Add an internal wrapper for clone, clone2 and clone3

The clone3 system call (since Linux 5.3) provides a superset of the
functionality of clone and clone2.  It also provides a number of API
improvements, including the ability to specify the size of the child's
stack area which can be used by kernel to compute the shadow stack size
when allocating the shadow stack.  Add:

extern int __clone_internal (struct clone_args *__cl_args,
			     int (*__func) (void *__arg), void *__arg);

to provide an abstract interface for clone, clone2 and clone3.

1. Simplify stack management for thread creation by passing both stack
base and size to create_thread.
2. Consolidate clone vs clone2 differences into a single file.
3. Call __clone3 if HAVE_CLONE3_WAPPER is defined.  If __clone3 returns
-1 with ENOSYS, fall back to clone or clone2.
4. Use only __clone_internal to clone a thread.  Since the stack size
argument for create_thread is now unconditional, always pass stack size
to create_thread.
5. Enable the public clone3 wrapper in the future after it has been
added to all targets.

NB: Sandbox will return ENOSYS on clone3 in both Chromium:

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src/+/218438259dd795456f0a48f67cbe5b4e520db88b

commit 218438259dd795456f0a48f67cbe5b4e520db88b
Author: Matthew Denton <mpdenton@chromium.org>
Date: Thu Jun 03 20:06:13 2021

Linux sandbox: return ENOSYS for clone3

Because clone3 uses a pointer argument rather than a flags argument, we
cannot examine the contents with seccomp, which is essential to
preventing sandboxed processes from starting other processes. So, we
won't be able to support clone3 in Chromium. This CL modifies the
BPF policy to return ENOSYS for clone3 so glibc always uses the fallback
to clone.

Bug: 1213452
Change-Id: I7c7c585a319e0264eac5b1ebee1a45be2d782303
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/2936184
Reviewed-by: Robert Sesek <rsesek@chromium.org>
Commit-Queue: Matthew Denton <mpdenton@chromium.org>
Cr-Commit-Position: refs/heads/master@{#888980}

[modify] https://crrev.com/218438259dd795456f0a48f67cbe5b4e520db88b/sandbox/linux/seccomp-bpf-helpers/baseline_policy.cc

and Firefox:

https://hg.mozilla.org/integration/autoland/rev/ecb4011a0c76

Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>

1 files changed, 9 insertions, 17 deletions

diff --git a/sysdeps/unix/sysv/linux/spawni.c b/sysdeps/unix/sysv/linux/spawni.c
index f7e7353a05..6b0bade4d4 100644
--- a/sysdeps/unix/sysv/linux/spawni.c
+++ b/sysdeps/unix/sysv/linux/spawni.c
@@ -26,6 +26,7 @@
 #include <spawn_int.h>
 #include <sysdep.h>
 #include <sys/resource.h>
+#include <clone_internal.h>
 
 /* The Linux implementation of posix_spawn{p} uses the clone syscall directly
    with CLONE_VM and CLONE_VFORK flags and an allocated stack.  The new stack
@@ -53,21 +54,6 @@
    normal program exit with the exit code 127.  */
 #define SPAWN_ERROR	127
 
-#ifdef __ia64__
-# define CLONE(__fn, __stackbase, __stacksize, __flags, __args) \
-  __clone2 (__fn, __stackbase, __stacksize, __flags, __args, 0, 0, 0)
-#else
-# define CLONE(__fn, __stack, __stacksize, __flags, __args) \
-  __clone (__fn, __stack, __flags, __args)
-#endif
-
-/* Since ia64 wants the stackbase w/clone2, re-use the grows-up macro.  */
-#if _STACK_GROWS_UP || defined (__ia64__)
-# define STACK(__stack, __stack_size) (__stack)
-#elif _STACK_GROWS_DOWN
-# define STACK(__stack, __stack_size) (__stack + __stack_size)
-#endif
-
 
 struct posix_spawn_args
 {
@@ -382,8 +368,14 @@ __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).  */
-  new_pid = CLONE (__spawni_child, STACK (stack, stack_size), stack_size,
-		   CLONE_VM | CLONE_VFORK | SIGCHLD, &args);
+  struct clone_args clone_args =
+    {
+      .flags = CLONE_VM | CLONE_VFORK,
+      .exit_signal = SIGCHLD,
+      .stack = (uintptr_t) stack,
+      .stack_size = stack_size,
+    };
+  new_pid = __clone_internal (&clone_args, __spawni_child, &args);
 
   /* It needs to collect the case where the auxiliary process was created
      but failed to execute the file (due either any preparation step or