Adjust sanitizers for FreeBSD 64-bit inode update

[dim]

Summary

Very recently, FreeBSD 12 has been updated to use 64-bit inode numbers:
https://svnweb.freebsd.org/changeset/base/318737. This entails many
user-visible changes, but for the sanitizers the modifications are
limited in scope:

• The stat and lstat syscalls were removed, and should be replaced with calls to fstatat.
• The getdents syscall was removed, and should be replaced with calls to getdirentries.
• The layout of struct dirent was changed to accomodate 64-bit inode numbers, and a new d_off field was added.
• The system header <sys/_types.h> now contains a macro __INO64 to determine whether the system uses 64-bit inode numbers.

I tested these changes on both FreeBSD 12.0-CURRENT (after r318959,
which adds the __INO64 macro), and FreeBSD 11.0-STABLE (which still
uses 32-bit inode numbers).

[dim]

I accidentally left a debugging aid in place. Remove it.

[vitalybuka]

Do we have public build bot for FreeBSD?

lib/sanitizer_common/sanitizer_linux.cc

240 ↗

(On Diff #100437)

Is this going to work for older versions?

[dim]

In D33600#766133, @vitalybuka wrote:

Do we have public build bot for FreeBSD?

No, unfortunately the one that used to exist has disappeared a long time ago. I cannot provide one myself, so I will see if there is something to be done in the FreeBSD infrastructure.

lib/sanitizer_common/sanitizer_linux.cc

240 ↗

(On Diff #100437)

The fstatat syscall was added in 2008, in FreeBSD 8.0. That particular version is now unsupported for ~7 years, so it is safe to assume the syscall exists in any recent (and usable) version of FreeBSD. :)

The getdirentries syscall used below is much older, even.

[dim]

Ping.

[vitalybuka]

LGTM

[krytarowski]

Why does this code live in a Linux file? Are there plans to split it out, rename?

[krytarowski]

I'm going to add there NetBSD in the near future.

[dim]

In D33600#772084, @krytarowski wrote:

Why does this code live in a Linux file? Are there plans to split it out, rename?

I guess because at that time it was easiest to add it with #ifdefs? At some point the ifdef maze will become too large, and then it will make sense to split it out, like the Mac and Windows versions.

[krytarowski]

In D33600#772087, @dim wrote:

In D33600#772084, @krytarowski wrote:

Why does this code live in a Linux file? Are there plans to split it out, rename?

I guess because at that time it was easiest to add it with #ifdefs? At some point the ifdef maze will become too large, and then it will make sense to split it out, like the Mac and Windows versions.

There is also an option to rename it to something generic like "posix". For now I will add NetBSD ifdefs and we will evaluate afterwards.

compiler-rt/trunk/lib/sanitizer_common/sanitizer_linux.cc

 #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
static void kernel_stat_to_stat(struct kernel_stat *in, struct stat *out) {
   out->st_mtime = in->st_mtime_nsec;
   out->st_ctime = in->st_ctime_nsec;
   out->st_ino = in->st_ino;
 }
 #endif
 
 uptr internal_stat(const char *path, void *buf) {
 #if SANITIZER_FREEBSD
-  return internal_syscall(SYSCALL(stat), path, buf);
+  return internal_syscall(SYSCALL(fstatat), AT_FDCWD, (uptr)path,
+                          (uptr)buf, 0);
 #elif SANITIZER_USES_CANONICAL_LINUX_SYSCALLS
   return internal_syscall(SYSCALL(newfstatat), AT_FDCWD, (uptr)path,
                           (uptr)buf, 0);
 #elif SANITIZER_LINUX_USES_64BIT_SYSCALLS
 # if defined(__mips64)
   // For mips64, stat syscall fills buffer in the format of kernel_stat
   struct kernel_stat kbuf;
   int res = internal_syscall(SYSCALL(stat), path, &kbuf);
   kernel_stat_to_stat(&kbuf, (struct stat *)buf);
   return res;
 # else
   return internal_syscall(SYSCALL(stat), (uptr)path, (uptr)buf);
 # endif
 #else
   struct stat64 buf64;
   int res = internal_syscall(SYSCALL(stat64), path, &buf64);
   stat64_to_stat(&buf64, (struct stat *)buf);
   return res;
 #endif
 }
 
