In prepare_vmcs02_rare, call vmx_segment_cache_clear, instead
of setting the segment_cache.bitmask directly.

No functional change intended.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 5 +++--
 arch/x86/kvm/vmx/vmx.c    | 4 ----
 arch/x86/kvm/vmx/vmx.h    | 5 +++++
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 643935a0f70ab..d3ca1a772ae67 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2469,6 +2469,9 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
 			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+
+		vmx_segment_cache_clear(vmx);
+
 		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
 		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
@@ -2505,8 +2508,6 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
 		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
-
-		vmx->segment_cache.bitmask = 0;
 	}
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b3c83c06f8265..fa9f307d9b18b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -524,10 +524,6 @@ static const struct kvm_vmx_segment_field {
 	VMX_SEGMENT_FIELD(LDTR),
 };
 
-static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
-{
-	vmx->segment_cache.bitmask = 0;
-}
 
 static unsigned long host_idt_base;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 7b64e271a9319..1689f0d59f435 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -755,4 +755,9 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
 	return  lapic_in_kernel(vcpu) && enable_ipiv;
 }
 
+static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
+{
+	vmx->segment_cache.bitmask = 0;
+}
+
 #endif /* __KVM_X86_VMX_H */
-- 
2.26.3

On Mon, Jul 15, 2024, Maxim Levitsky wrote:
> In prepare_vmcs02_rare, call vmx_segment_cache_clear, instead
> of setting the segment_cache.bitmask directly.
> 
> No functional change intended.
> 
> Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
> ---
>  arch/x86/kvm/vmx/nested.c | 5 +++--
>  arch/x86/kvm/vmx/vmx.c    | 4 ----
>  arch/x86/kvm/vmx/vmx.h    | 5 +++++
>  3 files changed, 8 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index 643935a0f70ab..d3ca1a772ae67 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -2469,6 +2469,9 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
>  
>  	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
>  			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
> +
> +		vmx_segment_cache_clear(vmx);
> +
>  		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
>  		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
>  		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
> @@ -2505,8 +2508,6 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
>  		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
>  		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
>  		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
> -
> -		vmx->segment_cache.bitmask = 0;

This actually exacerbates the bug that you're trying fix in patch 2.  Clearing
segment_cache.bitmask _after_ writing the relevant state limits the stale data
to only the accessor that's running in IRQ context (kvm_arch_vcpu_put()).

Clearing segment_cache.bitmask _before_ writing the relevant statement means
that kvm_arch_vcpu_put() _and_ all future readers will be exposed to the stale
data, because the stale data cached by kvm_arch_vcpu_put() won't mark it invalid.

On Tue, 2024-07-16 at 14:07 -0700, Sean Christopherson wrote:
> On Mon, Jul 15, 2024, Maxim Levitsky wrote:
> > In prepare_vmcs02_rare, call vmx_segment_cache_clear, instead
> > of setting the segment_cache.bitmask directly.
> > 
> > No functional change intended.
> > 
> > Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
> > ---
> >  arch/x86/kvm/vmx/nested.c | 5 +++--
> >  arch/x86/kvm/vmx/vmx.c    | 4 ----
> >  arch/x86/kvm/vmx/vmx.h    | 5 +++++
> >  3 files changed, 8 insertions(+), 6 deletions(-)
> > 
> > diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> > index 643935a0f70ab..d3ca1a772ae67 100644
> > --- a/arch/x86/kvm/vmx/nested.c
> > +++ b/arch/x86/kvm/vmx/nested.c
> > @@ -2469,6 +2469,9 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
> >  
> >  	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
> >  			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
> > +
> > +		vmx_segment_cache_clear(vmx);
> > +
> >  		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
> >  		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
> >  		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
> > @@ -2505,8 +2508,6 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
> >  		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
> >  		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
> >  		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
> > -
> > -		vmx->segment_cache.bitmask = 0;
> 
> This actually exacerbates the bug that you're trying fix in patch 2.  Clearing
> segment_cache.bitmask _after_ writing the relevant state limits the stale data
> to only the accessor that's running in IRQ context (kvm_arch_vcpu_put()).
> 
> Clearing segment_cache.bitmask _before_ writing the relevant statement means
> that kvm_arch_vcpu_put() _and_ all future readers will be exposed to the stale
> data, because the stale data cached by kvm_arch_vcpu_put() won't mark it invalid.
> 
I noticed that after I sent the patch series, this makes sense.

Best regards,
	Maxim Levitsky