kernel/trace/trace_events_hist.c

// SPDX-License-Identifier: GPL-2.0
/*
 * trace_events_hist - trace event hist triggers
 *
 * Copyright (C) 2015 Tom Zanussi <tom.zanussi@linux.intel.com>
 */

#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/stacktrace.h>
#include <linux/rculist.h>
#include <linux/tracefs.h>

#include "tracing_map.h"
#include "trace.h"
#include "trace_dynevent.h"

#define SYNTH_SYSTEM		"synthetic"
#define SYNTH_FIELDS_MAX	16

#define STR_VAR_LEN_MAX		32 /* must be multiple of sizeof(u64) */

struct hist_field;

typedef u64 (*hist_field_fn_t) (struct hist_field *field,
				struct tracing_map_elt *elt,
				struct ring_buffer_event *rbe,
				void *event);

#define HIST_FIELD_OPERANDS_MAX	2
#define HIST_FIELDS_MAX		(TRACING_MAP_FIELDS_MAX + TRACING_MAP_VARS_MAX)
#define HIST_ACTIONS_MAX	8

enum field_op_id {
	FIELD_OP_NONE,
	FIELD_OP_PLUS,
	FIELD_OP_MINUS,
	FIELD_OP_UNARY_MINUS,
};

/*
 * A hist_var (histogram variable) contains variable information for
 * hist_fields having the HIST_FIELD_FL_VAR or HIST_FIELD_FL_VAR_REF
 * flag set.  A hist_var has a variable name e.g. ts0, and is
 * associated with a given histogram trigger, as specified by
 * hist_data.  The hist_var idx is the unique index assigned to the
 * variable by the hist trigger's tracing_map.  The idx is what is
 * used to set a variable's value and, by a variable reference, to
 * retrieve it.
 */
struct hist_var {
	char				*name;
	struct hist_trigger_data	*hist_data;
	unsigned int			idx;
};

struct hist_field {
	struct ftrace_event_field	*field;
	unsigned long			flags;
	hist_field_fn_t			fn;
	unsigned int			size;
	unsigned int			offset;
	unsigned int                    is_signed;
	const char			*type;
	struct hist_field		*operands[HIST_FIELD_OPERANDS_MAX];
	struct hist_trigger_data	*hist_data;

	/*
	 * Variable fields contain variable-specific info in var.
	 */
	struct hist_var			var;
	enum field_op_id		operator;
	char				*system;
	char				*event_name;

	/*
	 * The name field is used for EXPR and VAR_REF fields.  VAR
	 * fields contain the variable name in var.name.
	 */
	char				*name;

	/*
	 * When a histogram trigger is hit, if it has any references
	 * to variables, the values of those variables are collected
	 * into a var_ref_vals array by resolve_var_refs().  The
	 * current value of each variable is read from the tracing_map
	 * using the hist field's hist_var.idx and entered into the
	 * var_ref_idx entry i.e. var_ref_vals[var_ref_idx].
	 */
	unsigned int			var_ref_idx;
	bool                            read_once;
};

static u64 hist_field_none(struct hist_field *field,
			   struct tracing_map_elt *elt,
			   struct ring_buffer_event *rbe,
			   void *event)
{
	return 0;
}

static u64 hist_field_counter(struct hist_field *field,
			      struct tracing_map_elt *elt,
			      struct ring_buffer_event *rbe,
			      void *event)
{
	return 1;
}

static u64 hist_field_string(struct hist_field *hist_field,
			     struct tracing_map_elt *elt,
			     struct ring_buffer_event *rbe,
			     void *event)
{
	char *addr = (char *)(event + hist_field->field->offset);

	return (u64)(unsigned long)addr;
}

static u64 hist_field_dynstring(struct hist_field *hist_field,
				struct tracing_map_elt *elt,
				struct ring_buffer_event *rbe,
				void *event)
{
	u32 str_item = *(u32 *)(event + hist_field->field->offset);
	int str_loc = str_item & 0xffff;
	char *addr = (char *)(event + str_loc);

	return (u64)(unsigned long)addr;
}

static u64 hist_field_pstring(struct hist_field *hist_field,
			      struct tracing_map_elt *elt,
			      struct ring_buffer_event *rbe,
			      void *event)
{
	char **addr = (char **)(event + hist_field->field->offset);

	return (u64)(unsigned long)*addr;
}

static u64 hist_field_log2(struct hist_field *hist_field,
			   struct tracing_map_elt *elt,
			   struct ring_buffer_event *rbe,
			   void *event)
{
	struct hist_field *operand = hist_field->operands[0];

	u64 val = operand->fn(operand, elt, rbe, event);

	return (u64) ilog2(roundup_pow_of_two(val));
}

static u64 hist_field_plus(struct hist_field *hist_field,
			   struct tracing_map_elt *elt,
			   struct ring_buffer_event *rbe,
			   void *event)
{
	struct hist_field *operand1 = hist_field->operands[0];
	struct hist_field *operand2 = hist_field->operands[1];

	u64 val1 = operand1->fn(operand1, elt, rbe, event);
	u64 val2 = operand2->fn(operand2, elt, rbe, event);

	return val1 + val2;
}

static u64 hist_field_minus(struct hist_field *hist_field,
			    struct tracing_map_elt *elt,
			    struct ring_buffer_event *rbe,
			    void *event)
{
	struct hist_field *operand1 = hist_field->operands[0];
	struct hist_field *operand2 = hist_field->operands[1];

	u64 val1 = operand1->fn(operand1, elt, rbe, event);
	u64 val2 = operand2->fn(operand2, elt, rbe, event);

	return val1 - val2;
}

static u64 hist_field_unary_minus(struct hist_field *hist_field,
				  struct tracing_map_elt *elt,
				  struct ring_buffer_event *rbe,
				  void *event)
{
	struct hist_field *operand = hist_field->operands[0];

	s64 sval = (s64)operand->fn(operand, elt, rbe, event);
	u64 val = (u64)-sval;

	return val;
}

#define DEFINE_HIST_FIELD_FN(type)					\
	static u64 hist_field_##type(struct hist_field *hist_field,	\
				     struct tracing_map_elt *elt,	\
				     struct ring_buffer_event *rbe,	\
				     void *event)			\
{									\
	type *addr = (type *)(event + hist_field->field->offset);	\
									\
	return (u64)(unsigned long)*addr;				\
}

DEFINE_HIST_FIELD_FN(s64);
DEFINE_HIST_FIELD_FN(u64);
DEFINE_HIST_FIELD_FN(s32);
DEFINE_HIST_FIELD_FN(u32);
DEFINE_HIST_FIELD_FN(s16);
DEFINE_HIST_FIELD_FN(u16);
DEFINE_HIST_FIELD_FN(s8);
DEFINE_HIST_FIELD_FN(u8);

#define for_each_hist_field(i, hist_data)	\
	for ((i) = 0; (i) < (hist_data)->n_fields; (i)++)

#define for_each_hist_val_field(i, hist_data)	\
	for ((i) = 0; (i) < (hist_data)->n_vals; (i)++)

#define for_each_hist_key_field(i, hist_data)	\
	for ((i) = (hist_data)->n_vals; (i) < (hist_data)->n_fields; (i)++)

#define HIST_STACKTRACE_DEPTH	16
#define HIST_STACKTRACE_SIZE	(HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
#define HIST_STACKTRACE_SKIP	5

#define HITCOUNT_IDX		0
#define HIST_KEY_SIZE_MAX	(MAX_FILTER_STR_VAL + HIST_STACKTRACE_SIZE)

enum hist_field_flags {
	HIST_FIELD_FL_HITCOUNT		= 1 << 0,
	HIST_FIELD_FL_KEY		= 1 << 1,
	HIST_FIELD_FL_STRING		= 1 << 2,
	HIST_FIELD_FL_HEX		= 1 << 3,
	HIST_FIELD_FL_SYM		= 1 << 4,
	HIST_FIELD_FL_SYM_OFFSET	= 1 << 5,
	HIST_FIELD_FL_EXECNAME		= 1 << 6,
	HIST_FIELD_FL_SYSCALL		= 1 << 7,
	HIST_FIELD_FL_STACKTRACE	= 1 << 8,
	HIST_FIELD_FL_LOG2		= 1 << 9,
	HIST_FIELD_FL_TIMESTAMP		= 1 << 10,
	HIST_FIELD_FL_TIMESTAMP_USECS	= 1 << 11,
	HIST_FIELD_FL_VAR		= 1 << 12,
	HIST_FIELD_FL_EXPR		= 1 << 13,
	HIST_FIELD_FL_VAR_REF		= 1 << 14,
	HIST_FIELD_FL_CPU		= 1 << 15,
	HIST_FIELD_FL_ALIAS		= 1 << 16,
};

struct var_defs {
	unsigned int	n_vars;
	char		*name[TRACING_MAP_VARS_MAX];
	char		*expr[TRACING_MAP_VARS_MAX];
};

struct hist_trigger_attrs {
	char		*keys_str;
	char		*vals_str;
	char		*sort_key_str;
	char		*name;
	char		*clock;
	bool		pause;
	bool		cont;
	bool		clear;
	bool		ts_in_usecs;
	unsigned int	map_bits;

	char		*assignment_str[TRACING_MAP_VARS_MAX];
	unsigned int	n_assignments;

	char		*action_str[HIST_ACTIONS_MAX];
	unsigned int	n_actions;

	struct var_defs	var_defs;
};

struct field_var {
	struct hist_field	*var;
	struct hist_field	*val;
};

struct field_var_hist {
	struct hist_trigger_data	*hist_data;
	char				*cmd;
};

struct hist_trigger_data {
	struct hist_field               *fields[HIST_FIELDS_MAX];
	unsigned int			n_vals;
	unsigned int			n_keys;
	unsigned int			n_fields;
	unsigned int			n_vars;
	unsigned int			key_size;
	struct tracing_map_sort_key	sort_keys[TRACING_MAP_SORT_KEYS_MAX];
	unsigned int			n_sort_keys;
	struct trace_event_file		*event_file;
	struct hist_trigger_attrs	*attrs;
	struct tracing_map		*map;
	bool				enable_timestamps;
	bool				remove;
	struct hist_field               *var_refs[TRACING_MAP_VARS_MAX];
	unsigned int			n_var_refs;

