diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index b036710ba52cf4684936397aeb706bd6a3e2b039..42cd687e6608145be1dcbbe030162e73e57b7a52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -737,10 +737,10 @@ static inline
 struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     u16 wqe_counter, u32 cqe_bcnt)
 {
-	struct bpf_prog *xdp_prog = READ_ONCE(rq->xdp_prog);
 	struct mlx5e_dma_info *di;
 	struct sk_buff *skb;
 	void *va, *data;
+	bool consumed;
 
 	di             = &rq->dma_info[wqe_counter];
 	va             = page_address(di->page);
@@ -759,7 +759,11 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 		return NULL;
 	}
 
-	if (mlx5e_xdp_handle(rq, xdp_prog, di, data, cqe_bcnt))
+	rcu_read_lock();
+	consumed = mlx5e_xdp_handle(rq, READ_ONCE(rq->xdp_prog), di, data,
+				    cqe_bcnt);
+	rcu_read_unlock();
+	if (consumed)
 		return NULL; /* page/packet was consumed by XDP */
 
 	skb = build_skb(va, RQ_PAGE_SIZE(rq));
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 876ab3a92ad532c347afdd2baf9f017f0b9fd160..00d9a03be31df518b986eb5a14c1fb6377c1e1f8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1518,7 +1518,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
 	xdp.data = data;
 	xdp.data_end = data + len;
 
-	return BPF_PROG_RUN(prog, &xdp);
+	return bpf_prog_run_xdp(prog, &xdp);
 }
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 172ff6da92ad1f37fbf06aa0e0cee35031a2c8e5..faeaa9f3b197b58422f4d0308230f95e328ea0fb 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1497,7 +1497,14 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 
 	xdp.data = page_address(bd->data) + cqe->placement_offset;
 	xdp.data_end = xdp.data + len;
+
+	/* Queues always have a full reset currently, so for the time
+	 * being until there's atomic program replace just mark read
+	 * side for map helpers.
+	 */
+	rcu_read_lock();
 	act = bpf_prog_run_xdp(prog, &xdp);
+	rcu_read_unlock();
 
 	if (act == XDP_PASS)
 		return true;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7ba644626553274120d9b34467a931ab6c4bf051..97338134398f678bb96515df98960325fc09f85e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -498,16 +498,16 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
 	return BPF_PROG_RUN(prog, skb);
 }
 
-static inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
-				   struct xdp_buff *xdp)
+static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
+					    struct xdp_buff *xdp)
 {
-	u32 ret;
-
-	rcu_read_lock();
-	ret = BPF_PROG_RUN(prog, xdp);
-	rcu_read_unlock();
-
-	return ret;
+	/* Caller needs to hold rcu_read_lock() (!), otherwise program
+	 * can be released while still running, or map elements could be
+	 * freed early while still having concurrent users. XDP fastpath
+	 * already takes rcu_read_lock() when fetching the program, so
+	 * it's not necessary here anymore.
+	 */
+	return BPF_PROG_RUN(prog, xdp);
 }
 
 static inline unsigned int bpf_prog_size(unsigned int proglen)