Re: [PATCH v2 03/30] KVM: arm64: Extract PFN resolution in user_mem_abort()

[Anshuman Khandual <anshuman.khandual@arm.com>]

On 27/03/26 5:05 PM, Marc Zyngier wrote:
> From: Fuad Tabba <tabba@google.com>
> 
> Extract the section of code responsible for pinning the physical page
> frame number (PFN) backing the faulting IPA into a new helper,
> kvm_s2_fault_pin_pfn().
> 
> This helper encapsulates the critical section where the mmap_read_lock
> is held, the VMA is looked up, the mmu invalidate sequence is sampled,
> and the PFN is ultimately resolved via __kvm_faultin_pfn(). It also
> handles the early exits for hardware poisoned pages and noslot PFNs.
> 
> By isolating this region, we can begin to organize the state variables
> required for PFN resolution into the kvm_s2_fault struct, clearing out
> a significant amount of local variable clutter from user_mem_abort().
> 
> Signed-off-by: Fuad Tabba <tabba@google.com>
> Signed-off-by: Marc Zyngier <maz@kernel.org>

Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>

> ---
>  arch/arm64/kvm/mmu.c | 105 ++++++++++++++++++++++++-------------------
>  1 file changed, 59 insertions(+), 46 deletions(-)
> 
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index b366bde15a429..5079a58b65b14 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -1740,55 +1740,11 @@ struct kvm_s2_fault {
>  	vm_flags_t vm_flags;
>  };
>  
> -static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> -			  struct kvm_s2_trans *nested,
> -			  struct kvm_memory_slot *memslot, unsigned long hva,
> -			  bool fault_is_perm)
> +static int kvm_s2_fault_pin_pfn(struct kvm_s2_fault *fault)
>  {
> -	int ret = 0;
> -	struct kvm_s2_fault fault_data = {
> -		.vcpu = vcpu,
> -		.fault_ipa = fault_ipa,
> -		.nested = nested,
> -		.memslot = memslot,
> -		.hva = hva,
> -		.fault_is_perm = fault_is_perm,
> -		.ipa = fault_ipa,
> -		.logging_active = memslot_is_logging(memslot),
> -		.force_pte = memslot_is_logging(memslot),
> -		.s2_force_noncacheable = false,
> -		.vfio_allow_any_uc = false,
> -		.prot = KVM_PGTABLE_PROT_R,
> -	};
> -	struct kvm_s2_fault *fault = &fault_data;
> -	struct kvm *kvm = vcpu->kvm;
>  	struct vm_area_struct *vma;
> -	void *memcache;
> -	struct kvm_pgtable *pgt;
> -	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
> -
> -	if (fault->fault_is_perm)
> -		fault->fault_granule = kvm_vcpu_trap_get_perm_fault_granule(fault->vcpu);
> -	fault->write_fault = kvm_is_write_fault(fault->vcpu);
> -	fault->exec_fault = kvm_vcpu_trap_is_exec_fault(fault->vcpu);
> -	VM_WARN_ON_ONCE(fault->write_fault && fault->exec_fault);
> +	struct kvm *kvm = fault->vcpu->kvm;
>  
> -	/*
> -	 * Permission faults just need to update the existing leaf entry,
> -	 * and so normally don't require allocations from the memcache. The
> -	 * only exception to this is when dirty logging is enabled at runtime
> -	 * and a write fault needs to collapse a block entry into a table.
> -	 */
> -	fault->topup_memcache = !fault->fault_is_perm ||
> -				(fault->logging_active && fault->write_fault);
> -	ret = prepare_mmu_memcache(fault->vcpu, fault->topup_memcache, &memcache);
> -	if (ret)
> -		return ret;
> -
> -	/*
> -	 * Let's check if we will get back a huge page backed by hugetlbfs, or
> -	 * get block mapping for device MMIO region.
> -	 */
>  	mmap_read_lock(current->mm);
>  	vma = vma_lookup(current->mm, fault->hva);
>  	if (unlikely(!vma)) {
> @@ -1842,6 +1798,63 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>  	if (is_error_noslot_pfn(fault->pfn))
>  		return -EFAULT;
>  
> +	return 1;
> +}
> +
> +static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> +			  struct kvm_s2_trans *nested,
> +			  struct kvm_memory_slot *memslot, unsigned long hva,
> +			  bool fault_is_perm)
> +{
> +	int ret = 0;
> +	struct kvm_s2_fault fault_data = {
> +		.vcpu = vcpu,
> +		.fault_ipa = fault_ipa,
> +		.nested = nested,
> +		.memslot = memslot,
> +		.hva = hva,
> +		.fault_is_perm = fault_is_perm,
> +		.ipa = fault_ipa,
> +		.logging_active = memslot_is_logging(memslot),
> +		.force_pte = memslot_is_logging(memslot),
> +		.s2_force_noncacheable = false,
> +		.vfio_allow_any_uc = false,
> +		.prot = KVM_PGTABLE_PROT_R,
> +	};
> +	struct kvm_s2_fault *fault = &fault_data;
> +	struct kvm *kvm = vcpu->kvm;
> +	void *memcache;
> +	struct kvm_pgtable *pgt;
> +	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
> +
> +	if (fault->fault_is_perm)
> +		fault->fault_granule = kvm_vcpu_trap_get_perm_fault_granule(fault->vcpu);
> +	fault->write_fault = kvm_is_write_fault(fault->vcpu);
> +	fault->exec_fault = kvm_vcpu_trap_is_exec_fault(fault->vcpu);
> +	VM_WARN_ON_ONCE(fault->write_fault && fault->exec_fault);
> +
> +	/*
> +	 * Permission faults just need to update the existing leaf entry,
> +	 * and so normally don't require allocations from the memcache. The
> +	 * only exception to this is when dirty logging is enabled at runtime
> +	 * and a write fault needs to collapse a block entry into a table.
> +	 */
> +	fault->topup_memcache = !fault->fault_is_perm ||
> +				(fault->logging_active && fault->write_fault);
> +	ret = prepare_mmu_memcache(fault->vcpu, fault->topup_memcache, &memcache);
> +	if (ret)
> +		return ret;
> +
> +	/*
> +	 * Let's check if we will get back a huge page backed by hugetlbfs, or
> +	 * get block mapping for device MMIO region.
> +	 */
> +	ret = kvm_s2_fault_pin_pfn(fault);
> +	if (ret != 1)
> +		return ret;
> +
> +	ret = 0;
> +
>  	/*
>  	 * Check if this is non-struct page memory PFN, and cannot support
>  	 * CMOs. It could potentially be unsafe to access as cacheable.