SEV-ES TSC_AUX virtualization fix and optimization
cover SEV-ES TSC_AUX virtualization fix and optimization
This patch series provides a fix to the TSC_AUX virtualization support and an optimization to reduce the number of WRMSRs to TSC_AUX when it is virtualized.
---
Patches based on https://git.kernel.org/pub/scm/virt/kvm/kvm.git master
and commit:
7c7cce2cf7ee ("Merge tag 'kvmarm-fixes-6.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD")
Tom Lendacky (2):
KVM: SVM: Fix TSC_AUX virtualization setup
KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX
arch/x86/kvm/svm/sev.c | 41 ++++++++++++++++++++++++++++++++--------- arch/x86/kvm/svm/svm.c | 29 +++++++++++++++++++---------- arch/x86/kvm/svm/svm.h | 5 ++++- 3 files changed, 55 insertions(+), 20 deletions(-)
Signature · 1 line
2.41.0
PATCH 1/2 KVM: SVM: Fix TSC_AUX virtualization setup
The checks for virtualizing TSC_AUX occur during the vCPU reset processing path. However, at the time of initial vCPU reset processing, when the vCPU is first created, not all of the guest CPUID information has been set. In this case the RDTSCP and RDPID feature support for the guest is not in place and so TSC_AUX virtualization is not established.
This continues for each vCPU created for the guest. On the first boot of an AP, vCPU reset processing is executed as a result of an APIC INIT event, this time with all of the guest CPUID information set, resulting in TSC_AUX virtualization being enabled, but only for the APs. The BSP always sees a TSC_AUX value of 0 which probably went unnoticed because, at least for Linux, the BSP TSC_AUX value is 0.
Move the TSC_AUX virtualization enablement into the vcpu_after_set_cpuid() path to allow for proper initialization of the support after the guest CPUID information has been set.
--- arch/x86/kvm/svm/sev.c | 27 +++++++++++++++++++-------- arch/x86/kvm/svm/svm.c | 3 +++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 23 insertions(+), 8 deletions(-)
arch/x86/kvm/svm/sev.c +19 -8
@@ -2962,6 +2962,25 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_init_vmcb_after_set_cpuid (struct vcpu_svm *svm) +{ +struct kvm_vcpu *vcpu = &svm->vcpu; + +if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && + (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) || +guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { +set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 ); +if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP )) +svm_clr_intercept (svm,INTERCEPT_RDTSCP ); + } +} + +void sev_init_vmcb_after_set_cpuid (struct vcpu_svm *svm) +{ +if (sev_es_guest (svm->vcpu.kvm)) +sev_es_init_vmcb_after_set_cpuid (svm); +} +static void sev_es_init_vmcb (struct vcpu_svm *svm) {struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -3024,14 +3043,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)set_msr_interception (vcpu, svm->msrpm,MSR_IA32_LASTBRANCHTOIP ,1 ,1 );set_msr_interception (vcpu, svm->msrpm,MSR_IA32_LASTINTFROMIP ,1 ,1 );set_msr_interception (vcpu, svm->msrpm,MSR_IA32_LASTINTTOIP ,1 ,1 ); - -if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && - (guest_cpuid_has (&svm->vcpu,X86_FEATURE_RDTSCP ) || -guest_cpuid_has (&svm->vcpu,X86_FEATURE_RDPID ))) { -set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 ); -if (guest_cpuid_has (&svm->vcpu,X86_FEATURE_RDTSCP )) -svm_clr_intercept (svm,INTERCEPT_RDTSCP ); - } }void sev_init_vmcb (struct vcpu_svm *svm)
arch/x86/kvm/svm/svm.c +3 -0
@@ -1225,6 +1225,9 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)set_msr_interception (vcpu, svm->msrpm,MSR_IA32_SYSENTER_EIP ,1 ,1 );set_msr_interception (vcpu, svm->msrpm,MSR_IA32_SYSENTER_ESP ,1 ,1 ); } + +if (sev_guest (vcpu->kvm)) +sev_init_vmcb_after_set_cpuid (svm); }static void init_vmcb (struct kvm_vcpu *vcpu)
arch/x86/kvm/svm/svm.h +1 -0
@@ -684,6 +684,7 @@ void __init sev_hardware_setup(void);void sev_hardware_unsetup (void );int sev_cpu_init (struct svm_cpu_data *sd);void sev_init_vmcb (struct vcpu_svm *svm); +void sev_init_vmcb_after_set_cpuid (struct vcpu_svm *svm);void sev_free_vcpu (struct kvm_vcpu *vcpu);int sev_handle_vmgexit (struct kvm_vcpu *vcpu);int sev_es_string_io (struct vcpu_svm *svm,int size,unsigned int port,int in);
Signature · 1 line
2.41.0
Sean Christopherson
maintainerRe: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 30 lines · Tom Lendacky
The checks for virtualizing
TSC_AUXoccur during the vCPU reset processing path. However, at the time of initial vCPU reset processing, when the vCPU is first created, not all of the guest CPUID information has been set. In this case the RDTSCP and RDPID feature support for the guest is not in place and soTSC_AUXvirtualization is not established.This continues for each vCPU created for the guest. On the first boot of an AP, vCPU reset processing is executed as a result of an APIC INIT event, this time with all of the guest CPUID information set, resulting in
TSC_AUXvirtualization being enabled, but only for the APs. The BSP always sees aTSC_AUXvalue of 0 which probably went unnoticed because, at least for Linux, the BSPTSC_AUXvalue is 0.Move the
TSC_AUXvirtualization enablement into thevcpu_after_set_cpuid()path to allow for proper initialization of the support after the guest CPUID information has been set.Fixes 296d5a17e793 ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts")Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 27 +++++++++++++++++++-------- arch/x86/kvm/svm/svm.c | 3 +++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 23 insertions(+), 8 deletions(-)arch/x86/kvm/svm/sev.c +0
-0
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2965
Quoted 4 lines
arch/x86/kvm/svm/sev.c +1
-0@@ -2962,6 +2962,25 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_init_vmcb_after_set_cpuid (struct vcpu_svm *svm)
I would rather name this sev_es_after_set_cpuid() and call it directly from svm_vcpu_after_set_cpuid(). Or I suppose bounce through sev_after_set_cpuid(), but that seems gratuitous.
