KVM: x86: Add fastpath handling of HLT VM-Exits

Add a fastpath for HLT VM-Exits by immediately re-entering the guest if
it has a pending wake event.  When virtual interrupt delivery is enabled,
i.e. when KVM doesn't need to manually inject interrupts, this allows KVM
to stay in the fastpath run loop when a vIRQ arrives between the guest
doing CLI and STI;HLT.  Without AMD's Idle HLT-intercept support, the CPU
generates a HLT VM-Exit even though KVM will immediately resume the guest.

Note, on bare metal, it's relatively uncommon for a modern guest kernel to
actually trigger this scenario, as the window between the guest checking
for a wake event and committing to HLT is quite small.  But in a nested
environment, the timings change significantly, e.g. rudimentary testing
showed that ~50% of HLT exits where HLT-polling was successful would be
serviced by this fastpath, i.e. ~50% of the time that a nested vCPU gets
a wake event before KVM schedules out the vCPU, the wake event was pending
even before the VM-Exit.

Link: https://lore.kernel.org/all/20240528041926.3989-3-manali.shukla@amd.com
Link: https://lore.kernel.org/r/20240802195120.325560-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

arch/x86/kvm/svm/svm.c

@@ -4147,12 +4147,21 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
 
 static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
 	if (is_guest_mode(vcpu))
 		return EXIT_FASTPATH_NONE;
 
-	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
-	    to_svm(vcpu)->vmcb->control.exit_info_1)
+	switch (svm->vmcb->control.exit_code) {
+	case SVM_EXIT_MSR:
+		if (!svm->vmcb->control.exit_info_1)
+			break;
 		return handle_fastpath_set_msr_irqoff(vcpu);
+	case SVM_EXIT_HLT:
+		return handle_fastpath_hlt(vcpu);
+	default:
+		break;
+	}
 
 	return EXIT_FASTPATH_NONE;
 }

arch/x86/kvm/vmx/vmx.c

@@ -7265,6 +7265,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu,
 		return handle_fastpath_set_msr_irqoff(vcpu);
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return handle_fastpath_preemption_timer(vcpu, force_immediate_exit);
+	case EXIT_REASON_HLT:
+		return handle_fastpath_hlt(vcpu);
 	default:
 		return EXIT_FASTPATH_NONE;
 	}

arch/x86/kvm/x86.c

@@ -11363,7 +11363,10 @@ static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
 	 */
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
-		vcpu->arch.mp_state = state;
+		if (kvm_vcpu_has_events(vcpu))
+			vcpu->arch.pv.pv_unhalted = false;
+		else
+			vcpu->arch.mp_state = state;
 		return 1;
 	} else {
 		vcpu->run->exit_reason = reason;
@@ -11388,6 +11391,24 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
+fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	kvm_vcpu_srcu_read_lock(vcpu);
+	ret = kvm_emulate_halt(vcpu);
+	kvm_vcpu_srcu_read_unlock(vcpu);
+
+	if (!ret)
+		return EXIT_FASTPATH_EXIT_USERSPACE;
+
+	if (kvm_vcpu_running(vcpu))
+		return EXIT_FASTPATH_REENTER_GUEST;
+
+	return EXIT_FASTPATH_EXIT_HANDLED;
+}
+EXPORT_SYMBOL_GPL(handle_fastpath_hlt);
+
 int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu)
 {
 	int ret = kvm_skip_emulated_instruction(vcpu);

arch/x86/kvm/x86.h

@@ -334,6 +334,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len);
 fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
+fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu);
 
 extern struct kvm_caps kvm_caps;
 extern struct kvm_host_values kvm_host;