KVM: LAPIC: Fix reentrancy issues with preempt notifiers

Preempt can occur in the preemption timer expiration handler:

          CPU0                    CPU1

  preemption timer vmexit
  handle_preemption_timer(vCPU0)
    kvm_lapic_expired_hv_timer
      hv_timer_is_use == true
  sched_out
                           sched_in
                           kvm_arch_vcpu_load
                             kvm_lapic_restart_hv_timer
                               restart_apic_timer
                                 start_hv_timer
                                   already-expired timer or sw timer triggerd in the window
                                 start_sw_timer
                                   cancel_hv_timer
                           /* back in kvm_lapic_expired_hv_timer */
                           cancel_hv_timer
                             WARN_ON(!apic->lapic_timer.hv_timer_in_use);  ==> Oops

This can be reproduced if CONFIG_PREEMPT is enabled.

------------[ cut here ]------------
 WARNING: CPU: 4 PID: 2972 at /home/kernel/linux/arch/x86/kvm//lapic.c:1563 kvm_lapic_expired_hv_timer+0x9e/0xb0 [kvm]
 CPU: 4 PID: 2972 Comm: qemu-system-x86 Tainted: G           OE   4.13.0-rc2+ #16
 RIP: 0010:kvm_lapic_expired_hv_timer+0x9e/0xb0 [kvm]
Call Trace:
  handle_preemption_timer+0xe/0x20 [kvm_intel]
  vmx_handle_exit+0xb8/0xd70 [kvm_intel]
  kvm_arch_vcpu_ioctl_run+0xdd1/0x1be0 [kvm]
  ? kvm_arch_vcpu_load+0x47/0x230 [kvm]
  ? kvm_arch_vcpu_load+0x62/0x230 [kvm]
  kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? __fget+0xfc/0x210
  do_vfs_ioctl+0xa4/0x6a0
  ? __fget+0x11d/0x210
  SyS_ioctl+0x79/0x90
  do_syscall_64+0x81/0x220
  entry_SYSCALL64_slow_path+0x25/0x25
 ------------[ cut here ]------------
 WARNING: CPU: 4 PID: 2972 at /home/kernel/linux/arch/x86/kvm//lapic.c:1498 cancel_hv_timer.isra.40+0x4f/0x60 [kvm]
 CPU: 4 PID: 2972 Comm: qemu-system-x86 Tainted: G        W  OE   4.13.0-rc2+ #16
 RIP: 0010:cancel_hv_timer.isra.40+0x4f/0x60 [kvm]
Call Trace:
  kvm_lapic_expired_hv_timer+0x3e/0xb0 [kvm]
  handle_preemption_timer+0xe/0x20 [kvm_intel]
  vmx_handle_exit+0xb8/0xd70 [kvm_intel]
  kvm_arch_vcpu_ioctl_run+0xdd1/0x1be0 [kvm]
  ? kvm_arch_vcpu_load+0x47/0x230 [kvm]
  ? kvm_arch_vcpu_load+0x62/0x230 [kvm]
  kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? __fget+0xfc/0x210
  do_vfs_ioctl+0xa4/0x6a0
  ? __fget+0x11d/0x210
  SyS_ioctl+0x79/0x90
  do_syscall_64+0x81/0x220
  entry_SYSCALL64_slow_path+0x25/0x25

This patch fixes it by making the caller of cancel_hv_timer, start_hv_timer
and start_sw_timer be in preemption-disabled regions, which trivially
avoid any reentrancy issue with preempt notifier.

Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
[Add more WARNs. - Paolo]
Signed-off-by: Paolo Bonzini <[email protected]>

Author: Wanpeng Li

arch/x86/kvm/lapic.c

@@ -1495,18 +1495,18 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
 static void cancel_hv_timer(struct kvm_lapic *apic)
 {
+	WARN_ON(preemptible());
 	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
-	preempt_disable();
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
-	preempt_enable();
 }
 
 static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 	int r;
 
+	WARN_ON(preemptible());
 	if (!kvm_x86_ops->set_hv_timer)
 		return false;
 
@@ -1538,6 +1538,8 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 static void start_sw_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
+
+	WARN_ON(preemptible());
 	if (apic->lapic_timer.hv_timer_in_use)
 		cancel_hv_timer(apic);
 	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
@@ -1552,15 +1554,20 @@ static void start_sw_timer(struct kvm_lapic *apic)
 
 static void restart_apic_timer(struct kvm_lapic *apic)
 {
+	preempt_disable();
 	if (!start_hv_timer(apic))
 		start_sw_timer(apic);
+	preempt_enable();
 }
 
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	preempt_disable();
+	/* If the preempt notifier has already run, it also called apic_timer_expired */
+	if (!apic->lapic_timer.hv_timer_in_use)
+		goto out;
 	WARN_ON(swait_active(&vcpu->wq));
 	cancel_hv_timer(apic);
 	apic_timer_expired(apic);
@@ -1569,6 +1576,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 		advance_periodic_target_expiration(apic);
 		restart_apic_timer(apic);
 	}
+out:
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
 
@@ -1582,9 +1591,11 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	preempt_disable();
 	/* Possibly the TSC deadline timer is not enabled yet */
 	if (apic->lapic_timer.hv_timer_in_use)
 		start_sw_timer(apic);
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);