Re: [patch 02/16] x86: pvclock: make sure rdtsc doesnt speculate out of region

[Gleb Natapov <gleb@redhat.com>]

On Thu, Nov 01, 2012 at 08:21:51PM -0200, Marcelo Tosatti wrote:
> On Fri, Nov 02, 2012 at 12:13:54AM +0200, Gleb Natapov wrote:
> > On Thu, Nov 01, 2012 at 06:56:11PM -0200, Marcelo Tosatti wrote:
> > > On Thu, Nov 01, 2012 at 05:49:51PM +0400, Glauber Costa wrote:
> > > > On 11/01/2012 03:48 PM, Gleb Natapov wrote:
> > > > > On Wed, Oct 31, 2012 at 08:46:58PM -0200, Marcelo Tosatti wrote:
> > > > >> Originally from Jeremy Fitzhardinge.
> > > > >>
> > > > >> pvclock_get_time_values, which contains the memory barriers
> > > > >> will be removed by next patch.
> > > > >>
> > > > >> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
> > > > >>
> > > > >> Index: vsyscall/arch/x86/kernel/pvclock.c
> > > > >> ===================================================================
> > > > >> --- vsyscall.orig/arch/x86/kernel/pvclock.c
> > > > >> +++ vsyscall/arch/x86/kernel/pvclock.c
> > > > >> @@ -97,10 +97,10 @@ cycle_t pvclock_clocksource_read(struct 
> > > > >>  
> > > > >>  	do {
> > > > >>  		version = pvclock_get_time_values(&shadow, src);
> > > > >> -		barrier();
> > > > >> +		rdtsc_barrier();
> > > > >>  		offset = pvclock_get_nsec_offset(&shadow);
> > > > >>  		ret = shadow.system_timestamp + offset;
> > > > >> -		barrier();
> > > > >> +		rdtsc_barrier();
> > > > >>  	} while (version != src->version);
> > > > >>  
> > > > >>  	if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
> > > > >>
> > > > > On a guest without SSE2 rdtsc_barrier() will be nop while rmb() will
> > > > > be "lock; addl $0,0(%%esp)". I doubt pvclock will work correctly either
> > > > > way though.
> > > > > 
> > > > > --
> > > > > 			Gleb.
> > > > > 
> > > > Actually it shouldn't matter for KVM, since the page is only updated by
> > > > the vcpu, and the guest is never running while it happens. If Jeremy is
> > > > fine with this, so should I.
> > > 
> > > 17.13 TIME-STAMP COUNTER
> > > 
> > > "The RDTSC instruction is not serializing or ordered with other
> > > instructions. It does not necessarily wait until all previous
> > > instructions have been executed before reading the counter. Similarly,
> > > subsequent instructions may begin execution before the RDTSC instruction
> > > operation is performed."
> > > 
> > > Both instructions are TSC barriers. 
> > > 
> > Which both instructions?
> 
> static __always_inline void rdtsc_barrier(void)
> {
>         alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
>         alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
> }
Both of them will be patched to nop if guest does not have SSE2 cpuid bit.

--
			Gleb.