[PATCH v2 2/4] KVM: X86: implement the logic for spinlock optimization

[Longpeng(Mike)]

1. Implements the kvm_arch_vcpu_in_kernel(), because get_cpl requires
vcpu_load, so we must cache the result(whether the vcpu was preempted
when its cpl=0) in kvm_vcpu_arch.

2. Add ->spin_in_kernel hook, because we can get benefit from VMX.

Signed-off-by: Longpeng(Mike) <longpeng2@xxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  5 +++++
 arch/x86/kvm/hyperv.c           |  2 +-
 arch/x86/kvm/svm.c              |  8 +++++++-
 arch/x86/kvm/vmx.c              | 16 +++++++++++++++-
 arch/x86/kvm/x86.c              |  7 ++++++-
 5 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 87ac4fb..d2b2d57 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -688,6 +688,9 @@ struct kvm_vcpu_arch {
 
 	/* GPA available (AMD only) */
 	bool gpa_available;
+
+	/* be preempted when it's in kernel-mode(cpl=0) */
+	bool preempted_in_kernel;
 };
 
 struct kvm_lpage_info {
@@ -1057,6 +1060,8 @@ struct kvm_x86_ops {
 	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
 
 	void (*setup_mce)(struct kvm_vcpu *vcpu);
+
+	bool (*spin_in_kernel)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index cd0e6e6..dec5e8a 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1268,7 +1268,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 
 	switch (code) {
 	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
-		kvm_vcpu_on_spin(vcpu, kvm_arch_vcpu_in_kernel(vcpu));
+		kvm_vcpu_on_spin(vcpu, kvm_x86_ops->spin_in_kernel(vcpu));
 		break;
 	case HVCALL_POST_MESSAGE:
 	case HVCALL_SIGNAL_EVENT:
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e6ed24e..ccb6df7 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3751,7 +3751,7 @@ static int pause_interception(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &(svm->vcpu);
 
-	kvm_vcpu_on_spin(vcpu, kvm_arch_vcpu_in_kernel(vcpu));
+	kvm_vcpu_on_spin(vcpu, kvm_x86_ops->spin_in_kernel(vcpu));
 	return 1;
 }
 
@@ -5364,6 +5364,11 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu)
 	vcpu->arch.mcg_cap &= 0x1ff;
 }
 
+static bool svm_spin_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return svm_get_cpl(vcpu) == 0;
+}
+
 static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -5476,6 +5481,7 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu)
 	.deliver_posted_interrupt = svm_deliver_avic_intr,
 	.update_pi_irte = svm_update_pi_irte,
 	.setup_mce = svm_setup_mce,
+	.spin_in_kernel = svm_spin_in_kernel,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9d6223a..297a158 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6761,7 +6761,8 @@ static int handle_pause(struct kvm_vcpu *vcpu)
 	if (ple_gap)
 		grow_ple_window(vcpu);
 
-	kvm_vcpu_on_spin(vcpu, kvm_arch_vcpu_in_kernel(vcpu));
+	/* See comments in vmx_spin_in_kernel() */
+	kvm_vcpu_on_spin(vcpu, true);
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
@@ -11636,6 +11637,17 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
 			~FEATURE_CONTROL_LMCE;
 }
 
+static bool vmx_spin_in_kernel(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Intel sdm vol3 ch-25.1.3 says: The âPAUSE-loop exitingâ
+	 * VM-execution control is ignored if CPL > 0. OTOH, KVM
+	 * never set PAUSE_EXITING and just set PLE if supported,
+	 * so the vcpu must be CPL=0 if it gets a PAUSE exit.
+	 */
+	return true;
+}
+
 static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -11763,6 +11775,8 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
 #endif
 
 	.setup_mce = vmx_setup_mce,
+
+	.spin_in_kernel = vmx_spin_in_kernel,
 };
 
 static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4430be6..28299b9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2881,6 +2881,10 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
+
+	if (vcpu->preempted)
+		vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu);
+
 	/*
 	 * Disable page faults because we're in atomic context here.
 	 * kvm_write_guest_offset_cached() would call might_fault()
@@ -7992,6 +7996,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_pmu_init(vcpu);
 
 	vcpu->arch.pending_external_vector = -1;
+	vcpu->arch.preempted_in_kernel = false;
 
 	kvm_hv_vcpu_init(vcpu);
 
@@ -8441,7 +8446,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
-	return false;
+	return vcpu->arch.preempted_in_kernel;
 }
 EXPORT_SYMBOL_GPL(kvm_arch_vcpu_in_kernel);
 
-- 
1.8.3.1