From: Xiong Zhang <[email protected]>
In PMU passthrough mode, there are three requirements to manage
IA32_PERF_GLOBAL_CTRL:
- guest IA32_PERF_GLOBAL_CTRL MSR must be saved at vm exit.
- IA32_PERF_GLOBAL_CTRL MSR must be cleared at vm exit to avoid any
counter of running within KVM runloop.
- guest IA32_PERF_GLOBAL_CTRL MSR must be restored at vm entry.
Introduce vmx_set_perf_global_ctrl() function to auto switching
IA32_PERF_GLOBAL_CTR and invoke it after the VMM finishes setting up the
CPUID bits.
Signed-off-by: Xiong Zhang <[email protected]>
Signed-off-by: Mingwei Zhang <[email protected]>
---
arch/x86/include/asm/vmx.h | 1 +
arch/x86/kvm/vmx/vmx.c | 89 ++++++++++++++++++++++++++++++++------
arch/x86/kvm/vmx/vmx.h | 3 +-
3 files changed, 78 insertions(+), 15 deletions(-)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0e73616b82f3..f574e7b429a3 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -104,6 +104,7 @@
#define VM_EXIT_CLEAR_BNDCFGS 0x00800000
#define VM_EXIT_PT_CONCEAL_PIP 0x01000000
#define VM_EXIT_CLEAR_IA32_RTIT_CTL 0x02000000
+#define VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL 0x40000000
#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 33cb69ff0804..8ab266e1e2a7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4387,6 +4387,74 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
return pin_based_exec_ctrl;
}
+static void vmx_set_perf_global_ctrl(struct vcpu_vmx *vmx)
+{
+ u32 vmentry_ctrl = vm_entry_controls_get(vmx);
+ u32 vmexit_ctrl = vm_exit_controls_get(vmx);
+ int i;
+
+ /*
+ * PERF_GLOBAL_CTRL is toggled dynamically in emulated vPMU.
+ */
+ if (cpu_has_perf_global_ctrl_bug() ||
+ !is_passthrough_pmu_enabled(&vmx->vcpu)) {
+ vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+ vmexit_ctrl &= ~VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL;
+ }
+
+ if (is_passthrough_pmu_enabled(&vmx->vcpu)) {
+ /*
+ * Setup auto restore guest PERF_GLOBAL_CTRL MSR at vm entry.
+ */
+ if (vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, 0);
+ else {
+ i = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest,
+ MSR_CORE_PERF_GLOBAL_CTRL);
+ if (i < 0) {
+ i = vmx->msr_autoload.guest.nr++;
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT,
+ vmx->msr_autoload.guest.nr);
+ }
+ vmx->msr_autoload.guest.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
+ vmx->msr_autoload.guest.val[i].value = 0;
+ }
+ /*
+ * Setup auto clear host PERF_GLOBAL_CTRL msr at vm exit.
+ */
+ if (vmexit_ctrl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmcs_write64(HOST_IA32_PERF_GLOBAL_CTRL, 0);
+ else {
+ i = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.host,
+ MSR_CORE_PERF_GLOBAL_CTRL);
+ if (i < 0) {
+ i = vmx->msr_autoload.host.nr++;
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT,
+ vmx->msr_autoload.host.nr);
+ }
+ vmx->msr_autoload.host.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
+ vmx->msr_autoload.host.val[i].value = 0;
+ }
+ /*
+ * Setup auto save guest PERF_GLOBAL_CTRL msr at vm exit
+ */
+ if (!(vmexit_ctrl & VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL)) {
+ i = vmx_find_loadstore_msr_slot(&vmx->msr_autostore.guest,
+ MSR_CORE_PERF_GLOBAL_CTRL);
+ if (i < 0) {
+ i = vmx->msr_autostore.guest.nr++;
+ vmcs_write32(VM_EXIT_MSR_STORE_COUNT,
+ vmx->msr_autostore.guest.nr);
+ }
+ vmx->msr_autostore.guest.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
+ }
+ }
+
+ vm_entry_controls_set(vmx, vmentry_ctrl);
+ vm_exit_controls_set(vmx, vmexit_ctrl);
+}
+
static u32 vmx_vmentry_ctrl(void)
{
u32 vmentry_ctrl = vmcs_config.vmentry_ctrl;
@@ -4394,15 +4462,9 @@ static u32 vmx_vmentry_ctrl(void)
if (vmx_pt_mode_is_system())
vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP |
VM_ENTRY_LOAD_IA32_RTIT_CTL);
- /*
- * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically.
