;
                parser->buffer[parser->idx++] = ch;
                /* Make sure the parsed string always terminates with '\0'. */
                parser->buffer[parser->idx] = 0;
        } else {
                ret = -EINVAL;
                goto out;
        }

        *ppos += read;
        ret = read;

out:
        return ret;
}

/* TODO add a seq_buf_to_buffer() */
static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
{
        int len;

        if (trace_seq_used(s) <= s->seq.readpos)
                return -EBUSY;

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

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

unsigned long __read_mostly     tracing_thresh;
static const struct file_operations tracing_max_lat_fops;

#ifdef LATENCY_FS_NOTIFY

static struct workqueue_struct *fsnotify_wq;

static void latency_fsnotify_workfn(struct work_struct *work)
{
        struct trace_array *tr = container_of(work, struct trace_array,
                                              fsnotify_work);
        fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY);
}

static void latency_fsnotify_workfn_irq(struct irq_work *iwork)
{
        struct trace_array *tr = container_of(iwork, struct trace_array,
                                              fsnotify_irqwork);
        queue_work(fsnotify_wq, &tr->fsnotify_work);
}

static void trace_create_maxlat_file(struct trace_array *tr,
                                     struct dentry *d_tracer)
{
        INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn);
        init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq);
        tr->d_max_latency = trace_create_file("tracing_max_latency",
                                              TRACE_MODE_WRITE,
                                              d_tracer, &tr->max_latency,
                                              &tracing_max_lat_fops);
}

__init static int latency_fsnotify_init(void)
{
        fsnotify_wq = alloc_workqueue("tr_max_lat_wq",
                                      WQ_UNBOUND | WQ_HIGHPRI, 0);
        if (!fsnotify_wq) {
                pr_err("Unable to allocate tr_max_lat_wq\n");
                return -ENOMEM;
        }
        return 0;
}

late_initcall_sync(latency_fsnotify_init);

void latency_fsnotify(struct trace_array *tr)
{
        if (!fsnotify_wq)
                return;
        /*
         * We cannot call queue_work(&tr->fsnotify_work) from here because it's
         * possible that we are called from __schedule() or do_idle(), which
         * could cause a deadlock.
         */
        irq_work_queue(&tr->fsnotify_irqwork);
}

#elif defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)  \
        || defined(CONFIG_OSNOISE_TRACER)

#define trace_create_maxlat_file(tr, d_tracer)                          \
        trace_create_file("tracing_max_latency", TRACE_MODE_WRITE,      \
                          d_tracer, &tr->max_latency, &tracing_max_lat_fops)

#else
#define trace_create_maxlat_file(tr, d_tracer)   do { } while (0)
#endif

#ifdef CONFIG_TRACER_MAX_TRACE
/*
 * 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/tracing/tracing_max_latency)
 */
static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
        struct array_buffer *trace_buf = &tr->array_buffer;
        struct array_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 = tr->max_latency;
        max_data->critical_start = data->critical_start;
        max_data->critical_end = data->critical_end;

        strncpy(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);
        latency_fsnotify(tr);
}

/**
 * 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.
 * @cond_data: User data associated with a conditional snapshot
 *
 * 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,
              void *cond_data)
{
        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(&tr->max_lock);

        /* Inherit the recordable setting from array_buffer */
        if (ring_buffer_record_is_set_on(tr->array_buffer.buffer))
                ring_buffer_record_on(tr->max_buffer.buffer);
        else
                ring_buffer_record_off(tr->max_buffer.buffer);

#ifdef CONFIG_TRACER_SNAPSHOT
        if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data))
                goto out_unlock;
#endif
        swap(tr->array_buffer.buffer, tr->max_buffer.buffer);

        __update_max_tr(tr, tsk, cpu);

 out_unlock:
        arch_spin_unlock(&tr->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(&tr->max_lock);

        ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_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(&tr->max_lock);
}
#endif /* CONFIG_TRACER_MAX_TRACE */

static int wait_on_pipe(struct trace_iterator *iter, int full)
{
        /* Iterators are static, they should be filled or empty */
        if (trace_buffer_iter(iter, iter->cpu_file))
                return 0;

        return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file,
                                full);
}

#ifdef CONFIG_FTRACE_STARTUP_TEST
static bool selftests_can_run;

struct trace_selftests {
        struct list_head                list;
        struct tracer                   *type;
};

static LIST_HEAD(postponed_selftests);

static int save_selftest(struct tracer *type)
{
        struct trace_selftests *selftest;

        selftest = kmalloc(sizeof(*selftest), GFP_KERNEL);
        if (!selftest)
                return -ENOMEM;

        selftest->type = type;
        list_add(&selftest->list, &postponed_selftests);
        return 0;
}

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;

        /*
         * If a tracer registers early in boot up (before scheduling is
         * initialized and such), then do not run its selftests yet.
         * Instead, run it a little later in the boot process.
         */
        if (!selftests_can_run)
                return save_selftest(type);

        if (!tracing_is_on()) {
                pr_warn("Selftest for tracer %s skipped due to tracing disabled\n",
                        type->name);
                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->array_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->array_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;
}

static __init int init_trace_selftests(void)
{
        struct trace_selftests *p, *n;
        struct tracer *t, **last;
        int ret;

        selftests_can_run = true;

        mutex_lock(&trace_types_lock);

        if (list_empty(&postponed_selftests))
                goto out;

        pr_info("Running postponed tracer tests:\n");

        tracing_selftest_running = true;
        list_for_each_entry_safe(p, n, &postponed_selftests, list) {
                /* This loop can take minutes when sanitizers are enabled, so
                 * lets make sure we allow RCU processing.
                 */
                cond_resched();
                ret = run_tracer_selftest(p->type);
                /* If the test fails, then warn and remove from available_tracers */
                if (ret < 0) {
                        WARN(1, "tracer: %s failed selftest, disabling\n",
                             p->type->name);
                        last = &trace_types;
                        for (t = trace_types; t; t = t->next) {
                                if (t == p->type) {
                                        *last = t->next;
                                        break;
                                }
                                last = &t->next;
                        }
                }
                list_del(&p->list);
                kfree(p);
        }
        tracing_selftest_running = false;

 out:
        mutex_unlock(&trace_types_lock);

        return 0;
}
core_initcall(init_trace_selftests);
#else
static inline int run_tracer_selftest(struct tracer *type)
{
        return 0;
}
#endif /* CONFIG_FTRACE_STARTUP_TEST */

static void add_tracer_options(struct trace_array *tr, struct tracer *t);

static void __init apply_trace_boot_options(void);

