[PATCH v4] perf/arm-dmc620: Fix dmc620_pmu_irqs_lock/cpu_hotplug_lock circular lock dependency

[Waiman Long]

The following circular locking dependency was reported when running
cpus online/offline test on an arm64 system.

[   84.195923] Chain exists of:
                 dmc620_pmu_irqs_lock --> cpu_hotplug_lock --> cpuhp_state-down

[   84.207305]  Possible unsafe locking scenario:

[   84.213212]        CPU0                    CPU1
[   84.217729]        ----                    ----
[   84.222247]   lock(cpuhp_state-down);
[   84.225899]                                lock(cpu_hotplug_lock);
[   84.232068]                                lock(cpuhp_state-down);
[   84.238237]   lock(dmc620_pmu_irqs_lock);
[   84.242236]
                *** DEADLOCK ***

The problematic locking order seems to be

	lock(dmc620_pmu_irqs_lock) --> lock(cpu_hotplug_lock)

This locking order happens when dmc620_pmu_get_irq() calls
cpuhp_state_add_instance_nocalls(). Since dmc620_pmu_irqs_lock is used
for protecting the dmc620_pmu_irqs structure only, we don't actually need
to hold the lock when adding a new instance to the CPU hotplug subsystem.

Fix this possible deadlock scenario by adding a new
dmc620_pmu_get_irq_lock for protecting the call to __dmc620_pmu_get_irq()
and taking dmc620_pmu_irqs_lock inside __dmc620_pmu_get_irq()
only when dmc620_pmu_irqs is being searched or modified. As a
result, cpuhp_state_add_instance_nocalls() won't be called with
dmc620_pmu_irqs_lock held and cpu_hotplug_lock won't be acquired after
dmc620_pmu_irqs_lock.

Suggested-by: Robin Murphy <robin.murphy at arm.com>
Signed-off-by: Waiman Long <longman at redhat.com>
---
 drivers/perf/arm_dmc620_pmu.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 9d0f01c4455a..895971915f2d 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -68,6 +68,7 @@
 
 static LIST_HEAD(dmc620_pmu_irqs);
 static DEFINE_MUTEX(dmc620_pmu_irqs_lock);
+static DEFINE_MUTEX(dmc620_pmu_get_irq_lock);
 
 struct dmc620_pmu_irq {
 	struct hlist_node node;
@@ -421,11 +422,18 @@ static irqreturn_t dmc620_pmu_handle_irq(int irq_num, void *data)
 static struct dmc620_pmu_irq *__dmc620_pmu_get_irq(int irq_num)
 {
 	struct dmc620_pmu_irq *irq;
+	bool found = false;
 	int ret;
 
+	mutex_lock(&dmc620_pmu_irqs_lock);
 	list_for_each_entry(irq, &dmc620_pmu_irqs, irqs_node)
-		if (irq->irq_num == irq_num && refcount_inc_not_zero(&irq->refcount))
-			return irq;
+		if (irq->irq_num == irq_num && refcount_inc_not_zero(&irq->refcount)) {
+			found = true;
+			break;
+		}
+	mutex_unlock(&dmc620_pmu_irqs_lock);
+	if (found)
+		return irq;
 
 	irq = kzalloc(sizeof(*irq), GFP_KERNEL);
 	if (!irq)
@@ -452,7 +460,9 @@ static struct dmc620_pmu_irq *__dmc620_pmu_get_irq(int irq_num)
 		goto out_free_irq;
 
 	irq->irq_num = irq_num;
+	mutex_lock(&dmc620_pmu_irqs_lock);
 	list_add(&irq->irqs_node, &dmc620_pmu_irqs);
+	mutex_unlock(&dmc620_pmu_irqs_lock);
 
 	return irq;
 
@@ -467,9 +477,9 @@ static int dmc620_pmu_get_irq(struct dmc620_pmu *dmc620_pmu, int irq_num)
 {
 	struct dmc620_pmu_irq *irq;
 
-	mutex_lock(&dmc620_pmu_irqs_lock);
+	mutex_lock(&dmc620_pmu_get_irq_lock);
 	irq = __dmc620_pmu_get_irq(irq_num);
-	mutex_unlock(&dmc620_pmu_irqs_lock);
+	mutex_unlock(&dmc620_pmu_get_irq_lock);
 
 	if (IS_ERR(irq))
 		return PTR_ERR(irq);
-- 
2.31.1