KVM: x86: Fold kvm_arch_sched_in() into kvm_arch_vcpu_load()

Fold the guts of kvm_arch_sched_in() into kvm_arch_vcpu_load(), keying
off the recently added kvm_vcpu.scheduled_out as appropriate.

Note, there is a very slight functional change, as PLE shrink updates will
now happen after blasting WBINVD, but that is quite uninteresting as the
two operations do not interact in any way.
Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20240522014013.1672962-4-seanjc@google.comSigned-off-by: Sean Christopherson <seanjc@google.com>

arch/x86/include/asm/kvm-x86-ops.h

@@ -103,7 +103,6 @@ KVM_X86_OP(write_tsc_multiplier)
 KVM_X86_OP(get_exit_info)
 KVM_X86_OP(check_intercept)
 KVM_X86_OP(handle_exit_irqoff)
-KVM_X86_OP(sched_in)
 KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging)
 KVM_X86_OP_OPTIONAL(vcpu_blocking)
 KVM_X86_OP_OPTIONAL(vcpu_unblocking)

arch/x86/include/asm/kvm_host.h

@@ -1749,8 +1749,6 @@ struct kvm_x86_ops {
 			       struct x86_exception *exception);
 	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
 
-	void (*sched_in)(struct kvm_vcpu *vcpu, int cpu);
-
 	/*
 	 * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer.  A zero
 	 * value indicates CPU dirty logging is unsupported or disabled.

arch/x86/kvm/svm/svm.c

@@ -1545,6 +1545,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
 
+	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
+		shrink_ple_window(vcpu);
+
 	if (sd->current_vmcb != svm->vmcb) {
 		sd->current_vmcb = svm->vmcb;
 
@@ -4560,12 +4563,6 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 		vcpu->arch.at_instruction_boundary = true;
 }
 
-static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		shrink_ple_window(vcpu);
-}
-
 static void svm_setup_mce(struct kvm_vcpu *vcpu)
 {
 	/* [63:9] are reserved. */
@@ -5025,8 +5022,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.check_intercept = svm_check_intercept,
 	.handle_exit_irqoff = svm_handle_exit_irqoff,
 
-	.sched_in = svm_sched_in,
-
 	.nested_ops = &svm_nested_ops,
 
 	.deliver_interrupt = svm_deliver_interrupt,

arch/x86/kvm/vmx/main.c

@@ -122,8 +122,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
 
-	.sched_in = vmx_sched_in,
-
 	.cpu_dirty_log_size = PML_ENTITY_NUM,
 	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
 

arch/x86/kvm/vmx/vmx.c

@@ -1518,6 +1518,9 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
+		shrink_ple_window(vcpu);
+
 	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
@@ -8172,12 +8175,6 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
 }
 #endif
 
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		shrink_ple_window(vcpu);
-}
-
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);

arch/x86/kvm/vmx/x86_ops.h

@@ -112,7 +112,6 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
 void vmx_write_tsc_offset(struct kvm_vcpu *vcpu);
 void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu);
 void vmx_request_immediate_exit(struct kvm_vcpu *vcpu);
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu);
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_X86_64
 int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,

arch/x86/kvm/x86.c

@@ -5004,6 +5004,16 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	if (vcpu->scheduled_out) {
+		vcpu->arch.l1tf_flush_l1d = true;
+		if (pmu->version && unlikely(pmu->event_count)) {
+			pmu->need_cleanup = true;
+			kvm_make_request(KVM_REQ_PMU, vcpu);
+		}
+	}
+
 	/* Address WBINVD may be executed by guest */
 	if (need_emulate_wbinvd(vcpu)) {
 		if (static_call(kvm_x86_has_wbinvd_exit)())
@@ -12567,14 +12577,7 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
-	vcpu->arch.l1tf_flush_l1d = true;
-	if (pmu->version && unlikely(pmu->event_count)) {
-		pmu->need_cleanup = true;
-		kvm_make_request(KVM_REQ_PMU, vcpu);
-	}
-	static_call(kvm_x86_sched_in)(vcpu, cpu);
 }
 
 void kvm_arch_free_vm(struct kvm *kvm)