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

/* for gfp flag names */
#include <linux/trace_events.h>
#include <trace/events/mmflags.h>

#include "tracing_map.h"
#include "trace_synth.h"

#define ERRORS								\
	C(NONE,			"No error"),				\
	C(DUPLICATE_VAR,	"Variable already defined"),		\
	C(VAR_NOT_UNIQUE,	"Variable name not unique, need to use fully qualified name (subsys.event.var) for variable"), \
	C(TOO_MANY_VARS,	"Too many variables defined"),		\
	C(MALFORMED_ASSIGNMENT,	"Malformed assignment"),		\
	C(NAMED_MISMATCH,	"Named hist trigger doesn't match existing named trigger (includes variables)"), \
	C(TRIGGER_EEXIST,	"Hist trigger already exists"),		\
	C(TRIGGER_ENOENT_CLEAR,	"Can't clear or continue a nonexistent hist trigger"), \
	C(SET_CLOCK_FAIL,	"Couldn't set trace_clock"),		\
	C(BAD_FIELD_MODIFIER,	"Invalid field modifier"),		\
	C(TOO_MANY_SUBEXPR,	"Too many subexpressions (3 max)"),	\
	C(TIMESTAMP_MISMATCH,	"Timestamp units in expression don't match"), \
	C(TOO_MANY_FIELD_VARS,	"Too many field variables defined"),	\
	C(EVENT_FILE_NOT_FOUND,	"Event file not found"),		\
	C(HIST_NOT_FOUND,	"Matching event histogram not found"),	\
	C(HIST_CREATE_FAIL,	"Couldn't create histogram for field"),	\
	C(SYNTH_VAR_NOT_FOUND,	"Couldn't find synthetic variable"),	\
	C(SYNTH_EVENT_NOT_FOUND,"Couldn't find synthetic event"),	\
	C(SYNTH_TYPE_MISMATCH,	"Param type doesn't match synthetic event field type"), \
	C(SYNTH_COUNT_MISMATCH,	"Param count doesn't match synthetic event field count"), \
	C(FIELD_VAR_PARSE_FAIL,	"Couldn't parse field variable"),	\
	C(VAR_CREATE_FIND_FAIL,	"Couldn't create or find variable"),	\
	C(ONX_NOT_VAR,		"For onmax(x) or onchange(x), x must be a variable"), \
	C(ONX_VAR_NOT_FOUND,	"Couldn't find onmax or onchange variable"), \
	C(ONX_VAR_CREATE_FAIL,	"Couldn't create onmax or onchange variable"), \
	C(FIELD_VAR_CREATE_FAIL,"Couldn't create field variable"),	\
	C(TOO_MANY_PARAMS,	"Too many action params"),		\
	C(PARAM_NOT_FOUND,	"Couldn't find param"),			\
	C(INVALID_PARAM,	"Invalid action param"),		\
	C(ACTION_NOT_FOUND,	"No action found"),			\
	C(NO_SAVE_PARAMS,	"No params found for save()"),		\
	C(TOO_MANY_SAVE_ACTIONS,"Can't have more than one save() action per hist"), \
	C(ACTION_MISMATCH,	"Handler doesn't support action"),	\
	C(NO_CLOSING_PAREN,	"No closing paren found"),		\
	C(SUBSYS_NOT_FOUND,	"Missing subsystem"),			\
	C(INVALID_SUBSYS_EVENT,	"Invalid subsystem or event name"),	\
	C(INVALID_REF_KEY,	"Using variable references in keys not supported"), \
	C(VAR_NOT_FOUND,	"Couldn't find variable"),		\
	C(FIELD_NOT_FOUND,	"Couldn't find field"),			\
	C(EMPTY_ASSIGNMENT,	"Empty assignment"),			\
	C(INVALID_SORT_MODIFIER,"Invalid sort modifier"),		\
	C(EMPTY_SORT_FIELD,	"Empty sort field"),			\
	C(TOO_MANY_SORT_FIELDS,	"Too many sort fields (Max = 2)"),	\
	C(INVALID_SORT_FIELD,	"Sort field must be a key or a val"),	\
	C(INVALID_STR_OPERAND,	"String type can not be an operand in expression"), \
	C(EXPECT_NUMBER,	"Expecting numeric literal"),		\
	C(UNARY_MINUS_SUBEXPR,	"Unary minus not supported in sub-expressions"), \
	C(DIVISION_BY_ZERO,	"Division by zero"),

#undef C
#define C(a, b)		HIST_ERR_##a

enum { ERRORS };