AFAICT, there's no point in calling this from init_vmcb(); guest_cpuid_has() is guaranteed to be false when called during vCPU creation and so the intercept behavior will be correct, and even if SEV-ES called init_vmcb() from shutdown_interception(), which it doesn't, guest_cpuid_has() wouldn't change, i.e. the intercepts wouldn't need to be changed.
init_vmcb_after_set_cpuid() is a special snowflake because it handles both SVM's true defaults *and* guest CPUID updates.
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2972
Quoted 7 lines
arch/x86/kvm/svm/sev.c +7
-0+{ +struct kvm_vcpu *vcpu = &svm->vcpu; + +if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && + (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) || +guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { +set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );
This needs to toggled interception back on if RDTSCP and RDPID are hidden from the guest. KVM's wonderful ABI doesn't disallow multiple calls to KVM_SET_CPUID2 before KVM_RUN.
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2974
Quoted 2 lines
arch/x86/kvm/svm/sev.c +2
-0+if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP )) +svm_clr_intercept (svm,INTERCEPT_RDTSCP );
Same thing here.
Quoted 2 lines
arch/x86/kvm/svm/sev.c +2
-0+ } +}
Re: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 34 lines · Sean Christopherson
Quoted 33 lines · Tom Lendacky
The checks for virtualizing
TSC_AUXoccur during the vCPU reset processing path. However, at the time of initial vCPU reset processing, when the vCPU is first created, not all of the guest CPUID information has been set. In this case the RDTSCP and RDPID feature support for the guest is not in place and soTSC_AUXvirtualization is not established.This continues for each vCPU created for the guest. On the first boot of an AP, vCPU reset processing is executed as a result of an APIC INIT event, this time with all of the guest CPUID information set, resulting in
TSC_AUXvirtualization being enabled, but only for the APs. The BSP always sees aTSC_AUXvalue of 0 which probably went unnoticed because, at least for Linux, the BSPTSC_AUXvalue is 0.Move the
TSC_AUXvirtualization enablement into thevcpu_after_set_cpuid()path to allow for proper initialization of the support after the guest CPUID information has been set.Fixes 296d5a17e793 ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts")Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 27 +++++++++++++++++++-------- arch/x86/kvm/svm/svm.c | 3 +++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 23 insertions(+), 8 deletions(-)arch/x86/kvm/svm/sev.c +0
-0@@ -2962,6 +2962,25 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); }
Quoted 5 lines
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2965
Quoted 1 line
arch/x86/kvm/svm/sev.c +1
-0+static void sev_es_init_vmcb_after_set_cpuid (struct vcpu_svm *svm)I would rather name this
sev_es_after_set_cpuid()and call it directly fromsvm_vcpu_after_set_cpuid(). Or I suppose bounce throughsev_after_set_cpuid(), but that seems gratuitous.
There is a sev_guest() check in svm_vcpu_after_set_cpuid(), so I can move that into sev_vcpu_after_set_cpuid() and keep the separate sev_es_vcpu_after_set_cpuid(). And it looks like you would prefer to not have "vcpu" in the function name? Might be better search-wise if vcpu remains part of the name?
Quoted 6 lines
AFAICT, there's no point in calling this from
init_vmcb();guest_cpuid_has()is guaranteed to be false when called during vCPU creation and so the intercept behavior will be correct, and even if SEV-ES calledinit_vmcb()fromshutdown_interception(), which it doesn't,guest_cpuid_has()wouldn't change, i.e. the intercepts wouldn't need to be changed.
Ok, I thought that's how it worked, but wasn't 100% sure. I'll move it out of the init_vmcb() path.
Quoted 4 lines
init_vmcb_after_set_cpuid()is a special snowflake because it handles both SVM's true defaults *and* guest CPUID updates.
Quoted 11 lines
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2972
Quoted 7 lines
arch/x86/kvm/svm/sev.c +7
-0+{ +struct kvm_vcpu *vcpu = &svm->vcpu; + +if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && + (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) || +guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { +set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );This needs to toggled interception back on if RDTSCP and RDPID are hidden from the guest. KVM's wonderful ABI doesn't disallow multiple calls to
KVM_SET_CPUID2beforeKVM_RUN.
