* 0.57: 14 May 2006: Mac address set in probe/remove and order corrections.
* 0.58: 30 Oct 2006: Added support for sideband management unit.
* 0.59: 30 Oct 2006: Added support for recoverable error.
+ * 0.60: 20 Jan 2007: Code optimizations for rings, rx & tx data paths, and stats.
*
* Known bugs:
* We suspect that on some hardware no TX done interrupts are generated.
#else
#define DRIVERNAPI
#endif
-#define FORCEDETH_VERSION "0.59"
+#define FORCEDETH_VERSION "0.60"
#define DRV_NAME "forcedeth"
#include <linux/module.h>
#define DEV_HAS_MSI_X 0x0080 /* device supports MSI-X */
#define DEV_HAS_POWER_CNTRL 0x0100 /* device supports power savings */
#define DEV_HAS_PAUSEFRAME_TX 0x0200 /* device supports tx pause frames */
-#define DEV_HAS_STATISTICS 0x0400 /* device supports hw statistics */
-#define DEV_HAS_TEST_EXTENDED 0x0800 /* device supports extended diagnostic test */
-#define DEV_HAS_MGMT_UNIT 0x1000 /* device supports management unit */
+#define DEV_HAS_STATISTICS_V1 0x0400 /* device supports hw statistics version 1 */
+#define DEV_HAS_STATISTICS_V2 0x0800 /* device supports hw statistics version 2 */
+#define DEV_HAS_TEST_EXTENDED 0x1000 /* device supports extended diagnostic test */
+#define DEV_HAS_MGMT_UNIT 0x2000 /* device supports management unit */
enum {
NvRegIrqStatus = 0x000,
* NVREG_POLL_DEFAULT=97 would result in an interval length of 1 ms
*/
NvRegPollingInterval = 0x00c,
-#define NVREG_POLL_DEFAULT_THROUGHPUT 970
+#define NVREG_POLL_DEFAULT_THROUGHPUT 970 /* backup tx cleanup if loop max reached */
#define NVREG_POLL_DEFAULT_CPU 13
NvRegMSIMap0 = 0x020,
NvRegMSIMap1 = 0x024,
/* Miscelaneous hardware related defines: */
#define NV_PCI_REGSZ_VER1 0x270
-#define NV_PCI_REGSZ_VER2 0x604
+#define NV_PCI_REGSZ_VER2 0x2d4
+#define NV_PCI_REGSZ_VER3 0x604
/* various timeout delays: all in usec */
#define NV_TXRX_RESET_DELAY 4
{ "tx_carrier_errors" },
{ "tx_excess_deferral" },
{ "tx_retry_error" },
- { "tx_deferral" },
- { "tx_packets" },
- { "tx_pause" },
{ "rx_frame_error" },
{ "rx_extra_byte" },
{ "rx_late_collision" },
{ "rx_unicast" },
{ "rx_multicast" },
{ "rx_broadcast" },
+ { "rx_packets" },
+ { "rx_errors_total" },
+ { "tx_errors_total" },
+
+ /* version 2 stats */
+ { "tx_deferral" },
+ { "tx_packets" },
{ "rx_bytes" },
+ { "tx_pause" },
{ "rx_pause" },
- { "rx_drop_frame" },
- { "rx_packets" },
- { "rx_errors_total" }
+ { "rx_drop_frame" }
};
struct nv_ethtool_stats {
u64 tx_carrier_errors;
u64 tx_excess_deferral;
u64 tx_retry_error;
- u64 tx_deferral;
- u64 tx_packets;
- u64 tx_pause;
u64 rx_frame_error;
u64 rx_extra_byte;
u64 rx_late_collision;
u64 rx_unicast;
u64 rx_multicast;
u64 rx_broadcast;
+ u64 rx_packets;
+ u64 rx_errors_total;
+ u64 tx_errors_total;
+
+ /* version 2 stats */
+ u64 tx_deferral;
+ u64 tx_packets;
u64 rx_bytes;
+ u64 tx_pause;
u64 rx_pause;
u64 rx_drop_frame;
- u64 rx_packets;
- u64 rx_errors_total;
};
+#define NV_DEV_STATISTICS_V2_COUNT (sizeof(struct nv_ethtool_stats)/sizeof(u64))
+#define NV_DEV_STATISTICS_V1_COUNT (NV_DEV_STATISTICS_V2_COUNT - 6)
+
/* diagnostics */
#define NV_TEST_COUNT_BASE 3
#define NV_TEST_COUNT_EXTENDED 4
pci_push(base);
}
+static void nv_get_hw_stats(struct net_device *dev)
+{
+ struct fe_priv *np = netdev_priv(dev);
+ u8 __iomem *base = get_hwbase(dev);
+
+ np->estats.tx_bytes += readl(base + NvRegTxCnt);
+ np->estats.tx_zero_rexmt += readl(base + NvRegTxZeroReXmt);
+ np->estats.tx_one_rexmt += readl(base + NvRegTxOneReXmt);
+ np->estats.tx_many_rexmt += readl(base + NvRegTxManyReXmt);
+ np->estats.tx_late_collision += readl(base + NvRegTxLateCol);
+ np->estats.tx_fifo_errors += readl(base + NvRegTxUnderflow);
+ np->estats.tx_carrier_errors += readl(base + NvRegTxLossCarrier);
+ np->estats.tx_excess_deferral += readl(base + NvRegTxExcessDef);
+ np->estats.tx_retry_error += readl(base + NvRegTxRetryErr);
+ np->estats.rx_frame_error += readl(base + NvRegRxFrameErr);
+ np->estats.rx_extra_byte += readl(base + NvRegRxExtraByte);
+ np->estats.rx_late_collision += readl(base + NvRegRxLateCol);
+ np->estats.rx_runt += readl(base + NvRegRxRunt);
+ np->estats.rx_frame_too_long += readl(base + NvRegRxFrameTooLong);
+ np->estats.rx_over_errors += readl(base + NvRegRxOverflow);
+ np->estats.rx_crc_errors += readl(base + NvRegRxFCSErr);
+ np->estats.rx_frame_align_error += readl(base + NvRegRxFrameAlignErr);
+ np->estats.rx_length_error += readl(base + NvRegRxLenErr);
+ np->estats.rx_unicast += readl(base + NvRegRxUnicast);
+ np->estats.rx_multicast += readl(base + NvRegRxMulticast);
+ np->estats.rx_broadcast += readl(base + NvRegRxBroadcast);
+ np->estats.rx_packets =
+ np->estats.rx_unicast +
+ np->estats.rx_multicast +
+ np->estats.rx_broadcast;
+ np->estats.rx_errors_total =
+ np->estats.rx_crc_errors +
+ np->estats.rx_over_errors +
+ np->estats.rx_frame_error +
+ (np->estats.rx_frame_align_error - np->estats.rx_extra_byte) +
+ np->estats.rx_late_collision +
+ np->estats.rx_runt +
+ np->estats.rx_frame_too_long;
+ np->estats.tx_errors_total =
+ np->estats.tx_late_collision +
+ np->estats.tx_fifo_errors +
+ np->estats.tx_carrier_errors +
+ np->estats.tx_excess_deferral +
+ np->estats.tx_retry_error;
+
+ if (np->driver_data & DEV_HAS_STATISTICS_V2) {
+ np->estats.tx_deferral += readl(base + NvRegTxDef);
+ np->estats.tx_packets += readl(base + NvRegTxFrame);
+ np->estats.rx_bytes += readl(base + NvRegRxCnt);
+ np->estats.tx_pause += readl(base + NvRegTxPause);
+ np->estats.rx_pause += readl(base + NvRegRxPause);
+ np->estats.rx_drop_frame += readl(base + NvRegRxDropFrame);
+ }
+}
+
/*
* nv_get_stats: dev->get_stats function
* Get latest stats value from the nic.
