diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igb/igb_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 449 |
1 files changed, 305 insertions, 144 deletions
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a3f100769e39..9e9a5900e6e5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -106,8 +106,6 @@ static int igb_setup_all_rx_resources(struct igb_adapter *); static void igb_free_all_tx_resources(struct igb_adapter *); static void igb_free_all_rx_resources(struct igb_adapter *); static void igb_setup_mrqc(struct igb_adapter *); -static int igb_probe(struct pci_dev *, const struct pci_device_id *); -static void igb_remove(struct pci_dev *pdev); static void igb_init_queue_configuration(struct igb_adapter *adapter); static int igb_sw_init(struct igb_adapter *); int igb_open(struct net_device *); @@ -117,8 +115,6 @@ static void igb_configure_tx(struct igb_adapter *); static void igb_configure_rx(struct igb_adapter *); static void igb_clean_all_tx_rings(struct igb_adapter *); static void igb_clean_all_rx_rings(struct igb_adapter *); -static void igb_clean_tx_ring(struct igb_ring *); -static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); static void igb_update_phy_info(struct timer_list *); static void igb_watchdog(struct timer_list *); @@ -178,20 +174,6 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf); static int igb_disable_sriov(struct pci_dev *dev, bool reinit); #endif -static int igb_suspend(struct device *); -static int igb_resume(struct device *); -static int igb_runtime_suspend(struct device *dev); -static int igb_runtime_resume(struct device *dev); -static int igb_runtime_idle(struct device *dev); -#ifdef CONFIG_PM -static const struct dev_pm_ops igb_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(igb_suspend, igb_resume) - SET_RUNTIME_PM_OPS(igb_runtime_suspend, igb_runtime_resume, - igb_runtime_idle) -}; -#endif -static void igb_shutdown(struct pci_dev *); -static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs); #ifdef CONFIG_IGB_DCA static int igb_notify_dca(struct notifier_block *, unsigned long, void *); static struct notifier_block dca_notifier = { @@ -219,20 +201,6 @@ static const struct pci_error_handlers igb_err_handler = { static void igb_init_dmac(struct igb_adapter *adapter, u32 pba); -static struct pci_driver igb_driver = { - .name = igb_driver_name, - .id_table = igb_pci_tbl, - .probe = igb_probe, - .remove = igb_remove, -#ifdef CONFIG_PM - .driver.pm = &igb_pm_ops, -#endif - .shutdown = igb_shutdown, - .sriov_configure = igb_pci_sriov_configure, - .err_handler = &igb_err_handler -}; - -MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); MODULE_LICENSE("GPL v2"); @@ -504,12 +472,17 @@ rx_ring_summary: for (i = 0; i < rx_ring->count; i++) { const char *next_desc; - struct igb_rx_buffer *buffer_info; - buffer_info = &rx_ring->rx_buffer_info[i]; + dma_addr_t dma = (dma_addr_t)0; + struct igb_rx_buffer *buffer_info = NULL; rx_desc = IGB_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + if (!rx_ring->xsk_pool) { + buffer_info = &rx_ring->rx_buffer_info[i]; + dma = buffer_info->dma; + } + if (i == rx_ring->next_to_use) next_desc = " NTU"; else if (i == rx_ring->next_to_clean) @@ -529,11 +502,11 @@ rx_ring_summary: "R ", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - (u64)buffer_info->dma, + (u64)dma, next_desc); if (netif_msg_pktdata(adapter) && - buffer_info->dma && buffer_info->page) { + buffer_info && dma && buffer_info->page) { print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, @@ -647,6 +620,8 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw) return adapter->netdev; } +static struct pci_driver igb_driver; + /** * igb_init_module - Driver Registration Routine * @@ -664,6 +639,10 @@ static int __init igb_init_module(void) dca_register_notify(&dca_notifier); #endif ret = pci_register_driver(&igb_driver); +#ifdef CONFIG_IGB_DCA + if (ret) + dca_unregister_notify(&dca_notifier); +#endif return ret; } @@ -968,6 +947,9 @@ static int igb_request_msix(struct igb_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igb_configure_msix(adapter); @@ -1215,7 +1197,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, return -ENOMEM; /* initialize NAPI */ - netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll); + netif_napi_add_config(adapter->netdev, &q_vector->napi, igb_poll, + v_idx); /* tie q_vector and adapter together */ adapter->q_vector[v_idx] = q_vector; @@ -1231,7 +1214,7 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, /* initialize pointer to rings */ ring = q_vector->ring; - /* intialize ITR */ + /* initialize ITR */ if (rxr_count) { /* rx or rx/tx vector */ if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3) @@ -2013,7 +1996,11 @@ static void igb_configure(struct igb_adapter *adapter) */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); + if (ring->xsk_pool) + igb_alloc_rx_buffers_zc(ring, ring->xsk_pool, + igb_desc_unused(ring)); + else + igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); } } @@ -2113,6 +2100,22 @@ static void igb_check_swap_media(struct igb_adapter *adapter) wr32(E1000_CTRL_EXT, ctrl_ext); } +void igb_set_queue_napi(struct igb_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igb_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igb_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -2120,6 +2123,7 @@ static void igb_check_swap_media(struct igb_adapter *adapter) int igb_up(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + struct napi_struct *napi; int i; /* hardware has been reset, we need to reload some things */ @@ -2127,8 +2131,11 @@ int igb_up(struct igb_adapter *adapter) clear_bit(__IGB_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&(adapter->q_vector[i]->napi)); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igb_set_queue_napi(adapter, i, napi); + } if (adapter->flags & IGB_FLAG_HAS_MSIX) igb_configure_msix(adapter); @@ -2198,12 +2205,13 @@ void igb_down(struct igb_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igb_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); /* record the stats before reset*/ spin_lock(&adapter->stats64_lock); @@ -2513,7 +2521,7 @@ static int igb_set_features(struct net_device *netdev, static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, + u16 flags, bool *notified, struct netlink_ext_ack *extack) { /* guarantee we can provide a unique filter for the unicast address */ @@ -2624,6 +2632,9 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, return -EOPNOTSUPP; } + if (flow_rule_match_has_control_flags(rule, extack)) + return -EOPNOTSUPP; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -2931,34 +2942,20 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { + struct igb_adapter *adapter = netdev_priv(dev); + switch (xdp->command) { case XDP_SETUP_PROG: return igb_xdp_setup(dev, xdp); + case XDP_SETUP_XSK_POOL: + return igb_xsk_pool_setup(adapter, xdp->xsk.pool, + xdp->xsk.queue_id); default: return -EINVAL; } } -static void igb_xdp_ring_update_tail(struct igb_ring *ring) -{ - /* Force memory writes to complete before letting h/w know there - * are new descriptors to fetch. - */ - wmb(); - writel(ring->next_to_use, ring->tail); -} - -static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) -{ - unsigned int r_idx = smp_processor_id(); - - if (r_idx >= adapter->num_tx_queues) - r_idx = r_idx % adapter->num_tx_queues; - - return adapter->tx_ring[r_idx]; -} - -static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) { struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); int cpu = smp_processor_id(); @@ -2972,7 +2969,8 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return IGB_XDP_CONSUMED; @@ -3005,10 +3003,14 @@ static int igb_xdp_xmit(struct net_device *dev, int n, /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return -ENXIO; + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return -ENXIO; + nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); @@ -3025,11 +3027,11 @@ static int igb_xdp_xmit(struct net_device *dev, int n, nxmit++; } - __netif_tx_unlock(nq); - if (unlikely(flags & XDP_XMIT_FLUSH)) igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + return nxmit; } @@ -3059,6 +3061,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_setup_tc = igb_setup_tc, .ndo_bpf = igb_xdp, .ndo_xdp_xmit = igb_xdp_xmit, + .ndo_xsk_wakeup = igb_xsk_wakeup, }; /** @@ -3355,7 +3358,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_SUPP_NOFCS; netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; @@ -3881,8 +3885,8 @@ static void igb_remove(struct pci_dev *pdev) * disable watchdog from being rescheduled. */ set_bit(__IGB_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); @@ -3927,7 +3931,7 @@ static void igb_remove(struct pci_dev *pdev) * * This function initializes the vf specific data storage and then attempts to * allocate the VFs. The reason for ordering it this way is because it is much - * mor expensive time wise to disable SR-IOV than it is to allocate and free + * more expensive time wise to disable SR-IOV than it is to allocate and free * the memory for the VFs. **/ static void igb_probe_vfs(struct igb_adapter *adapter) @@ -4134,8 +4138,9 @@ static int igb_sw_init(struct igb_adapter *adapter) static int __igb_open(struct net_device *netdev, bool resuming) { struct igb_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; + struct e1000_hw *hw = &adapter->hw; + struct napi_struct *napi; int err; int i; @@ -4187,8 +4192,11 @@ static int __igb_open(struct net_device *netdev, bool resuming) /* From here on the code is the same as igb_up() */ clear_bit(__IGB_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&(adapter->q_vector[i]->napi)); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igb_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(E1000_TSICR); @@ -4381,6 +4389,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, u64 tdba = ring->dma; int reg_idx = ring->reg_idx; + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + wr32(E1000_TDLEN(reg_idx), ring->count * sizeof(union e1000_adv_tx_desc)); wr32(E1000_TDBAL(reg_idx), @@ -4441,7 +4451,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, 0); + rx_ring->queue_index, + rx_ring->q_vector->napi.napi_id); if (res < 0) { dev_err(dev, "Failed to register xdp_rxq index %u\n", rx_ring->queue_index); @@ -4737,12 +4748,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring) struct e1000_hw *hw = &adapter->hw; int reg_idx = ring->reg_idx; u32 srrctl = 0; + u32 buf_size; - srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - if (ring_uses_large_buffer(ring)) - srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring->xsk_pool) + buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool); + else if (ring_uses_large_buffer(ring)) + buf_size = IGB_RXBUFFER_3072; else - srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + buf_size = IGB_RXBUFFER_2048; + + srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; + srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -4774,8 +4790,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, u32 rxdctl = 0; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL)); + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL)); + } /* disable the queue */ wr32(E1000_RXDCTL(reg_idx), 0); @@ -4802,9 +4827,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; - /* initialize rx_buffer_info */ - memset(ring->rx_buffer_info, 0, - sizeof(struct igb_rx_buffer) * ring->count); + if (ring->xsk_pool) + memset(ring->rx_buffer_info_zc, 0, + sizeof(*ring->rx_buffer_info_zc) * ring->count); + else + memset(ring->rx_buffer_info, 0, + sizeof(*ring->rx_buffer_info) * ring->count); /* initialize Rx descriptor 0 */ rx_desc = IGB_RX_DESC(ring, 0); @@ -4833,6 +4861,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, #if (PAGE_SIZE < 8192) if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + IGB_2K_TOO_SMALL_WITH_PADDING || rd32(E1000_RCTL) & E1000_RCTL_SBP) set_ring_uses_large_buffer(rx_ring); #endif @@ -4904,19 +4933,24 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ -static void igb_clean_tx_ring(struct igb_ring *tx_ring) +void igb_clean_tx_ring(struct igb_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + u32 xsk_frames = 0; while (i != tx_ring->next_to_use) { union e1000_adv_tx_desc *eop_desc, *tx_desc; /* Free all the Tx ring sk_buffs or xdp frames */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { dev_kfree_skb_any(tx_buffer->skb); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -4947,6 +4981,7 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } +skip_for_xsk: tx_buffer->next_to_watch = NULL; /* move us one more past the eop_desc for start of next pkt */ @@ -4961,6 +4996,9 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); + if (tx_ring->xsk_pool && xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -4991,8 +5029,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring) rx_ring->xdp_prog = NULL; xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - vfree(rx_ring->rx_buffer_info); - rx_ring->rx_buffer_info = NULL; + if (rx_ring->xsk_pool) { + vfree(rx_ring->rx_buffer_info_zc); + rx_ring->rx_buffer_info_zc = NULL; + } else { + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + } /* if not set, then don't free */ if (!rx_ring->desc) @@ -5023,13 +5066,18 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) * igb_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from **/ -static void igb_clean_rx_ring(struct igb_ring *rx_ring) +void igb_clean_rx_ring(struct igb_ring *rx_ring) { u16 i = rx_ring->next_to_clean; dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; + if (rx_ring->xsk_pool) { + igb_clean_rx_ring_zc(rx_ring); + goto skip_for_xsk; + } + /* Free all the Rx ring sk_buffs */ while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; @@ -5057,6 +5105,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) i = 0; } +skip_for_xsk: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -5706,11 +5755,29 @@ no_wait: if (adapter->flags & IGB_FLAG_HAS_MSIX) { u32 eics = 0; - for (i = 0; i < adapter->num_q_vectors; i++) - eics |= adapter->q_vector[i]->eims_value; - wr32(E1000_EICS, eics); + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igb_q_vector *q_vector = adapter->q_vector[i]; + struct igb_ring *rx_ring; + + if (!q_vector->rx.ring) + continue; + + rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index]; + + if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + eics |= q_vector->eims_value; + clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + } + } + if (eics) + wr32(E1000_EICS, eics); } else { - wr32(E1000_ICS, E1000_ICS_RXDMT0); + struct igb_ring *rx_ring = adapter->rx_ring[0]; + + if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } } igb_spoof_check(adapter); @@ -6483,6 +6550,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return NETDEV_TX_BUSY; + /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; first->type = IGB_TYPE_SKB; @@ -6638,7 +6708,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_adapter *adapter = netdev_priv(netdev); int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; - if (adapter->xdp_prog) { + if (igb_xdp_is_enabled(adapter)) { int i; for (i = 0; i < adapter->num_rx_queues; i++) { @@ -6668,7 +6738,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) igb_up(adapter); @@ -6984,10 +7054,20 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) static void igb_tsync_interrupt(struct igb_adapter *adapter) { + const u32 mask = (TSINTR_SYS_WRAP | E1000_TSICR_TXTS | + TSINTR_TT0 | TSINTR_TT1 | + TSINTR_AUTT0 | TSINTR_AUTT1); struct e1000_hw *hw = &adapter->hw; u32 tsicr = rd32(E1000_TSICR); struct ptp_clock_event event; + if (hw->mac.type == e1000_82580) { + /* 82580 has a hardware bug that requires an explicit + * write to clear the TimeSync interrupt cause. + */ + wr32(E1000_TSICR, tsicr & mask); + } + if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) @@ -8201,6 +8281,7 @@ static int igb_poll(struct napi_struct *napi, int budget) struct igb_q_vector *q_vector = container_of(napi, struct igb_q_vector, napi); + struct xsk_buff_pool *xsk_pool; bool clean_complete = true; int work_done = 0; @@ -8212,7 +8293,12 @@ static int igb_poll(struct napi_struct *napi, int budget) clean_complete = igb_clean_tx_irq(q_vector, budget); if (q_vector->rx.ring) { - int cleaned = igb_clean_rx_irq(q_vector, budget); + int cleaned; + + xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool); + cleaned = xsk_pool ? + igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) : + igb_clean_rx_irq(q_vector, budget); work_done += cleaned; if (cleaned >= budget) @@ -8241,13 +8327,18 @@ static int igb_poll(struct napi_struct *napi, int budget) **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) { - struct igb_adapter *adapter = q_vector->adapter; - struct igb_ring *tx_ring = q_vector->tx.ring; - struct igb_tx_buffer *tx_buffer; - union e1000_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; + struct igb_adapter *adapter = q_vector->adapter; unsigned int budget = q_vector->tx.work_limit; + struct igb_ring *tx_ring = q_vector->tx.ring; unsigned int i = tx_ring->next_to_clean; + union e1000_adv_tx_desc *tx_desc; + struct igb_tx_buffer *tx_buffer; + struct xsk_buff_pool *xsk_pool; + int cpu = smp_processor_id(); + bool xsk_xmit_done = true; + struct netdev_queue *nq; + u32 xsk_frames = 0; if (test_bit(__IGB_DOWN, &adapter->state)) return true; @@ -8278,10 +8369,14 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) total_packets += tx_buffer->gso_segs; /* free the skb */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { napi_consume_skb(tx_buffer->skb, napi_budget); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -8313,6 +8408,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } +skip_for_xsk: /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; tx_desc++; @@ -8341,6 +8437,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + xsk_pool = READ_ONCE(tx_ring->xsk_pool); + if (xsk_pool) { + if (xsk_frames) + xsk_tx_completed(xsk_pool, xsk_frames); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + xsk_xmit_done = igb_xmit_zc(tx_ring, xsk_pool); + __netif_tx_unlock(nq); + } + if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct e1000_hw *hw = &adapter->hw; @@ -8403,7 +8514,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } - return !!budget; + return !!budget && xsk_xmit_done; } /** @@ -8594,9 +8705,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, return skb; } -static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, - struct igb_ring *rx_ring, - struct xdp_buff *xdp) +static int igb_run_xdp(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IGB_XDP_PASS; struct bpf_prog *xdp_prog; @@ -8636,7 +8746,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring, @@ -8762,10 +8872,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@ -8792,9 +8898,9 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, * order to populate the hash, checksum, VLAN, timestamp, protocol, and * other fields within the skb. **/ -static void igb_process_skb_fields(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *dev = rx_ring->netdev; @@ -8876,17 +8982,50 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring, rx_buffer->page = NULL; } +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + + if (status & IGB_XDP_REDIR) + xdp_do_flush(); + + if (status & IGB_XDP_TX) { + struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + } +} + +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes) +{ + struct igb_ring *ring = q_vector->rx.ring; + + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.packets += packets; + ring->rx_stats.bytes += bytes; + u64_stats_update_end(&ring->rx_syncp); + + q_vector->rx.total_packets += packets; + q_vector->rx.total_bytes += bytes; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { + unsigned int total_bytes = 0, total_packets = 0; struct igb_adapter *adapter = q_vector->adapter; struct igb_ring *rx_ring = q_vector->rx.ring; - struct sk_buff *skb = rx_ring->skb; - unsigned int total_bytes = 0, total_packets = 0; u16 cleaned_count = igb_desc_unused(rx_ring); + struct sk_buff *skb = rx_ring->skb; unsigned int xdp_xmit = 0; struct xdp_buff xdp; u32 frame_sz = 0; int rx_buf_pgcnt; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -8944,12 +9083,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size); #endif - skb = igb_run_xdp(adapter, rx_ring, &xdp); + xdp_res = igb_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) { xdp_xmit |= xdp_res; igb_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -8968,9 +9105,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) &xdp, timestamp); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); break; } @@ -8982,7 +9120,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igb_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igb_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -9005,21 +9143,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; - if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush(); - - if (xdp_xmit & IGB_XDP_TX) { - struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); - - igb_xdp_ring_update_tail(tx_ring); - } + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + igb_update_rx_stats(q_vector, total_packets, total_bytes); if (cleaned_count) igb_alloc_rx_buffers(rx_ring, cleaned_count); @@ -9041,6 +9168,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -9057,6 +9185,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, __free_pages(page, igb_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_failed++; + set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -9163,6 +9292,10 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return -EIO; break; case SIOCSMIIREG: + if (igb_write_phy_reg(&adapter->hw, data->reg_num & 0x1F, + data->val_in)) + return -EIO; + break; default: return -EOPNOTSUPP; } @@ -9453,12 +9586,12 @@ static void igb_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int __maybe_unused igb_suspend(struct device *dev) +static int igb_suspend(struct device *dev) { return __igb_shutdown(to_pci_dev(dev), NULL, 0); } -static int __maybe_unused __igb_resume(struct device *dev, bool rpm) +static int __igb_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -9514,12 +9647,12 @@ static int __maybe_unused __igb_resume(struct device *dev, bool rpm) return err; } -static int __maybe_unused igb_resume(struct device *dev) +static int igb_resume(struct device *dev) { return __igb_resume(dev, false); } -static int __maybe_unused igb_runtime_idle(struct device *dev) +static int igb_runtime_idle(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); struct igb_adapter *adapter = netdev_priv(netdev); @@ -9530,12 +9663,12 @@ static int __maybe_unused igb_runtime_idle(struct device *dev) return -EBUSY; } -static int __maybe_unused igb_runtime_suspend(struct device *dev) +static int igb_runtime_suspend(struct device *dev) { return __igb_shutdown(to_pci_dev(dev), NULL, 1); } -static int __maybe_unused igb_runtime_resume(struct device *dev) +static int igb_runtime_resume(struct device *dev) { return __igb_resume(dev, true); } @@ -9591,8 +9724,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, if (state == pci_channel_io_perm_failure) return PCI_ERS_RESULT_DISCONNECT; + rtnl_lock(); if (netif_running(netdev)) igb_down(adapter); + rtnl_unlock(); + pci_disable_device(pdev); /* Request a slot reset. */ @@ -9651,12 +9787,21 @@ static void igb_io_resume(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); if (netif_running(netdev)) { + if (!test_bit(__IGB_DOWN, &adapter->state)) { + dev_dbg(&pdev->dev, "Resuming from non-fatal error, do nothing.\n"); + rtnl_unlock(); + return; + } + if (igb_up(adapter)) { dev_err(&pdev->dev, "igb_up failed after reset\n"); + rtnl_unlock(); return; } } + rtnl_unlock(); netif_device_attach(netdev); @@ -10157,4 +10302,20 @@ static void igb_nfc_filter_restore(struct igb_adapter *adapter) spin_unlock(&adapter->nfc_lock); } + +static _DEFINE_DEV_PM_OPS(igb_pm_ops, igb_suspend, igb_resume, + igb_runtime_suspend, igb_runtime_resume, + igb_runtime_idle); + +static struct pci_driver igb_driver = { + .name = igb_driver_name, + .id_table = igb_pci_tbl, + .probe = igb_probe, + .remove = igb_remove, + .driver.pm = pm_ptr(&igb_pm_ops), + .shutdown = igb_shutdown, + .sriov_configure = igb_pci_sriov_configure, + .err_handler = &igb_err_handler +}; + /* igb_main.c */ |