Do you want that as a separate patch with the first patch purely addressing the current issue? Or combine them?
Quoted 5 lines
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2974
Quoted 3 lines
arch/x86/kvm/svm/sev.c +2
-0+if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP )) +svm_clr_intercept (svm,INTERCEPT_RDTSCP );Same thing here.
Will do.
Thanks,
Tom
Quoted 3 lines
Quoted 3 lines
arch/x86/kvm/svm/sev.c +2
-0+ } +}
Sean Christopherson
maintainerRe: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 40 lines · Tom Lendacky
Quoted 26 lines · Sean Christopherson
Quoted 25 lines · Tom Lendacky
The checks for virtualizing
TSC_AUXoccur during the vCPU reset processing path. However, at the time of initial vCPU reset processing, when the vCPU is first created, not all of the guest CPUID information has been set. In this case the RDTSCP and RDPID feature support for the guest is not in place and soTSC_AUXvirtualization is not established.This continues for each vCPU created for the guest. On the first boot of an AP, vCPU reset processing is executed as a result of an APIC INIT event, this time with all of the guest CPUID information set, resulting in
TSC_AUXvirtualization being enabled, but only for the APs. The BSP always sees aTSC_AUXvalue of 0 which probably went unnoticed because, at least for Linux, the BSPTSC_AUXvalue is 0.Move the
TSC_AUXvirtualization enablement into thevcpu_after_set_cpuid()path to allow for proper initialization of the support after the guest CPUID information has been set.Fixes 296d5a17e793 ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts")Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 27 +++++++++++++++++++-------- arch/x86/kvm/svm/svm.c | 3 +++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 23 insertions(+), 8 deletions(-)Quoted 12 lines
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2964
Quoted 8 lines
arch/x86/kvm/svm/sev.c +1
-0@@ -2962,6 +2962,25 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_init_vmcb_after_set_cpuid (struct vcpu_svm *svm)I would rather name this
sev_es_after_set_cpuid()and call it directly fromsvm_vcpu_after_set_cpuid(). Or I suppose bounce throughsev_after_set_cpuid(), but that seems gratuitous.
Quoted 3 lines
There is a
sev_guest()check insvm_vcpu_after_set_cpuid(), so I can move that intosev_vcpu_after_set_cpuid()and keep the separatesev_es_vcpu_after_set_cpuid().
Works for me.
Quoted 2 lines
And it looks like you would prefer to not have "vcpu" in the function name? Might be better search-wise if vcpu remains part of the name?
Oh, that was just a typo/oversight, not intentional.
Quoted 25 lines
Quoted 5 lines
AFAICT, there's no point in calling this from
init_vmcb();guest_cpuid_has()is guaranteed to be false when called during vCPU creation and so the intercept behavior will be correct, and even if SEV-ES calledinit_vmcb()fromshutdown_interception(), which it doesn't,guest_cpuid_has()wouldn't change, i.e. the intercepts wouldn't need to be changed.Ok, I thought that's how it worked, but wasn't 100% sure. I'll move it out of the
init_vmcb()path.Quoted 4 lines
init_vmcb_after_set_cpuid()is a special snowflake because it handles both SVM's true defaults *and* guest CPUID updates.Quoted 11 lines
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2972
Quoted 7 lines
arch/x86/kvm/svm/sev.c +7
-0+{ +struct kvm_vcpu *vcpu = &svm->vcpu; + +if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && + (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) || +guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { +set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );This needs to toggled interception back on if RDTSCP and RDPID are hidden from the guest. KVM's wonderful ABI doesn't disallow multiple calls to
KVM_SET_CPUID2beforeKVM_RUN.
Quoted 2 lines
Do you want that as a separate patch with the first patch purely addressing the current issue? Or combine them?
Hmm, now that you mention it, probably a seperate patch on top.
Re: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 77 lines · Sean Christopherson
Quoted 40 lines · Tom Lendacky
Quoted 26 lines · Sean Christopherson
Quoted 25 lines · Tom Lendacky
The checks for virtualizing
TSC_AUXoccur during the vCPU reset processing path. However, at the time of initial vCPU reset processing, when the vCPU is first created, not all of the guest CPUID information has been set. In this case the RDTSCP and RDPID feature support for the guest is not in place and soTSC_AUXvirtualization is not established.This continues for each vCPU created for the guest. On the first boot of an AP, vCPU reset processing is executed as a result of an APIC INIT event, this time with all of the guest CPUID information set, resulting in
TSC_AUXvirtualization being enabled, but only for the APs. The BSP always sees aTSC_AUXvalue of 0 which probably went unnoticed because, at least for Linux, the BSPTSC_AUXvalue is 0.Move the
TSC_AUXvirtualization enablement into thevcpu_after_set_cpuid()path to allow for proper initialization of the support after the guest CPUID information has been set.Fixes 296d5a17e793 ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts")Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 27 +++++++++++++++++++-------- arch/x86/kvm/svm/svm.c | 3 +++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 23 insertions(+), 8 deletions(-)Quoted 12 lines
arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2964
Quoted 8 lines
arch/x86/kvm/svm/sev.c +1
-0@@ -2962,6 +2962,25 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_init_vmcb_after_set_cpuid (struct vcpu_svm *svm)I would rather name this
sev_es_after_set_cpuid()and call it directly fromsvm_vcpu_after_set_cpuid(). Or I suppose bounce throughsev_after_set_cpuid(), but that seems gratuitous.Quoted 3 lines
There is a
sev_guest()check insvm_vcpu_after_set_cpuid(), so I can move that intosev_vcpu_after_set_cpuid()and keep the separatesev_es_vcpu_after_set_cpuid().Works for me.
