From 3cc7587b30032b7c4dd9610a55a77519e84da7db Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Fri, 17 May 2013 09:10:34 +0000 Subject: Documentation/sysctl/net.txt: fix (attribute removal). This patch removes mentioning the sysfsf net_device weight attribute (class/net//weight) in Documentation/sysctl/net.txt, since the net sysfs weight attribute was removed by the following patch: [NET]: Make NAPI polling independent of struct net_device objects bea3348eef27e6044b6161fd04c3152215f96411 Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 98335b7a5337..c1f8640c2fc8 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -93,8 +93,7 @@ netdev_budget Maximum number of packets taken from all interfaces in one polling cycle (NAPI poll). In one polling cycle interfaces which are registered to polling are -probed in a round-robin manner. The limit of packets in one such probe can be -set per-device via sysfs class/net//weight . +probed in a round-robin manner. netdev_max_backlog ------------------ -- cgit v1.2.3 From 6dffbe53fbdcc7bd5f6379fa18264f060b0cf61d Mon Sep 17 00:00:00 2001 From: Tony Prisk Date: Sat, 18 May 2013 09:39:07 +0000 Subject: net: velocity: Add platform device support to VIA velocity driver Add support for the VIA Velocity network driver to be bound to a OF created platform device. Signed-off-by: Tony Prisk Signed-off-by: David S. Miller --- .../devicetree/bindings/net/via-velocity.txt | 20 + drivers/net/ethernet/via/Kconfig | 3 +- drivers/net/ethernet/via/via-velocity.c | 408 ++++++++++++++------- drivers/net/ethernet/via/via-velocity.h | 3 +- 4 files changed, 305 insertions(+), 129 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/via-velocity.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/via-velocity.txt b/Documentation/devicetree/bindings/net/via-velocity.txt new file mode 100644 index 000000000000..b3db469b1ad7 --- /dev/null +++ b/Documentation/devicetree/bindings/net/via-velocity.txt @@ -0,0 +1,20 @@ +* VIA Velocity 10/100/1000 Network Controller + +Required properties: +- compatible : Should be "via,velocity-vt6110" +- reg : Address and length of the io space +- interrupts : Should contain the controller interrupt line + +Optional properties: +- no-eeprom : PCI network cards use an external EEPROM to store data. Embedded + devices quite often set this data in uboot and do not provide an eeprom. + Specify this option if you have no external eeprom. + +Examples: + +eth0@d8004000 { + compatible = "via,velocity-vt6110"; + reg = <0xd8004000 0x400>; + interrupts = <10>; + no-eeprom; +}; diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig index 68a9ba66feba..6a87097d88c0 100644 --- a/drivers/net/ethernet/via/Kconfig +++ b/drivers/net/ethernet/via/Kconfig @@ -5,7 +5,6 @@ config NET_VENDOR_VIA bool "VIA devices" default y - depends on PCI ---help--- If you have a network (Ethernet) card belonging to this class, say Y and read the Ethernet-HOWTO, available from @@ -45,7 +44,7 @@ config VIA_RHINE_MMIO config VIA_VELOCITY tristate "VIA Velocity support" - depends on PCI + depends on (PCI || USE_OF) select CRC32 select CRC_CCITT select NET_CORE diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 5996cee0ffa7..76919948b4ee 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -65,7 +65,11 @@ #include #include #include +#include +#include +#include #include +#include #include #include #include @@ -80,10 +84,24 @@ #include "via-velocity.h" +enum velocity_bus_type { + BUS_PCI, + BUS_PLATFORM, +}; static int velocity_nics; static int msglevel = MSG_LEVEL_INFO; +static void velocity_set_power_state(struct velocity_info *vptr, char state) +{ + void *addr = vptr->mac_regs; + + if (vptr->pdev) + pci_set_power_state(vptr->pdev, state); + else + writeb(state, addr + 0x154); +} + /** * mac_get_cam_mask - Read a CAM mask * @regs: register block for this velocity @@ -362,12 +380,23 @@ static struct velocity_info_tbl chip_info_table[] = { * Describe the PCI device identifiers that we support in this * device driver. Used for hotplug autoloading. */ -static DEFINE_PCI_DEVICE_TABLE(velocity_id_table) = { + +static DEFINE_PCI_DEVICE_TABLE(velocity_pci_id_table) = { { PCI_DEVICE(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_612X) }, { } }; -MODULE_DEVICE_TABLE(pci, velocity_id_table); +MODULE_DEVICE_TABLE(pci, velocity_pci_id_table); + +/** + * Describe the OF device identifiers that we support in this + * device driver. Used for devicetree nodes. + */ +static struct of_device_id velocity_of_ids[] = { + { .compatible = "via,velocity-vt6110", .data = &chip_info_table[0] }, + { /* Sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, velocity_of_ids); /** * get_chip_name - identifier to name @@ -385,29 +414,6 @@ static const char *get_chip_name(enum chip_type chip_id) return chip_info_table[i].name; } -/** - * velocity_remove1 - device unplug - * @pdev: PCI device being removed - * - * Device unload callback. Called on an unplug or on module - * unload for each active device that is present. Disconnects - * the device from the network layer and frees all the resources - */ -static void velocity_remove1(struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata(pdev); - struct velocity_info *vptr = netdev_priv(dev); - - unregister_netdev(dev); - iounmap(vptr->mac_regs); - pci_release_regions(pdev); - pci_disable_device(pdev); - pci_set_drvdata(pdev, NULL); - free_netdev(dev); - - velocity_nics--; -} - /** * velocity_set_int_opt - parser for integer options * @opt: pointer to option value @@ -1181,6 +1187,17 @@ static void mii_init(struct velocity_info *vptr, u32 mii_status) u16 BMCR; switch (PHYID_GET_PHY_ID(vptr->phy_id)) { + case PHYID_ICPLUS_IP101A: + MII_REG_BITS_ON((ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP), + MII_ADVERTISE, vptr->mac_regs); + if (vptr->mii_status & VELOCITY_DUPLEX_FULL) + MII_REG_BITS_ON(TCSR_ECHODIS, MII_SREVISION, + vptr->mac_regs); + else + MII_REG_BITS_OFF(TCSR_ECHODIS, MII_SREVISION, + vptr->mac_regs); + MII_REG_BITS_ON(PLED_LALBE, MII_TPISTATUS, vptr->mac_regs); + break; case PHYID_CICADA_CS8201: /* * Reset to hardware default @@ -1312,6 +1329,7 @@ static void velocity_init_registers(struct velocity_info *vptr, enum velocity_init_type type) { struct mac_regs __iomem *regs = vptr->mac_regs; + struct net_device *netdev = vptr->netdev; int i, mii_status; mac_wol_reset(regs); @@ -1320,7 +1338,7 @@ static void velocity_init_registers(struct velocity_info *vptr, case VELOCITY_INIT_RESET: case VELOCITY_INIT_WOL: - netif_stop_queue(vptr->netdev); + netif_stop_queue(netdev); /* * Reset RX to prevent RX pointer not on the 4X location @@ -1333,7 +1351,7 @@ static void velocity_init_registers(struct velocity_info *vptr, if (velocity_set_media_mode(vptr, mii_status) != VELOCITY_LINK_CHANGE) { velocity_print_link_status(vptr); if (!(vptr->mii_status & VELOCITY_LINK_FAIL)) - netif_wake_queue(vptr->netdev); + netif_wake_queue(netdev); } enable_flow_control_ability(vptr); @@ -1353,9 +1371,11 @@ static void velocity_init_registers(struct velocity_info *vptr, velocity_soft_reset(vptr); mdelay(5); - mac_eeprom_reload(regs); - for (i = 0; i < 6; i++) - writeb(vptr->netdev->dev_addr[i], &(regs->PAR[i])); + if (!vptr->no_eeprom) { + mac_eeprom_reload(regs); + for (i = 0; i < 6; i++) + writeb(netdev->dev_addr[i], regs->PAR + i); + } /* * clear Pre_ACPI bit. @@ -1378,7 +1398,7 @@ static void velocity_init_registers(struct velocity_info *vptr, /* * Set packet filter: Receive directed and broadcast address */ - velocity_set_multi(vptr->netdev); + velocity_set_multi(netdev); /* * Enable MII auto-polling @@ -1405,14 +1425,14 @@ static void velocity_init_registers(struct velocity_info *vptr, writel((CR0_DPOLL | CR0_TXON | CR0_RXON | CR0_STRT), ®s->CR0Set); mii_status = velocity_get_opt_media_mode(vptr); - netif_stop_queue(vptr->netdev); + netif_stop_queue(netdev); mii_init(vptr, mii_status); if (velocity_set_media_mode(vptr, mii_status) != VELOCITY_LINK_CHANGE) { velocity_print_link_status(vptr); if (!(vptr->mii_status & VELOCITY_LINK_FAIL)) - netif_wake_queue(vptr->netdev); + netif_wake_queue(netdev); } enable_flow_control_ability(vptr); @@ -2233,15 +2253,15 @@ static int velocity_open(struct net_device *dev) goto out; /* Ensure chip is running */ - pci_set_power_state(vptr->pdev, PCI_D0); + velocity_set_power_state(vptr, PCI_D0); velocity_init_registers(vptr, VELOCITY_INIT_COLD); - ret = request_irq(vptr->pdev->irq, velocity_intr, IRQF_SHARED, + ret = request_irq(dev->irq, velocity_intr, IRQF_SHARED, dev->name, dev); if (ret < 0) { /* Power down the chip */ - pci_set_power_state(vptr->pdev, PCI_D3hot); + velocity_set_power_state(vptr, PCI_D3hot); velocity_free_rings(vptr); goto out; } @@ -2314,6 +2334,7 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) tmp_vptr->netdev = dev; tmp_vptr->pdev = vptr->pdev; + tmp_vptr->dev = vptr->dev; tmp_vptr->options = vptr->options; tmp_vptr->tx.numq = vptr->tx.numq; @@ -2413,7 +2434,7 @@ static int velocity_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) saving then we need to bring the device back up to talk to it */ if (!netif_running(dev)) - pci_set_power_state(vptr->pdev, PCI_D0); + velocity_set_power_state(vptr, PCI_D0); switch (cmd) { case SIOCGMIIPHY: /* Get address of MII PHY in use. */ @@ -2426,7 +2447,7 @@ static int velocity_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) ret = -EOPNOTSUPP; } if (!netif_running(dev)) - pci_set_power_state(vptr->pdev, PCI_D3hot); + velocity_set_power_state(vptr, PCI_D3hot); return ret; @@ -2492,7 +2513,7 @@ static int velocity_close(struct net_device *dev) if (vptr->flags & VELOCITY_FLAGS_WOL_ENABLED) velocity_get_ip(vptr); - free_irq(vptr->pdev->irq, dev); + free_irq(dev->irq, dev); velocity_free_rings(vptr); @@ -2631,13 +2652,9 @@ static const struct net_device_ops velocity_netdev_ops = { * Set up the initial velocity_info struct for the device that has been * discovered. */ -static void velocity_init_info(struct pci_dev *pdev, struct velocity_info *vptr, - const struct velocity_info_tbl *info) +static void velocity_init_info(struct velocity_info *vptr, + const struct velocity_info_tbl *info) { - memset(vptr, 0, sizeof(struct velocity_info)); - - vptr->dev = &pdev->dev; - vptr->pdev = pdev; vptr->chip_id = info->chip_id; vptr->tx.numq = info->txqueue; vptr->multicast_limit = MCAM_SIZE; @@ -2652,10 +2669,9 @@ static void velocity_init_info(struct pci_dev *pdev, struct velocity_info *vptr, * Retrieve the PCI configuration space data that interests us from * the kernel PCI layer */ -static int velocity_get_pci_info(struct velocity_info *vptr, - struct pci_dev *pdev) +static int velocity_get_pci_info(struct velocity_info *vptr) { - vptr->rev_id = pdev->revision; + struct pci_dev *pdev = vptr->pdev; pci_set_master(pdev); @@ -2678,7 +2694,37 @@ static int velocity_get_pci_info(struct velocity_info *vptr, dev_err(&pdev->dev, "region #1 is too small.\n"); return -EINVAL; } - vptr->pdev = pdev; + + return 0; +} + +/** + * velocity_get_platform_info - retrieve platform info for device + * @vptr: velocity device + * @pdev: platform device it matches + * + * Retrieve the Platform configuration data that interests us + */ +static int velocity_get_platform_info(struct velocity_info *vptr) +{ + struct resource res; + int ret; + + if (of_get_property(vptr->dev->of_node, "no-eeprom", NULL)) + vptr->no_eeprom = 1; + + ret = of_address_to_resource(vptr->dev->of_node, 0, &res); + if (ret) { + dev_err(vptr->dev, "unable to find memory address\n"); + return ret; + } + + vptr->memaddr = res.start; + + if (resource_size(&res) < VELOCITY_IO_SIZE) { + dev_err(vptr->dev, "memory region is too small.\n"); + return -EINVAL; + } return 0; } @@ -2707,21 +2753,22 @@ static u32 velocity_get_link(struct net_device *dev) } /** - * velocity_found1 - set up discovered velocity card + * velocity_probe - set up discovered velocity device * @pdev: PCI device * @ent: PCI device table entry that matched + * @bustype: bus that device is connected to * * Configure a discovered adapter from scratch. Return a negative * errno error code on failure paths. */ -static int velocity_found1(struct pci_dev *pdev, - const struct pci_device_id *ent) +static int velocity_probe(struct device *dev, int irq, + const struct velocity_info_tbl *info, + enum velocity_bus_type bustype) { static int first = 1; - struct net_device *dev; + struct net_device *netdev; int i; const char *drv_string; - const struct velocity_info_tbl *info = &chip_info_table[ent->driver_data]; struct velocity_info *vptr; struct mac_regs __iomem *regs; int ret = -ENOMEM; @@ -2730,19 +2777,18 @@ static int velocity_found1(struct pci_dev *pdev, * can support more than MAX_UNITS. */ if (velocity_nics >= MAX_UNITS) { - dev_notice(&pdev->dev, "already found %d NICs.\n", - velocity_nics); + dev_notice(dev, "already found %d NICs.\n", velocity_nics); return -ENODEV; } - dev = alloc_etherdev(sizeof(struct velocity_info)); - if (!dev) + netdev = alloc_etherdev(sizeof(struct velocity_info)); + if (!netdev) goto out; /* Chain it all together */ - SET_NETDEV_DEV(dev, &pdev->dev); - vptr = netdev_priv(dev); + SET_NETDEV_DEV(netdev, dev); + vptr = netdev_priv(netdev); if (first) { printk(KERN_INFO "%s Ver. %s\n", @@ -2752,41 +2798,41 @@ static int velocity_found1(struct pci_dev *pdev, first = 0; } - velocity_init_info(pdev, vptr, info); + netdev->irq = irq; + vptr->netdev = netdev; + vptr->dev = dev; - vptr->netdev = dev; + velocity_init_info(vptr, info); - ret = pci_enable_device(pdev); - if (ret < 0) - goto err_free_dev; + if (bustype == BUS_PCI) { + vptr->pdev = to_pci_dev(dev); - ret = velocity_get_pci_info(vptr, pdev); - if (ret < 0) { - /* error message already printed */ - goto err_disable; - } - - ret = pci_request_regions(pdev, VELOCITY_NAME); - if (ret < 0) { - dev_err(&pdev->dev, "No PCI resources.\n"); - goto err_disable; + ret = velocity_get_pci_info(vptr); + if (ret < 0) + goto err_free_dev; + } else { + vptr->pdev = NULL; + ret = velocity_get_platform_info(vptr); + if (ret < 0) + goto err_free_dev; } regs = ioremap(vptr->memaddr, VELOCITY_IO_SIZE); if (regs == NULL) { ret = -EIO; - goto err_release_res; + goto err_free_dev; } vptr->mac_regs = regs; + vptr->rev_id = readb(®s->rev_id); mac_wol_reset(regs); for (i = 0; i < 6; i++) - dev->dev_addr[i] = readb(®s->PAR[i]); + netdev->dev_addr[i] = readb(®s->PAR[i]); - drv_string = dev_driver_string(&pdev->dev); + drv_string = dev_driver_string(dev); velocity_get_options(&vptr->options, velocity_nics, drv_string); @@ -2807,46 +2853,125 @@ static int velocity_found1(struct pci_dev *pdev, vptr->phy_id = MII_GET_PHY_ID(vptr->mac_regs); - dev->netdev_ops = &velocity_netdev_ops; - dev->ethtool_ops = &velocity_ethtool_ops; - netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT); + netdev->netdev_ops = &velocity_netdev_ops; + netdev->ethtool_ops = &velocity_ethtool_ops; + netif_napi_add(netdev, &vptr->napi, velocity_poll, + VELOCITY_NAPI_WEIGHT); - dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | + netdev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_TX; - dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER | - NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_IP_CSUM; + netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_IP_CSUM; - ret = register_netdev(dev); + ret = register_netdev(netdev); if (ret < 0) goto err_iounmap; - if (!velocity_get_link(dev)) { - netif_carrier_off(dev); + if (!velocity_get_link(netdev)) { + netif_carrier_off(netdev); vptr->mii_status |= VELOCITY_LINK_FAIL; } velocity_print_info(vptr); - pci_set_drvdata(pdev, dev); + dev_set_drvdata(vptr->dev, netdev); /* and leave the chip powered down */ - pci_set_power_state(pdev, PCI_D3hot); + velocity_set_power_state(vptr, PCI_D3hot); velocity_nics++; out: return ret; err_iounmap: iounmap(regs); -err_release_res: - pci_release_regions(pdev); -err_disable: - pci_disable_device(pdev); err_free_dev: - free_netdev(dev); + free_netdev(netdev); goto out; } -#ifdef CONFIG_PM +/** + * velocity_remove - device unplug + * @dev: device being removed + * + * Device unload callback. Called on an unplug or on module + * unload for each active device that is present. Disconnects + * the device from the network layer and frees all the resources + */ +static int velocity_remove(struct device *dev) +{ + struct net_device *netdev = dev_get_drvdata(dev); + struct velocity_info *vptr = netdev_priv(netdev); + + unregister_netdev(netdev); + iounmap(vptr->mac_regs); + free_netdev(netdev); + velocity_nics--; + + return 0; +} + +static int velocity_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + const struct velocity_info_tbl *info = + &chip_info_table[ent->driver_data]; + int ret; + + ret = pci_enable_device(pdev); + if (ret < 0) + return ret; + + ret = pci_request_regions(pdev, VELOCITY_NAME); + if (ret < 0) { + dev_err(&pdev->dev, "No PCI resources.\n"); + goto fail1; + } + + ret = velocity_probe(&pdev->dev, pdev->irq, info, BUS_PCI); + if (ret == 0) + return 0; + + pci_release_regions(pdev); +fail1: + pci_disable_device(pdev); + return ret; +} + +static void velocity_pci_remove(struct pci_dev *pdev) +{ + velocity_remove(&pdev->dev); + + pci_release_regions(pdev); + pci_disable_device(pdev); +} + +static int velocity_platform_probe(struct platform_device *pdev) +{ + const struct of_device_id *of_id; + const struct velocity_info_tbl *info; + int irq; + + of_id = of_match_device(velocity_of_ids, &pdev->dev); + if (!of_id) + return -EINVAL; + info = of_id->data; + + irq = irq_of_parse_and_map(pdev->dev.of_node, 0); + if (!irq) + return -EINVAL; + + return velocity_probe(&pdev->dev, irq, info, BUS_PLATFORM); +} + +static int velocity_platform_remove(struct platform_device *pdev) +{ + velocity_remove(&pdev->dev); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP /** * wol_calc_crc - WOL CRC * @pattern: data pattern @@ -3003,10 +3128,10 @@ static void velocity_save_context(struct velocity_info *vptr, struct velocity_co } -static int velocity_suspend(struct pci_dev *pdev, pm_message_t state) +static int velocity_suspend(struct device *dev) { - struct net_device *dev = pci_get_drvdata(pdev); - struct velocity_info *vptr = netdev_priv(dev); + struct net_device *netdev = dev_get_drvdata(dev); + struct velocity_info *vptr = netdev_priv(netdev); unsigned long flags; if (!netif_running(vptr->netdev)) @@ -3015,20 +3140,23 @@ static int velocity_suspend(struct pci_dev *pdev, pm_message_t state) netif_device_detach(vptr->netdev); spin_lock_irqsave(&vptr->lock, flags); - pci_save_state(pdev); + if (vptr->pdev) + pci_save_state(vptr->pdev); if (vptr->flags & VELOCITY_FLAGS_WOL_ENABLED) { velocity_get_ip(vptr); velocity_save_context(vptr, &vptr->context); velocity_shutdown(vptr); velocity_set_wol(vptr); - pci_enable_wake(pdev, PCI_D3hot, 1); - pci_set_power_state(pdev, PCI_D3hot); + if (vptr->pdev) + pci_enable_wake(vptr->pdev, PCI_D3hot, 1); + velocity_set_power_state(vptr, PCI_D3hot); } else { velocity_save_context(vptr, &vptr->context); velocity_shutdown(vptr); - pci_disable_device(pdev); - pci_set_power_state(pdev, pci_choose_state(pdev, state)); + if (vptr->pdev) + pci_disable_device(vptr->pdev); + velocity_set_power_state(vptr, PCI_D3hot); } spin_unlock_irqrestore(&vptr->lock, flags); @@ -3070,19 +3198,22 @@ static void velocity_restore_context(struct velocity_info *vptr, struct velocity writeb(*((u8 *) (context->mac_reg + i)), ptr + i); } -static int velocity_resume(struct pci_dev *pdev) +static int velocity_resume(struct device *dev) { - struct net_device *dev = pci_get_drvdata(pdev); - struct velocity_info *vptr = netdev_priv(dev); + struct net_device *netdev = dev_get_drvdata(dev); + struct velocity_info *vptr = netdev_priv(netdev); unsigned long flags; int i; if (!netif_running(vptr->netdev)) return 0; - pci_set_power_state(pdev, PCI_D0); - pci_enable_wake(pdev, 0, 0); - pci_restore_state(pdev); + velocity_set_power_state(vptr, PCI_D0); + + if (vptr->pdev) { + pci_enable_wake(vptr->pdev, 0, 0); + pci_restore_state(vptr->pdev); + } mac_wol_reset(vptr->mac_regs); @@ -3104,23 +3235,34 @@ static int velocity_resume(struct pci_dev *pdev) return 0; } -#endif +#endif /* CONFIG_PM_SLEEP */ + +static SIMPLE_DEV_PM_OPS(velocity_pm_ops, velocity_suspend, velocity_resume); /* * Definition for our device driver. The PCI layer interface * uses this to handle all our card discover and plugging */ -static struct pci_driver velocity_driver = { +static struct pci_driver velocity_pci_driver = { .name = VELOCITY_NAME, - .id_table = velocity_id_table, - .probe = velocity_found1, - .remove = velocity_remove1, -#ifdef CONFIG_PM - .suspend = velocity_suspend, - .resume = velocity_resume, -#endif + .id_table = velocity_pci_id_table, + .probe = velocity_pci_probe, + .remove = velocity_pci_remove, + .driver = { + .pm = &velocity_pm_ops, + }, }; +static struct platform_driver velocity_platform_driver = { + .probe = velocity_platform_probe, + .remove = velocity_platform_remove, + .driver = { + .name = "via-velocity", + .owner = THIS_MODULE, + .of_match_table = velocity_of_ids, + .pm = &velocity_pm_ops, + }, +}; /** * velocity_ethtool_up - pre hook for ethtool @@ -3133,7 +3275,7 @@ static int velocity_ethtool_up(struct net_device *dev) { struct velocity_info *vptr = netdev_priv(dev); if (!netif_running(dev)) - pci_set_power_state(vptr->pdev, PCI_D0); + velocity_set_power_state(vptr, PCI_D0); return 0; } @@ -3148,7 +3290,7 @@ static void velocity_ethtool_down(struct net_device *dev) { struct velocity_info *vptr = netdev_priv(dev); if (!netif_running(dev)) - pci_set_power_state(vptr->pdev, PCI_D3hot); + velocity_set_power_state(vptr, PCI_D3hot); } static int velocity_get_settings(struct net_device *dev, @@ -3268,9 +3410,14 @@ static int velocity_set_settings(struct net_device *dev, static void velocity_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct velocity_info *vptr = netdev_priv(dev); + strlcpy(info->driver, VELOCITY_NAME, sizeof(info->driver)); strlcpy(info->version, VELOCITY_VERSION, sizeof(info->version)); - strlcpy(info->bus_info, pci_name(vptr->pdev), sizeof(info->bus_info)); + if (vptr->pdev) + strlcpy(info->bus_info, pci_name(vptr->pdev), + sizeof(info->bus_info)); + else + strlcpy(info->bus_info, "platform", sizeof(info->bus_info)); } static void velocity_ethtool_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) @@ -3560,13 +3707,20 @@ static void velocity_unregister_notifier(void) */ static int __init velocity_init_module(void) { - int ret; + int ret_pci, ret_platform; velocity_register_notifier(); - ret = pci_register_driver(&velocity_driver); - if (ret < 0) + + ret_pci = pci_register_driver(&velocity_pci_driver); + ret_platform = platform_driver_register(&velocity_platform_driver); + + /* if both_registers failed, remove the notifier */ + if ((ret_pci < 0) && (ret_platform < 0)) { velocity_unregister_notifier(); - return ret; + return ret_pci; + } + + return 0; } /** @@ -3580,7 +3734,9 @@ static int __init velocity_init_module(void) static void __exit velocity_cleanup_module(void) { velocity_unregister_notifier(); - pci_unregister_driver(&velocity_driver); + + pci_unregister_driver(&velocity_pci_driver); + platform_driver_unregister(&velocity_platform_driver); } module_init(velocity_init_module); diff --git a/drivers/net/ethernet/via/via-velocity.h b/drivers/net/ethernet/via/via-velocity.h index c38bbaed4d12..9453bfa9324a 100644 --- a/drivers/net/ethernet/via/via-velocity.h +++ b/drivers/net/ethernet/via/via-velocity.h @@ -1265,7 +1265,7 @@ struct velocity_context { #define PHYID_VT3216_64BIT 0x000FC600UL #define PHYID_MARVELL_1000 0x01410C50UL #define PHYID_MARVELL_1000S 0x01410C40UL - +#define PHYID_ICPLUS_IP101A 0x02430C54UL #define PHYID_REV_ID_MASK 0x0000000FUL #define PHYID_GET_PHY_ID(i) ((i) & ~PHYID_REV_ID_MASK) @@ -1437,6 +1437,7 @@ struct velocity_info { struct device *dev; struct pci_dev *pdev; struct net_device *netdev; + int no_eeprom; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; u8 ip_addr[4]; -- cgit v1.2.3 From 0b8bf1baabe56f721d541953f083560d0660d78f Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Mon, 20 May 2013 09:16:58 +0000 Subject: net: dm9000: Allow instantiation using device tree This patch adds Device Tree support to dm9000 driver. Signed-off-by: Tomasz Figa Reviewed-by: Sylwester Nawrocki Reviewed-by: Sascha Hauer Signed-off-by: David S. Miller --- .../devicetree/bindings/net/davicom-dm9000.txt | 26 ++++++++++++++ .../devicetree/bindings/vendor-prefixes.txt | 1 + drivers/net/ethernet/davicom/dm9000.c | 42 ++++++++++++++++++++++ 3 files changed, 69 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/davicom-dm9000.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/davicom-dm9000.txt b/Documentation/devicetree/bindings/net/davicom-dm9000.txt new file mode 100644 index 000000000000..2d39c990e641 --- /dev/null +++ b/Documentation/devicetree/bindings/net/davicom-dm9000.txt @@ -0,0 +1,26 @@ +Davicom DM9000 Fast Ethernet controller + +Required properties: +- compatible = "davicom,dm9000"; +- reg : physical addresses and sizes of registers, must contain 2 entries: + first entry : address register, + second entry : data register. +- interrupt-parent : interrupt controller to which the device is connected +- interrupts : interrupt specifier specific to interrupt controller + +Optional properties: +- local-mac-address : A bytestring of 6 bytes specifying Ethernet MAC address + to use (from firmware or bootloader) +- davicom,no-eeprom : Configuration EEPROM is not available +- davicom,ext-phy : Use external PHY + +Example: + + ethernet@18000000 { + compatible = "davicom,dm9000"; + reg = <0x18000000 0x2 0x18000004 0x2>; + interrupt-parent = <&gpn>; + interrupts = <7 4>; + local-mac-address = [00 00 de ad be ef]; + davicom,no-eeprom; + }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 6931c4348d24..2fe74e6ec209 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -18,6 +18,7 @@ chrp Common Hardware Reference Platform cirrus Cirrus Logic, Inc. cortina Cortina Systems, Inc. dallas Maxim Integrated Products (formerly Dallas Semiconductor) +davicom DAVICOM Semiconductor, Inc. denx Denx Software Engineering emmicro EM Microelectronic epson Seiko Epson Corp. diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index a2408c84bbdd..dd243a1b03e0 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -29,6 +29,8 @@ #include #include #include +#include +#include #include #include #include @@ -1351,6 +1353,31 @@ static const struct net_device_ops dm9000_netdev_ops = { #endif }; +static struct dm9000_plat_data *dm9000_parse_dt(struct device *dev) +{ + struct dm9000_plat_data *pdata; + struct device_node *np = dev->of_node; + const void *mac_addr; + + if (!IS_ENABLED(CONFIG_OF) || !np) + return NULL; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return ERR_PTR(-ENOMEM); + + if (of_find_property(np, "davicom,ext-phy", NULL)) + pdata->flags |= DM9000_PLATF_EXT_PHY; + if (of_find_property(np, "davicom,no-eeprom", NULL)) + pdata->flags |= DM9000_PLATF_NO_EEPROM; + + mac_addr = of_get_mac_address(np); + if (mac_addr) + memcpy(pdata->dev_addr, mac_addr, sizeof(pdata->dev_addr)); + + return pdata; +} + /* * Search DM9000 board, allocate space and register it */ @@ -1366,6 +1393,12 @@ dm9000_probe(struct platform_device *pdev) int i; u32 id_val; + if (!pdata) { + pdata = dm9000_parse_dt(&pdev->dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + } + /* Init network device */ ndev = alloc_etherdev(sizeof(struct board_info)); if (!ndev) @@ -1676,11 +1709,20 @@ dm9000_drv_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_OF +static const struct of_device_id dm9000_of_matches[] = { + { .compatible = "davicom,dm9000", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, dm9000_of_matches); +#endif + static struct platform_driver dm9000_driver = { .driver = { .name = "dm9000", .owner = THIS_MODULE, .pm = &dm9000_drv_pm_ops, + .of_match_table = of_match_ptr(dm9000_of_matches), }, .probe = dm9000_probe, .remove = dm9000_drv_remove, -- cgit v1.2.3 From 191cb1f21afd9a7fbaa085ad9b86cb307e9a3891 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 22 May 2013 07:54:40 +0000 Subject: rps: document flow limit in scaling.txt Explain the mechanism and API of the recently merged rps flow limit patch. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- Documentation/networking/scaling.txt | 58 ++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'Documentation') diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index 579994afbe06..ca6977f5b2ed 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt @@ -163,6 +163,64 @@ and unnecessary. If there are fewer hardware queues than CPUs, then RPS might be beneficial if the rps_cpus for each queue are the ones that share the same memory domain as the interrupting CPU for that queue. +==== RPS Flow Limit + +RPS scales kernel receive processing across CPUs without introducing +reordering. The trade-off to sending all packets from the same flow +to the same CPU is CPU load imbalance if flows vary in packet rate. +In the extreme case a single flow dominates traffic. Especially on +common server workloads with many concurrent connections, such +behavior indicates a problem such as a misconfiguration or spoofed +source Denial of Service attack. + +Flow Limit is an optional RPS feature that prioritizes small flows +during CPU contention by dropping packets from large flows slightly +ahead of those from small flows. It is active only when an RPS or RFS +destination CPU approaches saturation. Once a CPU's input packet +queue exceeds half the maximum queue length (as set by sysctl +net.core.netdev_max_backlog), the kernel starts a per-flow packet +count over the last 256 packets. If a flow exceeds a set ratio (by +default, half) of these packets when a new packet arrives, then the +new packet is dropped. Packets from other flows are still only +dropped once the input packet queue reaches netdev_max_backlog. +No packets are dropped when the input packet queue length is below +the threshold, so flow limit does not sever connections outright: +even large flows maintain connectivity. + +== Interface + +Flow limit is compiled in by default (CONFIG_NET_FLOW_LIMIT), but not +turned on. It is implemented for each CPU independently (to avoid lock +and cache contention) and toggled per CPU by setting the relevant bit +in sysctl net.core.flow_limit_cpu_bitmap. It exposes the same CPU +bitmap interface as rps_cpus (see above) when called from procfs: + + /proc/sys/net/core/flow_limit_cpu_bitmap + +Per-flow rate is calculated by hashing each packet into a hashtable +bucket and incrementing a per-bucket counter. The hash function is +the same that selects a CPU in RPS, but as the number of buckets can +be much larger than the number of CPUs, flow limit has finer-grained +identification of large flows and fewer false positives. The default +table has 4096 buckets. This value can be modified through sysctl + + net.core.flow_limit_table_len + +The value is only consulted when a new table is allocated. Modifying +it does not update active tables. + +== Suggested Configuration + +Flow limit is useful on systems with many concurrent connections, +where a single connection taking up 50% of a CPU indicates a problem. +In such environments, enable the feature on all CPUs that handle +network rx interrupts (as set in /proc/irq/N/smp_affinity). + +The feature depends on the input packet queue length to exceed +the flow limit threshold (50%) + the flow history length (256). +Setting net.core.netdev_max_backlog to either 1000 or 10000 +performed well in experiments. + RFS: Receive Flow Steering ========================== -- cgit v1.2.3 From 8d61ffa5e01c5f676431d12caba17db164a48a86 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 10 May 2013 12:32:47 +0200 Subject: cfg80211/mac80211: use cfg80211 wdev mutex in mac80211 Using separate locks in cfg80211 and mac80211 has always caused issues, for example having to unlock in places in mac80211 to call cfg80211, which even needed a framework to make cfg80211 calls after some functions returned etc. Additionally, I suspect some issues people have reported with the cfg80211 state getting confused could be due to such issues, when cfg80211 is asking mac80211 to change state but mac80211 is in the process of telling cfg80211 that the state changed (in another way.) Signed-off-by: Johannes Berg --- Documentation/DocBook/80211.tmpl | 2 - include/net/cfg80211.h | 51 +++--- net/mac80211/cfg.c | 4 +- net/mac80211/debugfs_netdev.c | 10 +- net/mac80211/ht.c | 4 +- net/mac80211/ibss.c | 39 ++--- net/mac80211/ieee80211_i.h | 25 ++- net/mac80211/main.c | 4 +- net/mac80211/mesh.c | 32 ++-- net/mac80211/mesh_plink.c | 7 +- net/mac80211/mlme.c | 341 ++++++++++++++------------------------- net/mac80211/util.c | 4 +- net/wireless/mlme.c | 48 +----- net/wireless/trace.h | 4 +- 14 files changed, 220 insertions(+), 355 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index 0f6a3edcd44b..ebe89694cf81 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -132,9 +132,7 @@ !Finclude/net/cfg80211.h cfg80211_send_rx_assoc !Finclude/net/cfg80211.h cfg80211_send_assoc_timeout !Finclude/net/cfg80211.h cfg80211_send_deauth -!Finclude/net/cfg80211.h __cfg80211_send_deauth !Finclude/net/cfg80211.h cfg80211_send_disassoc -!Finclude/net/cfg80211.h __cfg80211_send_disassoc !Finclude/net/cfg80211.h cfg80211_ibss_joined !Finclude/net/cfg80211.h cfg80211_connect_result !Finclude/net/cfg80211.h cfg80211_roamed diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5430f70c63b3..9f45d74ce3c2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1867,7 +1867,9 @@ struct cfg80211_update_ft_ies_params { * @get_mpath: get a mesh path for the given parameters * @dump_mpath: dump mesh path callback -- resume dump at index @idx * @join_mesh: join the mesh network with the specified parameters + * (invoked with the wireless_dev mutex held) * @leave_mesh: leave the current mesh network + * (invoked with the wireless_dev mutex held) * * @get_mesh_config: Get the current mesh configuration * @@ -1894,20 +1896,28 @@ struct cfg80211_update_ft_ies_params { * the scan/scan_done bracket too. * * @auth: Request to authenticate with the specified peer + * (invoked with the wireless_dev mutex held) * @assoc: Request to (re)associate with the specified peer + * (invoked with the wireless_dev mutex held) * @deauth: Request to deauthenticate from the specified peer + * (invoked with the wireless_dev mutex held) * @disassoc: Request to disassociate from the specified peer + * (invoked with the wireless_dev mutex held) * * @connect: Connect to the ESS with the specified parameters. When connected, * call cfg80211_connect_result() with status code %WLAN_STATUS_SUCCESS. * If the connection fails for some reason, call cfg80211_connect_result() * with the status from the AP. + * (invoked with the wireless_dev mutex held) * @disconnect: Disconnect from the BSS/ESS. + * (invoked with the wireless_dev mutex held) * * @join_ibss: Join the specified IBSS (or create if necessary). Once done, call * cfg80211_ibss_joined(), also call that function when changing BSSID due * to a merge. + * (invoked with the wireless_dev mutex held) * @leave_ibss: Leave the IBSS. + * (invoked with the wireless_dev mutex held) * * @set_mcast_rate: Set the specified multicast rate (only if vif is in ADHOC or * MESH mode) @@ -2851,7 +2861,8 @@ struct cfg80211_cached_keys; * by cfg80211 on change_interface * @mgmt_registrations: list of registrations for management frames * @mgmt_registrations_lock: lock for the list - * @mtx: mutex used to lock data in this struct + * @mtx: mutex used to lock data in this struct, may be used by drivers + * and some API functions require it held * @cleanup_work: work struct used for cleanup that can't be done directly * @beacon_interval: beacon interval used on this device for transmitting * beacons, 0 when not valid @@ -3424,7 +3435,8 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); * This function is called whenever an authentication has been processed in * station mode. The driver is required to call either this function or * cfg80211_send_auth_timeout() to indicate the result of cfg80211_ops::auth() - * call. This function may sleep. + * call. This function may sleep. The caller must hold the corresponding wdev's + * mutex. */ void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len); @@ -3433,7 +3445,8 @@ void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len); * @dev: network device * @addr: The MAC address of the device with which the authentication timed out * - * This function may sleep. + * This function may sleep. The caller must hold the corresponding wdev's + * mutex. */ void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr); @@ -3448,7 +3461,8 @@ void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr); * This function is called whenever a (re)association response has been * processed in station mode. The driver is required to call either this * function or cfg80211_send_assoc_timeout() to indicate the result of - * cfg80211_ops::assoc() call. This function may sleep. + * cfg80211_ops::assoc() call. This function may sleep. The caller must hold + * the corresponding wdev's mutex. */ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, const u8 *buf, size_t len); @@ -3458,7 +3472,7 @@ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, * @dev: network device * @addr: The MAC address of the device with which the association timed out * - * This function may sleep. + * This function may sleep. The caller must hold the corresponding wdev's mutex. */ void cfg80211_send_assoc_timeout(struct net_device *dev, const u8 *addr); @@ -3470,20 +3484,11 @@ void cfg80211_send_assoc_timeout(struct net_device *dev, const u8 *addr); * * This function is called whenever deauthentication has been processed in * station mode. This includes both received deauthentication frames and - * locally generated ones. This function may sleep. + * locally generated ones. This function may sleep. The caller must hold the + * corresponding wdev's mutex. */ void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len); -/** - * __cfg80211_send_deauth - notification of processed deauthentication - * @dev: network device - * @buf: deauthentication frame (header + body) - * @len: length of the frame data - * - * Like cfg80211_send_deauth(), but doesn't take the wdev lock. - */ -void __cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len); - /** * cfg80211_send_disassoc - notification of processed disassociation * @dev: network device @@ -3492,21 +3497,11 @@ void __cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len); * * This function is called whenever disassociation has been processed in * station mode. This includes both received disassociation frames and locally - * generated ones. This function may sleep. + * generated ones. This function may sleep. The caller must hold the + * corresponding wdev's mutex. */ void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len); -/** - * __cfg80211_send_disassoc - notification of processed disassociation - * @dev: network device - * @buf: disassociation response frame (header + body) - * @len: length of the frame data - * - * Like cfg80211_send_disassoc(), but doesn't take the wdev lock. - */ -void __cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, - size_t len); - /** * cfg80211_send_unprot_deauth - notification of unprotected deauthentication * @dev: network device diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index eb4219051043..232edf78d5a9 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2318,7 +2318,7 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode old_req; int err; - lockdep_assert_held(&sdata->u.mgd.mtx); + lockdep_assert_held(&sdata->wdev.mtx); old_req = sdata->u.mgd.req_smps; sdata->u.mgd.req_smps = smps_mode; @@ -2375,9 +2375,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, local->dynamic_ps_forced_timeout = timeout; /* no change, but if automatic follow powersave */ - mutex_lock(&sdata->u.mgd.mtx); __ieee80211_request_smps(sdata, sdata->u.mgd.req_smps); - mutex_unlock(&sdata->u.mgd.mtx); if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index f83074fe6670..cafe614ef93d 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -228,9 +228,9 @@ static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata, if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; - mutex_lock(&sdata->u.mgd.mtx); + sdata_lock(sdata); err = __ieee80211_request_smps(sdata, smps_mode); - mutex_unlock(&sdata->u.mgd.mtx); + sdata_unlock(sdata); return err; } @@ -313,16 +313,16 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( case NL80211_IFTYPE_STATION: fc |= cpu_to_le16(IEEE80211_FCTL_TODS); /* BSSID SA DA */ - mutex_lock(&sdata->u.mgd.mtx); + sdata_lock(sdata); if (!sdata->u.mgd.associated) { - mutex_unlock(&sdata->u.mgd.mtx); + sdata_unlock(sdata); dev_kfree_skb(skb); return -ENOTCONN; } memcpy(hdr->addr1, sdata->u.mgd.associated->bssid, ETH_ALEN); memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr->addr3, addr, ETH_ALEN); - mutex_unlock(&sdata->u.mgd.mtx); + sdata_unlock(sdata); break; default: dev_kfree_skb(skb); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index af8cee06e4f3..75dff338f581 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -429,9 +429,9 @@ void ieee80211_request_smps_work(struct work_struct *work) container_of(work, struct ieee80211_sub_if_data, u.mgd.request_smps_work); - mutex_lock(&sdata->u.mgd.mtx); + sdata_lock(sdata); __ieee80211_request_smps(sdata, sdata->u.mgd.driver_smps_mode); - mutex_unlock(&sdata->u.mgd.mtx); + sdata_unlock(sdata); } void ieee80211_request_smps(struct ieee80211_vif *vif, diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 956ba6316da5..caa4b4f7f6e4 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -54,7 +54,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, struct beacon_data *presp; int frame_len; - lockdep_assert_held(&ifibss->mtx); + sdata_assert_lock(sdata); /* Reset own TSF to allow time synchronization work. */ drv_reset_tsf(local, sdata); @@ -74,7 +74,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, } presp = rcu_dereference_protected(ifibss->presp, - lockdep_is_held(&ifibss->mtx)); + lockdep_is_held(&sdata->wdev.mtx)); rcu_assign_pointer(ifibss->presp, NULL); if (presp) kfree_rcu(presp, rcu_head); @@ -263,7 +263,7 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, const struct cfg80211_bss_ies *ies; u64 tsf; - lockdep_assert_held(&sdata->u.ibss.mtx); + sdata_assert_lock(sdata); if (beacon_int < 10) beacon_int = 10; @@ -410,7 +410,7 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; u8 deauth_frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; - lockdep_assert_held(&sdata->u.ibss.mtx); + sdata_assert_lock(sdata); if (len < 24 + 6) return; @@ -677,7 +677,7 @@ static int ieee80211_sta_active_ibss(struct ieee80211_sub_if_data *sdata) int active = 0; struct sta_info *sta; - lockdep_assert_held(&sdata->u.ibss.mtx); + sdata_assert_lock(sdata); rcu_read_lock(); @@ -703,7 +703,7 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - lockdep_assert_held(&ifibss->mtx); + sdata_assert_lock(sdata); mod_timer(&ifibss->timer, round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL)); @@ -734,7 +734,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) u16 capability; int i; - lockdep_assert_held(&ifibss->mtx); + sdata_assert_lock(sdata); if (ifibss->fixed_bssid) { memcpy(bssid, ifibss->bssid, ETH_ALEN); @@ -777,7 +777,7 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) int active_ibss; u16 capability; - lockdep_assert_held(&ifibss->mtx); + sdata_assert_lock(sdata); active_ibss = ieee80211_sta_active_ibss(sdata); ibss_dbg(sdata, "sta_find_ibss (active_ibss=%d)\n", active_ibss); @@ -847,10 +847,10 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, struct beacon_data *presp; u8 *pos, *end; - lockdep_assert_held(&ifibss->mtx); + sdata_assert_lock(sdata); presp = rcu_dereference_protected(ifibss->presp, - lockdep_is_held(&ifibss->mtx)); + lockdep_is_held(&sdata->wdev.mtx)); if (ifibss->state != IEEE80211_IBSS_MLME_JOINED || len < 24 + 2 || !presp) @@ -934,7 +934,7 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, mgmt = (struct ieee80211_mgmt *) skb->data; fc = le16_to_cpu(mgmt->frame_control); - mutex_lock(&sdata->u.ibss.mtx); + sdata_lock(sdata); if (!sdata->u.ibss.ssid_len) goto mgmt_out; /* not ready to merge yet */ @@ -957,7 +957,7 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, } mgmt_out: - mutex_unlock(&sdata->u.ibss.mtx); + sdata_unlock(sdata); } void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata) @@ -965,7 +965,7 @@ void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct sta_info *sta; - mutex_lock(&ifibss->mtx); + sdata_lock(sdata); /* * Work could be scheduled after scan or similar @@ -1001,7 +1001,7 @@ void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata) } out: - mutex_unlock(&ifibss->mtx); + sdata_unlock(sdata); } static void ieee80211_ibss_timer(unsigned long data) @@ -1018,7 +1018,6 @@ void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata) setup_timer(&ifibss->timer, ieee80211_ibss_timer, (unsigned long) sdata); - mutex_init(&ifibss->mtx); INIT_LIST_HEAD(&ifibss->incomplete_stations); spin_lock_init(&ifibss->incomplete_lock); } @@ -1045,8 +1044,6 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, { u32 changed = 0; - mutex_lock(&sdata->u.ibss.mtx); - if (params->bssid) { memcpy(sdata->u.ibss.bssid, params->bssid, ETH_ALEN); sdata->u.ibss.fixed_bssid = true; @@ -1079,8 +1076,6 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, memcpy(sdata->u.ibss.ssid, params->ssid, params->ssid_len); sdata->u.ibss.ssid_len = params->ssid_len; - mutex_unlock(&sdata->u.ibss.mtx); - /* * 802.11n-2009 9.13.3.1: In an IBSS, the HT Protection field is * reserved, but an HT STA shall protect HT transmissions as though @@ -1116,8 +1111,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) struct sta_info *sta; struct beacon_data *presp; - mutex_lock(&sdata->u.ibss.mtx); - active_ibss = ieee80211_sta_active_ibss(sdata); if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) { @@ -1161,7 +1154,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) /* remove beacon */ kfree(sdata->u.ibss.ie); presp = rcu_dereference_protected(ifibss->presp, - lockdep_is_held(&sdata->u.ibss.mtx)); + lockdep_is_held(&sdata->wdev.mtx)); RCU_INIT_POINTER(sdata->u.ibss.presp, NULL); sdata->vif.bss_conf.ibss_joined = false; sdata->vif.bss_conf.ibss_creator = false; @@ -1177,7 +1170,5 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) del_timer_sync(&sdata->u.ibss.timer); - mutex_unlock(&sdata->u.ibss.mtx); - return 0; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ba3cd284d104..9eed6f1d1614 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -394,7 +394,6 @@ struct ieee80211_if_managed { bool nullfunc_failed; bool connection_loss; - struct mutex mtx; struct cfg80211_bss *associated; struct ieee80211_mgd_auth_data *auth_data; struct ieee80211_mgd_assoc_data *assoc_data; @@ -488,8 +487,6 @@ struct ieee80211_if_managed { struct ieee80211_if_ibss { struct timer_list timer; - struct mutex mtx; - unsigned long last_scan_completed; u32 basic_rates; @@ -580,8 +577,6 @@ struct ieee80211_if_mesh { bool accepting_plinks; int num_gates; struct beacon_data __rcu *beacon; - /* just protects beacon updates for now */ - struct mutex mtx; const u8 *ie; u8 ie_len; enum { @@ -778,6 +773,26 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) return container_of(p, struct ieee80211_sub_if_data, vif); } +static inline void sdata_lock(struct ieee80211_sub_if_data *sdata) + __acquires(&sdata->wdev.mtx) +{ + mutex_lock(&sdata->wdev.mtx); + __acquire(&sdata->wdev.mtx); +} + +static inline void sdata_unlock(struct ieee80211_sub_if_data *sdata) + __releases(&sdata->wdev.mtx) +{ + mutex_unlock(&sdata->wdev.mtx); + __release(&sdata->wdev.mtx); +} + +static inline void +sdata_assert_lock(struct ieee80211_sub_if_data *sdata) +{ + lockdep_assert_held(&sdata->wdev.mtx); +} + static inline enum ieee80211_band ieee80211_get_sdata_band(struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 8a7bfc47d577..1998f1475267 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -331,7 +331,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb, return NOTIFY_DONE; ifmgd = &sdata->u.mgd; - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); /* Copy the addresses to the bss_conf list */ ifa = idev->ifa_list; @@ -349,7 +349,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb, ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_ARP_FILTER); - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); return NOTIFY_DONE; } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index c14bb816c6a3..b3d1fdd46368 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -161,8 +161,11 @@ void mesh_sta_cleanup(struct sta_info *sta) del_timer_sync(&sta->plink_timer); } - if (changed) + if (changed) { + sdata_lock(sdata); ieee80211_mbss_info_change_notify(sdata, changed); + sdata_unlock(sdata); + } } int mesh_rmc_init(struct ieee80211_sub_if_data *sdata) @@ -577,7 +580,9 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata) mesh_path_expire(sdata); changed = mesh_accept_plinks_update(sdata); + sdata_lock(sdata); ieee80211_mbss_info_change_notify(sdata, changed); + sdata_unlock(sdata); mod_timer(&ifmsh->housekeeping_timer, round_jiffies(jiffies + @@ -697,25 +702,21 @@ out_free: } static int -ieee80211_mesh_rebuild_beacon(struct ieee80211_if_mesh *ifmsh) +ieee80211_mesh_rebuild_beacon(struct ieee80211_sub_if_data *sdata) { struct beacon_data *old_bcn; int ret; - mutex_lock(&ifmsh->mtx); - - old_bcn = rcu_dereference_protected(ifmsh->beacon, - lockdep_is_held(&ifmsh->mtx)); - ret = ieee80211_mesh_build_beacon(ifmsh); + old_bcn = rcu_dereference_protected(sdata->u.mesh.beacon, + lockdep_is_held(&sdata->wdev.mtx)); + ret = ieee80211_mesh_build_beacon(&sdata->u.mesh); if (ret) /* just reuse old beacon */ - goto out; + return ret; if (old_bcn) kfree_rcu(old_bcn, rcu_head); -out: - mutex_unlock(&ifmsh->mtx); - return ret; + return 0; } void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, @@ -726,7 +727,7 @@ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, BSS_CHANGED_HT | BSS_CHANGED_BASIC_RATES | BSS_CHANGED_BEACON_INT))) - if (ieee80211_mesh_rebuild_beacon(&sdata->u.mesh)) + if (ieee80211_mesh_rebuild_beacon(sdata)) return; ieee80211_bss_info_change_notify(sdata, changed); } @@ -788,12 +789,12 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) sdata->vif.bss_conf.enable_beacon = false; clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); - mutex_lock(&ifmsh->mtx); + sdata_lock(sdata); bcn = rcu_dereference_protected(ifmsh->beacon, - lockdep_is_held(&ifmsh->mtx)); + lockdep_is_held(&sdata->wdev.mtx)); rcu_assign_pointer(ifmsh->beacon, NULL); kfree_rcu(bcn, rcu_head); - mutex_unlock(&ifmsh->mtx); + sdata_unlock(sdata); /* flush STAs and mpaths on this iface */ sta_info_flush(sdata); @@ -1041,7 +1042,6 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) spin_lock_init(&ifmsh->mesh_preq_queue_lock); spin_lock_init(&ifmsh->sync_offset_lock); RCU_INIT_POINTER(ifmsh->beacon, NULL); - mutex_init(&ifmsh->mtx); sdata->vif.bss_conf.bssid = zero_addr; } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 09bebed99416..6c4da99bc4fb 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -517,7 +517,9 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, ieee80211_mps_frame_release(sta, elems); out: rcu_read_unlock(); + sdata_lock(sdata); ieee80211_mbss_info_change_notify(sdata, changed); + sdata_unlock(sdata); } static void mesh_plink_timer(unsigned long data) @@ -1068,6 +1070,9 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); - if (changed) + if (changed) { + sdata_lock(sdata); ieee80211_mbss_info_change_notify(sdata, changed); + sdata_unlock(sdata); + } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1da3d6be8e11..f44f4caa69ee 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -90,41 +90,6 @@ MODULE_PARM_DESC(probe_wait_ms, */ #define IEEE80211_SIGNAL_AVE_MIN_COUNT 4 -/* - * All cfg80211 functions have to be called outside a locked - * section so that they can acquire a lock themselves... This - * is much simpler than queuing up things in cfg80211, but we - * do need some indirection for that here. - */ -enum rx_mgmt_action { - /* no action required */ - RX_MGMT_NONE, - - /* caller must call cfg80211_send_deauth() */ - RX_MGMT_CFG80211_DEAUTH, - - /* caller must call cfg80211_send_disassoc() */ - RX_MGMT_CFG80211_DISASSOC, - - /* caller must call cfg80211_send_rx_auth() */ - RX_MGMT_CFG80211_RX_AUTH, - - /* caller must call cfg80211_send_rx_assoc() */ - RX_MGMT_CFG80211_RX_ASSOC, - - /* caller must call cfg80211_send_assoc_timeout() */ - RX_MGMT_CFG80211_ASSOC_TIMEOUT, - - /* used when a processed beacon causes a deauth */ - RX_MGMT_CFG80211_TX_DEAUTH, -}; - -/* utils */ -static inline void ASSERT_MGD_MTX(struct ieee80211_if_managed *ifmgd) -{ - lockdep_assert_held(&ifmgd->mtx); -} - /* * We can have multiple work items (and connection probing) * scheduling this timer, but we need to take care to only @@ -135,13 +100,14 @@ static inline void ASSERT_MGD_MTX(struct ieee80211_if_managed *ifmgd) * has happened -- the work that runs from this timer will * do that. */ -static void run_again(struct ieee80211_if_managed *ifmgd, unsigned long timeout) +static void run_again(struct ieee80211_sub_if_data *sdata, + unsigned long timeout) { - ASSERT_MGD_MTX(ifmgd); + sdata_assert_lock(sdata); - if (!timer_pending(&ifmgd->timer) || - time_before(timeout, ifmgd->timer.expires)) - mod_timer(&ifmgd->timer, timeout); + if (!timer_pending(&sdata->u.mgd.timer) || + time_before(timeout, sdata->u.mgd.timer.expires)) + mod_timer(&sdata->u.mgd.timer, timeout); } void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata) @@ -652,7 +618,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) struct ieee80211_channel *chan; u32 rates = 0; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); @@ -962,7 +928,7 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (!ieee80211_sdata_running(sdata)) return; - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); if (!ifmgd->associated) goto out; @@ -985,7 +951,7 @@ static void ieee80211_chswitch_work(struct work_struct *work) IEEE80211_QUEUE_STOP_REASON_CSA); out: ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); } void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success) @@ -1036,7 +1002,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_operation *ht_oper; int secondary_channel_offset = -1; - ASSERT_MGD_MTX(ifmgd); + sdata_assert_lock(sdata); if (!cbss) return; @@ -1845,7 +1811,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; u32 changed = 0; - ASSERT_MGD_MTX(ifmgd); + sdata_assert_lock(sdata); if (WARN_ON_ONCE(tx && !frame_buf)) return; @@ -2054,7 +2020,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) } ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); - run_again(ifmgd, ifmgd->probe_timeout); + run_again(sdata, ifmgd->probe_timeout); if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) ieee80211_flush_queues(sdata->local, sdata); } @@ -2068,7 +2034,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, if (!ieee80211_sdata_running(sdata)) return; - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); if (!ifmgd->associated) goto out; @@ -2122,7 +2088,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, ifmgd->probe_send_count = 0; ieee80211_mgd_probe_ap_send(sdata); out: - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); } struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, @@ -2138,7 +2104,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return NULL; - ASSERT_MGD_MTX(ifmgd); + sdata_assert_lock(sdata); if (ifmgd->associated) cbss = ifmgd->associated; @@ -2171,9 +2137,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); if (!ifmgd->associated) { - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); return; } @@ -2184,13 +2150,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) ieee80211_wake_queues_by_reason(&sdata->local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); - mutex_unlock(&ifmgd->mtx); - /* - * must be outside lock due to cfg80211, - * but that's not a problem. - */ cfg80211_send_deauth(sdata->dev, frame_buf, IEEE80211_DEAUTH_FRAME_LEN); + sdata_unlock(sdata); } static void ieee80211_beacon_connection_loss_work(struct work_struct *work) @@ -2257,7 +2219,7 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, { struct ieee80211_mgd_auth_data *auth_data = sdata->u.mgd.auth_data; - lockdep_assert_held(&sdata->u.mgd.mtx); + sdata_assert_lock(sdata); if (!assoc) { sta_info_destroy_addr(sdata, auth_data->bss->bssid); @@ -2298,27 +2260,26 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, auth_data->key_idx, tx_flags); } -static enum rx_mgmt_action __must_check -ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len) +static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 bssid[ETH_ALEN]; u16 auth_alg, auth_transaction, status_code; struct sta_info *sta; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); if (len < 24 + 6) - return RX_MGMT_NONE; + return; if (!ifmgd->auth_data || ifmgd->auth_data->done) - return RX_MGMT_NONE; + return; memcpy(bssid, ifmgd->auth_data->bss->bssid, ETH_ALEN); if (!ether_addr_equal(bssid, mgmt->bssid)) - return RX_MGMT_NONE; + return; auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction); @@ -2330,14 +2291,15 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, mgmt->sa, auth_alg, ifmgd->auth_data->algorithm, auth_transaction, ifmgd->auth_data->expected_transaction); - return RX_MGMT_NONE; + return; } if (status_code != WLAN_STATUS_SUCCESS) { sdata_info(sdata, "%pM denied authentication (status %d)\n", mgmt->sa, status_code); ieee80211_destroy_auth_data(sdata, false); - return RX_MGMT_CFG80211_RX_AUTH; + cfg80211_send_rx_auth(sdata->dev, (u8 *)mgmt, len); + return; } switch (ifmgd->auth_data->algorithm) { @@ -2350,20 +2312,20 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, if (ifmgd->auth_data->expected_transaction != 4) { ieee80211_auth_challenge(sdata, mgmt, len); /* need another frame */ - return RX_MGMT_NONE; + return; } break; default: WARN_ONCE(1, "invalid auth alg %d", ifmgd->auth_data->algorithm); - return RX_MGMT_NONE; + return; } sdata_info(sdata, "authenticated\n"); ifmgd->auth_data->done = true; ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_WAIT_ASSOC; ifmgd->auth_data->timeout_started = true; - run_again(ifmgd, ifmgd->auth_data->timeout); + run_again(sdata, ifmgd->auth_data->timeout); if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && ifmgd->auth_data->expected_transaction != 2) { @@ -2371,7 +2333,8 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, * Report auth frame to user space for processing since another * round of Authentication frames is still needed. */ - return RX_MGMT_CFG80211_RX_AUTH; + cfg80211_send_rx_auth(sdata->dev, (u8 *)mgmt, len); + return; } /* move station state to auth */ @@ -2387,30 +2350,29 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } mutex_unlock(&sdata->local->sta_mtx); - return RX_MGMT_CFG80211_RX_AUTH; + cfg80211_send_rx_auth(sdata->dev, (u8 *)mgmt, len); + return; out_err: mutex_unlock(&sdata->local->sta_mtx); /* ignore frame -- wait for timeout */ - return RX_MGMT_NONE; } -static enum rx_mgmt_action __must_check -ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len) +static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; const u8 *bssid = NULL; u16 reason_code; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); if (len < 24 + 2) - return RX_MGMT_NONE; + return; if (!ifmgd->associated || !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) - return RX_MGMT_NONE; + return; bssid = ifmgd->associated->bssid; @@ -2421,25 +2383,24 @@ ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, 0, 0, false, NULL); - return RX_MGMT_CFG80211_DEAUTH; + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, len); } -static enum rx_mgmt_action __must_check -ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len) +static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u16 reason_code; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); if (len < 24 + 2) - return RX_MGMT_NONE; + return; if (!ifmgd->associated || !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) - return RX_MGMT_NONE; + return; reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); @@ -2448,7 +2409,7 @@ ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, 0, 0, false, NULL); - return RX_MGMT_CFG80211_DISASSOC; + cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, len); } static void ieee80211_get_rates(struct ieee80211_supported_band *sband, @@ -2498,7 +2459,7 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, { struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data; - lockdep_assert_held(&sdata->u.mgd.mtx); + sdata_assert_lock(sdata); if (!assoc) { sta_info_destroy_addr(sdata, assoc_data->bss->bssid); @@ -2679,10 +2640,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, return true; } -static enum rx_mgmt_action __must_check -ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len, - struct cfg80211_bss **bss) +static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, + size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data; @@ -2690,13 +2650,14 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems elems; u8 *pos; bool reassoc; + struct cfg80211_bss *bss; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); if (!assoc_data) - return RX_MGMT_NONE; + return; if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid)) - return RX_MGMT_NONE; + return; /* * AssocResp and ReassocResp have identical structure, so process both @@ -2704,7 +2665,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, */ if (len < 24 + 6) - return RX_MGMT_NONE; + return; reassoc = ieee80211_is_reassoc_req(mgmt->frame_control); capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); @@ -2731,22 +2692,23 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, assoc_data->timeout = jiffies + msecs_to_jiffies(ms); assoc_data->timeout_started = true; if (ms > IEEE80211_ASSOC_TIMEOUT) - run_again(ifmgd, assoc_data->timeout); - return RX_MGMT_NONE; + run_again(sdata, assoc_data->timeout); + return; } - *bss = assoc_data->bss; + bss = assoc_data->bss; if (status_code != WLAN_STATUS_SUCCESS) { sdata_info(sdata, "%pM denied association (code=%d)\n", mgmt->sa, status_code); ieee80211_destroy_assoc_data(sdata, false); } else { - if (!ieee80211_assoc_success(sdata, *bss, mgmt, len)) { + if (!ieee80211_assoc_success(sdata, bss, mgmt, len)) { /* oops -- internal error -- send timeout for now */ ieee80211_destroy_assoc_data(sdata, false); - cfg80211_put_bss(sdata->local->hw.wiphy, *bss); - return RX_MGMT_CFG80211_ASSOC_TIMEOUT; + cfg80211_put_bss(sdata->local->hw.wiphy, bss); + cfg80211_send_assoc_timeout(sdata->dev, mgmt->bssid); + return; } sdata_info(sdata, "associated\n"); @@ -2758,7 +2720,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, ieee80211_destroy_assoc_data(sdata, true); } - return RX_MGMT_CFG80211_RX_ASSOC; + cfg80211_send_rx_assoc(sdata->dev, bss, (u8 *)mgmt, len); } static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, @@ -2772,7 +2734,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel; bool need_ps = false; - lockdep_assert_held(&sdata->u.mgd.mtx); + sdata_assert_lock(sdata); if ((sdata->u.mgd.associated && ether_addr_equal(mgmt->bssid, sdata->u.mgd.associated->bssid)) || @@ -2831,7 +2793,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ifmgd = &sdata->u.mgd; - ASSERT_MGD_MTX(ifmgd); + sdata_assert_lock(sdata); if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) return; /* ignore ProbeResp to foreign address */ @@ -2856,7 +2818,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ifmgd->auth_data->tries = 0; ifmgd->auth_data->timeout = jiffies; ifmgd->auth_data->timeout_started = true; - run_again(ifmgd, ifmgd->auth_data->timeout); + run_again(sdata, ifmgd->auth_data->timeout); } } @@ -2881,10 +2843,9 @@ static const u64 care_about_ies = (1ULL << WLAN_EID_HT_CAPABILITY) | (1ULL << WLAN_EID_HT_OPERATION); -static enum rx_mgmt_action -ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len, - u8 *deauth_buf, struct ieee80211_rx_status *rx_status) +static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len, + struct ieee80211_rx_status *rx_status) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; @@ -2899,24 +2860,25 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, u8 erp_value = 0; u32 ncrc; u8 *bssid; + u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN]; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); /* Process beacon from the current BSS */ baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt; if (baselen > len) - return RX_MGMT_NONE; + return; rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (!chanctx_conf) { rcu_read_unlock(); - return RX_MGMT_NONE; + return; } if (rx_status->freq != chanctx_conf->def.chan->center_freq) { rcu_read_unlock(); - return RX_MGMT_NONE; + return; } chan = chanctx_conf->def.chan; rcu_read_unlock(); @@ -2943,13 +2905,13 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, /* continue assoc process */ ifmgd->assoc_data->timeout = jiffies; ifmgd->assoc_data->timeout_started = true; - run_again(ifmgd, ifmgd->assoc_data->timeout); - return RX_MGMT_NONE; + run_again(sdata, ifmgd->assoc_data->timeout); + return; } if (!ifmgd->associated || !ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) - return RX_MGMT_NONE; + return; bssid = ifmgd->associated->bssid; /* Track average RSSI from the Beacon frames of the current AP */ @@ -3095,7 +3057,7 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) - return RX_MGMT_NONE; + return; ifmgd->beacon_crc = ncrc; ifmgd->beacon_crc_valid = true; @@ -3151,7 +3113,9 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DEAUTH_LEAVING, true, deauth_buf); - return RX_MGMT_CFG80211_TX_DEAUTH; + cfg80211_send_deauth(sdata->dev, deauth_buf, + sizeof(deauth_buf)); + return; } if (sta && elems.opmode_notif) @@ -3168,19 +3132,13 @@ ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, elems.pwr_constr_elem); ieee80211_bss_info_change_notify(sdata, changed); - - return RX_MGMT_NONE; } void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_rx_status *rx_status; struct ieee80211_mgmt *mgmt; - struct cfg80211_bss *bss = NULL; - enum rx_mgmt_action rma = RX_MGMT_NONE; - u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN]; u16 fc; struct ieee802_11_elems elems; int ies_len; @@ -3189,28 +3147,27 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, mgmt = (struct ieee80211_mgmt *) skb->data; fc = le16_to_cpu(mgmt->frame_control); - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); switch (fc & IEEE80211_FCTL_STYPE) { case IEEE80211_STYPE_BEACON: - rma = ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, - deauth_buf, rx_status); + ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, rx_status); break; case IEEE80211_STYPE_PROBE_RESP: ieee80211_rx_mgmt_probe_resp(sdata, skb); break; case IEEE80211_STYPE_AUTH: - rma = ieee80211_rx_mgmt_auth(sdata, mgmt, skb->len); + ieee80211_rx_mgmt_auth(sdata, mgmt, skb->len); break; case IEEE80211_STYPE_DEAUTH: - rma = ieee80211_rx_mgmt_deauth(sdata, mgmt, skb->len); + ieee80211_rx_mgmt_deauth(sdata, mgmt, skb->len); break; case IEEE80211_STYPE_DISASSOC: - rma = ieee80211_rx_mgmt_disassoc(sdata, mgmt, skb->len); + ieee80211_rx_mgmt_disassoc(sdata, mgmt, skb->len); break; case IEEE80211_STYPE_ASSOC_RESP: case IEEE80211_STYPE_REASSOC_RESP: - rma = ieee80211_rx_mgmt_assoc_resp(sdata, mgmt, skb->len, &bss); + ieee80211_rx_mgmt_assoc_resp(sdata, mgmt, skb->len); break; case IEEE80211_STYPE_ACTION: if (mgmt->u.action.category == WLAN_CATEGORY_SPECTRUM_MGMT) { @@ -3256,34 +3213,7 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, } break; } - mutex_unlock(&ifmgd->mtx); - - switch (rma) { - case RX_MGMT_NONE: - /* no action */ - break; - case RX_MGMT_CFG80211_DEAUTH: - cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len); - break; - case RX_MGMT_CFG80211_DISASSOC: - cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len); - break; - case RX_MGMT_CFG80211_RX_AUTH: - cfg80211_send_rx_auth(sdata->dev, (u8 *)mgmt, skb->len); - break; - case RX_MGMT_CFG80211_RX_ASSOC: - cfg80211_send_rx_assoc(sdata->dev, bss, (u8 *)mgmt, skb->len); - break; - case RX_MGMT_CFG80211_ASSOC_TIMEOUT: - cfg80211_send_assoc_timeout(sdata->dev, mgmt->bssid); - break; - case RX_MGMT_CFG80211_TX_DEAUTH: - cfg80211_send_deauth(sdata->dev, deauth_buf, - sizeof(deauth_buf)); - break; - default: - WARN(1, "unexpected: %d", rma); - } + sdata_unlock(sdata); } static void ieee80211_sta_timer(unsigned long data) @@ -3297,20 +3227,12 @@ static void ieee80211_sta_timer(unsigned long data) static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, u8 *bssid, u8 reason, bool tx) { - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, reason, tx, frame_buf); - mutex_unlock(&ifmgd->mtx); - /* - * must be outside lock due to cfg80211, - * but that's not a problem. - */ cfg80211_send_deauth(sdata->dev, frame_buf, IEEE80211_DEAUTH_FRAME_LEN); - - mutex_lock(&ifmgd->mtx); } static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) @@ -3320,7 +3242,7 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) struct ieee80211_mgd_auth_data *auth_data = ifmgd->auth_data; u32 tx_flags = 0; - lockdep_assert_held(&ifmgd->mtx); + sdata_assert_lock(sdata); if (WARN_ON_ONCE(!auth_data)) return -EINVAL; @@ -3393,7 +3315,7 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) if (tx_flags == 0) { auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; ifmgd->auth_data->timeout_started = true; - run_again(ifmgd, auth_data->timeout); + run_again(sdata, auth_data->timeout); } else { auth_data->timeout_started = false; } @@ -3406,7 +3328,7 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata) struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data; struct ieee80211_local *local = sdata->local; - lockdep_assert_held(&sdata->u.mgd.mtx); + sdata_assert_lock(sdata); assoc_data->tries++; if (assoc_data->tries > IEEE80211_ASSOC_MAX_TRIES) { @@ -3430,7 +3352,7 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata) if (!(local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)) { assoc_data->timeout = jiffies + IEEE80211_ASSOC_TIMEOUT; assoc_data->timeout_started = true; - run_again(&sdata->u.mgd, assoc_data->timeout); + run_again(sdata, assoc_data->timeout); } else { assoc_data->timeout_started = false; } @@ -3455,7 +3377,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); if (ifmgd->status_received) { __le16 fc = ifmgd->status_fc; @@ -3467,7 +3389,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) if (status_acked) { ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT_SHORT; - run_again(ifmgd, ifmgd->auth_data->timeout); + run_again(sdata, ifmgd->auth_data->timeout); } else { ifmgd->auth_data->timeout = jiffies - 1; } @@ -3478,7 +3400,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) if (status_acked) { ifmgd->assoc_data->timeout = jiffies + IEEE80211_ASSOC_TIMEOUT_SHORT; - run_again(ifmgd, ifmgd->assoc_data->timeout); + run_again(sdata, ifmgd->assoc_data->timeout); } else { ifmgd->assoc_data->timeout = jiffies - 1; } @@ -3501,12 +3423,10 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) ieee80211_destroy_auth_data(sdata, false); - mutex_unlock(&ifmgd->mtx); cfg80211_send_auth_timeout(sdata->dev, bssid); - mutex_lock(&ifmgd->mtx); } } else if (ifmgd->auth_data && ifmgd->auth_data->timeout_started) - run_again(ifmgd, ifmgd->auth_data->timeout); + run_again(sdata, ifmgd->auth_data->timeout); if (ifmgd->assoc_data && ifmgd->assoc_data->timeout_started && time_after(jiffies, ifmgd->assoc_data->timeout)) { @@ -3519,12 +3439,10 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) ieee80211_destroy_assoc_data(sdata, false); - mutex_unlock(&ifmgd->mtx); cfg80211_send_assoc_timeout(sdata->dev, bssid); - mutex_lock(&ifmgd->mtx); } } else if (ifmgd->assoc_data && ifmgd->assoc_data->timeout_started) - run_again(ifmgd, ifmgd->assoc_data->timeout); + run_again(sdata, ifmgd->assoc_data->timeout); if (ifmgd->flags & (IEEE80211_STA_BEACON_POLL | IEEE80211_STA_CONNECTION_POLL) && @@ -3558,7 +3476,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) false); } } else if (time_is_after_jiffies(ifmgd->probe_timeout)) - run_again(ifmgd, ifmgd->probe_timeout); + run_again(sdata, ifmgd->probe_timeout); else if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) { mlme_dbg(sdata, "Failed to send nullfunc to AP %pM after %dms, disconnecting\n", @@ -3587,7 +3505,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) } } - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); } static void ieee80211_sta_bcn_mon_timer(unsigned long data) @@ -3648,9 +3566,9 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); if (!ifmgd->associated) { - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); return; } @@ -3661,10 +3579,10 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) ifmgd->associated->bssid, WLAN_REASON_UNSPECIFIED, true); - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); return; } - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); } #endif @@ -3696,8 +3614,6 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ifmgd->uapsd_max_sp_len = sdata->local->hw.uapsd_max_sp_len; ifmgd->p2p_noa_index = -1; - mutex_init(&ifmgd->mtx); - if (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS) ifmgd->req_smps = IEEE80211_SMPS_AUTOMATIC; else @@ -4053,8 +3969,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, /* try to authenticate/probe */ - mutex_lock(&ifmgd->mtx); - if ((ifmgd->auth_data && !ifmgd->auth_data->done) || ifmgd->assoc_data) { err = -EBUSY; @@ -4074,8 +3988,8 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, WLAN_REASON_UNSPECIFIED, false, frame_buf); - __cfg80211_send_deauth(sdata->dev, frame_buf, - sizeof(frame_buf)); + cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); } sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid); @@ -4092,8 +4006,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, /* hold our own reference */ cfg80211_ref_bss(local->hw.wiphy, auth_data->bss); - err = 0; - goto out_unlock; + return 0; err_clear: memset(ifmgd->bssid, 0, ETH_ALEN); @@ -4101,9 +4014,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, ifmgd->auth_data = NULL; err_free: kfree(auth_data); - out_unlock: - mutex_unlock(&ifmgd->mtx); - return err; } @@ -4134,8 +4044,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, assoc_data->ssid_len = ssidie[1]; rcu_read_unlock(); - mutex_lock(&ifmgd->mtx); - if (ifmgd->associated) { u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; @@ -4143,8 +4051,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, WLAN_REASON_UNSPECIFIED, false, frame_buf); - __cfg80211_send_deauth(sdata->dev, frame_buf, - sizeof(frame_buf)); + cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); } if (ifmgd->auth_data && !ifmgd->auth_data->done) { @@ -4338,7 +4246,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } rcu_read_unlock(); - run_again(ifmgd, assoc_data->timeout); + run_again(sdata, assoc_data->timeout); if (bss->corrupt_data) { char *corrupt_type = "data"; @@ -4354,17 +4262,13 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, corrupt_type); } - err = 0; - goto out; + return 0; err_clear: memset(ifmgd->bssid, 0, ETH_ALEN); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); ifmgd->assoc_data = NULL; err_free: kfree(assoc_data); - out: - mutex_unlock(&ifmgd->mtx); - return err; } @@ -4376,8 +4280,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, bool tx = !req->local_state_change; bool report_frame = false; - mutex_lock(&ifmgd->mtx); - sdata_info(sdata, "deauthenticating from %pM by local choice (reason=%d)\n", req->bssid, req->reason_code); @@ -4389,7 +4291,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->reason_code, tx, frame_buf); ieee80211_destroy_auth_data(sdata, false); - mutex_unlock(&ifmgd->mtx); report_frame = true; goto out; @@ -4401,12 +4302,11 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->reason_code, tx, frame_buf); report_frame = true; } - mutex_unlock(&ifmgd->mtx); out: if (report_frame) - __cfg80211_send_deauth(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + cfg80211_send_deauth(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); return 0; } @@ -4418,18 +4318,14 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, u8 bssid[ETH_ALEN]; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; - mutex_lock(&ifmgd->mtx); - /* * cfg80211 should catch this ... but it's racy since * we can receive a disassoc frame, process it, hand it * to cfg80211 while that's in a