#undef C
#define C(a, b)		b

static const char *err_text[] = { ERRORS };

struct hist_field;

typedef u64 (*hist_field_fn_t) (struct hist_field *field,
				struct tracing_map_elt *elt,
				struct trace_buffer *buffer,
				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
#define HIST_CONST_DIGITS_MAX	21
#define HIST_DIV_SHIFT		20  /* For optimizing division by constants */

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

/*
 * 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			ref;
	unsigned int			size;
	unsigned int			offset;
	unsigned int                    is_signed;
	unsigned long			buckets;
	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;

	unsigned int			var_str_idx;

	/* Numeric literals are represented as u64 */
	u64				constant;
	/* Used to optimize division by constants */
	u64				div_multiplier;
};

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

static u64 hist_field_const(struct hist_field *field,
			   struct tracing_map_elt *elt,
			   struct trace_buffer *buffer,
			   struct ring_buffer_event *rbe,
			   void *event)
{
	return field->constant;
}

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

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

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

static u64 hist_field_bucket(struct hist_field *hist_field,
			     struct tracing_map_elt *elt,
			     struct trace_buffer *buffer,
			     struct ring_buffer_event *rbe,
			     void *event)
{
	struct hist_field *operand = hist_field->operands[0];
	unsigned long buckets = hist_field->buckets;

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

	if (WARN_ON_ONCE(!buckets))
		return val;

	if (val >= LONG_MAX)
		val = div64_ul(val, buckets);
	else
		val = (u64)((unsigned long)val / buckets);
	return val * buckets;
}

static u64 hist_field_plus(struct hist_field *hist_field,
			   struct tracing_map_elt *elt,
			   struct trace_buffer *buffer,
			   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, buffer, rbe, event);
	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);

	return val1 + val2;
}

static u64 hist_field_minus(struct hist_field *hist_field,
			    struct tracing_map_elt *elt,
			    struct trace_buffer *buffer,
			    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, buffer, rbe, event);
	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);

	return val1 - val2;
}

static u64 hist_field_div(struct hist_field *hist_field,
			   struct tracing_map_elt *elt,
			   struct trace_buffer *buffer,
			   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, buffer, rbe, event);
	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);

	/* Return -1 for the undefined case */
	if (!val2)
		return -1;

	/* Use shift if the divisor is a power of 2 */
	if (!(val2 & (val2 - 1)))
		return val1 >> __ffs64(val2);

	return div64_u64(val1, val2);
}

static u64 div_by_power_of_two(struct hist_field *hist_field,
				struct tracing_map_elt *elt,
				struct trace_buffer *buffer,
				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, buffer, rbe, event);

	return val1 >> __ffs64(operand2->constant);
}

static u64 div_by_not_power_of_two(struct hist_field *hist_field,
				struct tracing_map_elt *elt,
				struct trace_buffer *buffer,
				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, buffer, rbe, event);

	return div64_u64(val1, operand2->constant);
}

static u64 div_by_mult_and_shift(struct hist_field *hist_field,
				struct tracing_map_elt *elt,
				struct trace_buffer *buffer,
				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, buffer, rbe, event);

	/*
	 * If the divisor is a constant, do a multiplication and shift instead.
	 *
	 * Choose Z = some power of 2. If Y <= Z, then:
	 *     X / Y = (X * (Z / Y)) / Z
	 *
	 * (Z / Y) is a constant (mult) which is calculated at parse time, so:
	 *     X / Y = (X * mult) / Z
	 *
	 * The division by Z can be replaced by a shift since Z is a power of 2:
	 *     X / Y = (X * mult) >> HIST_DIV_SHIFT
	 *
	 * As long, as X < Z the results will not be off by more than 1.
	 */
	if (val1 < (1 << HIST_DIV_SHIFT)) {
		u64 mult = operand2->div_multiplier;

		return (val1 * mult + ((1 << HIST_DIV_SHIFT) - 1)) >> HIST_DIV_SHIFT;
	}

	return div64_u64(val1, operand2->constant);
}

static u64 hist_field_mult(struct hist_field *hist_field,
			   struct tracing_map_elt *elt,
			   struct trace_buffer *buffer,
			   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, buffer, rbe, event);
	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);

	return val1 * val2;
}

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

	s64 sval = (s64)operand->fn(operand, elt, buffer, 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 trace_buffer *buffer,	\
				     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,
	HIST_FIELD_FL_BUCKET		= 1 << 17,
	HIST_FIELD_FL_CONST		= 1 << 18,
};

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			n_var_str;
	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;
};

struct action_data;

typedef void (*action_fn_t) (struct hist_trigger_data *hist_data,
			     struct tracing_map_elt *elt,
			     struct trace_buffer *buffer, 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 array is an array of
	 * indices into the var_ref_vals array, one for each synthetic
	 * event param, and is passed to the synthetic event
	 * invocation.
	 */
	unsigned int		var_ref_idx[TRACING_MAP_VARS_MAX];
	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;
	int n_field_var_str;
};

