Excerpts from Fabiano Rosas's message of March 6, 2021 9:10 am:
> As one of the arguments of the H_ENTER_NESTED hypercall, the nested
> hypervisor (L1) prepares a structure containing the values of various
> hypervisor-privileged registers with which it wants the nested guest
> (L2) to run. Since the nested HV runs in supervisor mode it needs the
> host to write to these registers.
>
> To stop a nested HV manipulating this mechanism and using a nested
> guest as a proxy to access a facility that has been made unavailable
> to it, we have a routine that sanitises the values of the HV registers
> before copying them into the nested guest's vcpu struct.
>
> However, when coming out of the guest the values are copied as they
> were back into L1 memory, which means that any sanitisation we did
> during guest entry will be exposed to L1 after H_ENTER_NESTED returns.
>
> This is not a problem by itself, but in the case of the Hypervisor
> Facility Status and Control Register (HFSCR), we use the intersection
> between L2 hfscr bits and L1 hfscr bits. That means that L1 could use
> this to indirectly read the (hv-privileged) value from its vcpu
> struct.
>
> This patch fixes this by making sure that L1 only gets back the bits
> that are necessary for regular functioning.
The general idea of restricting exposure of HV privileged bits, but
for the case of HFSCR a guest can probe the HFCR anyway by testing which
facilities are available (and presumably an HV may need some way to know
what features are available for it to advertise to its own guests), so
is this necessary? Perhaps a comment would be sufficient.
Thanks,
Nick
>
> Signed-off-by: Fabiano Rosas <farosas@xxxxxxxxxxxxx>
> ---
> arch/powerpc/kvm/book3s_hv_nested.c | 22 +++++++++++++++++-----
> 1 file changed, 17 insertions(+), 5 deletions(-)
>
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 0cd0e7aad588..860004f46e08 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -98,12 +98,20 @@ static void byteswap_hv_regs(struct hv_guest_state *hr)
> }
>
> static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
> - struct hv_guest_state *hr)
> + struct hv_guest_state *hr, u64 saved_hfscr)
> {
> struct kvmppc_vcore *vc = vcpu->arch.vcore;
>
> + /*
> + * During sanitise_hv_regs() we used HFSCR bits from L1 state
> + * to restrict what the L2 state is allowed to be. Since L1 is
> + * not allowed to read this SPR, do not include these
> + * modifications in the return state.
> + */
> + hr->hfscr = ((~HFSCR_INTR_CAUSE & saved_hfscr) |
> + (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
> +
> hr->dpdes = vc->dpdes;
> - hr->hfscr = vcpu->arch.hfscr;
> hr->purr = vcpu->arch.purr;
> hr->spurr = vcpu->arch.spurr;
> hr->ic = vcpu->arch.ic;
> @@ -132,12 +140,14 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
> }
> }
>
> -static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
> +static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr,
> + u64 *saved_hfscr)
> {
> /*
> * Don't let L1 enable features for L2 which we've disabled for L1,
> * but preserve the interrupt cause field.
> */
> + *saved_hfscr = hr->hfscr;
> hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
>
> /* Don't let data address watchpoint match in hypervisor state */
> @@ -272,6 +282,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
> u64 hdec_exp;
> s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
> u64 mask;
> + u64 hfscr;
> unsigned long lpcr;
>
> if (vcpu->kvm->arch.l1_ptcr == 0)
> @@ -324,7 +335,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
> mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
> LPCR_LPES | LPCR_MER;
> lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
> - sanitise_hv_regs(vcpu, &l2_hv);
> +
> + sanitise_hv_regs(vcpu, &l2_hv, &hfscr);
> restore_hv_regs(vcpu, &l2_hv);
>
> vcpu->arch.ret = RESUME_GUEST;
> @@ -345,7 +357,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
> delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
> delta_ic = vcpu->arch.ic - l2_hv.ic;
> delta_vtb = vc->vtb - l2_hv.vtb;
> - save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
> + save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv, hfscr);
>
> /* restore L1 state */
> vcpu->arch.nested = NULL;
> --
> 2.29.2
>
>
