KVM: nVMX: Skip IBPB when switching between vmcs01 and vmcs02

commit 5c911beff20aa8639e7a1f28988736c13e03ed54 upstream.

Skip the Indirect Branch Prediction Barrier that is triggered on a VMCS
switch when running with spectre_v2_user=on/auto if the switch is
between two VMCSes in the same guest, i.e. between vmcs01 and vmcs02.
The IBPB is intended to prevent one guest from attacking another, which
is unnecessary in the nested case as it's the same guest from KVM's
perspective.

This all but eliminates the overhead observed for nested VMX transitions
when running with CONFIG_RETPOLINE=y and spectre_v2_user=on/auto, which
can be significant, e.g. roughly 3x on current systems.

Reported-by: Alexander Graf <graf@amazon.com>
Cc: KarimAllah Raslan <karahmed@amazon.de>
Cc: stable@vger.kernel.org
Fixes: 15d45071523d ("KVM/x86: Add IBPB support")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200501163117.4655-1-sean.j.christopherson@intel.com>
[Invert direction of bool argument. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 17 insertions, 6 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 4a09f40b24dc..532d9502e8ae 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -302,7 +302,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	cpu = get_cpu();
 	prev = vmx->loaded_vmcs;
 	vmx->loaded_vmcs = vmcs;
-	vmx_vcpu_load_vmcs(vcpu, cpu);
+	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
 	vmx_sync_vmcs_host_state(vmx, prev);
 	put_cpu();
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 7a2c05277f4c..5fac01865a2d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1286,10 +1286,12 @@ after_clear_sn:
 		pi_set_on(pi_desc);
 }
 
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
+			struct loaded_vmcs *buddy)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
+	struct vmcs *prev;
 
 	if (!already_loaded) {
 		loaded_vmcs_clear(vmx->loaded_vmcs);
@@ -1308,10 +1310,18 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
 		local_irq_enable();
 	}
 
-	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+	prev = per_cpu(current_vmcs, cpu);
+	if (prev != vmx->loaded_vmcs->vmcs) {
 		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
 		vmcs_load(vmx->loaded_vmcs->vmcs);
-		indirect_branch_prediction_barrier();
+
+		/*
+		 * No indirect branch prediction barrier needed when switching
+		 * the active VMCS within a guest, e.g. on nested VM-Enter.
+		 * The L1 VMM can protect itself with retpolines, IBPB or IBRS.
+		 */
+		if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
+			indirect_branch_prediction_barrier();
 	}
 
 	if (!already_loaded) {
@@ -1356,7 +1366,7 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	vmx_vcpu_load_vmcs(vcpu, cpu);
+	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 5a0f34b1e226..295c5f83842e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -304,7 +304,8 @@ struct kvm_vmx {
 };
 
 bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu);
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
+			struct loaded_vmcs *buddy);
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 int allocate_vpid(void);
 void free_vpid(int vpid);