[PATCH 05/17] KVM: arm64: Skip fixed-feature state flush for protected vCPUs

[Vincent Donnefort]

On Mon, Aug 31, 2026 at 05:34:09PM +0100, Fuad Tabba wrote:
> flush_hyp_vcpu() copies the host's mdcr_el2, TWI/TWE and debug state
> into the hyp vCPU on every entry, so for a protected vCPU the host's
> trap configuration overrides the one pkvm_vcpu_init_traps() computed
> at EL2. Move those copies into the non-protected branch, and sync the
> debug state back for non-protected vCPUs only: a protected guest's
> debug registers are hypervisor-owned, and it takes the host's TWI/TWE
> at vCPU load. MDCR_EL2.TDA traps only the guest's own accesses; it
> does not stop the world switch from loading host-supplied breakpoints
> and MDSCR_EL1.
> 
> EL2's mdcr_el2 starts from 0, and HPMN == 0 is reserved without
> FEAT_HPMN0. Set HPMN to the CPU's event counter count at vCPU load,
> the value the host's copy carried; a protected guest's PMU accesses
> trap regardless.
> 
> Signed-off-by: Fuad Tabba <fuad.tabba at linux.dev>
> ---
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c | 31 +++++++++++++++++++-----------
>  arch/arm64/kvm/hyp/nvhe/pkvm.c     |  2 +-
>  2 files changed, 21 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index ca7122b0bccdd..14e847b122abf 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -231,7 +231,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>  	u8 esr_ec;
>  
>  	fpsimd_sve_flush();
> -	flush_debug_state(hyp_vcpu);
>  
>  	/*
>  	 * If we deal with a non-protected guest and the state is potentially
> @@ -241,7 +240,14 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>  	if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu)) {
>  		if (vcpu_get_flag(host_vcpu, PKVM_HOST_STATE_DIRTY))
>  			flush_hyp_vcpu_state(hyp_vcpu);
> +
> +		hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
> +		hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
> +							 (HCR_TWI | HCR_TWE);
> +
> +		hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2;
>  		hyp_vcpu->vcpu.arch.iflags = host_vcpu->arch.iflags;
> +		flush_debug_state(hyp_vcpu);
>  	} else {
>  		hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt;
>  	}
> @@ -249,17 +255,13 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>  	/* __hyp_running_vcpu must be NULL in a guest context. */
>  	hyp_vcpu->vcpu.arch.ctxt.__hyp_running_vcpu = NULL;
>  
> -	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
>  	/*
> -	 * HCR_EL2.VSE is host-owned (a pending virtual SError to inject), not a
> -	 * trap-control bit, so it must flow to the hyp vCPU alongside TWI/TWE
> -	 * for the vSError to be delivered. sync_hyp_vcpu() reflects it back.
> +	 * A host-injected vSError is masked by the guest's own PSTATE.A, so it
> +	 * applies to protected guests too.
>  	 */
> -	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE | HCR_VSE);
> -	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
> -						 (HCR_TWI | HCR_TWE | HCR_VSE);
> -
> -	hyp_vcpu->vcpu.arch.vsesr_el2	= host_vcpu->arch.vsesr_el2;
> +	hyp_vcpu->vcpu.arch.hcr_el2 &= ~HCR_VSE;
> +	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) & HCR_VSE;
> +	hyp_vcpu->vcpu.arch.vsesr_el2 = host_vcpu->arch.vsesr_el2;
>  
>  	flush_hyp_vgic_state(hyp_vcpu);
>  
> @@ -288,7 +290,8 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, u32 exit_reason)
>  	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
>  
>  	fpsimd_sve_sync(&hyp_vcpu->vcpu);
> -	sync_debug_state(hyp_vcpu);
> +	if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu))
> +		sync_debug_state(hyp_vcpu);

nit: We can't use the else arm below?

>  
>  	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) {
>  		host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt;
> @@ -329,6 +332,12 @@ static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt)
>  		/* Propagate WFx trapping flags */
>  		hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI);
>  		hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI);
> +
> +		/* HPMN == 0 is reserved without FEAT_HPMN0. */
> +		if (system_supports_pmuv3())
> +			u64p_replace_bits(&hyp_vcpu->vcpu.arch.mdcr_el2,
> +					  FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)),
> +					  MDCR_EL2_HPMN);
>  	} else {
>  		memcpy(&hyp_vcpu->vcpu.arch.fgt, hyp_vcpu->host_vcpu->arch.fgt,
>  		       sizeof(hyp_vcpu->vcpu.arch.fgt));
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index 459bd9eb7e4bc..e85f13233da08 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -102,7 +102,7 @@ static void pvm_init_traps_mdcr(struct kvm_vcpu *vcpu)
>  
>  	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) {
>  		val |= MDCR_EL2_TPM | MDCR_EL2_TPMCR;
> -		val &= ~(MDCR_EL2_HPME | MDCR_EL2_MTPME | MDCR_EL2_HPMN_MASK);
> +		val &= ~(MDCR_EL2_HPME | MDCR_EL2_MTPME);
>  	}
>  
>  	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, IMP))
> -- 
> 2.39.5
>