On Sun, Dec 18, 2005 at 10:46:57PM +0100, pageexec@freemail.hu wrote:
> On 18 Dec 2005 at 23:05, matthew green wrote:
> >    ASLR calculates 3 random values on execution and saves these as offsets
> >    to be used when a random value is needed. How expensive are 3
> >    arc4random() calls in the context of an entire sys_execve()?
> > 
> > 
> > you fail to understand the performance issue here.  when, eg, libc is
> > not mapped at the same address as other processes, the performance hit
> > is in the range of 30-40% on some platforms.  it's not about start up
> > it is about the MMU being constantly trashed.
> 
> (while waiting for more details on this VI cache issue)

There are several issues.  The most obvious one, it seems to me, is that
this is going to repeatedly flush and reload libc when it ought to stay
resident in the cache, since it will be at a different virtual address in
each process.  If that's not the case, I'd like to know why it's not the
case.