Re: [PATCH v7 07/24] KVM: arm64: iommu: Shadow host stage-2 page table

On Wed, Jul 15, 2026 at 11:58:48AM +0000, Mostafa Saleh wrote:
> Create a page-table for the IOMMU that shadows the host CPU stage-2
> to establish DMA isolation.
> 
> An initial snapshot is created after the driver init, then
> on every permission change a callback would be called for
> the IOMMU driver to update the page table.
> 
> There are 3 different ways to add the callback:
> 1) In the high level memory transitions: (__pkvm_host_donate_hyp(),
>   __pkvm_host_donate_guest()...
> 
> 2) In Lower level functions covering all transitions
>   - host_stage2_set_owner_metadata_locked() which covers:
>    - __pkvm_host_donate_hyp()
>    - __pkvm_host_donate_guest()
>    - __pkvm_host_donate_hyp()
>    - __pkvm_guest_unshare_host()
>   - host_stage2_set_owner_locked() only for ID_HOST which covers:
>    - __pkvm_hyp_donate_host()
>    - __pkvm_host_force_reclaim_page_guest()
>    - __pkvm_host_reclaim_page_guest()
>   - __pkvm_guest_share_host()
> 
> 3) In the lowest level function __host_update_page_state(), which
>    requires only one callback. However, in that case the page state
>    is not enough as we might need to know the old state also.
> 
> Option #2 was implemented here.
> 
> For some cases, an SMMUv3 may be able to share the same page-table
> used with the host CPU stage-2 directly.
> 
> However, this is too strict and requires changes to the core hypervisor
> page-table code, plus it would require the hypervisor to handle IOMMU
> page-faults. This can be added later as an optimization for SMMUV3.
> 
> Signed-off-by: Mostafa Saleh <[email protected]>
> ---
>  arch/arm64/kvm/hyp/include/nvhe/iommu.h       |   4 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |   1 +
>  arch/arm64/kvm/hyp/nvhe/iommu.c               | 129 +++++++++++++++++-
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         |  27 ++--
>  4 files changed, 145 insertions(+), 16 deletions(-)
> 
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/iommu.h b/arch/arm64/kvm/hyp/include/nvhe/iommu.h
> index df3d0cc5d4db..857d7dd2ebc3 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/iommu.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/iommu.h
> @@ -3,11 +3,15 @@
>  #define __ARM64_KVM_NVHE_IOMMU_H__
>  
>  #include <asm/kvm_host.h>
> +#include <asm/kvm_pgtable.h>
>  
>  struct pkvm_iommu_ops {
>  	int (*init)(void);
> +	int (*host_stage2_idmap)(phys_addr_t start, phys_addr_t end, int prot);

Hi Mostafa,

Maybe host_stage2_idmap_locked, since it is invoked while the host
stage-2 lock is acquired ?