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

/*
 * Returns the specific division function to use if the divisor
 * is constant. This avoids extra branches when the trigger is hit.
 */
static hist_field_fn_t hist_field_get_div_fn(struct hist_field *divisor)
{
	u64 div = divisor->constant;

	if (!(div & (div - 1)))
		return div_by_power_of_two;

	/* If the divisor is too large, do a regular division */
	if (div > (1 << HIST_DIV_SHIFT))
		return div_by_not_power_of_two;

	divisor->div_multiplier = div64_u64((u64)(1 << HIST_DIV_SHIFT), div);
	return div_by_mult_and_shift;
}

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_cmd[MAX_FILTER_STR_VAL];
static char last_cmd_loc[MAX_FILTER_STR_VAL];

static int errpos(char *str)
{
	return err_pos(last_cmd, str);
}

static void last_cmd_set(struct trace_event_file *file, char *str)
{
	const char *system = NULL, *name = NULL;
	struct trace_event_call *call;

	if (!str)
		return;

	strcpy(last_cmd, "hist:");
	strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:"));

	if (file) {
		call = file->event_call;
		system = call->class->system;
		if (system) {
			name = trace_event_name(call);
			if (!name)
				system = NULL;
		}
	}

	if (system)
		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, "hist:%s:%s", system, name);
}

static void hist_err(struct trace_array *tr, u8 err_type, u8 err_pos)
{
	tracing_log_err(tr, last_cmd_loc, last_cmd, err_text,
			err_type, err_pos);
}

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

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 void action_trace(struct hist_trigger_data *hist_data,
			 struct tracing_map_elt *elt,
			 struct trace_buffer *buffer, 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 u64 hist_field_timestamp(struct hist_field *hist_field,
				struct tracing_map_elt *elt,
				struct trace_buffer *buffer,
				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(buffer, 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 trace_buffer *buffer,
			  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 (tracing_check_open_get_tr(tr))
		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;

	lockdep_assert_held(&event_mutex);

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

	list_for_each_entry(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(tr, HIST_ERR_VAR_NOT_UNIQUE, errpos(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;

	lockdep_assert_held(&event_mutex);

	list_for_each_entry(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(tr, HIST_ERR_VAR_NOT_UNIQUE,
						 errpos(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 trace_buffer *buffer,
			      struct ring_buffer_event *rbe,
			      void *event)
{
	struct hist_elt_data *elt_data;
	u64 var_val = 0;

	if (WARN_ON_ONCE(!elt))
		return var_val;

	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->flags & HIST_FIELD_FL_BUCKET)
		field_name = hist_field_name(field->operands[0], ++level);
	else if (field->flags & HIST_FIELD_FL_CPU)
		field_name = "common_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;

	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(struct trace_array *tr,
			    char *str, struct hist_trigger_attrs *attrs)
{
	int len, ret = 0;

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

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

		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(tr, HIST_ERR_TOO_MANY_VARS, errpos(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(struct trace_array *tr, 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, ":");
		char *rhs;

		rhs = strchr(str, '=');
		if (rhs) {
			if (!strlen(++rhs)) {
				ret = -EINVAL;
				hist_err(tr, HIST_ERR_EMPTY_ASSIGNMENT, errpos(str));
				goto free;
			}
			ret = parse_assignment(tr, 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 < elt_data->n_field_var_str; i++)
		kfree(elt_data->field_var_str[i]);

	kfree(elt_data->field_var_str);

	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 *hist_field;
	unsigned int i, n_str;

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

	for_each_hist_field(i, hist_data) {
		hist_field = hist_data->fields[i];

		if (hist_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 +
		hist_data->n_var_str;
	if (n_str > SYNTH_FIELDS_MAX) {
		hist_elt_data_free(elt_data);
		return -EINVAL;
	}

	BUILD_BUG_ON(STR_VAR_LEN_MAX & (sizeof(u64) - 1));

	size = STR_VAR_LEN_MAX;

	elt_data->field_var_str = kcalloc(n_str, sizeof(char *), GFP_KERNEL);
	if (!elt_data->field_var_str) {
		hist_elt_data_free(elt_data);
		return -EINVAL;
	}
	elt_data->n_field_var_str = n_str;

	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_BUCKET)
		flags_str = "buckets";
	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, "$");
	else if (field->flags & HIST_FIELD_FL_CONST) {
		char str[HIST_CONST_DIGITS_MAX];

		snprintf(str, HIST_CONST_DIGITS_MAX, "%llu", field->constant);
		strcat(expr, str);
	}

