From 2c5e168e5ce154592667a8e384012117c917d790 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 27 Nov 2024 17:34:06 -0800 Subject: KVM: x86: Rename "governed features" helpers to use "guest_cpu_cap" As the first step toward replacing KVM's so-called "governed features" framework with a more comprehensive, less poorly named implementation, replace the "kvm_governed_feature" function prefix with "guest_cpu_cap" and rename guest_can_use() to guest_cpu_cap_has(). The "guest_cpu_cap" naming scheme mirrors that of "kvm_cpu_cap", and provides a more clear distinction between guest capabilities, which are KVM controlled (heh, or one might say "governed"), and guest CPUID, which with few exceptions is fully userspace controlled. Opportunistically rewrite the comment about XSS passthrough for SEV-ES guests to avoid referencing so many functions, as such comments are prone to becoming stale (case in point...). No functional change intended. Reviewed-by: Maxim Levitsky Reviewed-by: Binbin Wu Link: https://lore.kernel.org/r/20241128013424.4096668-40-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/nested.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'arch/x86/kvm/svm/nested.c') diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b708bdf7eaff..d77b094d9a4d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -111,7 +111,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm) { - if (!guest_can_use(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) + if (!guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) return true; if (!nested_npt_enabled(svm)) @@ -594,7 +594,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 vmcb_mark_dirty(vmcb02, VMCB_DR); } - if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { /* * Reserved bits of DEBUGCTL are ignored. Be consistent with @@ -651,7 +651,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. */ - if (guest_can_use(vcpu, X86_FEATURE_VGIF) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VGIF) && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK)) int_ctl_vmcb12_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); else @@ -689,7 +689,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR) && svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) nested_svm_update_tsc_ratio_msr(vcpu); @@ -710,7 +710,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * what a nrips=0 CPU would do (L1 is responsible for advancing RIP * prior to injecting the event). */ - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) vmcb02->control.next_rip = svm->nested.ctl.next_rip; else if (boot_cpu_has(X86_FEATURE_NRIPS)) vmcb02->control.next_rip = vmcb12_rip; @@ -720,7 +720,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, svm->soft_int_injected = true; svm->soft_int_csbase = vmcb12_csbase; svm->soft_int_old_rip = vmcb12_rip; - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) svm->soft_int_next_rip = svm->nested.ctl.next_rip; else svm->soft_int_next_rip = vmcb12_rip; @@ -728,18 +728,18 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.virt_ext = vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK; - if (guest_can_use(vcpu, X86_FEATURE_LBRV)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV)) vmcb02->control.virt_ext |= (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - if (guest_can_use(vcpu, X86_FEATURE_PAUSEFILTER)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PAUSEFILTER)) pause_count12 = svm->nested.ctl.pause_filter_count; else pause_count12 = 0; - if (guest_can_use(vcpu, X86_FEATURE_PFTHRESHOLD)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PFTHRESHOLD)) pause_thresh12 = svm->nested.ctl.pause_filter_thresh; else pause_thresh12 = 0; @@ -1026,7 +1026,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (vmcb12->control.exit_code != SVM_EXIT_ERR) nested_save_pending_event_to_vmcb12(svm, vmcb12); - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; @@ -1065,7 +1065,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (!nested_exit_on_intr(svm)) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { svm_copy_lbrs(vmcb12, vmcb02); svm_update_lbrv(vcpu); -- cgit v1.2.3 From 46d6c6f3ef0eaff71c2db6d77d4e2ebb7adac34f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 29 Jan 2025 17:08:25 -0800 Subject: KVM: nSVM: Enter guest mode before initializing nested NPT MMU When preparing vmcb02 for nested VMRUN (or state restore), "enter" guest mode prior to initializing the MMU for nested NPT so that guest_mode is set in the MMU's role. KVM's model is that all L2 MMUs are tagged with guest_mode, as the behavior of hypervisor MMUs tends to be significantly different than kernel MMUs. Practically speaking, the bug is relatively benign, as KVM only directly queries role.guest_mode in kvm_mmu_free_guest_mode_roots() and kvm_mmu_page_ad_need_write_protect(), which SVM doesn't use, and in paths that are optimizations (mmu_page_zap_pte() and shadow_mmu_try_split_huge_pages()). And while the role is incorprated into shadow page usage, because nested NPT requires KVM to be using NPT for L1, reusing shadow pages across L1 and L2 is impossible as L1 MMUs will always have direct=1, while L2 MMUs will have direct=0. Hoist the TLB processing and setting of HF_GUEST_MASK to the beginning of the flow instead of forcing guest_mode in the MMU, as nothing in nested_vmcb02_prepare_control() between the old and new locations touches TLB flush requests or HF_GUEST_MASK, i.e. there's no reason to present inconsistent vCPU state to the MMU. Fixes: 69cb877487de ("KVM: nSVM: move MMU setup to nested_prepare_vmcb_control") Cc: stable@vger.kernel.org Reported-by: Yosry Ahmed Reviewed-by: Yosry Ahmed Link: https://lore.kernel.org/r/20250130010825.220346-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/svm/nested.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86/kvm/svm/nested.c') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 74c20dbb92da..d4ac4a1f8b81 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5540,7 +5540,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, union kvm_mmu_page_role root_role; /* NPT requires CR0.PG=1. */ - WARN_ON_ONCE(cpu_role.base.direct); + WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode); root_role = cpu_role.base; root_role.level = kvm_mmu_get_tdp_level(vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index d77b094d9a4d..04c375bf1ac2 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -646,6 +646,11 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, u32 pause_count12; u32 pause_thresh12; + nested_svm_transition_tlb_flush(vcpu); + + /* Enter Guest-Mode */ + enter_guest_mode(vcpu); + /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. @@ -762,11 +767,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, } } - nested_svm_transition_tlb_flush(vcpu); - - /* Enter Guest-Mode */ - enter_guest_mode(vcpu); - /* * Merge guest and host intercepts - must be called with vcpu in * guest-mode to take effect. -- cgit v1.2.3