libstore/local-derivation-goal: prohibit creating setuid/setgid binaries

With Linux kernel >=6.6 & glibc 2.39 a `fchmodat2(2)` is available that
isn't filtered away by the libseccomp sandbox.

Being able to use this to bypass that restriction has surprising results
for some builds such as lxc[1]:

> With kernel ≥6.6 and glibc 2.39, lxc's install phase uses fchmodat2,
> which slips through 9b88e52846/src/libstore/build/local-derivation-goal.cc (L1650-L1663).
> The fixupPhase then uses fchmodat, which fails.
> With older kernel or glibc, setting the suid bit fails in the
> install phase, which is not treated as fatal, and then the
> fixup phase does not try to set it again.

Please note that there are still ways to bypass this sandbox[2] and this is
mostly a fix for the breaking builds.

This change works by creating a syscall filter for the `fchmodat2`
syscall (number 452 on most systems). The problem is that glibc 2.39
and seccomp 2.5.5 are needed to have the correct syscall number available
via `__NR_fchmodat2` / `__SNR_fchmodat2`, but this flake is still on
nixpkgs 23.11. To have this change everywhere and not dependent on the
glibc this package is built against, I added a header
"fchmodat2-compat.hh" that sets the syscall number based on the
architecture. On most platforms its 452 according to glibc with a few
exceptions:

    $ rg --pcre2 'define __NR_fchmodat2 (?!452)'
    sysdeps/unix/sysv/linux/x86_64/x32/arch-syscall.h
    58:#define __NR_fchmodat2 1073742276

    sysdeps/unix/sysv/linux/mips/mips64/n32/arch-syscall.h
    67:#define __NR_fchmodat2 6452

    sysdeps/unix/sysv/linux/mips/mips64/n64/arch-syscall.h
    62:#define __NR_fchmodat2 5452

    sysdeps/unix/sysv/linux/mips/mips32/arch-syscall.h
    70:#define __NR_fchmodat2 4452

    sysdeps/unix/sysv/linux/alpha/arch-syscall.h
    59:#define __NR_fchmodat2 562

I tested the change by adding the diff below as patch to
`pkgs/tools/package-management/nix/common.nix` & then built a VM from
the following config using my dirty nixpkgs master:

    {
      vm = { pkgs, ... }: {
        virtualisation.writableStore = true;
        virtualisation.memorySize = 8192;
        virtualisation.diskSize = 12 * 1024;
        nix.package = pkgs.nixVersions.nix_2_21;
      };
    }

The original issue can be triggered via

    nix build -L github:nixos/nixpkgs/d6dc19adbda4fd92fe9a332327a8113eaa843894#lxc \
      --extra-experimental-features 'nix-command flakes'

however the problem disappears with this patch applied.

Closes #10424

[1] https://github.com/NixOS/nixpkgs/issues/300635#issuecomment-2031073804
[2] https://github.com/NixOS/nixpkgs/issues/300635#issuecomment-2030844251

src/libstore/linux/fchmodat2-compat.hh

@@ -0,0 +1,34 @@
+/*
+ * Determine the syscall number for `fchmodat2`.
+ *
+ * On most platforms this is 452. Exceptions can be found on
+ * a glibc git checkout via `rg --pcre2 'define __NR_fchmodat2 (?!452)'`.
+ *
+ * The problem is that glibc 2.39 and libseccomp 2.5.5 are needed to
+ * get the syscall number. However, a Nix built against nixpkgs 23.11
+ * (glibc 2.38) should still have the issue fixed without depending
+ * on the build environment.
+ *
+ * To achieve that, the macros below try to determine the platform and
+ * set the syscall number which is platform-specific, but
+ * in most cases 452.
+ *
+ * TODO: remove this when 23.11 is EOL and the entire (supported) ecosystem
+ * is on glibc 2.39.
+ */
+
+#if HAVE_SECCOMP
+#  if defined(__alpha__)
+#    define NIX_SYSCALL_FCHMODAT2 562
+#  elif defined(__x86_64__) && SIZE_MAX == 0xFFFFFFFF // x32
+#    define NIX_SYSCALL_FCHMODAT2 1073742276
+#  elif defined(__mips__) && defined(__mips64) && defined(_ABIN64) // mips64/n64
+#    define NIX_SYSCALL_FCHMODAT2 5452
+#  elif defined(__mips__) && defined(__mips64) && defined(_ABIN32) // mips64/n32
+#    define NIX_SYSCALL_FCHMODAT2 6452
+#  elif defined(__mips__) && defined(_ABIO32) // mips32
+#    define NIX_SYSCALL_FCHMODAT2 4452
+#  else
+#    define NIX_SYSCALL_FCHMODAT2 452
+#  endif
+#endif // HAVE_SECCOMP

src/libstore/unix/build/local-derivation-goal.cc

@@ -37,6 +37,7 @@
 
 /* Includes required for chroot support. */
 #if __linux__
+# include "linux/fchmodat2-compat.hh"
 # include <sys/ioctl.h>
 # include <net/if.h>
 # include <netinet/ip.h>
@@ -1672,6 +1673,10 @@ void setupSeccomp()
         if (seccomp_rule_add(ctx, SCMP_ACT_ERRNO(EPERM), SCMP_SYS(fchmodat), 1,
                 SCMP_A2(SCMP_CMP_MASKED_EQ, (scmp_datum_t) perm, (scmp_datum_t) perm)) != 0)
             throw SysError("unable to add seccomp rule");
+
+        if (seccomp_rule_add(ctx, SCMP_ACT_ERRNO(EPERM), NIX_SYSCALL_FCHMODAT2, 1,
+                SCMP_A2(SCMP_CMP_MASKED_EQ, (scmp_datum_t) perm, (scmp_datum_t) perm)) != 0)
+            throw SysError("unable to add seccomp rule");
     }
 
     /* Prevent builders from creating EAs or ACLs. Not all filesystems