	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;
	case FIELD_OP_DIV:
		strcat(expr, "/");
		break;
	case FIELD_OP_MULT:
		strcat(expr, "*");
		break;
	default:
		kfree(expr);
		return NULL;
	}

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

	return expr;
}

/*
 * If field_op != FIELD_OP_NONE, *sep points to the root operator
 * of the expression tree to be evaluated.
 */
static int contains_operator(char *str, char **sep)
{
	enum field_op_id field_op = FIELD_OP_NONE;
	char *minus_op, *plus_op, *div_op, *mult_op;


	/*
	 * Report the last occurrence of the operators first, so that the
	 * expression is evaluated left to right. This is important since
	 * subtraction and division are not associative.
	 *
	 *	e.g
	 *		64/8/4/2 is 1, i.e 64/8/4/2 = ((64/8)/4)/2
	 *		14-7-5-2 is 0, i.e 14-7-5-2 = ((14-7)-5)-2
	 */

	/*
	 * First, find lower precedence addition and subtraction
	 * since the expression will be evaluated recursively.
	 */
	minus_op = strrchr(str, '-');
	if (minus_op) {
		/*
		 * Unary minus is not supported in sub-expressions. If
		 * present, it is always the next root operator.
		 */
		if (minus_op == str) {
			field_op = FIELD_OP_UNARY_MINUS;
			goto out;
		}

		field_op = FIELD_OP_MINUS;
	}

	plus_op = strrchr(str, '+');
	if (plus_op || minus_op) {
		/*
		 * For operators of the same precedence use to rightmost as the
		 * root, so that the expression is evaluated left to right.
		 */
		if (plus_op > minus_op)
			field_op = FIELD_OP_PLUS;
		goto out;
	}

	/*
	 * Multiplication and division have higher precedence than addition and
	 * subtraction.
	 */
	div_op = strrchr(str, '/');
	if (div_op)
		field_op = FIELD_OP_DIV;

	mult_op = strrchr(str, '*');
	/*
	 * For operators of the same precedence use to rightmost as the
	 * root, so that the expression is evaluated left to right.
	 */
	if (mult_op > div_op)
		field_op = FIELD_OP_MULT;

out:
	if (sep) {
		switch (field_op) {
		case FIELD_OP_UNARY_MINUS:
		case FIELD_OP_MINUS:
			*sep = minus_op;
			break;
		case FIELD_OP_PLUS:
			*sep = plus_op;
			break;
		case FIELD_OP_DIV:
			*sep = div_op;
			break;
		case FIELD_OP_MULT:
			*sep = mult_op;
			break;
		case FIELD_OP_NONE:
		default:
			*sep = NULL;
			break;
		}
	}

	return field_op;
}

static void get_hist_field(struct hist_field *hist_field)
{
	hist_field->ref++;
}

static void __destroy_hist_field(struct hist_field *hist_field)
{
	if (--hist_field->ref > 1)
		return;

	kfree(hist_field->var.name);
	kfree(hist_field->name);

	/* Can likely be a const */
	kfree_const(hist_field->type);

	kfree(hist_field->system);
	kfree(hist_field->event_name);

	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->ref = 1;

	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 = "u64";
		goto out;
	}

	if (flags & HIST_FIELD_FL_CONST) {
		hist_field->fn = hist_field_const;
		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 | HIST_FIELD_FL_BUCKET)) {
		unsigned long fl = flags & ~(HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET);
		hist_field->fn = flags & HIST_FIELD_FL_LOG2 ? hist_field_log2 :
			hist_field_bucket;
		hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
		hist_field->size = hist_field->operands[0]->size;
		hist_field->type = kstrdup_const(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 = "u64";
		goto out;
	}

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

	if (WARN_ON_ONCE(!field))
		goto out;

	/* Pointers to strings are just pointers and dangerous to dereference */
	if (is_string_field(field) &&
	    (field->filter_type != FILTER_PTR_STRING)) {
		flags |= HIST_FIELD_FL_STRING;

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

		if (field->filter_type == FILTER_STATIC_STRING) {
			hist_field->fn = hist_field_string;
			hist_field->size = field->size;
		} 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_const(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_const(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;
}

static int find_var_ref_idx(struct hist_trigger_data *hist_data,
			    struct hist_field *var_field)
{
	struct hist_field *ref_field;
	int i;

	for (i = 0; i < hist_data->n_var_refs; i++) {
		ref_field = hist_data->var_refs[i];
		if (ref_field->var.idx == var_field->var.idx &&
		    ref_field->var.hist_data == var_field->hist_data)
			return i;
	}

	return -ENOENT;
}

/**
 * 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;
	int i;

