Retrieve command line arguments and environment correctly on FreeBSD

[dim]

Summary

Recently I saw the test TestCases/Posix/print_cmdline.cc failing on
FreeBSD, with "expected string not found in input". This is because
asan could not retrieve the command line arguments properly.

In lib/sanitizer_common/sanitizer_linux.cc, this is taken care of by
the GetArgsAndEnv() function, but it uses __libc_stack_end to get at
the required data. This variable does not exist on BSDs; the regular
way to retrieve the arguments and environment information is via the
kern.ps_strings sysctl.

I added this functionality in sanitizer_linux.cc, as a separate #ifdef
block in GetArgsAndEnv(). Also, ReadNullSepFileToArray() becomes
unused due to this change. (It won't work on FreeBSD anyway, since
/proc is not mounted by default.)

[davide]

LGTM. Probably the Asan owner should sign-off this anyway.

lib/sanitizer_common/sanitizer_linux.cc

451

Can you please add a comment explaining what this function is doing for first-readers who don't know sysctl&friends ?

[dim]

Add an explanatory comment. Also, ping. :-)

lib/sanitizer_common/sanitizer_linux.cc

 #include <sys/stat.h>
 #include <sys/syscall.h>
 #include <sys/time.h>
 #include <sys/types.h>
 #include <ucontext.h>
 #include <unistd.h>
 
 #if SANITIZER_FREEBSD
+#include <sys/exec.h>
 #include <sys/sysctl.h>
+#include <vm/vm_param.h>
+#include <vm/pmap.h>
 #include <machine/atomic.h>
 extern "C" {
 // <sys/umtx.h> must be included after <errno.h> and <sys/types.h> on
 // FreeBSD 9.2 and 10.0.
 #include <sys/umtx.h>
 }
 extern char **environ;  // provided by crt1
 #endif  // SANITIZER_FREEBSD
while (*p != '\0') {  // will happen at the \0\0 that terminates the buffer
     p = endp + 1;
   }
   return nullptr;  // Not found.
 #else
 #error "Unsupported platform"
 #endif
 }
 
+#if !SANITIZER_FREEBSD
 extern "C" {
   SANITIZER_WEAK_ATTRIBUTE extern void *__libc_stack_end;
 }
+#endif
 
-#if !SANITIZER_GO
+#if !SANITIZER_GO && !SANITIZER_FREEBSD
 static void ReadNullSepFileToArray(const char *path, char ***arr,
                                    int arr_size) {
   char *buff;
   uptr buff_size;
   uptr buff_len;
   *arr = (char **)MmapOrDie(arr_size * sizeof(char *), "NullSepFileArray");
   if (!ReadFileToBuffer(path, &buff, &buff_size, &buff_len, 1024 * 1024)) {
     (*arr)[0] = nullptr;
if (buff[i] == 0) {
       count++;
     }
   }
   (*arr)[count] = nullptr;
 }
 #endif
 
 static void GetArgsAndEnv(char ***argv, char ***envp) {
+#if !SANITIZER_FREEBSD
 #if !SANITIZER_GO
   if (&__libc_stack_end) {
 #endif
     uptr* stack_end = (uptr*)__libc_stack_end;
     int argc = *stack_end;
     *argv = (char**)(stack_end + 1);
     *envp = (char**)(stack_end + argc + 2);
 #if !SANITIZER_GO
   } else {
     static const int kMaxArgv = 2000, kMaxEnvp = 2000;
     ReadNullSepFileToArray("/proc/self/cmdline", argv, kMaxArgv);
     ReadNullSepFileToArray("/proc/self/environ", envp, kMaxEnvp);
   }
 #endif
+#else
+  // On FreeBSD, retrieving the argument and environment arrays is done via the
+  // kern.ps_strings sysctl, which returns a pointer to a structure containing
+  // this information.  If the sysctl is not available, a "hardcoded" address,
+  // PS_STRINGS, must be used instead.  See also <sys/exec.h>.
+  ps_strings *pss;
+  size_t sz = sizeof(pss);
+  if (sysctlbyname("kern.ps_strings", &pss, &sz, NULL, 0) == -1)
+    pss = (ps_strings*)PS_STRINGS;
+  *argv = pss->ps_argvstr;
+  *envp = pss->ps_envstr;
+#endif
 }
 
 char **GetArgv() {
   char **argv, **envp;
   GetArgsAndEnv(&argv, &envp);
   return argv;
 }