[RFC PATCH v4 2/7] KVM: x86: Move *_in_guest power management flags to vCPU scope

From: Kechen Lu
Date: Tue Jun 21 2022 - 20:55:07 EST


Make the runtime disabled mwait/hlt/pause/cstate exits flags vCPU scope
to allow finer-grained, per-vCPU control. The VM-scoped control is only
allowed before vCPUs are created, thus preserving the existing behavior
is a simple matter of snapshotting the flags at vCPU creation.

Signed-off-by: Kechen Lu <kechenl@xxxxxxxxxx>
Suggested-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Reviewed-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 5 +++++
arch/x86/kvm/cpuid.c | 4 ++--
arch/x86/kvm/lapic.c | 7 +++----
arch/x86/kvm/svm/nested.c | 4 ++--
arch/x86/kvm/svm/svm.c | 12 ++++++------
arch/x86/kvm/vmx/vmx.c | 16 ++++++++--------
arch/x86/kvm/x86.c | 6 +++++-
arch/x86/kvm/x86.h | 16 ++++++++--------
8 files changed, 39 insertions(+), 31 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9217bd6cf0d1..573a39bf7a84 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -924,6 +924,11 @@ struct kvm_vcpu_arch {
#if IS_ENABLED(CONFIG_HYPERV)
hpa_t hv_root_tdp;
#endif
+
+ bool mwait_in_guest;
+ bool hlt_in_guest;
+ bool pause_in_guest;
+ bool cstate_in_guest;
};

struct kvm_lpage_info {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index de6d44e07e34..f013ff4f49c5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -245,8 +245,8 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);

best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent);
- if (kvm_hlt_in_guest(vcpu->kvm) && best &&
- (best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
+ if (kvm_hlt_in_guest(vcpu) &&
+ best && (best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);

if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0e68b4c937fc..9e29d658a8c2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -147,14 +147,13 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
static bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu)
{
return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) &&
- (kvm_mwait_in_guest(vcpu->kvm) || kvm_hlt_in_guest(vcpu->kvm));
+ (kvm_mwait_in_guest(vcpu) || kvm_hlt_in_guest(vcpu));
}

bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu)
{
- return kvm_x86_ops.set_hv_timer
- && !(kvm_mwait_in_guest(vcpu->kvm) ||
- kvm_can_post_timer_interrupt(vcpu));
+ return kvm_x86_ops.set_hv_timer &&
+ !(kvm_mwait_in_guest(vcpu) || kvm_can_post_timer_interrupt(vcpu));
}
EXPORT_SYMBOL_GPL(kvm_can_use_hv_timer);

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index ba7cd26f438f..f143ec757467 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -675,7 +675,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)

pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0;
pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0;
- if (kvm_pause_in_guest(svm->vcpu.kvm)) {
+ if (kvm_pause_in_guest(&svm->vcpu)) {
/* use guest values since host doesn't intercept PAUSE */
vmcb02->control.pause_filter_count = pause_count12;
vmcb02->control.pause_filter_thresh = pause_thresh12;
@@ -951,7 +951,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
vmcb12->control.event_inj = svm->nested.ctl.event_inj;
vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err;

- if (!kvm_pause_in_guest(vcpu->kvm)) {
+ if (!kvm_pause_in_guest(vcpu)) {
vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count;
vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 87da90360bc7..b32987f54ace 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -921,7 +921,7 @@ static void grow_ple_window(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
int old = control->pause_filter_count;

- if (kvm_pause_in_guest(vcpu->kvm))
+ if (kvm_pause_in_guest(vcpu))
return;

control->pause_filter_count = __grow_ple_window(old,
@@ -942,7 +942,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
int old = control->pause_filter_count;

- if (kvm_pause_in_guest(vcpu->kvm))
+ if (kvm_pause_in_guest(vcpu))
return;

control->pause_filter_count =
@@ -1136,12 +1136,12 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
svm_set_intercept(svm, INTERCEPT_RDPRU);
svm_set_intercept(svm, INTERCEPT_RSM);

- if (!kvm_mwait_in_guest(vcpu->kvm)) {
+ if (!kvm_mwait_in_guest(vcpu)) {
svm_set_intercept(svm, INTERCEPT_MONITOR);
svm_set_intercept(svm, INTERCEPT_MWAIT);
}

- if (!kvm_hlt_in_guest(vcpu->kvm))
+ if (!kvm_hlt_in_guest(vcpu))
svm_set_intercept(svm, INTERCEPT_HLT);

control->iopm_base_pa = __sme_set(iopm_base);
@@ -1185,7 +1185,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
svm->nested.vmcb12_gpa = INVALID_GPA;
svm->nested.last_vmcb12_gpa = INVALID_GPA;