{
struct fe_priv *np = netdev_priv(dev);
- /* It seems that the nic always generates interrupts and doesn't
- * accumulate errors internally. Thus the current values in np->stats
- * are already up to date.
- */
+ /* If the nic supports hw counters then retrieve latest values */
+ if (np->driver_data & (DEV_HAS_STATISTICS_V1|DEV_HAS_STATISTICS_V2)) {
+ nv_get_hw_stats(dev);
+
+ /* copy to net_device stats */
+ np->stats.tx_bytes = np->estats.tx_bytes;
+ np->stats.tx_fifo_errors = np->estats.tx_fifo_errors;
+ np->stats.tx_carrier_errors = np->estats.tx_carrier_errors;
+ np->stats.rx_crc_errors = np->estats.rx_crc_errors;
+ np->stats.rx_over_errors = np->estats.rx_over_errors;
+ np->stats.rx_errors = np->estats.rx_errors_total;
+ np->stats.tx_errors = np->estats.tx_errors_total;
+ }
return &np->stats;
}
np->put_rx.orig->buf = cpu_to_le32(np->put_rx_ctx->dma);
wmb();
np->put_rx.orig->flaglen = cpu_to_le32(np->rx_buf_sz | NV_RX_AVAIL);
- if (np->put_rx.orig++ == np->last_rx.orig)
+ if (unlikely(np->put_rx.orig++ == np->last_rx.orig))
np->put_rx.orig = np->first_rx.orig;
- if (np->put_rx_ctx++ == np->last_rx_ctx)
+ if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx))
np->put_rx_ctx = np->first_rx_ctx;
} else {
return 1;
np->put_rx.ex->buflow = cpu_to_le64(np->put_rx_ctx->dma) & 0x0FFFFFFFF;
wmb();
np->put_rx.ex->flaglen = cpu_to_le32(np->rx_buf_sz | NV_RX2_AVAIL);
- if (np->put_rx.ex++ == np->last_rx.ex)
+ if (unlikely(np->put_rx.ex++ == np->last_rx.ex))
np->put_rx.ex = np->first_rx.ex;
- if (np->put_rx_ctx++ == np->last_rx_ctx)
+ if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx))
np->put_rx_ctx = np->first_rx_ctx;
} else {
return 1;
u32 size = skb->len-skb->data_len;
u32 entries = (size >> NV_TX2_TSO_MAX_SHIFT) + ((size & (NV_TX2_TSO_MAX_SIZE-1)) ? 1 : 0);
u32 empty_slots;
- u32 tx_flags_vlan = 0;
struct ring_desc* put_tx;
struct ring_desc* start_tx;
struct ring_desc* prev_tx;
}
empty_slots = nv_get_empty_tx_slots(np);
- if (empty_slots <= entries) {
+ if (unlikely(empty_slots <= entries)) {
spin_lock_irq(&np->lock);
netif_stop_queue(dev);
np->tx_stop = 1;
np->put_tx_ctx->dma_len = bcnt;
put_tx->buf = cpu_to_le32(np->put_tx_ctx->dma);
put_tx->flaglen = cpu_to_le32((bcnt-1) | tx_flags);
+
tx_flags = np->tx_flags;
offset += bcnt;
size -= bcnt;
- if (put_tx++ == np->last_tx.orig)
+ if (unlikely(put_tx++ == np->last_tx.orig))
put_tx = np->first_tx.orig;
- if (np->put_tx_ctx++ == np->last_tx_ctx)
+ if (unlikely(np->put_tx_ctx++ == np->last_tx_ctx))
np->put_tx_ctx = np->first_tx_ctx;
} while (size);
np->put_tx_ctx->dma = pci_map_page(np->pci_dev, frag->page, frag->page_offset+offset, bcnt,
PCI_DMA_TODEVICE);
np->put_tx_ctx->dma_len = bcnt;
-
put_tx->buf = cpu_to_le32(np->put_tx_ctx->dma);
put_tx->flaglen = cpu_to_le32((bcnt-1) | tx_flags);
+
offset += bcnt;
size -= bcnt;
- if (put_tx++ == np->last_tx.orig)
+ if (unlikely(put_tx++ == np->last_tx.orig))
put_tx = np->first_tx.orig;
- if (np->put_tx_ctx++ == np->last_tx_ctx)
+ if (unlikely(np->put_tx_ctx++ == np->last_tx_ctx))
np->put_tx_ctx = np->first_tx_ctx;
} while (size);
}
tx_flags_extra = skb->ip_summed == CHECKSUM_PARTIAL ?