locked section already * trying to tell us that the user wants to disconnect. */ - if (ifmgd->associated != req->bss) { - mutex_unlock(&ifmgd->mtx); + if (ifmgd->associated != req->bss) return -ENOLINK; - } sdata_info(sdata, "disassociating from %pM by local choice (reason=%d)\n", @@ -4439,10 +4335,9 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DISASSOC, req->reason_code, !req->local_state_change, frame_buf); - mutex_unlock(&ifmgd->mtx); - __cfg80211_send_disassoc(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + cfg80211_send_disassoc(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); return 0; } @@ -4462,13 +4357,13 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) cancel_work_sync(&ifmgd->csa_connection_drop_work); cancel_work_sync(&ifmgd->chswitch_work); - mutex_lock(&ifmgd->mtx); + sdata_lock(sdata); if (ifmgd->assoc_data) ieee80211_destroy_assoc_data(sdata, false); if (ifmgd->auth_data) ieee80211_destroy_auth_data(sdata, false); del_timer_sync(&ifmgd->timer); - mutex_unlock(&ifmgd->mtx); + sdata_unlock(sdata); } void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ffdfe4bc89ad..2a8d759324c2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1581,9 +1581,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (sdata->u.mgd.dtim_period) changed |= BSS_CHANGED_DTIM_PERIOD; - mutex_lock(&sdata->u.mgd.mtx); + sdata_lock(sdata); ieee80211_bss_info_change_notify(sdata, changed); - mutex_unlock(&sdata->u.mgd.mtx); + sdata_unlock(sdata); break; case NL80211_IFTYPE_ADHOC: changed |= BSS_CHANGED_IBSS; diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 68b40f21bc38..80ffb0138919 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -25,12 +25,9 @@ void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len) struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); trace_cfg80211_send_rx_auth(dev); - wdev_lock(wdev); nl80211_send_rx_auth(rdev, dev, buf, len, GFP_KERNEL); cfg80211_sme_rx_auth(dev, buf, len); - - wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_rx_auth); @@ -46,7 +43,6 @@ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, int ieoffs = offsetof(struct ieee80211_mgmt, u.assoc_resp.variable); trace_cfg80211_send_rx_assoc(dev, bss); - wdev_lock(wdev); status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); @@ -59,7 +55,7 @@ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, if (status_code != WLAN_STATUS_SUCCESS && wdev->conn && cfg80211_sme_failed_reassoc(wdev)) { cfg80211_put_bss(wiphy, bss); - goto out; + return; } nl80211_send_rx_assoc(rdev, dev, buf, len, GFP_KERNEL); @@ -71,7 +67,7 @@ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, * sme will schedule work that does it later. */ cfg80211_put_bss(wiphy, bss); - goto out; + return; } if (!wdev->conn && wdev->sme_state == CFG80211_SME_IDLE) { @@ -87,13 +83,11 @@ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, __cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, ie, len - ieoffs, status_code, status_code == WLAN_STATUS_SUCCESS, bss); - out: - wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_rx_assoc); -void __cfg80211_send_deauth(struct net_device *dev, - const u8 *buf, size_t len) +void cfg80211_send_deauth(struct net_device *dev, + const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; @@ -102,7 +96,7 @@ void __cfg80211_send_deauth(struct net_device *dev, const u8 *bssid = mgmt->bssid; bool was_current = false; - trace___cfg80211_send_deauth(dev); + trace_cfg80211_send_deauth(dev); ASSERT_WDEV_LOCK(wdev); if (wdev->current_bss && @@ -129,20 +123,10 @@ void __cfg80211_send_deauth(struct net_device *dev, false, NULL); } } -EXPORT_SYMBOL(__cfg80211_send_deauth); - -void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - - wdev_lock(wdev); - __cfg80211_send_deauth(dev, buf, len); - wdev_unlock(wdev); -} EXPORT_SYMBOL(cfg80211_send_deauth); -void __cfg80211_send_disassoc(struct net_device *dev, - const u8 *buf, size_t len) +void cfg80211_send_disassoc(struct net_device *dev, + const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; @@ -152,7 +136,7 @@ void __cfg80211_send_disassoc(struct net_device *dev, u16 reason_code; bool from_ap; - trace___cfg80211_send_disassoc(dev); + trace_cfg80211_send_disassoc(dev); ASSERT_WDEV_LOCK(wdev); nl80211_send_disassoc(rdev, dev, buf, len, GFP_KERNEL); @@ -175,16 +159,6 @@ void __cfg80211_send_disassoc(struct net_device *dev, from_ap = !ether_addr_equal(mgmt->sa, dev->dev_addr); __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } -EXPORT_SYMBOL(__cfg80211_send_disassoc); - -void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - - wdev_lock(wdev); - __cfg80211_send_disassoc(dev, buf, len); - wdev_unlock(wdev); -} EXPORT_SYMBOL(cfg80211_send_disassoc); void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr) @@ -194,15 +168,12 @@ void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr) struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); trace_cfg80211_send_auth_timeout(dev, addr); - wdev_lock(wdev); nl80211_send_auth_timeout(rdev, dev, addr, GFP_KERNEL); if (wdev->sme_state == CFG80211_SME_CONNECTING) __cfg80211_connect_result(dev, addr, NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, false, NULL); - - wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_auth_timeout); @@ -213,15 +184,12 @@ void cfg80211_send_assoc_timeout(struct net_device *dev, const u8 *addr) struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); trace_cfg80211_send_assoc_timeout(dev, addr); - wdev_lock(wdev); nl80211_send_assoc_timeout(rdev, dev, addr, GFP_KERNEL); if (wdev->sme_state == CFG80211_SME_CONNECTING) __cfg80211_connect_result(dev, addr, NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, false, NULL); - - wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_assoc_timeout); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 5755bc14abbd..23fafeae8a10 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1911,12 +1911,12 @@ TRACE_EVENT(cfg80211_send_rx_assoc, NETDEV_PR_ARG, MAC_PR_ARG(bssid), CHAN_PR_ARG) ); -DEFINE_EVENT(netdev_evt_only, __cfg80211_send_deauth, +DEFINE_EVENT(netdev_evt_only, cfg80211_send_deauth, TP_PROTO(struct net_device *netdev), TP_ARGS(netdev) ); -DEFINE_EVENT(netdev_evt_only, __cfg80211_send_disassoc, +DEFINE_EVENT(netdev_evt_only, cfg80211_send_disassoc, TP_PROTO(struct net_device *netdev), TP_ARGS(netdev) ); -- cgit v1.2.3 From 87227b8b2d4d556a6924ad9af87450fdc3fcd7e3 Mon Sep 17 00:00:00 2001 From: Jean-Christophe PLAGNIOL-VILLARD Date: Thu, 23 May 2013 23:01:22 +0000 Subject: net: micrel : ks8851-ml: add dt support Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- .../devicetree/bindings/net/micrel-ks8851.txt | 9 ++++++ drivers/net/ethernet/micrel/ks8851_mll.c | 33 +++++++++++++++++----- 2 files changed, 35 insertions(+), 7 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/micrel-ks8851.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt new file mode 100644 index 000000000000..11ace3c3d805 --- /dev/null +++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt @@ -0,0 +1,9 @@ +Micrel KS8851 Ethernet mac + +Required properties: +- compatible = "micrel,ks8851-ml" of parallel interface +- reg : 2 physical address and size of registers for data and command +- interrupts : interrupt connection + +Optional properties: +- local-mac-address : Ethernet mac address to use diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index e9b1a830d582..ac20098b542a 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -35,6 +35,9 @@ #include #include #include +#include +#include +#include #define DRV_NAME "ks8851_mll" @@ -1524,6 +1527,13 @@ static int ks_hw_init(struct ks_net *ks) return true; } +#if defined(CONFIG_OF) +static const struct of_device_id ks8851_ml_dt_ids[] = { + { .compatible = "micrel,ks8851-mll" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, ks8851_ml_dt_ids); +#endif static int ks8851_probe(struct platform_device *pdev) { @@ -1532,7 +1542,7 @@ static int ks8851_probe(struct platform_device *pdev) struct net_device *netdev; struct ks_net *ks; u16 id, data; - struct ks8851_mll_platform_data *pdata; + const char *mac; io_d = platform_get_resource(pdev, IORESOURCE_MEM, 0); io_c = platform_get_resource(pdev, IORESOURCE_MEM, 1); @@ -1619,13 +1629,21 @@ static int ks8851_probe(struct platform_device *pdev) ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16MA); /* overwriting the default MAC address */ - pdata = pdev->dev.platform_data; - if (!pdata) { - netdev_err(netdev, "No platform data\n"); - err = -ENODEV; - goto err_pdata; + if (pdev->dev.of_node) { + mac = of_get_mac_address(pdev->dev.of_node); + if (mac) + memcpy(ks->mac_addr, mac, ETH_ALEN); + } else { + struct ks8851_mll_platform_data *pdata; + + pdata = pdev->dev.platform_data; + if (!pdata) { + netdev_err(netdev, "No platform data\n"); + err = -ENODEV; + goto err_pdata; + } + memcpy(ks->mac_addr, pdata->mac_addr, ETH_ALEN); } - memcpy(ks->mac_addr, pdata->mac_addr, 6); if (!is_valid_ether_addr(ks->mac_addr)) { /* Use random MAC address if none passed */ eth_random_addr(ks->mac_addr); @@ -1679,6 +1697,7 @@ static struct platform_driver ks8851_platform_driver = { .driver = { .name = DRV_NAME, .owner = THIS_MODULE, + .of_match_table = of_match_ptr(ks8851_ml_dt_ids), }, .probe = ks8851_probe, .remove = ks8851_remove, -- cgit v1.2.3 From 3dd17edea018bf37ca1c33685ca0256270ccdb2c Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Fri, 24 May 2013 07:05:59 +0000 Subject: doc:networking: Fix typo in documentation/networking Correct spelling typo Signed-off-by: Masanari Iida Signed-off-by: David S. Miller --- Documentation/networking/ifenslave.c | 2 +- Documentation/networking/ip-sysctl.txt | 2 +- Documentation/networking/netlink_mmap.txt | 14 +++++++------- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ifenslave.c b/Documentation/networking/ifenslave.c index ac5debb2f16c..9f6a8fff9a78 100644 --- a/Documentation/networking/ifenslave.c +++ b/Documentation/networking/ifenslave.c @@ -501,7 +501,7 @@ out: static short mif_flags; -/* Get the inteface configuration from the kernel. */ +/* Get the interface configuration from the kernel. */ static int if_getconfig(char *ifname) { struct ifreq ifr; diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index f98ca633b528..398d0fb1dd0e 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -183,7 +183,7 @@ tcp_early_retrans - INTEGER for triggering fast retransmit when the amount of outstanding data is small and when no previously unsent data can be transmitted (such that limited transmit could be used). Also controls the use of - Tail loss probe (TLP) that converts RTOs occuring due to tail + Tail loss probe (TLP) that converts RTOs occurring due to tail losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01). Possible values: 0 disables ER diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt index 1c2dab409625..e6088baf109d 100644 --- a/Documentation/networking/netlink_mmap.txt +++ b/Documentation/networking/netlink_mmap.txt @@ -54,7 +54,7 @@ it will use an allocated socket buffer as usual and the contents will be copied to the ring on transmission, nullifying most of the performance gains. Dumps of kernel databases automatically support memory mapped I/O. -Conversion of the transmit path involves changing message contruction to +Conversion of the transmit path involves changing message construction to use memory from the TX ring instead of (usually) a buffer declared on the stack and setting up the frame header approriately. Optionally poll() can be used to wait for free frames in the TX ring. @@ -65,8 +65,8 @@ Structured and definitions for using memory mapped I/O are contained in RX and TX rings ---------------- -Each ring contains a number of continous memory blocks, containing frames of -fixed size dependant on the parameters used for ring setup. +Each ring contains a number of continuous memory blocks, containing frames of +fixed size dependent on the parameters used for ring setup. Ring: [ block 0 ] [ frame 0 ] @@ -80,7 +80,7 @@ Ring: [ block 0 ] [ frame 2 * n + 1 ] The blocks are only visible to the kernel, from the point of view of user-space -the ring just contains the frames in a continous memory zone. +the ring just contains the frames in a continuous memory zone. The ring parameters used for setting up the ring are defined as follows: @@ -91,7 +91,7 @@ struct nl_mmap_req { unsigned int nm_frame_nr; }; -Frames are grouped into blocks, where each block is a continous region of memory +Frames are grouped into blocks, where each block is a continuous region of memory and holds nm_block_size / nm_frame_size frames. The total number of frames in the ring is nm_frame_nr. The following invariants hold: @@ -113,8 +113,8 @@ Some parameters are constrained, specifically: - nm_frame_nr must equal the actual number of frames as specified above. -When the kernel can't allocate phsyically continous memory for a ring block, -it will fall back to use physically discontinous memory. This might affect +When the kernel can't allocate phsyically continuous memory for a ring block, +it will fall back to use physically discontinuous memory. This might affect performance negatively, in order to avoid this the nm_frame_size parameter should be chosen to be as small as possible for the required frame size and the number of blocks should be increased instead. -- cgit v1.2.3 From b1098bbe1b24d5d90cff92fbd716d2ef4bed2cff Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 27 May 2013 15:49:16 +0000 Subject: bonding: remove ifenslave.c from kernel source As Stephen proposed: Since bonding supports configuration via iproute (netlink) and sysfs, I think it is time to purge the old ifenslave code out of Documentation/networking and update the documentation. Suggested-by: Stephen Hemminger Cc: Stephen Hemminger Cc: Jay Vosburgh Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- Documentation/networking/.gitignore | 1 - Documentation/networking/00-INDEX | 2 - Documentation/networking/Makefile | 5 - Documentation/networking/bonding.txt | 54 +- Documentation/networking/ifenslave.c | 1105 ---------------------------------- 5 files changed, 10 insertions(+), 1157 deletions(-) delete mode 100644 Documentation/networking/ifenslave.c (limited to 'Documentation') diff --git a/Documentation/networking/.gitignore b/Documentation/networking/.gitignore index 286a5680f490..e69de29bb2d1 100644 --- a/Documentation/networking/.gitignore +++ b/Documentation/networking/.gitignore @@ -1 +0,0 @@ -ifenslave diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 258d9b92c36f..32dfbd924121 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -88,8 +88,6 @@ gianfar.txt - Gianfar Ethernet Driver. ieee802154.txt - Linux IEEE 802.15.4 implementation, API and drivers -ifenslave.c - - Configure network interfaces for parallel routing (bonding). igb.txt - README for the Intel Gigabit Ethernet Driver (igb). igbvf.txt diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile index 24c308dd3fd1..0aa1ac98fc2b 100644 --- a/Documentation/networking/Makefile +++ b/Documentation/networking/Makefile @@ -1,11 +1,6 @@ # kbuild trick to avoid linker error. Can be omitted if a module is built. obj- := dummy.o -# List of programs to build -hostprogs-y := ifenslave - -HOSTCFLAGS_ifenslave.o += -I$(objtree)/usr/include - # Tell kbuild to always build the programs always := $(hostprogs-y) diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 10a015c384b8..e7454fcc9176 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -104,8 +104,7 @@ Table of Contents ============================== Most popular distro kernels ship with the bonding driver -already available as a module and the ifenslave user level control -program installed and ready for use. If your distro does not, or you +already available as a module. If your distro does not, or you have need to compile bonding from source (e.g., configuring and installing a mainline kernel from kernel.org), you'll need to perform the following steps: @@ -124,46 +123,13 @@ device support" section. It is recommended that you configure the driver as module since it is currently the only way to pass parameters to the driver or configure more than one bonding device. - Build and install the new kernel and modules, then continue -below to install ifenslave. + Build and install the new kernel and modules. -1.2 Install ifenslave Control Utility +1.2 Bonding Control Utility ------------------------------------- - The ifenslave user level control program is included in the -kernel source tree, in the file Documentation/networking/ifenslave.c. -It is generally recommended that you use the ifenslave that -corresponds to the kernel that you are using (either from the same -source tree or supplied with the distro), however, ifenslave -executables from older kernels should function (but features newer -than the ifenslave release are not supported). Running an ifenslave -that is newer than the kernel is not supported, and may or may not -work. - - To install ifenslave, do the following: - -# gcc -Wall -O -I/usr/src/linux/include ifenslave.c -o ifenslave -# cp ifenslave /sbin/ifenslave - - If your kernel source is not in "/usr/src/linux," then replace -"/usr/src/linux/include" in the above with the location of your kernel -source include directory. - - You may wish to back up any existing /sbin/ifenslave, or, for -testing or informal use, tag the ifenslave to the kernel version -(e.g., name the ifenslave executable /sbin/ifenslave-2.6.10). - -IMPORTANT NOTE: - - If you omit the "-I" or specify an incorrect directory, you -may end up with an ifenslave that is incompatible with the kernel -you're trying to build it for. Some distros (e.g., Red Hat from 7.1 -onwards) do not have /usr/include/linux symbolically linked to the -default kernel source include directory. - -SECOND IMPORTANT NOTE: - If you plan to configure bonding using sysfs or using the -/etc/network/interfaces file, you do not need to use ifenslave. + It is recommended to configure bonding via iproute2 (netlink) +or sysfs, the old ifenslave control utility is obsolete. 2. Bonding Driver Options ========================= @@ -851,7 +817,7 @@ resend_igmp ============================== You can configure bonding using either your distro's network -initialization scripts, or manually using either ifenslave or the +initialization scripts, or manually using either iproute2 or the sysfs interface. Distros generally use one of three packages for the network initialization scripts: initscripts, sysconfig or interfaces. Recent versions of these packages have support for bonding, while older @@ -1160,7 +1126,7 @@ not support this method for specifying multiple bonding interfaces; for those instances, see the "Configuring Multiple Bonds Manually" section, below. -3.3 Configuring Bonding Manually with Ifenslave +3.3 Configuring Bonding Manually with iproute2 ----------------------------------------------- This section applies to distros whose network initialization @@ -1171,7 +1137,7 @@ version 8. The general method for these systems is to place the bonding module parameters into a config file in /etc/modprobe.d/ (as appropriate for the installed distro), then add modprobe and/or -ifenslave commands to the system's global init script. The name of +`ip link` commands to the system's global init script. The name of the global init script differs; for sysconfig, it is /etc/init.d/boot.local and for initscripts it is /etc/rc.d/rc.local. @@ -1183,8 +1149,8 @@ reboots, edit the appropriate file (/etc/init.d/boot.local or modprobe bonding mode=balance-alb miimon=100 modprobe e100 ifconfig bond0 192.168.1.1 netmask 255.255.255.0 up -ifenslave bond0 eth0 -ifenslave bond0 eth1 +ip link set eth0 master bond0 +ip link set eth1 master bond0 Replace the example bonding module parameters and bond0 network configuration (IP address, netmask, etc) with the appropriate diff --git a/Documentation/networking/ifenslave.c b/Documentation/networking/ifenslave.c deleted file mode 100644 index 9f6a8fff9a78..000000000000 --- a/Documentation/networking/ifenslave.c +++ /dev/null @@ -1,1105 +0,0 @@ -/* Mode: C; - * ifenslave.c: Configure network interfaces for parallel routing. - * - * This program controls the Linux implementation of running multiple - * network interfaces in parallel. - * - * Author: Donald Becker - * Copyright 1994-1996 Donald Becker - * - * This program is free software; you can redistribute it - * and/or modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation. - * - * The author may be reached as becker@CESDIS.gsfc.nasa.gov, or C/O - * Center of Excellence in Space Data and Information Sciences - * Code 930.5, Goddard Space Flight Center, Greenbelt MD 20771 - * - * Changes : - * - 2000/10/02 Willy Tarreau : - * - few fixes. Master's MAC address is now correctly taken from - * the first device when not previously set ; - * - detach support : call BOND_RELEASE to detach an enslaved interface. - * - give a mini-howto from command-line help : # ifenslave -h - * - * - 2001/02/16 Chad N. Tindel : - * - Master is now brought down before setting the MAC address. In - * the 2.4 kernel you can't change the MAC address while the device is - * up because you get EBUSY. - * - * - 2001/09/13 Takao Indoh - * - Added the ability to change the active interface on a mode 1 bond - * at runtime. - * - * - 2001/10/23 Chad N. Tindel : - * - No longer set the MAC address of the master. The bond device will - * take care of this itself - * - Try the SIOC*** versions of the bonding ioctls before using the - * old versions - * - 2002/02/18 Erik Habbinga : - * - ifr2.ifr_flags was not initialized in the hwaddr_notset case, - * SIOCGIFFLAGS now called before hwaddr_notset test - * - * - 2002/10/31 Tony Cureington : - * - If the master does not have a hardware address when the first slave - * is enslaved, the master is assigned the hardware address of that - * slave - there is a comment in bonding.c stating "ifenslave takes - * care of this now." This corrects the problem of slaves having - * different hardware addresses in active-backup mode when - * multiple interfaces are specified on a single ifenslave command - * (ifenslave bond0 eth0 eth1). - * - * - 2003/03/18 - Tsippy Mendelson and - * Shmulik Hen - * - Moved setting the slave's mac address and openning it, from - * the application to the driver. This enables support of modes - * that need to use the unique mac address of each slave. - * The driver also takes care of closing the slave and restoring its - * original mac address upon release. - * In addition, block possibility of enslaving before the master is up. - * This prevents putting the system in an undefined state. - * - * - 2003/05/01 - Amir Noam - * - Added ABI version control to restore compatibility between - * new/old ifenslave and new/old bonding. - * - Prevent adding an adapter that is already a slave. - * Fixes the problem of stalling the transmission and leaving - * the slave in a down state. - * - * - 2003/05/01 - Shmulik Hen - * - Prevent enslaving if the bond device is down. - * Fixes the problem of leaving the system in unstable state and - * halting when trying to remove the module. - * - Close socket on all abnormal exists. - * - Add versioning scheme that follows that of the bonding driver. - * current version is 1.0.0 as a base line. - * - * - 2003/05/22 - Jay Vosburgh - * - ifenslave -c was broken; it's now fixed - * - Fixed problem with routes vanishing from master during enslave - * processing. - * - * - 2003/05/27 - Amir Noam - * - Fix backward compatibility issues: - * For drivers not using ABI versions, slave was set down while - * it should be left up before enslaving. - * Also, master was not set down and the default set_mac_address() - * would fail and generate an error message in the system log. - * - For opt_c: slave should not be set to the master's setting - * while it is running. It was already set during enslave. To - * simplify things, it is now handled separately. - * - * - 2003/12/01 - Shmulik Hen - * - Code cleanup and style changes - * set version to 1.1.0 - */ - -#define APP_VERSION "1.1.0" -#define APP_RELDATE "December 1, 2003" -#define APP_NAME "ifenslave" - -static char *version = -APP_NAME ".c:v" APP_VERSION " (" APP_RELDATE ")\n" -"o Donald Becker (becker@cesdis.gsfc.nasa.gov).\n" -"o Detach support added on 2000/10/02 by Willy Tarreau (willy at meta-x.org).\n" -"o 2.4 kernel support added on 2001/02/16 by Chad N. Tindel\n" -" (ctindel at ieee dot org).\n"; - -static const char *usage_msg = -"Usage: ifenslave [-f] [...]\n" -" ifenslave -d [...]\n" -" ifenslave -c \n" -" ifenslave --help\n"; - -static const char *help_msg = -"\n" -" To create a bond device, simply follow these three steps :\n" -" - ensure that the required drivers are properly loaded :\n" -" # modprobe bonding ; modprobe <3c59x|eepro100|pcnet32|tulip|...>\n" -" - assign an IP address to the bond device :\n" -" # ifconfig bond0 netmask broadcast \n" -" - attach all the interfaces you need to the bond device :\n" -" # ifenslave [{-f|--force}] bond0 eth0 [eth1 [eth2]...]\n" -" If bond0 didn't have a MAC address, it will take eth0's. Then, all\n" -" interfaces attached AFTER this assignment will get the same MAC addr.\n" -" (except for ALB/TLB modes)\n" -"\n" -" To set the bond device down and automatically release all the slaves :\n" -" # ifconfig bond0 down\n" -"\n" -" To detach a dead interface without setting the bond device down :\n" -" # ifenslave {-d|--detach} bond0 eth0 [eth1 [eth2]...]\n" -"\n" -" To change active slave :\n" -" # ifenslave {-c|--change-active} bond0 eth0\n" -"\n" -" To show master interface info\n" -" # ifenslave bond0\n" -"\n" -" To show all interfaces info\n" -" # ifenslave {-a|--all-interfaces}\n" -"\n" -" To be more verbose\n" -" # ifenslave {-v|--verbose} ...\n" -"\n" -" # ifenslave {-u|--usage} Show usage\n" -" # ifenslave {-V|--version} Show version\n" -" # ifenslave {-h|--help} This message\n" -"\n"; - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -typedef unsigned long long u64; /* hack, so we may include kernel's ethtool.h */ -typedef __uint32_t u32; /* ditto */ -typedef __uint16_t u16; /* ditto */ -typedef __uint8_t u8; /* ditto */ -#include - -struct option longopts[] = { - /* { name has_arg *flag val } */ - {"all-interfaces", 0, 0, 'a'}, /* Show all interfaces. */ - {"change-active", 0, 0, 'c'}, /* Change the active slave. */ - {"detach", 0, 0, 'd'}, /* Detach a slave interface. */ - {"force", 0, 0, 'f'}, /* Force the operation. */ - {"help", 0, 0, 'h'}, /* Give help */ - {"usage", 0, 0, 'u'}, /* Give usage */ - {"verbose", 0, 0, 'v'}, /* Report each action taken. */ - {"version", 0, 0, 'V'}, /* Emit version information. */ - { 0, 0, 0, 0} -}; - -/* Command-line flags. */ -unsigned int -opt_a = 0, /* Show-all-interfaces flag. */ -opt_c = 0, /* Change-active-slave flag. */ -opt_d = 0, /* Detach a slave interface. */ -opt_f = 0, /* Force the operation. */ -opt_h = 0, /* Help */ -opt_u = 0, /* Usage */ -opt_v = 0, /* Verbose flag. */ -opt_V = 0; /* Version */ - -int skfd = -1; /* AF_INET socket for ioctl() calls.*/ -int abi_ver = 0; /* userland - kernel ABI version */ -int hwaddr_set = 0; /* Master's hwaddr is set */ -int saved_errno; - -struct ifreq master_mtu, master_flags, master_hwaddr; -struct ifreq slave_mtu, slave_flags, slave_hwaddr; - -struct dev_ifr { - struct ifreq *req_ifr; - char *req_name; - int req_type; -}; - -struct dev_ifr master_ifra[] = { - {&master_mtu, "SIOCGIFMTU", SIOCGIFMTU}, - {&master_flags, "SIOCGIFFLAGS", SIOCGIFFLAGS}, - {&master_hwaddr, "SIOCGIFHWADDR", SIOCGIFHWADDR}, - {NULL, "", 0} -}; - -struct dev_ifr slave_ifra[] = { - {&slave_mtu, "SIOCGIFMTU", SIOCGIFMTU}, - {&slave_flags, "SIOCGIFFLAGS", SIOCGIFFLAGS}, - {&slave_hwaddr, "SIOCGIFHWADDR", SIOCGIFHWADDR}, - {NULL, "", 0} -}; - -static void if_print(char *ifname); -static int get_drv_info(char *master_ifname); -static int get_if_settings(char *ifname, struct dev_ifr ifra[]); -static int get_slave_flags(char *slave_ifname); -static int set_master_hwaddr(char *master_ifname, struct sockaddr *hwaddr); -static int set_slave_hwaddr(char *slave_ifname, struct sockaddr *hwaddr); -static int set_slave_mtu(char *slave_ifname, int mtu); -static int set_if_flags(char *ifname, short flags); -static int set_if_up(char *ifname, short flags); -static int set_if_down(char *ifname, short flags); -static int clear_if_addr(char *ifname); -static int set_if_addr(char *master_ifname, char *slave_ifname); -static int change_active(char *master_ifname, char *slave_ifname); -static int enslave(char *master_ifname, char *slave_ifname); -static int release(char *master_ifname, char *slave_ifname); -#define v_print(fmt, args...) \ - if (opt_v) \ - fprintf(stderr, fmt, ## args ) - -int main(int argc, char *argv[]) -{ - char **spp, *master_ifname, *slave_ifname; - int c, i, rv; - int res = 0; - int exclusive = 0; - - while ((c = getopt_long(argc, argv, "acdfhuvV", longopts, 0)) != EOF) { - switch (c) { - case 'a': opt_a++; exclusive++; break; - case 'c': opt_c++; exclusive++; break; - case 'd': opt_d++; exclusive++; break; - case 'f': opt_f++; exclusive++; break; - case 'h': opt_h++; exclusive++; break; - case 'u': opt_u++; exclusive++; break; - case 'v': opt_v++; break; - case 'V': opt_V++; exclusive++; break; - - case '?': - fprintf(stderr, "%s", usage_msg); - res = 2; - goto out; - } - } - - /* options check */ - if (exclusive > 1) { - fprintf(stderr, "%s", usage_msg); - res = 2; - goto out; - } - - if (opt_v || opt_V) { - printf("%s", version); - if (opt_V) { - res = 0; - goto out; - } - } - - if (opt_u) { - printf("%s", usage_msg); - res = 0; - goto out; - } - - if (opt_h) { - printf("%s", usage_msg); - printf("%s", help_msg); - res = 0; - goto out; - } - - /* Open a basic socket */ - if ((skfd = socket(AF_INET, SOCK_DGRAM, 0)) < 0) { - perror("socket"); - res = 1; - goto out; - } - - if (opt_a) { - if (optind == argc) { - /* No remaining args */ - /* show all interfaces */ - if_print((char *)NULL); - goto out; - } else { - /* Just show usage */ - fprintf(stderr, "%s", usage_msg); - res = 2; - goto out; - } - } - - /* Copy the interface name */ - spp = argv + optind; - master_ifname = *spp++; - - if (master_ifname == NULL) { - fprintf(stderr, "%s", usage_msg); - res = 2; - goto out; - } - - /* exchange abi version with bonding module */ - res = get_drv_info(master_ifname); - if (res) { - fprintf(stderr, - "Master '%s': Error: handshake with driver failed. " - "Aborting\n", - master_ifname); - goto out; - } - - slave_ifname = *spp++; - - if (slave_ifname == NULL) { - if (opt_d || opt_c) { - fprintf(stderr, "%s", usage_msg); - res = 2; - goto out; - } - - /* A single arg means show the - * configuration for this interface - */ - if_print(master_ifname); - goto out; - } - - res = get_if_settings(master_ifname, master_ifra); - if (res) { - /* Probably a good reason not to go on */ - fprintf(stderr, - "Master '%s': Error: get settings failed: %s. " - "Aborting\n", - master_ifname, strerror(res)); - goto out; - } - - /* check if master is indeed a master; - * if not then fail any operation - */ - if (!(master_flags.ifr_flags & IFF_MASTER)) { - fprintf(stderr, - "Illegal operation; the specified interface '%s' " - "is not a master. Aborting\n", - master_ifname); - res = 1; - goto out; - } - - /* check if master is up; if not then fail any operation */ - if (!(master_flags.ifr_flags & IFF_UP)) { - fprintf(stderr, - "Illegal operation; the specified master interface " - "'%s' is not up.\n", - master_ifname); - res = 1; - goto out; - } - - /* Only for enslaving */ - if (!opt_c && !opt_d) { - sa_family_t master_family = master_hwaddr.ifr_hwaddr.sa_family; - unsigned char *hwaddr = - (unsigned char *)master_hwaddr.ifr_hwaddr.sa_data; - - /* The family '1' is ARPHRD_ETHER for ethernet. */ - if (master_family != 1 && !opt_f) { - fprintf(stderr, - "Illegal operation: The specified master " - "interface '%s' is not ethernet-like.\n " - "This program is designed to work with " - "ethernet-like network interfaces.\n " - "Use the '-f' option to force the " - "operation.\n", - master_ifname); - res = 1; - goto out; - } - - /* Check master's hw addr */ - for (i = 0; i < 6; i++) { - if (hwaddr[i] != 0) { - hwaddr_set = 1; - break; - } - } - - if (hwaddr_set) { - v_print("current hardware address of master '%s' " - "is %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x, " - "type %d\n", - master_ifname, - hwaddr[0], hwaddr[1], - hwaddr[2], hwaddr[3], - hwaddr[4], hwaddr[5], - master_family); - } - } - - /* Accepts only one slave */ - if (opt_c) { - /* change active slave */ - res = get_slave_flags(slave_ifname); - if (res) { - fprintf(stderr, - "Slave '%s': Error: get flags failed. " - "Aborting\n", - slave_ifname); - goto out; - } - res = change_active(master_ifname, slave_ifname); - if (res) { - fprintf(stderr, - "Master '%s', Slave '%s': Error: " - "Change active failed\n", - master_ifname, slave_ifname); - } - } else { - /* Accept multiple slaves */ - do { - if (opt_d) { - /* detach a slave interface from the master */ - rv = get_slave_flags(slave_ifname); - if (rv) { - /* Can't work with this slave. */ - /* remember the error and skip it*/ - fprintf(stderr, - "Slave '%s': Error: get flags " - "failed. Skipping\n", - slave_ifname); - res = rv; - continue; - } - rv = release(master_ifname, slave_ifname); - if (rv) { - fprintf(stderr, - "Master '%s', Slave '%s': Error: " - "Release failed\n", - master_ifname, slave_ifname); - res = rv; - } - } else { - /* attach a slave interface to the master */ - rv = get_if_settings(slave_ifname, slave_ifra); - if (rv) { - /* Can't work with this slave. */ - /* remember the error and skip it*/ - fprintf(stderr, - "Slave '%s': Error: get " - "settings failed: %s. " - "Skipping\n", - slave_ifname, strerror(rv)); - res = rv; - continue; - } - rv = enslave(master_ifname, slave_ifname); - if (rv) { - fprintf(stderr, - "Master '%s', Slave '%s': Error: " - "Enslave failed\n", - master_ifname, slave_ifname); - res = rv; - } - } - } while ((slave_ifname = *spp++) != NULL); - } - -out: - if (skfd >= 0) { - close(skfd); - } - - return res; -} - -static short mif_flags; - -/* Get the interface configuration from the kernel. */ -static int if_getconfig(char *ifname) -{ - struct ifreq ifr; - int metric, mtu; /* Parameters of the master interface. */ - struct sockaddr dstaddr, broadaddr, netmask; - unsigned char *hwaddr; - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFFLAGS, &ifr) < 0) - return -1; - mif_flags = ifr.ifr_flags; - printf("The result of SIOCGIFFLAGS on %s is %x.\n", - ifname, ifr.ifr_flags); - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFADDR, &ifr) < 0) - return -1; - printf("The result of SIOCGIFADDR is %2.2x.%2.2x.%2.2x.%2.2x.\n", - ifr.ifr_addr.sa_data[0], ifr.ifr_addr.sa_data[1], - ifr.ifr_addr.sa_data[2], ifr.ifr_addr.sa_data[3]); - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFHWADDR, &ifr) < 0) - return -1; - - /* Gotta convert from 'char' to unsigned for printf(). */ - hwaddr = (unsigned char *)ifr.ifr_hwaddr.sa_data; - printf("The result of SIOCGIFHWADDR is type %d " - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", - ifr.ifr_hwaddr.sa_family, hwaddr[0], hwaddr[1], - hwaddr[2], hwaddr[3], hwaddr[4], hwaddr[5]); - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFMETRIC, &ifr) < 0) { - metric = 0; - } else - metric = ifr.ifr_metric; - printf("The result of SIOCGIFMETRIC is %d\n", metric); - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFMTU, &ifr) < 0) - mtu = 0; - else - mtu = ifr.ifr_mtu; - printf("The result of SIOCGIFMTU is %d\n", mtu); - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFDSTADDR, &ifr) < 0) { - memset(&dstaddr, 0, sizeof(struct sockaddr)); - } else - dstaddr = ifr.ifr_dstaddr; - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFBRDADDR, &ifr) < 0) { - memset(&broadaddr, 0, sizeof(struct sockaddr)); - } else - broadaddr = ifr.ifr_broadaddr; - - strcpy(ifr.ifr_name, ifname); - if (ioctl(skfd, SIOCGIFNETMASK, &ifr) < 0) { - memset(&netmask, 0, sizeof(struct sockaddr)); - } else - netmask = ifr.ifr_netmask; - - return 0; -} - -static void if_print(char *ifname) -{ - char buff[1024]; - struct ifconf ifc; - struct ifreq *ifr; - int i; - - if (ifname == (char *)NULL) { - ifc.ifc_len = sizeof(buff); - ifc.ifc_buf = buff; - if (ioctl(skfd, SIOCGIFCONF, &ifc) < 0) { - perror("SIOCGIFCONF failed"); - return; - } - - ifr = ifc.ifc_req; - for (i = ifc.ifc_len / sizeof(struct ifreq); --i >= 0; ifr++) { - if (if_getconfig(ifr->ifr_name) < 0) { - fprintf(stderr, - "%s: unknown interface.\n", - ifr->ifr_name); - continue; - } - - if (((mif_flags & IFF_UP) == 0) && !opt_a) continue; - /*ife_print(&ife);*/ - } - } else { - if (if_getconfig(ifname) < 0) { - fprintf(stderr, - "%s: unknown interface.\n", ifname); - } - } -} - -static int get_drv_info(char *master_ifname) -{ - struct ifreq ifr; - struct ethtool_drvinfo info; - char *endptr; - - memset(&ifr, 0, sizeof(ifr)); - strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); - ifr.ifr_data = (caddr_t)&info; - - info.cmd = ETHTOOL_GDRVINFO; - strncpy(info.driver, "ifenslave", 32); - snprintf(info.fw_version, 32, "%d", BOND_ABI_VERSION); - - if (ioctl(skfd, SIOCETHTOOL, &ifr) < 0) { - if (errno == EOPNOTSUPP) { - goto out; - } - - saved_errno = errno; - v_print("Master '%s': Error: get bonding info failed %s\n", - master_ifname, strerror(saved_errno)); - return 1; - } - - abi_ver = strtoul(info.fw_version, &endptr, 0); - if (*endptr) { - v_print("Master '%s': Error: got invalid string as an ABI " - "version from the bonding module\n", - master_ifname); - return 1; - } - -out: - v_print("ABI ver is %d\n", abi_ver); - - return 0; -} - -static int change_active(char *master_ifname, char *slave_ifname) -{ - struct ifreq ifr; - int res = 0; - - if (!