X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fnet%2Fforcedeth.c;h=e7fc28b07e5a5ed7056955bed669eea278fba417;hb=9f68788856b134f93d9d10b19aa902924c61fc02;hp=7d93948aec83410e2ba2100111b4e88bd74a4909;hpb=739cdbf1d8f0739b80035b80d69d871e33749b86;p=linux-2.6-omap-h63xx.git diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 7d93948aec8..e7fc28b07e5 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -10,7 +10,7 @@ * trademarks of NVIDIA Corporation in the United States and other * countries. * - * Copyright (C) 2003,4 Manfred Spraul + * Copyright (C) 2003,4,5 Manfred Spraul * Copyright (C) 2004 Andrew de Quincey (wol support) * Copyright (C) 2004 Carl-Daniel Hailfinger (invalid MAC handling, insane * IRQ rate fixes, bigendian fixes, cleanups, verification) @@ -80,7 +80,7 @@ * into nv_close, otherwise reenabling for wol can * cause DMA to kfree'd memory. * 0.31: 14 Nov 2004: ethtool support for getting/setting link - * capabilities. + * capabilities. * 0.32: 16 Apr 2005: RX_ERROR4 handling added. * 0.33: 16 May 2005: Support for MCP51 added. * 0.34: 18 Jun 2005: Add DEV_NEED_LINKTIMER to all nForce nics. @@ -89,12 +89,22 @@ * 0.37: 10 Jul 2005: Additional ethtool support, cleanup of pci id list * 0.38: 16 Jul 2005: tx irq rewrite: Use global flags instead of * per-packet flags. - * 0.39: 18 Jul 2005: Add 64bit descriptor support. - * 0.40: 19 Jul 2005: Add support for mac address change. - * 0.41: 30 Jul 2005: Write back original MAC in nv_close instead + * 0.39: 18 Jul 2005: Add 64bit descriptor support. + * 0.40: 19 Jul 2005: Add support for mac address change. + * 0.41: 30 Jul 2005: Write back original MAC in nv_close instead * of nv_remove - * 0.42: 06 Aug 2005: Fix lack of link speed initialization + * 0.42: 06 Aug 2005: Fix lack of link speed initialization * in the second (and later) nv_open call + * 0.43: 10 Aug 2005: Add support for tx checksum. + * 0.44: 20 Aug 2005: Add support for scatter gather and segmentation. + * 0.45: 18 Sep 2005: Remove nv_stop/start_rx from every link check + * 0.46: 20 Oct 2005: Add irq optimization modes. + * 0.47: 26 Oct 2005: Add phyaddr 0 in phy scan. + * 0.48: 24 Dec 2005: Disable TSO, bugfix for pci_map_single + * 0.49: 10 Dec 2005: Fix tso for large buffers. + * 0.50: 20 Jan 2006: Add 8021pq tagging support. + * 0.51: 20 Jan 2006: Add 64bit consistent memory allocation for rings. + * 0.52: 20 Jan 2006: Add MSI/MSIX support. * * Known bugs: * We suspect that on some hardware no TX done interrupts are generated. @@ -106,7 +116,7 @@ * DEV_NEED_TIMERIRQ will not harm you on sane hardware, only generating a few * superfluous timer interrupts from the nic. */ -#define FORCEDETH_VERSION "0.41" +#define FORCEDETH_VERSION "0.52" #define DRV_NAME "forcedeth" #include @@ -145,6 +155,10 @@ #define DEV_NEED_LINKTIMER 0x0002 /* poll link settings. Relies on the timer irq */ #define DEV_HAS_LARGEDESC 0x0004 /* device supports jumbo frames and needs packet format 2 */ #define DEV_HAS_HIGH_DMA 0x0008 /* device supports 64bit dma */ +#define DEV_HAS_CHECKSUM 0x0010 /* device supports tx and rx checksum offloads */ +#define DEV_HAS_VLAN 0x0020 /* device supports vlan tagging and striping */ +#define DEV_HAS_MSI 0x0040 /* device supports MSI */ +#define DEV_HAS_MSI_X 0x0080 /* device supports MSI-X */ enum { NvRegIrqStatus = 0x000, @@ -158,13 +172,17 @@ enum { #define NVREG_IRQ_TX_OK 0x0010 #define NVREG_IRQ_TIMER 0x0020 #define NVREG_IRQ_LINK 0x0040 -#define NVREG_IRQ_TX_ERROR 0x0080 -#define NVREG_IRQ_TX1 0x0100 -#define NVREG_IRQMASK_WANTED 0x00df +#define NVREG_IRQ_RX_FORCED 0x0080 +#define NVREG_IRQ_TX_FORCED 0x0100 +#define NVREG_IRQMASK_THROUGHPUT 0x00df +#define NVREG_IRQMASK_CPU 0x0040 +#define NVREG_IRQ_TX_ALL (NVREG_IRQ_TX_ERR|NVREG_IRQ_TX_OK|NVREG_IRQ_TX_FORCED) +#define NVREG_IRQ_RX_ALL (NVREG_IRQ_RX_ERROR|NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF|NVREG_IRQ_RX_FORCED) +#define NVREG_IRQ_OTHER (NVREG_IRQ_TIMER|NVREG_IRQ_LINK) #define NVREG_IRQ_UNKNOWN (~(NVREG_IRQ_RX_ERROR|NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF|NVREG_IRQ_TX_ERR| \ - NVREG_IRQ_TX_OK|NVREG_IRQ_TIMER|NVREG_IRQ_LINK|NVREG_IRQ_TX_ERROR| \ - NVREG_IRQ_TX1)) + NVREG_IRQ_TX_OK|NVREG_IRQ_TIMER|NVREG_IRQ_LINK|NVREG_IRQ_RX_FORCED| \ + NVREG_IRQ_TX_FORCED)) NvRegUnknownSetupReg6 = 0x008, #define NVREG_UNKSETUP6_VAL 3 @@ -174,7 +192,12 @@ enum { * NVREG_POLL_DEFAULT=97 would result in an interval length of 1 ms */ NvRegPollingInterval = 0x00c, -#define NVREG_POLL_DEFAULT 970 +#define NVREG_POLL_DEFAULT_THROUGHPUT 970 +#define NVREG_POLL_DEFAULT_CPU 13 + NvRegMSIMap0 = 0x020, + NvRegMSIMap1 = 0x024, + NvRegMSIIrqMask = 0x030, +#define NVREG_MSI_VECTOR_0_ENABLED 0x01 NvRegMisc1 = 0x080, #define NVREG_MISC1_HD 0x02 #define NVREG_MISC1_FORCE 0x3b0f3c @@ -241,6 +264,13 @@ enum { #define NVREG_TXRXCTL_IDLE 0x0008 #define NVREG_TXRXCTL_RESET 0x0010 #define NVREG_TXRXCTL_RXCHECK 0x0400 +#define NVREG_TXRXCTL_DESC_1 0 +#define NVREG_TXRXCTL_DESC_2 0x02100 +#define NVREG_TXRXCTL_DESC_3 0x02200 +#define NVREG_TXRXCTL_VLANSTRIP 0x00040 +#define NVREG_TXRXCTL_VLANINS 0x00080 + NvRegTxRingPhysAddrHigh = 0x148, + NvRegRxRingPhysAddrHigh = 0x14C, NvRegMIIStatus = 0x180, #define NVREG_MIISTAT_ERROR 0x0001 #define NVREG_MIISTAT_LINKCHANGE 0x0008 @@ -290,6 +320,11 @@ enum { #define NVREG_POWERSTATE_D1 0x0001 #define NVREG_POWERSTATE_D2 0x0002 #define NVREG_POWERSTATE_D3 0x0003 + NvRegVlanControl = 0x300, +#define NVREG_VLANCONTROL_ENABLE 0x2000 + NvRegMSIXMap0 = 0x3e0, + NvRegMSIXMap1 = 0x3e4, + NvRegMSIXIrqStatus = 0x3f0, }; /* Big endian: should work, but is untested */ @@ -301,7 +336,7 @@ struct ring_desc { struct ring_desc_ex { u32 PacketBufferHigh; u32 PacketBufferLow; - u32 Reserved; + u32 TxVlan; u32 FlagLen; }; @@ -335,6 +370,14 @@ typedef union _ring_type { /* error and valid are the same for both */ #define NV_TX2_ERROR (1<<30) #define NV_TX2_VALID (1<<31) +#define NV_TX2_TSO (1<<28) +#define NV_TX2_TSO_SHIFT 14 +#define NV_TX2_TSO_MAX_SHIFT 14 +#define NV_TX2_TSO_MAX_SIZE (1<desc_ver with DESC_VER_xy. - * - It contains bits that are forced on when writing to NvRegTxRxControl. + * The nic supports three different descriptor types: + * - DESC_VER_1: Original + * - DESC_VER_2: support for jumbo frames. + * - DESC_VER_3: 64-bit format. */ -#define DESC_VER_1 0x0 -#define DESC_VER_2 (0x02100|NVREG_TXRXCTL_RXCHECK) -#define DESC_VER_3 (0x02200|NVREG_TXRXCTL_RXCHECK) +#define DESC_VER_1 1 +#define DESC_VER_2 2 +#define DESC_VER_3 3 /* PHY defines */ #define PHY_OUI_MARVELL 0x5043 @@ -456,6 +502,18 @@ typedef union _ring_type { #define LPA_1000FULL 0x0800 #define LPA_1000HALF 0x0400 +/* MSI/MSI-X defines */ +#define NV_MSI_X_MAX_VECTORS 8 +#define NV_MSI_X_VECTORS_MASK 0x000f +#define NV_MSI_CAPABLE 0x0010 +#define NV_MSI_X_CAPABLE 0x0020 +#define NV_MSI_ENABLED 0x0040 +#define NV_MSI_X_ENABLED 0x0080 + +#define NV_MSI_X_VECTOR_ALL 0x0 +#define NV_MSI_X_VECTOR_RX 0x0 +#define NV_MSI_X_VECTOR_TX 0x1 +#define NV_MSI_X_VECTOR_OTHER 0x2 /* * SMP locking: @@ -491,6 +549,8 @@ struct fe_priv { u32 orig_mac[2]; u32 irqmask; u32 desc_ver; + u32 txrxctl_bits; + u32 vlanctl_bits; void __iomem *base; @@ -505,6 +565,7 @@ struct fe_priv { unsigned int pkt_limit; struct timer_list oom_kick; struct timer_list nic_poll; + u32 nic_poll_irq; /* media detection workaround. * Locking: Within irq hander or disable_irq+spin_lock(&np->lock); @@ -518,7 +579,15 @@ struct fe_priv { unsigned int next_tx, nic_tx; struct sk_buff *tx_skbuff[TX_RING]; dma_addr_t tx_dma[TX_RING]; + unsigned int tx_dma_len[TX_RING]; u32 tx_flags; + + /* vlan fields */ + struct vlan_group *vlangrp; + + /* msi/msi-x fields */ + u32 msi_flags; + struct msix_entry msi_x_entry[NV_MSI_X_MAX_VECTORS]; }; /* @@ -527,6 +596,35 @@ struct fe_priv { */ static int max_interrupt_work = 5; +/* + * Optimization can be either throuput mode or cpu mode + * + * Throughput Mode: Every tx and rx packet will generate an interrupt. + * CPU Mode: Interrupts are controlled by a timer. + */ +#define NV_OPTIMIZATION_MODE_THROUGHPUT 0 +#define NV_OPTIMIZATION_MODE_CPU 1 +static int optimization_mode = NV_OPTIMIZATION_MODE_THROUGHPUT; + +/* + * Poll interval for timer irq + * + * This interval determines how frequent an interrupt is generated. + * The is value is determined by [(time_in_micro_secs * 100) / (2^10)] + * Min = 0, and Max = 65535 + */ +static int poll_interval = -1; + +/* + * Disable MSI interrupts + */ +static int disable_msi = 0; + +/* + * Disable MSIX interrupts + */ +static int disable_msix = 0; + static inline struct fe_priv *get_nvpriv(struct net_device *dev) { return netdev_priv(dev); @@ -534,7 +632,7 @@ static inline struct fe_priv *get_nvpriv(struct net_device *dev) static inline u8 __iomem *get_hwbase(struct net_device *dev) { - return get_nvpriv(dev)->base; + return ((struct fe_priv *)netdev_priv(dev))->base; } static inline void pci_push(u8 __iomem *base) @@ -572,6 +670,33 @@ static int reg_delay(struct net_device *dev, int offset, u32 mask, u32 target, return 0; } +#define NV_SETUP_RX_RING 0x01 +#define NV_SETUP_TX_RING 0x02 + +static void setup_hw_rings(struct net_device *dev, int rxtx_flags) +{ + struct fe_priv *np = get_nvpriv(dev); + u8 __iomem *base = get_hwbase(dev); + + if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) { + if (rxtx_flags & NV_SETUP_RX_RING) { + writel((u32) cpu_to_le64(np->ring_addr), base + NvRegRxRingPhysAddr); + } + if (rxtx_flags & NV_SETUP_TX_RING) { + writel((u32) cpu_to_le64(np->ring_addr + RX_RING*sizeof(struct ring_desc)), base + NvRegTxRingPhysAddr); + } + } else { + if (rxtx_flags & NV_SETUP_RX_RING) { + writel((u32) cpu_to_le64(np->ring_addr), base + NvRegRxRingPhysAddr); + writel((u32) (cpu_to_le64(np->ring_addr) >> 32), base + NvRegRxRingPhysAddrHigh); + } + if (rxtx_flags & NV_SETUP_TX_RING) { + writel((u32) cpu_to_le64(np->ring_addr + RX_RING*sizeof(struct ring_desc_ex)), base + NvRegTxRingPhysAddr); + writel((u32) (cpu_to_le64(np->ring_addr + RX_RING*sizeof(struct ring_desc_ex)) >> 32), base + NvRegTxRingPhysAddrHigh); + } + } +} + #define MII_READ (-1) /* mii_rw: read/write a register on the PHY. * @@ -623,7 +748,7 @@ static int mii_rw(struct net_device *dev, int addr, int miireg, int value) static int phy_reset(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u32 miicontrol; unsigned int tries = 0; @@ -726,7 +851,7 @@ static int phy_init(struct net_device *dev) static void nv_start_rx(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); dprintk(KERN_DEBUG "%s: nv_start_rx\n", dev->name); @@ -782,14 +907,14 @@ static void nv_stop_tx(struct net_device *dev) static void nv_txrx_reset(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); dprintk(KERN_DEBUG "%s: nv_txrx_reset\n", dev->name); - writel(NVREG_TXRXCTL_BIT2 | NVREG_TXRXCTL_RESET | np->desc_ver, base + NvRegTxRxControl); + writel(NVREG_TXRXCTL_BIT2 | NVREG_TXRXCTL_RESET | np->txrxctl_bits, base + NvRegTxRxControl); pci_push(base); udelay(NV_TXRX_RESET_DELAY); - writel(NVREG_TXRXCTL_BIT2 | np->desc_ver, base + NvRegTxRxControl); + writel(NVREG_TXRXCTL_BIT2 | np->txrxctl_bits, base + NvRegTxRxControl); pci_push(base); } @@ -801,7 +926,7 @@ static void nv_txrx_reset(struct net_device *dev) */ static struct net_device_stats *nv_get_stats(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + 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 @@ -817,7 +942,7 @@ static struct net_device_stats *nv_get_stats(struct net_device *dev) */ static int nv_alloc_rx(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); unsigned int refill_rx = np->refill_rx; int nr; @@ -836,8 +961,8 @@ static int nv_alloc_rx(struct net_device *dev) } else { skb = np->rx_skbuff[nr]; } - np->rx_dma[nr] = pci_map_single(np->pci_dev, skb->data, skb->len, - PCI_DMA_FROMDEVICE); + np->rx_dma[nr] = pci_map_single(np->pci_dev, skb->data, + skb->end-skb->data, PCI_DMA_FROMDEVICE); if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) { np->rx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->rx_dma[nr]); wmb(); @@ -861,21 +986,34 @@ static int nv_alloc_rx(struct net_device *dev) static void nv_do_rx_refill(unsigned long data) { struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); - disable_irq(dev->irq); + + if (!(np->msi_flags & NV_MSI_X_ENABLED) || + ((np->msi_flags & NV_MSI_X_ENABLED) && + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) { + disable_irq(dev->irq); + } else { + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + } 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); } - enable_irq(dev->irq); + if (!(np->msi_flags & NV_MSI_X_ENABLED) || + ((np->msi_flags & NV_MSI_X_ENABLED) && + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) { + enable_irq(dev->irq); + } else { + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + } } static void nv_init_rx(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); int i; np->cur_rx = RX_RING; @@ -889,15 +1027,18 @@ static void nv_init_rx(struct net_device *dev) static void nv_init_tx(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); int i; np->next_tx = np->nic_tx = 0; - for (i = 0; i < TX_RING; i++) + for (i = 0; i < TX_RING; i++) { if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) np->tx_ring.orig[i].FlagLen = 0; else np->tx_ring.ex[i].FlagLen = 0; + np->tx_skbuff[i] = NULL; + np->tx_dma[i] = 0; + } } static int nv_init_ring(struct net_device *dev) @@ -907,29 +1048,47 @@ static int nv_init_ring(struct net_device *dev) return nv_alloc_rx(dev); } +static int nv_release_txskb(struct net_device *dev, unsigned int skbnr) +{ + struct fe_priv *np = netdev_priv(dev); + + dprintk(KERN_INFO "%s: nv_release_txskb for skbnr %d\n", + dev->name, skbnr); + + if (np->tx_dma[skbnr]) { + pci_unmap_page(np->pci_dev, np->tx_dma[skbnr], + np->tx_dma_len[skbnr], + PCI_DMA_TODEVICE); + np->tx_dma[skbnr] = 0; + } + + if (np->tx_skbuff[skbnr]) { + dev_kfree_skb_any(np->tx_skbuff[skbnr]); + np->tx_skbuff[skbnr] = NULL; + return 1; + } else { + return 0; + } +} + static void nv_drain_tx(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); - int i; + struct fe_priv *np = netdev_priv(dev); + unsigned int i; + for (i = 0; i < TX_RING; i++) { if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) np->tx_ring.orig[i].FlagLen = 0; else np->tx_ring.ex[i].FlagLen = 0; - if (np->tx_skbuff[i]) { - pci_unmap_single(np->pci_dev, np->tx_dma[i], - np->tx_skbuff[i]->len, - PCI_DMA_TODEVICE); - dev_kfree_skb(np->tx_skbuff[i]); - np->tx_skbuff[i] = NULL; + if (nv_release_txskb(dev, i)) np->stats.tx_dropped++; - } } } static void nv_drain_rx(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); int i; for (i = 0; i < RX_RING; i++) { if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) @@ -939,7 +1098,7 @@ static void nv_drain_rx(struct net_device *dev) wmb(); if (np->rx_skbuff[i]) { pci_unmap_single(np->pci_dev, np->rx_dma[i], - np->rx_skbuff[i]->len, + np->rx_skbuff[i]->end-np->rx_skbuff[i]->data, PCI_DMA_FROMDEVICE); dev_kfree_skb(np->rx_skbuff[i]); np->rx_skbuff[i] = NULL; @@ -959,28 +1118,113 @@ static void drain_ring(struct net_device *dev) */ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); - int nr = np->next_tx % TX_RING; + struct fe_priv *np = netdev_priv(dev); + u32 tx_flags = 0; + u32 tx_flags_extra = (np->desc_ver == DESC_VER_1 ? NV_TX_LASTPACKET : NV_TX2_LASTPACKET); + unsigned int fragments = skb_shinfo(skb)->nr_frags; + unsigned int nr = (np->next_tx - 1) % TX_RING; + unsigned int start_nr = np->next_tx % TX_RING; + unsigned int i; + u32 offset = 0; + u32 bcnt; + 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 tx_flags_vlan = 0; + + /* add fragments to entries count */ + for (i = 0; i < fragments; i++) { + entries += (skb_shinfo(skb)->frags[i].size >> NV_TX2_TSO_MAX_SHIFT) + + ((skb_shinfo(skb)->frags[i].size & (NV_TX2_TSO_MAX_SIZE-1)) ? 1 : 0); + } - np->tx_skbuff[nr] = skb; - np->tx_dma[nr] = pci_map_single(np->pci_dev, skb->data,skb->len, - PCI_DMA_TODEVICE); + spin_lock_irq(&np->lock); - if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) - np->tx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->tx_dma[nr]); - else { - np->tx_ring.ex[nr].PacketBufferHigh = cpu_to_le64(np->tx_dma[nr]) >> 32; - np->tx_ring.ex[nr].PacketBufferLow = cpu_to_le64(np->tx_dma[nr]) & 0x0FFFFFFFF; + if ((np->next_tx - np->nic_tx + entries - 1) > TX_LIMIT_STOP) { + spin_unlock_irq(&np->lock); + netif_stop_queue(dev); + return NETDEV_TX_BUSY; } - spin_lock_irq(&np->lock); - wmb(); - if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) - np->tx_ring.orig[nr].FlagLen = cpu_to_le32( (skb->len-1) | np->tx_flags ); + /* setup the header buffer */ + do { + bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size; + nr = (nr + 1) % TX_RING; + + np->tx_dma[nr] = pci_map_single(np->pci_dev, skb->data + offset, bcnt, + PCI_DMA_TODEVICE); + np->tx_dma_len[nr] = bcnt; + + if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) { + np->tx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->tx_dma[nr]); + np->tx_ring.orig[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags); + } else { + np->tx_ring.ex[nr].PacketBufferHigh = cpu_to_le64(np->tx_dma[nr]) >> 32; + np->tx_ring.ex[nr].PacketBufferLow = cpu_to_le64(np->tx_dma[nr]) & 0x0FFFFFFFF; + np->tx_ring.ex[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags); + } + tx_flags = np->tx_flags; + offset += bcnt; + size -= bcnt; + } while(size); + + /* setup the fragments */ + for (i = 0; i < fragments; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + u32 size = frag->size; + offset = 0; + + do { + bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size; + nr = (nr + 1) % TX_RING; + + np->tx_dma[nr] = pci_map_page(np->pci_dev, frag->page, frag->page_offset+offset, bcnt, + PCI_DMA_TODEVICE); + np->tx_dma_len[nr] = bcnt; + + if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) { + np->tx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->tx_dma[nr]); + np->tx_ring.orig[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags); + } else { + np->tx_ring.ex[nr].PacketBufferHigh = cpu_to_le64(np->tx_dma[nr]) >> 32; + np->tx_ring.ex[nr].PacketBufferLow = cpu_to_le64(np->tx_dma[nr]) & 0x0FFFFFFFF; + np->tx_ring.ex[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags); + } + offset += bcnt; + size -= bcnt; + } while (size); + } + + /* set last fragment flag */ + if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) { + np->tx_ring.orig[nr].FlagLen |= cpu_to_le32(tx_flags_extra); + } else { + np->tx_ring.ex[nr].FlagLen |= cpu_to_le32(tx_flags_extra); + } + + np->tx_skbuff[nr] = skb; + +#ifdef NETIF_F_TSO + if (skb_shinfo(skb)->tso_size) + tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->tso_size << NV_TX2_TSO_SHIFT); else - np->tx_ring.ex[nr].FlagLen = cpu_to_le32( (skb->len-1) | np->tx_flags ); - dprintk(KERN_DEBUG "%s: nv_start_xmit: packet packet %d queued for transmission.\n", - dev->name, np->next_tx); +#endif + tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ? (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); + } + + /* set tx flags */ + if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) { + np->tx_ring.orig[start_nr].FlagLen |= cpu_to_le32(tx_flags | tx_flags_extra); + } else { + np->tx_ring.ex[start_nr].TxVlan = cpu_to_le32(tx_flags_vlan); + np->tx_ring.ex[start_nr].FlagLen |= cpu_to_le32(tx_flags | tx_flags_extra); + } + + dprintk(KERN_DEBUG "%s: nv_start_xmit: packet %d (entries %d) queued for transmission. tx_flags_extra: %x\n", + dev->name, np->next_tx, entries, tx_flags_extra); { int j; for (j=0; j<64; j++) { @@ -991,15 +1235,13 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev) dprintk("\n"); } - np->next_tx++; + np->next_tx += entries; dev->trans_start = jiffies; - if (np->next_tx - np->nic_tx >= TX_LIMIT_STOP) - netif_stop_queue(dev); spin_unlock_irq(&np->lock); - writel(NVREG_TXRXCTL_KICK|np->desc_ver, get_hwbase(dev) + NvRegTxRxControl); + writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl); pci_push(get_hwbase(dev)); - return 0; + return NETDEV_TX_OK; } /* @@ -1009,9 +1251,10 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev) */ static void nv_tx_done(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u32 Flags; - int i; + unsigned int i; + struct sk_buff *skb; while (np->nic_tx != np->next_tx) { i = np->nic_tx % TX_RING; @@ -1026,35 +1269,37 @@ static void nv_tx_done(struct net_device *dev) if (Flags & NV_TX_VALID) break; if (np->desc_ver == DESC_VER_1) { - if (Flags & (NV_TX_RETRYERROR|NV_TX_CARRIERLOST|NV_TX_LATECOLLISION| - NV_TX_UNDERFLOW|NV_TX_ERROR)) { - if (Flags & NV_TX_UNDERFLOW) - np->stats.tx_fifo_errors++; - if (Flags & NV_TX_CARRIERLOST) - np->stats.tx_carrier_errors++; - np->stats.tx_errors++; - } else { - np->stats.tx_packets++; - np->stats.tx_bytes += np->tx_skbuff[i]->len; + if (Flags & NV_TX_LASTPACKET) { + skb = np->tx_skbuff[i]; + if (Flags & (NV_TX_RETRYERROR|NV_TX_CARRIERLOST|NV_TX_LATECOLLISION| + NV_TX_UNDERFLOW|NV_TX_ERROR)) { + if (Flags & NV_TX_UNDERFLOW) + np->stats.tx_fifo_errors++; + if (Flags & NV_TX_CARRIERLOST) + np->stats.tx_carrier_errors++; + np->stats.tx_errors++; + } else { + np->stats.tx_packets++; + np->stats.tx_bytes += skb->len; + } } } else { - 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 { - np->stats.tx_packets++; - np->stats.tx_bytes += np->tx_skbuff[i]->len; + if (Flags & NV_TX2_LASTPACKET) { + skb = np->tx_skbuff[i]; + 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 { + np->stats.tx_packets++; + np->stats.tx_bytes += skb->len; + } } } - pci_unmap_single(np->pci_dev, np->tx_dma[i], - np->tx_skbuff[i]->len, - PCI_DMA_TODEVICE); - dev_kfree_skb_irq(np->tx_skbuff[i]); - np->tx_skbuff[i] = NULL; + nv_release_txskb(dev, i); np->nic_tx++; } if (np->next_tx - np->nic_tx < TX_LIMIT_START) @@ -1067,11 +1312,16 @@ static void nv_tx_done(struct net_device *dev) */ static void nv_tx_timeout(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); + u32 status; - printk(KERN_INFO "%s: Got tx_timeout. irq: %08x\n", dev->name, - readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK); + if (np->msi_flags & NV_MSI_X_ENABLED) + status = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK; + else + status = readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK; + + printk(KERN_INFO "%s: Got tx_timeout. irq: %08x\n", dev->name, status); { int i; @@ -1133,10 +1383,7 @@ static void nv_tx_timeout(struct net_device *dev) printk(KERN_DEBUG "%s: tx_timeout: dead entries!\n", dev->name); nv_drain_tx(dev); np->next_tx = np->nic_tx = 0; - if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) - writel((u32) (np->ring_addr + RX_RING*sizeof(struct ring_desc)), base + NvRegTxRingPhysAddr); - else - writel((u32) (np->ring_addr + RX_RING*sizeof(struct ring_desc_ex)), base + NvRegTxRingPhysAddr); + setup_hw_rings(dev, NV_SETUP_TX_RING); netif_wake_queue(dev); } @@ -1200,8 +1447,10 @@ static int nv_getlen(struct net_device *dev, void *packet, int datalen) static void nv_rx_process(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u32 Flags; + u32 vlanflags = 0; + for (;;) { struct sk_buff *skb; @@ -1217,6 +1466,7 @@ static void nv_rx_process(struct net_device *dev) } else { Flags = le32_to_cpu(np->rx_ring.ex[i].FlagLen); len = nv_descr_getlength_ex(&np->rx_ring.ex[i], np->desc_ver); + vlanflags = le32_to_cpu(np->rx_ring.ex[i].PacketBufferLow); } dprintk(KERN_DEBUG "%s: nv_rx_process: looking at packet %d, Flags 0x%x.\n", @@ -1231,7 +1481,7 @@ static void nv_rx_process(struct net_device *dev) * the performance. */ pci_unmap_single(np->pci_dev, np->rx_dma[i], - np->rx_skbuff[i]->len, + np->rx_skbuff[i]->end-np->rx_skbuff[i]->data, PCI_DMA_FROMDEVICE); { @@ -1249,67 +1499,71 @@ static void nv_rx_process(struct net_device *dev) if (!(Flags & NV_RX_DESCRIPTORVALID)) goto next_pkt; - if (Flags & NV_RX_MISSEDFRAME) { - np->stats.rx_missed_errors++; - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & (NV_RX_ERROR1|NV_RX_ERROR2|NV_RX_ERROR3)) { - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & NV_RX_CRCERR) { - np->stats.rx_crc_errors++; - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & NV_RX_OVERFLOW) { - np->stats.rx_over_errors++; - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & NV_RX_ERROR4) { - len = nv_getlen(dev, np->rx_skbuff[i]->data, len); - if (len < 0) { + if (Flags & NV_RX_ERROR) { + if (Flags & NV_RX_MISSEDFRAME) { + np->stats.rx_missed_errors++; np->stats.rx_errors++; goto next_pkt; } - } - /* framing errors are soft errors. */ - if (Flags & NV_RX_FRAMINGERR) { - if (Flags & NV_RX_SUBSTRACT1) { - len--; + if (Flags & (NV_RX_ERROR1|NV_RX_ERROR2|NV_RX_ERROR3)) { + np->stats.rx_errors++; + goto next_pkt; + } + if (Flags & NV_RX_CRCERR) { + np->stats.rx_crc_errors++; + np->stats.rx_errors++; + goto next_pkt; + } + if (Flags & NV_RX_OVERFLOW) { + np->stats.rx_over_errors++; + np->stats.rx_errors++; + goto next_pkt; + } + if (Flags & NV_RX_ERROR4) { + len = nv_getlen(dev, np->rx_skbuff[i]->data, len); + if (len < 0) { + np->stats.rx_errors++; + 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)) goto next_pkt; - if (Flags & (NV_RX2_ERROR1|NV_RX2_ERROR2|NV_RX2_ERROR3)) { - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & NV_RX2_CRCERR) { - np->stats.rx_crc_errors++; - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & NV_RX2_OVERFLOW) { - np->stats.rx_over_errors++; - np->stats.rx_errors++; - goto next_pkt; - } - if (Flags & NV_RX2_ERROR4) { - len = nv_getlen(dev, np->rx_skbuff[i]->data, len); - if (len < 0) { + if (Flags & NV_RX2_ERROR) { + if (Flags & (NV_RX2_ERROR1|NV_RX2_ERROR2|NV_RX2_ERROR3)) { np->stats.rx_errors++; goto next_pkt; } - } - /* framing errors are soft errors */ - if (Flags & NV_RX2_FRAMINGERR) { - if (Flags & NV_RX2_SUBSTRACT1) { - len--; + if (Flags & NV_RX2_CRCERR) { + np->stats.rx_crc_errors++; + np->stats.rx_errors++; + goto next_pkt; + } + if (Flags & NV_RX2_OVERFLOW) { + np->stats.rx_over_errors++; + np->stats.rx_errors++; + goto next_pkt; + } + if (Flags & NV_RX2_ERROR4) { + len = nv_getlen(dev, np->rx_skbuff[i]->data, len); + if (len < 0) { + np->stats.rx_errors++; + goto next_pkt; + } + } + /* framing errors are soft errors */ + if (Flags & NV_RX2_FRAMINGERR) { + if (Flags & NV_RX2_SUBSTRACT1) { + len--; + } } } Flags &= NV_RX2_CHECKSUMMASK; @@ -1330,7 +1584,11 @@ static void nv_rx_process(struct net_device *dev) skb->protocol = eth_type_trans(skb, dev); dprintk(KERN_DEBUG "%s: nv_rx_process: packet %d with %d bytes, proto %d accepted.\n", dev->name, np->cur_rx, len, skb->protocol); - netif_rx(skb); + 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); + } dev->last_rx = jiffies; np->stats.rx_packets++; np->stats.rx_bytes += len; @@ -1355,7 +1613,7 @@ static void set_bufsize(struct net_device *dev) */ static int nv_change_mtu(struct net_device *dev, int new_mtu) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); int old_mtu; if (new_mtu < 64 || new_mtu > np->pkt_limit) @@ -1372,14 +1630,22 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) /* synchronized against open : rtnl_lock() held by caller */ if (netif_running(dev)) { - u8 *base = get_hwbase(dev); + u8 __iomem *base = get_hwbase(dev); /* * It seems that the nic preloads valid ring entries into an * internal buffer. The procedure for flushing everything is * guessed, there is probably a simpler approach. * Changing the MTU is a rare event, it shouldn't matter. */ - disable_irq(dev->irq); + if (!