diff options
author | Jeff Garzik <jeff@garzik.org> | 2006-06-08 15:56:17 -0400 |
---|---|---|
committer | Jeff Garzik <jeff@garzik.org> | 2006-06-08 15:56:17 -0400 |
commit | cac925a4aab1b7233d3beb591f53498816058a08 (patch) | |
tree | a800537068aa05fd426ff44b8efd52d66e6d2051 | |
parent | bcd618e4eac6fbf82de05d23c15ecb694c62b8af (diff) | |
parent | 6224e01dccf2543a8f8b4d825baf1510c79c2878 (diff) |
Merge branch 'upstream' of git://lost.foo-projects.org/~ahkok/git/netdev-2.6 into tmp
-rw-r--r-- | Documentation/networking/bonding.txt | 323 | ||||
-rw-r--r-- | drivers/net/e100.c | 75 | ||||
-rw-r--r-- | drivers/net/e1000/e1000_main.c | 114 |
3 files changed, 417 insertions, 95 deletions
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 8d8b4e5ea18..afac780445c 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -1,7 +1,7 @@ Linux Ethernet Bonding Driver HOWTO - Latest update: 21 June 2005 + Latest update: 24 April 2006 Initial release : Thomas Davis <tadavis at lbl.gov> Corrections, HA extensions : 2000/10/03-15 : @@ -12,6 +12,8 @@ Corrections, HA extensions : 2000/10/03-15 : - Jay Vosburgh <fubar at us dot ibm dot com> Reorganized and updated Feb 2005 by Jay Vosburgh +Added Sysfs information: 2006/04/24 + - Mitch Williams <mitch.a.williams at intel.com> Introduction ============ @@ -38,61 +40,62 @@ Table of Contents 2. Bonding Driver Options 3. Configuring Bonding Devices -3.1 Configuration with sysconfig support -3.1.1 Using DHCP with sysconfig -3.1.2 Configuring Multiple Bonds with sysconfig -3.2 Configuration with initscripts support -3.2.1 Using DHCP with initscripts -3.2.2 Configuring Multiple Bonds with initscripts -3.3 Configuring Bonding Manually +3.1 Configuration with Sysconfig Support +3.1.1 Using DHCP with Sysconfig +3.1.2 Configuring Multiple Bonds with Sysconfig +3.2 Configuration with Initscripts Support +3.2.1 Using DHCP with Initscripts +3.2.2 Configuring Multiple Bonds with Initscripts +3.3 Configuring Bonding Manually with Ifenslave 3.3.1 Configuring Multiple Bonds Manually +3.4 Configuring Bonding Manually via Sysfs -5. Querying Bonding Configuration -5.1 Bonding Configuration -5.2 Network Configuration +4. Querying Bonding Configuration +4.1 Bonding Configuration +4.2 Network Configuration -6. Switch Configuration +5. Switch Configuration -7. 802.1q VLAN Support +6. 802.1q VLAN Support -8. Link Monitoring -8.1 ARP Monitor Operation -8.2 Configuring Multiple ARP Targets -8.3 MII Monitor Operation +7. Link Monitoring +7.1 ARP Monitor Operation +7.2 Configuring Multiple ARP Targets +7.3 MII Monitor Operation -9. Potential Trouble Sources -9.1 Adventures in Routing -9.2 Ethernet Device Renaming -9.3 Painfully Slow Or No Failed Link Detection By Miimon +8. Potential Trouble Sources +8.1 Adventures in Routing +8.2 Ethernet Device Renaming +8.3 Painfully Slow Or No Failed Link Detection By Miimon -10. SNMP agents +9. SNMP agents -11. Promiscuous mode +10. Promiscuous mode -12. Configuring Bonding for High Availability -12.1 High Availability in a Single Switch Topology -12.2 High Availability in a Multiple Switch Topology -12.2.1 HA Bonding Mode Selection for Multiple Switch Topology -12.2.2 HA Link Monitoring for Multiple Switch Topology +11. Configuring Bonding for High Availability +11.1 High Availability in a Single Switch Topology +11.2 High Availability in a Multiple Switch Topology +11.2.1 HA Bonding Mode Selection for Multiple Switch Topology +11.2.2 HA Link Monitoring for Multiple Switch Topology -13. Configuring Bonding for Maximum Throughput -13.1 Maximum Throughput in a Single Switch Topology -13.1.1 MT Bonding Mode Selection for Single Switch Topology -13.1.2 MT Link Monitoring for Single Switch Topology -13.2 Maximum Throughput in a Multiple Switch Topology -13.2.1 MT Bonding Mode Selection for Multiple Switch Topology -13.2.2 MT Link Monitoring for Multiple Switch Topology +12. Configuring Bonding for Maximum Throughput +12.1 Maximum Throughput in a Single Switch Topology +12.1.1 MT Bonding Mode Selection for Single Switch Topology +12.1.2 MT Link Monitoring for Single Switch Topology +12.2 Maximum Throughput in a Multiple Switch Topology +12.2.1 MT Bonding Mode Selection for Multiple Switch Topology +12.2.2 MT Link Monitoring for Multiple Switch Topology -14. Switch Behavior Issues -14.1 Link Establishment and Failover Delays -14.2 Duplicated Incoming Packets +13. Switch Behavior Issues +13.1 Link Establishment and Failover Delays +13.2 Duplicated Incoming Packets -15. Hardware Specific Considerations -15.1 IBM BladeCenter +14. Hardware Specific Considerations +14.1 IBM BladeCenter -16. Frequently Asked Questions +15. Frequently Asked Questions -17. Resources and Links +16. Resources and Links 1. Bonding Driver Installation @@ -156,6 +159,9 @@ 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, you do not need +to use ifenslave. 