[msan][asan] Add runtime flag intercept_strcmp

[vitalybuka]

Summary

Can be used to disable interceptor to workaround issues of
non-instrumented code.

[eugenis]

LGTM

[morehouse]

LGTM

compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors.inc

enum {
     CIMT_FILE
   } type;
   union {
     FileMetadata file;
   };
 };
 
 #if SI_POSIX
 typedef AddrHashMap<CommonInterceptorMetadata, 31051> MetadataHashMap;
 
 static MetadataHashMap *interceptor_metadata_map;
 
 UNUSED static void SetInterceptorMetadata(__sanitizer_FILE *addr,
                                           const FileMetadata &file) {
   MetadataHashMap::Handle h(interceptor_metadata_map, (uptr)addr);
   CHECK(h.created());
   h->type = CommonInterceptorMetadata::CIMT_FILE;
   h->file = file;
 }
 
 UNUSED static const FileMetadata *GetInterceptorMetadata(
     __sanitizer_FILE *addr) {

 
 UNUSED static void DeleteInterceptorMetadata(void *addr) {
   MetadataHashMap::Handle h(interceptor_metadata_map, (uptr)addr, true);
   CHECK(h.exists());
 }
 #endif  // SI_POSIX
 
 #if SANITIZER_INTERCEPT_STRLEN
 INTERCEPTOR(SIZE_T, strlen, const char *s) {
   // Sometimes strlen is called prior to InitializeCommonInterceptors,
   // in which case the REAL(strlen) typically used in
   // COMMON_INTERCEPTOR_ENTER will fail.  We use internal_strlen here
   // to handle that.
   if (COMMON_INTERCEPTOR_NOTHING_IS_INITIALIZED)
     return internal_strlen(s);
   void *ctx;
   COMMON_INTERCEPTOR_ENTER(ctx, strlen, s);
   SIZE_T result = REAL(strlen)(s);
   if (common_flags()->intercept_strlen)
     COMMON_INTERCEPTOR_READ_RANGE(ctx, s, result + 1);
   return result;
 }
 #define INIT_STRLEN COMMON_INTERCEPT_FUNCTION(strlen)
 #else
 #define INIT_STRLEN
 #endif
 
 #if SANITIZER_INTERCEPT_STRNLEN
 INTERCEPTOR(SIZE_T, strnlen, const char *s, SIZE_T maxlen) {
   void *ctx;
   COMMON_INTERCEPTOR_ENTER(ctx, strnlen, s, maxlen);
   SIZE_T length = REAL(strnlen)(s, maxlen);
   if (common_flags()->intercept_strlen)
     COMMON_INTERCEPTOR_READ_RANGE(ctx, s, Min(length + 1, maxlen));
   return length;
 }
 #define INIT_STRNLEN COMMON_INTERCEPT_FUNCTION(strnlen)
 #else
 #define INIT_STRNLEN
 #endif
 
 #if SANITIZER_INTERCEPT_STRNDUP
 INTERCEPTOR(char*, strndup, const char *s, uptr size) {
   void *ctx;
   COMMON_INTERCEPTOR_STRNDUP_IMPL(ctx, s, size);
 }
 #define INIT_STRNDUP COMMON_INTERCEPT_FUNCTION(strndup)
 #else
 #define INIT_STRNDUP
 #endif // SANITIZER_INTERCEPT_STRNDUP
 
INTERCEPTOR(int, strcmp, const char *s1, const char *s2) {
   COMMON_INTERCEPTOR_ENTER(ctx, strcmp, s1, s2);
   unsigned char c1, c2;
   uptr i;
   for (i = 0;; i++) {
     c1 = (unsigned char)s1[i];
     c2 = (unsigned char)s2[i];
     if (c1 != c2 || c1 == '\0') break;
   }
+  if (common_flags()->intercept_strcmp) {
     COMMON_INTERCEPTOR_READ_STRING(ctx, s1, i + 1);
     COMMON_INTERCEPTOR_READ_STRING(ctx, s2, i + 1);
+  }
   int result = CharCmpX(c1, c2);
   CALL_WEAK_INTERCEPTOR_HOOK(__sanitizer_weak_hook_strcmp, GET_CALLER_PC(), s1,
                              s2, result);
   return result;
 }
 
