* b: if a hw mac address already is there, eth0's hw mac address
* will then be set from bond0.
*
- * v0.1 - first working version.
- * v0.2 - changed stats to be calculated by summing slaves stats.
- *
- * Changes:
- * Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- * - fix leaks on failure at bond_init
- *
- * 2000/09/30 - Willy Tarreau <willy at meta-x.org>
- * - added trivial code to release a slave device.
- * - fixed security bug (CAP_NET_ADMIN not checked)
- * - implemented MII link monitoring to disable dead links :
- * All MII capable slaves are checked every <miimon> milliseconds
- * (100 ms seems good). This value can be changed by passing it to
- * insmod. A value of zero disables the monitoring (default).
- * - fixed an infinite loop in bond_xmit_roundrobin() when there's no
- * good slave.
- * - made the code hopefully SMP safe
- *
- * 2000/10/03 - Willy Tarreau <willy at meta-x.org>
- * - optimized slave lists based on relevant suggestions from Thomas Davis
- * - implemented active-backup method to obtain HA with two switches:
- * stay as long as possible on the same active interface, while we
- * also monitor the backup one (MII link status) because we want to know
- * if we are able to switch at any time. ( pass "mode=1" to insmod )
- * - lots of stress testings because we need it to be more robust than the
- * wires ! :->
- *
- * 2000/10/09 - Willy Tarreau <willy at meta-x.org>
- * - added up and down delays after link state change.
- * - optimized the slaves chaining so that when we run forward, we never
- * repass through the bond itself, but we can find it by searching
- * backwards. Renders the deletion more difficult, but accelerates the
- * scan.
- * - smarter enslaving and releasing.
- * - finer and more robust SMP locking
- *
- * 2000/10/17 - Willy Tarreau <willy at meta-x.org>
- * - fixed two potential SMP race conditions
- *
- * 2000/10/18 - Willy Tarreau <willy at meta-x.org>
- * - small fixes to the monitoring FSM in case of zero delays
- * 2000/11/01 - Willy Tarreau <willy at meta-x.org>
- * - fixed first slave not automatically used in trunk mode.
- * 2000/11/10 : spelling of "EtherChannel" corrected.
- * 2000/11/13 : fixed a race condition in case of concurrent accesses to ioctl().
- * 2000/12/16 : fixed improper usage of rtnl_exlock_nowait().
- *
- * 2001/1/3 - Chad N. Tindel <ctindel at ieee dot org>
- * - The bonding driver now simulates MII status monitoring, just like
- * a normal network device. It will show that the link is down iff
- * every slave in the bond shows that their links are down. If at least
- * one slave is up, the bond's MII status will appear as up.
- *
- * 2001/2/7 - Chad N. Tindel <ctindel at ieee dot org>
- * - Applications can now query the bond from user space to get
- * information which may be useful. They do this by calling
- * the BOND_INFO_QUERY ioctl. Once the app knows how many slaves
- * are in the bond, it can call the BOND_SLAVE_INFO_QUERY ioctl to
- * get slave specific information (# link failures, etc). See
- * <linux/if_bonding.h> for more details. The structs of interest
- * are ifbond and ifslave.
- *
- * 2001/4/5 - Chad N. Tindel <ctindel at ieee dot org>
- * - Ported to 2.4 Kernel
- *
- * 2001/5/2 - Jeffrey E. Mast <jeff at mastfamily dot com>
- * - When a device is detached from a bond, the slave device is no longer
- * left thinking that is has a master.
- *
- * 2001/5/16 - Jeffrey E. Mast <jeff at mastfamily dot com>
- * - memset did not appropriately initialized the bond rw_locks. Used
- * rwlock_init to initialize to unlocked state to prevent deadlock when
- * first attempting a lock
- * - Called SET_MODULE_OWNER for bond device
- *
- * 2001/5/17 - Tim Anderson <tsa at mvista.com>
- * - 2 paths for releasing for slave release; 1 through ioctl
- * and 2) through close. Both paths need to release the same way.
