4.9-stable review patch. If anyone has any objections, please let me know.
------------------ From: KarimAllah Ahmed <karah...@amazon.de> (cherry picked from commit d28b387fb74da95d69d2615732f50cceb38e9a4d) [ Based on a patch from Ashok Raj <ashok....@intel.com> ] Add direct access to MSR_IA32_SPEC_CTRL for guests. This is needed for guests that will only mitigate Spectre V2 through IBRS+IBPB and will not be using a retpoline+IBPB based approach. To avoid the overhead of saving and restoring the MSR_IA32_SPEC_CTRL for guests that do not actually use the MSR, only start saving and restoring when a non-zero is written to it. No attempt is made to handle STIBP here, intentionally. Filtering STIBP may be added in a future patch, which may require trapping all writes if we don't want to pass it through directly to the guest. [dwmw2: Clean up CPUID bits, save/restore manually, handle reset] Signed-off-by: KarimAllah Ahmed <karah...@amazon.de> Signed-off-by: David Woodhouse <d...@amazon.co.uk> Signed-off-by: Thomas Gleixner <t...@linutronix.de> Reviewed-by: Darren Kenny <darren.ke...@oracle.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.w...@oracle.com> Reviewed-by: Jim Mattson <jmatt...@google.com> Cc: Andrea Arcangeli <aarca...@redhat.com> Cc: Andi Kleen <a...@linux.intel.com> Cc: Jun Nakajima <jun.nakaj...@intel.com> Cc: k...@vger.kernel.org Cc: Dave Hansen <dave.han...@intel.com> Cc: Tim Chen <tim.c.c...@linux.intel.com> Cc: Andy Lutomirski <l...@kernel.org> Cc: Asit Mallick <asit.k.mall...@intel.com> Cc: Arjan Van De Ven <arjan.van.de....@intel.com> Cc: Greg KH <gre...@linuxfoundation.org> Cc: Paolo Bonzini <pbonz...@redhat.com> Cc: Dan Williams <dan.j.willi...@intel.com> Cc: Linus Torvalds <torva...@linux-foundation.org> Cc: Ashok Raj <ashok....@intel.com> Link: https://lkml.kernel.org/r/1517522386-18410-5-git-send-email-karah...@amazon.de Signed-off-by: David Woodhouse <d...@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org> --- arch/x86/kvm/cpuid.c | 8 ++- arch/x86/kvm/cpuid.h | 11 +++++ arch/x86/kvm/vmx.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 2 4 files changed, 118 insertions(+), 6 deletions(-) --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -357,7 +357,7 @@ static inline int __do_cpuid_ent(struct /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(IBPB); + F(IBPB) | F(IBRS); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -382,7 +382,7 @@ static inline int __do_cpuid_ent(struct /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - F(ARCH_CAPABILITIES); + F(SPEC_CTRL) | F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -618,9 +618,11 @@ static inline int __do_cpuid_ent(struct g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - /* IBPB isn't necessarily present in hardware cpuid */ + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ if (boot_cpu_has(X86_FEATURE_IBPB)) entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -171,6 +171,17 @@ static inline bool guest_cpuid_has_ibpb( return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); } +static inline bool guest_cpuid_has_ibrs(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBRS))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -552,6 +552,7 @@ struct vcpu_vmx { #endif u64 arch_capabilities; + u64 spec_ctrl; u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; @@ -1852,6 +1853,29 @@ static void update_exception_bitmap(stru } /* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* * Check if MSR is intercepted for L01 MSR bitmap. */ static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) @@ -2981,6 +3005,13 @@ static int vmx_get_msr(struct kvm_vcpu * case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated && !guest_cpuid_has_arch_capabilities(vcpu)) @@ -3091,6 +3122,36 @@ static int vmx_set_msr(struct kvm_vcpu * case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && !guest_cpuid_has_ibpb(vcpu)) @@ -5239,6 +5300,7 @@ static void vmx_vcpu_reset(struct kvm_vc u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->soft_vnmi_blocked = 0; @@ -8824,6 +8886,15 @@ static void __noclone vmx_vcpu_run(struc vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -8942,6 +9013,27 @@ static void __noclone vmx_vcpu_run(struc #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -9501,7 +9593,7 @@ static inline bool nested_vmx_merge_msr_ unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; /* - * pred_cmd is trying to verify two things: + * pred_cmd & spec_ctrl are trying to verify two things: * * 1. L0 gave a permission to L1 to actually passthrough the MSR. This * ensures that we do not accidentally generate an L02 MSR bitmap @@ -9514,9 +9606,10 @@ static inline bool nested_vmx_merge_msr_ * the MSR. */ bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && - !pred_cmd) + !pred_cmd && !spec_ctrl) return false; page = nested_get_page(vcpu, vmcs12->msr_bitmap); @@ -9550,6 +9643,12 @@ static inline bool nested_vmx_merge_msr_ } } + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + if (pred_cmd) nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,7 +975,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_ARCH_CAPABILITIES + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save;
