xsk: Propagate napi_id to XDP socket Rx path

Add napi_id to the xdp_rxq_info structure, and make sure the XDP
socket pick up the napi_id in the Rx path. The napi_id is used to find
the corresponding NAPI structure for socket busy polling.

Signed-off-by: Björn Töpel <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Acked-by: Ilias Apalodimas <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
Acked-by: Tariq Toukan <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Björn Töpel

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -416,7 +416,7 @@ static int ena_xdp_register_rxq_info(struct ena_ring *rx_ring)
 {
 	int rc;
 
-	rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid);
+	rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid, 0);
 
 	if (rc) {
 		netif_err(rx_ring->adapter, ifup, rx_ring->netdev,

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -2884,7 +2884,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 		if (rc)
 			return rc;
 
-		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i);
+		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0);
 		if (rc < 0)
 			return rc;
 

drivers/net/ethernet/cavium/thunder/nicvf_queues.c

@@ -770,7 +770,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 	rq->caching = 1;
 
 	/* Driver have no proper error path for failed XDP RX-queue info reg */
-	WARN_ON(xdp_rxq_info_reg(&rq->xdp_rxq, nic->netdev, qidx) < 0);
+	WARN_ON(xdp_rxq_info_reg(&rq->xdp_rxq, nic->netdev, qidx, 0) < 0);
 
 	/* Send a mailbox msg to PF to config RQ */
 	mbx.rq.msg = NIC_MBOX_MSG_RQ_CFG;

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -3334,7 +3334,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv,
 		return 0;
 
 	err = xdp_rxq_info_reg(&fq->channel->xdp_rxq, priv->net_dev,
-			       fq->flowid);
+			       fq->flowid, 0);
 	if (err) {
 		dev_err(dev, "xdp_rxq_info_reg failed\n");
 		return err;

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -1447,7 +1447,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	/* XDP RX-queue info only needed for RX rings exposed to XDP */
 	if (rx_ring->vsi->type == I40E_VSI_MAIN) {
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				       rx_ring->queue_index);
+				       rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);
 		if (err < 0)
 			return err;
 	}

drivers/net/ethernet/intel/ice/ice_base.c

@@ -306,7 +306,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 			/* coverity[check_return] */
 			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->q_index);
+					 ring->q_index, ring->q_vector->napi.napi_id);
 
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
@@ -333,7 +333,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 				/* coverity[check_return] */
 				xdp_rxq_info_reg(&ring->xdp_rxq,
 						 ring->netdev,
-						 ring->q_index);
+						 ring->q_index, ring->q_vector->napi.napi_id);
 
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_PAGE_SHARED,

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -483,7 +483,7 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring)
 	if (rx_ring->vsi->type == ICE_VSI_PF &&
 	    !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 		if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				     rx_ring->q_index))
+				     rx_ring->q_index, rx_ring->q_vector->napi.napi_id))
 			goto err;
 	return 0;
 

drivers/net/ethernet/intel/igb/igb_main.c

@@ -4352,7 +4352,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 
 	/* XDP RX-queue info */
 	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-			     rx_ring->queue_index) < 0)
+			     rx_ring->queue_index, 0) < 0)
 		goto err;
 
 	return 0;

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -6577,7 +6577,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 
 	/* XDP RX-queue info */
 	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
-			     rx_ring->queue_index) < 0)
+			     rx_ring->queue_index, rx_ring->q_vector->napi.napi_id) < 0)
 		goto err;
 
 	rx_ring->xdp_prog = adapter->xdp_prog;

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -3493,7 +3493,7 @@ int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter,
 
 	/* XDP RX-queue info */
 	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
-			     rx_ring->queue_index) < 0)
+			     rx_ring->queue_index, 0) < 0)
 		goto err;
 
 	rx_ring->xdp_prog = adapter->xdp_prog;

drivers/net/ethernet/marvell/mvneta.c

@@ -3227,7 +3227,7 @@ static int mvneta_create_page_pool(struct mvneta_port *pp,
 		return err;
 	}
 
