Skip to contentSkip to conversation

KVM: x86: Avoid issuing wbinvd twice

PATCH Applied Jan Kiszka 2 participants 2 messages Nov 1, 2010

Subsystems (3)
x86 KVM KVM x86
lore
Share & tools
lore

Jan Kiszka

author
#0 lore raw

PATCH 2/2 KVM: x86: Avoid issuing wbinvd twice

From: Jan Kiszka <[email protected]>

Micro optimization to avoid calling wbinvd twice on the CPU that has to emulate it. As we might be preempted between smp_call_function_many and the local wbinvd, the cache might be filled again so that real work could be done uselessly.

Signed-off-by Jan Kiszka <[email protected]>

---

I can fold the first patch into this one if it's preferred.

 arch/x86/kvm/x86.c |   10 ++++++----
 1 files changed, 6 insertions(+), 4 deletions(-)
arch/x86/kvm/x86.c +6 -4
index 0ed6dad..58e8232 100644
@@ -4012,13 +4012,15 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
 		return X86EMUL_CONTINUE;
 
 	if (kvm_x86_ops->has_wbinvd_exit()) {
-		preempt_disable();
+		int cpu = get_cpu();
+
+		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
 		smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
 				wbinvd_ipi, NULL, 1);
-		preempt_enable();
+		put_cpu();
 		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
-	}
-	wbinvd();
+	} else
+		wbinvd();
 	return X86EMUL_CONTINUE;
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
Applied
#1 lore raw
Quoted 8 lines · Jan Kiszka

From: Jan Kiszka <[email protected]>

Micro optimization to avoid calling wbinvd twice on the CPU that has to emulate it. As we might be preempted between smp_call_function_many and the local wbinvd, the cache might be filled again so that real work could be done uselessly.

Signed-off-by Jan Kiszka <[email protected]>

Applied both, thanks.