diff options
84 files changed, 2207 insertions, 642 deletions
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index fde510b..434224e 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -86,7 +86,7 @@ static int uml_net_rx(struct net_device *dev) drop_skb->dev = dev; /* Read a packet into drop_skb and don't do anything with it. */ (*lp->read)(lp->fd, drop_skb, lp); - lp->stats.rx_dropped++; + dev->stats.rx_dropped++; return 0; } @@ -99,8 +99,8 @@ static int uml_net_rx(struct net_device *dev) skb_trim(skb, pkt_len); skb->protocol = (*lp->protocol)(skb); - lp->stats.rx_bytes += skb->len; - lp->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; + dev->stats.rx_packets++; netif_rx(skb); return pkt_len; } @@ -224,8 +224,8 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) len = (*lp->write)(lp->fd, skb, lp); if (len == skb->len) { - lp->stats.tx_packets++; - lp->stats.tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; dev->trans_start = jiffies; netif_start_queue(dev); @@ -234,7 +234,7 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) } else if (len == 0) { netif_start_queue(dev); - lp->stats.tx_dropped++; + dev->stats.tx_dropped++; } else { netif_start_queue(dev); @@ -248,12 +248,6 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) return 0; } -static struct net_device_stats *uml_net_get_stats(struct net_device *dev) -{ - struct uml_net_private *lp = netdev_priv(dev); - return &lp->stats; -} - static void uml_net_set_multicast_list(struct net_device *dev) { return; @@ -377,6 +371,18 @@ static void net_device_release(struct device *dev) free_netdev(netdev); } +static const struct net_device_ops uml_netdev_ops = { + .ndo_open = uml_net_open, + .ndo_stop = uml_net_close, + .ndo_start_xmit = uml_net_start_xmit, + .ndo_set_multicast_list = uml_net_set_multicast_list, + .ndo_tx_timeout = uml_net_tx_timeout, + .ndo_set_mac_address = uml_net_set_mac, + .ndo_change_mtu = uml_net_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* * Ensures that platform_driver_register is called only once by * eth_configure. Will be set in an initcall. @@ -473,14 +479,7 @@ static void eth_configure(int n, void *init, char *mac, set_ether_mac(dev, device->mac); dev->mtu = transport->user->mtu; - dev->open = uml_net_open; - dev->hard_start_xmit = uml_net_start_xmit; - dev->stop = uml_net_close; - dev->get_stats = uml_net_get_stats; - dev->set_multicast_list = uml_net_set_multicast_list; - dev->tx_timeout = uml_net_tx_timeout; - dev->set_mac_address = uml_net_set_mac; - dev->change_mtu = uml_net_change_mtu; + dev->netdev_ops = ¨_netdev_ops; dev->ethtool_ops = ¨_net_ethtool_ops; dev->watchdog_timeo = (HZ >> 1); dev->irq = UM_ETH_IRQ; diff --git a/arch/um/include/shared/net_kern.h b/arch/um/include/shared/net_kern.h index d843c79..5c367f2 100644 --- a/arch/um/include/shared/net_kern.h +++ b/arch/um/include/shared/net_kern.h @@ -26,7 +26,7 @@ struct uml_net_private { spinlock_t lock; struct net_device *dev; struct timer_list tl; - struct net_device_stats stats; + struct work_struct work; int fd; unsigned char mac[ETH_ALEN]; diff --git a/drivers/net/3c503.c b/drivers/net/3c503.c index 5b91a85..4f08bd9 100644 --- a/drivers/net/3c503.c +++ b/drivers/net/3c503.c @@ -353,9 +353,6 @@ el2_probe1(struct net_device *dev, int ioaddr) dev->netdev_ops = &el2_netdev_ops; dev->ethtool_ops = &netdev_ethtool_ops; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = eip_poll; -#endif retval = register_netdev(dev); if (retval) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index e5ffc1c..f062b42 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -972,6 +972,14 @@ config ENC28J60_WRITEVERIFY Enable the verify after the buffer write useful for debugging purpose. If unsure, say N. +config ETHOC + tristate "OpenCores 10/100 Mbps Ethernet MAC support" + depends on NET_ETHERNET + select MII + select PHYLIB + help + Say Y here if you want to use the OpenCores 10/100 Mbps Ethernet MAC. + config SMC911X tristate "SMSC LAN911[5678] support" select CRC32 diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 758ecdf..98409c9 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -230,6 +230,7 @@ obj-$(CONFIG_PASEMI_MAC) += pasemi_mac_driver.o pasemi_mac_driver-objs := pasemi_mac.o pasemi_mac_ethtool.o obj-$(CONFIG_MLX4_CORE) += mlx4/ obj-$(CONFIG_ENC28J60) += enc28j60.o +obj-$(CONFIG_ETHOC) += ethoc.o obj-$(CONFIG_XTENSA_XT2000_SONIC) += xtsonic.o diff --git a/drivers/net/ac3200.c b/drivers/net/ac3200.c index 071a851..eac7338 100644 --- a/drivers/net/ac3200.c +++ b/drivers/net/ac3200.c @@ -143,6 +143,22 @@ out: } #endif +static const struct net_device_ops ac_netdev_ops = { + .ndo_open = ac_open, + .ndo_stop = ac_close_card, + + .ndo_start_xmit = ei_start_xmit, + .ndo_tx_timeout = ei_tx_timeout, + .ndo_get_stats = ei_get_stats, + .ndo_set_multicast_list = ei_set_multicast_list, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = eth_mac_addr, + .ndo_change_mtu = eth_change_mtu, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = ei_poll, +#endif +}; + static int __init ac_probe1(int ioaddr, struct net_device *dev) { int i, retval; @@ -253,11 +269,7 @@ static int __init ac_probe1(int ioaddr, struct net_device *dev) ei_status.block_output = &ac_block_output; ei_status.get_8390_hdr = &ac_get_8390_hdr; - dev->open = &ac_open; - dev->stop = &ac_close_card; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ei_poll; -#endif + dev->netdev_ops = &ac_netdev_ops; NS8390_init(dev, 0); retval = register_netdev(dev); diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index 54819a3..7f83254 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -171,7 +171,6 @@ static unsigned int cops_debug = COPS_DEBUG; struct cops_local { - struct net_device_stats stats; int board; /* Holds what board type is. */ int nodeid; /* Set to 1 once have nodeid. */ unsigned char node_acquire; /* Node ID when acquired. */ @@ -197,7 +196,6 @@ static int cops_send_packet (struct sk_buff *skb, struct net_device *dev); static void set_multicast_list (struct net_device *dev); static int cops_ioctl (struct net_device *dev, struct ifreq *rq, int cmd); static int cops_close (struct net_device *dev); -static struct net_device_stats *cops_get_stats (struct net_device *dev); static void cleanup_card(struct net_device *dev) { @@ -260,6 +258,15 @@ out: return ERR_PTR(err); } +static const struct net_device_ops cops_netdev_ops = { + .ndo_open = cops_open, + .ndo_stop = cops_close, + .ndo_start_xmit = cops_send_packet, + .ndo_tx_timeout = cops_timeout, + .ndo_do_ioctl = cops_ioctl, + .ndo_set_multicast_list = set_multicast_list, +}; + /* * This is the real probe routine. Linux has a history of friendly device * probes on the ISA bus. A good device probes avoids doing writes, and @@ -333,16 +340,9 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) /* Copy local board variable to lp struct. */ lp->board = board; - dev->hard_start_xmit = cops_send_packet; - dev->tx_timeout = cops_timeout; + dev->netdev_ops = &cops_netdev_ops; dev->watchdog_timeo = HZ * 2; - dev->get_stats = cops_get_stats; - dev->open = cops_open; - dev->stop = cops_close; - dev->do_ioctl = cops_ioctl; - dev->set_multicast_list = set_multicast_list; - dev->mc_list = NULL; /* Tell the user where the card is and what mode we're in. */ if(board==DAYNA) @@ -797,7 +797,7 @@ static void cops_rx(struct net_device *dev) { printk(KERN_WARNING "%s: Memory squeeze, dropping packet.\n", dev->name); - lp->stats.rx_dropped++; + dev->stats.rx_dropped++; while(pkt_len--) /* Discard packet */ inb(ioaddr); spin_unlock_irqrestore(&lp->lock, flags); @@ -819,7 +819,7 @@ static void cops_rx(struct net_device *dev) { printk(KERN_WARNING "%s: Bad packet length of %d bytes.\n", dev->name, pkt_len); - lp->stats.tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb_any(skb); return; } @@ -836,7 +836,7 @@ static void cops_rx(struct net_device *dev) if(rsp_type != LAP_RESPONSE) { printk(KERN_WARNING "%s: Bad packet type %d.\n", dev->name, rsp_type); - lp->stats.tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb_any(skb); return; } @@ -846,8 +846,8 @@ static void cops_rx(struct net_device *dev) skb_reset_transport_header(skb); /* Point to data (Skip header). */ /* Update the counters. */ - lp->stats.rx_packets++; - lp->stats.rx_bytes += skb->len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; /* Send packet to a higher place. */ netif_rx(skb); @@ -858,7 +858,7 @@ static void cops_timeout(struct net_device *dev) struct cops_local *lp = netdev_priv(dev); int ioaddr = dev->base_addr; - lp->stats.tx_errors++; + dev->stats.tx_errors++; if(lp->board==TANGENT) { if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0) @@ -916,8 +916,8 @@ static int cops_send_packet(struct sk_buff *skb, struct net_device *dev) spin_unlock_irqrestore(&lp->lock, flags); /* Restore interrupts. */ /* Done sending packet, update counters and cleanup. */ - lp->stats.tx_packets++; - lp->stats.tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; dev->trans_start = jiffies; dev_kfree_skb (skb); return 0; @@ -986,15 +986,6 @@ static int cops_close(struct net_device *dev) return 0; } -/* - * Get the current statistics. - * This may be called with the card open or closed. - */ -static struct net_device_stats *cops_get_stats(struct net_device *dev) -{ - struct cops_local *lp = netdev_priv(dev); - return &lp->stats; -} #ifdef MODULE static struct net_device *cops_dev; diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index dc4d496..78cc714 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -261,7 +261,6 @@ static unsigned char *ltdmacbuf; struct ltpc_private { - struct net_device_stats stats; struct atalk_addr my_addr; }; @@ -699,7 +698,6 @@ static int do_read(struct net_device *dev, void *cbuf, int cbuflen, static struct timer_list ltpc_timer; static int ltpc_xmit(struct sk_buff *skb, struct net_device *dev); -static struct net_device_stats *ltpc_get_stats(struct net_device *dev); static int read_30 ( struct net_device *dev) { @@ -726,8 +724,6 @@ static int sendup_buffer (struct net_device *dev) int dnode, snode, llaptype, len; int sklen; struct sk_buff *skb; - struct ltpc_private *ltpc_priv = netdev_priv(dev); - struct net_device_stats *stats = <pc_priv->stats; struct lt_rcvlap *ltc = (struct lt_rcvlap *) ltdmacbuf; if (ltc->command != LT_RCVLAP) { @@ -779,8 +775,8 @@ static int sendup_buffer (struct net_device *dev) skb_reset_transport_header(skb); - stats->rx_packets++; - stats->rx_bytes+=skb->len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; /* toss it onwards */ netif_rx(skb); @@ -904,10 +900,6 @@ static int ltpc_xmit(struct sk_buff *skb, struct net_device *dev) /* in kernel 1.3.xx, on entry skb->data points to ddp header, * and skb->len is the length of the ddp data + ddp header */ - - struct ltpc_private *ltpc_priv = netdev_priv(dev); - struct net_device_stats *stats = <pc_priv->stats; - int i; struct lt_sendlap cbuf; unsigned char *hdr; @@ -936,20 +928,13 @@ static int ltpc_xmit(struct sk_buff *skb, struct net_device *dev) printk("\n"); } - stats->tx_packets++; - stats->tx_bytes+=skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; dev_kfree_skb(skb); return 0; } -static struct net_device_stats *ltpc_get_stats(struct net_device *dev) -{ - struct ltpc_private *ltpc_priv = netdev_priv(dev); - struct net_device_stats *stats = <pc_priv->stats; - return stats; -} - /* initialization stuff */ static int __init ltpc_probe_dma(int base, int dma) @@ -1027,6 +1012,12 @@ static int __init ltpc_probe_dma(int base, int dma) return (want & 2) ? 3 : 1; } +static const struct net_device_ops ltpc_netdev = { + .ndo_start_xmit = ltpc_xmit, + .ndo_do_ioctl = ltpc_ioctl, + .ndo_set_multicast_list = set_multicast_list, +}; + struct net_device * __init ltpc_probe(void) { struct net_device *dev; @@ -1133,14 +1124,7 @@ struct net_device * __init ltpc_probe(void) else printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, DMA%d. Using polled mode.\n",io,dma); - /* Fill in the fields of the device structure with ethernet-generic values. */ - dev->hard_start_xmit = ltpc_xmit; - dev->get_stats = ltpc_get_stats; - - /* add the ltpc-specific things */ - dev->do_ioctl = <pc_ioctl; - - dev->set_multicast_list = &set_multicast_list; + dev->netdev_ops = <pc_netdev; dev->mc_list = NULL; dev->base_addr = io; dev->irq = irq; diff --git a/drivers/net/at1700.c b/drivers/net/at1700.c index ced7079..18b566a 100644 --- a/drivers/net/at1700.c +++ b/drivers/net/at1700.c @@ -249,6 +249,17 @@ out: return ERR_PTR(err); } +static const struct net_device_ops at1700_netdev_ops = { + .ndo_open = net_open, + .ndo_stop = net_close, + .ndo_start_xmit = net_send_packet, + .ndo_set_multicast_list = set_rx_mode, + .ndo_tx_timeout = net_tx_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* The Fujitsu datasheet suggests that the NIC be probed for by checking its "signature", the default bit pattern after a reset. This *doesn't* work -- there is no way to reset the bus interface without a complete power-cycle! @@ -448,13 +459,7 @@ found: if (net_debug) printk(version); - memset(lp, 0, sizeof(struct net_local)); - - dev->open = net_open; - dev->stop = net_close; - dev->hard_start_xmit = net_send_packet; - dev->set_multicast_list = &set_rx_mode; - dev->tx_timeout = net_tx_timeout; + dev->netdev_ops = &at1700_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; spin_lock_init(&lp->lock); diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index f901fee..9b75aa6 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -16,6 +16,7 @@ */ #include "be.h" +#include <asm/div64.h> MODULE_VERSION(DRV_VER); MODULE_DEVICE_TABLE(pci, be_dev_ids); @@ -290,6 +291,17 @@ static struct net_device_stats *be_get_stats(struct net_device *dev) return &adapter->stats.net_stats; } +static u32 be_calc_rate(u64 bytes, unsigned long ticks) +{ + u64 rate = bytes; + + do_div(rate, ticks / HZ); + rate <<= 3; /* bytes/sec -> bits/sec */ + do_div(rate, 1000000ul); /* MB/Sec */ + + return rate; +} + static void be_tx_rate_update(struct be_adapter *adapter) { struct be_drvr_stats *stats = drvr_stats(adapter); @@ -303,11 +315,9 @@ static void be_tx_rate_update(struct be_adapter *adapter) /* Update tx rate once in two seconds */ if ((now - stats->be_tx_jiffies) > 2 * HZ) { - u32 r; - r = (stats->be_tx_bytes - stats->be_tx_bytes_prev) / - ((now - stats->be_tx_jiffies) / HZ); - r = r / 1000000; /* M bytes/s */ - stats->be_tx_rate = r * 8; /* M bits/s */ + stats->be_tx_rate = be_calc_rate(stats->be_tx_bytes + - stats->be_tx_bytes_prev, + now - stats->be_tx_jiffies); stats->be_tx_jiffies = now; stats->be_tx_bytes_prev = stats->be_tx_bytes; } @@ -599,7 +609,6 @@ static void be_rx_rate_update(struct be_adapter *adapter) { struct be_drvr_stats *stats = drvr_stats(adapter); ulong now = jiffies; - u32 rate; /* Wrapped around */ if (time_before(now, stats->be_rx_jiffies)) { @@ -611,10 +620,9 @@ static void be_rx_rate_update(struct be_adapter *adapter) if ((now - stats->be_rx_jiffies) < 2 * HZ) return; - rate = (stats->be_rx_bytes - stats->be_rx_bytes_prev) / - ((now - stats->be_rx_jiffies) / HZ); - rate = rate / 1000000; /* MB/Sec */ - stats->be_rx_rate = rate * 8; /* Mega Bits/Sec */ + stats->be_rx_rate = be_calc_rate(stats->be_rx_bytes + - stats->be_rx_bytes_prev, + now - stats->be_rx_jiffies); stats->be_rx_jiffies = now; stats->be_rx_bytes_prev = stats->be_rx_bytes; } diff --git a/drivers/net/cs89x0.c b/drivers/net/cs89x0.c index ff64976..7433b88 100644 --- a/drivers/net/cs89x0.c +++ b/drivers/net/cs89x0.c @@ -501,6 +501,21 @@ static void net_poll_controller(struct net_device *dev) } #endif +static const struct net_device_ops net_ops = { + .ndo_open = net_open, + .ndo_stop = net_close, + .ndo_tx_timeout = net_timeout, + .ndo_start_xmit = net_send_packet, + .ndo_get_stats = net_get_stats, + .ndo_set_multicast_list = set_multicast_list, + .ndo_set_mac_address = set_mac_address, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = net_poll_controller, +#endif + .ndo_change_mtu = eth_change_mtu, + .ndo_validate_addr = eth_validate_addr, +}; + /* This is the real probe routine. Linux has a history of friendly device probes on the ISA bus. A good device probes avoids doing writes, and verifies that the correct device exists and functions. @@ -843,17 +858,8 @@ cs89x0_probe1(struct net_device *dev, int ioaddr, int modular) /* print the ethernet address. */ printk(", MAC %pM", dev->dev_addr); - dev->open = net_open; - dev->stop = net_close; - dev->tx_timeout = net_timeout; - dev->watchdog_timeo = HZ; - dev->hard_start_xmit = net_send_packet; - dev->get_stats = net_get_stats; - dev->set_multicast_list = set_multicast_list; - dev->set_mac_address = set_mac_address; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = net_poll_controller; -#endif + dev->netdev_ops = &net_ops; + dev->watchdog_timeo = HZ; printk("\n"); if (net_debug) diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h index 71eaa43..714df2b 100644 --- a/drivers/net/cxgb3/adapter.h +++ b/drivers/net/cxgb3/adapter.h @@ -85,6 +85,8 @@ struct fl_pg_chunk { struct page *page; void *va; unsigned int offset; + u64 *p_cnt; + DECLARE_PCI_UNMAP_ADDR(mapping); }; struct rx_desc; @@ -101,6 +103,7 @@ struct sge_fl { /* SGE per free-buffer list state */ struct fl_pg_chunk pg_chunk;/* page chunk cache */ unsigned int use_pages; /* whether FL uses pages or sk_buffs */ unsigned int order; /* order of page allocations */ + unsigned int alloc_size; /* size of allocated buffer */ struct rx_desc *desc; /* address of HW Rx descriptor ring */ struct rx_sw_desc *sdesc; /* address of SW Rx descriptor ring */ dma_addr_t phys_addr; /* physical address of HW ring start */ @@ -291,6 +294,7 @@ void t3_os_link_fault_handler(struct adapter *adapter, int port_id); void t3_sge_start(struct adapter *adap); void t3_sge_stop(struct adapter *adap); +void t3_start_sge_timers(struct adapter *adap); void t3_stop_sge_timers(struct adapter *adap); void t3_free_sge_resources(struct adapter *adap); void t3_sge_err_intr_handler(struct adapter *adapter); diff --git a/drivers/net/cxgb3/common.h b/drivers/net/cxgb3/common.h index 9ee021e..e508dc3 100644 --- a/drivers/net/cxgb3/common.h +++ b/drivers/net/cxgb3/common.h @@ -191,7 +191,8 @@ struct mdio_ops { }; struct adapter_info { - unsigned char nports; /* # of ports */ + unsigned char nports0; /* # of ports on channel 0 */ + unsigned char nports1; /* # of ports on channel 1 */ unsigned char phy_base_addr; /* MDIO PHY base address */ unsigned int gpio_out; /* GPIO output settings */ unsigned char gpio_intr[MAX_NPORTS]; /* GPIO PHY IRQ pins */ @@ -422,6 +423,7 @@ struct adapter_params { unsigned short b_wnd[NCCTRL_WIN]; unsigned int nports; /* # of ethernet ports */ + unsigned int chan_map; /* bitmap of in-use Tx channels */ unsigned int stats_update_period; /* MAC stats accumulation period */ unsigned int linkpoll_period; /* link poll period in 0.1s */ unsigned int rev; /* chip revision */ diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c index d8be896..2c2aaa7 100644 --- a/drivers/net/cxgb3/cxgb3_main.c +++ b/drivers/net/cxgb3/cxgb3_main.c @@ -602,7 +602,6 @@ static int setup_sge_qsets(struct adapter *adap) &adap->params.sge.qset[qset_idx], ntxq, dev, netdev_get_tx_queue(dev, j)); if (err) { - t3_stop_sge_timers(adap); t3_free_sge_resources(adap); return err; } @@ -1046,6 +1045,8 @@ static int cxgb_up(struct adapter *adap) setup_rss(adap); if (!