Merge branch 'kvm-pi-fix-lockdep' into HEAD

arch/x86/kvm/vmx/posted_intr.c

@@ -31,6 +31,8 @@ static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu);
  */
 static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
 
+#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING
+
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
 	return &(to_vmx(vcpu)->pi_desc);
@@ -89,9 +91,20 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 * current pCPU if the task was migrated.
 	 */
 	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
-		raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+		raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu);
+
+		/*
+		 * In addition to taking the wakeup lock for the regular/IRQ
+		 * context, tell lockdep it is being taken for the "sched out"
+		 * context as well.  vCPU loads happens in task context, and
+		 * this is taking the lock of the *previous* CPU, i.e. can race
+		 * with both the scheduler and the wakeup handler.
+		 */
+		raw_spin_lock(spinlock);
+		spin_acquire(&spinlock->dep_map, PI_LOCK_SCHED_OUT, 0, _RET_IP_);
 		list_del(&vmx->pi_wakeup_list);
-		raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+		spin_release(&spinlock->dep_map, _RET_IP_);
+		raw_spin_unlock(spinlock);
 	}
 
 	dest = cpu_physical_id(cpu);
@@ -148,11 +161,23 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct pi_desc old, new;
-	unsigned long flags;
 
-	local_irq_save(flags);
+	lockdep_assert_irqs_disabled();
 
-	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+	/*
+	 * Acquire the wakeup lock using the "sched out" context to workaround
+	 * a lockdep false positive.  When this is called, schedule() holds
+	 * various per-CPU scheduler locks.  When the wakeup handler runs, it
+	 * holds this CPU's wakeup lock while calling try_to_wake_up(), which
+	 * can eventually take the aforementioned scheduler locks, which causes
+	 * lockdep to assume there is deadlock.
+	 *
+	 * Deadlock can't actually occur because IRQs are disabled for the
+	 * entirety of the sched_out critical section, i.e. the wakeup handler
+	 * can't run while the scheduler locks are held.
+	 */
+	raw_spin_lock_nested(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu),
+			     PI_LOCK_SCHED_OUT);
 	list_add_tail(&vmx->pi_wakeup_list,
 		      &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
 	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
@@ -176,8 +201,6 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 	 */
 	if (pi_test_on(&new))
 		__apic_send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
-
-	local_irq_restore(flags);
 }
 
 static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu)