[v10,071/108] KVM: x86: Allow to update cached values in kvm_user_return_msrs w/o wrmsr

  From: Chao Gao <chao.gao@intel.com>

Several MSRs are constant and only used in userspace(ring 3).  But VMs may
have different values.  KVM uses kvm_set_user_return_msr() to switch to
guest's values and leverages user return notifier to restore them when the
kernel is to return to userspace.  To eliminate unnecessary wrmsr, KVM also
caches the value it wrote to an MSR last time.

TDX module unconditionally resets some of these MSRs to architectural INIT
state on TD exit.  It makes the cached values in kvm_user_return_msrs are
inconsistent with values in hardware.  This inconsistency needs to be
fixed.  Otherwise, it may mislead kvm_on_user_return() to skip restoring
some MSRs to the host's values.  kvm_set_user_return_msr() can help correct
this case, but it is not optimal as it always does a wrmsr.  So, introduce
a variation of kvm_set_user_return_msr() to update cached values and skip
that wrmsr.

Signed-off-by: Chao Gao <chao.gao@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/x86.c              | 26 +++++++++++++++++++++-----
 2 files changed, 22 insertions(+), 5 deletions(-)
  

On 10/30/2022 2:23 PM, isaku.yamahata@intel.com wrote:
> From: Chao Gao <chao.gao@intel.com>
>
> Several MSRs are constant and only used in userspace(ring 3).  But VMs may
> have different values.  KVM uses kvm_set_user_return_msr() to switch to
> guest's values and leverages user return notifier to restore them when the
> kernel is to return to userspace.  To eliminate unnecessary wrmsr, KVM also
> caches the value it wrote to an MSR last time.
>
> TDX module unconditionally resets some of these MSRs to architectural INIT
> state on TD exit.  It makes the cached values in kvm_user_return_msrs are
> inconsistent with values in hardware.  This inconsistency needs to be
> fixed.  Otherwise, it may mislead kvm_on_user_return() to skip restoring
> some MSRs to the host's values.  kvm_set_user_return_msr() can help correct
> this case, but it is not optimal as it always does a wrmsr.  So, introduce
> a variation of kvm_set_user_return_msr() to update cached values and skip
> that wrmsr.
>
> Signed-off-by: Chao Gao <chao.gao@intel.com>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   arch/x86/include/asm/kvm_host.h |  1 +
>   arch/x86/kvm/x86.c              | 26 +++++++++++++++++++++-----
>   2 files changed, 22 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index b225cdfac4bc..fdb00d96e954 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -2082,6 +2082,7 @@ int kvm_add_user_return_msr(u32 msr);
>   int kvm_find_user_return_msr(u32 msr);
>   void kvm_user_return_msr_init_cpu(void);
>   int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
> +void kvm_user_return_update_cache(unsigned int index, u64 val);
>   
>   static inline bool kvm_is_supported_user_return_msr(u32 msr)
>   {
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 65541bfebb37..4d4b71c4cdb1 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -440,6 +440,15 @@ void kvm_user_return_msr_init_cpu(void)
>   }
>   EXPORT_SYMBOL_GPL(kvm_user_return_msr_init_cpu);
>   
> +static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs)
> +{
> +	if (!msrs->registered) {
> +		msrs->urn.on_user_return = kvm_on_user_return;
> +		user_return_notifier_register(&msrs->urn);
> +		msrs->registered = true;
> +	}
> +}
> +
>   int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
>   {
>   	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
> @@ -455,15 +464,22 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
>   		return 1;
>   
>   	msrs->values[slot].curr = value;
> -	if (!msrs->registered) {
> -		msrs->urn.on_user_return = kvm_on_user_return;
> -		user_return_notifier_register(&msrs->urn);
> -		msrs->registered = true;
> -	}
> +	kvm_user_return_register_notifier(msrs);
>   	return 0;
>   }
>   EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
>   
> +/* Update the cache, "curr", and register the notifier */
> +void kvm_user_return_update_cache(unsigned int slot, u64 value)
> +{
> +	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
> +
> +	WARN_ON_ONCE(!msrs->initialized);
> +	msrs->values[slot].curr = value;

If the value is the same as the cached one, can it just skip notifier 
registration?


> +	kvm_user_return_register_notifier(msrs);
> +}
> +EXPORT_SYMBOL_GPL(kvm_user_return_update_cache);
> +
>   static void drop_user_return_notifiers(void)
>   {
>   	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
  

On Mon, Nov 14, 2022 at 03:36:27PM +0800,
Binbin Wu <binbin.wu@linux.intel.com> wrote:

> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> > index 65541bfebb37..4d4b71c4cdb1 100644
> > --- a/arch/x86/kvm/x86.c
> > +++ b/arch/x86/kvm/x86.c
> > @@ -440,6 +440,15 @@ void kvm_user_return_msr_init_cpu(void)
> >   }
> >   EXPORT_SYMBOL_GPL(kvm_user_return_msr_init_cpu);
> > +static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs)
> > +{
> > +	if (!msrs->registered) {
> > +		msrs->urn.on_user_return = kvm_on_user_return;
> > +		user_return_notifier_register(&msrs->urn);
> > +		msrs->registered = true;
> > +	}
> > +}
> > +
> >   int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
> >   {
> >   	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
> > @@ -455,15 +464,22 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
> >   		return 1;
> >   	msrs->values[slot].curr = value;
> > -	if (!msrs->registered) {
> > -		msrs->urn.on_user_return = kvm_on_user_return;
> > -		user_return_notifier_register(&msrs->urn);
> > -		msrs->registered = true;
> > -	}
> > +	kvm_user_return_register_notifier(msrs);
> >   	return 0;
> >   }
> >   EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
> > +/* Update the cache, "curr", and register the notifier */
> > +void kvm_user_return_update_cache(unsigned int slot, u64 value)
> > +{
> > +	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
> > +
> > +	WARN_ON_ONCE(!msrs->initialized);
> > +	msrs->values[slot].curr = value;
> 
> If the value is the same as the cached one, can it just skip notifier
> registration?

We know tha the the user of the function (in the next patch) passes the
different value, the initial reset value in the return of TDH.VP.ENTER.  So
such check isn't added.