	/* Check if the variable already exists */
	for (i = 0; i < hist_data->n_var_refs; i++) {
		ref_field = hist_data->var_refs[i];
		if (ref_field->var.idx == var_field->var.idx &&
		    ref_field->var.hist_data == var_field->hist_data) {
			get_hist_field(ref_field);
			return 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, NULL) || 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;
	struct trace_array *tr = hist_data->event_file->tr;

	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(tr, HIST_ERR_VAR_NOT_FOUND, errpos(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, unsigned long *buckets)
{
	struct ftrace_event_field *field = NULL;
	char *field_name, *modifier, *str;
	struct trace_array *tr = file->tr;

	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;
		/*
		 * 'sym-offset' occurrences in the trigger string are modified
		 * to 'symXoffset' to simplify arithmetic expression parsing.
		 */
		else if (strcmp(modifier, "symXoffset") == 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 if (strncmp(modifier, "bucket", 6) == 0) {
			int ret;

			modifier += 6;

			if (*modifier == 's')
				modifier++;
			if (*modifier != '=')
				goto error;
			modifier++;
			ret = kstrtoul(modifier, 0, buckets);
			if (ret || !(*buckets))
				goto error;
			*flags |= HIST_FIELD_FL_BUCKET;
		} else {
 error:
			hist_err(tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(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, "common_cpu") == 0)
		*flags |= HIST_FIELD_FL_CPU;
	else {
		field = trace_find_event_field(file->event_call, field_name);
		if (!field || !field->size) {
			/*
			 * For backward compatibility, if field_name
			 * was "cpu", then we treat this the same as
			 * common_cpu.
			 */
			if (strcmp(field_name, "cpu") == 0) {
				*flags |= HIST_FIELD_FL_CPU;
			} else {
				hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
					 errpos(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;
	}

	alias->var_ref_idx = var_ref->var_ref_idx;

	return alias;
}

static struct hist_field *parse_const(struct hist_trigger_data *hist_data,
				      char *str, char *var_name,
				      unsigned long *flags)
{
	struct trace_array *tr = hist_data->event_file->tr;
	struct hist_field *field = NULL;
	u64 constant;

	if (kstrtoull(str, 0, &constant)) {
		hist_err(tr, HIST_ERR_EXPECT_NUMBER, errpos(str));
		return NULL;
	}

	*flags |= HIST_FIELD_FL_CONST;
	field = create_hist_field(hist_data, NULL, *flags, var_name);
	if (!field)
		return NULL;

	field->constant = constant;

	return field;
}

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;
	unsigned long buckets = 0;
	int ret = 0;

	if (isdigit(str[0])) {
		hist_field = parse_const(hist_data, str, var_name, flags);
		if (!hist_field) {
			ret = -EINVAL;
			goto out;
		}
		return hist_field;
	}

	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, &buckets);
	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;
	}
	hist_field->buckets = buckets;

	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 *n_subexprs);

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 *n_subexprs)
{
	struct hist_field *operand1, *expr = NULL;
	unsigned long operand_flags;
	int ret = 0;
	char *s;

	/* Unary minus operator, increment n_subexprs */
	++*n_subexprs;

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

	if (*n_subexprs > 3) {
		hist_err(file->tr, HIST_ERR_TOO_MANY_SUBEXPR, errpos(str));
		ret = -EINVAL;
		goto free;
	}

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

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

	s = strrchr(str, ')');
	if (s) {
		 /* unary minus not supported in sub-expressions */
		if (*(s+1) != '\0') {
			hist_err(file->tr, HIST_ERR_UNARY_MINUS_SUBEXPR,
				 errpos(str));
			ret = -EINVAL;
			goto free;
		}
		*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, n_subexprs);
	if (IS_ERR(operand1)) {
		ret = PTR_ERR(operand1);
		goto free;
	}
	if (operand1->flags & HIST_FIELD_FL_STRING) {
		/* String type can not be the operand of unary operator. */
		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
		destroy_hist_field(operand1, 0);
		ret = -EINVAL;
		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_const(operand1->type, GFP_KERNEL);
	if (!expr->type) {
		ret = -ENOMEM;
		goto free;
	}

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

/*
 * If the operands are var refs, return pointers the
 * variable(s) referenced in var1 and var2, else NULL.
 */
static int check_expr_operands(struct trace_array *tr,
			       struct hist_field *operand1,
			       struct hist_field *operand2,
			       struct hist_field **var1,
			       struct hist_field **var2)
{
	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;
		*var1 = var;
	}