- * - the free slave in bond release is changing slave status before
- * the free. The netdev_set_master() is intended to change slave state
- * so it should not be done as part of the release process.
- * - Simple rule for slave state at release: only the active in A/B and
- * only one in the trunked case.
- *
- * 2001/6/01 - Tim Anderson <tsa at mvista.com>
- * - Now call dev_close when releasing a slave so it doesn't screw up
- * out routing table.
- *
- * 2001/6/01 - Chad N. Tindel <ctindel at ieee dot org>
- * - Added /proc support for getting bond and slave information.
- * Information is in /proc/net/<bond device>/info.
- * - Changed the locking when calling bond_close to prevent deadlock.
- *
- * 2001/8/05 - Janice Girouard <girouard at us.ibm.com>
- * - correct problem where refcnt of slave is not incremented in bond_ioctl
- * so the system hangs when halting.
- * - correct locking problem when unable to malloc in bond_enslave.
- * - adding bond_xmit_xor logic.
- * - adding multiple bond device support.
- *
- * 2001/8/13 - Erik Habbinga <erik_habbinga at hp dot com>
- * - correct locking problem with rtnl_exlock_nowait
- *
- * 2001/8/23 - Janice Girouard <girouard at us.ibm.com>
- * - bzero initial dev_bonds, to correct oops
- * - convert SIOCDEVPRIVATE to new MII ioctl calls
- *
- * 2001/9/13 - Takao Indoh <indou dot takao at jp dot fujitsu dot com>
- * - Add the BOND_CHANGE_ACTIVE ioctl implementation
- *
- * 2001/9/14 - Mark Huth <mhuth at mvista dot com>
- * - Change MII_LINK_READY to not check for end of auto-negotiation,
- * but only for an up link.
- *
- * 2001/9/20 - Chad N. Tindel <ctindel at ieee dot org>
- * - Add the device field to bonding_t. Previously the net_device
- * corresponding to a bond wasn't available from the bonding_t
- * structure.
- *
- * 2001/9/25 - Janice Girouard <girouard at us.ibm.com>
- * - add arp_monitor for active backup mode
- *
- * 2001/10/23 - Takao Indoh <indou dot takao at jp dot fujitsu dot com>
- * - Various memory leak fixes
- *
- * 2001/11/5 - Mark Huth <mark dot huth at mvista dot com>
- * - Don't take rtnl lock in bond_mii_monitor as it deadlocks under
- * certain hotswap conditions.
- * Note: this same change may be required in bond_arp_monitor ???
- * - Remove possibility of calling bond_sethwaddr with NULL slave_dev ptr
- * - Handle hot swap ethernet interface deregistration events to remove
- * kernel oops following hot swap of enslaved interface
- *
- * 2002/1/2 - Chad N. Tindel <ctindel at ieee dot org>
- * - Restore original slave flags at release time.
- *
- * 2002/02/18 - Erik Habbinga <erik_habbinga at hp dot com>
- * - bond_release(): calling kfree on our_slave after call to
- * bond_restore_slave_flags, not before
- * - bond_enslave(): saving slave flags into original_flags before
- * call to netdev_set_master, so the IFF_SLAVE flag doesn't end
- * up in original_flags
- *
- * 2002/04/05 - Mark Smith <mark.smith at comdev dot cc> and
- * Steve Mead <steve.mead at comdev dot cc>
- * - Port Gleb Natapov's multicast support patchs from 2.4.12
- * to 2.4.18 adding support for multicast.
- *
- * 2002/06/10 - Tony Cureington <tony.cureington * hp_com>
- * - corrected uninitialized pointer (ifr.ifr_data) in bond_check_dev_link;
- * actually changed function to use MIIPHY, then MIIREG, and finally
- * ETHTOOL to determine the link status
- * - fixed bad ifr_data pointer assignments in bond_ioctl
- * - corrected mode 1 being reported as active-backup in bond_get_info;
- * also added text to distinguish type of load balancing (rr or xor)
- * - change arp_ip_target module param from "1-12s" (array of 12 ptrs)
- * to "s" (a single ptr)
- *
- * 2002/08/30 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - Removed acquisition of xmit_lock in set_multicast_list; caused
- * deadlock on SMP (lock is held by caller).