	struct action_data		*actions[HIST_ACTIONS_MAX];
	unsigned int			n_actions;

	struct field_var		*field_vars[SYNTH_FIELDS_MAX];
	unsigned int			n_field_vars;
	unsigned int			n_field_var_str;
	struct field_var_hist		*field_var_hists[SYNTH_FIELDS_MAX];
	unsigned int			n_field_var_hists;

	struct field_var		*save_vars[SYNTH_FIELDS_MAX];
	unsigned int			n_save_vars;
	unsigned int			n_save_var_str;
};

static int synth_event_create(int argc, const char **argv);
static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
static int synth_event_release(struct dyn_event *ev);
static bool synth_event_is_busy(struct dyn_event *ev);
static bool synth_event_match(const char *system, const char *event,
			      struct dyn_event *ev);

static struct dyn_event_operations synth_event_ops = {
	.create = synth_event_create,
	.show = synth_event_show,
	.is_busy = synth_event_is_busy,
	.free = synth_event_release,
	.match = synth_event_match,
};

struct synth_field {
	char *type;
	char *name;
	size_t size;
	bool is_signed;
	bool is_string;
};

struct synth_event {
	struct dyn_event			devent;
	int					ref;
	char					*name;
	struct synth_field			**fields;
	unsigned int				n_fields;
	unsigned int				n_u64;
	struct trace_event_class		class;
	struct trace_event_call			call;
	struct tracepoint			*tp;
};

static bool is_synth_event(struct dyn_event *ev)
{
	return ev->ops == &synth_event_ops;
}

static struct synth_event *to_synth_event(struct dyn_event *ev)
{
	return container_of(ev, struct synth_event, devent);
}

static bool synth_event_is_busy(struct dyn_event *ev)
{
	struct synth_event *event = to_synth_event(ev);

	return event->ref != 0;
}

static bool synth_event_match(const char *system, const char *event,
			      struct dyn_event *ev)
{
	struct synth_event *sev = to_synth_event(ev);

	return strcmp(sev->name, event) == 0 &&
		(!system || strcmp(system, SYNTH_SYSTEM) == 0);
}

struct action_data;

typedef void (*action_fn_t) (struct hist_trigger_data *hist_data,
			     struct tracing_map_elt *elt, void *rec,
			     struct ring_buffer_event *rbe, void *key,
			     struct action_data *data, u64 *var_ref_vals);

typedef bool (*check_track_val_fn_t) (u64 track_val, u64 var_val);

enum handler_id {
	HANDLER_ONMATCH = 1,
	HANDLER_ONMAX,
	HANDLER_ONCHANGE,
};

enum action_id {
	ACTION_SAVE = 1,
	ACTION_TRACE,
	ACTION_SNAPSHOT,
};

struct action_data {
	enum handler_id		handler;
	enum action_id		action;
	char			*action_name;
	action_fn_t		fn;

	unsigned int		n_params;
	char			*params[SYNTH_FIELDS_MAX];

	/*
	 * When a histogram trigger is hit, the values of any
	 * references to variables, including variables being passed
	 * as parameters to synthetic events, are collected into a
	 * var_ref_vals array.  This var_ref_idx is the index of the
	 * first param in the array to be passed to the synthetic
	 * event invocation.
	 */
	unsigned int		var_ref_idx;
	struct synth_event	*synth_event;
	bool			use_trace_keyword;
	char			*synth_event_name;

	union {
		struct {
			char			*event;
			char			*event_system;
		} match_data;

		struct {
			/*
			 * var_str contains the $-unstripped variable
			 * name referenced by var_ref, and used when
			 * printing the action.  Because var_ref
			 * creation is deferred to create_actions(),
			 * we need a per-action way to save it until
			 * then, thus var_str.
			 */
			char			*var_str;

			/*
			 * var_ref refers to the variable being
			 * tracked e.g onmax($var).
			 */
			struct hist_field	*var_ref;

			/*
			 * track_var contains the 'invisible' tracking
			 * variable created to keep the current
			 * e.g. max value.
			 */
			struct hist_field	*track_var;

			check_track_val_fn_t	check_val;
			action_fn_t		save_data;
		} track_data;
	};
};

struct track_data {
	u64				track_val;
	bool				updated;

	unsigned int			key_len;
	void				*key;
	struct tracing_map_elt		elt;

	struct action_data		*action_data;
	struct hist_trigger_data	*hist_data;
};

struct hist_elt_data {
	char *comm;
	u64 *var_ref_vals;
	char *field_var_str[SYNTH_FIELDS_MAX];
};

struct snapshot_context {
	struct tracing_map_elt	*elt;
	void			*key;
};

static void track_data_free(struct track_data *track_data)
{
	struct hist_elt_data *elt_data;

	if (!track_data)
		return;

	kfree(track_data->key);

	elt_data = track_data->elt.private_data;
	if (elt_data) {
		kfree(elt_data->comm);
		kfree(elt_data);
	}

	kfree(track_data);
}

static struct track_data *track_data_alloc(unsigned int key_len,
					   struct action_data *action_data,
					   struct hist_trigger_data *hist_data)
{
	struct track_data *data = kzalloc(sizeof(*data), GFP_KERNEL);
	struct hist_elt_data *elt_data;

	if (!data)
		return ERR_PTR(-ENOMEM);

	data->key = kzalloc(key_len, GFP_KERNEL);
	if (!data->key) {
		track_data_free(data);
		return ERR_PTR(-ENOMEM);
	}

	data->key_len = key_len;
	data->action_data = action_data;
	data->hist_data = hist_data;

	elt_data = kzalloc(sizeof(*elt_data), GFP_KERNEL);
	if (!elt_data) {
		track_data_free(data);
		return ERR_PTR(-ENOMEM);
	}
	data->elt.private_data = elt_data;

	elt_data->comm = kzalloc(TASK_COMM_LEN, GFP_KERNEL);
	if (!elt_data->comm) {
		track_data_free(data);
		return ERR_PTR(-ENOMEM);
	}

	return data;
}

static char last_hist_cmd[MAX_FILTER_STR_VAL];
static char hist_err_str[MAX_FILTER_STR_VAL];

static void last_cmd_set(char *str)
{
	if (!str)
		return;

	strncpy(last_hist_cmd, str, MAX_FILTER_STR_VAL - 1);
}

static void hist_err(char *str, char *var)
{
	int maxlen = MAX_FILTER_STR_VAL - 1;

	if (!str)
		return;

	if (strlen(hist_err_str))
		return;

	if (!var)
		var = "";

	if (strlen(hist_err_str) + strlen(str) + strlen(var) > maxlen)
		return;

	strcat(hist_err_str, str);
	strcat(hist_err_str, var);
}

static void hist_err_event(char *str, char *system, char *event, char *var)
{
	char err[MAX_FILTER_STR_VAL];

	if (system && var)
		snprintf(err, MAX_FILTER_STR_VAL, "%s.%s.%s", system, event, var);
	else if (system)
		snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
	else
		strscpy(err, var, MAX_FILTER_STR_VAL);

	hist_err(str, err);
}

static void hist_err_clear(void)
{
	hist_err_str[0] = '\0';
}

static bool have_hist_err(void)
{
	if (strlen(hist_err_str))
		return true;

	return false;
}

struct synth_trace_event {
	struct trace_entry	ent;
	u64			fields[];
};

static int synth_event_define_fields(struct trace_event_call *call)
{
	struct synth_trace_event trace;
	int offset = offsetof(typeof(trace), fields);
	struct synth_event *event = call->data;
	unsigned int i, size, n_u64;
	char *name, *type;
	bool is_signed;
	int ret = 0;

	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
		size = event->fields[i]->size;
		is_signed = event->fields[i]->is_signed;
		type = event->fields[i]->type;
		name = event->fields[i]->name;
		ret = trace_define_field(call, type, name, offset, size,
					 is_signed, FILTER_OTHER);
		if (ret)
			break;

		if (event->fields[i]->is_string) {
			offset += STR_VAR_LEN_MAX;
			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
		} else {
			offset += sizeof(u64);
			n_u64++;
		}
	}

	event->n_u64 = n_u64;

	return ret;
}

static bool synth_field_signed(char *type)
{
	if (str_has_prefix(type, "u"))
		return false;

	return true;
}

static int synth_field_is_string(char *type)
{
	if (strstr(type, "char[") != NULL)
		return true;

	return false;
}

static int synth_field_string_size(char *type)
{
	char buf[4], *end, *start;
	unsigned int len;
	int size, err;

	start = strstr(type, "char[");
	if (start == NULL)
		return -EINVAL;
	start += sizeof("char[") - 1;

	end = strchr(type, ']');
	if (!end || end < start)
		return -EINVAL;

	len = end - start;
	if (len > 3)
		return -EINVAL;

	strncpy(buf, start, len);
	buf[len] = '\0';

	err = kstrtouint(buf, 0, &size);
	if (err)
		return err;

	if (size > STR_VAR_LEN_MAX)
		return -EINVAL;

	return size;
}

static int synth_field_size(char *type)
{
	int size = 0;

