perf tools: Add OCaml demangling

Detect symbols generated by the OCaml compiler based on their prefix.

Demangle OCaml symbols, returning a newly allocated string (like the
existing Java demangling functionality).

Move a helper function (hex) from tests/code-reading.c to util/string.c

To test:

  echo 'Printf.printf "%d\n" (Random.int 42)' > test.ml
  perf record ocamlopt.opt test.ml
  perf report -d ocamlopt.opt
Signed-off-by: Fabian Hemmer <copy@copy.sh>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LPU-Reference: 20210203211537.b25ytjb6dq5jfbwx@nyu
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/tests/Build

@@ -58,6 +58,7 @@ perf-y += time-utils-test.o
 perf-y += genelf.o
 perf-y += api-io.o
 perf-y += demangle-java-test.o
+perf-y += demangle-ocaml-test.o
 perf-y += pfm.o
 perf-y += parse-metric.o
 perf-y += pe-file-parsing.o

tools/perf/tests/builtin-test.c

@@ -338,6 +338,10 @@ static struct test generic_tests[] = {
 		.desc = "Demangle Java",
 		.func = test__demangle_java,
 	},
+	{
+		.desc = "Demangle OCaml",
+		.func = test__demangle_ocaml,
+	},
 	{
 		.desc = "Parse and process metrics",
 		.func = test__parse_metric,

tools/perf/tests/code-reading.c

@@ -26,6 +26,7 @@
 #include "event.h"
 #include "record.h"
 #include "util/mmap.h"
+#include "util/string2.h"
 #include "util/synthetic-events.h"
 #include "thread.h"
 
@@ -41,15 +42,6 @@ struct state {
 	size_t done_cnt;
 };
 
-static unsigned int hex(char c)
-{
-	if (c >= '0' && c <= '9')
-		return c - '0';
-	if (c >= 'a' && c <= 'f')
-		return c - 'a' + 10;
-	return c - 'A' + 10;
-}
-
 static size_t read_objdump_chunk(const char **line, unsigned char **buf,
 				 size_t *buf_len)
 {

tools/perf/tests/demangle-ocaml-test.c

+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "tests.h"
+#include "session.h"
+#include "debug.h"
+#include "demangle-ocaml.h"
+
+int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	int ret = TEST_OK;
+	char *buf = NULL;
+	size_t i;
+
+	struct {
+		const char *mangled, *demangled;
+	} test_cases[] = {
+		{ "main",
+		  NULL },
+		{ "camlStdlib__array__map_154",
+		  "Stdlib.array.map" },
+		{ "camlStdlib__anon_fn$5bstdlib$2eml$3a334$2c0$2d$2d54$5d_1453",
+		  "Stdlib.anon_fn[stdlib.ml:334,0--54]" },
+		{ "camlStdlib__bytes__$2b$2b_2205",
+		  "Stdlib.bytes.++" },
+	};
+
+	for (i = 0; i < sizeof(test_cases) / sizeof(test_cases[0]); i++) {
+		buf = ocaml_demangle_sym(test_cases[i].mangled);
+		if ((buf == NULL && test_cases[i].demangled != NULL)
+				|| (buf != NULL && test_cases[i].demangled == NULL)
+				|| (buf != NULL && strcmp(buf, test_cases[i].demangled))) {
+			pr_debug("FAILED: %s: %s != %s\n", test_cases[i].mangled,
+				 buf == NULL ? "(null)" : buf,
+				 test_cases[i].demangled == NULL ? "(null)" : test_cases[i].demangled);
+			ret = TEST_FAIL;
+		}
+		free(buf);
+	}
+
+	return ret;
+}

tools/perf/tests/tests.h

@@ -119,6 +119,7 @@ int test__time_utils(struct test *t, int subtest);
 int test__jit_write_elf(struct test *test, int subtest);
 int test__api_io(struct test *test, int subtest);
 int test__demangle_java(struct test *test, int subtest);
+int test__demangle_ocaml(struct test *test, int subtest);
 int test__pfm(struct test *test, int subtest);
 const char *test__pfm_subtest_get_desc(int subtest);
 int test__pfm_subtest_get_nr(void);

