[PATCH 4.14 083/104] x86/KVM/VMX: Move the l1tf_flush_l1d test to vmx_l1d_flush()

From: Greg Kroah-Hartman
Date: Tue Aug 14 2018 - 13:39:16 EST


4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Stange <nstange@xxxxxxx>

commit 5b6ccc6c3b1a477fbac9ec97a0b4c1c48e765209 upstream

Currently, vmx_vcpu_run() checks if l1tf_flush_l1d is set and invokes
vmx_l1d_flush() if so.

This test is unncessary for the "always flush L1D" mode.

Move the check to vmx_l1d_flush()'s conditional mode code path.

Notes:
- vmx_l1d_flush() is likely to get inlined anyway and thus, there's no
extra function call.

- This inverts the (static) branch prediction, but there hadn't been any
explicit likely()/unlikely() annotations before and so it stays as is.

Signed-off-by: Nicolai Stange <nstange@xxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)

--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9168,12 +9168,16 @@ static void vmx_l1d_flush(struct kvm_vcp
* 'always'
*/
if (static_branch_likely(&vmx_l1d_flush_cond)) {
+ bool flush_l1d = vcpu->arch.l1tf_flush_l1d;
+
/*
* Clear the flush bit, it gets set again either from
* vcpu_run() or from one of the unsafe VMEXIT
* handlers.
*/
vcpu->arch.l1tf_flush_l1d = false;
+ if (!flush_l1d)
+ return;
}

vcpu->stat.l1d_flush++;
@@ -9703,10 +9707,8 @@ static void __noclone vmx_vcpu_run(struc

vmx->__launched = vmx->loaded_vmcs->launched;

- if (static_branch_unlikely(&vmx_l1d_should_flush)) {
- if (vcpu->arch.l1tf_flush_l1d)
- vmx_l1d_flush(vcpu);
- }
+ if (static_branch_unlikely(&vmx_l1d_should_flush))
+ vmx_l1d_flush(vcpu);

asm(
/* Store host registers */