(slave_flags.ifr_flags & IFF_SLAVE)) { - fprintf(stderr, - "Illegal operation: The specified slave interface " - "'%s' is not a slave\n", - slave_ifname); - return 1; - } - - strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); - strncpy(ifr.ifr_slave, slave_ifname, IFNAMSIZ); - if ((ioctl(skfd, SIOCBONDCHANGEACTIVE, &ifr) < 0) && - (ioctl(skfd, BOND_CHANGE_ACTIVE_OLD, &ifr) < 0)) { - saved_errno = errno; - v_print("Master '%s': Error: SIOCBONDCHANGEACTIVE failed: " - "%s\n", - master_ifname, strerror(saved_errno)); - res = 1; - } - - return res; -} - -static int enslave(char *master_ifname, char *slave_ifname) -{ - struct ifreq ifr; - int res = 0; - - if (slave_flags.ifr_flags & IFF_SLAVE) { - fprintf(stderr, - "Illegal operation: The specified slave interface " - "'%s' is already a slave\n", - slave_ifname); - return 1; - } - - res = set_if_down(slave_ifname, slave_flags.ifr_flags); - if (res) { - fprintf(stderr, - "Slave '%s': Error: bring interface down failed\n", - slave_ifname); - return res; - } - - if (abi_ver < 2) { - /* Older bonding versions would panic if the slave has no IP - * address, so get the IP setting from the master. - */ - set_if_addr(master_ifname, slave_ifname); - } else { - res = clear_if_addr(slave_ifname); - if (res) { - fprintf(stderr, - "Slave '%s': Error: clear address failed\n", - slave_ifname); - return res; - } - } - - if (master_mtu.ifr_mtu != slave_mtu.ifr_mtu) { - res = set_slave_mtu(slave_ifname, master_mtu.ifr_mtu); - if (res) { - fprintf(stderr, - "Slave '%s': Error: set MTU failed\n", - slave_ifname); - return res; - } - } - - if (hwaddr_set) { - /* Master already has an hwaddr - * so set it's hwaddr to the slave - */ - if (abi_ver < 1) { - /* The driver is using an old ABI, so - * the application sets the slave's - * hwaddr - */ - res = set_slave_hwaddr(slave_ifname, - &(master_hwaddr.ifr_hwaddr)); - if (res) { - fprintf(stderr, - "Slave '%s': Error: set hw address " - "failed\n", - slave_ifname); - goto undo_mtu; - } - - /* For old ABI the application needs to bring the - * slave back up - */ - res = set_if_up(slave_ifname, slave_flags.ifr_flags); - if (res) { - fprintf(stderr, - "Slave '%s': Error: bring interface " - "down failed\n", - slave_ifname); - goto undo_slave_mac; - } - } - /* The driver is using a new ABI, - * so the driver takes care of setting - * the slave's hwaddr and bringing - * it up again - */ - } else { - /* No hwaddr for master yet, so - * set the slave's hwaddr to it - */ - if (abi_ver < 1) { - /* For old ABI, the master needs to be - * down before setting its hwaddr - */ - res = set_if_down(master_ifname, master_flags.ifr_flags); - if (res) { - fprintf(stderr, - "Master '%s': Error: bring interface " - "down failed\n", - master_ifname); - goto undo_mtu; - } - } - - res = set_master_hwaddr(master_ifname, - &(slave_hwaddr.ifr_hwaddr)); - if (res) { - fprintf(stderr, - "Master '%s': Error: set hw address " - "failed\n", - master_ifname); - goto undo_mtu; - } - - if (abi_ver < 1) { - /* For old ABI, bring the master - * back up - */ - res = set_if_up(master_ifname, master_flags.ifr_flags); - if (res) { - fprintf(stderr, - "Master '%s': Error: bring interface " - "up failed\n", - master_ifname); - goto undo_master_mac; - } - } - - hwaddr_set = 1; - } - - /* Do the real thing */ - strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); - strncpy(ifr.ifr_slave, slave_ifname, IFNAMSIZ); - if ((ioctl(skfd, SIOCBONDENSLAVE, &ifr) < 0) && - (ioctl(skfd, BOND_ENSLAVE_OLD, &ifr) < 0)) { - saved_errno = errno; - v_print("Master '%s': Error: SIOCBONDENSLAVE failed: %s\n", - master_ifname, strerror(saved_errno)); - res = 1; - } - - if (res) { - goto undo_master_mac; - } - - return 0; - -/* rollback (best effort) */ -undo_master_mac: - set_master_hwaddr(master_ifname, &(master_hwaddr.ifr_hwaddr)); - hwaddr_set = 0; - goto undo_mtu; -undo_slave_mac: - set_slave_hwaddr(slave_ifname, &(slave_hwaddr.ifr_hwaddr)); -undo_mtu: - set_slave_mtu(slave_ifname, slave_mtu.ifr_mtu); - return res; -} - -static int release(char *master_ifname, char *slave_ifname) -{ - struct ifreq ifr; - int res = 0; - - if (!(slave_flags.ifr_flags & IFF_SLAVE)) { - fprintf(stderr, - "Illegal operation: The specified slave interface " - "'%s' is not a slave\n", - slave_ifname); - return 1; - } - - strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); - strncpy(ifr.ifr_slave, slave_ifname, IFNAMSIZ); - if ((ioctl(skfd, SIOCBONDRELEASE, &ifr) < 0) && - (ioctl(skfd, BOND_RELEASE_OLD, &ifr) < 0)) { - saved_errno = errno; - v_print("Master '%s': Error: SIOCBONDRELEASE failed: %s\n", - master_ifname, strerror(saved_errno)); - return 1; - } else if (abi_ver < 1) { - /* The driver is using an old ABI, so we'll set the interface - * down to avoid any conflicts due to same MAC/IP - */ - res = set_if_down(slave_ifname, slave_flags.ifr_flags); - if (res) { - fprintf(stderr, - "Slave '%s': Error: bring interface " - "down failed\n", - slave_ifname); - } - } - - /* set to default mtu */ - set_slave_mtu(slave_ifname, 1500); - - return res; -} - -static int get_if_settings(char *ifname, struct dev_ifr ifra[]) -{ - int i; - int res = 0; - - for (i = 0; ifra[i].req_ifr; i++) { - strncpy(ifra[i].req_ifr->ifr_name, ifname, IFNAMSIZ); - res = ioctl(skfd, ifra[i].req_type, ifra[i].req_ifr); - if (res < 0) { - saved_errno = errno; - v_print("Interface '%s': Error: %s failed: %s\n", - ifname, ifra[i].req_name, - strerror(saved_errno)); - - return saved_errno; - } - } - - return 0; -} - -static int get_slave_flags(char *slave_ifname) -{ - int res = 0; - - strncpy(slave_flags.ifr_name, slave_ifname, IFNAMSIZ); - res = ioctl(skfd, SIOCGIFFLAGS, &slave_flags); - if (res < 0) { - saved_errno = errno; - v_print("Slave '%s': Error: SIOCGIFFLAGS failed: %s\n", - slave_ifname, strerror(saved_errno)); - } else { - v_print("Slave %s: flags %04X.\n", - slave_ifname, slave_flags.ifr_flags); - } - - return res; -} - -static int set_master_hwaddr(char *master_ifname, struct sockaddr *hwaddr) -{ - unsigned char *addr = (unsigned char *)hwaddr->sa_data; - struct ifreq ifr; - int res = 0; - - strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); - memcpy(&(ifr.ifr_hwaddr), hwaddr, sizeof(struct sockaddr)); - res = ioctl(skfd, SIOCSIFHWADDR, &ifr); - if (res < 0) { - saved_errno = errno; - v_print("Master '%s': Error: SIOCSIFHWADDR failed: %s\n", - master_ifname, strerror(saved_errno)); - return res; - } else { - v_print("Master '%s': hardware address set to " - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", - master_ifname, addr[0], addr[1], addr[2], - addr[3], addr[4], addr[5]); - } - - return res; -} - -static int set_slave_hwaddr(char *slave_ifname, struct sockaddr *hwaddr) -{ - unsigned char *addr = (unsigned char *)hwaddr->sa_data; - struct ifreq ifr; - int res = 0; - - strncpy(ifr.ifr_name, slave_ifname, IFNAMSIZ); - memcpy(&(ifr.ifr_hwaddr), hwaddr, sizeof(struct sockaddr)); - res = ioctl(skfd, SIOCSIFHWADDR, &ifr); - if (res < 0) { - saved_errno = errno; - - v_print("Slave '%s': Error: SIOCSIFHWADDR failed: %s\n", - slave_ifname, strerror(saved_errno)); - - if (saved_errno == EBUSY) { - v_print(" The device is busy: it must be idle " - "before running this command.\n"); - } else if (saved_errno == EOPNOTSUPP) { - v_print(" The device does not support setting " - "the MAC address.\n" - " Your kernel likely does not support slave " - "devices.\n"); - } else if (saved_errno == EINVAL) { - v_print(" The device's address type does not match " - "the master's address type.\n"); - } - return res; - } else { - v_print("Slave '%s': hardware address set to " - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", - slave_ifname, addr[0], addr[1], addr[2], - addr[3], addr[4], addr[5]); - } - - return res; -} - -static int set_slave_mtu(char *slave_ifname, int mtu) -{ - struct ifreq ifr; - int res = 0; - - ifr.ifr_mtu = mtu; - strncpy(ifr.ifr_name, slave_ifname, IFNAMSIZ); - - res = ioctl(skfd, SIOCSIFMTU, &ifr); - if (res < 0) { - saved_errno = errno; - v_print("Slave '%s': Error: SIOCSIFMTU failed: %s\n", - slave_ifname, strerror(saved_errno)); - } else { - v_print("Slave '%s': MTU set to %d.\n", slave_ifname, mtu); - } - - return res; -} - -static int set_if_flags(char *ifname, short flags) -{ - struct ifreq ifr; - int res = 0; - - ifr.ifr_flags = flags; - strncpy(ifr.ifr_name, ifname, IFNAMSIZ); - - res = ioctl(skfd, SIOCSIFFLAGS, &ifr); - if (res < 0) { - saved_errno = errno; - v_print("Interface '%s': Error: SIOCSIFFLAGS failed: %s\n", - ifname, strerror(saved_errno)); - } else { - v_print("Interface '%s': flags set to %04X.\n", ifname, flags); - } - - return res; -} - -static int set_if_up(char *ifname, short flags) -{ - return set_if_flags(ifname, flags | IFF_UP); -} - -static int set_if_down(char *ifname, short flags) -{ - return set_if_flags(ifname, flags & ~IFF_UP); -} - -static int clear_if_addr(char *ifname) -{ - struct ifreq ifr; - int res = 0; - - strncpy(ifr.ifr_name, ifname, IFNAMSIZ); - ifr.ifr_addr.sa_family = AF_INET; - memset(ifr.ifr_addr.sa_data, 0, sizeof(ifr.ifr_addr.sa_data)); - - res = ioctl(skfd, SIOCSIFADDR, &ifr); - if (res < 0) { - saved_errno = errno; - v_print("Interface '%s': Error: SIOCSIFADDR failed: %s\n", - ifname, strerror(saved_errno)); - } else { - v_print("Interface '%s': address cleared\n", ifname); - } - - return res; -} - -static int set_if_addr(char *master_ifname, char *slave_ifname) -{ - struct ifreq ifr; - int res; - unsigned char *ipaddr; - int i; - struct { - char *req_name; - char *desc; - int g_ioctl; - int s_ioctl; - } ifra[] = { - {"IFADDR", "addr", SIOCGIFADDR, SIOCSIFADDR}, - {"DSTADDR", "destination addr", SIOCGIFDSTADDR, SIOCSIFDSTADDR}, - {"BRDADDR", "broadcast addr", SIOCGIFBRDADDR, SIOCSIFBRDADDR}, - {"NETMASK", "netmask", SIOCGIFNETMASK, SIOCSIFNETMASK}, - {NULL, NULL, 0, 0}, - }; - - for (i = 0; ifra[i].req_name; i++) { - strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); - res = ioctl(skfd, ifra[i].g_ioctl, &ifr); - if (res < 0) { - int saved_errno = errno; - - v_print("Interface '%s': Error: SIOCG%s failed: %s\n", - master_ifname, ifra[i].req_name, - strerror(saved_errno)); - - ifr.ifr_addr.sa_family = AF_INET; - memset(ifr.ifr_addr.sa_data, 0, - sizeof(ifr.ifr_addr.sa_data)); - } - - strncpy(ifr.ifr_name, slave_ifname, IFNAMSIZ); - res = ioctl(skfd, ifra[i].s_ioctl, &ifr); - if (res < 0) { - int saved_errno = errno; - - v_print("Interface '%s': Error: SIOCS%s failed: %s\n", - slave_ifname, ifra[i].req_name, - strerror(saved_errno)); - - } - - ipaddr = (unsigned char *)ifr.ifr_addr.sa_data; - v_print("Interface '%s': set IP %s to %d.%d.%d.%d\n", - slave_ifname, ifra[i].desc, - ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]); - } - - return 0; -} - -/* - * Local variables: - * version-control: t - * kept-new-versions: 5 - * c-indent-level: 4 - * c-basic-offset: 4 - * tab-width: 4 - * compile-command: "gcc -Wall -Wstrict-prototypes -O -I/usr/src/linux/include ifenslave.c -o ifenslave" - * End: - */ - -- cgit v1.2.3 From 76723bca2802eb80990a5fefa179662e2e561d66 Mon Sep 17 00:00:00 2001 From: Sebastian Hesselbarth Date: Wed, 29 May 2013 09:32:48 +0000 Subject: net: mv643xx_eth: add DT parsing support This adds device tree parsing support for the shared driver of mv643xx_eth. As the bindings are slightly different from current PPC bindings new binding documentation is also added. Following PPC-style device setup, the shared driver now also adds port platform_devices and sets up port platform_data. Signed-off-by: Sebastian Hesselbarth Signed-off-by: David S. Miller --- .../devicetree/bindings/net/marvell-orion-net.txt | 85 ++++++++++++ drivers/net/ethernet/marvell/mv643xx_eth.c | 153 ++++++++++++++++++++- 2 files changed, 234 insertions(+), 4 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/marvell-orion-net.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/marvell-orion-net.txt b/Documentation/devicetree/bindings/net/marvell-orion-net.txt new file mode 100644 index 000000000000..a73b79f227e1 --- /dev/null +++ b/Documentation/devicetree/bindings/net/marvell-orion-net.txt @@ -0,0 +1,85 @@ +Marvell Orion/Discovery ethernet controller +============================================= + +The Marvell Discovery ethernet controller can be found on Marvell Orion SoCs +(Kirkwood, Dove, Orion5x, and Discovery Innovation) and as part of Marvell +Discovery system controller chips (mv64[345]60). + +The Discovery ethernet controller is described with two levels of nodes. The +first level describes the ethernet controller itself and the second level +describes up to 3 ethernet port nodes within that controller. The reason for +the multiple levels is that the port registers are interleaved within a single +set of controller registers. Each port node describes port-specific properties. + +Note: The above separation is only true for Discovery system controllers. +For Orion SoCs we stick to the separation, although there each controller has +only one port associated. Multiple ports are implemented as multiple single-port +controllers. As Kirkwood has some issues with proper initialization after reset, +an extra compatible string is added for it. + +* Ethernet controller node + +Required controller properties: + - #address-cells: shall be 1. + - #size-cells: shall be 0. + - compatible: shall be one of "marvell,orion-eth", "marvell,kirkwood-eth". + - reg: address and length of the controller registers. + +Optional controller properties: + - clocks: phandle reference to the controller clock. + - marvell,tx-checksum-limit: max tx packet size for hardware checksum. + +* Ethernet port node + +Required port properties: + - device_type: shall be "network". + - compatible: shall be one of "marvell,orion-eth-port", + "marvell,kirkwood-eth-port". + - reg: port number relative to ethernet controller, shall be 0, 1, or 2. + - interrupts: port interrupt. + - local-mac-address: 6 bytes MAC address. + +Optional port properties: + - marvell,tx-queue-size: size of the transmit ring buffer. + - marvell,tx-sram-addr: address of transmit descriptor buffer located in SRAM. + - marvell,tx-sram-size: size of transmit descriptor buffer located in SRAM. + - marvell,rx-queue-size: size of the receive ring buffer. + - marvell,rx-sram-addr: address of receive descriptor buffer located in SRAM. + - marvell,rx-sram-size: size of receive descriptor buffer located in SRAM. + +and + + - phy-handle: phandle reference to ethernet PHY. + +or + + - speed: port speed if no PHY connected. + - duplex: port mode if no PHY connected. + +* Node example: + +mdio-bus { + ... + ethphy: ethernet-phy@8 { + device_type = "ethernet-phy"; + ... + }; +}; + +eth: ethernet-controller@72000 { + compatible = "marvell,orion-eth"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x72000 0x2000>; + clocks = <&gate_clk 2>; + marvell,tx-checksum-limit = <1600>; + + ethernet@0 { + device_type = "network"; + compatible = "marvell,orion-eth-port"; + reg = <0>; + interrupts = <29>; + phy-handle = <ðphy>; + local-mac-address = [00 00 00 00 00 00]; + }; +}; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 1b31d752ff90..23ea7b6e23f1 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -60,6 +60,9 @@ #include #include #include +#include +#include +#include #include static char mv643xx_eth_driver_name[] = "mv643xx_eth"; @@ -2453,13 +2456,148 @@ static void infer_hw_params(struct mv643xx_eth_shared_private *msp) } } +#if defined(CONFIG_OF) +static const struct of_device_id mv643xx_eth_shared_ids[] = { + { .compatible = "marvell,orion-eth", }, + { .compatible = "marvell,kirkwood-eth", }, + { } +}; +MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids); +#endif + +#if defined(CONFIG_OF) && !defined(CONFIG_MV64X60) +#define mv643xx_eth_property(_np, _name, _v) \ + do { \ + u32 tmp; \ + if (!of_property_read_u32(_np, "marvell," _name, &tmp)) \ + _v = tmp; \ + } while (0) + +static struct platform_device *port_platdev[3]; + +static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, + struct device_node *pnp) +{ + struct platform_device *ppdev; + struct mv643xx_eth_platform_data ppd; + struct resource res; + const char *mac_addr; + int ret; + + memset(&ppd, 0, sizeof(ppd)); + ppd.shared = pdev; + + memset(&res, 0, sizeof(res)); + if (!of_irq_to_resource(pnp, 0, &res)) { + dev_err(&pdev->dev, "missing interrupt on %s\n", pnp->name); + return -EINVAL; + } + + if (of_property_read_u32(pnp, "reg", &ppd.port_number)) { + dev_err(&pdev->dev, "missing reg property on %s\n", pnp->name); + return -EINVAL; + } + + if (ppd.port_number >= 3) { + dev_err(&pdev->dev, "invalid reg property on %s\n", pnp->name); + return -EINVAL; + } + + mac_addr = of_get_mac_address(pnp); + if (mac_addr) + memcpy(ppd.mac_addr, mac_addr, 6); + + mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size); + mv643xx_eth_property(pnp, "tx-sram-addr", ppd.tx_sram_addr); + mv643xx_eth_property(pnp, "tx-sram-size", ppd.tx_sram_size); + mv643xx_eth_property(pnp, "rx-queue-size", ppd.rx_queue_size); + mv643xx_eth_property(pnp, "rx-sram-addr", ppd.rx_sram_addr); + mv643xx_eth_property(pnp, "rx-sram-size", ppd.rx_sram_size); + + ppd.phy_node = of_parse_phandle(pnp, "phy-handle", 0); + if (!ppd.phy_node) { + ppd.phy_addr = MV643XX_ETH_PHY_NONE; + of_property_read_u32(pnp, "speed", &ppd.speed); + of_property_read_u32(pnp, "duplex", &ppd.duplex); + } + + ppdev = platform_device_alloc(MV643XX_ETH_NAME, ppd.port_number); + if (!ppdev) + return -ENOMEM; + ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + + ret = platform_device_add_resources(ppdev, &res, 1); + if (ret) + goto port_err; + + ret = platform_device_add_data(ppdev, &ppd, sizeof(ppd)); + if (ret) + goto port_err; + + ret = platform_device_add(ppdev); + if (ret) + goto port_err; + + port_platdev[ppd.port_number] = ppdev; + + return 0; + +port_err: + platform_device_put(ppdev); + return ret; +} + +static int mv643xx_eth_shared_of_probe(struct platform_device *pdev) +{ + struct mv643xx_eth_shared_platform_data *pd; + struct device_node *pnp, *np = pdev->dev.of_node; + int ret; + + /* bail out if not registered from DT */ + if (!np) + return 0; + + pd = devm_kzalloc(&pdev->dev, sizeof(*pd), GFP_KERNEL); + if (!pd) + return -ENOMEM; + pdev->dev.platform_data = pd; + + mv643xx_eth_property(np, "tx-checksum-limit", pd->tx_csum_limit); + + for_each_available_child_of_node(np, pnp) { + ret = mv643xx_eth_shared_of_add_port(pdev, pnp); + if (ret) + return ret; + } + return 0; +} + +static void mv643xx_eth_shared_of_remove(void) +{ + int n; + + for (n = 0; n < 3; n++) { + platform_device_del(port_platdev[n]); + port_platdev[n] = NULL; + } +} +#else +static int mv643xx_eth_shared_of_probe(struct platform_device *pdev) +{ + return 0 +} + +#define mv643xx_eth_shared_of_remove() +#endif + static int mv643xx_eth_shared_probe(struct platform_device *pdev) { static int mv643xx_eth_version_printed; - struct mv643xx_eth_shared_platform_data *pd = pdev->dev.platform_data; + struct mv643xx_eth_shared_platform_data *pd; struct mv643xx_eth_shared_private *msp; const struct mbus_dram_target_info *dram; struct resource *res; + int ret; if (!mv643xx_eth_version_printed++) pr_notice("MV-643xx 10/100/1000 ethernet driver version %s\n", @@ -2472,6 +2610,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) msp = devm_kzalloc(&pdev->dev, sizeof(*msp), GFP_KERNEL); if (msp == NULL) return -ENOMEM; + platform_set_drvdata(pdev, msp); msp->base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (msp->base == NULL) @@ -2488,12 +2627,15 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) if (dram) mv643xx_eth_conf_mbus_windows(msp, dram); + ret = mv643xx_eth_shared_of_probe(pdev); + if (ret) + return ret; + pd = pdev->dev.platform_data; + msp->tx_csum_limit = (pd != NULL && pd->tx_csum_limit) ? pd->tx_csum_limit : 9 * 1024; infer_hw_params(msp); - platform_set_drvdata(pdev, msp); - return 0; } @@ -2501,9 +2643,9 @@ static int mv643xx_eth_shared_remove(struct platform_device *pdev) { struct mv643xx_eth_shared_private *msp = platform_get_drvdata(pdev); + mv643xx_eth_shared_of_remove(); if (!IS_ERR(msp->clk)) clk_disable_unprepare(msp->clk); - return 0; } @@ -2513,6 +2655,7 @@ static struct platform_driver mv643xx_eth_shared_driver = { .driver = { .name = MV643XX_ETH_SHARED_NAME, .owner = THIS_MODULE, + .of_match_table = of_match_ptr(mv643xx_eth_shared_ids), }, }; @@ -2721,6 +2864,8 @@ static int mv643xx_eth_probe(struct platform_device *pdev) if (!IS_ERR(mp->clk)) { clk_prepare_enable(mp->clk); mp->t_clk = clk_get_rate(mp->clk); + } else if (!IS_ERR(mp->shared->clk)) { + mp->t_clk = clk_get_rate(mp->shared->clk); } set_params(mp, pd); -- cgit v1.2.3 From 492205050d77bcc4f85f6dc0da6b6fdbca1d6ff7 Mon Sep 17 00:00:00 2001 From: Stefan Roese Date: Thu, 30 May 2013 03:49:20 +0000 Subject: net: Add EMAC ethernet driver found on Allwinner A10 SoC's The Allwinner A10 has an ethernet controller that seem to be developped internally by them. The exact feature set of this controller is unknown, since there is no public documentation for this IP, and this driver is mostly the one published by Allwinner that has been heavily cleaned up. Signed-off-by: Stefan Roese Signed-off-by: Maxime Ripard Tested-by: Richard Genoud Signed-off-by: David S. Miller --- .../bindings/net/allwinner,sun4i-emac.txt | 22 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/allwinner/Kconfig | 36 + drivers/net/ethernet/allwinner/Makefile | 5 + drivers/net/ethernet/allwinner/sun4i-emac.c | 960 +++++++++++++++++++++ drivers/net/ethernet/allwinner/sun4i-emac.h | 108 +++ 7 files changed, 1133 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt create mode 100644 drivers/net/ethernet/allwinner/Kconfig create mode 100644 drivers/net/ethernet/allwinner/Makefile create mode 100644 drivers/net/ethernet/allwinner/sun4i-emac.c create mode 100644 drivers/net/ethernet/allwinner/sun4i-emac.h (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt new file mode 100644 index 000000000000..b90bfcd138ff --- /dev/null +++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt @@ -0,0 +1,22 @@ +* Allwinner EMAC ethernet controller + +Required properties: +- compatible: should be "allwinner,sun4i-emac". +- reg: address and length of the register set for the device. +- interrupts: interrupt for the device +- phy: A phandle to a phy node defining the PHY address (as the reg + property, a single integer). +- clocks: A phandle to the reference clock for this device + +Optional properties: +- (local-)mac-address: mac address to be used by this driver + +Example: + +emac: ethernet@01c0b000 { + compatible = "allwinner,sun4i-emac"; + reg = <0x01c0b000 0x1000>; + interrupts = <55>; + clocks = <&ahb_gates 17>; + phy = <&phy0>; +}; diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index ed956e08d38b..18fd6fbeb109 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -20,6 +20,7 @@ config SUNGEM_PHY source "drivers/net/ethernet/3com/Kconfig" source "drivers/net/ethernet/adaptec/Kconfig" source "drivers/net/ethernet/aeroflex/Kconfig" +source "drivers/net/ethernet/allwinner/Kconfig" source "drivers/net/ethernet/alteon/Kconfig" source "drivers/net/ethernet/amd/Kconfig" source "drivers/net/ethernet/apple/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 8268d85f9448..009da27b6e26 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_NET_VENDOR_3COM) += 3com/ obj-$(CONFIG_NET_VENDOR_8390) += 8390/ obj-$(CONFIG_NET_VENDOR_ADAPTEC) += adaptec/ obj-$(CONFIG_GRETH) += aeroflex/ +obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/ obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/ obj-$(CONFIG_NET_VENDOR_AMD) += amd/ obj-$(CONFIG_NET_VENDOR_APPLE) += apple/ diff --git a/drivers/net/ethernet/allwinner/Kconfig b/drivers/net/ethernet/allwinner/Kconfig new file mode 100644 index 000000000000..66d35324f31e --- /dev/null +++ b/drivers/net/ethernet/allwinner/Kconfig @@ -0,0 +1,36 @@ +# +# Allwinner device configuration +# + +config NET_VENDOR_ALLWINNER + bool "Allwinner devices" + default y + depends on ARCH_SUNXI + ---help--- + If you have a network (Ethernet) card belonging to this + class, say Y and read the Ethernet-HOWTO, available from + . + + Note that the answer to this question doesn't directly + affect the kernel: saying N will just cause the configurator + to skip all the questions about Allwinner cards. If you say Y, + you will be asked for your specific card in the following + questions. + +if NET_VENDOR_ALLWINNER + +config SUN4I_EMAC + tristate "Allwinner A10 EMAC support" + depends on ARCH_SUNXI + depends on OF + select CRC32 + select NET_CORE + select MII + select PHYLIB + ---help--- + Support for Allwinner A10 EMAC ethernet driver. + + To compile this driver as a module, choose M here. The module + will be called sun4i-emac. + +endif # NET_VENDOR_ALLWINNER diff --git a/drivers/net/ethernet/allwinner/Makefile b/drivers/net/ethernet/allwinner/Makefile new file mode 100644 index 000000000000..03129f796514 --- /dev/null +++ b/drivers/net/ethernet/allwinner/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the Allwinner device drivers. +# + +obj-$(CONFIG_SUN4I_EMAC) += sun4i-emac.o diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c new file mode 100644 index 000000000000..b411344e719e --- /dev/null +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -0,0 +1,960 @@ +/* + * Allwinner EMAC Fast Ethernet driver for Linux. + * + * Copyright 2012-2013 Stefan Roese + * Copyright 2013 Maxime Ripard + * + * Based on the Linux driver provided by Allwinner: + * Copyright (C) 1997 Sten Wang + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "sun4i-emac.h" + +#define DRV_NAME "sun4i-emac" +#define DRV_VERSION "1.02" + +#define EMAC_MAX_FRAME_LEN 0x0600 + +/* Transmit timeout, default 5 seconds. */ +static int watchdog = 5000; +module_param(watchdog, int, 0400); +MODULE_PARM_DESC(watchdog, "transmit timeout in milliseconds"); + +/* EMAC register address locking. + * + * The EMAC uses an address register to control where data written + * to the data register goes. This means that the address register + * must be preserved over interrupts or similar calls. + * + * During interrupt and other critical calls, a spinlock is used to + * protect the system, but the calls themselves save the address + * in the address register in case they are interrupting another + * access to the device. + * + * For general accesses a lock is provided so that calls which are + * allowed to sleep are serialised so that the address register does + * not need to be saved. This lock also serves to serialise access + * to the EEPROM and PHY access registers which are shared between + * these two devices. + */ + +/* The driver supports the original EMACE, and now the two newer + * devices, EMACA and EMACB. + */ + +struct emac_board_info { + struct clk *clk; + struct device *dev; + struct platform_device *pdev; + spinlock_t lock; + void __iomem *membase; + u32 msg_enable; + struct net_device *ndev; + struct sk_buff *skb_last; + u16 tx_fifo_stat; + + int emacrx_completed_flag; + + struct phy_device *phy_dev; + struct device_node *phy_node; + unsigned int link; + unsigned int speed; + unsigned int duplex; + + phy_interface_t phy_interface; +}; + +static void emac_update_speed(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + unsigned int reg_val; + + /* set EMAC SPEED, depend on PHY */ + reg_val = readl(db->membase + EMAC_MAC_SUPP_REG); + reg_val &= ~(0x1 << 8); + if (db->speed == SPEED_100) + reg_val |= 1 << 8; + writel(reg_val, db->membase + EMAC_MAC_SUPP_REG); +} + +static void emac_update_duplex(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + unsigned int reg_val; + + /* set duplex depend on phy */ + reg_val = readl(db->membase + EMAC_MAC_CTL1_REG); + reg_val &= ~EMAC_MAC_CTL1_DUPLEX_EN; + if (db->duplex) + reg_val |= EMAC_MAC_CTL1_DUPLEX_EN; + writel(reg_val, db->membase + EMAC_MAC_CTL1_REG); +} + +static void emac_handle_link_change(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + struct phy_device *phydev = db->phy_dev; + unsigned long flags; + int status_change = 0; + + if (phydev->link) { + if (db->speed != phydev->speed) { + spin_lock_irqsave(&db->lock, flags); + db->speed = phydev->speed; + emac_update_speed(dev); + spin_unlock_irqrestore(&db->lock, flags); + status_change = 1; + } + + if (db->duplex != phydev->duplex) { + spin_lock_irqsave(&db->lock, flags); + db->duplex = phydev->duplex; + emac_update_duplex(dev); + spin_unlock_irqrestore(&db->lock, flags); + status_change = 1; + } + } + + if (phydev->link != db->link) { + if (!phydev->link) { + db->speed = 0; + db->duplex = -1; + } + db->link = phydev->link; + + status_change = 1; + } + + if (status_change) + phy_print_status(phydev); +} + +static int emac_mdio_probe(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + + /* to-do: PHY interrupts are currently not supported */ + + /* attach the mac to the phy */ + db->phy_dev = of_phy_connect(db->ndev, db->phy_node, + &emac_handle_link_change, 0, + db->phy_interface); + if (!db->phy_dev) { + netdev_err(db->ndev, "could not find the PHY\n"); + return -ENODEV; + } + + /* mask with MAC supported features */ + db->phy_dev->supported &= PHY_BASIC_FEATURES; + db->phy_dev->advertising = db->phy_dev->supported; + + db->link = 0; + db->speed = 0; + db->duplex = -1; + + return 0; +} + +static void emac_mdio_remove(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + + phy_disconnect(db->phy_dev); + db->phy_dev = NULL; +} + +static void emac_reset(struct emac_board_info *db) +{ + dev_dbg(db->dev, "resetting device\n"); + + /* RESET device */ + writel(0, db->membase + EMAC_CTL_REG); + udelay(200); + writel(EMAC_CTL_RESET, db->membase + EMAC_CTL_REG); + udelay(200); +} + +static void emac_outblk_32bit(void __iomem *reg, void *data, int count) +{ + writesl(reg, data, round_up(count, 4) / 4); +} + +static void emac_inblk_32bit(void __iomem *reg, void *data, int count) +{ + readsl(reg, data, round_up(count, 4) / 4); +} + +static int emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + struct emac_board_info *dm = netdev_priv(dev); + struct phy_device *phydev = dm->phy_dev; + + if (!netif_running(dev)) + return -EINVAL; + + if (!phydev) + return -ENODEV; + + return phy_mii_ioctl(phydev, rq, cmd); +} + +/* ethtool ops */ +static void emac_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, DRV_NAME, sizeof(DRV_NAME)); + strlcpy(info->version, DRV_VERSION, sizeof(DRV_VERSION)); + strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info)); +} + +static int emac_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct emac_board_info *dm = netdev_priv(dev); + struct phy_device *phydev = dm->phy_dev; + + if (!phydev) + return -ENODEV; + + return phy_ethtool_gset(phydev, cmd); +} + +static int emac_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct emac_board_info *dm = netdev_priv(dev); + struct phy_device *phydev = dm->phy_dev; + + if (!phydev) + return -ENODEV; + + return phy_ethtool_sset(phydev, cmd); +} + +static const struct ethtool_ops emac_ethtool_ops = { + .get_drvinfo = emac_get_drvinfo, + .get_settings = emac_get_settings, + .set_settings = emac_set_settings, + .get_link = ethtool_op_get_link, +}; + +unsigned int emac_setup(struct net_device *ndev) +{ + struct emac_board_info *db = netdev_priv(ndev); + unsigned int reg_val; + + /* set up TX */ + reg_val = readl(db->membase + EMAC_TX_MODE_REG); + + writel(reg_val | EMAC_TX_MODE_ABORTED_FRAME_EN, + db->membase + EMAC_TX_MODE_REG); + + /* set up RX */ + reg_val = readl(db->membase + EMAC_RX_CTL_REG); + + writel(reg_val | EMAC_RX_CTL_PASS_LEN_OOR_EN | + EMAC_RX_CTL_ACCEPT_UNICAST_EN | EMAC_RX_CTL_DA_FILTER_EN | + EMAC_RX_CTL_ACCEPT_MULTICAST_EN | + EMAC_RX_CTL_ACCEPT_BROADCAST_EN, + db->membase + EMAC_RX_CTL_REG); + + /* set MAC */ + /* set MAC CTL0 */ + reg_val = readl(db->membase + EMAC_MAC_CTL0_REG); + writel(reg_val | EMAC_MAC_CTL0_RX_FLOW_CTL_EN | + EMAC_MAC_CTL0_TX_FLOW_CTL_EN, + db->membase + EMAC_MAC_CTL0_REG); + + /* set MAC CTL1 */ + reg_val = readl(db->membase + EMAC_MAC_CTL1_REG); + reg_val |= EMAC_MAC_CTL1_LEN_CHECK_EN; + reg_val |= EMAC_MAC_CTL1_CRC_EN; + reg_val |= EMAC_MAC_CTL1_PAD_EN; + writel(reg_val, db->membase + EMAC_MAC_CTL1_REG); + + /* set up IPGT */ + writel(EMAC_MAC_IPGT_FULL_DUPLEX, db->membase + EMAC_MAC_IPGT_REG); + + /* set up IPGR */ + writel((EMAC_MAC_IPGR_IPG1 << 8) | EMAC_MAC_IPGR_IPG2, + db->membase + EMAC_MAC_IPGR_REG); + + /* set up Collison window */ + writel((EMAC_MAC_CLRT_COLLISION_WINDOW << 8) | EMAC_MAC_CLRT_RM, + db->membase + EMAC_MAC_CLRT_REG); + + /* set up Max Frame Length */ + writel(EMAC_MAX_FRAME_LEN, + db->membase + EMAC_MAC_MAXF_REG); + + return 0; +} + +unsigned int emac_powerup(struct net_device *ndev) +{ + struct emac_board_info *db = netdev_priv(ndev); + unsigned int reg_val; + + /* initial EMAC */ + /* flush RX FIFO */ + reg_val = readl(db->membase + EMAC_RX_CTL_REG); + reg_val |= 0x8; + writel(reg_val, db->membase + EMAC_RX_CTL_REG); + udelay(1); + + /* initial MAC */ + /* soft reset MAC */ + reg_val = readl(db->membase + EMAC_MAC_CTL0_REG); + reg_val &= ~EMAC_MAC_CTL0_SOFT_RESET; + writel(reg_val, db->membase + EMAC_MAC_CTL0_REG); + + /* set MII clock */ + reg_val = readl(db->membase + EMAC_MAC_MCFG_REG); + reg_val &= (~(0xf << 2)); + reg_val |= (0xD << 2); + writel(reg_val, db->membase + EMAC_MAC_MCFG_REG); + + /* clear RX counter */ + writel(0x0, db->membase + EMAC_RX_FBC_REG); + + /* disable all interrupt and clear interrupt status */ + writel(0, db->membase + EMAC_INT_CTL_REG); + reg_val = readl(db->membase + EMAC_INT_STA_REG); + writel(reg_val, db->membase + EMAC_INT_STA_REG); + + udelay(1); + + /* set up EMAC */ + emac_setup(ndev); + + /* set mac_address to chip */ + writel(ndev->dev_addr[0] << 16 | ndev->dev_addr[1] << 8 | ndev-> + dev_addr[2], db->membase + EMAC_MAC_A1_REG); + writel(ndev->dev_addr[3] << 16 | ndev->dev_addr[4] << 8 | ndev-> + dev_addr[5], db->membase + EMAC_MAC_A0_REG); + + mdelay(1); + + return 0; +} + +static int emac_set_mac_address(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + struct emac_board_info *db = netdev_priv(dev); + + if (netif_running(dev)) + return -EBUSY; + + memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + + writel(dev->dev_addr[0] << 16 | dev->dev_addr[1] << 8 | dev-> + dev_addr[2], db->membase + EMAC_MAC_A1_REG); + writel(dev->dev_addr[3] << 16 | dev->dev_addr[4] << 8 | dev-> + dev_addr[5], db->membase + EMAC_MAC_A0_REG); + + return 0; +} + +/* Initialize emac board */ +static void emac_init_device(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + unsigned long flags; + unsigned int reg_val; + + spin_lock_irqsave(&db->lock, flags); + + emac_update_speed(dev); + emac_update_duplex(dev); + + /* enable RX/TX */ + reg_val = readl(db->membase + EMAC_CTL_REG); + writel(reg_val | EMAC_CTL_RESET | EMAC_CTL_TX_EN | EMAC_CTL_RX_EN, + db->membase + EMAC_CTL_REG); + + /* enable RX/TX0/RX Hlevel interrup */ + reg_val = readl(db->membase + EMAC_INT_CTL_REG); + reg_val |= (0xf << 0) | (0x01 << 8); + writel(reg_val, db->membase + EMAC_INT_CTL_REG); + + spin_unlock_irqrestore(&db->lock, flags); +} + +/* Our watchdog timed out. Called by the networking layer */ +static void emac_timeout(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + unsigned long flags; + + if (netif_msg_timer(db)) + dev_err(db->dev, "tx time out.\n"); + + /* Save previous register address */ + spin_lock_irqsave(&db->lock, flags); + + netif_stop_queue(dev); + emac_reset(db); + emac_init_device(dev); + /* We can accept TX packets again */ + dev->trans_start = jiffies; + netif_wake_queue(dev); + + /* Restore previous register address */ + spin_unlock_irqrestore(&db->lock, flags); +} + +/* Hardware start transmission. + * Send a packet to media from the upper layer. + */ +static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + unsigned long channel; + unsigned long flags; + + channel = db->tx_fifo_stat & 3; + if (channel == 3) + return 1; + + channel = (channel == 1 ? 1 : 0); + + spin_lock_irqsave(&db->lock, flags); + + writel(channel, db->membase + EMAC_TX_INS_REG); + + emac_outblk_32bit(db->membase + EMAC_TX_IO_DATA_REG, + skb->data, skb->len); + dev->stats.tx_bytes += skb->len; + + db->tx_fifo_stat |= 1 << channel; + /* TX control: First packet immediately send, second packet queue */ + if (channel == 0) { + /* set TX len */ + writel(skb->len, db->membase + EMAC_TX_PL0_REG); + /* start translate from fifo to phy */ + writel(readl(db->membase + EMAC_TX_CTL0_REG) | 1, + db->membase + EMAC_TX_CTL0_REG); + + /* save the time stamp */ + dev->trans_start = jiffies; + } else if (channel == 1) { + /* set TX len */ + writel(skb->len, db->membase + EMAC_TX_PL1_REG); + /* start translate from fifo to phy */ + writel(readl(db->membase + EMAC_TX_CTL1_REG) | 1, + db->membase + EMAC_TX_CTL1_REG); + + /* save the time stamp */ + dev->trans_start = jiffies; + } + + if ((db->tx_fifo_stat & 3) == 3) { + /* Second packet */ + netif_stop_queue(dev); + } + + spin_unlock_irqrestore(&db->lock, flags); + + /* free this SKB */ + dev_kfree_skb(skb); + + return NETDEV_TX_OK; +} + +/* EMAC interrupt handler + * receive the packet to upper layer, free the transmitted packet + */ +static void emac_tx_done(struct net_device *dev, struct emac_board_info *db, + unsigned int tx_status) +{ + /* One packet sent complete */ + db->tx_fifo_stat &= ~(tx_status & 3); + if (3 == (tx_status & 3)) + dev->stats.tx_packets += 2; + else + dev->stats.tx_packets++; + + if (netif_msg_tx_done(db)) + dev_dbg(db->dev, "tx done, NSR %02x\n", tx_status); + + netif_wake_queue(dev); +} + +/* Received a packet and pass to upper layer + */ +static void emac_rx(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + struct sk_buff *skb; + u8 *rdptr; + bool good_packet; + static int rxlen_last; + unsigned int reg_val; + u32 rxhdr, rxstatus, rxcount, rxlen; + + /* Check packet ready or not */ + while (1) { + /* race warning: the first packet might arrive with + * the interrupts disabled, but the second will fix + * it + */ + rxcount = readl(db->membase + EMAC_RX_FBC_REG); + + if (netif_msg_rx_status(db)) + dev_dbg(db->dev, "RXCount: %x\n", rxcount); + + if ((db->skb_last != NULL) && (rxlen_last > 0)) { + dev->stats.rx_bytes += rxlen_last; + + /* Pass to upper layer */ + db->skb_last->protocol = eth_type_trans(db->skb_last, + dev); + netif_rx(db->skb_last); + dev->stats.rx_packets++; + db->skb_last = NULL; + rxlen_last = 0; + + reg_val = readl(db->membase + EMAC_RX_CTL_REG); + reg_val &= ~EMAC_RX_CTL_DMA_EN; + writel(reg_val, db->membase + EMAC_RX_CTL_REG); + } + + if (!rxcount) { + db->emacrx_completed_flag = 1; + reg_val = readl(db->membase + EMAC_INT_CTL_REG); + reg_val |= (0xf << 0) | (0x01 << 8); + writel(reg_val, db->membase + EMAC_INT_CTL_REG); + + /* had one stuck? */ + rxcount = readl(db->membase + EMAC_RX_FBC_REG); + if (!rxcount) + return; + } + + reg_val = readl(db->membase + EMAC_RX_IO_DATA_REG); + if (netif_msg_rx_status(db)) + dev_dbg(db->dev, "receive header: %x\n", reg_val); + if (reg_val != EMAC_UNDOCUMENTED_MAGIC) { + /* disable RX */ + reg_val = readl(db->membase + EMAC_CTL_REG); + writel(reg_val & ~EMAC_CTL_RX_EN, + db->membase + EMAC_CTL_REG); + + /* Flush RX FIFO */ + reg_val = readl(db->membase + EMAC_RX_CTL_REG); + writel(reg_val | (1 << 3), + db->membase + EMAC_RX_CTL_REG); + + do { + reg_val = readl(db->membase + EMAC_RX_CTL_REG); + } while (reg_val & (1 << 3)); + + /* enable RX */ + reg_val = readl(db->membase + EMAC_CTL_REG); + writel(reg_val | EMAC_CTL_RX_EN, + db->membase + EMAC_CTL_REG); + reg_val = readl(db->membase + EMAC_INT_CTL_REG); + reg_val |= (0xf << 0) | (0x01 << 8); + writel(reg_val, db->membase + EMAC_INT_CTL_REG); + + db->emacrx_completed_flag = 1; + + return; + } + + /* A packet ready now & Get status/length */ + good_packet = true; + + emac_inblk_32bit(db->membase + EMAC_RX_IO_DATA_REG, + &rxhdr, sizeof(rxhdr)); + + if (netif_msg_rx_status(db)) + dev_dbg(db->dev, "rxhdr: %x\n", *((int *)(&rxhdr))); + + rxlen = EMAC_RX_IO_DATA_LEN(rxhdr); + rxstatus = EMAC_RX_IO_DATA_STATUS(rxhdr); + + if (netif_msg_rx_status(db)) + dev_dbg(db->dev, "RX: status %02x, length %04x\n", + rxstatus, rxlen); + + /* Packet Status check */ + if (rxlen < 0x40) { + good_packet = false; + if (netif_msg_rx_err(db)) + dev_dbg(db->dev, "RX: Bad Packet (runt)\n"); + } + + if (unlikely(!