cc: Support glob+offset format in USDT arguments (#753)

Modern versions of USDT probes (such as what's found in
PostgreSQL when compiled with `--enable-dtrace`) may have
the offset listed after the global symbol for USDT
arguments of the format `4@symbol+8(%rip)`. This commit
extends the argument parser to support these cases, adds
tests for these cases, and makes sure that in case of a
parse error, the parser always moves forward and consumes
at least one character. Presently, the parser would get
stuck on the problematic position and enter an infinite
loop.

src/cc/usdt_args.cc

@@ -146,6 +146,9 @@ ssize_t ArgumentParser::parse_expr(ssize_t pos, Argument *dest) {
   } else {
     dest->deref_offset_ = 0;
     pos = parse_identifier(pos, &dest->deref_ident_);
+    if (arg_[pos] == '+' || arg_[pos] == '-') {
+      pos = parse_number(pos, &dest->deref_offset_);
+    }
   }
 
   if (arg_[pos] != '(')
@@ -184,10 +187,12 @@ bool ArgumentParser::parse(Argument *dest) {
   ssize_t res = parse_1(cur_pos_, dest);
   if (res < 0) {
     print_error(-res);
+    cur_pos_ = -res;
     return false;
   }
   if (!isspace(arg_[res]) && arg_[res] != '\0') {
     print_error(res);
+    cur_pos_ = res;
     return false;
   }
   while (isspace(arg_[res])) res++;

tests/cc/test_usdt_args.cc

@@ -48,12 +48,25 @@ static void verify_register(USDT::ArgumentParser_x64 &parser, int arg_size,
 }
 
 TEST_CASE("test usdt argument parsing", "[usdt]") {
+  SECTION("parse failure") {
+    USDT::ArgumentParser_x64 parser("4@i%ra+1r");
+    USDT::Argument arg;
+    REQUIRE(!parser.parse(&arg));
+    int i;
+    for (i = 0; i < 10 && !parser.done(); ++i) {
+      parser.parse(&arg);
+    }
+    // Make sure we reach termination
+    REQUIRE(i < 10);
+  }
   SECTION("argument examples from the Python implementation") {
     USDT::ArgumentParser_x64 parser(
         "-4@$0 8@$1234 %rdi %rax %rsi "
         "-8@%rbx 4@%r12 8@-8(%rbp) 4@(%rax) "
         "-4@global_max_action(%rip) "
-        "8@24+mp_(%rip) ");
+        "8@24+mp_(%rip) "
+        "-4@CheckpointStats+40(%rip) "
+        "4@glob-2(%rip) ");
 
     verify_register(parser, -4, 0);
     verify_register(parser, 8, 1234);
@@ -69,6 +82,8 @@ TEST_CASE("test usdt argument parsing", "[usdt]") {
 
     verify_register(parser, -4, "ip", 0, std::string("global_max_action"));
     verify_register(parser, 8, "ip", 24, std::string("mp_"));
+    verify_register(parser, -4, "ip", 40, std::string("CheckpointStats"));
+    verify_register(parser, 4, "ip", -2, std::string("glob"));
 
     REQUIRE(parser.done());
   }