Re: [PATCH] Enable mprotect on huge pages
From: David Gibson
Date: Tue Feb 28 2006 - 03:22:55 EST
On Tue, Feb 28, 2006 at 11:23:54AM +0800, Zhang, Yanmin wrote:
> On Tue, 2006-02-28 at 09:34, Andrew Morton wrote:
> > "Zhang, Yanmin" <yanmin_zhang@xxxxxxxxxxxxxxx> wrote:
> > >
> > > > > > > 2.6.16-rc3 uses hugetlb on-demand paging, but it doesn_t support hugetlb
> > > > > > > mprotect. My patch against 2.6.16-rc3 enables this capability.
> > >
> > > Based on David's comments, I worked out a new patch against 2.6.16-rc4.
> > > Thank David.
> > >
> >
> > Please always send an updated changelog when sending an updated patch.
> > Otherwise I have to go trolling back through the email thread to find it,
> > then work out what needs to be changed.
> Thanks for your kind reminder. I would do so next time.
>
> >
> > >
> > > I tested it on i386/x86_64/ia64. Who could help test it on other
> > > platforms, such like PPC64?
> >
> > I can do that - please send me your test app?
> I attach a test case. It will create directory /mnt/hugepages and delete it
> after testing automatically.
>
> To run it by user root:
> #gcc -o mprotect_testcase mprotect_testcase.c
> #echo "5">/proc/sys/vm/nr_hugepages
> #./mprotect_testcase
>
> You could use gdb to step it to see the changing of the process vma maps.
I've just added a simpler testcase than this one to the libhugetlbfs
testsuite. Both R->RW and RW->R transitions appear to work (I haven't
tested EXEC transitions yet, that's hairier).
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/