(np->msi_flags & NV_MSI_X_ENABLED) || + ((np->msi_flags & NV_MSI_X_ENABLED) && + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) { + disable_irq(dev->irq); + } else { + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); + } spin_lock_bh(&dev->xmit_lock); spin_lock(&np->lock); /* stop engines */ @@ -1400,15 +1666,11 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) } /* reinit nic view of the rx queue */ writel(np->rx_buf_sz, base + NvRegOffloadConfig); - writel((u32) np->ring_addr, base + NvRegRxRingPhysAddr); - if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) - writel((u32) (np->ring_addr + RX_RING*sizeof(struct ring_desc)), base + NvRegTxRingPhysAddr); - else - writel((u32) (np->ring_addr + RX_RING*sizeof(struct ring_desc_ex)), base + NvRegTxRingPhysAddr); + setup_hw_rings(dev, NV_SETUP_RX_RING | NV_SETUP_TX_RING); writel( ((RX_RING-1) << NVREG_RINGSZ_RXSHIFT) + ((TX_RING-1) << NVREG_RINGSZ_TXSHIFT), base + NvRegRingSizes); pci_push(base); - writel(NVREG_TXRXCTL_KICK|np->desc_ver, get_hwbase(dev) + NvRegTxRxControl); + writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl); pci_push(base); /* restart rx engine */ @@ -1416,14 +1678,22 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) nv_start_tx(dev); spin_unlock(&np->lock); spin_unlock_bh(&dev->xmit_lock); - enable_irq(dev->irq); + if (!(np->msi_flags & NV_MSI_X_ENABLED) || + ((np->msi_flags & NV_MSI_X_ENABLED) && + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) { + enable_irq(dev->irq); + } else { + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); + } } return 0; } static void nv_copy_mac_to_hw(struct net_device *dev) { - u8 *base = get_hwbase(dev); + u8 __iomem *base = get_hwbase(dev); u32 mac[2]; mac[0] = (dev->dev_addr[0] << 0) + (dev->dev_addr[1] << 8) + @@ -1440,7 +1710,7 @@ static void nv_copy_mac_to_hw(struct net_device *dev) */ static int nv_set_mac_address(struct net_device *dev, void *addr) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); struct sockaddr *macaddr = (struct sockaddr*)addr; if(!is_valid_ether_addr(macaddr->sa_data)) @@ -1475,7 +1745,7 @@ static int nv_set_mac_address(struct net_device *dev, void *addr) */ static void nv_set_multicast(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); u32 addr[2]; u32 mask[2]; @@ -1533,9 +1803,20 @@ static void nv_set_multicast(struct net_device *dev) spin_unlock_irq(&np->lock); } +/** + * nv_update_linkspeed: Setup the MAC according to the link partner + * @dev: Network device to be configured + * + * The function queries the PHY and checks if there is a link partner. + * If yes, then it sets up the MAC accordingly. Otherwise, the MAC is + * set to 10 MBit HD. + * + * The function returns 0 if there is no link partner and 1 if there is + * a good link partner. + */ static int nv_update_linkspeed(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); int adv, lpa; int newls = np->linkspeed; @@ -1672,13 +1953,11 @@ set_speed: static void nv_linkchange(struct net_device *dev) { if (nv_update_linkspeed(dev)) { - if (netif_carrier_ok(dev)) { - nv_stop_rx(dev); - } else { + if (!netif_carrier_ok(dev)) { netif_carrier_on(dev); printk(KERN_INFO "%s: link up.\n", dev->name); + nv_start_rx(dev); } - nv_start_rx(dev); } else { if (netif_carrier_ok(dev)) { netif_carrier_off(dev); @@ -1705,7 +1984,7 @@ static void nv_link_irq(struct net_device *dev) static irqreturn_t nv_nic_irq(int foo, void *data, struct pt_regs *regs) { struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); u32 events; int i; @@ -1713,29 +1992,30 @@ static irqreturn_t nv_nic_irq(int foo, void *data, struct pt_regs *regs) dprintk(KERN_DEBUG "%s: nv_nic_irq\n", dev->name); for (i=0; ; i++) { - events = readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK; - writel(NVREG_IRQSTAT_MASK, base + NvRegIrqStatus); + if (!(np->msi_flags & NV_MSI_X_ENABLED)) { + events = readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK; + writel(NVREG_IRQSTAT_MASK, base + NvRegIrqStatus); + } else { + 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; - if (events & (NVREG_IRQ_TX1|NVREG_IRQ_TX_OK|NVREG_IRQ_TX_ERROR|NVREG_IRQ_TX_ERR)) { + spin_lock(&np->lock); + nv_tx_done(dev); + spin_unlock(&np->lock); + + nv_rx_process(dev); + if (nv_alloc_rx(dev)) { spin_lock(&np->lock); - nv_tx_done(dev); + if (!np->in_shutdown) + mod_timer(&np->oom_kick, jiffies + OOM_REFILL); spin_unlock(&np->lock); } - - if (events & (NVREG_IRQ_RX_ERROR|NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF)) { - nv_rx_process(dev); - 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); - } - } - + if (events & NVREG_IRQ_LINK) { spin_lock(&np->lock); nv_link_irq(dev); @@ -1758,11 +2038,16 @@ static irqreturn_t nv_nic_irq(int foo, void *data, struct pt_regs *regs) if (i > max_interrupt_work) { spin_lock(&np->lock); /* disable interrupts on the nic */ - writel(0, base + NvRegIrqMask); + if (!(np->msi_flags & NV_MSI_X_ENABLED)) + writel(0, base + NvRegIrqMask); + else + writel(np->irqmask, base + NvRegIrqMask); pci_push(base); - if (!np->in_shutdown) + if (!np->in_shutdown) { + np->nic_poll_irq = np->irqmask; mod_timer(&np->nic_poll, jiffies + POLL_WAIT); + } printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq.\n", dev->name, i); spin_unlock(&np->lock); break; @@ -1774,22 +2059,212 @@ static irqreturn_t nv_nic_irq(int foo, void *data, struct pt_regs *regs) return IRQ_RETVAL(i); } +static irqreturn_t nv_nic_irq_tx(int foo, void *data, struct pt_regs *regs) +{ + struct net_device *dev = (struct net_device *) data; + struct fe_priv *np = netdev_priv(dev); + u8 __iomem *base = get_hwbase(dev); + u32 events; + int i; + + dprintk(KERN_DEBUG "%s: nv_nic_irq_tx\n", dev->name); + + 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(&np->lock); + nv_tx_done(dev); + spin_unlock(&np->lock); + + if (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) { + spin_lock(&np->lock); + /* disable interrupts on the nic */ + writel(NVREG_IRQ_TX_ALL, base + NvRegIrqMask); + pci_push(base); + + if (!np->in_shutdown) { + np->nic_poll_irq |= NVREG_IRQ_TX_ALL; + mod_timer(&np->nic_poll, jiffies + POLL_WAIT); + } + printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_tx.\n", dev->name, i); + spin_unlock(&np->lock); + break; + } + + } + dprintk(KERN_DEBUG "%s: nv_nic_irq_tx completed\n", dev->name); + + return IRQ_RETVAL(i); +} + +static irqreturn_t nv_nic_irq_rx(int foo, void *data, struct pt_regs *regs) +{ + struct net_device *dev = (struct net_device *) data; + struct fe_priv *np = netdev_priv(dev); + u8 __iomem *base = get_hwbase(dev); + u32 events; + int i; + + dprintk(KERN_DEBUG "%s: nv_nic_irq_rx\n", dev->name); + + 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(dev); + 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); + } + + if (i > max_interrupt_work) { + spin_lock(&np->lock); + /* disable interrupts on the nic */ + writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask); + pci_push(base); + + if (!np->in_shutdown) { + np->nic_poll_irq |= NVREG_IRQ_RX_ALL; + mod_timer(&np->nic_poll, jiffies + POLL_WAIT); + } + printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_rx.