From: Wanpeng Li <wanpengli@xxxxxxxxxxx>
If host CPUs are dedicated to a VM, we can avoid VM exits on HLT.
This patch adds the per-VM non-HLT-exiting capability.
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpengli@xxxxxxxxxxx>
---
Documentation/virtual/kvm/api.txt | 1 +
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/svm.c | 3 +++
arch/x86/kvm/vmx.c | 23 +++++++++++++++++++++++
arch/x86/kvm/x86.c | 3 +++
arch/x86/kvm/x86.h | 9 ++++++++-
6 files changed, 39 insertions(+), 1 deletion(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 4df35c0..c07e775 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4368,6 +4368,7 @@ Returns: 0 on success, -EINVAL when args[0] contains invalid exits
Valid exits in args[0] are
#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
Enabling this capability on a VM provides userspace with a way to no
longer intercepts some instructions for improved latency in some
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6bd754f..ee739ad 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -808,6 +808,7 @@ struct kvm_arch {
gpa_t wall_clock;
bool mwait_in_guest;
+ bool hlt_in_guest;
bool ept_identity_pagetable_done;
gpa_t ept_identity_map_addr;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index dff3a5d..fcf8339 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1394,6 +1394,9 @@ static void init_vmcb(struct vcpu_svm *svm)
set_intercept(svm, INTERCEPT_MWAIT);
}
+ if (!kvm_hlt_in_guest(svm->vcpu.kvm))
+ set_intercept(svm, INTERCEPT_HLT);
+
control->iopm_base_pa = __sme_set(iopm_base);
control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
control->int_ctl = V_INTR_MASKING_MASK;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b551067..f9f887a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2525,6 +2525,19 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit
return 0;
}
+static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
+{
+ /*
+ * Ensure that we clear the HLT state in the VMCS. We don't need to
+ * explicitly skip the instruction because if the HLT state is set,
+ * then the instruction is already executing and RIP has already been
+ * advanced.
+ */
+ if (kvm_hlt_in_guest(vcpu->kvm) &&
+ vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
+ vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
+}
+
static void vmx_queue_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2555,6 +2568,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
intr_info |= INTR_TYPE_HARD_EXCEPTION;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
+
+ vmx_clear_hlt(vcpu);
}
static bool vmx_rdtscp_supported(void)
@@ -5504,6 +5519,8 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
if (kvm_mwait_in_guest(vmx->vcpu.kvm))
exec_control &= ~(CPU_BASED_MWAIT_EXITING |
CPU_BASED_MONITOR_EXITING);
+ if (kvm_hlt_in_guest(vmx->vcpu.kvm))
+ exec_control &= ~CPU_BASED_HLT_EXITING;
return exec_control;
}
@@ -5865,6 +5882,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
update_exception_bitmap(vcpu);
vpid_sync_context(vmx->vpid);
+ if (init_event)
+ vmx_clear_hlt(vcpu);
}
/*
@@ -5936,6 +5955,8 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu)
} else
intr |= INTR_TYPE_EXT_INTR;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
+
+ vmx_clear_hlt(vcpu);
}
static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
@@ -5966,6 +5987,8 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
+
+ vmx_clear_hlt(vcpu);
}
static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c1d9bbb..13f01d7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2845,6 +2845,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = KVM_CLOCK_TSC_STABLE;
break;
case KVM_CAP_X86_DISABLE_EXITS:
+ r |= KVM_X86_DISABLE_EXITS_HTL;
if(kvm_mwait_can_in_guest())
r |= KVM_X86_DISABLE_EXITS_MWAIT;
break;
@@ -4199,6 +4200,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) &&
kvm_mwait_can_in_guest())
kvm->arch.mwait_in_guest = true;
+ if (cap->args[0] & KVM_X86_DISABLE_EXITS_HTL)
+ kvm->arch.hlt_in_guest = true;
r = 0;
break;
default:
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index cd1215e..d4ddb00 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -263,11 +263,18 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
})
#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
-#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT)
+#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HTL)
static inline bool kvm_mwait_in_guest(struct kvm *kvm)
{
return kvm->arch.mwait_in_guest;
}
+static inline bool kvm_hlt_in_guest(struct kvm *kvm)
+{
+ return kvm->arch.hlt_in_guest;
+}
+
#endif
--
2.7.4
