Archived
14
0
Fork 0
This repository has been archived on 2022-02-17. You can view files and clone it, but cannot push or open issues or pull requests.
linux-2.6/tools/perf/util/string.c
Masami Hiramatsu 2a9c8c3609 perf probe: Add lazy line matching support
Add lazy line matching support for specifying new probes.
This also changes the syntax of perf probe a bit. Now
perf probe accepts one of below probe event definitions.

1) Define event based on function name
 [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...]

2) Define event based on source file with line number
 [EVENT=]SRC:ALN [ARG ...]

3) Define event based on source file with lazy pattern
 [EVENT=]SRC;PTN [ARG ...]

- New lazy matching pattern(PTN) follows ';' (semicolon). And it
  must be put the end of the definition.
- So, @SRC is no longer the part which must be put at the end
  of the definition.

Note that ';' (semicolon) can be interpreted as the end of
a command by the shell. This means that you need to quote it.
(anyway you will need to quote the lazy pattern itself too,
because it may contains other sensitive characters, like
'[',']' etc.).

Lazy matching
-------------
The lazy line matching is similar to glob matching except
ignoring spaces in both of pattern and target.

e.g.
'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.

This provides some sort of flexibility and robustness to
probe point definitions against minor code changes.
(for example, actual 10th line of schedule() can be changed
 easily by modifying schedule(), but the same line matching
 'rq=cpu_rq*' may still exist.)

Changes in v3:
 - Cast Dwarf_Addr to uintmax_t for printf-formats.

Changes in v2:
 - Cast Dwarf_Addr to unsigned long long for printf-formats.

Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: systemtap <systemtap@sources.redhat.com>
Cc: DLE <dle-develop@lists.sourceforge.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: K.Prasad <prasad@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 17:49:30 +01:00

