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>

6 files changed, 106 insertions, 2 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 188521f34347..e3e12f9d4733 100644
--- a/tools/perf/util/Build
+++ b/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
 
diff --git a/tools/perf/util/demangle-ocaml.c b/tools/perf/util/demangle-ocaml.c
new file mode 100644
index 000000000000..3df14e67c622
--- /dev/null
+++ b/tools/perf/util/demangle-ocaml.c
@@ -0,0 +1,80 @@
+// 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;
+}
diff --git a/tools/perf/util/demangle-ocaml.h b/tools/perf/util/demangle-ocaml.h
new file mode 100644
index 000000000000..843cc4fa10a6
--- /dev/null
+++ b/tools/perf/util/demangle-ocaml.h
@@ -0,0 +1,7 @@
+/* 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 */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 52603876c548..f6d90cdd9225 100644
--- a/tools/perf/util/string.c
+++ b/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;
+}
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 73df616ced43..56c30fef9682 100644
--- a/tools/perf/util/string2.h
+++ b/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 */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index ecc05aa8399d..6dff843fd883 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/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