	if (strcmp(type, "s64") == 0)
		size = sizeof(s64);
	else if (strcmp(type, "u64") == 0)
		size = sizeof(u64);
	else if (strcmp(type, "s32") == 0)
		size = sizeof(s32);
	else if (strcmp(type, "u32") == 0)
		size = sizeof(u32);
	else if (strcmp(type, "s16") == 0)
		size = sizeof(s16);
	else if (strcmp(type, "u16") == 0)
		size = sizeof(u16);
	else if (strcmp(type, "s8") == 0)
		size = sizeof(s8);
	else if (strcmp(type, "u8") == 0)
		size = sizeof(u8);
	else if (strcmp(type, "char") == 0)
		size = sizeof(char);
	else if (strcmp(type, "unsigned char") == 0)
		size = sizeof(unsigned char);
	else if (strcmp(type, "int") == 0)
		size = sizeof(int);
	else if (strcmp(type, "unsigned int") == 0)
		size = sizeof(unsigned int);
	else if (strcmp(type, "long") == 0)
		size = sizeof(long);
	else if (strcmp(type, "unsigned long") == 0)
		size = sizeof(unsigned long);
	else if (strcmp(type, "pid_t") == 0)
		size = sizeof(pid_t);
	else if (synth_field_is_string(type))
		size = synth_field_string_size(type);

	return size;
}

static const char *synth_field_fmt(char *type)
{
	const char *fmt = "%llu";

	if (strcmp(type, "s64") == 0)
		fmt = "%lld";
	else if (strcmp(type, "u64") == 0)
		fmt = "%llu";
	else if (strcmp(type, "s32") == 0)
		fmt = "%d";
	else if (strcmp(type, "u32") == 0)
		fmt = "%u";
	else if (strcmp(type, "s16") == 0)
		fmt = "%d";
	else if (strcmp(type, "u16") == 0)
		fmt = "%u";
	else if (strcmp(type, "s8") == 0)
		fmt = "%d";
	else if (strcmp(type, "u8") == 0)
		fmt = "%u";
	else if (strcmp(type, "char") == 0)
		fmt = "%d";
	else if (strcmp(type, "unsigned char") == 0)
		fmt = "%u";
	else if (strcmp(type, "int") == 0)
		fmt = "%d";
	else if (strcmp(type, "unsigned int") == 0)
		fmt = "%u";
	else if (strcmp(type, "long") == 0)
		fmt = "%ld";
	else if (strcmp(type, "unsigned long") == 0)
		fmt = "%lu";
	else if (strcmp(type, "pid_t") == 0)
		fmt = "%d";
	else if (synth_field_is_string(type))
		fmt = "%s";

	return fmt;
}

static enum print_line_t print_synth_event(struct trace_iterator *iter,
					   int flags,
					   struct trace_event *event)
{
	struct trace_array *tr = iter->tr;
	struct trace_seq *s = &iter->seq;
	struct synth_trace_event *entry;
	struct synth_event *se;
	unsigned int i, n_u64;
	char print_fmt[32];
	const char *fmt;

	entry = (struct synth_trace_event *)iter->ent;
	se = container_of(event, struct synth_event, call.event);

	trace_seq_printf(s, "%s: ", se->name);

	for (i = 0, n_u64 = 0; i < se->n_fields; i++) {
		if (trace_seq_has_overflowed(s))
			goto end;

		fmt = synth_field_fmt(se->fields[i]->type);

		/* parameter types */
		if (tr->trace_flags & TRACE_ITER_VERBOSE)
			trace_seq_printf(s, "%s ", fmt);

		snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt);

		/* parameter values */
		if (se->fields[i]->is_string) {
			trace_seq_printf(s, print_fmt, se->fields[i]->name,
					 (char *)&entry->fields[n_u64],
					 i == se->n_fields - 1 ? "" : " ");
			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
		} else {
			trace_seq_printf(s, print_fmt, se->fields[i]->name,
					 entry->fields[n_u64],
					 i == se->n_fields - 1 ? "" : " ");
			n_u64++;
		}
	}
end:
	trace_seq_putc(s, '\n');

	return trace_handle_return(s);
}

static struct trace_event_functions synth_event_funcs = {
	.trace		= print_synth_event
};

static notrace void trace_event_raw_event_synth(void *__data,
						u64 *var_ref_vals,
						unsigned int var_ref_idx)
{
	struct trace_event_file *trace_file = __data;
	struct synth_trace_event *entry;
	struct trace_event_buffer fbuffer;
	struct ring_buffer *buffer;
	struct synth_event *event;
	unsigned int i, n_u64;
	int fields_size = 0;

	event = trace_file->event_call->data;

	if (trace_trigger_soft_disabled(trace_file))
		return;

	fields_size = event->n_u64 * sizeof(u64);

	/*
	 * Avoid ring buffer recursion detection, as this event
	 * is being performed within another event.
	 */
	buffer = trace_file->tr->trace_buffer.buffer;
	ring_buffer_nest_start(buffer);

	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
					   sizeof(*entry) + fields_size);
	if (!entry)
		goto out;

	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
		if (event->fields[i]->is_string) {
			char *str_val = (char *)(long)var_ref_vals[var_ref_idx + i];
			char *str_field = (char *)&entry->fields[n_u64];

			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
		} else {
			entry->fields[n_u64] = var_ref_vals[var_ref_idx + i];
			n_u64++;
		}
	}

	trace_event_buffer_commit(&fbuffer);
out:
	ring_buffer_nest_end(buffer);
}

static void free_synth_event_print_fmt(struct trace_event_call *call)
{
	if (call) {
		kfree(call->print_fmt);
		call->print_fmt = NULL;
	}
}

static int __set_synth_event_print_fmt(struct synth_event *event,
				       char *buf, int len)
{
	const char *fmt;
	int pos = 0;
	int i;

	/* When len=0, we just calculate the needed length */
#define LEN_OR_ZERO (len ? len - pos : 0)

	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
	for (i = 0; i < event->n_fields; i++) {
		fmt = synth_field_fmt(event->fields[i]->type);
		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s%s",
				event->fields[i]->name, fmt,
				i == event->n_fields - 1 ? "" : ", ");
	}
	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");

	for (i = 0; i < event->n_fields; i++) {
		pos += snprintf(buf + pos, LEN_OR_ZERO,
				", REC->%s", event->fields[i]->name);
	}

#undef LEN_OR_ZERO

	/* return the length of print_fmt */
	return pos;
}

static int set_synth_event_print_fmt(struct trace_event_call *call)
{
	struct synth_event *event = call->data;
	char *print_fmt;
	int len;

	/* First: called with 0 length to calculate the needed length */
	len = __set_synth_event_print_fmt(event, NULL, 0);

	print_fmt = kmalloc(len + 1, GFP_KERNEL);
	if (!print_fmt)
		return -ENOMEM;

	/* Second: actually write the @print_fmt */
	__set_synth_event_print_fmt(event, print_fmt, len + 1);
	call->print_fmt = print_fmt;

	return 0;
}

static void free_synth_field(struct synth_field *field)
{
	kfree(field->type);
	kfree(field->name);
	kfree(field);
}

static struct synth_field *parse_synth_field(int argc, const char **argv,
					     int *consumed)
{
	struct synth_field *field;
	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
	int len, ret = 0;

	if (field_type[0] == ';')
		field_type++;

	if (!strcmp(field_type, "unsigned")) {
		if (argc < 3)
			return ERR_PTR(-EINVAL);
		prefix = "unsigned ";
		field_type = argv[1];
		field_name = argv[2];
		*consumed = 3;
	} else {
		field_name = argv[1];
		*consumed = 2;
	}

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

	len = strlen(field_name);
	array = strchr(field_name, '[');
	if (array)
		len -= strlen(array);
	else if (field_name[len - 1] == ';')
		len--;

	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
	if (!field->name) {
		ret = -ENOMEM;
		goto free;
	}

	if (field_type[0] == ';')
		field_type++;
	len = strlen(field_type) + 1;
	if (array)
		len += strlen(array);
	if (prefix)
		len += strlen(prefix);

	field->type = kzalloc(len, GFP_KERNEL);
	if (!field->type) {
		ret = -ENOMEM;
		goto free;
	}
	if (prefix)
		strcat(field->type, prefix);
	strcat(field->type, field_type);
	if (array) {
		strcat(field->type, array);
		if (field->type[len - 1] == ';')
			field->type[len - 1] = '\0';
	}

	field->size = synth_field_size(field->type);
	if (!field->size) {
		ret = -EINVAL;
		goto free;
	}

	if (synth_field_is_string(field->type))
		field->is_string = true;

	field->is_signed = synth_field_signed(field->type);

 out:
	return field;
 free:
	free_synth_field(field);
	field = ERR_PTR(ret);
	goto out;
}

static void free_synth_tracepoint(struct tracepoint *tp)
{
	if (!tp)
		return;

	kfree(tp->name);
	kfree(tp);
}

static struct tracepoint *alloc_synth_tracepoint(char *name)
{
	struct tracepoint *tp;

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

	tp->name = kstrdup(name, GFP_KERNEL);
	if (!tp->name) {
		kfree(tp);
		return ERR_PTR(-ENOMEM);
	}

	return tp;
}

typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals,
				    unsigned int var_ref_idx);

static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
			       unsigned int var_ref_idx)
{
	struct tracepoint *tp = event->tp;

	if (unlikely(atomic_read(&tp->key.enabled) > 0)) {
		struct tracepoint_func *probe_func_ptr;
		synth_probe_func_t probe_func;
		void *__data;

		if (!(cpu_online(raw_smp_processor_id())))
			return;

		probe_func_ptr = rcu_dereference_sched((tp)->funcs);
		if (probe_func_ptr) {
			do {
				probe_func = probe_func_ptr->func;
				__data = probe_func_ptr->data;
				probe_func(__data, var_ref_vals, var_ref_idx);
			} while ((++probe_func_ptr)->func);
		}
	}
}

static struct synth_event *find_synth_event(const char *name)
{
	struct dyn_event *pos;
	struct synth_event *event;

	for_each_dyn_event(pos) {
		if (!is_synth_event(pos))
			continue;
		event = to_synth_event(pos);
		if (strcmp(event->name, name) == 0)
			return event;
	}

	return NULL;
}

static int register_synth_event(struct synth_event *event)
{
	struct trace_event_call *call = &event->call;
	int ret = 0;

	event->call.class = &event->class;
	event->class.system = kstrdup(SYNTH_SYSTEM, GFP_KERNEL);
	if (!event->class.system) {
		ret = -ENOMEM;
		goto out;
	}

	event->tp = alloc_synth_tracepoint(event->name);
	if (IS_ERR(event->tp)) {
		ret = PTR_ERR(event->tp);
		event->tp = NULL;
		goto out;
	}