	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;
		*var2 = var;
	}

	if ((operand1_flags & HIST_FIELD_FL_TIMESTAMP_USECS) !=
	    (operand2_flags & HIST_FIELD_FL_TIMESTAMP_USECS)) {
		hist_err(tr, HIST_ERR_TIMESTAMP_MISMATCH, 0);
		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 *n_subexprs)
{
	struct hist_field *operand1 = NULL, *operand2 = NULL, *expr = NULL;
	struct hist_field *var1 = NULL, *var2 = NULL;
	unsigned long operand_flags, operand2_flags;
	int field_op, ret = -EINVAL;
	char *sep, *operand1_str;
	hist_field_fn_t op_fn;
	bool combine_consts;

	if (*n_subexprs > 3) {
		hist_err(file->tr, HIST_ERR_TOO_MANY_SUBEXPR, errpos(str));
		return ERR_PTR(-EINVAL);
	}

	field_op = contains_operator(str, &sep);

	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, n_subexprs);

	/* Binary operator found, increment n_subexprs */
	++*n_subexprs;

	/* Split the expression string at the root operator */
	if (!sep)
		return ERR_PTR(-EINVAL);

	*sep = '\0';
	operand1_str = str;
	str = sep+1;

	/* Binary operator requires both operands */
	if (*operand1_str == '\0' || *str == '\0')
		return ERR_PTR(-EINVAL);

	operand_flags = 0;

	/* LHS of string is an expression e.g. a+b in a+b+c */
	operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs);
	if (IS_ERR(operand1))
		return ERR_CAST(operand1);

	if (operand1->flags & HIST_FIELD_FL_STRING) {
		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
		ret = -EINVAL;
		goto free_op1;
	}

	/* RHS of string is another expression e.g. c in a+b+c */
	operand_flags = 0;
	operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs);
	if (IS_ERR(operand2)) {
		ret = PTR_ERR(operand2);
		goto free_op1;
	}
	if (operand2->flags & HIST_FIELD_FL_STRING) {
		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
		ret = -EINVAL;
		goto free_operands;
	}

	switch (field_op) {
	case FIELD_OP_MINUS:
		op_fn = hist_field_minus;
		break;
	case FIELD_OP_PLUS:
		op_fn = hist_field_plus;
		break;
	case FIELD_OP_DIV:
		op_fn = hist_field_div;
		break;
	case FIELD_OP_MULT:
		op_fn = hist_field_mult;
		break;
	default:
		ret = -EINVAL;
		goto free_operands;
	}

	ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2);
	if (ret)
		goto free_operands;

	operand_flags = var1 ? var1->flags : operand1->flags;
	operand2_flags = var2 ? var2->flags : operand2->flags;

	/*
	 * If both operands are constant, the expression can be
	 * collapsed to a single constant.
	 */
	combine_consts = operand_flags & operand2_flags & HIST_FIELD_FL_CONST;

	flags |= combine_consts ? HIST_FIELD_FL_CONST : 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_operands;
	}

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

	/* The operands are now owned and free'd by 'expr' */
	expr->operands[0] = operand1;
	expr->operands[1] = operand2;

	if (field_op == FIELD_OP_DIV &&
			operand2_flags & HIST_FIELD_FL_CONST) {
		u64 divisor = var2 ? var2->constant : operand2->constant;

		if (!divisor) {
			hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str));
			ret = -EDOM;
			goto free_expr;
		}

		/*
		 * Copy the divisor here so we don't have to look it up
		 * later if this is a var ref
		 */
		operand2->constant = divisor;
		op_fn = hist_field_get_div_fn(operand2);
	}

	if (combine_consts) {
		if (var1)
			expr->operands[0] = var1;
		if (var2)
			expr->operands[1] = var2;

		expr->constant = op_fn(expr, NULL, NULL, NULL, NULL);

		expr->operands[0] = NULL;
		expr->operands[1] = NULL;

		/*
		 * var refs won't be destroyed immediately
		 * See: destroy_hist_field()
		 */
		destroy_hist_field(operand2, 0);
		destroy_hist_field(operand1, 0);

		expr->name = expr_str(expr, 0);
	} else {
		expr->fn = op_fn;

		/* The operand sizes should be the same, so just pick one */
		expr->size = operand1->size;

		expr->operator = field_op;
		expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
		if (!expr->type) {
			ret = -ENOMEM;
			goto free_expr;
		}

		expr->name = expr_str(expr, 0);
	}

	return expr;

free_operands:
	destroy_hist_field(operand2, 0);
free_op1:
	destroy_hist_field(operand1, 0);
	return ERR_PTR(ret);

free_expr:
	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;

	lockdep_assert_held(&event_mutex);

	list_for_each_entry(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;
}

static struct event_command trigger_hist_cmd;
static int event_hist_trigger_func(struct event_command *cmd_ops,
				   struct trace_event_file *file,
				   char *glob, char *cmd, char *param);