/**
 * register_tracer - register a tracer with the ftrace system.
 * @type: the plugin for the tracer
 *
 * Register a new plugin tracer.
 */
int __init 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;
        }

        if (security_locked_down(LOCKDOWN_TRACEFS)) {
                pr_warn("Can not register tracer %s due to lockdown\n",
                           type->name);
                return -EPERM;
        }

        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) {
                /*allocate a dummy tracer_flags*/
                type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL);
                if (!type->flags) {
                        ret = -ENOMEM;
                        goto out;
                }
                type->flags->val = 0;
                type->flags->opts = dummy_tracer_opt;
        } else
                if (!type->flags->opts)
                        type->flags->opts = dummy_tracer_opt;

        /* store the tracer for __set_tracer_option */
        type->flags->trace = type;

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

        type->next = trace_types;
        trace_types = type;
        add_tracer_options(&global_trace, 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(&global_trace, type->name);
        default_bootup_tracer = NULL;

        apply_trace_boot_options();

        /* disable other selftests, since this will break it. */
        disable_tracing_selftest("running a tracer");

 out_unlock:
        return ret;
}

static void tracing_reset_cpu(struct array_buffer *buf, int cpu)
{
        struct trace_buffer *buffer = buf->buffer;

        if (!buffer)
                return;

        ring_buffer_record_disable(buffer);

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

        ring_buffer_record_enable(buffer);
}

void tracing_reset_online_cpus(struct array_buffer *buf)
{
        struct trace_buffer *buffer = buf->buffer;

        if (!buffer)
                return;

        ring_buffer_record_disable(buffer);

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

        buf->time_start = buffer_ftrace_now(buf, buf->cpu);

        ring_buffer_reset_online_cpus(buffer);

        ring_buffer_record_enable(buffer);
}

/* Must have trace_types_lock held */
void tracing_reset_all_online_cpus(void)
{
        struct trace_array *tr;

        list_for_each_entry(tr, &ftrace_trace_arrays, list) {
                if (!tr->clear_trace)
                        continue;
                tr->clear_trace = false;
                tracing_reset_online_cpus(&tr->array_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
                tracing_reset_online_cpus(&tr->max_buffer);
#endif
        }
}

/*
 * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
 * is the tgid last observed corresponding to pid=i.
 */
static int *tgid_map;

/* The maximum valid index into tgid_map. */
static size_t tgid_map_max;

#define SAVED_CMDLINES_DEFAULT 128
#define NO_CMDLINE_MAP UINT_MAX
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
        unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
        unsigned *map_cmdline_to_pid;
        unsigned cmdline_num;
        int cmdline_idx;
        char *saved_cmdlines;
};
static struct saved_cmdlines_buffer *savedcmd;

static inline char *get_saved_cmdlines(int idx)
{
        return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
}

static inline void set_cmdline(int idx, const char *cmdline)
{
        strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
}

static int allocate_cmdlines_buffer(unsigned int val,
                                    struct saved_cmdlines_buffer *s)
{
        s->map_cmdline_to_pid = kmalloc_array(val,
                                              sizeof(*s->map_cmdline_to_pid),
                                              GFP_KERNEL);
        if (!s->map_cmdline_to_pid)
                return -ENOMEM;

        s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
        if (!s->saved_cmdlines) {
                kfree(s->map_cmdline_to_pid);
                return -ENOMEM;
        }

        s->cmdline_idx = 0;
        s->cmdline_num = val;
        memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
               sizeof(s->map_pid_to_cmdline));
        memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
               val * sizeof(*s->map_cmdline_to_pid));

        return 0;
}

static int trace_create_savedcmd(void)
{
        int ret;

        savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
        if (!savedcmd)
                return -ENOMEM;

        ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
        if (ret < 0) {
                kfree(savedcmd);
                savedcmd = NULL;
                return -ENOMEM;
        }

        return 0;
}

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

/**
 * 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 trace_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(&global_trace.max_lock);

        buffer = global_trace.array_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(&global_trace.max_lock);

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

static void tracing_start_tr(struct trace_array *tr)
{
        struct trace_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->array_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 trace_buffer *buffer;
        unsigned long flags;

        raw_spin_lock_irqsave(&global_trace.start_lock, flags);
        if (global_trace.stop_count++)
                goto out;

        /* Prevent the buffers from switching */
        arch_spin_lock(&global_trace.max_lock);

        buffer = global_trace.array_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(&global_trace.max_lock);

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

static void tracing_stop_tr(struct trace_array *tr)
{
        struct trace_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->array_buffer.buffer;
        if (buffer)
                ring_buffer_record_disable(buffer);

 out:
        raw_spin_unlock_irqrestore(&tr->start_lock, flags);
}

static int trace_save_cmdline(struct task_struct *tsk)
{
        unsigned tpid, idx;

        /* treat recording of idle task as a success */
        if (!tsk->pid)
                return 1;

        tpid = tsk->pid & (PID_MAX_DEFAULT - 1);

        /*
         * 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 0;

        idx = savedcmd->map_pid_to_cmdline[tpid];
        if (idx == NO_CMDLINE_MAP) {
                idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;

                savedcmd->map_pid_to_cmdline[tpid] = idx;
                savedcmd->cmdline_idx = idx;
        }

        savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
        set_cmdline(idx, tsk->comm);

        arch_spin_unlock(&trace_cmdline_lock);

        return 1;
}

static void __trace_find_cmdline(int pid, char comm[])
{
        unsigned map;
        int tpid;

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

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

        tpid = pid & (PID_MAX_DEFAULT - 1);
        map = savedcmd->map_pid_to_cmdline[tpid];
        if (map != NO_CMDLINE_MAP) {
                tpid = savedcmd->map_cmdline_to_pid[map];
                if (tpid == pid) {
                        strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
                        return;
                }
        }
        strcpy(comm, "<...>");
}

void trace_find_cmdline(int pid, char comm[])
{
        preempt_disable();
        arch_spin_lock(&trace_cmdline_lock);

