Re: [PATCH v12 20/46] arm64: RMI: Allow populating initial contents

[Marc Zyngier]

On Wed, 17 Dec 2025 10:10:57 +0000,
Steven Price <steven.price@xxxxxxx> wrote:
> 
> The VMM needs to populate the realm with some data before starting (e.g.
> a kernel and initrd). This is measured by the RMM and used as part of
> the attestation later on.
> 
> Signed-off-by: Steven Price <steven.price@xxxxxxx>
> ---
> Changes since v11:
>  * The multiplex CAP is gone and there's a new ioctl which makes use of
>    the generic kvm_gmem_populate() functionality.
> Changes since v7:
>  * Improve the error codes.
>  * Other minor changes from review.
> Changes since v6:
>  * Handle host potentially having a larger page size than the RMM
>    granule.
>  * Drop historic "par" (protected address range) from
>    populate_par_region() - it doesn't exist within the current
>    architecture.
>  * Add a cond_resched() call in kvm_populate_realm().
> Changes since v5:
>  * Refactor to use PFNs rather than tracking struct page in
>    realm_create_protected_data_page().
>  * Pull changes from a later patch (in the v5 series) for accessing
>    pages from a guest memfd.
>  * Do the populate in chunks to avoid holding locks for too long and
>    triggering RCU stall warnings.
> ---
>  arch/arm64/include/asm/kvm_rmi.h |   4 +
>  arch/arm64/kvm/Kconfig           |   1 +
>  arch/arm64/kvm/arm.c             |   9 ++
>  arch/arm64/kvm/rmi.c             | 175 +++++++++++++++++++++++++++++++
>  4 files changed, 189 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/kvm_rmi.h b/arch/arm64/include/asm/kvm_rmi.h
> index 8a862fc1a99d..b5e36344975c 100644
> --- a/arch/arm64/include/asm/kvm_rmi.h
> +++ b/arch/arm64/include/asm/kvm_rmi.h
> @@ -99,6 +99,10 @@ int kvm_rec_enter(struct kvm_vcpu *vcpu);
>  int kvm_rec_pre_enter(struct kvm_vcpu *vcpu);
>  int handle_rec_exit(struct kvm_vcpu *vcpu, int rec_run_status);
>  
> +struct kvm_arm_rmi_populate;
> +
> +int kvm_arm_rmi_populate(struct kvm *kvm,
> +			 struct kvm_arm_rmi_populate *arg);
>  void kvm_realm_unmap_range(struct kvm *kvm,
>  			   unsigned long ipa,
>  			   unsigned long size,
> diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
> index 1cac6dfc0972..b495dfd3a8b4 100644
> --- a/arch/arm64/kvm/Kconfig
> +++ b/arch/arm64/kvm/Kconfig
> @@ -39,6 +39,7 @@ menuconfig KVM
>  	select GUEST_PERF_EVENTS if PERF_EVENTS
>  	select KVM_GUEST_MEMFD
>  	select KVM_GENERIC_MEMORY_ATTRIBUTES
> +	select HAVE_KVM_ARCH_GMEM_POPULATE
>  	help
>  	  Support hosting virtualized guest machines.
>  
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index 7927181887cf..0a06ed9d1a64 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -2037,6 +2037,15 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
>  			return -EFAULT;
>  		return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range);
>  	}
> +	case KVM_ARM_RMI_POPULATE: {
> +		struct kvm_arm_rmi_populate req;
> +
> +		if (!kvm_is_realm(kvm))
> +			return -EPERM;

EPERM is odd. It isn't that the VMM doesn't have the right to do it,
it is that it shouldn't have called that, because the ioctl doesn't
exist for a normal VM. -ENOSYS?

> +		if (copy_from_user(&req, argp, sizeof(req)))
> +			return -EFAULT;
> +		return kvm_arm_rmi_populate(kvm, &req);
> +	}
>  	default:
>  		return -EINVAL;
>  	}
> diff --git a/arch/arm64/kvm/rmi.c b/arch/arm64/kvm/rmi.c
> index fe15b400091c..39577e956a59 100644
> --- a/arch/arm64/kvm/rmi.c
> +++ b/arch/arm64/kvm/rmi.c
> @@ -558,6 +558,150 @@ void kvm_realm_unmap_range(struct kvm *kvm, unsigned long start,
>  		realm_unmap_private_range(kvm, start, end, may_block);
>  }
>  
> +static int realm_create_protected_data_granule(struct realm *realm,
> +					       unsigned long ipa,
> +					       phys_addr_t dst_phys,
> +					       phys_addr_t src_phys,
> +					       unsigned long flags)
> +{
> +	phys_addr_t rd = virt_to_phys(realm->rd);
> +	int ret;
> +
> +	if (rmi_granule_delegate(dst_phys))
> +		return -ENXIO;
> +
> +	ret = rmi_data_create(rd, dst_phys, ipa, src_phys, flags);
> +	if (RMI_RETURN_STATUS(ret) == RMI_ERROR_RTT) {
> +		/* Create missing RTTs and retry */
> +		int level = RMI_RETURN_INDEX(ret);
> +
> +		WARN_ON(level == RMM_RTT_MAX_LEVEL);

If this is unexpected, why do we still try to handle it? We should
abort hard on anything that doesn't seem 100% correct, and mark the
realm dead.

