[sanitizer] Remove crypt and crypt_r interceptors

[MaskRay]

Summary

From Florian Weimer's D144073

On GNU/Linux (glibc), the crypt and crypt_r functions are not part of the main shared object (libc.so.6), but libcrypt (with multiple possible sonames). The sanitizer libraries do not depend on libcrypt, so it can happen that during sanitizer library initialization, no real implementation will be found because the crypt, crypt_r functions are not present in the process image (yet). If its interceptors are called nevertheless, this results in a call through a null pointer when the sanitizer library attempts to forward the call to the real implementation.

Many distributions have already switched to libxcrypt, a library that is separate from glibc and that can be build with sanitizers directly (avoiding the need for interceptors). This patch disables building the interceptor for glibc targets.

Let's remove crypt and crypt_r interceptors (D68431) to fix issues with
newer glibc.

For older glibc, msan will not know that an uninstrumented crypt_r call
initializes data, so there is a risk for false positives. However, with some
codebase survey, I think crypt_r uses are very few and the call sites typically
have a memset(&data, 0, sizeof(data)); anyway.

Fix https://github.com/google/sanitizers/issues/1365
Related: https://bugzilla.redhat.com/show_bug.cgi?id=2169432

[MaskRay]

remove Posix/crypt.cpp

[thesamesam]

This loses us coverage on musl and other libcs, unfortunately. musl will be keeping crypt indefinitely, although it does "support" overriding/interposition as well w/ libxcrypt (even if it's somewhat discouraged). But I'm also not sure how we can actually prevent that, so right now, sanitizing crypt at all is dangerous (c.f. the bugs @fweimer shared).

I agree it's cleaner to drop it entirely, the crypt situation is special.

compiler-rt/lib/sanitizer_common/sanitizer_common_interceptors.inc

INTERCEPTOR(SSIZE_T, getrandom, void *buf, SIZE_T buflen, unsigned int flags) {
   }
   return n;
 }
 #define INIT_GETRANDOM COMMON_INTERCEPT_FUNCTION(getrandom)
 #else
 #define INIT_GETRANDOM
 #endif
 
-#if SANITIZER_INTERCEPT_CRYPT
-INTERCEPTOR(char *, crypt, char *key, char *salt) {
-  void *ctx;
-  COMMON_INTERCEPTOR_ENTER(ctx, crypt, key, salt);
-  COMMON_INTERCEPTOR_READ_RANGE(ctx, key, internal_strlen(key) + 1);
-  COMMON_INTERCEPTOR_READ_RANGE(ctx, salt, internal_strlen(salt) + 1);
-  char *res = REAL(crypt)(key, salt);
-  if (res != nullptr)
-    COMMON_INTERCEPTOR_INITIALIZE_RANGE(res, internal_strlen(res) + 1);
-  return res;
-}
-#define INIT_CRYPT COMMON_INTERCEPT_FUNCTION(crypt);
-#else
-#define INIT_CRYPT
-#endif
-
-#if SANITIZER_INTERCEPT_CRYPT_R
-INTERCEPTOR(char *, crypt_r, char *key, char *salt, void *data) {
-  void *ctx;
-  COMMON_INTERCEPTOR_ENTER(ctx, crypt_r, key, salt, data);
-  COMMON_INTERCEPTOR_READ_RANGE(ctx, key, internal_strlen(key) + 1);
-  COMMON_INTERCEPTOR_READ_RANGE(ctx, salt, internal_strlen(salt) + 1);
-  char *res = REAL(crypt_r)(key, salt, data);
-  if (res != nullptr) {
-    COMMON_INTERCEPTOR_WRITE_RANGE(ctx, data,
-                                   __sanitizer::struct_crypt_data_sz);
-    COMMON_INTERCEPTOR_INITIALIZE_RANGE(res, internal_strlen(res) + 1);
-  }
-  return res;
-}
-#define INIT_CRYPT_R COMMON_INTERCEPT_FUNCTION(crypt_r);
-#else
-#define INIT_CRYPT_R
-#endif
-
 #if SANITIZER_INTERCEPT_GETENTROPY
 INTERCEPTOR(int, getentropy, void *buf, SIZE_T buflen) {
   void *ctx;
   COMMON_INTERCEPTOR_ENTER(ctx, getentropy, buf, buflen);
   int r = REAL(getentropy)(buf, buflen);
   if (r == 0) {
     COMMON_INTERCEPTOR_WRITE_RANGE(ctx, buf, buflen);
   }
#endif
   INIT_POPENVE;
   INIT_PCLOSE;
   INIT_FUNOPEN;
   INIT_FUNOPEN2;
   INIT_FDEVNAME;
   INIT_GETUSERSHELL;
   INIT_SL_INIT;
   INIT_GETRANDOM;
-  INIT_CRYPT;
-  INIT_CRYPT_R;
   INIT_GETENTROPY;
   INIT_QSORT;
   INIT_QSORT_R;
   INIT_BSEARCH;
   INIT_SIGALTSTACK;
   INIT_PROCCTL
   INIT_UNAME;
   INIT___XUNAME;
   INIT_HEXDUMP;
   INIT_ARGP_PARSE;
 