(adap->flags & NAPI_INIT)) init_napi(adap); + + t3_start_sge_timers(adap); adap->flags |= FULL_INIT_DONE; } @@ -2870,6 +2871,9 @@ static void t3_io_resume(struct pci_dev *pdev) { struct adapter *adapter = pci_get_drvdata(pdev); + CH_ALERT(adapter, "adapter recovering, PEX ERR 0x%x\n", + t3_read_reg(adapter, A_PCIE_PEX_ERR)); + t3_resume_ports(adapter); } @@ -3002,7 +3006,7 @@ static int __devinit init_one(struct pci_dev *pdev, static int version_printed; int i, err, pci_using_dac = 0; - unsigned long mmio_start, mmio_len; + resource_size_t mmio_start, mmio_len; const struct adapter_info *ai; struct adapter *adapter = NULL; struct port_info *pi; @@ -3082,7 +3086,7 @@ static int __devinit init_one(struct pci_dev *pdev, INIT_WORK(&adapter->fatal_error_handler_task, fatal_error_task); INIT_DELAYED_WORK(&adapter->adap_check_task, t3_adap_check_task); - for (i = 0; i < ai->nports; ++i) { + for (i = 0; i < ai->nports0 + ai->nports1; ++i) { struct net_device *netdev; netdev = alloc_etherdev_mq(sizeof(struct port_info), SGE_QSETS); @@ -3172,7 +3176,7 @@ static int __devinit init_one(struct pci_dev *pdev, out_free_dev: iounmap(adapter->regs); - for (i = ai->nports - 1; i >= 0; --i) + for (i = ai->nports0 + ai->nports1 - 1; i >= 0; --i) if (adapter->port[i]) free_netdev(adapter->port[i]); diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c index a7555cb..26d3587 100644 --- a/drivers/net/cxgb3/sge.c +++ b/drivers/net/cxgb3/sge.c @@ -50,6 +50,7 @@ #define SGE_RX_COPY_THRES 256 #define SGE_RX_PULL_LEN 128 +#define SGE_PG_RSVD SMP_CACHE_BYTES /* * Page chunk size for FL0 buffers if FL0 is to be populated with page chunks. * It must be a divisor of PAGE_SIZE. If set to 0 FL0 will use sk_buffs @@ -57,8 +58,10 @@ */ #define FL0_PG_CHUNK_SIZE 2048 #define FL0_PG_ORDER 0 +#define FL0_PG_ALLOC_SIZE (PAGE_SIZE << FL0_PG_ORDER) #define FL1_PG_CHUNK_SIZE (PAGE_SIZE > 8192 ? 16384 : 8192) #define FL1_PG_ORDER (PAGE_SIZE > 8192 ? 0 : 1) +#define FL1_PG_ALLOC_SIZE (PAGE_SIZE << FL1_PG_ORDER) #define SGE_RX_DROP_THRES 16 #define RX_RECLAIM_PERIOD (HZ/4) @@ -345,13 +348,21 @@ static inline int should_restart_tx(const struct sge_txq *q) return q->in_use - r < (q->size >> 1); } -static void clear_rx_desc(const struct sge_fl *q, struct rx_sw_desc *d) +static void clear_rx_desc(struct pci_dev *pdev, const struct sge_fl *q, + struct rx_sw_desc *d) { - if (q->use_pages) { - if (d->pg_chunk.page) - put_page(d->pg_chunk.page); + if (q->use_pages && d->pg_chunk.page) { + (*d->pg_chunk.p_cnt)--; + if (!*d->pg_chunk.p_cnt) + pci_unmap_page(pdev, + pci_unmap_addr(&d->pg_chunk, mapping), + q->alloc_size, PCI_DMA_FROMDEVICE); + + put_page(d->pg_chunk.page); d->pg_chunk.page = NULL; } else { + pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr), + q->buf_size, PCI_DMA_FROMDEVICE); kfree_skb(d->skb); d->skb = NULL; } @@ -372,9 +383,8 @@ static void free_rx_bufs(struct pci_dev *pdev, struct sge_fl *q) while (q->credits--) { struct rx_sw_desc *d = &q->sdesc[cidx]; - pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr), - q->buf_size, PCI_DMA_FROMDEVICE); - clear_rx_desc(q, d); + + clear_rx_desc(pdev, q, d); if (++cidx == q->size) cidx = 0; } @@ -417,18 +427,39 @@ static inline int add_one_rx_buf(void *va, unsigned int len, return 0; } -static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp, +static inline int add_one_rx_chunk(dma_addr_t mapping, struct rx_desc *d, + unsigned int gen) +{ + d->addr_lo = cpu_to_be32(mapping); + d->addr_hi = cpu_to_be32((u64) mapping >> 32); + wmb(); + d->len_gen = cpu_to_be32(V_FLD_GEN1(gen)); + d->gen2 = cpu_to_be32(V_FLD_GEN2(gen)); + return 0; +} + +static int alloc_pg_chunk(struct adapter *adapter, struct sge_fl *q, + struct rx_sw_desc *sd, gfp_t gfp, unsigned int order) { if (!q->pg_chunk.page) { + dma_addr_t mapping; + q->pg_chunk.page = alloc_pages(gfp, order); if (unlikely(!q->pg_chunk.page)) return -ENOMEM; q->pg_chunk.va = page_address(q->pg_chunk.page); + q->pg_chunk.p_cnt = q->pg_chunk.va + (PAGE_SIZE << order) - + SGE_PG_RSVD; q->pg_chunk.offset = 0; + mapping = pci_map_page(adapter->pdev, q->pg_chunk.page, + 0, q->alloc_size, PCI_DMA_FROMDEVICE); + pci_unmap_addr_set(&q->pg_chunk, mapping, mapping); } sd->pg_chunk = q->pg_chunk; + prefetch(sd->pg_chunk.p_cnt); + q->pg_chunk.offset += q->buf_size; if (q->pg_chunk.offset == (PAGE_SIZE << order)) q->pg_chunk.page = NULL; @@ -436,6 +467,12 @@ static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp, q->pg_chunk.va += q->buf_size; get_page(q->pg_chunk.page); } + + if (sd->pg_chunk.offset == 0) + *sd->pg_chunk.p_cnt = 1; + else + *sd->pg_chunk.p_cnt += 1; + return 0; } @@ -460,35 +497,43 @@ static inline void ring_fl_db(struct adapter *adap, struct sge_fl *q) */ static int refill_fl(struct adapter *adap, struct sge_fl *q, int n, gfp_t gfp) { - void *buf_start; struct rx_sw_desc *sd = &q->sdesc[q->pidx]; struct rx_desc *d = &q->desc[q->pidx]; unsigned int count = 0; while (n--) { + dma_addr_t mapping; int err; if (q->use_pages) { - if (unlikely(alloc_pg_chunk(q, sd, gfp, q->order))) { + if (unlikely(alloc_pg_chunk(adap, q, sd, gfp, + q->order))) { nomem: q->alloc_failed++; break; } - buf_start = sd->pg_chunk.va; + mapping = pci_unmap_addr(&sd->pg_chunk, mapping) + + sd->pg_chunk.offset; + pci_unmap_addr_set(sd, dma_addr, mapping); + + add_one_rx_chunk(mapping, d, q->gen); + pci_dma_sync_single_for_device(adap->pdev, mapping, + q->buf_size - SGE_PG_RSVD, + PCI_DMA_FROMDEVICE); } else { - struct sk_buff *skb = alloc_skb(q->buf_size, gfp); + void *buf_start; + struct sk_buff *skb = alloc_skb(q->buf_size, gfp); if (!skb) goto nomem; sd->skb = skb; buf_start = skb->data; - } - - err = add_one_rx_buf(buf_start, q->buf_size, d, sd, q->gen, - adap->pdev); - if (unlikely(err)) { - clear_rx_desc(q, sd); - break; + err = add_one_rx_buf(buf_start, q->buf_size, d, sd, + q->gen, adap->pdev); + if (unlikely(err)) { + clear_rx_desc(adap->pdev, q, sd); + break; + } } d++; @@ -795,19 +840,19 @@ static struct sk_buff *get_packet_pg(struct adapter *adap, struct sge_fl *fl, struct sk_buff *newskb, *skb; struct rx_sw_desc *sd = &fl->sdesc[fl->cidx]; - newskb = skb = q->pg_skb; + dma_addr_t dma_addr = pci_unmap_addr(sd, dma_addr); + newskb = skb = q->pg_skb; if (!skb && (len <= SGE_RX_COPY_THRES)) { newskb = alloc_skb(len, GFP_ATOMIC); if (likely(newskb != NULL)) { __skb_put(newskb, len); - pci_dma_sync_single_for_cpu(adap->pdev, - pci_unmap_addr(sd, dma_addr), len, + pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len, PCI_DMA_FROMDEVICE); memcpy(newskb->data, sd->pg_chunk.va, len); - pci_dma_sync_single_for_device(adap->pdev, - pci_unmap_addr(sd, dma_addr), len, - PCI_DMA_FROMDEVICE); + pci_dma_sync_single_for_device(adap->pdev, dma_addr, + len, + PCI_DMA_FROMDEVICE); } else if (!drop_thres) return NULL; recycle: @@ -820,16 +865,25 @@ recycle: if (unlikely(q->rx_recycle_buf || (!skb && fl->credits <= drop_thres))) goto recycle; + prefetch(sd->pg_chunk.p_cnt); + if (!skb) newskb = alloc_skb(SGE_RX_PULL_LEN, GFP_ATOMIC); + if (unlikely(!newskb)) { if (!drop_thres) return NULL; goto recycle; } - pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr), - fl->buf_size, PCI_DMA_FROMDEVICE); + pci_dma_sync_single_for_cpu(adap->pdev, dma_addr, len, + PCI_DMA_FROMDEVICE); + (*sd->pg_chunk.p_cnt)--; + if (!*sd->pg_chunk.p_cnt) + pci_unmap_page(adap->pdev, + pci_unmap_addr(&sd->pg_chunk, mapping), + fl->alloc_size, + PCI_DMA_FROMDEVICE); if (!skb) { __skb_put(newskb, SGE_RX_PULL_LEN); memcpy(newskb->data, sd->pg_chunk.va, SGE_RX_PULL_LEN); @@ -1089,7 +1143,7 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb, struct tx_desc *d = &q->desc[pidx]; struct cpl_tx_pkt *cpl = (struct cpl_tx_pkt *)d; - cpl->len = htonl(skb->len | 0x80000000); + cpl->len = htonl(skb->len); cntrl = V_TXPKT_INTF(pi->port_id); if (vlan_tx_tag_present(skb) && pi->vlan_grp) @@ -1958,8 +2012,8 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq, skb_pull(skb, sizeof(*p) + pad); skb->protocol = eth_type_trans(skb, adap->port[p->iff]); pi = netdev_priv(skb->dev); - if ((pi->rx_offload & T3_RX_CSUM) && p->csum_valid && p->csum == htons(0xffff) && - !p->fragment) { + if ((pi->rx_offload & T3_RX_CSUM) && p->csum_valid && + p->csum == htons(0xffff) && !p->fragment) { qs->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++; skb->ip_summed = CHECKSUM_UNNECESSARY; } else @@ -2034,10 +2088,19 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, fl->credits--; len -= offset; - pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr), - fl->buf_size, PCI_DMA_FROMDEVICE); + pci_dma_sync_single_for_cpu(adap->pdev, + pci_unmap_addr(sd, dma_addr), + fl->buf_size - SGE_PG_RSVD, + PCI_DMA_FROMDEVICE); - prefetch(&qs->lro_frag_tbl); + (*sd->pg_chunk.p_cnt)--; + if (!*sd->pg_chunk.p_cnt) + pci_unmap_page(adap->pdev, + pci_unmap_addr(&sd->pg_chunk, mapping), + fl->alloc_size, + PCI_DMA_FROMDEVICE); + + prefetch(qs->lro_va); rx_frag += nr_frags; rx_frag->page = sd->pg_chunk.page; @@ -2047,6 +2110,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, qs->lro_frag_tbl.nr_frags++; qs->lro_frag_tbl.len = frag_len; + if (!complete) return; @@ -2236,6 +2300,8 @@ no_mem: if (fl->use_pages) { void *addr = fl->sdesc[fl->cidx].pg_chunk.va; + prefetch(&qs->lro_frag_tbl); + prefetch(addr); #if L1_CACHE_BYTES < 128 prefetch(addr + L1_CACHE_BYTES); @@ -2972,21 +3038,23 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports, q->fl[1].use_pages = FL1_PG_CHUNK_SIZE > 0; q->fl[0].order = FL0_PG_ORDER; q->fl[1].order = FL1_PG_ORDER; + q->fl[0].alloc_size = FL0_PG_ALLOC_SIZE; + q->fl[1].alloc_size = FL1_PG_ALLOC_SIZE; spin_lock_irq(&adapter->sge.reg_lock); /* FL threshold comparison uses < */ ret = t3_sge_init_rspcntxt(adapter, q->rspq.cntxt_id, irq_vec_idx, q->rspq.phys_addr, q->rspq.size, - q->fl[0].buf_size, 1, 0); + q->fl[0].buf_size - SGE_PG_RSVD, 1, 0); if (ret) goto err_unlock; for (i = 0; i < SGE_RXQ_PER_SET; ++i) { ret = t3_sge_init_flcntxt(adapter, q->fl[i].cntxt_id, 0, q->fl[i].phys_addr, q->fl[i].size, - q->fl[i].buf_size, p->cong_thres, 1, - 0); + q->fl[i].buf_size - SGE_PG_RSVD, + p->cong_thres, 1, 0); if (ret) goto err_unlock; } @@ -3044,9 +3112,6 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports, t3_write_reg(adapter, A_SG_GTS, V_RSPQ(q->rspq.cntxt_id) | V_NEWTIMER(q->rspq.holdoff_tmr)); - mod_timer(&q->tx_reclaim_timer, jiffies + TX_RECLAIM_PERIOD); - mod_timer(&q->rx_reclaim_timer, jiffies + RX_RECLAIM_PERIOD); - return 0; err_unlock: @@ -3057,6 +3122,27 @@ err: } /** + * t3_start_sge_timers - start SGE timer call backs + * @adap: the adapter + * + * Starts each SGE queue set's timer call back + */ +void t3_start_sge_timers(struct adapter *adap) +{ + int i; + + for (i = 0; i < SGE_QSETS; ++i) { + struct sge_qset *q = &adap->sge.qs[i]; + + if (q->tx_reclaim_timer.function) + mod_timer(&q->tx_reclaim_timer, jiffies + TX_RECLAIM_PERIOD); + + if (q->rx_reclaim_timer.function) + mod_timer(&q->rx_reclaim_timer, jiffies + RX_RECLAIM_PERIOD); + } +} + +/** * t3_stop_sge_timers - stop SGE timer call backs * @adap: the adapter * diff --git a/drivers/net/cxgb3/t3_hw.c b/drivers/net/cxgb3/t3_hw.c index ff262a0..31ed31a 100644 --- a/drivers/net/cxgb3/t3_hw.c +++ b/drivers/net/cxgb3/t3_hw.c @@ -493,20 +493,20 @@ int t3_phy_lasi_intr_handler(struct cphy *phy) } static const struct adapter_info t3_adap_info[] = { - {2, 0, + {1, 1, 0, F_GPIO2_OEN | F_GPIO4_OEN | F_GPIO2_OUT_VAL | F_GPIO4_OUT_VAL, { S_GPIO3, S_GPIO5 }, 0, &mi1_mdio_ops, "Chelsio PE9000"}, - {2, 0, + {1, 1, 0, F_GPIO2_OEN | F_GPIO4_OEN | F_GPIO2_OUT_VAL | F_GPIO4_OUT_VAL, { S_GPIO3, S_GPIO5 }, 0, &mi1_mdio_ops, "Chelsio T302"}, - {1, 0, + {1, 0, 0, F_GPIO1_OEN | F_GPIO6_OEN | F_GPIO7_OEN | F_GPIO10_OEN | F_GPIO11_OEN | F_GPIO1_OUT_VAL | F_GPIO6_OUT_VAL | F_GPIO10_OUT_VAL, { 0 }, SUPPORTED_10000baseT_Full | SUPPORTED_AUI, &mi1_mdio_ext_ops, "Chelsio T310"}, - {2, 0, + {1, 1, 0, F_GPIO1_OEN | F_GPIO2_OEN | F_GPIO4_OEN | F_GPIO5_OEN | F_GPIO6_OEN | F_GPIO7_OEN | F_GPIO10_OEN | F_GPIO11_OEN | F_GPIO1_OUT_VAL | F_GPIO5_OUT_VAL | F_GPIO6_OUT_VAL | F_GPIO10_OUT_VAL, @@ -514,7 +514,7 @@ static const struct adapter_info t3_adap_info[] = { &mi1_mdio_ext_ops, "Chelsio T320"}, {}, {}, - {1, 0, + {1, 0, 0, F_GPIO1_OEN | F_GPIO2_OEN | F_GPIO4_OEN | F_GPIO6_OEN | F_GPIO7_OEN | F_GPIO10_OEN | F_GPIO1_OUT_VAL | F_GPIO6_OUT_VAL | F_GPIO10_OUT_VAL, { S_GPIO9 }, SUPPORTED_10000baseT_Full | SUPPORTED_AUI, @@ -2128,16 +2128,40 @@ void t3_port_intr_clear(struct adapter *adapter, int idx) static int t3_sge_write_context(struct adapter *adapter, unsigned int id, unsigned int type) { - t3_write_reg(adapter, A_SG_CONTEXT_MASK0, 0xffffffff); - t3_write_reg(adapter, A_SG_CONTEXT_MASK1, 0xffffffff); - t3_write_reg(adapter, A_SG_CONTEXT_MASK2, 0xffffffff); - t3_write_reg(adapter, A_SG_CONTEXT_MASK3, 0xffffffff); + if (type == F_RESPONSEQ) { + /* + * Can't write the Response Queue Context bits for + * Interrupt Armed or the Reserve bits after the chip + * has been initialized out of reset. Writing to these + * bits can confuse the hardware. + */ + t3_write_reg(adapter, A_SG_CONTEXT_MASK0, 0xffffffff); + t3_write_reg(adapter, A_SG_CONTEXT_MASK1, 0xffffffff); + t3_write_reg(adapter, A_SG_CONTEXT_MASK2, 0x17ffffff); + t3_write_reg(adapter, A_SG_CONTEXT_MASK3, 0xffffffff); + } else { + t3_write_reg(adapter, A_SG_CONTEXT_MASK0, 0xffffffff); + t3_write_reg(adapter, A_SG_CONTEXT_MASK1, 0xffffffff); + t3_write_reg(adapter, A_SG_CONTEXT_MASK2, 0xffffffff); + t3_write_reg(adapter, A_SG_CONTEXT_MASK3, 0xffffffff); + } t3_write_reg(adapter, A_SG_CONTEXT_CMD, V_CONTEXT_CMD_OPCODE(1) | type | V_CONTEXT(id)); return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY, 0, SG_CONTEXT_CMD_ATTEMPTS, 1); } +/** + * clear_sge_ctxt - completely clear an SGE context + * @adapter: the adapter + * @id: the context id + * @type: the context type + * + * Completely clear an SGE context. Used predominantly at post-reset + * initialization. Note in particular that we don't skip writing to any + * "sensitive bits" in the contexts the way that t3_sge_write_context() + * does ... + */ static int clear_sge_ctxt(struct adapter *adap, unsigned int id, unsigned int type) { @@ -2145,7 +2169,14 @@ static int clear_sge_ctxt(struct adapter *adap, unsigned int id, t3_write_reg(adap, A_SG_CONTEXT_DATA1, 0); t3_write_reg(adap, A_SG_CONTEXT_DATA2, 0); t3_write_reg(adap, A_SG_CONTEXT_DATA3, 0); - return t3_sge_write_context(adap, id, type); + t3_write_reg(adap, A_SG_CONTEXT_MASK0, 0xffffffff); + t3_write_reg(adap, A_SG_CONTEXT_MASK1, 0xffffffff); + t3_write_reg(adap, A_SG_CONTEXT_MASK2, 0xffffffff); + t3_write_reg(adap, A_SG_CONTEXT_MASK3, 0xffffffff); + t3_write_reg(adap, A_SG_CONTEXT_CMD, + V_CONTEXT_CMD_OPCODE(1) | type | V_CONTEXT(id)); + return t3_wait_op_done(adap, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY, + 0, SG_CONTEXT_CMD_ATTEMPTS, 1); } /** @@ -2729,10 +2760,10 @@ static void tp_config(struct adapter *adap, const struct tp_params *p) F_TCPCHECKSUMOFFLOAD | V_IPTTL(64)); t3_write_reg(adap, A_TP_TCP_OPTIONS, V_MTUDEFAULT(576) | F_MTUENABLE | V_WINDOWSCALEMODE(1) | - V_TIMESTAMPSMODE(0) | V_SACKMODE(1) | V_SACKRX(1)); + V_TIMESTAMPSMODE(1) | V_SACKMODE(1) | V_SACKRX(1)); t3_write_reg(adap, A_TP_DACK_CONFIG, V_AUTOSTATE3(1) | V_AUTOSTATE2(1) | V_AUTOSTATE1(0) | - V_BYTETHRESHOLD(16384) | V_MSSTHRESHOLD(2) | + V_BYTETHRESHOLD(26880) | V_MSSTHRESHOLD(2) | F_AUTOCAREFUL | F_AUTOENABLE | V_DACK_MODE(1)); t3_set_reg_field(adap, A_TP_IN_CONFIG, F_RXFBARBPRIO | F_TXFBARBPRIO, F_IPV6ENABLE | F_NICMODE); @@ -3196,20 +3227,22 @@ int t3_mps_set_active_ports(struct adapter *adap, unsigned int port_mask) } /* - * Perform the bits of HW initialization that are dependent on the number - * of available ports. + * Perform the bits of HW initialization that are dependent on the Tx + * channels being used. */ -static void init_hw_for_avail_ports(struct adapter *adap, int nports) +static void chan_init_hw(struct adapter *adap, unsigned int chan_map) { int i; - if (nports == 1) { + if (chan_map != 3) { /* one channel */ t3_set_reg_field(adap, A_ULPRX_CTL, F_ROUND_ROBIN, 0); t3_set_reg_field(adap, A_ULPTX_CONFIG, F_CFG_RR_ARB, 0); - t3_write_reg(adap, A_MPS_CFG, F_TPRXPORTEN | F_TPTXPORT0EN | - F_PORT0ACTIVE | F_ENFORCEPKT); - t3_write_reg(adap, A_PM1_TX_CFG, 0xffffffff); - } else { + t3_write_reg(adap, A_MPS_CFG, F_TPRXPORTEN | F_ENFORCEPKT | + (chan_map == 1 ? F_TPTXPORT0EN | F_PORT0ACTIVE : + F_TPTXPORT1EN | F_PORT1ACTIVE)); + t3_write_reg(adap, A_PM1_TX_CFG, + chan_map == 1 ? 0xffffffff : 0); + } else { /* two channels */ t3_set_reg_field(adap, A_ULPRX_CTL, 0, F_ROUND_ROBIN); t3_set_reg_field(adap, A_ULPTX_CONFIG, 0, F_CFG_RR_ARB); t3_write_reg(adap, A_ULPTX_DMA_WEIGHT, @@ -3517,7 +3550,7 @@ int t3_init_hw(struct adapter *adapter, u32 fw_params) t3_write_reg(adapter, A_PM1_RX_CFG, 0xffffffff); t3_write_reg(adapter, A_PM1_RX_MODE, 0); t3_write_reg(adapter, A_PM1_TX_MODE, 0); - init_hw_for_avail_ports(adapter, adapter->params.nports); + chan_init_hw(adapter, adapter->params.chan_map); t3_sge_init(adapter, &adapter->params.sge); t3_write_reg(adapter, A_T3DBG_GPIO_ACT_LOW, calc_gpio_intr(adapter)); @@ -3754,7 +3787,8 @@ int t3_prep_adapter(struct adapter *adapter, const struct adapter_info *ai, get_pci_mode(adapter, &adapter->params.pci); adapter->params.info = ai; - adapter->params.nports = ai->nports; + adapter->params.nports = ai->nports0 + ai->nports1; + adapter->params.chan_map = !!ai->nports0 | (!!ai->nports1 << 1); adapter->params.rev = t3_read_reg(adapter, A_PL_REV); /* * We used to only run the "adapter check task" once a second if @@ -3785,7 +3819,7 @@ int t3_prep_adapter(struct adapter *adapter, const struct adapter_info *ai, mc7_prep(adapter, &adapter->pmtx, MC7_PMTX_BASE_ADDR, "PMTX"); mc7_prep(adapter, &adapter->cm, MC7_CM_BASE_ADDR, "CM"); - p->nchan = ai->nports; + p->nchan = adapter->params.chan_map == 3 ? 