A-A+
ethtool的内核流程跟踪
这些天开始下决心写写Linux网络方面的文章。由于能力和时间有限，当前还没有对Linux的网络有深入的了解。我一开始打算从网卡基本知识到PHY寄存器，到MAC控制器，到以太网协议栈，一步一步地学习。但实际中发现不能如此，在公司不同在学校，不可能有集中的时间精力去学习的，比如，刚刚使用了iperf来测试网卡性能，又要在内核中打印出PHY芯片寄存器，而前提是要对PHY有一定了解。同时又要了解设备所处的网络拓扑，又不得不去看看交换机方面的资料。在这种情形下，似乎没有规律地做事，完全由工作需求来驱动。在做事的同时我也在记录要点，希望可以整理出主线。在业余时便将这些要点发散、整理。因此，在写文章时就已经对自己进行定位，从感性的认识上入手，慢慢去学习，去接触。比如，因工作上的需要学习了ethtool，于是以此为切入点，看看内核关于ethtool到底是怎么控制的。再比如从网卡使能到禁止跟踪相关的内核流程。
前面的文章讲了ethtool工具的源码分析，内核集成了ethtool命令的控制，所以用户空间才能如此方便地查询、设置以太网卡。本文主要讲一下内核空间ethtool的跟踪。
ethtool可以认为是一种框架，内核已经集成了，它担负着用户空间和具体网络设备驱动之间的交互，包括查询、设置网卡信息。
主要结构体在函数在include/linux/ethtool.h中定义。
控制命令结构体如下：
struct ethtool_cmd { __u32 cmd; __u32 supported; /* Features this interface supports */ __u32 advertising; /* Features this interface advertises */ __u16 speed; /* The forced speed, 10Mb, 100Mb, gigabit */ __u8 duplex; /* Duplex, half or full */ __u8 port; /* Which connector port */ __u8 phy_address; __u8 transceiver; /* Which transceiver to use */ __u8 autoneg; /* Enable or disable autonegotiation */ __u8 mdio_support; __u32 maxtxpkt; /* Tx pkts before generating tx int */ __u32 maxrxpkt; /* Rx pkts before generating rx int */ __u16 speed_hi; __u8 eth_tp_mdix; __u8 reserved2; __u32 lp_advertising; /* Features the link partner advertises */ __u32 reserved[2]; };
当查询网卡信息时这个结构体保存着查询到的信息，比如网速、双工，是否自动协商，等。当设置网卡时，里面的字段就是用户指定的信息。这个结构体负责着信息传递的作用。
另一个重要的网络操作函数集结构体定义如下：
struct ethtool_ops { int (*get_settings)(struct net_device *, struct ethtool_cmd *); int (*set_settings)(struct net_device *, struct ethtool_cmd *); void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); void (*get_wol)(struct net_device *, struct ethtool_wolinfo *); int (*set_wol)(struct net_device *, struct ethtool_wolinfo *); u32 (*get_msglevel)(struct net_device *); void (*set_msglevel)(struct net_device *, u32); int (*nway_reset)(struct net_device *); u32 (*get_link)(struct net_device *); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); int (*set_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); int (*get_coalesce)(struct net_device *, struct ethtool_coalesce *); int (*set_coalesce)(struct net_device *, struct ethtool_coalesce *); void (*get_ringparam)(struct net_device *, struct ethtool_ringparam *); int (*set_ringparam)(struct net_device *, struct ethtool_ringparam *); void (*get_pauseparam)(struct net_device *, struct ethtool_pauseparam*); int (*set_pauseparam)(struct net_device *, struct ethtool_pauseparam*); u32 (*get_rx_csum)(struct net_device *); int (*set_rx_csum)(struct net_device *, u32); u32 (*get_tx_csum)(struct net_device *); int (*set_tx_csum)(struct net_device *, u32); u32 (*get_sg)(struct net_device *); int (*set_sg)(struct net_device *, u32); u32 (*get_tso)(struct net_device *); int (*set_tso)(struct net_device *, u32); void (*self_test)(struct net_device *, struct ethtool_test *, u64 *); void (*get_strings)(struct net_device *, u32 stringset, u8 *); int (*phys_id)(struct net_device *, u32); void (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *); int (*begin)(struct net_device *); void (*complete)(struct net_device *); u32 (*get_ufo)(struct net_device *); int (*set_ufo)(struct net_device *, u32); u32 (*get_flags)(struct net_device *); int (*set_flags)(struct net_device *, u32); u32 (*get_priv_flags)(struct net_device *); int (*set_priv_flags)(struct net_device *, u32); int (*get_sset_count)(struct net_device *, int); int (*get_rxnfc)(struct net_device *, struct ethtool_rxnfc *, void *); int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); int (*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *); int (*get_rx_ntuple)(struct net_device *, u32 stringset, void *); int (*get_rxfh_indir)(struct net_device *, struct ethtool_rxfh_indir *); int (*set_rxfh_indir)(struct net_device *, const struct ethtool_rxfh_indir *); };
