[PATCH v2 06/17] KVM: arm64: Add system register reset framework for protected VMs
Fuad Tabba
fuad.tabba at linux.dev
Thu Sep 10 03:05:56 PDT 2026
Hi Joey,
On Wed, 9 Sept 2026 at 14:51, Joey Gouly <joey.gouly at arm.com> wrote:
>
> Hi Fuad,
>
> On Mon, Sep 07, 2026 at 07:59:51AM +0100, Fuad Tabba wrote:
> > Add kvm_reset_pvm_sys_regs() and the pvm_sys_reg_reset_vals[] table
> > that drives it, and call it from init_pkvm_hyp_vcpu() for protected
> > vCPUs. The table holds the registers sys_regs.c resets that
> > __sysreg_restore_state_nvhe() loads for a protected vCPU. The rest of
> > the context keeps the zero the donated hyp vCPU page is cleared to. A
>
> If the context is zero'd, why is there RESET_ZERO()? If it's just for
> 'completeness', worth noting here.
I'll answer your question with part of the updated commit message for V3:
A register that resets to 0 still needs an entry: a later patch calls
kvm_reset_pvm_sys_regs() again for PSCI CPU_ON at EL2, on a context
that has run.
>
> > poison value stands in where sys_regs.c resets to UNKNOWN, and for
> > VBAR_EL1 and CONTEXTIDR_EL1 in place of the 0 it uses. MPIDR_EL1 is
> > derived from vcpu_id, as for any KVM guest. AMAIR_EL1 resets to 0
> > where sys_regs.c reads the hardware: the host writes it freely before
> > the hypercall, and it's loaded on every guest entry.
>
> Also if you can just put a new line for each 'category' here would make
> it simpler to read.
Done for V3.
>
> >
> > Until the per-EC marshalling patch removes the host's full-context
> > copy from flush_hyp_vcpu(), that copy overwrites these values on every
> > entry, so this patch has no observable effect on its own.
>
> Thanks for adding this!
Thank you for your reviews. They've been very helpful!
Cheers,
/fuad
>
> >
> > Signed-off-by: Fuad Tabba <fuad.tabba at linux.dev>
> > ---
> > arch/arm64/kvm/hyp/include/nvhe/pkvm.h | 1 +
> > arch/arm64/kvm/hyp/nvhe/pkvm.c | 5 ++
> > arch/arm64/kvm/hyp/nvhe/sys_regs.c | 73 ++++++++++++++++++++++++--
> > 3 files changed, 75 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> > index 49a0a992047ba..a04b7c04d5135 100644
> > --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> > +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> > @@ -95,6 +95,7 @@ bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code);
> > bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code);
> > bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code);
> > void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu);
> > +void kvm_reset_pvm_sys_regs(struct kvm_vcpu *vcpu);
> > int kvm_check_pvm_sysreg_table(void);
> >
> > #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
> > diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> > index e85f13233da08..af334318d0a03 100644
> > --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> > +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> > @@ -551,6 +551,11 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
> > goto done;
> >
> > ret = pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
> > + if (ret)
> > + goto done;
> > +
> > + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
> > + kvm_reset_pvm_sys_regs(&hyp_vcpu->vcpu);
> > done:
> > if (ret)
> > unpin_host_vcpu(host_vcpu);
> > diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
> > index 8758c68017765..03d2c2447e0fd 100644
> > --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