        __trace_find_cmdline(pid, comm);

        arch_spin_unlock(&trace_cmdline_lock);
        preempt_enable();
}

static int *trace_find_tgid_ptr(int pid)
{
        /*
         * Pairs with the smp_store_release in set_tracer_flag() to ensure that
         * if we observe a non-NULL tgid_map then we also observe the correct
         * tgid_map_max.
         */
        int *map = smp_load_acquire(&tgid_map);

        if (unlikely(!map || pid > tgid_map_max))
                return NULL;

        return &map[pid];
}

int trace_find_tgid(int pid)
{
        int *ptr = trace_find_tgid_ptr(pid);

        return ptr ? *ptr : 0;
}

static int trace_save_tgid(struct task_struct *tsk)
{
        int *ptr;

        /* treat recording of idle task as a success */
        if (!tsk->pid)
                return 1;

        ptr = trace_find_tgid_ptr(tsk->pid);
        if (!ptr)
                return 0;

        *ptr = tsk->tgid;
        return 1;
}

static bool tracing_record_taskinfo_skip(int flags)
{
        if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
                return true;
        if (!__this_cpu_read(trace_taskinfo_save))
                return true;
        return false;
}

/**
 * tracing_record_taskinfo - record the task info of a task
 *
 * @task:  task to record
 * @flags: TRACE_RECORD_CMDLINE for recording comm
 *         TRACE_RECORD_TGID for recording tgid
 */
void tracing_record_taskinfo(struct task_struct *task, int flags)
{
        bool done;

        if (tracing_record_taskinfo_skip(flags))
                return;

        /*
         * Record as much task information as possible. If some fail, continue
         * to try to record the others.
         */
        done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task);
        done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task);

        /* If recording any information failed, retry again soon. */
        if (!done)
                return;

        __this_cpu_write(trace_taskinfo_save, false);
}

/**
 * tracing_record_taskinfo_sched_switch - record task info for sched_switch
 *
 * @prev: previous task during sched_switch
 * @next: next task during sched_switch
 * @flags: TRACE_RECORD_CMDLINE for recording comm
 *         TRACE_RECORD_TGID for recording tgid
 */
void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
                                          struct task_struct *next, int flags)
{
        bool done;

        if (tracing_record_taskinfo_skip(flags))
                return;

        /*
         * Record as much task information as possible. If some fail, continue
         * to try to record the others.
         */
        done  = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev);
        done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next);
        done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev);
        done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next);

        /* If recording any information failed, retry again soon. */
        if (!done)
                return;

        __this_cpu_write(trace_taskinfo_save, false);
}

/* Helpers to record a specific task information */
void tracing_record_cmdline(struct task_struct *task)
{
        tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE);
}

void tracing_record_tgid(struct task_struct *task)
{
        tracing_record_taskinfo(task, TRACE_RECORD_TGID);
}

/*
 * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq
 * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function
 * simplifies those functions and keeps them in sync.
 */
enum print_line_t trace_handle_return(struct trace_seq *s)
{
        return trace_seq_has_overflowed(s) ?
                TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED;
}
EXPORT_SYMBOL_GPL(trace_handle_return);

static unsigned short migration_disable_value(void)
{
#if defined(CONFIG_SMP)
        return current->migration_disabled;
#else
        return 0;
#endif
}

unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status)
{
        unsigned int trace_flags = irqs_status;
        unsigned int pc;

        pc = preempt_count();

        if (pc & NMI_MASK)
                trace_flags |= TRACE_FLAG_NMI;
        if (pc & HARDIRQ_MASK)
                trace_flags |= TRACE_FLAG_HARDIRQ;
        if (in_serving_softirq())
                trace_flags |= TRACE_FLAG_SOFTIRQ;
        if (softirq_count() >> (SOFTIRQ_SHIFT + 1))
                trace_flags |= TRACE_FLAG_BH_OFF;

        if (tif_need_resched())
                trace_flags |= TRACE_FLAG_NEED_RESCHED;
        if (test_preempt_need_resched())
                trace_flags |= TRACE_FLAG_PREEMPT_RESCHED;
        return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) |
                (min_t(unsigned int, migration_disable_value(), 0xf)) << 4;
}

struct ring_buffer_event *
trace_buffer_lock_reserve(struct trace_buffer *buffer,
                          int type,
                          unsigned long len,
                          unsigned int trace_ctx)
{
        return __trace_buffer_lock_reserve(buffer, type, len, trace_ctx);
}

DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event);
DEFINE_PER_CPU(int, trace_buffered_event_cnt);
static int trace_buffered_event_ref;

/**
 * trace_buffered_event_enable - enable buffering events
 *
 * When events are being filtered, it is quicker to use a temporary
 * buffer to write the event data into if there's a likely chance
 * that it will not be committed. The discard of the ring buffer
 * is not as fast as committing, and is much slower than copying
 * a commit.
 *
 * When an event is to be filtered, allocate per cpu buffers to
 * write the event data into, and if the event is filtered and discarded
 * it is simply dropped, otherwise, the entire data is to be committed
 * in one shot.
 */
void trace_buffered_event_enable(void)
{
        struct ring_buffer_event *event;
        struct page *page;
        int cpu;

        WARN_ON_ONCE(!mutex_is_locked(&event_mutex));

        if (trace_buffered_event_ref++)
                return;

        for_each_tracing_cpu(cpu) {
                page = alloc_pages_node(cpu_to_node(cpu),
                                        GFP_KERNEL | __GFP_NORETRY, 0);
                if (!page)
                        goto failed;

                event = page_address(page);
                memset(event, 0, sizeof(*event));

                per_cpu(trace_buffered_event, cpu) = event;

                preempt_disable();
                if (cpu == smp_processor_id() &&
                    __this_cpu_read(trace_buffered_event) !=
                    per_cpu(trace_buffered_event, cpu))
                        WARN_ON_ONCE(1);
                preempt_enable();
        }

        return;
 failed:
        trace_buffered_event_disable();
}

static void enable_trace_buffered_event(void *data)
{
        /* Probably not needed, but do it anyway */
        smp_rmb();
        this_cpu_dec(trace_buffered_event_cnt);
}

static void disable_trace_buffered_event(void *data)
{
        this_cpu_inc(trace_buffered_event_cnt);
}

