[sanitizer] More accurate scanf parsing without GNU extensions.

In __isoc99_*scanf we don't have to worry about GNUisms, and can parse
%a accurately.

Patch by Jakub Jelinek.

llvm-svn: 174969

diff --git a/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors.inc b/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors.inc
index 42d8d82..f402f20 100644 (file)
--- a/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors.inc
+++ b/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors.inc
@@ -150,7 +150,7 @@ INTERCEPTOR(int, prctl, int option, unsigned long arg2,
 
 #include "sanitizer_common_interceptors_scanf.inc"
 
-#define VSCANF_INTERCEPTOR_IMPL(vname, ...)                                    \
+#define VSCANF_INTERCEPTOR_IMPL(vname, allowGnuMalloc, ...)                    \
   {                                                                            \
     void *ctx;                                                                 \
     COMMON_INTERCEPTOR_ENTER(ctx, vname, __VA_ARGS__);                         \
@@ -158,29 +158,29 @@ INTERCEPTOR(int, prctl, int option, unsigned long arg2,
     va_copy(aq, ap);                                                           \
     int res = REAL(vname)(__VA_ARGS__);                                        \
     if (res > 0)                                                               \
-      scanf_common(ctx, res, format, aq);                                      \
+      scanf_common(ctx, res, allowGnuMalloc, format, aq);                      \
     va_end(aq);                                                                \
     return res;                                                                \
   }
 
 INTERCEPTOR(int, vscanf, const char *format, va_list ap)
-VSCANF_INTERCEPTOR_IMPL(vscanf, format, ap)
+VSCANF_INTERCEPTOR_IMPL(vscanf, true, format, ap)
 
 INTERCEPTOR(int, vsscanf, const char *str, const char *format, va_list ap)
-VSCANF_INTERCEPTOR_IMPL(vsscanf, str, format, ap)
+VSCANF_INTERCEPTOR_IMPL(vsscanf, true, str, format, ap)
 
 INTERCEPTOR(int, vfscanf, void *stream, const char *format, va_list ap)
-VSCANF_INTERCEPTOR_IMPL(vfscanf, stream, format, ap)
+VSCANF_INTERCEPTOR_IMPL(vfscanf, true, stream, format, ap)
 
 INTERCEPTOR(int, __isoc99_vscanf, const char *format, va_list ap)
-VSCANF_INTERCEPTOR_IMPL(__isoc99_vscanf, format, ap)
+VSCANF_INTERCEPTOR_IMPL(__isoc99_vscanf, false, format, ap)
 
 INTERCEPTOR(int, __isoc99_vsscanf, const char *str, const char *format,
             va_list ap)
-VSCANF_INTERCEPTOR_IMPL(__isoc99_vsscanf, str, format, ap)
+VSCANF_INTERCEPTOR_IMPL(__isoc99_vsscanf, false, str, format, ap)
 
 INTERCEPTOR(int, __isoc99_vfscanf, void *stream, const char *format, va_list ap)
-VSCANF_INTERCEPTOR_IMPL(__isoc99_vfscanf, stream, format, ap)
+VSCANF_INTERCEPTOR_IMPL(__isoc99_vfscanf, false, stream, format, ap)
 
 #define SCANF_INTERCEPTOR_IMPL(name, vname, ...)                               \
   {                                                                            \

diff --git a/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors_scanf.inc b/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors_scanf.inc
index 9ab5ae2..8bb5cd8 100644 (file)
--- a/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors_scanf.inc
+++ b/compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors_scanf.inc
@@ -39,7 +39,8 @@ static bool char_is_one_of(char c, const char *s) {
 // returned in dir. This function returns the pointer to the first
 // unprocessed character, or 0 in case of error.
 // In case of the end-of-string, a pointer to the closing \0 is returned.
-static const char *scanf_parse_next(const char *p, ScanfDirective *dir) {
+static const char *scanf_parse_next(const char *p, bool allowGnuMalloc,
+                                    ScanfDirective *dir) {
   internal_memset(dir, 0, sizeof(*dir));
   dir->argIdx = -1;
 
@@ -121,7 +122,8 @@ static const char *scanf_parse_next(const char *p, ScanfDirective *dir) {
     // This is unfortunately ambiguous between old GNU extension
     // of %as, %aS and %a[...] and newer POSIX %a followed by
     // letters s, S or [.
-    if (dir->convSpecifier == 'a' && !dir->lengthModifier[0]) {
+    if (allowGnuMalloc && dir->convSpecifier == 'a' &&
+        !dir->lengthModifier[0]) {
       if (*p == 's' || *p == 'S') {
         dir->maybeGnuMalloc = true;
         ++p;
@@ -271,14 +273,14 @@ static int scanf_get_store_size(ScanfDirective *dir) {
 // Common part of *scanf interceptors.
 // Process format string and va_list, and report all store ranges.
 // Stops when "consuming" n_inputs input items.
-static void scanf_common(void *ctx, int n_inputs, const char *format,
-                         va_list aq) {
+static void scanf_common(void *ctx, int n_inputs, bool allowGnuMalloc,
+                         const char *format, va_list aq) {
   CHECK_GT(n_inputs, 0);
   const char *p = format;
 
   while (*p && n_inputs) {
     ScanfDirective dir;
-    p = scanf_parse_next(p, &dir);
+    p = scanf_parse_next(p, allowGnuMalloc, &dir);
     if (!p)
       break;
     if (dir.convSpecifier == 0) {