diff options
Diffstat (limited to 'drivers/net/ethernet/cisco/enic/enic_main.c')
-rw-r--r-- | drivers/net/ethernet/cisco/enic/enic_main.c | 345 |
1 files changed, 43 insertions, 302 deletions
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 49f6cab01ed5..c753c35b26eb 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -58,18 +58,15 @@ #include "enic_dev.h" #include "enic_pp.h" #include "enic_clsf.h" +#include "enic_rq.h" +#include "enic_wq.h" #define ENIC_NOTIFY_TIMER_PERIOD (2 * HZ) -#define WQ_ENET_MAX_DESC_LEN (1 << WQ_ENET_LEN_BITS) -#define MAX_TSO (1 << 16) -#define ENIC_DESC_MAX_SPLITS (MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1) #define PCI_DEVICE_ID_CISCO_VIC_ENET 0x0043 /* ethernet vnic */ #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN 0x0044 /* enet dynamic vnic */ #define PCI_DEVICE_ID_CISCO_VIC_ENET_VF 0x0071 /* enet SRIOV VF */ -#define RX_COPYBREAK_DEFAULT 256 - /* Supported devices */ static const struct pci_device_id enic_id_table[] = { { PCI_VDEVICE(CISCO, PCI_DEVICE_ID_CISCO_VIC_ENET) }, @@ -322,54 +319,6 @@ int enic_is_valid_vf(struct enic *enic, int vf) #endif } -static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf) -{ - struct enic *enic = vnic_dev_priv(wq->vdev); - - if (buf->sop) - dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, - DMA_TO_DEVICE); - else - dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len, - DMA_TO_DEVICE); - - if (buf->os_buf) - dev_kfree_skb_any(buf->os_buf); -} - -static void enic_wq_free_buf(struct vnic_wq *wq, - struct cq_desc *cq_desc, struct vnic_wq_buf *buf, void *opaque) -{ - struct enic *enic = vnic_dev_priv(wq->vdev); - - enic->wq[wq->index].stats.cq_work++; - enic->wq[wq->index].stats.cq_bytes += buf->len; - enic_free_wq_buf(wq, buf); -} - -static int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, - u8 type, u16 q_number, u16 completed_index, void *opaque) -{ - struct enic *enic = vnic_dev_priv(vdev); - - spin_lock(&enic->wq[q_number].lock); - - vnic_wq_service(&enic->wq[q_number].vwq, cq_desc, - completed_index, enic_wq_free_buf, - opaque); - - if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number)) && - vnic_wq_desc_avail(&enic->wq[q_number].vwq) >= - (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) { - netif_wake_subqueue(enic->netdev, q_number); - enic->wq[q_number].stats.wake++; - } - - spin_unlock(&enic->wq[q_number].lock); - - return 0; -} - static bool enic_log_q_error(struct enic *enic) { unsigned int i; @@ -1313,243 +1262,6 @@ nla_put_failure: return -EMSGSIZE; } -static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf) -{ - struct enic *enic = vnic_dev_priv(rq->vdev); - - if (!buf->os_buf) - return; - - dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, - DMA_FROM_DEVICE); - dev_kfree_skb_any(buf->os_buf); - buf->os_buf = NULL; -} - -static int enic_rq_alloc_buf(struct vnic_rq *rq) -{ - struct enic *enic = vnic_dev_priv(rq->vdev); - struct net_device *netdev = enic->netdev; - struct sk_buff *skb; - unsigned int len = netdev->mtu + VLAN_ETH_HLEN; - unsigned int os_buf_index = 0; - dma_addr_t dma_addr; - struct vnic_rq_buf *buf = rq->to_use; - - if (buf->os_buf) { - enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr, - buf->len); - - return 0; - } - skb = netdev_alloc_skb_ip_align(netdev, len); - if (!skb) { - enic->rq[rq->index].stats.no_skb++; - return -ENOMEM; - } - - dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len, - DMA_FROM_DEVICE); - if (unlikely(enic_dma_map_check(enic, dma_addr))) { - dev_kfree_skb(skb); - return -ENOMEM; - } - - enic_queue_rq_desc(rq, skb, os_buf_index, - dma_addr, len); - - return 0; -} - -static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size, - u32 pkt_len) -{ - if (ENIC_LARGE_PKT_THRESHOLD <= pkt_len) - pkt_size->large_pkt_bytes_cnt += pkt_len; - else - pkt_size->small_pkt_bytes_cnt += pkt_len; -} - -static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb, - struct vnic_rq_buf *buf, u16 len) -{ - struct enic *enic = netdev_priv(netdev); - struct sk_buff *new_skb; - - if (len > enic->rx_copybreak) - return false; - new_skb = netdev_alloc_skb_ip_align(netdev, len); - if (!new_skb) - return false; - dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len, - DMA_FROM_DEVICE); - memcpy(new_skb->data, (*skb)->data, len); - *skb = new_skb; - - return true; -} - -static void enic_rq_indicate_buf(struct vnic_rq *rq, - struct cq_desc *cq_desc, struct vnic_rq_buf *buf, - int skipped, void *opaque) -{ - struct enic *enic = vnic_dev_priv(rq->vdev); - struct net_device *netdev = enic->netdev; - struct sk_buff *skb; - struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)]; - struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats; - - u8 type, color, eop, sop, ingress_port, vlan_stripped; - u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof; - u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok; - u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc; - u8 packet_error; - u16 q_number, completed_index, bytes_written, vlan_tci, checksum; - u32 rss_hash; - bool outer_csum_ok = true, encap = false; - - rqstats->packets++; - if (skipped) { - rqstats->desc_skip++; - return; - } - - skb = buf->os_buf; - - cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, - &type, &color, &q_number, &completed_index, - &ingress_port, &fcoe, &eop, &sop, &rss_type, - &csum_not_calc, &rss_hash, &bytes_written, - &packet_error, &vlan_stripped, &vlan_tci, &checksum, - &fcoe_sof, &fcoe_fc_crc_ok, &fcoe_enc_error, - &fcoe_eof, &tcp_udp_csum_ok, &udp, &tcp, - &ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment, - &fcs_ok); - - if (packet_error) { - - if (!fcs_ok) { - if (bytes_written > 0) - rqstats->bad_fcs++; - else if (bytes_written == 0) - rqstats->pkt_truncated++; - } - - dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, - DMA_FROM_DEVICE); - dev_kfree_skb_any(skb); - buf->os_buf = NULL; - - return; - } - - if (eop && bytes_written > 0) { - - /* Good receive - */ - rqstats->bytes += bytes_written; - if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) { - buf->os_buf = NULL; - dma_unmap_single(&enic->pdev->dev, buf->dma_addr, - buf->len, DMA_FROM_DEVICE); - } - prefetch(skb->data - NET_IP_ALIGN); - - skb_put(skb, bytes_written); - skb->protocol = eth_type_trans(skb, netdev); - skb_record_rx_queue(skb, q_number); - if ((netdev->features & NETIF_F_RXHASH) && rss_hash && - (type == 3)) { - switch (rss_type) { - case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4: - case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6: - case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX: - skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4); - rqstats->l4_rss_hash++; - break; - case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4: - case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6: - case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX: - skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3); - rqstats->l3_rss_hash++; - break; - } - } - if (enic->vxlan.vxlan_udp_port_number) { - switch (enic->vxlan.patch_level) { - case 0: - if (fcoe) { - encap = true; - outer_csum_ok = fcoe_fc_crc_ok; - } - break; - case 2: - if ((type == 7) && - (rss_hash & BIT(0))) { - encap = true; - outer_csum_ok = (rss_hash & BIT(1)) && - (rss_hash & BIT(2)); - } - break; - } - } - - /* Hardware does not provide whole packet checksum. It only - * provides pseudo checksum. Since hw validates the packet - * checksum but not provide us the checksum value. use - * CHECSUM_UNNECESSARY. - * - * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is - * inner csum_ok. outer_csum_ok is set by hw when outer udp - * csum is correct or is zero. - */ - if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc && - tcp_udp_csum_ok && outer_csum_ok && - (ipv4_csum_ok || ipv6)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = encap; - if (encap) - rqstats->csum_unnecessary_encap++; - else - rqstats->csum_unnecessary++; - } - - if (vlan_stripped) { - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); - rqstats->vlan_stripped++; - } - skb_mark_napi_id(skb, &enic->napi[rq->index]); - if (!(netdev->features & NETIF_F_GRO)) - netif_receive_skb(skb); - else - napi_gro_receive(&enic->napi[q_number], skb); - if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce) - enic_intr_update_pkt_size(&cq->pkt_size_counter, - bytes_written); - } else { - - /* Buffer overflow - */ - rqstats->pkt_truncated++; - dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len, - DMA_FROM_DEVICE); - dev_kfree_skb_any(skb); - buf->os_buf = NULL; - } -} - -static int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, - u8 type, u16 q_number, u16 completed_index, void *opaque) -{ - struct enic *enic = vnic_dev_priv(vdev); - - vnic_rq_service(&enic->rq[q_number].vrq, cq_desc, - completed_index, VNIC_RQ_RETURN_DESC, - enic_rq_indicate_buf, opaque); - - return 0; -} - static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq) { unsigned int intr = enic_msix_rq_intr(enic, rq->index); @@ -1620,12 +1332,10 @@ static int enic_poll(struct napi_struct *napi, int budget) unsigned int work_done, rq_work_done = 0, wq_work_done; int err; - wq_work_done = vnic_cq_service(&enic->cq[cq_wq], wq_work_to_do, - enic_wq_service, NULL); + wq_work_done = enic_wq_cq_service(enic, cq_wq, wq_work_to_do); if (budget > 0) - rq_work_done = vnic_cq_service(&enic->cq[cq_rq], - rq_work_to_do, enic_rq_service, NULL); + rq_work_done = enic_rq_cq_service(enic, cq_rq, rq_work_to_do); /* Accumulate intr event credits for this polling * cycle. An intr event is the completion of a @@ -1724,8 +1434,8 @@ static int enic_poll_msix_wq(struct napi_struct *napi, int budget) wq_irq = wq->index; cq = enic_cq_wq(enic, wq_irq); intr = enic_msix_wq_intr(enic, wq_irq); - wq_work_done = vnic_cq_service(&enic->cq[cq], wq_work_to_do, - enic_wq_service, NULL); + + wq_work_done = enic_wq_cq_service(enic, cq, wq_work_to_do); vnic_intr_return_credits(&enic->intr[intr], wq_work_done, 0 /* don't unmask intr */, @@ -1754,8 +1464,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget) */ if (budget > 0) - work_done = vnic_cq_service(&enic->cq[cq], - work_to_do, enic_rq_service, NULL); + work_done = enic_rq_cq_service(enic, cq, work_to_do); /* Return intr event credits for this polling * cycle. An intr event is the completion of a @@ -1972,6 +1681,17 @@ static int enic_open(struct net_device *netdev) struct enic *enic = netdev_priv(netdev); unsigned int i; int err, ret; + unsigned int max_pkt_len = netdev->mtu + VLAN_ETH_HLEN; + struct