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>

2 files changed, 27 insertions, 70 deletions

diff --git a/nptl/allocatestack.c b/nptl/allocatestack.c
index 9be6c42..cfe37a3 100644
--- a/nptl/allocatestack.c
+++ b/nptl/allocatestack.c
@@ -33,47 +33,6 @@
 #include <kernel-features.h>
 #include <nptl-stack.h>
 
-#ifndef NEED_SEPARATE_REGISTER_STACK
-
-/* Most architectures have exactly one stack pointer.  Some have more.  */
-# define STACK_VARIABLES void *stackaddr = NULL
-
-/* How to pass the values to the 'create_thread' function.  */
-# define STACK_VARIABLES_ARGS stackaddr
-
-/* How to declare function which gets there parameters.  */
-# define STACK_VARIABLES_PARMS void *stackaddr
-
-/* How to declare allocate_stack.  */
-# define ALLOCATE_STACK_PARMS void **stack
-
-/* This is how the function is called.  We do it this way to allow
-   other variants of the function to have more parameters.  */
-# define ALLOCATE_STACK(attr, pd) allocate_stack (attr, pd, &stackaddr)
-
-#else
-
-/* We need two stacks.  The kernel will place them but we have to tell
-   the kernel about the size of the reserved address space.  */
-# define STACK_VARIABLES void *stackaddr = NULL; size_t stacksize = 0
-
-/* How to pass the values to the 'create_thread' function.  */
-# define STACK_VARIABLES_ARGS stackaddr, stacksize
-
-/* How to declare function which gets there parameters.  */
-# define STACK_VARIABLES_PARMS void *stackaddr, size_t stacksize
-
-/* How to declare allocate_stack.  */
-# define ALLOCATE_STACK_PARMS void **stack, size_t *stacksize
-
-/* This is how the function is called.  We do it this way to allow
-   other variants of the function to have more parameters.  */
-# define ALLOCATE_STACK(attr, pd) \
-  allocate_stack (attr, pd, &stackaddr, &stacksize)
-
-#endif
-
-
 /* Default alignment of stack.  */
 #ifndef STACK_ALIGN
 # define STACK_ALIGN __alignof__ (long double)
@@ -252,7 +211,7 @@ advise_stack_range (void *mem, size_t size, uintptr_t pd, size_t guardsize)
    PDP must be non-NULL.  */
 static int
 allocate_stack (const struct pthread_attr *attr, struct pthread **pdp,
-		ALLOCATE_STACK_PARMS)
+		void **stack, size_t *stacksize)
 {
   struct pthread *pd;
   size_t size;
@@ -603,25 +562,17 @@ allocate_stack (const struct pthread_attr *attr, struct pthread **pdp,
   /* We place the thread descriptor at the end of the stack.  */
   *pdp = pd;
 
-#if _STACK_GROWS_DOWN
   void *stacktop;
 
-# if TLS_TCB_AT_TP
+#if TLS_TCB_AT_TP
   /* The stack begins before the TCB and the static TLS block.  */
   stacktop = ((char *) (pd + 1) - tls_static_size_for_stack);
-# elif TLS_DTV_AT_TP
+#elif TLS_DTV_AT_TP
   stacktop = (char *) (pd - 1);
-# endif
+#endif
 
-# ifdef NEED_SEPARATE_REGISTER_STACK
+  *stacksize = stacktop - pd->stackblock;
   *stack = pd->stackblock;
-  *stacksize = stacktop - *stack;
-# else
-  *stack = stacktop;
-# endif
-#else
-  *stack = pd->stackblock;
-#endif
 
   return 0;
 }
diff --git a/nptl/pthread_create.c b/nptl/pthread_create.c
index 440adc2..d8ec299 100644
--- a/nptl/pthread_create.c
+++ b/nptl/pthread_create.c
@@ -36,6 +36,7 @@
 #include "libioP.h"
 #include <sys/single_threaded.h>
 #include <version.h>
+#include <clone_internal.h>
 
 #include <shlib-compat.h>
 
@@ -227,8 +228,8 @@ late_init (void)
 static int _Noreturn start_thread (void *arg);
 
 static int create_thread (struct pthread *pd, const struct pthread_attr *attr,
-			  bool *stopped_start, STACK_VARIABLES_PARMS,
-			  bool *thread_ran)
+			  bool *stopped_start, void *stackaddr,
+			  size_t stacksize, bool *thread_ran)
 {
   /* Determine whether the newly created threads has to be started
      stopped since we have to set the scheduling parameters or set the
@@ -280,14 +281,18 @@ static int create_thread (struct pthread *pd, const struct pthread_attr *attr,
 
   TLS_DEFINE_INIT_TP (tp, pd);
 
-#ifdef __NR_clone2
-# define ARCH_CLONE __clone2
-#else
-# define ARCH_CLONE __clone
-#endif
-  if (__glibc_unlikely (ARCH_CLONE (&start_thread, STACK_VARIABLES_ARGS,
-				    clone_flags, pd, &pd->tid, tp, &pd->tid)
-			== -1))
+  struct clone_args args =
+    {
+      .flags = clone_flags,
+      .pidfd = (uintptr_t) &pd->tid,
+      .parent_tid = (uintptr_t) &pd->tid,
+      .child_tid = (uintptr_t) &pd->tid,
+      .stack = (uintptr_t) stackaddr,
+      .stack_size = stacksize,
+      .tls = (uintptr_t) tp,
+    };
+  int ret = __clone_internal (&args, &start_thread, pd);
+  if (__glibc_unlikely (ret == -1))
     return errno;
 
   /* It's started now, so if we fail below, we'll have to let it clean itself
@@ -576,7 +581,8 @@ int
 __pthread_create_2_1 (pthread_t *newthread, const pthread_attr_t *attr,
 		      void *(*start_routine) (void *), void *arg)
 {
-  STACK_VARIABLES;
+  void *stackaddr = NULL;
+  size_t stacksize = 0;
 
   /* Avoid a data race in the multi-threaded case, and call the
      deferred initialization only once.  */
@@ -600,7 +606,7 @@ __pthread_create_2_1 (pthread_t *newthread, const pthread_attr_t *attr,
     }
 
   struct pthread *pd = NULL;
-  int err = ALLOCATE_STACK (iattr, &pd);
+  int err = allocate_stack (iattr, &pd, &stackaddr, &stacksize);
   int retval = 0;
 
   if (__glibc_unlikely (err != 0))
@@ -744,8 +750,8 @@ __pthread_create_2_1 (pthread_t *newthread, const pthread_attr_t *attr,
 
       /* We always create the thread stopped at startup so we can
 	 notify the debugger.  */
-      retval = create_thread (pd, iattr, &stopped_start,
-			      STACK_VARIABLES_ARGS, &thread_ran);
+      retval = create_thread (pd, iattr, &stopped_start, stackaddr,
+			      stacksize, &thread_ran);
       if (retval == 0)
 	{
 	  /* We retain ownership of PD until (a) (see CONCURRENCY NOTES
@@ -776,8 +782,8 @@ __pthread_create_2_1 (pthread_t *newthread, const pthread_attr_t *attr,
 	}
     }
   else
-    retval = create_thread (pd, iattr, &stopped_start,
-			    STACK_VARIABLES_ARGS, &thread_ran);
+    retval = create_thread (pd, iattr, &stopped_start, stackaddr,
+			    stacksize, &thread_ran);
 
   /* Return to the previous signal mask, after creating the new
      thread.  */