/**
 * trace_buffered_event_disable - disable buffering events
 *
 * When a filter is removed, it is faster to not use the buffered
 * events, and to commit directly into the ring buffer. Free up
 * the temp buffers when there are no more users. This requires
 * special synchronization with current events.
 */
void trace_buffered_event_disable(void)
{
        int cpu;

        WARN_ON_ONCE(!mutex_is_locked(&event_mutex));

        if (WARN_ON_ONCE(!trace_buffered_event_ref))
                return;

        if (--trace_buffered_event_ref)
                return;

        preempt_disable();
        /* For each CPU, set the buffer as used. */
        smp_call_function_many(tracing_buffer_mask,
                               disable_trace_buffered_event, NULL, 1);
        preempt_enable();

        /* Wait for all current users to finish */
        synchronize_rcu();

        for_each_tracing_cpu(cpu) {
                free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
                per_cpu(trace_buffered_event, cpu) = NULL;
        }
        /*
         * Make sure trace_buffered_event is NULL before clearing
         * trace_buffered_event_cnt.
         */
        smp_wmb();

        preempt_disable();
        /* Do the work on each cpu */
        smp_call_function_many(tracing_buffer_mask,
                               enable_trace_buffered_event, NULL, 1);
        preempt_enable();
}

static struct trace_buffer *temp_buffer;

struct ring_buffer_event *
trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
                          struct trace_event_file *trace_file,
                          int type, unsigned long len,
                          unsigned int trace_ctx)
{
        struct ring_buffer_event *entry;
        struct trace_array *tr = trace_file->tr;
        int val;

        *current_rb = tr->array_buffer.buffer;

        if (!tr->no_filter_buffering_ref &&
            (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) {
                preempt_disable_notrace();
                /*
                 * Filtering is on, so try to use the per cpu buffer first.
                 * This buffer will simulate a ring_buffer_event,
                 * where the type_len is zero and the array[0] will
                 * hold the full length.
                 * (see include/linux/ring-buffer.h for details on
                 *  how the ring_buffer_event is structured).
                 *
                 * Using a temp buffer during filtering and copying it
                 * on a matched filter is quicker than writing directly
                 * into the ring buffer and then discarding it when
                 * it doesn't match. That is because the discard
                 * requires several atomic operations to get right.
                 * Copying on match and doing nothing on a failed match
                 * is still quicker than no copy on match, but having
                 * to discard out of the ring buffer on a failed match.
                 */
                if ((entry = __this_cpu_read(trace_buffered_event))) {
                        int max_len = PAGE_SIZE - struct_size(entry, array, 1);

                        val = this_cpu_inc_return(trace_buffered_event_cnt);

                        /*
                         * Preemption is disabled, but interrupts and NMIs
                         * can still come in now. If that happens after
                         * the above increment, then it will have to go
                         * back to the old method of allocating the event
                         * on the ring buffer, and if the filter fails, it
                         * will have to call ring_buffer_discard_commit()
                         * to remove it.
                         *
                         * Need to also check the unlikely case that the
                         * length is bigger than the temp buffer size.
                         * If that happens, then the reserve is pretty much
                         * guaranteed to fail, as the ring buffer currently
                         * only allows events less than a page. But that may
                         * change in the future, so let the ring buffer reserve
                         * handle the failure in that case.
                         */
                        if (val == 1 && likely(len <= max_len)) {
                                trace_event_setup(entry, type, trace_ctx);
                                entry->array[0] = len;
                                /* Return with preemption disabled */
                                return entry;
                        }
                        this_cpu_dec(trace_buffered_event_cnt);
                }
                /* __trace_buffer_lock_reserve() disables preemption */
                preempt_enable_notrace();
        }

        entry = __trace_buffer_lock_reserve(*current_rb, type, len,
                                            trace_ctx);
        /*
         * If tracing is off, but we have triggers enabled
         * we still need to look at the event data. Use the temp_buffer
         * to store the trace event for the trigger to use. It's recursive
         * safe and will not be recorded anywhere.
         */
        if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) {
                *current_rb = temp_buffer;
                entry = __trace_buffer_lock_reserve(*current_rb, type, len,
                                                    trace_ctx);
        }
        return entry;
}
EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);

static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock);
static DEFINE_MUTEX(tracepoint_printk_mutex);

static void output_printk(struct trace_event_buffer *fbuffer)
{
        struct trace_event_call *event_call;
        struct trace_event_file *file;
        struct trace_event *event;
        unsigned long flags;
        struct trace_iterator *iter = tracepoint_print_iter;

        /* We should never get here if iter is NULL */
        if (WARN_ON_ONCE(!iter))
                return;

        event_call = fbuffer->trace_file->event_call;
        if (!event_call || !event_call->event.funcs ||
            !event_call->event.funcs->trace)
                return;

        file = fbuffer->trace_file;
        if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
            (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
             !filter_match_preds(file->filter, fbuffer->entry)))
                return;

        event = &fbuffer->trace_file->event_call->event;

        raw_spin_lock_irqsave(&tracepoint_iter_lock, flags);
        trace_seq_init(&iter->seq);
        iter->ent = fbuffer->entry;
        event_call->event.funcs->trace(iter, 0, event);
        trace_seq_putc(&iter->seq, 0);
        printk("%s", iter->seq.buffer);

        raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
}

int tracepoint_printk_sysctl(struct ctl_table *table, int write,
                             void *buffer, size_t *lenp,
                             loff_t *ppos)
{
        int save_tracepoint_printk;
        int ret;

        mutex_lock(&tracepoint_printk_mutex);
        save_tracepoint_printk = tracepoint_printk;

        ret = proc_dointvec(table, write, buffer, lenp, ppos);

