Re: [RFC PATCH 09/28] arm64: RME: RTT handling

[Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>]

On 27-01-2023 04:59 pm, 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.
> 
> Signed-off-by: Steven Price <steven.price@arm.com>
> ---
>   arch/arm64/include/asm/kvm_rme.h |  19 +++++
>   arch/arm64/kvm/mmu.c             |   7 +-
>   arch/arm64/kvm/rme.c             | 139 +++++++++++++++++++++++++++++++
>   3 files changed, 162 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_rme.h b/arch/arm64/include/asm/kvm_rme.h
> index a6318af3ed11..eea5118dfa8a 100644
> --- a/arch/arm64/include/asm/kvm_rme.h
> +++ b/arch/arm64/include/asm/kvm_rme.h
> @@ -35,5 +35,24 @@ u32 kvm_realm_ipa_limit(void);
>   int kvm_realm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap);
>   int kvm_init_realm_vm(struct kvm *kvm);
>   void kvm_destroy_realm(struct kvm *kvm);
> +void kvm_realm_destroy_rtts(struct realm *realm, u32 ia_bits, u32 start_level);
> +
> +#define RME_RTT_BLOCK_LEVEL	2
> +#define RME_RTT_MAX_LEVEL	3
> +
> +#define RME_PAGE_SHIFT		12
> +#define RME_PAGE_SIZE		BIT(RME_PAGE_SHIFT)

Can we use PAGE_SIZE and PAGE_SHIFT instead of redefining?
May be we can use them to define RME_PAGE_SIZE and RME_PAGE_SHIFT.

> +/* See ARM64_HW_PGTABLE_LEVEL_SHIFT() */
> +#define RME_RTT_LEVEL_SHIFT(l)	\
> +	((RME_PAGE_SHIFT - 3) * (4 - (l)) + 3)

Instead of defining again, can we define to
ARM64_HW_PGTABLE_LEVEL_SHIFT?