- * - Revamped SIOCGMIIPHY, SIOCGMIIREG portion of bond_check_dev_link().
- *
- * 2002/09/18 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - Fixed up bond_check_dev_link() (and callers): removed some magic
- * numbers, banished local MII_ defines, wrapped ioctl calls to
- * prevent EFAULT errors
- *
- * 2002/9/30 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - make sure the ip target matches the arp_target before saving the
- * hw address.
- *
- * 2002/9/30 - Dan Eisner <eisner at 2robots dot com>
- * - make sure my_ip is set before taking down the link, since
- * not all switches respond if the source ip is not set.
- *
- * 2002/10/8 - Janice Girouard <girouard at us dot ibm dot com>
- * - read in the local ip address when enslaving a device
- * - add primary support
- * - make sure 2*arp_interval has passed when a new device
- * is brought on-line before taking it down.
- *
- * 2002/09/11 - Philippe De Muyter <phdm at macqel dot be>
- * - Added bond_xmit_broadcast logic.
- * - Added bond_mode() support function.
- *
- * 2002/10/26 - Laurent Deniel <laurent.deniel at free.fr>
- * - allow to register multicast addresses only on active slave
- * (useful in active-backup mode)
- * - add multicast module parameter
- * - fix deletion of multicast groups after unloading module
- *
- * 2002/11/06 - Kameshwara Rayaprolu <kameshwara.rao * wipro_com>
- * - Changes to prevent panic from closing the device twice; if we close
- * the device in bond_release, we must set the original_flags to down
- * so it won't be closed again by the network layer.
- *
- * 2002/11/07 - Tony Cureington <tony.cureington * hp_com>
- * - Fix arp_target_hw_addr memory leak
- * - Created activebackup_arp_monitor function to handle arp monitoring
- * in active backup mode - the bond_arp_monitor had several problems...
- * such as allowing slaves to tx arps sequentially without any delay
- * for a response
- * - Renamed bond_arp_monitor to loadbalance_arp_monitor and re-wrote
- * this function to just handle arp monitoring in load-balancing mode;
- * it is a lot more compact now
- * - Changes to ensure one and only one slave transmits in active-backup
- * mode
- * - Robustesize parameters; warn users about bad combinations of
- * parameters; also if miimon is specified and a network driver does
- * not support MII or ETHTOOL, inform the user of this
- * - Changes to support link_failure_count when in arp monitoring mode
- * - Fix up/down delay reported in /proc
- * - Added version; log version; make version available from "modinfo -d"
- * - Fixed problem in bond_check_dev_link - if the first IOCTL (SIOCGMIIPH)
- * failed, the ETHTOOL ioctl never got a chance
- *
- * 2002/11/16 - Laurent Deniel <laurent.deniel at free.fr>
- * - fix multicast handling in activebackup_arp_monitor
- * - remove one unnecessary and confusing curr_active_slave == slave test
- * in activebackup_arp_monitor
- *
- * 2002/11/17 - Laurent Deniel <laurent.deniel at free.fr>
- * - fix bond_slave_info_query when slave_id = num_slaves
- *
- * 2002/11/19 - Janice Girouard <girouard at us dot ibm dot com>
- * - correct ifr_data reference. Update ifr_data reference
- * to mii_ioctl_data struct values to avoid confusion.
- *
- * 2002/11/22 - Bert Barbe <bert.barbe at oracle dot com>
- * - Add support for multiple arp_ip_target
- *
- * 2002/12/13 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - Changed to allow text strings for mode and multicast, e.g.,
- * insmod bonding mode=active-backup. The numbers still work.
- * One change: an invalid choice will cause module load failure,
- * rather than the previous behavior of just picking one.
