diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 8a9d2314d67c..69631309b6af 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3822,6 +3822,72 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) } } +/* call our hypervisor to load up HV regs and go */ +static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long host_psscr; + struct hv_guest_state hvregs; + int trap; + s64 dec; + + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_vcpu_entry_p9() below otherwise. + */ + host_psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); + kvmhv_save_hv_regs(vcpu, &hvregs); + hvregs.lpcr = lpcr; + vcpu->arch.regs.msr = vcpu->arch.shregs.msr; + hvregs.version = HV_GUEST_STATE_VERSION; + if (vcpu->arch.nested) { + hvregs.lpid = vcpu->arch.nested->shadow_lpid; + hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; + } else { + hvregs.lpid = vcpu->kvm->arch.lpid; + hvregs.vcpu_token = vcpu->vcpu_id; + } + hvregs.hdec_expiry = time_limit; + + /* + * When setting DEC, we must always deal with irq_work_raise + * via NMI vs setting DEC. The problem occurs right as we + * switch into guest mode if a NMI hits and sets pending work + * and sets DEC, then that will apply to the guest and not + * bring us back to the host. + * + * irq_work_raise could check a flag (or possibly LPCR[HDICE] + * for example) and set HDEC to 1? That wouldn't solve the + * nested hv case which needs to abort the hcall or zero the + * time limit. + * + * XXX: Another day's problem. + */ + mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb); + + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); + trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), + __pa(&vcpu->arch.regs)); + kvmhv_restore_hv_return_state(vcpu, &hvregs); + vcpu->arch.shregs.msr = vcpu->arch.regs.msr; + vcpu->arch.shregs.dar = mfspr(SPRN_DAR); + vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, host_psscr); + + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset); + + return trap; +} + /* * Guest entry for POWER9 and later CPUs. */ @@ -3830,7 +3896,6 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, { struct kvmppc_vcore *vc = vcpu->arch.vcore; struct p9_host_os_sprs host_os_sprs; - s64 dec; u64 next_timer; unsigned long msr; int trap; @@ -3883,63 +3948,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, switch_pmu_to_guest(vcpu, &host_os_sprs); if (kvmhv_on_pseries()) { - /* - * We need to save and restore the guest visible part of the - * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor - * doesn't do this for us. Note only required if pseries since - * this is done in kvmhv_vcpu_entry_p9() below otherwise. - */ - unsigned long host_psscr; - /* call our hypervisor to load up HV regs and go */ - struct hv_guest_state hvregs; - - host_psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); - kvmhv_save_hv_regs(vcpu, &hvregs); - hvregs.lpcr = lpcr; - vcpu->arch.regs.msr = vcpu->arch.shregs.msr; - hvregs.version = HV_GUEST_STATE_VERSION; - if (vcpu->arch.nested) { - hvregs.lpid = vcpu->arch.nested->shadow_lpid; - hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; - } else { - hvregs.lpid = vcpu->kvm->arch.lpid; - hvregs.vcpu_token = vcpu->vcpu_id; - } - hvregs.hdec_expiry = time_limit; - - /* - * When setting DEC, we must always deal with irq_work_raise - * via NMI vs setting DEC. The problem occurs right as we - * switch into guest mode if a NMI hits and sets pending work - * and sets DEC, then that will apply to the guest and not - * bring us back to the host. - * - * irq_work_raise could check a flag (or possibly LPCR[HDICE] - * for example) and set HDEC to 1? That wouldn't solve the - * nested hv case which needs to abort the hcall or zero the - * time limit. - * - * XXX: Another day's problem. - */ - mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb); - - mtspr(SPRN_DAR, vcpu->arch.shregs.dar); - mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); - trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), - __pa(&vcpu->arch.regs)); - kvmhv_restore_hv_return_state(vcpu, &hvregs); - vcpu->arch.shregs.msr = vcpu->arch.regs.msr; - vcpu->arch.shregs.dar = mfspr(SPRN_DAR); - vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); - vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, host_psscr); - - dec = mfspr(SPRN_DEC); - if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ - dec = (s32) dec; - *tb = mftb(); - vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset); + trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&