Il 17/01/2014 14:18, Marcelo Tosatti ha scritto:
> On Fri, Jan 17, 2014 at 10:06:00PM +1100, Vadim Rozenfeld wrote:
>> On Thu, 2014-01-16 at 20:23 -0200, Marcelo Tosatti wrote:
>>> On Thu, Jan 16, 2014 at 08:18:37PM +1100, Vadim Rozenfeld wrote:
>>>> Signed-off: Peter Lieven <pl@xxxxxxx>
>>>> Signed-off: Gleb Natapov
>>>> Signed-off: Vadim Rozenfeld <vrozenfe@xxxxxxxxxx>
>>>>
>>>> After some consideration I decided to submit only Hyper-V reference
>>>> counters support this time. I will submit iTSC support as a separate
>>>> patch as soon as it is ready.
>>>>
>>>> v1 -> v2
>>>> 1. mark TSC page dirty as suggested by
>>>> Eric Northup <digitaleric@xxxxxxxxxx> and Gleb
>>>> 2. disable local irq when calling get_kernel_ns,
>>>> as it was done by Peter Lieven <pl@xxxxxx>
>>>> 3. move check for TSC page enable from second patch
>>>> to this one.
>>>>
>>>> v3 -> v4
>>>> Get rid of ref counter offset.
>>>>
>>>> v4 -> v5
>>>> replace __copy_to_user with kvm_write_guest
>>>> when updateing iTSC page.
>>>>
>>>> ---
>>>> arch/x86/include/asm/kvm_host.h | 1 +
>>>> arch/x86/include/uapi/asm/hyperv.h | 13 +++++++++++++
>>>> arch/x86/kvm/x86.c | 28 +++++++++++++++++++++++++++-
>>>> include/uapi/linux/kvm.h | 1 +
>>>> 4 files changed, 42 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
>>>> index ae5d783..33fef07 100644
>>>> --- a/arch/x86/include/asm/kvm_host.h
>>>> +++ b/arch/x86/include/asm/kvm_host.h
>>>> @@ -605,6 +605,7 @@ struct kvm_arch {
>>>> /* fields used by HYPER-V emulation */
>>>> u64 hv_guest_os_id;
>>>> u64 hv_hypercall;
>>>> + 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 b8f1c01..462efe7 100644
>>>> --- a/arch/x86/include/uapi/asm/hyperv.h
>>>> +++ b/arch/x86/include/uapi/asm/hyperv.h
>>>> @@ -28,6 +28,9 @@
>>>> /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
>>>> #define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
>>>>
>>>> +/* A partition's reference time stamp counter (TSC) page */
>>>> +#define HV_X64_MSR_REFERENCE_TSC 0x40000021
>>>> +
>>>> /*
>>>> * There is a single feature flag that signifies the presence of the MSR
>>>> * that can be used to retrieve both the local APIC Timer frequency as
>>>> @@ -198,6 +201,9 @@
>>>> #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
>>>> @@ -210,4 +216,11 @@
>>>> #define HV_STATUS_INVALID_ALIGNMENT 4
>>>> #define HV_STATUS_INSUFFICIENT_BUFFERS 19
>>>>
>>>> +typedef struct _HV_REFERENCE_TSC_PAGE {
>>>> + __u32 tsc_sequence;
>>>> + __u32 res1;
>>>> + __u64 tsc_scale;
>>>> + __s64 tsc_offset;
>>>> +} HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE;
>>>> +
>>>> #endif
>>>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>>>> index 5d004da..8e685b8 100644
>>>> --- a/arch/x86/kvm/x86.c
>>>> +++ b/arch/x86/kvm/x86.c
>>>> @@ -836,11 +836,12 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
>>>> * kvm-specific. Those are put in the beginning of the list.
>>>> */
>>>>
>>>> -#define KVM_SAVE_MSRS_BEGIN 10
>>>> +#define KVM_SAVE_MSRS_BEGIN 12
>>>> 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_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
>>>> 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,
>>>> @@ -1826,6 +1827,8 @@ 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;
>>>> }
>>>> @@ -1867,6 +1870,20 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
>>>> kvm->arch.hv_hypercall = data;
>>>> break;
>>>> }
>>>> + case HV_X64_MSR_REFERENCE_TSC: {
>>>> + u64 gfn;
>>>> + HV_REFERENCE_TSC_PAGE tsc_ref;
>>>> + memset(&tsc_ref, 0, sizeof(tsc_ref));
>>>> + kvm->arch.hv_tsc_page = data;
>>>
>>> Comment 1)
>>>
>>> Is there a reason (that is compliance with spec) to maintain
>>> value, for HV_X64_MSR_REFERENCE_TSC wrmsr operation, in case
>>> HV_X64_MSR_TSC_REFERENCE_ENABLE is not set?
