linux/tools/perf/util/demangle-java.c
Nick Gasson 0bdf31811b perf jvmti: Fix demangling Java symbols
For a Java method signature like:

    Ljava/lang/AbstractStringBuilder;appendChars(Ljava/lang/String;II)V

The demangler produces:

    void class java.lang.AbstractStringBuilder.appendChars(class java.lang., shorttring., int, int)

The arguments should be (java.lang.String, int, int) but the demangler
interprets the "S" in String as the type code for "short". Correct this
and two other minor things:

- There is no "bool" type in Java, should be "boolean".

- The demangler prepends "class" to every Java class name. This is not
  standard Java syntax and it wastes a lot of horizontal space if the
  signature is long. Remove this as there isn't any ambiguity between
  class names and primitives.

Committer notes:

This was split from a larger patch that also added a java demangler
'perf test' entry, that, before this patch shows the error being fixed
by it:

  $ perf test java
  65: Demangle Java                                         : FAILED!
  $ perf test -v java
  Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc
  65: Demangle Java                                         :
  --- start ---
  test child forked, pid 307264
  FAILED: Ljava/lang/StringLatin1;equals([B[B)Z: bool class java.lang.StringLatin1.equals(byte[], byte[]) != boolean java.lang.StringLatin1.equals(byte[], byte[])
  FAILED: Ljava/util/zip/ZipUtils;CENSIZ([BI)J: long class java.util.zip.ZipUtils.CENSIZ(byte[], int) != long java.util.zip.ZipUtils.CENSIZ(byte[], int)
  FAILED: Ljava/util/regex/Pattern$BmpCharProperty;match(Ljava/util/regex/Matcher;ILjava/lang/CharSequence;)Z: bool class java.util.regex.Pattern$BmpCharProperty.match(class java.util.regex.Matcher., int, class java.lang., charhar, shortequence) != boolean java.util.regex.Pattern$BmpCharProperty.match(java.util.regex.Matcher, int, java.lang.CharSequence)
  FAILED: Ljava/lang/AbstractStringBuilder;appendChars(Ljava/lang/String;II)V: void class java.lang.AbstractStringBuilder.appendChars(class java.lang., shorttring., int, int) != void java.lang.AbstractStringBuilder.appendChars(java.lang.String, int, int)
  FAILED: Ljava/lang/Object;<init>()V: void class java.lang.Object<init>() != void java.lang.Object<init>()
  test child finished with -1
  ---- end ----
  Demangle Java: FAILED!
  $

After applying this patch:

  $ perf test  java
  65: Demangle Java                                         : Ok
  $

Signed-off-by: Nick Gasson <nick.gasson@arm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200427061520.24905-4-nick.gasson@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-28 10:03:28 -03:00

204 lines
4.2 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <sys/types.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "symbol.h"
#include "demangle-java.h"
#include <linux/ctype.h>
#include <linux/kernel.h>
enum {
MODE_PREFIX = 0,
MODE_CLASS = 1,
MODE_FUNC = 2,
MODE_TYPE = 3,
MODE_CTYPE = 4, /* class arg */
};
#define BASE_ENT(c, n) [c - 'A']=n
static const char *base_types['Z' - 'A' + 1] = {
BASE_ENT('B', "byte" ),
BASE_ENT('C', "char" ),
BASE_ENT('D', "double" ),
BASE_ENT('F', "float" ),
BASE_ENT('I', "int" ),
BASE_ENT('J', "long" ),
BASE_ENT('S', "short" ),
BASE_ENT('Z', "boolean" ),
};
/*
* demangle Java symbol between str and end positions and stores
* up to maxlen characters into buf. The parser starts in mode.
*
* Use MODE_PREFIX to process entire prototype till end position
* Use MODE_TYPE to process return type if str starts on return type char
*
* Return:
* success: buf
* error : NULL
*/
static char *
__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode)
{
int rlen = 0;
int array = 0;
int narg = 0;
const char *q;
if (!end)
end = str + strlen(str);
for (q = str; q != end; q++) {
if (rlen == (maxlen - 1))
break;
switch (*q) {
case 'L':
if (mode == MODE_PREFIX || mode == MODE_TYPE) {
if (mode == MODE_TYPE) {
if (narg)
rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
narg++;
}
if (mode == MODE_PREFIX)
mode = MODE_CLASS;
else
mode = MODE_CTYPE;
} else
buf[rlen++] = *q;
break;
case 'B':
case 'C':
case 'D':
case 'F':
case 'I':
case 'J':
case 'S':
case 'Z':
if (mode == MODE_TYPE) {
if (narg)
rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
rlen += scnprintf(buf + rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
while (array--)
rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
array = 0;
narg++;
} else
buf[rlen++] = *q;
break;
case 'V':
if (mode == MODE_TYPE) {
rlen += scnprintf(buf + rlen, maxlen - rlen, "void");
while (array--)
rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
array = 0;
} else
buf[rlen++] = *q;
break;
case '[':
if (mode != MODE_TYPE)
goto error;
array++;
break;
case '(':
if (mode != MODE_FUNC)
goto error;
buf[rlen++] = *q;
mode = MODE_TYPE;
break;
case ')':
if (mode != MODE_TYPE)
goto error;
buf[rlen++] = *q;
narg = 0;
break;
case ';':
if (mode != MODE_CLASS && mode != MODE_CTYPE)
goto error;
/* safe because at least one other char to process */
if (isalpha(*(q + 1)) && mode == MODE_CLASS)
rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
if (mode == MODE_CLASS)
mode = MODE_FUNC;
else if (mode == MODE_CTYPE)
mode = MODE_TYPE;
break;
case '/':
if (mode != MODE_CLASS && mode != MODE_CTYPE)
goto error;
rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
break;
default :
buf[rlen++] = *q;
}
}
buf[rlen] = '\0';
return buf;
error:
return NULL;
}
/*
* Demangle Java function signature (openJDK, not GCJ)
* input:
* str: string to parse. String is not modified
* flags: comobination of JAVA_DEMANGLE_* flags to modify demangling
* return:
* if input can be demangled, then a newly allocated string is returned.
* if input cannot be demangled, then NULL is returned
*
* Note: caller is responsible for freeing demangled string
*/
char *
java_demangle_sym(const char *str, int flags)
{
char *buf, *ptr;
char *p;
size_t len, l1 = 0;
if (!str)
return NULL;
/* find start of retunr type */
p = strrchr(str, ')');
if (!p)
return NULL;
/*
* expansion factor estimated to 3x
*/
len = strlen(str) * 3 + 1;
buf = malloc(len);
if (!buf)
return NULL;
buf[0] = '\0';
if (!(flags & JAVA_DEMANGLE_NORET)) {
/*
* get return type first
*/
ptr = __demangle_java_sym(p + 1, NULL, buf, len, MODE_TYPE);
if (!ptr)
goto error;
/* add space between return type and function prototype */
l1 = strlen(buf);
buf[l1++] = ' ';
}
/* process function up to return type */
ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX);
if (!ptr)
goto error;
return buf;
error:
free(buf);
return NULL;
}