-	err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id);
+	err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0);
 	if (err < 0)
 		goto err_free_pp;
 

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -2614,11 +2614,11 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
 	mvpp2_rxq_status_update(port, rxq->id, 0, rxq->size);
 
 	if (priv->percpu_pools) {
-		err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id);
+		err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id, 0);
 		if (err < 0)
 			goto err_free_dma;
 
-		err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id);
+		err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id, 0);
 		if (err < 0)
 			goto err_unregister_rxq_short;
 

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -283,7 +283,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->log_stride = ffs(ring->stride) - 1;
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
-	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index) < 0)
+	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
 		goto err_ring;
 
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -434,7 +434,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq_xdp_ix = rq->ix;
 	if (xsk)
 		rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK;
-	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix);
+	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix, 0);
 	if (err < 0)
 		goto err_rq_xdp_prog;
 

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

@@ -2533,7 +2533,7 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 
 	if (dp->netdev) {
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, dp->netdev,
-				       rx_ring->idx);
+				       rx_ring->idx, rx_ring->r_vec->napi.napi_id);
 		if (err < 0)
 			return err;
 	}

drivers/net/ethernet/qlogic/qede/qede_main.c

@@ -1762,7 +1762,7 @@ static void qede_init_fp(struct qede_dev *edev)
 
 			/* Driver have no error path from here */
 			WARN_ON(xdp_rxq_info_reg(&fp->rxq->xdp_rxq, edev->ndev,
-						 fp->rxq->rxq_id) < 0);
+						 fp->rxq->rxq_id, 0) < 0);
 
 			if (xdp_rxq_info_reg_mem_model(&fp->rxq->xdp_rxq,
 						       MEM_TYPE_PAGE_ORDER0,

drivers/net/ethernet/sfc/rx_common.c

@@ -262,7 +262,7 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue)
 
 	/* Initialise XDP queue information */
 	rc = xdp_rxq_info_reg(&rx_queue->xdp_rxq_info, efx->net_dev,
-			      rx_queue->core_index);
+			      rx_queue->core_index, 0);
 
 	if (rc) {
 		netif_err(efx, rx_err, efx->net_dev,

drivers/net/ethernet/socionext/netsec.c

@@ -1304,7 +1304,7 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 		goto err_out;
 	}
 
-	err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0);
+	err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0, priv->napi.napi_id);
 	if (err)
 		goto err_out;
 

drivers/net/ethernet/ti/cpsw_priv.c

@@ -1186,7 +1186,7 @@ static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch)
 	pool = cpsw->page_pool[ch];
 	rxq = &priv->xdp_rxq[ch];
 
-	ret = xdp_rxq_info_reg(rxq, priv->ndev, ch);
+	ret = xdp_rxq_info_reg(rxq, priv->ndev, ch, 0);
 	if (ret)
 		return ret;
 

drivers/net/hyperv/netvsc.c

@@ -1499,7 +1499,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 		u64_stats_init(&nvchan->tx_stats.syncp);
 		u64_stats_init(&nvchan->rx_stats.syncp);
 
-		ret = xdp_rxq_info_reg(&nvchan->xdp_rxq, ndev, i);
+		ret = xdp_rxq_info_reg(&nvchan->xdp_rxq, ndev, i, 0);
 
 		if (ret) {
 			netdev_err(ndev, "xdp_rxq_info_reg fail: %d\n", ret);

drivers/net/tun.c

@@ -780,7 +780,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	} else {
 		/* Setup XDP RX-queue info, for new tfile getting attached */
 		err = xdp_rxq_info_reg(&tfile->xdp_rxq,
-				       tun->dev, tfile->queue_index);
+				       tun->dev, tfile->queue_index, 0);
 		if (err < 0)
 			goto out;
 		err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq,

drivers/net/veth.c

@@ -884,7 +884,6 @@ static int veth_napi_add(struct net_device *dev)
 	for (i = 0; i < dev->real_num_rx_queues; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
-		netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
 		napi_enable(&rq->xdp_napi);
 	}
 