	INIT_LIST_HEAD(&call->class->fields);
	call->event.funcs = &synth_event_funcs;
	call->class->define_fields = synth_event_define_fields;

	ret = register_trace_event(&call->event);
	if (!ret) {
		ret = -ENODEV;
		goto out;
	}
	call->flags = TRACE_EVENT_FL_TRACEPOINT;
	call->class->reg = trace_event_reg;
	call->class->probe = trace_event_raw_event_synth;
	call->data = event;
	call->tp = event->tp;

	ret = trace_add_event_call(call);
	if (ret) {
		pr_warn("Failed to register synthetic event: %s\n",
			trace_event_name(call));
		goto err;
	}

	ret = set_synth_event_print_fmt(call);
	if (ret < 0) {
		trace_remove_event_call(call);
		goto err;
	}
 out:
	return ret;
 err:
	unregister_trace_event(&call->event);
	goto out;
}

static int unregister_synth_event(struct synth_event *event)
{
	struct trace_event_call *call = &event->call;
	int ret;

	ret = trace_remove_event_call(call);

	return ret;
}

static void free_synth_event(struct synth_event *event)
{
	unsigned int i;

	if (!event)
		return;

	for (i = 0; i < event->n_fields; i++)
		free_synth_field(event->fields[i]);

	kfree(event->fields);
	kfree(event->name);
	kfree(event->class.system);
	free_synth_tracepoint(event->tp);
	free_synth_event_print_fmt(&event->call);
	kfree(event);
}

static struct synth_event *alloc_synth_event(const char *name, int n_fields,
					     struct synth_field **fields)
{
	struct synth_event *event;
	unsigned int i;

	event = kzalloc(sizeof(*event), GFP_KERNEL);
	if (!event) {
		event = ERR_PTR(-ENOMEM);
		goto out;
	}

	event->name = kstrdup(name, GFP_KERNEL);
	if (!event->name) {
		kfree(event);
		event = ERR_PTR(-ENOMEM);
		goto out;
	}

	event->fields = kcalloc(n_fields, sizeof(*event->fields), GFP_KERNEL);
	if (!event->fields) {
		free_synth_event(event);
		event = ERR_PTR(-ENOMEM);
		goto out;
	}

	dyn_event_init(&event->devent, &synth_event_ops);

	for (i = 0; i < n_fields; i++)
		event->fields[i] = fields[i];

	event->n_fields = n_fields;
 out:
	return event;
}

static void action_trace(struct hist_trigger_data *hist_data,
			 struct tracing_map_elt *elt, void *rec,
			 struct ring_buffer_event *rbe, void *key,
			 struct action_data *data, u64 *var_ref_vals)
{
	struct synth_event *event = data->synth_event;

	trace_synth(event, var_ref_vals, data->var_ref_idx);
}

struct hist_var_data {
	struct list_head list;
	struct hist_trigger_data *hist_data;
};

static int __create_synth_event(int argc, const char *name, const char **argv)
{
	struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
	struct synth_event *event = NULL;
	int i, consumed = 0, n_fields = 0, ret = 0;

	/*
	 * Argument syntax:
	 *  - Add synthetic event: <event_name> field[;field] ...
	 *  - Remove synthetic event: !<event_name> field[;field] ...
	 *      where 'field' = type field_name
	 */

	if (name[0] == '\0' || argc < 1)
		return -EINVAL;

	mutex_lock(&event_mutex);

	event = find_synth_event(name);
	if (event) {
		ret = -EEXIST;
		goto out;
	}

	for (i = 0; i < argc - 1; i++) {
		if (strcmp(argv[i], ";") == 0)
			continue;
		if (n_fields == SYNTH_FIELDS_MAX) {
			ret = -EINVAL;
			goto err;
		}

		field = parse_synth_field(argc - i, &argv[i], &consumed);
		if (IS_ERR(field)) {
			ret = PTR_ERR(field);
			goto err;
		}
		fields[n_fields++] = field;
		i += consumed - 1;
	}

	if (i < argc && strcmp(argv[i], ";") != 0) {
		ret = -EINVAL;
		goto err;
	}

	event = alloc_synth_event(name, n_fields, fields);
	if (IS_ERR(event)) {
		ret = PTR_ERR(event);
		event = NULL;
		goto err;
	}
	ret = register_synth_event(event);
	if (!ret)
		dyn_event_add(&event->devent);
	else
		free_synth_event(event);
 out:
	mutex_unlock(&event_mutex);

	return ret;
 err:
	for (i = 0; i < n_fields; i++)
		free_synth_field(fields[i]);

	goto out;
}

static int create_or_delete_synth_event(int argc, char **argv)
{
	const char *name = argv[0];
	struct synth_event *event = NULL;
	int ret;

	/* trace_run_command() ensures argc != 0 */
	if (name[0] == '!') {
		mutex_lock(&event_mutex);
		event = find_synth_event(name + 1);
		if (event) {
			if (event->ref)
				ret = -EBUSY;
			else {
				ret = unregister_synth_event(event);
				if (!ret) {
					dyn_event_remove(&event->devent);
					free_synth_event(event);
				}
			}
		} else
			ret = -ENOENT;
		mutex_unlock(&event_mutex);
		return ret;
	}

	ret = __create_synth_event(argc - 1, name, (const char **)argv + 1);
	return ret == -ECANCELED ? -EINVAL : ret;
}

static int synth_event_create(int argc, const char **argv)
{
	const char *name = argv[0];
	int len;

	if (name[0] != 's' || name[1] != ':')
		return -ECANCELED;
	name += 2;

	/* This interface accepts group name prefix */
	if (strchr(name, '/')) {
		len = str_has_prefix(name, SYNTH_SYSTEM "/");
		if (len == 0)
			return -EINVAL;
		name += len;
	}
	return __create_synth_event(argc - 1, name, argv + 1);
}

static int synth_event_release(struct dyn_event *ev)
{
	struct synth_event *event = to_synth_event(ev);
	int ret;

	if (event->ref)
		return -EBUSY;

	ret = unregister_synth_event(event);
	if (ret)
		return ret;

	dyn_event_remove(ev);
	free_synth_event(event);
	return 0;
}

static int __synth_event_show(struct seq_file *m, struct synth_event *event)
{
	struct synth_field *field;
	unsigned int i;

	seq_printf(m, "%s\t", event->name);

	for (i = 0; i < event->n_fields; i++) {
		field = event->fields[i];

		/* parameter values */
		seq_printf(m, "%s %s%s", field->type, field->name,
			   i == event->n_fields - 1 ? "" : "; ");
	}

	seq_putc(m, '\n');

	return 0;
}

static int synth_event_show(struct seq_file *m, struct dyn_event *ev)
{
	struct synth_event *event = to_synth_event(ev);

	seq_printf(m, "s:%s/", event->class.system);

	return __synth_event_show(m, event);
}

static int synth_events_seq_show(struct seq_file *m, void *v)
{
	struct dyn_event *ev = v;

	if (!is_synth_event(ev))
		return 0;

	return __synth_event_show(m, to_synth_event(ev));
}

static const struct seq_operations synth_events_seq_op = {
	.start	= dyn_event_seq_start,
	.next	= dyn_event_seq_next,
	.stop	= dyn_event_seq_stop,
	.show	= synth_events_seq_show,
};

static int synth_events_open(struct inode *inode, struct file *file)
{
	int ret;

	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
		ret = dyn_events_release_all(&synth_event_ops);
		if (ret < 0)
			return ret;
	}

	return seq_open(file, &synth_events_seq_op);
}

static ssize_t synth_events_write(struct file *file,
				  const char __user *buffer,
				  size_t count, loff_t *ppos)
{
	return trace_parse_run_command(file, buffer, count, ppos,
				       create_or_delete_synth_event);
}

static const struct file_operations synth_events_fops = {
	.open           = synth_events_open,
	.write		= synth_events_write,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = seq_release,
};

static u64 hist_field_timestamp(struct hist_field *hist_field,
				struct tracing_map_elt *elt,
				struct ring_buffer_event *rbe,
				void *event)
{
	struct hist_trigger_data *hist_data = hist_field->hist_data;
	struct trace_array *tr = hist_data->event_file->tr;

	u64 ts = ring_buffer_event_time_stamp(rbe);

	if (hist_data->attrs->ts_in_usecs && trace_clock_in_ns(tr))
		ts = ns2usecs(ts);

	return ts;
}

static u64 hist_field_cpu(struct hist_field *hist_field,
			  struct tracing_map_elt *elt,
			  struct ring_buffer_event *rbe,
			  void *event)
{
	int cpu = smp_processor_id();

	return cpu;
}

/**
 * check_field_for_var_ref - Check if a VAR_REF field references a variable
 * @hist_field: The VAR_REF field to check
 * @var_data: The hist trigger that owns the variable
 * @var_idx: The trigger variable identifier
 *
 * Check the given VAR_REF field to see whether or not it references
 * the given variable associated with the given trigger.
 *
 * Return: The VAR_REF field if it does reference the variable, NULL if not
 */
static struct hist_field *
check_field_for_var_ref(struct hist_field *hist_field,
			struct hist_trigger_data *var_data,
			unsigned int var_idx)
{
	WARN_ON(!(hist_field && hist_field->flags & HIST_FIELD_FL_VAR_REF));

	if (hist_field && hist_field->var.idx == var_idx &&
	    hist_field->var.hist_data == var_data)
		return hist_field;

