diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 05ebe841270b..84522c796987 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2228,14 +2228,11 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 	unsigned long flags;
 	int ctxn, err;
 
-	if (!task && cpu != -1) {
+	if (!task) {
 		/* Must be root to operate on a CPU event: */
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
-		if (cpu < 0 || cpu >= nr_cpumask_bits)
-			return ERR_PTR(-EINVAL);
-
 		/*
 		 * We could be clever and allow to attach a event to an
 		 * offline CPU and activate it when the CPU comes up, but
@@ -5541,6 +5538,11 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	struct hw_perf_event *hwc;
 	long err;
 
+	if ((unsigned)cpu >= nr_cpu_ids) {
+		if (!task || cpu != -1)
+			return ERR_PTR(-EINVAL);
+	}
+
 	event = kzalloc(sizeof(*event), GFP_KERNEL);
 	if (!event)
 		return ERR_PTR(-ENOMEM);
@@ -5589,7 +5591,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	if (!overflow_handler && parent_event)
 		overflow_handler = parent_event->overflow_handler;
-	
+
 	event->overflow_handler	= overflow_handler;
 
 	if (attr->disabled)
@@ -6494,7 +6496,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
 	parent_ctx->rotate_disable = 0;
-	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
 
 	child_ctx = child->perf_event_ctxp[ctxn];
 
@@ -6502,12 +6503,11 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 		/*
 		 * Mark the child context as a clone of the parent
 		 * context, or of whatever the parent is a clone of.
-		 * Note that if the parent is a clone, it could get
-		 * uncloned at any point, but that doesn't matter
-		 * because the list of events and the generation
-		 * count can't have changed since we took the mutex.
+		 *
+		 * Note that if the parent is a clone, the holding of
+		 * parent_ctx->lock avoids it from being uncloned.
 		 */
-		cloned_ctx = rcu_dereference(parent_ctx->parent_ctx);
+		cloned_ctx = parent_ctx->parent_ctx;
 		if (cloned_ctx) {
 			child_ctx->parent_ctx = cloned_ctx;
 			child_ctx->parent_gen = parent_ctx->parent_gen;
@@ -6518,6 +6518,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 		get_ctx(child_ctx->parent_ctx);
 	}
 
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);