\n", dev->name, i); + spin_unlock(&np->lock); + break; + } + + } + dprintk(KERN_DEBUG "%s: nv_nic_irq_rx completed\n", dev->name); + + return IRQ_RETVAL(i); +} + +static irqreturn_t nv_nic_irq_other(int foo, void *data, struct pt_regs *regs) +{ + struct net_device *dev = (struct net_device *) data; + struct fe_priv *np = netdev_priv(dev); + u8 __iomem *base = get_hwbase(dev); + u32 events; + int i; + + dprintk(KERN_DEBUG "%s: nv_nic_irq_other\n", dev->name); + + 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; + + if (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)) { + spin_lock(&np->lock); + nv_linkchange(dev); + spin_unlock(&np->lock); + np->link_timeout = jiffies + LINK_TIMEOUT; + } + if (events & (NVREG_IRQ_UNKNOWN)) { + printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n", + dev->name, events); + } + if (i > max_interrupt_work) { + spin_lock(&np->lock); + /* disable interrupts on the nic */ + writel(NVREG_IRQ_OTHER, base + NvRegIrqMask); + pci_push(base); + + if (!np->in_shutdown) { + np->nic_poll_irq |= NVREG_IRQ_OTHER; + mod_timer(&np->nic_poll, jiffies + POLL_WAIT); + } + printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_other.\n", dev->name, i); + spin_unlock(&np->lock); + break; + } + + } + dprintk(KERN_DEBUG "%s: nv_nic_irq_other completed\n", dev->name); + + return IRQ_RETVAL(i); +} + static void nv_do_nic_poll(unsigned long data) { struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); + u32 mask = 0; - disable_irq(dev->irq); - /* FIXME: Do we need synchronize_irq(dev->irq) here? */ /* + * First disable irq(s) and then * reenable interrupts on the nic, we have to do this before calling * nv_nic_irq because that may decide to do otherwise */ - writel(np->irqmask, base + NvRegIrqMask); + + if (!(np->msi_flags & NV_MSI_X_ENABLED) || + ((np->msi_flags & NV_MSI_X_ENABLED) && + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) { + disable_irq(dev->irq); + mask = np->irqmask; + } else { + if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) { + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + mask |= NVREG_IRQ_RX_ALL; + } + if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) { + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); + mask |= NVREG_IRQ_TX_ALL; + } + if (np->nic_poll_irq & NVREG_IRQ_OTHER) { + disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); + mask |= NVREG_IRQ_OTHER; + } + } + np->nic_poll_irq = 0; + + /* FIXME: Do we need synchronize_irq(dev->irq) here? */ + + writel(mask, base + NvRegIrqMask); pci_push(base); - nv_nic_irq((int) 0, (void *) data, (struct pt_regs *) NULL); - enable_irq(dev->irq); + + if (!(np->msi_flags & NV_MSI_X_ENABLED) || + ((np->msi_flags & NV_MSI_X_ENABLED) && + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) { + nv_nic_irq((int) 0, (void *) data, (struct pt_regs *) NULL); + enable_irq(dev->irq); + } else { + if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) { + nv_nic_irq_rx((int) 0, (void *) data, (struct pt_regs *) NULL); + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + } + if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) { + nv_nic_irq_tx((int) 0, (void *) data, (struct pt_regs *) NULL); + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); + } + if (np->nic_poll_irq & NVREG_IRQ_OTHER) { + nv_nic_irq_other((int) 0, (void *) data, (struct pt_regs *) NULL); + enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); + } + } } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -1801,7 +2276,7 @@ static void nv_poll_controller(struct net_device *dev) static void nv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); strcpy(info->driver, "forcedeth"); strcpy(info->version, FORCEDETH_VERSION); strcpy(info->bus_info, pci_name(np->pci_dev)); @@ -1809,7 +2284,7 @@ static void nv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) static void nv_get_wol(struct net_device *dev, struct ethtool_wolinfo *wolinfo) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); wolinfo->supported = WAKE_MAGIC; spin_lock_irq(&np->lock); @@ -1820,7 +2295,7 @@ static void nv_get_wol(struct net_device *dev, struct ethtool_wolinfo *wolinfo) static int nv_set_wol(struct net_device *dev, struct ethtool_wolinfo *wolinfo) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); spin_lock_irq(&np->lock); @@ -2021,7 +2496,7 @@ static int nv_get_regs_len(struct net_device *dev) static void nv_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *buf) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); u32 *rbuf = buf; int i; @@ -2035,7 +2510,7 @@ static void nv_get_regs(struct net_device *dev, struct ethtool_regs *regs, void static int nv_nway_reset(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); int ret; spin_lock_irq(&np->lock); @@ -2065,13 +2540,69 @@ static struct ethtool_ops ops = { .get_regs_len = nv_get_regs_len, .get_regs = nv_get_regs, .nway_reset = nv_nway_reset, + .get_perm_addr = ethtool_op_get_perm_addr, }; -static int nv_open(struct net_device *dev) +static void nv_vlan_rx_register(struct net_device *dev, struct vlan_group *grp) { struct fe_priv *np = get_nvpriv(dev); + + spin_lock_irq(&np->lock); + + /* save vlan group */ + np->vlangrp = grp; + + if (grp) { + /* enable vlan on MAC */ + np->txrxctl_bits |= NVREG_TXRXCTL_VLANSTRIP | NVREG_TXRXCTL_VLANINS; + } else { + /* disable vlan on MAC */ + np->txrxctl_bits &= ~NVREG_TXRXCTL_VLANSTRIP; + np->txrxctl_bits &= ~NVREG_TXRXCTL_VLANINS; + } + + writel(np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl); + + spin_unlock_irq(&np->lock); +}; + +static void nv_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) +{ + /* nothing to do */ +}; + +static void set_msix_vector_map(struct net_device *dev, u32 vector, u32 irqmask) +{ + u8 __iomem *base = get_hwbase(dev); + int i; + u32 msixmap = 0; + + /* Each interrupt bit can be mapped to a MSIX vector (4 bits). + * MSIXMap0 represents the first 8 interrupts and MSIXMap1 represents + * the remaining 8 interrupts. + */ + for (i = 0; i < 8; i++) { + if ((irqmask >> i) & 0x1) { + msixmap |= vector << (i << 2); + } + } + writel(readl(base + NvRegMSIXMap0) | msixmap, base + NvRegMSIXMap0); + + msixmap = 0; + for (i = 0; i < 8; i++) { + if ((irqmask >> (i + 8)) & 0x1) { + msixmap |= vector << (i << 2); + } + } + writel(readl(base + NvRegMSIXMap1) | msixmap, base + NvRegMSIXMap1); +} + +static int nv_open(struct net_device *dev) +{ + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); - int ret, oom, i; + int ret = 1; + int oom, i; dprintk(KERN_DEBUG "nv_open: begin\n"); @@ -2103,20 +2634,17 @@ static int nv_open(struct net_device *dev) nv_copy_mac_to_hw(dev); /* 4) give hw rings */ - writel((u32) np->ring_addr, base + NvRegRxRingPhysAddr); - if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) - writel((u32) (np->ring_addr + RX_RING*sizeof(struct ring_desc)), base + NvRegTxRingPhysAddr); - else - writel((u32) (np->ring_addr + RX_RING*sizeof(struct ring_desc_ex)), base + NvRegTxRingPhysAddr); + setup_hw_rings(dev, NV_SETUP_RX_RING | NV_SETUP_TX_RING); writel( ((RX_RING-1) << NVREG_RINGSZ_RXSHIFT) + ((TX_RING-1) << NVREG_RINGSZ_TXSHIFT), base + NvRegRingSizes); /* 5) continue setup */ writel(np->linkspeed, base + NvRegLinkSpeed); writel(NVREG_UNKSETUP3_VAL1, base + NvRegUnknownSetupReg3); - writel(np->desc_ver, base + NvRegTxRxControl); + writel(np->txrxctl_bits, base + NvRegTxRxControl); + writel(np->vlanctl_bits, base + NvRegVlanControl); pci_push(base); - writel(NVREG_TXRXCTL_BIT1|np->desc_ver, base + NvRegTxRxControl); + writel(NVREG_TXRXCTL_BIT1|np->txrxctl_bits, base + NvRegTxRxControl); reg_delay(dev, NvRegUnknownSetupReg5, NVREG_UNKSETUP5_BIT31, NVREG_UNKSETUP5_BIT31, NV_SETUP5_DELAY, NV_SETUP5_DELAYMAX, KERN_INFO "open: SetupReg5, Bit 31 remained off\n"); @@ -2136,7 +2664,14 @@ static int nv_open(struct net_device *dev) writel(NVREG_RNDSEED_FORCE | (i&NVREG_RNDSEED_MASK), base + NvRegRandomSeed); writel(NVREG_UNKSETUP1_VAL, base + NvRegUnknownSetupReg1); writel(NVREG_UNKSETUP2_VAL, base + NvRegUnknownSetupReg2); - writel(NVREG_POLL_DEFAULT, base + NvRegPollingInterval); + if (poll_interval == -1) { + if (optimization_mode == NV_OPTIMIZATION_MODE_THROUGHPUT) + writel(NVREG_POLL_DEFAULT_THROUGHPUT, base + NvRegPollingInterval); + else + writel(NVREG_POLL_DEFAULT_CPU, base + NvRegPollingInterval); + } + else + writel(poll_interval & 0xFFFF, base + NvRegPollingInterval); writel(NVREG_UNKSETUP6_VAL, base + NvRegUnknownSetupReg6); writel((np->phyaddr << NVREG_ADAPTCTL_PHYSHIFT)|NVREG_ADAPTCTL_PHYVALID|NVREG_ADAPTCTL_RUNNING, base + NvRegAdapterControl); @@ -2158,9 +2693,77 @@ static int nv_open(struct net_device *dev) writel(NVREG_IRQSTAT_MASK, base + NvRegIrqStatus); pci_push(base); - ret = request_irq(dev->irq, &nv_nic_irq, SA_SHIRQ, dev->name, dev); - if (ret) - goto out_drain; + if (np->msi_flags & NV_MSI_X_CAPABLE) { + for (i = 0; i < (np->msi_flags & NV_MSI_X_VECTORS_MASK); i++) { + np->msi_x_entry[i].entry = i; + } + if ((ret = pci_enable_msix(np->pci_dev, np->msi_x_entry, (np->msi_flags & NV_MSI_X_VECTORS_MASK))) == 0) { + np->msi_flags |= NV_MSI_X_ENABLED; + if (optimization_mode == NV_OPTIMIZATION_MODE_THROUGHPUT) { + /* Request irq for rx handling */ + if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector, &nv_nic_irq_rx, SA_SHIRQ, dev->name, dev) != 0) { + printk(KERN_INFO "forcedeth: request_irq failed for rx %d\n", ret); + pci_disable_msix(np->pci_dev); + np->msi_flags &= ~NV_MSI_X_ENABLED; + goto out_drain; + } + /* Request irq for tx handling */ + if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector, &nv_nic_irq_tx, SA_SHIRQ, dev->name, dev) != 0) { + printk(KERN_INFO "forcedeth: request_irq failed for tx %d\n", ret); + pci_disable_msix(np->pci_dev); + np->msi_flags &= ~NV_MSI_X_ENABLED; + goto out_drain; + } + /* Request irq for link and timer handling */ + if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector, &nv_nic_irq_other, SA_SHIRQ, dev->name, dev) != 0) { + printk(KERN_INFO "forcedeth: request_irq failed for link %d\n", ret); + pci_disable_msix(np->pci_dev); + np->msi_flags &= ~NV_MSI_X_ENABLED; + goto out_drain; + } + + /* map interrupts to their respective vector */ + writel(0, base + NvRegMSIXMap0); + writel(0, base + NvRegMSIXMap1); + set_msix_vector_map(dev, NV_MSI_X_VECTOR_RX, NVREG_IRQ_RX_ALL); + set_msix_vector_map(dev, NV_MSI_X_VECTOR_TX, NVREG_IRQ_TX_ALL); + set_msix_vector_map(dev, NV_MSI_X_VECTOR_OTHER, NVREG_IRQ_OTHER); + } else { + /* Request irq for all interrupts */ + if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector, &nv_nic_irq, SA_SHIRQ, dev->name, dev) != 0) { + printk(KERN_INFO "forcedeth: request_irq failed %d\n", ret); + pci_disable_msix(np->pci_dev); + np->msi_flags &= ~NV_MSI_X_ENABLED; + goto out_drain; + } + + /* map interrupts to vector 0 */ + writel(0, base + NvRegMSIXMap0); + writel(0, base + NvRegMSIXMap1); + } + } + } + if (ret != 0 && np->msi_flags & NV_MSI_CAPABLE) { + if ((ret = pci_enable_msi(np->pci_dev)) == 0) { + np->msi_flags |= NV_MSI_ENABLED; + if (request_irq(np->pci_dev->irq, &nv_nic_irq, SA_SHIRQ, dev->name, dev) != 0) { + printk(KERN_INFO "forcedeth: request_irq failed %d\n", ret); + pci_disable_msi(np->pci_dev); + np->msi_flags &= ~NV_MSI_ENABLED; + goto out_drain; + } + + /* map interrupts to vector 0 */ + writel(0, base + NvRegMSIMap0); + writel(0, base + NvRegMSIMap1); + /* enable msi vector 0 */ + writel(NVREG_MSI_VECTOR_0_ENABLED, base + NvRegMSIIrqMask); + } + } + if (ret != 0) { + if (request_irq(np->pci_dev->irq, &nv_nic_irq, SA_SHIRQ, dev->name, dev) != 0) + goto out_drain; + } /* ask for interrupts */ writel(np->irqmask, base + NvRegIrqMask); @@ -2205,8 +2808,9 @@ out_drain: static int nv_close(struct net_device *dev) { - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); u8 __iomem *base; + int i; spin_lock_irq(&np->lock); np->in_shutdown = 1; @@ -2224,13 +2828,31 @@ static int nv_close(struct net_device *dev) /* disable interrupts on the nic or we will lock up */ base = get_hwbase(dev); - writel(0, base + NvRegIrqMask); + if (np->msi_flags & NV_MSI_X_ENABLED) { + writel(np->irqmask, base + NvRegIrqMask); + } else { + if (np->msi_flags & NV_MSI_ENABLED) + writel(0, base + NvRegMSIIrqMask); + writel(0, base + NvRegIrqMask); + } pci_push(base); dprintk(KERN_INFO "%s: Irqmask is zero again\n", dev->name); spin_unlock_irq(&np->lock); - free_irq(dev->irq, dev); + if (np->msi_flags & NV_MSI_X_ENABLED) { + for (i = 0; i < (np->msi_flags & NV_MSI_X_VECTORS_MASK); i++) { + free_irq(np->msi_x_entry[i].vector, dev); + } + pci_disable_msix(np->pci_dev); + np->msi_flags &= ~NV_MSI_X_ENABLED; + } else { + free_irq(np->pci_dev->irq, dev); + if (np->msi_flags & NV_MSI_ENABLED) { + pci_disable_msi(np->pci_dev); + np->msi_flags &= ~NV_MSI_ENABLED; + } + } drain_ring(dev); @@ -2261,7 +2883,7 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i if (!dev) goto out; - np = get_nvpriv(dev); + np = netdev_priv(dev); np->pci_dev = pci_dev; spin_lock_init(&np->lock); SET_MODULE_OWNER(dev); @@ -2313,19 +2935,55 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i if (pci_set_dma_mask(pci_dev, 0x0000007fffffffffULL)) { printk(KERN_INFO "forcedeth: 64-bit DMA failed, using 32-bit addressing for device %s.\n", pci_name(pci_dev)); + } else { + if (pci_set_consistent_dma_mask(pci_dev, 0x0000007fffffffffULL)) { + printk(KERN_INFO "forcedeth: 64-bit DMA (consistent) failed for device %s.