2. Bonding Driver Options ========================= @@ -270,7 +276,7 @@ mode In bonding version 2.6.2 or later, when a failover occurs in active-backup mode, bonding will issue one or more gratuitous ARPs on the newly active slave. - One gratutious ARP is issued for the bonding master + One gratuitous ARP is issued for the bonding master interface and each VLAN interfaces configured above it, provided that the interface has at least one IP address configured. Gratuitous ARPs issued for VLAN @@ -377,7 +383,7 @@ mode When a link is reconnected or a new slave joins the bond the receive traffic is redistributed among all active slaves in the bond by initiating ARP Replies - with the selected mac address to each of the + with the selected MAC address to each of the clients. The updelay parameter (detailed below) must be set to a value equal or greater than the switch's forwarding delay so that the ARP Replies sent to the @@ -498,11 +504,12 @@ not exist, and the layer2 policy is the only policy. 3. Configuring Bonding Devices ============================== - There are, essentially, two methods for configuring bonding: -with support from the distro's network initialization scripts, and -without. Distros generally use one of two packages for the network -initialization scripts: initscripts or sysconfig. Recent versions of -these packages have support for bonding, while older versions do not. + You can configure bonding using either your distro's network +initialization scripts, or manually using either ifenslave or the +sysfs interface. Distros generally use one of two packages for the +network initialization scripts: initscripts or sysconfig. Recent +versions of these packages have support for bonding, while older +versions do not. We will first describe the options for configuring bonding for distros using versions of initscripts and sysconfig with full or @@ -530,7 +537,7 @@ $ grep ifenslave /sbin/ifup If this returns any matches, then your initscripts or sysconfig has support for bonding. -3.1 Configuration with sysconfig support +3.1 Configuration with Sysconfig Support ---------------------------------------- This section applies to distros using a version of sysconfig @@ -538,7 +545,7 @@ with bonding support, for example, SuSE Linux Enterprise Server 9. SuSE SLES 9's networking configuration system does support bonding, however, at this writing, the YaST system configuration -frontend does not provide any means to work with bonding devices. +front end does not provide any means to work with bonding devices. Bonding devices can be managed by hand, however, as follows. First, if they have not already been configured, configure the @@ -660,7 +667,7 @@ format can be found in an example ifcfg template file: Note that the template does not document the various BONDING_ settings described above, but does describe many of the other options. -3.1.1 Using DHCP with sysconfig +3.1.1 Using DHCP with Sysconfig ------------------------------- Under sysconfig, configuring a device with BOOTPROTO='dhcp' @@ -670,7 +677,7 @@ attempt to obtain the device address from DHCP prior to adding any of the slave devices. Without active slaves, the DHCP requests are not sent to the network. -3.1.2 Configuring Multiple Bonds with sysconfig +3.1.2 Configuring Multiple Bonds with Sysconfig ----------------------------------------------- The sysconfig network initialization system is capable of @@ -685,7 +692,7 @@ ifcfg-bondX files. options in the ifcfg-bondX file, it is not necessary to add them to the system /etc/modules.conf or /etc/modprobe.conf configuration file. -3.2 Configuration with initscripts support +3.2 Configuration with Initscripts Support ------------------------------------------ This section applies to distros using a version of initscripts @@ -756,7 +763,7 @@ options for your configuration. will restart the networking subsystem and your bond link should be now up and running. -3.2.1 Using DHCP with initscripts +3.2.1 Using DHCP with Initscripts --------------------------------- Recent versions of initscripts (the version supplied with @@ -768,7 +775,7 @@ above, except replace the line "BOOTPROTO=none" with "BOOTPROTO=dhcp" and add a line consisting of "TYPE=Bonding". Note that the TYPE value is