[PATCH v14 17/44] arm64: RMI: RTT tear down

[Wei-Lin Chang]

Hi,

On Wed, May 13, 2026 at 02:17:25PM +0100, Steven Price wrote:
> The RMM owns the stage 2 page tables for a realm, and KVM must request
> that the RMM creates/destroys entries as necessary. The physical pages
> to store the page tables are delegated to the realm as required, and can
> be undelegated when no longer used.
> 
> Creating new RTTs is the easy part, tearing down is a little more
> tricky. The result of realm_rtt_destroy() can be used to effectively
> walk the tree and destroy the entries (undelegating pages that were
> given to the realm).
> 
> Signed-off-by: Steven Price <steven.price at arm.com>
> ---
> Changes since v13:
>  * Avoid the double call of kvm_free_stage2_pgd() by splitting the work
>    across that and a new function kvm_realm_uninit_stage2() which is
>    only called for realm guests.
> Changes since v12:
>  * Simplify some functions now we know RMM page size is the same as the
>    host's.
> Changes since v11:
>  * Moved some code from earlier in the series to this one so that it's
>    added when it's first used.
> Changes since v10:
>  * RME->RMI rename.
>  * Some code to handle freeing stage 2 PGD moved into this patch where
>    it belongs.
> Changes since v9:
>  * Add a comment clarifying that root level RTTs are not destroyed until
>    after the RD is destroyed.
> Changes since v8:
>  * Introduce free_rtt() wrapper which calls free_delegated_granule()
>    followed by kvm_account_pgtable_pages(). This makes it clear where an
>    RTT is being freed rather than just a delegated granule.
> Changes since v6:
>  * Move rme_rtt_level_mapsize() and supporting defines from kvm_rme.h
>    into rme.c as they are only used in that file.
> Changes since v5:
>  * Rename some RME_xxx defines to do with page sizes as RMM_xxx - they are
>    a property of the RMM specification not the RME architecture.
> Changes since v2:
>  * Moved {alloc,free}_delegated_page() and ensure_spare_page() to a
>    later patch when they are actually used.
>  * Some simplifications now rmi_xxx() functions allow NULL as an output
>    parameter.
>  * Improved comments and code layout.
> ---
>  arch/arm64/include/asm/kvm_rmi.h |   7 ++
>  arch/arm64/kvm/mmu.c             |  21 ++++-
>  arch/arm64/kvm/rmi.c             | 148 +++++++++++++++++++++++++++++++
>  3 files changed, 174 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_rmi.h b/arch/arm64/include/asm/kvm_rmi.h
> index 9de34983ee52..06ba0d4745c6 100644
> --- a/arch/arm64/include/asm/kvm_rmi.h
> +++ b/arch/arm64/include/asm/kvm_rmi.h
> @@ -64,5 +64,12 @@ u32 kvm_realm_ipa_limit(void);
>  
>  int kvm_init_realm(struct kvm *kvm);
>  void kvm_destroy_realm(struct kvm *kvm);
> +void kvm_realm_destroy_rtts(struct kvm *kvm);
> +
> +static inline bool kvm_realm_is_private_address(struct realm *realm,
> +						unsigned long addr)
> +{
> +	return !(addr & BIT(realm->ia_bits - 1));
> +}
>  
>  #endif /* __ASM_KVM_RMI_H */
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index ba8286472286..eb56d4e7f21a 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -1024,9 +1024,26 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
>  	return err;
>  }
>  
> +static void kvm_realm_uninit_stage2(struct kvm_s2_mmu *mmu)
> +{
> +	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
> +	struct realm *realm = &kvm->arch.realm;
> +
> +	if (kvm_realm_state(kvm) != REALM_STATE_ACTIVE)
> +		return;
> +
> +	write_lock(&kvm->mmu_lock);
> +	kvm_stage2_unmap_range(mmu, 0, BIT(realm->ia_bits - 1), true);
> +	write_unlock(&kvm->mmu_lock);
> +	kvm_realm_destroy_rtts(kvm);
> +}
> +
>  void kvm_uninit_stage2_mmu(struct kvm *kvm)
>  {
> -	kvm_free_stage2_pgd(&kvm->arch.mmu);
> +	if (kvm_is_realm(kvm))
> +		kvm_realm_uninit_stage2(&kvm->arch.mmu);
> +	else
> +		kvm_free_stage2_pgd(&kvm->arch.mmu);
>  	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
>  }
>  
> @@ -1103,7 +1120,7 @@ void stage2_unmap_vm(struct kvm *kvm)
>  void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
>  {
>  	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
> -	struct kvm_pgtable *pgt = NULL;
> +	struct kvm_pgtable *pgt;
>  
>  	write_lock(&kvm->mmu_lock);
>  	pgt = mmu->pgt;
> diff --git a/arch/arm64/kvm/rmi.c b/arch/arm64/kvm/rmi.c
> index f51ec667445e..5b00ccca4af3 100644
> --- a/arch/arm64/kvm/rmi.c
> +++ b/arch/arm64/kvm/rmi.c
> @@ -11,6 +11,14 @@
>  #include <asm/rmi_cmds.h>
>  #include <asm/virt.h>
>  
> +static inline unsigned long rmi_rtt_level_mapsize(int level)
> +{
> +	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
> +		return PAGE_SIZE;
> +
> +	return (1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
> +}
> +
>  static bool rmi_has_feature(unsigned long feature)
>  {
>  	return !!u64_get_bits(rmm_feat_reg0, feature);
> @@ -21,6 +29,144 @@ u32 kvm_realm_ipa_limit(void)
>  	return u64_get_bits(rmm_feat_reg0, RMI_FEATURE_REGISTER_0_S2SZ);
>  }
>  
> +static int get_start_level(struct realm *realm)
> +{
> +	return 4 - stage2_pgtable_levels(realm->ia_bits);
> +}
> +
> +static void free_rtt(phys_addr_t phys)
> +{
> +	if (free_delegated_page(phys))
> +		return;
> +
> +	kvm_account_pgtable_pages(phys_to_virt(phys), -1);
> +}
> +
> +/*
> + * realm_rtt_destroy - Destroy an RTT at @level for @addr.
> + *
> + * Returns - Result of the RMI_RTT_DESTROY call, and:
> + * @rtt_granule:	RTT granule, if the RTT was destroyed.
> + * @next_addr:		IPA corresponding to the next possible valid entry we
> + *			can target
> + */
> +static int realm_rtt_destroy(struct realm *realm, unsigned long addr,
> +			     int level, phys_addr_t *rtt_granule,
> +			     unsigned long *next_addr)
> +{
> +	unsigned long out_rtt;
> +	int ret;
> +
> +	ret = rmi_rtt_destroy(virt_to_phys(realm->rd), addr, level,
> +			      &out_rtt, next_addr);
> +
> +	*rtt_granule = out_rtt;
> +
> +	return ret;
> +}

Looks like out_rtt can be simplified out.

[...]

Thanks,
Wei-Lin Chang