- * - Minor cleanups; got rid of dup ctype stuff, atoi function
- *
- * 2003/02/07 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - Added use_carrier module parameter that causes miimon to
- * use netif_carrier_ok() test instead of MII/ETHTOOL ioctls.
- * - Minor cleanups; consolidated ioctl calls to one function.
- *
- * 2003/02/07 - Tony Cureington <tony.cureington * hp_com>
- * - Fix bond_mii_monitor() logic error that could result in
- * bonding round-robin mode ignoring links after failover/recovery
- *
- * 2003/03/17 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - kmalloc fix (GFP_KERNEL to GFP_ATOMIC) reported by
- * Shmulik dot Hen at intel.com.
- * - Based on discussion on mailing list, changed use of
- * update_slave_cnt(), created wrapper functions for adding/removing
- * slaves, changed bond_xmit_xor() to check slave_cnt instead of
- * checking slave and slave->dev (which only worked by accident).
- * - Misc code cleanup: get arp_send() prototype from header file,
- * add max_bonds to bonding.txt.
- *
- * 2003/03/18 - Tsippy Mendelson <tsippy.mendelson at intel dot com> and
- * Shmulik Hen <shmulik.hen at intel dot com>
- * - Make sure only bond_attach_slave() and bond_detach_slave() can
- * manipulate the slave list, including slave_cnt, even when in
- * bond_release_all().
- * - Fixed hang in bond_release() with traffic running:
- * netdev_set_master() must not be called from within the bond lock.
- *
- * 2003/03/18 - Tsippy Mendelson <tsippy.mendelson at intel dot com> and
- * Shmulik Hen <shmulik.hen at intel dot com>
- * - Fixed hang in bond_enslave() with traffic running:
- * netdev_set_master() must not be called from within the bond lock.
- *
- * 2003/03/18 - Amir Noam <amir.noam at intel dot com>
- * - Added support for getting slave's speed and duplex via ethtool.
- * Needed for 802.3ad and other future modes.
- *
- * 2003/03/18 - Tsippy Mendelson <tsippy.mendelson at intel dot com> and
- * Shmulik Hen <shmulik.hen at intel dot com>
- * - Enable support of modes that need to use the unique mac address of
- * each slave.
- * * bond_enslave(): Moved setting the slave's mac address, and
- * openning it, from the application to the driver. This breaks
- * backward comaptibility with old versions of ifenslave that open
- * the slave before enalsving it !!!.
- * * bond_release(): The driver also takes care of closing the slave
- * and restoring its original mac address.
- * - Removed the code that restores all base driver's flags.
- * Flags are automatically restored once all undo stages are done
- * properly.
- * - Block possibility of enslaving before the master is up. This
- * prevents putting the system in an unstable state.
- *
- * 2003/03/18 - Amir Noam <amir.noam at intel dot com>,
- * Tsippy Mendelson <tsippy.mendelson at intel dot com> and
- * Shmulik Hen <shmulik.hen at intel dot com>
- * - Added support for IEEE 802.3ad Dynamic link aggregation mode.
- *
- * 2003/05/01 - Amir Noam <amir.noam at intel dot com>
- * - Added ABI version control to restore compatibility between
- * new/old ifenslave and new/old bonding.
- *
- * 2003/05/01 - Shmulik Hen <shmulik.hen at intel dot com>
- * - Fixed bug in bond_release_all(): save old value of curr_active_slave
- * before setting it to NULL.
- * - Changed driver versioning scheme to include version number instead
- * of release date (that is already in another field). There are 3
- * fields X.Y.Z where:
- * X - Major version - big behavior changes
- * Y - Minor version - addition of features
- * Z - Extra version - minor changes and bug fixes
- * The current version is 1.0.0 as a base line.
- *
- * 2003/05/01 - Tsippy Mendelson <tsippy.mendelson at intel dot com> and
- * Amir Noam <amir.noam at intel dot com>
- * - Added support for lacp_rate module param.
