linux: Add posix_spawnattr_{get, set}cgroup_np (BZ 26371)

These functions allow to posix_spawn and posix_spawnp to use
CLONE_INTO_CGROUP with clone3, allowing the child process to
be created in a different cgroup version 2.  These are GNU
extensions that are available only for Linux, and also only
for the architectures that implement clone3 wrapper
(HAVE_CLONE3_WRAPPER).

To create a process on a different cgroupv2, one can use the:

  posix_spawnattr_t attr;
  posix_spawnattr_init (&attr);
  posix_spawnattr_setflags (&attr, POSIX_SPAWN_SETCGROUP);
  posix_spawnattr_setcgroup_np (&attr, cgroup);
  posix_spawn (...)

Similar to other posix_spawn flags, POSIX_SPAWN_SETCGROUP control
whether the cgroup file descriptor will be used or not with
clone3.

There is no fallback if either clone3 does not support the flag
or if the architecture does not provide the clone3 wrapper, in
this case posix_spawn returns EOPNOTSUPP.

Checked on x86_64-linux-gnu.

Reviewed-by: Florian Weimer <fweimer@redhat.com>

1 files changed, 19 insertions, 3 deletions

diff --git a/sysdeps/unix/sysv/linux/spawni.c b/sysdeps/unix/sysv/linux/spawni.c
index ec687cb423..f0d4c62ae6 100644
--- a/sysdeps/unix/sysv/linux/spawni.c
+++ b/sysdeps/unix/sysv/linux/spawni.c
@@ -380,14 +380,19 @@ __spawnix (pid_t * pid, const char *file,
      need for CLONE_SETTLS.  Although parent and child share the same TLS
      namespace, there will be no concurrent access for TLS variables (errno
      for instance).  */
+  bool set_cgroup = attrp ? (attrp->__flags & POSIX_SPAWN_SETCGROUP) : false;
   struct clone_args clone_args =
     {
       /* Unsupported flags like CLONE_CLEAR_SIGHAND will be cleared up by
 	 __clone_internal_fallback.  */
-      .flags = CLONE_CLEAR_SIGHAND | CLONE_VM | CLONE_VFORK,
+      .flags = (set_cgroup ? CLONE_INTO_CGROUP : 0)
+	       | CLONE_CLEAR_SIGHAND
+	       | CLONE_VM
+	       | CLONE_VFORK,
       .exit_signal = SIGCHLD,
       .stack = (uintptr_t) stack,
       .stack_size = stack_size,
+      .cgroup = (set_cgroup ? attrp->__cgroup : 0)
     };
 #ifdef HAVE_CLONE3_WRAPPER
   args.use_clone3 = true;
@@ -398,8 +403,19 @@ __spawnix (pid_t * pid, const char *file,
 #endif
     {
       args.use_clone3 = false;
-      new_pid = __clone_internal_fallback (&clone_args, __spawni_child,
-					   &args);
+      if (!set_cgroup)
+	new_pid = __clone_internal_fallback (&clone_args, __spawni_child,
+					     &args);
+      else
+	{
+	  /* No fallback for POSIX_SPAWN_SETCGROUP if clone3 is not
+	     supported.  */
+	  new_pid = -1;
+#ifdef HAVE_CLONE3_WRAPPER
+	  if (errno == ENOSYS)
+#endif
+	    errno = ENOTSUP;
+	}
     }
 
   /* It needs to collect the case where the auxiliary process was created