Re: [PATCH] x86:pvclock: add missing barriers

[Minfei Huang <mnghuan@gmail.com>]

On 06/08/16 at 09:45P, Borislav Petkov wrote:
> On Wed, Jun 08, 2016 at 09:11:39PM +0300, Roman Kagan wrote:
> > Gradual removal of excessive barriers in pvclock reading functions
> > (commits 502dfeff239e8313bfbe906ca0a1a6827ac8481b,
> > a3eb97bd80134ba07864ca00747466c02118aca1) ended up removing too much:
> > although rdtsc is now orderd WRT other loads, there's no protection
> > against the compiler reordering the loads of ->version with the loads of
> > other fields.
> > 
> > E.g. on my system gcc-5.3.1 generates code which loads ->system_time and
> > ->flags outside of the ->version test loop.
> > 
> > (Re)introduce the compiler barriers around accesses to the contents of
> > pvclock.  While at this, make the function a bit more compact by
> > removing unnecessary local variables.
> > 
> > Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
> > Cc: Thomas Gleixner <tglx@linutronix.de>
> > Cc: Ingo Molnar <mingo@redhat.com>
> > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > Cc: x86@kernel.org
> > Cc: Andy Lutomirski <luto@kernel.org>
> > Cc: Borislav Petkov <bp@suse.de>
> > Cc: Paolo Bonzini <pbonzini@redhat.com>
> > Cc: stable@vger.kernel.org
> > ---
> >  arch/x86/include/asm/pvclock.h | 17 +++++------------
> >  1 file changed, 5 insertions(+), 12 deletions(-)
> > 
> > diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
> > index fdcc040..65c4de2 100644
> > --- a/arch/x86/include/asm/pvclock.h
> > +++ b/arch/x86/include/asm/pvclock.h
> > @@ -80,18 +80,11 @@ static __always_inline
> >  unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
> >  			       cycle_t *cycles, u8 *flags)
> >  {
> > -	unsigned version;
> > -	cycle_t ret, offset;
> > -	u8 ret_flags;
> > -
> > -	version = src->version;
> > -
> > -	offset = pvclock_get_nsec_offset(src);
> > -	ret = src->system_time + offset;
> > -	ret_flags = src->flags;
> > -
> > -	*cycles = ret;
> > -	*flags = ret_flags;
> > +	unsigned version = src->version;
> > +	barrier();
> > +	*cycles = src->system_time + pvclock_get_nsec_offset(src);
> > +	*flags = src->flags;
> > +	barrier();
> >  	return version;
> 
> I have a similar patchset in my mbox starting here:
> 
> https://lkml.kernel.org/r/1464329832-4638-1-git-send-email-mnghuan@gmail.com
> 
> Care to take a look?

Hi, Boris.

I had a vocation last several days, and sorry for replying it
later.

As Roman said in this thread, both his and mine are similar way
to fix this inconsistent issue, and I have a wrapper function
smp_rmb in my patch which the root function is barriers in x86
as well.


Thanks
Minfei