2 : 1; p->pmrx_size = t3_mc7_size(&adapter->pmrx); p->pmtx_size = t3_mc7_size(&adapter->pmtx); p->cm_size = t3_mc7_size(&adapter->cm); diff --git a/drivers/net/depca.c b/drivers/net/depca.c index 55625db..357f565 100644 --- a/drivers/net/depca.c +++ b/drivers/net/depca.c @@ -566,6 +566,18 @@ MODULE_LICENSE("GPL"); outw(CSR0, DEPCA_ADDR);\ outw(STOP, DEPCA_DATA) +static const struct net_device_ops depca_netdev_ops = { + .ndo_open = depca_open, + .ndo_start_xmit = depca_start_xmit, + .ndo_stop = depca_close, + .ndo_set_multicast_list = set_multicast_list, + .ndo_do_ioctl = depca_ioctl, + .ndo_tx_timeout = depca_tx_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __init depca_hw_init (struct net_device *dev, struct device *device) { struct depca_private *lp; @@ -793,12 +805,7 @@ static int __init depca_hw_init (struct net_device *dev, struct device *device) } /* The DEPCA-specific entries in the device structure. */ - dev->open = &depca_open; - dev->hard_start_xmit = &depca_start_xmit; - dev->stop = &depca_close; - dev->set_multicast_list = &set_multicast_list; - dev->do_ioctl = &depca_ioctl; - dev->tx_timeout = depca_tx_timeout; + dev->netdev_ops = &depca_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; dev->mem_start = 0; diff --git a/drivers/net/eepro.c b/drivers/net/eepro.c index e187c88..cc2ab64 100644 --- a/drivers/net/eepro.c +++ b/drivers/net/eepro.c @@ -739,6 +739,17 @@ static void __init eepro_print_info (struct net_device *dev) static const struct ethtool_ops eepro_ethtool_ops; +static const struct net_device_ops eepro_netdev_ops = { + .ndo_open = eepro_open, + .ndo_stop = eepro_close, + .ndo_start_xmit = eepro_send_packet, + .ndo_set_multicast_list = set_multicast_list, + .ndo_tx_timeout = eepro_tx_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* This is the real probe routine. Linux has a history of friendly device probes on the ISA bus. A good device probe avoids doing writes, and verifies that the correct device exists and functions. */ @@ -851,11 +862,7 @@ static int __init eepro_probe1(struct net_device *dev, int autoprobe) } } - dev->open = eepro_open; - dev->stop = eepro_close; - dev->hard_start_xmit = eepro_send_packet; - dev->set_multicast_list = &set_multicast_list; - dev->tx_timeout = eepro_tx_timeout; + dev->netdev_ops = &eepro_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; dev->ethtool_ops = &eepro_ethtool_ops; diff --git a/drivers/net/eexpress.c b/drivers/net/eexpress.c index 9ff3f2f..1686dca 100644 --- a/drivers/net/eexpress.c +++ b/drivers/net/eexpress.c @@ -1043,6 +1043,17 @@ static void eexp_hw_tx_pio(struct net_device *dev, unsigned short *buf, lp->last_tx = jiffies; } +static const struct net_device_ops eexp_netdev_ops = { + .ndo_open = eexp_open, + .ndo_stop = eexp_close, + .ndo_start_xmit = eexp_xmit, + .ndo_set_multicast_list = eexp_set_multicast, + .ndo_tx_timeout = eexp_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* * Sanity check the suspected EtherExpress card * Read hardware address, reset card, size memory and initialize buffer @@ -1163,11 +1174,7 @@ static int __init eexp_hw_probe(struct net_device *dev, unsigned short ioaddr) lp->rx_buf_start = TX_BUF_START + (lp->num_tx_bufs*TX_BUF_SIZE); lp->width = buswidth; - dev->open = eexp_open; - dev->stop = eexp_close; - dev->hard_start_xmit = eexp_xmit; - dev->set_multicast_list = &eexp_set_multicast; - dev->tx_timeout = eexp_timeout; + dev->netdev_ops = &eexp_netdev_ops; dev->watchdog_timeo = 2*HZ; return register_netdev(dev); diff --git a/drivers/net/eth16i.c b/drivers/net/eth16i.c index 5c048f2..0d8b6da 100644 --- a/drivers/net/eth16i.c +++ b/drivers/net/eth16i.c @@ -475,6 +475,17 @@ out: } #endif +static const struct net_device_ops eth16i_netdev_ops = { + .ndo_open = eth16i_open, + .ndo_stop = eth16i_close, + .ndo_start_xmit = eth16i_tx, + .ndo_set_multicast_list = eth16i_multicast, + .ndo_tx_timeout = eth16i_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __init eth16i_probe1(struct net_device *dev, int ioaddr) { struct eth16i_local *lp = netdev_priv(dev); @@ -549,12 +560,7 @@ static int __init eth16i_probe1(struct net_device *dev, int ioaddr) BITCLR(ioaddr + CONFIG_REG_1, POWERUP); /* Initialize the device structure */ - memset(lp, 0, sizeof(struct eth16i_local)); - dev->open = eth16i_open; - dev->stop = eth16i_close; - dev->hard_start_xmit = eth16i_tx; - dev->set_multicast_list = eth16i_multicast; - dev->tx_timeout = eth16i_timeout; + dev->netdev_ops = ð16i_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; spin_lock_init(&lp->lock); diff --git a/drivers/net/ethoc.c b/drivers/net/ethoc.c new file mode 100644 index 0000000..91a9b1a --- /dev/null +++ b/drivers/net/ethoc.c @@ -0,0 +1,1112 @@ +/* + * linux/drivers/net/ethoc.c + * + * Copyright (C) 2007-2008 Avionic Design Development GmbH + * Copyright (C) 2008-2009 Avionic Design GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Written by Thierry Reding <thierry.reding@avionic-design.de> + */ + +#include <linux/etherdevice.h> +#include <linux/crc32.h> +#include <linux/io.h> +#include <linux/mii.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <net/ethoc.h> + +/* register offsets */ +#define MODER 0x00 +#define INT_SOURCE 0x04 +#define INT_MASK 0x08 +#define IPGT 0x0c +#define IPGR1 0x10 +#define IPGR2 0x14 +#define PACKETLEN 0x18 +#define COLLCONF 0x1c +#define TX_BD_NUM 0x20 +#define CTRLMODER 0x24 +#define MIIMODER 0x28 +#define MIICOMMAND 0x2c +#define MIIADDRESS 0x30 +#define MIITX_DATA 0x34 +#define MIIRX_DATA 0x38 +#define MIISTATUS 0x3c +#define MAC_ADDR0 0x40 +#define MAC_ADDR1 0x44 +#define ETH_HASH0 0x48 +#define ETH_HASH1 0x4c +#define ETH_TXCTRL 0x50 + +/* mode register */ +#define MODER_RXEN (1 << 0) /* receive enable */ +#define MODER_TXEN (1 << 1) /* transmit enable */ +#define MODER_NOPRE (1 << 2) /* no preamble */ +#define MODER_BRO (1 << 3) /* broadcast address */ +#define MODER_IAM (1 << 4) /* individual address mode */ +#define MODER_PRO (1 << 5) /* promiscuous mode */ +#define MODER_IFG (1 << 6) /* interframe gap for incoming frames */ +#define MODER_LOOP (1 << 7) /* loopback */ +#define MODER_NBO (1 << 8) /* no back-off */ +#define MODER_EDE (1 << 9) /* excess defer enable */ +#define MODER_FULLD (1 << 10) /* full duplex */ +#define MODER_RESET (1 << 11) /* FIXME: reset (undocumented) */ +#define MODER_DCRC (1 << 12) /* delayed CRC enable */ +#define MODER_CRC (1 << 13) /* CRC enable */ +#define MODER_HUGE (1 << 14) /* huge packets enable */ +#define MODER_PAD (1 << 15) /* padding enabled */ +#define MODER_RSM (1 << 16) /* receive small packets */ + +/* interrupt source and mask registers */ +#define INT_MASK_TXF (1 << 0) /* transmit frame */ +#define INT_MASK_TXE (1 << 1) /* transmit error */ +#define INT_MASK_RXF (1 << 2) /* receive frame */ +#define INT_MASK_RXE (1 << 3) /* receive error */ +#define INT_MASK_BUSY (1 << 4) +#define INT_MASK_TXC (1 << 5) /* transmit control frame */ +#define INT_MASK_RXC (1 << 6) /* receive control frame */ + +#define INT_MASK_TX (INT_MASK_TXF | INT_MASK_TXE) +#define INT_MASK_RX (INT_MASK_RXF | INT_MASK_RXE) + +#define INT_MASK_ALL ( \ + INT_MASK_TXF | INT_MASK_TXE | \ + INT_MASK_RXF | INT_MASK_RXE | \ + INT_MASK_TXC | INT_MASK_RXC | \ + INT_MASK_BUSY \ + ) + +/* packet length register */ +#define PACKETLEN_MIN(min) (((min) & 0xffff) << 16) +#define PACKETLEN_MAX(max) (((max) & 0xffff) << 0) +#define PACKETLEN_MIN_MAX(min, max) (PACKETLEN_MIN(min) | \ + PACKETLEN_MAX(max)) + +/* transmit buffer number register */ +#define TX_BD_NUM_VAL(x) (((x) <= 0x80) ? (x) : 0x80) + +/* control module mode register */ +#define CTRLMODER_PASSALL (1 << 0) /* pass all receive frames */ +#define CTRLMODER_RXFLOW (1 << 1) /* receive control flow */ +#define CTRLMODER_TXFLOW (1 << 2) /* transmit control flow */ + +/* MII mode register */ +#define MIIMODER_CLKDIV(x) ((x) & 0xfe) /* needs to be an even number */ +#define MIIMODER_NOPRE (1 << 8) /* no preamble */ + +/* MII command register */ +#define MIICOMMAND_SCAN (1 << 0) /* scan status */ +#define MIICOMMAND_READ (1 << 1) /* read status */ +#define MIICOMMAND_WRITE (1 << 2) /* write control data */ + +/* MII address register */ +#define MIIADDRESS_FIAD(x) (((x) & 0x1f) << 0) +#define MIIADDRESS_RGAD(x) (((x) & 0x1f) << 8) +#define MIIADDRESS_ADDR(phy, reg) (MIIADDRESS_FIAD(phy) | \ + MIIADDRESS_RGAD(reg)) + +/* MII transmit data register */ +#define MIITX_DATA_VAL(x) ((x) & 0xffff) + +/* MII receive data register */ +#define MIIRX_DATA_VAL(x) ((x) & 0xffff) + +/* MII status register */ +#define MIISTATUS_LINKFAIL (1 << 0) +#define MIISTATUS_BUSY (1 << 1) +#define MIISTATUS_INVALID (1 << 2) + +/* TX buffer descriptor */ +#define TX_BD_CS (1 << 0) /* carrier sense lost */ +#define TX_BD_DF (1 << 1) /* defer indication */ +#define TX_BD_LC (1 << 2) /* late collision */ +#define TX_BD_RL (1 << 3) /* retransmission limit */ +#define TX_BD_RETRY_MASK (0x00f0) +#define TX_BD_RETRY(x) (((x) & 0x00f0) >> 4) +#define TX_BD_UR (1 << 8) /* transmitter underrun */ +#define TX_BD_CRC (1 << 11) /* TX CRC enable */ +#define TX_BD_PAD (1 << 12) /* pad enable for short packets */ +#define TX_BD_WRAP (1 << 13) +#define TX_BD_IRQ (1 << 14) /* interrupt request enable */ +#define TX_BD_READY (1 << 15) /* TX buffer ready */ +#define TX_BD_LEN(x) (((x) & 0xffff) << 16) +#define TX_BD_LEN_MASK (0xffff << 16) + +#define TX_BD_STATS (TX_BD_CS | TX_BD_DF | TX_BD_LC | \ + TX_BD_RL | TX_BD_RETRY_MASK | TX_BD_UR) + +/* RX buffer descriptor */ +#define RX_BD_LC (1 << 0) /* late collision */ +#define RX_BD_CRC (1 << 1) /* RX CRC error */ +#define RX_BD_SF (1 << 2) /* short frame */ +#define RX_BD_TL (1 << 3) /* too long */ +#define RX_BD_DN (1 << 4) /* dribble nibble */ +#define RX_BD_IS (1 << 5) /* invalid symbol */ +#define RX_BD_OR (1 << 6) /* receiver overrun */ +#define RX_BD_MISS (1 << 7) +#define RX_BD_CF (1 << 8) /* control frame */ +#define RX_BD_WRAP (1 << 13) +#define RX_BD_IRQ (1 << 14) /* interrupt request enable */ +#define RX_BD_EMPTY (1 << 15) +#define RX_BD_LEN(x) (((x) & 0xffff) << 16) + +#define RX_BD_STATS (RX_BD_LC | RX_BD_CRC | RX_BD_SF | RX_BD_TL | \ + RX_BD_DN | RX_BD_IS | RX_BD_OR | RX_BD_MISS) + +#define ETHOC_BUFSIZ 1536 +#define ETHOC_ZLEN 64 +#define ETHOC_BD_BASE 0x400 +#define ETHOC_TIMEOUT (HZ / 2) +#define ETHOC_MII_TIMEOUT (1 + (HZ / 5)) + +/** + * struct ethoc - driver-private device structure + * @iobase: pointer to I/O memory region + * @membase: pointer to buffer memory region + * @num_tx: number of send buffers + * @cur_tx: last send buffer written + * @dty_tx: last buffer actually sent + * @num_rx: number of receive buffers + * @cur_rx: current receive buffer + * @netdev: pointer to network device structure + * @napi: NAPI structure + * @stats: network device statistics + * @msg_enable: device state flags + * @rx_lock: receive lock + * @lock: device lock + * @phy: attached PHY + * @mdio: MDIO bus for PHY access + * @phy_id: address of attached PHY + */ +struct ethoc { + void __iomem *iobase; + void __iomem *membase; + + unsigned int num_tx; + unsigned int cur_tx; + unsigned int dty_tx; + + unsigned int num_rx; + unsigned int cur_rx; + + struct net_device *netdev; + struct napi_struct napi; + struct net_device_stats stats; + u32 msg_enable; + + spinlock_t rx_lock; + spinlock_t lock; + + struct phy_device *phy; + struct mii_bus *mdio; + s8 phy_id; +}; + +/** + * struct ethoc_bd - buffer descriptor + * @stat: buffer statistics + * @addr: physical memory address + */ +struct ethoc_bd { + u32 stat; + u32 addr; +}; + +static u32 ethoc_read(struct ethoc *dev, loff_t offset) +{ + return ioread32(dev->iobase + offset); +} + +static void ethoc_write(struct ethoc *dev, loff_t offset, u32 data) +{ + iowrite32(data, dev->iobase + offset); +} + +static void ethoc_read_bd(struct ethoc *dev, int index, struct ethoc_bd *bd) +{ + loff_t offset = ETHOC_BD_BASE + (index * sizeof(struct ethoc_bd)); + bd->stat = ethoc_read(dev, offset + 0); + bd->addr = ethoc_read(dev, offset + 4); +} + +static void ethoc_write_bd(struct ethoc *dev, int index, + const struct ethoc_bd *bd) +{ + loff_t offset = ETHOC_BD_BASE + (index * sizeof(struct ethoc_bd)); + ethoc_write(dev, offset + 0, bd->stat); + ethoc_write(dev, offset + 4, bd->addr); +} + +static void ethoc_enable_irq(struct ethoc *dev, u32 mask) +{ + u32 imask = ethoc_read(dev, INT_MASK); + imask |= mask; + ethoc_write(dev, INT_MASK, imask); +} + +static void ethoc_disable_irq(struct ethoc *dev, u32 mask) +{ + u32 imask = ethoc_read(dev, INT_MASK); + imask &= ~mask; + ethoc_write(dev, INT_MASK, imask); +} + +static void ethoc_ack_irq(struct ethoc *dev, u32 mask) +{ + ethoc_write(dev, INT_SOURCE, mask); +} + +static void ethoc_enable_rx_and_tx(struct ethoc *dev) +{ + u32 mode = ethoc_read(dev, MODER); + mode |= MODER_RXEN | MODER_TXEN; + ethoc_write(dev, MODER, mode); +} + +static void ethoc_disable_rx_and_tx(struct ethoc *dev) +{ + u32 mode = ethoc_read(dev, MODER); + mode &= ~(MODER_RXEN | MODER_TXEN); + ethoc_write(dev, MODER, mode); +} + +static int ethoc_init_ring(struct ethoc *dev) +{ + struct ethoc_bd bd; + int i; + + dev->cur_tx = 0; + dev->dty_tx = 0; + dev->cur_rx = 0; + + /* setup transmission buffers */ + bd.addr = 0; + bd.stat = TX_BD_IRQ | TX_BD_CRC; + + for (i = 0; i < dev->num_tx; i++) { + if (i == dev->num_tx - 1) + bd.stat |= TX_BD_WRAP; + + ethoc_write_bd(dev, i, &bd); + bd.addr += ETHOC_BUFSIZ; + } + + bd.addr = dev->num_tx * ETHOC_BUFSIZ; + bd.stat = RX_BD_EMPTY | RX_BD_IRQ; + + for (i = 0; i < dev->num_rx; i++) { + if (i == dev->num_rx - 1) + bd.stat |= RX_BD_WRAP; + + ethoc_write_bd(dev, dev->num_tx + i, &bd); + bd.addr += ETHOC_BUFSIZ; + } + + return 0; +} + +static int ethoc_reset(struct ethoc *dev) +{ + u32 mode; + + /* TODO: reset controller? */ + + ethoc_disable_rx_and_tx(dev); + + /* TODO: setup registers */ + + /* enable FCS generation and automatic padding */ + mode = ethoc_read(dev, MODER); + mode |= MODER_CRC | MODER_PAD; + ethoc_write(dev, MODER, mode); + + /* set full-duplex mode */ + mode = ethoc_read(dev, MODER); + mode |= MODER_FULLD; + ethoc_write(dev, MODER, mode); + ethoc_write(dev, IPGT, 0x15); + + ethoc_ack_irq(dev, INT_MASK_ALL); + ethoc_enable_irq(dev, INT_MASK_ALL); + ethoc_enable_rx_and_tx(dev); + return 0; +} + +static unsigned int ethoc_update_rx_stats(struct ethoc *dev, + struct ethoc_bd *bd) +{ + struct net_device *netdev = dev->netdev; + unsigned int ret = 0; + + if (bd->stat & RX_BD_TL) { + dev_err(&netdev->dev, "RX: frame too long\n"); + dev->stats.rx_length_errors++; + ret++; + } + + if (bd->stat & RX_BD_SF) { + dev_err(&netdev->dev, "RX: frame too short\n"); + dev->stats.rx_length_errors++; + ret++; + } + + if (bd->stat & RX_BD_DN) { + dev_err(&netdev->dev, "RX: dribble nibble\n"); + dev->stats.rx_frame_errors++; + } + + if (bd->stat & RX_BD_CRC) { + dev_err(&netdev->dev, "RX: wrong CRC\n"); + dev->stats.rx_crc_errors++; + ret++; + } + + if (bd->stat & RX_BD_OR) { + dev_err(&netdev->dev, "RX: overrun\n"); + dev->stats.rx_over_errors++; + ret++; + } + + if (bd->stat & RX_BD_MISS) + dev->stats.rx_missed_errors++; + + if (bd->stat & RX_BD_LC) { + dev_err(&netdev->dev, "RX: late collision\n"); + dev->stats.collisions++; + ret++; + } + + return ret; +} + +static int ethoc_rx(struct net_device *dev, int limit) +{ + struct ethoc *priv = netdev_priv(dev); + int count; + + for (count = 0; count < limit; ++count) { + unsigned int entry; + struct ethoc_bd bd; + + entry = priv->num_tx + (priv->cur_rx % priv->num_rx); + ethoc_read_bd(priv, entry, &bd); + if (bd.stat & RX_BD_EMPTY) + break; + + if (ethoc_update_rx_stats(priv, &bd) == 0) { + int size = bd.stat >> 16; + struct sk_buff *skb = netdev_alloc_skb(dev, size); + if (likely(skb)) { + void *src = priv->membase + bd.addr; + memcpy_fromio(skb_put(skb, size), src, size); + skb->protocol = eth_type_trans(skb, dev); + dev->last_rx = jiffies; + priv->stats.rx_packets++; + priv->stats.rx_bytes += size; + netif_receive_skb(skb); + } else { + if (net_ratelimit()) + dev_warn(&dev->dev, "low on memory - " + "packet dropped\n"); + + priv->stats.rx_dropped++; + break; + } + } + + /* clear the buffer descriptor so it can be reused */ + bd.stat &= ~RX_BD_STATS; + bd.stat |= RX_BD_EMPTY; + ethoc_write_bd(priv, entry, &bd); + priv->cur_rx++; + } + + return count; +} + +static int ethoc_update_tx_stats(struct ethoc *dev, struct ethoc_bd *bd) +{ + struct net_device *netdev = dev->netdev; + + if (bd->stat & TX_BD_LC) { + dev_err(&netdev->dev, "TX: late collision\n"); + dev->stats.tx_window_errors++; + } + + if (bd->stat & TX_BD_RL) { + dev_err(&netdev->dev, "TX: retransmit limit\n"); + dev->stats.tx_aborted_errors++; + } + + if (bd->stat & TX_BD_UR) { + dev_err(&netdev->dev, "TX: underrun\n"); + dev->stats.tx_fifo_errors++; + } + + if (bd->stat & TX_BD_CS) { + dev_err(&netdev->dev, "TX: carrier sense lost\n"); + dev->stats.tx_carrier_errors++; + } + + if (bd->stat & TX_BD_STATS) + dev->stats.tx_errors++; + + dev->stats.collisions += (bd->stat >> 4) & 0xf; + dev->stats.tx_bytes += bd->stat >> 16; + dev->stats.tx_packets++; + return 0; +} + +static void ethoc_tx(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + + spin_lock(&priv->lock); + + while (priv->dty_tx != priv->cur_tx) { + unsigned int entry = priv->dty_tx % priv->num_tx; + struct ethoc_bd bd; + + ethoc_read_bd(priv, entry, &bd); + if (bd.stat & TX_BD_READY) + break; + + entry = (++priv->dty_tx) % priv->num_tx; + (void)ethoc_update_tx_stats(priv, &bd); + } + + if ((priv->cur_tx - priv->dty_tx) <= (priv->num_tx / 2)) + netif_wake_queue(dev); + + ethoc_ack_irq(priv, INT_MASK_TX); + spin_unlock(&priv->lock); +} + +static irqreturn_t ethoc_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = (struct net_device *)dev_id; + struct ethoc *priv = netdev_priv(dev); + u32 pending; + + ethoc_disable_irq(priv, INT_MASK_ALL); + pending = ethoc_read(priv, INT_SOURCE); + if (unlikely(pending == 0)) { + ethoc_enable_irq(priv, INT_MASK_ALL); + return IRQ_NONE; + } + + ethoc_ack_irq(priv, INT_MASK_ALL); + + if (pending & INT_MASK_BUSY) { + dev_err(&dev->dev, "packet dropped\n"); + priv->stats.rx_dropped++; + } + + if (pending & INT_MASK_RX) { + if (napi_schedule_prep(&priv->napi)) + __napi_schedule(&priv->napi); + } else { + ethoc_enable_irq(priv, INT_MASK_RX); + } + + if (pending & INT_MASK_TX) + ethoc_tx(dev); + + ethoc_enable_irq(priv, INT_MASK_ALL & ~INT_MASK_RX); + return IRQ_HANDLED; +} + +static int ethoc_get_mac_address(struct net_device *dev, void *addr) +{ + struct ethoc *priv = netdev_priv(dev); + u8 *mac = (u8 *)addr; + u32 reg; + + reg = ethoc_read(priv, MAC_ADDR0); + mac[2] = (reg >> 24) & 0xff; + mac[3] = (reg >> 16) & 0xff; + mac[4] = (reg >> 8) & 0xff; + mac[5] = (reg >> 0) & 0xff; + + reg = ethoc_read(priv, MAC_ADDR1); + mac[0] = (reg >> 8) & 0xff; + mac[1] = (reg >> 0) & 0xff; + + return 0; +} + +static int ethoc_poll(struct napi_struct *napi, int budget) +{ + struct ethoc *priv = container_of(napi, struct ethoc, napi); + int work_done = 0; + + work_done = ethoc_rx(priv->netdev, budget); + if (work_done < budget) { + ethoc_enable_irq(priv, INT_MASK_RX); + napi_complete(napi); + } + + return work_done; +} + +static int ethoc_mdio_read(struct mii_bus *bus, int phy, int reg) +{ + unsigned long timeout = jiffies + ETHOC_MII_TIMEOUT; + struct ethoc *priv = bus->priv; + + ethoc_write(priv, MIIADDRESS, MIIADDRESS_ADDR(phy, reg)); + ethoc_write(priv, MIICOMMAND, MIICOMMAND_READ); + + while (time_before(jiffies, timeout)) { + u32 status = ethoc_read(priv, MIISTATUS); + if (!(status & MIISTATUS_BUSY)) { + u32 data = ethoc_read(priv, MIIRX_DATA); + /* reset MII command register */ + ethoc_write(priv, MIICOMMAND, 0); + return data; + } + + schedule(); + } + + return -EBUSY; +} + +static int ethoc_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) +{ + unsigned long timeout = jiffies + ETHOC_MII_TIMEOUT; + struct ethoc *priv = bus->priv; + + ethoc_write(priv, MIIADDRESS, MIIADDRESS_ADDR(phy, reg)); + ethoc_write(priv, MIITX_DATA, val); + ethoc_write(priv, MIICOMMAND, MIICOMMAND_WRITE); + + while (time_before(jiffies, timeout)) { + u32 stat = ethoc_read(priv, MIISTATUS); + if (!