case sensitive. -3.2.2 Configuring Multiple Bonds with initscripts +3.2.2 Configuring Multiple Bonds with Initscripts ------------------------------------------------- At this writing, the initscripts package does not directly @@ -784,8 +791,8 @@ Fedora Core kernels, and has been seen on RHEL 4 as well. On kernels exhibiting this problem, it will be impossible to configure multiple bonds with differing parameters. -3.3 Configuring Bonding Manually --------------------------------- +3.3 Configuring Bonding Manually with Ifenslave +----------------------------------------------- This section applies to distros whose network initialization scripts (the sysconfig or initscripts package) do not have specific @@ -889,11 +896,139 @@ install bond1 /sbin/modprobe --ignore-install bonding -o bond1 \ This may be repeated any number of times, specifying a new and unique name in place of bond1 for each subsequent instance. +3.4 Configuring Bonding Manually via Sysfs +------------------------------------------ + + Starting with version 3.0, Channel Bonding may be configured +via the sysfs interface. This interface allows dynamic configuration +of all bonds in the system without unloading the module. It also +allows for adding and removing bonds at runtime. Ifenslave is no +longer required, though it is still supported. + + Use of the sysfs interface allows you to use multiple bonds +with different configurations without having to reload the module. +It also allows you to use multiple, differently configured bonds when +bonding is compiled into the kernel. + + You must have the sysfs filesystem mounted to configure +bonding this way. The examples in this document assume that you +are using the standard mount point for sysfs, e.g. /sys. If your +sysfs filesystem is mounted elsewhere, you will need to adjust the +example paths accordingly. + +Creating and Destroying Bonds +----------------------------- +To add a new bond foo: +# echo +foo > /sys/class/net/bonding_masters + +To remove an existing bond bar: +# echo -bar > /sys/class/net/bonding_masters + +To show all existing bonds: +# cat /sys/class/net/bonding_masters + +NOTE: due to 4K size limitation of sysfs files, this list may be +truncated if you have more than a few hundred bonds. This is unlikely +to occur under normal operating conditions. + +Adding and Removing Slaves +-------------------------- + Interfaces may be enslaved to a bond using the file +/sys/class/net/<bond>/bonding/slaves. The semantics for this file +are the same as for the bonding_masters file. + +To enslave interface eth0 to bond bond0: +# ifconfig bond0 up +# echo +eth0 > /sys/class/net/bond0/bonding/slaves + +To free slave eth0 from bond bond0: +# echo -eth0 > /sys/class/net/bond0/bonding/slaves + + NOTE: The bond must be up before slaves can be added. All +slaves are freed when the interface is brought down. + + When an interface is enslaved to a bond, symlinks between the +two are created in the sysfs filesystem. In this case, you would get +/sys/class/net/bond0/slave_eth0 pointing to /sys/class/net/eth0, and +/sys/class/net/eth0/master pointing to /sys/class/net/bond0. + + This means that you can tell quickly whether or not an +interface is enslaved by looking for the master symlink. Thus: +# echo -eth0 > /sys/class/net/eth0/master/bonding/slaves +will free eth0 from whatever bond it is enslaved to, regardless of +the name of the bond interface. + +Changing a Bond's Configuration +------------------------------- + Each bond may be configured individually by manipulating the +files located in /sys/class/net/<bond name>/bonding + + The names of these files correspond directly with the command- +line parameters described elsewhere in in this file, and, with the +exception of arp_ip_target, they accept the same values. To see the +current setting, simply cat the appropriate file. + + A few examples will be given here; for specific usage +guidelines for each parameter, see the appropriate section in this +document. + +To configure bond0 for balance-alb mode: +# ifconfig bond0 down +# echo 6 > /sys/class/net/bond0/bonding/mode + - or - +# echo balance-alb > /sys/class/net/bond0/bonding/mode + NOTE: The bond interface must be down before the mode can be +changed. + +To enable MII monitoring on bond0 with a 1 second interval: +# echo 1000 > /sys/class/net/bond0/bonding/miimon + NOTE: If ARP monitoring is enabled, it will disabled when MII +monitoring is enabled, and vice-versa. + +To add ARP targets: +# echo +192.168.0.100 > /sys/class/net/bond0/bonding/arp_ip_target +# echo +192.168.0.101 > /sys/class/net/bond0/bonding/arp_ip_target + NOTE: up to 10 target addresses may be specified. + +To remove an ARP target: +# echo -192.168.0.100 > /sys/class/net/bond0/bonding/arp_ip_target + +Example Configuration +--------------------- + We begin with the same example that is shown in section 3.3, +executed with sysfs, and without using ifenslave. + + To make a simple bond of two e100 devices (presumed to be eth0 +and eth1), and have it persist across reboots, edit the appropriate +file (/etc/init.d/boot.local or /etc/rc.d/rc.local), and add the +following: + +modprobe bonding +modprobe e100 +echo balance-alb > /sys/class/net/bond0/bonding/mode +ifconfig bond0 192.168.1.1 netmask 255.255.255.0 up +echo 100 > /sys/class/net/bond0/bonding/miimon +echo +eth0 > /sys/class/net/bond0/bonding/slaves +echo +eth1 > /sys/class/net/bond0/bonding/slaves + + To add a second bond, with two e1000 interfaces in +active-backup mode, using ARP monitoring, add the following lines to +your init script: + +modprobe e1000 +echo +bond1 > /sys/class/net/bonding_masters +echo active-backup > /sys/class/net/bond1/bonding/mode +ifconfig bond1 192.168.2.1 netmask 255.255.255.0 up +echo +192.168.2.100 /sys/class/net/bond1/bonding/arp_ip_target +echo 2000 > /sys/class/net/bond1/bonding/arp_interval +echo +eth2 > /sys/class/net/bond1/bonding/slaves +echo +eth3 > /sys/class/net/bond1/bonding/slaves + -5. Querying Bonding Configuration +4. Querying Bonding Configuration ================================= -5.1 Bonding Configuration +4.1 Bonding Configuration ------------------------- Each bonding device has a read-only file residing in the @@ -923,7 +1058,7 @@ generally as follows: The precise format and contents will change depending upon the bonding configuration, state, and version of the bonding driver. -5.2 Network configuration +4.2 Network configuration ------------------------- The network configuration can be inspected using the ifconfig @@ -958,7 +1093,7 @@ eth1 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 collisions:0 txqueuelen:100 Interrupt:9 Base address:0x1400 -6. Switch Configuration +5. Switch Configuration ======================= For this section, "switch" refers to whatever system the @@ -991,7 +1126,7 @@ transmit policy for an EtherChannel group; all three will interoperate with another EtherChannel group. -7. 802.1q VLAN Support +6. 802.1q VLAN Support ====================== It is possible to configure VLAN devices over a bond interface @@ -1042,7 +1177,7 @@ underlying device -- i.e. the bonding interface -- to promiscuous mode, which might not be what you want. -8. Link Monitoring +7. Link Monitoring ================== The bonding driver at present supports two schemes for @@ -1053,7 +1188,7 @@ monitor. bonding driver itself, it is not possible to enable both ARP and MII monitoring simultaneously. -8.1 ARP Monitor Operation +7.1 ARP Monitor Operation ------------------------- The ARP monitor operates as its name suggests: it sends ARP @@ -1071,7 +1206,7 @@ those slaves will stay down. If networking monitoring (tcpdump, etc) shows the ARP requests and replies on the network, then it may be that your device driver is not updating last_rx and trans_start. -8.2 Configuring Multiple ARP Targets +7.2 Configuring Multiple ARP Targets ------------------------------------ While ARP monitoring can be done with just one target, it can @@ -1094,7 +1229,7 @@ alias bond0 bonding options bond0 arp_interval=60 arp_ip_target=192.168.0.100 -8.3 MII Monitor Operation +7.3 MII Monitor Operation ------------------------- The MII monitor monitors only the carrier state of the local @@ -1120,14 +1255,14 @@ does not support or had some error in processing both the MII register and ethtool requests), then the MII monitor will assume the link is up. -9. Potential Sources of Trouble +8. Potential Sources of Trouble =============================== -9.1 Adventures in Routing +8.1 Adventures in Routing ------------------------- When bonding is configured, it is important that the slave -devices not have routes that supercede routes of the master (or, +devices not have routes that supersede routes of the master (or, generally, not have routes at all). For example, suppose the bonding device bond0 has two slaves, eth0 and eth1, and the routing table is as follows: @@ -1154,11 +1289,11 @@ by the state of the routing table. The solution here is simply to insure that slaves do not have routes of their own, and if for some reason they must, those routes do -not supercede routes of their