[PATCH v3 01/11] arm/arm64: KVM: Fix ordering of timer/GIC on guest entry

Marc Zyngier marc.zyngier at arm.com
Fri Jul 24 08:54:59 PDT 2015


As we now inject the timer interrupt when we're about to enter
the guest, it makes a lot more sense to make sure this happens
before the vgic code queues the pending interrupts.

Otherwise, we get the interrupt on the following exit, which is
not great for latency (and leads to all kind of bizarre issues
when using with active interrupts at the HW level).

Signed-off-by: Marc Zyngier <marc.zyngier at arm.com>
Reviewed-by: Alex Bennée <alex.bennee at linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall at linaro.org>
---
 arch/arm/kvm/arm.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9ce5cf0..1141d21 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -523,8 +523,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (vcpu->arch.pause)
 			vcpu_pause(vcpu);
 
-		kvm_vgic_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
+		kvm_vgic_flush_hwstate(vcpu);
 
 		preempt_disable();
 		local_irq_disable();
@@ -540,8 +540,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
 			local_irq_enable();
 			preempt_enable();
-			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
+			kvm_timer_sync_hwstate(vcpu);
 			continue;
 		}
 
@@ -587,9 +587,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 		preempt_enable();
 
-
-		kvm_timer_sync_hwstate(vcpu);
 		kvm_vgic_sync_hwstate(vcpu);
+		kvm_timer_sync_hwstate(vcpu);
 
 		ret = handle_exit(vcpu, run, ret);
 	}
-- 
2.1.4




More information about the linux-arm-kernel mailing list