NV_TX2_CHECKSUM_L3 | NV_TX2_CHECKSUM_L4 : 0;
- /* vlan tag */
- if (np->vlangrp && vlan_tx_tag_present(skb)) {
- tx_flags_vlan = NV_TX3_VLAN_TAG_PRESENT | vlan_tx_tag_get(skb);
- }
-
spin_lock_irq(&np->lock);
/* set tx flags */
dev->trans_start = jiffies;
writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl);
- pci_push(get_hwbase(dev));
return NETDEV_TX_OK;
}
{
struct fe_priv *np = netdev_priv(dev);
u32 tx_flags = 0;
- u32 tx_flags_extra = NV_TX2_LASTPACKET;
+ u32 tx_flags_extra;
unsigned int fragments = skb_shinfo(skb)->nr_frags;
unsigned int i;
u32 offset = 0;
u32 size = skb->len-skb->data_len;
u32 entries = (size >> NV_TX2_TSO_MAX_SHIFT) + ((size & (NV_TX2_TSO_MAX_SIZE-1)) ? 1 : 0);
u32 empty_slots;
- u32 tx_flags_vlan = 0;
struct ring_desc_ex* put_tx;
struct ring_desc_ex* start_tx;
struct ring_desc_ex* prev_tx;
}
empty_slots = nv_get_empty_tx_slots(np);
- if (empty_slots <= entries) {
+ if (unlikely(empty_slots <= entries)) {
spin_lock_irq(&np->lock);
netif_stop_queue(dev);
np->tx_stop = 1;
put_tx->bufhigh = cpu_to_le64(np->put_tx_ctx->dma) >> 32;
put_tx->buflow = cpu_to_le64(np->put_tx_ctx->dma) & 0x0FFFFFFFF;
put_tx->flaglen = cpu_to_le32((bcnt-1) | tx_flags);
- tx_flags = np->tx_flags;
+
+ tx_flags = NV_TX2_VALID;
offset += bcnt;
size -= bcnt;
- if (put_tx++ == np->last_tx.ex)
+ if (unlikely(put_tx++ == np->last_tx.ex))
put_tx = np->first_tx.ex;
- if (np->put_tx_ctx++ == np->last_tx_ctx)
+ if (unlikely(np->put_tx_ctx++ == np->last_tx_ctx))
np->put_tx_ctx = np->first_tx_ctx;
} while (size);
np->put_tx_ctx->dma = pci_map_page(np->pci_dev, frag->page, frag->page_offset+offset, bcnt,
PCI_DMA_TODEVICE);
np->put_tx_ctx->dma_len = bcnt;
-
put_tx->bufhigh = cpu_to_le64(np->put_tx_ctx->dma) >> 32;
put_tx->buflow = cpu_to_le64(np->put_tx_ctx->dma) & 0x0FFFFFFFF;
put_tx->flaglen = cpu_to_le32((bcnt-1) | tx_flags);
+
offset += bcnt;
size -= bcnt;
- if (put_tx++ == np->last_tx.ex)
+ if (unlikely(put_tx++ == np->last_tx.ex))
put_tx = np->first_tx.ex;
- if (np->put_tx_ctx++ == np->last_tx_ctx)
+ if (unlikely(np->put_tx_ctx++ == np->last_tx_ctx))
np->put_tx_ctx = np->first_tx_ctx;
} while (size);
}
/* set last fragment flag */
- prev_tx->flaglen |= cpu_to_le32(tx_flags_extra);
+ prev_tx->flaglen |= cpu_to_le32(NV_TX2_LASTPACKET);
/* save skb in this slot's context area */
prev_tx_ctx->skb = skb;
NV_TX2_CHECKSUM_L3 | NV_TX2_CHECKSUM_L4 : 0;
/* vlan tag */
- if (np->vlangrp && vlan_tx_tag_present(skb)) {
- tx_flags_vlan = NV_TX3_VLAN_TAG_PRESENT | vlan_tx_tag_get(skb);
+ if (likely(!np->vlangrp)) {
+ start_tx->txvlan = 0;
+ } else {
+ if (vlan_tx_tag_present(skb))
+ start_tx->txvlan = cpu_to_le32(NV_TX3_VLAN_TAG_PRESENT | vlan_tx_tag_get(skb));
+ else
+ start_tx->txvlan = 0;
}
spin_lock_irq(&np->lock);
/* set tx flags */
- start_tx->txvlan = cpu_to_le32(tx_flags_vlan);
start_tx->flaglen |= cpu_to_le32(tx_flags | tx_flags_extra);
np->put_tx.ex = put_tx;
dev->trans_start = jiffies;
writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl);
- pci_push(get_hwbase(dev));
return NETDEV_TX_OK;
}
{
struct fe_priv *np = netdev_priv(dev);
u32 flags;
- struct sk_buff *skb;
struct ring_desc* orig_get_tx = np->get_tx.orig;
- while (np->get_tx.orig != np->put_tx.orig) {
- flags = le32_to_cpu(np->get_tx.orig->flaglen);
+ while ((np->get_tx.orig != np->put_tx.orig) &&
+ !((flags = le32_to_cpu(np->get_tx.orig->flaglen)) & NV_TX_VALID)) {
dprintk(KERN_DEBUG "%s: nv_tx_done: flags 0x%x.\n",
dev->name, flags);
- if (flags & NV_TX_VALID)
- break;
+
+ pci_unmap_page(np->pci_dev, np->get_tx_ctx->dma,
+ np->get_tx_ctx->dma_len,
+ PCI_DMA_TODEVICE);
+ np->get_tx_ctx->dma = 0;
+
if (np->desc_ver == DESC_VER_1) {
if (flags & NV_TX_LASTPACKET) {
- skb = np->get_tx_ctx->skb;
- if (flags & (NV_TX_RETRYERROR|NV_TX_CARRIERLOST|NV_TX_LATECOLLISION|
- NV_TX_UNDERFLOW|NV_TX_ERROR)) {
+ if (flags & NV_TX_ERROR) {
if (flags & NV_TX_UNDERFLOW)
np->stats.tx_fifo_errors++;
if (flags & NV_TX_CARRIERLOST)
np->stats.tx_errors++;
