diff options
Diffstat (limited to 'drivers/net/vmxnet3')
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_drv.c | 1832 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_ethtool.c | 521 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_int.h | 111 |
3 files changed, 1614 insertions, 850 deletions
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index e3658e10db3..b76f7dcde0d 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -24,6 +24,7 @@ * */ +#include <linux/module.h> #include <net/ip6_checksum.h> #include "vmxnet3_int.h" @@ -42,8 +43,10 @@ static DEFINE_PCI_DEVICE_TABLE(vmxnet3_pciid_table) = { MODULE_DEVICE_TABLE(pci, vmxnet3_pciid_table); -static atomic_t devices_found; +static int enable_mq = 1; +static void +vmxnet3_write_mac_addr(struct vmxnet3_adapter *adapter, u8 *mac); /* * Enable/Disable the given intr @@ -99,7 +102,7 @@ vmxnet3_ack_events(struct vmxnet3_adapter *adapter, u32 events) static bool vmxnet3_tq_stopped(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { - return netif_queue_stopped(adapter->netdev); + return tq->stopped; } @@ -107,7 +110,7 @@ static void vmxnet3_tq_start(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { tq->stopped = false; - netif_start_queue(adapter->netdev); + netif_start_subqueue(adapter->netdev, tq - adapter->tx_queue); } @@ -115,7 +118,7 @@ static void vmxnet3_tq_wake(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { tq->stopped = false; - netif_wake_queue(adapter->netdev); + netif_wake_subqueue(adapter->netdev, (tq - adapter->tx_queue)); } @@ -124,7 +127,7 @@ vmxnet3_tq_stop(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { tq->stopped = true; tq->num_stop++; - netif_stop_queue(adapter->netdev); + netif_stop_subqueue(adapter->netdev, (tq - adapter->tx_queue)); } @@ -135,32 +138,41 @@ static void vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue) { u32 ret; + int i; + unsigned long flags; + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_LINK); ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + adapter->link_speed = ret >> 16; if (ret & 1) { /* Link is up. */ - printk(KERN_INFO "%s: NIC Link is Up %d Mbps\n", - adapter->netdev->name, adapter->link_speed); - if (!netif_carrier_ok(adapter->netdev)) - netif_carrier_on(adapter->netdev); - - if (affectTxQueue) - vmxnet3_tq_start(&adapter->tx_queue, adapter); + netdev_info(adapter->netdev, "NIC Link is Up %d Mbps\n", + adapter->link_speed); + netif_carrier_on(adapter->netdev); + + if (affectTxQueue) { + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_start(&adapter->tx_queue[i], + adapter); + } } else { - printk(KERN_INFO "%s: NIC Link is Down\n", - adapter->netdev->name); - if (netif_carrier_ok(adapter->netdev)) - netif_carrier_off(adapter->netdev); + netdev_info(adapter->netdev, "NIC Link is Down\n"); + netif_carrier_off(adapter->netdev); - if (affectTxQueue) - vmxnet3_tq_stop(&adapter->tx_queue, adapter); + if (affectTxQueue) { + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_stop(&adapter->tx_queue[i], adapter); + } } } static void vmxnet3_process_events(struct vmxnet3_adapter *adapter) { + int i; + unsigned long flags; u32 events = le32_to_cpu(adapter->shared->ecr); if (!events) return; @@ -173,19 +185,23 @@ vmxnet3_process_events(struct vmxnet3_adapter *adapter) /* Check if there is an error on xmit/recv queues */ if (events & (VMXNET3_ECR_TQERR | VMXNET3_ECR_RQERR)) { + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_QUEUE_STATUS); - - if (adapter->tqd_start->status.stopped) { - printk(KERN_ERR "%s: tq error 0x%x\n", - adapter->netdev->name, - le32_to_cpu(adapter->tqd_start->status.error)); - } - if (adapter->rqd_start->status.stopped) { - printk(KERN_ERR "%s: rq error 0x%x\n", - adapter->netdev->name, - adapter->rqd_start->status.error); - } + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + for (i = 0; i < adapter->num_tx_queues; i++) + if (adapter->tqd_start[i].status.stopped) + dev_err(&adapter->netdev->dev, + "%s: tq[%d] error 0x%x\n", + adapter->netdev->name, i, le32_to_cpu( + adapter->tqd_start[i].status.error)); + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->rqd_start[i].status.stopped) + dev_err(&adapter->netdev->dev, + "%s: rq[%d] error 0x%x\n", + adapter->netdev->name, i, + adapter->rqd_start[i].status.error); schedule_work(&adapter->work); } @@ -297,10 +313,10 @@ vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, struct pci_dev *pdev) { if (tbi->map_type == VMXNET3_MAP_SINGLE) - pci_unmap_single(pdev, tbi->dma_addr, tbi->len, + dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len, PCI_DMA_TODEVICE); else if (tbi->map_type == VMXNET3_MAP_PAGE) - pci_unmap_page(pdev, tbi->dma_addr, tbi->len, + dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len, PCI_DMA_TODEVICE); else BUG_ON(tbi->map_type != VMXNET3_MAP_NONE); @@ -383,10 +399,8 @@ vmxnet3_tq_cleanup(struct vmxnet3_tx_queue *tq, while (tq->tx_ring.next2comp != tq->tx_ring.next2fill) { struct vmxnet3_tx_buf_info *tbi; - union Vmxnet3_GenericDesc *gdesc; tbi = tq->buf_info + tq->tx_ring.next2comp; - gdesc = tq->tx_ring.base + tq->tx_ring.next2comp; vmxnet3_unmap_tx_buf(tbi, adapter->pdev); if (tbi->skb) { @@ -410,30 +424,45 @@ vmxnet3_tq_cleanup(struct vmxnet3_tx_queue *tq, } -void +static void vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { if (tq->tx_ring.base) { - pci_free_consistent(adapter->pdev, tq->tx_ring.size * - sizeof(struct Vmxnet3_TxDesc), - tq->tx_ring.base, tq->tx_ring.basePA); + dma_free_coherent(&adapter->pdev->dev, tq->tx_ring.size * + sizeof(struct Vmxnet3_TxDesc), + tq->tx_ring.base, tq->tx_ring.basePA); tq->tx_ring.base = NULL; } if (tq->data_ring.base) { - pci_free_consistent(adapter->pdev, tq->data_ring.size * - sizeof(struct Vmxnet3_TxDataDesc), - tq->data_ring.base, tq->data_ring.basePA); + dma_free_coherent(&adapter->pdev->dev, tq->data_ring.size * + sizeof(struct Vmxnet3_TxDataDesc), + tq->data_ring.base, tq->data_ring.basePA); tq->data_ring.base = NULL; } if (tq->comp_ring.base) { - pci_free_consistent(adapter->pdev, tq->comp_ring.size * - sizeof(struct Vmxnet3_TxCompDesc), - tq->comp_ring.base, tq->comp_ring.basePA); + dma_free_coherent(&adapter->pdev->dev, tq->comp_ring.size * + sizeof(struct Vmxnet3_TxCompDesc), + tq->comp_ring.base, tq->comp_ring.basePA); tq->comp_ring.base = NULL; } - kfree(tq->buf_info); - tq->buf_info = NULL; + if (tq->buf_info) { + dma_free_coherent(&adapter->pdev->dev, + tq->tx_ring.size * sizeof(tq->buf_info[0]), + tq->buf_info, tq->buf_info_pa); + tq->buf_info = NULL; + } +} + + +/* Destroy all tx queues */ +void +vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_destroy(&adapter->tx_queue[i], adapter); } @@ -471,45 +500,40 @@ static int vmxnet3_tq_create(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { + size_t sz; + BUG_ON(tq->tx_ring.base || tq->data_ring.base || tq->comp_ring.base || tq->buf_info); - tq->tx_ring.base = pci_alloc_consistent(adapter->pdev, tq->tx_ring.size - * sizeof(struct Vmxnet3_TxDesc), - &tq->tx_ring.basePA); + tq->tx_ring.base = dma_alloc_coherent(&adapter->pdev->dev, + tq->tx_ring.size * sizeof(struct Vmxnet3_TxDesc), + &tq->tx_ring.basePA, GFP_KERNEL); if (!tq->tx_ring.base) { - printk(KERN_ERR "%s: failed to allocate tx ring\n", - adapter->netdev->name); + netdev_err(adapter->netdev, "failed to allocate tx ring\n"); goto err; } - tq->data_ring.base = pci_alloc_consistent(adapter->pdev, - tq->data_ring.size * - sizeof(struct Vmxnet3_TxDataDesc), - &tq->data_ring.basePA); + tq->data_ring.base = dma_alloc_coherent(&adapter->pdev->dev, + tq->data_ring.size * sizeof(struct Vmxnet3_TxDataDesc), + &tq->data_ring.basePA, GFP_KERNEL); if (!tq->data_ring.base) { - printk(KERN_ERR "%s: failed to allocate data ring\n", - adapter->netdev->name); + netdev_err(adapter->netdev, "failed to allocate data ring\n"); goto err; } - tq->comp_ring.base = pci_alloc_consistent(adapter->pdev, - tq->comp_ring.size * - sizeof(struct Vmxnet3_TxCompDesc), - &tq->comp_ring.basePA); + tq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, + tq->comp_ring.size * sizeof(struct Vmxnet3_TxCompDesc), + &tq->comp_ring.basePA, GFP_KERNEL); if (!tq->comp_ring.base) { - printk(KERN_ERR "%s: failed to allocate tx comp ring\n", - adapter->netdev->name); + netdev_err(adapter->netdev, "failed to allocate tx comp ring\n"); goto err; } - tq->buf_info = kcalloc(tq->tx_ring.size, sizeof(tq->buf_info[0]), - GFP_KERNEL); - if (!tq->buf_info) { - printk(KERN_ERR "%s: failed to allocate tx bufinfo\n", - adapter->netdev->name); + sz = tq->tx_ring.size * sizeof(tq->buf_info[0]); + tq->buf_info = dma_zalloc_coherent(&adapter->pdev->dev, sz, + &tq->buf_info_pa, GFP_KERNEL); + if (!tq->buf_info) goto err; - } return 0; @@ -518,6 +542,14 @@ err: return -ENOMEM; } +static void +vmxnet3_tq_cleanup_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_cleanup(&adapter->tx_queue[i], adapter); +} /* * starting from ring->next2fill, allocate rx buffers for the given ring @@ -534,7 +566,7 @@ 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; @@ -543,16 +575,16 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (rbi->buf_type == VMXNET3_RX_BUF_SKB) { if (rbi->skb == NULL) { - rbi->skb = dev_alloc_skb(rbi->len + - NET_IP_ALIGN); + rbi->skb = __netdev_alloc_skb_ip_align(adapter->netdev, + rbi->len, + GFP_KERNEL); if (unlikely(rbi->skb == NULL)) { rq->stats.rx_buf_alloc_failure++; break; } - rbi->skb->dev = adapter->netdev; - skb_reserve(rbi->skb, NET_IP_ALIGN); - rbi->dma_addr = pci_map_single(adapter->pdev, + rbi->dma_addr = dma_map_single( + &adapter->pdev->dev, rbi->skb->data, rbi->len, PCI_DMA_FROMDEVICE); } else { @@ -569,7 +601,8 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, rq->stats.rx_buf_alloc_failure++; break; } - rbi->dma_addr = pci_map_page(adapter->pdev, + rbi->dma_addr = dma_map_page( + &adapter->pdev->dev, rbi->page, 0, PAGE_SIZE, PCI_DMA_FROMDEVICE); } else { @@ -580,18 +613,22 @@ 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); } - rq->uncommitted[ring_idx] += num_allocated; - dev_dbg(&adapter->netdev->dev, - "alloc_rx_buf: %d allocated, next2fill %u, next2comp " - "%u, uncommited %u\n", num_allocated, ring->next2fill, - ring->next2comp, rq->uncommitted[ring_idx]); + netdev_dbg(adapter->netdev, + "alloc_rx_buf: %d allocated, next2fill %u, next2comp %u\n", + num_allocated, ring->next2fill, ring->next2comp); /* so that the device can distinguish a full ring and an empty ring */ BUG_ON(num_allocated != 0 && ring->next2fill == ring->next2comp); @@ -609,10 +646,11 @@ vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd, BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); - frag->page = rbi->page; + __skb_frag_set_page(frag, rbi->page); frag->page_offset = 0; - frag->size = rcd->len; - skb->data_len += frag->size; + skb_frag_size_set(frag, rcd->len); + skb->data_len += rcd->len; + skb->truesize += PAGE_SIZE; skb_shinfo(skb)->nr_frags++; } @@ -647,7 +685,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, tbi = tq->buf_info + tq->tx_ring.next2fill; tbi->map_type = VMXNET3_MAP_NONE; - dev_dbg(&adapter->netdev->dev, + netdev_dbg(adapter->netdev, "txd[%u]: 0x%Lx 0x%x 0x%x\n", tq->tx_ring.next2fill, le64_to_cpu(ctx->sop_txd->txd.addr), @@ -674,7 +712,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, tbi = tq->buf_info + tq->tx_ring.next2fill; tbi->map_type = VMXNET3_MAP_SINGLE; - tbi->dma_addr = pci_map_single(adapter->pdev, + tbi->dma_addr = dma_map_single(&adapter->pdev->dev, skb->data + buf_offset, buf_size, PCI_DMA_TODEVICE); @@ -687,7 +725,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, gdesc->dword[2] = cpu_to_le32(dw2); gdesc->dword[3] = 0; - dev_dbg(&adapter->netdev->dev, + netdev_dbg(adapter->netdev, "txd[%u]: 0x%Lx 0x%x 0x%x\n", tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr), le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]); @@ -699,29 +737,44 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + u32 buf_size; - tbi = tq->buf_info + tq->tx_ring.next2fill; - tbi->map_type = VMXNET3_MAP_PAGE; - tbi->dma_addr = pci_map_page(adapter->pdev, frag->page, - frag->page_offset, frag->size, - PCI_DMA_TODEVICE); + buf_offset = 0; + len = skb_frag_size(frag); + while (len) { + tbi = tq->buf_info + tq->tx_ring.next2fill; + if (len < VMXNET3_MAX_TX_BUF_SIZE) { + buf_size = len; + dw2 |= len; + } else { + buf_size = VMXNET3_MAX_TX_BUF_SIZE; + /* spec says that for TxDesc.len, 0 == 2^14 */ + } + tbi->map_type = VMXNET3_MAP_PAGE; + tbi->dma_addr = skb_frag_dma_map(&adapter->pdev->dev, frag, + buf_offset, buf_size, + DMA_TO_DEVICE); - tbi->len = frag->size; + tbi->len = buf_size; - gdesc = tq->tx_ring.base + tq->tx_ring.next2fill; - BUG_ON(gdesc->txd.gen == tq->tx_ring.gen); + gdesc = tq->tx_ring.base + tq->tx_ring.next2fill; + BUG_ON(gdesc->txd.gen == tq->tx_ring.gen); - gdesc->txd.addr = cpu_to_le64(tbi->dma_addr); - gdesc->dword[2] = cpu_to_le32(dw2 | frag->size); - gdesc->dword[3] = 0; + gdesc->txd.addr = cpu_to_le64(tbi->dma_addr); + gdesc->dword[2] = cpu_to_le32(dw2); + gdesc->dword[3] = 0; - dev_dbg(&adapter->netdev->dev, - "txd[%u]: 0x%llu %u %u\n", - tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr), - le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]); - vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); - dw2 = tq->tx_ring.gen << VMXNET3_TXD_GEN_SHIFT; + netdev_dbg(adapter->netdev, + "txd[%u]: 0x%llu %u %u\n", + tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr), + le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]); + vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); + dw2 = tq->tx_ring.gen << VMXNET3_TXD_GEN_SHIFT; + + len -= buf_size; + buf_offset += buf_size; + } } ctx->eop_txd = gdesc; @@ -732,6 +785,17 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, } +/* Init all tx queues */ +static void +vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_init(&adapter->tx_queue[i], adapter); +} + + /* * parse and copy relevant protocol headers: * For a tso pkt, relevant headers are L2/3/4 including options @@ -756,42 +820,29 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, { struct Vmxnet3_TxDataDesc *tdd; - if (ctx->mss) { + if (ctx->mss) { /* TSO */ ctx->eth_ip_hdr_size = skb_transport_offset(skb); - ctx->l4_hdr_size = ((struct tcphdr *) - skb_transport_header(skb))->doff * 4; + ctx->l4_hdr_size = tcp_hdrlen(skb); ctx->copy_size = ctx->eth_ip_hdr_size + ctx->l4_hdr_size; } else { - unsigned int pull_size; - if (skb->ip_summed == CHECKSUM_PARTIAL) { - ctx->eth_ip_hdr_size = skb_transport_offset(skb); + ctx->eth_ip_hdr_size = skb_checksum_start_offset(skb); if (ctx->ipv4) { - struct iphdr *iph = (struct iphdr *) - skb_network_header(skb); - if (iph->protocol == IPPROTO_TCP) { - pull_size = ctx->eth_ip_hdr_size + - sizeof(struct tcphdr); - - if (unlikely(!pskb_may_pull(skb, - pull_size))) { - goto err; - } - ctx->l4_hdr_size = ((struct tcphdr *) - skb_transport_header(skb))->doff * 4; - } else if (iph->protocol == IPPROTO_UDP) { - ctx->l4_hdr_size = - sizeof(struct udphdr); - } else { + const struct iphdr *iph = ip_hdr(skb); + + if (iph->protocol == IPPROTO_TCP) + ctx->l4_hdr_size = tcp_hdrlen(skb); + else if (iph->protocol == IPPROTO_UDP) + ctx->l4_hdr_size = sizeof(struct udphdr); + else ctx->l4_hdr_size = 0; - } } else { /* for simplicity, don't copy L4 headers */ ctx->l4_hdr_size = 0; } - ctx->copy_size = ctx->eth_ip_hdr_size + - ctx->l4_hdr_size; + ctx->copy_size = min(ctx->eth_ip_hdr_size + + ctx->l4_hdr_size, skb->len); } else { ctx->eth_ip_hdr_size = 0; ctx->l4_hdr_size = 0; @@ -814,7 +865,7 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, tdd = tq->data_ring.base + tq->tx_ring.next2fill; memcpy(tdd->data, skb->data, ctx->copy_size); - dev_dbg(&adapter->netdev->dev, + netdev_dbg(adapter->netdev, "copy %u bytes to dataRing[%u]\n", ctx->copy_size, tq->tx_ring.next2fill); return 1; @@ -828,25 +879,40 @@ static void vmxnet3_prepare_tso(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx) { - struct tcphdr *tcph = (struct tcphdr *)skb_transport_header(skb); + struct tcphdr *tcph = tcp_hdr(skb); + if (ctx->ipv4) { - struct iphdr *iph = (struct iphdr *)skb_network_header(skb); + struct iphdr *iph = ip_hdr(skb); + iph->check = 0; tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, 0, IPPROTO_TCP, 0); } else { - struct ipv6hdr *iph = (struct ipv6hdr *)skb_network_header(skb); + struct ipv6hdr *iph = ipv6_hdr(skb); + tcph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, 0, IPPROTO_TCP, 0); } } +static int txd_estimate(const struct sk_buff *skb) +{ + int count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + 1; + int i; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + + count += VMXNET3_TXD_NEEDED(skb_frag_size(frag)); + } + return count; +} /* * Transmits a pkt thru a given tq * Returns: * NETDEV_TX_OK: descriptors are setup successfully - * NETDEV_TX_OK: error occured, the pkt is dropped + * NETDEV_TX_OK: error occurred, the pkt is dropped * NETDEV_TX_BUSY: tx ring is full, queue is stopped * * Side-effects: @@ -869,11 +935,9 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, union Vmxnet3_GenericDesc tempTxDesc; #endif - /* conservatively estimate # of descriptors to use */ - count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + - skb_shinfo(skb)->nr_frags + 1; + count = txd_estimate(skb); - ctx.ipv4 = (skb->protocol == __constant_ntohs(ETH_P_IP)); + ctx.ipv4 = (vlan_get_protocol(skb) == cpu_to_be16(ETH_P_IP)); ctx.mss = skb_shinfo(skb)->gso_size; if (ctx.mss) { @@ -903,6 +967,21 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } + spin_lock_irqsave(&tq->tx_lock, flags); + + if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { + tq->stats.tx_ring_full++; + netdev_dbg(adapter->netdev, + "tx queue stopped on %s, next2comp %u" + " next2fill %u\n", adapter->netdev->name, + tq->tx_ring.next2comp, tq->tx_ring.next2fill); + + vmxnet3_tq_stop(tq, adapter); + spin_unlock_irqrestore(&tq->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + ret = vmxnet3_parse_and_copy_hdr(skb, tq, &ctx, adapter); if (ret >= 0) { BUG_ON(ret <= 0 && ctx.copy_size != 0); @@ -923,21 +1002,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } else { tq->stats.drop_hdr_inspect_err++; - goto drop_pkt; - } - - spin_lock_irqsave(&tq->tx_lock, flags); - - if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { - tq->stats.tx_ring_full++; - dev_dbg(&adapter->netdev->dev, - "tx queue stopped on %s, next2comp %u" - " next2fill %u\n", adapter->netdev->name, - tq->tx_ring.next2comp, tq->tx_ring.next2fill); - - vmxnet3_tq_stop(tq, adapter); - spin_unlock_irqrestore(&tq->tx_lock, flags); - return NETDEV_TX_BUSY; + goto unlock_drop_pkt; } /* fill tx descs related to addr & len */ @@ -989,9 +1054,9 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, (struct Vmxnet3_TxDesc *)ctx.sop_txd); gdesc = ctx.sop_txd; #endif - dev_dbg(&adapter->netdev->dev, + netdev_dbg(adapter->netdev, "txd[%u]: SOP 0x%Lx 0x%x 0x%x\n", - (u32)((union Vmxnet3_GenericDesc *)ctx.sop_txd - + (u32)(ctx.sop_txd - tq->tx_ring.base), le64_to_cpu(gdesc->txd.addr), le32_to_cpu(gdesc->dword[2]), le32_to_cpu(gdesc->dword[3])); @@ -1000,7 +1065,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, if (le32_to_cpu(tq->shared->txNumDeferred) >= le32_to_cpu(tq->shared->txThreshold)) { tq->shared->txNumDeferred = 0; - VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_TXPROD, + VMXNET3_WRITE_BAR0_REG(adapter, + VMXNET3_REG_TXPROD + tq->qid * 8, tq->tx_ring.next2fill); } @@ -1008,9 +1074,11 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, hdr_too_big: tq->stats.drop_oversized_hdr++; +unlock_drop_pkt: + spin_unlock_irqrestore(&tq->tx_lock, flags); drop_pkt: tq->stats.drop_total++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1020,7 +1088,10 @@ vmxnet3_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - return vmxnet3_tq_xmit(skb, &adapter->tx_queue, adapter, netdev); + BUG_ON(skb->queue_mapping > adapter->num_tx_queues); + return vmxnet3_tq_xmit(skb, + &adapter->tx_queue[skb->queue_mapping], + adapter, netdev); } @@ -1029,7 +1100,7 @@ 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) { @@ -1082,8 +1153,11 @@ static int vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter, int quota) { - static u32 rxprod_reg[2] = {VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2}; + static const u32 rxprod_reg[2] = { + 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 @@ -1094,11 +1168,12 @@ 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 @@ -1106,9 +1181,10 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, break; } num_rxd++; - + BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2); idx = rcd->rxdIdx; - ring_idx = rcd->rqID == rq->qid ? 0 : 1; + 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; @@ -1131,88 +1207,139 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, if (unlikely(rcd->len == 0)) { /* Pretend the rx buffer is skipped. */ BUG_ON(!(rcd->sop && rcd->eop)); - dev_dbg(&adapter->netdev->dev, + netdev_dbg(adapter->netdev, "rxRing[%u][%u] 0 length\n", ring_idx, idx); goto rcd_done; } + skip_page_frags = false; ctx->skb = rbi->skb; - rbi->skb = NULL; + new_skb = netdev_alloc_skb_ip_align(adapter->netdev, + rbi->len); + 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, + dma_unmap_single(&adapter->pdev->dev, rbi->dma_addr, + rbi->len, PCI_DMA_FROMDEVICE); +#ifdef VMXNET3_RSS + if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE && + (adapter->netdev->features & NETIF_F_RXHASH)) + skb_set_hash(ctx->skb, + le32_to_cpu(rcd->rssHash), + PKT_HASH_TYPE_L3); +#endif skb_put(ctx->skb, rcd->len); + + /* Immediate refill */ + rbi->skb = new_skb; + rbi->dma_addr = dma_map_single(&adapter->pdev->dev, + 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) { + dma_unmap_page(&adapter->pdev->dev, + rbi->dma_addr, rbi->len, + PCI_DMA_FROMDEVICE); + + vmxnet3_append_frag(ctx->skb, rcd, rbi); + } + + /* Immediate refill */ + rbi->page = new_page; + rbi->dma_addr = dma_map_page(&adapter->pdev->dev, + 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; - skb->truesize += skb->data_len; vmxnet3_rx_csum(adapter, skb, (union Vmxnet3_GenericDesc *)rcd); skb->protocol = eth_type_trans(skb, adapter->netdev); - if (unlikely(adapter->vlan_grp && rcd->ts)) { - vlan_hwaccel_receive_skb(skb, - adapter->vlan_grp, rcd->tci); - } else { + if (unlikely(rcd->ts)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rcd->tci); + + if (adapter->netdev->features & NETIF_F_LRO) netif_receive_skb(skb); - } + else + napi_gro_receive(&rq->napi, skb); ctx->skb = NULL; } 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); } vmxnet3_comp_ring_adv_next2proc(&rq->comp_ring); vmxnet3_getRxComp(rcd, - &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp); + &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp); } return num_rxd; @@ -1236,13 +1363,13 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD && rq->buf_info[ring_idx][i].skb) { - pci_unmap_single(adapter->pdev, rxd->addr, + dma_unmap_single(&adapter->pdev->dev, rxd->addr, rxd->len, PCI_DMA_FROMDEVICE); dev_kfree_skb(rq->buf_info[ring_idx][i].skb); rq->buf_info[ring_idx][i].skb = NULL; } else if (rxd->btype == VMXNET3_RXD_BTYPE_BODY && rq->buf_info[ring_idx][i].page) { - pci_unmap_page(adapter->pdev, rxd->addr, + dma_unmap_page(&adapter->pdev->dev, rxd->addr, rxd->len, PCI_DMA_FROMDEVICE); put_page(rq->buf_info[ring_idx][i].page); rq->buf_info[ring_idx][i].page = NULL; @@ -1252,7 +1379,6 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, rq->rx_ring[ring_idx].gen = VMXNET3_INIT_GEN; rq->rx_ring[ring_idx].next2fill = rq->rx_ring[ring_idx].next2comp = 0; - rq->uncommitted[ring_idx] = 0; } rq->comp_ring.gen = VMXNET3_INIT_GEN; @@ -1260,8 +1386,18 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, } -void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, - struct vmxnet3_adapter *adapter) +static void +vmxnet3_rq_cleanup_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_rq_cleanup(&adapter->rx_queue[i], adapter); +} + + +static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, + struct vmxnet3_adapter *adapter) { int i; int j; @@ -1275,25 +1411,31 @@ void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, } - kfree(rq->buf_info[0]); - for (i = 0; i < 2; i++) { if (rq->rx_ring[i].base) { - pci_free_consistent(adapter->pdev, rq->rx_ring[i].size - * sizeof(struct Vmxnet3_RxDesc), - rq->rx_ring[i].base, - rq->rx_ring[i].basePA); + dma_free_coherent(&adapter->pdev->dev, + rq->rx_ring[i].size + * sizeof(struct Vmxnet3_RxDesc), + rq->rx_ring[i].base, + rq->rx_ring[i].basePA); rq->rx_ring[i].base = NULL; } rq->buf_info[i] = NULL; } if (rq->comp_ring.base) { - pci_free_consistent(adapter->pdev, rq->comp_ring.size * - sizeof(struct Vmxnet3_RxCompDesc), - rq->comp_ring.base, rq->comp_ring.basePA); + dma_free_coherent(&adapter->pdev->dev, rq->comp_ring.size + * sizeof(struct Vmxnet3_RxCompDesc), + rq->comp_ring.base, rq->comp_ring.basePA); rq->comp_ring.base = NULL; } + + if (rq->buf_info[0]) { + size_t sz = sizeof(struct vmxnet3_rx_buf_info) * + (rq->rx_ring[0].size + rq->rx_ring[1].size); + dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0], + rq->buf_info_pa); + } } @@ -1323,7 +1465,6 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq, /* reset internal state and allocate buffers for both rings */ for (i = 0; i < 2; i++) { rq->rx_ring[i].next2fill = rq->rx_ring[i].next2comp = 0; - rq->uncommitted[i] = 0; memset(rq->rx_ring[i].base, 0, rq->rx_ring[i].size * sizeof(struct Vmxnet3_RxDesc)); @@ -1351,6 +1492,25 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq, static int +vmxnet3_rq_init_all(struct vmxnet3_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = vmxnet3_rq_init(&adapter->rx_queue[i], adapter); + if (unlikely(err)) { + dev_err(&adapter->netdev->dev, "%s: failed to " + "initialize rx queue%i\n", + adapter->netdev->name, i); + break; + } + } + return err; + +} + + +static int vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter) { int i; @@ -1360,32 +1520,33 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter) for (i = 0; i < 2; i++) { sz = rq->rx_ring[i].size * sizeof(struct Vmxnet3_RxDesc); - rq->rx_ring[i].base = pci_alloc_consistent(adapter->pdev, sz, - &rq->rx_ring[i].basePA); + rq->rx_ring[i].base = dma_alloc_coherent( + &adapter->pdev->dev, sz, + &rq->rx_ring[i].basePA, + GFP_KERNEL); if (!rq->rx_ring[i].base) { - printk(KERN_ERR "%s: failed to allocate rx ring %d\n", - adapter->netdev->name, i); + netdev_err(adapter->netdev, + "failed to allocate rx ring %d\n", i); goto err; } } sz = rq->comp_ring.size * sizeof(struct Vmxnet3_RxCompDesc); - rq->comp_ring.base = pci_alloc_consistent(adapter->pdev, sz, - &rq->comp_ring.basePA); + rq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, sz, + &rq->comp_ring.basePA, + GFP_KERNEL); if (!rq->comp_ring.base) { - printk(KERN_ERR "%s: failed to allocate rx comp ring\n", - adapter->netdev->name); + netdev_err(adapter->netdev, "failed to allocate rx comp