Since commits 668fffa3f838 ("kvm: better MWAIT emulation for guests”)
and 4d5422cea3b6 ("KVM: X86: Provide a capability to disable MWAIT intercepts”),
KVM was modified to allow an admin to configure certain guests to execute
MONITOR/MWAIT inside guest without being intercepted by host.
This is useful in case admin wishes to allocate a dedicated logical
processor for each vCPU thread. Thus, making it safe for guest to
completely control the power-state of the logical processor.
The ability to use this new KVM capability was introduced to QEMU by
commits 6f131f13e68d ("kvm: support -overcommit cpu-pm=on|off”) and
2266d4431132 ("i386/cpu: make -cpu host support monitor/mwait”).
However, exposing MONITOR/MWAIT to a Linux guest may cause it's intel_idle
kernel module to execute c1e_promotion_disable() which will attempt to
RDMSR/WRMSR from/to MSR_IA32_POWER_CTL to manipulate the "C1E Enable"
bit. This behaviour was introduced by commit
32e9518005c8 ("intel_idle: export both C1 and C1E”).
Becuase KVM doesn't emulate this MSR, running KVM with ignore_msrs=0
will cause the above guest behaviour to raise a #GP which will cause
guest to kernel panic.
Therefore, add support for nop emulation of MSR_IA32_POWER_CTL to
avoid #GP in guest in this scenario.
Future commits can optimise emulation further by reflecting guest
MSR changes to host MSR to provide guest with the ability to
fine-tune the dedicated logical processor power-state.
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Signed-off-by: Liran Alon <liran.alon@xxxxxxxxxx>
---
arch/x86/kvm/vmx/vmx.c | 6 ++++++
arch/x86/kvm/vmx/vmx.h | 2 ++
arch/x86/kvm/x86.c | 1 +
3 files changed, 9 insertions(+)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2634ee8c9dc8..6246d782b746 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1696,6 +1696,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_SYSENTER_ESP:
msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
+ case MSR_IA32_POWER_CTL:
+ msr_info->data = vmx->msr_ia32_power_ctl;
+ break;
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
(!msr_info->host_initiated &&
@@ -1826,6 +1829,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_SYSENTER_ESP:
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
+ case MSR_IA32_POWER_CTL:
+ vmx->msr_ia32_power_ctl = data;
+ break;
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
(!msr_info->host_initiated &&
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 99328954c2fc..e9772850a2a1 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -259,6 +259,8 @@ struct vcpu_vmx {
unsigned long host_debugctlmsr;
+ u64 msr_ia32_power_ctl;
+
/*
* Only bits masked by msr_ia32_feature_control_valid_bits can be set in
* msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02c8e095a239..39ee4087f954 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1167,6 +1167,7 @@ static u32 emulated_msrs[] = {
MSR_PLATFORM_INFO,
MSR_MISC_FEATURES_ENABLES,
MSR_AMD64_VIRT_SPEC_CTRL,
+ MSR_IA32_POWER_CTL,
};
static unsigned num_emulated_msrs;
--
2.20.1
