[PATCH v2 1/2] KVM: arm64: Validate the host vCPU's VM before reading it under pKVM

[Vincent Donnefort]

On Tue, Sep 15, 2026 at 08:04:17AM +0100, Fuad Tabba wrote:
> On an MTE-capable host under pKVM, enter_exception64() reads the VM's
> MTE flag through vcpu->kvm, which for a host vCPU is a host-writable
> pointer nothing validates. The host can point it at any address in the
> hyp linear map and read back bit 1 of that word through PSR_TCO in the
> vCPU's CPSR, or panic the hypervisor with an unmapped one.
> 
> Get the VM through a get/put pair around the read: a loaded vCPU's is
> the hyp VM, an unloaded host vCPU's is read once and pinned, and a
> pointer the host never shared leaves TCO clear.
> 
> Fixes: ea7fc1bb1cd1b ("KVM: arm64: Introduce MTE VM feature")
> Reported-by: Sashiko <sashiko-bot at kernel.org>
> Closes: https://lore.kernel.org/all/20260914070536.877D91F000FF@smtp.kernel.org/
> Cc: stable at vger.kernel.org
> Signed-off-by: Fuad Tabba <fuad.tabba at linux.dev>
> ---
>  arch/arm64/kvm/hyp/exception.c             |  5 ++-
>  arch/arm64/kvm/hyp/include/hyp/adjust_pc.h | 18 ++++++++++
>  arch/arm64/kvm/hyp/nvhe/pkvm.c             | 39 ++++++++++++++++++++++
>  3 files changed, 61 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
> index 754e2dc1df54a..6e60d890afa4a 100644
> --- a/arch/arm64/kvm/hyp/exception.c
> +++ b/arch/arm64/kvm/hyp/exception.c
> @@ -70,6 +70,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
>  			      enum exception_type type)
>  {
>  	unsigned long sctlr, vbar, old, new, mode;
> +	struct kvm *kvm;
>  	u64 exc_offset;
>  
>  	mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
> @@ -109,8 +110,10 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
>  	new |= (old & PSR_C_BIT);
>  	new |= (old & PSR_V_BIT);
>  
> -	if (kvm_has_mte(kern_hyp_va(vcpu->kvm)))
> +	kvm = vcpu_get_kvm(vcpu);
> +	if (kvm && kvm_has_mte(kvm))
>  		new |= PSR_TCO_BIT;
> +	vcpu_put_kvm(vcpu, kvm);
>  
>  	new |= (old & PSR_DIT_BIT);
>  
> diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
> index 4fdfeabefeb43..a4fb04faa7d09 100644
> --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
> +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
> @@ -13,6 +13,24 @@
>  #include <asm/kvm_emulate.h>
>  #include <asm/kvm_host.h>
>  
> +/*
> + * Under pKVM a host vCPU's ->kvm is host-writable: the nVHE pair
> + * validates it.
> + */
> +#ifdef __KVM_NVHE_HYPERVISOR__
> +struct kvm *vcpu_get_kvm(struct kvm_vcpu *vcpu);
> +void vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm);
> +#else
> +static inline struct kvm *vcpu_get_kvm(struct kvm_vcpu *vcpu)
> +{
> +	return vcpu->kvm;
> +}
> +
> +static inline void vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm)
> +{
> +}
> +#endif
> +
>  static inline void kvm_skip_instr(struct kvm_vcpu *vcpu)
>  {
>  	if (vcpu_mode_is_32bit(vcpu)) {
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index 459bd9eb7e4bc..9bdc7a9b84b8c 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -11,6 +11,8 @@
>  
>  #include <asm/kvm_emulate.h>
>  
> +#include <hyp/adjust_pc.h>
> +
>  #include <nvhe/mem_protect.h>
>  #include <nvhe/memory.h>
>  #include <nvhe/pkvm.h>
> @@ -304,6 +306,43 @@ struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void)
>  
>  }
>  
> +static struct pkvm_hyp_vm *loaded_hyp_vm_of(struct kvm_vcpu *vcpu)

pkvm_get_loaded_hyp_vm()? to align with the other.

> +{
> +	struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
> +
> +	if (hyp_vcpu &&
> +	    (vcpu == &hyp_vcpu->vcpu || vcpu == hyp_vcpu->host_vcpu))
> +		return pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
> +
> +	return NULL;
> +}
> +
> +/* An unloaded host vCPU's VM is mapped at EL2 only while pinned. */

Could we get the last paragraph of the commit here? As this describes quite well
what this is doing.

> +struct kvm *vcpu_get_kvm(struct kvm_vcpu *vcpu)
> +{
> +	struct pkvm_hyp_vm *hyp_vm;
> +	struct kvm *kvm;
> +
> +	if (!is_protected_kvm_enabled())
> +		return kern_hyp_va(vcpu->kvm);
> +
> +	hyp_vm = loaded_hyp_vm_of(vcpu);
> +	if (hyp_vm)
> +		return &hyp_vm->kvm;
> +
> +	kvm = kern_hyp_va(READ_ONCE(vcpu->kvm));
> +	if (hyp_pin_shared_mem(kvm, kvm + 1))
> +		return NULL;
> +
> +	return kvm;
> +}
> +
> +void vcpu_put_kvm(struct kvm_vcpu *vcpu, struct kvm *kvm)
> +{
> +	if (kvm && is_protected_kvm_enabled() && !loaded_hyp_vm_of(vcpu))
> +		hyp_unpin_shared_mem(kvm, kvm + 1);
> +}
> +

It seems strange for pkvm.c to provides function that aren't prefixed with pkvm_
and declared into adjust_pc.h and not pkvm.h. I wonder if adjust_pc.h should't
just

struct kvm *vcpu_get_kvm(struct kvm_vcpu *vcpu)
{
	if (is_protected_kvm_enabled())
		return pkvm_vcpu_get_kvm()
	else
		kern_hyp_va(vcpu->kvm);
}

>  struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
>  {
>  	struct pkvm_hyp_vm *hyp_vm;
> -- 
> 2.39.5
> 

Beside those nits:

Reviewed-by: Vincent Donnefort <vdonnefort at google.com>

-- 
Vincent