diff options
40 files changed, 300 insertions, 107 deletions
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index de6c4df61082..57420356ce4c 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -124,6 +124,9 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index d0a9ed2ca2d6..2d949969313b 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -135,6 +135,9 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 10173c32195e..f60904329bbc 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -116,6 +116,9 @@ #define SO_DETACH_REUSEPORT_BPF 0x4042 +#define SO_PREFER_BUSY_POLL 0x4043 +#define SO_BUSY_POLL_BUDGET 0x4044 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 8029b681fc7c..848a22fbac20 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -117,6 +117,9 @@ #define SO_DETACH_REUSEPORT_BPF 0x0047 +#define SO_PREFER_BUSY_POLL 0x0048 +#define SO_BUSY_POLL_BUDGET 0x0049 + #if !defined(__KERNEL__) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index e8131dadc22c..6ad59f0068f6 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/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, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7975f59735d6..725d929eddb1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/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; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 7a141ce32e86..f782e6af45e9 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/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; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index cf9400a9886d..40953980e846 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/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; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index c21548c71bb1..9f73cd7aee09 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/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; } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index fe4320e2d1f2..3124a3bf519a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/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, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index eae75260fe20..77d5eae6b4c2 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/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; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5fc2c381da55..6a4ef4934fcf 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/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; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 45ae33e15303..50e6b8b6ba7b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/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; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 82fce27f682b..4061cd7db5dd 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/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; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 183530ed4d1d..ba6dcb19bb1d 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/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; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 3069e192d773..5504cbc24970 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/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; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b0f79a5151cf..40775cb8fb2a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/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 * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 527c5f12c5af..427fc376fe1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/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; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index b150da43adb2..b4acf2f41e84 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/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; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 05e3a3b60269..9cf960a6d007 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/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, diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 19cf7cac1e6e..68fc7d317693 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/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, diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 1503cc9ec6e2..27d3c9d9210e 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/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; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 31c5e36ff706..6dd73bd0f458 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/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; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 0c3de94b5178..fa8341f8359a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/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); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3d45d56172cb..8867d39db6ac 100644 --- a/drivers/net/tun.c +++ b/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, diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 8c737668008a..9bd37c7151f8 100644 --- a/drivers/net/veth.c +++ b/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; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 21b71148c532..052975ea0af4 100644 --- a/drivers/net/virtio_net.c +++ b/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; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 920cac4385bf..b01848ef4649 100644 --- a/drivers/net/xen-netfront.c +++ b/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; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 