	return NULL;
}

/**
 * find_var_ref - Check if a trigger has a reference to a trigger variable
 * @hist_data: The hist trigger that might have a reference to the variable
 * @var_data: The hist trigger that owns the variable
 * @var_idx: The trigger variable identifier
 *
 * Check the list of var_refs[] on the first hist trigger to see
 * whether any of them are references to the variable on the second
 * trigger.
 *
 * Return: The VAR_REF field referencing the variable if so, NULL if not
 */
static struct hist_field *find_var_ref(struct hist_trigger_data *hist_data,
				       struct hist_trigger_data *var_data,
				       unsigned int var_idx)
{
	struct hist_field *hist_field;
	unsigned int i;

	for (i = 0; i < hist_data->n_var_refs; i++) {
		hist_field = hist_data->var_refs[i];
		if (check_field_for_var_ref(hist_field, var_data, var_idx))
			return hist_field;
	}

	return NULL;
}

/**
 * find_any_var_ref - Check if there is a reference to a given trigger variable
 * @hist_data: The hist trigger
 * @var_idx: The trigger variable identifier
 *
 * Check to see whether the given variable is currently referenced by
 * any other trigger.
 *
 * The trigger the variable is defined on is explicitly excluded - the
 * assumption being that a self-reference doesn't prevent a trigger
 * from being removed.
 *
 * Return: The VAR_REF field referencing the variable if so, NULL if not
 */
static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data,
					   unsigned int var_idx)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_field *found = NULL;
	struct hist_var_data *var_data;

	list_for_each_entry(var_data, &tr->hist_vars, list) {
		if (var_data->hist_data == hist_data)
			continue;
		found = find_var_ref(var_data->hist_data, hist_data, var_idx);
		if (found)
			break;
	}

	return found;
}

/**
 * check_var_refs - Check if there is a reference to any of trigger's variables
 * @hist_data: The hist trigger
 *
 * A trigger can define one or more variables.  If any one of them is
 * currently referenced by any other trigger, this function will
 * determine that.

 * Typically used to determine whether or not a trigger can be removed
 * - if there are any references to a trigger's variables, it cannot.
 *
 * Return: True if there is a reference to any of trigger's variables
 */
static bool check_var_refs(struct hist_trigger_data *hist_data)
{
	struct hist_field *field;
	bool found = false;
	int i;

	for_each_hist_field(i, hist_data) {
		field = hist_data->fields[i];
		if (field && field->flags & HIST_FIELD_FL_VAR) {
			if (find_any_var_ref(hist_data, field->var.idx)) {
				found = true;
				break;
			}
		}
	}

	return found;
}

static struct hist_var_data *find_hist_vars(struct hist_trigger_data *hist_data)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_var_data *var_data, *found = NULL;

	list_for_each_entry(var_data, &tr->hist_vars, list) {
		if (var_data->hist_data == hist_data) {
			found = var_data;
			break;
		}
	}

	return found;
}

static bool field_has_hist_vars(struct hist_field *hist_field,
				unsigned int level)
{
	int i;

	if (level > 3)
		return false;

	if (!hist_field)
		return false;

	if (hist_field->flags & HIST_FIELD_FL_VAR ||
	    hist_field->flags & HIST_FIELD_FL_VAR_REF)
		return true;

	for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++) {
		struct hist_field *operand;

		operand = hist_field->operands[i];
		if (field_has_hist_vars(operand, level + 1))
			return true;
	}

	return false;
}

static bool has_hist_vars(struct hist_trigger_data *hist_data)
{
	struct hist_field *hist_field;
	int i;

	for_each_hist_field(i, hist_data) {
		hist_field = hist_data->fields[i];
		if (field_has_hist_vars(hist_field, 0))
			return true;
	}

	return false;
}

static int save_hist_vars(struct hist_trigger_data *hist_data)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_var_data *var_data;

	var_data = find_hist_vars(hist_data);
	if (var_data)
		return 0;

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

	var_data = kzalloc(sizeof(*var_data), GFP_KERNEL);
	if (!var_data) {
		trace_array_put(tr);
		return -ENOMEM;
	}

	var_data->hist_data = hist_data;
	list_add(&var_data->list, &tr->hist_vars);

	return 0;
}

static void remove_hist_vars(struct hist_trigger_data *hist_data)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_var_data *var_data;

	var_data = find_hist_vars(hist_data);
	if (!var_data)
		return;

	if (WARN_ON(check_var_refs(hist_data)))
		return;

	list_del(&var_data->list);

	kfree(var_data);

	trace_array_put(tr);
}

static struct hist_field *find_var_field(struct hist_trigger_data *hist_data,
					 const char *var_name)
{
	struct hist_field *hist_field, *found = NULL;
	int i;

	for_each_hist_field(i, hist_data) {
		hist_field = hist_data->fields[i];
		if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR &&
		    strcmp(hist_field->var.name, var_name) == 0) {
			found = hist_field;
			break;
		}
	}

	return found;
}

static struct hist_field *find_var(struct hist_trigger_data *hist_data,
				   struct trace_event_file *file,
				   const char *var_name)
{
	struct hist_trigger_data *test_data;
	struct event_trigger_data *test;
	struct hist_field *hist_field;

	hist_field = find_var_field(hist_data, var_name);
	if (hist_field)
		return hist_field;

	list_for_each_entry_rcu(test, &file->triggers, list) {
		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
			test_data = test->private_data;
			hist_field = find_var_field(test_data, var_name);
			if (hist_field)
				return hist_field;
		}
	}

	return NULL;
}

static struct trace_event_file *find_var_file(struct trace_array *tr,
					      char *system,
					      char *event_name,
					      char *var_name)
{
	struct hist_trigger_data *var_hist_data;
	struct hist_var_data *var_data;
	struct trace_event_file *file, *found = NULL;

	if (system)
		return find_event_file(tr, system, event_name);

	list_for_each_entry(var_data, &tr->hist_vars, list) {
		var_hist_data = var_data->hist_data;
		file = var_hist_data->event_file;
		if (file == found)
			continue;

		if (find_var_field(var_hist_data, var_name)) {
			if (found) {
				hist_err_event("Variable name not unique, need to use fully qualified name (subsys.event.var) for variable: ", system, event_name, var_name);
				return NULL;
			}

			found = file;
		}
	}

	return found;
}

static struct hist_field *find_file_var(struct trace_event_file *file,
					const char *var_name)
{
	struct hist_trigger_data *test_data;
	struct event_trigger_data *test;
	struct hist_field *hist_field;

	list_for_each_entry_rcu(test, &file->triggers, list) {
		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
			test_data = test->private_data;
			hist_field = find_var_field(test_data, var_name);
			if (hist_field)
				return hist_field;
		}
	}

	return NULL;
}

static struct hist_field *
find_match_var(struct hist_trigger_data *hist_data, char *var_name)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_field *hist_field, *found = NULL;
	struct trace_event_file *file;
	unsigned int i;

	for (i = 0; i < hist_data->n_actions; i++) {
		struct action_data *data = hist_data->actions[i];

		if (data->handler == HANDLER_ONMATCH) {
			char *system = data->match_data.event_system;
			char *event_name = data->match_data.event;

			file = find_var_file(tr, system, event_name, var_name);
			if (!file)
				continue;
			hist_field = find_file_var(file, var_name);
			if (hist_field) {
				if (found) {
					hist_err_event("Variable name not unique, need to use fully qualified name (subsys.event.var) for variable: ", system, event_name, var_name);
					return ERR_PTR(-EINVAL);
				}

				found = hist_field;
			}
		}
	}
	return found;
}

static struct hist_field *find_event_var(struct hist_trigger_data *hist_data,
					 char *system,
					 char *event_name,
					 char *var_name)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_field *hist_field = NULL;
	struct trace_event_file *file;

	if (!system || !event_name) {
		hist_field = find_match_var(hist_data, var_name);
		if (IS_ERR(hist_field))
			return NULL;
		if (hist_field)
			return hist_field;
	}

	file = find_var_file(tr, system, event_name, var_name);
	if (!file)
		return NULL;

	hist_field = find_file_var(file, var_name);

	return hist_field;
}

static u64 hist_field_var_ref(struct hist_field *hist_field,
			      struct tracing_map_elt *elt,
			      struct ring_buffer_event *rbe,
			      void *event)
{
	struct hist_elt_data *elt_data;
	u64 var_val = 0;

	elt_data = elt->private_data;
	var_val = elt_data->var_ref_vals[hist_field->var_ref_idx];

	return var_val;
}

static bool resolve_var_refs(struct hist_trigger_data *hist_data, void *key,
			     u64 *var_ref_vals, bool self)
{
	struct hist_trigger_data *var_data;
	struct tracing_map_elt *var_elt;
	struct hist_field *hist_field;
	unsigned int i, var_idx;
	bool resolved = true;
	u64 var_val = 0;

	for (i = 0; i < hist_data->n_var_refs; i++) {
		hist_field = hist_data->var_refs[i];
		var_idx = hist_field->var.idx;
		var_data = hist_field->var.hist_data;

		if (var_data == NULL) {
			resolved = false;
			break;
		}

		if ((self && var_data != hist_data) ||
		    (!self && var_data == hist_data))
			continue;

		var_elt = tracing_map_lookup(var_data->map, key);
		if (!var_elt) {
			resolved = false;
			break;
		}

		if (!tracing_map_var_set(var_elt, var_idx)) {
			resolved = false;
			break;
		}

		if (self || !hist_field->read_once)
			var_val = tracing_map_read_var(var_elt, var_idx);
		else
			var_val = tracing_map_read_var_once(var_elt, var_idx);

		var_ref_vals[i] = var_val;
	}

	return resolved;
}

static const char *hist_field_name(struct hist_field *field,
				   unsigned int level)
{
	const char *field_name = "";

	if (level > 1)
		return field_name;

	if (field->field)
		field_name = field->field->name;
	else if (field->flags & HIST_FIELD_FL_LOG2 ||
		 field->flags & HIST_FIELD_FL_ALIAS)
		field_name = hist_field_name(field->operands[0], ++level);
	else if (field->flags & HIST_FIELD_FL_CPU)
		field_name = "cpu";
	else if (field->flags & HIST_FIELD_FL_EXPR ||
		 field->flags & HIST_FIELD_FL_VAR_REF) {
		if (field->system) {
			static char full_name[MAX_FILTER_STR_VAL];

