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/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;
+}