4df61129566d..73c346e503d7 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -397,7 +397,8 @@ static void ep_busy_loop(struct eventpoll *ep, int nonblock) unsigned int napi_id = READ_ONCE(ep->napi_id); if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) - napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep); + napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false, + BUSY_POLL_BUDGET); } static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7ce648a564f7..52d1cc2bd8a7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -350,23 +350,25 @@ struct napi_struct { }; enum { - NAPI_STATE_SCHED, /* Poll is scheduled */ - NAPI_STATE_MISSED, /* reschedule a napi */ - NAPI_STATE_DISABLE, /* Disable pending */ - NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_LISTED, /* NAPI added to system lists */ - NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ - NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ + NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ + NAPI_STATE_DISABLE, /* Disable pending */ + NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ + NAPI_STATE_LISTED, /* NAPI added to system lists */ + NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ + NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ + NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ }; enum { - NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), - NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), - NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), - NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), - NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), - NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), + NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), }; enum gro_result { @@ -437,6 +439,11 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } +static inline bool napi_prefer_busy_poll(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); +} + bool napi_schedule_prep(struct napi_struct *n); /** diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index b001fa91c14e..45b3e04b99d3 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -23,6 +23,8 @@ */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) +#define BUSY_POLL_BUDGET 8 + #ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; @@ -43,7 +45,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time); void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), - void *loop_end_arg); + void *loop_end_arg, bool prefer_busy_poll, u16 budget); #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) @@ -105,7 +107,9 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) unsigned int napi_id = READ_ONCE(sk->sk_napi_id); if (napi_id >= MIN_NAPI_ID) - napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk); + napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, + READ_ONCE(sk->sk_prefer_busy_poll), + READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); #endif } @@ -131,14 +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 */ diff --git a/include/net/sock.h b/include/net/sock.h index a5c6ae78df77..77ba2c2737db 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -301,6 +301,8 @@ struct bpf_local_storage; * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner + * @sk_prefer_busy_poll: prefer busypolling over softirq processing + * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family @@ -479,6 +481,10 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; +#ifdef CONFIG_NET_RX_BUSY_POLL + u8 sk_prefer_busy_poll; + u16 sk_busy_poll_budget; +#endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; diff --git a/include/net/xdp.h b/include/net/xdp.h index 7d48b2ae217a..700ad5db7f5d 100644 --- a/include/net/xdp.h +++ b/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); diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 77f7c1638eb1..4dcd13d097a9 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -119,6 +119,9 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/core/dev.c b/net/core/dev.c index 60d325bda0d7..3b6b0e175fe7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6458,7 +6458,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); - new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED); + new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | + NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. @@ -6495,10 +6496,30 @@ static struct napi_struct *napi_by_id(unsigned int napi_id) #if defined(CONFIG_NET_RX_BUSY_POLL) -#define BUSY_POLL_BUDGET 8 +static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) +{ + if (!skip_schedule) { + gro_normal_list(napi); + __napi_schedule(napi); + return; + } + + if (napi->gro_bitmask) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + napi_gro_flush(napi, HZ >= 1000); + } -static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) + gro_normal_list(napi); + clear_bit(NAPI_STATE_SCHED, &napi->state); +} + +static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll, + u16 budget) { + bool skip_schedule = false; + unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq @@ -6515,29 +6536,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) local_bh_disable(); + if (prefer_busy_poll) { + napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); + timeout = READ_ONCE(napi->dev->gro_flush_timeout); + if (napi->defer_hard_irqs_count && timeout) { + hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); + skip_schedule = true; + } + } + /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ - rc = napi->poll(napi, BUSY_POLL_BUDGET); + rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ - trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); + trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) { - /* As the whole budget was spent, we still own the napi so can - * safely handle the rx_list. - */ - gro_normal_list(napi); - __napi_schedule(napi); - } + if (rc == budget) + __busy_poll_stop(napi, skip_schedule); local_bh_enable(); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), - void *loop_end_arg) + void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); @@ -6565,17 +6590,23 @@ restart: * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | - NAPIF_STATE_IN_BUSY_POLL)) + NAPIF_STATE_IN_BUSY_POLL)) { + if (prefer_busy_poll) + set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; + } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | - NAPIF_STATE_SCHED) != val) + NAPIF_STATE_SCHED) != val) { + if (prefer_busy_poll) + set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; + } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } - work = napi_poll(napi, BUSY_POLL_BUDGET); - trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + work = napi_poll(napi, budget); + trace_napi_poll(napi, work, budget); gro_normal_list(napi); count: if (work > 0) @@ -6588,7 +6619,7 @@ count: if (unlikely(need_resched())) { if (napi_poll) - busy_poll_stop(napi, have_poll_lock); + busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); rcu_read_unlock(); cond_resched(); @@ -6599,7 +6630,7 @@ count: cpu_relax(); } if (napi_poll) - busy_poll_stop(napi, have_poll_lock); + busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); out: rcu_read_unlock(); @@ -6650,8 +6681,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && - !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) + !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { + clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); + } return HRTIMER_NORESTART; } @@ -6709,6 +6742,7 @@ void napi_disable(struct napi_struct *n) hrtimer_cancel(&n->timer); + clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable); @@ -6781,6 +6815,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + /* The NAPI context has more processing work, but busy-polling + * is preferred. Exit early. + */ + if (napi_prefer_busy_poll(n)) { + if (napi_complete_done(n, work)) { + /* If timeout is not set, we need to make sure + * that the NAPI is re-scheduled. + */ + napi_schedule(n); + } + goto out_unlock; + } + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -9763,7 +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; } diff --git a/net/core/sock.c b/net/core/sock.c index 727ea1cc633c..d422a6808405 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1159,6 +1159,22 @@ set_sndbuf: sk->sk_ll_usec = val; } break; + case SO_PREFER_BUSY_POLL: + if (valbool && !capable(CAP_NET_ADMIN)) + ret = -EPERM; + else + WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); + break; + case SO_BUSY_POLL_BUDGET: + if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) { + ret = -EPERM; + } else { + if (val < 0 || val > U16_MAX) + ret = -EINVAL; + else + WRITE_ONCE(sk->sk_busy_poll_budget, val); + } + break; #endif case SO_MAX_PACING_RATE: @@ -1523,6 +1539,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; + case SO_PREFER_BUSY_POLL: + v.val = READ_ONCE(sk->sk_prefer_busy_poll); + break; #endif case SO_MAX_PACING_RATE: diff --git a/net/core/xdp.c b/net/core/xdp.c index 3d330ebda893..17ffd33c6b18 100644 --- a/net/core/xdp.c +++ b/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; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3e33cb6e68e6..7588e599a048 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -23,6 +23,7 @@ #include <linux/netdevice.h> #include <linux/rculist.h> #include <net/xdp_sock_drv.h> +#include <net/busy_poll.h> #include <net/xdp.h> #include "xsk_queue.h" @@ -232,6 +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 ? @@ -517,18 +519,65 @@ static int __xsk_sendmsg(struct sock *sk) return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk); } +static bool xsk_no_wakeup(struct sock *sk) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + /* Prefer busy-polling, skip the wakeup. */ + return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) && + READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID; +#else + return false; +#endif +} + static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); + struct xsk_buff_pool *pool; if (unlikely(!xsk_is_bound(xs))) return -ENXIO; if (unlikely(need_wait)) return -EOPNOTSUPP; - return __xsk_sendmsg(sk); + if (sk_can_busy_loop(sk)) + sk_busy_loop(sk, 1); /* only support non-blocking sockets */ + + if (xsk_no_wakeup(sk)) + return 0; + + pool = xs->pool; + if (pool->cached_need_wakeup & XDP_WAKEUP_TX) + return __xsk_sendmsg(sk); + return 0; +} + +static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) +{ + bool need_wait = !