From: Vadim Rozenfeld <vrozenfe@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org, gleb@redhat.com, pl@dlh.net
Subject: Re: [RFC PATCH v2 1/2] add support for Hyper-V reference time counter
Date: Wed, 22 May 2013 03:32:57 -0400 (EDT) [thread overview]
Message-ID: <745195650.5763962.1369207977883.JavaMail.root@redhat.com> (raw)
In-Reply-To: <20130522004614.GA7322@amt.cnet>
----- Original Message -----
From: "Marcelo Tosatti" <mtosatti@redhat.com>
To: "Vadim Rozenfeld" <vrozenfe@redhat.com>
Cc: kvm@vger.kernel.org, gleb@redhat.com, pl@dlh.net
Sent: Wednesday, May 22, 2013 10:46:14 AM
Subject: Re: [RFC PATCH v2 1/2] add support for Hyper-V reference time counter
On Sun, May 19, 2013 at 05:06:36PM +1000, 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 | 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?
[VR] Windows writs this MSR only once, during HAL initialization.
So, I decided to treat this call as a partition crate event.
> + }
> + 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.
next prev parent reply other threads:[~2013-05-22 7:33 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-19 7:06 [RFC PATCH v2 0/2] Hyper-V timers Vadim Rozenfeld
2013-05-19 7:06 ` [RFC PATCH v2 1/2] add support for Hyper-V reference time counter Vadim Rozenfeld
2013-05-19 13:47 ` Gleb Natapov
2013-05-19 14:37 ` Paolo Bonzini
2013-05-22 0:46 ` Marcelo Tosatti
2013-05-22 3:28 ` Gleb Natapov
2013-05-22 3:32 ` Marcelo Tosatti
2013-05-22 3:38 ` Gleb Natapov
2013-05-22 14:31 ` Marcelo Tosatti
2013-05-22 7:32 ` Vadim Rozenfeld [this message]
2013-05-22 21:55 ` Paolo Bonzini
2013-05-23 6:17 ` Peter Lieven
2013-05-23 9:54 ` Paolo Bonzini
2013-05-23 10:45 ` Peter Lieven
2013-05-23 12:25 ` Vadim Rozenfeld
2013-05-23 13:18 ` Paolo Bonzini
2013-05-23 13:20 ` Peter Lieven
2013-05-23 13:23 ` Paolo Bonzini
2013-05-23 13:30 ` Peter Lieven
2013-05-23 13:40 ` Paolo Bonzini
2013-05-19 7:06 ` [RFC PATCH v2 2/2] add support for Hyper-V invariant TSC Vadim Rozenfeld
2013-05-22 0:50 ` Marcelo Tosatti
2013-05-22 7:22 ` Vadim Rozenfeld
2013-05-22 21:23 ` Marcelo Tosatti
2013-05-23 6:18 ` Peter Lieven
2013-05-23 9:13 ` Gleb Natapov
2013-05-23 13:35 ` Marcelo Tosatti
2013-05-23 15:14 ` Gleb Natapov
2013-05-24 9:57 ` Vadim Rozenfeld
2013-05-23 12:33 ` Vadim Rozenfeld
2013-05-23 12:44 ` Peter Lieven
2013-05-23 12:45 ` Gleb Natapov
2013-05-23 12:54 ` Vadim Rozenfeld
2013-05-23 9:12 ` Gleb Natapov
2013-05-23 13:53 ` Marcelo Tosatti
2013-05-23 15:31 ` Gleb Natapov
2013-05-24 10:11 ` Vadim Rozenfeld
2013-05-24 19:41 ` Marcelo Tosatti
2013-05-27 12:33 ` Vadim Rozenfeld
2013-05-23 12:21 ` Vadim Rozenfeld
2013-05-23 13:47 ` Marcelo Tosatti
2013-05-24 10:01 ` Vadim Rozenfeld
2013-05-23 16:44 ` Paolo Bonzini
2013-05-24 10:16 ` Vadim Rozenfeld
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=745195650.5763962.1369207977883.JavaMail.root@redhat.com \
--to=vrozenfe@redhat.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pl@dlh.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.