> +
> +		ret = realm_create_rtt_levels(realm, ipa, level,
> +					      RMM_RTT_MAX_LEVEL, NULL);
> +		if (ret)
> +			return -EIO;
> +
> +		ret = rmi_data_create(rd, dst_phys, ipa, src_phys, flags);
> +	}
> +	if (ret)
> +		return -EIO;
> +
> +	return 0;
> +}
> +
> +static int realm_create_protected_data_page(struct realm *realm,
> +					    unsigned long ipa,
> +					    kvm_pfn_t dst_pfn,
> +					    kvm_pfn_t src_pfn,
> +					    unsigned long flags)
> +{
> +	unsigned long rd = virt_to_phys(realm->rd);
> +	phys_addr_t dst_phys, src_phys;
> +	bool undelegate_failed = false;
> +	int ret, offset;
> +
> +	dst_phys = __pfn_to_phys(dst_pfn);
> +	src_phys = __pfn_to_phys(src_pfn);
> +
> +	for (offset = 0; offset < PAGE_SIZE; offset += RMM_PAGE_SIZE) {
> +		ret = realm_create_protected_data_granule(realm,
> +							  ipa,
> +							  dst_phys,
> +							  src_phys,
> +							  flags);
> +		if (ret)
> +			goto err;
> +
> +		ipa += RMM_PAGE_SIZE;
> +		dst_phys += RMM_PAGE_SIZE;
> +		src_phys += RMM_PAGE_SIZE;
> +	}
> +
> +	return 0;
> +
> +err:
> +	if (ret == -EIO) {
> +		/* current offset needs undelegating */
> +		if (WARN_ON(rmi_granule_undelegate(dst_phys)))
> +			undelegate_failed = true;
> +	}
> +	while (offset > 0) {
> +		ipa -= RMM_PAGE_SIZE;
> +		offset -= RMM_PAGE_SIZE;
> +		dst_phys -= RMM_PAGE_SIZE;
> +
> +		rmi_data_destroy(rd, ipa, NULL, NULL);
> +
> +		if (WARN_ON(rmi_granule_undelegate(dst_phys)))
> +			undelegate_failed = true;
> +	}
> +
> +	if (undelegate_failed) {
> +		/*
> +		 * A granule could not be undelegated,
> +		 * so the page has to be leaked
> +		 */
> +		get_page(pfn_to_page(dst_pfn));
> +	}
> +
> +	return -ENXIO;
> +}
> +
> +static int populate_region_cb(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
> +			      void __user *src, int order, void *opaque)
> +{
> +	struct realm *realm = &kvm->arch.realm;
> +	unsigned long data_flags = *(unsigned long *)opaque;
> +	phys_addr_t ipa = gfn_to_gpa(gfn);
> +	int npages = (1 << order);
> +	int i;
> +
> +	for (i = 0; i < npages; i++) {
> +		struct page *src_page;
> +		int ret;
> +
> +		ret = get_user_pages((unsigned long)src, 1, 0, &src_page);
> +		if (ret < 0)
> +			return ret;
> +		if (ret != 1)
> +			return -ENOMEM;
> +
> +		ret = realm_create_protected_data_page(realm, ipa, pfn,
> +						       page_to_pfn(src_page),
> +						       data_flags);
> +
> +		put_page(src_page);
> +
> +		if (ret)
> +			return ret;
> +
> +		ipa += PAGE_SIZE;
> +		pfn++;
> +		src += PAGE_SIZE;
> +	}
> +
> +	return 0;
> +}
> +
> +static long populate_region(struct kvm *kvm,
> +			    gfn_t base_gfn,
> +			    unsigned long pages,
> +			    u64 uaddr,
> +			    unsigned long data_flags)
> +{
> +	long ret = 0;
> +
> +	mutex_lock(&kvm->slots_lock);
> +	mmap_read_lock(current->mm);
> +	ret = kvm_gmem_populate(kvm, base_gfn, u64_to_user_ptr(uaddr), pages,
> +				populate_region_cb, &data_flags);
> +	mmap_read_unlock(current->mm);
> +	mutex_unlock(&kvm->slots_lock);
> +
> +	return ret;
> +}
> +
>  enum ripas_action {
>  	RIPAS_INIT,
>  	RIPAS_SET,
> @@ -655,6 +799,37 @@ static int realm_ensure_created(struct kvm *kvm)
>  	return -ENXIO;
>  }
>  
> +int kvm_arm_rmi_populate(struct kvm *kvm,
> +			 struct kvm_arm_rmi_populate *args)
> +{
> +	unsigned long data_flags = 0;
> +	unsigned long ipa_start = args->base;
> +	unsigned long ipa_end = ipa_start + args->size;
> +	int ret;
> +
> +	if (args->reserved ||
> +	    (args->flags & ~KVM_ARM_RMI_POPULATE_FLAGS_MEASURE) ||
> +	    !IS_ALIGNED(ipa_start, PAGE_SIZE) ||
> +	    !IS_ALIGNED(ipa_end, PAGE_SIZE))
> +		return -EINVAL;
> +
> +	ret = realm_ensure_created(kvm);
> +	if (ret)
> +		return ret;
> +
> +	if (args->flags & KVM_ARM_RMI_POPULATE_FLAGS_MEASURE)

This flag isn't documented.

> +		data_flags |= RMI_MEASURE_CONTENT;
> +
> +	ret = populate_region(kvm, gpa_to_gfn(ipa_start),
> +			      args->size >> PAGE_SHIFT,
> +			      args->source_uaddr, args->flags);
> +
> +	if (ret < 0)
> +		return ret;
> +
> +	return ret * PAGE_SIZE;

Bits of the code works on PAGE_SIZE, other bits on RMM_PAGE_SIZE. It
is pretty confusing. Are you in the middle of reworking this?

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.