Quoted 2 lines
And it looks like you would prefer to not have "vcpu" in the function name? Might be better search-wise if vcpu remains part of the name?
Oh, that was just a typo/oversight, not intentional.
Quoted 25 lines
Quoted 5 lines
AFAICT, there's no point in calling this from
init_vmcb();guest_cpuid_has()is guaranteed to be false when called during vCPU creation and so the intercept behavior will be correct, and even if SEV-ES calledinit_vmcb()fromshutdown_interception(), which it doesn't,guest_cpuid_has()wouldn't change, i.e. the intercepts wouldn't need to be changed.Ok, I thought that's how it worked, but wasn't 100% sure. I'll move it out of the
init_vmcb()path.Quoted 15 lines
init_vmcb_after_set_cpuid()is a special snowflake because it handles both SVM's true defaults *and* guest CPUID updates.arch/x86/kvm/svm/sev.c int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) · line 2972
Quoted 7 lines
arch/x86/kvm/svm/sev.c +7
-0+{ +struct kvm_vcpu *vcpu = &svm->vcpu; + +if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && + (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) || +guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { +set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );This needs to toggled interception back on if RDTSCP and RDPID are hidden from the guest. KVM's wonderful ABI doesn't disallow multiple calls to
KVM_SET_CPUID2beforeKVM_RUN.
Quoted 4 lines
Quoted 2 lines
Do you want that as a separate patch with the first patch purely addressing the current issue? Or combine them?
Hmm, now that you mention it, probably a seperate patch on top.
This toggling possibility raises a question related to the second patch in this series that eliminates the use of the user return MSR for TSC_AUX. Depending on when the interfaces are called (set CPUID, host-initiated WRMSR of TSC_AUX, set CPUID again), I think we could end up in a state where the host TSC_AUX may not get restored properly, not 100% sure at the moment, though.
Let me drop that patch from the series for now and just send the fix(es). I'll work through the other scenarios and code paths and send the user return MSR optimization as a separate series later.
Thanks,
Tom
Sean Christopherson
maintainerRe: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 7 lines · Tom Lendacky
On 9/14/23 16:13, Sean Christopherson wrote:
This toggling possibility raises a question related to the second patch in this series that eliminates the use of the user return MSR forTSC_AUX. Depending on when the interfaces are called (set CPUID, host-initiated WRMSR ofTSC_AUX, set CPUID again), I think we could end up in a state where the hostTSC_AUXmay not get restored properly, not 100% sure at the moment, though.
Give me a few minutes to respond to patch 2, I think it can be much simpler, more performant, and avoid any races.
Quoted 3 lines
Let me drop that patch from the series for now and just send the fix(es). I'll work through the other scenarios and code paths and send the user return MSR optimization as a separate series later.
Re: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
In reply to Tom LendackyQuoted 11 lines · Tom Lendacky
Quoted 8 lines · Sean Christopherson
Quoted 2 lines · Tom Lendacky
+ if (
guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) +svm_clr_intercept(svm, INTERCEPT_RDTSCP);Same thing here.
Will do.
For RDTSCP, svm_recalc_instruction_intercepts() will set/clear the RDTSCP intercept as part of the svm_vcpu_set_after_cpuid() path, but it will only do it based on kvm_cpu_cap_has(X86_FEATURE_RDTSCP) being true, which is very likely.
Do you think that is good enough and we can drop the setting and clearing of the RDTSCP intercept in the sev_es_vcpu_set_after_cpuid() function and only deal with the TSC_AUX MSR intercept?
On a side note, it looks like RDTSCP would not be intercepted if the KVM cap X86_FEATURE_RDTSCP feature is cleared, however unlikely, in kvm_set_cpu_caps() and RDTSCP is not advertised to the guest (assuming the guest is ignoring the RDTSCP CPUID bit).
Thanks,
Tom
Quoted 7 lines
Thanks,
TomQuoted 3 lines
Quoted 3 lines
+ }
+}
Sean Christopherson
maintainerRe: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 13 lines · Tom Lendacky
Quoted 11 lines · Tom Lendacky
Quoted 8 lines · Sean Christopherson
Quoted 2 lines · Tom Lendacky
+ if (
guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) +svm_clr_intercept(svm, INTERCEPT_RDTSCP);Same thing here.
Will do.
Quoted 8 lines
For RDTSCP,
svm_recalc_instruction_intercepts()will set/clear the RDTSCP intercept as part of thesvm_vcpu_set_after_cpuid()path, but it will only do it based onkvm_cpu_cap_has(X86_FEATURE_RDTSCP)being true, which is very likely.Do you think that is good enough and we can drop the setting and clearing of the RDTSCP intercept in the
sev_es_vcpu_set_after_cpuid()function and only deal with theTSC_AUXMSR intercept?
The common handling should be good enough.