static bool compatible_keys(struct hist_trigger_data *target_hist_data,
			    struct hist_trigger_data *hist_data,
			    unsigned int n_keys)
{
	struct hist_field *target_hist_field, *hist_field;
	unsigned int n, i, j;

	if (hist_data->n_fields - hist_data->n_vals != n_keys)
		return false;

	i = hist_data->n_vals;
	j = target_hist_data->n_vals;

	for (n = 0; n < n_keys; n++) {
		hist_field = hist_data->fields[i + n];
		target_hist_field = target_hist_data->fields[j + n];

		if (strcmp(hist_field->type, target_hist_field->type) != 0)
			return false;
		if (hist_field->size != target_hist_field->size)
			return false;
		if (hist_field->is_signed != target_hist_field->is_signed)
			return false;
	}

	return true;
}

static struct hist_trigger_data *
find_compatible_hist(struct hist_trigger_data *target_hist_data,
		     struct trace_event_file *file)
{
	struct hist_trigger_data *hist_data;
	struct event_trigger_data *test;
	unsigned int n_keys;

	lockdep_assert_held(&event_mutex);

	n_keys = target_hist_data->n_fields - target_hist_data->n_vals;

	list_for_each_entry(test, &file->triggers, list) {
		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
			hist_data = test->private_data;

			if (compatible_keys(target_hist_data, hist_data, n_keys))
				return hist_data;
		}
	}

	return NULL;
}

static struct trace_event_file *event_file(struct trace_array *tr,
					   char *system, char *event_name)
{
	struct trace_event_file *file;

	file = __find_event_file(tr, system, event_name);
	if (!file)
		return ERR_PTR(-EINVAL);

	return file;
}

static struct hist_field *
find_synthetic_field_var(struct hist_trigger_data *target_hist_data,
			 char *system, char *event_name, char *field_name)
{
	struct hist_field *event_var;
	char *synthetic_name;

	synthetic_name = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL);
	if (!synthetic_name)
		return ERR_PTR(-ENOMEM);

	strcpy(synthetic_name, "synthetic_");
	strcat(synthetic_name, field_name);

	event_var = find_event_var(target_hist_data, system, event_name, synthetic_name);

	kfree(synthetic_name);

	return event_var;
}

/**
 * create_field_var_hist - Automatically create a histogram and var for a field
 * @target_hist_data: The target hist trigger
 * @subsys_name: Optional subsystem name
 * @event_name: Optional event name
 * @field_name: The name of the field (and the resulting variable)
 *
 * Hist trigger actions fetch data from variables, not directly from
 * events.  However, for convenience, users are allowed to directly
 * specify an event field in an action, which will be automatically
 * converted into a variable on their behalf.
 *
 * If a user specifies a field on an event that isn't the event the
 * histogram currently being defined (the target event histogram), the
 * only way that can be accomplished is if a new hist trigger is
 * created and the field variable defined on that.
 *
 * This function creates a new histogram compatible with the target
 * event (meaning a histogram with the same key as the target
 * histogram), and creates a variable for the specified field, but
 * with 'synthetic_' prepended to the variable name in order to avoid
 * collision with normal field variables.
 *
 * Return: The variable created for the field.
 */
static struct hist_field *
create_field_var_hist(struct hist_trigger_data *target_hist_data,
		      char *subsys_name, char *event_name, char *field_name)
{
	struct trace_array *tr = target_hist_data->event_file->tr;
	struct hist_trigger_data *hist_data;
	unsigned int i, n, first = true;
	struct field_var_hist *var_hist;
	struct trace_event_file *file;
	struct hist_field *key_field;
	struct hist_field *event_var;
	char *saved_filter;
	char *cmd;
	int ret;

	if (target_hist_data->n_field_var_hists >= SYNTH_FIELDS_MAX) {
		hist_err(tr, HIST_ERR_TOO_MANY_FIELD_VARS, errpos(field_name));
		return ERR_PTR(-EINVAL);
	}

	file = event_file(tr, subsys_name, event_name);

	if (IS_ERR(file)) {
		hist_err(tr, HIST_ERR_EVENT_FILE_NOT_FOUND, errpos(field_name));
		ret = PTR_ERR(file);
		return ERR_PTR(ret);
	}

	/*
	 * Look for a histogram compatible with target.  We'll use the
	 * found histogram specification to create a new matching
	 * histogram with our variable on it.  target_hist_data is not
	 * yet a registered histogram so we can't use that.
	 */
	hist_data = find_compatible_hist(target_hist_data, file);
	if (!hist_data) {
		hist_err(tr, HIST_ERR_HIST_NOT_FOUND, errpos(field_name));
		return ERR_PTR(-EINVAL);
	}

