Re: [PATCH v3 1/4] perf tools: add Java demangling support

[Namhyung Kim]

Hi Stephane,

On Wed, Feb 18, 2015 at 10:40:25PM +0100, Stephane Eranian wrote:
> Add Java function descriptor demangling support.
> Something bfd cannot do.
> 
> Use the JAVA_DEMANGLE_NORET flag to avoid decoding the
> return type of functions.
> 
> Signed-off-by: Stephane Eranian <eranian@xxxxxxxxxx>
> ---
>  tools/perf/Makefile.perf        |   2 +
>  tools/perf/util/demangle-java.c | 199 ++++++++++++++++++++++++++++++++++++++++
>  tools/perf/util/demangle-java.h |  10 ++
>  tools/perf/util/symbol-elf.c    |   3 +
>  tools/perf/util/symbol.c        |   6 +-
>  5 files changed, 219 insertions(+), 1 deletion(-)
>  create mode 100644 tools/perf/util/demangle-java.c
>  create mode 100644 tools/perf/util/demangle-java.h
> 
> diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
> index aa6a504..53a44be 100644
> --- a/tools/perf/Makefile.perf
> +++ b/tools/perf/Makefile.perf
> @@ -331,6 +331,7 @@ LIB_H += ui/ui.h
>  LIB_H += util/data.h
>  LIB_H += util/kvm-stat.h
>  LIB_H += util/thread-stack.h
> +LIB_H += util/demangle-java.h
>  
>  LIB_OBJS += $(OUTPUT)util/abspath.o
>  LIB_OBJS += $(OUTPUT)util/alias.o
> @@ -410,6 +411,7 @@ LIB_OBJS += $(OUTPUT)util/data.o
>  LIB_OBJS += $(OUTPUT)util/tsc.o
>  LIB_OBJS += $(OUTPUT)util/cloexec.o
>  LIB_OBJS += $(OUTPUT)util/thread-stack.o
> +LIB_OBJS += $(OUTPUT)util/demangle-java.o
>  
>  LIB_OBJS += $(OUTPUT)ui/setup.o
>  LIB_OBJS += $(OUTPUT)ui/helpline.o
> diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
> new file mode 100644
> index 0000000..79d5484
> --- /dev/null
> +++ b/tools/perf/util/demangle-java.c
> @@ -0,0 +1,199 @@
> +#include <sys/types.h>
> +#include <stdio.h>
> +#include <string.h>
> +#include "util.h"
> +#include "debug.h"
> +#include "symbol.h"
> +
> +#include "demangle-java.h"
> +
> +enum {
> +	MODE_PREFIX=0,
> +	MODE_CLASS=1,
> +	MODE_FUNC=2,
> +	MODE_TYPE=3,
> +	MODE_CTYPE=3, /* 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', "bool" ),
> +};
> +
> +/*
> + * 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

So this still includes the argument (type) right?  I just worry about
that it might fill up the precious screen width of TUI like C++
symbols did before..


> + * Use MODE_TYPE to process return type if str starts on return type char

What about MODE_CTYPE?  I cannot find where it's used..


> + *
> + *  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_CTYPE) {
> +				if (mode == MODE_CTYPE) {
> +					if (narg)
> +						rlen += snprintf(buf+rlen, maxlen - rlen, ", ");
> +					narg++;
> +				}
> +				rlen += snprintf(buf+rlen, maxlen - rlen, "class ");
> +				if (mode == MODE_PREFIX)
> +					mode = MODE_CLASS;
> +			} 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 += snprintf(buf+rlen, maxlen - rlen, ", ");
> +				rlen += snprintf(buf+rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
> +				while(array--)
> +					rlen += snprintf(buf+rlen, maxlen - rlen, "[]");
> +				array = 0;
> +				narg++;
> +			} else
> +				buf[rlen++] = *q;
> +			break;
> +		case 'V':
> +			if (mode == MODE_TYPE) {
> +				rlen += snprintf(buf+rlen, maxlen - rlen, "void");
> +				while(array--)
> +					rlen += snprintf(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)))
> +				rlen += snprintf(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 += snprintf(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;
> +}
> diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
> new file mode 100644
> index 0000000..a981c1f
> --- /dev/null
> +++ b/tools/perf/util/demangle-java.h
> @@ -0,0 +1,10 @@
> +#ifndef __PERF_DEMANGLE_JAVA
> +#define __PERF_DEMANGLE_JAVA 1
> +/*
> + * demangle function flags
> + */
> +#define JAVA_DEMANGLE_NORET	0x1 /* do not process return type */
> +
> +char * java_demangle_sym(const char *str, int flags);
> +
> +#endif /* __PERF_DEMANGLE_JAVA */
> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
> index b24f9d8..73b3e8f 100644
> --- a/tools/perf/util/symbol-elf.c
> +++ b/tools/perf/util/symbol-elf.c
> @@ -6,6 +6,7 @@
>  #include <inttypes.h>
>  
>  #include "symbol.h"
> +#include "demangle-java.h"
>  #include "machine.h"
>  #include "vdso.h"
>  #include <symbol/kallsyms.h>
> @@ -1019,6 +1020,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
>  				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
>  
>  			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
> +			if (demangled == NULL)
> +				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
>  			if (demangled != NULL)
>  				elf_name = demangled;
>  		}
> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
> index a690668..3bc779b 100644
> --- a/tools/perf/util/symbol.c
> +++ b/tools/perf/util/symbol.c
> @@ -9,6 +9,7 @@
>  #include <fcntl.h>
>  #include <unistd.h>
>  #include <inttypes.h>
> +#include <bfd.h>

Wouldn't it break build on systems don't have the bfd devel package?
And I don't see why it's needed here..


>  #include "build-id.h"
>  #include "util.h"
>  #include "debug.h"
> @@ -1257,6 +1258,7 @@ static int dso__load_perf_map(struct dso *dso, struct map *map,
>  		u64 start, size;
>  		struct symbol *sym;
>  		int line_len, len;
> +		char *name;
>  
>  		line_len = getline(&line, &n, file);
>  		if (line_len < 0)
> @@ -1279,7 +1281,9 @@ static int dso__load_perf_map(struct dso *dso, struct map *map,
>  		if (len + 2 >= line_len)
>  			continue;
>  
> -		sym = symbol__new(start, size, STB_GLOBAL, line + len);
> +		name = line + len;
> +
> +		sym = symbol__new(start, size, STB_GLOBAL, name);

I think this file is not a part of this changeset.

Thanks,
Namhyung


>  
>  		if (sym == NULL)
>  			goto out_delete_line;
> -- 
> 1.9.1
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/