Quoted 4 lines
On a side note, it looks like RDTSCP would not be intercepted if the KVM cap
X86_FEATURE_RDTSCPfeature is cleared, however unlikely, inkvm_set_cpu_caps()and RDTSCP is not advertised to the guest (assuming the guest is ignoring the RDTSCP CPUID bit).
Hmm, yes, though the only scenario in which KVM clears RDTSCP on AMD comes with a WARN (it's a guard against KVM bugs). If the guest ignores CPUID and uses RDTSCP anyways, the guest deserves its death, and leaking the host pCPU doesn't seem like a major issue.
That said, if hardware behavior is to ignore unknown intercepts, e.g. if KVM can safely set INTERCEPT_RDTSCP even when hardware doesn't support said intercept, then I wouldn't be opposed to doing:
/* * Intercept INVPCID if shadow paging is enabled to sync/free shadow * roots, or if INVPCID is disabled in the guest to inject #UD. */ if (!kvm_cpu_cap_has(X86_FEATURE_INVPCID) || !npt_enabled || !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) svm_set_intercept(svm, INTERCEPT_INVPCID); else svm_clr_intercept(svm, INTERCEPT_INVPCID); if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) svm_clr_intercept(svm, INTERCEPT_RDTSCP); else svm_set_intercept(svm, INTERCEPT_RDTSCP);
Alternatively, KVM could check boot_cpu_has() instead or kvm_cpu_cap_has(), but that's not foolproof either, e.g. see Intel's of hiding PCID to workaround the TLB flushing bug on Alderlake. So my vote would either be to keep things as-is, or do the above (if that's safe).
Re: [PATCH 1/2] KVM: SVM: Fix TSC_AUX virtualization setup
Quoted 55 lines · Sean Christopherson
Quoted 13 lines · Tom Lendacky
Quoted 11 lines · Tom Lendacky
Quoted 8 lines · Sean Christopherson
Quoted 2 lines · Tom Lendacky
+ if (
guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) +svm_clr_intercept(svm, INTERCEPT_RDTSCP);Same thing here.
Will do.
Quoted 8 lines
For RDTSCP,
svm_recalc_instruction_intercepts()will set/clear the RDTSCP intercept as part of thesvm_vcpu_set_after_cpuid()path, but it will only do it based onkvm_cpu_cap_has(X86_FEATURE_RDTSCP)being true, which is very likely.Do you think that is good enough and we can drop the setting and clearing of the RDTSCP intercept in the
sev_es_vcpu_set_after_cpuid()function and only deal with theTSC_AUXMSR intercept?The common handling should be good enough.
Quoted 4 lines
On a side note, it looks like RDTSCP would not be intercepted if the KVM cap
X86_FEATURE_RDTSCPfeature is cleared, however unlikely, inkvm_set_cpu_caps()and RDTSCP is not advertised to the guest (assuming the guest is ignoring the RDTSCP CPUID bit).Hmm, yes, though the only scenario in which KVM clears RDTSCP on AMD comes with a WARN (it's a guard against KVM bugs). If the guest ignores CPUID and uses RDTSCP anyways, the guest deserves its death, and leaking the host pCPU doesn't seem like a major issue.
That said, if hardware behavior is to ignore unknown intercepts, e.g. if KVM can safely set
INTERCEPT_RDTSCPeven when hardware doesn't support said intercept, then I wouldn't be opposed to doing:/* * Intercept INVPCID if shadow paging is enabled to sync/free shadow * roots, or if INVPCID is disabled in the guest to inject #UD. */ if (!kvm_cpu_cap_has(X86_FEATURE_INVPCID) || !npt_enabled || !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) svm_set_intercept(svm, INTERCEPT_INVPCID); else svm_clr_intercept(svm, INTERCEPT_INVPCID); if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) svm_clr_intercept(svm, INTERCEPT_RDTSCP); else svm_set_intercept(svm, INTERCEPT_RDTSCP);
Quoted 4 lines
Alternatively, KVM could check
boot_cpu_has()instead orkvm_cpu_cap_has(), but that's not foolproof either, e.g. see Intel's of hiding PCID to workaround the TLB flushing bug on Alderlake. So my vote would either be to keep things as-is, or do the above (if that's safe).
Keep things as-is works for me :)
Thanks,
Tom
PATCH 2/2 KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX
In reply to Tom LendackyWhen the TSC_AUX MSR is virtualized, the TSC_AUX value is swap type "B" within the VMSA. This means that the guest value is loaded on VMRUN and the host value is restored from the host save area on #VMEXIT.
Since the value is restored on #VMEXIT, the KVM user return MSR support for TSC_AUX can be replaced by populating the host save area with current host value of TSC_AUX. This replaces two WRMSR instructions with a single RDMSR instruction.
