The original IBRS hack in microcode is horribly slow. For the next generation of CPUs, as a stopgap until we get a proper fix, Intel promise an "Enhanced IBRS" which will be fast. The assumption is that predictions in the BTB/RSB will be tagged with the VMX mode and ring that they were learned in, and thus the CPU will avoid consuming unsafe predictions without a performance penalty. Intel's documentation says that it is still required to set the IBRS bit in the SPEC_CTRL MSR and ensure that it remains set. Cope with this by trapping and emulating *all* access to SPEC_CTRL from KVM guests when the IBRS_ALL feature is present, so it can never be turned off. Guests who see IBRS_ALL should never do anything except turn it on at boot anyway. And if they didn't know about IBRS_ALL and they keep frobbing IBRS on every kernel entry/exit... well the vmexit for a no-op is probably going to be faster than they were expecting anyway, so they'll live. Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx> Acked-by: Arjan van de Ven <arjan.van.de.ven@xxxxxxxxx> --- arch/x86/include/asm/nospec-branch.h | 9 ++++++++- arch/x86/kernel/cpu/bugs.c | 17 +++++++++++++++-- arch/x86/kvm/vmx.c | 31 +++++++++++++++++++------------ 3 files changed, 42 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 0995c6a..34cbce3 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -141,9 +141,16 @@ enum spectre_v2_mitigation { SPECTRE_V2_RETPOLINE_MINIMAL_AMD, SPECTRE_V2_RETPOLINE_GENERIC, SPECTRE_V2_RETPOLINE_AMD, - SPECTRE_V2_IBRS, + SPECTRE_V2_IBRS_ALL, }; +extern enum spectre_v2_mitigation spectre_v2_enabled; + +static inline bool spectre_v2_ibrs_all(void) +{ + return spectre_v2_enabled == SPECTRE_V2_IBRS_ALL; +} + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bfca937..505c467 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -88,12 +88,14 @@ static const char *spectre_v2_strings[] = { [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", + [SPECTRE_V2_IBRS_ALL] = "Mitigation: Enhanced IBRS", }; #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt -static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +EXPORT_SYMBOL_GPL(spectre_v2_enabled); #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -237,6 +239,16 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { + u64 ia32_cap = 0; + + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + if (ia32_cap & ARCH_CAP_IBRS_ALL) { + mode = SPECTRE_V2_IBRS_ALL; + wrmsrl(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS); + goto ibrs_all; + } + } if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_auto; break; @@ -274,6 +286,7 @@ static void __init spectre_v2_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RETPOLINE); } + ibrs_all: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -305,7 +318,7 @@ static void __init spectre_v2_select_mitigation(void) * Retpoline means the kernel is safe because it has no indirect * branches. But firmware isn't, so use IBRS to protect that. */ - if (boot_cpu_has(X86_FEATURE_IBRS)) { + if (mode != SPECTRE_V2_IBRS_ALL && boot_cpu_has(X86_FEATURE_IBRS)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 91e3539..62ad7e3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3419,13 +3419,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx->spec_ctrl = data; - if (!data) + if (!data && !spectre_v2_ibrs_all()) break; /* * For non-nested: * When it's written (to non-zero) for the first time, pass - * it through. + * it through unless we have IBRS_ALL and it should just be + * set for ever. * * For nested: * The handling of the MSR bitmap for L2 guests is done in @@ -9441,7 +9442,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (vmx->spec_ctrl) + if (!spectre_v2_ibrs_all() && vmx->spec_ctrl) wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); vmx->__launched = vmx->loaded_vmcs->launched; @@ -9563,11 +9564,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) ); /* - * 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. + * Without IBRS_ALL, 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 @@ -9576,12 +9578,17 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * For nested case: * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. + * + * If IBRS_ALL is present then the whole thing is a no-op fiction + * for guests and every access is trapped, so do nothing. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + if (!spectre_v2_ibrs_all()) { + 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); + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + } /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); -- 2.7.4