里面的函数指针由具体的网络驱动程序来赋值。在下面将要分析到的函数，我们可以看到实际上就是调用ethtool_ops中的函数指针的。
常用的共用函数：
u32 ethtool_op_get_link(struct net_device *dev); u32 ethtool_op_get_rx_csum(struct net_device *dev); u32 ethtool_op_get_tx_csum(struct net_device *dev); int ethtool_op_set_tx_csum(struct net_device *dev, u32 data); int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data); int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data); u32 ethtool_op_get_sg(struct net_device *dev); int ethtool_op_set_sg(struct net_device *dev, u32 data); u32 ethtool_op_get_tso(struct net_device *dev); int ethtool_op_set_tso(struct net_device *dev, u32 data); u32 ethtool_op_get_ufo(struct net_device *dev); int ethtool_op_set_ufo(struct net_device *dev, u32 data); u32 ethtool_op_get_flags(struct net_device *dev); int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported); void ethtool_ntuple_flush(struct net_device *dev);
这些函数可以由具体的驱动程序来使用，比如获取当前连接状态的ethtool_op_get_link，就有很多驱动在使用。当然至于使用哪些，由网络驱动来决定。
下面是常见的控制命令和宏定义：
//支持的命令： /* CMDs currently supported */ #define ETHTOOL_GSET 0x00000001 /* Get settings. */ #define ETHTOOL_SSET 0x00000002 /* Set settings. */ #define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */ #define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ #define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ #define ETHTOOL_SWOL 0x00000006 /* Set wake-on-lan options. */ #define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ #define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ #define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ #define ETHTOOL_GLINK 0x0000000a /* Get link status (ethtool_value) */ #define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ #define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ #define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ #define ETHTOOL_SCOALESCE 0x0000000f /* Set coalesce config. */ #define ETHTOOL_GRINGPARAM 0x00000010 /* Get ring parameters */ #define ETHTOOL_SRINGPARAM 0x00000011 /* Set ring parameters. */ #define ETHTOOL_GPAUSEPARAM 0x00000012 /* Get pause parameters */ #define ETHTOOL_SPAUSEPARAM 0x00000013 /* Set pause parameters. */ #define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ #define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ #define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ #define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ //网卡特性 //设备支持的特性： /* Indicates what features are supported by the interface. */ #define SUPPORTED_10baseT_Half (1 << 0) #define SUPPORTED_10baseT_Full (1 << 1) #define SUPPORTED_100baseT_Half (1 << 2) #define SUPPORTED_100baseT_Full (1 << 3) #define SUPPORTED_1000baseT_Half (1 << 4) #define SUPPORTED_1000baseT_Full (1 << 5) #define SUPPORTED_Autoneg (1 << 6) #define SUPPORTED_TP (1 << 7) #define SUPPORTED_AUI (1 << 8) #define SUPPORTED_MII (1 << 9) #define SUPPORTED_FIBRE (1 << 10) #define SUPPORTED_BNC (1 << 11) #define SUPPORTED_10000baseT_Full (1 << 12) #define SUPPORTED_Pause (1 << 13) #define SUPPORTED_Asym_Pause (1 << 14) #define SUPPORTED_2500baseX_Full (1 << 15) #define SUPPORTED_Backplane (1 << 16) #define SUPPORTED_1000baseKX_Full (1 << 17) #define SUPPORTED_10000baseKX4_Full (1 << 18) #define SUPPORTED_10000baseKR_Full (1 << 19) #define SUPPORTED_10000baseR_FEC (1 << 20) //设备宣称所支持的特性(此处待继续学习) /* Indicates what features are advertised by the interface. */ #define ADVERTISED_10baseT_Half (1 << 0) #define ADVERTISED_10baseT_Full (1 << 1) #define ADVERTISED_100baseT_Half (1 << 2) #define ADVERTISED_100baseT_Full (1 << 3) #define ADVERTISED_1000baseT_Half (1 << 4) #define ADVERTISED_1000baseT_Full (1 << 5) #define ADVERTISED_Autoneg (1 << 6) #define ADVERTISED_TP (1 << 7) #define ADVERTISED_AUI (1 << 8) #define ADVERTISED_MII (1 << 9) #define ADVERTISED_FIBRE (1 << 10) #define ADVERTISED_BNC (1 << 11) #define ADVERTISED_10000baseT_Full (1 << 12) #define ADVERTISED_Pause (1 << 13) #define ADVERTISED_Asym_Pause (1 << 14) #define ADVERTISED_2500baseX_Full (1 << 15) #define ADVERTISED_Backplane (1 << 16) #define ADVERTISED_1000baseKX_Full (1 << 17) #define ADVERTISED_10000baseKX4_Full (1 << 18) #define ADVERTISED_10000baseKR_Full (1 << 19) #define ADVERTISED_10000baseR_FEC (1 << 20) // 速度 /* The forced speed, 10Mb, 100Mb, gigabit, 2.5Gb, 10GbE. */ #define SPEED_10 10 #define SPEED_100 100 #define SPEED_1000 1000 #define SPEED_2500 2500 #define SPEED_10000 10000 // 双工 /* Duplex, half or full. */ #define DUPLEX_HALF 0x00 #define DUPLEX_FULL 0x01 // 端口类型 /* Which connector port. */ #define PORT_TP 0x00 //双绞线 #define PORT_AUI 0x01 #define PORT_MII 0x02 #define PORT_FIBRE 0x03 #define PORT_BNC 0x04 #define PORT_DA 0x05 #define PORT_NONE 0xef #define PORT_OTHER 0xff // 自动协商 /* Enable or disable autonegotiation. If this is set to enable, * the forced link modes above are completely ignored. */ #define AUTONEG_DISABLE 0x00 #define AUTONEG_ENABLE 0x01
ethtool的关键函数为dev_ethtool，在该函数中根据不同的命令调用不同的函数。函数如下：
/* The main entry point in this file. Called from net/core/dev.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) { struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); void __user *useraddr = ifr->ifr_data; u32 ethcmd; int rc; unsigned long old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; if (!dev->ethtool_ops) { /* ETHTOOL_GDRVINFO does not require any driver support. * It is also unprivileged and does not change anything, * so we can take a shortcut to it. */ if (ethcmd == ETHTOOL_GDRVINFO) return ethtool_get_drvinfo(dev, useraddr); else return -EOPNOTSUPP; } /* Allow some commands to be done by anyone */ switch (ethcmd) { case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: case ETHTOOL_GCOALESCE: case ETHTOOL_GRINGPARAM: case ETHTOOL_GPAUSEPARAM: case ETHTOOL_GRXCSUM: case ETHTOOL_GTXCSUM: case ETHTOOL_GSG: case ETHTOOL_GSTRINGS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: case ETHTOOL_GUFO: case ETHTOOL_GGSO: case ETHTOOL_GGRO: case ETHTOOL_GFLAGS: case ETHTOOL_GPFLAGS: case ETHTOOL_GRXFH: case ETHTOOL_GRXRINGS: case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: break; default: if (!capable(CAP_NET_ADMIN)) return -EPERM; } if (dev->ethtool_ops->begin) { rc = dev->ethtool_ops->begin(dev); if (rc < 0) return rc; } old_features = dev->features; switch (ethcmd) { case ETHTOOL_GSET: rc = ethtool_get_settings(dev, useraddr); break; case ETHTOOL_SSET: rc = ethtool_set_settings(dev, useraddr); break; case ETHTOOL_GDRVINFO: rc = ethtool_get_drvinfo(dev, useraddr); break; case ETHTOOL_GREGS: rc = ethtool_get_regs(dev, useraddr); break; case ETHTOOL_GWOL: rc = ethtool_get_wol(dev, useraddr); break; case ETHTOOL_SWOL: rc = ethtool_set_wol(dev, useraddr); break; case ETHTOOL_GMSGLVL: rc = ethtool_get_value(dev, useraddr, ethcmd, dev->ethtool_ops->get_msglevel); break; case ETHTOOL_SMSGLVL: rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); break; case ETHTOOL_GLINK: rc = ethtool_get_value(dev, useraddr, ethcmd, dev->ethtool_ops->get_link); break; case ETHTOOL_GEEPROM: rc = ethtool_get_eeprom(dev, useraddr); break; case ETHTOOL_SEEPROM: rc = ethtool_set_eeprom(dev, useraddr); break; case ETHTOOL_GCOALESCE: rc = ethtool_get_coalesce(dev, useraddr); break; case ETHTOOL_SCOALESCE: rc = ethtool_set_coalesce(dev, useraddr); break; case ETHTOOL_GRINGPARAM: rc = ethtool_get_ringparam(dev, useraddr); break; case ETHTOOL_SRINGPARAM: rc = ethtool_set_ringparam(dev, useraddr); break; case ETHTOOL_GPAUSEPARAM: rc = ethtool_get_pauseparam(dev, useraddr); break; case ETHTOOL_SPAUSEPARAM: rc = ethtool_set_pauseparam(dev, useraddr); break; case ETHTOOL_GRXCSUM: rc = ethtool_get_value(dev, useraddr, ethcmd, (dev->ethtool_ops->get_rx_csum ? dev->ethtool_ops->get_rx_csum : ethtool_op_get_rx_csum)); break; case ETHTOOL_SRXCSUM: rc = ethtool_set_rx_csum(dev, useraddr); break; case ETHTOOL_GTXCSUM: rc = ethtool_get_value(dev, useraddr, ethcmd, (dev->ethtool_ops->get_tx_csum ? dev->ethtool_ops->get_tx_csum : ethtool_op_get_tx_csum)); break; case ETHTOOL_STXCSUM: rc = ethtool_set_tx_csum(dev, useraddr); break; case ETHTOOL_GSG: rc = ethtool_get_value(dev, useraddr, ethcmd, (dev->ethtool_ops->get_sg ? dev->ethtool_ops->get_sg : ethtool_op_get_sg)); break; case ETHTOOL_SSG: rc = ethtool_set_sg(dev, useraddr); break; case ETHTOOL_GTSO: rc = ethtool_get_value(dev, useraddr, ethcmd, (dev->ethtool_ops->get_tso ? dev->ethtool_ops->get_tso : ethtool_op_get_tso)); break; case ETHTOOL_STSO: rc = ethtool_set_tso(dev, useraddr); break; case ETHTOOL_TEST: rc = ethtool_self_test(dev, useraddr); break; case ETHTOOL_GSTRINGS: rc = ethtool_get_strings(dev, useraddr); break; case ETHTOOL_PHYS_ID: rc = ethtool_phys_id(dev, useraddr); break; default: rc = -EOPNOTSUPP; } if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (old_features != dev->features) netdev_features_change(dev); return rc; }
dev_ethtool函数是被dev_ioctl函数(位于net/core/dev.c)调用的，dev_ioctl是网络设备的ioctl总入口函数，ethtool用到的SIOCETHTOOL命令，实际是其中的一个命令分支，而如ETHTOOL_GSET之类的命令，是dev_ethtool函数的中命令。这两类的命令层次是十分明显的。dev_ioctl：
int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) { /* * See which interface the caller is talking about. */ switch (cmd) { case SIOCETHTOOL: dev_load(net, ifr.ifr_name); rtnl_lock(); ret = dev_ethtool(net, &ifr); rtnl_unlock(); if (!ret) { if (colon) *colon = ':'; if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) ret = -EFAULT; } return ret; } }
获取网卡信息的控制命令为ETHTOOL_GSET，调用的函数为ethtool_get_settings：
static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; int err; if (!dev->ethtool_ops->get_settings) return -EOPNOTSUPP; err = dev->ethtool_ops->get_settings(dev, &cmd); if (err < 0) return err; if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; return 0; }
而该函数实际调用的是ethtool_ops结构体中的get_settings。所有的命令控制过程大多是如此。
设置网卡信息：