--- arch/x86/kvm/svm/sev.c | 14 +++++++++++++- arch/x86/kvm/svm/svm.c | 26 ++++++++++++++++---------- arch/x86/kvm/svm/svm.h | 4 +++- 3 files changed, 32 insertions(+), 12 deletions(-)
arch/x86/kvm/svm/sev.c +13 -1
@@ -2969,6 +2969,7 @@ static void sev_es_init_vmcb_after_set_cpuid(struct vcpu_svm *svm)if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) ||guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { + svm->v_tsc_aux = true;set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ))svm_clr_intercept (svm,INTERCEPT_RDTSCP );
@@ -3071,8 +3072,10 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest (struct sev_es_save_area *hostsa) +void sev_es_prepare_switch_to_guest (struct vcpu_svm *svm,struct sev_es_save_area *hostsa) { +u32 msr_hi; +/* * All host state for SEV-ES guests is categorized into three swap types * based on how it is handled by hardware during a world switch:
@@ -3109,6 +3112,15 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) hostsa->dr2_addr_mask =amd_get_dr_addr_mask (2 ); hostsa->dr3_addr_mask =amd_get_dr_addr_mask (3 ); } + +/* +* If TSC_AUX virtualization is enabled, MSR_TSC_AUX is loaded but NOT +* saved by the CPU (Type-B). If TSC_AUX is not virtualized, the user +* return MSR support takes care of restoring MSR_TSC_AUX. This +* exchanges two WRMSRs for one RDMSR. +*/ +if (svm->v_tsc_aux) +rdmsr (MSR_TSC_AUX , hostsa->tsc_aux, msr_hi); }void sev_vcpu_deliver_sipi_vector (struct kvm_vcpu *vcpu,u8 vector)
arch/x86/kvm/svm/svm.c +16 -10
@@ -1529,13 +1529,13 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)struct sev_es_save_area *hostsa; hostsa = (struct sev_es_save_area *)(page_address (sd->save_area) +0x400 ); -sev_es_prepare_switch_to_guest (hostsa); +sev_es_prepare_switch_to_guest (svm, hostsa); }if (tsc_scaling)__svm_write_tsc_multiplier (vcpu->arch.tsc_scaling_ratio); -if (likely (tsc_aux_uret_slot >=0 )) +if (likely (tsc_aux_uret_slot >=0 ) && !svm->v_tsc_aux)kvm_set_user_return_msr (tsc_aux_uret_slot, svm->tsc_aux,-1ull ); svm->guest_state_loaded = true;
@@ -3090,15 +3090,21 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)break ;case MSR_TSC_AUX :/* -* TSC_AUX is usually changed only during boot and never read -* directly. Intercept TSC_AUX instead of exposing it to the -* guest via direct_access_msrs, and switch it via user return. +* If TSC_AUX is being virtualized, do not use the user return +* MSR support because TSC_AUX is restored on #VMEXIT. */ -preempt_disable (); - ret =kvm_set_user_return_msr (tsc_aux_uret_slot, data,-1ull ); -preempt_enable (); -if (ret) -break ; +if (!svm->v_tsc_aux) { +/* +* TSC_AUX is usually changed only during boot and never read +* directly. Intercept TSC_AUX instead of exposing it to the +* guest via direct_access_msrs, and switch it via user return. +*/ +preempt_disable (); + ret =kvm_set_user_return_msr (tsc_aux_uret_slot, data,-1ull ); +preempt_enable (); +if (ret) +break ; + } svm->tsc_aux = data;break ;
arch/x86/kvm/svm/svm.h +3 -1
@@ -213,6 +213,8 @@ struct vcpu_svm {u32 asid;u32 sysenter_esp_hi;u32 sysenter_eip_hi; + +bool v_tsc_aux;uint64_t tsc_aux;u64 msr_decfg;
@@ -690,7 +692,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu);int sev_es_string_io (struct vcpu_svm *svm,int size,unsigned int port,int in);void sev_es_vcpu_reset (struct vcpu_svm *svm);void sev_vcpu_deliver_sipi_vector (struct kvm_vcpu *vcpu,u8 vector); -void sev_es_prepare_switch_to_guest (struct sev_es_save_area *hostsa); +void sev_es_prepare_switch_to_guest (struct vcpu_svm *svm,struct sev_es_save_area *hostsa);void sev_es_unmap_ghcb (struct vcpu_svm *svm);/* vmenter.S */
Signature · 1 line
2.41.0
Sean Christopherson
maintainerRe: [PATCH 2/2] KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX
Quoted 43 lines · Tom Lendacky
When the
TSC_AUXMSR is virtualized, theTSC_AUXvalue is swap type "B" within the VMSA. This means that the guest value is loaded on VMRUN and the host value is restored from the host save area on #VMEXIT.Since the value is restored on #VMEXIT, the KVM user return MSR support for
TSC_AUXcan be replaced by populating the host save area with current host value ofTSC_AUX. This replaces two WRMSR instructions with a single RDMSR instruction.Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 14 +++++++++++++- arch/x86/kvm/svm/svm.c | 26 ++++++++++++++++---------- arch/x86/kvm/svm/svm.h | 4 +++- 3 files changed, 32 insertions(+), 12 deletions(-)arch/x86/kvm/svm/sev.c +4
-1@@ -2969,6 +2969,7 @@ static void sev_es_init_vmcb_after_set_cpuid(struct vcpu_svm *svm)if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) ||guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { + svm->v_tsc_aux = true;set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ))svm_clr_intercept (svm,INTERCEPT_RDTSCP );@@ -3071,8 +3072,10 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest (struct sev_es_save_area *hostsa) +void sev_es_prepare_switch_to_guest (struct vcpu_svm *svm,struct sev_es_save_area *hostsa) { +u32 msr_hi; +/* * All host state for SEV-ES guests is categorized into three swap types * based on how it is handled by hardware during a world switch: @@ -3109,6 +3112,15 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) hostsa->dr2_addr_mask =amd_get_dr_addr_mask (2 ); hostsa->dr3_addr_mask =amd_get_dr_addr_mask (3 );
arch/x86/kvm/svm/sev.c void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) · line 3123
Quoted 10 lines
arch/x86/kvm/svm/sev.c +9
-0} + +/* +* If TSC_AUX virtualization is enabled, MSR_TSC_AUX is loaded but NOT +* saved by the CPU (Type-B). If TSC_AUX is not virtualized, the user +* return MSR support takes care of restoring MSR_TSC_AUX. This +* exchanges two WRMSRs for one RDMSR. +*/ +if (svm->v_tsc_aux) +rdmsr (MSR_TSC_AUX , hostsa->tsc_aux, msr_hi);
IIUC, when V_TSC_AUX is supported, SEV-ES guests context switch MSR_TSC_AUX regardless of what has been exposed to the guest. So rather than condition the hostsa->tsc_aux update on guest CPUID, just do it if V_TSC_AUX is supported.
