In some cases, the handling of quirks is split between platform-specific
code and generic code, or it is done entirely in generic code, but the
relevant bug does not trigger on some platforms; for example,
KVM_X86_QUIRK_CD_NW_CLEARED is only applicable to AMD systems. In that
case, allow unaffected vendor modules to disable handling of the quirk.
The quirk remains available in KVM_CAP_DISABLE_QUIRKS2, because that API
tells userspace that KVM *knows* that some of its past behavior was bogus
or just undesirable. In other words, it's plausible for userspace to
refuse to run if a quirk is not listed by KVM_CAP_DISABLE_QUIRKS2.
In kvm_check_has_quirk(), in addition to checking if a quirk is not
explicitly disabled by the user, also verify if the quirk applies to
the hardware.
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Message-ID: <20250224070832.31394-1-yan.y.zhao@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/vmx/vmx.c | 1 +
arch/x86/kvm/x86.c | 1 +
arch/x86/kvm/x86.h | 12 +++++++-----
3 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 486fbdb4365c..75df4caea2f7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8506,6 +8506,7 @@ __init int vmx_hardware_setup(void)
kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
+ kvm_caps.inapplicable_quirks = KVM_X86_QUIRK_CD_NW_CLEARED;
return r;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 856ceeb4fb35..fd0a44e59314 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9775,6 +9775,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
}
+ kvm_caps.inapplicable_quirks = 0;
rdmsrl_safe(MSR_EFER, &kvm_host.efer);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 8ce6da98b5a2..9af199c8e5c8 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -34,6 +34,7 @@ struct kvm_caps {
u64 supported_xcr0;
u64 supported_xss;
u64 supported_perf_cap;
+ u64 inapplicable_quirks;
};
struct kvm_host_values {
@@ -354,11 +355,6 @@ static inline void kvm_register_write(struct kvm_vcpu *vcpu,
return kvm_register_write_raw(vcpu, reg, val);
}
-static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
-{
- return !(kvm->arch.disabled_quirks & quirk);
-}
-
void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
u64 get_kvmclock_ns(struct kvm *kvm);
@@ -394,6 +390,12 @@ extern struct kvm_host_values kvm_host;
extern bool enable_pmu;
+static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
+{
+ u64 disabled_quirks = kvm_caps.inapplicable_quirks | kvm->arch.disabled_quirks;
+ return !(disabled_quirks & quirk);
+}
+
/*
* Get a filtered version of KVM's supported XCR0 that strips out dynamic
* features for which the current process doesn't (yet) have permission to use.
--
2.43.5On Sat, Mar 01, 2025 at 02:34:25AM -0500, Paolo Bonzini wrote:
> In some cases, the handling of quirks is split between platform-specific
> code and generic code, or it is done entirely in generic code, but the
> relevant bug does not trigger on some platforms; for example,
> KVM_X86_QUIRK_CD_NW_CLEARED is only applicable to AMD systems. In that
> case, allow unaffected vendor modules to disable handling of the quirk.
>
> The quirk remains available in KVM_CAP_DISABLE_QUIRKS2, because that API
> tells userspace that KVM *knows* that some of its past behavior was bogus
> or just undesirable. In other words, it's plausible for userspace to
> refuse to run if a quirk is not listed by KVM_CAP_DISABLE_QUIRKS2.
>
> In kvm_check_has_quirk(), in addition to checking if a quirk is not
> explicitly disabled by the user, also verify if the quirk applies to
> the hardware.
>
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
> Message-ID: <20250224070832.31394-1-yan.y.zhao@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
> arch/x86/kvm/vmx/vmx.c | 1 +
> arch/x86/kvm/x86.c | 1 +
> arch/x86/kvm/x86.h | 12 +++++++-----
> 3 files changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 486fbdb4365c..75df4caea2f7 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -8506,6 +8506,7 @@ __init int vmx_hardware_setup(void)
>
> kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
>
> + kvm_caps.inapplicable_quirks = KVM_X86_QUIRK_CD_NW_CLEARED;
As you mentioned, KVM_X86_QUIRK_CD_NW_CLEARED has no effect on Intel's
platforms, no matter kvm_check_has_quirk() returns true or false.
So, what's the purpose to introduce kvm_caps.inapplicable_quirks?
One concern is that since KVM_X86_QUIRK_CD_NW_CLEARED is not for Intel
platforms, it's unnatural for Intel's code to add it into the
kvm_caps.inapplicable_quirks.
If AMD introduces new quirks that apply only to its own platform in future,
they may have no idea whether it's applicable to Intel as well.