tools/perf/util/Build

@@ -173,6 +173,7 @@ perf-$(CONFIG_ZSTD) += zstd.o
 
 perf-$(CONFIG_LIBCAP) += cap.o
 
+perf-y += demangle-ocaml.o
 perf-y += demangle-java.o
 perf-y += demangle-rust.o
 

tools/perf/util/demangle-ocaml.c

+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <stdlib.h>
+#include "util/string2.h"
+
+#include "demangle-ocaml.h"
+
+#include <linux/ctype.h>
+
+static const char *caml_prefix = "caml";
+static const size_t caml_prefix_len = 4;
+
+/* mangled OCaml symbols start with "caml" followed by an upper-case letter */
+static bool
+ocaml_is_mangled(const char *sym)
+{
+	return 0 == strncmp(sym, caml_prefix, caml_prefix_len)
+		&& isupper(sym[caml_prefix_len]);
+}
+
+/*
+ * input:
+ *     sym: a symbol which may have been mangled by the OCaml compiler
+ * return:
+ *     if the input doesn't look like a mangled OCaml symbol, NULL is returned
+ *     otherwise, a newly allocated string containing the demangled symbol is returned
+ */
+char *
+ocaml_demangle_sym(const char *sym)
+{
+	char *result;
+	int j = 0;
+	int i;
+	int len;
+
+	if (!ocaml_is_mangled(sym)) {
+		return NULL;
+	}
+
+	len = strlen(sym);
+
+	/* the demangled symbol is always smaller than the mangled symbol */
+	result = malloc(len + 1);
+	if (!result)
+		return NULL;
+
+	/* skip "caml" prefix */
+	i = caml_prefix_len;
+
+	while (i < len) {
+		if (sym[i] == '_' && sym[i + 1] == '_') {
+			/* "__" -> "." */
+			result[j++] = '.';
+			i += 2;
+		}
+		else if (sym[i] == '$' && isxdigit(sym[i + 1]) && isxdigit(sym[i + 2])) {
+			/* "$xx" is a hex-encoded character */
+			result[j++] = (hex(sym[i + 1]) << 4) | hex(sym[i + 2]);
+			i += 3;
+		}
+		else {
+			result[j++] = sym[i++];
+		}
+	}
+	result[j] = '\0';
+
+	/* scan backwards to remove an "_" followed by decimal digits */
+	if (j != 0 && isdigit(result[j - 1])) {
+		while (--j) {
+			if (!isdigit(result[j])) {
+				break;
+			}
+		}
+		if (result[j] == '_') {
+			result[j] = '\0';
+		}
+	}
+
+	return result;
+}

tools/perf/util/demangle-ocaml.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_DEMANGLE_OCAML
+#define __PERF_DEMANGLE_OCAML 1
+
+char * ocaml_demangle_sym(const char *str);
+
+#endif /* __PERF_DEMANGLE_OCAML */

tools/perf/util/string.c

@@ -293,3 +293,12 @@ char *strdup_esc(const char *str)
 
 	return ret;
 }
+
+unsigned int hex(char c)
+{
+	if (c >= '0' && c <= '9')
+		return c - '0';
+	if (c >= 'a' && c <= 'f')
+		return c - 'a' + 10;
+	return c - 'A' + 10;
+}

tools/perf/util/string2.h

@@ -38,4 +38,6 @@ char *asprintf__tp_filter_pids(size_t npids, pid_t *pids);
 char *strpbrk_esc(char *str, const char *stopset);
 char *strdup_esc(const char *str);
 
+unsigned int hex(char c);
+
 #endif /* PERF_STRING_H */

tools/perf/util/symbol-elf.c

@@ -12,6 +12,7 @@
 #include "maps.h"
 #include "symbol.h"
 #include "symsrc.h"
+#include "demangle-ocaml.h"
 #include "demangle-java.h"
 #include "demangle-rust.h"
 #include "machine.h"
@@ -251,8 +252,12 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 	    return demangled;
 
 	demangled = bfd_demangle(NULL, elf_name, demangle_flags);
-	if (demangled == NULL)
-		demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+	if (demangled == NULL) {
+		demangled = ocaml_demangle_sym(elf_name);
+		if (demangled == NULL) {
+			demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+		}
+	}
 	else if (rust_is_mangled(demangled))
 		/*
 		    * Input to Rust demangling is the BFD-demangled