From: Kechen Lu <kechenl@nvidia.com>
To: <kvm@vger.kernel.org>, <seanjc@google.com>, <pbonzini@redhat.com>
Cc: <chao.gao@intel.com>, <shaoqin.huang@intel.com>,
<vkuznets@redhat.com>, <kechenl@nvidia.com>,
<linux-kernel@vger.kernel.org>
Subject: [RFC PATCH v5 2/6] KVM: x86: Move *_in_guest power management flags to vCPU scope
Date: Fri, 13 Jan 2023 22:01:10 +0000 [thread overview]
Message-ID: <20230113220114.2437-3-kechenl@nvidia.com> (raw)
In-Reply-To: <20230113220114.2437-1-kechenl@nvidia.com>
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@nvidia.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
---
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 6aaae18f1854..41b998234a04 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1009,6 +1009,11 @@ 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 596061c1610e..20e427dc608c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -283,8 +283,8 @@ 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 4efdb4a4d72c..8f74f9a80aa5 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -151,14 +151,13 @@ 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));
}
static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index add65dd59756..ed26b6de3007 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -721,7 +721,7 @@ 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;
@@ -1012,7 +1012,7 @@ 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 9a194aa1a75a..dc7176605e01 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1014,7 +1014,7 @@ 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,
@@ -1035,7 +1035,7 @@ 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 =
@@ -1229,12 +1229,12 @@ 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);
@@ -1278,7 +1278,7 @@ 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;
@@ -4362,7 +4362,7 @@ 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 fc9008dbed33..019a20029878 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1689,7 +1689,7 @@ 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);
}
@@ -4412,10 +4412,10 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_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;
}
@@ -4515,7 +4515,7 @@ 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 |
@@ -4661,7 +4661,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write16(LAST_PID_POINTER_INDEX, kvm->arch.max_vcpu_ids - 1);
}
- if (!kvm_pause_in_guest(kvm)) {
+ if (!kvm_pause_in_guest(&vmx->vcpu)) {
vmcs_write32(PLE_GAP, ple_gap);
vmx->ple_window = ple_window;
vmx->ple_window_dirty = true;
@@ -5833,7 +5833,7 @@ 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);
/*
@@ -7379,7 +7379,7 @@ 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);
@@ -7935,7 +7935,7 @@ 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 c8ae9c4f9f08..9a77b55142c6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11634,6 +11634,10 @@ 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)
@@ -12885,7 +12889,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
kvm_is_exception_pending(vcpu)))
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 9de72586f406..b8e49a9d353d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -351,24 +351,24 @@ 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;
}
static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm)
--
2.34.1
next prev parent reply other threads:[~2023-01-13 22:02 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-13 22:01 [RFC PATCH v5 0/6] KVM: x86: add per-vCPU exits disable capability Kechen Lu
2023-01-13 22:01 ` [RFC PATCH v5 1/6] KVM: x86: only allow exits disable before vCPUs created Kechen Lu
2023-01-13 22:01 ` Kechen Lu [this message]
2023-01-13 22:01 ` [RFC PATCH v5 3/6] KVM: x86: Reject disabling of MWAIT interception when not allowed Kechen Lu
2023-01-13 22:01 ` [RFC PATCH v5 4/6] KVM: x86: Let userspace re-enable previously disabled exits Kechen Lu
2023-01-13 22:01 ` [RFC PATCH v5 5/6] KVM: x86: add vCPU scoped toggling for " Kechen Lu
2023-01-13 22:01 ` [RFC PATCH v5 6/6] KVM: selftests: Add tests for VM and vCPU cap KVM_CAP_X86_DISABLE_EXITS Kechen Lu
2023-01-18 20:03 ` Zhi Wang
2023-01-18 20:26 ` Kechen Lu
2023-01-18 20:43 ` Kechen Lu
2023-01-18 8:30 ` [RFC PATCH v5 0/6] KVM: x86: add per-vCPU exits disable capability Zhi Wang
2023-01-18 13:32 ` Zhi Wang
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=20230113220114.2437-3-kechenl@nvidia.com \
--to=kechenl@nvidia.com \
--cc=chao.gao@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=shaoqin.huang@intel.com \
--cc=vkuznets@redhat.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox