Re: [RFC PATCH 1/2] Hyper-H reference counter

[Gleb Natapov <gleb@redhat.com>]

On Tue, May 14, 2013 at 07:46:36PM +1000, Vadim Rozenfeld wrote:
> On Mon, 2013-05-13 at 16:30 -0700, Eric Northup wrote:
> > On Mon, May 13, 2013 at 4:45 AM, Vadim Rozenfeld <vrozenfe@redhat.com> wrote:
> > > Signed-off: Peter Lieven <pl@dlh.net>
> > > Signed-off: Gleb Natapov <gleb@redhat.com>
> > > Signed-off: Vadim Rozenfeld <vrozenfe@redhat.com>
> > >
> > > The following patch allows to activate Hyper-V
> > > reference time counter
> > > ---
> > >  arch/x86/include/asm/kvm_host.h    |  2 ++
> > >  arch/x86/include/uapi/asm/hyperv.h |  3 +++
> > >  arch/x86/kvm/x86.c                 | 25 ++++++++++++++++++++++++-
> > >  3 files changed, 29 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> > > index 3741c65..f0fee35 100644
> > > --- a/arch/x86/include/asm/kvm_host.h
> > > +++ b/arch/x86/include/asm/kvm_host.h
> > > @@ -575,6 +575,8 @@ struct kvm_arch {
> > >         /* fields used by HYPER-V emulation */
> > >         u64 hv_guest_os_id;
> > >         u64 hv_hypercall;
> > > +       u64 hv_ref_count;
> > > +       u64 hv_tsc_page;
> > >
> > >         #ifdef CONFIG_KVM_MMU_AUDIT
> > >         int audit_point;
> > > diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
> > > index b80420b..9711819 100644
> > > --- a/arch/x86/include/uapi/asm/hyperv.h
> > > +++ b/arch/x86/include/uapi/asm/hyperv.h
> > > @@ -136,6 +136,9 @@
> > >  /* MSR used to read the per-partition time reference counter */
> > >  #define HV_X64_MSR_TIME_REF_COUNT              0x40000020
> > >
> > > +/* A partition's reference time stamp counter (TSC) page */
> > > +#define HV_X64_MSR_REFERENCE_TSC               0x40000021
> > > +
> > >  /* Define the virtual APIC registers */
> > >  #define HV_X64_MSR_EOI                         0x40000070
> > >  #define HV_X64_MSR_ICR                         0x40000071
> > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> > > index 094b5d9..1a4036d 100644
> > > --- a/arch/x86/kvm/x86.c
> > > +++ b/arch/x86/kvm/x86.c
> > > @@ -843,7 +843,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
> > >  static u32 msrs_to_save[] = {
> > >         MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
> > >         MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
> > > -       HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
> > > +       HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,HV_X64_MSR_TIME_REF_COUNT,
> > >         HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
> > >         MSR_KVM_PV_EOI_EN,
> > >         MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
> > > @@ -1764,6 +1764,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
> > >         switch (msr) {
> > >         case HV_X64_MSR_GUEST_OS_ID:
> > >         case HV_X64_MSR_HYPERCALL:
> > > +       case HV_X64_MSR_REFERENCE_TSC:
> > > +       case HV_X64_MSR_TIME_REF_COUNT:
> > >                 r = true;
> > >                 break;
> > >         }
> > > @@ -1803,6 +1805,21 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
> > >                 if (__copy_to_user((void __user *)addr, instructions, 4))
> > >                         return 1;
> > >                 kvm->arch.hv_hypercall = data;
> > > +               kvm->arch.hv_ref_count = get_kernel_ns();
> > > +               break;
> > > +       }
> > > +       case HV_X64_MSR_REFERENCE_TSC: {
> > > +               u64 gfn;
> > > +               unsigned long addr;
> > > +               u32 tsc_ref;
> > > +               gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
> > > +               addr = gfn_to_hva(kvm, gfn);
> > > +               if (kvm_is_error_hva(addr))
> > > +                       return 1;
> > > +               tsc_ref = 0;
> > > +               if(__copy_to_user((void __user *)addr, &tsc_ref, sizeof(tsc_ref)))
> > 
> > Does this do the right thing when we're migrating?  How does usermode
> > learn that the guest page has been dirtied?
> > 
> 
> No, it shouldn't be a problem for this patch. Guest allocates a page
> from nonpaged physical memory, maps it to the system address space, gets
> physical address and sends it to KVM. KVM sets the first DWORD
> (TscSequence) to zero, which means that guest will use reference time
> counter as a timestamp source even after migration.
> 
Eric is right, we need mark_page_dirty() here and in HV_X64_MSR_HYPERCALL
too.  Without it QEMU will not know that content of the page has changed
and will not migrate it.

--
			Gleb.