From mboxrd@z Thu Jan 1 00:00:00 1970 From: Greg Banks Subject: [PATCH] make tg3 NAPI support configurable Date: Fri, 19 Dec 2003 23:48:39 +1100 Sender: netdev-bounce@oss.sgi.com Message-ID: <3FE2F3A7.2A109F28@melbourne.sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: Linux Network Development list Return-path: To: "David S. Miller" , Jeff Garzik Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org G'day, I've been having some issues with irq rates and cpu usage in the tg3 driver. In short, on Altix machines they're far too high. It turned out that reverting the driver to its pre-NAPI interrupt coalescing scheme made the situation a lot better. How much better? Running 8192 byte UDP packets across gige with NAPI takes 99.5% of a CPU to service 29,100 irqs per second. With the pre-NAPI code the figures are 36.0% CPU and 4880 irq/sec. Similar improvements are seen for non-fragmented UDP and for TCP. So, this patch against 2.6.0-test11 makes NAPI support in the tg3 driver selectable with a config option. The default value is to enable NAPI, on the assumption that NAPI must be working for most people. The non-NAPI case is the code from before NAPI was added, with tweaks for locking and ethtool_ops. The patch also applies against 2.6.0 with a few offsets. =========================================================================== linux/drivers/net/Kconfig =========================================================================== --- /usr/tmp/TmpDir.7858-0/linux/drivers/net/Kconfig_1.22 Thu Dec 18 11:45:52 2003 +++ linux/drivers/net/Kconfig Thu Dec 18 11:45:11 2003 @@ -2017,6 +2017,14 @@ To compile this driver as a module, choose M here: the module will be called tg3. This is recommended. +config TIGON3_NAPI + bool "Use Rx Polling (NAPI)" + default y + depends on TIGON3 + help + NAPI is a new driver API designed to reduce CPU and interrupt load + when the driver is receiving lots of packets from the card. + endmenu # =========================================================================== linux/drivers/net/tg3.c =========================================================================== --- /usr/tmp/TmpDir.26498-0/linux/drivers/net/tg3.c_1.20 Tue Nov 11 12:38:57 2003 +++ linux/drivers/net/tg3.c Tue Nov 11 12:03:11 2003 @@ -2306,7 +2306,13 @@ desc->err_vlan & RXD_VLAN_MASK); } else #endif + { +#ifdef CONFIG_TIGON3_NAPI netif_receive_skb(skb); +#else /* !CONFIG_TIGON3_NAPI */ + netif_rx(skb); +#endif /* !CONFIG_TIGON3_NAPI */ + } tp->dev->last_rx = jiffies; received++; @@ -2345,6 +2351,146 @@ return received; } +#ifndef CONFIG_TIGON3_NAPI + +#define PKT_RATE_LOW 22000 +#define PKT_RATE_HIGH 61000 + +static void tg3_rate_sample(struct tg3 *tp, unsigned long ticks) +{ + u32 delta, rx_now, tx_now; + int new_vals, do_tx, do_rx; + + rx_now = tp->hw_stats->rx_ucast_packets.low; + tx_now = tp->hw_stats->COS_out_packets[0].low; + + delta = (rx_now - tp->last_rx_count); + delta += (tx_now - tp->last_tx_count); + delta /= (ticks / tp->coalesce_config.rate_sample_jiffies); + + tp->last_rx_count = rx_now; + tp->last_tx_count = tx_now; + + new_vals = 0; + do_tx = (tp->tg3_flags2 & TG3_FLG2_ADAPTIVE_TX) != 0; + do_rx = (tp->tg3_flags2 & TG3_FLG2_ADAPTIVE_RX) != 0; + if (delta < tp->coalesce_config.pkt_rate_low) { + if (do_rx && + tp->coalesce_config.rx_max_coalesced_frames != + tp->coalesce_config.rx_max_coalesced_frames_low) { + tp->coalesce_config.rx_max_coalesced_frames = + LOW_RXMAX_FRAMES; + tp->coalesce_config.rx_coalesce_ticks = + LOW_RXCOL_TICKS; + new_vals = 1; + } + if (do_tx && + tp->coalesce_config.tx_max_coalesced_frames != + tp->coalesce_config.tx_max_coalesced_frames_low) { + tp->coalesce_config.tx_max_coalesced_frames = + tp->coalesce_config.tx_max_coalesced_frames_low; + tp->coalesce_config.tx_coalesce_ticks = + tp->coalesce_config.tx_coalesce_ticks_low; + new_vals = 1; + } + } else if (delta < tp->coalesce_config.pkt_rate_high) { + if (do_rx && + tp->coalesce_config.rx_max_coalesced_frames != + tp->coalesce_config.rx_max_coalesced_frames_def) { + tp->coalesce_config.rx_max_coalesced_frames = + tp->coalesce_config.rx_max_coalesced_frames_def; + tp->coalesce_config.rx_coalesce_ticks = + tp->coalesce_config.rx_coalesce_ticks_def; + new_vals = 1; + } + if (do_tx && + tp->coalesce_config.tx_max_coalesced_frames != + tp->coalesce_config.tx_max_coalesced_frames_def) { + tp->coalesce_config.tx_max_coalesced_frames = + tp->coalesce_config.tx_max_coalesced_frames_def; + tp->coalesce_config.tx_coalesce_ticks = + tp->coalesce_config.tx_coalesce_ticks_def; + new_vals = 1; + } + } else { + if (do_rx && + tp->coalesce_config.rx_max_coalesced_frames != + tp->coalesce_config.rx_max_coalesced_frames_high) { + tp->coalesce_config.rx_max_coalesced_frames = + tp->coalesce_config.rx_max_coalesced_frames_high; + tp->coalesce_config.rx_coalesce_ticks = + tp->coalesce_config.rx_coalesce_ticks_high; + new_vals = 1; + } + if (do_tx && + tp->coalesce_config.tx_max_coalesced_frames != + tp->coalesce_config.tx_max_coalesced_frames_high) { + tp->coalesce_config.tx_max_coalesced_frames = + tp->coalesce_config.tx_max_coalesced_frames_high; + tp->coalesce_config.tx_coalesce_ticks = + tp->coalesce_config.tx_coalesce_ticks_high; + new_vals = 1; + } + } + + if (new_vals) { + if (do_rx) { + tw32(HOSTCC_RXCOL_TICKS, + tp->coalesce_config.rx_coalesce_ticks); + tw32(HOSTCC_RXMAX_FRAMES, + tp->coalesce_config.rx_max_coalesced_frames); + } + if (do_tx) { + tw32(HOSTCC_TXCOL_TICKS, + tp->coalesce_config.tx_coalesce_ticks); + tw32(HOSTCC_TXMAX_FRAMES, + tp->coalesce_config.tx_max_coalesced_frames); + } + } + + tp->last_rate_sample = jiffies; +} + +static void tg3_interrupt_main_work(struct tg3 *tp) +{ + struct tg3_hw_status *sblk = tp->hw_status; + int did_pkts; + + if (!