[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH v6 16/19] x86/VPMU: Save VPMU state for PV guests during context switch



> From: Jan Beulich [mailto:JBeulich@xxxxxxxx]
> Sent: Monday, May 26, 2014 5:04 AM
> 
> >>> On 13.05.14 at 17:53, <boris.ostrovsky@xxxxxxxxxx> wrote:
> > Save VPMU state during context switch for both HVM and PV guests unless
> we
> > are in PMU privileged mode (i.e. dom0 is doing all profiling).
> >
> > Signed-off-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
> > Acked-by: Kevin Tian <kevin.tian@xxxxxxxxx>
> 
> May I ask that you don't put in inapplicable acks - there's no VMX
> code being modfied here, i.e. the above either should be dropped
> or become a Reviewed-by.

OK, please replace with a Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>

> 
> > Reviewed-by: Dietmar Hahn <dietmar.hahn@xxxxxxxxxxxxxx>
> > Tested-by: Dietmar Hahn <dietmar.hahn@xxxxxxxxxxxxxx>
> 
> Acked-by: Jan Beulich <jbeulich@xxxxxxxx>
> 
> > ---
> >  xen/arch/x86/domain.c | 12 +++++-------
> >  1 file changed, 5 insertions(+), 7 deletions(-)
> >
> > diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
> > index 4a122da..a853071 100644
> > --- a/xen/arch/x86/domain.c
> > +++ b/xen/arch/x86/domain.c
> > @@ -1478,16 +1478,14 @@ void context_switch(struct vcpu *prev, struct
> vcpu
> > *next)
> >      }
> >
> >      if ( prev != next )
> > -        _update_runstate_area(prev);
> > -
> > -    if ( is_hvm_vcpu(prev) )
> >      {
> > -        if ( (prev != next) && (vpmu_mode & XENPMU_MODE_ON) )
> > +        _update_runstate_area(prev);
> > +        if ( vpmu_mode & XENPMU_MODE_ON )
> >              vpmu_save(prev);
> > +    }
> >
> > -        if ( !list_empty(&prev->arch.hvm_vcpu.tm_list) )
> > +    if ( is_hvm_vcpu(prev)
> &&  !list_empty(&prev->arch.hvm_vcpu.tm_list) )
> >              pt_save_timer(prev);
> > -    }
> >
> >      local_irq_disable();
> >
> > @@ -1526,7 +1524,7 @@ void context_switch(struct vcpu *prev, struct vcpu
> > *next)
> >                             !is_hardware_domain(next->domain));
> >      }
> >
> > -    if ( is_hvm_vcpu(next) && (prev != next) && (vpmu_mode &
> XENPMU_MODE_ON) )
> > +    if ( (prev != next) && (vpmu_mode & XENPMU_MODE_ON) )
> >          /* Must be done with interrupts enabled */
> >          vpmu_load(next);
> >
> > --
> > 1.8.1.4
> 
> 


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.