master. This should generally be the +not supersede routes of their master. This should generally be the case, but unusual configurations or errant manual or automatic static route additions may cause trouble. -9.2 Ethernet Device Renaming +8.2 Ethernet Device Renaming ---------------------------- On systems with network configuration scripts that do not @@ -1207,7 +1342,7 @@ modprobe with --ignore-install to cause the normal action to then take place. Full documentation on this can be found in the modprobe.conf and modprobe manual pages. -9.3. Painfully Slow Or No Failed Link Detection By Miimon +8.3. Painfully Slow Or No Failed Link Detection By Miimon --------------------------------------------------------- By default, bonding enables the use_carrier option, which @@ -1235,7 +1370,7 @@ carrier state. It has no way to determine the state of devices on or beyond other ports of a switch, or if a switch is refusing to pass traffic while still maintaining carrier on. -10. SNMP agents +9. SNMP agents =============== If running SNMP agents, the bonding driver should be loaded @@ -1281,7 +1416,7 @@ ifDescr, the association between the IP address and IfIndex remains and SNMP functions such as Interface_Scan_Next will report that association. -11. Promiscuous mode +10. Promiscuous mode ==================== When running network monitoring tools, e.g., tcpdump, it is @@ -1308,7 +1443,7 @@ sending to peers that are unassigned or if the load is unbalanced. the active slave changes (e.g., due to a link failure), the promiscuous setting will be propagated to the new active slave. -12. Configuring Bonding for High Availability +11. Configuring Bonding for High Availability ============================================= High Availability refers to configurations that provide @@ -1318,7 +1453,7 @@ goal is to provide the maximum availability of network connectivity (i.e., the network always works), even though other configurations could provide higher throughput. -12.1 High Availability in a Single Switch Topology +11.1 High Availability in a Single Switch Topology -------------------------------------------------- If two hosts (or a host and a single switch) are directly @@ -1332,7 +1467,7 @@ the load will be rebalanced across the remaining devices. See Section 13, "Configuring Bonding for Maximum Throughput" for information on configuring bonding with one peer device. -12.2 High Availability in a Multiple Switch Topology +11.2 High Availability in a Multiple Switch Topology ---------------------------------------------------- With multiple switches, the configuration of bonding and the @@ -1359,7 +1494,7 @@ switches (ISL, or inter switch link), and multiple ports connecting to the outside world ("port3" on each switch). There is no technical reason that this could not be extended to a third switch. -12.2.1 HA Bonding Mode Selection for Multiple Switch Topology +11.2.1 HA Bonding Mode Selection for Multiple Switch Topology ------------------------------------------------------------- In a topology such as the example above, the active-backup and @@ -1381,7 +1516,7 @@ broadcast: This mode is really a special purpose mode, and is suitable necessary for some specific one-way traffic to reach both independent networks, then the broadcast mode may be suitable. -12.2.2 HA Link Monitoring Selection for Multiple Switch Topology +11.2.2 HA Link Monitoring Selection for Multiple Switch Topology ---------------------------------------------------------------- The choice of link monitoring ultimately depends upon your @@ -1402,10 +1537,10 @@ regardless of which switch is active, the ARP monitor has a suitable target to query. -13. Configuring Bonding for Maximum Throughput +12. Configuring Bonding for Maximum Throughput ============================================== -13.1 Maximizing Throughput in a Single Switch Topology +12.1 Maximizing Throughput in a Single Switch Topology ------------------------------------------------------ In a single switch configuration, the best method to maximize @@ -1476,7 +1611,7 @@ destination to make load balancing decisions. The behavior of each mode is described below. -13.1.1 MT Bonding Mode Selection for Single Switch Topology +12.1.1 MT Bonding Mode Selection for Single Switch Topology ----------------------------------------------------------- This configuration is the easiest to set up and to understand, @@ -1607,7 +1742,7 @@ balance-alb: This mode is everything that balance-tlb is, and more. device driver must support changing the hardware address while the device