Re: [RFC PATCH v3 1/2] add support for Hyper-V reference time counter

[Marcelo Tosatti <mtosatti@redhat.com>]

On Thu, Jan 02, 2014 at 02:15:48PM +0100, Peter Lieven wrote:
> Am 11.12.2013 19:53, schrieb Marcelo Tosatti:
> > On Sun, Dec 08, 2013 at 10:33:38PM +1100, Vadim Rozenfeld wrote:
> >> Signed-off: Peter Lieven <pl@dlh.net>
> >> Signed-off: Gleb Natapov <gleb@redhat.com>
> >> Signed-off: Vadim Rozenfeld <vrozenfe@redhat.com>
> >>
> >> v1 -> v2
> >> 1. mark TSC page dirty as suggested by 
> >>     Eric Northup <digitaleric@google.com> and Gleb
> >> 2. disable local irq when calling get_kernel_ns, 
> >>     as it was done by Peter Lieven <pl@dlhnet.de>
> >> 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 | 13 +++++++++++++
> >>  arch/x86/kvm/x86.c                 | 39 +++++++++++++++++++++++++++++++++++++-
> >>  include/uapi/linux/kvm.h           |  1 +
> >>  4 files changed, 54 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> >> index ae5d783..2fd0753 100644
> >> --- a/arch/x86/include/asm/kvm_host.h
> >> +++ b/arch/x86/include/asm/kvm_host.h
> >> @@ -605,6 +605,8 @@ 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 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 21ef1ba..5e4e495a 100644
> >> --- a/arch/x86/kvm/x86.c
> >> +++ b/arch/x86/kvm/x86.c
> >> @@ -840,7 +840,7 @@ 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,
> >> @@ -1826,6 +1826,8 @@ 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;
> >>  	}
> >> @@ -1865,6 +1867,29 @@ 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() + kvm->arch.kvmclock_offset;
> >> +		local_irq_enable();
> > 
> > Where does the docs say that HV_X64_MSR_HYPERCALL is the where the clock
> > starts counting?
> > 
> > No need to store kvmclock_offset in hv_ref_count? (moreover
> > the name is weird, better name would be "hv_ref_start_time".
> > 
> >> +		break;
> >> +	}
> >> +	case HV_X64_MSR_REFERENCE_TSC: {
> >> +		u64 gfn;
> >> +		unsigned long addr;
> >> +		HV_REFERENCE_TSC_PAGE tsc_ref;
> >> +		tsc_ref.tsc_sequence = 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:
> >> @@ -2291,6 +2316,17 @@ 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();
> > 
> > No need for irq disable/enable pairs.
> 
> KVM_GET_CLOCK / KVM_SET_CLOCK do the irq disable/enable pairs. What is right?
> 
> Peter


                local_irq_disable();
                now_ns = get_kernel_ns();
                delta = user_ns.clock - now_ns;
                local_irq_enable();

Not using irq disable/enable pairs. The subtraction is not dependant on
any particular time.

                local_irq_disable();
                now_ns = get_kernel_ns();
                local_irq_enable();
                delta = user_ns.clock - now_ns;

Any interrupt that would affect the value of get_kernel_ns(), would
have a similar effect before the interrupts are disabled. So the 
disable/enable pair achieves nothing in practice. It was copied from
kvm_guest_time_update.