 DECLARE_WEAK_INTERCEPTOR_HOOK(__sanitizer_weak_hook_strncmp, uptr called_pc,
                               const char *s1, const char *s2, uptr n,

compiler-rt/lib/sanitizer_common/sanitizer_flags.inc

 //===-- sanitizer_flags.h ---------------------------------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file describes common flags available in all sanitizers.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef COMMON_FLAG
 #error "Define COMMON_FLAG prior to including this file!"
 #endif
 
 // COMMON_FLAG(Type, Name, DefaultValue, Description)
 // Supported types: bool, const char *, int, uptr.
 // Default value must be a compile-time constant.
 // Description must be a string literal.
 
 COMMON_FLAG(
     bool, symbolize, true,
     "If set, use the online symbolizer from common sanitizer runtime to turn "
     "virtual addresses to file/line locations.")
 COMMON_FLAG(
     const char *, external_symbolizer_path, nullptr,
     "Path to external symbolizer. If empty, the tool will search $PATH for "
     "the symbolizer.")
 COMMON_FLAG(
     bool, allow_addr2line, false,
     "If set, allows online symbolizer to run addr2line binary to symbolize "
     "stack traces (addr2line will only be used if llvm-symbolizer binary is "
     "unavailable.")
COMMON_FLAG(bool, intercept_strspn, true,
             "If set, uses custom wrappers for strspn and strcspn function "
             "to find more errors.")
 COMMON_FLAG(bool, intercept_strtok, true,
             "If set, uses a custom wrapper for the strtok function "
             "to find more errors.")
 COMMON_FLAG(bool, intercept_strpbrk, true,
             "If set, uses custom wrappers for strpbrk function "
             "to find more errors.")
+COMMON_FLAG(
+    bool, intercept_strcmp, true,
+    "If set, uses custom wrappers for strcmp functions to find more errors.")
 COMMON_FLAG(bool, intercept_strlen, true,
             "If set, uses custom wrappers for strlen and strnlen functions "
             "to find more errors.")
 COMMON_FLAG(bool, intercept_strndup, true,
             "If set, uses custom wrappers for strndup functions "
             "to find more errors.")
 COMMON_FLAG(bool, intercept_strchr, true,
             "If set, uses custom wrappers for strchr, strchrnul, and strrchr "

compiler-rt/test/asan/TestCases/strcmp.c

+// RUN: %clang_asan %s -o %t
+// RUN: %env_asan_opts=intercept_strcmp=false %run %t 2>&1
+// RUN: %env_asan_opts=intercept_strcmp=true not %run %t 2>&1 | FileCheck %s
+// RUN:                                      not %run %t 2>&1 | FileCheck %s
+
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+
+int main(int argc, char **argv) {
+  char s1[] = "abcd";
+  char s2[] = "1234";
+  assert(strcmp(s1, s2) > 0);
+  assert(strcmp(s1 - 1, s2));
+
+  // CHECK: {{.*ERROR: AddressSanitizer: stack-buffer-underflow on address}}
+  // CHECK: READ of size 1
+  return 0;
+}

compiler-rt/test/msan/strcmp.c

+// RUN: %clang_msan %s -o %t
+// RUN: MSAN_OPTIONS=intercept_strcmp=false %run %t 2>&1
+// RUN: MSAN_OPTIONS=intercept_strcmp=true not %run %t 2>&1 | FileCheck %s
+// RUN:                                    not %run %t 2>&1 | FileCheck %s
+
+#include <assert.h>
+#include <stdlib.h>
+#include <string.h>
+
+int main(int argc, char **argv) {
+  char undef;
+  char s1[] = "abcd";
+  char s2[] = "1234";
+  assert(strcmp(s1, s2) > 0);
+  s2[0] = undef;
+  assert(strcmp(s1, s2));
+
+  // CHECK: {{.*WARNING: MemorySanitizer: use-of-uninitialized-value}}
+  return 0;
+}