        /*
         * This will force exiting early, as tracepoint_printk
         * is always zero when tracepoint_printk_iter is not allocated
         */
        if (!tracepoint_print_iter)
                tracepoint_printk = 0;

        if (save_tracepoint_printk == tracepoint_printk)
                goto out;

        if (tracepoint_printk)
                static_key_enable(&tracepoint_printk_key.key);
        else
                static_key_disable(&tracepoint_printk_key.key);

 out:
        mutex_unlock(&tracepoint_printk_mutex);

        return ret;
}

void trace_event_buffer_commit(struct trace_event_buffer *fbuffer)
{
        enum event_trigger_type tt = ETT_NONE;
        struct trace_event_file *file = fbuffer->trace_file;

        if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event,
                        fbuffer->entry, &tt))
                goto discard;

        if (static_key_false(&tracepoint_printk_key.key))
                output_printk(fbuffer);

        if (static_branch_unlikely(&trace_event_exports_enabled))
                ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT);

        trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer,
                        fbuffer->event, fbuffer->trace_ctx, fbuffer->regs);

discard:
        if (tt)
                event_triggers_post_call(file, tt);

}
EXPORT_SYMBOL_GPL(trace_event_buffer_commit);

/*
 * Skip 3:
 *
 *   trace_buffer_unlock_commit_regs()
 *   trace_event_buffer_commit()
 *   trace_event_raw_event_xxx()
 */
# define STACK_SKIP 3

void trace_buffer_unlock_commit_regs(struct trace_array *tr,
                                     struct trace_buffer *buffer,
                                     struct ring_buffer_event *event,
                                     unsigned int trace_ctx,
                                     struct pt_regs *regs)
{
        __buffer_unlock_commit(buffer, event);

        /*
         * If regs is not set, then skip the necessary functions.
         * Note, we can still get here via blktrace, wakeup tracer
         * and mmiotrace, but that's ok if they lose a function or
         * two. They are not that meaningful.
         */
        ftrace_trace_stack(tr, buffer, trace_ctx, regs ? 0 : STACK_SKIP, regs);
        ftrace_trace_userstack(tr, buffer, trace_ctx);
}

/*
 * Similar to trace_buffer_unlock_commit_regs() but do not dump stack.
 */
void
trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
                                   struct ring_buffer_event *event)
{
        __buffer_unlock_commit(buffer, event);
}

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

        event = __trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
                                            trace_ctx);
        if (!event)
                return;
        entry   = ring_buffer_event_data(event);
        entry->ip                       = ip;
        entry->parent_ip                = parent_ip;

        if (!call_filter_check_discard(call, entry, buffer, event)) {
                if (static_branch_unlikely(&trace_function_exports_enabled))
                        ftrace_exports(event, TRACE_EXPORT_FUNCTION);
                __buffer_unlock_commit(buffer, event);
        }
}

#ifdef CONFIG_STACKTRACE

/* Allow 4 levels of nesting: normal, softirq, irq, NMI */

#define FTRACE_KSTACK_NESTING   4

#define FTRACE_KSTACK_ENTRIES   (PAGE_SIZE / FTRACE_KSTACK_NESTING)

struct ftrace_stack {
        unsigned long           calls[FTRACE_KSTACK_ENTRIES];
};


struct ftrace_stacks {
        struct ftrace_stack     stacks[FTRACE_KSTACK_NESTING];
};

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

static void __ftrace_trace_stack(struct trace_buffer *buffer,
                                 unsigned int trace_ctx,
                                 int skip, struct pt_regs *regs)
{
        struct trace_event_call *call = &event_kernel_stack;
        struct ring_buffer_event *event;
        unsigned int size, nr_entries;
        struct ftrace_stack *fstack;
        struct stack_entry *entry;
        int stackidx;

        /*
         * Add one, for this function and the call to save_stack_trace()
         * If regs is set, then these functions will not be in the way.
         */
#ifndef CONFIG_UNWINDER_ORC
        if (!regs)
                skip++;
#endif

        preempt_disable_notrace();

        stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;

        /* This should never happen. If it does, yell once and skip */
        if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING))
                goto out;

        /*
         * The above __this_cpu_inc_return() is 'atomic' cpu local. An
         * interrupt will either see the value pre increment or post
         * increment. If the interrupt happens pre increment it will have
         * restored the counter when it returns.  We just need a barrier to
         * keep gcc from moving things around.
         */
        barrier();

        fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx;
        size = ARRAY_SIZE(fstack->calls);

        if (regs) {
                nr_entries = stack_trace_save_regs(regs, fstack->calls,
                                                   size, skip);
        } else {
                nr_entries = stack_trace_save(fstack->calls, size, skip);
        }

        size = nr_entries * sizeof(unsigned long);
        event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
                                    (sizeof(*entry) - sizeof(entry->caller)) + size,
                                    trace_ctx);
        if (!event)
                goto out;
        entry = ring_buffer_event_data(event);

        memcpy(&entry->caller, fstack->calls, size);
        entry->size = nr_entries;

        if (!call_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();

}

static inline void ftrace_trace_stack(struct trace_array *tr,
                                      struct trace_buffer *buffer,
                                      unsigned int trace_ctx,
                                      int skip, struct pt_regs *regs)
{
        if (!(tr->trace_flags & TRACE_ITER_STACKTRACE))
                return;

        __ftrace_trace_stack(buffer, trace_ctx, skip, regs);
}

void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
                   int skip)
{
        struct trace_buffer *buffer = tr->array_buffer.buffer;

        if (rcu_is_watching()) {
                __ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
                return;
        }

        /*
         * When an NMI triggers, RCU is enabled via rcu_nmi_enter(),
         * but if the above rcu_is_watching() failed, then the NMI
         * triggered someplace critical, and rcu_irq_enter() should
         * not be called from NMI.
         */
        if (unlikely(in_nmi()))
                return;

        rcu_irq_enter_irqson();
        __ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
        rcu_irq_exit_irqson();
}

/**
 * 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)
{
        if (tracing_disabled || tracing_selftest_running)
                return;

#ifndef CONFIG_UNWINDER_ORC
        /* Skip 1 to skip this function. */
        skip++;
#endif
        __ftrace_trace_stack(global_trace.array_buffer.buffer,
                             tracing_gen_ctx(), skip, NULL);
}
EXPORT_SYMBOL_GPL(trace_dump_stack);

