Re: [PATCH] KVM: arm64: Reject the stage-2 MMU pointer hypercalls under pKVM

[Marc Zyngier <maz@kernel.org>]

On Mon, 14 Sep 2026 18:45:21 +0100,
Fuad Tabba <fuad.tabba@linux.dev> wrote:
> 
> The five hypercalls that take a struct kvm_s2_mmu pointer remain
> callable after pKVM finalises, and each dereferences the host pointer
> in __load_stage2(). Under pKVM none of them has a valid caller: the
> host walks no guest stage-2, its TLB flushes go through the handle-based
> __pkvm_tlb_flush_vmid, and kvm_arch_vcpu_load() skips the CPU context
> flush.
> 
> Reject all five when protected mode is enabled.
> 
> Reported-by: Sashiko <sashiko-bot@kernel.org>
> Closes: https://lore.kernel.org/all/20260914130152.F0D5F1F000FF@smtp.kernel.org/
> Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
> ---
> 
> Notes:
>     No in-tree host path reaches these, so no Fixes: tag.
> 
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c | 15 +++++++++++++++
>  1 file changed, 15 insertions(+)
> 
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 9a3b92e626adb..4b0d00e55e2ea 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -557,6 +557,9 @@ static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt)
>  	DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2);
>  	DECLARE_REG(int, level, host_ctxt, 3);
>  
> +	if (unlikely(is_protected_kvm_enabled()))
> +		return;
> +
>  	__kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level);
>  }
>  
> @@ -566,6 +569,9 @@ static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctx
>  	DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2);
>  	DECLARE_REG(int, level, host_ctxt, 3);
>  
> +	if (unlikely(is_protected_kvm_enabled()))
> +		return;
> +
>  	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
>  }
>  
> @@ -576,6 +582,9 @@ handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
>  	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
>  	DECLARE_REG(unsigned long, pages, host_ctxt, 3);
>  
> +	if (unlikely(is_protected_kvm_enabled()))
> +		return;
> +
>  	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages);
>  }
>  
> @@ -583,6 +592,9 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
>  {
>  	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
>  
> +	if (unlikely(is_protected_kvm_enabled()))
> +		return;
> +
>  	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
>  }
>  
> @@ -602,6 +614,9 @@ static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
>  {
>  	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
>  
> +	if (unlikely(is_protected_kvm_enabled()))
> +		return;
> +
>  	__kvm_flush_cpu_context(kern_hyp_va(mmu));
>  }
>  

Anf why not __kvm_flush_vm_context()? It doesn't take a S2 MMU
pointer, but it is still logically wrong to let this being called.

And the whole sprinkling of guards like this is just horrible. We
already have a filtering mechanism, just make use of it:

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index bffdeb36da1d2..51bf30b671fe4 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -62,6 +62,11 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config,
+	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,
 
 	MARKER(__KVM_HOST_SMCCC_FUNC_MIN_PKVM),
 
@@ -70,11 +75,6 @@ enum __kvm_host_smccc_func {
 	/* Hypercalls that are always available and common to [nh]VHE/pKVM. */
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
-	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
-	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
-	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
-	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
-	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___tracing_load,


Thanks,

	M.

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