} else {
np->stats.tx_packets++;
- np->stats.tx_bytes += skb->len;
+ np->stats.tx_bytes += np->get_tx_ctx->skb->len;
}
+ dev_kfree_skb_any(np->get_tx_ctx->skb);
+ np->get_tx_ctx->skb = NULL;
}
} else {
if (flags & NV_TX2_LASTPACKET) {
- skb = np->get_tx_ctx->skb;
- if (flags & (NV_TX2_RETRYERROR|NV_TX2_CARRIERLOST|NV_TX2_LATECOLLISION|
- NV_TX2_UNDERFLOW|NV_TX2_ERROR)) {
+ if (flags & NV_TX2_ERROR) {
if (flags & NV_TX2_UNDERFLOW)
np->stats.tx_fifo_errors++;
if (flags & NV_TX2_CARRIERLOST)
np->stats.tx_errors++;
} else {
np->stats.tx_packets++;
- np->stats.tx_bytes += skb->len;
+ np->stats.tx_bytes += np->get_tx_ctx->skb->len;
}
+ dev_kfree_skb_any(np->get_tx_ctx->skb);
+ np->get_tx_ctx->skb = NULL;
}
}
- nv_release_txskb(dev, np->get_tx_ctx);
- if (np->get_tx.orig++ == np->last_tx.orig)
+ if (unlikely(np->get_tx.orig++ == np->last_tx.orig))
np->get_tx.orig = np->first_tx.orig;
- if (np->get_tx_ctx++ == np->last_tx_ctx)
+ if (unlikely(np->get_tx_ctx++ == np->last_tx_ctx))
np->get_tx_ctx = np->first_tx_ctx;
}
- if ((np->tx_stop == 1) && (np->get_tx.orig != orig_get_tx)) {
+ if (unlikely((np->tx_stop == 1) && (np->get_tx.orig != orig_get_tx))) {
np->tx_stop = 0;
netif_wake_queue(dev);
}
}
-static void nv_tx_done_optimized(struct net_device *dev)
+static void nv_tx_done_optimized(struct net_device *dev, int limit)
{
struct fe_priv *np = netdev_priv(dev);
u32 flags;
- struct sk_buff *skb;
struct ring_desc_ex* orig_get_tx = np->get_tx.ex;
- while (np->get_tx.ex == np->put_tx.ex) {
- flags = le32_to_cpu(np->get_tx.ex->flaglen);
+ while ((np->get_tx.ex != np->put_tx.ex) &&
+ !((flags = le32_to_cpu(np->get_tx.ex->flaglen)) & NV_TX_VALID) &&
+ (limit-- > 0)) {
dprintk(KERN_DEBUG "%s: nv_tx_done_optimized: flags 0x%x.\n",
dev->name, flags);
- if (flags & NV_TX_VALID)
- break;
+
+ pci_unmap_page(np->pci_dev, np->get_tx_ctx->dma,
+ np->get_tx_ctx->dma_len,
+ PCI_DMA_TODEVICE);
+ np->get_tx_ctx->dma = 0;
+
if (flags & NV_TX2_LASTPACKET) {
- skb = np->get_tx_ctx->skb;
- if (flags & (NV_TX2_RETRYERROR|NV_TX2_CARRIERLOST|NV_TX2_LATECOLLISION|
- NV_TX2_UNDERFLOW|NV_TX2_ERROR)) {
- if (flags & NV_TX2_UNDERFLOW)
- np->stats.tx_fifo_errors++;
- if (flags & NV_TX2_CARRIERLOST)
- np->stats.tx_carrier_errors++;
- np->stats.tx_errors++;
- } else {
+ if (!(flags & NV_TX2_ERROR))
np->stats.tx_packets++;
- np->stats.tx_bytes += skb->len;
- }
+ dev_kfree_skb_any(np->get_tx_ctx->skb);
+ np->get_tx_ctx->skb = NULL;
}
- nv_release_txskb(dev, np->get_tx_ctx);
- if (np->get_tx.ex++ == np->last_tx.ex)
+ if (unlikely(np->get_tx.ex++ == np->last_tx.ex))
np->get_tx.ex = np->first_tx.ex;
- if (np->get_tx_ctx++ == np->last_tx_ctx)
+ if (unlikely(np->get_tx_ctx++ == np->last_tx_ctx))
np->get_tx_ctx = np->first_tx_ctx;
}
- if ((np->tx_stop == 1) && (np->get_tx.ex != orig_get_tx)) {
+ if (unlikely((np->tx_stop == 1) && (np->get_tx.ex != orig_get_tx))) {
np->tx_stop = 0;
netif_wake_queue(dev);
}
if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
nv_tx_done(dev);
else
- nv_tx_done_optimized(dev);
+ nv_tx_done_optimized(dev, np->tx_ring_size);
/* 3) if there are dead entries: clear everything */
if (np->get_tx_ctx != np->put_tx_ctx) {
{
struct fe_priv *np = netdev_priv(dev);
u32 flags;
- u32 vlanflags = 0;
- int count;
-
- for (count = 0; count < limit; ++count) {
- struct sk_buff *skb;
- int len;
+ u32 rx_processed_cnt = 0;
+ struct sk_buff *skb;
+ int len;
- if (np->get_rx.orig == np->put_rx.orig)
- break; /* we scanned the whole ring - do not continue */
- flags = le32_to_cpu(np->get_rx.orig->flaglen);
- len = nv_descr_getlength(np->get_rx.orig, np->desc_ver);
+ while((np->get_rx.orig != np->put_rx.orig) &&
+ !((flags = le32_to_cpu(np->get_rx.orig->flaglen)) & NV_RX_AVAIL) &&
+ (rx_processed_cnt++ < limit)) {
dprintk(KERN_DEBUG "%s: nv_rx_process: flags 0x%x.\n",
dev->name, flags);
- if (flags & NV_RX_AVAIL)
- break; /* still owned by hardware, */
-
/*
* the packet is for us - immediately tear down the pci mapping.