page_pool_params pp_params = { + .order = get_order(max_pkt_len), + .pool_size = enic->config.rq_desc_count, + .nid = dev_to_node(&enic->pdev->dev), + .dev = &enic->pdev->dev, + .dma_dir = DMA_FROM_DEVICE, + .max_len = (max_pkt_len > PAGE_SIZE) ? max_pkt_len : PAGE_SIZE, + .netdev = netdev, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + }; err = enic_request_intr(enic); if (err) { @@ -1989,6 +1709,16 @@ static int enic_open(struct net_device *netdev) } for (i = 0; i < enic->rq_count; i++) { + /* create a page pool for each RQ */ + pp_params.napi = &enic->napi[i]; + pp_params.queue_idx = i; + enic->rq[i].pool = page_pool_create(&pp_params); + if (IS_ERR(enic->rq[i].pool)) { + err = PTR_ERR(enic->rq[i].pool); + enic->rq[i].pool = NULL; + goto err_out_free_rq; + } + /* enable rq before updating rq desc */ vnic_rq_enable(&enic->rq[i].vrq); vnic_rq_fill(&enic->rq[i].vrq, enic_rq_alloc_buf); @@ -2029,8 +1759,11 @@ static int enic_open(struct net_device *netdev) err_out_free_rq: for (i = 0; i < enic->rq_count; i++) { ret = vnic_rq_disable(&enic->rq[i].vrq); - if (!ret) + if (!ret) { vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf); + page_pool_destroy(enic->rq[i].pool); + enic->rq[i].pool = NULL; + } } enic_dev_notify_unset(enic); err_out_free_intr: @@ -2054,7 +1787,7 @@ static int enic_stop(struct net_device *netdev) enic_synchronize_irqs(enic); - del_timer_sync(&enic->notify_timer); + timer_delete_sync(&enic->notify_timer); enic_rfs_flw_tbl_free(enic); enic_dev_disable(enic); @@ -2088,8 +1821,11 @@ static int enic_stop(struct net_device *netdev) for (i = 0; i < enic->wq_count; i++) vnic_wq_clean(&enic->wq[i].vwq, enic_free_wq_buf); - for (i = 0; i < enic->rq_count; i++) + for (i = 0; i < enic->rq_count; i++) { vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf); + page_pool_destroy(enic->rq[i].pool); + enic->rq[i].pool = NULL; + } for (i = 0; i < enic->cq_count; i++) vnic_cq_clean(&enic->cq[i]); for (i = 0; i < enic->intr_count; i++) @@ -2405,6 +2141,7 @@ static void enic_reset(struct work_struct *work) enic_init_vnic_resources(enic); enic_set_rss_nic_cfg(enic); enic_dev_set_ig_vlan_rewrite_mode(enic); + enic_ext_cq(enic); enic_open(enic->netdev); /* Allow infiniband to fiddle with the device again */ @@ -2431,6 +2168,7 @@ static void enic_tx_hang_reset(struct work_struct *work) enic_init_vnic_resources(enic); enic_set_rss_nic_cfg(enic); enic_dev_set_ig_vlan_rewrite_mode(enic); + enic_ext_cq(enic); enic_open(enic->netdev); /* Allow infiniband to fiddle with the device again */ @@ -2599,6 +2337,7 @@ static void enic_get_queue_stats_rx(struct net_device *dev, int idx, rxs->hw_drop_overruns = rqstats->pkt_truncated; rxs->csum_unnecessary = rqstats->csum_unnecessary + rqstats->csum_unnecessary_encap; + rxs->alloc_fail = rqstats->pp_alloc_fail; } static void enic_get_queue_stats_tx(struct net_device *dev, int idx, @@ -2626,6 +2365,7 @@ static void enic_get_base_stats(struct net_device *dev, rxs->hw_drops = 0; rxs->hw_drop_overruns = 0; rxs->csum_unnecessary = 0; + rxs->alloc_fail = 0; txs->bytes = 0; txs->packets = 0; txs->csum_none = 0; @@ -2803,6 +2543,8 @@ static int enic_dev_init(struct enic *enic) enic_get_res_counts(enic); + enic_ext_cq(enic); + err = enic_alloc_enic_resources(enic); if (err) { dev_err(dev, "Failed to allocate enic resources\n"); @@ -3179,7 +2921,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(dev, "Cannot register net device, aborting\n"); goto err_out_dev_deinit; } - enic->rx_copybreak = RX_COPYBREAK_DEFAULT; return 0; |