>  };
>  
>  int pkvm_iommu_init(void);
>  
> +int pkvm_iommu_host_stage2_idmap(phys_addr_t start, phys_addr_t end,
> +				 enum kvm_pgtable_prot prot);
>  #endif /* __ARM64_KVM_NVHE_IOMMU_H__ */
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index 51b0eb3844a9..99b821b3cf65 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -59,6 +59,7 @@ int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct
>  int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu);
>  
>  bool addr_is_memory(phys_addr_t phys);
> +
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
>  int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id);
>  int kvm_host_prepare_stage2(void *pgt_pool_base);
> diff --git a/arch/arm64/kvm/hyp/nvhe/iommu.c b/arch/arm64/kvm/hyp/nvhe/iommu.c
> index ef456eff42d2..08009609ec59 100644
> --- a/arch/arm64/kvm/hyp/nvhe/iommu.c
> +++ b/arch/arm64/kvm/hyp/nvhe/iommu.c
> @@ -4,16 +4,137 @@
>   *
>   * Copyright (C) 2022 Linaro Ltd.
>   */
> +#include <linux/iommu.h>
> +#include <asm/kvm_pkvm.h>
> +
>  #include <nvhe/iommu.h>
> +#include <nvhe/mem_protect.h>
> +#include <nvhe/spinlock.h>
>  
>  /* Only one set of ops supported */
>  struct pkvm_iommu_ops *pkvm_iommu_ops;
>  
> -int pkvm_iommu_init(void)
> +/* Protected by host_mmu.lock */
> +static bool pkvm_idmap_initialized;
> +
> +static inline int pkvm_to_iommu_prot(enum kvm_pgtable_prot prot)
>  {
> -	/* Keep DMA isolation optional. */
> -	if (!pkvm_iommu_ops || !pkvm_iommu_ops->init)
> +	int iommu_prot = 0;
> +
> +	if (prot & KVM_PGTABLE_PROT_R)
> +		iommu_prot |= IOMMU_READ;
> +	if (prot & KVM_PGTABLE_PROT_W)
> +		iommu_prot |= IOMMU_WRITE;
> +
> +	/* We don't understand that, might be dangerous. */
> +	WARN_ON(prot & ~PKVM_HOST_MEM_PROT);
> +	return iommu_prot;
> +}
> +
> +/*
> + * IOMMU page tables are shadowed and not shared, that is mainly because:
> + * - Possible inconsistency between IOMMU and CPU features or format.
> + * - KVM relies on handling in page faults (BBM, lazy mapping).
> + */
> +static int __snapshot_host_stage2(const struct kvm_pgtable_visit_ctx *ctx,
> +				  enum kvm_pgtable_walk_flags visit)
> +{
> +	u64 start = ctx->addr;
> +	u64 block_end = ALIGN_DOWN(ctx->addr, kvm_granule_size(ctx->level)) +
> +			kvm_granule_size(ctx->level);
> +	u64 end = min(ctx->end, block_end);
> +	kvm_pte_t pte = *ctx->ptep;
> +	bool is_memory = *(bool *)ctx->arg;
> +	int prot;
> +
> +	/*
> +	 * Keep annotated PTEs unmapped, and map everything else even lazily
> +	 * mapped PTEs(0), as the IOMMU can't handle page faults.
> +	 * That maps the whole address space which can be large, but that doesn't
> +	 * use a lot of memory as it will be mostly large block (1 GB with 4kb pages)
> +	 */
> +	if (pte && !kvm_pte_valid(pte))
>  		return 0;

>  
> -	return pkvm_iommu_ops->init();
> +	if (kvm_pte_valid(pte))
> +		prot = pkvm_to_iommu_prot(kvm_pgtable_stage2_pte_prot(pte));
> +	else
> +		prot = IOMMU_READ | IOMMU_WRITE;

If it's invalid in the host stage-2 why do you make it read/write in the IOMMU
? Shouldn't it be an invalid descriptor in the IOMMU pagetables as well
?

> +
> +	if (!is_memory)
> +		prot |= IOMMU_MMIO;
> +
> +	return pkvm_iommu_ops->host_stage2_idmap(start, end, prot);
> +}
> +
> +static int pkvm_iommu_snapshot_host_stage2(void)
> +{
> +	struct kvm_pgtable *pgt = &host_mmu.pgt;
> +	bool is_memory;
> +	struct kvm_pgtable_walker walker = {
> +		.cb	= __snapshot_host_stage2,
> +		.flags	= KVM_PGTABLE_WALK_LEAF,
> +		.arg	= &is_memory,
> +	};
> +	int ret = 0, i;
> +	u64 start = 0;
> +
> +	hyp_spin_lock(&host_mmu.lock);
> +	for (i = 0; i < hyp_memblock_nr; i++) {
> +		struct memblock_region *reg = &hyp_memory[i];
> +
> +		if (start < reg->base) {
> +			is_memory = false;
> +			ret = kvm_pgtable_walk(pgt, start, reg->base - start, &walker);
> +			if (ret)
> +				goto out_unlock;
> +		}
> +
> +		is_memory = true;
> +		ret = kvm_pgtable_walk(pgt, reg->base, reg->size, &walker);
> +		if (ret)
> +			goto out_unlock;
> +
> +		start = reg->base + reg->size;
> +	}
> +
> +	if (start < BIT(pgt->ia_bits)) {
> +		is_memory = false;
> +		ret = kvm_pgtable_walk(pgt, start, BIT(pgt->ia_bits) - start, &walker);
> +		if (ret)
> +			goto out_unlock;
> +	}
> +
> +	pkvm_idmap_initialized = true;
> +
> +out_unlock:
> +	hyp_spin_unlock(&host_mmu.lock);
> +	return ret;
> +}
> +
> +int pkvm_iommu_init(void)
> +{
> +	int ret;
> +
> +	/* Keep DMA isolation optional. */
> +	if (!pkvm_iommu_ops || !pkvm_iommu_ops->init ||
> +	    !pkvm_iommu_ops->host_stage2_idmap)
> +		return 0;