* TODO: check if a prefetch of the first cacheline improves
}
/* look at what we actually got: */
if (np->desc_ver == DESC_VER_1) {
- if (!(flags & NV_RX_DESCRIPTORVALID)) {
- dev_kfree_skb(skb);
- goto next_pkt;
- }
-
- if (flags & NV_RX_ERROR) {
- if (flags & NV_RX_MISSEDFRAME) {
- np->stats.rx_missed_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & (NV_RX_ERROR1|NV_RX_ERROR2|NV_RX_ERROR3)) {
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX_CRCERR) {
- np->stats.rx_crc_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX_OVERFLOW) {
- np->stats.rx_over_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX_ERROR4) {
- len = nv_getlen(dev, skb->data, len);
- if (len < 0) {
+ if (likely(flags & NV_RX_DESCRIPTORVALID)) {
+ len = flags & LEN_MASK_V1;
+ if (unlikely(flags & NV_RX_ERROR)) {
+ if (flags & NV_RX_ERROR4) {
+ len = nv_getlen(dev, skb->data, len);
+ if (len < 0) {
+ np->stats.rx_errors++;
+ dev_kfree_skb(skb);
+ goto next_pkt;
+ }
+ }
+ /* framing errors are soft errors */
+ else if (flags & NV_RX_FRAMINGERR) {
+ if (flags & NV_RX_SUBSTRACT1) {
+ len--;
+ }
+ }
+ /* the rest are hard errors */
+ else {
+ if (flags & NV_RX_MISSEDFRAME)
+ np->stats.rx_missed_errors++;
+ if (flags & NV_RX_CRCERR)
+ np->stats.rx_crc_errors++;
+ if (flags & NV_RX_OVERFLOW)
+ np->stats.rx_over_errors++;
np->stats.rx_errors++;
dev_kfree_skb(skb);
goto next_pkt;
}
}
- /* framing errors are soft errors. */
- if (flags & NV_RX_FRAMINGERR) {
- if (flags & NV_RX_SUBSTRACT1) {
- len--;
- }
- }
- }
- } else {
- if (!(flags & NV_RX2_DESCRIPTORVALID)) {
+ } else {
dev_kfree_skb(skb);
goto next_pkt;
}
-
- if (flags & NV_RX2_ERROR) {
- if (flags & (NV_RX2_ERROR1|NV_RX2_ERROR2|NV_RX2_ERROR3)) {
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX2_CRCERR) {
- np->stats.rx_crc_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX2_OVERFLOW) {
- np->stats.rx_over_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX2_ERROR4) {
- len = nv_getlen(dev, skb->data, len);
- if (len < 0) {
+ } else {
+ if (likely(flags & NV_RX2_DESCRIPTORVALID)) {
+ len = flags & LEN_MASK_V2;
+ if (unlikely(flags & NV_RX2_ERROR)) {
+ if (flags & NV_RX2_ERROR4) {
+ len = nv_getlen(dev, skb->data, len);
+ if (len < 0) {
+ np->stats.rx_errors++;
+ dev_kfree_skb(skb);
+ goto next_pkt;
+ }
+ }
+ /* framing errors are soft errors */
+ else if (flags & NV_RX2_FRAMINGERR) {
+ if (flags & NV_RX2_SUBSTRACT1) {
+ len--;
+ }
+ }
+ /* the rest are hard errors */
+ else {
+ if (flags & NV_RX2_CRCERR)
+ np->stats.rx_crc_errors++;
+ if (flags & NV_RX2_OVERFLOW)
+ np->stats.rx_over_errors++;
np->stats.rx_errors++;
dev_kfree_skb(skb);
goto next_pkt;
}
}
- /* framing errors are soft errors */
- if (flags & NV_RX2_FRAMINGERR) {
- if (flags & NV_RX2_SUBSTRACT1) {
- len--;
- }
- }
- }
- if (np->rx_csum) {
- flags &= NV_RX2_CHECKSUMMASK;
- if (flags == NV_RX2_CHECKSUMOK1 ||
- flags == NV_RX2_CHECKSUMOK2 ||
- flags == NV_RX2_CHECKSUMOK3) {
- dprintk(KERN_DEBUG "%s: hw checksum hit!.\n", dev->name);
+ if ((flags & NV_RX2_CHECKSUMMASK) == NV_RX2_CHECKSUMOK2)/*ip and tcp */ {
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else {
- dprintk(KERN_DEBUG "%s: hwchecksum miss!.\n", dev->name);
+ if ((flags & NV_RX2_CHECKSUMMASK) == NV_RX2_CHECKSUMOK1 ||
+ (flags & NV_RX2_CHECKSUMMASK) == NV_RX2_CHECKSUMOK3) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ }
}
+ } else {
+ dev_kfree_skb(skb);
+ goto next_pkt;
}
}
/* got a valid packet - forward it to the network core */
dprintk(KERN_DEBUG "%s: nv_rx_process: %d bytes, proto %d accepted.\n",
dev->name, len, skb->protocol);
#ifdef CONFIG_FORCEDETH_NAPI
- if (np->vlangrp && (vlanflags & NV_RX3_VLAN_TAG_PRESENT))
- vlan_hwaccel_receive_skb(skb, np->vlangrp,
- vlanflags & NV_RX3_VLAN_TAG_MASK);
- else
- netif_receive_skb(skb);
+ netif_receive_skb(skb);
#else
- if (np->vlangrp && (vlanflags & NV_RX3_VLAN_TAG_PRESENT))
- vlan_hwaccel_rx(skb, np->vlangrp,
- vlanflags & NV_RX3_VLAN_TAG_MASK);
- else
- netif_rx(skb);
+ netif_rx(skb);
#endif
dev->last_rx = jiffies;
np->stats.rx_packets++;
np->stats.rx_bytes += len;
next_pkt:
- if (np->get_rx.orig++ == np->last_rx.orig)
+ if (unlikely(np->get_rx.orig++ == np->last_rx.orig))
np->get_rx.orig = np->first_rx.orig;
- if (np->get_rx_ctx++ == np->last_rx_ctx)
+ if (unlikely(np->get_rx_ctx++ == np->last_rx_ctx))
np->get_rx_ctx = np->first_rx_ctx;
}
- return count;
+ return rx_processed_cnt;
}
static int nv_rx_process_optimized(struct net_device *dev, int limit)
struct fe_priv *np = netdev_priv(dev);
u32 flags;
u32 vlanflags = 0;
- int count;
-
- for (count = 0; count < limit; ++count) {
- struct sk_buff *skb;
- int len;
+ u32 rx_processed_cnt = 0;
+ struct sk_buff *skb;
+ int len;
- if (np->get_rx.ex == np->put_rx.ex)
- break; /* we scanned the whole ring - do not continue */
- flags = le32_to_cpu(np->get_rx.ex->flaglen);
- len = nv_descr_getlength_ex(np->get_rx.ex, np->desc_ver);
- vlanflags = le32_to_cpu(np->get_rx.ex->buflow);
+ while((np->get_rx.ex != np->put_rx.ex) &&
+ !((flags = le32_to_cpu(np->get_rx.ex->flaglen)) & NV_RX2_AVAIL) &&
+ (rx_processed_cnt++ < limit)) {
dprintk(KERN_DEBUG "%s: nv_rx_process_optimized: flags 0x%x.\n",
dev->name, flags);
- if (flags & NV_RX_AVAIL)
- break; /* still owned by hardware, */
-
/*
* the packet is for us - immediately tear down the pci mapping.