(rxstatus & EMAC_RX_IO_DATA_STATUS_OK))) { + good_packet = false; + + if (rxstatus & EMAC_RX_IO_DATA_STATUS_CRC_ERR) { + if (netif_msg_rx_err(db)) + dev_dbg(db->dev, "crc error\n"); + dev->stats.rx_crc_errors++; + } + + if (rxstatus & EMAC_RX_IO_DATA_STATUS_LEN_ERR) { + if (netif_msg_rx_err(db)) + dev_dbg(db->dev, "length error\n"); + dev->stats.rx_length_errors++; + } + } + + /* Move data from EMAC */ + skb = dev_alloc_skb(rxlen + 4); + if (good_packet && skb) { + skb_reserve(skb, 2); + rdptr = (u8 *) skb_put(skb, rxlen - 4); + + /* Read received packet from RX SRAM */ + if (netif_msg_rx_status(db)) + dev_dbg(db->dev, "RxLen %x\n", rxlen); + + emac_inblk_32bit(db->membase + EMAC_RX_IO_DATA_REG, + rdptr, rxlen); + dev->stats.rx_bytes += rxlen; + + /* Pass to upper layer */ + skb->protocol = eth_type_trans(skb, dev); + netif_rx(skb); + dev->stats.rx_packets++; + } + } +} + +static irqreturn_t emac_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct emac_board_info *db = netdev_priv(dev); + int int_status; + unsigned long flags; + unsigned int reg_val; + + /* A real interrupt coming */ + + /* holders of db->lock must always block IRQs */ + spin_lock_irqsave(&db->lock, flags); + + /* Disable all interrupts */ + writel(0, db->membase + EMAC_INT_CTL_REG); + + /* Got EMAC interrupt status */ + /* Got ISR */ + int_status = readl(db->membase + EMAC_INT_STA_REG); + /* Clear ISR status */ + writel(int_status, db->membase + EMAC_INT_STA_REG); + + if (netif_msg_intr(db)) + dev_dbg(db->dev, "emac interrupt %02x\n", int_status); + + /* Received the coming packet */ + if ((int_status & 0x100) && (db->emacrx_completed_flag == 1)) { + /* carrier lost */ + db->emacrx_completed_flag = 0; + emac_rx(dev); + } + + /* Transmit Interrupt check */ + if (int_status & (0x01 | 0x02)) + emac_tx_done(dev, db, int_status); + + if (int_status & (0x04 | 0x08)) + netdev_info(dev, " ab : %x\n", int_status); + + /* Re-enable interrupt mask */ + if (db->emacrx_completed_flag == 1) { + reg_val = readl(db->membase + EMAC_INT_CTL_REG); + reg_val |= (0xf << 0) | (0x01 << 8); + writel(reg_val, db->membase + EMAC_INT_CTL_REG); + } + spin_unlock_irqrestore(&db->lock, flags); + + return IRQ_HANDLED; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +/* + * Used by netconsole + */ +static void emac_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + emac_interrupt(dev->irq, dev); + enable_irq(dev->irq); +} +#endif + +/* Open the interface. + * The interface is opened whenever "ifconfig" actives it. + */ +static int emac_open(struct net_device *dev) +{ + struct emac_board_info *db = netdev_priv(dev); + int ret; + + if (netif_msg_ifup(db)) + dev_dbg(db->dev, "enabling %s\n", dev->name); + + if (devm_request_irq(db->dev, dev->irq, &emac_interrupt, + 0, dev->name, dev)) + return -EAGAIN; + + /* Initialize EMAC board */ + emac_reset(db); + emac_init_device(dev); + + ret = emac_mdio_probe(dev); + if (ret < 0) { + netdev_err(dev, "cannot probe MDIO bus\n"); + return ret; + } + + phy_start(db->phy_dev); + netif_start_queue(dev); + + return 0; +} + +static void emac_shutdown(struct net_device *dev) +{ + unsigned int reg_val; + struct emac_board_info *db = netdev_priv(dev); + + /* Disable all interrupt */ + writel(0, db->membase + EMAC_INT_CTL_REG); + + /* clear interupt status */ + reg_val = readl(db->membase + EMAC_INT_STA_REG); + writel(reg_val, db->membase + EMAC_INT_STA_REG); + + /* Disable RX/TX */ + reg_val = readl(db->membase + EMAC_CTL_REG); + reg_val &= ~(EMAC_CTL_TX_EN | EMAC_CTL_RX_EN | EMAC_CTL_RESET); + writel(reg_val, db->membase + EMAC_CTL_REG); +} + +/* Stop the interface. + * The interface is stopped when it is brought. + */ +static int emac_stop(struct net_device *ndev) +{ + struct emac_board_info *db = netdev_priv(ndev); + + if (netif_msg_ifdown(db)) + dev_dbg(db->dev, "shutting down %s\n", ndev->name); + + netif_stop_queue(ndev); + netif_carrier_off(ndev); + + phy_stop(db->phy_dev); + + emac_mdio_remove(ndev); + + emac_shutdown(ndev); + + return 0; +} + +static const struct net_device_ops emac_netdev_ops = { + .ndo_open = emac_open, + .ndo_stop = emac_stop, + .ndo_start_xmit = emac_start_xmit, + .ndo_tx_timeout = emac_timeout, + .ndo_do_ioctl = emac_ioctl, + .ndo_change_mtu = eth_change_mtu, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = emac_set_mac_address, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = emac_poll_controller, +#endif +}; + +/* Search EMAC board, allocate space and register it + */ +static int emac_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct emac_board_info *db; + struct net_device *ndev; + int ret = 0; + const char *mac_addr; + + ndev = alloc_etherdev(sizeof(struct emac_board_info)); + if (!ndev) { + dev_err(&pdev->dev, "could not allocate device.\n"); + return -ENOMEM; + } + + SET_NETDEV_DEV(ndev, &pdev->dev); + + db = netdev_priv(ndev); + memset(db, 0, sizeof(*db)); + + db->dev = &pdev->dev; + db->ndev = ndev; + db->pdev = pdev; + + spin_lock_init(&db->lock); + + db->membase = of_iomap(np, 0); + if (!db->membase) { + dev_err(&pdev->dev, "failed to remap registers\n"); + return -ENOMEM; + goto out; + } + + /* fill in parameters for net-dev structure */ + ndev->base_addr = (unsigned long)db->membase; + ndev->irq = irq_of_parse_and_map(np, 0); + if (ndev->irq == -ENXIO) { + netdev_err(ndev, "No irq resource\n"); + ret = ndev->irq; + goto out; + } + + db->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(db->clk)) + goto out; + + clk_prepare_enable(db->clk); + + db->phy_node = of_parse_phandle(np, "phy", 0); + if (!db->phy_node) { + dev_err(&pdev->dev, "no associated PHY\n"); + ret = -ENODEV; + goto out; + } + + /* Read MAC-address from DT */ + mac_addr = of_get_mac_address(np); + if (mac_addr) + memcpy(ndev->dev_addr, mac_addr, ETH_ALEN); + + /* Check if the MAC address is valid, if not get a random one */ + if (!is_valid_ether_addr(ndev->dev_addr)) { + eth_hw_addr_random(ndev); + dev_warn(&pdev->dev, "using random MAC address %pM\n", + ndev->dev_addr); + } + + db->emacrx_completed_flag = 1; + emac_powerup(ndev); + emac_reset(db); + + ether_setup(ndev); + + ndev->netdev_ops = &emac_netdev_ops; + ndev->watchdog_timeo = msecs_to_jiffies(watchdog); + ndev->ethtool_ops = &emac_ethtool_ops; + +#ifdef CONFIG_NET_POLL_CONTROLLER + ndev->poll_controller = &emac_poll_controller; +#endif + + platform_set_drvdata(pdev, ndev); + + /* Carrier starts down, phylib will bring it up */ + netif_carrier_off(ndev); + + ret = register_netdev(ndev); + if (ret) { + dev_err(&pdev->dev, "Registering netdev failed!\n"); + ret = -ENODEV; + goto out; + } + + dev_info(&pdev->dev, "%s: at %p, IRQ %d MAC: %pM\n", + ndev->name, db->membase, ndev->irq, ndev->dev_addr); + + return 0; + +out: + dev_err(db->dev, "not found (%d).\n", ret); + + free_netdev(ndev); + + return ret; +} + +static int emac_remove(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + + platform_set_drvdata(pdev, NULL); + + unregister_netdev(ndev); + free_netdev(ndev); + + dev_dbg(&pdev->dev, "released and freed device\n"); + return 0; +} + +static int emac_suspend(struct platform_device *dev, pm_message_t state) +{ + struct net_device *ndev = platform_get_drvdata(dev); + + netif_carrier_off(ndev); + netif_device_detach(ndev); + emac_shutdown(ndev); + + return 0; +} + +static int emac_resume(struct platform_device *dev) +{ + struct net_device *ndev = platform_get_drvdata(dev); + struct emac_board_info *db = netdev_priv(ndev); + + emac_reset(db); + emac_init_device(ndev); + netif_device_attach(ndev); + + return 0; +} + +static const struct of_device_id emac_of_match[] = { + {.compatible = "allwinner,sun4i-emac",}, + {}, +}; + +MODULE_DEVICE_TABLE(of, emac_of_match); + +static struct platform_driver emac_driver = { + .driver = { + .name = "sun4i-emac", + .of_match_table = emac_of_match, + }, + .probe = emac_probe, + .remove = emac_remove, + .suspend = emac_suspend, + .resume = emac_resume, +}; + +module_platform_driver(emac_driver); + +MODULE_AUTHOR("Stefan Roese "); +MODULE_AUTHOR("Maxime Ripard "); +MODULE_DESCRIPTION("Allwinner A10 emac network driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.h b/drivers/net/ethernet/allwinner/sun4i-emac.h new file mode 100644 index 000000000000..38c72d9ec600 --- /dev/null +++ b/drivers/net/ethernet/allwinner/sun4i-emac.h @@ -0,0 +1,108 @@ +/* + * Allwinner EMAC Fast Ethernet driver for Linux. + * + * Copyright 2012 Stefan Roese + * Copyright 2013 Maxime Ripard + * + * Based on the Linux driver provided by Allwinner: + * Copyright (C) 1997 Sten Wang + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _SUN4I_EMAC_H_ +#define _SUN4I_EMAC_H_ + +#define EMAC_CTL_REG (0x00) +#define EMAC_CTL_RESET (1 << 0) +#define EMAC_CTL_TX_EN (1 << 1) +#define EMAC_CTL_RX_EN (1 << 2) +#define EMAC_TX_MODE_REG (0x04) +#define EMAC_TX_MODE_ABORTED_FRAME_EN (1 << 0) +#define EMAC_TX_MODE_DMA_EN (1 << 1) +#define EMAC_TX_FLOW_REG (0x08) +#define EMAC_TX_CTL0_REG (0x0c) +#define EMAC_TX_CTL1_REG (0x10) +#define EMAC_TX_INS_REG (0x14) +#define EMAC_TX_PL0_REG (0x18) +#define EMAC_TX_PL1_REG (0x1c) +#define EMAC_TX_STA_REG (0x20) +#define EMAC_TX_IO_DATA_REG (0x24) +#define EMAC_TX_IO_DATA1_REG (0x28) +#define EMAC_TX_TSVL0_REG (0x2c) +#define EMAC_TX_TSVH0_REG (0x30) +#define EMAC_TX_TSVL1_REG (0x34) +#define EMAC_TX_TSVH1_REG (0x38) +#define EMAC_RX_CTL_REG (0x3c) +#define EMAC_RX_CTL_AUTO_DRQ_EN (1 << 1) +#define EMAC_RX_CTL_DMA_EN (1 << 2) +#define EMAC_RX_CTL_PASS_ALL_EN (1 << 4) +#define EMAC_RX_CTL_PASS_CTL_EN (1 << 5) +#define EMAC_RX_CTL_PASS_CRC_ERR_EN (1 << 6) +#define EMAC_RX_CTL_PASS_LEN_ERR_EN (1 << 7) +#define EMAC_RX_CTL_PASS_LEN_OOR_EN (1 << 8) +#define EMAC_RX_CTL_ACCEPT_UNICAST_EN (1 << 16) +#define EMAC_RX_CTL_DA_FILTER_EN (1 << 17) +#define EMAC_RX_CTL_ACCEPT_MULTICAST_EN (1 << 20) +#define EMAC_RX_CTL_HASH_FILTER_EN (1 << 21) +#define EMAC_RX_CTL_ACCEPT_BROADCAST_EN (1 << 22) +#define EMAC_RX_CTL_SA_FILTER_EN (1 << 24) +#define EMAC_RX_CTL_SA_FILTER_INVERT_EN (1 << 25) +#define EMAC_RX_HASH0_REG (0x40) +#define EMAC_RX_HASH1_REG (0x44) +#define EMAC_RX_STA_REG (0x48) +#define EMAC_RX_IO_DATA_REG (0x4c) +#define EMAC_RX_IO_DATA_LEN(x) (x & 0xffff) +#define EMAC_RX_IO_DATA_STATUS(x) ((x >> 16) & 0xffff) +#define EMAC_RX_IO_DATA_STATUS_CRC_ERR (1 << 4) +#define EMAC_RX_IO_DATA_STATUS_LEN_ERR (3 << 5) +#define EMAC_RX_IO_DATA_STATUS_OK (1 << 7) +#define EMAC_RX_FBC_REG (0x50) +#define EMAC_INT_CTL_REG (0x54) +#define EMAC_INT_STA_REG (0x58) +#define EMAC_MAC_CTL0_REG (0x5c) +#define EMAC_MAC_CTL0_RX_FLOW_CTL_EN (1 << 2) +#define EMAC_MAC_CTL0_TX_FLOW_CTL_EN (1 << 3) +#define EMAC_MAC_CTL0_SOFT_RESET (1 << 15) +#define EMAC_MAC_CTL1_REG (0x60) +#define EMAC_MAC_CTL1_DUPLEX_EN (1 << 0) +#define EMAC_MAC_CTL1_LEN_CHECK_EN (1 << 1) +#define EMAC_MAC_CTL1_HUGE_FRAME_EN (1 << 2) +#define EMAC_MAC_CTL1_DELAYED_CRC_EN (1 << 3) +#define EMAC_MAC_CTL1_CRC_EN (1 << 4) +#define EMAC_MAC_CTL1_PAD_EN (1 << 5) +#define EMAC_MAC_CTL1_PAD_CRC_EN (1 << 6) +#define EMAC_MAC_CTL1_AD_SHORT_FRAME_EN (1 << 7) +#define EMAC_MAC_CTL1_BACKOFF_DIS (1 << 12) +#define EMAC_MAC_IPGT_REG (0x64) +#define EMAC_MAC_IPGT_HALF_DUPLEX (0x12) +#define EMAC_MAC_IPGT_FULL_DUPLEX (0x15) +#define EMAC_MAC_IPGR_REG (0x68) +#define EMAC_MAC_IPGR_IPG1 (0x0c) +#define EMAC_MAC_IPGR_IPG2 (0x12) +#define EMAC_MAC_CLRT_REG (0x6c) +#define EMAC_MAC_CLRT_COLLISION_WINDOW (0x37) +#define EMAC_MAC_CLRT_RM (0x0f) +#define EMAC_MAC_MAXF_REG (0x70) +#define EMAC_MAC_SUPP_REG (0x74) +#define EMAC_MAC_TEST_REG (0x78) +#define EMAC_MAC_MCFG_REG (0x7c) +#define EMAC_MAC_A0_REG (0x98) +#define EMAC_MAC_A1_REG (0x9c) +#define EMAC_MAC_A2_REG (0xa0) +#define EMAC_SAFX_L_REG0 (0xa4) +#define EMAC_SAFX_H_REG0 (0xa8) +#define EMAC_SAFX_L_REG1 (0xac) +#define EMAC_SAFX_H_REG1 (0xb0) +#define EMAC_SAFX_L_REG2 (0xb4) +#define EMAC_SAFX_H_REG2 (0xb8) +#define EMAC_SAFX_L_REG3 (0xbc) +#define EMAC_SAFX_H_REG3 (0xc0) + +#define EMAC_PHY_DUPLEX (1 << 8) + +#define EMAC_EEPROM_MAGIC (0x444d394b) +#define EMAC_UNDOCUMENTED_MAGIC (0x0143414d) +#endif /* _SUN4I_EMAC_H_ */ -- cgit v1.2.3 From 4bdcb1dd9feb03608e12cfa46aba385035af8ea5 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 30 May 2013 03:49:21 +0000 Subject: net: Add MDIO bus driver for the Allwinner EMAC This patch adds a separate driver for the MDIO interface of the Allwinner ethernet controllers. Signed-off-by: Maxime Ripard Tested-by: Richard Genoud Signed-off-by: David S. Miller --- .../bindings/net/allwinner,sun4i-mdio.txt | 26 +++ drivers/net/phy/Kconfig | 10 ++ drivers/net/phy/Makefile | 1 + drivers/net/phy/mdio-sun4i.c | 194 +++++++++++++++++++++ 4 files changed, 231 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt create mode 100644 drivers/net/phy/mdio-sun4i.c (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt new file mode 100644 index 000000000000..00b9f9a3ec1d --- /dev/null +++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt @@ -0,0 +1,26 @@ +* Allwinner A10 MDIO Ethernet Controller interface + +Required properties: +- compatible: should be "allwinner,sun4i-mdio". +- reg: address and length of the register set for the device. + +Optional properties: +- phy-supply: phandle to a regulator if the PHY needs one + +Example at the SoC level: +mdio@01c0b080 { + compatible = "allwinner,sun4i-mdio"; + reg = <0x01c0b080 0x14>; + #address-cells = <1>; + #size-cells = <0>; +}; + +And at the board level: + +mdio@01c0b080 { + phy-supply = <®_emac_3v3>; + + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 1e11f2bfd9ce..3a316b30089f 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -144,6 +144,16 @@ config MDIO_OCTEON If in doubt, say Y. +config MDIO_SUN4I + tristate "Allwinner sun4i MDIO interface support" + depends on ARCH_SUNXI + select REGULATOR + select REGULATOR_FIXED_VOLTAGE + help + This driver supports the MDIO interface found in the network + interface units of the Allwinner SoC that have an EMAC (A10, + A12, A10s, etc.) + config MDIO_BUS_MUX tristate depends on OF_MDIO diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 9645e389a58d..23a2ab2e847e 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -30,3 +30,4 @@ obj-$(CONFIG_AMD_PHY) += amd.o obj-$(CONFIG_MDIO_BUS_MUX) += mdio-mux.o obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o +obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c new file mode 100644 index 000000000000..61d3f4ebf52e --- /dev/null +++ b/drivers/net/phy/mdio-sun4i.c @@ -0,0 +1,194 @@ +/* + * Allwinner EMAC MDIO interface driver + * + * Copyright 2012-2013 Stefan Roese + * Copyright 2013 Maxime Ripard + * + * Based on the Linux driver provided by Allwinner: + * Copyright (C) 1997 Sten Wang + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define EMAC_MAC_MCMD_REG (0x00) +#define EMAC_MAC_MADR_REG (0x04) +#define EMAC_MAC_MWTD_REG (0x08) +#define EMAC_MAC_MRDD_REG (0x0c) +#define EMAC_MAC_MIND_REG (0x10) +#define EMAC_MAC_SSRR_REG (0x14) + +#define MDIO_TIMEOUT (msecs_to_jiffies(100)) + +struct sun4i_mdio_data { + void __iomem *membase; + struct regulator *regulator; +}; + +static int sun4i_mdio_read(struct mii_bus *bus, int mii_id, int regnum) +{ + struct sun4i_mdio_data *data = bus->priv; + unsigned long start_jiffies; + int value; + + /* issue the phy address and reg */ + writel((mii_id << 8) | regnum, data->membase + EMAC_MAC_MADR_REG); + /* pull up the phy io line */ + writel(0x1, data->membase + EMAC_MAC_MCMD_REG); + + /* Wait read complete */ + start_jiffies = jiffies; + while (readl(data->membase + EMAC_MAC_MIND_REG) & 0x1) { + if (time_after(start_jiffies, + start_jiffies + MDIO_TIMEOUT)) + return -ETIMEDOUT; + msleep(1); + } + + /* push down the phy io line */ + writel(0x0, data->membase + EMAC_MAC_MCMD_REG); + /* and read data */ + value = readl(data->membase + EMAC_MAC_MRDD_REG); + + return value; +} + +static int sun4i_mdio_write(struct mii_bus *bus, int mii_id, int regnum, + u16 value) +{ + struct sun4i_mdio_data *data = bus->priv; + unsigned long start_jiffies; + + /* issue the phy address and reg */ + writel((mii_id << 8) | regnum, data->membase + EMAC_MAC_MADR_REG); + /* pull up the phy io line */ + writel(0x1, data->membase + EMAC_MAC_MCMD_REG); + + /* Wait read complete */ + start_jiffies = jiffies; + while (readl(data->membase + EMAC_MAC_MIND_REG) & 0x1) { + if (time_after(start_jiffies, + start_jiffies + MDIO_TIMEOUT)) + return -ETIMEDOUT; + msleep(1); + } + + /* push down the phy io line */ + writel(0x0, data->membase + EMAC_MAC_MCMD_REG); + /* and write data */ + writel(value, data->membase + EMAC_MAC_MWTD_REG); + + return 0; +} + +static int sun4i_mdio_reset(struct mii_bus *bus) +{ + return 0; +} + +static int sun4i_mdio_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct mii_bus *bus; + struct sun4i_mdio_data *data; + int ret, i; + + bus = mdiobus_alloc_size(sizeof(*data)); + if (!bus) + return -ENOMEM; + + bus->name = "sun4i_mii_bus"; + bus->read = &sun4i_mdio_read; + bus->write = &sun4i_mdio_write; + bus->reset = &sun4i_mdio_reset; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(&pdev->dev)); + bus->parent = &pdev->dev; + + bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL); + if (!bus->irq) { + ret = -ENOMEM; + goto err_out_free_mdiobus; + } + + for (i = 0; i < PHY_MAX_ADDR; i++) + bus->irq[i] = PHY_POLL; + + data = bus->priv; + data->membase = of_iomap(np, 0); + if (!data->membase) { + ret = -ENOMEM; + goto err_out_free_mdio_irq; + } + + data->regulator = devm_regulator_get(&pdev->dev, "phy"); + if (IS_ERR(data->regulator)) { + if (PTR_ERR(data->regulator) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + dev_info(&pdev->dev, "no regulator found\n"); + } else { + ret = regulator_enable(data->regulator); + if (ret) + goto err_out_free_mdio_irq; + } + + ret = of_mdiobus_register(bus, np); + if (ret < 0) + goto err_out_disable_regulator; + + platform_set_drvdata(pdev, bus); + + return 0; + +err_out_disable_regulator: + regulator_disable(data->regulator); +err_out_free_mdio_irq: + kfree(bus->irq); +err_out_free_mdiobus: + mdiobus_free(bus); + return ret; +} + +static int sun4i_mdio_remove(struct platform_device *pdev) +{ + struct mii_bus *bus = platform_get_drvdata(pdev); + + mdiobus_unregister(bus); + kfree(bus->irq); + mdiobus_free(bus); + + return 0; +} + +static const struct of_device_id sun4i_mdio_dt_ids[] = { + { .compatible = "allwinner,sun4i-mdio" }, + { } +}; +MODULE_DEVICE_TABLE(of, sun4i_mdio_dt_ids); + +static struct platform_driver sun4i_mdio_driver = { + .probe = sun4i_mdio_probe, + .remove = sun4i_mdio_remove, + .driver = { + .name = "sun4i-mdio", + .of_match_table = sun4i_mdio_dt_ids, + }, +}; + +module_platform_driver(sun4i_mdio_driver); + +MODULE_DESCRIPTION("Allwinner EMAC MDIO interface driver"); +MODULE_AUTHOR("Maxime Ripard "); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From c5ceea7a2813fecded01567383cca4d6855164ab Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 3 Jun 2013 20:10:10 +0000 Subject: drivers: net: ethernet: cpsw: add phy-mode support to cpsw driver Adding phy-mode support to cpsw driver and updating the cpsw binding documentation. Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/cpsw.txt | 6 ++++++ drivers/net/ethernet/ti/cpsw.c | 2 ++ 2 files changed, 8 insertions(+) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 4f2ca6b4a182..05d660e4ac64 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -28,6 +28,8 @@ Optional properties: Slave Properties: Required properties: - phy_id : Specifies slave phy id +- phy-mode : The interface between the SoC and the PHY (a string + that of_get_phy_mode() can understand) - mac-address : Specifies slave MAC address Optional properties: @@ -58,11 +60,13 @@ Examples: cpts_clock_shift = <29>; cpsw_emac0: slave@0 { phy_id = <&davinci_mdio>, <0>; + phy-mode = "rgmii-txid"; /* Filled in by U-Boot */ mac-address = [ 00 00 00 00 00 00 ]; }; cpsw_emac1: slave@1 { phy_id = <&davinci_mdio>, <1>; + phy-mode = "rgmii-txid"; /* Filled in by U-Boot */ mac-address = [ 00 00 00 00 00 00 ]; }; @@ -84,11 +88,13 @@ Examples: cpts_clock_shift = <29>; cpsw_emac0: slave@0 { phy_id = <&davinci_mdio>, <0>; + phy-mode = "rgmii-txid"; /* Filled in by U-Boot */ mac-address = [ 00 00 00 00 00 00 ]; }; cpsw_emac1: slave@1 { phy_id = <&davinci_mdio>, <1>; + phy-mode = "rgmii-txid"; /* Filled in by U-Boot */ mac-address = [ 00 00 00 00 00 00 ]; }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 89a4c40d6d83..a45f64eef870 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1554,6 +1554,8 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, if (mac_addr) memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); + slave_data->phy_if = of_get_phy_mode(slave_node); + if (data->dual_emac) { if (of_property_read_u32(slave_node, "dual_emac_res_vlan", &prop)) { -- cgit v1.2.3 From 780b40df12cf0161d8ccc5381940e04584793933 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 Jun 2013 09:32:50 +0200 Subject: wireless: fix kernel-doc Some kernel-doc fixes for forgotten fields and renamed things. Signed-off-by: Johannes Berg --- Documentation/DocBook/80211.tmpl | 11 +++++------ include/net/cfg80211.h | 11 ++++++++++- net/mac80211/sta_info.h | 3 +++ 3 files changed, 18 insertions(+), 7 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index ebe89694cf81..49267ea97568 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -127,12 +127,11 @@ !Finclude/net/cfg80211.h cfg80211_ibss_params !Finclude/net/cfg80211.h cfg80211_connect_params !Finclude/net/cfg80211.h cfg80211_pmksa -!Finclude/net/cfg80211.h cfg80211_send_rx_auth -!Finclude/net/cfg80211.h cfg80211_send_auth_timeout -!Finclude/net/cfg80211.h cfg80211_send_rx_assoc -!Finclude/net/cfg80211.h cfg80211_send_assoc_timeout -!Finclude/net/cfg80211.h cfg80211_send_deauth -!Finclude/net/cfg80211.h cfg80211_send_disassoc +!Finclude/net/cfg80211.h cfg80211_rx_mlme_mgmt +!Finclude/net/cfg80211.h cfg80211_auth_timeout +!Finclude/net/cfg80211.h cfg80211_rx_assoc_resp +!Finclude/net/cfg80211.h cfg80211_assoc_timeout +!Finclude/net/cfg80211.h cfg80211_tx_mlme_mgmt !Finclude/net/cfg80211.h cfg80211_ibss_joined !Finclude/net/cfg80211.h cfg80211_connect_result !Finclude/net/cfg80211.h cfg80211_roamed diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5b208064f1bd..855c76ccff38 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2853,7 +2853,7 @@ struct cfg80211_cached_keys; * @current_bss: (private) Used by the internal configuration code * @channel: (private) Used by the internal configuration code to track * the user-set AP, monitor and WDS channel - * @preset_chan: (private) Used by the internal configuration code to + * @preset_chandef: (private) Used by the internal configuration code to * track the channel to be used for AP later * @bssid: (private) Used by the internal configuration code * @ssid: (private) Used by the internal configuration code @@ -2875,6 +2875,15 @@ struct cfg80211_cached_keys; * @p2p_started: true if this is a P2P Device that has been started * @cac_started: true if DFS channel availability check has been started * @cac_start_time: timestamp (jiffies) when the dfs state was entered. + * @ps: powersave mode is enabled + * @ps_timeout: dynamic powersave timeout + * @ap_unexpected_nlportid: (private) netlink port ID of application + * registered for unexpected class 3 frames (AP mode) + * @conn: (private) cfg80211 software SME connection state machine data + * @connect_keys: (private) keys to set after connection is established + * @ibss_fixed: (private) IBSS is using fixed BSSID + * @event_list: (private) list for internal event processing + * @event_lock: (private) lock for event list */ struct wireless_dev { struct wiphy *wiphy; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 41c28b977f7c..bd12fc54266c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -297,6 +297,9 @@ struct sta_ampdu_mlme { * @rcu_head: RCU head used for freeing this station struct * @cur_max_bandwidth: maximum bandwidth to use for TX to the station, * taken from HT/VHT capabilities or VHT operating mode notification + * @chains: chains ever used for RX from this station + * @chain_signal_last: last signal (per chain) + * @chain_signal_avg: signal average (per chain) */ struct sta_info { /* General information, mostly static */ -- cgit v1.2.3 From d70a3f887a38cb0acc7233a1d05f15c2b6e0be2b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 6 Jun 2013 14:08:13 +0000 Subject: doc: packet: simplify tpacket example code This patch simplifies the tpacket_v3 example code a bit by getting rid of unecessary macro wrappers, removing some debugging code so that it is more to the point, and also adds a header comment. Now this example code is the very minimum one needs to start from when dealing with tpacket_v3 and ~100 lines smaller than before. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- Documentation/networking/packet_mmap.txt | 133 +++++++------------------------ 1 file changed, 28 insertions(+), 105 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 23dd80e82b8e..8572796b1eb6 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -704,6 +704,12 @@ So it seems to be a good candidate to be used with packet fanout. Minimal example code by Daniel Borkmann based on Chetan Loke's lolpcap (compile it with gcc -Wall -O2 blob.c, and try things like "./a.out eth0", etc.): +/* Written from scratch, but kernel-to-user space API usage + * dissected from lolpcap: + * Copyright 2011, Chetan Loke + * License: GPL, version 2.0 + */ + #include #include #include @@ -722,27 +728,6 @@ it with gcc -Wall -O2 blob.c, and try things like "./a.out eth0", etc.): #include #include -#define BLOCK_SIZE (1 << 22) -#define FRAME_SIZE 2048 - -#define NUM_BLOCKS 64 -#define NUM_FRAMES ((BLOCK_SIZE * NUM_BLOCKS) / FRAME_SIZE) - -#define BLOCK_RETIRE_TOV_IN_MS 64 -#define BLOCK_PRIV_AREA_SZ 13 - -#define ALIGN_8(x) (((x) + 8 - 1) & ~(8 - 1)) - -#define BLOCK_STATUS(x) ((x)->h1.block_status) -#define BLOCK_NUM_PKTS(x) ((x)->h1.num_pkts) -#define BLOCK_O2FP(x) ((x)->h1.offset_to_first_pkt) -#define BLOCK_LEN(x) ((x)->h1.blk_len) -#define BLOCK_SNUM(x) ((x)->h1.seq_num) -#define BLOCK_O2PRIV(x) ((x)->offset_to_priv) -#define BLOCK_PRIV(x) ((void *) ((uint8_t *) (x) + BLOCK_O2PRIV(x))) -#define BLOCK_HDR_LEN (ALIGN_8(sizeof(struct block_desc))) -#define BLOCK_PLUS_PRIV(sz_pri) (BLOCK_HDR_LEN + ALIGN_8((sz_pri))) - #ifndef likely # define likely(x) __builtin_expect(!!(x), 1) #endif @@ -765,7 +750,7 @@ struct ring { static unsigned long packets_total = 0, bytes_total = 0; static sig_atomic_t sigint = 0; -void sighandler(int num) +static void sighandler(int num) { sigint = 1; } @@ -774,6 +759,8 @@ static int setup_socket(struct ring *ring, char *netdev) { int err, i, fd, v = TPACKET_V3; struct sockaddr_ll ll; + unsigned int blocksiz = 1 << 22, framesiz = 1 << 11; + unsigned int blocknum = 64; fd = socket(AF_PACKET, SOCK_RAW, htons(ETH_P_ALL)); if (fd < 0) { @@ -788,13 +775,12 @@ static int setup_socket(struct ring *ring, char *netdev) } memset(&ring->req, 0, sizeof(ring->req)); - ring->req.tp_block_size = BLOCK_SIZE; - ring->req.tp_frame_size = FRAME_SIZE; - ring->req.tp_block_nr = NUM_BLOCKS; - ring->req.tp_frame_nr = NUM_FRAMES; - ring->req.tp_retire_blk_tov = BLOCK_RETIRE_TOV_IN_MS; - ring->req.tp_sizeof_priv = BLOCK_PRIV_AREA_SZ; - ring->req.tp_feature_req_word |= TP_FT_REQ_FILL_RXHASH; + ring->req.tp_block_size = blocksiz; + ring->req.tp_frame_size = framesiz; + ring->req.tp_block_nr = blocknum; + ring->req.tp_frame_nr = (blocksiz * blocknum) / framesiz; + ring->req.tp_retire_blk_tov = 60; + ring->req.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH; err = setsockopt(fd, SOL_PACKET, PACKET_RX_RING, &ring->req, sizeof(ring->req)); @@ -804,8 +790,7 @@ static int setup_socket(struct ring *ring, char *netdev) } ring->map = mmap(NULL, ring->req.tp_block_size * ring->req.tp_block_nr, - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED, - fd, 0); + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED, fd, 0); if (ring->map == MAP_FAILED) { perror("mmap"); exit(1); @@ -835,58 +820,6 @@ static int setup_socket(struct ring *ring, char *netdev) return fd; } -#ifdef __checked -static uint64_t prev_block_seq_num = 0; - -void assert_block_seq_num(struct block_desc *pbd) -{ - if (unlikely(prev_block_seq_num + 1 != BLOCK_SNUM(pbd))) { - printf("prev_block_seq_num:%"PRIu64", expected seq:%"PRIu64" != " - "actual seq:%"PRIu64"\n", prev_block_seq_num, - prev_block_seq_num + 1, (uint64_t) BLOCK_SNUM(pbd)); - exit(1); - } - - prev_block_seq_num = BLOCK_SNUM(pbd); -} - -static void assert_block_len(struct block_desc *pbd, uint32_t bytes, int block_num) -{ - if (BLOCK_NUM_PKTS(pbd)) { - if (unlikely(bytes != BLOCK_LEN(pbd))) { - printf("block:%u with %upackets, expected len:%u != actual len:%u\n", - block_num, BLOCK_NUM_PKTS(pbd), bytes, BLOCK_LEN(pbd)); - exit(1); - } - } else { - if (unlikely(BLOCK_LEN(pbd) != BLOCK_PLUS_PRIV(BLOCK_PRIV_AREA_SZ))) { - printf("block:%u, expected len:%lu != actual len:%u\n", - block_num, BLOCK_HDR_LEN, BLOCK_LEN(pbd)); - exit(1); - } - } -} - -static void assert_block_header(struct block_desc *pbd, const int block_num) -{ - uint32_t block_status = BLOCK_STATUS(pbd); - - if (unlikely((block_status & TP_STATUS_USER) == 0)) { - printf("block:%u, not in TP_STATUS_USER\n", block_num); - exit(1); - } - - assert_block_seq_num(pbd); -} -#else -static inline void assert_block_header(struct block_desc *pbd, const int block_num) -{ -} -static void assert_block_len(struct block_desc *pbd, uint32_t bytes, int block_num) -{ -} -#endif - static void display(struct tpacket3_hdr *ppd) { struct ethhdr *eth = (struct ethhdr *) ((uint8_t *) ppd + ppd->tp_mac); @@ -916,37 +849,27 @@ static void display(struct tpacket3_hdr *ppd) static void walk_block(struct block_desc *pbd, const int block_num) { - int num_pkts = BLOCK_NUM_PKTS(pbd), i; + int num_pkts = pbd->h1.num_pkts, i; unsigned long bytes = 0; - unsigned long bytes_with_padding = BLOCK_PLUS_PRIV(BLOCK_PRIV_AREA_SZ); struct tpacket3_hdr *ppd; - assert_block_header(pbd, block_num); - - ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd + BLOCK_O2FP(pbd)); + ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd + + pbd->h1.offset_to_first_pkt); for (i = 0; i < num_pkts; ++i) { bytes += ppd->tp_snaplen; - if (ppd->tp_next_offset) - bytes_with_padding += ppd->tp_next_offset; - else - bytes_with_padding += ALIGN_8(ppd->tp_snaplen + ppd->tp_mac); - display(ppd); - ppd = (struct tpacket3_hdr *) ((uint8_t *) ppd + ppd->tp_next_offset); - __sync_synchronize(); + ppd = (struct tpacket3_hdr *) ((uint8_t *) ppd + + ppd->tp_next_offset); } - assert_block_len(pbd, bytes_with_padding, block_num); - packets_total += num_pkts; bytes_total += bytes; } -void flush_block(struct block_desc *pbd) +static void flush_block(struct block_desc *pbd) { - BLOCK_STATUS(pbd) = TP_STATUS_KERNEL; - __sync_synchronize(); + pbd->h1.block_status = TP_STATUS_KERNEL; } static void teardown_socket(struct ring *ring, int fd) @@ -962,7 +885,7 @@ int main(int argc, char **argp) socklen_t len; struct ring ring; struct pollfd pfd; - unsigned int block_num = 0; + unsigned int block_num = 0, blocks = 64; struct block_desc *pbd; struct tpacket_stats_v3 stats; @@ -984,15 +907,15 @@ int main(int argc, char **argp) while (likely(!sigint)) { pbd = (struct block_desc *) ring.rd[block_num].iov_base; -retry_block: - if ((BLOCK_STATUS(pbd) & TP_STATUS_USER) == 0) { + + if ((pbd->h1.block_status & TP_STATUS_USER) == 0) { poll(&pfd, 1, -1); - goto retry_block; + continue; } walk_block(pbd, block_num); flush_block(pbd); - block_num = (block_num + 1) % NUM_BLOCKS; + block_num = (block_num + 1) % blocks; } len = sizeof(stats); -- cgit v1.2.3 From e8b265e8ba322a01bb746504f6f64b5506853eac Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Fri, 7 Jun 2013 20:16:19 +0000 Subject: doc:networking: Fix default value (icmp_ignore_bogus_error_responses). This patch fixes icmp_ignore_bogus_error_responses default value to be 1 instead of FALSE. It is initialized to 1 in icmp_sk_init(). Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 398d0fb1dd0e..9cea5d3b3c50 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -729,7 +729,7 @@ icmp_ignore_bogus_error_responses - BOOLEAN frames. Such violations are normally logged via a kernel warning. If this is set to TRUE, the kernel will not give such warnings, which will avoid log file clutter. - Default: FALSE + Default: 1 icmp_errors_use_inbound_ifaddr - BOOLEAN -- cgit v1.2.3 From 060212928670593fb89243640bf05cf89560b023 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Mon, 10 Jun 2013 11:39:50 +0300 Subject: net: add low latency socket poll Adds an ndo_ll_poll method and the code that supports it. This method can be used by low latency applications to busy-poll Ethernet device queues directly from the socket code. sysctl_net_ll_poll controls how many microseconds to poll. Default is zero (disabled). Individual protocol support will be added by subsequent patches. Signed-off-by: Alexander Duyck Signed-off-by: Jesse Brandeburg Signed-off-by: Eliezer Tamir Acked-by: Eric Dumazet Tested-by: Willem de Bruijn Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 7 ++ include/linux/netdevice.h | 3 + include/linux/skbuff.h | 8 ++- include/net/ll_poll.h | 148 +++++++++++++++++++++++++++++++++++++++++++ include/net/sock.h | 4 ++ include/uapi/linux/snmp.h | 1 + net/Kconfig | 12 ++++ net/core/skbuff.c | 4 ++ net/core/sock.c | 6 ++ net/core/sysctl_net_core.c | 10 +++ net/ipv4/proc.c | 1 + net/socket.c | 6 ++ 12 files changed, 208 insertions(+), 2 deletions(-) create mode 100644 include/net/ll_poll.h (limited to 'Documentation') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index c1f8640c2fc8..85ab72dcdc3c 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -50,6 +50,13 @@ The maximum number of packets that kernel can handle on a NAPI interrupt, it's a Per-CPU variable. Default: 64 +low_latency_poll +---------------- +Low latency busy poll timeout. (needs CONFIG_NET_LL_RX_POLL) +Approximate time in us to spin waiting for packets on the device queue. +Recommended value is 50. May increase power usage. +Default: 0 (off) + rmem_default ------------ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 39bbd462d68e..2ecb96d9a1e5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -971,6 +971,9 @@ struct net_device_ops { struct netpoll_info *info, gfp_t gfp); void (*ndo_netpoll_cleanup)(struct net_device *dev); +#endif +#ifdef CONFIG_NET_LL_RX_POLL + int (*ndo_ll_poll)(struct napi_struct *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9995834d2cb6..400d82ae2b03 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -386,6 +386,7 @@ typedef unsigned char *sk_buff_data_t; * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @dma_cookie: a cookie to one of several possible DMA operations * done by skb DMA functions + * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark * @dropcount: total number of sk_receive_queue overflows @@ -500,8 +501,11 @@ struct sk_buff { /* 7/9 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); -#ifdef CONFIG_NET_DMA - dma_cookie_t dma_cookie; +#if defined CONFIG_NET_DMA || defined CONFIG_NET_LL_RX_POLL + union { + unsigned int napi_id; + dma_cookie_t dma_cookie; + }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; diff --git a/include/net/ll_poll.h b/include/net/ll_poll.h new file mode 100644 index 000000000000..bc262f88173f --- /dev/null +++ b/include/net/ll_poll.h @@ -0,0 +1,148 @@ +/* + * Low Latency Sockets + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * + * Author: Eliezer Tamir + * + * Contact Information: + * e1000-devel Mailing List + */ + +/* + * For now this depends on CONFIG_X86_TSC + */ + +#ifndef _LINUX_NET_LL_POLL_H +#define _LINUX_NET_LL_POLL_H + +#include +#include + +#ifdef CONFIG_NET_LL_RX_POLL + +struct napi_struct; +extern unsigned long sysctl_net_ll_poll __read_mostly; + +/* return values from ndo_ll_poll */ +#define LL_FLUSH_FAILED -1 +#define LL_FLUSH_BUSY -2 + +/* we don't mind a ~2.5% imprecision */ +#define TSC_MHZ (tsc_khz >> 10) + +static inline cycles_t ll_end_time(void) +{ + return TSC_MHZ * ACCESS_ONCE(sysctl_net_ll_poll) + get_cycles(); +} + +static inline bool sk_valid_ll(struct sock *sk) +{ + return sysctl_net_ll_poll && sk->sk_napi_id && + !need_resched() && !signal_pending(current); +} + +static inline bool can_poll_ll(cycles_t end_time) +{ + return !time_after((unsigned long)get_cycles(), + (unsigned long)end_time); +} + +static inline bool sk_poll_ll(struct sock *sk, int nonblock) +{ + cycles_t end_time = ll_end_time(); + const struct net_device_ops *ops; + struct napi_struct *napi; + int rc = false; + + /* + * rcu read lock for napi hash + * bh so we don't race with net_rx_action + */ + rcu_read_lock_bh(); + + napi = napi_by_id(sk->sk_napi_id); + if (!napi) + goto out; + + ops = napi->dev->netdev_ops; + if (!ops->ndo_ll_poll) + goto out; + + do { + + rc = ops->ndo_ll_poll(napi); + + if (rc == LL_FLUSH_FAILED) + break; /* permanent failure */ + + if (rc > 0) + /* local bh are disabled so it is ok to use _BH */ + NET_ADD_STATS_BH(sock_net(sk), + LINUX_MIB_LOWLATENCYRXPACKETS, rc); + + } while (skb_queue_empty(&sk->sk_receive_queue) + && can_poll_ll(end_time) && !nonblock); + + rc = !skb_queue_empty(&sk->sk_receive_queue); +out: + rcu_read_unlock_bh(); + return rc; +} + +/* used in the NIC receive handler to mark the skb */ +static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi) +{ + skb->napi_id = napi->napi_id; +} + +/* used in the protocol hanlder to propagate the napi_id to the socket */ +static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) +{ + sk->sk_napi_id = skb->napi_id; +} + +#else /* CONFIG_NET_LL_RX_POLL */ + +static inline cycles_t ll_end_time(void) +{ + return 0; +} + +static inline bool sk_valid_ll(struct sock *sk) +{ + return false; +} + +static inline bool sk_poll_ll(struct sock *sk, int nonblock) +{ + return false; +} + +static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi) +{ +} + +static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) +{ +} + +static inline bool can_poll_ll(cycles_t end_time) +{ + return false; +} + +#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* _LINUX_NET_LL_POLL_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 66772cf8c3c5..ac8e1818380c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -229,6 +229,7 @@ struct cg_proto; * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward + * @sk_napi_id: id of the last napi context to receive data for sk * @sk_allocation: allocation mode * @sk_sndbuf: size of send buffer in bytes * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, @@ -324,6 +325,9 @@ struct sock { int sk_forward_alloc; #ifdef CONFIG_RPS __u32 sk_rxhash; +#endif +#ifdef CONFIG_NET_LL_RX_POLL + unsigned int sk_napi_id; #endif atomic_t sk_drops; int sk_rcvbuf; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index df2e8b4f9c03..26cbf76f8058 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -253,6 +253,7 @@ enum LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */ LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */ LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */ + LINUX_MIB_LOWLATENCYRXPACKETS, /* LowLatencyRxPackets */ __LINUX_MIB_MAX }; diff --git a/net/Kconfig b/net/Kconfig index 523e43e6da1b..d6a9ce6e1800 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -243,6 +243,18 @@ config NETPRIO_CGROUP Cgroup subsystem for use in assigning processes to network priorities on a per-interface basis +config NET_LL_RX_POLL + bool "Low Latency Receive Poll" + depends on X86_TSC + default n + ---help--- + Support Low Latency Receive Queue Poll. + (For network card drivers which support this option.) + When waiting for data in read or poll call directly into the the device driver + to flush packets which may be pending on the device queues into the stack. + + If unsure, say N. + config BQL boolean depends on SYSFS diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 73f57a0e1523..4a4181e16c1a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -733,6 +733,10 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->vlan_tci = old->vlan_tci; skb_copy_secmark(new, old); + +#ifdef CONFIG_NET_LL_RX_POLL + new->napi_id = old->napi_id; +#endif } /* diff --git a/net/core/sock.c b/net/core/sock.c index 88868a9d21da..788c0da5eed1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,6 +139,8 @@ #include #endif +#include + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -2284,6 +2286,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); +#ifdef CONFIG_NET_LL_RX_POLL + sk->sk_napi_id = 0; +#endif + /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 741db5fc7806..4b48f39582b0 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -19,6 +19,7 @@ #include #include #include +#include static int one = 1; @@ -284,6 +285,15 @@ static struct ctl_table net_core_table[] = { .proc_handler = flow_limit_table_len_sysctl }, #endif /* CONFIG_NET_FLOW_LIMIT */ +#ifdef CONFIG_NET_LL_RX_POLL + { + .procname = "low_latency_poll", + .data = &sysctl_net_ll_poll, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 2a5bf86d2415..6577a1149a47 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD), SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), + SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS), SNMP_MIB_SENTINEL }; diff --git a/net/socket.c b/net/socket.c index 3ebdcb805c51..21fd29f63ed2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,6 +104,12 @@ #include #include #include +#include + +#ifdef CONFIG_NET_LL_RX_POLL +unsigned long sysctl_net_ll_poll __read_mostly; +EXPORT_SYMBOL_GPL(sysctl_net_ll_poll); +#endif static int sock_no_open(struct inode *irrelevant, struct file *dontcare); static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, -- cgit v1.2.3 From e3d73bcedfdf66d21349fee00241b0931d28a943 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 11 Jun 2013 18:54:39 +0800 Subject: net: add doc for ip_early_demux sysctl commit 6648bd7e0e62c0c8c03b (ipv4: Add sysctl knob to control early socket demux) introduced such sysctl, but forgot to add doc into Documentation/networking/ip-sysctl.txt. This patch adds it. Basically I grab the doc from the description of commit 41063e9dd11956f2d285 (ipv4: Early TCP socket demux.) and the above commit. Cc: Eric Dumazet Cc: Alexander Duyck Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 9cea5d3b3c50..36e5a402ed0e 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -685,6 +685,15 @@ ip_dynaddr - BOOLEAN occurs. Default: 0 +ip_early_demux - BOOLEAN + Optimize input packet processing down to one demux for + certain kinds of local sockets. Currently we only do this + for established TCP sockets. + + It may add an additional cost for pure routing workloads that + reduces overall throughput, in such case you should disable it. + Default: 1 + icmp_echo_ignore_all - BOOLEAN If set non-zero, then the kernel will ignore all ICMP ECHO requests sent to it. -- cgit v1.2.3 From cc79dd1ba9c1021c2ac6ae200a65ec38ee8db351 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 17 Jun 2013 10:54:37 -0400 Subject: tipc: change socket buffer overflow control to respect sk_rcvbuf As per feedback from the netdev community, we change the buffer overflow protection algorithm in receiving sockets so that it always respects the nominal upper limit set in sk_rcvbuf. Instead of scaling up from a small sk_rcvbuf value, which leads to violation of the configured sk_rcvbuf limit, we now calculate the weighted per-message limit by scaling down from a much bigger value, still in the same field, according to the importance priority of the received message. To allow for administrative tunability of the socket receive buffer size, we create a tipc_rmem sysctl variable to allow the user to configure an even bigger value via sysctl command. It is a size of three (min/default/max) to be consistent with things like tcp_rmem. By default, the value initialized in tipc_rmem[1] is equal to the receive socket size needed by a TIPC_CRITICAL_IMPORTANCE message. This value is also set as the default value of sk_rcvbuf. Originally-by: Jon Maloy Cc: Neil Horman Cc: Jon Maloy [Ying: added sysctl variation to Jon's original patch] Signed-off-by: Ying Xue [PG: don't compile sysctl.c if not config'd; add Documentation] Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 17 +++++++++++- net/tipc/Makefile | 1 + net/tipc/core.c | 12 +++++++-- net/tipc/core.h | 9 +++++++ net/tipc/port.h | 2 ++ net/tipc/socket.c | 19 ++++++------- net/tipc/sysctl.c | 64 ++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 112 insertions(+), 12 deletions(-) create mode 100644 net/tipc/sysctl.c (limited to 'Documentation') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 85ab72dcdc3c..5369879eafe2 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -26,7 +26,7 @@ Table : Subdirectories in /proc/sys/net ipv4 IP version 4 x25 X.25 protocol ipx IPX token-ring IBM token ring bridge Bridging decnet DEC net - ipv6 IP version 6 + ipv6 IP version 6 tipc TIPC .............................................................................. 1. /proc/sys/net/core - Network core options @@ -207,3 +207,18 @@ IPX. The /proc/net/ipx_route table holds a list of IPX routes. For each route it gives the destination network, the router node (or Directly) and the network address of the router (or Connected) for internal networks. + +6. TIPC +------------------------------------------------------- + +The TIPC protocol now has a tunable for the receive memory, similar to the +tcp_rmem - i.e. a vector of 3 INTEGERs: (min, default, max) + + # cat /proc/sys/net/tipc/tipc_rmem + 4252725 34021800 68043600 + # + +The max value is set to CONN_OVERLOAD_LIMIT, and the default and min values +are scaled (shifted) versions of that same value. Note that the min value +is not at this point in time used in any meaningful way, but the triplet is +preserved in order to be consistent with things like tcp_rmem. diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 4df8e02d9008..02636d0a90cf 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -11,3 +11,4 @@ tipc-y += addr.o bcast.o bearer.o config.o \ socket.o log.o eth_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o +tipc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/tipc/core.c b/net/tipc/core.c index 7ec2c1eb94f1..b0e42a087291 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -39,6 +39,7 @@ #include "name_table.h" #include "subscr.h" #include "config.h" +#include "port.h" #include @@ -50,7 +51,7 @@ u32 tipc_own_addr __read_mostly; int tipc_max_ports __read_mostly; int tipc_net_id __read_mostly; int tipc_remote_management __read_mostly; - +int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */ /** * tipc_buf_acquire - creates a TIPC message buffer @@ -118,6 +119,7 @@ static void tipc_core_stop(void) tipc_nametbl_stop(); tipc_ref_table_stop(); tipc_socket_stop(); + tipc_unregister_sysctl(); } /** @@ -142,13 +144,14 @@ static int tipc_core_start(void) res = tipc_netlink_start(); if (!res) res = tipc_socket_init(); + if (!res) + res = tipc_register_sysctl(); if (res) tipc_core_stop(); return res; } - static int __init tipc_init(void) { int res; @@ -160,6 +163,11 @@ static int __init tipc_init(void) tipc_max_ports = CONFIG_TIPC_PORTS; tipc_net_id = 4711; + sysctl_tipc_rmem[0] = CONN_OVERLOAD_LIMIT >> 4 << TIPC_LOW_IMPORTANCE; + sysctl_tipc_rmem[1] = CONN_OVERLOAD_LIMIT >> 4 << + TIPC_CRITICAL_IMPORTANCE; + sysctl_tipc_rmem[2] = CONN_OVERLOAD_LIMIT; + res = tipc_core_start(); if (res) pr_err("Unable to start in single node mode\n"); diff --git a/net/tipc/core.h b/net/tipc/core.h index 0207db04179a..fe7f2b7c19fe 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -80,6 +80,7 @@ extern u32 tipc_own_addr __read_mostly; extern int tipc_max_ports __read_mostly; extern int tipc_net_id __read_mostly; extern int tipc_remote_management __read_mostly; +extern int sysctl_tipc_rmem[3] __read_mostly; /* * Other global variables @@ -97,6 +98,14 @@ extern void tipc_netlink_stop(void); extern int tipc_socket_init(void); extern void tipc_socket_stop(void); +#ifdef CONFIG_SYSCTL +extern int tipc_register_sysctl(void); +extern void tipc_unregister_sysctl(void); +#else +#define tipc_register_sysctl() 0 +#define tipc_unregister_sysctl() +#endif + /* * TIPC timer and signal code */ diff --git a/net/tipc/port.h b/net/tipc/port.h index fb66e2e5f4d1..2485649c408a 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -43,6 +43,8 @@ #include "node_subscr.h" #define TIPC_FLOW_CONTROL_WIN 512 +#define CONN_OVERLOAD_LIMIT ((TIPC_FLOW_CONTROL_WIN * 2 + 1) * \ + SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) typedef void (*tipc_msg_err_event) (void *usr_handle, u32 portref, struct sk_buff **buf, unsigned char const *data, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 515ce38e4f4c..aba4255f297b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -43,8 +43,6 @@ #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ -#define CONN_OVERLOAD_LIMIT ((TIPC_FLOW_CONTROL_WIN * 2 + 1) * \ - SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ struct tipc_sock { @@ -203,6 +201,7 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, sock_init_data(sock, sk); sk->sk_backlog_rcv = backlog_rcv; + sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; tipc_sk(sk)->p = tp_ptr; @@ -1233,10 +1232,10 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) * For all connectionless messages, by default new queue limits are * as belows: * - * TIPC_LOW_IMPORTANCE (5MB) - * TIPC_MEDIUM_IMPORTANCE (10MB) - * TIPC_HIGH_IMPORTANCE (20MB) - * TIPC_CRITICAL_IMPORTANCE (40MB) + * TIPC_LOW_IMPORTANCE (4 MB) + * TIPC_MEDIUM_IMPORTANCE (8 MB) + * TIPC_HIGH_IMPORTANCE (16 MB) + * TIPC_CRITICAL_IMPORTANCE (32 MB) * * Returns overload limit according to corresponding message importance */ @@ -1246,9 +1245,10 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) unsigned int limit; if (msg_connected(msg)) - limit = CONN_OVERLOAD_LIMIT; + limit = sysctl_tipc_rmem[2]; else - limit = sk->sk_rcvbuf << (msg_importance(msg) + 5); + limit = sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE << + msg_importance(msg); return limit; } @@ -1847,7 +1847,8 @@ static const struct net_proto_family tipc_family_ops = { static struct proto tipc_proto = { .name = "TIPC", .owner = THIS_MODULE, - .obj_size = sizeof(struct tipc_sock) + .obj_size = sizeof(struct tipc_sock), + .sysctl_rmem = sysctl_tipc_rmem }; /** diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c new file mode 100644 index 000000000000..f3fef93325a8 --- /dev/null +++ b/net/tipc/sysctl.c @@ -0,0 +1,64 @@ +/* + * net/tipc/sysctl.c: sysctl interface to TIPC subsystem + * + * Copyright (c) 2013, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" + +#include + +static struct ctl_table_header *tipc_ctl_hdr; + +static struct ctl_table tipc_table[] = { + { + .procname = "tipc_rmem", + .data = &sysctl_tipc_rmem, + .maxlen = sizeof(sysctl_tipc_rmem), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +int tipc_register_sysctl(void) +{ + tipc_ctl_hdr = register_net_sysctl(&init_net, "net/tipc", tipc_table); + if (tipc_ctl_hdr == NULL) + return -ENOMEM; + return 0; +} + +void tipc_unregister_sysctl(void) +{ + unregister_net_sysctl_table(tipc_ctl_hdr); +} -- cgit v1.2.3 From e4f2379db6c6823c5d4a4c2c912df00c65de51d7 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Mon, 24 Jun 2013 09:54:27 +0400 Subject: ethernet/arc/arc_emac - Add new driver Driver for non-standard on-chip ethernet device ARC EMAC 10/100, instantiated in some legacy ARC (Synopsys) FPGA Boards such as ARCAngel4/ML50x. Signed-off-by: Alexey Brodkin Cc: Andy Shevchenko Cc: Francois Romieu Cc: Joe Perches Cc: Vineet Gupta Cc: Mischa Jonker Cc: Arnd Bergmann Cc: Grant Likely Cc: Rob Herring Cc: Paul Gortmaker Cc: "David S. Miller" Cc: linux-kernel@vger.kernel.org Cc: devicetree-discuss@lists.ozlabs.org Cc: Florian Fainelli Cc: David Laight Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/arc_emac.txt | 38 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/arc/Kconfig | 31 + drivers/net/ethernet/arc/Makefile | 6 + drivers/net/ethernet/arc/emac.h | 214 ++++++ drivers/net/ethernet/arc/emac_main.c | 806 +++++++++++++++++++++ drivers/net/ethernet/arc/emac_mdio.c | 152 ++++ 8 files changed, 1249 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/arc_emac.txt create mode 100644 drivers/net/ethernet/arc/Kconfig create mode 100644 drivers/net/ethernet/arc/Makefile create mode 100644 drivers/net/ethernet/arc/emac.h create mode 100644 drivers/net/ethernet/arc/emac_main.c create mode 100644 drivers/net/ethernet/arc/emac_mdio.c (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/arc_emac.txt b/Documentation/devicetree/bindings/net/arc_emac.txt new file mode 100644 index 000000000000..bcbc3f009158 --- /dev/null +++ b/Documentation/devicetree/bindings/net/arc_emac.txt @@ -0,0 +1,38 @@ +* Synopsys ARC EMAC 10/100 Ethernet driver (EMAC) + +Required properties: +- compatible: Should be "snps,arc-emac" +- reg: Address and length of the register set for the device +- interrupts: Should contain the EMAC interrupts +- clock-frequency: CPU frequency. It is needed to calculate and set polling +period of EMAC. +- max-speed: Maximum supported data-rate in Mbit/s. In some HW configurations +bandwidth of external memory controller might be a limiting factor. That's why +it's required to specify which data-rate is supported on current SoC or FPGA. +For example if only 10 Mbit/s is supported (10BASE-T) set "10". If 100 Mbit/s is +supported (100BASE-TX) set "100". +- phy: PHY device attached to the EMAC via MDIO bus + +Child nodes of the driver are the individual PHY devices connected to the +MDIO bus. They must have a "reg" property given the PHY address on the MDIO bus. + +Optional properties: +- mac-address: 6 bytes, mac address + +Examples: + + ethernet@c0fc2000 { + compatible = "snps,arc-emac"; + reg = <0xc0fc2000 0x3c>; + interrupts = <6>; + mac-address = [ 00 11 22 33 44 55 ]; + clock-frequency = <80000000>; + max-speed = <100>; + phy = <&phy0>; + + #address-cells = <1>; + #size-cells = <0>; + phy0: ethernet-phy@0 { + reg = <1>; + }; + }; diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index a989669b353a..2037080c504d 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -24,6 +24,7 @@ source "drivers/net/ethernet/allwinner/Kconfig" source "drivers/net/ethernet/alteon/Kconfig" source "drivers/net/ethernet/amd/Kconfig" source "drivers/net/ethernet/apple/Kconfig" +source "drivers/net/ethernet/arc/Kconfig" source "drivers/net/ethernet/atheros/Kconfig" source "drivers/net/ethernet/cadence/Kconfig" source "drivers/net/ethernet/adi/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 009da27b6e26..390bd0bfaa27 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/ obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/ obj-$(CONFIG_NET_VENDOR_AMD) += amd/ obj-$(CONFIG_NET_VENDOR_APPLE) += apple/ +obj-$(CONFIG_NET_VENDOR_ARC) += arc/ obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/ obj-$(CONFIG_NET_CADENCE) += cadence/ obj-$(CONFIG_NET_BFIN) += adi/ diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig new file mode 100644 index 000000000000..514c57fd26f1 --- /dev/null +++ b/drivers/net/ethernet/arc/Kconfig @@ -0,0 +1,31 @@ +# +# ARC EMAC network device configuration +# + +config NET_VENDOR_ARC + bool "ARC devices" + default y + ---help--- + If you have a network (Ethernet) card belonging to this class, say Y + and read the Ethernet-HOWTO, available from + . + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about ARC cards. If you say Y, you will be asked for + your specific card in the following questions. + +if NET_VENDOR_ARC + +config ARC_EMAC + tristate "ARC EMAC support" + select MII + select PHYLIB + depends on OF_IRQ + depends on OF_NET + ---help--- + On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x + non-standard on-chip ethernet device ARC EMAC 10/100 is used. + Say Y here if you have such a board. If unsure, say N. + +endif # NET_VENDOR_ARC diff --git a/drivers/net/ethernet/arc/Makefile b/drivers/net/ethernet/arc/Makefile new file mode 100644 index 000000000000..00c8657637d5 --- /dev/null +++ b/drivers/net/ethernet/arc/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for the ARC network device drivers. +# + +arc_emac-objs := emac_main.o emac_mdio.o +obj-$(CONFIG_ARC_EMAC) += arc_emac.o diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h new file mode 100644 index 000000000000..dc08678bf9a4 --- /dev/null +++ b/drivers/net/ethernet/arc/emac.h @@ -0,0 +1,214 @@ +/* + * Copyright (C) 2004-2013 Synopsys, Inc. (www.synopsys.com) + * + * Registers and bits definitions of ARC EMAC + */ + +#ifndef ARC_EMAC_H +#define ARC_EMAC_H + +#include +#include +#include +#include + +/* STATUS and ENABLE Register bit masks */ +#define TXINT_MASK (1<<0) /* Transmit interrupt */ +#define RXINT_MASK (1<<1) /* Receive interrupt */ +#define ERR_MASK (1<<2) /* Error interrupt */ +#define TXCH_MASK (1<<3) /* Transmit chaining error interrupt */ +#define MSER_MASK (1<<4) /* Missed packet counter error */ +#define RXCR_MASK (1<<8) /* RXCRCERR counter rolled over */ +#define RXFR_MASK (1<<9) /* RXFRAMEERR counter rolled over */ +#define RXFL_MASK (1<<10) /* RXOFLOWERR counter rolled over */ +#define MDIO_MASK (1<<12) /* MDIO complete interrupt */ +#define TXPL_MASK (1<<31) /* Force polling of BD by EMAC */ + +/* CONTROL Register bit masks */ +#define EN_MASK (1<<0) /* VMAC enable */ +#define TXRN_MASK (1<<3) /* TX enable */ +#define RXRN_MASK (1<<4) /* RX enable */ +#define DSBC_MASK (1<<8) /* Disable receive broadcast */ +#define ENFL_MASK (1<<10) /* Enable Full-duplex */ +#define PROM_MASK (1<<11) /* Promiscuous mode */ + +/* Buffer descriptor INFO bit masks */ +#define OWN_MASK (1<<31) /* 0-CPU owns buffer, 1-EMAC owns buffer */ +#define FIRST_MASK (1<<16) /* First buffer in chain */ +#define LAST_MASK (1<<17) /* Last buffer in chain */ +#define LEN_MASK 0x000007FF /* last 11 bits */ +#define CRLS (1<<21) +#define DEFR (1<<22) +#define DROP (1<<23) +#define RTRY (1<<24) +#define LTCL (1<<28) +#define UFLO (1<<29) + +#define FOR_EMAC OWN_MASK +#define FOR_CPU 0 + +/* ARC EMAC register set combines entries for MAC and MDIO */ +enum { + R_ID = 0, + R_STATUS, + R_ENABLE, + R_CTRL, + R_POLLRATE, + R_RXERR, + R_MISS, + R_TX_RING, + R_RX_RING, + R_ADDRL, + R_ADDRH, + R_LAFL, + R_LAFH, + R_MDIO, +}; + +#define TX_TIMEOUT (400*HZ/1000) /* Transmission timeout */ + +#define ARC_EMAC_NAPI_WEIGHT 40 /* Workload for NAPI */ + +#define EMAC_BUFFER_SIZE 1536 /* EMAC buffer size */ + +/** + * struct arc_emac_bd - EMAC buffer descriptor (BD). + * + * @info: Contains status information on the buffer itself. + * @data: 32-bit byte addressable pointer to the packet data. + */ +struct arc_emac_bd { + __le32 info; + dma_addr_t data; +}; + +/* Number of Rx/Tx BD's */ +#define RX_BD_NUM 128 +#define TX_BD_NUM 128 + +#define RX_RING_SZ (RX_BD_NUM * sizeof(struct arc_emac_bd)) +#define TX_RING_SZ (TX_BD_NUM * sizeof(struct arc_emac_bd)) + +/** + * struct buffer_state - Stores Rx/Tx buffer state. + * @sk_buff: Pointer to socket buffer. + * @addr: Start address of DMA-mapped memory region. + * @len: Length of DMA-mapped memory region. + */ +struct buffer_state { + struct sk_buff *skb; + DEFINE_DMA_UNMAP_ADDR(addr); + DEFINE_DMA_UNMAP_LEN(len); +}; + +/** + * struct arc_emac_priv - Storage of EMAC's private information. + * @dev: Pointer to the current device. + * @ndev: Pointer to the current network device. + * @phy_dev: Pointer to attached PHY device. + * @bus: Pointer to the current MII bus. + * @regs: Base address of EMAC memory-mapped control registers. + * @napi: Structure for NAPI. + * @stats: Network device statistics. + * @rxbd: Pointer to Rx BD ring. + * @txbd: Pointer to Tx BD ring. + * @rxbd_dma: DMA handle for Rx BD ring. + * @txbd_dma: DMA handle for Tx BD ring. + * @rx_buff: Storage for Rx buffers states. + * @tx_buff: Storage for Tx buffers states. + * @txbd_curr: Index of Tx BD to use on the next "ndo_start_xmit". + * @txbd_dirty: Index of Tx BD to free on the next Tx interrupt. + * @last_rx_bd: Index of the last Rx BD we've got from EMAC. + * @link: PHY's last seen link state. + * @duplex: PHY's last set duplex mode. + * @speed: PHY's last set speed. + * @max_speed: Maximum supported by current system network data-rate. + */ +struct arc_emac_priv { + /* Devices */ + struct device *dev; + struct net_device *ndev; + struct phy_device *phy_dev; + struct mii_bus *bus; + + void __iomem *regs; + + struct napi_struct napi; + struct net_device_stats stats; + + struct arc_emac_bd *rxbd; + struct arc_emac_bd *txbd; + + dma_addr_t rxbd_dma; + dma_addr_t txbd_dma; + + struct buffer_state rx_buff[RX_BD_NUM]; + struct buffer_state tx_buff[TX_BD_NUM]; + unsigned int txbd_curr; + unsigned int txbd_dirty; + + unsigned int last_rx_bd; + + unsigned int link; + unsigned int duplex; + unsigned int speed; + unsigned int max_speed; +}; + +/** + * arc_reg_set - Sets EMAC register with provided value. + * @priv: Pointer to ARC EMAC private data structure. + * @reg: Register offset from base address. + * @value: Value to set in register. + */ +static inline void arc_reg_set(struct arc_emac_priv *priv, int reg, int value) +{ + iowrite32(value, priv->regs + reg * sizeof(int)); +} + +/** + * arc_reg_get - Gets value of specified EMAC register. + * @priv: Pointer to ARC EMAC private data structure. + * @reg: Register offset from base address. + * + * returns: Value of requested register. + */ +static inline unsigned int arc_reg_get(struct arc_emac_priv *priv, int reg) +{ + return ioread32(priv->regs + reg * sizeof(int)); +} + +/** + * arc_reg_or - Applies mask to specified EMAC register - ("reg" | "mask"). + * @priv: Pointer to ARC EMAC private data structure. + * @reg: Register offset from base address. + * @mask: Mask to apply to specified register. + * + * This function reads initial register value, then applies provided mask + * to it and then writes register back. + */ +static inline void arc_reg_or(struct arc_emac_priv *priv, int reg, int mask) +{ + unsigned int value = arc_reg_get(priv, reg); + arc_reg_set(priv, reg, value | mask); +} + +/** + * arc_reg_clr - Applies mask to specified EMAC register - ("reg" & ~"mask"). + * @priv: Pointer to ARC EMAC private data structure. + * @reg: Register offset from base address. + * @mask: Mask to apply to specified register. + * + * This function reads initial register value, then applies provided mask + * to it and then writes register back. + */ +static inline void arc_reg_clr(struct arc_emac_priv *priv, int reg, int mask) +{ + unsigned int value = arc_reg_get(priv, reg); + arc_reg_set(priv, reg, value & ~mask); +} + +int arc_mdio_probe(struct platform_device *pdev, struct arc_emac_priv *priv); +int arc_mdio_remove(struct arc_emac_priv *priv); + +#endif /* ARC_EMAC_H */ diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c new file mode 100644 index 000000000000..20345f6bf894 --- /dev/null +++ b/drivers/net/ethernet/arc/emac_main.c @@ -0,0 +1,806 @@ +/* + * Copyright (C) 2004-2013 Synopsys, Inc. (www.synopsys.com) + * + * 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. + * + * Driver for the ARC EMAC 10100 (hardware revision 5) + * + * Contributors: + * Amit Bhor + * Sameer Dhavale + * Vineet Gupta + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "emac.h" + +#define DRV_NAME "arc_emac" +#define DRV_VERSION "1.0" + +/** + * arc_emac_adjust_link - Adjust the PHY link duplex. + * @ndev: Pointer to the net_device structure. + * + * This function is called to change the duplex setting after auto negotiation + * is done by the PHY. + */ +static void arc_emac_adjust_link(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct phy_device *phy_dev = priv->phy_dev; + unsigned int reg, state_changed = 0; + + if (priv->link != phy_dev->link) { + priv->link = phy_dev->link; + state_changed = 1; + } + + if (priv->speed != phy_dev->speed) { + priv->speed = phy_dev->speed; + state_changed = 1; + } + + if (priv->duplex != phy_dev->duplex) { + reg = arc_reg_get(priv, R_CTRL); + + if (DUPLEX_FULL == phy_dev->duplex) + reg |= ENFL_MASK; + else + reg &= ~ENFL_MASK; + + arc_reg_set(priv, R_CTRL, reg); + priv->duplex = phy_dev->duplex; + state_changed = 1; + } + + if (state_changed) + phy_print_status(phy_dev); +} + +/** + * arc_emac_get_settings - Get PHY settings. + * @ndev: Pointer to net_device structure. + * @cmd: Pointer to ethtool_cmd structure. + * + * This implements ethtool command for getting PHY settings. If PHY could + * not be found, the function returns -ENODEV. This function calls the + * relevant PHY ethtool API to get the PHY settings. + * Issue "ethtool ethX" under linux prompt to execute this function. + */ +static int arc_emac_get_settings(struct net_device *ndev, + struct ethtool_cmd *cmd) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + + return phy_ethtool_gset(priv->phy_dev, cmd); +} + +/** + * arc_emac_set_settings - Set PHY settings as passed in the argument. + * @ndev: Pointer to net_device structure. + * @cmd: Pointer to ethtool_cmd structure. + * + * This implements ethtool command for setting various PHY settings. If PHY + * could not be found, the function returns -ENODEV. This function calls the + * relevant PHY ethtool API to set the PHY. + * Issue e.g. "ethtool -s ethX speed 1000" under linux prompt to execute this + * function. + */ +static int arc_emac_set_settings(struct net_device *ndev, + struct ethtool_cmd *cmd) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + return phy_ethtool_sset(priv->phy_dev, cmd); +} + +/** + * arc_emac_get_drvinfo - Get EMAC driver information. + * @ndev: Pointer to net_device structure. + * @info: Pointer to ethtool_drvinfo structure. + * + * This implements ethtool command for getting the driver information. + * Issue "ethtool -i ethX" under linux prompt to execute this function. + */ +static void arc_emac_get_drvinfo(struct net_device *ndev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); + strlcpy(info->version, DRV_VERSION, sizeof(info->version)); +} + +static const struct ethtool_ops arc_emac_ethtool_ops = { + .get_settings = arc_emac_get_settings, + .set_settings = arc_emac_set_settings, + .get_drvinfo = arc_emac_get_drvinfo, + .get_link = ethtool_op_get_link, +}; + +#define FIRST_OR_LAST_MASK (FIRST_MASK | LAST_MASK) + +/** + * arc_emac_tx_clean - clears processed by EMAC Tx BDs. + * @ndev: Pointer to the network device. + */ +static void arc_emac_tx_clean(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &priv->stats; + unsigned int i; + + for (i = 0; i < TX_BD_NUM; i++) { + unsigned int *txbd_dirty = &priv->txbd_dirty; + struct arc_emac_bd *txbd = &priv->txbd[*txbd_dirty]; + struct buffer_state *tx_buff = &priv->tx_buff[*txbd_dirty]; + struct sk_buff *skb = tx_buff->skb; + unsigned int info = le32_to_cpu(txbd->info); + + *txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM; + + if ((info & FOR_EMAC) || !txbd->data) + break; + + if (unlikely(info & (DROP | DEFR | LTCL | UFLO))) { + stats->tx_errors++; + stats->tx_dropped++; + + if (info & DEFR) + stats->tx_carrier_errors++; + + if (info & LTCL) + stats->collisions++; + + if (info & UFLO) + stats->tx_fifo_errors++; + } else if (likely(info & FIRST_OR_LAST_MASK)) { + stats->tx_packets++; + stats->tx_bytes += skb->len; + } + + dma_unmap_single(&ndev->dev, dma_unmap_addr(&tx_buff, addr), + dma_unmap_len(&tx_buff, len), DMA_TO_DEVICE); + + /* return the sk_buff to system */ + dev_kfree_skb_irq(skb); + + txbd->data = 0; + txbd->info = 0; + + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + } +} + +/** + * arc_emac_rx - processing of Rx packets. + * @ndev: Pointer to the network device. + * @budget: How many BDs to process on 1 call. + * + * returns: Number of processed BDs + * + * Iterate through Rx BDs and deliver received packages to upper layer. + */ +static int arc_emac_rx(struct net_device *ndev, int budget) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + unsigned int work_done; + + for (work_done = 0; work_done <= budget; work_done++) { + unsigned int *last_rx_bd = &priv->last_rx_bd; + struct net_device_stats *stats = &priv->stats; + struct buffer_state *rx_buff = &priv->rx_buff[*last_rx_bd]; + struct arc_emac_bd *rxbd = &priv->rxbd[*last_rx_bd]; + unsigned int buflen = EMAC_BUFFER_SIZE; + unsigned int pktlen, info = le32_to_cpu(rxbd->info); + struct sk_buff *skb; + dma_addr_t addr; + + if (unlikely((info & OWN_MASK) == FOR_EMAC)) + break; + + /* Make a note that we saw a packet at this BD. + * So next time, driver starts from this + 1 + */ + *last_rx_bd = (*last_rx_bd + 1) % RX_BD_NUM; + + if (unlikely((info & FIRST_OR_LAST_MASK) != + FIRST_OR_LAST_MASK)) { + /* We pre-allocate buffers of MTU size so incoming + * packets won't be split/chained. + */ + if (net_ratelimit()) + netdev_err(ndev, "incomplete packet received\n"); + + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | buflen); + stats->rx_errors++; + stats->rx_length_errors++; + continue; + } + + pktlen = info & LEN_MASK; + stats->rx_packets++; + stats->rx_bytes += pktlen; + skb = rx_buff->skb; + skb_put(skb, pktlen); + skb->dev = ndev; + skb->protocol = eth_type_trans(skb, ndev); + + dma_unmap_single(&ndev->dev, dma_unmap_addr(&rx_buff, addr), + dma_unmap_len(&rx_buff, len), DMA_FROM_DEVICE); + + /* Prepare the BD for next cycle */ + rx_buff->skb = netdev_alloc_skb_ip_align(ndev, buflen); + if (unlikely(!rx_buff->skb)) { + stats->rx_errors++; + /* Because receive_skb is below, increment rx_dropped */ + stats->rx_dropped++; + continue; + } + + /* receive_skb only if new skb was allocated to avoid holes */ + netif_receive_skb(skb); + + addr = dma_map_single(&ndev->dev, (void *)rx_buff->skb->data, + buflen, DMA_FROM_DEVICE); + if (dma_mapping_error(&ndev->dev, addr)) { + if (net_ratelimit()) + netdev_err(ndev, "cannot dma map\n"); + dev_kfree_skb(rx_buff->skb); + stats->rx_errors++; + continue; + } + dma_unmap_addr_set(&rx_buff, mapping, addr); + dma_unmap_len_set(&rx_buff, len, buflen); + + rxbd->data = cpu_to_le32(rx_buff->skb->data); + + /* Make sure pointer to data buffer is set */ + wmb(); + + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | buflen); + } + + return work_done; +} + +/** + * arc_emac_poll - NAPI poll handler. + * @napi: Pointer to napi_struct structure. + * @budget: How many BDs to process on 1 call. + * + * returns: Number of processed BDs + */ +static int arc_emac_poll(struct napi_struct *napi, int budget) +{ + struct net_device *ndev = napi->dev; + struct arc_emac_priv *priv = netdev_priv(ndev); + unsigned int work_done; + + arc_emac_tx_clean(ndev); + + work_done = arc_emac_rx(ndev, budget); + if (work_done < budget) { + napi_complete(napi); + arc_reg_or(priv, R_ENABLE, RXINT_MASK); + } + + return work_done; +} + +/** + * arc_emac_intr - Global interrupt handler for EMAC. + * @irq: irq number. + * @dev_instance: device instance. + * + * returns: IRQ_HANDLED for all cases. + * + * ARC EMAC has only 1 interrupt line, and depending on bits raised in + * STATUS register we may tell what is a reason for interrupt to fire. + */ +static irqreturn_t arc_emac_intr(int irq, void *dev_instance) +{ + struct net_device *ndev = dev_instance; + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &priv->stats; + unsigned int status; + + status = arc_reg_get(priv, R_STATUS); + status &= ~MDIO_MASK; + + /* Reset all flags except "MDIO complete" */ + arc_reg_set(priv, R_STATUS, status); + + if (status & RXINT_MASK) { + if (likely(napi_schedule_prep(&priv->napi))) { + arc_reg_clr(priv, R_ENABLE, RXINT_MASK); + __napi_schedule(&priv->napi); + } + } + + if (status & ERR_MASK) { + /* MSER/RXCR/RXFR/RXFL interrupt fires on corresponding + * 8-bit error counter overrun. + */ + + if (status & MSER_MASK) { + stats->rx_missed_errors += 0x100; + stats->rx_errors += 0x100; + } + + if (status & RXCR_MASK) { + stats->rx_crc_errors += 0x100; + stats->rx_errors += 0x100; + } + + if (status & RXFR_MASK) { + stats->rx_frame_errors += 0x100; + stats->rx_errors += 0x100; + } + + if (status & RXFL_MASK) { + stats->rx_over_errors += 0x100; + stats->rx_errors += 0x100; + } + } + + return IRQ_HANDLED; +} + +/** + * arc_emac_open - Open the network device. + * @ndev: Pointer to the network device. + * + * returns: 0, on success or non-zero error value on failure. + * + * This function sets the MAC address, requests and enables an IRQ + * for the EMAC device and starts the Tx queue. + * It also connects to the phy device. + */ +static int arc_emac_open(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct phy_device *phy_dev = priv->phy_dev; + struct arc_emac_bd *bd; + struct sk_buff *skb; + int i; + + phy_dev->autoneg = AUTONEG_ENABLE; + phy_dev->speed = 0; + phy_dev->duplex = 0; + phy_dev->advertising = phy_dev->supported; + + if (priv->max_speed > 100) { + phy_dev->advertising &= PHY_GBIT_FEATURES; + } else if (priv->max_speed <= 100) { + phy_dev->advertising &= PHY_BASIC_FEATURES; + if (priv->max_speed <= 10) { + phy_dev->advertising &= ~SUPPORTED_100baseT_Half; + phy_dev->advertising &= ~SUPPORTED_100baseT_Full; + } + } + + /* Allocate and set buffers for Rx BD's */ + bd = priv->rxbd; + for (i = 0; i < RX_BD_NUM; i++) { + skb = netdev_alloc_skb_ip_align(ndev, EMAC_BUFFER_SIZE); + if (unlikely(!skb)) + return -ENOMEM; + + priv->rx_buff[i].skb = skb; + bd->data = cpu_to_le32(skb->data); + + /* Make sure pointer to data buffer is set */ + wmb(); + + /* Set ownership to EMAC */ + bd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); + bd++; + } + + priv->last_rx_bd = 0; + + /* Clean Tx BD's */ + memset(priv->txbd, 0, TX_RING_SZ); + + /* Initialize logical address filter */ + arc_reg_set(priv, R_LAFL, 0); + arc_reg_set(priv, R_LAFH, 0); + + /* Set BD ring pointers for device side */ + arc_reg_set(priv, R_RX_RING, (unsigned int)priv->rxbd_dma); + arc_reg_set(priv, R_TX_RING, (unsigned int)priv->txbd_dma); + + /* Enable interrupts */ + arc_reg_set(priv, R_ENABLE, RXINT_MASK | ERR_MASK); + + /* Set CONTROL */ + arc_reg_set(priv, R_CTRL, + (RX_BD_NUM << 24) | /* RX BD table length */ + (TX_BD_NUM << 16) | /* TX BD table length */ + TXRN_MASK | RXRN_MASK); + + napi_enable(&priv->napi); + + /* Enable EMAC */ + arc_reg_or(priv, R_CTRL, EN_MASK); + + phy_start_aneg(priv->phy_dev); + + netif_start_queue(ndev); + + return 0; +} + +/** + * arc_emac_stop - Close the network device. + * @ndev: Pointer to the network device. + * + * This function stops the Tx queue, disables interrupts and frees the IRQ for + * the EMAC device. + * It also disconnects the PHY device associated with the EMAC device. + */ +static int arc_emac_stop(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + + napi_disable(&priv->napi); + netif_stop_queue(ndev); + + /* Disable interrupts */ + arc_reg_clr(priv, R_ENABLE, RXINT_MASK | ERR_MASK); + + /* Disable EMAC */ + arc_reg_clr(priv, R_CTRL, EN_MASK); + + return 0; +} + +/** + * arc_emac_stats - Get system network statistics. + * @ndev: Pointer to net_device structure. + * + * Returns the address of the device statistics structure. + * Statistics are updated in interrupt handler. + */ +static struct net_device_stats *arc_emac_stats(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &priv->stats; + unsigned long miss, rxerr; + u8 rxcrc, rxfram, rxoflow; + + rxerr = arc_reg_get(priv, R_RXERR); + miss = arc_reg_get(priv, R_MISS); + + rxcrc = rxerr; + rxfram = rxerr >> 8; + rxoflow = rxerr >> 16; + + stats->rx_errors += miss; + stats->rx_errors += rxcrc + rxfram + rxoflow; + + stats->rx_over_errors += rxoflow; + stats->rx_frame_errors += rxfram; + stats->rx_crc_errors += rxcrc; + stats->rx_missed_errors += miss; + + return stats; +} + +/** + * arc_emac_tx - Starts the data transmission. + * @skb: sk_buff pointer that contains data to be Transmitted. + * @ndev: Pointer to net_device structure. + * + * returns: NETDEV_TX_OK, on success + * NETDEV_TX_BUSY, if any of the descriptors are not free. + * + * This function is invoked from upper layers to initiate transmission. + */ +static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + unsigned int len, *txbd_curr = &priv->txbd_curr; + struct net_device_stats *stats = &priv->stats; + __le32 *info = &priv->txbd[*txbd_curr].info; + dma_addr_t addr; + + if (skb_padto(skb, ETH_ZLEN)) + return NETDEV_TX_OK; + + len = max_t(unsigned int, ETH_ZLEN, skb->len); + + /* EMAC still holds this buffer in its possession. + * CPU must not modify this buffer descriptor + */ + if (unlikely((le32_to_cpu(*info) & OWN_MASK) == FOR_EMAC)) { + netif_stop_queue(ndev); + return NETDEV_TX_BUSY; + } + + addr = dma_map_single(&ndev->dev, (void *)skb->data, len, + DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(&ndev->dev, addr))) { + stats->tx_dropped++; + stats->tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + dma_unmap_addr_set(&priv->tx_buff[*txbd_curr], mapping, addr); + dma_unmap_len_set(&priv->tx_buff[*txbd_curr], len, len); + + priv->tx_buff[*txbd_curr].skb = skb; + priv->txbd[*txbd_curr].data = cpu_to_le32(skb->data); + + /* Make sure pointer to data buffer is set */ + wmb(); + + *info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len); + + /* Increment index to point to the next BD */ + *txbd_curr = (*txbd_curr + 1) % TX_BD_NUM; + + /* Get "info" of the next BD */ + info = &priv->txbd[*txbd_curr].info; + + /* Check if if Tx BD ring is full - next BD is still owned by EMAC */ + if (unlikely((le32_to_cpu(*info) & OWN_MASK) == FOR_EMAC)) + netif_stop_queue(ndev); + + arc_reg_set(priv, R_STATUS, TXPL_MASK); + + skb_tx_timestamp(skb); + + return NETDEV_TX_OK; +} + +/** + * arc_emac_set_address - Set the MAC address for this device. + * @ndev: Pointer to net_device structure. + * @p: 6 byte Address to be written as MAC address. + * + * This function copies the HW address from the sockaddr structure to the + * net_device structure and updates the address in HW. + * + * returns: -EBUSY if the net device is busy or 0 if the address is set + * successfully. + */ +static int arc_emac_set_address(struct net_device *ndev, void *p) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct sockaddr *addr = p; + unsigned int addr_low, addr_hi; + + if (netif_running(ndev)) + return -EBUSY; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(ndev->dev_addr, addr->sa_data, ndev->addr_len); + + addr_low = le32_to_cpu(*(__le32 *) &ndev->dev_addr[0]); + addr_hi = le16_to_cpu(*(__le16 *) &ndev->dev_addr[4]); + + arc_reg_set(priv, R_ADDRL, addr_low); + arc_reg_set(priv, R_ADDRH, addr_hi); + + return 0; +} + +static const struct net_device_ops arc_emac_netdev_ops = { + .ndo_open = arc_emac_open, + .ndo_stop = arc_emac_stop, + .ndo_start_xmit = arc_emac_tx, + .ndo_set_mac_address = arc_emac_set_address, + .ndo_get_stats = arc_emac_stats, +}; + +static int arc_emac_probe(struct platform_device *pdev) +{ + struct resource res_regs, res_irq; + struct device_node *phy_node; + struct arc_emac_priv *priv; + struct net_device *ndev; + const char *mac_addr; + unsigned int id, clock_frequency; + int err; + + if (!pdev->dev.of_node) + return -ENODEV; + + /* Get PHY from device tree */ + phy_node = of_parse_phandle(pdev->dev.of_node, "phy", 0); + if (!phy_node) { + dev_err(&pdev->dev, "failed to retrieve phy description from device tree\n"); + return -ENODEV; + } + + /* Get EMAC registers base address from device tree */ + err = of_address_to_resource(pdev->dev.of_node, 0, &res_regs); + if (err) { + dev_err(&pdev->dev, "failed to retrieve registers base from device tree\n"); + return -ENODEV; + } + + /* Get CPU clock frequency from device tree */ + if (of_property_read_u32(pdev->dev.of_node, "clock-frequency", + &clock_frequency)) { + dev_err(&pdev->dev, "failed to retrieve from device tree\n"); + return -EINVAL; + } + + /* Get IRQ from device tree */ + err = of_irq_to_resource(pdev->dev.of_node, 0, &res_irq); + if (!err) { + dev_err(&pdev->dev, "failed to retrieve value from device tree\n"); + return -ENODEV; + } + + ndev = alloc_etherdev(sizeof(struct arc_emac_priv)); + if (!ndev) + return -ENOMEM; + + SET_NETDEV_DEV(ndev, &pdev->dev); + + ndev->netdev_ops = &arc_emac_netdev_ops; + ndev->ethtool_ops = &arc_emac_ethtool_ops; + ndev->watchdog_timeo = TX_TIMEOUT; + /* FIXME :: no multicast support yet */ + ndev->flags &= ~IFF_MULTICAST; + + priv = netdev_priv(ndev); + priv->dev = &pdev->dev; + priv->ndev = ndev; + + priv->regs = devm_ioremap_resource(&pdev->dev, &res_regs); + if (IS_ERR(priv->regs)) { + err = PTR_ERR(priv->regs); + goto out; + } + dev_dbg(&pdev->dev, "Registers base address is 0x%p\n", priv->regs); + + id = arc_reg_get(priv, R_ID); + + /* Check for EMAC revision 5 or 7, magic number */ + if (!