[PATCH v3 1/3] KVM: arm64: skip pKVM cache flushes for non cacheable mappings

[Vincent Donnefort]

On Wed, Jun 24, 2026 at 04:00:26PM +0000, Bradley Morgan wrote:
> pKVM keeps its own mapping list for stage 2 operations. Its flush path
> uses that list directly, so it lost the PTE attribute check done by the
> generic stage 2 walker.
> 
> Record whether a mapping is cacheable and skip cache maintenance for
> mappings that are not cacheable.
> 
> Fixes: e912efed485a ("KVM: arm64: Introduce the EL1 pKVM MMU")
> Signed-off-by: Bradley Morgan <include at grrlz.net>
> ---
>  arch/arm64/kvm/pkvm.c | 51 ++++++++++++++++++++++++++++++++++---------
>  1 file changed, 41 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
> index 428723b1b0f5..ca6e823028c2 100644
> --- a/arch/arm64/kvm/pkvm.c
> +++ b/arch/arm64/kvm/pkvm.c
> @@ -302,9 +302,32 @@ static u64 __pkvm_mapping_start(struct pkvm_mapping *m)
>  	return m->gfn * PAGE_SIZE;
>  }
>  
> +#define PKVM_MAPPING_NR_PAGES_MASK	GENMASK_ULL(47, 0)
> +#define PKVM_MAPPING_CACHEABLE		BIT_ULL(48)

Probably better to make it "_NC". Protected VMs only support cacheable and they
also use struct pkvm_mapping. 

> +
> +static u64 pkvm_mapping_nr_pages(struct pkvm_mapping *m)
> +{
> +	return m->nr_pages & PKVM_MAPPING_NR_PAGES_MASK;
> +}
> +
> +static bool pkvm_mapping_is_cacheable(struct pkvm_mapping *m)
> +{
> +	return m->nr_pages & PKVM_MAPPING_CACHEABLE;
> +}
> +
> +static void pkvm_mapping_set_nr_pages(struct pkvm_mapping *m, u64 nr_pages,
> +				      bool cacheable)
> +{
> +	WARN_ON_ONCE(nr_pages & ~PKVM_MAPPING_NR_PAGES_MASK);
> +
> +	m->nr_pages = nr_pages & PKVM_MAPPING_NR_PAGES_MASK;
> +	if (cacheable)
> +		m->nr_pages |= PKVM_MAPPING_CACHEABLE;
> +}
> +
>  static u64 __pkvm_mapping_end(struct pkvm_mapping *m)
>  {
> -	return (m->gfn + m->nr_pages) * PAGE_SIZE - 1;
> +	return (m->gfn + pkvm_mapping_nr_pages(m)) * PAGE_SIZE - 1;
>  }

Perhaps using a bitfield would heavily simplify this code?

struct pkvm_mapping {
  ...
  u64 nr_pages : 63
  u64 flags : 1
}

Or alternatively, could just make nr_pages u32 and flags u32. nr_pages will not
exceed PMD_SIZE / PAGE_SIZE, which is at worst 8192 on 64K systems.

>  
>  INTERVAL_TREE_DEFINE(struct pkvm_mapping, node, u64, __subtree_last,
> @@ -350,7 +373,7 @@ static int __pkvm_pgtable_stage2_reclaim(struct kvm_pgtable *pgt, u64 start, u64
>  			continue;
>  
>  		page = pfn_to_page(mapping->pfn);
> -		WARN_ON_ONCE(mapping->nr_pages != 1);
> +		WARN_ON_ONCE(pkvm_mapping_nr_pages(mapping) != 1);
>  		unpin_user_pages_dirty_lock(&page, 1, true);
>  		account_locked_vm(kvm->mm, 1, false);
>  		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
> @@ -369,7 +392,7 @@ static int __pkvm_pgtable_stage2_unshare(struct kvm_pgtable *pgt, u64 start, u64
>  
>  	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
>  		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
> -					mapping->nr_pages);
> +					pkvm_mapping_nr_pages(mapping));
>  		if (WARN_ON(ret))
>  			return ret;
>  		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
> @@ -448,7 +471,7 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  		 * permission faults are handled in the relax_perms() path.
>  		 */
>  		if (mapping) {
> -			if (size == (mapping->nr_pages * PAGE_SIZE))
> +			if (size == (pkvm_mapping_nr_pages(mapping) * PAGE_SIZE))
>  				return -EAGAIN;
>  
>  			/*
> @@ -472,7 +495,9 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  	swap(mapping, cache->mapping);
>  	mapping->gfn = gfn;
>  	mapping->pfn = pfn;
> -	mapping->nr_pages = size / PAGE_SIZE;
> +	pkvm_mapping_set_nr_pages(mapping, size / PAGE_SIZE,
> +				  !(prot & (KVM_PGTABLE_PROT_DEVICE |
> +					    KVM_PGTABLE_PROT_NORMAL_NC)));
>  	pkvm_mapping_insert(mapping, &pgt->pkvm_mappings);
>  
>  	return ret;
> @@ -503,7 +528,7 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
>  	lockdep_assert_held(&kvm->mmu_lock);
>  	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
>  		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,
> -					mapping->nr_pages);
> +					pkvm_mapping_nr_pages(mapping));
>  		if (WARN_ON(ret))
>  			break;
>  	}
> @@ -517,9 +542,13 @@ int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
>  	struct pkvm_mapping *mapping;
>  
>  	lockdep_assert_held(&kvm->mmu_lock);
> -	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
> +	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
> +		if (!pkvm_mapping_is_cacheable(mapping))
> +			continue;
> +
>  		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
> -					  PAGE_SIZE * mapping->nr_pages);
> +					  PAGE_SIZE * pkvm_mapping_nr_pages(mapping));
> +	}
>  
>  	return 0;
>  }
> @@ -536,8 +565,10 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
>  
>  	lockdep_assert_held(&kvm->mmu_lock);
>  	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
> -		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
> -					   mapping->nr_pages, mkold);
> +		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest,
> +					   handle, mapping->gfn,
> +					   pkvm_mapping_nr_pages(mapping),
> +					   mkold);
>  
>  	return young;
>  }
> -- 
> 2.53.0
>