ring\n"); goto err; } sz = sizeof(struct vmxnet3_rx_buf_info) * (rq->rx_ring[0].size + rq->rx_ring[1].size); - bi = kzalloc(sz, GFP_KERNEL); - if (!bi) { - printk(KERN_ERR "%s: failed to allocate rx bufinfo\n", - adapter->netdev->name); + bi = dma_zalloc_coherent(&adapter->pdev->dev, sz, &rq->buf_info_pa, + GFP_KERNEL); + if (!bi) goto err; - } + rq->buf_info[0] = bi; rq->buf_info[1] = bi + rq->rx_ring[0].size; @@ -1398,33 +1559,177 @@ err: static int +vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = vmxnet3_rq_create(&adapter->rx_queue[i], adapter); + if (unlikely(err)) { + dev_err(&adapter->netdev->dev, + "%s: failed to create rx queue%i\n", + adapter->netdev->name, i); + goto err_out; + } + } + return err; +err_out: + vmxnet3_rq_destroy_all(adapter); + return err; + +} + +/* Multiple queue aware polling function for tx and rx */ + +static int vmxnet3_do_poll(struct vmxnet3_adapter *adapter, int budget) { + int rcd_done = 0, i; if (unlikely(adapter->shared->ecr)) vmxnet3_process_events(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_tx_complete(&adapter->tx_queue[i], adapter); - vmxnet3_tq_tx_complete(&adapter->tx_queue, adapter); - return vmxnet3_rq_rx_complete(&adapter->rx_queue, adapter, budget); + for (i = 0; i < adapter->num_rx_queues; i++) + rcd_done += vmxnet3_rq_rx_complete(&adapter->rx_queue[i], + adapter, budget); + return rcd_done; } static int vmxnet3_poll(struct napi_struct *napi, int budget) { - struct vmxnet3_adapter *adapter = container_of(napi, - struct vmxnet3_adapter, napi); + struct vmxnet3_rx_queue *rx_queue = container_of(napi, + struct vmxnet3_rx_queue, napi); + int rxd_done; + + rxd_done = vmxnet3_do_poll(rx_queue->adapter, budget); + + if (rxd_done < budget) { + napi_complete(napi); + vmxnet3_enable_all_intrs(rx_queue->adapter); + } + return rxd_done; +} + +/* + * NAPI polling function for MSI-X mode with multiple Rx queues + * Returns the # of the NAPI credit consumed (# of rx descriptors processed) + */ + +static int +vmxnet3_poll_rx_only(struct napi_struct *napi, int budget) +{ + struct vmxnet3_rx_queue *rq = container_of(napi, + struct vmxnet3_rx_queue, napi); + struct vmxnet3_adapter *adapter = rq->adapter; int rxd_done; - rxd_done = vmxnet3_do_poll(adapter, budget); + /* When sharing interrupt with corresponding tx queue, process + * tx completions in that queue as well + */ + if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) { + struct vmxnet3_tx_queue *tq = + &adapter->tx_queue[rq - adapter->rx_queue]; + vmxnet3_tq_tx_complete(tq, adapter); + } + + rxd_done = vmxnet3_rq_rx_complete(rq, adapter, budget); if (rxd_done < budget) { napi_complete(napi); - vmxnet3_enable_intr(adapter, 0); + vmxnet3_enable_intr(adapter, rq->comp_ring.intr_idx); } return rxd_done; } +#ifdef CONFIG_PCI_MSI + +/* + * Handle completion interrupts on tx queues + * Returns whether or not the intr is handled + */ + +static irqreturn_t +vmxnet3_msix_tx(int irq, void *data) +{ + struct vmxnet3_tx_queue *tq = data; + struct vmxnet3_adapter *adapter = tq->adapter; + + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_intr(adapter, tq->comp_ring.intr_idx); + + /* Handle the case where only one irq is allocate for all tx queues */ + if (adapter->share_intr == VMXNET3_INTR_TXSHARE) { + int i; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *txq = &adapter->tx_queue[i]; + vmxnet3_tq_tx_complete(txq, adapter); + } + } else { + vmxnet3_tq_tx_complete(tq, adapter); + } + vmxnet3_enable_intr(adapter, tq->comp_ring.intr_idx); + + return IRQ_HANDLED; +} + + +/* + * Handle completion interrupts on rx queues. Returns whether or not the + * intr is handled + */ + +static irqreturn_t +vmxnet3_msix_rx(int irq, void *data) +{ + struct vmxnet3_rx_queue *rq = data; + struct vmxnet3_adapter *adapter = rq->adapter; + + /* disable intr if needed */ + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_intr(adapter, rq->comp_ring.intr_idx); + napi_schedule(&rq->napi); + + return IRQ_HANDLED; +} + +/* + *---------------------------------------------------------------------------- + * + * vmxnet3_msix_event -- + * + * vmxnet3 msix event intr handler + * + * Result: + * whether or not the intr is handled + * + *---------------------------------------------------------------------------- + */ + +static irqreturn_t +vmxnet3_msix_event(int irq, void *data) +{ + struct net_device *dev = data; + struct vmxnet3_adapter *adapter = netdev_priv(dev); + + /* disable intr if needed */ + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_intr(adapter, adapter->intr.event_intr_idx); + + if (adapter->shared->ecr) + vmxnet3_process_events(adapter); + + vmxnet3_enable_intr(adapter, adapter->intr.event_intr_idx); + + return IRQ_HANDLED; +} + +#endif /* CONFIG_PCI_MSI */ + + /* Interrupt handler for vmxnet3 */ static irqreturn_t vmxnet3_intr(int irq, void *dev_id) @@ -1432,7 +1737,7 @@ vmxnet3_intr(int irq, void *dev_id) struct net_device *dev = dev_id; struct vmxnet3_adapter *adapter = netdev_priv(dev); - if (unlikely(adapter->intr.type == VMXNET3_IT_INTX)) { + if (adapter->intr.type == VMXNET3_IT_INTX) { u32 icr = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR); if (unlikely(icr == 0)) /* not ours */ @@ -1442,77 +1747,155 @@ vmxnet3_intr(int irq, void *dev_id) /* disable intr if needed */ if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) - vmxnet3_disable_intr(adapter, 0); + vmxnet3_disable_all_intrs(adapter); - napi_schedule(&adapter->napi); + napi_schedule(&adapter->rx_queue[0].napi); return IRQ_HANDLED; } #ifdef CONFIG_NET_POLL_CONTROLLER - /* netpoll callback. */ static void vmxnet3_netpoll(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - int irq; + switch (adapter->intr.type) { #ifdef CONFIG_PCI_MSI - if (adapter->intr.type == VMXNET3_IT_MSIX) - irq = adapter->intr.msix_entries[0].vector; - else + case VMXNET3_IT_MSIX: { + int i; + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_msix_rx(0, &adapter->rx_queue[i]); + break; + } #endif - irq = adapter->pdev->irq; + case VMXNET3_IT_MSI: + default: + vmxnet3_intr(0, adapter->netdev); + break; + } - disable_irq(irq); - vmxnet3_intr(irq, netdev); - enable_irq(irq); } -#endif +#endif /* CONFIG_NET_POLL_CONTROLLER */ static int vmxnet3_request_irqs(struct vmxnet3_adapter *adapter) { - int err; + struct vmxnet3_intr *intr = &adapter->intr; + int err = 0, i; + int vector = 0; #ifdef CONFIG_PCI_MSI if (adapter->intr.type == VMXNET3_IT_MSIX) { - /* we only use 1 MSI-X vector */ - err = request_irq(adapter->intr.msix_entries[0].vector, - vmxnet3_intr, 0, adapter->netdev->name, - adapter->netdev); - } else if (adapter->intr.type == VMXNET3_IT_MSI) { + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) { + sprintf(adapter->tx_queue[i].name, "%s-tx-%d", + adapter->netdev->name, vector); + err = request_irq( + intr->msix_entries[vector].vector, + vmxnet3_msix_tx, 0, + adapter->tx_queue[i].name, + &adapter->tx_queue[i]); + } else { + sprintf(adapter->tx_queue[i].name, "%s-rxtx-%d", + adapter->netdev->name, vector); + } + if (err) { + dev_err(&adapter->netdev->dev, + "Failed to request irq for MSIX, %s, " + "error %d\n", + adapter->tx_queue[i].name, err); + return err; + } + + /* Handle the case where only 1 MSIx was allocated for + * all tx queues */ + if (adapter->share_intr == VMXNET3_INTR_TXSHARE) { + for (; i < adapter->num_tx_queues; i++) + adapter->tx_queue[i].comp_ring.intr_idx + = vector; + vector++; + break; + } else { + adapter->tx_queue[i].comp_ring.intr_idx + = vector++; + } + } + if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) + vector = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) + sprintf(adapter->rx_queue[i].name, "%s-rx-%d", + adapter->netdev->name, vector); + else + sprintf(adapter->rx_queue[i].name, "%s-rxtx-%d", + adapter->netdev->name, vector); + err = request_irq(intr->msix_entries[vector].vector, + vmxnet3_msix_rx, 0, + adapter->rx_queue[i].name, + &(adapter->rx_queue[i])); + if (err) { + netdev_err(adapter->netdev, + "Failed to request irq for MSIX, " + "%s, error %d\n", + adapter->rx_queue[i].name, err); + return err; + } + + adapter->rx_queue[i].comp_ring.intr_idx = vector++; + } + + sprintf(intr->event_msi_vector_name, "%s-event-%d", + adapter->netdev->name, vector); + err = request_irq(intr->msix_entries[vector].vector, + vmxnet3_msix_event, 0, + intr->event_msi_vector_name, adapter->netdev); + intr->event_intr_idx = vector; + + } else if (intr->type == VMXNET3_IT_MSI) { + adapter->num_rx_queues = 1; err = request_irq(adapter->pdev->irq, vmxnet3_intr, 0, adapter->netdev->name, adapter->netdev); - } else + } else { #endif - { + adapter->num_rx_queues = 1; err = request_irq(adapter->pdev->irq, vmxnet3_intr, IRQF_SHARED, adapter->netdev->name, adapter->netdev); +#ifdef CONFIG_PCI_MSI } +#endif + intr->num_intrs = vector + 1; + if (err) { + netdev_err(adapter->netdev, + "Failed to request irq (intr type:%d), error %d\n", + intr->type, err); + } else { + /* Number of rx queues will not change after this */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + rq->qid = i; + rq->qid2 = i + adapter->num_rx_queues; + } - if (err) - printk(KERN_ERR "Failed to request irq %s (intr type:%d), error" - ":%d\n", adapter->netdev->name, adapter->intr.type, err); - if (!err) { - int i; /* init our intr settings */ - for (i = 0; i < adapter->intr.num_intrs; i++) - adapter->intr.mod_levels[i] = UPT1_IML_ADAPTIVE; - - /* next setup intr index for all intr sources */ - adapter->tx_queue.comp_ring.intr_idx = 0; - adapter->rx_queue.comp_ring.intr_idx = 0; - adapter->intr.event_intr_idx = 0; + for (i = 0; i < intr->num_intrs; i++) + intr->mod_levels[i] = UPT1_IML_ADAPTIVE; + if (adapter->intr.type != VMXNET3_IT_MSIX) { + adapter->intr.event_intr_idx = 0; + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_queue[i].comp_ring.intr_idx = 0; + adapter->rx_queue[0].comp_ring.intr_idx = 0; + } - printk(KERN_INFO "%s: intr type %u, mode %u, %u vectors " - "allocated\n", adapter->netdev->name, adapter->intr.type, - adapter->intr.mask_mode, adapter->intr.num_intrs); + netdev_info(adapter->netdev, + "intr type %u, mode %u, %u vectors allocated\n", + intr->type, intr->mask_mode, intr->num_intrs); } return err; @@ -1522,18 +1905,32 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter) static void vmxnet3_free_irqs(struct vmxnet3_adapter *adapter) { - BUG_ON(adapter->intr.type == VMXNET3_IT_AUTO || - adapter->intr.num_intrs <= 0); + struct vmxnet3_intr *intr = &adapter->intr; + BUG_ON(intr->type == VMXNET3_IT_AUTO || intr->num_intrs <= 0); - switch (adapter->intr.type) { + switch (intr->type) { #ifdef CONFIG_PCI_MSI case VMXNET3_IT_MSIX: { - int i; + int i, vector = 0; + + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) { + for (i = 0; i < adapter->num_tx_queues; i++) { + free_irq(intr->msix_entries[vector++].vector, + &(adapter->tx_queue[i])); + if (adapter->share_intr == VMXNET3_INTR_TXSHARE) + break; + } + } - for (i = 0; i < adapter->intr.num_intrs; i++) - free_irq(adapter->intr.msix_entries[i].vector, - adapter->netdev); + for (i = 0; i < adapter->num_rx_queues; i++) { + free_irq(intr->msix_entries[vector++].vector, + &(adapter->rx_queue[i])); + } + + free_irq(intr->msix_entries[vector].vector, + adapter->netdev); + BUG_ON(vector >= intr->num_intrs); break; } #endif @@ -1544,112 +1941,66 @@ vmxnet3_free_irqs(struct vmxnet3_adapter *adapter) free_irq(adapter->pdev->irq, adapter->netdev); break; default: - BUG_ON(true); + BUG(); } } + static void -vmxnet3_vlan_rx_register(struct net_device *netdev, struct vlan_group *grp) +vmxnet3_restore_vlan(struct vmxnet3_adapter *adapter) { - struct vmxnet3_adapter *adapter = netdev_priv(netdev); - struct Vmxnet3_DriverShared *shared = adapter->shared; u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + u16 vid; - if (grp) { - /* add vlan rx stripping. */ - if (adapter->netdev->features & NETIF_F_HW_VLAN_RX) { - int i; - struct Vmxnet3_DSDevRead *devRead = &shared->devRead; - adapter->vlan_grp = grp; - - /* update FEATURES to device */ - devRead->misc.uptFeatures |= UPT1_F_RXVLAN; - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_FEATURE); - /* - * Clear entire vfTable; then enable untagged pkts. - * Note: setting one entry in vfTable to non-zero turns - * on VLAN rx filtering. - */ - for (i = 0; i < VMXNET3_VFT_SIZE; i++) - vfTable[i] = 0; - - VMXNET3_SET_VFTABLE_ENTRY(vfTable, 0); - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_VLAN_FILTERS); - } else { - printk(KERN_ERR "%s: vlan_rx_register when device has " - "no NETIF_F_HW_VLAN_RX\n", netdev->name); - } - } else { - /* remove vlan rx stripping. */ - struct Vmxnet3_DSDevRead *devRead = &shared->devRead; - adapter->vlan_grp = NULL; - - if (devRead->misc.uptFeatures & UPT1_F_RXVLAN) { - int i; - - for (i = 0; i < VMXNET3_VFT_SIZE; i++) { - /* clear entire vfTable; this also disables - * VLAN rx filtering - */ - vfTable[i] = 0; - } - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_VLAN_FILTERS); + /* allow untagged pkts */ + VMXNET3_SET_VFTABLE_ENTRY(vfTable, 0); - /* update FEATURES to device */ - devRead->misc.uptFeatures &= ~UPT1_F_RXVLAN; - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_FEATURE); - } - } + for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) + VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid); } -static void -vmxnet3_restore_vlan(struct vmxnet3_adapter *adapter) +static int +vmxnet3_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { - if (adapter->vlan_grp) { - u16 vid; + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (!(netdev->flags & IFF_PROMISC)) { u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; - bool activeVlan = false; + unsigned long flags; - for (vid = 0; vid < VLAN_N_VID; vid++) { - if (vlan_group_get_device(adapter->vlan_grp, vid)) { - VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid); - activeVlan = true; - } - } - if (activeVlan) { - /* continue to allow untagged pkts */ - VMXNET3_SET_VFTABLE_ENTRY(vfTable, 0); - } + VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); } + + set_bit(vid, adapter->active_vlans); + + return 0; } -static void -vmxnet3_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +static int +vmxnet3_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; - VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid); - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_VLAN_FILTERS); -} + if (!(netdev->flags & IFF_PROMISC)) { + u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + unsigned long flags; + VMXNET3_CLEAR_VFTABLE_ENTRY(vfTable, vid); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } -static void -vmxnet3_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) -{ - struct vmxnet3_adapter *adapter = netdev_priv(netdev); - u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + clear_bit(vid, adapter->active_vlans); - VMXNET3_CLEAR_VFTABLE_ENTRY(vfTable, vid); - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_VLAN_FILTERS); + return 0; } @@ -1680,13 +2031,21 @@ static void vmxnet3_set_mc(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; struct Vmxnet3_RxFilterConf *rxConf = &adapter->shared->devRead.rxFilterConf; u8 *new_table = NULL; + dma_addr_t new_table_pa = 0; u32 new_mode = VMXNET3_RXM_UCAST; - if (netdev->flags & IFF_PROMISC) + if (netdev->flags & IFF_PROMISC) { + u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + memset(vfTable, 0, VMXNET3_VFT_SIZE * sizeof(*vfTable)); + new_mode |= VMXNET3_RXM_PROMISC; + } else { + vmxnet3_restore_vlan(adapter); + } if (netdev->flags & IFF_BROADCAST) new_mode |= VMXNET3_RXM_BCAST; @@ -1700,11 +2059,15 @@ vmxnet3_set_mc(struct net_device *netdev) new_mode |= VMXNET3_RXM_MCAST; rxConf->mfTableLen = cpu_to_le16( netdev_mc_count(netdev) * ETH_ALEN); - rxConf->mfTablePA = cpu_to_le64(virt_to_phys( - new_table)); + new_table_pa = dma_map_single( + &adapter->pdev->dev, + new_table, + rxConf->mfTableLen, + PCI_DMA_TODEVICE); + rxConf->mfTablePA = cpu_to_le64(new_table_pa); } else { - printk(KERN_INFO "%s: failed to copy mcast list" - ", setting ALL_MULTI\n", netdev->name); + netdev_info(netdev, "failed to copy mcast list" + ", setting ALL_MULTI\n"); new_mode |= VMXNET3_RXM_ALL_MULTI; } } @@ -1715,16 +2078,33 @@ vmxnet3_set_mc(struct net_device *netdev) rxConf->mfTablePA = 0; } + spin_lock_irqsave(&adapter->cmd_lock, flags); if (new_mode != rxConf->rxMode) { rxConf->rxMode = cpu_to_le32(new_mode); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_UPDATE_RX_MODE); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); } VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_UPDATE_MAC_FILTERS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); - kfree(new_table); + if (new_table) { + dma_unmap_single(&adapter->pdev->dev, new_table_pa, + rxConf->mfTableLen, PCI_DMA_TODEVICE); + kfree(new_table); + } +} + +void +vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_rq_destroy(&adapter->rx_queue[i], adapter); } @@ -1755,59 +2135,99 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) devRead->misc.driverInfo.vmxnet3RevSpt = cpu_to_le32(1); devRead->misc.driverInfo.uptVerSpt = cpu_to_le32(1); - devRead->misc.ddPA = cpu_to_le64(virt_to_phys(adapter)); + devRead->misc.ddPA = cpu_to_le64(adapter->adapter_pa); 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); } - if ((adapter->netdev->features & NETIF_F_HW_VLAN_RX) && - adapter->vlan_grp) { + if (adapter->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) devRead->misc.uptFeatures |= UPT1_F_RXVLAN; - } devRead->misc.mtu = cpu_to_le32(adapter->netdev->mtu); devRead->misc.queueDescPA = cpu_to_le64(adapter->queue_desc_pa); devRead->misc.queueDescLen = cpu_to_le32( - sizeof(struct Vmxnet3_TxQueueDesc) + - sizeof(struct Vmxnet3_RxQueueDesc)); + adapter->num_tx_queues * sizeof(struct Vmxnet3_TxQueueDesc) + + adapter->num_rx_queues * sizeof(struct Vmxnet3_RxQueueDesc)); /* tx queue settings */ - BUG_ON(adapter->tx_queue.tx_ring.base == NULL); - - devRead->misc.numTxQueues = 1; - tqc = &adapter->tqd_start->conf; - tqc->txRingBasePA = cpu_to_le64(adapter->tx_queue.tx_ring.basePA); - tqc->dataRingBasePA = cpu_to_le64(adapter->tx_queue.data_ring.basePA); - tqc->compRingBasePA = cpu_to_le64(adapter->tx_queue.comp_ring.basePA); - tqc->ddPA = cpu_to_le64(virt_to_phys( - adapter->tx_queue.buf_info)); - tqc->txRingSize = cpu_to_le32(adapter->tx_queue.tx_ring.size); - tqc->dataRingSize = cpu_to_le32(adapter->tx_queue.data_ring.size); - tqc->compRingSize = cpu_to_le32(adapter->tx_queue.comp_ring.size); - tqc->ddLen = cpu_to_le32(sizeof(struct vmxnet3_tx_buf_info) * - tqc->txRingSize); - tqc->intrIdx = adapter->tx_queue.comp_ring.intr_idx; + devRead->misc.numTxQueues = adapter->num_tx_queues; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + BUG_ON(adapter->tx_queue[i].tx_ring.base == NULL); + tqc = &adapter->tqd_start[i].conf; + tqc->txRingBasePA = cpu_to_le64(tq->tx_ring.basePA); + tqc->dataRingBasePA = cpu_to_le64(tq->data_ring.basePA); + tqc->compRingBasePA = cpu_to_le64(tq->comp_ring.basePA); + tqc->ddPA = cpu_to_le64(tq->buf_info_pa); + tqc->txRingSize = cpu_to_le32(tq->tx_ring.size); + tqc->dataRingSize = cpu_to_le32(tq->data_ring.size); + tqc->compRingSize = cpu_to_le32(tq->comp_ring.size); + tqc->ddLen = cpu_to_le32( + sizeof(struct vmxnet3_tx_buf_info) * + tqc->txRingSize); + tqc->intrIdx = tq->comp_ring.intr_idx; + } /* rx queue settings */ - devRead->misc.numRxQueues = 1; - rqc = &adapter->rqd_start->conf; - rqc->rxRingBasePA[0] = cpu_to_le64(adapter->rx_queue.rx_ring[0].basePA); - rqc->rxRingBasePA[1] = cpu_to_le64(adapter->rx_queue.rx_ring[1].basePA); - rqc->compRingBasePA = cpu_to_le64(adapter->rx_queue.comp_ring.basePA); - rqc->ddPA = cpu_to_le64(virt_to_phys( - adapter->rx_queue.buf_info)); - rqc->rxRingSize[0] = cpu_to_le32(adapter->rx_queue.rx_ring[0].size); - rqc->rxRingSize[1] = cpu_to_le32(adapter->rx_queue.rx_ring[1].size); - rqc->compRingSize = cpu_to_le32(adapter->rx_queue.comp_ring.size); - rqc->ddLen = cpu_to_le32(sizeof(struct vmxnet3_rx_buf_info) * - (rqc->rxRingSize[0] + rqc->rxRingSize[1])); - rqc->intrIdx = adapter->rx_queue.comp_ring.intr_idx; + devRead->misc.numRxQueues = adapter->num_rx_queues; + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + rqc = &adapter->rqd_start[i].conf; + rqc->rxRingBasePA[0] = cpu_to_le64(rq->rx_ring[0].basePA); + rqc->rxRingBasePA[1] = cpu_to_le64(rq->rx_ring[1].basePA); + rqc->compRingBasePA = cpu_to_le64(rq->comp_ring.basePA); + rqc->ddPA = cpu_to_le64(rq->buf_info_pa); + rqc->rxRingSize[0] = cpu_to_le32(rq->rx_ring[0].size); + rqc->rxRingSize[1] = cpu_to_le32(rq->rx_ring[1].size); + rqc->compRingSize = cpu_to_le32(rq->comp_ring.size); + rqc->ddLen = cpu_to_le32( + sizeof(struct vmxnet3_rx_buf_info) * + (rqc->rxRingSize[0] + + rqc->rxRingSize[1])); + rqc->intrIdx = rq->comp_ring.intr_idx; + } + +#ifdef VMXNET3_RSS + memset(adapter->rss_conf, 0, sizeof(*adapter->rss_conf)); + + if (adapter->rss) { + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + static const uint8_t rss_key[UPT1_RSS_MAX_KEY_SIZE] = { + 0x3b, 0x56, 0xd1, 0x56, 0x13, 0x4a, 0xe7, 0xac, + 0xe8, 0x79, 0x09, 0x75, 0xe8, 0x65, 0x79, 0x28, + 0x35, 0x12, 0xb9, 0x56, 0x7c, 0x76, 0x4b, 0x70, + 0xd8, 0x56, 0xa3, 0x18, 0x9b, 0x0a, 0xee, 0xf3, + 0x96, 0xa6, 0x9f, 0x8f, 0x9e, 0x8c, 0x90, 0xc9, + }; + + devRead->misc.uptFeatures |= UPT1_F_RSS; + devRead->misc.numRxQueues = adapter->num_rx_queues; + rssConf->hashType = UPT1_RSS_HASH_TYPE_TCP_IPV4 | + UPT1_RSS_HASH_TYPE_IPV4 | + UPT1_RSS_HASH_TYPE_TCP_IPV6 | + UPT1_RSS_HASH_TYPE_IPV6; + rssConf->hashFunc = UPT1_RSS_HASH_FUNC_TOEPLITZ; + rssConf->hashKeySize = UPT1_RSS_MAX_KEY_SIZE; + rssConf->indTableSize = VMXNET3_RSS_IND_TABLE_SIZE; + memcpy(rssConf->hashKey, rss_key, sizeof(rss_key)); + + for (i = 0; i < rssConf->indTableSize; i++) + rssConf->indTable[i] = ethtool_rxfh_indir_default( + i, adapter->num_rx_queues); + + devRead->rssConfDesc.confVer = 1; + devRead->rssConfDesc.confLen = cpu_to_le32(sizeof(*rssConf)); + devRead->rssConfDesc.confPA = + cpu_to_le64(adapter->rss_conf_pa); + } + +#endif /* VMXNET3_RSS */ /* intr settings */ devRead->intrConf.autoMask = adapter->intr.mask_mode == @@ -1822,6 +2242,8 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) /* rx filter settings */ devRead->rxFilterConf.rxMode = 0; vmxnet3_restore_vlan(adapter); + vmxnet3_write_mac_addr(adapter, adapter->netdev->dev_addr); + /* the rest are already zeroed */ } @@ -1829,28 +2251,29 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) int vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) { - int err; + int err, i; u32 ret; + unsigned long flags; - dev_dbg(&adapter->netdev->dev, - "%s: skb_buf_size %d, rx_buf_per_pkt %d, ring sizes" - " %u %u %u\n", adapter->netdev->name, adapter->skb_buf_size, - adapter->rx_buf_per_pkt, adapter->tx_queue.tx_ring.size, - adapter->rx_queue.rx_ring[0].size, - adapter->rx_queue.rx_ring[1].size); + netdev_dbg(adapter->netdev, "%s: skb_buf_size %d, rx_buf_per_pkt %d," + " ring sizes %u %u %u\n", adapter->netdev->name, + adapter->skb_buf_size, adapter->rx_buf_per_pkt, + adapter->tx_queue[0].tx_ring.size, + adapter->rx_queue[0].rx_ring[0].size, + adapter->rx_queue[0].rx_ring[1].size); - vmxnet3_tq_init(&adapter->tx_queue, adapter); - err = vmxnet3_rq_init(&adapter->rx_queue, adapter); + vmxnet3_tq_init_all(adapter); + err = vmxnet3_rq_init_all(adapter); if (err) { - printk(KERN_ERR "Failed to init rx queue for %s: error %d\n", - adapter->netdev->name, err); + netdev_err(adapter->netdev, + "Failed to init rx queue error %d\n", err); goto rq_err; } err = vmxnet3_request_irqs(adapter); if (err) { - printk(KERN_ERR "Failed to setup irq for %s: error %d\n", - adapter->netdev->name, err); + netdev_err(adapter->netdev, + "Failed to setup irq for error %d\n", err); goto irq_err; } @@ -1860,20 +2283,27 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) adapter->shared_pa)); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DSAH, VMXNET3_GET_ADDR_HI( adapter->shared_pa)); + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_ACTIVATE_DEV); ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); if (ret != 0) { - printk(KERN_ERR "Failed to activate dev %s: error %u\n", - adapter->netdev->name, ret); + netdev_err(adapter->netdev, + "Failed to activate dev: error %u\n", ret); err = -EINVAL; goto activate_err; } - VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_RXPROD, - adapter->rx_queue.rx_ring[0].next2fill); - VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_RXPROD2, - adapter->rx_queue.rx_ring[1].next2fill); + + for (i = 0; i < adapter->num_rx_queues; i++) { + VMXNET3_WRITE_BAR0_REG(adapter, + VMXNET3_REG_RXPROD + i * VMXNET3_REG_ALIGN, + adapter->rx_queue[i].rx_ring[0].next2fill); + VMXNET3_WRITE_BAR0_REG(adapter, (VMXNET3_REG_RXPROD2 + + (i * VMXNET3_REG_ALIGN)), + adapter->rx_queue[i].rx_ring[1].next2fill); + } /* Apply the rx filter settins last. */ vmxnet3_set_mc(adapter->netdev); @@ -1883,8 +2313,8 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) * tx queue if the link is up. */ vmxnet3_check_link(adapter, true); - - napi_enable(&adapter->napi); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_queue[i].napi); vmxnet3_enable_all_intrs(adapter); clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); return 0; @@ -1896,7 +2326,7 @@ activate_err: irq_err: rq_err: /* free up buffers we allocated */ - vmxnet3_rq_cleanup(&adapter->rx_queue, adapter); + vmxnet3_rq_cleanup_all(adapter); return err; } @@ -1904,28 +2334,36 @@ rq_err: void vmxnet3_reset_dev(struct vmxnet3_adapter *adapter) { + unsigned long flags; + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_RESET_DEV); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); } int vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter) { + int i; + unsigned long flags; if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)) return 0; + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_QUIESCE_DEV); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); vmxnet3_disable_all_intrs(adapter); - napi_disable(&adapter->napi); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_disable(&adapter->rx_queue[i].napi); netif_tx_disable(adapter->netdev); adapter->link_speed = 0; netif_carrier_off(adapter->netdev); - vmxnet3_tq_cleanup(&adapter->tx_queue, adapter); - vmxnet3_rq_cleanup(&adapter->rx_queue, adapter); + vmxnet3_tq_cleanup_all(adapter); + vmxnet3_rq_cleanup_all(adapter); vmxnet3_free_irqs(adapter); return 0; } @@ -1968,23 +2406,22 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64) err = pci_enable_device(pdev); if (err) { - printk(KERN_ERR "Failed to enable adapter %s: error %d\n", - pci_name(pdev), err); + dev_err(&pdev->dev, "Failed to enable adapter: error %d\n", err); return err; } if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) { if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) { - printk(KERN_ERR "pci_set_consistent_dma_mask failed " - "for adapter %s\n", pci_name(pdev)); + dev_err(&pdev->dev, + "pci_set_consistent_dma_mask