(id == 0x0005fd02 || id == 0x0007fd02)) { + dev_err(&pdev->dev, "ARC EMAC not detected, id=0x%x\n", id); + err = -ENODEV; + goto out; + } + dev_info(&pdev->dev, "ARC EMAC detected with id: 0x%x\n", id); + + /* Set poll rate so that it polls every 1 ms */ + arc_reg_set(priv, R_POLLRATE, clock_frequency / 1000000); + + /* Get max speed of operation from device tree */ + if (of_property_read_u32(pdev->dev.of_node, "max-speed", + &priv->max_speed)) { + dev_err(&pdev->dev, "failed to retrieve from device tree\n"); + err = -EINVAL; + goto out; + } + + ndev->irq = res_irq.start; + dev_info(&pdev->dev, "IRQ is %d\n", ndev->irq); + + /* Register interrupt handler for device */ + err = devm_request_irq(&pdev->dev, ndev->irq, arc_emac_intr, 0, + ndev->name, ndev); + if (err) { + dev_err(&pdev->dev, "could not allocate IRQ\n"); + goto out; + } + + /* Get MAC address from device tree */ + mac_addr = of_get_mac_address(pdev->dev.of_node); + + if (!mac_addr || !is_valid_ether_addr(mac_addr)) + eth_hw_addr_random(ndev); + else + memcpy(ndev->dev_addr, mac_addr, ETH_ALEN); + + dev_info(&pdev->dev, "MAC address is now %pM\n", ndev->dev_addr); + + /* Do 1 allocation instead of 2 separate ones for Rx and Tx BD rings */ + priv->rxbd = dmam_alloc_coherent(&pdev->dev, RX_RING_SZ + TX_RING_SZ, + &priv->rxbd_dma, GFP_KERNEL); + + if (!priv->rxbd) { + dev_err(&pdev->dev, "failed to allocate data buffers\n"); + err = -ENOMEM; + goto out; + } + + priv->txbd = priv->rxbd + RX_BD_NUM; + + priv->txbd_dma = priv->rxbd_dma + RX_RING_SZ; + dev_dbg(&pdev->dev, "EMAC Device addr: Rx Ring [0x%x], Tx Ring[%x]\n", + (unsigned int)priv->rxbd_dma, (unsigned int)priv->txbd_dma); + + err = arc_mdio_probe(pdev, priv); + if (err) { + dev_err(&pdev->dev, "failed to probe MII bus\n"); + goto out; + } + + priv->phy_dev = of_phy_connect(ndev, phy_node, arc_emac_adjust_link, 0, + PHY_INTERFACE_MODE_MII); + if (!priv->phy_dev) { + dev_err(&pdev->dev, "of_phy_connect() failed\n"); + err = -ENODEV; + goto out; + } + + dev_info(&pdev->dev, "connected to %s phy with id 0x%x\n", + priv->phy_dev->drv->name, priv->phy_dev->phy_id); + + netif_napi_add(ndev, &priv->napi, arc_emac_poll, ARC_EMAC_NAPI_WEIGHT); + + err = register_netdev(ndev); + if (err) { + netif_napi_del(&priv->napi); + dev_err(&pdev->dev, "failed to register network device\n"); + goto out; + } + + return 0; + +out: + free_netdev(ndev); + return err; +} + +static int arc_emac_remove(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct arc_emac_priv *priv = netdev_priv(ndev); + + phy_disconnect(priv->phy_dev); + priv->phy_dev = NULL; + arc_mdio_remove(priv); + unregister_netdev(ndev); + netif_napi_del(&priv->napi); + free_netdev(ndev); + + return 0; +} + +static const struct of_device_id arc_emac_dt_ids[] = { + { .compatible = "snps,arc-emac" }, + { /* Sentinel */ } +}; +MODULE_DEVICE_TABLE(of, arc_emac_dt_ids); + +static struct platform_driver arc_emac_driver = { + .probe = arc_emac_probe, + .remove = arc_emac_remove, + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + .of_match_table = arc_emac_dt_ids, + }, +}; + +module_platform_driver(arc_emac_driver); + +MODULE_AUTHOR("Alexey Brodkin "); +MODULE_DESCRIPTION("ARC EMAC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c new file mode 100644 index 000000000000..26ba2423f33a --- /dev/null +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -0,0 +1,152 @@ +/* + * Copyright (C) 2004-2013 Synopsys, Inc. (www.synopsys.com) + * + * MDIO implementation for ARC EMAC + */ + +#include +#include +#include + +#include "emac.h" + +/* Number of seconds we wait for "MDIO complete" flag to appear */ +#define ARC_MDIO_COMPLETE_POLL_COUNT 1 + +/** + * arc_mdio_complete_wait - Waits until MDIO transaction is completed. + * @priv: Pointer to ARC EMAC private data structure. + * + * returns: 0 on success, -ETIMEDOUT on a timeout. + */ +static int arc_mdio_complete_wait(struct arc_emac_priv *priv) +{ + unsigned int i; + + for (i = 0; i < ARC_MDIO_COMPLETE_POLL_COUNT * 40; i++) { + unsigned int status = arc_reg_get(priv, R_STATUS); + + status &= MDIO_MASK; + + if (status) { + /* Reset "MDIO complete" flag */ + arc_reg_set(priv, R_STATUS, status); + return 0; + } + + msleep(25); + } + + return -ETIMEDOUT; +} + +/** + * arc_mdio_read - MDIO interface read function. + * @bus: Pointer to MII bus structure. + * @phy_addr: Address of the PHY device. + * @reg_num: PHY register to read. + * + * returns: The register contents on success, -ETIMEDOUT on a timeout. + * + * Reads the contents of the requested register from the requested PHY + * address. + */ +static int arc_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num) +{ + struct arc_emac_priv *priv = bus->priv; + unsigned int value; + int error; + + arc_reg_set(priv, R_MDIO, + 0x60020000 | (phy_addr << 23) | (reg_num << 18)); + + error = arc_mdio_complete_wait(priv); + if (error < 0) + return error; + + value = arc_reg_get(priv, R_MDIO) & 0xffff; + + dev_dbg(priv->dev, "arc_mdio_read(phy_addr=%i, reg_num=%x) = %x\n", + phy_addr, reg_num, value); + + return value; +} + +/** + * arc_mdio_write - MDIO interface write function. + * @bus: Pointer to MII bus structure. + * @phy_addr: Address of the PHY device. + * @reg_num: PHY register to write to. + * @value: Value to be written into the register. + * + * returns: 0 on success, -ETIMEDOUT on a timeout. + * + * Writes the value to the requested register. + */ +static int arc_mdio_write(struct mii_bus *bus, int phy_addr, + int reg_num, u16 value) +{ + struct arc_emac_priv *priv = bus->priv; + + dev_dbg(priv->dev, + "arc_mdio_write(phy_addr=%i, reg_num=%x, value=%x)\n", + phy_addr, reg_num, value); + + arc_reg_set(priv, R_MDIO, + 0x50020000 | (phy_addr << 23) | (reg_num << 18) | value); + + return arc_mdio_complete_wait(priv); +} + +/** + * arc_mdio_probe - MDIO probe function. + * @pdev: Pointer to platform device. + * @priv: Pointer to ARC EMAC private data structure. + * + * returns: 0 on success, -ENOMEM when mdiobus_alloc + * (to allocate memory for MII bus structure) fails. + * + * Sets up and registers the MDIO interface. + */ +int arc_mdio_probe(struct platform_device *pdev, struct arc_emac_priv *priv) +{ + struct mii_bus *bus; + int error; + + bus = mdiobus_alloc(); + if (!bus) + return -ENOMEM; + + priv->bus = bus; + bus->priv = priv; + bus->parent = priv->dev; + bus->name = "Synopsys MII Bus", + bus->read = &arc_mdio_read; + bus->write = &arc_mdio_write; + + snprintf(bus->id, MII_BUS_ID_SIZE, "%s", pdev->name); + + error = of_mdiobus_register(bus, pdev->dev.of_node); + if (error) { + dev_err(priv->dev, "cannot register MDIO bus %s\n", bus->name); + mdiobus_free(bus); + return error; + } + + return 0; +} + +/** + * arc_mdio_remove - MDIO remove function. + * @priv: Pointer to ARC EMAC private data structure. + * + * Unregisters the MDIO and frees any associate memory for MII bus. + */ +int arc_mdio_remove(struct arc_emac_priv *priv) +{ + mdiobus_unregister(priv->bus); + mdiobus_free(priv->bus); + priv->bus = NULL; + + return 0; +} -- cgit v1.2.3 From 2d48d67fa8cd129ea85ea02d91b4a793286866f8 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Mon, 24 Jun 2013 10:28:03 +0300 Subject: net: poll/select low latency socket support select/poll busy-poll support. Split sysctl value into two separate ones, one for read and one for poll. updated Documentation/sysctl/net.txt Add a new poll flag POLL_LL. When this flag is set, sock_poll will call sk_poll_ll if possible. sock_poll sets this flag in its return value to indicate to select/poll when a socket that can busy poll is found. When poll/select have nothing to report, call the low-level sock_poll again until we are out of time or we find something. Once the system call finds something, it stops setting POLL_LL, so it can return the result to the user ASAP. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 18 ++++++++++++++++-- fs/select.c | 34 +++++++++++++++++++++++++++++----- include/net/ll_poll.h | 35 ++++++++++++++++++++++------------- include/uapi/asm-generic/poll.h | 2 ++ net/core/sock.c | 2 +- net/core/sysctl_net_core.c | 8 ++++++++ net/socket.c | 14 +++++++++++++- 7 files changed, 91 insertions(+), 22 deletions(-) (limited to 'Documentation') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 5369879eafe2..e658bbfb641f 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -50,13 +50,27 @@ The maximum number of packets that kernel can handle on a NAPI interrupt, it's a Per-CPU variable. Default: 64 -low_latency_poll +low_latency_read ---------------- -Low latency busy poll timeout. (needs CONFIG_NET_LL_RX_POLL) +Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL) Approximate time in us to spin waiting for packets on the device queue. +This sets the default value of the SO_LL socket option. +Can be set or overridden per socket by setting socket option SO_LL. Recommended value is 50. May increase power usage. Default: 0 (off) +low_latency_poll +---------------- +Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL) +Approximate time in us to spin waiting for packets on the device queue. +Recommended value depends on the number of sockets you poll on. +For several sockets 50, for several hundreds 100. +For more than that you probably want to use epoll. +Note that only sockets with SO_LL set will be busy polled, so you want to either +selectively set SO_LL on those sockets or set sysctl.net.low_latency_read globally. +May increase power usage. +Default: 0 (off) + rmem_default ------------ diff --git a/fs/select.c b/fs/select.c index 8c1c96c27062..79b876eb91da 100644 --- a/fs/select.c +++ b/fs/select.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -384,9 +385,10 @@ get_max: #define POLLEX_SET (POLLPRI) static inline void wait_key_set(poll_table *wait, unsigned long in, - unsigned long out, unsigned long bit) + unsigned long out, unsigned long bit, + unsigned int ll_flag) { - wait->_key = POLLEX_SET; + wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) @@ -400,6 +402,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) poll_table *wait; int retval, i, timed_out = 0; unsigned long slack = 0; + unsigned int ll_flag = POLL_LL; + u64 ll_time = ll_end_time(); rcu_read_lock(); retval = max_select_fd(n, fds); @@ -422,6 +426,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; + bool can_ll = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; @@ -449,7 +454,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) f_op = f.file->f_op; mask = DEFAULT_POLLMASK; if (f_op && f_op->poll) { - wait_key_set(wait, in, out, bit); + wait_key_set(wait, in, out, + bit, ll_flag); mask = (*f_op->poll)(f.file, wait); } fdput(f); @@ -468,6 +474,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) retval++; wait->_qproc = NULL; } + if (mask & POLL_LL) + can_ll = true; + /* got something, stop busy polling */ + if (retval) + ll_flag = 0; } } if (res_in) @@ -486,6 +497,9 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) break; } + if (can_ll && can_poll_ll(ll_time)) + continue; + /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to @@ -717,7 +731,8 @@ struct poll_list { * pwait poll_table will be used by the fd-provided poll handler for waiting, * if pwait->_qproc is non-NULL. */ -static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait) +static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait, + bool *can_ll, unsigned int ll_flag) { unsigned int mask; int fd; @@ -731,7 +746,10 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait) mask = DEFAULT_POLLMASK; if (f.file->f_op && f.file->f_op->poll) { pwait->_key = pollfd->events|POLLERR|POLLHUP; + pwait->_key |= ll_flag; mask = f.file->f_op->poll(f.file, pwait); + if (mask & POLL_LL) + *can_ll = true; } /* Mask out unneeded events. */ mask &= pollfd->events | POLLERR | POLLHUP; @@ -750,6 +768,8 @@ static int do_poll(unsigned int nfds, struct poll_list *list, ktime_t expire, *to = NULL; int timed_out = 0, count = 0; unsigned long slack = 0; + unsigned int ll_flag = POLL_LL; + u64 ll_time = ll_end_time(); /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { @@ -762,6 +782,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list, for (;;) { struct poll_list *walk; + bool can_ll = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; @@ -776,9 +797,10 @@ static int do_poll(unsigned int nfds, struct poll_list *list, * this. They'll get immediately deregistered * when we break out and return. */ - if (do_pollfd(pfd, pt)) { + if (do_pollfd(pfd, pt, &can_ll, ll_flag)) { count++; pt->_qproc = NULL; + ll_flag = 0; } } } @@ -795,6 +817,8 @@ static int do_poll(unsigned int nfds, struct poll_list *list, if (count || timed_out) break; + if (can_ll && can_poll_ll(ll_time)) + continue; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to diff --git a/include/net/ll_poll.h b/include/net/ll_poll.h index fcc7c365cee5..5bf2b3a6129e 100644 --- a/include/net/ll_poll.h +++ b/include/net/ll_poll.h @@ -30,6 +30,7 @@ #ifdef CONFIG_NET_LL_RX_POLL struct napi_struct; +extern unsigned int sysctl_net_ll_read __read_mostly; extern unsigned int sysctl_net_ll_poll __read_mostly; /* return values from ndo_ll_poll */ @@ -38,17 +39,18 @@ extern unsigned int sysctl_net_ll_poll __read_mostly; /* we can use sched_clock() because we don't care much about precision * we only care that the average is bounded + * we don't mind a ~2.5% imprecision so <<10 instead of *1000 + * sk->sk_ll_usec is a u_int so this can't overflow */ -static inline u64 ll_end_time(struct sock *sk) +static inline u64 ll_sk_end_time(struct sock *sk) { - u64 end_time = ACCESS_ONCE(sk->sk_ll_usec); - - /* we don't mind a ~2.5% imprecision - * sk->sk_ll_usec is a u_int so this can't overflow - */ - end_time = (end_time << 10) + sched_clock(); + return ((u64)ACCESS_ONCE(sk->sk_ll_usec) << 10) + sched_clock(); +} - return end_time; +/* in poll/select we use the global sysctl_net_ll_poll value */ +static inline u64 ll_end_time(void) +{ + return ((u64)ACCESS_ONCE(sysctl_net_ll_poll) << 10) + sched_clock(); } static inline bool sk_valid_ll(struct sock *sk) @@ -62,10 +64,13 @@ static inline bool can_poll_ll(u64 end_time) return !time_after64(sched_clock(), end_time); } +/* when used in sock_poll() nonblock is known at compile time to be true + * so the loop and end_time will be optimized out + */ static inline bool sk_poll_ll(struct sock *sk, int nonblock) { + u64 end_time = nonblock ? 0 : ll_sk_end_time(sk); const struct net_device_ops *ops; - u64 end_time = ll_end_time(sk); struct napi_struct *napi; int rc = false; @@ -84,7 +89,6 @@ static inline bool sk_poll_ll(struct sock *sk, int nonblock) goto out; do { - rc = ops->ndo_ll_poll(napi); if (rc == LL_FLUSH_FAILED) @@ -95,8 +99,8 @@ static inline bool sk_poll_ll(struct sock *sk, int nonblock) NET_ADD_STATS_BH(sock_net(sk), LINUX_MIB_LOWLATENCYRXPACKETS, rc); - } while (skb_queue_empty(&sk->sk_receive_queue) - && can_poll_ll(end_time) && !nonblock); + } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) && + can_poll_ll(end_time)); rc = !skb_queue_empty(&sk->sk_receive_queue); out: @@ -118,7 +122,12 @@ static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) #else /* CONFIG_NET_LL_RX_POLL */ -static inline u64 ll_end_time(struct sock *sk) +static inline u64 sk_ll_end_time(struct sock *sk) +{ + return 0; +} + +static inline u64 ll_end_time(void) { return 0; } diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 9ce7f44aebd2..4aee586979ca 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -30,6 +30,8 @@ #define POLLFREE 0x4000 /* currently only for epoll */ +#define POLL_LL 0x8000 + struct pollfd { int fd; short events; diff --git a/net/core/sock.c b/net/core/sock.c index 1e744b12fda3..b6c619f4d47b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2307,7 +2307,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_LL_RX_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_ll_poll; + sk->sk_ll_usec = sysctl_net_ll_read; #endif /* diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 62702c2053de..afc677eadd93 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -306,6 +306,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "low_latency_read", + .data = &sysctl_net_ll_read, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +# #endif #endif /* CONFIG_NET */ { diff --git a/net/socket.c b/net/socket.c index 3eec3f76b49c..4da14cbd49b6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -107,6 +107,7 @@ #include #ifdef CONFIG_NET_LL_RX_POLL +unsigned int sysctl_net_ll_read __read_mostly; unsigned int sysctl_net_ll_poll __read_mostly; #endif @@ -1147,13 +1148,24 @@ EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ static unsigned int sock_poll(struct file *file, poll_table *wait) { + unsigned int ll_flag = 0; struct socket *sock; /* * We can't return errors to poll, so it's either yes or no. */ sock = file->private_data; - return sock->ops->poll(file, sock, wait); + + if (sk_valid_ll(sock->sk)) { + /* this socket can poll_ll so tell the system call */ + ll_flag = POLL_LL; + + /* once, only if requested by syscall */ + if (wait && (wait->_key & POLL_LL)) + sk_poll_ll(sock->sk, 1); + } + + return ll_flag | sock->ops->poll(file, sock, wait); } static int sock_mmap(struct file *file, struct vm_area_struct *vma) -- cgit v1.2.3 From 762375766143aba42e74713f8364b4953c40a354 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 24 Jun 2013 19:46:54 +0800 Subject: doc: fix some syntax errors in netlink mmap sample code Cc: Patrick McHardy Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- Documentation/networking/netlink_mmap.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt index e6088baf109d..5cc600587778 100644 --- a/Documentation/networking/netlink_mmap.txt +++ b/Documentation/networking/netlink_mmap.txt @@ -274,9 +274,9 @@ This example assumes some ring parameters of the ring setup are available. /* Get next frame header */ hdr = rx_ring + frame_offset; - if (hdr->nm_status == NL_MMAP_STATUS_VALID) + if (hdr->nm_status == NL_MMAP_STATUS_VALID) { /* Regular memory mapped frame */ - nlh = (void *hdr) + NL_MMAP_HDRLEN; + nlh = (void *)hdr + NL_MMAP_HDRLEN; len = hdr->nm_len; /* Release empty message immediately. May happen -- cgit v1.2.3 From d7d35c681fb4eae1fab3d93698e26a106ca7e79e Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Mon, 24 Jun 2013 11:49:33 +0200 Subject: bonding: doc: some details on backup slave arp validation Add some details to bonding documentation on how backup slave arp validation works. Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- Documentation/networking/bonding.txt | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'Documentation') diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index e7454fcc9176..adee3b4a75cb 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -303,6 +303,12 @@ arp_validate such a situation, validation of backup slaves must be disabled. + The validation of ARP requests on backup slaves is mainly + helping bonding to decide which slaves are more likely to + work in case of the active slave failure, it doesn't really + guarantee that the backup slave will work if it's selected + as the next active slave. + This option is useful in network configurations in which multiple bonding hosts are concurrently issuing ARPs to one or more targets beyond a common switch. Should the link between -- cgit v1.2.3 From 8599b52e14a1611dcb563289421bee76751f1d53 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Mon, 24 Jun 2013 11:49:34 +0200 Subject: bonding: add an option to fail when any of arp_ip_target is inaccessible Currently, we fail only when all of the ips in arp_ip_target are gone. However, in some situations we might need to fail if even one host from arp_ip_target becomes unavailable. All situations, obviously, rely on the idea that we need *completely* functional network, with all interfaces/addresses working correctly. One real world example might be: vlans on top on bond (hybrid port). If bond and vlans have ips assigned and we have their peers monitored via arp_ip_target - in case of switch misconfiguration (trunk/access port), slave driver malfunction or tagged/untagged traffic dropped on the way - we will be able to switch to another slave. Though any other configuration needs that if we need to have access to all arp_ip_targets. This patch adds this possibility by adding a new parameter - arp_all_targets (both as a module parameter and as a sysfs knob). It can be set to: 0 or any (the default) - which works exactly as it's working now - the slave is up if any of the arp_ip_targets are up. 1 or all - the slave is up if all of the arp_ip_targets are up. This parameter can be changed on the fly (via sysfs), and requires the mode to be active-backup and arp_validate to be enabled (it obeys the arp_validate config on which slaves to validate). Internally it's done through: 1) Add target_last_arp_rx[BOND_MAX_ARP_TARGETS] array to slave struct. It's an array of jiffies, meaning that slave->target_last_arp_rx[i] is the last time we've received arp from bond->params.arp_targets[i] on this slave. 2) If we successfully validate an arp from bond->params.arp_targets[i] in bond_validate_arp() - update the slave->target_last_arp_rx[i] with the current jiffies value. 3) When getting slave's last_rx via slave_last_rx(), we return the oldest time when we've received an arp from any address in bond->params.arp_targets[]. If the value of arp_all_targets == 0 - we still work the same way as before. Also, update the documentation to reflect the new parameter. v3->v4: Kill the forgotten rtnl_unlock(), rephrase the documentation part to be more clear, don't fail setting arp_all_targets if arp_validate is not set - it has no effect anyway but can be easier to set up. Also, print a warning if the last arp_ip_target is removed while the arp_interval is on, but not the arp_validate. v2->v3: Use _bh spinlock, remove useless rtnl_lock() and use jiffies for new arp_ip_target last arp, instead of slave_last_rx(). On bond_enslave(), use the same initialization value for target_last_arp_rx[] as is used for the default last_arp_rx, to avoid useless interface flaps. Also, instead of failing to remove the last arp_ip_target just print a warning - otherwise it might break existing scripts. v1->v2: Correctly handle adding/removing hosts in arp_ip_target - we need to shift/initialize all slave's target_last_arp_rx. Also, don't fail module loading on arp_all_targets misconfiguration, just disable it, and some minor style fixes. Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- Documentation/networking/bonding.txt | 19 +++++++++ drivers/net/bonding/bond_main.c | 33 ++++++++++++++- drivers/net/bonding/bond_sysfs.c | 79 +++++++++++++++++++++++++++++++----- drivers/net/bonding/bonding.h | 30 +++++++++++++- 4 files changed, 147 insertions(+), 14 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index adee3b4a75cb..87bbcfee2e06 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -321,6 +321,25 @@ arp_validate This option was added in bonding version 3.1.0. +arp_all_targets + + Specifies the quantity of arp_ip_targets that must be reachable + in order for the ARP monitor to consider a slave as being up. + This option affects only active-backup mode for slaves with + arp_validation enabled. + + Possible values are: + + any or 0 + + consider the slave up only when any of the arp_ip_targets + is reachable + + all or 1 + + consider the slave up only when all of the arp_ip_targets + are reachable + downdelay Specifies the time, in milliseconds, to wait before disabling diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d3a70c0d0edd..142d55dc526e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -104,6 +104,7 @@ static char *xmit_hash_policy; static int arp_interval = BOND_LINK_ARP_INTERV; static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; +static char *arp_all_targets; static char *fail_over_mac; static int all_slaves_active = 0; static struct bond_params bonding_defaults; @@ -166,6 +167,8 @@ module_param(arp_validate, charp, 0); MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; " "0 for none (default), 1 for active, " "2 for backup, 3 for all"); +module_param(arp_all_targets, charp, 0); +MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all"); module_param(fail_over_mac, charp, 0); MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to " "the same MAC; 0 for none (default), " @@ -216,6 +219,12 @@ const struct bond_parm_tbl xmit_hashtype_tbl[] = { { NULL, -1}, }; +const struct bond_parm_tbl arp_all_targets_tbl[] = { +{ "any", BOND_ARP_TARGETS_ANY}, +{ "all", BOND_ARP_TARGETS_ALL}, +{ NULL, -1}, +}; + const struct bond_parm_tbl arp_validate_tbl[] = { { "none", BOND_ARP_VALIDATE_NONE}, { "active", BOND_ARP_VALIDATE_ACTIVE}, @@ -1483,7 +1492,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) struct slave *new_slave = NULL; struct sockaddr addr; int link_reporting; - int res = 0; + int res = 0, i; if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && @@ -1712,6 +1721,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) new_slave->last_arp_rx = jiffies - (msecs_to_jiffies(bond->params.arp_interval) + 1); + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + new_slave->target_last_arp_rx[i] = new_slave->last_arp_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); @@ -2610,16 +2621,20 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { + int i; + if (!sip || !bond_has_this_ip(bond, tip)) { pr_debug("bva: sip %pI4 tip %pI4 not found\n", &sip, &tip); return; } - if (bond_get_targets_ip(bond->params.arp_targets, sip) == -1) { + i = bond_get_targets_ip(bond->params.arp_targets, sip); + if (i == -1) { pr_debug("bva: sip %pI4 not found in targets\n", &sip); return; } slave->last_arp_rx = jiffies; + slave->target_last_arp_rx[i] = jiffies; } static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, @@ -4409,6 +4424,7 @@ int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl) static int bond_check_params(struct bond_params *params) { int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; + int arp_all_targets_value; /* * Convert string parameters. @@ -4634,6 +4650,18 @@ static int bond_check_params(struct bond_params *params) } else arp_validate_value = 0; + arp_all_targets_value = 0; + if (arp_all_targets) { + arp_all_targets_value = bond_parse_parm(arp_all_targets, + arp_all_targets_tbl); + + if (arp_all_targets_value == -1) { + pr_err("Error: invalid arp_all_targets_value \"%s\"\n", + arp_all_targets); + arp_all_targets_value = 0; + } + } + if (miimon) { pr_info("MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { @@ -4698,6 +4726,7 @@ static int bond_check_params(struct bond_params *params) params->num_peer_notif = num_peer_notif; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; + params->arp_all_targets = arp_all_targets_value; params->updelay = updelay; params->downdelay = downdelay; params->use_carrier = use_carrier; diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index ece57f146a60..dc36a3d7d9e9 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -443,6 +443,44 @@ static ssize_t bonding_store_arp_validate(struct device *d, static DEVICE_ATTR(arp_validate, S_IRUGO | S_IWUSR, bonding_show_arp_validate, bonding_store_arp_validate); +/* + * Show and set arp_all_targets. + */ +static ssize_t bonding_show_arp_all_targets(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + int value = bond->params.arp_all_targets; + + return sprintf(buf, "%s %d\n", arp_all_targets_tbl[value].modename, + value); +} + +static ssize_t bonding_store_arp_all_targets(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bonding *bond = to_bond(d); + int new_value; + + new_value = bond_parse_parm(buf, arp_all_targets_tbl); + if (new_value < 0) { + pr_err("%s: Ignoring invalid arp_all_targets value %s\n", + bond->dev->name, buf); + return -EINVAL; + } + pr_info("%s: setting arp_all_targets to %s (%d).\n", + bond->dev->name, arp_all_targets_tbl[new_value].modename, + new_value); + + bond->params.arp_all_targets = new_value; + + return count; +} + +static DEVICE_ATTR(arp_all_targets, S_IRUGO | S_IWUSR, + bonding_show_arp_all_targets, bonding_store_arp_all_targets); /* * Show and store fail_over_mac. User only allowed to change the @@ -590,10 +628,11 @@ static ssize_t bonding_store_arp_targets(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - __be32 newtarget; - int i = 0, ret = -EINVAL; struct bonding *bond = to_bond(d); - __be32 *targets; + struct slave *slave; + __be32 newtarget, *targets; + unsigned long *targets_rx; + int ind, i, j, ret = -EINVAL; targets = bond->params.arp_targets; newtarget = in_aton(buf + 1); @@ -611,8 +650,8 @@ static ssize_t bonding_store_arp_targets(struct device *d, goto out; } - i = bond_get_targets_ip(targets, 0); /* first free slot */ - if (i == -1) { + ind = bond_get_targets_ip(targets, 0); /* first free slot */ + if (ind == -1) { pr_err("%s: ARP target table is full!\n", bond->dev->name); goto out; @@ -620,7 +659,12 @@ static ssize_t bonding_store_arp_targets(struct device *d, pr_info("%s: adding ARP target %pI4.\n", bond->dev->name, &newtarget); - targets[i] = newtarget; + /* not to race with bond_arp_rcv */ + write_lock_bh(&bond->lock); + bond_for_each_slave(bond, slave, i) + slave->target_last_arp_rx[ind] = jiffies; + targets[ind] = newtarget; + write_unlock_bh(&bond->lock); } else if (buf[0] == '-') { if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) { pr_err("%s: invalid ARP target %pI4 specified for removal\n", @@ -628,18 +672,32 @@ static ssize_t bonding_store_arp_targets(struct device *d, goto out; } - i = bond_get_targets_ip(targets, newtarget); - if (i == -1) { - pr_info("%s: unable to remove nonexistent ARP target %pI4.\n", + ind = bond_get_targets_ip(targets, newtarget); + if (ind == -1) { + pr_err("%s: unable to remove nonexistent ARP target %pI4.\n", bond->dev->name, &newtarget); goto out; } + if (ind == 0 && !targets[1] && bond->params.arp_interval) + pr_warn("%s: removing last arp target with arp_interval on\n", + bond->dev->name); + pr_info("%s: removing ARP target %pI4.\n", bond->dev->name, &newtarget); - for (; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) + + write_lock_bh(&bond->lock); + bond_for_each_slave(bond, slave, i) { + targets_rx = slave->target_last_arp_rx; + j = ind; + for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++) + targets_rx[j] = targets_rx[j+1]; + targets_rx[j] = 0; + } + for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) targets[i] = targets[i+1]; targets[i] = 0; + write_unlock_bh(&bond->lock); } else { pr_err("no command found in arp_ip_targets file for bond %s. Use + or -.