Re: [PATCH v8 7/8] KVM: Handle page fault for private memory

[Chao Peng <chao.p.peng@linux.intel.com>]

On Fri, Oct 14, 2022 at 06:57:20PM +0000, Sean Christopherson wrote:
> On Thu, Sep 15, 2022, Chao Peng wrote:
> > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > index a0f198cede3d..81ab20003824 100644
> > --- a/arch/x86/kvm/mmu/mmu.c
> > +++ b/arch/x86/kvm/mmu/mmu.c
> > @@ -3028,6 +3028,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
> >  			break;
> >  	}
> >  
> > +	if (kvm_mem_is_private(kvm, gfn))
> 
> Rather than reload the Xarray info, which is unnecessary overhead, pass in
> @is_private.  The caller must hold mmu_lock, i.e. invalidations from
> private<->shared conversions will be stalled and will zap the new SPTE if the
> state is changed.

Make sense. TDX/SEV should be easy to query that.

Chao
> 
> E.g.
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index d68944f07b4b..44eea47697d8 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3072,8 +3072,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>          * Enforce the iTLB multihit workaround after capturing the requested
>          * level, which will be used to do precise, accurate accounting.
>          */
> -       fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> -                                                    fault->gfn, fault->max_level);
> +       fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, fault->gfn,
> +                                                    fault->max_level, fault->is_private);
>         if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
>                 return;
>  
> @@ -6460,7 +6460,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
>                  */
>                 if (sp->role.direct &&
>                     sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> -                                                              PG_LEVEL_NUM)) {
> +                                                              PG_LEVEL_NUM, false)) {
>                         kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
>  
>                         if (kvm_available_flush_tlb_with_range())
> diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
> index 7670c13ce251..9acdf72537ce 100644
> --- a/arch/x86/kvm/mmu/spte.h
> +++ b/arch/x86/kvm/mmu/spte.h
> @@ -315,6 +315,12 @@ static inline bool is_dirty_spte(u64 spte)
>         return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
>  }
>  
> +static inline bool is_private_spte(u64 spte)
> +{
> +       /* FIXME: Query C-bit/S-bit for SEV/TDX. */
> +       return false;
> +}
> +
>  static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
>                                 int level)
>  {
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 672f0432d777..69ba00157e90 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -1767,8 +1767,9 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
>                 if (iter.gfn < start || iter.gfn >= end)
>                         continue;
>  
> -               max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
> -                                                             iter.gfn, PG_LEVEL_NUM);
> +               max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot, iter.gfn,
> +                                                             PG_LEVEL_NUM,
> +                                                             is_private_spte(iter.old_spte));
>                 if (max_mapping_level < iter.level)
>                         continue;
>