failed\n"); err = -EIO; goto err_set_mask; } *dma64 = true; } else { if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) { - printk(KERN_ERR "pci_set_dma_mask failed for adapter " - "%s\n", pci_name(pdev)); + dev_err(&pdev->dev, + "pci_set_dma_mask failed\n"); err = -EIO; goto err_set_mask; } @@ -1994,8 +2431,8 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64) err = pci_request_selected_regions(pdev, (1 << 2) - 1, vmxnet3_driver_name); if (err) { - printk(KERN_ERR "Failed to request region for adapter %s: " - "error %d\n", pci_name(pdev), err); + dev_err(&pdev->dev, + "Failed to request region for adapter: error %d\n", err); goto err_set_mask; } @@ -2005,8 +2442,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64) mmio_len = pci_resource_len(pdev, 0); adapter->hw_addr0 = ioremap(mmio_start, mmio_len); if (!adapter->hw_addr0) { - printk(KERN_ERR "Failed to map bar0 for adapter %s\n", - pci_name(pdev)); + dev_err(&pdev->dev, "Failed to map bar0\n"); err = -EIO; goto err_ioremap; } @@ -2015,8 +2451,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64) mmio_len = pci_resource_len(pdev, 1); adapter->hw_addr1 = ioremap(mmio_start, mmio_len); if (!adapter->hw_addr1) { - printk(KERN_ERR "Failed to map bar1 for adapter %s\n", - pci_name(pdev)); + dev_err(&pdev->dev, "Failed to map bar1\n"); err = -EIO; goto err_bar1; } @@ -2047,7 +2482,9 @@ vmxnet3_free_pci_resources(struct vmxnet3_adapter *adapter) static void vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter) { - size_t sz; + size_t sz, i, ring0_size, ring1_size, comp_size; + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[0]; + if (adapter->netdev->mtu <= VMXNET3_MAX_SKB_BUF_SIZE - VMXNET3_MAX_ETH_HDR_SIZE) { @@ -2069,11 +2506,19 @@ vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter) * rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN */ sz = adapter->rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN; - adapter->rx_queue.rx_ring[0].size = (adapter->rx_queue.rx_ring[0].size + - sz - 1) / sz * sz; - adapter->rx_queue.rx_ring[0].size = min_t(u32, - adapter->rx_queue.rx_ring[0].size, - VMXNET3_RX_RING_MAX_SIZE / sz * sz); + ring0_size = adapter->rx_queue[0].rx_ring[0].size; + ring0_size = (ring0_size + sz - 1) / sz * sz; + ring0_size = min_t(u32, ring0_size, VMXNET3_RX_RING_MAX_SIZE / + sz * sz); + ring1_size = adapter->rx_queue[0].rx_ring[1].size; + comp_size = ring0_size + ring1_size; + + for (i = 0; i < adapter->num_rx_queues; i++) { + rq = &adapter->rx_queue[i]; + rq->rx_ring[0].size = ring0_size; + rq->rx_ring[1].size = ring1_size; + rq->comp_ring.size = comp_size; + } } @@ -2081,29 +2526,55 @@ int vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size) { - int err; - - adapter->tx_queue.tx_ring.size = tx_ring_size; - adapter->tx_queue.data_ring.size = tx_ring_size; - adapter->tx_queue.comp_ring.size = tx_ring_size; - adapter->tx_queue.shared = &adapter->tqd_start->ctrl; - adapter->tx_queue.stopped = true; - err = vmxnet3_tq_create(&adapter->tx_queue, adapter); - if (err) - return err; + int err = 0, i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + tq->tx_ring.size = tx_ring_size; + tq->data_ring.size = tx_ring_size; + tq->comp_ring.size = tx_ring_size; + tq->shared = &adapter->tqd_start[i].ctrl; + tq->stopped = true; + tq->adapter = adapter; + tq->qid = i; + err = vmxnet3_tq_create(tq, adapter); + /* + * Too late to change num_tx_queues. We cannot do away with + * lesser number of queues than what we asked for + */ + if (err) + goto queue_err; + } - adapter->rx_queue.rx_ring[0].size = rx_ring_size; - adapter->rx_queue.rx_ring[1].size = rx_ring2_size; + adapter->rx_queue[0].rx_ring[0].size = rx_ring_size; + adapter->rx_queue[0].rx_ring[1].size = rx_ring2_size; vmxnet3_adjust_rx_ring_size(adapter); - adapter->rx_queue.comp_ring.size = adapter->rx_queue.rx_ring[0].size + - adapter->rx_queue.rx_ring[1].size; - adapter->rx_queue.qid = 0; - adapter->rx_queue.qid2 = 1; - adapter->rx_queue.shared = &adapter->rqd_start->ctrl; - err = vmxnet3_rq_create(&adapter->rx_queue, adapter); - if (err) - vmxnet3_tq_destroy(&adapter->tx_queue, adapter); - + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + /* qid and qid2 for rx queues will be assigned later when num + * of rx queues is finalized after allocating intrs */ + rq->shared = &adapter->rqd_start[i].ctrl; + rq->adapter = adapter; + err = vmxnet3_rq_create(rq, adapter); + if (err) { + if (i == 0) { + netdev_err(adapter->netdev, + "Could not allocate any rx queues. " + "Aborting.\n"); + goto queue_err; + } else { + netdev_info(adapter->netdev, + "Number of rx queues changed " + "to : %d.\n", i); + adapter->num_rx_queues = i; + err = 0; + break; + } + } + } + return err; +queue_err: + vmxnet3_tq_destroy_all(adapter); return err; } @@ -2111,14 +2582,15 @@ static int vmxnet3_open(struct net_device *netdev) { struct vmxnet3_adapter *adapter; - int err; + int err, i; adapter = netdev_priv(netdev); - spin_lock_init(&adapter->tx_queue.tx_lock); + for (i = 0; i < adapter->num_tx_queues; i++) + spin_lock_init(&adapter->tx_queue[i].tx_lock); - err = vmxnet3_create_queues(adapter, VMXNET3_DEF_TX_RING_SIZE, - VMXNET3_DEF_RX_RING_SIZE, + err = vmxnet3_create_queues(adapter, adapter->tx_ring_size, + adapter->rx_ring_size, VMXNET3_DEF_RX_RING_SIZE); if (err) goto queue_err; @@ -2130,8 +2602,8 @@ vmxnet3_open(struct net_device *netdev) return 0; activate_err: - vmxnet3_rq_destroy(&adapter->rx_queue, adapter); - vmxnet3_tq_destroy(&adapter->tx_queue, adapter); + vmxnet3_rq_destroy_all(adapter); + vmxnet3_tq_destroy_all(adapter); queue_err: return err; } @@ -2151,8 +2623,8 @@ vmxnet3_close(struct net_device *netdev) vmxnet3_quiesce_dev(adapter); - vmxnet3_rq_destroy(&adapter->rx_queue, adapter); - vmxnet3_tq_destroy(&adapter->tx_queue, adapter); + vmxnet3_rq_destroy_all(adapter); + vmxnet3_tq_destroy_all(adapter); clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); @@ -2164,6 +2636,8 @@ vmxnet3_close(struct net_device *netdev) void vmxnet3_force_close(struct vmxnet3_adapter *adapter) { + int i; + /* * we must clear VMXNET3_STATE_BIT_RESETTING, otherwise * vmxnet3_close() will deadlock. @@ -2171,7 +2645,8 @@ vmxnet3_force_close(struct vmxnet3_adapter *adapter) BUG_ON(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)); /* we need to enable NAPI, otherwise dev_close will deadlock */ - napi_enable(&adapter->napi); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_queue[i].napi); dev_close(adapter->netdev); } @@ -2185,9 +2660,6 @@ 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; /* @@ -2202,22 +2674,21 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) vmxnet3_reset_dev(adapter); /* we need to re-create the rx queue based on the new mtu */ - vmxnet3_rq_destroy(&adapter->rx_queue, adapter); + vmxnet3_rq_destroy_all(adapter); vmxnet3_adjust_rx_ring_size(adapter); - adapter->rx_queue.comp_ring.size = - adapter->rx_queue.rx_ring[0].size + - adapter->rx_queue.rx_ring[1].size; - err = vmxnet3_rq_create(&adapter->rx_queue, adapter); + err = vmxnet3_rq_create_all(adapter); if (err) { - printk(KERN_ERR "%s: failed to re-create rx queue," - " error %d. Closing it.\n", netdev->name, err); + netdev_err(netdev, + "failed to re-create rx queues, " + " error %d. Closing it.\n", err); goto out; } err = vmxnet3_activate_dev(adapter); if (err) { - printk(KERN_ERR "%s: failed to re-activate, error %d. " - "Closing it\n", netdev->name, err); + netdev_err(netdev, + "failed to re-activate, error %d. " + "Closing it\n", err); goto out; } } @@ -2236,28 +2707,16 @@ 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 | + netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | 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->features |= NETIF_F_HIGHDMA; - printk(" highDMA"); - } - - netdev->vlan_features = netdev->features; - printk("\n"); + if (dma64) + netdev->hw_features |= NETIF_F_HIGHDMA; + netdev->vlan_features = netdev->hw_features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + netdev->features = netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; } @@ -2274,16 +2733,57 @@ vmxnet3_read_mac_addr(struct vmxnet3_adapter *adapter, u8 *mac) mac[5] = (tmp >> 8) & 0xff; } +#ifdef CONFIG_PCI_MSI + +/* + * Enable MSIx vectors. + * Returns : + * VMXNET3_LINUX_MIN_MSIX_VECT when only minimum number of vectors required + * were enabled. + * number of vectors which were enabled otherwise (this number is greater + * than VMXNET3_LINUX_MIN_MSIX_VECT) + */ + +static int +vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter, int nvec) +{ + int ret = pci_enable_msix_range(adapter->pdev, + adapter->intr.msix_entries, nvec, nvec); + + if (ret == -ENOSPC && nvec > VMXNET3_LINUX_MIN_MSIX_VECT) { + dev_err(&adapter->netdev->dev, + "Failed to enable %d MSI-X, trying %d\n", + nvec, VMXNET3_LINUX_MIN_MSIX_VECT); + + ret = pci_enable_msix_range(adapter->pdev, + adapter->intr.msix_entries, + VMXNET3_LINUX_MIN_MSIX_VECT, + VMXNET3_LINUX_MIN_MSIX_VECT); + } + + if (ret < 0) { + dev_err(&adapter->netdev->dev, + "Failed to enable MSI-X, error: %d\n", ret); + } + + return ret; +} + + +#endif /* CONFIG_PCI_MSI */ static void vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) { u32 cfg; + unsigned long flags; /* intr settings */ + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_CONF_INTR); cfg = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); adapter->intr.type = cfg & 0x3; adapter->intr.mask_mode = (cfg >> 2) & 0x3; @@ -2293,29 +2793,60 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) #ifdef CONFIG_PCI_MSI if (adapter->intr.type == VMXNET3_IT_MSIX) { - int err; + int i, nvec; - adapter->intr.msix_entries[0].entry = 0; - err = pci_enable_msix(adapter->pdev, adapter->intr.msix_entries, - VMXNET3_LINUX_MAX_MSIX_VECT); - if (!err) { - adapter->intr.num_intrs = 1; - adapter->intr.type = VMXNET3_IT_MSIX; - return; + nvec = adapter->share_intr == VMXNET3_INTR_TXSHARE ? + 1 : adapter->num_tx_queues; + nvec += adapter->share_intr == VMXNET3_INTR_BUDDYSHARE ? + 0 : adapter->num_rx_queues; + nvec += 1; /* for link event */ + nvec = nvec > VMXNET3_LINUX_MIN_MSIX_VECT ? + nvec : VMXNET3_LINUX_MIN_MSIX_VECT; + + for (i = 0; i < nvec; i++) + adapter->intr.msix_entries[i].entry = i; + + nvec = vmxnet3_acquire_msix_vectors(adapter, nvec); + if (nvec < 0) + goto msix_err; + + /* If we cannot allocate one MSIx vector per queue + * then limit the number of rx queues to 1 + */ + if (nvec == VMXNET3_LINUX_MIN_MSIX_VECT) { + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE + || adapter->num_rx_queues != 1) { + adapter->share_intr = VMXNET3_INTR_TXSHARE; + netdev_err(adapter->netdev, + "Number of rx queues : 1\n"); + adapter->num_rx_queues = 1; + } } + + adapter->intr.num_intrs = nvec; + return; + +msix_err: + /* If we cannot allocate MSIx vectors use only one rx queue */ + dev_info(&adapter->pdev->dev, + "Failed to enable MSI-X, error %d. " + "Limiting #rx queues to 1, try MSI.\n", nvec); + adapter->intr.type = VMXNET3_IT_MSI; } if (adapter->intr.type == VMXNET3_IT_MSI) { - int err; - err = pci_enable_msi(adapter->pdev); - if (!err) { + if (!pci_enable_msi(adapter->pdev)) { + adapter->num_rx_queues = 1; adapter->intr.num_intrs = 1; return; } } #endif /* CONFIG_PCI_MSI */ + adapter->num_rx_queues = 1; + dev_info(&adapter->netdev->dev, + "Using INTx interrupt, #Rx queues: 1.\n"); adapter->intr.type = VMXNET3_IT_INTX; /* INT-X related setting */ @@ -2341,8 +2872,9 @@ vmxnet3_tx_timeout(struct net_device *netdev) struct vmxnet3_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - printk(KERN_ERR "%s: tx hang\n", adapter->netdev->name); + netdev_err(adapter->netdev, "tx hang\n"); schedule_work(&adapter->work); + netif_wake_queue(adapter->netdev); } @@ -2360,12 +2892,12 @@ vmxnet3_reset_work(struct work_struct *data) /* if the device is closed, we must leave it alone */ rtnl_lock(); if (netif_running(adapter->netdev)) { - printk(KERN_INFO "%s: resetting\n", adapter->netdev->name); + netdev_notice(adapter->netdev, "resetting\n"); vmxnet3_quiesce_dev(adapter); vmxnet3_reset_dev(adapter); vmxnet3_activate_dev(adapter); } else { - printk(KERN_INFO "%s: already closed\n", adapter->netdev->name); + netdev_info(adapter->netdev, "already closed\n"); } rtnl_unlock(); @@ -2373,7 +2905,7 @@ vmxnet3_reset_work(struct work_struct *data) } -static int __devinit +static int vmxnet3_probe_device(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -2383,10 +2915,10 @@ 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_get_stats = vmxnet3_get_stats, + .ndo_set_features = vmxnet3_set_features, + .ndo_get_stats64 = vmxnet3_get_stats64, .ndo_tx_timeout = vmxnet3_tx_timeout, - .ndo_set_multicast_list = vmxnet3_set_mc, - .ndo_vlan_rx_register = vmxnet3_vlan_rx_register, + .ndo_set_rx_mode = vmxnet3_set_mc, .ndo_vlan_rx_add_vid = vmxnet3_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = vmxnet3_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -2399,51 +2931,99 @@ vmxnet3_probe_device(struct pci_dev *pdev, struct net_device *netdev; struct vmxnet3_adapter *adapter; u8 mac[ETH_ALEN]; + int size; + 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, + (int)num_online_cpus()); + 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, + (int)num_online_cpus()); + else + num_tx_queues = 1; - netdev = alloc_etherdev(sizeof(struct vmxnet3_adapter)); - if (!netdev) { - printk(KERN_ERR "Failed to alloc ethernet device for adapter " - "%s\n", pci_name(pdev)); + 