\n", bond->dev->name); @@ -1623,6 +1681,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_mode.attr, &dev_attr_fail_over_mac.attr, &dev_attr_arp_validate.attr, + &dev_attr_arp_all_targets.attr, &dev_attr_arp_interval.attr, &dev_attr_arp_ip_target.attr, &dev_attr_downdelay.attr, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 486e532f77e4..3fb73cc8c34a 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -144,6 +144,7 @@ struct bond_params { u8 num_peer_notif; int arp_interval; int arp_validate; + int arp_all_targets; int use_carrier; int fail_over_mac; int updelay; @@ -179,6 +180,7 @@ struct slave { int delay; unsigned long jiffies; unsigned long last_arp_rx; + unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 new_link; u8 backup:1, /* indicates backup slave. Value corresponds with @@ -322,6 +324,9 @@ static inline bool bond_is_active_slave(struct slave *slave) #define BOND_FOM_ACTIVE 1 #define BOND_FOM_FOLLOW 2 +#define BOND_ARP_TARGETS_ANY 0 +#define BOND_ARP_TARGETS_ALL 1 + #define BOND_ARP_VALIDATE_NONE 0 #define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) @@ -334,11 +339,31 @@ static inline int slave_do_arp_validate(struct bonding *bond, return bond->params.arp_validate & (1 << bond_slave_state(slave)); } +/* Get the oldest arp which we've received on this slave for bond's + * arp_targets. + */ +static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, + struct slave *slave) +{ + int i = 1; + unsigned long ret = slave->target_last_arp_rx[0]; + + for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) + if (time_before(slave->target_last_arp_rx[i], ret)) + ret = slave->target_last_arp_rx[i]; + + return ret; +} + static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { - if (slave_do_arp_validate(bond, slave)) - return slave->last_arp_rx; + if (slave_do_arp_validate(bond, slave)) { + if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) + return slave_oldest_target_arp_rx(bond, slave); + else + return slave->last_arp_rx; + } return slave->dev->last_rx; } @@ -486,6 +511,7 @@ extern const struct bond_parm_tbl bond_lacp_tbl[]; extern const struct bond_parm_tbl bond_mode_tbl[]; extern const struct bond_parm_tbl xmit_hashtype_tbl[]; extern const struct bond_parm_tbl arp_validate_tbl[]; +extern const struct bond_parm_tbl arp_all_targets_tbl[]; extern const struct bond_parm_tbl fail_over_mac_tbl[]; extern const struct bond_parm_tbl pri_reselect_tbl[]; extern struct bond_parm_tbl ad_select_tbl[]; -- cgit v1.2.3 From 4d0c875dcc4923476f364e83912d134da2df224c Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Mon, 24 Jun 2013 22:44:41 +0300 Subject: ipvs: add sync_persist_mode flag Add sync_persist_mode flag to reduce sync traffic by syncing only persistent templates. Signed-off-by: Julian Anastasov Tested-by: Aleksey Chudov Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 13 +++++++++++++ include/net/ip_vs.h | 11 +++++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 7 +++++++ net/netfilter/ipvs/ip_vs_sync.c | 12 ++++++++++++ 4 files changed, 43 insertions(+) (limited to 'Documentation') diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 9573d0c48c6e..7a3c04729591 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -181,6 +181,19 @@ snat_reroute - BOOLEAN always be the same as the original route so it is an optimisation to disable snat_reroute and avoid the recalculation. +sync_persist_mode - INTEGER + default 0 + + Controls the synchronisation of connections when using persistence + + 0: All types of connections are synchronised + 1: Attempt to reduce the synchronisation traffic depending on + the connection type. For persistent services avoid synchronisation + for normal connections, do it only for persistence templates. + In such case, for TCP and SCTP it may need enabling sloppy_tcp and + sloppy_sctp flags on backup servers. For non-persistent services + such optimization is not applied, mode 0 is assumed. + sync_version - INTEGER default 1 diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e667df171003..f0d70f066f3d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -975,6 +975,7 @@ struct netns_ipvs { int sysctl_snat_reroute; int sysctl_sync_ver; int sysctl_sync_ports; + int sysctl_sync_persist_mode; unsigned long sysctl_sync_qlen_max; int sysctl_sync_sock_size; int sysctl_cache_bypass; @@ -1076,6 +1077,11 @@ static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) return ACCESS_ONCE(ipvs->sysctl_sync_ports); } +static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_sync_persist_mode; +} + static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs) { return ipvs->sysctl_sync_qlen_max; @@ -1139,6 +1145,11 @@ static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs) +{ + return 0; +} + static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs) { return IPVS_SYNC_QLEN_MAX; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index da035fc01eb2..c8148e487386 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1714,6 +1714,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = &proc_do_sync_ports, }, + { + .procname = "sync_persist_mode", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "sync_qlen_max", .maxlen = sizeof(unsigned long), @@ -3729,6 +3735,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_sync_ver; ipvs->sysctl_sync_ports = 1; tbl[idx++].data = &ipvs->sysctl_sync_ports; + tbl[idx++].data = &ipvs->sysctl_sync_persist_mode; ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32; tbl[idx++].data = &ipvs->sysctl_sync_qlen_max; ipvs->sysctl_sync_sock_size = 0; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 2fc66394d86d..f4484719f3e6 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -425,6 +425,16 @@ ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) return sb; } +/* Check if connection is controlled by persistence */ +static inline bool in_persistence(struct ip_vs_conn *cp) +{ + for (cp = cp->control; cp; cp = cp->control) { + if (cp->flags & IP_VS_CONN_F_TEMPLATE) + return true; + } + return false; +} + /* Check if conn should be synced. * pkts: conn packets, use sysctl_sync_threshold to avoid packet check * - (1) sync_refresh_period: reduce sync rate. Additionally, retry @@ -447,6 +457,8 @@ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, /* Check if we sync in current state */ if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE)) force = 0; + else if (unlikely(sysctl_sync_persist_mode(ipvs) && in_persistence(cp))) + return 0; else if (likely(cp->protocol == IPPROTO_TCP)) { if (!((1 << cp->state) & ((1 << IP_VS_TCP_S_ESTABLISHED) | -- cgit v1.2.3 From b7c4114b07bbacfe0aee1d04ad1ade9e42309620 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 10 Jun 2013 23:12:57 -0300 Subject: can: flexcan: Use a regulator to control the CAN transceiver Instead of using a GPIO to turn on/off the CAN transceiver, it is better to use a regulator as some systems may use a PMIC to power the CAN transceiver. Acked-by: Shawn Guo Signed-off-by: Fabio Estevam Signed-off-by: Marc Kleine-Budde --- .../devicetree/bindings/net/can/fsl-flexcan.txt | 2 + arch/arm/boot/dts/imx28-evk.dts | 12 ++++++ arch/arm/mach-mxs/mach-mxs.c | 50 +--------------------- drivers/net/can/flexcan.c | 25 +++++------ 4 files changed, 28 insertions(+), 61 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt index 8ff324eaa889..56d6cc336e1c 100644 --- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt +++ b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt @@ -16,6 +16,8 @@ Optional properties: - clock-frequency : The oscillator frequency driving the flexcan device +- xceiver-supply: Regulator that powers the CAN transceiver + Example: can@1c000 { diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts index 3637bf3b1d59..1f0d38d7b16f 100644 --- a/arch/arm/boot/dts/imx28-evk.dts +++ b/arch/arm/boot/dts/imx28-evk.dts @@ -155,12 +155,14 @@ can0: can@80032000 { pinctrl-names = "default"; pinctrl-0 = <&can0_pins_a>; + xceiver-supply = <®_can_3v3>; status = "okay"; }; can1: can@80034000 { pinctrl-names = "default"; pinctrl-0 = <&can1_pins_a>; + xceiver-supply = <®_can_3v3>; status = "okay"; }; }; @@ -319,6 +321,16 @@ gpio = <&gpio3 30 0>; enable-active-high; }; + + reg_can_3v3: can-3v3 { + compatible = "regulator-fixed"; + regulator-name = "can-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio2 13 0>; + enable-active-high; + }; + }; sound { diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index 5b62b6489d4b..97b8a44101cd 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -60,41 +59,6 @@ static inline void __mxs_togl(u32 mask, void __iomem *reg) __raw_writel(mask, reg + MXS_TOG_ADDR); } -/* - * MX28EVK_FLEXCAN_SWITCH is shared between both flexcan controllers - */ -#define MX28EVK_FLEXCAN_SWITCH MXS_GPIO_NR(2, 13) - -static int flexcan0_en, flexcan1_en; - -static void mx28evk_flexcan_switch(void) -{ - if (flexcan0_en || flexcan1_en) - gpio_set_value(MX28EVK_FLEXCAN_SWITCH, 1); - else - gpio_set_value(MX28EVK_FLEXCAN_SWITCH, 0); -} - -static void mx28evk_flexcan0_switch(int enable) -{ - flexcan0_en = enable; - mx28evk_flexcan_switch(); -} - -static void mx28evk_flexcan1_switch(int enable) -{ - flexcan1_en = enable; - mx28evk_flexcan_switch(); -} - -static struct flexcan_platform_data flexcan_pdata[2]; - -static struct of_dev_auxdata mxs_auxdata_lookup[] __initdata = { - OF_DEV_AUXDATA("fsl,imx28-flexcan", 0x80032000, NULL, &flexcan_pdata[0]), - OF_DEV_AUXDATA("fsl,imx28-flexcan", 0x80034000, NULL, &flexcan_pdata[1]), - { /* sentinel */ } -}; - #define OCOTP_WORD_OFFSET 0x20 #define OCOTP_WORD_COUNT 0x20 @@ -254,15 +218,6 @@ static void __init imx28_evk_init(void) mxs_saif_clkmux_select(MXS_DIGCTL_SAIF_CLKMUX_EXTMSTR0); } -static void __init imx28_evk_post_init(void) -{ - if (!gpio_request_one(MX28EVK_FLEXCAN_SWITCH, GPIOF_DIR_OUT, - "flexcan-switch")) { - flexcan_pdata[0].transceiver_switch = mx28evk_flexcan0_switch; - flexcan_pdata[1].transceiver_switch = mx28evk_flexcan1_switch; - } -} - static int apx4devkit_phy_fixup(struct phy_device *phy) { phy->dev_flags |= MICREL_PHY_50MHZ_CLK; @@ -374,13 +329,10 @@ static void __init mxs_machine_init(void) cfa10049_init(); of_platform_populate(NULL, of_default_bus_match_table, - mxs_auxdata_lookup, NULL); + NULL, NULL); if (of_machine_is_compatible("karo,tx28")) tx28_post_init(); - - if (of_machine_is_compatible("fsl,imx28-evk")) - imx28_evk_post_init(); } #define MX23_CLKCTRL_RESET_OFFSET 0x120 diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index f873b9f8d4d4..7b0be0910f4b 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -37,6 +36,7 @@ #include #include #include +#include #define DRV_NAME "flexcan" @@ -211,6 +211,7 @@ struct flexcan_priv { struct clk *clk_per; struct flexcan_platform_data *pdata; const struct flexcan_devtype_data *devtype_data; + struct regulator *reg_xceiver; }; static struct flexcan_devtype_data fsl_p1010_devtype_data = { @@ -258,15 +259,6 @@ static inline void flexcan_write(u32 val, void __iomem *addr) } #endif -/* - * Swtich transceiver on or off - */ -static void flexcan_transceiver_switch(const struct flexcan_priv *priv, int on) -{ - if (priv->pdata && priv->pdata->transceiver_switch) - priv->pdata->transceiver_switch(on); -} - static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv, u32 reg_esr) { @@ -799,7 +791,11 @@ static int flexcan_chip_start(struct net_device *dev) if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES) flexcan_write(0x0, ®s->rxfgmask); - flexcan_transceiver_switch(priv, 1); + if (priv->reg_xceiver) { + err = regulator_enable(priv->reg_xceiver); + if (err) + goto out; + } /* synchronize with the can bus */ reg_mcr = flexcan_read(®s->mcr); @@ -842,7 +838,8 @@ static void flexcan_chip_stop(struct net_device *dev) reg |= FLEXCAN_MCR_MDIS | FLEXCAN_MCR_HALT; flexcan_write(reg, ®s->mcr); - flexcan_transceiver_switch(priv, 0); + if (priv->reg_xceiver) + regulator_disable(priv->reg_xceiver); priv->can.state = CAN_STATE_STOPPED; return; @@ -1084,6 +1081,10 @@ static int flexcan_probe(struct platform_device *pdev) priv->pdata = pdev->dev.platform_data; priv->devtype_data = devtype_data; + priv->reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); + if (IS_ERR(priv->reg_xceiver)) + priv->reg_xceiver = NULL; + netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT); dev_set_drvdata(&pdev->dev, dev); -- cgit v1.2.3 From 1067964305df131ede2c08c2f3c9b3892640f1c6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Jun 2013 19:49:39 +0200 Subject: lib: vsprintf: add IPv4/v6 generic %p[Ii]S[pfs] format specifier In order to avoid making code that deals with printing both, IPv4 and IPv6 addresses, unnecessary complicated as for example ... if (sa.sa_family == AF_INET6) printk("... %pI6 ...", ..sin6_addr); else printk("... %pI4 ...", ..sin_addr.s_addr); ... it would be better to introduce a format specifier that can deal with those kind of situations internally; just as we have a "struct sockaddr" for generic mapping into "struct sockaddr_in" or "struct sockaddr_in6" as e.g. done in "union sctp_addr". Then, we could reduce the above statement into something like: printk("... %pIS ..", &sockaddr); In case our pointer is NULL, pointer() then deals with that already at an earlier point in time internally. While we're at it, support for both %piS/%pIS, where 'S' stands for sockaddr, comes (almost) for free. Additionally to that, postfix specifiers 'p', 'f' and 's' are supported as suggested and initially implemented in 2009 by Joe Perches [1]. Handling of those additional specifiers orientate on the initial RFC that was proposed. Also we support IPv6 compressed format specified by 'c' and various other IPv4 extensions as stated in the documentation part. Likely, there are many other areas than just SCTP in the kernel to make use of this extension as well. [1] http://patchwork.ozlabs.org/patch/31480/ Signed-off-by: Daniel Borkmann CC: Joe Perches CC: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller --- Documentation/printk-formats.txt | 32 ++++++++++ lib/vsprintf.c | 124 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 154 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index 3af5ae6c9c11..3e8cb73ac43c 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -121,6 +121,38 @@ IPv6 addresses: print a compressed IPv6 address as described by http://tools.ietf.org/html/rfc5952 +IPv4/IPv6 addresses (generic, with port, flowinfo, scope): + + %pIS 1.2.3.4 or 0001:0002:0003:0004:0005:0006:0007:0008 + %piS 001.002.003.004 or 00010002000300040005000600070008 + %pISc 1.2.3.4 or 1:2:3:4:5:6:7:8 + %pISpc 1.2.3.4:12345 or [1:2:3:4:5:6:7:8]:12345 + %p[Ii]S[pfschnbl] + + For printing an IP address without the need to distinguish whether it's + of type AF_INET or AF_INET6, a pointer to a valid 'struct sockaddr', + specified through 'IS' or 'iS', can be passed to this format specifier. + + The additional 'p', 'f', and 's' specifiers are used to specify port + (IPv4, IPv6), flowinfo (IPv6) and scope (IPv6). Ports have a ':' prefix, + flowinfo a '/' and scope a '%', each followed by the actual value. + + In case of an IPv6 address the compressed IPv6 address as described by + http://tools.ietf.org/html/rfc5952 is being used if the additional + specifier 'c' is given. The IPv6 address is surrounded by '[', ']' in + case of additional specifiers 'p', 'f' or 's' as suggested by + https://tools.ietf.org/html/draft-ietf-6man-text-addr-representation-07 + + In case of IPv4 addresses, the additional 'h', 'n', 'b', and 'l' + specifiers can be used as well and are ignored in case of an IPv6 + address. + + Further examples: + + %pISfc 1.2.3.4 or [1:2:3:4:5:6:7:8]/123456789 + %pISsc 1.2.3.4 or [1:2:3:4:5:6:7:8]%1234567890 + %pISpfc 1.2.3.4:12345 or [1:2:3:4:5:6:7:8]:12345/123456789 + UUID/GUID addresses: %pUb 00010203-0405-0607-0809-0a0b0c0d0e0f diff --git a/lib/vsprintf.c b/lib/vsprintf.c index e149c6416384..31febc0b70df 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -922,6 +922,103 @@ char *ip4_addr_string(char *buf, char *end, const u8 *addr, return string(buf, end, ip4_addr, spec); } +static noinline_for_stack +char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, + struct printf_spec spec, const char *fmt) +{ + bool have_p = false, have_s = false, have_f = false, have_c = false; + char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + + sizeof(":12345") + sizeof("/123456789") + + sizeof("%1234567890")]; + char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); + const u8 *addr = (const u8 *) &sa->sin6_addr; + char fmt6[2] = { fmt[0], '6' }; + u8 off = 0; + + fmt++; + while (isalpha(*++fmt)) { + switch (*fmt) { + case 'p': + have_p = true; + break; + case 'f': + have_f = true; + break; + case 's': + have_s = true; + break; + case 'c': + have_c = true; + break; + } + } + + if (have_p || have_s || have_f) { + *p = '['; + off = 1; + } + + if (fmt6[0] == 'I' && have_c) + p = ip6_compressed_string(ip6_addr + off, addr); + else + p = ip6_string(ip6_addr + off, addr, fmt6); + + if (have_p || have_s || have_f) + *p++ = ']'; + + if (have_p) { + *p++ = ':'; + p = number(p, pend, ntohs(sa->sin6_port), spec); + } + if (have_f) { + *p++ = '/'; + p = number(p, pend, ntohl(sa->sin6_flowinfo & + IPV6_FLOWINFO_MASK), spec); + } + if (have_s) { + *p++ = '%'; + p = number(p, pend, sa->sin6_scope_id, spec); + } + *p = '\0'; + + return string(buf, end, ip6_addr, spec); +} + +static noinline_for_stack +char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, + struct printf_spec spec, const char *fmt) +{ + bool have_p = false; + char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; + char *pend = ip4_addr + sizeof(ip4_addr); + const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; + char fmt4[3] = { fmt[0], '4', 0 }; + + fmt++; + while (isalpha(*++fmt)) { + switch (*fmt) { + case 'p': + have_p = true; + break; + case 'h': + case 'l': + case 'n': + case 'b': + fmt4[2] = *fmt; + break; + } + } + + p = ip4_string(ip4_addr, addr, fmt4); + if (have_p) { + *p++ = ':'; + p = number(p, pend, ntohs(sa->sin_port), spec); + } + *p = '\0'; + + return string(buf, end, ip4_addr, spec); +} + static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) @@ -1007,11 +1104,17 @@ int kptr_restrict __read_mostly; * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's + * [S][pfs] + * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to + * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) - * - '[Ii]4[hnbl]' IPv4 addresses in host, network, big or little endian order - * - 'I6c' for IPv6 addresses printed as specified by + * [S][pfs] + * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to + * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] + * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order + * - 'I[6S]c' for IPv6 addresses printed as specified by * http://tools.ietf.org/html/rfc5952 * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" @@ -1093,6 +1196,21 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); + case 'S': { + const union { + struct sockaddr raw; + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } *sa = ptr; + + switch (sa->raw.sa_family) { + case AF_INET: + return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); + case AF_INET6: + return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); + default: + return string(buf, end, "(invalid address)", spec); + }} } break; case 'U': @@ -1370,6 +1488,8 @@ qualifier: * %pI6 print an IPv6 address with colons * %pi6 print an IPv6 address without colons * %pI6c print an IPv6 address as specified by RFC 5952 + * %pIS depending on sa_family of 'struct sockaddr *' print IPv4/IPv6 address + * %piS depending on sa_family of 'struct sockaddr *' print IPv4/IPv6 address * %pU[bBlL] print a UUID/GUID in big or little endian using lower or upper * case. * %*ph[CDN] a variable-length hex string with a separator (supports up to 64 -- cgit v1.2.3 From 25c83b5c2e82560406d5265f42cd147f1eb441d0 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 4 Jul 2013 10:35:41 +0100 Subject: dt:net:stmmac: Add support to dwmac version 3.610 and 3.710 This patch adds dt support to dwmac version 3.610 and 3.710 these versions are integrated in STiH415 and STiH416 ARM A9 SOCs. To support these IP version, some of the device tree properties are extended. Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/stmmac.txt | 4 ++++ .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 26 ++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 060bbf098ef3..e1ddfcc46a4e 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -12,6 +12,10 @@ Required properties: property - phy-mode: String, operation mode of the PHY interface. Supported values are: "mii", "rmii", "gmii", "rgmii". +- snps,phy-addr phy address to connect to. +- snps,pbl Programmable Burst Length +- snps,fixed-burst Program the DMA to use the fixed burst mode +- snps,mixed-burst Program the DMA to use the mixed burst mode Optional properties: - mac-address: 6 bytes, mac address diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index adfb9a3ce6c5..03de76c7a177 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -34,12 +34,20 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) { struct device_node *np = pdev->dev.of_node; + struct stmmac_dma_cfg *dma_cfg; if (!np) return -ENODEV; *mac = of_get_mac_address(np); plat->interface = of_get_phy_mode(np); + + plat->bus_id = of_alias_get_id(np, "ethernet"); + if (plat->bus_id < 0) + plat->bus_id = 0; + + of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr); + plat->mdio_bus_data = devm_kzalloc(&pdev->dev, sizeof(struct stmmac_mdio_bus_data), GFP_KERNEL); @@ -56,6 +64,22 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, plat->pmt = 1; } + if (of_device_is_compatible(np, "snps,dwmac-3.610") || + of_device_is_compatible(np, "snps,dwmac-3.710")) { + plat->enh_desc = 1; + plat->bugged_jumbo = 1; + plat->force_sf_dma_mode = 1; + } + + dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); + if (!dma_cfg) + return -ENOMEM; + + plat->dma_cfg = dma_cfg; + of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl); + dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst"); + dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst"); + return 0; } #else @@ -228,7 +252,9 @@ static const struct dev_pm_ops stmmac_pltfr_pm_ops; static const struct of_device_id stmmac_dt_ids[] = { { .compatible = "st,spear600-gmac"}, + { .compatible = "snps,dwmac-3.610"}, { .compatible = "snps,dwmac-3.70a"}, + { .compatible = "snps,dwmac-3.710"}, { .compatible = "snps,dwmac"}, { /* sentinel */ } }; -- cgit v1.2.3 From 0e0764715d8116484d808f5b3985ca043080788e Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 4 Jul 2013 10:35:48 +0100 Subject: dt:net:stmmac: Add dt specific phy reset callback support. This patch adds phy reset callback support for stmmac driver via device trees. It adds three new properties to gmac device tree bindings to define the reset signal via gpio. With this patch users can conveniently pass reset gpio number with pre, pulse and post delay in micro secs via DTs. active low: _________ ____________ | | | | |_______________| active high: ________________ | | | | ________| |___________ Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/stmmac.txt | 6 +++ drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 48 ++++++++++++++++++++++- include/linux/stmmac.h | 4 ++ 3 files changed, 56 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index e1ddfcc46a4e..261c563b5f06 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -13,6 +13,12 @@ Required properties: - phy-mode: String, operation mode of the PHY interface. Supported values are: "mii", "rmii", "gmii", "rgmii". - snps,phy-addr phy address to connect to. +- snps,reset-gpio gpio number for phy reset. +- snps,reset-active-low boolean flag to indicate if phy reset is active low. +- snps,reset-delays-us is triplet of delays + The 1st cell is reset pre-delay in micro seconds. + The 2nd cell is reset pulse in micro seconds. + The 3rd cell is reset post-delay in micro seconds. - snps,pbl Programmable Burst Length - snps,fixed-burst Program the DMA to use the fixed burst mode - snps,mixed-burst Program the DMA to use the mixed burst mode diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index cc15039eaa47..fe7bc9903867 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -27,6 +27,9 @@ #include #include #include +#include +#include + #include #include "stmmac.h" @@ -131,10 +134,46 @@ static int stmmac_mdio_reset(struct mii_bus *bus) struct net_device *ndev = bus->priv; struct stmmac_priv *priv = netdev_priv(ndev); unsigned int mii_address = priv->hw->mii.addr; + struct stmmac_mdio_bus_data *data = priv->plat->mdio_bus_data; + +#ifdef CONFIG_OF + if (priv->device->of_node) { + int reset_gpio, active_low; + + if (data->reset_gpio < 0) { + struct device_node *np = priv->device->of_node; + if (!np) + return 0; + + data->reset_gpio = of_get_named_gpio(np, + "snps,reset-gpio", 0); + if (data->reset_gpio < 0) + return 0; + + data->active_low = of_property_read_bool(np, + "snps,reset-active-low"); + of_property_read_u32_array(np, + "snps,reset-delays-us", data->delays, 3); + } + + reset_gpio = data->reset_gpio; + active_low = data->active_low; + + if (!gpio_request(reset_gpio, "mdio-reset")) { + gpio_direction_output(reset_gpio, active_low ? 1 : 0); + udelay(data->delays[0]); + gpio_set_value(reset_gpio, active_low ? 0 : 1); + udelay(data->delays[1]); + gpio_set_value(reset_gpio, active_low ? 1 : 0); + udelay(data->delays[2]); + gpio_free(reset_gpio); + } + } +#endif - if (priv->plat->mdio_bus_data->phy_reset) { + if (data->phy_reset) { pr_debug("stmmac_mdio_reset: calling phy_reset\n"); - priv->plat->mdio_bus_data->phy_reset(priv->plat->bsp_priv); + data->phy_reset(priv->plat->bsp_priv); } /* This is a workaround for problems with the STE101P PHY. @@ -172,6 +211,11 @@ int stmmac_mdio_register(struct net_device *ndev) else irqlist = priv->mii_irq; +#ifdef CONFIG_OF + if (priv->device->of_node) + mdio_bus_data->reset_gpio = -1; +#endif + new_bus->name = "stmmac"; new_bus->read = &stmmac_mdio_read; new_bus->write = &stmmac_mdio_write; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c1b3ed3fb787..9e495d31516e 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -80,6 +80,10 @@ struct stmmac_mdio_bus_data { unsigned int phy_mask; int *irqs; int probed_phy_irq; +#ifdef CONFIG_OF + int reset_gpio, active_low; + u32 delays[3]; +#endif }; struct stmmac_dma_cfg { -- cgit v1.2.3 From cbf55001b2ddb814329735641be5d29b08c82b08 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Mon, 8 Jul 2013 16:20:34 +0300 Subject: net: rename low latency sockets functions to busy poll Rename functions in include/net/ll_poll.h to busy wait. Clarify documentation about expected power use increase. Rename POLL_LL to POLL_BUSY_LOOP. Add need_resched() testing to poll/select busy loops. Note, that in select and poll can_busy_poll is dynamic and is updated continuously to reflect the existence of supported sockets with valid queue information. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 12 +++++---- fs/select.c | 60 +++++++++++++++++++++++++---------------- include/net/ll_poll.h | 46 ++++++++++++++++--------------- include/uapi/asm-generic/poll.h | 2 +- net/core/datagram.c | 3 ++- net/ipv4/tcp.c | 6 ++--- net/socket.c | 12 ++++----- 7 files changed, 80 insertions(+), 61 deletions(-) (limited to 'Documentation') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index e658bbfb641f..7323b88e26be 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -53,22 +53,24 @@ Default: 64 low_latency_read ---------------- Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL) -Approximate time in us to spin waiting for packets on the device queue. +Approximate time in us to busy loop waiting for packets on the device queue. This sets the default value of the SO_LL socket option. -Can be set or overridden per socket by setting socket option SO_LL. -Recommended value is 50. May increase power usage. +Can be set or overridden per socket by setting socket option SO_LL, which is +the preferred method of enabling. +If you need to enable the feature globally via sysctl, a value of 50 is recommended. +Will increase power usage. Default: 0 (off) low_latency_poll ---------------- Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL) -Approximate time in us to spin waiting for packets on the device queue. +Approximate time in us to busy loop waiting for events. Recommended value depends on the number of sockets you poll on. For several sockets 50, for several hundreds 100. For more than that you probably want to use epoll. Note that only sockets with SO_LL set will be busy polled, so you want to either selectively set SO_LL on those sockets or set sysctl.net.low_latency_read globally. -May increase power usage. +Will increase power usage. Default: 0 (off) rmem_default diff --git a/fs/select.c b/fs/select.c index f28a58592725..25cac5faf6d6 100644 --- a/fs/select.c +++ b/fs/select.c @@ -402,9 +402,9 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) poll_table *wait; int retval, i, timed_out = 0; unsigned long slack = 0; - unsigned int ll_flag = ll_get_flag(); - u64 ll_start = ll_start_time(ll_flag); - u64 ll_time = ll_run_time(); + unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; + u64 busy_start = busy_loop_start_time(busy_flag); + u64 busy_end = busy_loop_end_time(); rcu_read_lock(); retval = max_select_fd(n, fds); @@ -427,7 +427,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; - bool can_ll = false; + bool can_busy_loop = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; @@ -456,7 +456,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) mask = DEFAULT_POLLMASK; if (f_op && f_op->poll) { wait_key_set(wait, in, out, - bit, ll_flag); + bit, busy_flag); mask = (*f_op->poll)(f.file, wait); } fdput(f); @@ -475,11 +475,18 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) retval++; wait->_qproc = NULL; } - if (mask & POLL_LL) - can_ll = true; /* got something, stop busy polling */ - if (retval) - ll_flag = 0; + if (retval) { + can_busy_loop = false; + busy_flag = 0; + + /* + * only remember a returned + * POLL_BUSY_LOOP if we asked for it + */ + } else if (busy_flag & mask) + can_busy_loop = true; + } } if (res_in) @@ -498,8 +505,9 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) break; } - /* only if on, have sockets with POLL_LL and not out of time */ - if (ll_flag && can_ll && can_poll_ll(ll_start, ll_time)) + /* only if found POLL_BUSY_LOOP sockets && not out of time */ + if (!need_resched() && can_busy_loop && + busy_loop_range(busy_start, busy_end)) continue; /* @@ -734,7 +742,8 @@ struct poll_list { * if pwait->_qproc is non-NULL. */ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait, - bool *can_ll, unsigned int ll_flag) + bool *can_busy_poll, + unsigned int busy_flag) { unsigned int mask; int fd; @@ -748,10 +757,10 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait, mask = DEFAULT_POLLMASK; if (f.file->f_op && f.file->f_op->poll) { pwait->_key = pollfd->events|POLLERR|POLLHUP; - pwait->_key |= ll_flag; + pwait->_key |= busy_flag; mask = f.file->f_op->poll(f.file, pwait); - if (mask & POLL_LL) - *can_ll = true; + if (mask & busy_flag) + *can_busy_poll = true; } /* Mask out unneeded events. */ mask &= pollfd->events | POLLERR | POLLHUP; @@ -770,9 +779,10 @@ static int do_poll(unsigned int nfds, struct poll_list *list, ktime_t expire, *to = NULL; int timed_out = 0, count = 0; unsigned long slack = 0; - unsigned int ll_flag = ll_get_flag(); - u64 ll_start = ll_start_time(ll_flag); - u64 ll_time = ll_run_time(); + unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; + u64 busy_start = busy_loop_start_time(busy_flag); + u64 busy_end = busy_loop_end_time(); + /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { @@ -785,7 +795,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list, for (;;) { struct poll_list *walk; - bool can_ll = false; + bool can_busy_loop = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; @@ -800,10 +810,13 @@ static int do_poll(unsigned int nfds, struct poll_list *list, * this. They'll get immediately deregistered * when we break out and return. */ - if (do_pollfd(pfd, pt, &can_ll, ll_flag)) { + if (do_pollfd(pfd, pt, &can_busy_loop, + busy_flag)) { count++; pt->_qproc = NULL; - ll_flag = 0; + /* found something, stop busy polling */ + busy_flag = 0; + can_busy_loop = false; } } } @@ -820,8 +833,9 @@ static int do_poll(unsigned int nfds, struct poll_list *list, if (count || timed_out) break; - /* only if on, have sockets with POLL_LL and not out of time */ - if (ll_flag && can_ll && can_poll_ll(ll_start, ll_time)) + /* only if found POLL_BUSY_LOOP sockets && not out of time */ + if (!need_resched() && can_busy_loop && + busy_loop_range(busy_start, busy_end)) continue; /* diff --git a/include/net/ll_poll.h b/include/net/ll_poll.h index 0d620ba19bc5..f14dd88dafc8 100644 --- a/include/net/ll_poll.h +++ b/include/net/ll_poll.h @@ -37,9 +37,9 @@ extern unsigned int sysctl_net_ll_poll __read_mostly; #define LL_FLUSH_FAILED -1 #define LL_FLUSH_BUSY -2 -static inline unsigned int ll_get_flag(void) +static inline bool net_busy_loop_on(void) { - return sysctl_net_ll_poll ? POLL_LL : 0; + return sysctl_net_ll_poll; } /* a wrapper to make debug_smp_processor_id() happy @@ -47,7 +47,7 @@ static inline unsigned int ll_get_flag(void) * we only care that the average is bounded */ #ifdef CONFIG_DEBUG_PREEMPT -static inline u64 ll_sched_clock(void) +static inline u64 busy_loop_sched_clock(void) { u64 rc; @@ -58,7 +58,7 @@ static inline u64 ll_sched_clock(void) return rc; } #else /* CONFIG_DEBUG_PREEMPT */ -static inline u64 ll_sched_clock(void) +static inline u64 busy_loop_sched_clock(void) { return sched_clock(); } @@ -67,7 +67,7 @@ static inline u64 ll_sched_clock(void) /* we don't mind a ~2.5% imprecision so <<10 instead of *1000 * sk->sk_ll_usec is a u_int so this can't overflow */ -static inline u64 ll_sk_run_time(struct sock *sk) +static inline u64 sk_busy_loop_end_time(struct sock *sk) { return (u64)ACCESS_ONCE(sk->sk_ll_usec) << 10; } @@ -75,27 +75,29 @@ static inline u64 ll_sk_run_time(struct sock *sk) /* in poll/select we use the global sysctl_net_ll_poll value * only call sched_clock() if enabled */ -static inline u64 ll_run_time(void) +static inline u64 busy_loop_end_time(void) { return (u64)ACCESS_ONCE(sysctl_net_ll_poll) << 10; } -/* if flag is not set we don't need to know the time */ -static inline u64 ll_start_time(unsigned int flag) +/* if flag is not set we don't need to know the time + * so we want to avoid a potentially expensive sched_clock() + */ +static inline u64 busy_loop_start_time(unsigned int flag) { - return flag ? ll_sched_clock() : 0; + return flag ? busy_loop_sched_clock() : 0; } -static inline bool sk_valid_ll(struct sock *sk) +static inline bool sk_can_busy_loop(struct sock *sk) { return sk->sk_ll_usec && sk->sk_napi_id && !need_resched() && !signal_pending(current); } /* careful! time_in_range64 will evaluate now twice */ -static inline bool can_poll_ll(u64 start_time, u64 run_time) +static inline bool busy_loop_range(u64 start_time, u64 run_time) { - u64 now = ll_sched_clock(); + u64 now = busy_loop_sched_clock(); return time_in_range64(now, start_time, start_time + run_time); } @@ -103,10 +105,10 @@ static inline bool can_poll_ll(u64 start_time, u64 run_time) /* when used in sock_poll() nonblock is known at compile time to be true * so the loop and end_time will be optimized out */ -static inline bool sk_poll_ll(struct sock *sk, int nonblock) +static inline bool sk_busy_loop(struct sock *sk, int nonblock) { - u64 start_time = ll_start_time(!nonblock); - u64 run_time = ll_sk_run_time(sk); + u64 start_time = busy_loop_start_time(!nonblock); + u64 end_time = sk_busy_loop_end_time(sk); const struct net_device_ops *ops; struct napi_struct *napi; int rc = false; @@ -137,7 +139,7 @@ static inline bool sk_poll_ll(struct sock *sk, int nonblock) LINUX_MIB_LOWLATENCYRXPACKETS, rc); } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) && - can_poll_ll(start_time, run_time)); + busy_loop_range(start_time, end_time)); rc = !skb_queue_empty(&sk->sk_receive_queue); out: @@ -158,27 +160,27 @@ static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) } #else /* CONFIG_NET_LL_RX_POLL */ -static inline unsigned long ll_get_flag(void) +static inline unsigned long net_busy_loop_on(void) { return 0; } -static inline u64 ll_start_time(unsigned int flag) +static inline u64 busy_loop_start_time(unsigned int flag) { return 0; } -static inline u64 ll_run_time(void) +static inline u64 busy_loop_end_time(void) { return 0; } -static inline bool sk_valid_ll(struct sock *sk) +static inline bool sk_can_busy_loop(struct sock *sk) { return false; } -static inline bool sk_poll_ll(struct sock *sk, int nonblock) +static inline bool sk_busy_poll(struct sock *sk, int nonblock) { return false; } @@ -191,7 +193,7 @@ static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) { } -static inline bool can_poll_ll(u64 start_time, u64 run_time) +static inline bool busy_loop_range(u64 start_time, u64 run_time) { return false; } diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 4aee586979ca..a9694982689f 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -30,7 +30,7 @@ #define POLLFREE 0x4000 /* currently only for epoll */ -#define POLL_LL 0x8000 +#define POLL_BUSY_LOOP 0x8000 struct pollfd { int fd; diff --git a/net/core/datagram.c b/net/core/datagram.c index 9cbaba98ce4c..6e9ab31e457e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -208,7 +208,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, } spin_unlock_irqrestore(&queue->lock, cpu_flags); - if (sk_valid_ll(sk) && sk_poll_ll(sk, flags & MSG_DONTWAIT)) + if (sk_can_busy_loop(sk) && + sk_busy_loop(sk, flags & MSG_DONTWAIT)) continue; /* User doesn't want to wait */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46ed9afd1f5e..15cbfa94bd8e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1554,9 +1554,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct sk_buff *skb; u32 urg_hole = 0; - if (sk_valid_ll(sk) && skb_queue_empty(&sk->sk_receive_queue) - && (sk->sk_state == TCP_ESTABLISHED)) - sk_poll_ll(sk, nonblock); + if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + (sk->sk_state == TCP_ESTABLISHED)) + sk_busy_loop(sk, nonblock); lock_sock(sk); diff --git a/net/socket.c b/net/socket.c index 4da14cbd49b6..45afa648364a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1148,7 +1148,7 @@ EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ static unsigned int sock_poll(struct file *file, poll_table *wait) { - unsigned int ll_flag = 0; + unsigned int busy_flag = 0; struct socket *sock; /* @@ -1156,16 +1156,16 @@ static unsigned int sock_poll(struct file *file, poll_table *wait) */ sock = file->private_data; - if (sk_valid_ll(sock->sk)) { + if (sk_can_busy_loop(sock->sk)) { /* this socket can poll_ll so tell the system call */ - ll_flag = POLL_LL; + busy_flag = POLL_BUSY_LOOP; /* once, only if requested by syscall */ - if (wait && (wait->_key & POLL_LL)) - sk_poll_ll(sock->sk, 1); + if (wait && (wait->_key & POLL_BUSY_LOOP)) + sk_busy_loop(sock->sk, 1); } - return ll_flag | sock->ops->poll(file, sock, wait); + return busy_flag | sock->ops->poll(file, sock, wait); } static int sock_mmap(struct file *file, struct vm_area_struct *vma) -- cgit v1.2.3 From b78ba72cda78314c11ac8f47617240bc8d0e89da Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 9 Jul 2013 10:22:31 +0200 Subject: Documentation: Fix references to defunct linux-net@vger.kernel.org linux-net@vger.kernel.org was replaced by netdev@oss.sgi.com was replaced by netdev@vger.kernel.org. Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- Documentation/networking/arcnet.txt | 7 ++++--- Documentation/networking/vortex.txt | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/arcnet.txt b/Documentation/networking/arcnet.txt index 9ff579502151..aff97f47c05c 100644 --- a/Documentation/networking/arcnet.txt +++ b/Documentation/networking/arcnet.txt @@ -70,9 +70,10 @@ list, mail to linux-arcnet@tichy.ch.uj.edu.pl. There are archives of the mailing list at: http://epistolary.org/mailman/listinfo.cgi/arcnet -The people on linux-net@vger.kernel.org have also been known to be very -helpful, especially when we're talking about ALPHA Linux kernels that may or -may not work right in the first place. +The people on linux-net@vger.kernel.org (now defunct, replaced by +netdev@vger.kernel.org) have also been known to be very helpful, especially +when we're talking about ALPHA Linux kernels that may or may not work right +in the first place. Other Drivers and Info diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt index b4038ffb3bc5..9a8041dcbb53 100644 --- a/Documentation/networking/vortex.txt +++ b/Documentation/networking/vortex.txt @@ -359,7 +359,7 @@ steps you should take: - OK, it's a driver problem. You need to generate a report. Typically this is an email to the - maintainer and/or linux-net@vger.kernel.org. The maintainer's + maintainer and/or netdev@vger.kernel.org. The maintainer's email address will be in the driver source or in the MAINTAINERS file. - The contents of your report will vary a lot depending upon the -- cgit v1.2.3