(stat & MIISTATUS_BUSY)) + return 0; + + schedule(); + } + + return -EBUSY; +} + +static int ethoc_mdio_reset(struct mii_bus *bus) +{ + return 0; +} + +static void ethoc_mdio_poll(struct net_device *dev) +{ +} + +static int ethoc_mdio_probe(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + struct phy_device *phy; + int i; + + for (i = 0; i < PHY_MAX_ADDR; i++) { + phy = priv->mdio->phy_map[i]; + if (phy) { + if (priv->phy_id != -1) { + /* attach to specified PHY */ + if (priv->phy_id == phy->addr) + break; + } else { + /* autoselect PHY if none was specified */ + if (phy->addr != 0) + break; + } + } + } + + if (!phy) { + dev_err(&dev->dev, "no PHY found\n"); + return -ENXIO; + } + + phy = phy_connect(dev, dev_name(&phy->dev), ðoc_mdio_poll, 0, + PHY_INTERFACE_MODE_GMII); + if (IS_ERR(phy)) { + dev_err(&dev->dev, "could not attach to PHY\n"); + return PTR_ERR(phy); + } + + priv->phy = phy; + return 0; +} + +static int ethoc_open(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + unsigned int min_tx = 2; + unsigned int num_bd; + int ret; + + ret = request_irq(dev->irq, ethoc_interrupt, IRQF_SHARED, + dev->name, dev); + if (ret) + return ret; + + /* calculate the number of TX/RX buffers */ + num_bd = (dev->mem_end - dev->mem_start + 1) / ETHOC_BUFSIZ; + priv->num_tx = min(min_tx, num_bd / 4); + priv->num_rx = num_bd - priv->num_tx; + ethoc_write(priv, TX_BD_NUM, priv->num_tx); + + ethoc_init_ring(priv); + ethoc_reset(priv); + + if (netif_queue_stopped(dev)) { + dev_dbg(&dev->dev, " resuming queue\n"); + netif_wake_queue(dev); + } else { + dev_dbg(&dev->dev, " starting queue\n"); + netif_start_queue(dev); + } + + phy_start(priv->phy); + napi_enable(&priv->napi); + + if (netif_msg_ifup(priv)) { + dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n", + dev->base_addr, dev->mem_start, dev->mem_end); + } + + return 0; +} + +static int ethoc_stop(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + + napi_disable(&priv->napi); + + if (priv->phy) + phy_stop(priv->phy); + + ethoc_disable_rx_and_tx(priv); + free_irq(dev->irq, dev); + + if (!netif_queue_stopped(dev)) + netif_stop_queue(dev); + + return 0; +} + +static int ethoc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct ethoc *priv = netdev_priv(dev); + struct mii_ioctl_data *mdio = if_mii(ifr); + struct phy_device *phy = NULL; + + if (!netif_running(dev)) + return -EINVAL; + + if (cmd != SIOCGMIIPHY) { + if (mdio->phy_id >= PHY_MAX_ADDR) + return -ERANGE; + + phy = priv->mdio->phy_map[mdio->phy_id]; + if (!phy) + return -ENODEV; + } else { + phy = priv->phy; + } + + return phy_mii_ioctl(phy, mdio, cmd); +} + +static int ethoc_config(struct net_device *dev, struct ifmap *map) +{ + return -ENOSYS; +} + +static int ethoc_set_mac_address(struct net_device *dev, void *addr) +{ + struct ethoc *priv = netdev_priv(dev); + u8 *mac = (u8 *)addr; + + ethoc_write(priv, MAC_ADDR0, (mac[2] << 24) | (mac[3] << 16) | + (mac[4] << 8) | (mac[5] << 0)); + ethoc_write(priv, MAC_ADDR1, (mac[0] << 8) | (mac[1] << 0)); + + return 0; +} + +static void ethoc_set_multicast_list(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + u32 mode = ethoc_read(priv, MODER); + struct dev_mc_list *mc = NULL; + u32 hash[2] = { 0, 0 }; + + /* set loopback mode if requested */ + if (dev->flags & IFF_LOOPBACK) + mode |= MODER_LOOP; + else + mode &= ~MODER_LOOP; + + /* receive broadcast frames if requested */ + if (dev->flags & IFF_BROADCAST) + mode &= ~MODER_BRO; + else + mode |= MODER_BRO; + + /* enable promiscuous mode if requested */ + if (dev->flags & IFF_PROMISC) + mode |= MODER_PRO; + else + mode &= ~MODER_PRO; + + ethoc_write(priv, MODER, mode); + + /* receive multicast frames */ + if (dev->flags & IFF_ALLMULTI) { + hash[0] = 0xffffffff; + hash[1] = 0xffffffff; + } else { + for (mc = dev->mc_list; mc; mc = mc->next) { + u32 crc = ether_crc(mc->dmi_addrlen, mc->dmi_addr); + int bit = (crc >> 26) & 0x3f; + hash[bit >> 5] |= 1 << (bit & 0x1f); + } + } + + ethoc_write(priv, ETH_HASH0, hash[0]); + ethoc_write(priv, ETH_HASH1, hash[1]); +} + +static int ethoc_change_mtu(struct net_device *dev, int new_mtu) +{ + return -ENOSYS; +} + +static void ethoc_tx_timeout(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + u32 pending = ethoc_read(priv, INT_SOURCE); + if (likely(pending)) + ethoc_interrupt(dev->irq, dev); +} + +static struct net_device_stats *ethoc_stats(struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + return &priv->stats; +} + +static int ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ethoc *priv = netdev_priv(dev); + struct ethoc_bd bd; + unsigned int entry; + void *dest; + + if (unlikely(skb->len > ETHOC_BUFSIZ)) { + priv->stats.tx_errors++; + return -EMSGSIZE; + } + + entry = priv->cur_tx % priv->num_tx; + spin_lock_irq(&priv->lock); + priv->cur_tx++; + + ethoc_read_bd(priv, entry, &bd); + if (unlikely(skb->len < ETHOC_ZLEN)) + bd.stat |= TX_BD_PAD; + else + bd.stat &= ~TX_BD_PAD; + + dest = priv->membase + bd.addr; + memcpy_toio(dest, skb->data, skb->len); + + bd.stat &= ~(TX_BD_STATS | TX_BD_LEN_MASK); + bd.stat |= TX_BD_LEN(skb->len); + ethoc_write_bd(priv, entry, &bd); + + bd.stat |= TX_BD_READY; + ethoc_write_bd(priv, entry, &bd); + + if (priv->cur_tx == (priv->dty_tx + priv->num_tx)) { + dev_dbg(&dev->dev, "stopping queue\n"); + netif_stop_queue(dev); + } + + dev->trans_start = jiffies; + dev_kfree_skb(skb); + + spin_unlock_irq(&priv->lock); + return NETDEV_TX_OK; +} + +static const struct net_device_ops ethoc_netdev_ops = { + .ndo_open = ethoc_open, + .ndo_stop = ethoc_stop, + .ndo_do_ioctl = ethoc_ioctl, + .ndo_set_config = ethoc_config, + .ndo_set_mac_address = ethoc_set_mac_address, + .ndo_set_multicast_list = ethoc_set_multicast_list, + .ndo_change_mtu = ethoc_change_mtu, + .ndo_tx_timeout = ethoc_tx_timeout, + .ndo_get_stats = ethoc_stats, + .ndo_start_xmit = ethoc_start_xmit, +}; + +/** + * ethoc_probe() - initialize OpenCores ethernet MAC + * pdev: platform device + */ +static int ethoc_probe(struct platform_device *pdev) +{ + struct net_device *netdev = NULL; + struct resource *res = NULL; + struct resource *mmio = NULL; + struct resource *mem = NULL; + struct ethoc *priv = NULL; + unsigned int phy; + int ret = 0; + + /* allocate networking device */ + netdev = alloc_etherdev(sizeof(struct ethoc)); + if (!netdev) { + dev_err(&pdev->dev, "cannot allocate network device\n"); + ret = -ENOMEM; + goto out; + } + + SET_NETDEV_DEV(netdev, &pdev->dev); + platform_set_drvdata(pdev, netdev); + + /* obtain I/O memory space */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "cannot obtain I/O memory space\n"); + ret = -ENXIO; + goto free; + } + + mmio = devm_request_mem_region(&pdev->dev, res->start, + res->end - res->start + 1, res->name); + if (!res) { + dev_err(&pdev->dev, "cannot request I/O memory space\n"); + ret = -ENXIO; + goto free; + } + + netdev->base_addr = mmio->start; + + /* obtain buffer memory space */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) { + dev_err(&pdev->dev, "cannot obtain memory space\n"); + ret = -ENXIO; + goto free; + } + + mem = devm_request_mem_region(&pdev->dev, res->start, + res->end - res->start + 1, res->name); + if (!mem) { + dev_err(&pdev->dev, "cannot request memory space\n"); + ret = -ENXIO; + goto free; + } + + netdev->mem_start = mem->start; + netdev->mem_end = mem->end; + + /* obtain device IRQ number */ + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!res) { + dev_err(&pdev->dev, "cannot obtain IRQ\n"); + ret = -ENXIO; + goto free; + } + + netdev->irq = res->start; + + /* setup driver-private data */ + priv = netdev_priv(netdev); + priv->netdev = netdev; + + priv->iobase = devm_ioremap_nocache(&pdev->dev, netdev->base_addr, + mmio->end - mmio->start + 1); + if (!priv->iobase) { + dev_err(&pdev->dev, "cannot remap I/O memory space\n"); + ret = -ENXIO; + goto error; + } + + priv->membase = devm_ioremap_nocache(&pdev->dev, netdev->mem_start, + mem->end - mem->start + 1); + if (!priv->membase) { + dev_err(&pdev->dev, "cannot remap memory space\n"); + ret = -ENXIO; + goto error; + } + + /* Allow the platform setup code to pass in a MAC address. */ + if (pdev->dev.platform_data) { + struct ethoc_platform_data *pdata = + (struct ethoc_platform_data *)pdev->dev.platform_data; + memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN); + priv->phy_id = pdata->phy_id; + } + + /* Check that the given MAC address is valid. If it isn't, read the + * current MAC from the controller. */ + if (!is_valid_ether_addr(netdev->dev_addr)) + ethoc_get_mac_address(netdev, netdev->dev_addr); + + /* Check the MAC again for validity, if it still isn't choose and + * program a random one. */ + if (!is_valid_ether_addr(netdev->dev_addr)) + random_ether_addr(netdev->dev_addr); + + ethoc_set_mac_address(netdev, netdev->dev_addr); + + /* register MII bus */ + priv->mdio = mdiobus_alloc(); + if (!priv->mdio) { + ret = -ENOMEM; + goto free; + } + + priv->mdio->name = "ethoc-mdio"; + snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "%s-%d", + priv->mdio->name, pdev->id); + priv->mdio->read = ethoc_mdio_read; + priv->mdio->write = ethoc_mdio_write; + priv->mdio->reset = ethoc_mdio_reset; + priv->mdio->priv = priv; + + priv->mdio->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL); + if (!priv->mdio->irq) { + ret = -ENOMEM; + goto free_mdio; + } + + for (phy = 0; phy < PHY_MAX_ADDR; phy++) + priv->mdio->irq[phy] = PHY_POLL; + + ret = mdiobus_register(priv->mdio); + if (ret) { + dev_err(&netdev->dev, "failed to register MDIO bus\n"); + goto free_mdio; + } + + ret = ethoc_mdio_probe(netdev); + if (ret) { + dev_err(&netdev->dev, "failed to probe MDIO bus\n"); + goto error; + } + + ether_setup(netdev); + + /* setup the net_device structure */ + netdev->netdev_ops = ðoc_netdev_ops; + netdev->watchdog_timeo = ETHOC_TIMEOUT; + netdev->features |= 0; + + /* setup NAPI */ + memset(&priv->napi, 0, sizeof(priv->napi)); + netif_napi_add(netdev, &priv->napi, ethoc_poll, 64); + + spin_lock_init(&priv->rx_lock); + spin_lock_init(&priv->lock); + + ret = register_netdev(netdev); + if (ret < 0) { + dev_err(&netdev->dev, "failed to register interface\n"); + goto error; + } + + goto out; + +error: + mdiobus_unregister(priv->mdio); +free_mdio: + kfree(priv->mdio->irq); + mdiobus_free(priv->mdio); +free: + free_netdev(netdev); +out: + return ret; +} + +/** + * ethoc_remove() - shutdown OpenCores ethernet MAC + * @pdev: platform device + */ +static int ethoc_remove(struct platform_device *pdev) +{ + struct net_device *netdev = platform_get_drvdata(pdev); + struct ethoc *priv = netdev_priv(netdev); + + platform_set_drvdata(pdev, NULL); + + if (netdev) { + phy_disconnect(priv->phy); + priv->phy = NULL; + + if (priv->mdio) { + mdiobus_unregister(priv->mdio); + kfree(priv->mdio->irq); + mdiobus_free(priv->mdio); + } + + unregister_netdev(netdev); + free_netdev(netdev); + } + + return 0; +} + +#ifdef CONFIG_PM +static int ethoc_suspend(struct platform_device *pdev, pm_message_t state) +{ + return -ENOSYS; +} + +static int ethoc_resume(struct platform_device *pdev) +{ + return -ENOSYS; +} +#else +# define ethoc_suspend NULL +# define ethoc_resume NULL +#endif + +static struct platform_driver ethoc_driver = { + .probe = ethoc_probe, + .remove = ethoc_remove, + .suspend = ethoc_suspend, + .resume = ethoc_resume, + .driver = { + .name = "ethoc", + }, +}; + +static int __init ethoc_init(void) +{ + return platform_driver_register(ðoc_driver); +} + +static void __exit ethoc_exit(void) +{ + platform_driver_unregister(ðoc_driver); +} + +module_init(ethoc_init); +module_exit(ethoc_exit); + +MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>"); +MODULE_DESCRIPTION("OpenCores Ethernet MAC driver"); +MODULE_LICENSE("GPL v2"); + diff --git a/drivers/net/ewrk3.c b/drivers/net/ewrk3.c index b852303..1a685a0 100644 --- a/drivers/net/ewrk3.c +++ b/drivers/net/ewrk3.c @@ -388,6 +388,18 @@ static int __init ewrk3_probe1(struct net_device *dev, u_long iobase, int irq) return err; } +static const struct net_device_ops ewrk3_netdev_ops = { + .ndo_open = ewrk3_open, + .ndo_start_xmit = ewrk3_queue_pkt, + .ndo_stop = ewrk3_close, + .ndo_set_multicast_list = set_multicast_list, + .ndo_do_ioctl = ewrk3_ioctl, + .ndo_tx_timeout = ewrk3_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __init ewrk3_hw_init(struct net_device *dev, u_long iobase) { @@ -603,16 +615,11 @@ ewrk3_hw_init(struct net_device *dev, u_long iobase) printk(version); } /* The EWRK3-specific entries in the device structure. */ - dev->open = ewrk3_open; - dev->hard_start_xmit = ewrk3_queue_pkt; - dev->stop = ewrk3_close; - dev->set_multicast_list = set_multicast_list; - dev->do_ioctl = ewrk3_ioctl; + dev->netdev_ops = &ewrk3_netdev_ops; if (lp->adapter_name[4] == '3') SET_ETHTOOL_OPS(dev, ðtool_ops_203); else SET_ETHTOOL_OPS(dev, ðtool_ops); - dev->tx_timeout = ewrk3_timeout; dev->watchdog_timeo = QUEUE_PKT_TIMEOUT; dev->mem_start = 0; diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index 9d81e7a..44cbf26 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -1239,19 +1239,9 @@ static int gfar_enet_open(struct net_device *dev) return err; } -static inline struct txfcb *gfar_add_fcb(struct sk_buff **skbp) +static inline struct txfcb *gfar_add_fcb(struct sk_buff *skb) { - struct txfcb *fcb; - struct sk_buff *skb = *skbp; - - if (unlikely(skb_headroom(skb) < GMAC_FCB_LEN)) { - struct sk_buff *old_skb = skb; - skb = skb_realloc_headroom(old_skb, GMAC_FCB_LEN); - if (!skb) - return NULL; - dev_kfree_skb_any(old_skb); - } - fcb = (struct txfcb *)skb_push(skb, GMAC_FCB_LEN); + struct txfcb *fcb = (struct txfcb *)skb_push(skb, GMAC_FCB_LEN); cacheable_memzero(fcb, GMAC_FCB_LEN); return fcb; @@ -1320,6 +1310,20 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) base = priv->tx_bd_base; + /* make space for additional header */ + if (skb_headroom(skb) < GMAC_FCB_LEN) { + struct sk_buff *skb_new; + + skb_new = skb_realloc_headroom(skb, GMAC_FCB_LEN); + if (!skb_new) { + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; + } + kfree_skb(skb); + skb = skb_new; + } + /* total number of fragments in the SKB */ nr_frags = skb_shinfo(skb)->nr_frags; @@ -1372,20 +1376,18 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Set up checksumming */ if (CHECKSUM_PARTIAL == skb->ip_summed) { - fcb = gfar_add_fcb(&skb); - if (likely(fcb != NULL)) { - lstatus |= BD_LFLAG(TXBD_TOE); - gfar_tx_checksum(skb, fcb); - } + fcb = gfar_add_fcb(skb); + lstatus |= BD_LFLAG(TXBD_TOE); + gfar_tx_checksum(skb, fcb); } if (priv->vlgrp && vlan_tx_tag_present(skb)) { - if (unlikely(NULL == fcb)) - fcb = gfar_add_fcb(&skb); - if (likely(fcb != NULL)) { + if (unlikely(NULL == fcb)) { + fcb = gfar_add_fcb(skb); lstatus |= BD_LFLAG(TXBD_TOE); - gfar_tx_vlan(skb, fcb); } + + gfar_tx_vlan(skb, fcb); } /* setup the TxBD length and buffer pointer for the first BD */ @@ -1433,7 +1435,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Unlock priv */ spin_unlock_irqrestore(&priv->txlock, flags); - return 0; + return NETDEV_TX_OK; } /* Stops the kernel queue, and halts the controller */ diff --git a/drivers/net/ibmlana.c b/drivers/net/ibmlana.c index 5b5bf9f..c25bc0b 100644 --- a/drivers/net/ibmlana.c +++ b/drivers/net/ibmlana.c @@ -905,6 +905,17 @@ static char *ibmlana_adapter_names[] __devinitdata = { NULL }; + +static const struct net_device_ops ibmlana_netdev_ops = { + .ndo_open = ibmlana_open, + .ndo_stop = ibmlana_close, + .ndo_start_xmit = ibmlana_tx, + .ndo_set_multicast_list = ibmlana_set_multicast_list, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __devinit ibmlana_init_one(struct device *kdev) { struct mca_device *mdev = to_mca_device(kdev); @@ -973,11 +984,7 @@ static int __devinit ibmlana_init_one(struct device *kdev) mca_device_set_claim(mdev, 1); /* set methods */ - - dev->open = ibmlana_open; - dev->stop = ibmlana_close; - dev->hard_start_xmit = ibmlana_tx; - dev->set_multicast_list = ibmlana_set_multicast_list; + dev->netdev_ops = &ibmlana_netdev_ops; dev->flags |= IFF_MULTICAST; /* copy out MAC address */ diff --git a/drivers/net/irda/donauboe.c b/drivers/net/irda/donauboe.c index 6f3e7f7..6b6548b 100644 --- a/drivers/net/irda/donauboe.c +++ b/drivers/net/irda/donauboe.c @@ -1524,6 +1524,13 @@ toshoboe_close (struct pci_dev *pci_dev) free_netdev(self->netdev); } +static const struct net_device_ops toshoboe_netdev_ops = { + .ndo_open = toshoboe_net_open, + .ndo_stop = toshoboe_net_close, + .ndo_start_xmit = toshoboe_hard_xmit, + .ndo_do_ioctl = toshoboe_net_ioctl, +}; + static int toshoboe_open (struct pci_dev *pci_dev, const struct pci_device_id *pdid) { @@ -1657,10 +1664,7 @@ toshoboe_open (struct pci_dev *pci_dev, const struct pci_device_id *pdid) #endif SET_NETDEV_DEV(dev, &pci_dev->dev); - dev->hard_start_xmit = toshoboe_hard_xmit; - dev->open = toshoboe_net_open; - dev->stop = toshoboe_net_close; - dev->do_ioctl = toshoboe_net_ioctl; + dev->netdev_ops = &toshoboe_netdev_ops; err = register_netdev(dev); if (err) diff --git a/drivers/net/lance.c b/drivers/net/lance.c index d83d401..633808d 100644 --- a/drivers/net/lance.c +++ b/drivers/net/lance.c @@ -454,6 +454,18 @@ out: } #endif +static const struct net_device_ops lance_netdev_ops = { + .ndo_open = lance_open, + .ndo_start_xmit = lance_start_xmit, + .ndo_stop = lance_close, + .ndo_get_stats = lance_get_stats, + .ndo_set_multicast_list = set_multicast_list, + .ndo_tx_timeout = lance_tx_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int options) { struct lance_private *lp; @@ -714,12 +726,7 @@ static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int printk(version); /* The LANCE-specific entries in the device structure. */ - dev->open = lance_open; - dev->hard_start_xmit = lance_start_xmit; - dev->stop = lance_close; - dev->get_stats = lance_get_stats; - dev->set_multicast_list = set_multicast_list; - dev->tx_timeout = lance_tx_timeout; + dev->netdev_ops = &lance_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; err = register_netdev(dev); diff --git a/drivers/net/lp486e.c b/drivers/net/lp486e.c index 4d1a059..d44bddb 100644 --- a/drivers/net/lp486e.c +++ b/drivers/net/lp486e.c @@ -952,6 +952,17 @@ static void print_eth(char *add) (unsigned char) add[12], (unsigned char) add[13]); } +static const struct net_device_ops i596_netdev_ops = { + .ndo_open = i596_open, + .ndo_stop = i596_close, + .ndo_start_xmit = i596_start_xmit, + .ndo_set_multicast_list = set_multicast_list, + .ndo_tx_timeout = i596_tx_timeout, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __init lp486e_probe(struct net_device *dev) { struct i596_private *lp; unsigned char eth_addr[6] = { 0, 0xaa, 0, 0, 0, 0 }; @@ -1014,12 +1025,8 @@ static int __init lp486e_probe(struct net_device *dev) { printk("\n"); /* The LP486E-specific entries in the device structure. */ - dev->open = &i596_open; - dev->stop = &i596_close; - dev->hard_start_xmit = &i596_start_xmit; - dev->set_multicast_list = &set_multicast_list; + dev->netdev_ops = &i596_netdev_ops; dev->watchdog_timeo = 5*HZ; - dev->tx_timeout = i596_tx_timeout; #if 0 /* selftest reports 0x320925ae - don't know what that means */ diff --git a/drivers/net/ni52.c b/drivers/net/ni52.c index a8bcc00..77d44a0 100644 --- a/drivers/net/ni52.c +++ b/drivers/net/ni52.c @@ -441,6 +441,18 @@ out: return ERR_PTR(err); } +static const struct net_device_ops ni52_netdev_ops = { + .ndo_open = ni52_open, + .ndo_stop = ni52_close, + .ndo_get_stats = ni52_get_stats, + .ndo_tx_timeout = ni52_timeout, + .ndo_start_xmit = ni52_send_packet, + .ndo_set_multicast_list = set_multicast_list, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + static int __init ni52_probe1(struct net_device *dev, int ioaddr) { int i, size, retval; @@ -561,15 +573,8 @@ static int __init ni52_probe1(struct net_device *dev, int ioaddr) printk("IRQ %d (assigned and not checked!).