340 lines
6.1 KiB
C

#include "string.h"
#include "util.h"
static int hex(char ch)
{
if ((ch >= '0') && (ch <= '9'))
return ch - '0';
if ((ch >= 'a') && (ch <= 'f'))
return ch - 'a' + 10;
if ((ch >= 'A') && (ch <= 'F'))
return ch - 'A' + 10;
return -1;
}
/*
* While we find nice hex chars, build a long_val.
* Return number of chars processed.
*/
int hex2u64(const char *ptr, u64 *long_val)
{
const char *p = ptr;
*long_val = 0;
while (*p) {
const int hex_val = hex(*p);
if (hex_val < 0)
break;
*long_val = (*long_val << 4) | hex_val;
p++;
}
return p - ptr;
}
char *strxfrchar(char *s, char from, char to)
{
char *p = s;
while ((p = strchr(p, from)) != NULL)
*p++ = to;
return s;
}
#define K 1024LL
/*
* perf_atoll()
* Parse (\d+)(b|B|kb|KB|mb|MB|gb|GB|tb|TB) (e.g. "256MB")
* and return its numeric value
*/
s64 perf_atoll(const char *str)
{
unsigned int i;
s64 length = -1, unit = 1;
if (!isdigit(str[0]))
goto out_err;
for (i = 1; i < strlen(str); i++) {
switch (str[i]) {
case 'B':
case 'b':
break;
case 'K':
if (str[i + 1] != 'B')
goto out_err;
else
goto kilo;
case 'k':
if (str[i + 1] != 'b')
goto out_err;
kilo:
unit = K;
break;
case 'M':
if (str[i + 1] != 'B')
goto out_err;
else
goto mega;
case 'm':
if (str[i + 1] != 'b')
goto out_err;
mega:
unit = K * K;
break;
case 'G':
if (str[i + 1] != 'B')
goto out_err;
else
goto giga;
case 'g':
if (str[i + 1] != 'b')
goto out_err;
giga:
unit = K * K * K;
break;
case 'T':
if (str[i + 1] != 'B')
goto out_err;
else
goto tera;
case 't':
if (str[i + 1] != 'b')
goto out_err;
tera:
unit = K * K * K * K;
break;
case '\0': /* only specified figures */
unit = 1;
break;
default:
if (!isdigit(str[i]))
goto out_err;
break;
}
}
length = atoll(str) * unit;
goto out;
out_err:
length = -1;
out:
return length;
}
/*
* Helper function for splitting a string into an argv-like array.
* originaly copied from lib/argv_split.c
*/
static const char *skip_sep(const char *cp)
{
while (*cp && isspace(*cp))
cp++;
return cp;
}
static const char *skip_arg(const char *cp)
{
while (*cp && !isspace(*cp))
cp++;
return cp;
}
static int count_argc(const char *str)
{
int count = 0;
while (*str) {
str = skip_sep(str);
if (*str) {
count++;
str = skip_arg(str);
}
}
return count;
}
/**
* argv_free - free an argv
* @argv - the argument vector to be freed
*
* Frees an argv and the strings it points to.
*/
void argv_free(char **argv)
{
char **p;
for (p = argv; *p; p++)
free(*p);
free(argv);
}
/**
* argv_split - split a string at whitespace, returning an argv
* @str: the string to be split
* @argcp: returned argument count
*
* Returns an array of pointers to strings which are split out from
* @str. This is performed by strictly splitting on white-space; no
* quote processing is performed. Multiple whitespace characters are
* considered to be a single argument separator. The returned array
* is always NULL-terminated. Returns NULL on memory allocation
* failure.
*/
char **argv_split(const char *str, int *argcp)
{
int argc = count_argc(str);
char **argv = zalloc(sizeof(*argv) * (argc+1));
char **argvp;
if (argv == NULL)
goto out;
if (argcp)
*argcp = argc;
argvp = argv;
while (*str) {
str = skip_sep(str);
if (*str) {
const char *p = str;
char *t;
str = skip_arg(str);
t = strndup(p, str-p);
if (t == NULL)
goto fail;
*argvp++ = t;
}
}
*argvp = NULL;
out:
return argv;
fail:
argv_free(argv);
return NULL;
}
/* Character class matching */
static bool __match_charclass(const char *pat, char c, const char **npat)
{
bool complement = false, ret = true;
if (*pat == '!') {
complement = true;
pat++;
}
if (*pat++ == c) /* First character is special */
goto end;
while (*pat && *pat != ']') { /* Matching */
if (*pat == '-' && *(pat + 1) != ']') { /* Range */
if (*(pat - 1) <= c && c <= *(pat + 1))
goto end;
if (*(pat - 1) > *(pat + 1))
goto error;
pat += 2;
} else if (*pat++ == c)
goto end;
}
if (!*pat)
goto error;
ret = false;
end:
while (*pat && *pat != ']') /* Searching closing */
pat++;
if (!*pat)
goto error;
*npat = pat + 1;
return complement ? !ret : ret;
error:
return false;
}
/* Glob/lazy pattern matching */
static bool __match_glob(const char *str, const char *pat, bool ignore_space)
{
while (*str && *pat && *pat != '*') {
if (ignore_space) {
/* Ignore spaces for lazy matching */
if (isspace(*str)) {
str++;
continue;
}
if (isspace(*pat)) {
pat++;
continue;
}
}
if (*pat == '?') { /* Matches any single character */
str++;
pat++;
continue;
} else if (*pat == '[') /* Character classes/Ranges */
if (__match_charclass(pat + 1, *str, &pat)) {
str++;
continue;
} else
return false;
else if (*pat == '\\') /* Escaped char match as normal char */
pat++;
if (*str++ != *pat++)
return false;
}
/* Check wild card */
if (*pat == '*') {
while (*pat == '*')
pat++;
if (!*pat) /* Tail wild card matches all */
return true;
while (*str)
if (strglobmatch(str++, pat))
return true;
}
return !*str && !*pat;
}
/**
* strglobmatch - glob expression pattern matching
* @str: the target string to match
* @pat: the pattern string to match
*
* This returns true if the @str matches @pat. @pat can includes wildcards
* ('*','?') and character classes ([CHARS], complementation and ranges are
* also supported). Also, this supports escape character ('\') to use special
* characters as normal character.
*
* Note: if @pat syntax is broken, this always returns false.
*/
bool strglobmatch(const char *str, const char *pat)
{
return __match_glob(str, pat, false);
}
/**
* strlazymatch - matching pattern strings lazily with glob pattern
* @str: the target string to match
* @pat: the pattern string to match
*
* This is similar to strglobmatch, except this ignores spaces in
* the target string.
*/
bool strlazymatch(const char *str, const char *pat)
{
return __match_glob(str, pat, true);
}