(flags & MSG_DONTWAIT); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + if (unlikely(!xs->rx)) + return -ENOBUFS; + if (unlikely(!xsk_is_bound(xs))) + return -ENXIO; + if (unlikely(need_wait)) + return -EOPNOTSUPP; + + if (sk_can_busy_loop(sk)) + sk_busy_loop(sk, 1); /* only support non-blocking sockets */ + + if (xsk_no_wakeup(sk)) + return 0; + + if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc) + return xsk_wakeup(xs, XDP_WAKEUP_RX); + return 0; } static __poll_t xsk_poll(struct file *file, struct socket *sock, @@ -1191,7 +1240,7 @@ static const struct proto_ops xsk_proto_ops = { .setsockopt = xsk_setsockopt, .getsockopt = xsk_getsockopt, .sendmsg = xsk_sendmsg, - .recvmsg = sock_no_recvmsg, + .recvmsg = xsk_recvmsg, .mmap = xsk_mmap, .sendpage = sock_no_sendpage, }; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 8a3bf4e1318e..96bb607853ad 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -144,14 +144,13 @@ static int __xp_assign_dev(struct xsk_buff_pool *pool, if (err) return err; - if (flags & XDP_USE_NEED_WAKEUP) { + if (flags & XDP_USE_NEED_WAKEUP) pool->uses_need_wakeup = true; - /* Tx needs to be explicitly woken up the first time. - * Also for supporting drivers that do not implement this - * feature. They will always have to call sendto(). - */ - pool->cached_need_wakeup = XDP_WAKEUP_TX; - } + /* Tx needs to be explicitly woken up the first time. Also + * for supporting drivers that do not implement this + * feature. They will always have to call sendto() or poll(). + */ + pool->cached_need_wakeup = XDP_WAKEUP_TX; dev_hold(netdev); diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 2567f0db5aca..036bd019e400 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -95,6 +95,7 @@ static int opt_timeout = 1000; static bool opt_need_wakeup = true; static u32 opt_num_xsks = 1; static u32 prog_id; +static bool opt_busy_poll; struct xsk_ring_stats { unsigned long rx_npkts; @@ -911,6 +912,7 @@ static struct option long_options[] = { {"quiet", no_argument, 0, 'Q'}, {"app-stats", no_argument, 0, 'a'}, {"irq-string", no_argument, 0, 'I'}, + {"busy-poll", no_argument, 0, 'B'}, {0, 0, 0, 0} }; @@ -949,6 +951,7 @@ static void usage(const char *prog) " -Q, --quiet Do not display any stats.\n" " -a, --app-stats Display application (syscall) statistics.\n" " -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n" + " -B, --busy-poll Busy poll.\n" "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE, @@ -964,7 +967,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:", + c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:B", long_options, &option_index); if (c == -1) break; @@ -1062,7 +1065,9 @@ static void parse_command_line(int argc, char **argv) fprintf(stderr, "ERROR: Failed to get irqs for %s\n", opt_irq_str); usage(basename(argv[0])); } - + break; + case 'B': + opt_busy_poll = 1; break; default: usage(basename(argv[0])); @@ -1098,8 +1103,7 @@ static void kick_tx(struct xsk_socket_info *xsk) exit_with_error(errno); } -static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, - struct pollfd *fds) +static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) { struct xsk_umem_info *umem = xsk->umem; u32 idx_cq = 0, idx_fq = 0; @@ -1132,9 +1136,10 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, + NULL); } ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } @@ -1170,7 +1175,7 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk, } } -static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) +static void rx_drop(struct xsk_socket_info *xsk) { unsigned int rcvd, i; u32 idx_rx = 0, idx_fq = 0; @@ -1178,9 +1183,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } return; } @@ -1189,9 +1194,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); } @@ -1233,7 +1238,7 @@ static void rx_drop_all(void) } for (i = 0; i < num_socks; i++) - rx_drop(xsks[i], fds); + rx_drop(xsks[i]); if (benchmark_done) break; @@ -1331,19 +1336,19 @@ static void tx_only_all(void) complete_tx_only_all(); } -static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) +static void l2fwd(struct xsk_socket_info *xsk) { unsigned int rcvd, i; u32 idx_rx = 0, idx_tx = 0; int ret; - complete_tx_l2fwd(xsk, fds); + complete_tx_l2fwd(xsk); rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } return; } @@ -1353,8 +1358,8 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - complete_tx_l2fwd(xsk, fds); - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + complete_tx_l2fwd(xsk); + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->tx)) { xsk->app_stats.tx_wakeup_sendtos++; kick_tx(xsk); } @@ -1388,22 +1393,20 @@ static void l2fwd_all(void) struct pollfd fds[MAX_SOCKS] = {}; int i, ret; - for (i = 0; i < num_socks; i++) { - fds[i].fd = xsk_socket__fd(xsks[i]->xsk); - fds[i].events = POLLOUT | POLLIN; - } - for (;;) { if (opt_poll) { - for (i = 0; i < num_socks; i++) + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); + fds[i].events = POLLOUT | POLLIN; xsks[i]->app_stats.opt_polls++; + } ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; } for (i = 0; i < num_socks; i++) - l2fwd(xsks[i], fds); + l2fwd(xsks[i]); if (benchmark_done) break; @@ -1461,6 +1464,29 @@ static void enter_xsks_into_map(struct bpf_object *obj) } } +static void apply_setsockopt(struct xsk_socket_info *xsk) +{ + int sock_opt; + + if (!opt_busy_poll) + return; + + sock_opt = 1; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = 20; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = opt_batch_size; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); +} + int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; @@ -1502,6 +1528,9 @@ int main(int argc, char **argv) for (i = 0; i < opt_num_xsks; i++) xsks[num_socks++] = xsk_configure_socket(umem, rx, tx); + for (i = 0; i < opt_num_xsks; i++) + apply_setsockopt(xsks[i]); + if (opt_bench == BENCH_TXONLY) { gen_eth_hdr_data(); |