is open. -13.1.2 MT Link Monitoring for Single Switch Topology +12.1.2 MT Link Monitoring for Single Switch Topology ---------------------------------------------------- The choice of link monitoring may largely depend upon which @@ -1616,7 +1751,7 @@ support the use of the ARP monitor, and are thus restricted to using the MII monitor (which does not provide as high a level of end to end assurance as the ARP monitor). -13.2 Maximum Throughput in a Multiple Switch Topology +12.2 Maximum Throughput in a Multiple Switch Topology ----------------------------------------------------- Multiple switches may be utilized to optimize for throughput @@ -1651,7 +1786,7 @@ a single 72 port switch. can be equipped with an additional network device connected to an external network; this host then additionally acts as a gateway. -13.2.1 MT Bonding Mode Selection for Multiple Switch Topology +12.2.1 MT Bonding Mode Selection for Multiple Switch Topology ------------------------------------------------------------- In actual practice, the bonding mode typically employed in @@ -1664,7 +1799,7 @@ packets has arrived). When employed in this fashion, the balance-rr mode allows individual connections between two hosts to effectively utilize greater than one interface's bandwidth. -13.2.2 MT Link Monitoring for Multiple Switch Topology +12.2.2 MT Link Monitoring for Multiple Switch Topology ------------------------------------------------------ Again, in actual practice, the MII monitor is most often used @@ -1674,10 +1809,10 @@ advantages over the MII monitor are mitigated by the volume of probes needed as the number of systems involved grows (remember that each host in the network is configured with bonding). -14. Switch Behavior Issues +13. Switch Behavior Issues ========================== -14.1 Link Establishment and Failover Delays +13.1 Link Establishment and Failover Delays ------------------------------------------- Some switches exhibit undesirable behavior with regard to the @@ -1712,7 +1847,7 @@ switches take a long time to go into backup mode, it may be desirable to not activate a backup interface immediately after a link goes down. Failover may be delayed via the downdelay bonding module option. -14.2 Duplicated Incoming Packets +13.2 Duplicated Incoming Packets -------------------------------- It is not uncommon to observe a short burst of duplicated @@ -1751,14 +1886,14 @@ behavior, it can be induced by clearing the MAC forwarding table (on most Cisco switches, the privileged command "clear mac address-table dynamic" will accomplish this). -15. Hardware Specific Considerations +14. Hardware Specific Considerations ==================================== This section contains additional information for configuring bonding on specific hardware platforms, or for interfacing bonding with particular switches or other devices. -15.1 IBM BladeCenter +14.1 IBM BladeCenter -------------------- This applies to the JS20 and similar systems. @@ -1861,7 +1996,7 @@ bonding driver. avoid fail-over delay issues when using bonding. -16. Frequently Asked Questions +15. Frequently Asked Questions ============================== 1. Is it SMP safe? @@ -1925,7 +2060,7 @@ not have special switch requirements, but do need device drivers that support specific features (described in the appropriate section under module parameters, above). - In 802.3ad mode, it works with with systems that support IEEE + In 802.3ad mode, it works with systems that support IEEE 802.3ad Dynamic Link Aggregation. Most managed and many unmanaged switches currently available support 802.3ad. diff --git a/drivers/net/e100.c b/drivers/net/e100.c index 31ac001f551..f37170cc1a3 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -2780,6 +2780,80 @@ static void e100_shutdown(struct pci_dev *pdev) DPRINTK(PROBE,ERR, "Error enabling wake\n"); } +/* ------------------ PCI Error Recovery infrastructure -------------- */ +/** + * e100_io_error_detected - called when PCI error is detected. + * @pdev: Pointer to PCI device + * @state: The current pci conneection state + */ +static pci_ers_result_t e100_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + + /* Similar to calling e100_down(), but avoids adpater I/O. */ + netdev->stop(netdev); + + /* Detach; put netif into state similar to hotplug unplug. */ + netif_poll_enable(netdev); + netif_device_detach(netdev); + + /* Request a slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * e100_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch. + */ +static pci_ers_result_t