Shouldn't this scream or return not supported ? 

> +
> +	ret = pkvm_iommu_ops->init();
> +	if (ret)
> +		return ret;
> +
> +	return pkvm_iommu_snapshot_host_stage2();

If pkvm_iommu_snapshot_host_stage2() fails would you have to provide a
->deinit() corresponding callback ?

> +}
> +
> +int pkvm_iommu_host_stage2_idmap(phys_addr_t start, phys_addr_t end,
> +				enum kvm_pgtable_prot prot)
> +{
> +	hyp_assert_lock_held(&host_mmu.lock);
> +
> +	if (!pkvm_idmap_initialized)
> +		return 0;
> +
> +	return pkvm_iommu_ops->host_stage2_idmap(start, end, pkvm_to_iommu_prot(prot));
>  }
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index d803b3dd4cb4..ce610274bda0 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -17,6 +17,7 @@
>  
>  #include <nvhe/arm-smccc.h>
>  #include <nvhe/gfp.h>
> +#include <nvhe/iommu.h>
>  #include <nvhe/memory.h>
>  #include <nvhe/mem_protect.h>
>  #include <nvhe/mm.h>
> @@ -596,16 +597,15 @@ static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size,
>  	ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt,
>  			      addr, size, &host_s2_pool,
>  			      KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation);
> -	if (!ret) {
> -		/*
> -		 * After stage2 maintenance has happened, but before the page
> -		 * owner has changed.
> -		 */
> -		pkvm_sme_dvmsync_fw_call();
> -		__host_update_page_state(addr, size, PKVM_NOPAGE);
> -	}
> -
> -	return ret;
> +	if (ret)
> +		return ret;
> +	/*
> +	 * After stage2 maintenance has happened, but before the page
> +	 * owner has changed.
> +	 */
> +	pkvm_sme_dvmsync_fw_call();
> +	__host_update_page_state(addr, size, PKVM_NOPAGE);
> +	return pkvm_iommu_host_stage2_idmap(addr, addr + size, 0);
>  }
>  
>  int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
> @@ -618,8 +618,10 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
>  			return -EPERM;
>  
>  		ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
> -		if (!ret)
> -			__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
> +		if (ret)
> +			break;
> +		__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
> +		ret = pkvm_iommu_host_stage2_idmap(addr, addr + size, PKVM_HOST_MEM_PROT);
>  		break;
>  	case PKVM_ID_HYP:
>  		ret = host_stage2_set_owner_metadata_locked(addr, size,
> @@ -1022,6 +1024,7 @@ int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn)
>  				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED),
>  				       &vcpu->vcpu.arch.pkvm_memcache, 0));
>  	WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED));
> +	WARN_ON(pkvm_iommu_host_stage2_idmap(phys, phys + PAGE_SIZE, PKVM_HOST_MEM_PROT));
>  unlock:
>  	guest_unlock_component(vm);
>  	host_unlock_component();
> -- 
> 2.55.0.141.g00534a21ce-goog
>