*
* TODO
* rx_copybreak/alignment
- * Scatter gather
* More testing
*
* The changes are (c) Copyright 2004, Red Hat Inc. <alan@lxorguk.ukuu.org.uk>
#define DMA_LENGTH_MIN 0
#define DMA_LENGTH_MAX 7
-#define DMA_LENGTH_DEF 0
+#define DMA_LENGTH_DEF 6
/* DMA_length[] is used for controlling the DMA length
0: 8 DWORDs
*/
VELOCITY_PARAM(IP_byte_align, "Enable IP header dword aligned");
-#define TX_CSUM_DEF 1
-/* txcsum_offload[] is used for setting the checksum offload ability of NIC.
- (We only support RX checksum offload now)
- 0: disable csum_offload[checksum offload
- 1: enable checksum offload. (Default)
-*/
-VELOCITY_PARAM(txcsum_offload, "Enable transmit packet checksum offload");
-
#define FLOW_CNTL_DEF 1
#define FLOW_CNTL_MIN 1
#define FLOW_CNTL_MAX 5
*/
VELOCITY_PARAM(wol_opts, "Wake On Lan options");
-#define INT_WORKS_DEF 20
-#define INT_WORKS_MIN 10
-#define INT_WORKS_MAX 64
-
-VELOCITY_PARAM(int_works, "Number of packets per interrupt services");
-
static int rx_copybreak = 200;
module_param(rx_copybreak, int, 0644);
MODULE_PARM_DESC(rx_copybreak, "Copy breakpoint for copy-only-tiny-frames");
velocity_set_int_opt(&opts->numrx, RxDescriptors[index], RX_DESC_MIN, RX_DESC_MAX, RX_DESC_DEF, "RxDescriptors", devname);
velocity_set_int_opt(&opts->numtx, TxDescriptors[index], TX_DESC_MIN, TX_DESC_MAX, TX_DESC_DEF, "TxDescriptors", devname);
- velocity_set_bool_opt(&opts->flags, txcsum_offload[index], TX_CSUM_DEF, VELOCITY_FLAGS_TX_CSUM, "txcsum_offload", devname);
velocity_set_int_opt(&opts->flow_cntl, flow_control[index], FLOW_CNTL_MIN, FLOW_CNTL_MAX, FLOW_CNTL_DEF, "flow_control", devname);
velocity_set_bool_opt(&opts->flags, IP_byte_align[index], IP_ALIG_DEF, VELOCITY_FLAGS_IP_ALIGN, "IP_byte_align", devname);
velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname);
velocity_set_int_opt((int *) &opts->spd_dpx, speed_duplex[index], MED_LNK_MIN, MED_LNK_MAX, MED_LNK_DEF, "Media link mode", devname);
velocity_set_int_opt((int *) &opts->wol_opts, wol_opts[index], WOL_OPT_MIN, WOL_OPT_MAX, WOL_OPT_DEF, "Wake On Lan options", devname);
- velocity_set_int_opt((int *) &opts->int_works, int_works[index], INT_WORKS_MIN, INT_WORKS_MAX, INT_WORKS_DEF, "Interrupt service works", devname);
opts->numrx = (opts->numrx & ~3);
}
/*
Check if new status is consisent with current status
- if (((mii_status & curr_status) & VELOCITY_AUTONEG_ENABLE)
- || (mii_status==curr_status)) {
+ if (((mii_status & curr_status) & VELOCITY_AUTONEG_ENABLE) ||
+ (mii_status==curr_status)) {
vptr->mii_status=mii_check_media_mode(vptr->mac_regs);
vptr->mii_status=check_connection_type(vptr->mac_regs);
VELOCITY_PRT(MSG_LEVEL_INFO, "Velocity link no change\n");
writel(0xffffffff, ®s->MARCAM[0]);
writel(0xffffffff, ®s->MARCAM[4]);
rx_mode = (RCR_AM | RCR_AB | RCR_PROM);
- } else if ((dev->mc_count > vptr->multicast_limit)
- || (dev->flags & IFF_ALLMULTI)) {
+ } else if ((dev->mc_count > vptr->multicast_limit) ||
+ (dev->flags & IFF_ALLMULTI)) {
writel(0xffffffff, ®s->MARCAM[0]);
writel(0xffffffff, ®s->MARCAM[4]);
rx_mode = (RCR_AM | RCR_AB);
*/
static int velocity_init_td_ring(struct velocity_info *vptr)
{
- dma_addr_t curr;
int j;
/* Init the TD ring entries */
for (j = 0; j < vptr->tx.numq; j++) {
- curr = vptr->tx.pool_dma[j];
vptr->tx.infos[j] = kcalloc(vptr->options.numtx,
sizeof(struct velocity_td_info),
* Release an transmit buffer. If the buffer was preallocated then
* recycle it, if not then unmap the buffer.
