[gcc r12-8746] libstdc++: Check for overflow in regex back-reference [PR106607]

[gcc r12-8746] libstdc++: Check for overflow in regex back-reference [PR106607]

[Jonathan Wakely]

https://gcc.gnu.org/g:87da20c6e280925d885c5472de9189515f46880b

commit r12-8746-g87da20c6e280925d885c5472de9189515f46880b
Author: Jonathan Wakely <jwakely@redhat.com>
Date:   Mon Aug 22 15:16:16 2022 +0100

    libstdc++: Check for overflow in regex back-reference [PR106607]
    
    Currently we fail to notice integer overflow when parsing a
    back-reference expression, or when converting the parsed result from
    long to int. This changes the result to be int, so no conversion is
    needed, and uses the overflow-checking built-ins to detect an
    out-of-range back-reference.
    
    libstdc++-v3/ChangeLog:
    
            PR libstdc++/106607
            * include/bits/regex_compiler.tcc (_Compiler::_M_cur_int_value):
            Use built-ins to check for integer overflow in back-reference
            number.
            * testsuite/28_regex/basic_regex/106607.cc: New test.
    
    (cherry picked from commit 1b09eea33f2bf9d1eae73b25cc25efb05ea1dc3f)

Diff:
---
 libstdc++-v3/include/bits/regex_compiler.tcc       | 10 +++++----
 .../testsuite/28_regex/basic_regex/106607.cc       | 25 ++++++++++++++++++++++
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/libstdc++-v3/include/bits/regex_compiler.tcc b/libstdc++-v3/include/bits/regex_compiler.tcc
index c12f7502538..9f3ca63af51 100644
--- a/libstdc++-v3/include/bits/regex_compiler.tcc
+++ b/libstdc++-v3/include/bits/regex_compiler.tcc
@@ -583,10 +583,12 @@ namespace __detail
     _Compiler<_TraitsT>::
     _M_cur_int_value(int __radix)
     {
-      long __v = 0;
-      for (typename _StringT::size_type __i = 0;
-	   __i < _M_value.length(); ++__i)
-	__v =__v * __radix + _M_traits.value(_M_value[__i], __radix);
+      int __v = 0;
+      for (_CharT __c : _M_value)
+	if (__builtin_mul_overflow(__v, __radix, &__v)
+	    || __builtin_add_overflow(__v, _M_traits.value(__c, __radix), &__v))
+	    std::__throw_regex_error(regex_constants::error_backref,
+				     "invalid back reference");
       return __v;
     }
 
diff --git a/libstdc++-v3/testsuite/28_regex/basic_regex/106607.cc b/libstdc++-v3/testsuite/28_regex/basic_regex/106607.cc
new file mode 100644
index 00000000000..f8e7fb2364d
--- /dev/null
+++ b/libstdc++-v3/testsuite/28_regex/basic_regex/106607.cc
@@ -0,0 +1,25 @@
+// { dg-do run { target c++11 } }
+
+#include <regex>
+#include <string>
+#include <climits>
+#include <testsuite_hooks.h>
+
+// PR libstdc++/106607 - Regex integer overflow on large backreference value
+
+int main()
+{
+  std::regex r("(.)\\1"); // OK
+
+  try
+  {
+    long long n = (unsigned)-1 + 2LL;          // 4294967297 for 32-bit int
+    VERIFY( (int)n == 1 );                     // 4294967297 % 2^32 == 1
+    std::regex r("(.)\\" + std::to_string(n)); // Invalid back reference.
+    VERIFY(false);
+  }
+  catch (const std::regex_error& e)
+  {
+    VERIFY( e.code() == std::regex_constants::error_backref );
+  }
+}