x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume

MSR_KVM_POLL_CONTROL is cleared on reset, thus reverting guests to
host-side polling after suspend/resume.  Non-bootstrap CPUs are
restored correctly by the haltpoll driver because they are hot-unplugged
during suspend and hot-plugged during resume; however, the BSP
is not hotpluggable and remains in host-sde polling mode after
the guest resume.  The makes the guest pay for the cost of vmexits
every time the guest enters idle.

Fix 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>
Message-Id: <1650267752-46796-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a22deb58f86d2e6d2f5709af95671be9c63c39c6..8b1c45c9cda8771a446aed8b4a62849dda08e77e 100644 (file)
--- 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 = {