xen: Use wmb instead of rmb in xen_evtchn_do_upcall().

This patch is ported one from 534:77db69c38249 of
linux-2.6.18-xen.hg.
Use wmb instead of rmb to enforce ordering between
evtchn_upcall_pending and evtchn_pending_sel stores
in xen_evtchn_do_upcall().

Cc: Samuel Thibault <samuel.thibaulteu.citrix.com>
Signed-off-by: Isaku Yamahata <yamahatavalinux.co.jp>
---
 drivers/xen/events.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 73d78dc..332dd63 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
 -529,7
+529,7  void xen_evtchn_do_upcall(struct pt_regs *regs)
 
 #ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a
barrier on x86. */
 		/* Clear master flag /before/ clearing selector flag. */
-		rmb();
+		wmb();
 #endif
 		pending_words =
xchg(&vcpu_info->evtchn_pending_sel, 0);
 		while (pending_words != 0) {
-- 
1.5.3

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devellists.xensource.com
http://list
s.xensource.com/xen-ia64-devel

On Tue, Jun 10, 2008 at 05:41:39PM +1000, Nick Piggin
wrote:
> On Tuesday 10 June 2008 17:35, Isaku Yamahata wrote:
> > This patch is ported one from 534:77db69c38249 of
linux-2.6.18-xen.hg.
> > Use wmb instead of rmb to enforce ordering
between
> > evtchn_upcall_pending and evtchn_pending_sel
stores
> > in xen_evtchn_do_upcall().
> 
> There are a whole load of places in the kernel that
should be using
> smp_ variants of memory barriers. This seemed to me
like one of them,
> but I could be wrong.

Thank you for your comment.
Non smp_ version is intentionally used.
Because here the synchronization is done between other guest
kernel
which might be running on another physical cpu. So non smp
version is
really necessary even if this kernel is build for UP.


> Also, if you do that can you get rid of the ifdef? If
it really *really*
> mattered, we could introduce smp_mb before/after
xchg... but if you
> use smp_wmb anyway then it definitely does not matter
because that is a
> noop on x86.

To be honest, I don't know whether the overhead of mb here
matters
on x86 or not. I'm wondering Jeremy might have an idea.


>
> 
> Thanks,
> Nick
> 
> >
>  Cc: Samuel Thibault <samuel.thibaulteu.citrix.com>
> > Signed-off-by: Isaku Yamahata <yamahatavalinux.co.jp>
> > ---
> >  drivers/xen/events.c |    2 +-
> >  1 files changed, 1 insertions(+), 1 deletions(-)
> >
> > diff --git a/drivers/xen/events.c
b/drivers/xen/events.c
> > index 73d78dc..332dd63 100644
> > --- a/drivers/xen/events.c
> > +++ b/drivers/xen/events.c
> >  -529,7 +529,7  void xen_evtchn_do_upcall(struct pt_regs
*regs)
> >
> >  #ifndef CONFIG_X86 /* No need for a barrier --
XCHG is a barrier on x86.
> > */ /* Clear master flag /before/ clearing selector
flag. */
> > -		rmb();
> > +		wmb();
> >  #endif
> >  		pending_words =
xchg(&vcpu_info->evtchn_pending_sel, 0);
> >  		while (pending_words != 0) {
> 

-- 
yamahata

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devellists.xensource.com
http://list
s.xensource.com/xen-ia64-devel