(tp->tg3_flags & + (TG3_FLAG_USE_LINKCHG_REG | + TG3_FLAG_POLL_SERDES))) { + if (sblk->status & SD_STATUS_LINK_CHG) { + sblk->status = SD_STATUS_UPDATED | + (sblk->status & ~SD_STATUS_LINK_CHG); + tg3_setup_phy(tp); + } + } + + /* gnbTODO: check locking here */ + + did_pkts = 0; + if (sblk->idx[0].rx_producer != tp->rx_rcb_ptr) { + tg3_rx(tp, 1024); + did_pkts = 1; + } + + if (sblk->idx[0].tx_consumer != tp->tx_cons) { + spin_lock(&tp->tx_lock); + tg3_tx(tp); + spin_unlock(&tp->tx_lock); + } + + if (did_pkts && + (tp->tg3_flags2 & (TG3_FLG2_ADAPTIVE_RX | TG3_FLG2_ADAPTIVE_TX))) { + unsigned long ticks = jiffies - tp->last_rate_sample; + + if (ticks >= tp->coalesce_config.rate_sample_jiffies) + tg3_rate_sample(tp, ticks); + } +} + +#else /* CONFIG_TIGON3_NAPI */ + static int tg3_poll(struct net_device *netdev, int *budget) { struct tg3 *tp = netdev->priv; @@ -2406,6 +2552,8 @@ return (done ? 0 : 1); } +#endif /* CONFIG_TIGON3_NAPI */ + static inline unsigned int tg3_has_work(struct net_device *dev, struct tg3 *tp) { struct tg3_hw_status *sblk = tp->hw_status; @@ -2432,10 +2580,12 @@ struct tg3 *tp = dev->priv; struct tg3_hw_status *sblk = tp->hw_status; unsigned long flags; - unsigned int handled = 1; + unsigned int handled; spin_lock_irqsave(&tp->lock, flags); +#ifdef CONFIG_TIGON3_NAPI + handled = 1; if (sblk->status & SD_STATUS_UPDATED) { /* * writing any value to intr-mbox-0 clears PCI INTA# and @@ -2466,6 +2616,21 @@ } else { /* shared interrupt */ handled = 0; } +#else + handled = 0; + while (sblk->status & SD_STATUS_UPDATED) { + handled = 1; + tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW, + 0x00000001); + sblk->status &= ~SD_STATUS_UPDATED; + + tg3_interrupt_main_work(tp); + + tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW, + 0x00000000); + tr32(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW); + } +#endif spin_unlock_irqrestore(&tp->lock, flags); @@ -4894,6 +5059,7 @@ udelay(10); } +#ifdef CONFIG_TIGON3_NAPI tw32(HOSTCC_RXCOL_TICKS, 0); tw32(HOSTCC_TXCOL_TICKS, LOW_TXCOL_TICKS); tw32(HOSTCC_RXMAX_FRAMES, 1); @@ -4904,6 +5070,28 @@ tw32(HOSTCC_TXCOAL_TICK_INT, 0); tw32(HOSTCC_RXCOAL_MAXF_INT, 1); tw32(HOSTCC_TXCOAL_MAXF_INT, 0); +#else /* !CONFIG_TIGON3_NAPI */ + tw32(HOSTCC_RXCOL_TICKS, + tp->coalesce_config.rx_coalesce_ticks); + tw32(HOSTCC_RXMAX_FRAMES, + tp->coalesce_config.rx_max_coalesced_frames); + if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5705) + tw32(HOSTCC_RXCOAL_TICK_INT, + tp->coalesce_config.rx_coalesce_ticks_during_int); + tw32(HOSTCC_RXCOAL_MAXF_INT, + tp->coalesce_config.rx_max_coalesced_frames_during_int); + tw32(HOSTCC_TXCOL_TICKS, + tp->coalesce_config.tx_coalesce_ticks); + tw32(HOSTCC_TXMAX_FRAMES, + tp->coalesce_config.tx_max_coalesced_frames); + if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5705) + tw32(HOSTCC_TXCOAL_TICK_INT, + tp->coalesce_config.tx_coalesce_ticks_during_int); + tw32(HOSTCC_TXCOAL_MAXF_INT, + tp->coalesce_config.tx_max_coalesced_frames_during_int); + tw32(HOSTCC_STAT_COAL_TICKS, + tp->coalesce_config.stats_coalesce_ticks); +#endif /* !CONFIG_TIGON3_NAPI */ /* set status