[PATCH 1/5] KVM: x86: avoid atomic operations on APICv vmentry

[Paolo Bonzini <pbonzini@redhat.com>]

On some benchmarks (e.g. netperf with ioeventfd disabled), APICv
posted interrupts turn out to be slower than interrupt injection via
KVM_REQ_EVENT.

This patch optimizes a bit the IRR update, avoiding expensive atomic
operations in the common case where PI.ON=0 at vmentry or the PIR vector
is mostly zero.  This saves at least 20 cycles (1%) per vmexit, as
measured by kvm-unit-tests' inl_from_qemu test (20 runs):

              | enable_apicv=1  |  enable_apicv=0
              | mean     stdev  |  mean     stdev
    ----------|-----------------|------------------
    before    | 5826     32.65  |  5765     47.09
    after     | 5809     43.42  |  5777     77.02

Of course, any change in the right column is just placebo effect. :)
The savings are bigger if interrupts are frequent.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 6 ++++--
 arch/x86/kvm/vmx.c   | 9 ++++++++-
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 23b99f305382..63a442aefc12 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -342,9 +342,11 @@ void __kvm_apic_update_irr(u32 *pir, void *regs)
 	u32 i, pir_val;
 
 	for (i = 0; i <= 7; i++) {
-		pir_val = xchg(&pir[i], 0);
-		if (pir_val)
+		pir_val = READ_ONCE(pir[i]);
+		if (pir_val) {
+			pir_val = xchg(&pir[i], 0);
 			*((u32 *)(regs + APIC_IRR + i * 0x10)) |= pir_val;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2577183b40d9..7c79d6c6b6ed 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -521,6 +521,12 @@ static inline void pi_set_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+static inline void pi_clear_on(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_ON,
+  		  (unsigned long *)&pi_desc->control);
+}
+
 static inline int pi_test_on(struct pi_desc *pi_desc)
 {
 	return test_bit(POSTED_INTR_ON,
@@ -4854,9 +4860,10 @@ static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!pi_test_and_clear_on(&vmx->pi_desc))
+	if (!pi_test_on(&vmx->pi_desc))
 		return;
 
+	pi_clear_on(&vmx->pi_desc);
 	kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
 }
 
-- 
1.8.3.1