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)); + dev_info(&pdev->dev, + "# of Tx queues : %d, # of Rx queues : %d\n", + num_tx_queues, num_rx_queues); + + if (!netdev) return -ENOMEM; - } pci_set_drvdata(pdev, netdev); adapter = netdev_priv(netdev); adapter->netdev = netdev; adapter->pdev = pdev; - adapter->shared = pci_alloc_consistent(adapter->pdev, - sizeof(struct Vmxnet3_DriverShared), - &adapter->shared_pa); + adapter->tx_ring_size = VMXNET3_DEF_TX_RING_SIZE; + adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE; + + spin_lock_init(&adapter->cmd_lock); + adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter, + sizeof(struct vmxnet3_adapter), + PCI_DMA_TODEVICE); + adapter->shared = dma_alloc_coherent( + &adapter->pdev->dev, + sizeof(struct Vmxnet3_DriverShared), + &adapter->shared_pa, GFP_KERNEL); if (!adapter->shared) { - printk(KERN_ERR "Failed to allocate memory for %s\n", - pci_name(pdev)); + dev_err(&pdev->dev, "Failed to allocate memory\n"); err = -ENOMEM; goto err_alloc_shared; } - adapter->tqd_start = pci_alloc_consistent(adapter->pdev, - sizeof(struct Vmxnet3_TxQueueDesc) + - sizeof(struct Vmxnet3_RxQueueDesc), - &adapter->queue_desc_pa); + adapter->num_rx_queues = num_rx_queues; + adapter->num_tx_queues = num_tx_queues; + adapter->rx_buf_per_pkt = 1; + + size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues; + size += sizeof(struct Vmxnet3_RxQueueDesc) * adapter->num_rx_queues; + adapter->tqd_start = dma_alloc_coherent(&adapter->pdev->dev, size, + &adapter->queue_desc_pa, + GFP_KERNEL); if (!adapter->tqd_start) { - printk(KERN_ERR "Failed to allocate memory for %s\n", - pci_name(pdev)); + dev_err(&pdev->dev, "Failed to allocate memory\n"); err = -ENOMEM; goto err_alloc_queue_desc; } - adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start - + 1); + adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start + + adapter->num_tx_queues); - adapter->pm_conf = kmalloc(sizeof(struct Vmxnet3_PMConf), GFP_KERNEL); + adapter->pm_conf = dma_alloc_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_PMConf), + &adapter->pm_conf_pa, + GFP_KERNEL); if (adapter->pm_conf == NULL) { - printk(KERN_ERR "Failed to allocate memory for %s\n", - pci_name(pdev)); err = -ENOMEM; goto err_alloc_pm; } +#ifdef VMXNET3_RSS + + adapter->rss_conf = dma_alloc_coherent(&adapter->pdev->dev, + sizeof(struct UPT1_RSSConf), + &adapter->rss_conf_pa, + GFP_KERNEL); + if (adapter->rss_conf == NULL) { + err = -ENOMEM; + goto err_alloc_rss; + } +#endif /* VMXNET3_RSS */ + err = vmxnet3_alloc_pci_resources(adapter, &dma64); if (err < 0) goto err_alloc_pci; @@ -2452,8 +3032,8 @@ vmxnet3_probe_device(struct pci_dev *pdev, if (ver & 1) { VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1); } else { - printk(KERN_ERR "Incompatible h/w version (0x%x) for adapter" - " %s\n", ver, pci_name(pdev)); + dev_err(&pdev->dev, + "Incompatible h/w version (0x%x) for adapter\n", ver); err = -EBUSY; goto err_ver; } @@ -2462,39 +3042,68 @@ vmxnet3_probe_device(struct pci_dev *pdev, if (ver & 1) { VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_UVRS, 1); } else { - printk(KERN_ERR "Incompatible upt version (0x%x) for " - "adapter %s\n", ver, pci_name(pdev)); + dev_err(&pdev->dev, + "Incompatible upt version (0x%x) for adapter\n", ver); err = -EBUSY; goto err_ver; } + SET_NETDEV_DEV(netdev, &pdev->dev); vmxnet3_declare_features(adapter, dma64); - adapter->dev_number = atomic_read(&devices_found); + if (adapter->num_tx_queues == adapter->num_rx_queues) + adapter->share_intr = VMXNET3_INTR_BUDDYSHARE; + else + adapter->share_intr = VMXNET3_INTR_DONTSHARE; + vmxnet3_alloc_intr_resources(adapter); +#ifdef VMXNET3_RSS + if (adapter->num_rx_queues > 1 && + adapter->intr.type == VMXNET3_IT_MSIX) { + adapter->rss = true; + netdev->hw_features |= NETIF_F_RXHASH; + netdev->features |= NETIF_F_RXHASH; + dev_dbg(&pdev->dev, "RSS is enabled.\n"); + } else { + adapter->rss = false; + } +#endif + vmxnet3_read_mac_addr(adapter, mac); memcpy(netdev->dev_addr, mac, netdev->addr_len); netdev->netdev_ops = &vmxnet3_netdev_ops; - netdev->watchdog_timeo = 5 * HZ; vmxnet3_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; INIT_WORK(&adapter->work, vmxnet3_reset_work); + set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); - netif_napi_add(netdev, &adapter->napi, vmxnet3_poll, 64); - SET_NETDEV_DEV(netdev, &pdev->dev); + if (adapter->intr.type == VMXNET3_IT_MSIX) { + int i; + for (i = 0; i < adapter->num_rx_queues; i++) { + netif_napi_add(adapter->netdev, + &adapter->rx_queue[i].napi, + vmxnet3_poll_rx_only, 64); + } + } else { + netif_napi_add(adapter->netdev, &adapter->rx_queue[0].napi, + vmxnet3_poll, 64); + } + + netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); + netif_set_real_num_rx_queues(adapter->netdev, adapter->num_rx_queues); + + netif_carrier_off(netdev); err = register_netdev(netdev); if (err) { - printk(KERN_ERR "Failed to register adapter %s\n", - pci_name(pdev)); + dev_err(&pdev->dev, "Failed to register adapter\n"); goto err_register; } - set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); vmxnet3_check_link(adapter, false); - atomic_inc(&devices_found); return 0; err_register: @@ -2502,39 +3111,67 @@ err_register: err_ver: vmxnet3_free_pci_resources(adapter); err_alloc_pci: - kfree(adapter->pm_conf); +#ifdef VMXNET3_RSS + dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf), + adapter->rss_conf, adapter->rss_conf_pa); +err_alloc_rss: +#endif + dma_free_coherent(&adapter->pdev->dev, sizeof(struct Vmxnet3_PMConf), + adapter->pm_conf, adapter->pm_conf_pa); err_alloc_pm: - pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_TxQueueDesc) + - sizeof(struct Vmxnet3_RxQueueDesc), - adapter->tqd_start, adapter->queue_desc_pa); + dma_free_coherent(&adapter->pdev->dev, size, adapter->tqd_start, + adapter->queue_desc_pa); err_alloc_queue_desc: - pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_DriverShared), - adapter->shared, adapter->shared_pa); + dma_free_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_DriverShared), + adapter->shared, adapter->shared_pa); err_alloc_shared: - pci_set_drvdata(pdev, NULL); + dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa, + sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE); free_netdev(netdev); return err; } -static void __devexit +static void vmxnet3_remove_device(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int size = 0; + int num_rx_queues; + +#ifdef VMXNET3_RSS + if (enable_mq) + num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES, + (int)num_online_cpus()); + else +#endif + num_rx_queues = 1; + num_rx_queues = rounddown_pow_of_two(num_rx_queues); - flush_scheduled_work(); + cancel_work_sync(&adapter->work); unregister_netdev(netdev); vmxnet3_free_intr_resources(adapter); vmxnet3_free_pci_resources(adapter); - kfree(adapter->pm_conf); - pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_TxQueueDesc) + - sizeof(struct Vmxnet3_RxQueueDesc), - adapter->tqd_start, adapter->queue_desc_pa); - pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_DriverShared), - adapter->shared, adapter->shared_pa); +#ifdef VMXNET3_RSS + dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf), + adapter->rss_conf, adapter->rss_conf_pa); +#endif + dma_free_coherent(&adapter->pdev->dev, sizeof(struct Vmxnet3_PMConf), + adapter->pm_conf, adapter->pm_conf_pa); + + size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues; + size += sizeof(struct Vmxnet3_RxQueueDesc) * num_rx_queues; + dma_free_coherent(&adapter->pdev->dev, size, adapter->tqd_start, + adapter->queue_desc_pa); + dma_free_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_DriverShared), + adapter->shared, adapter->shared_pa); + dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa, + sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE); free_netdev(netdev); } @@ -2553,17 +3190,21 @@ vmxnet3_suspend(struct device *device) u8 *arpreq; struct in_device *in_dev; struct in_ifaddr *ifa; + unsigned long flags; int i = 0; if (!netif_running(netdev)) return 0; + for (i = 0; i < adapter->num_rx_queues; i++) + napi_disable(&adapter->rx_queue[i].napi); + vmxnet3_disable_all_intrs(adapter); vmxnet3_free_irqs(adapter); vmxnet3_free_intr_resources(adapter); netif_device_detach(netdev); - netif_stop_queue(netdev); + netif_tx_stop_all_queues(netdev); /* Create wake-up filters. */ pmConf = adapter->pm_conf; @@ -2630,11 +3271,13 @@ skip_arp: adapter->shared->devRead.pmConfDesc.confVer = cpu_to_le32(1); adapter->shared->devRead.pmConfDesc.confLen = cpu_to_le32(sizeof( *pmConf)); - adapter->shared->devRead.pmConfDesc.confPA = cpu_to_le64(virt_to_phys( - pmConf)); + adapter->shared->devRead.pmConfDesc.confPA = + cpu_to_le64(adapter->pm_conf_pa); + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_UPDATE_PMCFG); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); pci_save_state(pdev); pci_enable_wake(pdev, pci_choose_state(pdev, PMSG_SUSPEND), @@ -2649,7 +3292,8 @@ skip_arp: static int vmxnet3_resume(struct device *device) { - int err; + int err, i = 0; + unsigned long flags; struct pci_dev *pdev = to_pci_dev(device); struct net_device *netdev = pci_get_drvdata(pdev); struct vmxnet3_adapter *adapter = netdev_priv(netdev); @@ -2665,8 +3309,8 @@ vmxnet3_resume(struct device *device) adapter->shared->devRead.pmConfDesc.confVer = cpu_to_le32(1); adapter->shared->devRead.pmConfDesc.confLen = cpu_to_le32(sizeof( *pmConf)); - adapter->shared->devRead.pmConfDesc.confPA = cpu_to_le64(virt_to_phys( - pmConf)); + adapter->shared->devRead.pmConfDesc.confPA = + cpu_to_le64(adapter->pm_conf_pa); netif_device_attach(netdev); pci_set_power_state(pdev, PCI_D0); @@ -2677,10 +3321,14 @@ vmxnet3_resume(struct device *device) pci_enable_wake(pdev, PCI_D0, 0); + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_UPDATE_PMCFG); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); vmxnet3_alloc_intr_resources(adapter); vmxnet3_request_irqs(adapter); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_queue[i].napi); vmxnet3_enable_all_intrs(adapter); return 0; @@ -2696,7 +3344,7 @@ static struct pci_driver vmxnet3_driver = { .name = vmxnet3_driver_name, .id_table = vmxnet3_pciid_table, .probe = vmxnet3_probe_device, - .remove = __devexit_p(vmxnet3_remove_device), + .remove = vmxnet3_remove_device, #ifdef CONFIG_PM .driver.pm = &vmxnet3_pm_ops, #endif @@ -2706,7 +3354,7 @@ static struct pci_driver vmxnet3_driver = { static int __init vmxnet3_init_module(void) { - printk(KERN_INFO "%s - version %s\n", VMXNET3_DRIVER_DESC, + pr_info("%s - version %s\n", VMXNET3_DRIVER_DESC, VMXNET3_DRIVER_VERSION_REPORT); return pci_register_driver(&vmxnet3_driver); } diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index b79070bcc92..b725fd9e780 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -33,174 +33,149 @@ struct vmxnet3_stat_desc { }; -static u32 -vmxnet3_get_rx_csum(struct net_device *netdev) -{ - struct vmxnet3_adapter *adapter = netdev_priv(netdev); - return adapter->rxcsum; -} - - -static int -vmxnet3_set_rx_csum(struct net_device *netdev, u32 val) -{ - struct vmxnet3_adapter *adapter = netdev_priv(netdev); - - if (adapter->rxcsum != val) { - adapter->rxcsum = val; - if (netif_running(netdev)) { - if (val) - adapter->shared->devRead.misc.uptFeatures |= - UPT1_F_RXCSUM; - else - adapter->shared->devRead.misc.uptFeatures &= - ~UPT1_F_RXCSUM; - - VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, - VMXNET3_CMD_UPDATE_FEATURE); - } - } - return 0; -} - - /* per tq stats maintained by the device */ static const struct vmxnet3_stat_desc vmxnet3_tq_dev_stats[] = { /* description, offset */ - { "TSO pkts tx", offsetof(struct UPT1_TxStats, TSOPktsTxOK) }, - { "TSO bytes tx", offsetof(struct UPT1_TxStats, TSOBytesTxOK) }, - { "ucast pkts tx", offsetof(struct UPT1_TxStats, ucastPktsTxOK) }, - { "ucast bytes tx", offsetof(struct UPT1_TxStats, ucastBytesTxOK) }, - { "mcast pkts tx", offsetof(struct UPT1_TxStats, mcastPktsTxOK) }, - { "mcast bytes tx", offsetof(struct UPT1_TxStats, mcastBytesTxOK) }, - { "bcast pkts tx", offsetof(struct UPT1_TxStats, bcastPktsTxOK) }, - { "bcast bytes tx", offsetof(struct UPT1_TxStats, bcastBytesTxOK) }, - { "pkts tx err", offsetof(struct UPT1_TxStats, pktsTxError) }, - { "pkts tx discard", offsetof(struct UPT1_TxStats, pktsTxDiscard) }, + { "Tx Queue#", 0 }, + { " TSO pkts tx", offsetof(struct UPT1_TxStats, TSOPktsTxOK) }, + { " TSO bytes tx", offsetof(struct UPT1_TxStats, TSOBytesTxOK) }, + { " ucast pkts tx", offsetof(struct UPT1_TxStats, ucastPktsTxOK) }, + { " ucast bytes tx", offsetof(struct UPT1_TxStats, ucastBytesTxOK) }, + { " mcast pkts tx", offsetof(struct UPT1_TxStats, mcastPktsTxOK) }, + { " mcast bytes tx", offsetof(struct UPT1_TxStats, mcastBytesTxOK) }, + { " bcast pkts tx", offsetof(struct UPT1_TxStats, bcastPktsTxOK) }, + { " bcast bytes tx", offsetof(struct UPT1_TxStats, bcastBytesTxOK) }, + { " pkts tx err", offsetof(struct UPT1_TxStats, pktsTxError) }, + { " pkts tx discard", offsetof(struct UPT1_TxStats, pktsTxDiscard) }, }; /* per tq stats maintained by the driver */ static const struct vmxnet3_stat_desc vmxnet3_tq_driver_stats[] = { /* description, offset */ - {"drv dropped tx total", offsetof(struct vmxnet3_tq_driver_stats, - drop_total) }, - { " too many frags", offsetof(struct vmxnet3_tq_driver_stats, - drop_too_many_frags) }, - { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, - drop_oversized_hdr) }, - { " hdr err", offsetof(struct