When nested NPT is enabled and KVM_SET_NESTED_STATE is used to restore an old checkpoint (without a valid gPAT), the current IA32_PAT value must be used as L2's gPAT. Unfortunately, checkpoint restore is non-atomic, and the order in which state components are restored is not specified. Hence, the current IA32_PAT value may be restored by KVM_SET_MSRS after KVM_SET_NESTED_STATE. To further complicate matters, there may be a KVM_GET_NESTED_STATE before the next KVM_RUN. Introduce a new boolean, svm->nested.legacy_gpat_semantics. When set, hPAT updates are also applied to gPAT, preserving the old behavior (i.e. L2 shares L1's PAT). Set this boolean when restoring legacy state (i.e. nested NPT is enabled, but no GPAT is provided) in KVM_SET_NESTED_STATE. Clear this boolean in svm_vcpu_pre_run(), to ensure that hPAT and gPAT are decoupled before the vCPU resumes execution. Also clear this boolean when the vCPU is forced out of guest mode by svm_leave_nested(). Signed-off-by: Jim Mattson --- arch/x86/kvm/svm/nested.c | 13 ++++++++++--- arch/x86/kvm/svm/svm.c | 8 ++++++-- arch/x86/kvm/svm/svm.h | 9 +++++++++ 3 files changed, 25 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 5a35277f2364..b68eddcbc217 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1537,6 +1537,7 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; svm->nested.vmcb12_gpa = INVALID_GPA; + svm->nested.legacy_gpat_semantics = false; leave_guest_mode(vcpu); @@ -2075,9 +2076,15 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm_switch_vmcb(svm, &svm->nested.vmcb02); - if (nested_npt_enabled(svm) && - (kvm_state->hdr.svm.flags & KVM_STATE_SVM_VALID_GPAT)) - vmcb_set_gpat(svm->vmcb, kvm_state->hdr.svm.gpat); + svm->nested.legacy_gpat_semantics = + nested_npt_enabled(svm) && + !(kvm_state->hdr.svm.flags & KVM_STATE_SVM_VALID_GPAT); + if (nested_npt_enabled(svm)) { + u64 g_pat = svm->nested.legacy_gpat_semantics ? + vcpu->arch.pat : kvm_state->hdr.svm.gpat; + + vmcb_set_gpat(svm->nested.vmcb02.ptr, g_pat); + } nested_vmcb02_prepare_control(svm, svm->vmcb->save.rip, svm->vmcb->save.cs.base); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 00dba10991a5..ac45702f566e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2727,7 +2727,8 @@ static bool svm_pat_accesses_gpat(struct kvm_vcpu *vcpu, bool from_host) * with older kernels. */ WARN_ON_ONCE(from_host && vcpu->wants_to_run); - return !from_host && is_guest_mode(vcpu) && nested_npt_enabled(svm); + return !svm->nested.legacy_gpat_semantics && !from_host && + is_guest_mode(vcpu) && nested_npt_enabled(svm); } static u64 svm_get_pat(struct kvm_vcpu *vcpu, bool from_host) @@ -2749,7 +2750,8 @@ static void svm_set_pat(struct kvm_vcpu *vcpu, bool from_host, u64 data) if (npt_enabled) { vmcb_set_gpat(svm->vmcb01.ptr, data); if (is_guest_mode(&svm->vcpu) && - !nested_npt_enabled(svm)) + (svm->nested.legacy_gpat_semantics || + !nested_npt_enabled(svm))) vmcb_set_gpat(svm->vmcb, data); } } @@ -4262,6 +4264,8 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) if (to_kvm_sev_info(vcpu->kvm)->need_init) return -EINVAL; + to_svm(vcpu)->nested.legacy_gpat_semantics = false; + return 1; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 58b0b935d049..626efef878a5 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -238,6 +238,15 @@ struct svm_nested_state { * on its side. */ bool force_msr_bitmap_recalc; + + /* + * Indicates that a legacy nested state (without a valid gPAT) was + * recently restored. Until the next KVM_RUN, updates to hPAT are + * also applied to gPAT, preserving legacy behavior (i.e. L2 shares + * L1's PAT). Because checkpoint restore is non-atomic, this + * complication is necessary for backward compatibility. + */ + bool legacy_gpat_semantics; }; struct vcpu_sev_es_state { -- 2.53.0.371.g1d285c8824-goog