diff options
Diffstat (limited to 'drivers/net/vmxnet3/vmxnet3_drv.c')
-rw-r--r-- | drivers/net/vmxnet3/vmxnet3_drv.c | 181 |
1 files changed, 114 insertions, 67 deletions
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index c16ed961153..67402350d0d 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -575,7 +575,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, struct vmxnet3_cmd_ring *ring = &rq->rx_ring[ring_idx]; u32 val; - while (num_allocated < num_to_alloc) { + while (num_allocated <= num_to_alloc) { struct vmxnet3_rx_buf_info *rbi; union Vmxnet3_GenericDesc *gd; @@ -621,9 +621,15 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, BUG_ON(rbi->dma_addr == 0); gd->rxd.addr = cpu_to_le64(rbi->dma_addr); - gd->dword[2] = cpu_to_le32((ring->gen << VMXNET3_RXD_GEN_SHIFT) + gd->dword[2] = cpu_to_le32((!ring->gen << VMXNET3_RXD_GEN_SHIFT) | val | rbi->len); + /* Fill the last buffer but dont mark it ready, or else the + * device will think that the queue is full */ + if (num_allocated == num_to_alloc) + break; + + gd->dword[2] |= cpu_to_le32(ring->gen << VMXNET3_RXD_GEN_SHIFT); num_allocated++; vmxnet3_cmd_ring_adv_next2fill(ring); } @@ -1083,7 +1089,7 @@ vmxnet3_rx_csum(struct vmxnet3_adapter *adapter, struct sk_buff *skb, union Vmxnet3_GenericDesc *gdesc) { - if (!gdesc->rcd.cnc && adapter->rxcsum) { + if (!gdesc->rcd.cnc && adapter->netdev->features & NETIF_F_RXCSUM) { /* typical case: TCP/UDP over IP and both csums are correct */ if ((le32_to_cpu(gdesc->dword[3]) & VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) { @@ -1140,6 +1146,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2 }; u32 num_rxd = 0; + bool skip_page_frags = false; struct Vmxnet3_RxCompDesc *rcd; struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx; #ifdef __BIG_ENDIAN_BITFIELD @@ -1150,11 +1157,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, &rxComp); while (rcd->gen == rq->comp_ring.gen) { struct vmxnet3_rx_buf_info *rbi; - struct sk_buff *skb; + struct sk_buff *skb, *new_skb = NULL; + struct page *new_page = NULL; int num_to_alloc; struct Vmxnet3_RxDesc *rxd; u32 idx, ring_idx; - + struct vmxnet3_cmd_ring *ring = NULL; if (num_rxd >= quota) { /* we may stop even before we see the EOP desc of * the current pkt @@ -1165,6 +1173,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2); idx = rcd->rxdIdx; ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1; + ring = rq->rx_ring + ring_idx; vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd, &rxCmdDesc); rbi = rq->buf_info[ring_idx] + idx; @@ -1193,37 +1202,80 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, goto rcd_done; } + skip_page_frags = false; ctx->skb = rbi->skb; - rbi->skb = NULL; + new_skb = dev_alloc_skb(rbi->len + NET_IP_ALIGN); + if (new_skb == NULL) { + /* Skb allocation failed, do not handover this + * skb to stack. Reuse it. Drop the existing pkt + */ + rq->stats.rx_buf_alloc_failure++; + ctx->skb = NULL; + rq->stats.drop_total++; + skip_page_frags = true; + goto rcd_done; + } pci_unmap_single(adapter->pdev, rbi->dma_addr, rbi->len, PCI_DMA_FROMDEVICE); skb_put(ctx->skb, rcd->len); + + /* Immediate refill */ + new_skb->dev = adapter->netdev; + skb_reserve(new_skb, NET_IP_ALIGN); + rbi->skb = new_skb; + rbi->dma_addr = pci_map_single(adapter->pdev, + rbi->skb->data, rbi->len, + PCI_DMA_FROMDEVICE); + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; + } else { - BUG_ON(ctx->skb == NULL); + BUG_ON(ctx->skb == NULL && !skip_page_frags); + /* non SOP buffer must be type 1 in most cases */ - if (rbi->buf_type == VMXNET3_RX_BUF_PAGE) { - BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_BODY); + BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_PAGE); + BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_BODY); - if (rcd->len) { - pci_unmap_page(adapter->pdev, - rbi->dma_addr, rbi->len, - PCI_DMA_FROMDEVICE); + /* If an sop buffer was dropped, skip all + * following non-sop fragments. They will be reused. + */ + if (skip_page_frags) + goto rcd_done; - vmxnet3_append_frag(ctx->skb, rcd, rbi); - rbi->page = NULL; - } - } else { - /* - * The only time a non-SOP buffer is type 0 is - * when it's EOP and error flag is raised, which - * has already been handled. + new_page = alloc_page(GFP_ATOMIC); + if (unlikely(new_page == NULL)) { + /* Replacement page frag could not be allocated. + * Reuse this page. Drop the pkt and free the + * skb which contained this page as a frag. Skip + * processing all the following non-sop frags. */ - BUG_ON(true); + rq->stats.rx_buf_alloc_failure++; + dev_kfree_skb(ctx->skb); + ctx->skb = NULL; + skip_page_frags = true; + goto rcd_done; } + + if (rcd->len) { + pci_unmap_page(adapter->pdev, + rbi->dma_addr, rbi->len, + PCI_DMA_FROMDEVICE); + + vmxnet3_append_frag(ctx->skb, rcd, rbi); + } + + /* Immediate