block DMA address */ tw32(HOSTCC_STATUS_BLK_HOST_ADDR + TG3_64BIT_REG_HIGH, @@ -5922,8 +6110,13 @@ cmd->phy_address = PHY_ADDR; cmd->transceiver = 0; cmd->autoneg = tp->link_config.autoneg; +#ifdef CONFIG_TIGON3_NAPI cmd->maxtxpkt = 0; cmd->maxrxpkt = 0; +#else + cmd->maxtxpkt = tp->coalesce_config.tx_max_coalesced_frames_def; + cmd->maxrxpkt = tp->coalesce_config.rx_max_coalesced_frames_def; +#endif return 0; } @@ -5944,6 +6137,25 @@ tp->link_config.duplex = cmd->duplex; } +#ifndef CONFIG_TIGON3_NAPI + if (cmd->maxtxpkt || cmd->maxrxpkt) { + tp->coalesce_config.tx_max_coalesced_frames_def = + tp->coalesce_config.tx_max_coalesced_frames = + cmd->maxtxpkt; + tp->coalesce_config.rx_max_coalesced_frames_def = + tp->coalesce_config.rx_max_coalesced_frames = + cmd->maxrxpkt; + + /* Coalescing config bits can be updated without + * a full chip reset. + */ + tw32(HOSTCC_TXMAX_FRAMES, + tp->coalesce_config.tx_max_coalesced_frames); + tw32(HOSTCC_RXMAX_FRAMES, + tp->coalesce_config.rx_max_coalesced_frames); + } +#endif /* !CONFIG_TIGON3_NAPI */ + tg3_setup_phy(tp); spin_unlock(&tp->tx_lock); spin_unlock_irq(&tp->lock); @@ -6036,7 +6248,186 @@ return r; } - + +#ifndef CONFIG_TIGON3_NAPI +static int tg3_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ecoal) +{ + struct tg3 *tp = dev->priv; + + ecoal->rx_coalesce_usecs = + tp->coalesce_config.rx_coalesce_ticks_def; + ecoal->rx_max_coalesced_frames = + tp->coalesce_config.rx_max_coalesced_frames_def; + ecoal->rx_coalesce_usecs_irq = + tp->coalesce_config.rx_coalesce_ticks_during_int_def; + ecoal->rx_max_coalesced_frames_irq = + tp->coalesce_config.rx_max_coalesced_frames_during_int_def; + + ecoal->tx_coalesce_usecs = + tp->coalesce_config.tx_coalesce_ticks_def; + ecoal->tx_max_coalesced_frames = + tp->coalesce_config.tx_max_coalesced_frames_def; + ecoal->tx_coalesce_usecs_irq = + tp->coalesce_config.tx_coalesce_ticks_during_int_def; + ecoal->tx_max_coalesced_frames_irq = + tp->coalesce_config.tx_max_coalesced_frames_during_int_def; + + ecoal->stats_block_coalesce_usecs = + tp->coalesce_config.stats_coalesce_ticks_def; + + ecoal->use_adaptive_rx_coalesce = + (tp->tg3_flags2 & TG3_FLG2_ADAPTIVE_RX) != 0; + ecoal->use_adaptive_tx_coalesce = + (tp->tg3_flags2 & TG3_FLG2_ADAPTIVE_TX) != 0; + + ecoal->pkt_rate_low = + tp->coalesce_config.pkt_rate_low; + ecoal->rx_coalesce_usecs_low = + tp->coalesce_config.rx_coalesce_ticks_low; + ecoal->rx_max_coalesced_frames_low = + tp->coalesce_config.rx_max_coalesced_frames_low; + ecoal->tx_coalesce_usecs_low = + tp->coalesce_config.tx_coalesce_ticks_low; + ecoal->tx_max_coalesced_frames_low = + tp->coalesce_config.tx_max_coalesced_frames_low; + + ecoal->pkt_rate_high = + tp->coalesce_config.pkt_rate_high; + ecoal->rx_coalesce_usecs_high = + tp->coalesce_config.rx_coalesce_ticks_high; + ecoal->rx_max_coalesced_frames_high = + tp->coalesce_config.rx_max_coalesced_frames_high; + ecoal->tx_coalesce_usecs_high = + tp->coalesce_config.tx_coalesce_ticks_high; + ecoal->tx_max_coalesced_frames_high = + tp->coalesce_config.tx_max_coalesced_frames_high; + + ecoal->rate_sample_interval = + tp->coalesce_config.rate_sample_jiffies / HZ; + + return 0; +} + +static int tg3_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ecoal) +{ + struct tg3 *tp = dev->priv; + + /* Make sure we are not getting garbage. */ + if ((ecoal->rx_coalesce_usecs == 0 && + ecoal->rx_max_coalesced_frames == 0) || + (ecoal->tx_coalesce_usecs == 0 && + ecoal->tx_max_coalesced_frames == 0) || + ecoal->stats_block_coalesce_usecs == 0) + return -EINVAL; + if (ecoal->use_adaptive_rx_coalesce || + ecoal->use_adaptive_tx_coalesce) { + if (ecoal->pkt_rate_low > ecoal->pkt_rate_high) + return -EINVAL; + if (ecoal->rate_sample_interval == 0) + return -EINVAL; + if (ecoal->use_adaptive_rx_coalesce && + ((ecoal->rx_coalesce_usecs_low == 0 && + ecoal->rx_max_coalesced_frames_low == 0) || + (ecoal->rx_coalesce_usecs_high == 0 && + ecoal->rx_max_coalesced_frames_high == 0))) + return -EINVAL; + if (ecoal->use_adaptive_tx_coalesce && + ((ecoal->tx_coalesce_usecs_low == 0 && + ecoal->tx_max_coalesced_frames_low == 0) || + (ecoal->tx_coalesce_usecs_high == 0 && + ecoal->tx_max_coalesced_frames_high == 0))) + return -EINVAL; + } + + /* Looks good, let it rip. */ + spin_lock_irq(&tp->lock); + tp->coalesce_config.rx_coalesce_ticks = + tp->coalesce_config.rx_coalesce_ticks_def = + ecoal->rx_coalesce_usecs; + tp->coalesce_config.rx_max_coalesced_frames = + tp->coalesce_config.rx_max_coalesced_frames_def = + ecoal->rx_max_coalesced_frames; + tp->coalesce_config.rx_coalesce_ticks_during_int = + tp->coalesce_config.rx_coalesce_ticks_during_int_def = + ecoal->rx_coalesce_usecs_irq; + tp->coalesce_config.rx_max_coalesced_frames_during_int = + tp->coalesce_config.rx_max_coalesced_frames_during_int_def = + ecoal->rx_max_coalesced_frames_irq; + tp->coalesce_config.tx_coalesce_ticks = + tp->coalesce_config.tx_coalesce_ticks_def = + ecoal->tx_coalesce_usecs; + tp->coalesce_config.tx_max_coalesced_frames = + tp->coalesce_config.tx_max_coalesced_frames_def = + ecoal->tx_max_coalesced_frames; + tp->coalesce_config.tx_coalesce_ticks_during_int = + tp->coalesce_config.tx_coalesce_ticks_during_int_def = + ecoal->tx_coalesce_usecs_irq; + tp->coalesce_config.tx_max_coalesced_frames_during_int = + tp->coalesce_config.tx_max_coalesced_frames_during_int_def = + ecoal->tx_max_coalesced_frames_irq; + tp->coalesce_config.stats_coalesce_ticks = + tp->coalesce_config.stats_coalesce_ticks_def = + ecoal->stats_block_coalesce_usecs; + + if (ecoal->use_adaptive_rx_coalesce) + tp->tg3_flags2 |= TG3_FLG2_ADAPTIVE_RX; + else + tp->tg3_flags2 &= ~TG3_FLG2_ADAPTIVE_RX; + if (ecoal->use_adaptive_tx_coalesce) + tp->tg3_flags2 |= TG3_FLG2_ADAPTIVE_TX; + else + tp->tg3_flags2 &= ~TG3_FLG2_ADAPTIVE_TX; + + tp->coalesce_config.pkt_rate_low = ecoal->pkt_rate_low; + tp->coalesce_config.pkt_rate_high = ecoal->pkt_rate_high; + tp->coalesce_config.rate_sample_jiffies = + ecoal->rate_sample_interval * HZ; + + tp->coalesce_config.rx_coalesce_ticks_low = + ecoal->rx_coalesce_usecs_low; + tp->coalesce_config.rx_max_coalesced_frames_low = + ecoal->rx_max_coalesced_frames_low; + tp->coalesce_config.tx_coalesce_ticks_low = + ecoal->tx_coalesce_usecs_low; + tp->coalesce_config.tx_max_coalesced_frames_low = + ecoal->tx_max_coalesced_frames_low; + + tp->coalesce_config.rx_coalesce_ticks_high = + ecoal->rx_coalesce_usecs_high; + tp->coalesce_config.rx_max_coalesced_frames_high = + ecoal->rx_max_coalesced_frames_high; + tp->coalesce_config.tx_coalesce_ticks_high = + ecoal->tx_coalesce_usecs_high; + tp->coalesce_config.tx_max_coalesced_frames_high = + ecoal->tx_max_coalesced_frames_high; + + tw32(HOSTCC_RXCOL_TICKS, + tp->coalesce_config.rx_coalesce_ticks_def); + tw32(HOSTCC_RXMAX_FRAMES, + tp->coalesce_config.rx_max_coalesced_frames_def); + tw32(HOSTCC_RXCOAL_TICK_INT, + tp->coalesce_config.rx_coalesce_ticks_during_int_def); + tw32(HOSTCC_RXCOAL_MAXF_INT, + tp->coalesce_config.rx_max_coalesced_frames_during_int_def); + tw32(HOSTCC_TXCOL_TICKS, + tp->coalesce_config.tx_coalesce_ticks_def); + tw32(HOSTCC_TXMAX_FRAMES, + tp->coalesce_config.tx_max_coalesced_frames_def); + tw32(HOSTCC_TXCOAL_TICK_INT, + tp->coalesce_config.tx_coalesce_ticks_during_int_def); + tw32(HOSTCC_TXCOAL_MAXF_INT, + tp->coalesce_config.tx_max_coalesced_frames_during_int_def); + tw32(HOSTCC_STAT_COAL_TICKS, + tp->coalesce_config.stats_coalesce_ticks_def); + + spin_unlock_irq(&tp->lock); + + return 0; +} +#endif /* !CONFIG_TIGON3_NAPI */ + static void tg3_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering) { struct tg3 *tp = dev->priv; @@ -6245,6 +6636,10 @@ .set_msglevel = tg3_set_msglevel, .nway_reset = tg3_nway_reset, .get_link = ethtool_op_get_link, +#ifndef CONFIG_TIGON3_NAPI + .get_coalesce = tg3_get_coalesce, + .set_coalesce = tg3_set_coalesce, +#endif .get_ringparam = tg3_get_ringparam, .set_ringparam = tg3_set_ringparam, .get_pauseparam = tg3_get_pauseparam, @@ -6889,6 +7284,7 @@ (tp->pci_chip_rev_id != CHIPREV_ID_5705_A1))) tp->tg3_flags2 |= TG3_FLG2_NO_ETH_WIRE_SPEED; +#ifdef CONFIG_TIGON3_NAPI /* Only 5701 and later support tagged irq status mode. * Also, 5788 chips cannot use tagged irq status. * @@ -6897,6 +7293,10 @@ * fully clear in that mode. */ tp->coalesce_mode = 0; +#else + tp->coalesce_mode = (HOSTCC_MODE_CLRTICK_RXBD | + HOSTCC_MODE_CLRTICK_TXBD); +#endif if (GET_CHIP_REV(tp->pci_chip_rev_id) != CHIPREV_5700_AX && GET_CHIP_REV(tp->pci_chip_rev_id) != CHIPREV_5700_BX) @@ -7424,6 +7824,63 @@ tp->link_config.orig_autoneg = AUTONEG_INVALID; } +#ifndef CONFIG_TIGON3_NAPI +static void __devinit tg3_init_coalesce_config(struct tg3 *tp) +{ + tp->coalesce_config.rx_coalesce_ticks_def = DEFAULT_RXCOL_TICKS; + tp->coalesce_config.rx_max_coalesced_frames_def = DEFAULT_RXMAX_FRAMES; + tp->coalesce_config.rx_coalesce_ticks_during_int_def = + DEFAULT_RXCOAL_TICK_INT; + tp->coalesce_config.rx_max_coalesced_frames_during_int_def = + DEFAULT_RXCOAL_MAXF_INT; + tp->coalesce_config.tx_coalesce_ticks_def = DEFAULT_TXCOL_TICKS; + tp->coalesce_config.tx_max_coalesced_frames_def = DEFAULT_TXMAX_FRAMES; + tp->coalesce_config.tx_coalesce_ticks_during_int_def = + DEFAULT_TXCOAL_TICK_INT; + tp->coalesce_config.tx_max_coalesced_frames_during_int_def = + DEFAULT_TXCOAL_MAXF_INT; + tp->coalesce_config.stats_coalesce_ticks_def = + DEFAULT_STAT_COAL_TICKS; + + tp->coalesce_config.rx_coalesce_ticks_low = + LOW_RXCOL_TICKS; + tp->coalesce_config.rx_max_coalesced_frames_low = + LOW_RXMAX_FRAMES; + tp->coalesce_config.tx_coalesce_ticks_low = + LOW_TXCOL_TICKS; + tp->coalesce_config.tx_max_coalesced_frames_low = + LOW_TXMAX_FRAMES; + + tp->coalesce_config.rx_coalesce_ticks_high = + HIGH_RXCOL_TICKS; + tp->coalesce_config.rx_max_coalesced_frames_high = + HIGH_RXMAX_FRAMES; + tp->coalesce_config.tx_coalesce_ticks_high = + HIGH_TXCOL_TICKS; + tp->coalesce_config.tx_max_coalesced_frames_high = + HIGH_TXMAX_FRAMES; + + /* Active == default */ + tp->coalesce_config.rx_coalesce_ticks = + tp->coalesce_config.rx_coalesce_ticks_def; + tp->coalesce_config.rx_max_coalesced_frames = + tp->coalesce_config.rx_max_coalesced_frames_def; + tp->coalesce_config.tx_coalesce_ticks = + tp->coalesce_config.tx_coalesce_ticks_def; + tp->coalesce_config.tx_max_coalesced_frames = + tp->coalesce_config.tx_max_coalesced_frames_def; + tp->coalesce_config.stats_coalesce_ticks = + tp->coalesce_config.stats_coalesce_ticks_def; + + tp->coalesce_config.rate_sample_jiffies = (1 * HZ); + tp->coalesce_config.pkt_rate_low = 22000; + tp->coalesce_config.pkt_rate_high = 61000; + + tp->tg3_flags2 |= TG3_FLG2_ADAPTIVE_RX; + tp->tg3_flags2 &= ~(TG3_FLG2_ADAPTIVE_TX); +} +#endif /* !CONFIG_TIGON3_NAPI */ + static void __devinit tg3_init_bufmgr_config(struct tg3 *tp) { tp->bufmgr_config.mbuf_read_dma_low_water = @@ -7613,6 +8070,10 @@ tg3_init_link_config(tp); +#ifndef CONFIG_TIGON3_NAPI + tg3_init_coalesce_config(tp); +#endif /* !CONFIG_TIGON3_NAPI */ + tg3_init_bufmgr_config(tp); tp->rx_pending = TG3_DEF_RX_RING_PENDING; @@ -7626,9 +8087,11 @@ dev->set_mac_address = tg3_set_mac_addr; dev->do_ioctl = tg3_ioctl; dev->tx_timeout = tg3_tx_timeout; - dev->poll = tg3_poll; dev->ethtool_ops = &tg3_ethtool_ops; +#ifdef CONFIG_TIGON3_NAPI + dev->poll = tg3_poll; dev->weight = 64; +#endif /* CONFIG_TIGON3_NAPI */ dev->watchdog_timeo = TG3_TX_TIMEOUT; dev->change_mtu = tg3_change_mtu; dev->irq = pdev->irq; @@ -7718,7 +8181,7 @@ */ pci_save_state(tp->pdev, tp->pci_cfg_state); - printk(KERN_INFO "%s: Tigon3 [partno(%s) rev %04x PHY(%s)] (PCI%s:%s:%s) %sBaseT Ethernet ", + printk(KERN_INFO "%s: Tigon3 [partno(%s) rev %04x PHY(%s)] (PCI%s:%s:%s) %sBaseT Ethernet (%s) ", dev->name, tp->board_part_number, tp->pci_chip_rev_id, @@ -7728,7 +8191,13 @@ ((tp->tg3_flags & TG3_FLAG_PCIX_MODE) ? "133MHz" : "66MHz") : ((tp->tg3_flags & TG3_FLAG_PCIX_MODE) ? "100MHz" : "33MHz")), ((tp->tg3_flags & TG3_FLAG_PCI_32BIT) ? "32-bit" : "64-bit"), - (tp->tg3_flags & TG3_FLAG_10_100_ONLY) ? "10/100" : "10/100/1000"); + (tp->tg3_flags & TG3_FLAG_10_100_ONLY) ? "10/100" : "10/100/1000", +#ifdef CONFIG_TIGON3_NAPI + "NAPI" +#else + "no NAPI" +#endif + ); for (i = 0; i < 6; i++) printk("%2.2x%c", dev->dev_addr[i], =========================================================================== linux/drivers/net/tg3.h =========================================================================== --- /usr/tmp/TmpDir.26498-0/linux/drivers/net/tg3.h_1.9 Tue Nov 11 12:38:57 2003 +++ linux/drivers/net/tg3.h Tue Nov 11 12:38:24 2003 @@ -1801,6 +1801,47 @@ u8 orig_autoneg; }; +#ifndef CONFIG_TIGON3_NAPI +struct tg3_coalesce_config { + /* Current settings. */ + u32 rx_coalesce_ticks; + u32 rx_max_coalesced_frames; + u32 rx_coalesce_ticks_during_int; + u32 rx_max_coalesced_frames_during_int; + u32 tx_coalesce_ticks; + u32 tx_max_coalesced_frames; + u32 tx_coalesce_ticks_during_int; + u32 tx_max_coalesced_frames_during_int; + u32 stats_coalesce_ticks; + + /* Default settings. */ + u32 rx_coalesce_ticks_def; + u32 rx_max_coalesced_frames_def; + u32 rx_coalesce_ticks_during_int_def; + u32 rx_max_coalesced_frames_during_int_def; + u32 tx_coalesce_ticks_def; + u32 tx_max_coalesced_frames_def; + u32 tx_coalesce_ticks_during_int_def; + u32 tx_max_coalesced_frames_during_int_def; + u32 stats_coalesce_ticks_def; + + /* Adaptive RX/TX coalescing parameters. */ + u32 rate_sample_jiffies; + u32 pkt_rate_low; + u32 pkt_rate_high; + + u32 rx_coalesce_ticks_low; + u32 rx_max_coalesced_frames_low; + u32 tx_coalesce_ticks_low; + u32 tx_max_coalesced_frames_low; + + u32 rx_coalesce_ticks_high; + u32 rx_max_coalesced_frames_high; + u32 tx_coalesce_ticks_high; + u32 tx_max_coalesced_frames_high; +}; +#endif /* !CONFIG_TIGON3_NAPI */ + struct tg3_bufmgr_config { u32 mbuf_read_dma_low_water; u32 mbuf_mac_rx_low_water; @@ -1879,6 +1920,13 @@ struct net_device_stats net_stats_prev; unsigned long phy_crc_errors; +#ifndef CONFIG_TIGON3_NAPI + /* Adaptive coalescing engine. */ + unsigned long last_rate_sample; + u32 last_rx_count; + u32 last_tx_count; +#endif /* !CONFIG_TIGON3_NAPI */ + u32 rx_offset; u32 tg3_flags; #define TG3_FLAG_HOST_TXDS 0x00000001 @@ -1920,6 +1968,8 @@ #define TG3_FLG2_IS_5788 0x00000008 #define TG3_FLG2_MAX_RXPEND_64 0x00000010 #define TG3_FLG2_TSO_CAPABLE 0x00000020 +#define TG3_FLG2_ADAPTIVE_RX 0x00000040 +#define TG3_FLG2_ADAPTIVE_TX 0x00000080 u32 split_mode_max_reqs; #define SPLIT_MODE_5704_MAX_REQ 3 @@ -1932,6 +1982,9 @@ u16 asf_multiplier; struct tg3_link_config link_config; +#ifndef CONFIG_TIGON3_NAPI + struct tg3_coalesce_config coalesce_config; +#endif /* !CONFIG_TIGON3_NAPI */ struct tg3_bufmgr_config bufmgr_config; /* cache h/w values, often passed straight to h/w */ Greg. -- Greg Banks, R&D Software Engineer, SGI Australian Software Group. I don't speak for SGI.