From: Marc Zyngier maz@kernel.org
mainline inclusion from mainline-v5.4-rc1 commit 07ab0f8d9a129add914aff3e988da4033471dfc0 category: feature feature: guest VLPI during the halt poll window can be immediately recognised
-------------------------------------------------
When a vpcu is about to block by calling kvm_vcpu_block, we call back into the arch code to allow any form of synchronization that may be required at this point (SVN stops the AVIC, ARM synchronises the VMCR and enables GICv4 doorbells). But this synchronization comes in quite late, as we've potentially waited for halt_poll_ns to expire.
Instead, let's move kvm_arch_vcpu_blocking() to the beginning of kvm_vcpu_block(), which on ARM has several benefits:
- VMCR gets synchronised early, meaning that any interrupt delivered during the polling window will be evaluated with the correct guest PMR - GICv4 doorbells are enabled, which means that any guest interrupt directly injected during that window will be immediately recognised
Tang Nianyao ran some tests on a GICv4 machine to evaluate such change, and reported up to a 10% improvement for netperf:
<quote> netperf result: D06 as server, intel 8180 server as client with change: package 512 bytes - 5500 Mbits/s package 64 bytes - 760 Mbits/s without change: package 512 bytes - 5000 Mbits/s package 64 bytes - 710 Mbits/s </quote>
Acked-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Zenghui Yu yuzenghui@huawei.com Reviewed-by: Hailiang Zhang zhang.zhanghailiang@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- virt/kvm/kvm_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d7b7418..9c17696 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2212,6 +2212,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) bool waited = false; u64 block_ns;
+ kvm_arch_vcpu_blocking(vcpu); + start = cur = ktime_get(); if (vcpu->halt_poll_ns) { ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); @@ -2232,8 +2234,6 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) } while (single_task_running() && ktime_before(cur, stop)); }
- kvm_arch_vcpu_blocking(vcpu); - for (;;) { prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
@@ -2247,8 +2247,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) finish_swait(&vcpu->wq, &wait); cur = ktime_get();
- kvm_arch_vcpu_unblocking(vcpu); out: + kvm_arch_vcpu_unblocking(vcpu); block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
if (!vcpu_valid_wakeup(vcpu))