*/
-static void velocity_free_tx_buf(struct velocity_info *vptr, struct velocity_td_info *tdinfo)
+static void velocity_free_tx_buf(struct velocity_info *vptr,
+ struct velocity_td_info *tdinfo, struct tx_desc *td)
{
struct sk_buff *skb = tdinfo->skb;
- int i;
- int pktlen;
/*
* Don't unmap the pre-allocated tx_bufs
*/
if (tdinfo->skb_dma) {
+ int i;
- pktlen = max_t(unsigned int, skb->len, ETH_ZLEN);
for (i = 0; i < tdinfo->nskb_dma; i++) {
- pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i], pktlen, PCI_DMA_TODEVICE);
- tdinfo->skb_dma[i] = 0;
+ size_t pktlen = max_t(size_t, skb->len, ETH_ZLEN);
+
+ /* For scatter-gather */
+ if (skb_shinfo(skb)->nr_frags > 0)
+ pktlen = max_t(size_t, pktlen,
+ td->td_buf[i].size & ~TD_QUEUE);
+
+ pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i],
+ le16_to_cpu(pktlen), PCI_DMA_TODEVICE);
}
}
dev_kfree_skb_irq(skb);
stats->tx_packets++;
stats->tx_bytes += tdinfo->skb->len;
}
- velocity_free_tx_buf(vptr, tdinfo);
+ velocity_free_tx_buf(vptr, tdinfo, td);
vptr->tx.used[qnum]--;
}
vptr->tx.tail[qnum] = idx;
* Look to see if we should kick the transmit network
* layer for more work.
*/
- if (netif_queue_stopped(vptr->dev) && (full == 0)
- && (!(vptr->mii_status & VELOCITY_LINK_FAIL))) {
+ if (netif_queue_stopped(vptr->dev) && (full == 0) &&
+ (!(vptr->mii_status & VELOCITY_LINK_FAIL))) {
netif_wake_queue(vptr->dev);
}
return works;
* any received packets from the receive queue. Hand the ring
* slots back to the adapter for reuse.
*/
-static int velocity_rx_srv(struct velocity_info *vptr, int status)
+static int velocity_rx_srv(struct velocity_info *vptr, int status,
+ int budget_left)
{
struct net_device_stats *stats = &vptr->dev->stats;
int rd_curr = vptr->rx.curr;
int works = 0;
- do {
+ while (works < budget_left) {
struct rx_desc *rd = vptr->rx.ring + rd_curr;
if (!vptr->rx.info[rd_curr].skb)
rd_curr++;
if (rd_curr >= vptr->options.numrx)
rd_curr = 0;
- } while (++works <= 15);
+ works++;
+ }
vptr->rx.curr = rd_curr;
return works;
}
+static int velocity_poll(struct napi_struct *napi, int budget)
+{
+ struct velocity_info *vptr = container_of(napi,
+ struct velocity_info, napi);
+ unsigned int rx_done;
+ u32 isr_status;
+
+ spin_lock(&vptr->lock);
+ isr_status = mac_read_isr(vptr->mac_regs);
+
+ /* Ack the interrupt */
+ mac_write_isr(vptr->mac_regs, isr_status);
+ if (isr_status & (~(ISR_PRXI | ISR_PPRXI | ISR_PTXI | ISR_PPTXI)))
+ velocity_error(vptr, isr_status);
+
+ /*
+ * Do rx and tx twice for performance (taken from the VIA
+ * out-of-tree driver).