			strcat(full_name, field->system);
			strcat(full_name, ".");
			strcat(full_name, field->event_name);
			strcat(full_name, ".");
			strcat(full_name, field->name);
			field_name = full_name;
		} else
			field_name = field->name;
	} else if (field->flags & HIST_FIELD_FL_TIMESTAMP)
		field_name = "common_timestamp";

	if (field_name == NULL)
		field_name = "";

	return field_name;
}

static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
{
	hist_field_fn_t fn = NULL;

	switch (field_size) {
	case 8:
		if (field_is_signed)
			fn = hist_field_s64;
		else
			fn = hist_field_u64;
		break;
	case 4:
		if (field_is_signed)
			fn = hist_field_s32;
		else
			fn = hist_field_u32;
		break;
	case 2:
		if (field_is_signed)
			fn = hist_field_s16;
		else
			fn = hist_field_u16;
		break;
	case 1:
		if (field_is_signed)
			fn = hist_field_s8;
		else
			fn = hist_field_u8;
		break;
	}

	return fn;
}

static int parse_map_size(char *str)
{
	unsigned long size, map_bits;
	int ret;

	strsep(&str, "=");
	if (!str) {
		ret = -EINVAL;
		goto out;
	}

	ret = kstrtoul(str, 0, &size);
	if (ret)
		goto out;

	map_bits = ilog2(roundup_pow_of_two(size));
	if (map_bits < TRACING_MAP_BITS_MIN ||
	    map_bits > TRACING_MAP_BITS_MAX)
		ret = -EINVAL;
	else
		ret = map_bits;
 out:
	return ret;
}

static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
{
	unsigned int i;

	if (!attrs)
		return;

	for (i = 0; i < attrs->n_assignments; i++)
		kfree(attrs->assignment_str[i]);

	for (i = 0; i < attrs->n_actions; i++)
		kfree(attrs->action_str[i]);

	kfree(attrs->name);
	kfree(attrs->sort_key_str);
	kfree(attrs->keys_str);
	kfree(attrs->vals_str);
	kfree(attrs->clock);
	kfree(attrs);
}

static int parse_action(char *str, struct hist_trigger_attrs *attrs)
{
	int ret = -EINVAL;

	if (attrs->n_actions >= HIST_ACTIONS_MAX)
		return ret;

	if ((str_has_prefix(str, "onmatch(")) ||
	    (str_has_prefix(str, "onmax(")) ||
	    (str_has_prefix(str, "onchange("))) {
		attrs->action_str[attrs->n_actions] = kstrdup(str, GFP_KERNEL);
		if (!attrs->action_str[attrs->n_actions]) {
			ret = -ENOMEM;
			return ret;
		}
		attrs->n_actions++;
		ret = 0;
	}

	return ret;
}

static int parse_assignment(char *str, struct hist_trigger_attrs *attrs)
{
	int ret = 0;

	if ((str_has_prefix(str, "key=")) ||
	    (str_has_prefix(str, "keys="))) {
		attrs->keys_str = kstrdup(str, GFP_KERNEL);
		if (!attrs->keys_str) {
			ret = -ENOMEM;
			goto out;
		}
	} else if ((str_has_prefix(str, "val=")) ||
		   (str_has_prefix(str, "vals=")) ||
		   (str_has_prefix(str, "values="))) {
		attrs->vals_str = kstrdup(str, GFP_KERNEL);
		if (!attrs->vals_str) {
			ret = -ENOMEM;
			goto out;
		}
	} else if (str_has_prefix(str, "sort=")) {
		attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
		if (!attrs->sort_key_str) {
			ret = -ENOMEM;
			goto out;
		}
	} else if (str_has_prefix(str, "name=")) {
		attrs->name = kstrdup(str, GFP_KERNEL);
		if (!attrs->name) {
			ret = -ENOMEM;
			goto out;
		}
	} else if (str_has_prefix(str, "clock=")) {
		strsep(&str, "=");
		if (!str) {
			ret = -EINVAL;
			goto out;
		}

		str = strstrip(str);
		attrs->clock = kstrdup(str, GFP_KERNEL);
		if (!attrs->clock) {
			ret = -ENOMEM;
			goto out;
		}
	} else if (str_has_prefix(str, "size=")) {
		int map_bits = parse_map_size(str);

		if (map_bits < 0) {
			ret = map_bits;
			goto out;
		}
		attrs->map_bits = map_bits;
	} else {
		char *assignment;

		if (attrs->n_assignments == TRACING_MAP_VARS_MAX) {
			hist_err("Too many variables defined: ", str);
			ret = -EINVAL;
			goto out;
		}

		assignment = kstrdup(str, GFP_KERNEL);
		if (!assignment) {
			ret = -ENOMEM;
			goto out;
		}

		attrs->assignment_str[attrs->n_assignments++] = assignment;
	}
 out:
	return ret;
}

static struct hist_trigger_attrs *parse_hist_trigger_attrs(char *trigger_str)
{
	struct hist_trigger_attrs *attrs;
	int ret = 0;

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

	while (trigger_str) {
		char *str = strsep(&trigger_str, ":");

		if (strchr(str, '=')) {
			ret = parse_assignment(str, attrs);
			if (ret)
				goto free;
		} else if (strcmp(str, "pause") == 0)
			attrs->pause = true;
		else if ((strcmp(str, "cont") == 0) ||
			 (strcmp(str, "continue") == 0))
			attrs->cont = true;
		else if (strcmp(str, "clear") == 0)
			attrs->clear = true;
		else {
			ret = parse_action(str, attrs);
			if (ret)
				goto free;
		}
	}

	if (!attrs->keys_str) {
		ret = -EINVAL;
		goto free;
	}

	if (!attrs->clock) {
		attrs->clock = kstrdup("global", GFP_KERNEL);
		if (!attrs->clock) {
			ret = -ENOMEM;
			goto free;
		}
	}

	return attrs;
 free:
	destroy_hist_trigger_attrs(attrs);

	return ERR_PTR(ret);
}

static inline void save_comm(char *comm, struct task_struct *task)
{
	if (!task->pid) {
		strcpy(comm, "<idle>");
		return;
	}

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

	strncpy(comm, task->comm, TASK_COMM_LEN);
}

static void hist_elt_data_free(struct hist_elt_data *elt_data)
{
	unsigned int i;

	for (i = 0; i < SYNTH_FIELDS_MAX; i++)
		kfree(elt_data->field_var_str[i]);

	kfree(elt_data->comm);
	kfree(elt_data);
}

static void hist_trigger_elt_data_free(struct tracing_map_elt *elt)
{
	struct hist_elt_data *elt_data = elt->private_data;

	hist_elt_data_free(elt_data);
}

static int hist_trigger_elt_data_alloc(struct tracing_map_elt *elt)
{
	struct hist_trigger_data *hist_data = elt->map->private_data;
	unsigned int size = TASK_COMM_LEN;
	struct hist_elt_data *elt_data;
	struct hist_field *key_field;
	unsigned int i, n_str;

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

	for_each_hist_key_field(i, hist_data) {
		key_field = hist_data->fields[i];

		if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
			elt_data->comm = kzalloc(size, GFP_KERNEL);
			if (!elt_data->comm) {
				kfree(elt_data);
				return -ENOMEM;
			}
			break;
		}
	}

	n_str = hist_data->n_field_var_str + hist_data->n_save_var_str;

	size = STR_VAR_LEN_MAX;

	for (i = 0; i < n_str; i++) {
		elt_data->field_var_str[i] = kzalloc(size, GFP_KERNEL);
		if (!elt_data->field_var_str[i]) {
			hist_elt_data_free(elt_data);
			return -ENOMEM;
		}
	}

	elt->private_data = elt_data;

	return 0;
}

static void hist_trigger_elt_data_init(struct tracing_map_elt *elt)
{
	struct hist_elt_data *elt_data = elt->private_data;

	if (elt_data->comm)
		save_comm(elt_data->comm, current);
}

static const struct tracing_map_ops hist_trigger_elt_data_ops = {
	.elt_alloc	= hist_trigger_elt_data_alloc,
	.elt_free	= hist_trigger_elt_data_free,
	.elt_init	= hist_trigger_elt_data_init,
};

static const char *get_hist_field_flags(struct hist_field *hist_field)
{
	const char *flags_str = NULL;

	if (hist_field->flags & HIST_FIELD_FL_HEX)
		flags_str = "hex";
	else if (hist_field->flags & HIST_FIELD_FL_SYM)
		flags_str = "sym";
	else if (hist_field->flags & HIST_FIELD_FL_SYM_OFFSET)
		flags_str = "sym-offset";
	else if (hist_field->flags & HIST_FIELD_FL_EXECNAME)
		flags_str = "execname";
	else if (hist_field->flags & HIST_FIELD_FL_SYSCALL)
		flags_str = "syscall";
	else if (hist_field->flags & HIST_FIELD_FL_LOG2)
		flags_str = "log2";
	else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP_USECS)
		flags_str = "usecs";

	return flags_str;
}

static void expr_field_str(struct hist_field *field, char *expr)
{
	if (field->flags & HIST_FIELD_FL_VAR_REF)
		strcat(expr, "$");

	strcat(expr, hist_field_name(field, 0));

	if (field->flags && !(field->flags & HIST_FIELD_FL_VAR_REF)) {
		const char *flags_str = get_hist_field_flags(field);

		if (flags_str) {
			strcat(expr, ".");
			strcat(expr, flags_str);
		}
	}
}

static char *expr_str(struct hist_field *field, unsigned int level)
{
	char *expr;

	if (level > 1)
		return NULL;

	expr = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL);
	if (!expr)
		return NULL;

	if (!field->operands[0]) {
		expr_field_str(field, expr);
		return expr;
	}

	if (field->operator == FIELD_OP_UNARY_MINUS) {
		char *subexpr;