> +#define RME_L2_BLOCK_SIZE	BIT(RME_RTT_LEVEL_SHIFT(2))
> +
> +static inline unsigned long rme_rtt_level_mapsize(int level)
> +{
> +	if (WARN_ON(level > RME_RTT_MAX_LEVEL))
> +		return RME_PAGE_SIZE;
> +
> +	return (1UL << RME_RTT_LEVEL_SHIFT(level));
> +}
>   
>   #endif
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index 22c00274884a..f29558c5dcbc 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -834,16 +834,17 @@ 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;
>   	if (kvm_is_realm(kvm) &&
>   	    kvm_realm_state(kvm) != REALM_STATE_DYING) {
> -		/* TODO: teardown rtts */
>   		write_unlock(&kvm->mmu_lock);
> +		kvm_realm_destroy_rtts(&kvm->arch.realm, pgt->ia_bits,
> +				       pgt->start_level);
>   		return;
>   	}
> -	pgt = mmu->pgt;
>   	if (pgt) {
>   		mmu->pgd_phys = 0;
>   		mmu->pgt = NULL;
> diff --git a/arch/arm64/kvm/rme.c b/arch/arm64/kvm/rme.c
> index 0c9d70e4d9e6..f7b0e5a779f8 100644
> --- a/arch/arm64/kvm/rme.c
> +++ b/arch/arm64/kvm/rme.c
> @@ -73,6 +73,28 @@ static int rmi_check_version(void)
>   	return 0;
>   }
>   
> +static void realm_destroy_undelegate_range(struct realm *realm,
> +					   unsigned long ipa,
> +					   unsigned long addr,
> +					   ssize_t size)
> +{
> +	unsigned long rd = virt_to_phys(realm->rd);
> +	int ret;
> +
> +	while (size > 0) {
> +		ret = rmi_data_destroy(rd, ipa);
> +		WARN_ON(ret);
> +		ret = rmi_granule_undelegate(addr);
> +
> +		if (ret)
> +			get_page(phys_to_page(addr));
> +
> +		addr += PAGE_SIZE;
> +		ipa += PAGE_SIZE;
> +		size -= PAGE_SIZE;
> +	}
> +}
> +
>   static unsigned long create_realm_feat_reg0(struct kvm *kvm)
>   {
>   	unsigned long ia_bits = VTCR_EL2_IPA(kvm->arch.vtcr);
> @@ -170,6 +192,123 @@ static int realm_create_rd(struct kvm *kvm)
>   	return r;
>   }
>   
> +static int realm_rtt_destroy(struct realm *realm, unsigned long addr,
> +			     int level, phys_addr_t rtt_granule)
> +{
> +	addr = ALIGN_DOWN(addr, rme_rtt_level_mapsize(level - 1));
> +	return rmi_rtt_destroy(rtt_granule, virt_to_phys(realm->rd), addr,
> +			level);
> +}
> +
> +static int realm_destroy_free_rtt(struct realm *realm, unsigned long addr,
> +				  int level, phys_addr_t rtt_granule)
> +{
> +	if (realm_rtt_destroy(realm, addr, level, rtt_granule))
> +		return -ENXIO;
> +	if (!WARN_ON(rmi_granule_undelegate(rtt_granule)))
> +		put_page(phys_to_page(rtt_granule));
> +
> +	return 0;
> +}
> +
> +static int realm_rtt_create(struct realm *realm,
> +			    unsigned long addr,
> +			    int level,
> +			    phys_addr_t phys)
> +{
> +	addr = ALIGN_DOWN(addr, rme_rtt_level_mapsize(level - 1));
> +	return rmi_rtt_create(phys, virt_to_phys(realm->rd), addr, level);
> +}
> +
> +static int realm_tear_down_rtt_range(struct realm *realm, int level,
> +				     unsigned long start, unsigned long end)
> +{
> +	phys_addr_t rd = virt_to_phys(realm->rd);
> +	ssize_t map_size = rme_rtt_level_mapsize(level);
> +	unsigned long addr, next_addr;
> +	bool failed = false;
> +
> +	for (addr = start; addr < end; addr = next_addr) {
> +		phys_addr_t rtt_addr, tmp_rtt;
> +		struct rtt_entry rtt;
> +		unsigned long end_addr;
> +
> +		next_addr = ALIGN(addr + 1, map_size);
> +
> +		end_addr = min(next_addr, end);
> +
> +		if (rmi_rtt_read_entry(rd, ALIGN_DOWN(addr, map_size),
> +				       level, &rtt)) {
> +			failed = true;
> +			continue;
> +		}
> +
> +		rtt_addr = rmi_rtt_get_phys(&rtt);
> +		WARN_ON(level != rtt.walk_level);
> +
> +		switch (rtt.state) {
> +		case RMI_UNASSIGNED:
> +		case RMI_DESTROYED:
> +			break;
> +		case RMI_TABLE:
> +			if (realm_tear_down_rtt_range(realm, level + 1,
> +						      addr, end_addr)) {
> +				failed = true;
> +				break;
> +			}
> +			if (IS_ALIGNED(addr, map_size) &&
> +			    next_addr <= end &&
> +			    realm_destroy_free_rtt(realm, addr, level + 1,
> +						   rtt_addr))
> +				failed = true;
> +			break;
> +		case RMI_ASSIGNED:
> +			WARN_ON(!rtt_addr);
> +			/*
> +			 * If there is a block mapping, break it now, using the
> +			 * spare_page. We are sure to have a valid delegated
> +			 * page at spare_page before we enter here, otherwise
> +			 * WARN once, which will be followed by further
> +			 * warnings.
> +			 */
> +			tmp_rtt = realm->spare_page;
> +			if (level == 2 &&
> +			    !WARN_ON_ONCE(tmp_rtt == PHYS_ADDR_MAX) &&
> +			    realm_rtt_create(realm, addr,
> +					     RME_RTT_MAX_LEVEL, tmp_rtt)) {
> +				WARN_ON(1);
> +				failed = true;
> +				break;
> +			}
> +			realm_destroy_undelegate_range(realm, addr,
> +						       rtt_addr, map_size);
> +			/*
> +			 * Collapse the last level table and make the spare page
> +			 * reusable again.
> +			 */
> +			if (level == 2 &&
> +			    realm_rtt_destroy(realm, addr, RME_RTT_MAX_LEVEL,
> +					      tmp_rtt))
> +				failed = true;
> +			break;
> +		case RMI_VALID_NS:
> +			WARN_ON(rmi_rtt_unmap_unprotected(rd, addr, level));
> +			break;
> +		default:
> +			WARN_ON(1);
> +			failed = true;
> +			break;
> +		}
> +	}
> +
> +	return failed ? -EINVAL : 0;
> +}
> +
> +void kvm_realm_destroy_rtts(struct realm *realm, u32 ia_bits, u32 start_level)
> +{
> +	realm_tear_down_rtt_range(realm, start_level, 0, (1UL << ia_bits));
> +}
> +
>   /* Protects access to rme_vmid_bitmap */
>   static DEFINE_SPINLOCK(rme_vmid_lock);
>   static unsigned long *rme_vmid_bitmap;

Thanks,
Ganapat