vmxnet3_tq_driver_stats, - drop_hdr_inspect_err) }, - { " tso", offsetof(struct vmxnet3_tq_driver_stats, - drop_tso) }, - { "ring full", offsetof(struct vmxnet3_tq_driver_stats, - tx_ring_full) }, - { "pkts linearized", offsetof(struct vmxnet3_tq_driver_stats, - linearized) }, - { "hdr cloned", offsetof(struct vmxnet3_tq_driver_stats, - copy_skb_header) }, - { "giant hdr", offsetof(struct vmxnet3_tq_driver_stats, - oversized_hdr) }, + {" drv dropped tx total", offsetof(struct vmxnet3_tq_driver_stats, + drop_total) }, + { " too many frags", offsetof(struct vmxnet3_tq_driver_stats, + drop_too_many_frags) }, + { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, + drop_oversized_hdr) }, + { " hdr err", offsetof(struct vmxnet3_tq_driver_stats, + drop_hdr_inspect_err) }, + { " tso", offsetof(struct vmxnet3_tq_driver_stats, + drop_tso) }, + { " ring full", offsetof(struct vmxnet3_tq_driver_stats, + tx_ring_full) }, + { " pkts linearized", offsetof(struct vmxnet3_tq_driver_stats, + linearized) }, + { " hdr cloned", offsetof(struct vmxnet3_tq_driver_stats, + copy_skb_header) }, + { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, + oversized_hdr) }, }; /* per rq stats maintained by the device */ static const struct vmxnet3_stat_desc vmxnet3_rq_dev_stats[] = { - { "LRO pkts rx", offsetof(struct UPT1_RxStats, LROPktsRxOK) }, - { "LRO byte rx", offsetof(struct UPT1_RxStats, LROBytesRxOK) }, - { "ucast pkts rx", offsetof(struct UPT1_RxStats, ucastPktsRxOK) }, - { "ucast bytes rx", offsetof(struct UPT1_RxStats, ucastBytesRxOK) }, - { "mcast pkts rx", offsetof(struct UPT1_RxStats, mcastPktsRxOK) }, - { "mcast bytes rx", offsetof(struct UPT1_RxStats, mcastBytesRxOK) }, - { "bcast pkts rx", offsetof(struct UPT1_RxStats, bcastPktsRxOK) }, - { "bcast bytes rx", offsetof(struct UPT1_RxStats, bcastBytesRxOK) }, - { "pkts rx out of buf", offsetof(struct UPT1_RxStats, pktsRxOutOfBuf) }, - { "pkts rx err", offsetof(struct UPT1_RxStats, pktsRxError) }, + { "Rx Queue#", 0 }, + { " LRO pkts rx", offsetof(struct UPT1_RxStats, LROPktsRxOK) }, + { " LRO byte rx", offsetof(struct UPT1_RxStats, LROBytesRxOK) }, + { " ucast pkts rx", offsetof(struct UPT1_RxStats, ucastPktsRxOK) }, + { " ucast bytes rx", offsetof(struct UPT1_RxStats, ucastBytesRxOK) }, + { " mcast pkts rx", offsetof(struct UPT1_RxStats, mcastPktsRxOK) }, + { " mcast bytes rx", offsetof(struct UPT1_RxStats, mcastBytesRxOK) }, + { " bcast pkts rx", offsetof(struct UPT1_RxStats, bcastPktsRxOK) }, + { " bcast bytes rx", offsetof(struct UPT1_RxStats, bcastBytesRxOK) }, + { " pkts rx OOB", offsetof(struct UPT1_RxStats, pktsRxOutOfBuf) }, + { " pkts rx err", offsetof(struct UPT1_RxStats, pktsRxError) }, }; /* per rq stats maintained by the driver */ static const struct vmxnet3_stat_desc vmxnet3_rq_driver_stats[] = { /* description, offset */ - { "drv dropped rx total", offsetof(struct vmxnet3_rq_driver_stats, - drop_total) }, - { " err", offsetof(struct vmxnet3_rq_driver_stats, - drop_err) }, - { " fcs", offsetof(struct vmxnet3_rq_driver_stats, - drop_fcs) }, - { "rx buf alloc fail", offsetof(struct vmxnet3_rq_driver_stats, - rx_buf_alloc_failure) }, + { " drv dropped rx total", offsetof(struct vmxnet3_rq_driver_stats, + drop_total) }, + { " err", offsetof(struct vmxnet3_rq_driver_stats, + drop_err) }, + { " fcs", offsetof(struct vmxnet3_rq_driver_stats, + drop_fcs) }, + { " rx buf alloc fail", offsetof(struct vmxnet3_rq_driver_stats, + rx_buf_alloc_failure) }, }; /* gloabl stats maintained by the driver */ static const struct vmxnet3_stat_desc vmxnet3_global_stats[] = { /* description, offset */ - { "tx timeout count", offsetof(struct vmxnet3_adapter, + { "tx timeout count", offsetof(struct vmxnet3_adapter, tx_timeout_count) } }; -struct net_device_stats * -vmxnet3_get_stats(struct net_device *netdev) +struct rtnl_link_stats64 * +vmxnet3_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct vmxnet3_adapter *adapter; struct vmxnet3_tq_driver_stats *drvTxStats; struct vmxnet3_rq_driver_stats *drvRxStats; struct UPT1_TxStats *devTxStats; struct UPT1_RxStats *devRxStats; - struct net_device_stats *net_stats = &netdev->stats; + unsigned long flags; + int i; adapter = netdev_priv(netdev); /* Collect the dev stats into the shared area */ + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + for (i = 0; i < adapter->num_tx_queues; i++) { + devTxStats = &adapter->tqd_start[i].stats; + drvTxStats = &adapter->tx_queue[i].stats; + stats->tx_packets += devTxStats->ucastPktsTxOK + + devTxStats->mcastPktsTxOK + + devTxStats->bcastPktsTxOK; + stats->tx_bytes += devTxStats->ucastBytesTxOK + + devTxStats->mcastBytesTxOK + + devTxStats->bcastBytesTxOK; + stats->tx_errors += devTxStats->pktsTxError; + stats->tx_dropped += drvTxStats->drop_total; + } - /* Assuming that we have a single queue device */ - devTxStats = &adapter->tqd_start->stats; - devRxStats = &adapter->rqd_start->stats; - - /* Get access to the driver stats per queue */ - drvTxStats = &adapter->tx_queue.stats; - drvRxStats = &adapter->rx_queue.stats; - - memset(net_stats, 0, sizeof(*net_stats)); - - net_stats->rx_packets = devRxStats->ucastPktsRxOK + - devRxStats->mcastPktsRxOK + - devRxStats->bcastPktsRxOK; - - net_stats->tx_packets = devTxStats->ucastPktsTxOK + - devTxStats->mcastPktsTxOK + - devTxStats->bcastPktsTxOK; - - net_stats->rx_bytes = devRxStats->ucastBytesRxOK + - devRxStats->mcastBytesRxOK + - devRxStats->bcastBytesRxOK; + for (i = 0; i < adapter->num_rx_queues; i++) { + devRxStats = &adapter->rqd_start[i].stats; + drvRxStats = &adapter->rx_queue[i].stats; + stats->rx_packets += devRxStats->ucastPktsRxOK + + devRxStats->mcastPktsRxOK + + devRxStats->bcastPktsRxOK; - net_stats->tx_bytes = devTxStats->ucastBytesTxOK + - devTxStats->mcastBytesTxOK + - devTxStats->bcastBytesTxOK; + stats->rx_bytes += devRxStats->ucastBytesRxOK + + devRxStats->mcastBytesRxOK + + devRxStats->bcastBytesRxOK; - net_stats->rx_errors = devRxStats->pktsRxError; - net_stats->tx_errors = devTxStats->pktsTxError; - net_stats->rx_dropped = drvRxStats->drop_total; - net_stats->tx_dropped = drvTxStats->drop_total; - net_stats->multicast = devRxStats->mcastPktsRxOK; + stats->rx_errors += devRxStats->pktsRxError; + stats->rx_dropped += drvRxStats->drop_total; + stats->multicast += devRxStats->mcastPktsRxOK; + } - return net_stats; + return stats; } static int vmxnet3_get_sset_count(struct net_device *netdev, int sset) { + struct vmxnet3_adapter *adapter = netdev_priv(netdev); switch (sset) { case ETH_SS_STATS: - return ARRAY_SIZE(vmxnet3_tq_dev_stats) + - ARRAY_SIZE(vmxnet3_tq_driver_stats) + - ARRAY_SIZE(vmxnet3_rq_dev_stats) + - ARRAY_SIZE(vmxnet3_rq_driver_stats) + + return (ARRAY_SIZE(vmxnet3_tq_dev_stats) + + ARRAY_SIZE(vmxnet3_tq_driver_stats)) * + adapter->num_tx_queues + + (ARRAY_SIZE(vmxnet3_rq_dev_stats) + + ARRAY_SIZE(vmxnet3_rq_driver_stats)) * + adapter->num_rx_queues + ARRAY_SIZE(vmxnet3_global_stats); default: return -EOPNOTSUPP; @@ -208,10 +183,16 @@ vmxnet3_get_sset_count(struct net_device *netdev, int sset) } +/* Should be multiple of 4 */ +#define NUM_TX_REGS 8 +#define NUM_RX_REGS 12 + static int vmxnet3_get_regs_len(struct net_device *netdev) { - return 20 * sizeof(u32); + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + return (adapter->num_tx_queues * NUM_TX_REGS * sizeof(u32) + + adapter->num_rx_queues * NUM_RX_REGS * sizeof(u32)); } @@ -221,17 +202,12 @@ vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) struct vmxnet3_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, vmxnet3_driver_name, sizeof(drvinfo->driver)); - drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; strlcpy(drvinfo->version, VMXNET3_DRIVER_VERSION_REPORT, sizeof(drvinfo->version)); - drvinfo->driver[sizeof(drvinfo->version) - 1] = '\0'; - - strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); - drvinfo->fw_version[sizeof(drvinfo->fw_version) - 1] = '\0'; strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), - ETHTOOL_BUSINFO_LEN); + sizeof(drvinfo->bus_info)); drvinfo->n_stats = vmxnet3_get_sset_count(netdev, ETH_SS_STATS); drvinfo->testinfo_len = 0; drvinfo->eedump_len = 0; @@ -242,29 +218,37 @@ vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) static void vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) { + struct vmxnet3_adapter *adapter = netdev_priv(netdev); if (stringset == ETH_SS_STATS) { - int i; - - for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) { - memcpy(buf, vmxnet3_tq_dev_stats[i].desc, - ETH_GSTRING_LEN); - buf += ETH_GSTRING_LEN; - } - for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) { - memcpy(buf, vmxnet3_tq_driver_stats[i].desc, - ETH_GSTRING_LEN); - buf += ETH_GSTRING_LEN; - } - for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) { - memcpy(buf, vmxnet3_rq_dev_stats[i].desc, - ETH_GSTRING_LEN); - buf += ETH_GSTRING_LEN; + int i, j; + for (j = 0; j < adapter->num_tx_queues; j++) { + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) { + memcpy(buf, vmxnet3_tq_dev_stats[i].desc, + ETH_GSTRING_LEN); + buf += ETH_GSTRING_LEN; + } + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); + i++) { + memcpy(buf, vmxnet3_tq_driver_stats[i].desc, + ETH_GSTRING_LEN); + buf += ETH_GSTRING_LEN; + } } - for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) { - memcpy(buf, vmxnet3_rq_driver_stats[i].desc, - ETH_GSTRING_LEN); - buf += ETH_GSTRING_LEN; + + for (j = 0; j < adapter->num_rx_queues; j++) { + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) { + memcpy(buf, vmxnet3_rq_dev_stats[i].desc, + ETH_GSTRING_LEN); + buf += ETH_GSTRING_LEN; + } + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); + i++) { + memcpy(buf, vmxnet3_rq_driver_stats[i].desc, + ETH_GSTRING_LEN); + buf += ETH_GSTRING_LEN; + } } + for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) { memcpy(buf, vmxnet3_global_stats[i].desc, ETH_GSTRING_LEN); @@ -273,29 +257,40 @@ vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) } } -static int -vmxnet3_set_flags(struct net_device *netdev, u32 data) +int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - u8 lro_requested = (data & ETH_FLAG_LRO) == 0 ? 0 : 1; - u8 lro_present = (netdev->features & NETIF_F_LRO) == 0 ? 0 : 1; + unsigned long flags; + netdev_features_t changed = features ^ netdev->features; - if (data & ~ETH_FLAG_LRO) - return -EOPNOTSUPP; - - if (lro_requested ^ lro_present) { - /* toggle the LRO feature*/ - netdev->features ^= NETIF_F_LRO; + if (changed & (NETIF_F_RXCSUM | NETIF_F_LRO | + NETIF_F_HW_VLAN_CTAG_RX)) { + if (features & NETIF_F_RXCSUM) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXCSUM; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXCSUM; /* update harware LRO capability accordingly */ - if (lro_requested) + if (features & NETIF_F_LRO) adapter->shared->devRead.misc.uptFeatures |= UPT1_F_LRO; else adapter->shared->devRead.misc.uptFeatures &= ~UPT1_F_LRO; + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXVLAN; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXVLAN; + + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_UPDATE_FEATURE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); } return 0; } @@ -305,28 +300,41 @@ vmxnet3_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *buf) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; u8 *base; int i; + int j = 0; + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); /* this does assume each counter is 64-bit wide */ + for (j = 0; j < adapter->num_tx_queues; j++) { + base = (u8 *)&adapter->tqd_start[j].stats; + *buf++ = (u64)j; + for (i = 1; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_tq_dev_stats[i].offset); + + base = (u8 *)&adapter->tx_queue[j].stats; + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_tq_driver_stats[i].offset); + } - base = (u8 *)&adapter->tqd_start->stats; - for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) - *buf++ = *(u64 *)(base + vmxnet3_tq_dev_stats[i].offset); - - base = (u8 *)&adapter->tx_queue.stats; - for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) - *buf++ = *(u64 *)(base + vmxnet3_tq_driver_stats[i].offset); - - base = (u8 *)&adapter->rqd_start->stats; - for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) - *buf++ = *(u64 *)(base + vmxnet3_rq_dev_stats[i].offset); - - base = (u8 *)&adapter->rx_queue.stats; - for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) - *buf++ = *(u64 *)(base + vmxnet3_rq_driver_stats[i].offset); + for (j = 0; j < adapter->num_tx_queues; j++) { + base = (u8 *)&adapter->rqd_start[j].stats; + *buf++ = (u64) j; + for (i = 1; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_rq_dev_stats[i].offset); + + base = (u8 *)&adapter->rx_queue[j].stats; + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_rq_driver_stats[i].offset); + } base = (u8 *)adapter; for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) @@ -339,6 +347,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); u32 *buf = p; + int i = 0, j = 0; memset(p, 0, vmxnet3_get_regs_len(netdev)); @@ -347,30 +356,35 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) /* Update vmxnet3_get_regs_len if we want to dump more registers */ /* make each ring use multiple of 16 bytes */ - buf[0] = adapter->tx_queue.tx_ring.next2fill; - buf[1] = adapter->tx_queue.tx_ring.next2comp; - buf[2] = adapter->tx_queue.tx_ring.gen; - buf[3] = 0; - - buf[4] = adapter->tx_queue.comp_ring.next2proc; - buf[5] = adapter->tx_queue.comp_ring.gen; - buf[6] = adapter->tx_queue.stopped; - buf[7] = 