答复: [PATCH] [v3] kvm: x86: support APERF/MPERF registers
> -邮件原件-
> 发件人: Wei Huang [mailto:wei.hua...@amd.com]
> 发送时间: 2020年5月2日 5:31
> 收件人: Li,Rongqing
> 抄送: linux-kernel@vger.kernel.org; k...@vger.kernel.org; x...@kernel.org;
> h...@zytor.com; b...@alien8.de; mi...@redhat.com; t...@linutronix.de;
> jmatt...@google.com; wanpen...@tencent.com; vkuzn...@redhat.com;
> sean.j.christopher...@intel.com; pbonz...@redhat.com; xiaoyao...@intel.com
> 主题: Re: [PATCH] [v3] kvm: x86: support APERF/MPERF registers
> 重要性: 高
>
> On 04/30 06:45, Li RongQing wrote:
> > Guest kernel reports a fixed cpu frequency in /proc/cpuinfo, this is
> > confused to user when turbo is enable, and aperf/mperf can be used to
> > show current cpu frequency after 7d5905dc14a
> > "(x86 / CPU: Always show current CPU frequency in /proc/cpuinfo)"
> > so guest should support aperf/mperf capability
> >
> > this patch implements aperf/mperf by three mode: none, software
>
> This
>
> > emulation, and pass-through
> >
> > none: default mode, guest does not support aperf/mperf
> >
> > software emulation: the period of aperf/mperf in guest mode are
> > accumulated as emulated value
> >
> > pass-though: it is only suitable for KVM_HINTS_REALTIME, Because that
> > hint guarantees we have a 1:1 vCPU:CPU binding and guaranteed no
> > over-commit.
>
> If we save/restore the values of aperf/mperf properly during vcpu migration
> among different cores, is pinning still required?
>
I think it can be as a new mode, it maybe add more msr operation, like write
> >
> > and a per-VM capability is added to configure aperfmperf mode
> >
> > Signed-off-by: Li RongQing
> > Signed-off-by: Chai Wen
> > Signed-off-by: Jia Lina
> > ---
> > diff v2:
> > support aperfmperf pass though
> > move common codes to kvm_get_msr_common
> >
> > diff v1:
> > 1. support AMD, but not test
>
> pt-mode doesn't work doesn't work on AMD. See below.
>
> > 2. support per-vm capability to enable Documentation/virt/kvm/api.rst
> > | 10 ++ arch/x86/include/asm/kvm_host.h | 11 +++
> > arch/x86/kvm/cpuid.c| 13 -
> > arch/x86/kvm/svm.c | 8
> > arch/x86/kvm/vmx/vmx.c | 6 ++
> > arch/x86/kvm/x86.c | 42
> +
> > arch/x86/kvm/x86.h | 15 +++
> > include/uapi/linux/kvm.h| 1 +
> > 8 files changed, 105 insertions(+), 1 deletion(-)
> >
> > diff --git a/Documentation/virt/kvm/api.rst
> > b/Documentation/virt/kvm/api.rst index efbbe570aa9b..c3be3b6a1717
> > 100644
> > --- a/Documentation/virt/kvm/api.rst
> > +++ b/Documentation/virt/kvm/api.rst
> > @@ -6109,3 +6109,13 @@ KVM can therefore start protected VMs.
> > This capability governs the KVM_S390_PV_COMMAND ioctl and the
> > KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for
> protected
> > guests when the state change is invalid.
> > +
> > +8.23 KVM_CAP_APERFMPERF
> > +
> > +
> > +:Architectures: x86
> > +:Parameters: args[0] is aperfmperf mode;
> > + 0 for not support, 1 for software emulation, 2 for
> > +pass-through
> > +:Returns: 0 on success; -1 on error
> > +
> > +This capability indicates that KVM supports APERF and MPERF MSR
> > +registers
> > diff --git a/arch/x86/include/asm/kvm_host.h
> > b/arch/x86/include/asm/kvm_host.h index 42a2d0d3984a..81477f676f60
> > 100644
> > --- a/arch/x86/include/asm/kvm_host.h
> > +++ b/arch/x86/include/asm/kvm_host.h
> > @@ -820,6 +820,9 @@ struct kvm_vcpu_arch {
> >
> > /* AMD MSRC001_0015 Hardware Configuration */
> > u64 msr_hwcr;
> > +
> > + u64 v_mperf;
> > + u64 v_aperf;
> > };
> >
> > struct kvm_lpage_info {
> > @@ -885,6 +888,12 @@ enum kvm_irqchip_mode {
> > KVM_IRQCHIP_SPLIT,/* created with KVM_CAP_SPLIT_IRQCHIP
> */
> > };
> >
> > +enum kvm_aperfmperf_mode {
> > + KVM_APERFMPERF_NONE,
> > + KVM_APERFMPERF_SOFT, /* software emulate aperfmperf */
> > + KVM_APERFMPERF_PT,/* pass-through aperfmperf to guest */
> > +};
> > +
> > #define APICV_INHIBIT_REASON_DISABLE0
> > #define APICV_INHIBIT_REASON_HYPERV 1
> > #define APICV_INHIBIT_REASON_NESTED 2
> > @@ -982,6 +991,8 @@ struct kvm_arch {
> >
> > struct kvm_pmu_event_filter *pmu_event_filter;
> > struct task_struct *nx_lpage_recovery_thread;
> > +
> &g
Re: [PATCH] [v3] kvm: x86: support APERF/MPERF registers
On 04/30 06:45, Li RongQing wrote:
> Guest kernel reports a fixed cpu frequency in /proc/cpuinfo,
> this is confused to user when turbo is enable, and aperf/mperf
> can be used to show current cpu frequency after 7d5905dc14a
> "(x86 / CPU: Always show current CPU frequency in /proc/cpuinfo)"
> so guest should support aperf/mperf capability
>
> this patch implements aperf/mperf by three mode: none, software
This
> emulation, and pass-through
>
> none: default mode, guest does not support aperf/mperf
>
> software emulation: the period of aperf/mperf in guest mode are
> accumulated as emulated value
>
> pass-though: it is only suitable for KVM_HINTS_REALTIME, Because
> that hint guarantees we have a 1:1 vCPU:CPU binding and guaranteed
> no over-commit.