And then to avoid the RDMSR, which is presumably the motivation for checking guest CPUID, grab the host value from user return framework. The host values are per-CPU, but constant after boot, so the only requirement is that KVM sets up MSR_TSC_AUX in the user return framework.
Quoted 10 lines
arch/x86/kvm/svm/sev.c +0
-0}void sev_vcpu_deliver_sipi_vector (struct kvm_vcpu *vcpu,u8 vector)arch/x86/kvm/svm/svm.c +0
-0@@ -1529,13 +1529,13 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)struct sev_es_save_area *hostsa; hostsa = (struct sev_es_save_area *)(page_address (sd->save_area) +0x400 );
arch/x86/kvm/svm/svm.c static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) · line 1538
Quoted 10 lines
arch/x86/kvm/svm/svm.c +2
-2-sev_es_prepare_switch_to_guest (hostsa); +sev_es_prepare_switch_to_guest (svm, hostsa); }if (tsc_scaling)__svm_write_tsc_multiplier (vcpu->arch.tsc_scaling_ratio); -if (likely (tsc_aux_uret_slot >=0 )) +if (likely (tsc_aux_uret_slot >=0 ) && !svm->v_tsc_aux)
And then this too becomes something like
if (likely(tsc_aux_uret_slot >= 0) && (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
arch/x86/kvm/svm/svm.c static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) · line 3091
Quoted 6 lines
arch/x86/kvm/svm/svm.c +0
-0kvm_set_user_return_msr (tsc_aux_uret_slot, svm->tsc_aux,-1ull ); svm->guest_state_loaded = true;@@ -3090,15 +3090,21 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)break ;case MSR_TSC_AUX :
And this also is simply:
if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) break;
Because svm->tsc_aux will never be consumed.
Quoted 27 lines
arch/x86/kvm/svm/svm.c +14
-8/* -* TSC_AUX is usually changed only during boot and never read -* directly. Intercept TSC_AUX instead of exposing it to the -* guest via direct_access_msrs, and switch it via user return. +* If TSC_AUX is being virtualized, do not use the user return +* MSR support because TSC_AUX is restored on #VMEXIT. */ -preempt_disable (); - ret =kvm_set_user_return_msr (tsc_aux_uret_slot, data,-1ull ); -preempt_enable (); -if (ret) -break ; +if (!svm->v_tsc_aux) { +/* +* TSC_AUX is usually changed only during boot and never read +* directly. Intercept TSC_AUX instead of exposing it to the +* guest via direct_access_msrs, and switch it via user return. +*/ +preempt_disable (); + ret =kvm_set_user_return_msr (tsc_aux_uret_slot, data,-1ull ); +preempt_enable (); +if (ret) +break ; + } svm->tsc_aux = data;break ;
Sean Christopherson
maintainerRe: [PATCH 2/2] KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX
Quoted 59 lines · Sean Christopherson
Quoted 43 lines · Tom Lendacky
When the
TSC_AUXMSR is virtualized, theTSC_AUXvalue is swap type "B" within the VMSA. This means that the guest value is loaded on VMRUN and the host value is restored from the host save area on #VMEXIT.Since the value is restored on #VMEXIT, the KVM user return MSR support for
TSC_AUXcan be replaced by populating the host save area with current host value ofTSC_AUX. This replaces two WRMSR instructions with a single RDMSR instruction.Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 14 +++++++++++++- arch/x86/kvm/svm/svm.c | 26 ++++++++++++++++---------- arch/x86/kvm/svm/svm.h | 4 +++- 3 files changed, 32 insertions(+), 12 deletions(-)arch/x86/kvm/svm/sev.c +4
-1@@ -2969,6 +2969,7 @@ static void sev_es_init_vmcb_after_set_cpuid(struct vcpu_svm *svm)if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) ||guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { + svm->v_tsc_aux = true;set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ))svm_clr_intercept (svm,INTERCEPT_RDTSCP );@@ -3071,8 +3072,10 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest (struct sev_es_save_area *hostsa) +void sev_es_prepare_switch_to_guest (struct vcpu_svm *svm,struct sev_es_save_area *hostsa) { +u32 msr_hi; +/* * All host state for SEV-ES guests is categorized into three swap types * based on how it is handled by hardware during a world switch: @@ -3109,6 +3112,15 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) hostsa->dr2_addr_mask =amd_get_dr_addr_mask (2 ); hostsa->dr3_addr_mask =amd_get_dr_addr_mask (3 );arch/x86/kvm/svm/sev.c void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) · line 3123
Quoted 10 lines
arch/x86/kvm/svm/sev.c +9
-0} + +/* +* If TSC_AUX virtualization is enabled, MSR_TSC_AUX is loaded but NOT +* saved by the CPU (Type-B). If TSC_AUX is not virtualized, the user +* return MSR support takes care of restoring MSR_TSC_AUX. This +* exchanges two WRMSRs for one RDMSR. +*/ +if (svm->v_tsc_aux) +rdmsr (MSR_TSC_AUX , hostsa->tsc_aux, msr_hi);IIUC, when
V_TSC_AUXis supported, SEV-ES guests context switchMSR_TSC_AUXregardless of what has been exposed to the guest. So rather than condition thehostsa->tsc_auxupdate on guest CPUID, just do it ifV_TSC_AUXis supported.