\n", dev->irq); } - dev->open = ni52_open; - dev->stop = ni52_close; - dev->get_stats = ni52_get_stats; - dev->tx_timeout = ni52_timeout; + dev->netdev_ops = &ni52_netdev_ops; dev->watchdog_timeo = HZ/20; - dev->hard_start_xmit = ni52_send_packet; - dev->set_multicast_list = set_multicast_list; - - dev->if_port = 0; return 0; out: diff --git a/drivers/net/ni65.c b/drivers/net/ni65.c index df5f869..6474f02 100644 --- a/drivers/net/ni65.c +++ b/drivers/net/ni65.c @@ -237,7 +237,7 @@ struct priv void *tmdbounce[TMDNUM]; int tmdbouncenum; int lock,xmit_queued; - struct net_device_stats stats; + void *self; int cmdr_addr; int cardno; @@ -257,7 +257,6 @@ static void ni65_timeout(struct net_device *dev); static int ni65_close(struct net_device *dev); static int ni65_alloc_buffer(struct net_device *dev); static void ni65_free_buffer(struct priv *p); -static struct net_device_stats *ni65_get_stats(struct net_device *); static void set_multicast_list(struct net_device *dev); static int irqtab[] __initdata = { 9,12,15,5 }; /* irq config-translate */ @@ -401,6 +400,17 @@ out: return ERR_PTR(err); } +static const struct net_device_ops ni65_netdev_ops = { + .ndo_open = ni65_open, + .ndo_stop = ni65_close, + .ndo_start_xmit = ni65_send_packet, + .ndo_tx_timeout = ni65_timeout, + .ndo_set_multicast_list = set_multicast_list, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* * this is the real card probe .. */ @@ -549,13 +559,9 @@ static int __init ni65_probe1(struct net_device *dev,int ioaddr) } dev->base_addr = ioaddr; - dev->open = ni65_open; - dev->stop = ni65_close; - dev->hard_start_xmit = ni65_send_packet; - dev->tx_timeout = ni65_timeout; + dev->netdev_ops = &ni65_netdev_ops; dev->watchdog_timeo = HZ/2; - dev->get_stats = ni65_get_stats; - dev->set_multicast_list = set_multicast_list; + return 0; /* everything is OK */ } @@ -901,13 +907,13 @@ static irqreturn_t ni65_interrupt(int irq, void * dev_id) if(debuglevel > 1) printk(KERN_ERR "%s: general error: %04x.\n",dev->name,csr0); if(csr0 & CSR0_BABL) - p->stats.tx_errors++; + dev->stats.tx_errors++; if(csr0 & CSR0_MISS) { int i; for(i=0;i<RMDNUM;i++) printk("%02x ",p->rmdhead[i].u.s.status); printk("\n"); - p->stats.rx_errors++; + dev->stats.rx_errors++; } if(csr0 & CSR0_MERR) { if(debuglevel > 1) @@ -997,12 +1003,12 @@ static void ni65_xmit_intr(struct net_device *dev,int csr0) #endif /* checking some errors */ if(tmdp->status2 & XMIT_RTRY) - p->stats.tx_aborted_errors++; + dev->stats.tx_aborted_errors++; if(tmdp->status2 & XMIT_LCAR) - p->stats.tx_carrier_errors++; + dev->stats.tx_carrier_errors++; if(tmdp->status2 & (XMIT_BUFF | XMIT_UFLO )) { /* this stops the xmitter */ - p->stats.tx_fifo_errors++; + dev->stats.tx_fifo_errors++; if(debuglevel > 0) printk(KERN_ERR "%s: Xmit FIFO/BUFF error\n",dev->name); if(p->features & INIT_RING_BEFORE_START) { @@ -1016,12 +1022,12 @@ static void ni65_xmit_intr(struct net_device *dev,int csr0) if(debuglevel > 2) printk(KERN_ERR "%s: xmit-error: %04x %02x-%04x\n",dev->name,csr0,(int) tmdstat,(int) tmdp->status2); if(!(csr0 & CSR0_BABL)) /* don't count errors twice */ - p->stats.tx_errors++; + dev->stats.tx_errors++; tmdp->status2 = 0; } else { - p->stats.tx_bytes -= (short)(tmdp->blen); - p->stats.tx_packets++; + dev->stats.tx_bytes -= (short)(tmdp->blen); + dev->stats.tx_packets++; } #ifdef XMT_VIA_SKB @@ -1057,7 +1063,7 @@ static void ni65_recv_intr(struct net_device *dev,int csr0) if(!(rmdstat & RCV_ERR)) { if(rmdstat & RCV_START) { - p->stats.rx_length_errors++; + dev->stats.rx_length_errors++; printk(KERN_ERR "%s: recv, packet too long: %d\n",dev->name,rmdp->mlen & 0x0fff); } } @@ -1066,16 +1072,16 @@ static void ni65_recv_intr(struct net_device *dev,int csr0) printk(KERN_ERR "%s: receive-error: %04x, lance-status: %04x/%04x\n", dev->name,(int) rmdstat,csr0,(int) inw(PORT+L_DATAREG) ); if(rmdstat & RCV_FRAM) - p->stats.rx_frame_errors++; + dev->stats.rx_frame_errors++; if(rmdstat & RCV_OFLO) - p->stats.rx_over_errors++; + dev->stats.rx_over_errors++; if(rmdstat & RCV_CRC) - p->stats.rx_crc_errors++; + dev->stats.rx_crc_errors++; if(rmdstat & RCV_BUF_ERR) - p->stats.rx_fifo_errors++; + dev->stats.rx_fifo_errors++; } if(!(csr0 & CSR0_MISS)) /* don't count errors twice */ - p->stats.rx_errors++; + dev->stats.rx_errors++; } else if( (len = (rmdp->mlen & 0x0fff) - 4) >= 60) { @@ -1106,20 +1112,20 @@ static void ni65_recv_intr(struct net_device *dev,int csr0) skb_put(skb,len); skb_copy_to_linear_data(skb, (unsigned char *) p->recvbounce[p->rmdnum],len); #endif - p->stats.rx_packets++; - p->stats.rx_bytes += len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; skb->protocol=eth_type_trans(skb,dev); netif_rx(skb); } else { printk(KERN_ERR "%s: can't alloc new sk_buff\n",dev->name); - p->stats.rx_dropped++; + dev->stats.rx_dropped++; } } else { printk(KERN_INFO "%s: received runt packet\n",dev->name); - p->stats.rx_errors++; + dev->stats.rx_errors++; } rmdp->blen = -(R_BUF_SIZE-8); rmdp->mlen = 0; @@ -1213,23 +1219,6 @@ static int ni65_send_packet(struct sk_buff *skb, struct net_device *dev) return 0; } -static struct net_device_stats *ni65_get_stats(struct net_device *dev) -{ - -#if 0 - int i; - struct priv *p = dev->ml_priv; - for(i=0;i<RMDNUM;i++) - { - struct rmd *rmdp = p->rmdhead + ((p->rmdnum + i) & (RMDNUM-1)); - printk("%02x ",rmdp->u.s.status); - } - printk("\n"); -#endif - - return &((struct priv *)dev->ml_priv)->stats; -} - static void set_multicast_list(struct net_device *dev) { if(!ni65_lance_reinit(dev)) diff --git a/drivers/net/seeq8005.c b/drivers/net/seeq8005.c index 12a8fff..ebbbe09 100644 --- a/drivers/net/seeq8005.c +++ b/drivers/net/seeq8005.c @@ -143,6 +143,17 @@ out: return ERR_PTR(err); } +static const struct net_device_ops seeq8005_netdev_ops = { + .ndo_open = seeq8005_open, + .ndo_stop = seeq8005_close, + .ndo_start_xmit = seeq8005_send_packet, + .ndo_tx_timeout = seeq8005_timeout, + .ndo_set_multicast_list = set_multicast_list, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* This is the real probe routine. Linux has a history of friendly device probes on the ISA bus. A good device probes avoids doing writes, and verifies that the correct device exists and functions. */ @@ -332,12 +343,8 @@ static int __init seeq8005_probe1(struct net_device *dev, int ioaddr) } } #endif - dev->open = seeq8005_open; - dev->stop = seeq8005_close; - dev->hard_start_xmit = seeq8005_send_packet; - dev->tx_timeout = seeq8005_timeout; + dev->netdev_ops = &seeq8005_netdev_ops; dev->watchdog_timeo = HZ/20; - dev->set_multicast_list = set_multicast_list; dev->flags &= ~IFF_MULTICAST; return 0; diff --git a/drivers/net/smc-ultra.c b/drivers/net/smc-ultra.c index 2033fee..0291ea0 100644 --- a/drivers/net/smc-ultra.c +++ b/drivers/net/smc-ultra.c @@ -142,9 +142,6 @@ static int __init do_ultra_probe(struct net_device *dev) int base_addr = dev->base_addr; int irq = dev->irq; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = &ultra_poll; -#endif if (base_addr > 0x1ff) /* Check a single specified location. */ return ultra_probe1(dev, base_addr); else if (base_addr != 0) /* Don't probe at all. */ @@ -199,7 +196,7 @@ static const struct net_device_ops ultra_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = eth_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ei_poll, + .ndo_poll_controller = ultra_poll, #endif }; diff --git a/drivers/net/smc-ultra32.c b/drivers/net/smc-ultra32.c index cb6c097..7a554ad 100644 --- a/drivers/net/smc-ultra32.c +++ b/drivers/net/smc-ultra32.c @@ -153,6 +153,22 @@ out: return ERR_PTR(err); } + +static const struct net_device_ops ultra32_netdev_ops = { + .ndo_open = ultra32_open, + .ndo_stop = ultra32_close, + .ndo_start_xmit = ei_start_xmit, + .ndo_tx_timeout = ei_tx_timeout, + .ndo_get_stats = ei_get_stats, + .ndo_set_multicast_list = ei_set_multicast_list, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = eth_mac_addr, + .ndo_change_mtu = eth_change_mtu, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = ei_poll, +#endif +}; + static int __init ultra32_probe1(struct net_device *dev, int ioaddr) { int i, edge, media, retval; @@ -273,11 +289,8 @@ static int __init ultra32_probe1(struct net_device *dev, int ioaddr) ei_status.block_output = &ultra32_block_output; ei_status.get_8390_hdr = &ultra32_get_8390_hdr; ei_status.reset_8390 = &ultra32_reset_8390; - dev->open = &ultra32_open; - dev->stop = &ultra32_close; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ei_poll; -#endif + + dev->netdev_ops = &ultra32_netdev_ops; NS8390_init(dev, 0); return 0; diff --git a/drivers/net/smc9194.c b/drivers/net/smc9194.c index 18d653b..9a7973a 100644 --- a/drivers/net/smc9194.c +++ b/drivers/net/smc9194.c @@ -831,6 +831,17 @@ static int __init smc_findirq(int ioaddr) #endif } +static const struct net_device_ops smc_netdev_ops = { + .ndo_open = smc_open, + .ndo_stop = smc_close, + .ndo_start_xmit = smc_wait_to_send_packet, + .ndo_tx_timeout = smc_timeout, + .ndo_set_multicast_list = smc_set_multicast_list, + .ndo_change_mtu = eth_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /*---------------------------------------------------------------------- . Function: smc_probe( int ioaddr ) . @@ -1044,12 +1055,8 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) goto err_out; } - dev->open = smc_open; - dev->stop = smc_close; - dev->hard_start_xmit = smc_wait_to_send_packet; - dev->tx_timeout = smc_timeout; + dev->netdev_ops = &smc_netdev_ops; dev->watchdog_timeo = HZ/20; - dev->set_multicast_list = smc_set_multicast_list; return 0; diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index ad3cbc9..af8f60c 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -1680,6 +1680,7 @@ static int smsc911x_eeprom_write_location(struct smsc911x_data *pdata, u8 address, u8 data) { u32 op = E2P_CMD_EPC_CMD_ERASE_ | address; + u32 temp; int ret; SMSC_TRACE(DRV, "address 0x%x, data 0x%x", address, data); @@ -1688,6 +1689,10 @@ static int smsc911x_eeprom_write_location(struct smsc911x_data *pdata, if (!ret) { op = E2P_CMD_EPC_CMD_WRITE_ | address; smsc911x_reg_write(pdata, E2P_DATA, (u32)data); + + /* Workaround for hardware read-after-write restriction */ + temp = smsc911x_reg_read(pdata, BYTE_TEST); + ret = smsc911x_eeprom_send_cmd(pdata, op); } diff --git a/drivers/net/tokenring/madgemc.c b/drivers/net/tokenring/madgemc.c index 1933081..456f8bf 100644 --- a/drivers/net/tokenring/madgemc.c +++ b/drivers/net/tokenring/madgemc.c @@ -142,7 +142,7 @@ static void madgemc_sifwritew(struct net_device *dev, unsigned short val, unsign return; } - +static struct net_device_ops madgemc_netdev_ops __read_mostly; static int __devinit madgemc_probe(struct device *device) { @@ -168,7 +168,7 @@ static int __devinit madgemc_probe(struct device *device) goto getout; } - dev->dma = 0; + dev->netdev_ops = &madgemc_netdev_ops; card = kmalloc(sizeof(struct card_info), GFP_KERNEL); if (card==NULL) { @@ -348,9 +348,6 @@ static int __devinit madgemc_probe(struct device *device) memcpy(tp->ProductID, "Madge MCA 16/4 ", PROD_ID_SIZE + 1); - dev->open = madgemc_open; - dev->stop = madgemc_close; - tp->tmspriv = card; dev_set_drvdata(device, dev); @@ -758,6 +755,10 @@ static struct mca_driver madgemc_driver = { static int __init madgemc_init (void) { + madgemc_netdev_ops = tms380tr_netdev_ops; + madgemc_netdev_ops.ndo_open = madgemc_open; + madgemc_netdev_ops.ndo_stop = madgemc_close; + return mca_register_driver (&madgemc_driver); } diff --git a/drivers/net/tokenring/proteon.c b/drivers/net/tokenring/proteon.c index b8c955f..16e8783 100644 --- a/drivers/net/tokenring/proteon.c +++ b/drivers/net/tokenring/proteon.c @@ -116,6 +116,8 @@ nodev: return -ENODEV; } +static struct net_device_ops proteon_netdev_ops __read_mostly; + static int __init setup_card(struct net_device *dev, struct device *pdev) { struct net_local *tp; @@ -167,8 +169,7 @@ static int __init setup_card(struct net_device *dev, struct device *pdev) tp->tmspriv = NULL; - dev->open = proteon_open; - dev->stop = tms380tr_close; + dev->netdev_ops = &proteon_netdev_ops; if (dev->irq == 0) { @@ -352,6 +353,10 @@ static int __init proteon_init(void) struct platform_device *pdev; int i, num = 0, err = 0; + proteon_netdev_ops = tms380tr_netdev_ops; + proteon_netdev_ops.ndo_open = proteon_open; + proteon_netdev_ops.ndo_stop = tms380tr_close; + err = platform_driver_register(&proteon_driver); if (err) return err; diff --git a/drivers/net/tokenring/skisa.c b/drivers/net/tokenring/skisa.c index c0f58f0..46db5c5 100644 --- a/drivers/net/tokenring/skisa.c +++ b/drivers/net/tokenring/skisa.c @@ -133,6 +133,8 @@ static int __init sk_isa_probe1(struct net_device *dev, int ioaddr) return 0; } +static struct net_device_ops sk_isa_netdev_ops __read_mostly; + static int __init setup_card(struct net_device *dev, struct device *pdev) { struct net_local *tp; @@ -184,8 +186,7 @@ static int __init setup_card(struct net_device *dev, struct device *pdev) tp->tmspriv = NULL; - dev->open = sk_isa_open; - dev->stop = tms380tr_close; + dev->netdev_ops = &sk_isa_netdev_ops; if (dev->irq == 0) { @@ -362,6 +363,10 @@ static int __init sk_isa_init(void) struct platform_device *pdev; int i, num = 0, err = 0; + sk_isa_netdev_ops = tms380tr_netdev_ops; + sk_isa_netdev_ops.ndo_open = sk_isa_open; + sk_isa_netdev_ops.ndo_stop = tms380tr_close; + err = platform_driver_register(&sk_isa_driver); if (err) return err; diff --git a/drivers/net/tokenring/smctr.c b/drivers/net/tokenring/smctr.c index 9d7db2c..a91d9c5 100644 --- a/drivers/net/tokenring/smctr.c +++ b/drivers/net/tokenring/smctr.c @@ -124,7 +124,6 @@ static unsigned int smctr_get_num_rx_bdbs(struct net_device *dev); static int smctr_get_physical_drop_number(struct net_device *dev); static __u8 *smctr_get_rx_pointer(struct net_device *dev, short queue); static int smctr_get_station_id(struct net_device *dev); -static struct net_device_stats *smctr_get_stats(struct net_device *dev); static FCBlock *smctr_get_tx_fcb(struct net_device *dev, __u16 queue, __u16 bytes_count); static int smctr_get_upstream_neighbor_addr(struct net_device *dev); @@ -3633,6 +3632,14 @@ out: return ERR_PTR(err); } +static const struct net_device_ops smctr_netdev_ops = { + .ndo_open = smctr_open, + .ndo_stop = smctr_close, + .ndo_start_xmit = smctr_send_packet, + .ndo_tx_timeout = smctr_timeout, + .ndo_get_stats = smctr_get_stats, + .ndo_set_multicast_list = smctr_set_multicast_list, +}; static int __init smctr_probe1(struct net_device *dev, int ioaddr) { @@ -3683,13 +3690,8 @@ static int __init smctr_probe1(struct net_device *dev, int ioaddr) (unsigned int)dev->base_addr, dev->irq, tp->rom_base, tp->ram_base); - dev->open = smctr_open; - dev->stop = smctr_close; - dev->hard_start_xmit = smctr_send_packet; - dev->tx_timeout = smctr_timeout; + dev->netdev_ops = &smctr_netdev_ops; dev->watchdog_timeo = HZ; - dev->get_stats = smctr_get_stats; - dev->set_multicast_list = &smctr_set_multicast_list; return (0); out: diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c index 6a07ba9..1d637f4 100644 --- a/drivers/net/wan/sdla.c +++ b/drivers/net/wan/sdla.c @@ -714,19 +714,19 @@ static int sdla_transmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case SDLA_RET_OK: - flp->stats.tx_packets++; + dev->stats.tx_packets++; ret = DLCI_RET_OK; break; case SDLA_RET_CIR_OVERFLOW: case SDLA_RET_BUF_OVERSIZE: case SDLA_RET_NO_BUFS: - flp->stats.tx_dropped++; + dev->stats.tx_dropped++; ret = DLCI_RET_DROP; break; default: - flp->stats.tx_errors++; + dev->stats.tx_errors++; ret = DLCI_RET_ERR; break; } @@ -807,7 +807,7 @@ static void sdla_receive(struct net_device *dev) if (i == CONFIG_DLCI_MAX) { printk(KERN_NOTICE "%s: Received packet from invalid DLCI %i, ignoring.", dev->name, dlci); - flp->stats.rx_errors++; + dev->stats.rx_errors++; success = 0; } } @@ -819,7 +819,7 @@ static void sdla_receive(struct net_device *dev) if (skb == NULL) { printk(KERN_NOTICE "%s: Memory squeeze, dropping packet.\n", dev->name); - flp->stats.rx_dropped++; + dev->stats.rx_dropped++; success = 0; } else @@ -859,7 +859,7 @@ static void sdla_receive(struct net_device *dev) if (success) { - flp->stats.rx_packets++; + dev->stats.rx_packets++; dlp = netdev_priv(master); (*dlp->receive)(skb, master); } @@ -1590,13 +1590,14 @@ fail: return err; } -static struct net_device_stats *sdla_stats(struct net_device *dev) -{ - struct frad_local *flp; - flp = netdev_priv(dev); - - return(&flp->stats); -} +static const struct net_device_ops sdla_netdev_ops = { + .ndo_open = sdla_open, + .ndo_stop = sdla_close, + .ndo_do_ioctl = sdla_ioctl, + .ndo_set_config = sdla_set_config, + .ndo_start_xmit = sdla_transmit, + .ndo_change_mtu = sdla_change_mtu, +}; static void setup_sdla(struct net_device *dev) { @@ -1604,20 +1605,13 @@ static void setup_sdla(struct net_device *dev) netdev_boot_setup_check(dev); + dev->netdev_ops = &sdla_netdev_ops; dev->flags = 0; dev->type = 0xFFFF; dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = SDLA_MAX_MTU; - dev->open = sdla_open; - dev->stop = sdla_close; - dev->do_ioctl = sdla_ioctl; - dev->set_config = sdla_set_config; - dev->get_stats = sdla_stats; - dev->hard_start_xmit = sdla_transmit; - dev->change_mtu = sdla_change_mtu; - flp->activate = sdla_activate; flp->deactivate = sdla_deactivate; flp->assoc = sdla_assoc; diff --git a/drivers/net/wireless/arlan-main.c b/drivers/net/wireless/arlan-main.c index bfca15d..5b9f1e0 100644 --- a/drivers/net/wireless/arlan-main.c +++ b/drivers/net/wireless/arlan-main.c @@ -1030,7 +1030,17 @@ static int arlan_mac_addr(struct net_device *dev, void *p) return 0; } - +static const struct net_device_ops arlan_netdev_ops = { + .ndo_open = arlan_open, + .ndo_stop = arlan_close, + .ndo_start_xmit = arlan_tx, + .ndo_get_stats = arlan_statistics, + .ndo_set_multicast_list = arlan_set_multicast, + .ndo_change_mtu = arlan_change_mtu, + .ndo_set_mac_address = arlan_mac_addr, + .ndo_tx_timeout = arlan_tx_timeout, + .ndo_validate_addr = eth_validate_addr, +}; static int __init arlan_setup_device(struct net_device *dev, int num) { @@ -1042,14 +1052,7 @@ static int __init arlan_setup_device(struct net_device *dev, int num) ap->conf = (struct arlan_shmem *)(ap+1); dev->tx_queue_len = tx_queue_len; - dev->open = arlan_open; - dev->stop = arlan_close; - dev->hard_start_xmit = arlan_tx; - dev->get_stats = arlan_statistics; - dev->set_multicast_list = arlan_set_multicast; - dev->change_mtu = arlan_change_mtu; - dev->set_mac_address = arlan_mac_addr; - dev->tx_timeout = arlan_tx_timeout; + dev->netdev_ops = &arlan_netdev_ops; dev->watchdog_timeo = 3*HZ; ap->irq_test_done = 0; diff --git a/drivers/net/wireless/wavelan.c b/drivers/net/wireless/wavelan.c index b728541..3ab3eb9 100644 --- a/drivers/net/wireless/wavelan.c +++ b/drivers/net/wireless/wavelan.c @@ -735,9 +735,9 @@ if (lp->tx_n_in_use > 0) if (tx_status & AC_SFLD_OK) { int ncollisions; - lp->stats.tx_packets++; + dev->stats.tx_packets++; ncollisions = tx_status & AC_SFLD_MAXCOL; - lp->stats.collisions += ncollisions; + dev->stats.collisions += ncollisions; #ifdef DEBUG_TX_INFO if (ncollisions > 0) printk(KERN_DEBUG @@ -745,9 +745,9 @@ if (lp->tx_n_in_use > 0) dev->name, ncollisions); #endif } else { - lp->stats.tx_errors++; + dev->stats.tx_errors++; if (tx_status & AC_SFLD_S10) { - lp->stats.tx_carrier_errors++; + dev->stats.tx_carrier_errors++; #ifdef DEBUG_TX_FAIL printk(KERN_DEBUG "%s: wv_complete(): tx error: no CS.