Re: [RFC PATCH v2 07/18] KVM: TDX: Fold tdx_sept_drop_private_spte() into tdx_sept_remove_private_spte()

[Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx>]

On 8/29/2025 8:06 AM, Sean Christopherson wrote:
> Fold tdx_sept_drop_private_spte() into tdx_sept_remove_private_spte() to
> avoid having to differnatiate between "zap", "drop", and "remove", and to
> eliminate dead code due to redundant checks, e.g. on an HKID being
> assigned.
>
> No functional change intended.
>
> Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>

Reviewed-by: Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx>

> ---
>   arch/x86/kvm/vmx/tdx.c | 90 +++++++++++++++++++-----------------------
>   1 file changed, 40 insertions(+), 50 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index 50a9d81dad53..8cb6a2627eb2 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -1651,55 +1651,6 @@ static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
>   	return tdx_mem_page_record_premap_cnt(kvm, gfn, level, pfn);
>   }
>   
> -static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
> -				      enum pg_level level, struct page *page)
> -{
> -	int tdx_level = pg_level_to_tdx_sept_level(level);
> -	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
> -	gpa_t gpa = gfn_to_gpa(gfn);
> -	u64 err, entry, level_state;
> -
> -	/* TODO: handle large pages. */
> -	if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
> -		return -EIO;
> -
> -	if (KVM_BUG_ON(!is_hkid_assigned(kvm_tdx), kvm))
> -		return -EIO;
> -
> -	/*
> -	 * When zapping private page, write lock is held. So no race condition
> -	 * with other vcpu sept operation.
> -	 * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs.
> -	 */
> -	err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
> -				  &level_state);
> -
> -	if (unlikely(tdx_operand_busy(err))) {
> -		/*
> -		 * The second retry is expected to succeed after kicking off all
> -		 * other vCPUs and prevent them from invoking TDH.VP.ENTER.
> -		 */
> -		tdx_no_vcpus_enter_start(kvm);
> -		err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
> -					  &level_state);
> -		tdx_no_vcpus_enter_stop(kvm);
> -	}
> -
> -	if (KVM_BUG_ON(err, kvm)) {
> -		pr_tdx_error_2(TDH_MEM_PAGE_REMOVE, err, entry, level_state);
> -		return -EIO;
> -	}
> -
> -	err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page);
> -
> -	if (KVM_BUG_ON(err, kvm)) {
> -		pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
> -		return -EIO;
> -	}
> -	tdx_clear_page(page);
> -	return 0;
> -}
> -
>   static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
>   				     enum pg_level level, void *private_spt)
>   {
> @@ -1861,7 +1812,11 @@ static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
>   static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
>   					enum pg_level level, kvm_pfn_t pfn)
>   {
> +	int tdx_level = pg_level_to_tdx_sept_level(level);
> +	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
>   	struct page *page = pfn_to_page(pfn);
> +	gpa_t gpa = gfn_to_gpa(gfn);
> +	u64 err, entry, level_state;
>   	int ret;
>   
>   	/*
> @@ -1872,6 +1827,10 @@ static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
>   	if (KVM_BUG_ON(!is_hkid_assigned(to_kvm_tdx(kvm)), kvm))
>   		return -EIO;
>   
> +	/* TODO: handle large pages. */
> +	if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
> +		return -EIO;
> +
>   	ret = tdx_sept_zap_private_spte(kvm, gfn, level, page);
>   	if (ret <= 0)
>   		return ret;
> @@ -1882,7 +1841,38 @@ static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
>   	 */
>   	tdx_track(kvm);
>   
> -	return tdx_sept_drop_private_spte(kvm, gfn, level, page);
> +	/*
> +	 * When zapping private page, write lock is held. So no race condition
> +	 * with other vcpu sept operation.
> +	 * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs.
> +	 */
> +	err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
> +				  &level_state);
> +
> +	if (unlikely(tdx_operand_busy(err))) {
> +		/*
> +		 * The second retry is expected to succeed after kicking off all
> +		 * other vCPUs and prevent them from invoking TDH.VP.ENTER.
> +		 */
> +		tdx_no_vcpus_enter_start(kvm);
> +		err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
> +					  &level_state);
> +		tdx_no_vcpus_enter_stop(kvm);
> +	}
> +
> +	if (KVM_BUG_ON(err, kvm)) {
> +		pr_tdx_error_2(TDH_MEM_PAGE_REMOVE, err, entry, level_state);
> +		return -EIO;
> +	}
> +
> +	err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page);
> +	if (KVM_BUG_ON(err, kvm)) {
> +		pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
> +		return -EIO;
> +	}
> +
> +	tdx_clear_page(page);
> +	return 0;
>   }
>   
>   void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,