[PATCH] KVM: VMX: fix lockdep warning on posted intr wakeup

[Yan Zhao]

Use rcu list to break the possible circular locking dependency reported
by lockdep.

path 1, ``sysvec_kvm_posted_intr_wakeup_ipi()`` --> ``pi_wakeup_handler()``
         -->  ``kvm_vcpu_wake_up()`` --> ``try_to_wake_up()``,
         the lock sequence is
         &per_cpu(wakeup_vcpus_on_cpu_lock, cpu) --> &p->pi_lock.

path 2, ``schedule()`` --> ``kvm_sched_out()`` --> ``vmx_vcpu_put()`` -->
        ``vmx_vcpu_pi_put()`` --> ``pi_enable_wakeup_handler()``,
         the lock sequence is
         &rq->__lock --> &per_cpu(wakeup_vcpus_on_cpu_lock, cpu).

path 3, ``task_rq_lock()``,
        the lock sequence is &p->pi_lock --> &rq->__lock

lockdep report:
 Chain exists of:
   &p->pi_lock --> &rq->__lock --> &per_cpu(wakeup_vcpus_on_cpu_lock, cpu)

  Possible unsafe locking scenario:

        CPU0                CPU1
        ----                ----
   lock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
                            lock(&rq->__lock);
                            lock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
   lock(&p->pi_lock);

  *** DEADLOCK ***

Signed-off-by: Yan Zhao <yan.y.zhao@xxxxxxxxx>
---
 arch/x86/kvm/vmx/posted_intr.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 94c38bea60e7..e3ffc45c0a7b 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -90,7 +90,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 */
 	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
 		raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
-		list_del(&vmx->pi_wakeup_list);
+		list_del_rcu(&vmx->pi_wakeup_list);
 		raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 	}
 
@@ -153,7 +153,7 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 	local_irq_save(flags);
 
 	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
-	list_add_tail(&vmx->pi_wakeup_list,
+	list_add_tail_rcu(&vmx->pi_wakeup_list,
 		      &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
 	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 
@@ -219,16 +219,14 @@ void pi_wakeup_handler(void)
 {
 	int cpu = smp_processor_id();
 	struct list_head *wakeup_list = &per_cpu(wakeup_vcpus_on_cpu, cpu);
-	raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, cpu);
 	struct vcpu_vmx *vmx;
 
-	raw_spin_lock(spinlock);
-	list_for_each_entry(vmx, wakeup_list, pi_wakeup_list) {
-
+	rcu_read_lock();
+	list_for_each_entry_rcu(vmx, wakeup_list, pi_wakeup_list) {
 		if (pi_test_on(&vmx->pi_desc))
 			kvm_vcpu_wake_up(&vmx->vcpu);
 	}
-	raw_spin_unlock(spinlock);
+	rcu_read_unlock();
 }
 
 void __init pi_init_cpu(int cpu)

base-commit: 89400df96a7570b651404bbc3b7afe627c52a192
-- 
2.17.1