- */
- vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |
- VM_ENTRY_LOAD_IA32_EFER |
- VM_ENTRY_IA32E_MODE);
- if (cpu_has_perf_global_ctrl_bug())
- vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ /* IA32e mode, and loading of EFER is toggled dynamically. */
+ vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_EFER | VM_ENTRY_IA32E_MODE);
return vmentry_ctrl;
}
@@ -4422,12 +4484,8 @@ static u32 vmx_vmexit_ctrl(void)
vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP |
VM_EXIT_CLEAR_IA32_RTIT_CTL);
- if (cpu_has_perf_global_ctrl_bug())
- vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
-
- /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
- return vmexit_ctrl &
- ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER);
+ /* Loading of EFER is toggled dynamically */
+ return vmexit_ctrl & ~VM_EXIT_LOAD_IA32_EFER;
}
static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
@@ -4765,6 +4823,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write64(VM_FUNCTION_CONTROL, 0);
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val));
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
@@ -7822,6 +7881,8 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
if (is_passthrough_pmu_enabled(&vmx->vcpu))
exec_controls_clearbit(vmx, CPU_BASED_RDPMC_EXITING);
+ vmx_set_perf_global_ctrl(vmx);
+
/* Refresh #PF interception to account for MAXPHYADDR changes. */
vmx_update_exception_bitmap(vcpu);
}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index c2130d2c8e24..c89db35e1de8 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -502,7 +502,8 @@ static inline u8 vmx_get_rvi(void)
VM_EXIT_LOAD_IA32_EFER | \
VM_EXIT_CLEAR_BNDCFGS | \
VM_EXIT_PT_CONCEAL_PIP | \
- VM_EXIT_CLEAR_IA32_RTIT_CTL)
+ VM_EXIT_CLEAR_IA32_RTIT_CTL | \
+ VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL)
#define KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL \
(PIN_BASED_EXT_INTR_MASK | \
--
2.34.1
On Fri, Jan 26, 2024, Xiong Zhang wrote:
> + if (is_passthrough_pmu_enabled(&vmx->vcpu)) {
> + /*
> + * Setup auto restore guest PERF_GLOBAL_CTRL MSR at vm entry.
> + */
> + if (vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
> + vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, 0);
> + else {
> + i = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest,
> + MSR_CORE_PERF_GLOBAL_CTRL);
> + if (i < 0) {
> + i = vmx->msr_autoload.guest.nr++;
> + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT,
> + vmx->msr_autoload.guest.nr);
> + }
> + vmx->msr_autoload.guest.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
> + vmx->msr_autoload.guest.val[i].value = 0;
Eww, no. Just make cpu_has_load_perf_global_ctrl() and VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL
hard requirements for enabling passthrough mode. And then have clear_atomic_switch_msr()
yell if KVM tries to disable loading MSR_CORE_PERF_GLOBAL_CTRL.
On Thu, Apr 11, 2024 at 2:21 PM Sean Christopherson <[email protected]> wrote:
>
> On Fri, Jan 26, 2024, Xiong Zhang wrote:
> > + if (is_passthrough_pmu_enabled(&vmx->vcpu)) {
> > + /*
> > + * Setup auto restore guest PERF_GLOBAL_CTRL MSR at vm entry.
> > + */
> > + if (vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
> > + vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, 0);
> > + else {
> > + i = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest,
> > + MSR_CORE_PERF_GLOBAL_CTRL);
> > + if (i < 0) {
> > + i = vmx->msr_autoload.guest.nr++;
> > + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT,
> > + vmx->msr_autoload.guest.nr);
> > + }
> > + vmx->msr_autoload.guest.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
> > + vmx->msr_autoload.guest.val[i].value = 0;
>
> Eww, no. Just make cpu_has_load_perf_global_ctrl() and VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL
> hard requirements for enabling passthrough mode. And then have clear_atomic_switch_msr()
> yell if KVM tries to disable loading MSR_CORE_PERF_GLOBAL_CTRL.
