diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 04171fbc39cb..32b43cb9061b 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -29,6 +29,7 @@
 #include <linux/sched.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
+#include <linux/local_lock.h>
 #include <linux/completion.h>
 #include <trace/events/xdp.h>
 #include <linux/btf_ids.h>
@@ -52,6 +53,7 @@ struct xdp_bulk_queue {
 	struct list_head flush_node;
 	struct bpf_cpu_map_entry *obj;
 	unsigned int count;
+	local_lock_t bq_lock;
 };
 
 /* Struct for every remote "destination" CPU in map */
@@ -451,6 +453,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	for_each_possible_cpu(i) {
 		bq = per_cpu_ptr(rcpu->bulkq, i);
 		bq->obj = rcpu;
+		local_lock_init(&bq->bq_lock);
 	}
 
 	/* Alloc queue */
@@ -722,6 +725,8 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 	struct ptr_ring *q;
 	int i;
 
+	lockdep_assert_held(&bq->bq_lock);
+
 	if (unlikely(!bq->count))
 		return;
 
@@ -749,11 +754,15 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 }
 
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
- * Thus, safe percpu variable access.
+ * Thus, safe percpu variable access. PREEMPT_RT relies on
+ * local_lock_nested_bh() to serialise access to the per-CPU bq.
  */
 static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 {
-	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+	struct xdp_bulk_queue *bq;
+
+	local_lock_nested_bh(&rcpu->bulkq->bq_lock);
+	bq = this_cpu_ptr(rcpu->bulkq);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
 		bq_flush_to_queue(bq);
@@ -774,6 +783,8 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 
 		list_add(&bq->flush_node, flush_list);
 	}
+
+	local_unlock_nested_bh(&rcpu->bulkq->bq_lock);
 }
 
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
@@ -810,7 +821,9 @@ void __cpu_map_flush(struct list_head *flush_list)
 	struct xdp_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
+		local_lock_nested_bh(&bq->obj->bulkq->bq_lock);
 		bq_flush_to_queue(bq);
+		local_unlock_nested_bh(&bq->obj->bulkq->bq_lock);
 
 		/* If already running, costs spin_lock_irqsave + smb_mb */
 		wake_up_process(bq->obj->kthread);