- if (!kvm_pause_in_guest(vcpu->kvm)) {
+ if (!kvm_pause_in_guest(vcpu)) {
control->pause_filter_count = pause_filter_count;
if (pause_filter_thresh)
control->pause_filter_thresh = pause_filter_thresh;
@@ -4269,7 +4269,7 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)

static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
- if (!kvm_pause_in_guest(vcpu->kvm))
+ if (!kvm_pause_in_guest(vcpu))
shrink_ple_window(vcpu);
}

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 553dd2317b9c..f24c9a357f70 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1597,7 +1597,7 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
* then the instruction is already executing and RIP has already been
* advanced.
*/
- if (kvm_hlt_in_guest(vcpu->kvm) &&
+ if (kvm_hlt_in_guest(vcpu) &&
vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
}
@@ -4212,10 +4212,10 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
exec_control |= CPU_BASED_CR3_STORE_EXITING |
CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_INVLPG_EXITING;
- if (kvm_mwait_in_guest(vmx->vcpu.kvm))
+ if (kvm_mwait_in_guest(&vmx->vcpu))
exec_control &= ~(CPU_BASED_MWAIT_EXITING |
CPU_BASED_MONITOR_EXITING);
- if (kvm_hlt_in_guest(vmx->vcpu.kvm))
+ if (kvm_hlt_in_guest(&vmx->vcpu))
exec_control &= ~CPU_BASED_HLT_EXITING;
return exec_control;
}
@@ -4294,7 +4294,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
}
if (!enable_unrestricted_guest)
exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
- if (kvm_pause_in_guest(vmx->vcpu.kvm))
+ if (kvm_pause_in_guest(&vmx->vcpu))
exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
if (!kvm_vcpu_apicv_active(vcpu))
exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -4397,7 +4397,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
}

- if (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
+ if (!kvm_pause_in_guest(&vmx->vcpu)) {
vmcs_write32(PLE_GAP, ple_gap);
vmx->ple_window = ple_window;
vmx->ple_window_dirty = true;
@@ -5562,7 +5562,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
*/
static int handle_pause(struct kvm_vcpu *vcpu)
{
- if (!kvm_pause_in_guest(vcpu->kvm))
+ if (!kvm_pause_in_guest(vcpu))
grow_ple_window(vcpu);

/*
@@ -7059,7 +7059,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu)
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
- if (kvm_cstate_in_guest(vcpu->kvm)) {
+ if (kvm_cstate_in_guest(vcpu)) {
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
@@ -7597,7 +7597,7 @@ static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)

static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
- if (!kvm_pause_in_guest(vcpu->kvm))
+ if (!kvm_pause_in_guest(vcpu))
shrink_ple_window(vcpu);
}

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3ac6329e6d43..b419b258ed90 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11355,6 +11355,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
#if IS_ENABLED(CONFIG_HYPERV)
vcpu->arch.hv_root_tdp = INVALID_PAGE;
#endif
+ vcpu->arch.mwait_in_guest = vcpu->kvm->arch.mwait_in_guest;
+ vcpu->arch.hlt_in_guest = vcpu->kvm->arch.hlt_in_guest;
+ vcpu->arch.pause_in_guest = vcpu->kvm->arch.pause_in_guest;
+ vcpu->arch.cstate_in_guest = vcpu->kvm->arch.cstate_in_guest;

r = static_call(kvm_x86_vcpu_create)(vcpu);
if (r)
@@ -12539,7 +12543,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
vcpu->arch.exception.pending))
return false;

- if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu))
+ if (kvm_hlt_in_guest(vcpu) && !kvm_can_deliver_async_pf(vcpu))
return false;

/*
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 588792f00334..a59b73e11726 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -324,24 +324,24 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
__rem; \
})

-static inline bool kvm_mwait_in_guest(struct kvm *kvm)
+static inline bool kvm_mwait_in_guest(struct kvm_vcpu *vcpu)
{
- return kvm->arch.mwait_in_guest;
+ return vcpu->arch.mwait_in_guest;
}

-static inline bool kvm_hlt_in_guest(struct kvm *kvm)
+static inline bool kvm_hlt_in_guest(struct kvm_vcpu *vcpu)
{
- return kvm->arch.hlt_in_guest;
+ return vcpu->arch.hlt_in_guest;
}

-static inline bool kvm_pause_in_guest(struct kvm *kvm)
+static inline bool kvm_pause_in_guest(struct kvm_vcpu *vcpu)
{
- return kvm->arch.pause_in_guest;
+ return vcpu->arch.pause_in_guest;
}

-static inline bool kvm_cstate_in_guest(struct kvm *kvm)
+static inline bool kvm_cstate_in_guest(struct kvm_vcpu *vcpu)
{
- return kvm->arch.cstate_in_guest;
+ return vcpu->arch.cstate_in_guest;
}

enum kvm_intr_type {
--
2.32.0