If we save/restore the values of aperf/mperf properly during vcpu migration
among different cores, is pinning still required?
>
> and a per-VM capability is added to configure aperfmperf mode
>
> Signed-off-by: Li RongQing
> Signed-off-by: Chai Wen
> Signed-off-by: Jia Lina
> ---
> diff v2:
> support aperfmperf pass though
> move common codes to kvm_get_msr_common
>
> diff v1:
> 1. support AMD, but not test
pt-mode doesn't work doesn't work on AMD. See below.
> 2. support per-vm capability to enable
> Documentation/virt/kvm/api.rst | 10 ++
> arch/x86/include/asm/kvm_host.h | 11 +++
> arch/x86/kvm/cpuid.c| 13 -
> arch/x86/kvm/svm.c | 8
> arch/x86/kvm/vmx/vmx.c | 6 ++
> arch/x86/kvm/x86.c | 42
> +
> arch/x86/kvm/x86.h | 15 +++
> include/uapi/linux/kvm.h| 1 +
> 8 files changed, 105 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index efbbe570aa9b..c3be3b6a1717 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -6109,3 +6109,13 @@ KVM can therefore start protected VMs.
> This capability governs the KVM_S390_PV_COMMAND ioctl and the
> KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
> guests when the state change is invalid.
> +
> +8.23 KVM_CAP_APERFMPERF
> +
> +
> +:Architectures: x86
> +:Parameters: args[0] is aperfmperf mode;
> + 0 for not support, 1 for software emulation, 2 for pass-through
> +:Returns: 0 on success; -1 on error
> +
> +This capability indicates that KVM supports APERF and MPERF MSR registers
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 42a2d0d3984a..81477f676f60 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -820,6 +820,9 @@ struct kvm_vcpu_arch {
>
> /* AMD MSRC001_0015 Hardware Configuration */
> u64 msr_hwcr;
> +
> + u64 v_mperf;
> + u64 v_aperf;
> };
>
> struct kvm_lpage_info {
> @@ -885,6 +888,12 @@ enum kvm_irqchip_mode {
> KVM_IRQCHIP_SPLIT,/* created with KVM_CAP_SPLIT_IRQCHIP */
> };
>
> +enum kvm_aperfmperf_mode {
> + KVM_APERFMPERF_NONE,
> + KVM_APERFMPERF_SOFT, /* software emulate aperfmperf */
> + KVM_APERFMPERF_PT,/* pass-through aperfmperf to guest */
> +};
> +
> #define APICV_INHIBIT_REASON_DISABLE0
> #define APICV_INHIBIT_REASON_HYPERV 1
> #define APICV_INHIBIT_REASON_NESTED 2
> @@ -982,6 +991,8 @@ struct kvm_arch {
>
> struct kvm_pmu_event_filter *pmu_event_filter;
> struct task_struct *nx_lpage_recovery_thread;
> +
> + enum kvm_aperfmperf_mode aperfmperf_mode;
> };
>
> struct kvm_vm_stat {
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index 901cd1fdecd9..7a64ea2c3eef 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -124,6 +124,14 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
> MSR_IA32_MISC_ENABLE_MWAIT);
> }
>
> + best = kvm_find_cpuid_entry(vcpu, 6, 0);
> + if (best) {
> + if (guest_has_aperfmperf(vcpu->kvm) &&
> + boot_cpu_has(X86_FEATURE_APERFMPERF))
> + best->ecx |= 1;
> + else
> + best->ecx &= ~1;
> + }
> /* Update physical-address width */
> vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
> kvm_mmu_reset_context(vcpu);
> @@ -558,7 +566,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array
> *array, u32 function)
> case 6: /* Thermal management */
> entry->eax = 0x4; /* allow ARAT */
> entry->ebx = 0;
> - entry->ecx = 0;
> + if (boot_cpu_has(X86_FEATURE_APERFMPERF))
> + entry->ecx = 0x1;
> + else
> + entry->ecx = 0x0;
> entry->edx = 0;
> break;
> /* function 7 has additional index. */
> diff --git
[PATCH] [v3] kvm: x86: support APERF/MPERF registers
Guest kernel reports a fixed cpu frequency in /proc/cpuinfo,
this is confused to user when turbo is enable, and aperf/mperf
can be used to show current cpu frequency after 7d5905dc14a
"(x86 / CPU: Always show current CPU frequency in /proc/cpuinfo)"
so guest should support aperf/mperf capability
this patch implements aperf/mperf by three mode: none, software
emulation, and pass-through
none: default mode, guest does not support aperf/mperf
software emulation: the period of aperf/mperf in guest mode are
accumulated as emulated value
pass-though: it is only suitable for KVM_HINTS_REALTIME, Because
that hint guarantees we have a 1:1 vCPU:CPU binding and guaranteed
no over-commit.
