diff options
Diffstat (limited to 'common/recipes-kernel/linux/linux-yocto-4.9.21/0020-KVM-x86-Add-IBPB-support.patch')
| -rw-r--r-- | common/recipes-kernel/linux/linux-yocto-4.9.21/0020-KVM-x86-Add-IBPB-support.patch | 352 |
1 files changed, 352 insertions, 0 deletions
diff --git a/common/recipes-kernel/linux/linux-yocto-4.9.21/0020-KVM-x86-Add-IBPB-support.patch b/common/recipes-kernel/linux/linux-yocto-4.9.21/0020-KVM-x86-Add-IBPB-support.patch new file mode 100644 index 00000000..731a182a --- /dev/null +++ b/common/recipes-kernel/linux/linux-yocto-4.9.21/0020-KVM-x86-Add-IBPB-support.patch @@ -0,0 +1,352 @@ +From b70d7889c078c97d11ae6412760f3231fda324cd Mon Sep 17 00:00:00 2001 +From: Ashok Raj <ashok.raj@intel.com> +Date: Thu, 1 Feb 2018 22:59:43 +0100 +Subject: [PATCH 20/33] KVM/x86: Add IBPB support + +(cherry picked from commit 15d45071523d89b3fb7372e2135fbd72f6af9506) + +The Indirect Branch Predictor Barrier (IBPB) is an indirect branch +control mechanism. It keeps earlier branches from influencing +later ones. + +Unlike IBRS and STIBP, IBPB does not define a new mode of operation. +It's a command that ensures predicted branch targets aren't used after +the barrier. Although IBRS and IBPB are enumerated by the same CPUID +enumeration, IBPB is very different. + +IBPB helps mitigate against three potential attacks: + +* Mitigate guests from being attacked by other guests. + - This is addressed by issing IBPB when we do a guest switch. + +* Mitigate attacks from guest/ring3->host/ring3. + These would require a IBPB during context switch in host, or after + VMEXIT. The host process has two ways to mitigate + - Either it can be compiled with retpoline + - If its going through context switch, and has set !dumpable then + there is a IBPB in that path. + (Tim's patch: https://patchwork.kernel.org/patch/10192871) + - The case where after a VMEXIT you return back to Qemu might make + Qemu attackable from guest when Qemu isn't compiled with retpoline. + There are issues reported when doing IBPB on every VMEXIT that resulted + in some tsc calibration woes in guest. + +* Mitigate guest/ring0->host/ring0 attacks. + When host kernel is using retpoline it is safe against these attacks. + If host kernel isn't using retpoline we might need to do a IBPB flush on + every VMEXIT. + +Even when using retpoline for indirect calls, in certain conditions 'ret' +can use the BTB on Skylake-era CPUs. There are other mitigations +available like RSB stuffing/clearing. + +* IBPB is issued only for SVM during svm_free_vcpu(). + VMX has a vmclear and SVM doesn't. Follow discussion here: + https://lkml.org/lkml/2018/1/15/146 + +Please refer to the following spec for more details on the enumeration +and control. + +Refer here to get documentation about mitigations. + +https://software.intel.com/en-us/side-channel-security-support + +[peterz: rebase and changelog rewrite] +[karahmed: - rebase + - vmx: expose PRED_CMD if guest has it in CPUID + - svm: only pass through IBPB if guest has it in CPUID + - vmx: support !cpu_has_vmx_msr_bitmap()] + - vmx: support nested] +[dwmw2: Expose CPUID bit too (AMD IBPB only for now as we lack IBRS) + PRED_CMD is a write-only MSR] + +Signed-off-by: Ashok Raj <ashok.raj@intel.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> +Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> +Signed-off-by: KarimAllah Ahmed <karahmed@amazon.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> +Cc: Andrea Arcangeli <aarcange@redhat.com> +Cc: Andi Kleen <ak@linux.intel.com> +Cc: kvm@vger.kernel.org +Cc: Asit Mallick <asit.k.mallick@intel.com> +Cc: Linus Torvalds <torvalds@linux-foundation.org> +Cc: Andy Lutomirski <luto@kernel.org> +Cc: Dave Hansen <dave.hansen@intel.com> +Cc: Arjan Van De Ven <arjan.van.de.ven@intel.com> +Cc: Greg KH <gregkh@linuxfoundation.org> +Cc: Jun Nakajima <jun.nakajima@intel.com> +Cc: Paolo Bonzini <pbonzini@redhat.com> +Cc: Dan Williams <dan.j.williams@intel.com> +Cc: Tim Chen <tim.c.chen@linux.intel.com> +Link: http://lkml.kernel.org/r/1515720739-43819-6-git-send-email-ashok.raj@intel.com +Link: https://lkml.kernel.org/r/1517522386-18410-3-git-send-email-karahmed@amazon.de +Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> +Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +--- + arch/x86/kvm/cpuid.c | 11 +++++++- + arch/x86/kvm/cpuid.h | 12 ++++++++ + arch/x86/kvm/svm.c | 28 +++++++++++++++++++ + arch/x86/kvm/vmx.