\n", @@ -755,7 +755,7 @@ if (lp->tx_n_in_use > 0) #endif } if (tx_status & AC_SFLD_S9) { - lp->stats.tx_carrier_errors++; + dev->stats.tx_carrier_errors++; #ifdef DEBUG_TX_FAIL printk(KERN_DEBUG "%s: wv_complete(): tx error: lost CTS.\n", @@ -763,7 +763,7 @@ if (lp->tx_n_in_use > 0) #endif } if (tx_status & AC_SFLD_S8) { - lp->stats.tx_fifo_errors++; + dev->stats.tx_fifo_errors++; #ifdef DEBUG_TX_FAIL printk(KERN_DEBUG "%s: wv_complete(): tx error: slow DMA.\n", @@ -771,7 +771,7 @@ if (lp->tx_n_in_use > 0) #endif } if (tx_status & AC_SFLD_S6) { - lp->stats.tx_heartbeat_errors++; + dev->stats.tx_heartbeat_errors++; #ifdef DEBUG_TX_FAIL printk(KERN_DEBUG "%s: wv_complete(): tx error: heart beat.\n", @@ -779,7 +779,7 @@ if (lp->tx_n_in_use > 0) #endif } if (tx_status & AC_SFLD_S5) { - lp->stats.tx_aborted_errors++; + dev->stats.tx_aborted_errors++; #ifdef DEBUG_TX_FAIL printk(KERN_DEBUG "%s: wv_complete(): tx error: too many collisions.\n", @@ -1346,20 +1346,6 @@ static void wv_init_info(struct net_device * dev) * or wireless extensions */ -/*------------------------------------------------------------------*/ -/* - * Get the current Ethernet statistics. This may be called with the - * card open or closed. - * Used when the user read /proc/net/dev - */ -static en_stats *wavelan_get_stats(struct net_device * dev) -{ -#ifdef DEBUG_IOCTL_TRACE - printk(KERN_DEBUG "%s: <>wavelan_get_stats()\n", dev->name); -#endif - - return &((net_local *)netdev_priv(dev))->stats; -} /*------------------------------------------------------------------*/ /* @@ -2466,7 +2452,7 @@ wv_packet_read(struct net_device * dev, u16 buf_off, int sksize) "%s: wv_packet_read(): could not alloc_skb(%d, GFP_ATOMIC).\n", dev->name, sksize); #endif - lp->stats.rx_dropped++; + dev->stats.rx_dropped++; return; } @@ -2526,8 +2512,8 @@ wv_packet_read(struct net_device * dev, u16 buf_off, int sksize) netif_rx(skb); /* Keep statistics up to date */ - lp->stats.rx_packets++; - lp->stats.rx_bytes += sksize; + dev->stats.rx_packets++; + dev->stats.rx_bytes += sksize; #ifdef DEBUG_RX_TRACE printk(KERN_DEBUG "%s: <-wv_packet_read()\n", dev->name); @@ -2608,7 +2594,7 @@ static void wv_receive(struct net_device * dev) #endif } else { /* If reception was no successful */ - lp->stats.rx_errors++; + dev->stats.rx_errors++; #ifdef DEBUG_RX_INFO printk(KERN_DEBUG @@ -2624,7 +2610,7 @@ static void wv_receive(struct net_device * dev) #endif if ((fd.fd_status & FD_STATUS_S7) != 0) { - lp->stats.rx_length_errors++; + dev->stats.rx_length_errors++; #ifdef DEBUG_RX_FAIL printk(KERN_DEBUG "%s: wv_receive(): frame too short.\n", @@ -2633,7 +2619,7 @@ static void wv_receive(struct net_device * dev) } if ((fd.fd_status & FD_STATUS_S8) != 0) { - lp->stats.rx_over_errors++; + dev->stats.rx_over_errors++; #ifdef DEBUG_RX_FAIL printk(KERN_DEBUG "%s: wv_receive(): rx DMA overrun.\n", @@ -2642,7 +2628,7 @@ static void wv_receive(struct net_device * dev) } if ((fd.fd_status & FD_STATUS_S9) != 0) { - lp->stats.rx_fifo_errors++; + dev->stats.rx_fifo_errors++; #ifdef DEBUG_RX_FAIL printk(KERN_DEBUG "%s: wv_receive(): ran out of resources.\n", @@ -2651,7 +2637,7 @@ static void wv_receive(struct net_device * dev) } if ((fd.fd_status & FD_STATUS_S10) != 0) { - lp->stats.rx_frame_errors++; + dev->stats.rx_frame_errors++; #ifdef DEBUG_RX_FAIL printk(KERN_DEBUG "%s: wv_receive(): alignment error.\n", @@ -2660,7 +2646,7 @@ static void wv_receive(struct net_device * dev) } if ((fd.fd_status & FD_STATUS_S11) != 0) { - lp->stats.rx_crc_errors++; + dev->stats.rx_crc_errors++; #ifdef DEBUG_RX_FAIL printk(KERN_DEBUG "%s: wv_receive(): CRC error.\n", @@ -2826,7 +2812,7 @@ static int wv_packet_write(struct net_device * dev, void *buf, short length) dev->trans_start = jiffies; /* Keep stats up to date. */ - lp->stats.tx_bytes += length; + dev->stats.tx_bytes += length; if (lp->tx_first_in_use == I82586NULL) lp->tx_first_in_use = txblock; @@ -4038,6 +4024,22 @@ static int wavelan_close(struct net_device * dev) return 0; } +static const struct net_device_ops wavelan_netdev_ops = { + .ndo_open = wavelan_open, + .ndo_stop = wavelan_close, + .ndo_start_xmit = wavelan_packet_xmit, + .ndo_set_multicast_list = wavelan_set_multicast_list, + .ndo_tx_timeout = wavelan_watchdog, + .ndo_change_mtu = eth_change_mtu, + .ndo_validate_addr = eth_validate_addr, +#ifdef SET_MAC_ADDRESS + .ndo_set_mac_address = wavelan_set_mac_address +#else + .ndo_set_mac_address = eth_mac_addr, +#endif +}; + + /*------------------------------------------------------------------*/ /* * Probe an I/O address, and if the WaveLAN is there configure the @@ -4130,17 +4132,8 @@ static int __init wavelan_config(struct net_device *dev, unsigned short ioaddr) /* Init spinlock */ spin_lock_init(&lp->spinlock); - dev->open = wavelan_open; - dev->stop = wavelan_close; - dev->hard_start_xmit = wavelan_packet_xmit; - dev->get_stats = wavelan_get_stats; - dev->set_multicast_list = &wavelan_set_multicast_list; - dev->tx_timeout = &wavelan_watchdog; - dev->watchdog_timeo = WATCHDOG_JIFFIES; -#ifdef SET_MAC_ADDRESS - dev->set_mac_address = &wavelan_set_mac_address; -#endif /* SET_MAC_ADDRESS */ - + dev->netdev_ops = &wavelan_netdev_ops; + dev->watchdog_timeo = WATCHDOG_JIFFIES; dev->wireless_handlers = &wavelan_handler_def; lp->wireless_data.spy_data = &lp->spy_data; dev->wireless_data = &lp->wireless_data; diff --git a/drivers/net/wireless/wavelan.p.h b/drivers/net/wireless/wavelan.p.h index 44d31bb..2daa021 100644 --- a/drivers/net/wireless/wavelan.p.h +++ b/drivers/net/wireless/wavelan.p.h @@ -459,11 +459,9 @@ static const char *version = "wavelan.c : v24 (SMP + wireless extensions) 11/12/ /****************************** TYPES ******************************/ /* Shortcuts */ -typedef struct net_device_stats en_stats; typedef struct iw_statistics iw_stats; typedef struct iw_quality iw_qual; -typedef struct iw_freq iw_freq; -typedef struct net_local net_local; +typedef struct iw_freq iw_freq;typedef struct net_local net_local; typedef struct timer_list timer_list; /* Basic types */ @@ -475,15 +473,12 @@ typedef u_char mac_addr[WAVELAN_ADDR_SIZE]; /* Hardware address */ * For each network interface, Linux keeps data in two structures: "device" * keeps the generic data (same format for everybody) and "net_local" keeps * additional specific data. - * Note that some of this specific data is in fact generic (en_stats, for - * example). */ struct net_local { net_local * next; /* linked list of the devices */ struct net_device * dev; /* reverse link */ spinlock_t spinlock; /* Serialize access to the hardware (SMP) */ - en_stats stats; /* Ethernet interface statistics */ int nresets; /* number of hardware resets */ u_char reconfig_82586; /* We need to reconfigure the controller. */ u_char promiscuous; /* promiscuous mode */ @@ -601,8 +596,6 @@ static void static inline void wv_init_info(struct net_device *); /* display startup info */ /* ------------------- IOCTL, STATS & RECONFIG ------------------- */ -static en_stats * - wavelan_get_stats(struct net_device *); /* Give stats /proc/net/dev */ static iw_stats * wavelan_get_wireless_stats(struct net_device *); static void diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 60e16a5..673f220 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -153,7 +153,6 @@ struct frhdr struct dlci_local { - struct net_device_stats stats; struct net_device *master; struct net_device *slave; struct dlci_conf config; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index adbc50a..7b1a652 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -437,6 +437,29 @@ extern void xt_free_table_info(struct xt_table_info *info); extern void xt_table_entry_swap_rcu(struct xt_table_info *old, struct xt_table_info *new); +/* + * This helper is performance critical and must be inlined + */ +static inline unsigned long ifname_compare_aligned(const char *_a, + const char *_b, + const char *_mask) +{ + const unsigned long *a = (const unsigned long *)_a; + const unsigned long *b = (const unsigned long *)_b; + const unsigned long *mask = (const unsigned long *)_mask; + unsigned long ret; + + ret = (a[0] ^ b[0]) & mask[0]; + if (IFNAMSIZ > sizeof(unsigned long)) + ret |= (a[1] ^ b[1]) & mask[1]; + if (IFNAMSIZ > 2 * sizeof(unsigned long)) + ret |= (a[2] ^ b[2]) & mask[2]; + if (IFNAMSIZ > 3 * sizeof(unsigned long)) + ret |= (a[3] ^ b[3]) & mask[3]; + BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); + return ret; +} + #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/net/ethoc.h b/include/net/ethoc.h new file mode 100644 index 0000000..96f3789 --- /dev/null +++ b/include/net/ethoc.h @@ -0,0 +1,22 @@ +/* + * linux/include/net/ethoc.h + * + * Copyright (C) 2008-2009 Avionic Design GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Written by Thierry Reding <thierry.reding@avionic-design.de> + */ + +#ifndef LINUX_NET_ETHOC_H +#define LINUX_NET_ETHOC_H 1 + +struct ethoc_platform_data { + u8 hwaddr[IFHWADDRLEN]; + s8 phy_id; +}; + +#endif /* !LINUX_NET_ETHOC_H */ + diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 4dfb793..6c3f964 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -91,8 +91,7 @@ struct nf_conn_help { #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> -struct nf_conn -{ +struct nf_conn { /* Usage count in here is 1 for hash table/destruct timer, 1 per skb, plus 1 for any connection(s) we are `master' for */ struct nf_conntrack ct_general; @@ -126,7 +125,6 @@ struct nf_conn #ifdef CONFIG_NET_NS struct net *ct_net; #endif - struct rcu_head rcu; }; static inline struct nf_conn * @@ -190,9 +188,13 @@ static inline void nf_ct_put(struct nf_conn *ct) extern int nf_ct_l3proto_try_module_get(unsigned short l3proto); extern void nf_ct_l3proto_module_put(unsigned short l3proto); -extern struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced); -extern void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced, - unsigned int size); +/* + * Allocate a hashtable of hlist_head (if nulls == 0), + * or hlist_nulls_head (if nulls == 1) + */ +extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls); + +extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple); diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 66d65a7..ee2a4b3 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -14,6 +14,8 @@ struct module; +#define NF_CT_HELPER_NAME_LEN 16 + struct nf_conntrack_helper { struct hlist_node hnode; /* Internal use. */ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index 0378676..9f99d36 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -53,10 +53,17 @@ struct nf_conntrack_l3proto int (*tuple_to_nlattr)(struct sk_buff *skb, const struct nf_conntrack_tuple *t); + /* + * Calculate size of tuple nlattr + */ + int (*nlattr_tuple_size)(void); + int (*nlattr_to_tuple)(struct nlattr *tb[], struct nf_conntrack_tuple *t); const struct nla_policy *nla_policy; + size_t nla_size; + #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_header; struct ctl_path *ctl_table_path; diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index b01070b..ba32ed7 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -64,16 +64,22 @@ struct nf_conntrack_l4proto /* convert protoinfo to nfnetink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, const struct nf_conn *ct); + /* Calculate protoinfo nlattr size */ + int (*nlattr_size)(void); /* convert nfnetlink attributes to protoinfo */ int (*from_nlattr)(struct nlattr *tb[], struct nf_conn *ct); int (*tuple_to_nlattr)(struct sk_buff *skb, const struct nf_conntrack_tuple *t); + /* Calculate tuple nlattr size */ + int (*nlattr_tuple_size)(void); int (*nlattr_to_tuple)(struct nlattr *tb[], struct nf_conntrack_tuple *t); const struct nla_policy *nla_policy; + size_t nla_size; + #ifdef CONFIG_SYSCTL struct ctl_table_header **ctl_table_header; struct ctl_table *ctl_table; @@ -107,6 +113,7 @@ extern int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple); extern int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t); +extern int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; #ifdef CONFIG_SYSCTL diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index f2f6aa7..2628c15 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -12,6 +12,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <linux/list_nulls.h> /* A `tuple' is a structure containing the information to uniquely identify a connection. ie. if two packets have the same tuple, they @@ -146,9 +147,8 @@ static inline void nf_ct_dump_tuple(const struct nf_conntrack_tuple *t) ((enum ip_conntrack_dir)(h)->tuple.dst.dir) /* Connections have two entries in the hash table: one for each way */ -struct nf_conntrack_tuple_hash -{ - struct hlist_node hnode; +struct nf_conntrack_tuple_hash { + struct hlist_nulls_node hnnode; struct nf_conntrack_tuple tuple; }; diff --git a/include/net/netlink.h b/include/net/netlink.h index 8a6150a..eddb502 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -230,6 +230,7 @@ extern int nla_validate(struct nlattr *head, int len, int maxtype, extern int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, const struct nla_policy *policy); +extern int nla_policy_len(const struct nla_policy *, int); extern struct nlattr * nla_find(struct nlattr *head, int len, int attrtype); extern size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize); diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index f4498a6..9dc5840 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -2,6 +2,7 @@ #define __NETNS_CONNTRACK_H #include <linux/list.h> +#include <linux/list_nulls.h> #include <asm/atomic.h> struct ctl_table_header; @@ -10,9 +11,9 @@ struct nf_conntrack_ecache; struct netns_ct { atomic_t count; unsigned int expect_count; - struct hlist_head *hash; + struct hlist_nulls_head *hash; struct hlist_head *expect_hash; - struct hlist_head unconfirmed; + struct hlist_nulls_head unconfirmed; struct ip_conntrack_stat *stat; #ifdef CONFIG_NF_CONNTRACK_EVENTS struct nf_conntrack_ecache *ecache; diff --git a/lib/nlattr.c b/lib/nlattr.c index 80009a2..c4706eb 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -133,6 +133,32 @@ errout: } /** + * nla_policy_len - Determin the max. length of a policy + * @policy: policy to use + * @n: number of policies + * + * Determines the max. length of the policy. It is currently used + * to allocated Netlink buffers roughly the size of the actual + * message. + * + * Returns 0 on success or a negative error code. + */ +int +nla_policy_len(const struct nla_policy *p, int n) +{ + int i, len = 0; + + for (i = 0; i < n; i++) { + if (p->len) + len += nla_total_size(p->len); + else if (nla_attr_minlen[p->type]) + len += nla_total_size(nla_attr_minlen[p->type]); + } + + return len; +} + +/** * nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected @@ -467,6 +493,7 @@ EXPORT_SYMBOL(nla_append); #endif EXPORT_SYMBOL(nla_validate); +EXPORT_SYMBOL(nla_policy_len); EXPORT_SYMBOL(nla_parse); EXPORT_SYMBOL(nla_find); EXPORT_SYMBOL(nla_strlcpy); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 3e0671d..d6a9243 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1571,14 +1571,10 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr usat->sat_family != AF_APPLETALK) return -EINVAL; - /* netatalk doesn't implement this check */ + /* netatalk didn't implement this check */ if (usat->sat_addr.s_node == ATADDR_BCAST && !sock_flag(sk, SOCK_BROADCAST)) { - printk(KERN_INFO "SO_BROADCAST: Fix your netatalk as " - "it will break before 2.2\n"); -#if 0 return -EPERM; -#endif } } else { if (sk->sk_state != TCP_ESTABLISHED) diff --git a/net/core/dev.c b/net/core/dev.c index 052dd47..63ec4bf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2627,18 +2627,15 @@ static int process_backlog(struct napi_struct *napi, int quota) local_irq_disable(); skb = __skb_dequeue(&queue->input_pkt_queue); if (!skb) { + __napi_complete(napi); local_irq_enable(); - napi_complete(napi); - goto out; + break; } local_irq_enable(); - napi_gro_receive(napi, skb); + netif_receive_skb(skb); } while (++work < quota && jiffies == start_time); - napi_gro_flush(napi); - -out: return work; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 84b9c17..35c5f6a 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -81,19 +81,7 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask) { #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - const unsigned long *a = (const unsigned long *)_a; - const unsigned long *b = (const unsigned long *)_b; - const unsigned long *mask = (const unsigned long *)_mask; - unsigned long ret; - - ret = (a[0] ^ b[0]) & mask[0]; - if (IFNAMSIZ > sizeof(unsigned long)) - ret |= (a[1] ^ b[1]) & mask[1]; - if (IFNAMSIZ > 2 * sizeof(unsigned long)) - ret |= (a[2] ^ b[2]) & mask[2]; - if (IFNAMSIZ > 3 * sizeof(unsigned long)) - ret |= (a[3] ^ b[3]) & mask[3]; - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); + unsigned long ret = ifname_compare_aligned(_a, _b, _mask); #else unsigned long ret = 0; const u16 *a = (const u16 *)_a; @@ -404,7 +392,9 @@ static int mark_source_chains(struct xt_table_info *newinfo, && unconditional(&e->arp)) || visited) { unsigned int oldpos, size; - if (t->verdict < -NF_MAX_VERDICT - 1) { + if ((strcmp(t->target.u.user.name, + ARPT_STANDARD_TARGET) == 0) && + t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", t->verdict); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e5294ae..82ee7c9 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -74,25 +74,6 @@ do { \ Hence the start of any table is given by get_table() below. */ -static unsigned long ifname_compare(const char *_a, const char *_b, - const unsigned char *_mask) -{ - const unsigned long *a = (const unsigned long *)_a; - const unsigned long *b = (const unsigned long *)_b; - const unsigned long *mask = (const unsigned long *)_mask; - unsigned long ret; - - ret = (a[0] ^ b[0]) & mask[0]; - if (IFNAMSIZ > sizeof(unsigned long)) - ret |= (a[1] ^ b[1]) & mask[1]; - if (IFNAMSIZ > 2 * sizeof(unsigned long)) - ret |= (a[2] ^ b[2]) & mask[2]; - if (IFNAMSIZ > 3 * sizeof(unsigned long)) - ret |= (a[3] ^ b[3]) & mask[3]; - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); - return ret; -} - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -121,7 +102,7 @@ ip_packet_match(const struct iphdr *ip, return false; } - ret = ifname_compare(indev, ipinfo->iniface, ipinfo->iniface_mask); + ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask); if (FWINV(ret != 0, IPT_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", @@ -130,7 +111,7 @@ ip_packet_match(const struct iphdr *ip, return