#ifdef CONFIG_USER_STACKTRACE_SUPPORT
static DEFINE_PER_CPU(int, user_stack_count);

static void
ftrace_trace_userstack(struct trace_array *tr,
                       struct trace_buffer *buffer, unsigned int trace_ctx)
{
        struct trace_event_call *call = &event_user_stack;
        struct ring_buffer_event *event;
        struct userstack_entry *entry;

        if (!(tr->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), trace_ctx);
        if (!event)
                goto out_drop_count;
        entry   = ring_buffer_event_data(event);

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

        stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
        if (!call_filter_check_discard(call, entry, buffer, event))
                __buffer_unlock_commit(buffer, event);

 out_drop_count:
        __this_cpu_dec(user_stack_count);
 out:
        preempt_enable();
}
#else /* CONFIG_USER_STACKTRACE_SUPPORT */
static void ftrace_trace_userstack(struct trace_array *tr,
                                   struct trace_buffer *buffer,
                                   unsigned int trace_ctx)
{
}
#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */

#endif /* CONFIG_STACKTRACE */

static inline void
func_repeats_set_delta_ts(struct func_repeats_entry *entry,
                          unsigned long long delta)
{
        entry->bottom_delta_ts = delta & U32_MAX;
        entry->top_delta_ts = (delta >> 32);
}

void trace_last_func_repeats(struct trace_array *tr,
                             struct trace_func_repeats *last_info,
                             unsigned int trace_ctx)
{
        struct trace_buffer *buffer = tr->array_buffer.buffer;
        struct func_repeats_entry *entry;
        struct ring_buffer_event *event;
        u64 delta;

        event = __trace_buffer_lock_reserve(buffer, TRACE_FUNC_REPEATS,
                                            sizeof(*entry), trace_ctx);
        if (!event)
                return;

        delta = ring_buffer_event_time_stamp(buffer, event) -
                last_info->ts_last_call;

        entry = ring_buffer_event_data(event);
        entry->ip = last_info->ip;
        entry->parent_ip = last_info->parent_ip;
        entry->count = last_info->count;
        func_repeats_set_delta_ts(entry, delta);

        __buffer_unlock_commit(buffer, event);
}

/* created for use with alloc_percpu */
struct trace_buffer_struct {
        int nesting;
        char buffer[4][TRACE_BUF_SIZE];
};

static struct trace_buffer_struct __percpu *trace_percpu_buffer;

/*
 * This allows for lockless recording.  If we're nested too deeply, then
 * this returns NULL.
 */
static char *get_trace_buf(void)
{
        struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);

        if (!trace_percpu_buffer || buffer->nesting >= 4)
                return NULL;

        buffer->nesting++;

        /* Interrupts must see nesting incremented before we use the buffer */
        barrier();
        return &buffer->buffer[buffer->nesting - 1][0];
}

static void put_trace_buf(void)
{
        /* Don't let the decrement of nesting leak before this */
        barrier();
        this_cpu_dec(trace_percpu_buffer->nesting);
}

static int alloc_percpu_trace_buffer(void)
{
        struct trace_buffer_struct __percpu *buffers;

        if (trace_percpu_buffer)
                return 0;

        buffers = alloc_percpu(struct trace_buffer_struct);
        if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer"))
                return -ENOMEM;

        trace_percpu_buffer = buffers;
        return 0;
}

static int buffers_allocated;

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

        if (alloc_percpu_trace_buffer())
                return;

        /* trace_printk() is for debug use only. Don't use it in production. */

        pr_warn("\n");
        pr_warn("**********************************************************\n");
        pr_warn("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
        pr_warn("**                                                      **\n");
        pr_warn("** trace_printk() being used. Allocating extra memory.  **\n");
        pr_warn("**                                                      **\n");
        pr_warn("** This means that this is a DEBUG kernel and it is     **\n");
        pr_warn("** unsafe for production use.                           **\n");
        pr_warn("**                                                      **\n");
        pr_warn("** If you see this message and you are not debugging    **\n");
        pr_warn("** the kernel, report this immediately to your vendor!  **\n");
        pr_warn("**                                                      **\n");
        pr_warn("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
        pr_warn("**********************************************************\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.array_buffer.buffer)
                tracing_start_cmdline_record();
}
EXPORT_SYMBOL_GPL(trace_printk_init_buffers);

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
 * @ip:    The address of the caller
 * @fmt:   The string format to write to the buffer
 * @args:  Arguments for @fmt
 */
int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
{
        struct trace_event_call *call = &event_bprint;
        struct ring_buffer_event *event;
        struct trace_buffer *buffer;
        struct trace_array *tr = &global_trace;
        struct bprint_entry *entry;
        unsigned int trace_ctx;
        char *tbuffer;
        int len = 0, size;

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

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

        trace_ctx = tracing_gen_ctx();
        preempt_disable_notrace();

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

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

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

        size = sizeof(*entry) + sizeof(u32) * len;
        buffer = tr->array_buffer.buffer;
        ring_buffer_nest_start(buffer);
        event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
                                            trace_ctx);
        if (!event)
                goto out;
        entry = ring_buffer_event_data(event);
        entry->ip                       = ip;
        entry->fmt                      = fmt;

        memcpy(entry->buf, tbuffer, sizeof(u32) * len);
        if (!call_filter_check_discard(call, entry, buffer, event)) {
                __buffer_unlock_commit(buffer, event);
                ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
        }

out:
        ring_buffer_nest_end(buffer);
out_put:
        put_trace_buf();

out_nobuffer:
        preempt_enable_notrace();
        unpause_graph_tracing();

        return len;
}
EXPORT_SYMBOL_GPL(trace_vbprintk);

__printf(3, 0)
static int
__trace_array_vprintk(struct trace_buffer *buffer,
                      unsigned long ip, const char *fmt, va_list args)
{
        struct trace_event_call *call = &event_print;
        struct ring_buffer_event *event;
        int len = 0, size;
        struct print_entry *entry;
        unsigned int trace_ctx;
        char *tbuffer;

        if (tracing_disabled || tracing_selftest_running)
                return 0;

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

        trace_ctx = tracing_gen_ctx();
        preempt_disable_notrace();


