[PATCH v2 6/8] x86/kvm: Add IBPB support

From: David Woodhouse <dwmw@amazon.co.uk>
To: arjan@linux.intel.com, tglx@linutronix.de, karahmed@amazon.de,
	x86@kernel.org, linux-kernel@vger.kernel.org,
	tim.c.chen@linux.intel.com, bp@alien8.de, peterz@infradead.org,
	pbonzini@redhat.com, ak@linux.intel.com,
	torvalds@linux-foundation.org, gregkh@linux-foundation.org
Subject: [PATCH v2 6/8] x86/kvm: Add IBPB support
Date: Sun, 21 Jan 2018 09:49:07 +0000	[thread overview]
Message-ID: <1516528149-9370-7-git-send-email-dwmw@amazon.co.uk> (raw)
In-Reply-To: <1516528149-9370-1-git-send-email-dwmw@amazon.co.uk>

From: Ashok Raj <ashok.raj@intel.com>

Add MSR passthrough for MSR_IA32_PRED_CMD and place branch predictor
barriers on switching between VMs to avoid inter VM specte-v2 attacks.

[peterz: rebase and changelog rewrite]
[karahmed: - vmx: expose PRED_CMD whenever it is available
	   - svm: only pass through IBPB if it is available]
[dwmw2:    - vmx: allow X86_FEATURE_AMD_PRED_CMD too]
Cc: Asit Mallick <asit.k.mallick@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Arjan Van De Ven <arjan.van.de.ven@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1515720739-43819-6-git-send-email-ashok.raj@intel.com

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: KarimAllah Ahmed <karahmed@amazon.de>
---
 arch/x86/kvm/svm.c | 14 ++++++++++++++
 arch/x86/kvm/vmx.c | 11 +++++++++++
 2 files changed, 25 insertions(+)

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2744b973..cfdb9ab 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -529,6 +529,7 @@ 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);
@@ -918,6 +919,9 @@ static void svm_vcpu_init_msrpm(u32 *msrpm)
 
 		set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
 	}
+
+	if (boot_cpu_has(X86_FEATURE_AMD_PRED_CMD))
+		set_msr_interception(msrpm, MSR_IA32_PRED_CMD, 1, 1);
 }
 
 static void add_msr_offset(u32 offset)
@@ -1706,11 +1710,17 @@ 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 +1749,10 @@ 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);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d1e25db..1e45bb3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2279,6 +2279,7 @@ 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) {
@@ -6791,6 +6792,16 @@ static __init int hardware_setup(void)
 		kvm_tsc_scaling_ratio_frac_bits = 48;
 	}
 
+	/*
+	 * The AMD_PRED_CMD bit might be exposed by hypervisors on Intel
+	 * chips which only want to expose PRED_CMD to guests and not
+	 * SPEC_CTRL. Because PRED_CMD is one-shot write-only, while
+	 * PRED_CMD requires storage, live migration support, etc.
+	 */
+	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) ||
+	    boot_cpu_has(X86_FEATURE_AMD_PRED_CMD))
+		vmx_disable_intercept_for_msr(MSR_IA32_PRED_CMD, false);
+
 	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
 	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
 	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
-- 
2.7.4
