Re: [PATCH 2/9] KVM: arm64: Add a range to __pkvm_host_share_guest()

[Quentin Perret <qperret@google.com>]

On Friday 28 Feb 2025 at 10:25:18 (+0000), Vincent Donnefort wrote:
> +int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
>  			    enum kvm_pgtable_prot prot)
>  {
>  	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
>  	u64 phys = hyp_pfn_to_phys(pfn);
>  	u64 ipa = hyp_pfn_to_phys(gfn);
>  	struct hyp_page *page;
> +	u64 size;
>  	int ret;
>  
>  	if (prot & ~KVM_PGTABLE_PROT_RWX)
>  		return -EINVAL;
>  
> -	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);

I'm not sure it is safe to drop this check here, see below.

> +	ret = __guest_check_transition_size(phys, ipa, nr_pages, &size);
>  	if (ret)
>  		return ret;
>  
>  	host_lock_component();
>  	guest_lock_component(vm);
>  
> -	ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE);
> +	ret = __guest_check_page_state_range(vm, ipa, size, PKVM_NOPAGE);
>  	if (ret)
>  		goto unlock;
>  
>  	page = hyp_phys_to_page(phys);

Phys really needs to be a valid memory address here for 'page' to be
present in the vmemma -- dereference right below. So we can't rely on
the check in __host_check_page_state_range() sadly ...

> +	ret = __host_check_page_state_range(phys, size, page->host_state);
> +	if (ret)
> +		goto unlock;
> +
>  	switch (page->host_state) {
>  	case PKVM_PAGE_OWNED:
> -		WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED));
> +		WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED));
>  		break;
>  	case PKVM_PAGE_SHARED_OWNED:
> -		if (page->host_share_guest_count)
> -			break;
> -		/* Only host to np-guest multi-sharing is tolerated */
> -		WARN_ON(1);
> -		fallthrough;
> +		for_each_hyp_page(phys, size, page) {
> +			/* Only host to np-guest multi-sharing is tolerated */
> +			if (WARN_ON(!page->host_share_guest_count)) {
> +				ret = -EPERM;
> +				goto unlock;
> +			}
> +		}
> +		break;
>  	default:
>  		ret = -EPERM;
>  		goto unlock;
>  	}
>  
> -	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
> +	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, size, phys,
>  				       pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED),
>  				       &vcpu->vcpu.arch.pkvm_memcache, 0));
> -	page->host_share_guest_count++;
> +	__host_update_share_guest_count(phys, size, true);
>  
>  unlock:
>  	guest_unlock_component(vm);
> diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
> index 930b677eb9b0..00fd9a524bf7 100644
> --- a/arch/arm64/kvm/pkvm.c
> +++ b/arch/arm64/kvm/pkvm.c
> @@ -361,7 +361,7 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  		return -EINVAL;
>  
>  	lockdep_assert_held_write(&kvm->mmu_lock);
> -	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot);
> +	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, 1, prot);
>  	if (ret) {
>  		/* Is the gfn already mapped due to a racing vCPU? */
>  		if (ret == -EPERM)
> -- 
> 2.48.1.711.g2feabab25a-goog
>