- * - Code beautification and style changes (mainly in comments).
- * new version - 1.0.1
- *
- * 2003/05/01 - Shmulik Hen <shmulik.hen at intel dot com>
- * - Based on discussion on mailing list, changed locking scheme
- * to use lock/unlock or lock_bh/unlock_bh appropriately instead
- * of lock_irqsave/unlock_irqrestore. The new scheme helps exposing
- * hidden bugs and solves system hangs that occurred due to the fact
- * that holding lock_irqsave doesn't prevent softirqs from running.
- * This also increases total throughput since interrupts are not
- * blocked on each transmitted packets or monitor timeout.
- * new version - 2.0.0
- *
- * 2003/05/01 - Shmulik Hen <shmulik.hen at intel dot com>
- * - Added support for Transmit load balancing mode.
- * - Concentrate all assignments of curr_active_slave to a single point
- * so specific modes can take actions when the primary adapter is
- * changed.
- * - Take the updelay parameter into consideration during bond_enslave
- * since some adapters loose their link during setting the device.
- * - Renamed bond_3ad_link_status_changed() to
- * bond_3ad_handle_link_change() for compatibility with TLB.
- * new version - 2.1.0
- *
- * 2003/05/01 - Tsippy Mendelson <tsippy.mendelson at intel dot com>
- * - Added support for Adaptive load balancing mode which is
- * equivalent to Transmit load balancing + Receive load balancing.
- * new version - 2.2.0
- *
- * 2003/05/15 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - Applied fix to activebackup_arp_monitor posted to bonding-devel
- * by Tony Cureington <tony.cureington * hp_com>. Fixes ARP
- * monitor endless failover bug. Version to 2.2.10
- *
- * 2003/05/20 - Amir Noam <amir.noam at intel dot com>
- * - Fixed bug in ABI version control - Don't commit to a specific
- * ABI version if receiving unsupported ioctl commands.
- *
- * 2003/05/22 - Jay Vosburgh <fubar at us dot ibm dot com>
- * - Fix ifenslave -c causing bond to loose existing routes;
- * added bond_set_mac_address() that doesn't require the
- * bond to be down.
- * - In conjunction with fix for ifenslave -c, in
- * bond_change_active(), changing to the already active slave
- * is no longer an error (it successfully does nothing).
- *
- * 2003/06/30 - Amir Noam <amir.noam at intel dot com>
- * - Fixed bond_change_active() for ALB/TLB modes.
- * Version to 2.2.14.
- *
- * 2003/07/29 - Amir Noam <amir.noam at intel dot com>
- * - Fixed ARP monitoring bug.
- * Version to 2.2.15.
- *
- * 2003/07/31 - Willy Tarreau <willy at ods dot org>
- * - Fixed kernel panic when using ARP monitoring without
- * setting bond's IP address.
- * Version to 2.2.16.
- *
- * 2003/08/06 - Amir Noam <amir.noam at intel dot com>
- * - Back port from 2.6: use alloc_netdev(); fix /proc handling;
- * made stats a part of bond struct so no need to allocate
- * and free it separately; use standard list operations instead
- * of pre-allocated array of bonds.
- * Version to 2.3.0.
- *
- * 2003/08/07 - Jay Vosburgh <fubar at us dot ibm dot com>,
- * Amir Noam <amir.noam at intel dot com> and
- * Shmulik Hen <shmulik.hen at intel dot com>
- * - Propagating master's settings: Distinguish between modes that
- * use a primary slave from those that don't, and propagate settings
- * accordingly; Consolidate change_active opeartions and add
- * reselect_active and find_best opeartions; Decouple promiscuous
- * handling from the multicast mode setting; Add support for changing
- * HW address and MTU with proper unwind; Consolidate procfs code,
- * add CHANGENAME handler; Enhance netdev notification handling.
- * Version to 2.4.0.
- *
- * 2003/09/15 - Stephen Hemminger <shemminger at osdl dot org>,
- * Amir Noam <amir.noam at intel dot com>
- * - Convert /proc to seq_file interface.