\n", + pci_name(pci_dev)); + goto out_relreg; + } else { + dev->features |= NETIF_F_HIGHDMA; + printk(KERN_INFO "forcedeth: using HIGHDMA\n"); + } } + np->txrxctl_bits = NVREG_TXRXCTL_DESC_3; } else if (id->driver_data & DEV_HAS_LARGEDESC) { /* packet format 2: supports jumbo frames */ np->desc_ver = DESC_VER_2; + np->txrxctl_bits = NVREG_TXRXCTL_DESC_2; } else { /* original packet format */ np->desc_ver = DESC_VER_1; + np->txrxctl_bits = NVREG_TXRXCTL_DESC_1; } np->pkt_limit = NV_PKTLIMIT_1; if (id->driver_data & DEV_HAS_LARGEDESC) np->pkt_limit = NV_PKTLIMIT_2; + if (id->driver_data & DEV_HAS_CHECKSUM) { + np->txrxctl_bits |= NVREG_TXRXCTL_RXCHECK; + dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG; +#ifdef NETIF_F_TSO + dev->features |= NETIF_F_TSO; +#endif + } + + np->vlanctl_bits = 0; + if (id->driver_data & DEV_HAS_VLAN) { + np->vlanctl_bits = NVREG_VLANCONTROL_ENABLE; + dev->features |= NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX; + dev->vlan_rx_register = nv_vlan_rx_register; + dev->vlan_rx_kill_vid = nv_vlan_rx_kill_vid; + } + + np->msi_flags = 0; + if ((id->driver_data & DEV_HAS_MSI) && !disable_msi) { + np->msi_flags |= NV_MSI_CAPABLE; + } + if ((id->driver_data & DEV_HAS_MSI_X) && !disable_msix) { + np->msi_flags |= NV_MSI_X_CAPABLE; + } + err = -ENOMEM; np->base = ioremap(addr, NV_PCI_REGSZ); if (!np->base) @@ -2377,8 +3035,9 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i dev->dev_addr[3] = (np->orig_mac[0] >> 16) & 0xff; dev->dev_addr[4] = (np->orig_mac[0] >> 8) & 0xff; dev->dev_addr[5] = (np->orig_mac[0] >> 0) & 0xff; + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); - if (!is_valid_ether_addr(dev->dev_addr)) { + if (!is_valid_ether_addr(dev->perm_addr)) { /* * Bad mac address. At least one bios sets the mac address * to 01:23:45:67:89:ab @@ -2403,11 +3062,20 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i np->wolenabled = 0; if (np->desc_ver == DESC_VER_1) { - np->tx_flags = NV_TX_LASTPACKET|NV_TX_VALID; + np->tx_flags = NV_TX_VALID; } else { - np->tx_flags = NV_TX2_LASTPACKET|NV_TX2_VALID; + np->tx_flags = NV_TX2_VALID; } - np->irqmask = NVREG_IRQMASK_WANTED; + if (optimization_mode == NV_OPTIMIZATION_MODE_THROUGHPUT) { + np->irqmask = NVREG_IRQMASK_THROUGHPUT; + if (np->msi_flags & NV_MSI_X_CAPABLE) /* set number of vectors */ + np->msi_flags |= 0x0003; + } else { + np->irqmask = NVREG_IRQMASK_CPU; + if (np->msi_flags & NV_MSI_X_CAPABLE) /* set number of vectors */ + np->msi_flags |= 0x0001; + } + if (id->driver_data & DEV_NEED_TIMERIRQ) np->irqmask |= NVREG_IRQ_TIMER; if (id->driver_data & DEV_NEED_LINKTIMER) { @@ -2420,16 +3088,17 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i } /* find a suitable phy */ - for (i = 1; i < 32; i++) { + for (i = 1; i <= 32; i++) { int id1, id2; + int phyaddr = i & 0x1F; spin_lock_irq(&np->lock); - id1 = mii_rw(dev, i, MII_PHYSID1, MII_READ); + id1 = mii_rw(dev, phyaddr, MII_PHYSID1, MII_READ); spin_unlock_irq(&np->lock); if (id1 < 0 || id1 == 0xffff) continue; spin_lock_irq(&np->lock); - id2 = mii_rw(dev, i, MII_PHYSID2, MII_READ); + id2 = mii_rw(dev, phyaddr, MII_PHYSID2, MII_READ); spin_unlock_irq(&np->lock); if (id2 < 0 || id2 == 0xffff) continue; @@ -2437,23 +3106,19 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i id1 = (id1 & PHYID1_OUI_MASK) << PHYID1_OUI_SHFT; id2 = (id2 & PHYID2_OUI_MASK) >> PHYID2_OUI_SHFT; dprintk(KERN_DEBUG "%s: open: Found PHY %04x:%04x at address %d.\n", - pci_name(pci_dev), id1, id2, i); - np->phyaddr = i; + pci_name(pci_dev), id1, id2, phyaddr); + np->phyaddr = phyaddr; np->phy_oui = id1 | id2; break; } - if (i == 32) { - /* PHY in isolate mode? No phy attached and user wants to - * test loopback? Very odd, but can be correct. - */ + if (i == 33) { printk(KERN_INFO "%s: open: Could not find a valid PHY.\n", - pci_name(pci_dev)); - } - - if (i != 32) { - /* reset it */ - phy_init(dev); + pci_name(pci_dev)); + goto out_freering; } + + /* reset it */ + phy_init(dev); /* set default link speed settings */ np->linkspeed = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_10; @@ -2494,7 +3159,7 @@ out: static void __devexit nv_remove(struct pci_dev *pci_dev) { struct net_device *dev = pci_get_drvdata(pci_dev); - struct fe_priv *np = get_nvpriv(dev); + struct fe_priv *np = netdev_priv(dev); unregister_netdev(dev); @@ -2525,35 +3190,35 @@ static struct pci_device_id pci_tbl[] = { }, { /* nForce3 Ethernet Controller */ PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_4), - .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM, }, { /* nForce3 Ethernet Controller */ PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_5), - .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM, }, { /* nForce3 Ethernet Controller */ PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_6), - .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM, }, { /* nForce3 Ethernet Controller */ PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_7), - .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM, }, { /* 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_HIGH_DMA, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA, }, { /* 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_HIGH_DMA, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA, }, { /* 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_HIGH_DMA, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA, }, { /* 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_HIGH_DMA, + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA, }, { /* MCP51 Ethernet Controller */ PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_12), @@ -2565,11 +3230,11 @@ static struct pci_device_id pci_tbl[] = { }, { /* 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_HIGH_DMA, + .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, }, { /* 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_HIGH_DMA, + .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, }, {0,}, }; @@ -2595,6 +3260,14 @@ static void __exit exit_nic(void) module_param(max_interrupt_work, int, 0); MODULE_PARM_DESC(max_interrupt_work, "forcedeth maximum events handled per interrupt"); +module_param(optimization_mode, int, 0); +MODULE_PARM_DESC(optimization_mode, "In throughput mode (0), every tx & rx packet will generate an interrupt. In CPU mode (1), interrupts are controlled by a timer."); +module_param(poll_interval, int, 0); +MODULE_PARM_DESC(poll_interval, "Interval determines how frequent timer interrupt is generated by [(time_in_micro_secs * 100) / (2^10)]. Min is 0 and Max is 65535."); +module_param(disable_msi, int, 0); +MODULE_PARM_DESC(disable_msi, "Disable MSI interrupts by setting to 1."); +module_param(disable_msix, int, 0); +MODULE_PARM_DESC(disable_msix, "Disable MSIX interrupts by setting to 1."); MODULE_AUTHOR("Manfred Spraul "); MODULE_DESCRIPTION("Reverse Engineered nForce ethernet driver");