[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH] don't use mlock() with Solaris tools


  • To: veillard@xxxxxxxxxx
  • From: "Mark Johnson" <johnson.nh@xxxxxxxxx>
  • Date: Fri, 20 Oct 2006 16:11:30 -0700
  • Cc: xen-devel@xxxxxxxxxxxxxxxxxxx, John Levon <levon@xxxxxxxxxxxxxxxxx>
  • Delivery-date: Sat, 21 Oct 2006 03:55:22 -0700
  • Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=mEEddvSLpQY2WjPOdBl8nlq5pOo0AKIS4Ei4P6fQIIkHxbhnQ6WIJT+fIy1RRCVznfkudnIii0cbNFf91JsYK5OLKtuR7UMWgW+9VH8uZ69E8YHF0Kr1NbrdUDbVY7o9XulEuU22skVAh++25h45amQ5hWd9OwAIQu+GzI0OnmI=
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>

On 10/20/06, Daniel Veillard <veillard@xxxxxxxxxx> wrote:
On Fri, Oct 20, 2006 at 04:42:47AM +0100, John Levon wrote:
> on solaris: mlock requires a page aligned address and mlock doesn't ensure 
the pages won't minor page fault; so don't use it on solaris.
[...]
> -/* NB: arr must be mlock'ed */
> +int lock_pages(void *addr, size_t len)
> +{
> +      int e = 0;
> +#ifndef __sun__
> +      e = mlock(addr, len);
> +#endif
> +      return (e);
> +}
> +
> +void unlock_pages(void *addr, size_t len)
> +{
> +#ifndef __sun__
> +     safe_munlock(addr, len);
> +#endif
> +}
> +

  So on Solaris you don't pin down the memory used for hypercall parameters
and results at all ? Is there really no risk associated with this strategy ?

  surprised,

We have to pin it down in the privcmd driver. There is no way to
ping the memory from a user app.


MRJ

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.