Merge tag 'perf-urgent-2025-03-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event fixes from Ingo Molnar:
 "Fix a race between PMU registration and event creation, and fix
  pmus_lock vs. pmus_srcu lock ordering"

* tag 'perf-urgent-2025-03-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/core: Fix perf_pmu_register() vs. perf_init_event()
  perf/core: Fix pmus_lock vs. pmus_srcu ordering

1 files changed, 28 insertions, 4 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6364319e2f88..823aa0824916 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11830,6 +11830,21 @@ free_dev:
 static struct lock_class_key cpuctx_mutex;
 static struct lock_class_key cpuctx_lock;
 
+static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
+{
+	void *tmp, *val = idr_find(idr, id);
+
+	if (val != old)
+		return false;
+
+	tmp = idr_replace(idr, new, id);
+	if (IS_ERR(tmp))
+		return false;
+
+	WARN_ON_ONCE(tmp != val);
+	return true;
+}
+
 int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 {
 	int cpu, ret, max = PERF_TYPE_MAX;
@@ -11856,7 +11871,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (type >= 0)
 		max = type;
 
-	ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
+	ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto free_pdc;
 
@@ -11864,6 +11879,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 
 	type = ret;
 	pmu->type = type;
+	atomic_set(&pmu->exclusive_cnt, 0);
 
 	if (pmu_bus_running && !pmu->dev) {
 		ret = pmu_dev_alloc(pmu);
@@ -11912,14 +11928,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
+	/*
+	 * Now that the PMU is complete, make it visible to perf_try_init_event().
+	 */
+	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
+		goto free_context;
 	list_add_rcu(&pmu->entry, &pmus);
-	atomic_set(&pmu->exclusive_cnt, 0);
+
 	ret = 0;
 unlock:
 	mutex_unlock(&pmus_lock);
 
 	return ret;
 
+free_context:
+	free_percpu(pmu->cpu_pmu_context);
+
 free_dev:
 	if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		device_del(pmu->dev);
@@ -11939,6 +11963,8 @@ void perf_pmu_unregister(struct pmu *pmu)
 {
 	mutex_lock(&pmus_lock);
 	list_del_rcu(&pmu->entry);
+	idr_remove(&pmu_idr, pmu->type);
+	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -11948,7 +11974,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	idr_remove(&pmu_idr, pmu->type);
 	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
@@ -11956,7 +11981,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
-	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);