		strcat(expr, "-(");
		subexpr = expr_str(field->operands[0], ++level);
		if (!subexpr) {
			kfree(expr);
			return NULL;
		}
		strcat(expr, subexpr);
		strcat(expr, ")");

		kfree(subexpr);

		return expr;
	}

	expr_field_str(field->operands[0], expr);

	switch (field->operator) {
	case FIELD_OP_MINUS:
		strcat(expr, "-");
		break;
	case FIELD_OP_PLUS:
		strcat(expr, "+");
		break;
	default:
		kfree(expr);
		return NULL;
	}

	expr_field_str(field->operands[1], expr);

	return expr;
}

static int contains_operator(char *str)
{
	enum field_op_id field_op = FIELD_OP_NONE;
	char *op;

	op = strpbrk(str, "+-");
	if (!op)
		return FIELD_OP_NONE;

	switch (*op) {
	case '-':
		if (*str == '-')
			field_op = FIELD_OP_UNARY_MINUS;
		else
			field_op = FIELD_OP_MINUS;
		break;
	case '+':
		field_op = FIELD_OP_PLUS;
		break;
	default:
		break;
	}

	return field_op;
}

static void __destroy_hist_field(struct hist_field *hist_field)
{
	kfree(hist_field->var.name);
	kfree(hist_field->name);
	kfree(hist_field->type);

	kfree(hist_field);
}

static void destroy_hist_field(struct hist_field *hist_field,
			       unsigned int level)
{
	unsigned int i;

	if (level > 3)
		return;

	if (!hist_field)
		return;

	if (hist_field->flags & HIST_FIELD_FL_VAR_REF)
		return; /* var refs will be destroyed separately */

	for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++)
		destroy_hist_field(hist_field->operands[i], level + 1);

	__destroy_hist_field(hist_field);
}

static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
					    struct ftrace_event_field *field,
					    unsigned long flags,
					    char *var_name)
{
	struct hist_field *hist_field;

	if (field && is_function_field(field))
		return NULL;

	hist_field = kzalloc(sizeof(struct hist_field), GFP_KERNEL);
	if (!hist_field)
		return NULL;

	hist_field->hist_data = hist_data;

	if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
		goto out; /* caller will populate */

	if (flags & HIST_FIELD_FL_VAR_REF) {
		hist_field->fn = hist_field_var_ref;
		goto out;
	}

	if (flags & HIST_FIELD_FL_HITCOUNT) {
		hist_field->fn = hist_field_counter;
		hist_field->size = sizeof(u64);
		hist_field->type = kstrdup("u64", GFP_KERNEL);
		if (!hist_field->type)
			goto free;
		goto out;
	}

	if (flags & HIST_FIELD_FL_STACKTRACE) {
		hist_field->fn = hist_field_none;
		goto out;
	}

	if (flags & HIST_FIELD_FL_LOG2) {
		unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
		hist_field->fn = hist_field_log2;
		hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
		hist_field->size = hist_field->operands[0]->size;
		hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL);
		if (!hist_field->type)
			goto free;
		goto out;
	}

	if (flags & HIST_FIELD_FL_TIMESTAMP) {
		hist_field->fn = hist_field_timestamp;
		hist_field->size = sizeof(u64);
		hist_field->type = kstrdup("u64", GFP_KERNEL);
		if (!hist_field->type)
			goto free;
		goto out;
	}

	if (flags & HIST_FIELD_FL_CPU) {
		hist_field->fn = hist_field_cpu;
		hist_field->size = sizeof(int);
		hist_field->type = kstrdup("unsigned int", GFP_KERNEL);
		if (!hist_field->type)
			goto free;
		goto out;
	}

	if (WARN_ON_ONCE(!field))
		goto out;

	if (is_string_field(field)) {
		flags |= HIST_FIELD_FL_STRING;

		hist_field->size = MAX_FILTER_STR_VAL;
		hist_field->type = kstrdup(field->type, GFP_KERNEL);
		if (!hist_field->type)
			goto free;

		if (field->filter_type == FILTER_STATIC_STRING)
			hist_field->fn = hist_field_string;
		else if (field->filter_type == FILTER_DYN_STRING)
			hist_field->fn = hist_field_dynstring;
		else
			hist_field->fn = hist_field_pstring;
	} else {
		hist_field->size = field->size;
		hist_field->is_signed = field->is_signed;
		hist_field->type = kstrdup(field->type, GFP_KERNEL);
		if (!hist_field->type)
			goto free;

		hist_field->fn = select_value_fn(field->size,
						 field->is_signed);
		if (!hist_field->fn) {
			destroy_hist_field(hist_field, 0);
			return NULL;
		}
	}
 out:
	hist_field->field = field;
	hist_field->flags = flags;

	if (var_name) {
		hist_field->var.name = kstrdup(var_name, GFP_KERNEL);
		if (!hist_field->var.name)
			goto free;
	}

	return hist_field;
 free:
	destroy_hist_field(hist_field, 0);
	return NULL;
}

static void destroy_hist_fields(struct hist_trigger_data *hist_data)
{
	unsigned int i;

	for (i = 0; i < HIST_FIELDS_MAX; i++) {
		if (hist_data->fields[i]) {
			destroy_hist_field(hist_data->fields[i], 0);
			hist_data->fields[i] = NULL;
		}
	}

	for (i = 0; i < hist_data->n_var_refs; i++) {
		WARN_ON(!(hist_data->var_refs[i]->flags & HIST_FIELD_FL_VAR_REF));
		__destroy_hist_field(hist_data->var_refs[i]);
		hist_data->var_refs[i] = NULL;
	}
}

static int init_var_ref(struct hist_field *ref_field,
			struct hist_field *var_field,
			char *system, char *event_name)
{
	int err = 0;

	ref_field->var.idx = var_field->var.idx;
	ref_field->var.hist_data = var_field->hist_data;
	ref_field->size = var_field->size;
	ref_field->is_signed = var_field->is_signed;
	ref_field->flags |= var_field->flags &
		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);

	if (system) {
		ref_field->system = kstrdup(system, GFP_KERNEL);
		if (!ref_field->system)
			return -ENOMEM;
	}

	if (event_name) {
		ref_field->event_name = kstrdup(event_name, GFP_KERNEL);
		if (!ref_field->event_name) {
			err = -ENOMEM;
			goto free;
		}
	}

	if (var_field->var.name) {
		ref_field->name = kstrdup(var_field->var.name, GFP_KERNEL);
		if (!ref_field->name) {
			err = -ENOMEM;
			goto free;
		}
	} else if (var_field->name) {
		ref_field->name = kstrdup(var_field->name, GFP_KERNEL);
		if (!ref_field->name) {
			err = -ENOMEM;
			goto free;
		}
	}

	ref_field->type = kstrdup(var_field->type, GFP_KERNEL);
	if (!ref_field->type) {
		err = -ENOMEM;
		goto free;
	}
 out:
	return err;
 free:
	kfree(ref_field->system);
	kfree(ref_field->event_name);
	kfree(ref_field->name);

	goto out;
}

/**
 * create_var_ref - Create a variable reference and attach it to trigger
 * @hist_data: The trigger that will be referencing the variable
 * @var_field: The VAR field to create a reference to
 * @system: The optional system string
 * @event_name: The optional event_name string
 *
 * Given a variable hist_field, create a VAR_REF hist_field that
 * represents a reference to it.
 *
 * This function also adds the reference to the trigger that
 * now references the variable.
 *
 * Return: The VAR_REF field if successful, NULL if not
 */
static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
					 struct hist_field *var_field,
					 char *system, char *event_name)
{
	unsigned long flags = HIST_FIELD_FL_VAR_REF;
	struct hist_field *ref_field;

	ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
	if (ref_field) {
		if (init_var_ref(ref_field, var_field, system, event_name)) {
			destroy_hist_field(ref_field, 0);
			return NULL;
		}

		hist_data->var_refs[hist_data->n_var_refs] = ref_field;
		ref_field->var_ref_idx = hist_data->n_var_refs++;
	}

	return ref_field;
}

static bool is_var_ref(char *var_name)
{
	if (!var_name || strlen(var_name) < 2 || var_name[0] != '$')
		return false;

	return true;
}

static char *field_name_from_var(struct hist_trigger_data *hist_data,
				 char *var_name)
{
	char *name, *field;
	unsigned int i;

	for (i = 0; i < hist_data->attrs->var_defs.n_vars; i++) {
		name = hist_data->attrs->var_defs.name[i];

		if (strcmp(var_name, name) == 0) {
			field = hist_data->attrs->var_defs.expr[i];
			if (contains_operator(field) || is_var_ref(field))
				continue;
			return field;
		}
	}

	return NULL;
}

static char *local_field_var_ref(struct hist_trigger_data *hist_data,
				 char *system, char *event_name,
				 char *var_name)
{
	struct trace_event_call *call;

	if (system && event_name) {
		call = hist_data->event_file->event_call;

		if (strcmp(system, call->class->system) != 0)
			return NULL;

		if (strcmp(event_name, trace_event_name(call)) != 0)
			return NULL;
	}

	if (!!system != !!event_name)
		return NULL;

	if (!is_var_ref(var_name))
		return NULL;

	var_name++;

	return field_name_from_var(hist_data, var_name);
}

static struct hist_field *parse_var_ref(struct hist_trigger_data *hist_data,
					char *system, char *event_name,
					char *var_name)
{
	struct hist_field *var_field = NULL, *ref_field = NULL;

	if (!is_var_ref(var_name))
		return NULL;

	var_name++;

	var_field = find_event_var(hist_data, system, event_name, var_name);
	if (var_field)
		ref_field = create_var_ref(hist_data, var_field,
					   system, event_name);

	if (!ref_field)
		hist_err_event("Couldn't find variable: $",
			       system, event_name, var_name);

	return ref_field;
}

static struct ftrace_event_field *
parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
	    char *field_str, unsigned long *flags)
{
	struct ftrace_event_field *field = NULL;
	char *field_name, *modifier, *str;

