Re: [PATCH v13 26/48] arm64: RMI: Create the realm descriptor

[Steven Price]

On 19/03/2026 18:25, Wei-Lin Chang wrote:
> On Wed, Mar 18, 2026 at 03:53:50PM +0000, Steven Price wrote:
>> Creating a realm involves first creating a realm descriptor (RD). This
>> involves passing the configuration information to the RMM. Do this as
>> part of realm_ensure_created() so that the realm is created when it is
>> first needed.
>>
>> Signed-off-by: Steven Price <steven.price@xxxxxxx>
>> ---
>> Changes since v12:
>>  * Since RMM page size is now equal to the host's page size various
>>    calculations are simplified.
>>  * Switch to using range based APIs to delegate/undelegate.
>>  * VMID handling is now handled entirely by the RMM.
>> ---
>>  arch/arm64/kvm/rmi.c | 94 +++++++++++++++++++++++++++++++++++++++++++-
>>  1 file changed, 92 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/kvm/rmi.c b/arch/arm64/kvm/rmi.c
>> index 38349c7b34f4..d5fee203824b 100644
>> --- a/arch/arm64/kvm/rmi.c
>> +++ b/arch/arm64/kvm/rmi.c
>> @@ -649,6 +649,83 @@ static void realm_unmap_shared_range(struct kvm *kvm,
>>  			     start, end);
>>  }
>>  
>> +static int realm_create_rd(struct kvm *kvm)
>> +{
>> +	struct realm *realm = &kvm->arch.realm;
>> +	struct realm_params *params = realm->params;
>> +	void *rd = NULL;
>> +	phys_addr_t rd_phys, params_phys;
>> +	size_t pgd_size = kvm_pgtable_stage2_pgd_size(kvm->arch.mmu.vtcr);
>> +	int i, r;
>> +
>> +	realm->ia_bits = VTCR_EL2_IPA(kvm->arch.mmu.vtcr);
>> +
>> +	if (WARN_ON(realm->rd || !realm->params))
>> +		return -EEXIST;
>> +
>> +	rd = (void *)__get_free_page(GFP_KERNEL);
> 
> Hi,
> 
> Should this be GFP_KERNEL_ACCOUNT?

Yes that would be better.

>> +	if (!rd)
>> +		return -ENOMEM;
>> +
>> +	rd_phys = virt_to_phys(rd);
>> +	if (delegate_page(rd_phys)) {
>> +		r = -ENXIO;
>> +		goto free_rd;
>> +	}
>> +
>> +	if (delegate_range(kvm->arch.mmu.pgd_phys, pgd_size)) {
>> +		r = -ENXIO;
>> +		goto out_undelegate_tables;
>> +	}
>> +
>> +	params->s2sz = VTCR_EL2_IPA(kvm->arch.mmu.vtcr);
>> +	params->rtt_level_start = get_start_level(realm);
>> +	params->rtt_num_start = pgd_size / PAGE_SIZE;
>> +	params->rtt_base = kvm->arch.mmu.pgd_phys;
>> +
>> +	if (kvm->arch.arm_pmu) {
>> +		params->pmu_num_ctrs = kvm->arch.nr_pmu_counters;
>> +		params->flags |= RMI_REALM_PARAM_FLAG_PMU;
>> +	}
>> +
>> +	if (kvm_lpa2_is_enabled())
>> +		params->flags |= RMI_REALM_PARAM_FLAG_LPA2;
>> +
>> +	params_phys = virt_to_phys(params);
>> +
>> +	if (rmi_realm_create(rd_phys, params_phys)) {
>> +		r = -ENXIO;
>> +		goto out_undelegate_tables;
>> +	}
>> +
>> +	if (WARN_ON(rmi_rec_aux_count(rd_phys, &realm->num_aux))) {
>> +		WARN_ON(rmi_realm_destroy(rd_phys));
>> +		r = -ENXIO;
>> +		goto out_undelegate_tables;
>> +	}
>> +
>> +	realm->rd = rd;
>> +	WRITE_ONCE(realm->state, REALM_STATE_NEW);
>> +	/* The realm is up, free the parameters.  */
>> +	free_page((unsigned long)realm->params);
>> +	realm->params = NULL;
>> +
>> +	return 0;
>> +
>> +out_undelegate_tables:
>> +	if (WARN_ON(undelegate_range(kvm->arch.mmu.pgd_phys, i))) {
>> +		/* Leak the pages if they cannot be returned */
>> +		kvm->arch.mmu.pgt = NULL;
> 
> Did you mean kvm->arch.mmu.pgd_phys = NULL; ?

No, although I agree this isn't exactly ideal. kvm_free_stage2_pgd()
uses mmu->pgt to decide whether to free the memory - pgd_phys isn't used
in that path. Technically here we end up leaking more than just the PGD
pages in this case, but as it's a "should never happen" case I didn't
see the need to worry about the leak being a bit larger than necessary.

Thanks,
Steve

> Thanks,
> Wei-Lin Chang
> 
>> +	}
>> +	if (WARN_ON(undelegate_page(rd_phys))) {
>> +		/* Leak the page if it isn't returned */
>> +		return r;
>> +	}
>> +free_rd:
>> +	free_page((unsigned long)rd);
>> +	return r;
>> +}
>> +
>>  static void realm_unmap_private_range(struct kvm *kvm,
>>  				      unsigned long start,
>>  				      unsigned long end,
>> @@ -893,8 +970,21 @@ static int realm_init_ipa_state(struct kvm *kvm,
>>  
>>  static int realm_ensure_created(struct kvm *kvm)
>>  {
>> -	/* Provided in later patch */
>> -	return -ENXIO;
>> +	int ret;
>> +
>> +	switch (kvm_realm_state(kvm)) {
>> +	case REALM_STATE_NONE:
>> +		break;
>> +	case REALM_STATE_NEW:
>> +		return 0;
>> +	case REALM_STATE_DEAD:
>> +		return -ENXIO;
>> +	default:
>> +		return -EBUSY;
>> +	}
>> +
>> +	ret = realm_create_rd(kvm);
>> +	return ret;
>>  }
>>  
>>  static int set_ripas_of_protected_regions(struct kvm *kvm)
>> -- 
>> 2.43.0
>>