Re: [PATCH v3 26/36] KVM: arm64: Return -EFAULT from VCPU_RUN on access to a poisoned pte

[Marc Zyngier <maz@kernel.org>]

On Thu, 05 Mar 2026 14:43:39 +0000,
Will Deacon <will@kernel.org> wrote:
> 
> If a protected vCPU faults on an IPA which appears to be mapped, query
> the hypervisor to determine whether or not the faulting pte has been
> poisoned by a forceful reclaim. If the pte has been poisoned, return
> -EFAULT back to userspace rather than retrying the instruction forever.
> 
> Signed-off-by: Will Deacon <will@kernel.org>
> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 10 +++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 43 +++++++++++++++++++
>  arch/arm64/kvm/pkvm.c                         |  9 ++--
>  5 files changed, 61 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 04a230e906a7..6c79f7504d80 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -90,6 +90,7 @@ enum __kvm_host_smccc_func {
>  	__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
> +	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_in_poison_fault,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_force_reclaim_guest_page,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_reclaim_dying_guest_page,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_start_teardown_vm,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index f27b037abaf3..5e6cdafcdd69 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -41,6 +41,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu);
> +int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu);
>  int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys);
>  int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm);
>  int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 456c83207717..90e3b14fe287 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -573,6 +573,15 @@ static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
>  	cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva);
>  }
>  
> +static void handle___pkvm_vcpu_in_poison_fault(struct kvm_cpu_context *host_ctxt)
> +{
> +	int ret;
> +	struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
> +
> +	ret = hyp_vcpu ? __pkvm_vcpu_in_poison_fault(hyp_vcpu) : -EINVAL;
> +	cpu_reg(host_ctxt, 1) = ret;
> +}
> +
>  static void handle___pkvm_force_reclaim_guest_page(struct kvm_cpu_context *host_ctxt)
>  {
>  	DECLARE_REG(phys_addr_t, phys, host_ctxt, 1);
> @@ -641,6 +650,7 @@ static const hcall_t host_hcall[] = {
>  	HANDLE_FUNC(__pkvm_unreserve_vm),
>  	HANDLE_FUNC(__pkvm_init_vm),
>  	HANDLE_FUNC(__pkvm_init_vcpu),
> +	HANDLE_FUNC(__pkvm_vcpu_in_poison_fault),
>  	HANDLE_FUNC(__pkvm_force_reclaim_guest_page),
>  	HANDLE_FUNC(__pkvm_reclaim_dying_guest_page),
>  	HANDLE_FUNC(__pkvm_start_teardown_vm),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 4ff31947579b..7f705f662c40 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -890,6 +890,49 @@ static int get_valid_guest_pte(struct pkvm_hyp_vm *vm, u64 ipa, kvm_pte_t *ptep,
>  	return 0;
>  }
>  
> +int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu)
> +{
> +	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
> +	kvm_pte_t pte;
> +	s8 level;
> +	u64 ipa;
> +	int ret;
> +
> +	switch (kvm_vcpu_trap_get_class(&hyp_vcpu->vcpu)) {
> +	case ESR_ELx_EC_DABT_LOW:
> +	case ESR_ELx_EC_IABT_LOW:
> +		if (kvm_vcpu_trap_is_translation_fault(&hyp_vcpu->vcpu))
> +			break;
> +		fallthrough;
> +	default:
> +		return -EINVAL;
> +	}
> +
> +	/*
> +	 * The host has the faulting IPA when it calls us from the guest
> +	 * fault handler but we retrieve it ourselves from the FAR so as
> +	 * to avoid exposing an "oracle" that could reveal data access
> +	 * patterns of the guest after initial donation of its pages.
> +	 */
> +	ipa = kvm_vcpu_get_fault_ipa(&hyp_vcpu->vcpu);
> +	ipa |= kvm_vcpu_get_hfar(&hyp_vcpu->vcpu) & GENMASK(11, 0);

nit: we now have FAR_TO_FIPA_OFFSET() for this.

> +
> +	guest_lock_component(vm);
> +	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
> +	if (ret)
> +		goto unlock;
> +
> +	if (level != KVM_PGTABLE_LAST_LEVEL) {
> +		ret = -EINVAL;
> +		goto unlock;
> +	}
> +
> +	ret = guest_pte_is_poisoned(pte);
> +unlock:
> +	guest_unlock_component(vm);
> +	return ret;
> +}
> +
>  int __pkvm_host_share_hyp(u64 pfn)
>  {
>  	u64 phys = hyp_pfn_to_phys(pfn);
> diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
> index 32294bd21dde..da0a45dab203 100644
> --- a/arch/arm64/kvm/pkvm.c
> +++ b/arch/arm64/kvm/pkvm.c
> @@ -417,10 +417,13 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  			return -EINVAL;
>  
>  		/*
> -		 * We raced with another vCPU.
> +		 * We either raced with another vCPU or the guest PTE
> +		 * has been poisoned by an erroneous host access.
>  		 */
> -		if (mapping)
> -			return -EAGAIN;
> +		if (mapping) {
> +			ret = kvm_call_hyp_nvhe(__pkvm_vcpu_in_poison_fault);
> +			return ret ? -EFAULT : -EAGAIN;
> +		}

I guess this considers that racing against another vcpu is an unlikely
situation, because calling back into EL2 and walking the PTs isn't
exactly cheap.

I wonder if there is a mechanism we could use to directly return this
information to the host at the point of the guest fault. The only
things I can figure out would require the PTE to be valid (access or
permission faults, for example), and that'd break the "full PTE
dedicated to annotations"...

	M.

-- 
Without deviation from the norm, progress is not possible.