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

        len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);

        size = sizeof(*entry) + len + 1;
        ring_buffer_nest_start(buffer);
        event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
                                            trace_ctx);
        if (!event)
                goto out;
        entry = ring_buffer_event_data(event);
        entry->ip = ip;

        memcpy(&entry->buf, tbuffer, len + 1);
        if (!call_filter_check_discard(call, entry, buffer, event)) {
                __buffer_unlock_commit(buffer, event);
                ftrace_trace_stack(&global_trace, buffer, trace_ctx, 6, NULL);
        }

out:
        ring_buffer_nest_end(buffer);
        put_trace_buf();

out_nobuffer:
        preempt_enable_notrace();
        unpause_graph_tracing();

        return len;
}

__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
                        unsigned long ip, const char *fmt, va_list args)
{
        return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
}

/**
 * trace_array_printk - Print a message to a specific instance
 * @tr: The instance trace_array descriptor
 * @ip: The instruction pointer that this is called from.
 * @fmt: The format to print (printf format)
 *
 * If a subsystem sets up its own instance, they have the right to
 * printk strings into their tracing instance buffer using this
 * function. Note, this function will not write into the top level
 * buffer (use trace_printk() for that), as writing into the top level
 * buffer should only have events that can be individually disabled.
 * trace_printk() is only used for debugging a kernel, and should not
 * be ever incorporated in normal use.
 *
 * trace_array_printk() can be used, as it will not add noise to the
 * top level tracing buffer.
 *
 * Note, trace_array_init_printk() must be called on @tr before this
 * can be used.
 */
__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
                       unsigned long ip, const char *fmt, ...)
{
        int ret;
        va_list ap;

        if (!tr)
                return -ENOENT;

        /* This is only allowed for created instances */
        if (tr == &global_trace)
                return 0;

        if (!(tr->trace_flags & TRACE_ITER_PRINTK))
                return 0;

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

/**
 * trace_array_init_printk - Initialize buffers for trace_array_printk()
 * @tr: The trace array to initialize the buffers for
 *
 * As trace_array_printk() only writes into instances, they are OK to
 * have in the kernel (unlike trace_printk()). This needs to be called
 * before trace_array_printk() can be used on a trace_array.
 */
int trace_array_init_printk(struct trace_array *tr)
{
        if (!tr)
                return -ENOENT;

        /* This is only allowed for created instances */
        if (tr == &global_trace)
                return -EINVAL;

        return alloc_percpu_trace_buffer();
}
EXPORT_SYMBOL_GPL(trace_array_init_printk);

__printf(3, 4)
int trace_array_printk_buf(struct trace_buffer *buffer,
                           unsigned long ip, const char *fmt, ...)
{
        int ret;
        va_list ap;

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

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

__printf(2, 0)
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_iter_advance(buf_iter);
}

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);
                if (lost_events)
                        *lost_events = ring_buffer_iter_dropped(buf_iter) ?
                                (unsigned long)-1 : 0;
        } else {
                event = ring_buffer_peek(iter->array_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 trace_buffer *buffer = iter->array_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;
}

#define STATIC_FMT_BUF_SIZE     128
static char static_fmt_buf[STATIC_FMT_BUF_SIZE];

static char *trace_iter_expand_format(struct trace_iterator *iter)
{
        char *tmp;

        /*
         * iter->tr is NULL when used with tp_printk, which makes
         * this get called where it is not safe to call krealloc().
         */
        if (!iter->tr || iter->fmt == static_fmt_buf)
                return NULL;

        tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE,
                       GFP_KERNEL);
        if (tmp) {
                iter->fmt_size += STATIC_FMT_BUF_SIZE;
                iter->fmt = tmp;
        }

        return tmp;
}

/* Returns true if the string is safe to dereference from an event */
static bool trace_safe_str(struct trace_iterator *iter, const char *str,
                           bool star, int len)
{
        unsigned long addr = (unsigned long)str;
        struct trace_event *trace_event;
        struct trace_event_call *event;

        /* Ignore strings with no length */
        if (star && !len)
                return true;

        /* OK if part of the event data */
        if ((addr >= (unsigned long)iter->ent) &&
            (addr < (unsigned long)iter->ent + iter->ent_size))
                return true;

        /* OK if part of the temp seq buffer */
        if ((addr >= (unsigned long)iter->tmp_seq.buffer) &&
            (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE))
                return true;

        /* Core rodata can not be freed */
        if (is_kernel_rodata(addr))
                return true;

        if (trace_is_tracepoint_string(str))
                return true;

        /*
         * Now this could be a module event, referencing core module
         * data, which is OK.
         */
        if (!iter->ent)
                return false;

        trace_event = ftrace_find_event(iter->ent->type);
        if (!trace_event)
                return false;

        event = container_of(trace_event, struct trace_event_call, event);
        if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module)
                return false;

        /* Would rather have rodata, but this will suffice */
        if (within_module_core(addr, event->module))
                return true;

        return false;
}

static const char *show_buffer(struct trace_seq *s)
{
        struct seq_buf *seq = &s->seq;

        seq_buf_terminate(seq);

        return seq->buffer;
}

static DEFINE_STATIC_KEY_FALSE(trace_no_verify);

static int test_can_verify_check(const char *fmt, ...)
{
        char buf[16];
        va_list ap;
        int ret;

        /*
         * The verifier is dependent on vsnprintf() modifies the va_list
         * passed to it, where it is sent as a reference. Some architectures
         * (like x86_32) passes it by value, which means that vsnprintf()
         * does not modify the va_list passed to it, and the verifier
         * would then need to be able to understand all the values that
         * vsnprintf can use. If it is passed by value, then the verifier
         * is disabled.
         */
        va_start(ap, fmt);
        vsnprintf(buf, 16, "%d", ap);
        ret = va_arg(ap, int);
        va_end(ap);

        return ret;
}

static void test_can_verify(void)
{
        if (!test_can_verify_check("%d %d", 0, 1)) {
                pr_info("trace event string verifier disabled\n");
                static_branch_inc(&trace_no_verify);
        }
}

/**
 * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer
 * @iter: The iterator that holds the seq buffer and the event being printed
 * @fmt: The format used to print the event
 * @ap: The va_list holding the data to print from @fmt.
 *
 * This writes the data into the @iter->seq buffer using the data from
 * @fmt and @ap. If the format has a %s, then the source of the string
 * is examined to make sure it is safe to print, otherwise it will
 * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string
 * pointer.
 */
void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
                         va_list ap)
{
        const char *p = fmt;
        const char *str;
        int i, j;

        if (WARN_ON_ONCE(!fmt))
                return;

        if (static_branch_unlikely(&trace_no_verify))
                goto print;