> return r;
> }
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 856ceeb4fb35..fd0a44e59314 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -9775,6 +9775,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
> kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
> kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
> }
> + kvm_caps.inapplicable_quirks = 0;
>
> rdmsrl_safe(MSR_EFER, &kvm_host.efer);
>
> diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> index 8ce6da98b5a2..9af199c8e5c8 100644
> --- a/arch/x86/kvm/x86.h
> +++ b/arch/x86/kvm/x86.h
> @@ -34,6 +34,7 @@ struct kvm_caps {
> u64 supported_xcr0;
> u64 supported_xss;
> u64 supported_perf_cap;
> + u64 inapplicable_quirks;
> };
>
> struct kvm_host_values {
> @@ -354,11 +355,6 @@ static inline void kvm_register_write(struct kvm_vcpu *vcpu,
> return kvm_register_write_raw(vcpu, reg, val);
> }
>
> -static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
> -{
> - return !(kvm->arch.disabled_quirks & quirk);
> -}
> -
> void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
>
> u64 get_kvmclock_ns(struct kvm *kvm);
> @@ -394,6 +390,12 @@ extern struct kvm_host_values kvm_host;
>
> extern bool enable_pmu;
>
> +static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
> +{
> + u64 disabled_quirks = kvm_caps.inapplicable_quirks | kvm->arch.disabled_quirks;
> + return !(disabled_quirks & quirk);
> +}
> +
> /*
> * Get a filtered version of KVM's supported XCR0 that strips out dynamic
> * features for which the current process doesn't (yet) have permission to use.
> --
> 2.43.5
>
>
On 3/3/25 02:15, Yan Zhao wrote: > On Sat, Mar 01, 2025 at 02:34:25AM -0500, Paolo Bonzini wrote: >> In some cases, the handling of quirks is split between platform-specific >> code and generic code, or it is done entirely in generic code, but the >> relevant bug does not trigger on some platforms; for example, >> KVM_X86_QUIRK_CD_NW_CLEARED is only applicable to AMD systems. In that >> case, allow unaffected vendor modules to disable handling of the quirk. >> >> The quirk remains available in KVM_CAP_DISABLE_QUIRKS2, because that API >> tells userspace that KVM *knows* that some of its past behavior was bogus >> or just undesirable. In other words, it's plausible for userspace to >> refuse to run if a quirk is not listed by KVM_CAP_DISABLE_QUIRKS2. >> >> In kvm_check_has_quirk(), in addition to checking if a quirk is not >> explicitly disabled by the user, also verify if the quirk applies to >> the hardware. >> >> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com> >> Message-ID: <20250224070832.31394-1-yan.y.zhao@intel.com> >> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> >> --- >> arch/x86/kvm/vmx/vmx.c | 1 + >> arch/x86/kvm/x86.c | 1 + >> arch/x86/kvm/x86.h | 12 +++++++----- >> 3 files changed, 9 insertions(+), 5 deletions(-) >> >> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c >> index 486fbdb4365c..75df4caea2f7 100644 >> --- a/arch/x86/kvm/vmx/vmx.c >> +++ b/arch/x86/kvm/vmx/vmx.c >> @@ -8506,6 +8506,7 @@ __init int vmx_hardware_setup(void) >> >> kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); >> >> + kvm_caps.inapplicable_quirks = KVM_X86_QUIRK_CD_NW_CLEARED; > > As you mentioned, KVM_X86_QUIRK_CD_NW_CLEARED has no effect on Intel's > platforms, no matter kvm_check_has_quirk() returns true or false. > So, what's the purpose to introduce kvm_caps.inapplicable_quirks? The purpose is to later mark IGNORE_GUEST_PAT as inapplicable, so that the relevant code does not run on AMD. However you have a point here: > One concern is that since KVM_X86_QUIRK_CD_NW_CLEARED is not for Intel > platforms, it's unnatural for Intel's code to add it into the > kvm_caps.inapplicable_quirks. So let's instead have kvm-amd.ko clear it from inapplicable_quirks. And likewise kvm-intel.ko can clear IGNORE_GUEST_PAT. Paolo
On Mon, Mar 03, 2025 at 05:04:40PM +0100, Paolo Bonzini wrote: > On 3/3/25 02:15, Yan Zhao wrote: > > On Sat, Mar 01, 2025 at 02:34:25AM -0500, Paolo Bonzini wrote: > > > In some cases, the handling of quirks is split between platform-specific > > > code and generic code, or it is done entirely in generic code, but the > > > relevant bug does not trigger on some platforms; for example, > > > KVM_X86_QUIRK_CD_NW_CLEARED is only applicable to AMD systems. In that > > > case, allow unaffected vendor modules to disable handling of the quirk. > > > > > > The quirk remains available in KVM_CAP_DISABLE_QUIRKS2, because that API > > > tells userspace that KVM *knows* that some of its past behavior was bogus > > > or just undesirable. In other words, it's plausible for userspace to > > > refuse to run if a quirk is not listed by KVM_CAP_DISABLE_QUIRKS2. > > > > > > In kvm_check_has_quirk(), in addition to checking if a quirk is not > > > explicitly disabled by the user, also verify if the quirk applies to > > > the hardware. > > > > > > Signed-off-by: Yan Zhao <yan.y.zhao@intel.com> > > > Message-ID: <20250224070832.31394-1-yan.y.zhao@intel.com> > > > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > > > --- > > > arch/x86/kvm/vmx/vmx.c | 1 + > > > arch/x86/kvm/x86.c | 1 + > > > arch/x86/kvm/x86.h | 12 +++++++----- > > > 3 files changed, 9 insertions(+), 5 deletions(-) > > > > > > diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c > > > index 486fbdb4365c..75df4caea2f7 100644 > > > --- a/arch/x86/kvm/vmx/vmx.c > > > +++ b/arch/x86/kvm/vmx/vmx.c > > > @@ -8506,6 +8506,7 @@ __init int vmx_hardware_setup(void) > > > kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); > > > + kvm_caps.inapplicable_quirks = KVM_X86_QUIRK_CD_NW_CLEARED; > > > > As you mentioned, KVM_X86_QUIRK_CD_NW_CLEARED has no effect on Intel's > > platforms, no matter kvm_check_has_quirk() returns true or false. > > So, what's the purpose to introduce kvm_caps.inapplicable_quirks? > > The purpose is to later mark IGNORE_GUEST_PAT as inapplicable, so that the > relevant code does not run on AMD. However you have a point here: Or naming it kvm_caps.platform_disabled_quirks? > > > One concern is that since KVM_X86_QUIRK_CD_NW_CLEARED is not for Intel > > platforms, it's unnatural for Intel's code to add it into the > > kvm_caps.inapplicable_quirks. > > So let's instead have kvm-amd.ko clear it from inapplicable_quirks. And > likewise kvm-intel.ko can clear IGNORE_GUEST_PAT. Sounds good.
