[PATCH 14/19] perf symbols: add Java demangling support

[Arnaldo Carvalho de Melo]

See http://www.infradead.org/rpr.html

From: Stephane Eranian <eranian@xxxxxxxxxx>

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>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Carl Love <cel@xxxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: John McCutchan <johnmccutchan@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Pawel Moll <pawel.moll@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Sonny Rao <sonnyrao@xxxxxxxxxxxx>
Cc: Sukadev Bhattiprolu <sukadev@xxxxxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1448874143-7269-2-git-send-email-eranian@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/Build           |   1 +
 tools/perf/util/demangle-java.c | 199 ++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/demangle-java.h |  10 ++
 tools/perf/util/symbol-elf.c    |   3 +
 4 files changed, 213 insertions(+)
 create mode 100644 tools/perf/util/demangle-java.c
 create mode 100644 tools/perf/util/demangle-java.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5eec53a3f4ac..edae107416b6 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -105,6 +105,7 @@ libperf-y += scripting-engines/
 
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
+libperf-y += demangle-java.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
new file mode 100644
index 000000000000..3e6062ab2cdd
--- /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
+ * 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_CTYPE) {
+				if (mode == MODE_CTYPE) {
+					if (narg)
+						rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+					narg++;
+				}
+				rlen += scnprintf(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 += 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)))
+				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;
+}
diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
new file mode 100644
index 000000000000..a981c1f968fe
--- /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 562b8ebeae5b..b1dd68f358fc 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>
@@ -1077,6 +1078,8 @@ new_symbol:
 				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;
 		}
-- 
2.5.0