Date: Tue, 23 Mar 2010 12:14:12 +0100 From: Grzegorz Bernacki <gjb@semihalf.com> To: Mark Tinguely <tinguely@casselton.net> Cc: freebsd-arm@freebsd.org, cognet@freebsd.org Subject: Re: Performance of SheevaPlug on 8-stable Message-ID: <4BA8A284.1060508@semihalf.com> In-Reply-To: <201003221626.o2MGQ9n8074143@casselton.net> References: <201003221626.o2MGQ9n8074143@casselton.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Mark Tinguely wrote:
> On Mon, 22 Mar 2010 16:06:33 Olivier Houchard said:
>> On Mon, Mar 22, 2010 at 09:55:04AM -0500, Mark Tinguely wrote:
>> > On Mon, 08 Mar 2010 16:50:58, Grzegorz Bernacki said:
>> >
>> > > This is probably caused by mechanism which turns of cache for shared pages.
>> > > When I add applied following path:
>> > >
>> > > diff --git a/sys/arm/arm/pmap.c b/sys/arm/arm/pmap.c
>> > > index 390dc3c..d17c0cc 100644
>> > > --- a/sys/arm/arm/pmap.c
>> > > +++ b/sys/arm/arm/pmap.c
>> > > @@ -1401,6 +1401,8 @@ pmap_fix_cache(struct vm_page *pg, pmap_t pm, vm_offset_t va)
>> > > */
>> > >
>> > > TAILQ_FOREACH(pv, &pg->md.pv_list, pv_list) {
>> > > + if (pv->pv_flags & PVF_EXEC)
>> > > + return;
>> > > /* generate a count of the pv_entry uses */
>> > > if (pv->pv_flags & PVF_WRITE) {
>> > > if (pv->pv_pmap == pmap_kernel())
>> > >
>> > > execution time of 'test' program is:
>> > > mv78100-4# time ./test
>> > > 5.000u 0.000s 0:05.40 99.8% 40+1324k 0+0io 0pf+0w
>> > >
>> > > and without this path is:
>> > > mv78100-4# time ./test
>> > > 295.000u 0.000s 4:56.01 99.7% 40+1322k 0+0io 0pf+0w
>> > >
>> > >
>> > > I think we need to handle executable pages in different way.
>> > >
>> > > grzesiek
>> >
>> > Good going Oliver and thank-you on the pmap_enter_pv kernel map patch Revision
>> > 205425.
>> >
>> > Last week, before this patch, Maks Verver was so kind to put some statements
>> > in the VM (vm_page_free_toq()) for the SheevaPlug because I could not cause
>> > these paths with the Gumstix emulator. Maks, could you add to
>> > vm_phys_free_pages():
>> >
>> > if (m->md.pv_kva)
>> > + {
>> > + printf("vm_phys_free_pages: md.pv_kva 0x%08x\n", m->md.pv_kva);
>> > m->md.pv_kva = 0;
>> > + }
>> >
>> > Even on the Gumstix emulator with the current patch, pmap_fix_cache() still
>> > has many executable pages that have both a kernel and user pv_entry. Looks
>> > like something like the above patch is still needed.
>> >
>> I added a few printf and saw the same thing, however isn't assuming we
>> shouldn't modify the cache settings if the page is executable a bit dangerous ?
>> Or did I misread your patch ?
>>
>> Olivier
>
> The pmap_fix_cache() PVF_EXEC is Grzegorz's patch. In his defense, he
> later stated that we may need to flush the buffer. If the kernel map
> is a read-in page, the DMA probably did a POST-READ flush; the user page
> if was previously accessed - <thinking as I type: why should it?> - could
> be stale and need to be invalidated.
Patch I've send is not a solution for this problem. I just send it to show
that excluding executable pages from fix_cache mechanism fixes the problem
and as I wrote in this mail, we need to handle executable pages with writable
kernel mapping differently.
I think that Mark is right. Kernel mapping should be already flushed out (we
can just do it again to make sure). I am not sure it there is any chance that
user mapping can have some cached data.
grzesiek
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4BA8A284.1060508>