Quoted 4 lines
And then to avoid the RDMSR, which is presumably the motivation for checking guest CPUID, grab the host value from user return framework. The host values are per-CPU, but constant after boot, so the only requirement is that KVM sets up
MSR_TSC_AUXin the user return framework.
Actually, duh. The save area is also per-CPU, so just fill hostsa->tsc_aux in svm_hardware_setup() and then sev_es_prepare_switch_to_guest() never has to do anything.
Re: [PATCH 2/2] KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX
Quoted 60 lines · Sean Christopherson
Quoted 59 lines · Sean Christopherson
Quoted 43 lines · Tom Lendacky
When the
TSC_AUXMSR is virtualized, theTSC_AUXvalue is swap type "B" within the VMSA. This means that the guest value is loaded on VMRUN and the host value is restored from the host save area on #VMEXIT.Since the value is restored on #VMEXIT, the KVM user return MSR support for
TSC_AUXcan be replaced by populating the host save area with current host value ofTSC_AUX. This replaces two WRMSR instructions with a single RDMSR instruction.Signed-off-by Tom Lendacky <[email protected]>--- arch/x86/kvm/svm/sev.c | 14 +++++++++++++- arch/x86/kvm/svm/svm.c | 26 ++++++++++++++++---------- arch/x86/kvm/svm/svm.h | 4 +++- 3 files changed, 32 insertions(+), 12 deletions(-)arch/x86/kvm/svm/sev.c +4
-1@@ -2969,6 +2969,7 @@ static void sev_es_init_vmcb_after_set_cpuid(struct vcpu_svm *svm)if (boot_cpu_has (X86_FEATURE_V_TSC_AUX ) && (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ) ||guest_cpuid_has (vcpu,X86_FEATURE_RDPID ))) { + svm->v_tsc_aux = true;set_msr_interception (vcpu, svm->msrpm,MSR_TSC_AUX ,1 ,1 );if (guest_cpuid_has (vcpu,X86_FEATURE_RDTSCP ))svm_clr_intercept (svm,INTERCEPT_RDTSCP );@@ -3071,8 +3072,10 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest (struct sev_es_save_area *hostsa) +void sev_es_prepare_switch_to_guest (struct vcpu_svm *svm,struct sev_es_save_area *hostsa) { +u32 msr_hi; +/* * All host state for SEV-ES guests is categorized into three swap types * based on how it is handled by hardware during a world switch: @@ -3109,6 +3112,15 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) hostsa->dr2_addr_mask =amd_get_dr_addr_mask (2 ); hostsa->dr3_addr_mask =amd_get_dr_addr_mask (3 );arch/x86/kvm/svm/sev.c void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) · line 3123
Quoted 10 lines
arch/x86/kvm/svm/sev.c +9
-0} + +/* +* If TSC_AUX virtualization is enabled, MSR_TSC_AUX is loaded but NOT +* saved by the CPU (Type-B). If TSC_AUX is not virtualized, the user +* return MSR support takes care of restoring MSR_TSC_AUX. This +* exchanges two WRMSRs for one RDMSR. +*/ +if (svm->v_tsc_aux) +rdmsr (MSR_TSC_AUX , hostsa->tsc_aux, msr_hi);IIUC, when
V_TSC_AUXis supported, SEV-ES guests context switchMSR_TSC_AUXregardless of what has been exposed to the guest. So rather than condition thehostsa->tsc_auxupdate on guest CPUID, just do it ifV_TSC_AUXis supported.
Quoted 8 lines
Quoted 4 lines
And then to avoid the RDMSR, which is presumably the motivation for checking guest CPUID, grab the host value from user return framework. The host values are per-CPU, but constant after boot, so the only requirement is that KVM sets up
MSR_TSC_AUXin the user return framework.Actually, duh. The save area is also per-CPU, so just fill
hostsa->tsc_auxinsvm_hardware_setup()and thensev_es_prepare_switch_to_guest()never has to do anything.
Ah, right, because Linux never changes TSC_AUX post boot. Much simpler.
I'll rework based on the comments and send a v2 series.
Thanks,
Tom