[PATCH v4 6/7] KVM: X86: TSCDEADLINE MSR emulation fastpath

[Wanpeng Li <kernellwp@gmail.com>]

From: Wanpeng Li <wanpengli@tencent.com>

This patch implements tscdealine msr emulation fastpath, after wrmsr 
tscdeadline vmexit, handle it as soon as possible and vmentry immediately 
without checking various kvm stuff when possible.

Tested-by: Haiwei Li <lihaiwei@tencent.com>
Cc: Haiwei Li <lihaiwei@tencent.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/kvm/lapic.c   | 18 ++++++++++++------
 arch/x86/kvm/vmx/vmx.c | 12 ++++++++----
 arch/x86/kvm/x86.c     | 30 ++++++++++++++++++++++++------
 3 files changed, 44 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 38f7dc9..3589237 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1593,7 +1593,7 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
 	}
 }
 
-static void apic_timer_expired(struct kvm_lapic *apic)
+static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
 	struct kvm_timer *ktimer = &apic->lapic_timer;
@@ -1604,6 +1604,12 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
 
+	if (!from_timer_fn && vcpu->arch.apicv_active) {
+		WARN_ON(kvm_get_running_vcpu() != vcpu);
+		kvm_apic_inject_pending_timer_irqs(apic);
+		return;
+	}
+
 	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
 		if (apic->lapic_timer.timer_advance_ns)
 			__kvm_wait_lapic_expire(vcpu);
@@ -1643,7 +1649,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 		expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
 		hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD);
 	} else
-		apic_timer_expired(apic);
+		apic_timer_expired(apic, false);
 
 	local_irq_restore(flags);
 }
@@ -1751,7 +1757,7 @@ static void start_sw_period(struct kvm_lapic *apic)
 
 	if (ktime_after(ktime_get(),
 			apic->lapic_timer.target_expiration)) {
-		apic_timer_expired(apic);
+		apic_timer_expired(apic, false);
 
 		if (apic_lvtt_oneshot(apic))
 			return;
@@ -1813,7 +1819,7 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 		if (atomic_read(&ktimer->pending)) {
 			cancel_hv_timer(apic);
 		} else if (expired) {
-			apic_timer_expired(apic);
+			apic_timer_expired(apic, false);
 			cancel_hv_timer(apic);
 		}
 	}
@@ -1863,7 +1869,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 		goto out;
 	WARN_ON(swait_active(&vcpu->wq));
 	cancel_hv_timer(apic);
-	apic_timer_expired(apic);
+	apic_timer_expired(apic, false);
 
 	if (apic_lvtt_period(apic) && apic->lapic_timer.period) {
 		advance_periodic_target_expiration(apic);
@@ -2369,7 +2375,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
 	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
 	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
 
-	apic_timer_expired(apic);
+	apic_timer_expired(apic, true);
 
 	if (lapic_is_periodic(apic)) {
 		advance_periodic_target_expiration(apic);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ce19b0e..bb5c4f1 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5994,7 +5994,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) {
 		kvm_skip_emulated_instruction(vcpu);
 		return 1;
-	}
+	} else if (exit_fastpath == EXIT_FASTPATH_NOP)
+		return 1;
 
 	if (exit_reason >= kvm_vmx_max_exit_handlers)
 		goto unexpected_vmexit;
@@ -6605,6 +6606,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long cr3, cr4;
 
+REENTER_GUEST:
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!enable_vnmi &&
 		     vmx->loaded_vmcs->soft_vnmi_blocked))
@@ -6779,10 +6781,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	exit_fastpath = vmx_exit_handlers_fastpath(vcpu);
 	if (exit_fastpath == EXIT_FASTPATH_REENTER_GUEST) {
-		if (!kvm_vcpu_exit_request(vcpu))
+		if (!kvm_vcpu_exit_request(vcpu)) {
 			vmx_sync_pir_to_irr(vcpu);
-		else
-			exit_fastpath = EXIT_FASTPATH_NOP;
+			/* static call is better with retpolines */
+			goto REENTER_GUEST;
+		}
+		exit_fastpath = EXIT_FASTPATH_NOP;
 	}
 
 	return exit_fastpath;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index afe052c..f3a5fe4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1616,27 +1616,45 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data
 	return 1;
 }
 
+static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data)
+{
+	if (!kvm_x86_ops.set_hv_timer ||
+		kvm_mwait_in_guest(vcpu->kvm) ||
+		kvm_can_post_timer_interrupt(vcpu))
+		return 1;
+
+	kvm_set_lapic_tscdeadline_msr(vcpu, data);
+	return 0;
+}
+
 fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu)
 {
 	u32 msr = kvm_rcx_read(vcpu);
 	u64 data;
-	int ret = 0;
+	int ret = EXIT_FASTPATH_NONE;
 
 	switch (msr) {
 	case APIC_BASE_MSR + (APIC_ICR >> 4):
 		data = kvm_read_edx_eax(vcpu);
-		ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data);
+		if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data))
+			ret = EXIT_FASTPATH_SKIP_EMUL_INS;
+		break;
+	case MSR_IA32_TSCDEADLINE:
+		data = kvm_read_edx_eax(vcpu);
+		if (!handle_fastpath_set_tscdeadline(vcpu, data))
+			ret = EXIT_FASTPATH_REENTER_GUEST;
 		break;
 	default:
-		return EXIT_FASTPATH_NONE;
+		ret = EXIT_FASTPATH_NONE;
 	}
 
-	if (!ret) {
+	if (ret != EXIT_FASTPATH_NONE) {
 		trace_kvm_msr_write(msr, data);
-		return EXIT_FASTPATH_SKIP_EMUL_INS;
+		if (ret == EXIT_FASTPATH_REENTER_GUEST)
+			kvm_skip_emulated_instruction(vcpu);
 	}
 
-	return EXIT_FASTPATH_NONE;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff);
 
-- 
2.7.4