Re: [PATCH v19 016/130] KVM: x86/mmu: Introduce kvm_mmu_map_tdp_page() for use by TDX

[Binbin Wu]

On 2/26/2024 4:25 PM, isaku.yamahata@xxxxxxxxx wrote:
> From: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
>
> Introduce a helper to directly (pun intended) fault-in a TDP page
> without having to go through the full page fault path.  This allows
> TDX to get the resulting pfn and also allows the RET_PF_* enums to
> stay in mmu.c where they belong.
>
> Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> ---
> v19:
> - Move up for KVM_MEMORY_MAPPING.
> - Add goal_level for the caller to know how many pages are mapped.
>
> v14 -> v15:
> - Remove loop in kvm_mmu_map_tdp_page() and return error code based on
>    RET_FP_xxx value to avoid potential infinite loop.  The caller should
>    loop on -EAGAIN instead now.
>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> ---
>   arch/x86/kvm/mmu.h     |  3 +++
>   arch/x86/kvm/mmu/mmu.c | 58 ++++++++++++++++++++++++++++++++++++++++++
>   2 files changed, 61 insertions(+)
>
> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
> index 60f21bb4c27b..d96c93a25b3b 100644
> --- a/arch/x86/kvm/mmu.h
> +++ b/arch/x86/kvm/mmu.h
> @@ -183,6 +183,9 @@ static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu,
>   	__kvm_mmu_refresh_passthrough_bits(vcpu, mmu);
>   }
>   
> +int kvm_mmu_map_tdp_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
> +			 u8 max_level, u8 *goal_level);
> +
>   /*
>    * Check if a given access (described through the I/D, W/R and U/S bits of a
>    * page fault error code pfec) causes a permission fault with the given PTE
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 61674d6b17aa..ca0c91f14063 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -4615,6 +4615,64 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>   	return direct_page_fault(vcpu, fault);
>   }
>   
> +int kvm_mmu_map_tdp_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
> +			 u8 max_level, u8 *goal_level)
> +{
> +	int r;
> +	struct kvm_page_fault fault = (struct kvm_page_fault) {
> +		.addr = gpa,
> +		.error_code = error_code,
> +		.exec = error_code & PFERR_FETCH_MASK,
> +		.write = error_code & PFERR_WRITE_MASK,
> +		.present = error_code & PFERR_PRESENT_MASK,
> +		.rsvd = error_code & PFERR_RSVD_MASK,
> +		.user = error_code & PFERR_USER_MASK,
> +		.prefetch = false,
> +		.is_tdp = true,
> +		.is_private = error_code & PFERR_GUEST_ENC_MASK,
> +		.nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(vcpu->kvm),
> +	};
> +
> +	WARN_ON_ONCE(!vcpu->arch.mmu->root_role.direct);
> +	fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn);
> +
> +	r = mmu_topup_memory_caches(vcpu, false);

Does it need a cache topup here?
Both kvm_tdp_mmu_page_fault() and direct_page_fault() will call
mmu_topup_memory_caches() when needed.

> +	if (r)
> +		return r;
> +
> +	fault.max_level = max_level;
> +	fault.req_level = PG_LEVEL_4K;
> +	fault.goal_level = PG_LEVEL_4K;
> +
> +#ifdef CONFIG_X86_64
> +	if (tdp_mmu_enabled)
> +		r = kvm_tdp_mmu_page_fault(vcpu, &fault);
> +	else
> +#endif
> +		r = direct_page_fault(vcpu, &fault);
> +
> +	if (is_error_noslot_pfn(fault.pfn) || vcpu->kvm->vm_bugged)
> +		return -EFAULT;
> +
> +	switch (r) {
> +	case RET_PF_RETRY:
> +		return -EAGAIN;
> +
> +	case RET_PF_FIXED:
> +	case RET_PF_SPURIOUS:
> +		if (goal_level)
> +			*goal_level = fault.goal_level;
> +		return 0;
> +
> +	case RET_PF_CONTINUE:
> +	case RET_PF_EMULATE:
> +	case RET_PF_INVALID:
> +	default:
> +		return -EIO;
> +	}
> +}
> +EXPORT_SYMBOL_GPL(kvm_mmu_map_tdp_page);
> +
>   static void nonpaging_init_context(struct kvm_mmu *context)
>   {
>   	context->page_fault = nonpaging_page_fault;