On Sun, May 19, 2013 at 05:06:36PM +1000, Vadim Rozenfeld wrote:
> Signed-off: Peter Lieven <[email protected]>
> Signed-off: Gleb Natapov <[email protected]>
> Signed-off: Vadim Rozenfeld <[email protected]>
>
> v1 -> v2
> 1. mark TSC page dirty as suggested by
> Eric Northup <[email protected]> and Gleb
> 2. disable local irq when calling get_kernel_ns,
> as it was done by Peter Lieven <[email protected]>
> 3. move check for TSC page enable from second patch
> to this one.
>
> ---
> arch/x86/include/asm/kvm_host.h | 2 ++
> arch/x86/include/uapi/asm/hyperv.h | 14 ++++++++++++++
> arch/x86/kvm/x86.c | 39
> +++++++++++++++++++++++++++++++++++++-
> include/uapi/linux/kvm.h | 1 +
> 4 files changed, 55 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..890dfc3 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
> @@ -179,6 +182,9 @@
> #define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK \
> (~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
>
> +#define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001
> +#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12
> +
> #define HV_PROCESSOR_POWER_STATE_C0 0
> #define HV_PROCESSOR_POWER_STATE_C1 1
> #define HV_PROCESSOR_POWER_STATE_C2 2
> @@ -191,4 +197,12 @@
> #define HV_STATUS_INVALID_ALIGNMENT 4
> #define HV_STATUS_INSUFFICIENT_BUFFERS 19
>
> +typedef struct _HV_REFERENCE_TSC_PAGE {
> + __u32 TscSequence;
> + __u32 Rserved1;
> + __u64 TscScale;
> + __s64 TscOffset;
> +} HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE;
> +
> +
> #endif
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 8d28810..9645dab 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, not needed.
> - 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,
> @@ -1788,6 +1788,8 @@ 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;
> }
> @@ -1827,6 +1829,29 @@ 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;
> + local_irq_disable();
> + kvm->arch.hv_ref_count = get_kernel_ns();
> + local_irq_enable();
> + break;
local_irq_disable/local_irq_enable not needed.
What is the reasoning behind reading this time value at msr write time?
> + }
> + case HV_X64_MSR_REFERENCE_TSC: {
> + u64 gfn;
> + unsigned long addr;
> + HV_REFERENCE_TSC_PAGE tsc_ref;
> + tsc_ref.TscSequence = 0;
> + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) {
> + kvm->arch.hv_tsc_page = data;
> + break;
> + }
> + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
> + addr = gfn_to_hva(kvm, data >>
> + HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT);
> + if (kvm_is_error_hva(addr))
> + return 1;
> + if (__copy_to_user((void __user *)addr, &tsc_ref,
> sizeof(tsc_ref)))
> + return 1;
> + mark_page_dirty(kvm, gfn);
> + kvm->arch.hv_tsc_page = data;
> break;
> }
> default:
> @@ -2253,6 +2278,17 @@ static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu,
> u32 msr, u64 *pdata)
> case HV_X64_MSR_HYPERCALL:
> data = kvm->arch.hv_hypercall;
> break;
> + case HV_X64_MSR_TIME_REF_COUNT: {
> + u64 now_ns;
> + local_irq_disable();
> + now_ns = get_kernel_ns() + kvm->arch.kvmclock_offset;
> + data = div_u64(now_ns - kvm->arch.hv_ref_count, 100);
> + local_irq_enable();
> + break;
> + }
local_irq_disable/enable not needed.
It would be nice to have a testcase to compare reference tsc versus MSR.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
