[PATCH 5/5] x86/feature: Detect the x86 feature Indirect Branch Prediction Barrier

[Ashok Raj]

cpuid ax=0x7, return rdx bit 26 to indicate presence of both
IA32_SPEC_CTRL(MSR 0x48) and IA32_PRED_CMD(MSR 0x49)

BIT0: Indirect Branch Prediction Barrier

When this MSR is written with IBPB=1 it ensures that earlier code's behavior
doesn't control later indirect branch predictions.

Note this MSR is only writable and does not carry any state. Its a barrier
so the code should perform a wrmsr when the barrier is needed.

Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/include/asm/msr-index.h   |  3 +++
 arch/x86/kernel/cpu/spec_ctrl.c    |  7 +++++++
 arch/x86/kvm/svm.c                 | 16 ++++++++++++++++
 arch/x86/kvm/vmx.c                 | 10 ++++++++++
 5 files changed, 37 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 624b58e..52f37fc 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -213,6 +213,7 @@
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_SPEC_CTRL		( 7*32+19) /* Speculation Control */
 #define X86_FEATURE_SPEC_CTRL_IBRS	( 7*32+20) /* Speculation Control, use IBRS */
+#define X86_FEATURE_PRED_CMD	( 7*32+21) /* Indirect Branch Prediction Barrier */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 3e1cb18..1888e19 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -46,6 +46,9 @@
 #define SPEC_CTRL_DISABLE_IBRS		(0 << 0)
 #define SPEC_CTRL_ENABLE_IBRS		(1 << 0)
 
+#define MSR_IA32_PRED_CMD		0x00000049
+#define FEATURE_SET_IBPB		(1<<0)
+
 #define MSR_IA32_PERFCTR0		0x000000c1
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
diff --git a/arch/x86/kernel/cpu/spec_ctrl.c b/arch/x86/kernel/cpu/spec_ctrl.c
index 02fc630..6cfec19 100644
--- a/arch/x86/kernel/cpu/spec_ctrl.c
+++ b/arch/x86/kernel/cpu/spec_ctrl.c
@@ -15,6 +15,13 @@ void spec_ctrl_scan_feature(struct cpuinfo_x86 *c)
 			if (!c->cpu_index)
 				static_branch_enable(&spec_ctrl_dynamic_ibrs);
 		}
+		/*
+		 * For Intel CPU's this MSR is shared the same cpuid
+		 * enumeration. When MSR_IA32_SPEC_CTRL is present
+		 * MSR_IA32_SPEC_CTRL is also available
+		 * TBD: AMD might have a separate enumeration for each.
+		 */
+		set_cpu_cap(c, X86_FEATURE_PRED_CMD);
 	}
 }
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7c14471a..36924c9 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -251,6 +251,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_SYSCALL_MASK,			.always = true  },
 #endif
 	{ .index = MSR_IA32_SPEC_CTRL,          .always = true  },
+	{ .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 },
@@ -531,6 +532,7 @@ 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);
@@ -923,6 +925,8 @@ static void svm_vcpu_init_msrpm(u32 *msrpm)
 
 	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL))
 		set_msr_interception(msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+	if (boot_cpu_has(X86_FEATURE_PRED_CMD))
+		set_msr_interception(msrpm, MSR_IA32_PRED_CMD, 1, 1);
 }
 
 static void add_msr_offset(u32 offset)
@@ -1711,11 +1715,18 @@ 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 could be recycled, causing a false negative in svm_vcpu_load;
+     * block speculative execution.
+     */
+	if (boot_cpu_has(X86_FEATURE_PRED_CMD))
+        native_wrmsrl(MSR_IA32_PRED_CMD, FEATURE_SET_IBPB);
 }
 
 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)) {
@@ -1744,6 +1755,11 @@ 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;
+		if (boot_cpu_has(X86_FEATURE_PRED_CMD))
+			native_wrmsrl(MSR_IA32_PRED_CMD, FEATURE_SET_IBPB);
+	}
 	avic_vcpu_load(vcpu, cpu);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1913896..caeb9ff 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2280,6 +2280,8 @@ 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);
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+			native_wrmsrl(MSR_IA32_PRED_CMD, FEATURE_SET_IBPB);
 	}
 
 	if (!already_loaded) {
@@ -3837,6 +3839,12 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	free_vmcs(loaded_vmcs->vmcs);
 	loaded_vmcs->vmcs = NULL;
 	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
+    /*
+     * The VMCS could be recycled, causing a false negative in vmx_vcpu_load
+     * block speculative execution.
+     */
+	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+        native_wrmsrl(MSR_IA32_PRED_CMD, FEATURE_SET_IBPB);
 }
 
 static void free_kvm_area(void)
@@ -6804,6 +6812,8 @@ static __init int hardware_setup(void)
 	 */
 	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL))
 		vmx_disable_intercept_for_msr(MSR_IA32_SPEC_CTRL, false);
+	if (boot_cpu_has(X86_FEATURE_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);
-- 
2.7.4