0; - - buf[8] = adapter->rx_queue.rx_ring[0].next2fill; - buf[9] = adapter->rx_queue.rx_ring[0].next2comp; - buf[10] = adapter->rx_queue.rx_ring[0].gen; - buf[11] = 0; - - buf[12] = adapter->rx_queue.rx_ring[1].next2fill; - buf[13] = adapter->rx_queue.rx_ring[1].next2comp; - buf[14] = adapter->rx_queue.rx_ring[1].gen; - buf[15] = 0; - - buf[16] = adapter->rx_queue.comp_ring.next2proc; - buf[17] = adapter->rx_queue.comp_ring.gen; - buf[18] = 0; - buf[19] = 0; + for (i = 0; i < adapter->num_tx_queues; i++) { + buf[j++] = adapter->tx_queue[i].tx_ring.next2fill; + buf[j++] = adapter->tx_queue[i].tx_ring.next2comp; + buf[j++] = adapter->tx_queue[i].tx_ring.gen; + buf[j++] = 0; + + buf[j++] = adapter->tx_queue[i].comp_ring.next2proc; + buf[j++] = adapter->tx_queue[i].comp_ring.gen; + buf[j++] = adapter->tx_queue[i].stopped; + buf[j++] = 0; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + buf[j++] = adapter->rx_queue[i].rx_ring[0].next2fill; + buf[j++] = adapter->rx_queue[i].rx_ring[0].next2comp; + buf[j++] = adapter->rx_queue[i].rx_ring[0].gen; + buf[j++] = 0; + + buf[j++] = adapter->rx_queue[i].rx_ring[1].next2fill; + buf[j++] = adapter->rx_queue[i].rx_ring[1].next2comp; + buf[j++] = adapter->rx_queue[i].rx_ring[1].gen; + buf[j++] = 0; + + buf[j++] = adapter->rx_queue[i].comp_ring.next2proc; + buf[j++] = adapter->rx_queue[i].comp_ring.gen; + buf[j++] = 0; + buf[j++] = 0; + } + } @@ -414,11 +428,11 @@ vmxnet3_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) ecmd->transceiver = XCVR_INTERNAL; if (adapter->link_speed) { - ecmd->speed = adapter->link_speed; + ethtool_cmd_speed_set(ecmd, adapter->link_speed); ecmd->duplex = DUPLEX_FULL; } else { - ecmd->speed = -1; - ecmd->duplex = -1; + ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); + ecmd->duplex = DUPLEX_UNKNOWN; } return 0; } @@ -435,8 +449,8 @@ vmxnet3_get_ringparam(struct net_device *netdev, param->rx_mini_max_pending = 0; param->rx_jumbo_max_pending = 0; - param->rx_pending = adapter->rx_queue.rx_ring[0].size; - param->tx_pending = adapter->tx_queue.tx_ring.size; + param->rx_pending = adapter->rx_ring_size; + param->tx_pending = adapter->tx_ring_size; param->rx_mini_pending = 0; param->rx_jumbo_pending = 0; } @@ -459,6 +473,12 @@ vmxnet3_set_ringparam(struct net_device *netdev, VMXNET3_RX_RING_MAX_SIZE) return -EINVAL; + /* if adapter not yet initialized, do nothing */ + if (adapter->rx_buf_per_pkt == 0) { + netdev_err(netdev, "adapter not completely initialized, " + "ring size cannot be changed yet\n"); + return -EOPNOTSUPP; + } /* round it up to a multiple of VMXNET3_RING_SIZE_ALIGN */ new_tx_ring_size = (param->tx_pending + VMXNET3_RING_SIZE_MASK) & @@ -480,8 +500,8 @@ vmxnet3_set_ringparam(struct net_device *netdev, sz) != 0) return -EINVAL; - if (new_tx_ring_size == adapter->tx_queue.tx_ring.size && - new_rx_ring_size == adapter->rx_queue.rx_ring[0].size) { + if (new_tx_ring_size == adapter->tx_queue[0].tx_ring.size && + new_rx_ring_size == adapter->rx_queue[0].rx_ring[0].size) { return 0; } @@ -498,33 +518,37 @@ vmxnet3_set_ringparam(struct net_device *netdev, /* recreate the rx queue and the tx queue based on the * new sizes */ - vmxnet3_tq_destroy(&adapter->tx_queue, adapter); - vmxnet3_rq_destroy(&adapter->rx_queue, adapter); + vmxnet3_tq_destroy_all(adapter); + vmxnet3_rq_destroy_all(adapter); err = vmxnet3_create_queues(adapter, new_tx_ring_size, new_rx_ring_size, VMXNET3_DEF_RX_RING_SIZE); + if (err) { /* failed, most likely because of OOM, try default * size */ - printk(KERN_ERR "%s: failed to apply new sizes, try the" - " default ones\n", netdev->name); + netdev_err(netdev, "failed to apply new sizes, " + "try the default ones\n"); + new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE; + new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE; err = vmxnet3_create_queues(adapter, - VMXNET3_DEF_TX_RING_SIZE, - VMXNET3_DEF_RX_RING_SIZE, + new_tx_ring_size, + new_rx_ring_size, VMXNET3_DEF_RX_RING_SIZE); if (err) { - printk(KERN_ERR "%s: failed to create queues " - "with default sizes. Closing it\n", - netdev->name); + netdev_err(netdev, "failed to create queues " + "with default sizes. Closing it\n"); goto out; } } err = vmxnet3_activate_dev(adapter); if (err) - printk(KERN_ERR "%s: failed to re-activate, error %d." - " Closing it\n", netdev->name, err); + netdev_err(netdev, "failed to re-activate, error %d." + " Closing it\n", err); } + adapter->tx_ring_size = new_tx_ring_size; + adapter->rx_ring_size = new_rx_ring_size; out: clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); @@ -535,7 +559,64 @@ out: } -static struct ethtool_ops vmxnet3_ethtool_ops = { +static int +vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info, + u32 *rules) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = adapter->num_rx_queues; + return 0; + } + return -EOPNOTSUPP; +} + +#ifdef VMXNET3_RSS +static u32 +vmxnet3_get_rss_indir_size(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + return rssConf->indTableSize; +} + +static int +vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + unsigned int n = rssConf->indTableSize; + + while (n--) + p[n] = rssConf->indTable[n]; + return 0; + +} + +static int +vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key) +{ + unsigned int i; + unsigned long flags; + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + for (i = 0; i < rssConf->indTableSize; i++) + rssConf->indTable[i] = p[i]; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_RSSIDT); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + return 0; + +} +#endif + +static const struct ethtool_ops vmxnet3_ethtool_ops = { .get_settings = vmxnet3_get_settings, .get_drvinfo = vmxnet3_get_drvinfo, .get_regs_len = vmxnet3_get_regs_len, @@ -543,24 +624,20 @@ static struct ethtool_ops vmxnet3_ethtool_ops = { .get_wol = vmxnet3_get_wol, .set_wol = vmxnet3_set_wol, .get_link = ethtool_op_get_link, - .get_rx_csum = vmxnet3_get_rx_csum, - .set_rx_csum = vmxnet3_set_rx_csum, - .get_tx_csum = ethtool_op_get_tx_csum, - .set_tx_csum = ethtool_op_set_tx_hw_csum, - .get_sg = ethtool_op_get_sg, - .set_sg = ethtool_op_set_sg, - .get_tso = ethtool_op_get_tso, - .set_tso = ethtool_op_set_tso, .get_strings = vmxnet3_get_strings, - .get_flags = ethtool_op_get_flags, - .set_flags = vmxnet3_set_flags, .get_sset_count = vmxnet3_get_sset_count, .get_ethtool_stats = vmxnet3_get_ethtool_stats, .get_ringparam = vmxnet3_get_ringparam, .set_ringparam = vmxnet3_set_ringparam, + .get_rxnfc = vmxnet3_get_rxnfc, +#ifdef VMXNET3_RSS + .get_rxfh_indir_size = vmxnet3_get_rss_indir_size, + .get_rxfh = vmxnet3_get_rss, + .set_rxfh = vmxnet3_set_rss, +#endif }; void vmxnet3_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); + netdev->ethtool_ops = &vmxnet3_ethtool_ops; } diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 8a2f4712284..29ee77f2c97 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -27,6 +27,7 @@ #ifndef _VMXNET3_INT_H #define _VMXNET3_INT_H +#include <linux/bitops.h> #include <linux/ethtool.h> #include <linux/delay.h> #include <linux/netdevice.h> @@ -36,7 +37,6 @@ #include <linux/spinlock.h> #include <linux/ioport.h> #include <linux/highmem.h> -#include <linux/init.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/interrupt.h> @@ -55,6 +55,7 @@ #include <linux/if_vlan.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> +#include <linux/log2.h> #include "vmxnet3_defs.h" @@ -68,11 +69,15 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.0.14.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.2.0.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01000E00 +#define VMXNET3_DRIVER_VERSION_NUM 0x01020000 +#if defined(CONFIG_PCI_MSI) + /* RSS only makes sense if MSI-X is supported. */ + #define VMXNET3_RSS +#endif /* * Capabilities @@ -218,16 +223,20 @@ struct vmxnet3_tx_ctx { }; struct vmxnet3_tx_queue { + char name[IFNAMSIZ+8]; /* To identify interrupt */ + struct vmxnet3_adapter *adapter; spinlock_t tx_lock; struct vmxnet3_cmd_ring tx_ring; - struct vmxnet3_tx_buf_info *buf_info; + struct vmxnet3_tx_buf_info *buf_info; + dma_addr_t buf_info_pa; struct vmxnet3_tx_data_ring data_ring; struct vmxnet3_comp_ring comp_ring; - struct Vmxnet3_TxQueueCtrl *shared; + struct Vmxnet3_TxQueueCtrl *shared; struct vmxnet3_tq_driver_stats stats; bool stopped; int num_stop; /* # of times the queue is * stopped */ + int qid; } __attribute__((__aligned__(SMP_CACHE_BYTES))); enum vmxnet3_rx_buf_type { @@ -259,19 +268,30 @@ struct vmxnet3_rq_driver_stats { }; struct vmxnet3_rx_queue { + char name[IFNAMSIZ + 8]; /* To identify interrupt */ + struct vmxnet3_adapter *adapter; + struct napi_struct napi; struct vmxnet3_cmd_ring rx_ring[2]; struct vmxnet3_comp_ring comp_ring; struct vmxnet3_rx_ctx rx_ctx; u32 qid; /* rqID in RCD for buffer from 1st ring */ u32 qid2; /* rqID in RCD for buffer from 2nd ring */ - u32 uncommitted[2]; /* # of buffers allocated since last RXPROD - * update */ struct vmxnet3_rx_buf_info *buf_info[2]; + dma_addr_t buf_info_pa; struct Vmxnet3_RxQueueCtrl *shared; struct vmxnet3_rq_driver_stats stats; } __attribute__((__aligned__(SMP_CACHE_BYTES))); -#define VMXNET3_LINUX_MAX_MSIX_VECT 1 +#define VMXNET3_DEVICE_MAX_TX_QUEUES 8 +#define VMXNET3_DEVICE_MAX_RX_QUEUES 8 /* Keep this value as a power of 2 */ + +/* Should be less than UPT1_RSS_MAX_IND_TABLE_SIZE */ +#define VMXNET3_RSS_IND_TABLE_SIZE (VMXNET3_DEVICE_MAX_RX_QUEUES * 4) + +#define VMXNET3_LINUX_MAX_MSIX_VECT (VMXNET3_DEVICE_MAX_TX_QUEUES + \ + VMXNET3_DEVICE_MAX_RX_QUEUES + 1) +#define VMXNET3_LINUX_MIN_MSIX_VECT 2 /* 1 for tx-rx pair and 1 for event */ + struct vmxnet3_intr { enum vmxnet3_intr_mask_mode mask_mode; @@ -279,35 +299,42 @@ struct vmxnet3_intr { u8 num_intrs; /* # of intr vectors */ u8 event_intr_idx; /* idx of the intr vector for event */ u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */ + char event_msi_vector_name[IFNAMSIZ+11]; #ifdef CONFIG_PCI_MSI struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT]; #endif }; +/* Interrupt sharing schemes, share_intr */ +#define VMXNET3_INTR_BUDDYSHARE 0 /* Corresponding tx,rx queues share irq */ +#define VMXNET3_INTR_TXSHARE 1 /* All tx queues share one irq */ +#define VMXNET3_INTR_DONTSHARE 2 /* each queue has its own irq */ + + #define VMXNET3_STATE_BIT_RESETTING 0 #define VMXNET3_STATE_BIT_QUIESCED 1 struct vmxnet3_adapter { - struct vmxnet3_tx_queue tx_queue; - struct vmxnet3_rx_queue rx_queue; - struct napi_struct napi; - struct vlan_group *vlan_grp; - - struct vmxnet3_intr intr; - - struct Vmxnet3_DriverShared *shared; - struct Vmxnet3_PMConf *pm_conf; - struct Vmxnet3_TxQueueDesc *tqd_start; /* first tx queue desc */ - struct Vmxnet3_RxQueueDesc *rqd_start; /* first rx queue desc */ - struct net_device *netdev; - struct pci_dev *pdev; + struct vmxnet3_tx_queue tx_queue[VMXNET3_DEVICE_MAX_TX_QUEUES]; + struct vmxnet3_rx_queue rx_queue[VMXNET3_DEVICE_MAX_RX_QUEUES]; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + struct vmxnet3_intr intr; + spinlock_t cmd_lock; + struct Vmxnet3_DriverShared *shared; + struct Vmxnet3_PMConf *pm_conf; + struct Vmxnet3_TxQueueDesc *tqd_start; /* all tx queue desc */ + struct Vmxnet3_RxQueueDesc *rqd_start; /* all rx queue desc */ + struct net_device *netdev; + struct pci_dev *pdev; u8 __iomem *hw_addr0; /* for BAR 0 */ u8 __iomem *hw_addr1; /* for BAR 1 */ - /* feature control */ - bool rxcsum; - bool lro; - bool jumbo_frame; +#ifdef VMXNET3_RSS + struct UPT1_RSSConf *rss_conf; + bool rss; +#endif + u32 num_rx_queues; + u32 num_tx_queues; /* rx buffer related */ unsigned skb_buf_size; @@ -322,22 +349,31 @@ struct vmxnet3_adapter { u32 link_speed; /* in mbps */ u64 tx_timeout_count; + + /* Ring sizes */ + u32 tx_ring_size; + u32 rx_ring_size; + struct work_struct work; unsigned long state; /* VMXNET3_STATE_BIT_xxx */ - int dev_number; + int share_intr; + + dma_addr_t adapter_pa; + dma_addr_t pm_conf_pa; + dma_addr_t rss_conf_pa; }; #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val) \ - writel(cpu_to_le32(val), (adapter)->hw_addr0 + (reg)) + writel((val), (adapter)->hw_addr0 + (reg)) #define VMXNET3_READ_BAR0_REG(adapter, reg) \ - le32_to_cpu(readl((adapter)->hw_addr0 + (reg))) + readl((adapter)->hw_addr0 + (reg)) #define VMXNET3_WRITE_BAR1_REG(adapter, reg, val) \ - writel(cpu_to_le32(val), (adapter)->hw_addr1 + (reg)) + writel((val), (adapter)->hw_addr1 + (reg)) #define VMXNET3_READ_BAR1_REG(adapter, reg) \ - le32_to_cpu(readl((adapter)->hw_addr1 + (reg))) + readl((adapter)->hw_addr1 + (reg)) #define VMXNET3_WAKE_QUEUE_THRESHOLD(tq) (5) #define VMXNET3_RX_ALLOC_THRESHOLD(rq, ring_idx, adapter) \ @@ -366,19 +402,22 @@ void vmxnet3_reset_dev(struct vmxnet3_adapter *adapter); void -vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq, - struct vmxnet3_adapter *adapter); +vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter); void -vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, - struct vmxnet3_adapter *adapter); +vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter); + +int +vmxnet3_set_features(struct net_device *netdev, netdev_features_t features); int vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size); -extern void vmxnet3_set_ethtool_ops(struct net_device *netdev); -extern struct net_device_stats *vmxnet3_get_stats(struct net_device *netdev); +void vmxnet3_set_ethtool_ops(struct net_device *netdev); + +struct rtnl_link_stats64 * +vmxnet3_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats); extern char vmxnet3_driver_name[]; #endif |