summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/svm.c
diff options
context:
space:
mode:
authorAshok Raj <ashok.raj@intel.com>2018-02-01 22:59:43 +0100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2018-02-07 11:12:25 -0800
commitd395d69de67ea95760e1f207eb0f6fdfbcb6e069 (patch)
treeabc4d98c1495fe3e42a96c4ec7024ff089c6b4f5 /arch/x86/kvm/svm.c
parent8f7c4d52a0e82854e5ccc15a2b53d3ab3efe0452 (diff)
downloadlinux-stable-d395d69de67ea95760e1f207eb0f6fdfbcb6e069.tar.gz
linux-stable-d395d69de67ea95760e1f207eb0f6fdfbcb6e069.tar.bz2
linux-stable-d395d69de67ea95760e1f207eb0f6fdfbcb6e069.zip
KVM/x86: Add IBPB support
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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'arch/x86/kvm/svm.c')
-rw-r--r--arch/x86/kvm/svm.c28
1 files changed, 28 insertions, 0 deletions
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 6a8284f72328..bc310335baa6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -249,6 +249,7 @@ 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 },
@@ -529,6 +530,7 @@ 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);
@@ -1706,11 +1708,17 @@ 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)) {
@@ -1739,6 +1747,10 @@ 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);
}
@@ -3670,6 +3682,22 @@ 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(vcpu, X86_FEATURE_IBPB))
+ 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;