Re: How much of a mess does OpenVZ make? ;) Was: What can OpenVZ do?

Hi Serge:
I made a patch based on Oren's tree recently which implement a new
syscall clone_with_pid. I tested with checkpoint/restart process tree
and it works as expected.
This patch has some hack in it which i made a copy of libc's clone and
made modifications of passing one more argument(pid number). I will
try to clean up the code and do more testing.

New syscall clone_with_pid
Implement a new syscall which clone a thread with a preselected pid number.

clone_with_pid(child_func, child_stack + CHILD_STACK - 16,
			CLONE_WITH_PID|SIGCHLD, pid, NULL);

Signed-off-by: Ying Han <redacted>

diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 87803da..b5a1b03 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h

@@ -26,6 +26,7 @@ asmlinkage int sys_fork(struct pt_regs);
 asmlinkage int sys_clone(struct pt_regs);
 asmlinkage int sys_vfork(struct pt_regs);
 asmlinkage int sys_execve(struct pt_regs);
+asmlinkage int sys_clone_with_pid(struct pt_regs);

 /* kernel/signal_32.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);

diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32
index a5f9e09..f10ca0e 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h

@@ -340,6 +340,7 @@
 #define __NR_inotify_init1	332
 #define __NR_checkpoint		333
 #define __NR_restart		334
+#define __NR_clone_with_pid	335

 #ifdef __KERNEL__

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0a1302f..88ae634 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c

@@ -8,7 +8,6 @@
 /*
  * This file handles the architecture-dependent parts of process handling..
  */
-
 #include <stdarg.h>

 #include <linux/cpu.h>

@@ -652,6 +651,28 @@ asmlinkage int sys_clone(struct pt_regs regs)
 	return do_fork(clone_flags, newsp, &regs, 0, parent_tidptr, child_tidptr);
 }

+/**
+ * sys_clone_with_pid - clone a thread with pre-select pid number.
+ */
+asmlinkage int sys_clone_with_pid(struct pt_regs regs)
+{
+	unsigned long clone_flags;
+	unsigned long newsp;
+	int __user *parent_tidptr, *child_tidptr;
+	pid_t pid_nr;
+
+	clone_flags = regs.bx;
+	newsp = regs.cx;
+	parent_tidptr = (int __user *)regs.dx;
+	child_tidptr = (int __user *)regs.di;
+	pid_nr = regs.bp;

+	if (!newsp)
+		newsp = regs.sp;
+	return do_fork(clone_flags, newsp, &regs, pid_nr, parent_tidptr,
+			child_tidptr);
+}
+
 /*
  * This is trivial, and on the face of it looks like it
  * could equally well be done in user mode.

diff --git a/kernel/fork.c b/kernel/fork.c
index 085ce56..262ae1e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c

@@ -10,7 +10,7 @@
  * Fork is rather simple, once you get the hang of it, but the memory
  * management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
  */
-
+#define DEBUG
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/unistd.h>

@@ -959,10 +959,19 @@ static struct task_struct *copy_process(unsigned long cl
 	int retval;
 	struct task_struct *p;
 	int cgroup_callbacks_done = 0;
+	pid_t clone_pid = stack_size;