+ */
+ rx_done = velocity_rx_srv(vptr, isr_status, budget / 2);
+ velocity_tx_srv(vptr, isr_status);
+ rx_done += velocity_rx_srv(vptr, isr_status, budget - rx_done);
+ velocity_tx_srv(vptr, isr_status);
+
+ spin_unlock(&vptr->lock);
+
+ /* If budget not fully consumed, exit the polling mode */
+ if (rx_done < budget) {
+ napi_complete(napi);
+ mac_enable_int(vptr->mac_regs);
+ }
+
+ return rx_done;
+}
/**
* velocity_intr - interrupt callback
struct net_device *dev = dev_instance;
struct velocity_info *vptr = netdev_priv(dev);
u32 isr_status;
- int max_count = 0;
-
spin_lock(&vptr->lock);
isr_status = mac_read_isr(vptr->mac_regs);
return IRQ_NONE;
}
- mac_disable_int(vptr->mac_regs);
-
- /*
- * Keep processing the ISR until we have completed
- * processing and the isr_status becomes zero
- */
-
- while (isr_status != 0) {
- mac_write_isr(vptr->mac_regs, isr_status);
- if (isr_status & (~(ISR_PRXI | ISR_PPRXI | ISR_PTXI | ISR_PPTXI)))
- velocity_error(vptr, isr_status);
- if (isr_status & (ISR_PRXI | ISR_PPRXI))
- max_count += velocity_rx_srv(vptr, isr_status);
- if (isr_status & (ISR_PTXI | ISR_PPTXI))
- max_count += velocity_tx_srv(vptr, isr_status);
- isr_status = mac_read_isr(vptr->mac_regs);
- if (max_count > vptr->options.int_works) {
- printk(KERN_WARNING "%s: excessive work at interrupt.\n",
- dev->name);
- max_count = 0;
- }
+ if (likely(napi_schedule_prep(&vptr->napi))) {
+ mac_disable_int(vptr->mac_regs);
+ __napi_schedule(&vptr->napi);
}
spin_unlock(&vptr->lock);
- mac_enable_int(vptr->mac_regs);
- return IRQ_HANDLED;
+ return IRQ_HANDLED;
}
/**
/* Ensure chip is running */
pci_set_power_state(vptr->pdev, PCI_D0);
- velocity_give_many_rx_descs(vptr);
-
velocity_init_registers(vptr, VELOCITY_INIT_COLD);
ret = request_irq(vptr->pdev->irq, velocity_intr, IRQF_SHARED,
goto out;
}
+ velocity_give_many_rx_descs(vptr);
+
mac_enable_int(vptr->mac_regs);
netif_start_queue(dev);
+ napi_enable(&vptr->napi);
vptr->flags |= VELOCITY_FLAGS_OPENED;
out:
return ret;
dev->mtu = new_mtu;
- velocity_give_many_rx_descs(vptr);
-
velocity_init_registers(vptr, VELOCITY_INIT_COLD);
+ velocity_give_many_rx_descs(vptr);
+
mac_enable_int(vptr->mac_regs);
netif_start_queue(dev);
{
struct velocity_info *vptr = netdev_priv(dev);
+ napi_disable(&vptr->napi);
netif_stop_queue(dev);
velocity_shutdown(vptr);
struct velocity_td_info *tdinfo;
unsigned long flags;
int pktlen;
- __le16 len;
- int index;
+ int index, prev;
+ int i = 0;
if (skb_padto(skb, ETH_ZLEN))
goto out;
- pktlen = max_t(unsigned int, skb->len, ETH_ZLEN);
- len = cpu_to_le16(pktlen);
+ /* The hardware can handle at most 7 memory segments, so merge
+ * the skb if there are more */
+ if (skb_shinfo(skb)->nr_frags > 6 && __skb_linearize(skb)) {
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+
+ pktlen = skb_shinfo(skb)->nr_frags == 0 ?