static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd; if (!dev->ethtool_ops->set_settings) return -EOPNOTSUPP; if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; return dev->ethtool_ops->set_settings(dev, &cmd); }
常用的公共函数使用EXPORT_SYMBOL导出，以便其它模块也可以使用，如获取当前连接状态的函数：
u32 ethtool_op_get_link(struct net_device *dev) { return netif_carrier_ok(dev) ? 1 : 0; } EXPORT_SYMBOL(ethtool_op_get_link);
以Intel网卡驱动igb为例看看如何使用ethtool_ops。igb驱动代码位于drivers/net/igb。与ethtool有关的代码在igb_ethtool.c文件。ethtool_ops定义如下：
static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, .get_drvinfo = igb_get_drvinfo, .get_regs_len = igb_get_regs_len, .get_regs = igb_get_regs, .get_wol = igb_get_wol, .set_wol = igb_set_wol, .get_msglevel = igb_get_msglevel, .set_msglevel = igb_set_msglevel, .nway_reset = igb_nway_reset, .get_link = igb_get_link, .get_eeprom_len = igb_get_eeprom_len, .get_eeprom = igb_get_eeprom, .set_eeprom = igb_set_eeprom, .get_ringparam = igb_get_ringparam, .set_ringparam = igb_set_ringparam, .get_pauseparam = igb_get_pauseparam, .set_pauseparam = igb_set_pauseparam, .get_rx_csum = igb_get_rx_csum, .set_rx_csum = igb_set_rx_csum, .get_tx_csum = igb_get_tx_csum, .set_tx_csum = igb_set_tx_csum, .get_sg = ethtool_op_get_sg, .set_sg = ethtool_op_set_sg, .get_tso = ethtool_op_get_tso, .set_tso = igb_set_tso, .self_test = igb_diag_test, .get_strings = igb_get_strings, .phys_id = igb_phys_id, .get_sset_count = igb_get_sset_count, .get_ethtool_stats = igb_get_ethtool_stats, .get_coalesce = igb_get_coalesce, .set_coalesce = igb_set_coalesce, };
igb支持的函数(即ethtool工具可以使用的参数)很多。像get_sg，就直接使用了ethtool.c定义的ethtool_op_get_sg，其它大部分则自定义实现。igb_ethtool_ops在igb_set_ethtool_ops被调用，而igb_set_ethtool_ops则在igb的探测函数igb_probe中被调用，这样，当驱动运行时，ethtool也就可以使用了。
void igb_set_ethtool_ops(struct net_device *netdev) { SET_ETHTOOL_OPS(netdev, &igb_ethtool_ops); }
实际上就是将igb_ethtool_ops赋值给net_device结构体的ethtool_ops指针，从而使得ethtool.c中对应的函数指针可以被调用。比如dev->ethtool_ops->get_settings。
再看一下dm9000的使用，ethtool_ops定义：
static const struct ethtool_ops dm9000_ethtool_ops = { .get_drvinfo = dm9000_get_drvinfo, .get_settings = dm9000_get_settings, .set_settings = dm9000_set_settings, .get_msglevel = dm9000_get_msglevel, .set_msglevel = dm9000_set_msglevel, .nway_reset = dm9000_nway_reset, .get_link = dm9000_get_link, .get_wol = dm9000_get_wol, .set_wol = dm9000_set_wol, .get_eeprom_len = dm9000_get_eeprom_len, .get_eeprom = dm9000_get_eeprom, .set_eeprom = dm9000_set_eeprom, .get_rx_csum = dm9000_get_rx_csum, .set_rx_csum = dm9000_set_rx_csum, .get_tx_csum = ethtool_op_get_tx_csum, .set_tx_csum = dm9000_set_tx_csum, };
从上述结构体赋值可以看到，igb驱动支持的命令要比dm9000多很多。
同样在dm9000探测函数中进行赋值：
/* * Search DM9000 board, allocate space and register it */ static int __devinit dm9000_probe(struct platform_device *pdev) { struct dm9000_plat_data *pdata = pdev->dev.platform_data; struct board_info *db; /* Point a board information structure */ struct net_device *ndev; const unsigned char *mac_src; int ret = 0; int iosize; int i; u32 id_val; /* Init network device */ ndev = alloc_etherdev(sizeof(struct board_info)); if (!ndev) { dev_err(&pdev->dev, "could not allocate device.\n"); return -ENOMEM; } SET_NETDEV_DEV(ndev, &pdev->dev); dev_dbg(&pdev->dev, "dm9000_probe()\n"); /* setup board info structure */ db = netdev_priv(ndev); db->dev = &pdev->dev; db->ndev = ndev; // ... ndev->netdev_ops = &dm9000_netdev_ops; ndev->watchdog_timeo = msecs_to_jiffies(watchdog); ndev->ethtool_ops = &dm9000_ethtool_ops; // ... }
2015年3月29日 着手写
