KVM: add spinlock optimization framework

If a vcpu exits due to request a user mode spinlock, then
the spinlock-holder may be preempted in user mode or kernel mode.
(Note that not all architectures trap spin loops in user mode,
only AMD x86 and ARM/ARM64 currently do).

But if a vcpu exits in kernel mode, then the holder must be
preempted in kernel mode, so we should choose a vcpu in kernel mode
as a more likely candidate for the lock holder.

This introduces kvm_arch_vcpu_in_kernel() to decide whether the
vcpu is in kernel-mode when it's preempted.  kvm_vcpu_on_spin's
new argument says the same of the spinning VCPU.

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/arm/kvm/handle_exit.c

@@ -67,7 +67,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
 		trace_kvm_wfx(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
-		kvm_vcpu_on_spin(vcpu);
+		kvm_vcpu_on_spin(vcpu, false);
 	} else {
 		trace_kvm_wfx(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;

arch/arm64/kvm/handle_exit.c

@@ -84,7 +84,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
-		kvm_vcpu_on_spin(vcpu);
+		kvm_vcpu_on_spin(vcpu, false);
 	} else {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;

arch/mips/kvm/mips.c

@@ -98,6 +98,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return !!(vcpu->arch.pending_exceptions);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return 1;

arch/powerpc/kvm/powerpc.c

@@ -58,6 +58,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 	return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return 1;

arch/s390/kvm/diag.c

@@ -150,7 +150,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
 	vcpu->stat.diagnose_44++;
-	kvm_vcpu_on_spin(vcpu);
+	kvm_vcpu_on_spin(vcpu, false);
 	return 0;
 }
 

arch/s390/kvm/kvm-s390.c

@@ -2447,6 +2447,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_s390_vcpu_has_irq(vcpu, 0);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	atomic_or(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);

arch/x86/kvm/hyperv.c

@@ -1274,7 +1274,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 
 	switch (code) {
 	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
-		kvm_vcpu_on_spin(vcpu);
+		kvm_vcpu_on_spin(vcpu, false);
 		break;
 	case HVCALL_POST_MESSAGE:
 	case HVCALL_SIGNAL_EVENT:

arch/x86/kvm/svm.c

@@ -3749,7 +3749,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
 
 static int pause_interception(struct vcpu_svm *svm)
 {
-	kvm_vcpu_on_spin(&(svm->vcpu));
+	kvm_vcpu_on_spin(&svm->vcpu, false);
 	return 1;
 }
 

arch/x86/kvm/vmx.c

@@ -6781,7 +6781,7 @@ static int handle_pause(struct kvm_vcpu *vcpu)
 	if (ple_gap)
 		grow_ple_window(vcpu);
 
-	kvm_vcpu_on_spin(vcpu);
+	kvm_vcpu_on_spin(vcpu, false);
 	return kvm_skip_emulated_instruction(vcpu);
 }
 

arch/x86/kvm/x86.c

@@ -8432,6 +8432,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;

include/linux/kvm_host.h

@@ -720,7 +720,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 int kvm_vcpu_yield_to(struct kvm_vcpu *target);
-void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
+void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 
@@ -800,6 +800,7 @@ int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC

virt/kvm/arm/arm.c

@@ -416,6 +416,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 		&& !v->arch.power_off && !v->arch.pause);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 /* Just ensure a guest exit from a particular CPU */
 static void exit_vm_noop(void *info)
 {

virt/kvm/kvm_main.c

@@ -2317,7 +2317,7 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 #endif
 }
 
-void kvm_vcpu_on_spin(struct kvm_vcpu *me)
+void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 {
 	struct kvm *kvm = me->kvm;
 	struct kvm_vcpu *vcpu;
@@ -2348,6 +2348,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
 				continue;
+			if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
+				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;