* TODO: check if a prefetch of the first cacheline improves
dprintk("\n");
}
/* look at what we actually got: */
- if (!(flags & NV_RX2_DESCRIPTORVALID)) {
- dev_kfree_skb(skb);
- goto next_pkt;
- }
-
- if (flags & NV_RX2_ERROR) {
- if (flags & (NV_RX2_ERROR1|NV_RX2_ERROR2|NV_RX2_ERROR3)) {
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX2_CRCERR) {
- np->stats.rx_crc_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX2_OVERFLOW) {
- np->stats.rx_over_errors++;
- np->stats.rx_errors++;
- dev_kfree_skb(skb);
- goto next_pkt;
- }
- if (flags & NV_RX2_ERROR4) {
- len = nv_getlen(dev, skb->data, len);
- if (len < 0) {
- np->stats.rx_errors++;
+ if (likely(flags & NV_RX2_DESCRIPTORVALID)) {
+ len = flags & LEN_MASK_V2;
+ if (unlikely(flags & NV_RX2_ERROR)) {
+ if (flags & NV_RX2_ERROR4) {
+ len = nv_getlen(dev, skb->data, len);
+ if (len < 0) {
+ dev_kfree_skb(skb);
+ goto next_pkt;
+ }
+ }
+ /* framing errors are soft errors */
+ else if (flags & NV_RX2_FRAMINGERR) {
+ if (flags & NV_RX2_SUBSTRACT1) {
+ len--;
+ }
+ }
+ /* the rest are hard errors */
+ else {
dev_kfree_skb(skb);
goto next_pkt;
}
}
- /* framing errors are soft errors */
- if (flags & NV_RX2_FRAMINGERR) {
- if (flags & NV_RX2_SUBSTRACT1) {
- len--;
- }
- }
- }
- if (np->rx_csum) {
- flags &= NV_RX2_CHECKSUMMASK;
- if (flags == NV_RX2_CHECKSUMOK1 ||
- flags == NV_RX2_CHECKSUMOK2 ||
- flags == NV_RX2_CHECKSUMOK3) {
- dprintk(KERN_DEBUG "%s: hw checksum hit!.\n", dev->name);
+
+ if ((flags & NV_RX2_CHECKSUMMASK) == NV_RX2_CHECKSUMOK2)/*ip and tcp */ {
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else {
- dprintk(KERN_DEBUG "%s: hwchecksum miss!.\n", dev->name);
+ if ((flags & NV_RX2_CHECKSUMMASK) == NV_RX2_CHECKSUMOK1 ||
+ (flags & NV_RX2_CHECKSUMMASK) == NV_RX2_CHECKSUMOK3) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ }
}
- }
- /* got a valid packet - forward it to the network core */
- skb_put(skb, len);
- skb->protocol = eth_type_trans(skb, dev);
- dprintk(KERN_DEBUG "%s: nv_rx_process: %d bytes, proto %d accepted.\n",
- dev->name, len, skb->protocol);
+
+ /* got a valid packet - forward it to the network core */
+ skb_put(skb, len);
+ skb->protocol = eth_type_trans(skb, dev);
+ prefetch(skb->data);
+
+ dprintk(KERN_DEBUG "%s: nv_rx_process_optimized: %d bytes, proto %d accepted.\n",
+ dev->name, len, skb->protocol);
+
+ if (likely(!np->vlangrp)) {
#ifdef CONFIG_FORCEDETH_NAPI
- if (np->vlangrp && (vlanflags & NV_RX3_VLAN_TAG_PRESENT))
- vlan_hwaccel_receive_skb(skb, np->vlangrp,
- vlanflags & NV_RX3_VLAN_TAG_MASK);
- else
- netif_receive_skb(skb);
+ netif_receive_skb(skb);
#else
- if (np->vlangrp && (vlanflags & NV_RX3_VLAN_TAG_PRESENT))
- vlan_hwaccel_rx(skb, np->vlangrp,
- vlanflags & NV_RX3_VLAN_TAG_MASK);
- else
- netif_rx(skb);
+ netif_rx(skb);
#endif
- dev->last_rx = jiffies;
- np->stats.rx_packets++;
- np->stats.rx_bytes += len;
+ } else {
+ vlanflags = le32_to_cpu(np->get_rx.ex->buflow);
+ if (vlanflags & NV_RX3_VLAN_TAG_PRESENT) {
+#ifdef CONFIG_FORCEDETH_NAPI
+ vlan_hwaccel_receive_skb(skb, np->vlangrp,
+ vlanflags & NV_RX3_VLAN_TAG_MASK);
+#else
+ vlan_hwaccel_rx(skb, np->vlangrp,
+ vlanflags & NV_RX3_VLAN_TAG_MASK);
+#endif
+ } else {
+#ifdef CONFIG_FORCEDETH_NAPI
+ netif_receive_skb(skb);
+#else
+ netif_rx(skb);
+#endif
+ }
+ }
+
+ dev->last_rx = jiffies;
+ np->stats.rx_packets++;
+ np->stats.rx_bytes += len;
+ } else {
+ dev_kfree_skb(skb);
+ }
next_pkt:
- if (np->get_rx.ex++ == np->last_rx.ex)
+ if (unlikely(np->get_rx.ex++ == np->last_rx.ex))
np->get_rx.ex = np->first_rx.ex;
- if (np->get_rx_ctx++ == np->last_rx_ctx)
+ if (unlikely(np->get_rx_ctx++ == np->last_rx_ctx))
np->get_rx_ctx = np->first_rx_ctx;
}
- return count;
+ return rx_processed_cnt;
}
static void set_bufsize(struct net_device *dev)
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
writel(NVREG_IRQSTAT_MASK, base + NvRegMSIXIrqStatus);
}
- pci_push(base);
dprintk(KERN_DEBUG "%s: irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
nv_tx_done(dev);
spin_unlock(&np->lock);
- if (events & NVREG_IRQ_LINK) {
+#ifdef CONFIG_FORCEDETH_NAPI
+ if (events & NVREG_IRQ_RX_ALL) {
+ netif_rx_schedule(dev);
+
+ /* Disable furthur receive irq's */
+ spin_lock(&np->lock);
+ np->irqmask &= ~NVREG_IRQ_RX_ALL;
+
+ if (np->msi_flags & NV_MSI_X_ENABLED)
+ writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
+ else
+ writel(np->irqmask, base + NvRegIrqMask);
+ spin_unlock(&np->lock);
+ }
+#else
+ if (nv_rx_process(dev, dev->weight)) {
+ if (unlikely(nv_alloc_rx(dev))) {
+ spin_lock(&np->lock);
+ if (!np->in_shutdown)
+ mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
+ spin_unlock(&np->lock);
+ }
+ }
+#endif
+ if (unlikely(events & NVREG_IRQ_LINK)) {
spin_lock(&np->lock);
nv_link_irq(dev);
spin_unlock(&np->lock);
}
- if (np->need_linktimer && time_after(jiffies, np->link_timeout)) {
+ if (unlikely(np->need_linktimer && time_after(jiffies, np->link_timeout))) {
spin_lock(&np->lock);
nv_linkchange(dev);
spin_unlock(&np->lock);
np->link_timeout = jiffies + LINK_TIMEOUT;
}
- if (events & (NVREG_IRQ_TX_ERR)) {
+ if (unlikely(events & (NVREG_IRQ_TX_ERR))) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
- if (events & (NVREG_IRQ_UNKNOWN)) {
+ if (unlikely(events & (NVREG_IRQ_UNKNOWN))) {
printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n",
dev->name, events);
}
spin_unlock(&np->lock);
break;
}
-#ifdef CONFIG_FORCEDETH_NAPI
- if (events & NVREG_IRQ_RX_ALL) {
- netif_rx_schedule(dev);
-
- /* Disable furthur receive irq's */
- spin_lock(&np->lock);
- np->irqmask &= ~NVREG_IRQ_RX_ALL;
-
- if (np->msi_flags & NV_MSI_X_ENABLED)
- writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
- else
- writel(np->irqmask, base + NvRegIrqMask);
- spin_unlock(&np->lock);
- }
-#else
- nv_rx_process(dev, dev->weight);
- if (nv_alloc_rx(dev)) {
- spin_lock(&np->lock);
- if (!np->in_shutdown)
- mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock(&np->lock);
- }
-#endif
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock(&np->lock);
/* disable interrupts on the nic */
if (!(np->msi_flags & NV_MSI_X_ENABLED))
return IRQ_RETVAL(i);
}
+#define TX_WORK_PER_LOOP 64
+#define RX_WORK_PER_LOOP 64
+/**
+ * All _optimized functions are used to help increase performance
+ * (reduce CPU and increase throughput). They use descripter version 3,
+ * compiler directives, and reduce memory accesses.