On 3/1/2025 3:34 PM, Paolo Bonzini wrote:
> In some cases, the handling of quirks is split between platform-specific
> code and generic code, or it is done entirely in generic code, but the
> relevant bug does not trigger on some platforms; for example,
> KVM_X86_QUIRK_CD_NW_CLEARED is only applicable to AMD systems. In that
> case, allow unaffected vendor modules to disable handling of the quirk.
>
> The quirk remains available in KVM_CAP_DISABLE_QUIRKS2, because that API
> tells userspace that KVM *knows* that some of its past behavior was bogus
> or just undesirable. In other words, it's plausible for userspace to
> refuse to run if a quirk is not listed by KVM_CAP_DISABLE_QUIRKS2.
I think it's just for existing quirks for backwards compatibilities
reason. For new quirk bit that is vendor specific,
KVM_CAP_DISABLE_QUIRKS2 is OK to enumerate different value.
> In kvm_check_has_quirk(), in addition to checking if a quirk is not
> explicitly disabled by the user, also verify if the quirk applies to
> the hardware.
>
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
This is inconsistent with the Author.
> Message-ID: <20250224070832.31394-1-yan.y.zhao@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
> arch/x86/kvm/vmx/vmx.c | 1 +
> arch/x86/kvm/x86.c | 1 +
> arch/x86/kvm/x86.h | 12 +++++++-----
> 3 files changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 486fbdb4365c..75df4caea2f7 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -8506,6 +8506,7 @@ __init int vmx_hardware_setup(void)
>
> kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
>
> + kvm_caps.inapplicable_quirks = KVM_X86_QUIRK_CD_NW_CLEARED;
Suggest to make inapplicable_quirks per VM, as I comments in patch 4:
https://lore.kernel.org/all/338901b6-4d10-480d-bd0a-0db8ec4afad5@intel.com/https://lore.kernel.org/all/338901b6-4d10-480d-bd0a-0db8ec4afad5@intel.com/
> return r;
> }
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 856ceeb4fb35..fd0a44e59314 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -9775,6 +9775,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
> kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
> kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
> }
> + kvm_caps.inapplicable_quirks = 0;
>
> rdmsrl_safe(MSR_EFER, &kvm_host.efer);
>
> diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> index 8ce6da98b5a2..9af199c8e5c8 100644
> --- a/arch/x86/kvm/x86.h
> +++ b/arch/x86/kvm/x86.h
> @@ -34,6 +34,7 @@ struct kvm_caps {
> u64 supported_xcr0;
> u64 supported_xss;
> u64 supported_perf_cap;
> + u64 inapplicable_quirks;
> };
>
> struct kvm_host_values {
> @@ -354,11 +355,6 @@ static inline void kvm_register_write(struct kvm_vcpu *vcpu,
> return kvm_register_write_raw(vcpu, reg, val);
> }
>
> -static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
> -{
> - return !(kvm->arch.disabled_quirks & quirk);
> -}
> -
> void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
>
> u64 get_kvmclock_ns(struct kvm *kvm);
> @@ -394,6 +390,12 @@ extern struct kvm_host_values kvm_host;
>
> extern bool enable_pmu;
>
> +static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
> +{
> + u64 disabled_quirks = kvm_caps.inapplicable_quirks | kvm->arch.disabled_quirks;
> + return !(disabled_quirks & quirk);
> +}
> +
> /*
> * Get a filtered version of KVM's supported XCR0 that strips out dynamic
> * features for which the current process doesn't (yet) have permission to use.
© 2016 - 2026 Red Hat, Inc.