[uml-devel] why allocate page for stack in clone(, stack, ~CLONE_VM & (...)) ?

[uml-devel] why allocate page for stack in clone(, stack, ~CLONE_VM & (...)) ?

[John Reiser]

In arch/um/os/start_up.c, function start_ptraced_child() does:
        pid = clone(ptrace_child, (void *) sp, SIGCHLD, NULL);
where sp points into a newly- mmap()ed page.  Instead, why not
avoid the mmap() entirely via:
        pid = clone(ptrace_child, NULL,        SIGCHLD, NULL);

Because the flags to clone() do not contain CLONE_VM, then the clone()
is equivalent to a fork() with respect to address space.  The child does not
share VM with the parent, and using the same addresses for the stack
causes no overwrites.  Perhaps the Dcache efficiency is slightly
less, but much less costly than mmap() and the eventual munmap().

-- 
John Reiser, jreiser@BitWagon.com

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel

Re: [uml-devel] why allocate page for stack in clone(, stack, ~CLONE_VM & (...)) ?

[Jeff Dike]

On Thu, Nov 01, 2007 at 03:05:32PM -0700, John Reiser wrote:
> In arch/um/os/start_up.c, function start_ptraced_child() does:
>         pid = clone(ptrace_child, (void *) sp, SIGCHLD, NULL);
> where sp points into a newly- mmap()ed page.  Instead, why not
> avoid the mmap() entirely via:
>         pid = clone(ptrace_child, NULL,        SIGCHLD, NULL);
> 
> Because the flags to clone() do not contain CLONE_VM, then the clone()
> is equivalent to a fork() with respect to address space.

If you look at what's currently in mainline, you'll see it does
exactly what you suggest - the patch in question is this one:
	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=3cdaf45578b9aa1eb748d0a32678ee5a0180575b

				Jeff

-- 
Work email - jdike at linux dot intel dot com

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel