[PATCH] x86/kvm: Fix guest haltpoll after the guest suspend/resume

[Wanpeng Li <kernellwp@gmail.com>]

From: Wanpeng Li <wanpengli@tencent.com>

All AP cpus hot-unplugged during guest suspend and hot-plugged during
guest resume, qemu makes host haltpoll as default during vCPU reset,
it resets all the haltpoll to host haltpoll by KVM_SET_MSRS ioctl. All
AP cpus switch to guest haltpoll again by haltpoll driver hotplug
callbacks in the guest. However, BSP is not hotpluggable and keeps host 
haltpoll which means that the BSP switches from guest haltpoll to host 
haltpoll during the guest suspend and resume, this will have vmexit cost
each time the guest enters idle. This patch fixes it by recording BSP's 
haltpoll state and resuming it during guest resume.

Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/kernel/kvm.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d0bb2b3fb305..5c65643cb005 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align
 DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
+static int has_guest_poll = 0;
 /*
  * No need for any "IO delay" on KVM
  */
@@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
 static int kvm_suspend(void)
 {
+	u64 val = 0;
+
 	kvm_guest_cpu_offline(false);
 
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+	has_guest_poll = !(val & 1);
+#endif
 	return 0;
 }
 
 static void kvm_resume(void)
 {
 	kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
 }
 
 static struct syscore_ops kvm_syscore_ops = {
-- 
2.25.1