linux-kernel - [RFC 02/10] x86/kvm: Add IBPB support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Sat, 20 Jan 2018 20:22:53 +0100
From:   KarimAllah Ahmed <karahmed@...zon.de>
To:     linux-kernel@...r.kernel.org
Cc:     KarimAllah Ahmed <karahmed@...zon.de>,
        Andi Kleen <ak@...ux.intel.com>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Andy Lutomirski <luto@...nel.org>,
        Arjan van de Ven <arjan@...ux.intel.com>,
        Ashok Raj <ashok.raj@...el.com>,
        Asit Mallick <asit.k.mallick@...el.com>,
        Borislav Petkov <bp@...e.de>,
        Dan Williams <dan.j.williams@...el.com>,
        Dave Hansen <dave.hansen@...el.com>,
        David Woodhouse <dwmw@...zon.co.uk>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        "H . Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...hat.com>,
        Janakarajan Natarajan <Janakarajan.Natarajan@....com>,
        Joerg Roedel <joro@...tes.org>,
        Jun Nakajima <jun.nakajima@...el.com>,
        Laura Abbott <labbott@...hat.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Radim Krčmář <rkrcmar@...hat.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Tom Lendacky <thomas.lendacky@....com>, kvm@...r.kernel.org,
        x86@...nel.org, Arjan Van De Ven <arjan.van.de.ven@...el.com>
Subject: [RFC 02/10] x86/kvm: Add IBPB support

From: Ashok Raj <ashok.raj@...el.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]
[dwmw2: fixes]
[karahmed: - vmx: expose PRED_CMD whenever it is available
	   - svm: only pass through IBPB if it is available]

Cc: Asit Mallick <asit.k.mallick@...el.com>
Cc: Dave Hansen <dave.hansen@...el.com>
Cc: Arjan Van De Ven <arjan.van.de.ven@...el.com>
Cc: Tim Chen <tim.c.chen@...ux.intel.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Andrea Arcangeli <aarcange@...hat.com>
Cc: Andi Kleen <ak@...ux.intel.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Dan Williams <dan.j.williams@...el.com>
Cc: Jun Nakajima <jun.nakajima@...el.com>
Cc: Andy Lutomirski <luto@...nel.org>
Cc: Greg KH <gregkh@...uxfoundation.org>
Cc: David Woodhouse <dwmw@...zon.co.uk>
Cc: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Ashok Raj <ashok.raj@...el.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Link: http://lkml.kernel.org/r/1515720739-43819-6-git-send-email-ashok.raj@intel.com

Signed-off-by: David Woodhouse <dwmw@...zon.co.uk>
Signed-off-by: KarimAllah Ahmed <karahmed@...zon.de>
---
 arch/x86/kvm/svm.c | 14 ++++++++++++++
 arch/x86/kvm/vmx.c |  4 ++++
 2 files changed, 18 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..3b64de2 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 +6792,9 @@ static __init int hardware_setup(void)
 		kvm_tsc_scaling_ratio_frac_bits = 48;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		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