@@ -926,7 +925,8 @@ static int veth_enable_xdp(struct net_device *dev)
 		for (i = 0; i < dev->real_num_rx_queues; i++) {
 			struct veth_rq *rq = &priv->rq[i];
 
-			err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i);
+			netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
+			err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id);
 			if (err < 0)
 				goto err_rxq_reg;
 
@@ -952,8 +952,12 @@ static int veth_enable_xdp(struct net_device *dev)
 err_reg_mem:
 	xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
 err_rxq_reg:
-	for (i--; i >= 0; i--)
-		xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
+	for (i--; i >= 0; i--) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+		netif_napi_del(&rq->xdp_napi);
+	}
 
 	return err;
 }

drivers/net/virtio_net.c

@@ -1485,7 +1485,7 @@ static int virtnet_open(struct net_device *dev)
 			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
 				schedule_delayed_work(&vi->refill, 0);
 
-		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i);
+		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);
 		if (err < 0)
 			return err;
 

drivers/net/xen-netfront.c

@@ -2014,7 +2014,7 @@ static int xennet_create_page_pool(struct netfront_queue *queue)
 	}
 
 	err = xdp_rxq_info_reg(&queue->xdp_rxq, queue->info->netdev,
-			       queue->id);
+			       queue->id, 0);
 	if (err) {
 		netdev_err(queue->info->netdev, "xdp_rxq_info_reg failed\n");
 		goto err_free_pp;

include/net/busy_poll.h

@@ -135,14 +135,25 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 	sk_rx_queue_set(sk, skb);
 }
 
-/* variant used for unconnected sockets */
-static inline void sk_mark_napi_id_once(struct sock *sk,
-					const struct sk_buff *skb)
+static inline void __sk_mark_napi_id_once_xdp(struct sock *sk, unsigned int napi_id)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	if (!READ_ONCE(sk->sk_napi_id))
-		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+		WRITE_ONCE(sk->sk_napi_id, napi_id);
 #endif
 }
 
+/* variant used for unconnected sockets */
+static inline void sk_mark_napi_id_once(struct sock *sk,
+					const struct sk_buff *skb)
+{
+	__sk_mark_napi_id_once_xdp(sk, skb->napi_id);
+}
+
+static inline void sk_mark_napi_id_once_xdp(struct sock *sk,
+					    const struct xdp_buff *xdp)
+{
+	__sk_mark_napi_id_once_xdp(sk, xdp->rxq->napi_id);
+}
+
 #endif /* _LINUX_NET_BUSY_POLL_H */

include/net/xdp.h

@@ -59,6 +59,7 @@ struct xdp_rxq_info {
 	u32 queue_index;
 	u32 reg_state;
 	struct xdp_mem_info mem;
+	unsigned int napi_id;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
 struct xdp_txq_info {
@@ -226,7 +227,7 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf)
 }
 
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index);
+		     struct net_device *dev, u32 queue_index, unsigned int napi_id);
 void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
 bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);

net/core/dev.c

@@ -9810,7 +9810,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 		rx[i].dev = dev;
 
 		/* XDP RX-queue setup */
-		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0);
 		if (err < 0)
 			goto err_rxq_info;
 	}

net/core/xdp.c

@@ -158,7 +158,7 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
 
 /* Returns 0 on success, negative on failure */
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index)
+		     struct net_device *dev, u32 queue_index, unsigned int napi_id)
 {
 	if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
 		WARN(1, "Driver promised not to register this");
@@ -179,6 +179,7 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 	xdp_rxq_info_init(xdp_rxq);
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
+	xdp_rxq->napi_id = napi_id;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;
 	return 0;

net/xdp/xsk.c

@@ -233,6 +233,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
+	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	len = xdp->data_end - xdp->data;
 
 	return xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL ?