From 7487cabc7ed2f7716bf304e4e97c57fd995cf70e Mon Sep 17 00:00:00 2001 From: Fabiano Rosas Date: Thu, 12 Aug 2021 02:00:39 +1000 Subject: [PATCH] KVM: PPC: Book3S HV Nested: Sanitise vcpu registers 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 patch alters this sanitisation to have effect on the vcpu->arch registers directly before entering and after exiting the guest, leaving the structure that is copied back into L1 unchanged (except when we really want L1 to access the value, e.g the Cause bits of HFSCR). Signed-off-by: Fabiano Rosas Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Reviewed-by: Nicholas Piggin Link: https://lore.kernel.org/r/20210811160134.904987-6-npiggin@gmail.com --- arch/powerpc/kvm/book3s_hv_nested.c | 94 ++++++++++++++++++------------------- 1 file changed, 46 insertions(+), 48 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 898f942..1eb4e98 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -105,7 +105,6 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap, struct kvmppc_vcore *vc = vcpu->arch.vcore; hr->dpdes = vc->dpdes; - hr->hfscr = vcpu->arch.hfscr; hr->purr = vcpu->arch.purr; hr->spurr = vcpu->arch.spurr; hr->ic = vcpu->arch.ic; @@ -128,55 +127,17 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap, case BOOK3S_INTERRUPT_H_INST_STORAGE: hr->asdr = vcpu->arch.fault_gpa; break; + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: + hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) | + (HFSCR_INTR_CAUSE & vcpu->arch.hfscr)); + break; case BOOK3S_INTERRUPT_H_EMUL_ASSIST: hr->heir = vcpu->arch.emul_inst; break; } } -/* - * This can result in some L0 HV register state being leaked to an L1 - * hypervisor when the hv_guest_state is copied back to the guest after - * being modified here. - * - * There is no known problem with such a leak, and in many cases these - * register settings could be derived by the guest by observing behaviour - * and timing, interrupts, etc., but it is an issue to consider. - */ -static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr) -{ - struct kvmppc_vcore *vc = vcpu->arch.vcore; - u64 mask; - - /* - * Don't let L1 change LPCR bits for the L2 except these: - */ - mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD | - LPCR_LPES | LPCR_MER; - - /* - * Additional filtering is required depending on hardware - * and configuration. - */ - hr->lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm, - (vc->lpcr & ~mask) | (hr->lpcr & mask)); - - /* - * Don't let L1 enable features for L2 which we've disabled for L1, - * but preserve the interrupt cause field. - */ - hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr); - - /* Don't let data address watchpoint match in hypervisor state */ - hr->dawrx0 &= ~DAWRX_HYP; - hr->dawrx1 &= ~DAWRX_HYP; - - /* Don't let completed instruction address breakpt match in HV state */ - if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) - hr->ciabr &= ~CIABR_PRIV; -} - -static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr) +static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *hr) { struct kvmppc_vcore *vc = vcpu->arch.vcore; @@ -288,6 +249,43 @@ static int kvmhv_write_guest_state_and_regs(struct kvm_vcpu *vcpu, sizeof(struct pt_regs)); } +static void load_l2_hv_regs(struct kvm_vcpu *vcpu, + const struct hv_guest_state *l2_hv, + const struct hv_guest_state *l1_hv, u64 *lpcr) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + u64 mask; + + restore_hv_regs(vcpu, l2_hv); + + /* + * Don't let L1 change LPCR bits for the L2 except these: + */ + mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD | + LPCR_LPES | LPCR_MER; + + /* + * Additional filtering is required depending on hardware + * and configuration. + */ + *lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm, + (vc->lpcr & ~mask) | (*lpcr & mask)); + + /* + * Don't let L1 enable features for L2 which we've disabled for L1, + * but preserve the interrupt cause field. + */ + vcpu->arch.hfscr = l2_hv->hfscr & (HFSCR_INTR_CAUSE | vcpu->arch.hfscr); + + /* Don't let data address watchpoint match in hypervisor state */ + vcpu->arch.dawrx0 = l2_hv->dawrx0 & ~DAWRX_HYP; + vcpu->arch.dawrx1 = l2_hv->dawrx1 & ~DAWRX_HYP; + + /* Don't let completed instruction address breakpt match in HV state */ + if ((l2_hv->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) + vcpu->arch.ciabr = l2_hv->ciabr & ~CIABR_PRIV; +} + long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) { long int err, r; @@ -296,7 +294,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) struct hv_guest_state l2_hv = {0}, saved_l1_hv; struct kvmppc_vcore *vc = vcpu->arch.vcore; u64 hv_ptr, regs_ptr; - u64 hdec_exp; + u64 hdec_exp, lpcr; s64 delta_purr, delta_spurr, delta_ic, delta_vtb; if (vcpu->kvm->arch.l1_ptcr == 0) @@ -369,8 +367,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* Guest must always run with ME enabled, HV disabled. */ vcpu->arch.shregs.msr = (vcpu->arch.regs.msr | MSR_ME) & ~MSR_HV; - sanitise_hv_regs(vcpu, &l2_hv); - restore_hv_regs(vcpu, &l2_hv); + lpcr = l2_hv.lpcr; + load_l2_hv_regs(vcpu, &l2_hv, &saved_l1_hv, &lpcr); vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; @@ -380,7 +378,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) r = RESUME_HOST; break; } - r = kvmhv_run_single_vcpu(vcpu, hdec_exp, l2_hv.lpcr); + r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr); } while (is_kvmppc_resume_guest(r)); /* save L2 state for return */ -- 2.7.4