>>
>> Windows seems to be retrieving HV_X64_MSR_REFERENCE_TSC value only once
>> on boot-up, checks HV_X64_MSR_TSC_REFERENCE_ENABLE bit allocate one page
>> and maps it into the system space, and writes the page address to
>> HV_X64_MSR_REFERENCE_TSC MSR if this bit was not set. Windows keeps the
>> TSC page address value in HvlReferenceTscPage variable and uses it
>> every time when needs to read the TSC page content.
>
> Ok then it has to be saved/restored irrespective of the value of
> HV_X64_MSR_TSC_REFERENCE_ENABLE.
>
>>> If not, should only assign to kvm->arch.hv_tsc_page after proper checks.
>>>
>>>> + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
>>>> + break;
>>>> + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
>>>> + if (kvm_write_guest(kvm, data,
>>>> + &tsc_ref, sizeof(tsc_ref)))
>>>> + return 1;
>>>> + mark_page_dirty(kvm, gfn);
>>>> + break;
>>>> + }
>>>> default:
>>>> vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
>>>> "data 0x%llx\n", msr, data);
>>>> @@ -2291,6 +2308,14 @@ 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: {
>>>> + data =
>>>> + div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
>>>
>>> Comment 2)
>>>
>>> Is there any specification related to the initial value of the clock
>>> after it is enabled ?
>>
>> The MS documentation says the following:
>> "A partition's reference time counter is initialized to zero when the
>> partition is created. The reference time counter for all partitions
>> count at the same rate. However, at any time, the absolute value of each
>> reference time counter will typically differ because partitions will
>> have different creation times."
>>
>> http://msdn.microsoft.com/en-us/library/windows/hardware/ff542637%
>> 28v=vs.85%29.aspx
>>
>> However, Windows doesn't seem to be worried about the initial value.
>> HvlGetReferenceTime only reads HV_X64_MSR_TIME_REF_COUNT MSR and
>> returns the obtained value.
>
> Right. It might be better to initialize kvmclock_offset to zero
> in case of VM creation (QEMU's PUT_FULL state), in case Hyper-V timers
> enabled, with reference to MS docs on top.
>
> Otherwise might end up hitting Windows code timers bugs.
>
> But its a potential improvement, patch looks good.
>
>>>> + }
>>>> + case HV_X64_MSR_REFERENCE_TSC:
>>>> + data = kvm->arch.hv_tsc_page;
>>>> + break;
>>>> default:
>>>> vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
>>>> return 1;
>>>> @@ -2604,6 +2629,7 @@ int kvm_dev_ioctl_check_extension(long ext)
>>>> #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
>>>> case KVM_CAP_ASSIGN_DEV_IRQ:
>>>> case KVM_CAP_PCI_2_3:
>>>> + case KVM_CAP_HYPERV_TIME:
>>>> #endif
>>>> r = 1;
>>>> break;
>>>> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
>>>> index 902f124..686c1ca 100644
>>>> --- a/include/uapi/linux/kvm.h
>>>> +++ b/include/uapi/linux/kvm.h
>>>> @@ -674,6 +674,7 @@ struct kvm_ppc_smmu_info {
>>>> #define KVM_CAP_ARM_EL1_32BIT 93
>>>> #define KVM_CAP_SPAPR_MULTITCE 94
>>>> #define KVM_CAP_EXT_EMUL_CPUID 95
>>>> +#define KVM_CAP_HYPERV_TIME 96
>>>>
>>>> #ifdef KVM_CAP_IRQ_ROUTING
>>>>
>>>> --
>>>> 1.8.1.4
>>>>
>>>
>>> Comment 3)
>>>
>>> Missing qemu HV_X64_MSR_REFERENCE_TSC save/restore.
>> I have this code ready. I'm going to send it to qemu
>> list as soon as KVM patch will be accepted.
>
> Looks good to me.
>
Applied to kvm/queue, thanks!
Paolo
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