e100_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct nic *nic = netdev_priv(netdev); + + if (pci_enable_device(pdev)) { + printk(KERN_ERR "e100: Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + pci_set_master(pdev); + + /* Only one device per card can do a reset */ + if (0 != PCI_FUNC(pdev->devfn)) + return PCI_ERS_RESULT_RECOVERED; + e100_hw_reset(nic); + e100_phy_init(nic); + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * e100_io_resume - resume normal operations + * @pdev: Pointer to PCI device + * + * Resume normal operations after an error recovery + * sequence has been completed. + */ +static void e100_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct nic *nic = netdev_priv(netdev); + + /* ack any pending wake events, disable PME */ + pci_enable_wake(pdev, 0, 0); + + netif_device_attach(netdev); + if (netif_running(netdev)) { + e100_open(netdev); + mod_timer(&nic->watchdog, jiffies); + } +} + +static struct pci_error_handlers e100_err_handler = { + .error_detected = e100_io_error_detected, + .slot_reset = e100_io_slot_reset, + .resume = e100_io_resume, +}; static struct pci_driver e100_driver = { .name = DRV_NAME, @@ -2791,6 +2865,7 @@ static struct pci_driver e100_driver = { .resume = e100_resume, #endif .shutdown = e100_shutdown, + .err_handler = &e100_err_handler, }; static int __init e100_init_module(void) diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 115eff25d8c..56c7492e3e9 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -189,6 +189,16 @@ static void e1000_shutdown(struct pci_dev *pdev); static void e1000_netpoll (struct net_device *netdev); #endif +static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state); +static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev); +static void e1000_io_resume(struct pci_dev *pdev); + +static struct pci_error_handlers e1000_err_handler = { + .error_detected = e1000_io_error_detected, + .slot_reset = e1000_io_slot_reset, + .resume = e1000_io_resume, +}; static struct pci_driver e1000_driver = { .name = e1000_driver_name, @@ -200,7 +210,8 @@ static struct pci_driver e1000_driver = { .suspend = e1000_suspend, .resume = e1000_resume, #endif - .shutdown = e1000_shutdown + .shutdown = e1000_shutdown, + .err_handler = &e1000_err_handler }; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); @@ -3039,6 +3050,10 @@ e1000_update_stats(struct e1000_adapter *adapter) #define PHY_IDLE_ERROR_COUNT_MASK 0x00FF + /* Prevent stats update while adapter is being reset */ + if (adapter->link_speed == 0) + return; + spin_lock_irqsave(&adapter->stats_lock, flags); /* these counters are modified from e1000_adjust_tbi_stats, @@ -4590,4 +4605,101 @@ e1000_netpoll(struct net_device *netdev) } #endif +/** + * e1000_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci conneection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev->priv; + + netif_device_detach(netdev); + + if (netif_running(netdev)) + e1000_down(adapter); + + /* Request a slot slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * e1000_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the e1000_resume routine. + */ +static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev->priv; + + if (pci_enable_device(pdev)) { + printk(KERN_ERR "e1000: Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + pci_set_master(pdev); + + pci_enable_wake(pdev, 3, 0); + pci_enable_wake(pdev, 4, 0); /* 4 == D3 cold */ + + /* Perform card reset only on one instance of the card */ + if (PCI_FUNC (pdev->devfn) != 0) + return PCI_ERS_RESULT_RECOVERED; + + e1000_reset(adapter); + E1000_WRITE_REG(&adapter->hw, WUS, ~0); + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * e1000_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the e1000_resume routine. + */ +static void e1000_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev->priv; + uint32_t manc, swsm; + + if (netif_running(netdev)) { + if (e1000_up(adapter)) { + printk("e1000: can't bring device back up after reset\n"); + return; + } + } + + netif_device_attach(netdev); + + if (adapter->hw.mac_type >= e1000_82540 && + adapter->hw.media_type == e1000_media_type_copper) { + manc = E1000_READ_REG(&adapter->hw, MANC); + manc &= ~(E1000_MANC_ARP_EN); + E1000_WRITE_REG(&adapter->hw, MANC, manc); + } + + switch (adapter->hw.mac_type) { + case e1000_82573: + swsm = E1000_READ_REG(&adapter->hw, SWSM); + E1000_WRITE_REG(&adapter->hw, SWSM, + swsm | E1000_SWSM_DRV_LOAD); + break; + default: + break; + } + + if (netif_running(netdev)) + mod_timer(&adapter->watchdog_timer, jiffies); +} + /* e1000_main.c */ |