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++++++-- + 4 files changed, 127 insertions(+), 3 deletions(-) + +diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c +index afa7bbb..42323be 100644 +--- a/arch/x86/kvm/cpuid.c ++++ b/arch/x86/kvm/cpuid.c +@@ -355,6 +355,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + ++ /* cpuid 0x80000008.ebx */ ++ const u32 kvm_cpuid_8000_0008_ebx_x86_features = ++ F(IBPB); ++ + /* cpuid 0xC0000001.edx */ + const u32 kvm_cpuid_C000_0001_edx_x86_features = + F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | +@@ -607,7 +611,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + if (!g_phys_as) + g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); +- entry->ebx = entry->edx = 0; ++ entry->edx = 0; ++ /* IBPB isn't necessarily present in hardware cpuid */ ++ if (boot_cpu_has(X86_FEATURE_IBPB)) ++ entry->ebx |= F(IBPB); ++ entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; ++ cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + break; + } + case 0x80000019: +diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h +index 35058c2..f4a2a1a 100644 +--- a/arch/x86/kvm/cpuid.h ++++ b/arch/x86/kvm/cpuid.h +@@ -152,6 +152,18 @@ static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) + return best && (best->edx & bit(X86_FEATURE_RDTSCP)); + } + ++static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu) ++{ ++ struct kvm_cpuid_entry2 *best; ++ ++ best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); ++ if (best && (best->ebx & bit(X86_FEATURE_IBPB))) ++ return true; ++ best = kvm_find_cpuid_entry(vcpu, 7, 0); ++ return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); ++} ++ ++ + /* + * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 + */ +diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c +index 491f077..43e45b9 100644 +--- a/arch/x86/kvm/svm.c ++++ b/arch/x86/kvm/svm.c +@@ -248,6 +248,7 @@ static const struct svm_direct_access_msrs { + { .index = MSR_CSTAR, .always = true }, + { .index = MSR_SYSCALL_MASK, .always = true }, + #endif ++ { .index = MSR_IA32_PRED_CMD, .always = false }, + { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, +@@ -510,6 +511,7 @@ struct svm_cpu_data { + struct kvm_ldttss_desc *tss_desc; + + struct page *save_area; ++ struct vmcb *current_vmcb; + }; + + static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +@@ -1641,11 +1643,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) + __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); + kvm_vcpu_uninit(vcpu); + kmem_cache_free(kvm_vcpu_cache, svm); ++ /* ++ * The vmcb page can be recycled, causing a false negative in ++ * svm_vcpu_load(). So do a full IBPB now. ++ */ ++ indirect_branch_prediction_barrier(); + } + + static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) + { + struct vcpu_svm *svm = to_svm(vcpu); ++ struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + int i; + + if (unlikely(cpu != vcpu->cpu)) { +@@ -1674,6 +1682,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) + if (static_cpu_has(X86_FEATURE_RDTSCP)) + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + ++ if (sd->current_vmcb != svm->vmcb) { ++ sd->current_vmcb = svm->vmcb; ++ indirect_branch_prediction_barrier(); ++ } + avic_vcpu_load(vcpu, cpu); + } + +@@ -3587,6 +3599,22 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) + case MSR_IA32_TSC: + kvm_write_tsc(vcpu, msr); + break; ++ case MSR_IA32_PRED_CMD: ++ if (!msr->host_initiated && ++ !guest_cpuid_has_ibpb(vcpu)) ++ return 1; ++ ++ if (data & ~PRED_CMD_IBPB) ++ return 1; ++ ++ if (!data) ++ break; ++ ++ wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); ++ if (is_guest_mode(vcpu)) ++ break; ++ set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); ++ break; + case MSR_STAR: + svm->vmcb->save.star = data; + break; +diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c +index c6a7563..855df75 100644 +--- a/arch/x86/kvm/vmx.c ++++ b/arch/x86/kvm/vmx.c +@@ -550,6 +550,7 @@ struct vcpu_vmx { + u64 msr_host_kernel_gs_base; + u64 msr_guest_kernel_gs_base; + #endif ++ + u32 vm_entry_controls_shadow; + u32 vm_exit_controls_shadow; + /* +@@ -911,6 +912,8 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); + static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); + static int alloc_identity_pagetable(struct kvm *kvm); + static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); ++static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, ++ u32 msr, int type); + + static DEFINE_PER_CPU(struct vmcs *, vmxarea); + static DEFINE_PER_CPU(struct vmcs *, current_vmcs); +@@ -1841,6 +1844,29 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) + vmcs_write32(EXCEPTION_BITMAP, eb); + } + ++/* ++ * Check if MSR is intercepted for L01 MSR bitmap. ++ */ ++static bool msr_write_intercepted_l01(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)->vmcs01.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; ++} ++ + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, + unsigned long entry, unsigned long exit) + { +@@ -2252,6 +2278,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) + if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { + per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; + vmcs_load(vmx->loaded_vmcs->vmcs); ++ indirect_branch_prediction_barrier(); + } + + if (!already_loaded) { +@@ -3048,6 +3075,33 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) + case MSR_IA32_TSC: + kvm_write_tsc(vcpu, msr_info); + break; ++ case MSR_IA32_PRED_CMD: ++ if (!msr_info->host_initiated && ++ !guest_cpuid_has_ibpb(vcpu)) ++ return 1; ++ ++ if (data & ~PRED_CMD_IBPB) ++ return 1; ++ ++ if (!data) ++ break; ++ ++ wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); ++ ++ /* ++ * 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. ++ */ ++ vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, ++ MSR_TYPE_W); ++ break; + case MSR_IA32_CR_PAT: + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { + if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) +@@ -9406,9 +9460,23 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, + struct page *page; + 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: ++ * ++ * 1. L0 gave a permission to L1 to actually passthrough the MSR. This ++ * ensures that we do not accidentally generate an L02 MSR bitmap ++ * from the L12 MSR bitmap that is too permissive. ++ * 2. That L1 or L2s have actually used the MSR. This avoids ++ * unnecessarily merging of the bitmap if the MSR is unused. This ++ * works properly because we only update the L01 MSR bitmap lazily. ++ * So even if L0 should pass L1 these MSRs, the L01 bitmap is only ++ * updated to reflect this when L1 (or its L2s) actually write to ++ * the MSR. ++ */ ++ bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + +- /* This shortcut is ok because we support only x2APIC MSRs so far. */ +- if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) ++ if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && ++ !pred_cmd) + return false; + + page = nested_get_page(vcpu, vmcs12->msr_bitmap); +@@ -9443,6 +9511,13 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, + MSR_TYPE_W); + } + } ++ ++ if (pred_cmd) ++ nested_vmx_disable_intercept_for_msr( ++ msr_bitmap_l1, msr_bitmap_l0, ++ MSR_IA32_PRED_CMD, ++ MSR_TYPE_W); ++ + kunmap(page); + nested_release_page_clean(page); + +-- +2.7.4 + |