Weren't you just complaining about the PMU version 4 constraint in
another patch? And here, you are saying, "Don't support anything older
than Sapphire Rapids."
Sapphire Rapids has PMU version 4, so if we require
VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL, PMU version 4 is irrelevant.
On Thu, Apr 11, 2024, Jim Mattson wrote:
> On Thu, Apr 11, 2024 at 2:21 PM Sean Christopherson <[email protected]> wrote:
> >
> > On Fri, Jan 26, 2024, Xiong Zhang wrote:
> > > + if (is_passthrough_pmu_enabled(&vmx->vcpu)) {
> > > + /*
> > > + * Setup auto restore guest PERF_GLOBAL_CTRL MSR at vm entry.
> > > + */
> > > + if (vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
> > > + vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, 0);
> > > + else {
> > > + i = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest,
> > > + MSR_CORE_PERF_GLOBAL_CTRL);
> > > + if (i < 0) {
> > > + i = vmx->msr_autoload.guest.nr++;
> > > + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT,
> > > + vmx->msr_autoload.guest.nr);
> > > + }
> > > + vmx->msr_autoload.guest.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
> > > + vmx->msr_autoload.guest.val[i].value = 0;
> >
> > Eww, no. Just make cpu_has_load_perf_global_ctrl() and VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL
> > hard requirements for enabling passthrough mode. And then have clear_atomic_switch_msr()
> > yell if KVM tries to disable loading MSR_CORE_PERF_GLOBAL_CTRL.
>
> Weren't you just complaining about the PMU version 4 constraint in
> another patch? And here, you are saying, "Don't support anything older
> than Sapphire Rapids."
Heh, I didn't realize VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL was SPR+ when I wrote
this, I thought it existed alongside the "load" controls.
> Sapphire Rapids has PMU version 4, so if we require
> VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL, PMU version 4 is irrelevant.
On 4/12/2024 6:30 AM, Jim Mattson wrote:
> On Thu, Apr 11, 2024 at 2:21 PM Sean Christopherson <[email protected]> wrote:
>> On Fri, Jan 26, 2024, Xiong Zhang wrote:
>>> + if (is_passthrough_pmu_enabled(&vmx->vcpu)) {
>>> + /*
>>> + * Setup auto restore guest PERF_GLOBAL_CTRL MSR at vm entry.
>>> + */
>>> + if (vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
>>> + vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, 0);
>>> + else {
>>> + i = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest,
>>> + MSR_CORE_PERF_GLOBAL_CTRL);
>>> + if (i < 0) {
>>> + i = vmx->msr_autoload.guest.nr++;
>>> + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT,
>>> + vmx->msr_autoload.guest.nr);
>>> + }
>>> + vmx->msr_autoload.guest.val[i].index = MSR_CORE_PERF_GLOBAL_CTRL;
>>> + vmx->msr_autoload.guest.val[i].value = 0;
>> Eww, no. Just make cpu_has_load_perf_global_ctrl() and VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL
>> hard requirements for enabling passthrough mode. And then have clear_atomic_switch_msr()
>> yell if KVM tries to disable loading MSR_CORE_PERF_GLOBAL_CTRL.
> Weren't you just complaining about the PMU version 4 constraint in
> another patch? And here, you are saying, "Don't support anything older
> than Sapphire Rapids."
>
> Sapphire Rapids has PMU version 4, so if we require
> VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL, PMU version 4 is irrelevant.
Just clarify Sapphire Rapids has PMU version 5 :).
[ 2.687826] Performance Events: XSAVE Architectural LBR, PEBS
fmt4+-baseline, AnyThread deprecated, *Sapphire Rapids events*, 32-deep
LBR, full-width counters, Intel PMU driver.
[ 2.687925] ... version: 5
[ 2.687928] ... bit width: 48
[ 2.687929] ... generic counters: 8
>