 uptr internal_lstat(const char *path, void *buf) {
 #if SANITIZER_FREEBSD
-  return internal_syscall(SYSCALL(lstat), path, buf);
+  return internal_syscall(SYSCALL(fstatat), AT_FDCWD, (uptr)path,
+                          (uptr)buf, AT_SYMLINK_NOFOLLOW);
 #elif SANITIZER_USES_CANONICAL_LINUX_SYSCALLS
   return internal_syscall(SYSCALL(newfstatat), AT_FDCWD, (uptr)path,
                          (uptr)buf, AT_SYMLINK_NOFOLLOW);
 #elif SANITIZER_LINUX_USES_64BIT_SYSCALLS
 # if SANITIZER_MIPS64
   // For mips64, lstat syscall fills buffer in the format of kernel_stat
   struct kernel_stat kbuf;
   int res = internal_syscall(SYSCALL(lstat), path, &kbuf);
uptr internal_getpid() {
   return internal_syscall(SYSCALL(getpid));
 }
 
 uptr internal_getppid() {
   return internal_syscall(SYSCALL(getppid));
 }
 
 uptr internal_getdents(fd_t fd, struct linux_dirent *dirp, unsigned int count) {
-#if SANITIZER_USES_CANONICAL_LINUX_SYSCALLS
+#if SANITIZER_FREEBSD
+  return internal_syscall(SYSCALL(getdirentries), fd, (uptr)dirp, count, NULL);
+#elif SANITIZER_USES_CANONICAL_LINUX_SYSCALLS
   return internal_syscall(SYSCALL(getdents64), fd, (uptr)dirp, count);
 #else
   return internal_syscall(SYSCALL(getdents), fd, (uptr)dirp, count);
 #endif
 }
 
 uptr internal_lseek(fd_t fd, OFF_T offset, int whence) {
   return internal_syscall(SYSCALL(lseek), fd, offset, whence);

compiler-rt/trunk/lib/sanitizer_common/sanitizer_platform_limits_posix.h

 #include "sanitizer_internal_defs.h"
 #include "sanitizer_platform.h"
 
 #if SANITIZER_FREEBSD
 // FreeBSD's dlopen() returns a pointer to an Obj_Entry structure that
 // incorporates the map structure.
 # define GET_LINK_MAP_BY_DLOPEN_HANDLE(handle) \
     ((link_map*)((handle) == nullptr ? nullptr : ((char*)(handle) + 544)))
+// Get sys/_types.h, because that tells us whether 64-bit inodes are
+// used in struct dirent below.
+#include <sys/_types.h>
 #else
 # define GET_LINK_MAP_BY_DLOPEN_HANDLE(handle) ((link_map*)(handle))
 #endif  // !SANITIZER_FREEBSD
 
 #ifndef __GLIBC_PREREQ
 #define __GLIBC_PREREQ(x, y) 0
 #endif
 
#if SANITIZER_MAC
   struct __sanitizer_dirent {
     unsigned long long d_ino;
     unsigned long long d_seekoff;
     unsigned short d_reclen;
     // more fields that we don't care about
   };
 #elif SANITIZER_FREEBSD
   struct __sanitizer_dirent {
+#if defined(__INO64)
+    unsigned long long d_fileno;
+    unsigned long long d_off;
+#else
     unsigned int d_fileno;
+#endif
     unsigned short d_reclen;
     // more fields that we don't care about
   };
 #elif SANITIZER_ANDROID || defined(__x86_64__)
   struct __sanitizer_dirent {
     unsigned long long d_ino;
     unsigned long long d_off;
     unsigned short d_reclen;