        /* Don't bother checking when doing a ftrace_dump() */
        if (iter->fmt == static_fmt_buf)
                goto print;

        while (*p) {
                bool star = false;
                int len = 0;

                j = 0;

                /* We only care about %s and variants */
                for (i = 0; p[i]; i++) {
                        if (i + 1 >= iter->fmt_size) {
                                /*
                                 * If we can't expand the copy buffer,
                                 * just print it.
                                 */
                                if (!trace_iter_expand_format(iter))
                                        goto print;
                        }

                        if (p[i] == '\\' && p[i+1]) {
                                i++;
                                continue;
                        }
                        if (p[i] == '%') {
                                /* Need to test cases like %08.*s */
                                for (j = 1; p[i+j]; j++) {
                                        if (isdigit(p[i+j]) ||
                                            p[i+j] == '.')
                                                continue;
                                        if (p[i+j] == '*') {
                                                star = true;
                                                continue;
                                        }
                                        break;
                                }
                                if (p[i+j] == 's')
                                        break;
                                star = false;
                        }
                        j = 0;
                }
                /* If no %s found then just print normally */
                if (!p[i])
                        break;

                /* Copy up to the %s, and print that */
                strncpy(iter->fmt, p, i);
                iter->fmt[i] = '\0';
                trace_seq_vprintf(&iter->seq, iter->fmt, ap);

                /*
                 * If iter->seq is full, the above call no longer guarantees
                 * that ap is in sync with fmt processing, and further calls
                 * to va_arg() can return wrong positional arguments.
                 *
                 * Ensure that ap is no longer used in this case.
                 */
                if (iter->seq.full) {
                        p = "";
                        break;
                }

                if (star)
                        len = va_arg(ap, int);

                /* The ap now points to the string data of the %s */
                str = va_arg(ap, const char *);

                /*
                 * If you hit this warning, it is likely that the
                 * trace event in question used %s on a string that
                 * was saved at the time of the event, but may not be
                 * around when the trace is read. Use __string(),
                 * __assign_str() and __get_str() helpers in the TRACE_EVENT()
                 * instead. See samples/trace_events/trace-events-sample.h
                 * for reference.
                 */
                if (WARN_ONCE(!trace_safe_str(iter, str, star, len),
                              "fmt: '%s' current_buffer: '%s'",
                              fmt, show_buffer(&iter->seq))) {
                        int ret;

                        /* Try to safely read the string */
                        if (star) {
                                if (len + 1 > iter->fmt_size)
                                        len = iter->fmt_size - 1;
                                if (len < 0)
                                        len = 0;
                                ret = copy_from_kernel_nofault(iter->fmt, str, len);
                                iter->fmt[len] = 0;
                                star = false;
                        } else {
                                ret = strncpy_from_kernel_nofault(iter->fmt, str,
                                                                  iter->fmt_size);
                        }
                        if (ret < 0)
                                trace_seq_printf(&iter->seq, "(0x%px)", str);
                        else
                                trace_seq_printf(&iter->seq, "(0x%px:%s)",
                                                 str, iter->fmt);
                        str = "[UNSAFE-MEMORY]";
                        strcpy(iter->fmt, "%s");
                } else {
                        strncpy(iter->fmt, p + i, j + 1);
                        iter->fmt[j+1] = '\0';
                }
                if (star)
                        trace_seq_printf(&iter->seq, iter->fmt, len, str);
                else
                        trace_seq_printf(&iter->seq, iter->fmt, str);

                p += i + j + 1;
        }
 print:
        if (*p)
                trace_seq_vprintf(&iter->seq, p, ap);
}

const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
{
        const char *p, *new_fmt;
        char *q;

        if (WARN_ON_ONCE(!fmt))
                return fmt;

        if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
                return fmt;

        p = fmt;
        new_fmt = q = iter->fmt;
        while (*p) {
                if (unlikely(q - new_fmt + 3 > iter->fmt_size)) {
                        if (!trace_iter_expand_format(iter))
                                return fmt;

                        q += iter->fmt - new_fmt;
                        new_fmt = iter->fmt;
                }

                *q++ = *p++;

                /* Replace %p with %px */
                if (p[-1] == '%') {
                        if (p[0] == '%') {
                                *q++ = *p++;
                        } else if (p[0] == 'p' && !isalnum(p[1])) {
                                *q++ = *p++;
                                *q++ = 'x';
                        }
                }
        }
        *q = '\0';

        return new_fmt;
}

#define STATIC_TEMP_BUF_SIZE    128
static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4);

/* 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)
{
        /* __find_next_entry will reset ent_size */
        int ent_size = iter->ent_size;
        struct trace_entry *entry;

        /*
         * If called from ftrace_dump(), then the iter->temp buffer
         * will be the static_temp_buf and not created from kmalloc.
         * If the entry size is greater than the buffer, we can
         * not save it. Just return NULL in that case. This is only
         * used to add markers when two consecutive events' time
         * stamps have a large delta. See trace_print_lat_context()
         */
        if (iter->temp == static_temp_buf &&
            STATIC_TEMP_BUF_SIZE < ent_size)
                return NULL;

        /*
         * The __find_next_entry() may call peek_next_entry(), which may
         * call ring_buffer_peek() that may make the contents of iter->ent
         * undefined. Need to copy iter->ent now.
         */
        if (iter->ent && iter->ent != iter->temp) {
                if ((!iter->temp || iter->temp_size < iter->ent_size) &&
                    !WARN_ON_ONCE(iter->temp == static_temp_buf)) {
                        void *temp;
                        temp = kmalloc(iter->ent_size, GFP_KERNEL);
                        if (!temp)
                                return NULL;
                        kfree(iter->temp);
                        iter->temp = temp;
                        iter->temp_size = iter->ent_size;
                }
                memcpy(iter->temp, iter->ent, iter->ent_size);
                iter->ent = iter->temp;
        }
        entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
        /* Put back the original ent_size */
        iter->ent_size = ent_size;