   INIT___PRINTF_CHK;
 }

compiler-rt/lib/sanitizer_common/sanitizer_platform_interceptors.h

 #define SANITIZER_INTERCEPT_PCLOSE SI_POSIX
 #define SANITIZER_INTERCEPT_FUNOPEN (SI_NETBSD || SI_FREEBSD)
 #define SANITIZER_INTERCEPT_FUNOPEN2 SI_NETBSD
 #define SANITIZER_INTERCEPT_GETFSENT (SI_FREEBSD || SI_NETBSD || SI_MAC)
 #define SANITIZER_INTERCEPT_ARC4RANDOM (SI_FREEBSD || SI_NETBSD || SI_MAC)
 #define SANITIZER_INTERCEPT_FDEVNAME SI_FREEBSD
 #define SANITIZER_INTERCEPT_GETUSERSHELL (SI_POSIX && !SI_ANDROID)
 #define SANITIZER_INTERCEPT_SL_INIT (SI_FREEBSD || SI_NETBSD)
-#define SANITIZER_INTERCEPT_CRYPT (SI_POSIX && !SI_ANDROID)
-#define SANITIZER_INTERCEPT_CRYPT_R (SI_LINUX && !SI_ANDROID)
 
 #define SANITIZER_INTERCEPT_GETRANDOM \
   ((SI_LINUX && __GLIBC_PREREQ(2, 25)) || SI_FREEBSD)
 #define SANITIZER_INTERCEPT___CXA_ATEXIT SI_NETBSD
 #define SANITIZER_INTERCEPT_ATEXIT SI_NETBSD
 #define SANITIZER_INTERCEPT_PTHREAD_ATFORK SI_NETBSD
 #define SANITIZER_INTERCEPT_GETENTROPY SI_FREEBSD
 #define SANITIZER_INTERCEPT_QSORT \

compiler-rt/lib/sanitizer_common/sanitizer_platform_limits_posix.h

 };
 #endif
 
 #if SANITIZER_LINUX && !SANITIZER_ANDROID
 extern unsigned struct_msqid_ds_sz;
 extern unsigned struct_mq_attr_sz;
 extern unsigned struct_timex_sz;
 extern unsigned struct_statvfs_sz;
-extern unsigned struct_crypt_data_sz;
 #endif  // SANITIZER_LINUX && !SANITIZER_ANDROID
 
 struct __sanitizer_iovec {
   void *iov_base;
   uptr iov_len;
 };
 
 #if !SANITIZER_ANDROID

compiler-rt/lib/sanitizer_common/sanitizer_platform_limits_posix.cpp

 #endif
 
 // Include these after system headers to avoid name clashes and ambiguities.
 #  include "sanitizer_common.h"
 #  include "sanitizer_internal_defs.h"
 #  include "sanitizer_platform_interceptors.h"
 #  include "sanitizer_platform_limits_posix.h"
 