+ */
static irqreturn_t nv_nic_irq_optimized(int foo, void *data)
{
struct net_device *dev = (struct net_device *) data;
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
writel(NVREG_IRQSTAT_MASK, base + NvRegMSIXIrqStatus);
}
- pci_push(base);
dprintk(KERN_DEBUG "%s: irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
spin_lock(&np->lock);
- nv_tx_done_optimized(dev);
+ nv_tx_done_optimized(dev, TX_WORK_PER_LOOP);
spin_unlock(&np->lock);
- if (events & NVREG_IRQ_LINK) {
+#ifdef CONFIG_FORCEDETH_NAPI
+ if (events & NVREG_IRQ_RX_ALL) {
+ netif_rx_schedule(dev);
+
+ /* Disable furthur receive irq's */
+ spin_lock(&np->lock);
+ np->irqmask &= ~NVREG_IRQ_RX_ALL;
+
+ if (np->msi_flags & NV_MSI_X_ENABLED)
+ writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
+ else
+ writel(np->irqmask, base + NvRegIrqMask);
+ spin_unlock(&np->lock);
+ }
+#else
+ if (nv_rx_process_optimized(dev, dev->weight)) {
+ if (unlikely(nv_alloc_rx_optimized(dev))) {
+ spin_lock(&np->lock);
+ if (!np->in_shutdown)
+ mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
+ spin_unlock(&np->lock);
+ }
+ }
+#endif
+ if (unlikely(events & NVREG_IRQ_LINK)) {
spin_lock(&np->lock);
nv_link_irq(dev);
spin_unlock(&np->lock);
}
- if (np->need_linktimer && time_after(jiffies, np->link_timeout)) {
+ if (unlikely(np->need_linktimer && time_after(jiffies, np->link_timeout))) {
spin_lock(&np->lock);
nv_linkchange(dev);
spin_unlock(&np->lock);
np->link_timeout = jiffies + LINK_TIMEOUT;
}
- if (events & (NVREG_IRQ_TX_ERR)) {
+ if (unlikely(events & (NVREG_IRQ_TX_ERR))) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
- if (events & (NVREG_IRQ_UNKNOWN)) {
+ if (unlikely(events & (NVREG_IRQ_UNKNOWN))) {
printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n",
dev->name, events);
}
break;
}
-#ifdef CONFIG_FORCEDETH_NAPI
- if (events & NVREG_IRQ_RX_ALL) {
- netif_rx_schedule(dev);
-
- /* Disable furthur receive irq's */
- spin_lock(&np->lock);
- np->irqmask &= ~NVREG_IRQ_RX_ALL;
-
- if (np->msi_flags & NV_MSI_X_ENABLED)
- writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
- else
- writel(np->irqmask, base + NvRegIrqMask);
- spin_unlock(&np->lock);
- }
-#else
- nv_rx_process_optimized(dev, dev->weight);
- if (nv_alloc_rx_optimized(dev)) {
- spin_lock(&np->lock);
- if (!np->in_shutdown)
- mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock(&np->lock);
- }
-#endif
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock(&np->lock);
/* disable interrupts on the nic */
if (!(np->msi_flags & NV_MSI_X_ENABLED))
for (i=0; ; i++) {
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQ_TX_ALL;
writel(NVREG_IRQ_TX_ALL, base + NvRegMSIXIrqStatus);
- pci_push(base);
dprintk(KERN_DEBUG "%s: tx irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
spin_lock_irqsave(&np->lock, flags);
- nv_tx_done_optimized(dev);
+ nv_tx_done_optimized(dev, TX_WORK_PER_LOOP);
spin_unlock_irqrestore(&np->lock, flags);
- if (events & (NVREG_IRQ_TX_ERR)) {
+ if (unlikely(events & (NVREG_IRQ_TX_ERR))) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_TX_ALL, base + NvRegIrqMask);
for (i=0; ; i++) {
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQ_RX_ALL;
writel(NVREG_IRQ_RX_ALL, base + NvRegMSIXIrqStatus);
- pci_push(base);
dprintk(KERN_DEBUG "%s: rx irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
- nv_rx_process_optimized(dev, dev->weight);
- if (nv_alloc_rx_optimized(dev)) {
- spin_lock_irqsave(&np->lock, flags);
- if (!np->in_shutdown)
- mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock_irqrestore(&np->lock, flags);
+ if (nv_rx_process_optimized(dev, dev->weight)) {
+ if (unlikely(nv_alloc_rx_optimized(dev))) {
+ spin_lock_irqsave(&np->lock, flags);
+ if (!np->in_shutdown)
+ mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
+ spin_unlock_irqrestore(&np->lock, flags);
+ }
}
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
for (i=0; ; i++) {
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQ_OTHER;
writel(NVREG_IRQ_OTHER, base + NvRegMSIXIrqStatus);
- pci_push(base);
dprintk(KERN_DEBUG "%s: irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
+ /* check tx in case we reached max loop limit in tx isr */
+ spin_lock_irqsave(&np->lock, flags);
+ nv_tx_done_optimized(dev, TX_WORK_PER_LOOP);
+ spin_unlock_irqrestore(&np->lock, flags);
+
if (events & NVREG_IRQ_LINK) {
spin_lock_irqsave(&np->lock, flags);
nv_link_irq(dev);
printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n",
dev->name, events);
}
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_OTHER, base + NvRegIrqMask);
{
struct net_device *dev = (struct net_device *) data;
struct fe_priv *np = netdev_priv(dev);
- u8 __iomem *base = get_hwbase(dev);
- np->estats.tx_bytes += readl(base + NvRegTxCnt);
- np->estats.tx_zero_rexmt += readl(base + NvRegTxZeroReXmt);
- np->estats.tx_one_rexmt += readl(base + NvRegTxOneReXmt);
- np->estats.tx_many_rexmt += readl(base + NvRegTxManyReXmt);
- np->estats.tx_late_collision += readl(base + NvRegTxLateCol);
- np->estats.tx_fifo_errors += readl(base + NvRegTxUnderflow);
- np->estats.tx_carrier_errors += readl(base + NvRegTxLossCarrier);
- np->estats.tx_excess_deferral += readl(base + NvRegTxExcessDef);
- np->estats.tx_retry_error += readl(base + NvRegTxRetryErr);
- np->estats.tx_deferral += readl(base + NvRegTxDef);
- np->estats.tx_packets += readl(base + NvRegTxFrame);
- np->estats.tx_pause += readl(base + NvRegTxPause);
- np->estats.rx_frame_error += readl(base + NvRegRxFrameErr);
- np->estats.rx_extra_byte += readl(base + NvRegRxExtraByte);
- np->estats.rx_late_collision += readl(base + NvRegRxLateCol);
