Re: [PATCH v6 02/25] KVM: arm64: Donate MMIO to the hypervisor

[Vincent Donnefort <vdonnefort@google.com>]

On Fri, May 01, 2026 at 11:19:04AM +0000, Mostafa Saleh wrote:
> Add a function to donate MMIO to the hypervisor so IOMMU hypervisor
> drivers can protect and access the MMIO of IOMMUs.
> 
> As donating MMIO is very rare, and we don’t need to encode the full
> state, it’s reasonable to have a separate function to do this.
> It will init the host s2 page table with an invalid leaf with the owner ID
> to prevent the host from mapping the page on faults.
> 
> Also, prevent kvm_pgtable_stage2_unmap() from removing owner ID from
> stage-2 PTEs, as this can be triggered from recycle logic under memory
> pressure. There is no code relying on this, as all ownership changes is
> done via kvm_pgtable_stage2_set_owner()
> 
> For the error path in IOMMU drivers, add a function to donate MMIO
> back from hyp to host. However, that leaks the hypervisor virtual
> address range which should be acceptable as this is quite rare and
> it matches the behaviour of fix_map/block.
> 
> Signed-off-by: Mostafa Saleh <smostafa@google.com>
> ---
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |   2 +
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 119 +++++++++++++++++-
>  arch/arm64/kvm/hyp/pgtable.c                  |   9 +-
>  3 files changed, 121 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index 3cbfae0e3dda..ff440204d2c7 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -36,6 +36,8 @@ int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn);
>  int __pkvm_guest_unshare_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn);
>  int __pkvm_host_unshare_hyp(u64 pfn);
>  int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
> +int __pkvm_host_donate_hyp_mmio(phys_addr_t addr, size_t size, unsigned long *haddr);
> +int __pkvm_hyp_donate_host_mmio(phys_addr_t addr, size_t size);

Can we have u64 pfn, u64 nr_pages here to match all the other functions?

Also, as this is used by a "module" perhaps a sort of kerneldoc would be nice,
especially to explain this isn't mapped into the hyp idmap range.

>  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);
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 28a471d1927c..2fb20a63a417 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -353,6 +353,38 @@ int __pkvm_prot_finalize(void)
>  	return 0;
>  }
>  
> +/* Unmap MMIO region while skipping donated PTEs. */
> +static int host_stage2_unmap_mmio_region(u64 start, u64 size)
> +{
> +	struct kvm_pgtable *pgt = &host_mmu.pgt;
> +	u64 unmap_start = start;
> +	u64 addr = start;
> +	kvm_pte_t pte;
> +	int ret = 0;
> +	u8 level;
> +
> +	while (addr < start + size) {
> +		ret = kvm_pgtable_get_leaf(pgt, addr, &pte, &level);
> +		if (ret)
> +			return ret;
> +		if (!kvm_pte_valid(pte) && pte != 0) {
> +			if (addr > unmap_start) {
> +				ret = kvm_pgtable_stage2_unmap(pgt, unmap_start,
> +							       addr - unmap_start);
> +				if (ret)
> +					return ret;
> +			}
> +			addr += kvm_granule_size(level);
> +			unmap_start = addr;
> +		} else {
> +			addr += kvm_granule_size(level);
> +		}
> +	}
> +	if (addr > unmap_start)
> +		ret = kvm_pgtable_stage2_unmap(pgt, unmap_start, addr - unmap_start);

Ah shame, that's a lot of table walking. I guess we could:

 * create our own custom walker here but that would duplicate a lot of logic
   from pgtable.c. So doesn't look great.

 * Retry kvm_pgtable_stage2_unmap() as long as it return -EPERM... but then we
   it needs to return where it has stopped?

 * Modify kvm_pgtable_stage2_unmap() to just skip the refcounted entries?
   There's already a flag something that looks like this: KVM_PGTABLE_WALK_IGNORE_EAGAIN

I am not so convinced by the first two points but the last one is probably worth
exploring.
 
> +	return ret;
> +}
> +
>  static int host_stage2_unmap_dev_all(void)
>  {
>  	struct kvm_pgtable *pgt = &host_mmu.pgt;
> @@ -363,11 +395,11 @@ static int host_stage2_unmap_dev_all(void)
>  	/* Unmap all non-memory regions to recycle the pages */
>  	for (i = 0; i < hyp_memblock_nr; i++, addr = reg->base + reg->size) {
>  		reg = &hyp_memory[i];
> -		ret = kvm_pgtable_stage2_unmap(pgt, addr, reg->base - addr);
> +		ret = host_stage2_unmap_mmio_region(addr, reg->base - addr);
>  		if (ret)
>  			return ret;
>  	}
> -	return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr);
> +	return host_stage2_unmap_mmio_region(addr, BIT(pgt->ia_bits) - addr);
>  }
>  
>  /*
> @@ -1087,6 +1119,89 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
>  	return ret;
>  }
>  
> +int __pkvm_host_donate_hyp_mmio(phys_addr_t addr, size_t size, unsigned long *haddr)
> +{
> +	kvm_pte_t pte;
> +	u64 offset;
> +	int ret;
> +
> +	/* Only before de-privilege. */
> +	if (static_branch_unlikely(&kvm_protected_mode_initialized))
> +		return -EPERM;
> +
> +	if (!PAGE_ALIGNED(addr | size))
> +		return -EINVAL;