false; } - ret = ifname_compare(outdev, ipinfo->outiface, ipinfo->outiface_mask); + ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask); if (FWINV(ret != 0, IPT_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", @@ -507,7 +488,9 @@ mark_source_chains(struct xt_table_info *newinfo, && unconditional(&e->ip)) || visited) { unsigned int oldpos, size; - if (t->verdict < -NF_MAX_VERDICT - 1) { + if ((strcmp(t->target.u.user.name, + IPT_STANDARD_TARGET) == 0) && + t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", t->verdict); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 8b681f2..7d2ead7 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -328,6 +328,11 @@ static int ipv4_nlattr_to_tuple(struct nlattr *tb[], return 0; } + +static int ipv4_nlattr_tuple_size(void) +{ + return nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1); +} #endif static struct nf_sockopt_ops so_getorigdst = { @@ -347,6 +352,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .get_l4proto = ipv4_get_l4proto, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = ipv4_tuple_to_nlattr, + .nlattr_tuple_size = ipv4_nlattr_tuple_size, .nlattr_to_tuple = ipv4_nlattr_to_tuple, .nla_policy = ipv4_nla_policy, #endif diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 6ba5c55..8668a3d 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -25,40 +25,42 @@ struct ct_iter_state { unsigned int bucket; }; -static struct hlist_node *ct_get_first(struct seq_file *seq) +static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - struct hlist_node *n; + struct hlist_nulls_node *n; for (st->bucket = 0; st->bucket < nf_conntrack_htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); - if (n) + if (!is_a_nulls(n)) return n; } return NULL; } -static struct hlist_node *ct_get_next(struct seq_file *seq, - struct hlist_node *head) +static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, + struct hlist_nulls_node *head) { struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; head = rcu_dereference(head->next); - while (head == NULL) { - if (++st->bucket >= nf_conntrack_htable_size) - return NULL; + while (is_a_nulls(head)) { + if (likely(get_nulls_value(head) == st->bucket)) { + if (++st->bucket >= nf_conntrack_htable_size) + return NULL; + } head = rcu_dereference(net->ct.hash[st->bucket].first); } return head; } -static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos) +static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) { - struct hlist_node *head = ct_get_first(seq); + struct hlist_nulls_node *head = ct_get_first(seq); if (head) while (pos && (head = ct_get_next(seq, head))) @@ -87,69 +89,76 @@ static void ct_seq_stop(struct seq_file *s, void *v) static int ct_seq_show(struct seq_file *s, void *v) { - const struct nf_conntrack_tuple_hash *hash = v; - const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); + struct nf_conntrack_tuple_hash *hash = v; + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + int ret = 0; NF_CT_ASSERT(ct); + if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + return 0; + /* we only want to print DIR_ORIGINAL */ if (NF_CT_DIRECTION(hash)) - return 0; + goto release; if (nf_ct_l3num(ct) != AF_INET) - return 0; + goto release; l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); NF_CT_ASSERT(l4proto); + ret = -ENOSPC; if (seq_printf(s, "%-8s %u %ld ", l4proto->name, nf_ct_protonum(ct), timer_pending(&ct->timeout) ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0) - return -ENOSPC; + goto release; if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct)) - return -ENOSPC; + goto release; if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, l3proto, l4proto)) - return -ENOSPC; + goto release; if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) - return -ENOSPC; + goto release; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) if (seq_printf(s, "[UNREPLIED] ")) - return -ENOSPC; + goto release; if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l3proto, l4proto)) - return -ENOSPC; + goto release; if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) - return -ENOSPC; + goto release; if (test_bit(IPS_ASSURED_BIT, &ct->status)) if (seq_printf(s, "[ASSURED] ")) - return -ENOSPC; + goto release; #ifdef CONFIG_NF_CONNTRACK_MARK if (seq_printf(s, "mark=%u ", ct->mark)) - return -ENOSPC; + goto release; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK if (seq_printf(s, "secmark=%u ", ct->secmark)) - return -ENOSPC; + goto release; #endif if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) - return -ENOSPC; - - return 0; + goto release; + ret = 0; +release: + nf_ct_put(ct); + return ret; } static const struct seq_operations ct_seq_ops = { diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 2a8bee2..23b2c2e 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -262,6 +262,11 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[], return 0; } + +static int icmp_nlattr_tuple_size(void) +{ + return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); +} #endif #ifdef CONFIG_SYSCTL @@ -309,6 +314,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .me = NULL, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = icmp_tuple_to_nlattr, + .nlattr_tuple_size = icmp_nlattr_tuple_size, .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index a65cf69..fe65187 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -679,7 +679,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, static int __net_init nf_nat_net_init(struct net *net) { net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, - &net->ipv4.nat_vmalloced); + &net->ipv4.nat_vmalloced, 0); if (!net->ipv4.nat_bysource) return -ENOMEM; return 0; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index f171e8d..8f04bd9 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -75,8 +75,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || !idev || unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); - rcu_read_unlock(); - goto out; + goto drop; } memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); @@ -147,7 +146,6 @@ err: drop: rcu_read_unlock(); kfree_skb(skb); -out: return 0; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 34af7bb..e89cfa3 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -89,25 +89,6 @@ ip6t_ext_hdr(u8 nexthdr) (nexthdr == IPPROTO_DSTOPTS) ); } -static unsigned long ifname_compare(const char *_a, const char *_b, - const unsigned char *_mask) -{ - const unsigned long *a = (const unsigned long *)_a; - const unsigned long *b = (const unsigned long *)_b; - const unsigned long *mask = (const unsigned long *)_mask; - unsigned long ret; - - ret = (a[0] ^ b[0]) & mask[0]; - if (IFNAMSIZ > sizeof(unsigned long)) - ret |= (a[1] ^ b[1]) & mask[1]; - if (IFNAMSIZ > 2 * sizeof(unsigned long)) - ret |= (a[2] ^ b[2]) & mask[2]; - if (IFNAMSIZ > 3 * sizeof(unsigned long)) - ret |= (a[3] ^ b[3]) & mask[3]; - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); - return ret; -} - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -138,7 +119,7 @@ ip6_packet_match(const struct sk_buff *skb, return false; } - ret = ifname_compare(indev, ip6info->iniface, ip6info->iniface_mask); + ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (FWINV(ret != 0, IP6T_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", @@ -147,7 +128,7 @@ ip6_packet_match(const struct sk_buff *skb, return false; } - ret = ifname_compare(outdev, ip6info->outiface, ip6info->outiface_mask); + ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (FWINV(ret != 0, IP6T_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", @@ -536,7 +517,9 @@ mark_source_chains(struct xt_table_info *newinfo, && unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; - if (t->verdict < -NF_MAX_VERDICT - 1) { + if ((strcmp(t->target.u.user.name, + IP6T_STANDARD_TARGET) == 0) && + t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", t->verdict); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index e6852f6..2a15c2d 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -342,6 +342,11 @@ static int ipv6_nlattr_to_tuple(struct nlattr *tb[], return 0; } + +static int ipv6_nlattr_tuple_size(void) +{ + return nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1); +} #endif struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { @@ -353,6 +358,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { .get_l4proto = ipv6_get_l4proto, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = ipv6_tuple_to_nlattr, + .nlattr_tuple_size = ipv6_nlattr_tuple_size, .nlattr_to_tuple = ipv6_nlattr_to_tuple, .nla_policy = ipv6_nla_policy, #endif diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 41b8a95..9903227 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -269,6 +269,11 @@ static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], return 0; } + +static int icmpv6_nlattr_tuple_size(void) +{ + return nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); +} #endif #ifdef CONFIG_SYSCTL @@ -300,6 +305,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .error = icmpv6_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, + .nlattr_tuple_size = icmpv6_nlattr_tuple_size, .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 2562d05..2c967e4 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -374,7 +374,7 @@ config NETFILTER_XT_TARGET_HL config NETFILTER_XT_TARGET_LED tristate '"LED" target support' - depends on LEDS_CLASS + depends on LEDS_CLASS && LED_TRIGGERS depends on NETFILTER_ADVANCED help This option adds a `LED' target, which allows you to blink LEDs in diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index dfb447b..8020db6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -29,6 +29,7 @@ #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/mm.h> +#include <linux/rculist_nulls.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> @@ -163,8 +164,8 @@ static void clean_from_lists(struct nf_conn *ct) { pr_debug("clean_from_lists(%p)\n", ct); - hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode); - hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode); /* Destroy all pending expectations */ nf_ct_remove_expectations(ct); @@ -204,8 +205,8 @@ destroy_conntrack(struct nf_conntrack *nfct) /* We overload first tuple to link into unconfirmed list. */ if (!nf_ct_is_confirmed(ct)) { - BUG_ON(hlist_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode)); - hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode); + BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); } NF_CT_STAT_INC(net, delete); @@ -242,18 +243,26 @@ static void death_by_timeout(unsigned long ul_conntrack) nf_ct_put(ct); } +/* + * Warning : + * - Caller must take a reference on returned object + * and recheck nf_ct_tuple_equal(tuple, &h->tuple) + * OR + * - Caller must lock nf_conntrack_lock before calling this function + */ struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_tuple_hash *h; - struct hlist_node *n; + struct hlist_nulls_node *n; unsigned int hash = hash_conntrack(tuple); /* Disable BHs the entire time since we normally need to disable them * at least once for the stats anyway. */ local_bh_disable(); - hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) { +begin: + hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { if (nf_ct_tuple_equal(tuple, &h->tuple)) { NF_CT_STAT_INC(net, found); local_bh_enable(); @@ -261,6 +270,13 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple) } NF_CT_STAT_INC(net, searched); } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(n) != hash) + goto begin; local_bh_enable(); return NULL; @@ -275,11 +291,18 @@ nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple) struct nf_conn *ct; rcu_read_lock(); +begin: h = __nf_conntrack_find(net, tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; + else { + if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) { + nf_ct_put(ct); + goto begin; + } + } } rcu_read_unlock(); @@ -293,9 +316,9 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, { struct net *net = nf_ct_net(ct); - hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode, + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.hash[hash]); - hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode, + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &net->ct.hash[repl_hash]); } @@ -318,7 +341,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; - struct hlist_node *n; + struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -350,17 +373,17 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ - hlist_for_each_entry(h, n, &net->ct.hash[hash], hnode) + hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, &h->tuple)) goto out; - hlist_for_each_entry(h, n, &net->ct.hash[repl_hash], hnode) + hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple)) goto out; /* Remove from unconfirmed list */ - hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); __nf_conntrack_hash_insert(ct, hash, repl_hash); /* Timer relative to confirmation time, not original @@ -399,14 +422,14 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, { struct net *net = nf_ct_net(ignored_conntrack); struct nf_conntrack_tuple_hash *h; - struct hlist_node *n; + struct hlist_nulls_node *n; unsigned int hash = hash_conntrack(tuple); /* Disable BHs the entire time since we need to disable them at * least once for the stats anyway. */ rcu_read_lock_bh(); - hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) { + hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack && nf_ct_tuple_equal(tuple, &h->tuple)) { NF_CT_STAT_INC(net, found); @@ -430,14 +453,14 @@ static noinline int early_drop(struct net *net, unsigned int hash) /* Use oldest entry, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; struct nf_conn *ct = NULL, *tmp; - struct hlist_node *n; + struct hlist_nulls_node *n; unsigned int i, cnt = 0; int dropped = 0; rcu_read_lock(); for (i = 0; i < nf_conntrack_htable_size; i++) { - hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], - hnode) { + hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], + hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); if (!test_bit(IPS_ASSURED_BIT, &tmp->status)) ct = tmp; @@ -508,27 +531,19 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, #ifdef CONFIG_NET_NS ct->ct_net = net; #endif - INIT_RCU_HEAD(&ct->rcu); return ct; } EXPORT_SYMBOL_GPL(nf_conntrack_alloc); -static void nf_conntrack_free_rcu(struct rcu_head *head) -{ - struct nf_conn *ct = container_of(head, struct nf_conn, rcu); - - nf_ct_ext_free(ct); - kmem_cache_free(nf_conntrack_cachep, ct); -} - void nf_conntrack_free(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); nf_ct_ext_destroy(ct); atomic_dec(&net->ct.count); - call_rcu(&ct->rcu, nf_conntrack_free_rcu); + nf_ct_ext_free(ct); + kmem_cache_free(nf_conntrack_cachep, ct); } EXPORT_SYMBOL_GPL(nf_conntrack_free); @@ -594,7 +609,7 @@ init_conntrack(struct net *net, } /* Overload tuple linked list to put us in unconfirmed list. */ - hlist_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode, + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.unconfirmed); spin_unlock_bh(&nf_conntrack_lock); @@ -906,6 +921,12 @@ int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], return 0; } EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple); + +int nf_ct_port_nlattr_tuple_size(void) +{ + return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); +} +EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size); #endif /* Used by ipt_REJECT and ip6t_REJECT. */ @@ -934,17 +955,17 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; - struct hlist_node *n; + struct hlist_nulls_node *n; spin_lock_bh(&nf_conntrack_lock); for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { - hlist_for_each_entry(h, n, &net->ct.hash[*bucket], hnode) { + hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) goto found; } } - hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode) { + hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) set_bit(IPS_DYING_BIT, &ct->status); @@ -992,7 +1013,7 @@ static int kill_all(struct nf_conn *i, void *data) return 1; } -void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced, unsigned int size) +void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size) { if (vmalloced) vfree(hash); @@ -1060,26 +1081,28 @@ void nf_conntrack_cleanup(struct net *net) } } -struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced) +void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls) { - struct hlist_head *hash; - unsigned int size, i; + struct hlist_nulls_head *hash; + unsigned int nr_slots, i; + size_t sz; *vmalloced = 0; - size = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_head)); - hash = (void*)__get_free_pages(GFP_KERNEL|__GFP_NOWARN, - get_order(sizeof(struct hlist_head) - * size)); + BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); + nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); + sz = nr_slots * sizeof(struct hlist_nulls_head); + hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, + get_order(sz)); if (!hash) { *vmalloced = 1; printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); - hash = vmalloc(sizeof(struct hlist_head) * size); + hash = __vmalloc(sz, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); } - if (hash) - for (i = 0; i < size; i++) - INIT_HLIST_HEAD(&hash[i]); + if (hash && nulls) + for (i = 0; i < nr_slots; i++) + INIT_HLIST_NULLS_HEAD(&hash[i], i); return hash; } @@ -1090,7 +1113,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) int i, bucket, vmalloced, old_vmalloced; unsigned int hashsize, old_size; int rnd; - struct hlist_head *hash, *old_hash; + struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; /* On boot, we can set this without any fancy locking. */ @@ -1101,7 +1124,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hashsize) return -EINVAL; - hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced); + hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1); if (!hash) return -ENOMEM; @@ -1116,12 +1139,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) */ spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < nf_conntrack_htable_size; i++) { - while (!hlist_empty(&init_net.ct.hash[i])) { - h = hlist_entry(init_net.ct.hash[i].first, - struct nf_conntrack_tuple_hash, hnode); - hlist_del_rcu(&h->hnode); + while (!hlist_nulls_empty(&init_net.ct.hash[i])) { + h = hlist_nulls_entry(init_net.ct.hash[i].first, + struct nf_conntrack_tuple_hash, hnnode); + hlist_nulls_del_rcu(&h->hnnode); bucket = __hash_conntrack(&h->tuple, hashsize, rnd); - hlist_add_head(&h->hnode, &hash[bucket]); + hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } old_size = nf_conntrack_htable_size; @@ -1172,7 +1195,7 @@ static int nf_conntrack_init_init_net(void) nf_conntrack_cachep = kmem_cache_create("nf_conntrack", sizeof(struct nf_conn), - 0, 0, NULL); + 0, SLAB_DESTROY_BY_RCU, NULL); if (!nf_conntrack_cachep) { printk(KERN_ERR "Unable to create nf_conn slab cache\n"); ret = -ENOMEM; @@ -1202,7 +1225,7 @@ static int nf_conntrack_init_net(struct net *net) int ret; atomic_set(&net->ct.count, 0); - INIT_HLIST_HEAD(&net->ct.unconfirmed); + INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; @@ -1212,7 +1235,7 @@ static int nf_conntrack_init_net(struct net *net) if (ret < 0) goto err_ecache; net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, - &net->ct.hash_vmalloc); + &net->ct.hash_vmalloc, 1); if (!net->ct.hash) { ret = -ENOMEM; printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 357ba39..3940f99 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -604,7 +604,7 @@ int nf_conntrack_expect_init(struct net *net) net->ct.expect_count = 0; net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, - &net->ct.expect_vmalloc); + &net->ct.expect_vmalloc, 0); if (net->ct.expect_hash == NULL) goto err1; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index a51bdac..30b8e90 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -142,6 +142,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(me->expect_policy == NULL); BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); + BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); mutex_lock(&nf_ct_helper_mutex); hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); @@ -158,6 +159,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; const struct hlist_node *n, *next; + const struct hlist_nulls_node *nn; unsigned int i; /* Get rid of expectations */ @@ -174,10 +176,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } /* Get rid of expecteds, set helpers to NULL. */ - hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode) + hlist_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) unhelp(h, me); for (i = 0; i < nf_conntrack_htable_size; i++) { - hlist_for_each_entry(h, n, &net->ct.hash[i], hnode) + hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) unhelp(h, me); } } @@ -217,7 +219,7 @@ int nf_conntrack_helper_init(void) nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, - &nf_ct_helper_vmalloc); + &nf_ct_helper_vmalloc, 0); if (!nf_ct_helper_hash) return -ENOMEM; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7a16bd4..c6439c7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/rculist.h> +#include <linux/rculist_nulls.