refill */ + rbi->page = new_page; + rbi->dma_addr = pci_map_page(adapter->pdev, rbi->page, + 0, PAGE_SIZE, + PCI_DMA_FROMDEVICE); + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; } + skb = ctx->skb; if (rcd->eop) { skb->len += skb->data_len; @@ -1244,26 +1296,27 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, } rcd_done: - /* device may skip some rx descs */ - rq->rx_ring[ring_idx].next2comp = idx; - VMXNET3_INC_RING_IDX_ONLY(rq->rx_ring[ring_idx].next2comp, - rq->rx_ring[ring_idx].size); - - /* refill rx buffers frequently to avoid starving the h/w */ - num_to_alloc = vmxnet3_cmd_ring_desc_avail(rq->rx_ring + - ring_idx); - if (unlikely(num_to_alloc > VMXNET3_RX_ALLOC_THRESHOLD(rq, - ring_idx, adapter))) { - vmxnet3_rq_alloc_rx_buf(rq, ring_idx, num_to_alloc, - adapter); - - /* if needed, update the register */ - if (unlikely(rq->shared->updateRxProd)) { - VMXNET3_WRITE_BAR0_REG(adapter, - rxprod_reg[ring_idx] + rq->qid * 8, - rq->rx_ring[ring_idx].next2fill); - rq->uncommitted[ring_idx] = 0; - } + /* device may have skipped some rx descs */ + ring->next2comp = idx; + num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring); + ring = rq->rx_ring + ring_idx; + while (num_to_alloc) { + vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd, + &rxCmdDesc); + BUG_ON(!rxd->addr); + + /* Recv desc is ready to be used by the device */ + rxd->gen = ring->gen; + vmxnet3_cmd_ring_adv_next2fill(ring); + num_to_alloc--; + } + + /* if needed, update the register */ + if (unlikely(rq->shared->updateRxProd)) { + VMXNET3_WRITE_BAR0_REG(adapter, + rxprod_reg[ring_idx] + rq->qid * 8, + ring->next2fill); + rq->uncommitted[ring_idx] = 0; } vmxnet3_comp_ring_adv_next2proc(&rq->comp_ring); @@ -2082,10 +2135,10 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) devRead->misc.ddLen = cpu_to_le32(sizeof(struct vmxnet3_adapter)); /* set up feature flags */ - if (adapter->rxcsum) + if (adapter->netdev->features & NETIF_F_RXCSUM) devRead->misc.uptFeatures |= UPT1_F_RXCSUM; - if (adapter->lro) { + if (adapter->netdev->features & NETIF_F_LRO) { devRead->misc.uptFeatures |= UPT1_F_LRO; devRead->misc.maxNumRxSG = cpu_to_le16(1 + MAX_SKB_FRAGS); } @@ -2594,9 +2647,6 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) if (new_mtu < VMXNET3_MIN_MTU || new_mtu > VMXNET3_MAX_MTU) return -EINVAL; - if (new_mtu > 1500 && !adapter->jumbo_frame) - return -EINVAL; - netdev->mtu = new_mtu; /* @@ -2642,28 +2692,18 @@ vmxnet3_declare_features(struct vmxnet3_adapter *adapter, bool dma64) { struct net_device *netdev = adapter->netdev; - netdev->features = NETIF_F_SG | - NETIF_F_HW_CSUM | - NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER | - NETIF_F_TSO | - NETIF_F_TSO6 | - NETIF_F_LRO; - - printk(KERN_INFO "features: sg csum vlan jf tso tsoIPv6 lro"); - - adapter->rxcsum = true; - adapter->jumbo_frame = true; - adapter->lro = true; - - if (dma64) { + netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_TX | + NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_LRO; + if (dma64) netdev->features |= NETIF_F_HIGHDMA; - printk(" highDMA"); - } + netdev->vlan_features = netdev->hw_features & ~NETIF_F_HW_VLAN_TX; + netdev->features = netdev->hw_features | + NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER; - netdev->vlan_features = netdev->features; - printk("\n"); + netdev_info(adapter->netdev, + "features: sg csum vlan jf tso tsoIPv6 lro%s\n", + dma64 ? " highDMA" : ""); } @@ -2876,6 +2916,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, .ndo_start_xmit = vmxnet3_xmit_frame, .ndo_set_mac_address = vmxnet3_set_mac_addr, .ndo_change_mtu = vmxnet3_change_mtu, + .ndo_set_features = vmxnet3_set_features, .ndo_get_stats = vmxnet3_get_stats, .ndo_tx_timeout = vmxnet3_tx_timeout, .ndo_set_multicast_list = vmxnet3_set_mc, @@ -2896,6 +2937,9 @@ vmxnet3_probe_device(struct pci_dev *pdev, int num_tx_queues; int num_rx_queues; + if (!pci_msi_enabled()) + enable_mq = 0; + #ifdef VMXNET3_RSS if (enable_mq) num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES, @@ -2903,6 +2947,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, else #endif num_rx_queues = 1; + num_rx_queues = rounddown_pow_of_two(num_rx_queues); if (enable_mq) num_tx_queues = min(VMXNET3_DEVICE_MAX_TX_QUEUES, @@ -2910,6 +2955,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, else num_tx_queues = 1; + num_tx_queues = rounddown_pow_of_two(num_tx_queues); netdev = alloc_etherdev_mq(sizeof(struct vmxnet3_adapter), max(num_tx_queues, num_rx_queues)); printk(KERN_INFO "# of Tx queues : %d, # of Rx queues : %d\n", @@ -3094,6 +3140,7 @@ vmxnet3_remove_device(struct pci_dev *pdev) else #endif num_rx_queues = 1; + num_rx_queues = rounddown_pow_of_two(num_rx_queues); cancel_work_sync(&adapter->work); |