-#if SANITIZER_INTERCEPT_CRYPT_R
-#include <crypt.h>
-#endif
-
 namespace __sanitizer {
   unsigned struct_utsname_sz = sizeof(struct utsname);
   unsigned struct_stat_sz = sizeof(struct stat);
 #if SANITIZER_HAS_STAT64
   unsigned struct_stat64_sz = sizeof(struct stat64);
 #endif // SANITIZER_HAS_STAT64
   unsigned struct_rusage_sz = sizeof(struct rusage);
   unsigned struct_tm_sz = sizeof(struct tm);

 #    else
 #      error Unknown size of struct ustat
 #    endif
   unsigned struct_ustat_sz = SIZEOF_STRUCT_USTAT;
   unsigned struct_rlimit64_sz = sizeof(struct rlimit64);
   unsigned struct_statvfs64_sz = sizeof(struct statvfs64);
 #endif // SANITIZER_GLIBC
 
-#if SANITIZER_INTERCEPT_CRYPT_R
-  unsigned struct_crypt_data_sz = sizeof(struct crypt_data);
-#endif
-
 #if SANITIZER_LINUX && !SANITIZER_ANDROID
   unsigned struct_timex_sz = sizeof(struct timex);
   unsigned struct_msqid_ds_sz = sizeof(struct msqid_ds);
   unsigned struct_mq_attr_sz = sizeof(struct mq_attr);
   unsigned struct_statvfs_sz = sizeof(struct statvfs);
 #endif // SANITIZER_LINUX && !SANITIZER_ANDROID
 
   const uptr sig_ign = (uptr)SIG_IGN;

compiler-rt/test/sanitizer_common/TestCases/Linux/crypt_r.cpp

-// RUN: %clangxx -O0 -g %s -lcrypt -o %t && %run %t
-
-// crypt.h is missing from Android.
-// UNSUPPORTED: android
-
-#include <assert.h>
-#include <unistd.h>
-#include <cstring>
-#include <crypt.h>
-
-int main(int argc, char **argv) {
-  {
-    crypt_data cd;
-    cd.initialized = 0;
-    char *p = crypt_r("abcdef", "xz", &cd);
-    volatile size_t z = strlen(p);
-  }
-  {
-    crypt_data cd;
-    cd.initialized = 0;
-    char *p = crypt_r("abcdef", "$1$", &cd);
-    volatile size_t z = strlen(p);
-  }
-  {
-    crypt_data cd;
-    cd.initialized = 0;
-    char *p = crypt_r("abcdef", "$5$", &cd);
-    volatile size_t z = strlen(p);
-  }
-  {
-    crypt_data cd;
-    cd.initialized = 0;
-    char *p = crypt_r("abcdef", "$6$", &cd);
-    volatile size_t z = strlen(p);
-  }
-}

compiler-rt/test/sanitizer_common/TestCases/Posix/crypt.cpp

-// RUN: %clangxx -O0 -g %s -o %t -lcrypt && %run %t
-
-// crypt() is missing from Android and -lcrypt from darwin.
-// UNSUPPORTED: android, darwin
-
-#include <assert.h>
-#include <unistd.h>
-#include <cstring>
-#if __has_include(<crypt.h>)
-#include <crypt.h>
-#endif
-
-int
-main (int argc, char** argv)
-{
-  {
-    char *p = crypt("abcdef", "xz");
-    volatile size_t z = strlen(p);
-  }
-  {
-    char *p = crypt("abcdef", "$1$");
-    volatile size_t z = strlen(p);
-  }
-  {
-    char *p = crypt("abcdef", "$5$");
-    volatile size_t z = strlen(p);
-  }
-  {
-    char *p = crypt("abcdef", "$6$");
-    volatile size_t z = strlen(p);
-  }
-}