[PATCH v2] KVM: LAPIC: Fix cancel preemption timer repeatedly due to preemption

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

Preemption 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 don't cancel preemption timer repeatedly if 
the preemption timer has already been cancelled due to preemption 
since already-expired timer or sw timer triggered in the window.

Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
 arch/x86/kvm/lapic.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 2819d4c..8341b40 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1560,9 +1560,13 @@ 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);
-	WARN_ON(swait_active(&vcpu->wq));
-	cancel_hv_timer(apic);
+	preempt_disable();
+	if (!(!apic_lvtt_period(apic) && atomic_read(&apic->lapic_timer.pending))) {
+		WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+		WARN_ON(swait_active(&vcpu->wq));
+		cancel_hv_timer(apic);
+	}
+	preempt_enable();
 	apic_timer_expired(apic);
 
 	if (apic_lvtt_period(apic) && apic->lapic_timer.period) {
-- 
2.7.4