Would be nice here to have pfn_range_is_valid() even though this is only
used by modules? (ditto __pkvm_hyp_donate_host_mmio())

> +
> +	ret = __pkvm_create_private_mapping(addr, size, PAGE_HYP_DEVICE, haddr);
> +	if (ret)
> +		return ret;

Perhaps better to do it once it's been annotated into the host s2, so that we
don't burn the private range in case of failure.

> +
> +	host_lock_component();
> +	for (offset = 0; offset < size; offset += PAGE_SIZE) {
> +		if (addr_is_memory(addr + offset)) {
> +			ret = -EINVAL;
> +			goto unlock;
> +		}
> +		ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr + offset, &pte, NULL);
> +		if (ret)
> +			goto unlock;
> +		if (pte && !kvm_pte_valid(pte)) {
> +			ret = -EPERM;
> +			goto unlock;
> +		}
> +	}
> +	/*
> +	 * We set HYP as the owner of the MMIO pages in the host stage-2, for:
> +	 * - host aborts: host_stage2_adjust_range() would fail for invalid non zero PTEs.
> +	 * - recycle under memory pressure: host_stage2_unmap_dev_all() would call
> +	 *   kvm_pgtable_stage2_unmap() which will not clear non zero invalid ptes (counted).
> +	 * - other MMIO donation: Would fail as we check that the PTE is valid or empty.
> +	 */
> +	ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt,
> +			      addr, size, &host_s2_pool,
> +			      KVM_HOST_INVALID_PTE_TYPE_DONATION,
> +			      FIELD_PREP(KVM_HOST_DONATION_PTE_OWNER_MASK, PKVM_ID_HYP));
> +unlock:
> +	host_unlock_component();
> +	return ret;
> +}
> +
> +int __pkvm_hyp_donate_host_mmio(phys_addr_t addr, size_t size)
> +{
> +	kvm_pte_t pte;
> +	u64 offset;
> +	int ret = 0;
> +
> +	if (static_branch_unlikely(&kvm_protected_mode_initialized))
> +		return -EPERM;
> +
> +	if (!PAGE_ALIGNED(addr | size))
> +		return -EINVAL;
> +
> +	host_lock_component();
> +	for (offset = 0; offset < size; offset += PAGE_SIZE) {
> +		if (addr_is_memory(addr + offset)) {
> +			ret = -EINVAL;
> +			goto unlock;
> +		}
> +		ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr + offset, &pte, NULL);
> +		if (ret)
> +			goto unlock;
> +		if (!pte || kvm_pte_valid(pte)) {
> +			ret = -EINVAL;
> +			goto unlock;
> +		}

It should probably verify it is also mapped as we expect into the hyp.


> +		if (FIELD_GET(KVM_HOST_DONATION_PTE_OWNER_MASK, pte) != PKVM_ID_HYP) {
> +			ret = -EPERM;
> +			goto unlock;
> +		}
> +	}
> +	WARN_ON(host_stage2_idmap_locked(addr, size, PKVM_HOST_MMIO_PROT));

Perhaps we are better of simply zapping the entry and not map it proactively?

And even if we can't "reclaim" the VA-space from the private range, it would be
good to unmap it. I have made a function for that as part of the allocator
series:

https://lore.kernel.org/all/20260706175415.2604046-3-vdonnefort@google.com/

> +unlock:
> +	host_unlock_component();
> +	return ret;
> +}
> +
>  int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
>  {
>  	u64 phys = hyp_pfn_to_phys(pfn);
> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> index 0c1defa5fb0f..b64a50f9bfa8 100644
> --- a/arch/arm64/kvm/hyp/pgtable.c
> +++ b/arch/arm64/kvm/hyp/pgtable.c
> @@ -1159,13 +1159,8 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
>  	kvm_pte_t *childp = NULL;
>  	bool need_flush = false;
>  
> -	if (!kvm_pte_valid(ctx->old)) {
> -		if (stage2_pte_is_counted(ctx->old)) {
> -			kvm_clear_pte(ctx->ptep);
> -			mm_ops->put_page(ctx->ptep);
> -		}
> -		return 0;
> -	}
> +	if (!kvm_pte_valid(ctx->old))
> +		return stage2_pte_is_counted(ctx->old) ? -EPERM : 0;
>  
>  	if (kvm_pte_table(ctx->old, ctx->level)) {
>  		childp = kvm_pte_follow(ctx->old, mm_ops);
> -- 
> 2.54.0.545.g6539524ca2-goog
>