and a per-VM capability is added to configure aperfmperf mode
Signed-off-by: Li RongQing
Signed-off-by: Chai Wen
Signed-off-by: Jia Lina
---
diff v2:
support aperfmperf pass though
move common codes to kvm_get_msr_common
diff v1:
1. support AMD, but not test
2. support per-vm capability to enable
Documentation/virt/kvm/api.rst | 10 ++
arch/x86/include/asm/kvm_host.h | 11 +++
arch/x86/kvm/cpuid.c| 13 -
arch/x86/kvm/svm.c | 8
arch/x86/kvm/vmx/vmx.c | 6 ++
arch/x86/kvm/x86.c | 42 +
arch/x86/kvm/x86.h | 15 +++
include/uapi/linux/kvm.h| 1 +
8 files changed, 105 insertions(+), 1 deletion(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index efbbe570aa9b..c3be3b6a1717 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6109,3 +6109,13 @@ KVM can therefore start protected VMs.
This capability governs the KVM_S390_PV_COMMAND ioctl and the
KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
guests when the state change is invalid.
+
+8.23 KVM_CAP_APERFMPERF
+
+
+:Architectures: x86
+:Parameters: args[0] is aperfmperf mode;
+ 0 for not support, 1 for software emulation, 2 for pass-through
+:Returns: 0 on success; -1 on error
+
+This capability indicates that KVM supports APERF and MPERF MSR registers
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 42a2d0d3984a..81477f676f60 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -820,6 +820,9 @@ struct kvm_vcpu_arch {
/* AMD MSRC001_0015 Hardware Configuration */
u64 msr_hwcr;
+
+ u64 v_mperf;
+ u64 v_aperf;
};
struct kvm_lpage_info {
@@ -885,6 +888,12 @@ enum kvm_irqchip_mode {
KVM_IRQCHIP_SPLIT,/* created with KVM_CAP_SPLIT_IRQCHIP */
};
+enum kvm_aperfmperf_mode {
+ KVM_APERFMPERF_NONE,
+ KVM_APERFMPERF_SOFT, /* software emulate aperfmperf */
+ KVM_APERFMPERF_PT,/* pass-through aperfmperf to guest */
+};
+
#define APICV_INHIBIT_REASON_DISABLE0
#define APICV_INHIBIT_REASON_HYPERV 1
#define APICV_INHIBIT_REASON_NESTED 2
@@ -982,6 +991,8 @@ struct kvm_arch {
struct kvm_pmu_event_filter *pmu_event_filter;
struct task_struct *nx_lpage_recovery_thread;
+
+ enum kvm_aperfmperf_mode aperfmperf_mode;
};
struct kvm_vm_stat {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 901cd1fdecd9..7a64ea2c3eef 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -124,6 +124,14 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
MSR_IA32_MISC_ENABLE_MWAIT);
}
+ best = kvm_find_cpuid_entry(vcpu, 6, 0);
+ if (best) {
+ if (guest_has_aperfmperf(vcpu->kvm) &&
+ boot_cpu_has(X86_FEATURE_APERFMPERF))
+ best->ecx |= 1;
+ else
+ best->ecx &= ~1;
+ }
/* Update physical-address width */
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -558,7 +566,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array
*array, u32 function)
case 6: /* Thermal management */
entry->eax = 0x4; /* allow ARAT */
entry->ebx = 0;
- entry->ecx = 0;
+ if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+ entry->ecx = 0x1;
+ else
+ entry->ecx = 0x0;
entry->edx = 0;
break;
/* function 7 has additional index. */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 851e9cc79930..5646b6475049 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2292,6 +2292,14 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
svm->msrpm = page_address(msrpm_pages);
svm_vcpu_init_msrpm(svm->msrpm);
+ if (guest_aperfmperf_soft(vcpu->kvm)) {
+ set_msr_interception(svm->msrpm, MSR_IA32_MPERF, 1, 0);
+