	modifier = str = kstrdup(field_str, GFP_KERNEL);
	if (!modifier)
		return ERR_PTR(-ENOMEM);

	field_name = strsep(&modifier, ".");
	if (modifier) {
		if (strcmp(modifier, "hex") == 0)
			*flags |= HIST_FIELD_FL_HEX;
		else if (strcmp(modifier, "sym") == 0)
			*flags |= HIST_FIELD_FL_SYM;
		else if (strcmp(modifier, "sym-offset") == 0)
			*flags |= HIST_FIELD_FL_SYM_OFFSET;
		else if ((strcmp(modifier, "execname") == 0) &&
			 (strcmp(field_name, "common_pid") == 0))
			*flags |= HIST_FIELD_FL_EXECNAME;
		else if (strcmp(modifier, "syscall") == 0)
			*flags |= HIST_FIELD_FL_SYSCALL;
		else if (strcmp(modifier, "log2") == 0)
			*flags |= HIST_FIELD_FL_LOG2;
		else if (strcmp(modifier, "usecs") == 0)
			*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
		else {
			hist_err("Invalid field modifier: ", modifier);
			field = ERR_PTR(-EINVAL);
			goto out;
		}
	}

	if (strcmp(field_name, "common_timestamp") == 0) {
		*flags |= HIST_FIELD_FL_TIMESTAMP;
		hist_data->enable_timestamps = true;
		if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
			hist_data->attrs->ts_in_usecs = true;
	} else if (strcmp(field_name, "cpu") == 0)
		*flags |= HIST_FIELD_FL_CPU;
	else {
		field = trace_find_event_field(file->event_call, field_name);
		if (!field || !field->size) {
			hist_err("Couldn't find field: ", field_name);
			field = ERR_PTR(-EINVAL);
			goto out;
		}
	}
 out:
	kfree(str);

	return field;
}

static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
				       struct hist_field *var_ref,
				       char *var_name)
{
	struct hist_field *alias = NULL;
	unsigned long flags = HIST_FIELD_FL_ALIAS | HIST_FIELD_FL_VAR;

	alias = create_hist_field(hist_data, NULL, flags, var_name);
	if (!alias)
		return NULL;

	alias->fn = var_ref->fn;
	alias->operands[0] = var_ref;

	if (init_var_ref(alias, var_ref, var_ref->system, var_ref->event_name)) {
		destroy_hist_field(alias, 0);
		return NULL;
	}

	return alias;
}

static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
				     struct trace_event_file *file, char *str,
				     unsigned long *flags, char *var_name)
{
	char *s, *ref_system = NULL, *ref_event = NULL, *ref_var = str;
	struct ftrace_event_field *field = NULL;
	struct hist_field *hist_field = NULL;
	int ret = 0;

	s = strchr(str, '.');
	if (s) {
		s = strchr(++s, '.');
		if (s) {
			ref_system = strsep(&str, ".");
			if (!str) {
				ret = -EINVAL;
				goto out;
			}
			ref_event = strsep(&str, ".");
			if (!str) {
				ret = -EINVAL;
				goto out;
			}
			ref_var = str;
		}
	}

	s = local_field_var_ref(hist_data, ref_system, ref_event, ref_var);
	if (!s) {
		hist_field = parse_var_ref(hist_data, ref_system, ref_event, ref_var);
		if (hist_field) {
			if (var_name) {
				hist_field = create_alias(hist_data, hist_field, var_name);
				if (!hist_field) {
					ret = -ENOMEM;
					goto out;
				}
			}
			return hist_field;
		}
	} else
		str = s;

	field = parse_field(hist_data, file, str, flags);
	if (IS_ERR(field)) {
		ret = PTR_ERR(field);
		goto out;
	}

	hist_field = create_hist_field(hist_data, field, *flags, var_name);
	if (!hist_field) {
		ret = -ENOMEM;
		goto out;
	}

	return hist_field;
 out:
	return ERR_PTR(ret);
}

static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
				     struct trace_event_file *file,
				     char *str, unsigned long flags,
				     char *var_name, unsigned int level);

static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
				      struct trace_event_file *file,
				      char *str, unsigned long flags,
				      char *var_name, unsigned int level)
{
	struct hist_field *operand1, *expr = NULL;
	unsigned long operand_flags;
	int ret = 0;
	char *s;

	/* we support only -(xxx) i.e. explicit parens required */

	if (level > 3) {
		hist_err("Too many subexpressions (3 max): ", str);
		ret = -EINVAL;
		goto free;
	}

	str++; /* skip leading '-' */

	s = strchr(str, '(');
	if (s)
		str++;
	else {
		ret = -EINVAL;
		goto free;
	}

	s = strrchr(str, ')');
	if (s)
		*s = '\0';
	else {
		ret = -EINVAL; /* no closing ')' */
		goto free;
	}

	flags |= HIST_FIELD_FL_EXPR;
	expr = create_hist_field(hist_data, NULL, flags, var_name);
	if (!expr) {
		ret = -ENOMEM;
		goto free;
	}

	operand_flags = 0;
	operand1 = parse_expr(hist_data, file, str, operand_flags, NULL, ++level);
	if (IS_ERR(operand1)) {
		ret = PTR_ERR(operand1);
		goto free;
	}

	expr->flags |= operand1->flags &
		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
	expr->fn = hist_field_unary_minus;
	expr->operands[0] = operand1;
	expr->operator = FIELD_OP_UNARY_MINUS;
	expr->name = expr_str(expr, 0);
	expr->type = kstrdup(operand1->type, GFP_KERNEL);
	if (!expr->type) {
		ret = -ENOMEM;
		goto free;
	}

	return expr;
 free:
	destroy_hist_field(expr, 0);
	return ERR_PTR(ret);
}

static int check_expr_operands(struct hist_field *operand1,
			       struct hist_field *operand2)
{
	unsigned long operand1_flags = operand1->flags;
	unsigned long operand2_flags = operand2->flags;

	if ((operand1_flags & HIST_FIELD_FL_VAR_REF) ||
	    (operand1_flags & HIST_FIELD_FL_ALIAS)) {
		struct hist_field *var;

		var = find_var_field(operand1->var.hist_data, operand1->name);
		if (!var)
			return -EINVAL;
		operand1_flags = var->flags;
	}

	if ((operand2_flags & HIST_FIELD_FL_VAR_REF) ||
	    (operand2_flags & HIST_FIELD_FL_ALIAS)) {
		struct hist_field *var;

		var = find_var_field(operand2->var.hist_data, operand2->name);
		if (!var)
			return -EINVAL;
		operand2_flags = var->flags;
	}

	if ((operand1_flags & HIST_FIELD_FL_TIMESTAMP_USECS) !=
	    (operand2_flags & HIST_FIELD_FL_TIMESTAMP_USECS)) {
		hist_err("Timestamp units in expression don't match", NULL);
		return -EINVAL;
	}

	return 0;
}

static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
				     struct trace_event_file *file,
				     char *str, unsigned long flags,
				     char *var_name, unsigned int level)
{
	struct hist_field *operand1 = NULL, *operand2 = NULL, *expr = NULL;
	unsigned long operand_flags;
	int field_op, ret = -EINVAL;
	char *sep, *operand1_str;

	if (level > 3) {
		hist_err("Too many subexpressions (3 max): ", str);
		return ERR_PTR(-EINVAL);
	}

	field_op = contains_operator(str);

	if (field_op == FIELD_OP_NONE)
		return parse_atom(hist_data, file, str, &flags, var_name);

	if (field_op == FIELD_OP_UNARY_MINUS)
		return parse_unary(hist_data, file, str, flags, var_name, ++level);

	switch (field_op) {
	case FIELD_OP_MINUS:
		sep = "-";
		break;
	case FIELD_OP_PLUS:
		sep = "+";
		break;
	default:
		goto free;
	}

	operand1_str = strsep(&str, sep);
	if (!operand1_str || !str)
		goto free;

	operand_flags = 0;
	operand1 = parse_atom(hist_data, file, operand1_str,
			      &operand_flags, NULL);
	if (IS_ERR(operand1)) {
		ret = PTR_ERR(operand1);
		operand1 = NULL;
		goto free;
	}

	/* rest of string could be another expression e.g. b+c in a+b+c */
	operand_flags = 0;
	operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, ++level);
	if (IS_ERR(operand2)) {
		ret = PTR_ERR(operand2);
		operand2 = NULL;
		goto free;
	}

	ret = check_expr_operands(operand1, operand2);
	if (ret)
		goto free;

	flags |= HIST_FIELD_FL_EXPR;

	flags |= operand1->flags &
		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);

	expr = create_hist_field(hist_data, NULL, flags, var_name);
	if (!expr) {
		ret = -ENOMEM;
		goto free;
	}

	operand1->read_once = true;
	operand2->read_once = true;

	expr->operands[0] = operand1;
	expr->operands[1] = operand2;
	expr->operator = field_op;
	expr->name = expr_str(expr, 0);
	expr->type = kstrdup(operand1->type, GFP_KERNEL);
	if (!expr->type) {
		ret = -ENOMEM;
		goto free;
	}

	switch (field_op) {
	case FIELD_OP_MINUS:
		expr->fn = hist_field_minus;
		break;
	case FIELD_OP_PLUS:
		expr->fn = hist_field_plus;
		break;
	default:
		ret = -EINVAL;
		goto free;
	}

	return expr;
 free:
	destroy_hist_field(operand1, 0);
	destroy_hist_field(operand2, 0);
	destroy_hist_field(expr, 0);

	return ERR_PTR(ret);
}

static char *find_trigger_filter(struct hist_trigger_data *hist_data,
				 struct trace_event_file *file)
{
	struct event_trigger_data *test;

	list_for_each_entry_rcu(test, &file->triggers, list) {
		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
			if (test->private_data == hist_data)
				return test->filter_str;
		}
	}

	return NULL;
}