+ max_t(unsigned int, skb->len, ETH_ZLEN) :
+ skb_headlen(skb);
spin_lock_irqsave(&vptr->lock, flags);
*/
tdinfo->skb = skb;
tdinfo->skb_dma[0] = pci_map_single(vptr->pdev, skb->data, pktlen, PCI_DMA_TODEVICE);
- td_ptr->tdesc0.len = len;
+ td_ptr->tdesc0.len = cpu_to_le16(pktlen);
td_ptr->td_buf[0].pa_low = cpu_to_le32(tdinfo->skb_dma[0]);
td_ptr->td_buf[0].pa_high = 0;
- td_ptr->td_buf[0].size = len;
- tdinfo->nskb_dma = 1;
+ td_ptr->td_buf[0].size = cpu_to_le16(pktlen);
+
+ /* Handle fragments */
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ tdinfo->skb_dma[i + 1] = pci_map_page(vptr->pdev, frag->page,
+ frag->page_offset, frag->size,
+ PCI_DMA_TODEVICE);
+
+ td_ptr->td_buf[i + 1].pa_low = cpu_to_le32(tdinfo->skb_dma[i + 1]);
+ td_ptr->td_buf[i + 1].pa_high = 0;
+ td_ptr->td_buf[i + 1].size = cpu_to_le16(frag->size);
+ }
+ tdinfo->nskb_dma = i + 1;
td_ptr->tdesc1.cmd = TCPLS_NORMAL + (tdinfo->nskb_dma + 1) * 16;
/*
* Handle hardware checksum
*/
- if ((vptr->flags & VELOCITY_FLAGS_TX_CSUM)
- && (skb->ip_summed == CHECKSUM_PARTIAL)) {
+ if ((dev->features & NETIF_F_IP_CSUM) &&
+ (skb->ip_summed == CHECKSUM_PARTIAL)) {
const struct iphdr *ip = ip_hdr(skb);
if (ip->protocol == IPPROTO_TCP)
td_ptr->tdesc1.TCR |= TCR0_TCPCK;
td_ptr->tdesc1.TCR |= (TCR0_UDPCK);
td_ptr->tdesc1.TCR |= TCR0_IPCK;
}
- {
- int prev = index - 1;
+ prev = index - 1;
+ if (prev < 0)
+ prev = vptr->options.numtx - 1;
+ td_ptr->tdesc0.len |= OWNED_BY_NIC;
+ vptr->tx.used[qnum]++;
+ vptr->tx.curr[qnum] = (index + 1) % vptr->options.numtx;
- if (prev < 0)
- prev = vptr->options.numtx - 1;
- td_ptr->tdesc0.len |= OWNED_BY_NIC;
- vptr->tx.used[qnum]++;
- vptr->tx.curr[qnum] = (index + 1) % vptr->options.numtx;
+ if (AVAIL_TD(vptr, qnum) < 1)
+ netif_stop_queue(dev);
- if (AVAIL_TD(vptr, qnum) < 1)
- netif_stop_queue(dev);
+ td_ptr = &(vptr->tx.rings[qnum][prev]);
+ td_ptr->td_buf[0].size |= TD_QUEUE;
+ mac_tx_queue_wake(vptr->mac_regs, qnum);
- td_ptr = &(vptr->tx.rings[qnum][prev]);
- td_ptr->td_buf[0].size |= TD_QUEUE;
- mac_tx_queue_wake(vptr->mac_regs, qnum);
- }
dev->trans_start = jiffies;
spin_unlock_irqrestore(&vptr->lock, flags);
out:
dev->irq = pdev->irq;
dev->netdev_ops = &velocity_netdev_ops;
dev->ethtool_ops = &velocity_ethtool_ops;
+ netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT);
dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER |
- NETIF_F_HW_VLAN_RX;
-
- if (vptr->flags & VELOCITY_FLAGS_TX_CSUM)
- dev->features |= NETIF_F_IP_CSUM;
+ NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM;
ret = register_netdev(dev);
if (ret < 0)
.get_settings = velocity_get_settings,
.set_settings = velocity_set_settings,
.get_drvinfo = velocity_get_drvinfo,
+ .set_tx_csum = ethtool_op_set_tx_csum,
+ .get_tx_csum = ethtool_op_get_tx_csum,
.get_wol = velocity_ethtool_get_wol,
.set_wol = velocity_ethtool_set_wol,
.get_msglevel = velocity_get_msglevel,
.set_msglevel = velocity_set_msglevel,
+ .set_sg = ethtool_op_set_sg,
.get_link = velocity_get_link,
.get_coalesce = velocity_get_coalesce,
.set_coalesce = velocity_set_coalesce,