	/* See if a synthetic field variable has already been created */
	event_var = find_synthetic_field_var(target_hist_data, subsys_name,
					     event_name, field_name);
	if (!IS_ERR_OR_NULL(event_var))
		return event_var;

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

	cmd = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL);
	if (!cmd) {
		kfree(var_hist);
		return ERR_PTR(-ENOMEM);
	}

	/* Use the same keys as the compatible histogram */
	strcat(cmd, "keys=");

	for_each_hist_key_field(i, hist_data) {
		key_field = hist_data->fields[i];
		if (!first)
			strcat(cmd, ",");
		strcat(cmd, key_field->field->name);
		first = false;
	}

	/* Create the synthetic field variable specification */
	strcat(cmd, ":synthetic_");
	strcat(cmd, field_name);
	strcat(cmd, "=");
	strcat(cmd, field_name);

	/* Use the same filter as the compatible histogram */
	saved_filter = find_trigger_filter(hist_data, file);
	if (saved_filter) {
		strcat(cmd, " if ");
		strcat(cmd, saved_filter);
	}

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

	/* Save the compatible histogram information */
	var_hist->hist_data = hist_data;

	/* Create the new histogram with our variable */
	ret = event_hist_trigger_func(&trigger_hist_cmd, file,
				      "", "hist", cmd);
	if (ret) {
		kfree(cmd);
		kfree(var_hist->cmd);
		kfree(var_hist);
		hist_err(tr, HIST_ERR_HIST_CREATE_FAIL, errpos(field_name));
		return ERR_PTR(ret);
	}

	kfree(cmd);

	/* If we can't find the variable, something went wrong */
	event_var = find_synthetic_field_var(target_hist_data, subsys_name,
					     event_name, field_name);
	if (IS_ERR_OR_NULL(event_var)) {
		kfree(var_hist->cmd);
		kfree(var_hist);
		hist_err(tr, HIST_ERR_SYNTH_VAR_NOT_FOUND, errpos(field_name));
		return ERR_PTR(-EINVAL);
	}

	n = target_hist_data->n_field_var_hists;
	target_hist_data->field_var_hists[n] = var_hist;
	target_hist_data->n_field_var_hists++;

	return event_var;
}

static struct hist_field *
find_target_event_var(struct hist_trigger_data *hist_data,
		      char *subsys_name, char *event_name, char *var_name)
{
	struct trace_event_file *file = hist_data->event_file;
	struct hist_field *hist_field = NULL;

	if (subsys_name) {
		struct trace_event_call *call;

		if (!event_name)
			return NULL;

		call = file->event_call;

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

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

	hist_field = find_var_field(hist_data, var_name);

	return hist_field;
}

static inline void __update_field_vars(struct tracing_map_elt *elt,
				       struct trace_buffer *buffer,
				       struct ring_buffer_event *rbe,
				       void *rec,
				       struct field_var **field_vars,
				       unsigned int n_field_vars,
				       unsigned int field_var_str_start)
{
	struct hist_elt_data *elt_data = elt->private_data;
	unsigned int i, j, var_idx;
	u64 var_val;

	for (i = 0, j = field_var_str_start; i < n_field_vars; i++) {
		struct field_var *field_var = field_vars[i];
		struct hist_field *var = field_var->var;
		struct hist_field *val = field_var->val;

		var_val = val->fn(val, elt, buffer, rbe, rec);
		var_idx = var->var.idx;

		if (val->flags & HIST_FIELD_FL_STRING) {
			char *str = elt_data->field_var_str[j++];
			char *val_str = (char *)(uintptr_t)var_val;
			unsigned int size;

			size = min(val->size, STR_VAR_LEN_MAX);
			strscpy(str, val_str, size);
			var_val = (u64)(uintptr_t)str;
		}
		tracing_map_set_var(elt, var_idx, var_val);
	}
}

static void update_field_vars(struct hist_trigger_data *hist_data,
			      struct tracing_map_elt *elt,
			      struct trace_buffer *buffer,
			      struct ring_buffer_event *rbe,
			      void *rec)
{
	__update_field_vars(elt, buffer, rbe, rec, hist_data->field_vars,
			    hist_data->n_field_vars, 0);
}

static void save_track_data_vars(struct hist_trigger_data *hist_data,
				 struct tracing_map_elt *elt,
				 struct trace_buffer *buffer,  void *rec,
				 struct ring_buffer_event *rbe, void *key,
				 struct action_data *data, u64 *var_ref_vals)
{
	__update_field_vars(elt, buffer, rbe, rec, hist_data->save_vars,
			    hist_data->n_save_vars, hist_data->n_field_var_str);
}

static