KVM: LAPIC: Micro optimize IPI latency (2b0911d1) · Commits · 戴 / test

This patch optimizes the virtual IPI emulation sequence: write ICR2 write ICR2 write ICR read ICR2 read ICR ==> send virtual IPI read ICR2 write ICR send virtual IPI It can reduce kvm-unit-tests/vmexit.flat IPI testing latency(from sender send IPI to sender receive the ACK) from 3319 cycles to 3203 cycles on SKylake server. Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Signed-off-by:

Wanpeng Li <wanpengli@tencent.com> Signed-off-by:

Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/lapic.c

+4 −5

Original line number	Diff line number	Diff line
		@@ -1198,10 +1198,8 @@ void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector)
		}
		EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated);

		static void apic_send_ipi(struct kvm_lapic *apic)
		static void apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high)
		{
		u32 icr_low = kvm_lapic_get_reg(apic, APIC_ICR);
		u32 icr_high = kvm_lapic_get_reg(apic, APIC_ICR2);
		struct kvm_lapic_irq irq;

		irq.vector = icr_low & APIC_VECTOR_MASK;
		@@ -1914,8 +1912,9 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
		}
		case APIC_ICR:
		/* No delay here, so we always clear the pending bit */
		kvm_lapic_set_reg(apic, APIC_ICR, val & ~(1 << 12));
		apic_send_ipi(apic);
		val &= ~(1 << 12);
		apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2));
		kvm_lapic_set_reg(apic, APIC_ICR, val);
		break;

		case APIC_ICR2:

Admin message