> > +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
> > @@ -525,6 +525,66 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
> > /* Performance Monitoring Registers are restricted. */
> > };
> >
> > +struct sys_reg_desc_reset {
> > + int reg;
> > + void (*reset)(struct kvm_vcpu *vcpu, const struct sys_reg_desc_reset *rd);
> > + u64 value;
> > +};
> > +
> > +static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc_reset *r)
> > +{
> > + __vcpu_assign_sys_reg(vcpu, r->reg, kvm_calculate_mpidr(vcpu));
> > +}
> > +
> > +static void reset_value(struct kvm_vcpu *vcpu, const struct sys_reg_desc_reset *r)
> > +{
> > + __vcpu_assign_sys_reg(vcpu, r->reg, r->value);
> > +}
> > +
> > +#define RESET_VAL(REG, RESET_VAL) { REG, reset_value, RESET_VAL }
> > +
> > +#define RESET_ZERO(REG) RESET_VAL(REG, 0)
> > +
> > +#define RESET_UNKNOWN(REG) RESET_VAL(REG, 0x1de7ec7edbadc0deULL)
> > +
> > +#define RESET_FUNC(REG, RESET_FUNC) { REG, RESET_FUNC, 0 }
> > +
> > +/* Sorted ascending by reg; kvm_check_pvm_sysreg_table() enforces it. */
> > +static const struct sys_reg_desc_reset pvm_sys_reg_reset_vals[] = {
> > + RESET_FUNC(MPIDR_EL1, reset_mpidr),
> > + RESET_UNKNOWN(TPIDR_EL0),
> > + RESET_UNKNOWN(TPIDRRO_EL0),
> > + RESET_UNKNOWN(TPIDR_EL1),
> > + RESET_ZERO(CNTKCTL_EL1),
> > + RESET_UNKNOWN(PAR_EL1),
> > + RESET_ZERO(DISR_EL1),
> > + RESET_ZERO(CPACR_EL1),
> > + RESET_VAL(CONTEXTIDR_EL1, 0x00000000dbadc0deULL),
> > + RESET_VAL(SCTLR_EL1, 0x00C50078ULL),
> > + RESET_ZERO(TCR_EL1),
> > + RESET_UNKNOWN(AFSR0_EL1),
> > + RESET_UNKNOWN(AFSR1_EL1),
> > + RESET_UNKNOWN(ESR_EL1),
> > + RESET_UNKNOWN(MAIR_EL1),
> > + RESET_ZERO(AMAIR_EL1),
> > + RESET_ZERO(MDSCR_EL1),
> > + RESET_UNKNOWN(TTBR0_EL1),
> > + RESET_UNKNOWN(TTBR1_EL1),
> > + RESET_UNKNOWN(FAR_EL1),
> > + RESET_VAL(VBAR_EL1, 0x1de7ec7edbadc000ULL),
> > +};
> > +
> > +void kvm_reset_pvm_sys_regs(struct kvm_vcpu *vcpu)
> > +{
> > + unsigned long i;
> > +
> > + for (i = 0; i < ARRAY_SIZE(pvm_sys_reg_reset_vals); i++) {
> > + const struct sys_reg_desc_reset *r = &pvm_sys_reg_reset_vals[i];
> > +
> > + r->reset(vcpu, r);
> > + }
> > +}
> > +
> > /*
> > * Initializes feature registers for protected vms.
> > */
> > @@ -550,16 +610,21 @@ void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu)
> > }
> >
> > /*
> > - * Checks that the sysreg table is unique and in-order.
> > - *
> > - * Returns 0 if the table is consistent, or 1 otherwise.
> > + * Both tables must be unique and sorted ascending. pvm_sys_reg_descs.reg is the
> > + * sys_reg() encoding, pvm_sys_reg_reset_vals.reg the vcpu_sysreg index, so they
> > + * compare differently. BUG_ON() at __pkvm_init: fatal at boot.
> > */
> > int kvm_check_pvm_sysreg_table(void)
> > {
> > unsigned int i;
> >
> > for (i = 1; i < ARRAY_SIZE(pvm_sys_reg_descs); i++) {
> > - if (cmp_sys_reg(&pvm_sys_reg_descs[i-1], &pvm_sys_reg_descs[i]) >= 0)
> > + if (cmp_sys_reg(&pvm_sys_reg_descs[i - 1], &pvm_sys_reg_descs[i]) >= 0)
> > + return 1;
> > + }
> > +
> > + for (i = 1; i < ARRAY_SIZE(pvm_sys_reg_reset_vals); i++) {
> > + if (pvm_sys_reg_reset_vals[i - 1].reg >= pvm_sys_reg_reset_vals[i].reg)
> > return 1;
> > }
> >
>
> Some minor commit message nits, and I see you're going to remove this
> sorting check.
>
> Reviewed-by: Joey Gouly <joey.gouly at arm.com>
>
> Thanks,
> Joey
More information about the linux-arm-kernel
mailing list