[sanitizer] Correct GetTls for x32

[hjl.tools]

Summary

Since x32 pointer size is 4 bytes, the self pointer offset in TCB:

struct
{
  void *tcb;
  dtv_t *dtv;
  void *self;
  ...

should be 8, not 16.

Fixes https://github.com/llvm/llvm-project/issues/55288

[eugenis]

LGTM

compiler-rt/lib/sanitizer_common/sanitizer_linux_libcdep.cpp

*size =
         reinterpret_cast<uptr>(end_addr) - reinterpret_cast<uptr>(start_addr);
   } else {
     *addr = 0;
     *size = 0;
   }
 #elif SANITIZER_GLIBC && defined(__x86_64__)
   // For aarch64 and x86-64, use an O(1) approach which requires relatively
   // precise ThreadDescriptorSize. g_tls_size was initialized in InitTlsSize.
+#  if SANITIZER_X32
+  asm("mov %%fs:8,%0" : "=r"(*addr));
+#  else
   asm("mov %%fs:16,%0" : "=r"(*addr));
+#  endif
   *size = g_tls_size;
   *addr -= *size;
   *addr += ThreadDescriptorSize();
 #elif SANITIZER_GLIBC && defined(__aarch64__)
   *addr = reinterpret_cast<uptr>(__builtin_thread_pointer()) -
           ThreadDescriptorSize();
   *size = g_tls_size + ThreadDescriptorSize();
 #elif SANITIZER_GLIBC && defined(__powerpc64__)