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/skbuff.h> @@ -404,6 +405,78 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_EVENTS +/* + * The general structure of a ctnetlink event is + * + * CTA_TUPLE_ORIG + * <l3/l4-proto-attributes> + * CTA_TUPLE_REPLY + * <l3/l4-proto-attributes> + * CTA_ID + * ... + * CTA_PROTOINFO + * <l4-proto-attributes> + * CTA_TUPLE_MASTER + * <l3/l4-proto-attributes> + * + * Therefore the formular is + * + * size = sizeof(headers) + sizeof(generic_nlas) + 3 * sizeof(tuple_nlas) + * + sizeof(protoinfo_nlas) + */ +static struct sk_buff * +ctnetlink_alloc_skb(const struct nf_conntrack_tuple *tuple, gfp_t gfp) +{ + struct nf_conntrack_l3proto *l3proto; + struct nf_conntrack_l4proto *l4proto; + int len; + +#define NLA_TYPE_SIZE(type) nla_total_size(sizeof(type)) + + /* proto independant part */ + len = NLMSG_SPACE(sizeof(struct nfgenmsg)) + + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + + 3 * NLA_TYPE_SIZE(u_int8_t) /* CTA_PROTO_NUM */ + + NLA_TYPE_SIZE(u_int32_t) /* CTA_ID */ + + NLA_TYPE_SIZE(u_int32_t) /* CTA_STATUS */ +#ifdef CONFIG_NF_CT_ACCT + + 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ + + 2 * NLA_TYPE_SIZE(uint64_t) /* CTA_COUNTERS_PACKETS */ + + 2 * NLA_TYPE_SIZE(uint64_t) /* CTA_COUNTERS_BYTES */ +#endif + + NLA_TYPE_SIZE(u_int32_t) /* CTA_TIMEOUT */ + + nla_total_size(0) /* CTA_PROTOINFO */ + + nla_total_size(0) /* CTA_HELP */ + + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ +#ifdef CONFIG_NF_CONNTRACK_SECMARK + + NLA_TYPE_SIZE(u_int32_t) /* CTA_SECMARK */ +#endif +#ifdef CONFIG_NF_NAT_NEEDED + + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_POS */ + + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_BEFORE */ + + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_AFTER */ +#endif +#ifdef CONFIG_NF_CONNTRACK_MARK + + NLA_TYPE_SIZE(u_int32_t) /* CTA_MARK */ +#endif + ; + +#undef NLA_TYPE_SIZE + + rcu_read_lock(); + l3proto = __nf_ct_l3proto_find(tuple->src.l3num); + len += l3proto->nla_size; + + l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); + len += l4proto->nla_size; + rcu_read_unlock(); + + return alloc_skb(len, gfp); +} + static int ctnetlink_conntrack_event(struct notifier_block *this, unsigned long events, void *ptr) { @@ -437,7 +510,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, if (!item->report && !nfnetlink_has_listeners(group)) return NOTIFY_DONE; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + skb = ctnetlink_alloc_skb(tuple(ct, IP_CT_DIR_ORIGINAL), GFP_ATOMIC); if (!skb) return NOTIFY_DONE; @@ -536,7 +609,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; - struct hlist_node *n; + struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; @@ -544,27 +617,27 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: - hlist_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]], - hnode) { + hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]], + hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); + if (!atomic_inc_not_zero(&ct->ct_general.use)) + continue; /* Dump entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then dump everything. */ if (l3proto && nf_ct_l3num(ct) != l3proto) - continue; + goto releasect; if (cb->args[1]) { if (ct != last) - continue; + goto releasect; cb->args[1] = 0; } if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, IPCTNL_MSG_CT_NEW, 1, ct) < 0) { - if (!atomic_inc_not_zero(&ct->ct_general.use)) - continue; cb->args[1] = (unsigned long)ct; goto out; } @@ -577,6 +650,8 @@ restart: if (acct) memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX])); } +releasect: + nf_ct_put(ct); } if (cb->args[1]) { cb->args[1] = 0; @@ -1242,13 +1317,12 @@ ctnetlink_create_conntrack(struct nlattr *cda[], if (err < 0) goto err2; - master_h = __nf_conntrack_find(&init_net, &master); + master_h = nf_conntrack_find_get(&init_net, &master); if (master_h == NULL) { err = -ENOENT; goto err2; } master_ct = nf_ct_tuplehash_to_ctrack(master_h); - nf_conntrack_get(&master_ct->ct_general); __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 9a62b4e..1a4568b 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -167,6 +167,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) if (proto->l3proto >= AF_MAX) return -EBUSY; + if (proto->tuple_to_nlattr && !proto->nlattr_tuple_size) + return -EINVAL; + mutex_lock(&nf_ct_proto_mutex); if (nf_ct_l3protos[proto->l3proto] != &nf_conntrack_l3proto_generic) { ret = -EBUSY; @@ -177,6 +180,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) if (ret < 0) goto out_unlock; + if (proto->nlattr_tuple_size) + proto->nla_size = 3 * proto->nlattr_tuple_size(); + rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto); out_unlock: @@ -263,6 +269,10 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) if (l4proto->l3proto >= PF_MAX) return -EBUSY; + if ((l4proto->to_nlattr && !l4proto->nlattr_size) + || (l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size)) + return -EINVAL; + mutex_lock(&nf_ct_proto_mutex); if (!nf_ct_protos[l4proto->l3proto]) { /* l3proto may be loaded latter. */ @@ -290,6 +300,12 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) if (ret < 0) goto out_unlock; + l4proto->nla_size = 0; + if (l4proto->nlattr_size) + l4proto->nla_size += l4proto->nlattr_size(); + if (l4proto->nlattr_tuple_size) + l4proto->nla_size += 3 * l4proto->nlattr_tuple_size(); + rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], l4proto); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index d3d5a7f..50dac8db 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -669,6 +669,12 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) write_unlock_bh(&dccp_lock); return 0; } + +static int dccp_nlattr_size(void) +{ + return nla_total_size(0) /* CTA_PROTOINFO_DCCP */ + + nla_policy_len(dccp_nla_policy, CTA_PROTOINFO_DCCP_MAX + 1); +} #endif #ifdef CONFIG_SYSCTL @@ -749,8 +755,10 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .print_conntrack = dccp_print_conntrack, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = dccp_to_nlattr, + .nlattr_size = dccp_nlattr_size, .from_nlattr = nlattr_to_dccp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif @@ -771,6 +779,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .to_nlattr = dccp_to_nlattr, .from_nlattr = nlattr_to_dccp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 1b279f9..117b801 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -293,6 +293,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .me = THIS_MODULE, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 74e0379..101b4ad 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -537,6 +537,12 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) return 0; } + +static int sctp_nlattr_size(void) +{ + return nla_total_size(0) /* CTA_PROTOINFO_SCTP */ + + nla_policy_len(sctp_nla_policy, CTA_PROTOINFO_SCTP_MAX + 1); +} #endif #ifdef CONFIG_SYSCTL @@ -668,8 +674,10 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .me = THIS_MODULE, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = sctp_to_nlattr, + .nlattr_size = sctp_nlattr_size, .from_nlattr = nlattr_to_sctp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif @@ -696,8 +704,10 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .me = THIS_MODULE, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = sctp_to_nlattr, + .nlattr_size = sctp_nlattr_size, .from_nlattr = nlattr_to_sctp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 0aeb8b0..b5ccf2b 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1184,6 +1184,17 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) return 0; } + +static int tcp_nlattr_size(void) +{ + return nla_total_size(0) /* CTA_PROTOINFO_TCP */ + + nla_policy_len(tcp_nla_policy, CTA_PROTOINFO_TCP_MAX + 1); +} + +static int tcp_nlattr_tuple_size(void) +{ + return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); +} #endif #ifdef CONFIG_SYSCTL @@ -1399,9 +1410,11 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = .error = tcp_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = tcp_to_nlattr, + .nlattr_size = tcp_nlattr_size, .from_nlattr = nlattr_to_tcp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, + .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_SYSCTL @@ -1429,9 +1442,11 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = .error = tcp_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = tcp_to_nlattr, + .nlattr_size = tcp_nlattr_size, .from_nlattr = nlattr_to_tcp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, + .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_SYSCTL diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index d402117..70809d1 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -195,6 +195,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_SYSCTL @@ -222,6 +223,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_SYSCTL diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4579d8d..4614696 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -180,6 +180,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = .error = udplite_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4da54b0..1935153 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -44,40 +44,42 @@ struct ct_iter_state { unsigned int bucket; }; -static struct hlist_node *ct_get_first(struct seq_file *seq) +static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - struct hlist_node *n; + struct hlist_nulls_node *n; for (st->bucket = 0; st->bucket < nf_conntrack_htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); - if (n) + if (!is_a_nulls(n)) return n; } return NULL; } -static struct hlist_node *ct_get_next(struct seq_file *seq, - struct hlist_node *head) +static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, + struct hlist_nulls_node *head) { struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; head = rcu_dereference(head->next); - while (head == NULL) { - if (++st->bucket >= nf_conntrack_htable_size) - return NULL; + while (is_a_nulls(head)) { + if (likely(get_nulls_value(head) == st->bucket)) { + if (++st->bucket >= nf_conntrack_htable_size) + return NULL; + } head = rcu_dereference(net->ct.hash[st->bucket].first); } return head; } -static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos) +static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) { - struct hlist_node *head = ct_get_first(seq); + struct hlist_nulls_node *head = ct_get_first(seq); if (head) while (pos && (head = ct_get_next(seq, head))) @@ -107,67 +109,74 @@ static void ct_seq_stop(struct seq_file *s, void *v) /* return 0 on success, 1 in case of error */ static int ct_seq_show(struct seq_file *s, void *v) { - const struct nf_conntrack_tuple_hash *hash = v; - const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); + struct nf_conntrack_tuple_hash *hash = v; + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + int ret = 0; NF_CT_ASSERT(ct); + if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + return 0; /* we only want to print DIR_ORIGINAL */ if (NF_CT_DIRECTION(hash)) - return 0; + goto release; l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); NF_CT_ASSERT(l4proto); + ret = -ENOSPC; if (seq_printf(s, "%-8s %u %-8s %u %ld ", l3proto->name, nf_ct_l3num(ct), l4proto->name, nf_ct_protonum(ct), timer_pending(&ct->timeout) ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0) - return -ENOSPC; + goto release; if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct)) - return -ENOSPC; + goto release; if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, l3proto, l4proto)) - return -ENOSPC; + goto release; if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) - return -ENOSPC; + goto release; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) if (seq_printf(s, "[UNREPLIED] ")) - return -ENOSPC; + goto release; if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l3proto, l4proto)) - return -ENOSPC; + goto release; if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) - return -ENOSPC; + goto release; if (test_bit(IPS_ASSURED_BIT, &ct->status)) if (seq_printf(s, "[ASSURED] ")) - return -ENOSPC; + goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) if (seq_printf(s, "mark=%u ", ct->mark)) - return -ENOSPC; + goto release; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK if (seq_printf(s, "secmark=%u ", ct->secmark)) - return -ENOSPC; + goto release; #endif if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) - return -ENOSPC; + goto release; + ret = 0; +release: + nf_ct_put(ct); return 0; } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 7f404cc..6809809 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -108,7 +108,7 @@ static int count_them(struct xt_connlimit_data *data, const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; struct xt_connlimit_conn *tmp; - const struct nf_conn *found_ct; + struct nf_conn *found_ct; struct list_head *hash; bool addit = true; int matches = 0; @@ -123,7 +123,7 @@ static int count_them(struct xt_connlimit_data *data, /* check the saved connections */ list_for_each_entry_safe(conn, tmp, hash, list) { - found = __nf_conntrack_find(&init_net, &conn->tuple); + found = nf_conntrack_find_get(&init_net, &conn->tuple); found_ct = NULL; if (found != NULL) @@ -151,6 +151,7 @@ static int count_them(struct xt_connlimit_data *data, * we do not care about connections which are * closed already -> ditch it */ + nf_ct_put(found_ct); list_del(&conn->list); kfree(conn); continue; @@ -160,6 +161,7 @@ static int count_them(struct xt_connlimit_data *data, match->family)) /* same source network -> be counted! */ ++matches; + nf_ct_put(found_ct); } rcu_read_unlock(); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 44a234e..8d28ca5 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -20,23 +20,6 @@ MODULE_DESCRIPTION("Xtables: Bridge physical device match"); MODULE_ALIAS("ipt_physdev"); MODULE_ALIAS("ip6t_physdev"); -static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask) -{ - const unsigned long *a = (const unsigned long *)_a; - const unsigned long *b = (const unsigned long *)_b; - const unsigned long *mask = (const unsigned long *)_mask; - unsigned long ret; - - ret = (a[0] ^ b[0]) & mask[0]; - if (IFNAMSIZ > sizeof(unsigned long)) - ret |= (a[1] ^ b[1]) & mask[1]; - if (IFNAMSIZ > 2 * sizeof(unsigned long)) - ret |= (a[2] ^ b[2]) & mask[2]; - if (IFNAMSIZ > 3 * sizeof(unsigned long)) - ret |= (a[3] ^ b[3]) & mask[3]; - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); - return ret; -} static bool physdev_mt(const struct sk_buff *skb, const struct xt_match_param *par) @@ -85,7 +68,7 @@ physdev_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (!(info->bitmask & XT_PHYSDEV_OP_IN)) goto match_outdev; indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname; - ret = ifname_compare(indev, info->physindev, info->in_mask); + ret = ifname_compare_aligned(indev, info->physindev, info->in_mask); if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN)) return false; @@ -95,7 +78,7 @@ match_outdev: return true; outdev = nf_bridge->physoutdev ? nf_bridge->physoutdev->name : nulldevname; - ret = ifname_compare(outdev, info->physoutdev, info->out_mask); + ret = ifname_compare_aligned(outdev, info->physoutdev, info->out_mask); return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT)); } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 6d9c58e..d1c16bb 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1086,7 +1086,11 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, SOCK_DEBUG(sk, "NET/ROM: sendto: Addresses built.\n"); - /* Build a packet */ + /* Build a packet - the conventional user limit is 236 bytes. We can + do ludicrously large NetROM frames but must not overflow */ + if (len > 65536) + return -EMSGSIZE; + SOCK_DEBUG(sk, "NET/ROM: sendto: building packet.\n"); size = len + NR_NETWORK_LEN + NR_TRANSPORT_LEN; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 6501396..0f36e8d 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1124,6 +1124,10 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, /* Build a packet */ SOCK_DEBUG(sk, "ROSE: sendto: building packet.\n"); + /* Sanity check the packet size */ + if (len > 65535) + return -EMSGSIZE; + size = len + AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN; if ((skb = sock_alloc_send_skb(sk, size, msg->msg_flags & MSG_DONTWAIT, &err)) == NULL) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 9ca17b1..ed80af8 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1035,6 +1035,12 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, sx25.sx25_addr = x25->dest_addr; } + /* Sanity check the packet size */ + if (len > 65535) { + rc = -EMSGSIZE; + goto out; + } + SOCK_DEBUG(sk, "x25_sendmsg: sendto: Addresses built.\n"); /* Build a packet */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 62a5425..8227172 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1615,7 +1615,7 @@ void xfrm_state_walk_done(struct xfrm_state_walk *walk) spin_lock_bh(&xfrm_state_lock); list_del(&walk->all); - spin_lock_bh(&xfrm_state_lock); + spin_unlock_bh(&xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); |