- np->estats.rx_runt += readl(base + NvRegRxRunt);
- np->estats.rx_frame_too_long += readl(base + NvRegRxFrameTooLong);
- np->estats.rx_over_errors += readl(base + NvRegRxOverflow);
- np->estats.rx_crc_errors += readl(base + NvRegRxFCSErr);
- np->estats.rx_frame_align_error += readl(base + NvRegRxFrameAlignErr);
- np->estats.rx_length_error += readl(base + NvRegRxLenErr);
- np->estats.rx_unicast += readl(base + NvRegRxUnicast);
- np->estats.rx_multicast += readl(base + NvRegRxMulticast);
- np->estats.rx_broadcast += readl(base + NvRegRxBroadcast);
- np->estats.rx_bytes += readl(base + NvRegRxCnt);
- np->estats.rx_pause += readl(base + NvRegRxPause);
- np->estats.rx_drop_frame += readl(base + NvRegRxDropFrame);
- np->estats.rx_packets =
- np->estats.rx_unicast +
- np->estats.rx_multicast +
- np->estats.rx_broadcast;
- np->estats.rx_errors_total =
- np->estats.rx_crc_errors +
- np->estats.rx_over_errors +
- np->estats.rx_frame_error +
- (np->estats.rx_frame_align_error - np->estats.rx_extra_byte) +
- np->estats.rx_late_collision +
- np->estats.rx_runt +
- np->estats.rx_frame_too_long;
+ nv_get_hw_stats(dev);
if (!np->in_shutdown)
mod_timer(&np->stats_poll, jiffies + STATS_INTERVAL);
{
struct fe_priv *np = netdev_priv(dev);
- if (np->driver_data & DEV_HAS_STATISTICS)
- return sizeof(struct nv_ethtool_stats)/sizeof(u64);
+ if (np->driver_data & DEV_HAS_STATISTICS_V1)
+ return NV_DEV_STATISTICS_V1_COUNT;
+ else if (np->driver_data & DEV_HAS_STATISTICS_V2)
+ return NV_DEV_STATISTICS_V2_COUNT;
else
return 0;
}
mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
/* start statistics timer */
- if (np->driver_data & DEV_HAS_STATISTICS)
+ if (np->driver_data & (DEV_HAS_STATISTICS_V1|DEV_HAS_STATISTICS_V2))
mod_timer(&np->stats_poll, jiffies + STATS_INTERVAL);
spin_unlock_irq(&np->lock);
if (err < 0)
goto out_disable;
- if (id->driver_data & (DEV_HAS_VLAN|DEV_HAS_MSI_X|DEV_HAS_POWER_CNTRL|DEV_HAS_STATISTICS))
+ if (id->driver_data & (DEV_HAS_VLAN|DEV_HAS_MSI_X|DEV_HAS_POWER_CNTRL|DEV_HAS_STATISTICS_V2))
+ np->register_size = NV_PCI_REGSZ_VER3;
+ else if (id->driver_data & DEV_HAS_STATISTICS_V1)
np->register_size = NV_PCI_REGSZ_VER2;
else
np->register_size = NV_PCI_REGSZ_VER1;
np->txrxctl_bits |= NVREG_TXRXCTL_RXCHECK;
dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG;
dev->features |= NETIF_F_TSO;
- }
+ }
np->vlanctl_bits = 0;
if (id->driver_data & DEV_HAS_VLAN) {
#ifdef CONFIG_NET_POLL_CONTROLLER
dev->poll_controller = nv_poll_controller;
#endif
- dev->weight = 64;
+ dev->weight = RX_WORK_PER_LOOP;
#ifdef CONFIG_FORCEDETH_NAPI
dev->poll = nv_napi_poll;
#endif
},
{ /* CK804 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_8),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_STATISTICS_V1,
},
{ /* CK804 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_9),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_STATISTICS_V1,
},
{ /* MCP04 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_10),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_STATISTICS_V1,
},
{ /* MCP04 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_11),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_STATISTICS_V1,
},
{ /* MCP51 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_12),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_STATISTICS_V1,
},
{ /* MCP51 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_13),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_STATISTICS_V1,
},
{ /* MCP55 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_14),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_VLAN|DEV_HAS_MSI|DEV_HAS_MSI_X|DEV_HAS_POWER_CNTRL|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_VLAN|DEV_HAS_MSI|DEV_HAS_MSI_X|DEV_HAS_POWER_CNTRL|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP55 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_15),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_VLAN|DEV_HAS_MSI|DEV_HAS_MSI_X|DEV_HAS_POWER_CNTRL|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_VLAN|DEV_HAS_MSI|DEV_HAS_MSI_X|DEV_HAS_POWER_CNTRL|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP61 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_16),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP61 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_17),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP61 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_18),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP61 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_19),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP65 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_20),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP65 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_21),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP65 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_22),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP65 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_23),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP67 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_24),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP67 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_25),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP67 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_26),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{ /* MCP67 Ethernet Controller */
PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_27),
- .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+ .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
},
{0,},
};