- * Change /proc/net/bondX/info to /proc/net/bonding/bondX.
- * Set version to 2.4.1.
- *
- * 2003/11/20 - Amir Noam <amir.noam at intel dot com>
- * - Fix /proc creation/destruction.
- *
- * 2003/12/01 - Shmulik Hen <shmulik.hen at intel dot com>
- * - Massive cleanup - Set version to 2.5.0
- * Code changes:
- * o Consolidate format of prints and debug prints.
- * o Remove bonding_t/slave_t typedefs and consolidate all casts.
- * o Remove dead code and unnecessary checks.
- * o Consolidate starting/stopping timers.
- * o Consolidate handling of primary module param throughout the code.
- * o Removed multicast module param support - all settings are done
- * according to mode.
- * o Slave list iteration - bond is no longer part of the list,
- * added cyclic list iteration macros.
- * o Consolidate error handling in all xmit functions.
- * Style changes:
- * o Consolidate function naming and declarations.
- * o Consolidate function params and local variables names.
- * o Consolidate return values.
- * o Consolidate curly braces.
- * o Consolidate conditionals format.
- * o Change struct member names and types.
- * o Chomp trailing spaces, remove empty lines, fix indentations.
- * o Re-organize code according to context.
- *
- * 2003/12/30 - Amir Noam <amir.noam at intel dot com>
- * - Fixed: Cannot remove and re-enslave the original active slave.
- * - Fixed: Releasing the original active slave causes mac address
- * duplication.
- * - Add support for slaves that use ethtool_ops.
- * Set version to 2.5.3.
- *
- * 2004/01/05 - Amir Noam <amir.noam at intel dot com>
- * - Save bonding parameters per bond instead of using the global values.
- * Set version to 2.5.4.
- *
- * 2004/01/14 - Shmulik Hen <shmulik.hen at intel dot com>
- * - Enhance VLAN support:
- * * Add support for VLAN hardware acceleration capable slaves.
- * * Add capability to tag self generated packets in ALB/TLB modes.
- * Set version to 2.6.0.
- * 2004/10/29 - Mitch Williams <mitch.a.williams at intel dot com>
- * - Fixed bug when unloading module while using 802.3ad. If
- * spinlock debugging is turned on, this causes a stack dump.
- * Solution is to move call to dev_remove_pack outside of the
- * spinlock.
- * Set version to 2.6.1.
- * 2005/06/05 - Jay Vosburgh <fubar@us.ibm.com>
- * - Support for generating gratuitous ARPs in active-backup mode.
- * Includes support for VLAN tagging all bonding-generated ARPs
- * as needed. Set version to 2.6.2.
- * 2005/06/08 - Jason Gabler <jygabler at lbl dot gov>
- * - alternate hashing policy support for mode 2
- * * Added kernel parameter "xmit_hash_policy" to allow the selection
- * of different hashing policies for mode 2. The original mode 2
- * policy is the default, now found in xmit_hash_policy_layer2().
- * * Added xmit_hash_policy_layer34()
- * - Modified by Jay Vosburgh <fubar@us.ibm.com> to also support mode 4.
- * Set version to 2.6.3.
- * 2005/09/26 - Jay Vosburgh <fubar@us.ibm.com>
- * - Removed backwards compatibility for old ifenslaves. Version 2.6.4.
*/
-//#define BONDING_DEBUG 1
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/sched.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/interrupt.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
+#include <linux/io.h>
#include <asm/system.h>
-#include <asm/io.h>
#include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
+#include <linux/igmp.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
+#include <linux/jiffies.h>
#include <net/route.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"
#define BOND_LINK_ARP_INTERV 0
static int max_bonds = BOND_DEFAULT_MAX_BONDS;
+static int num_grat_arp = 1;
+static int num_unsol_na = 1;
static int miimon = BOND_LINK_MON_INTERV;
-static int updelay = 0;
-static int downdelay = 0;
+static int updelay;
+static int downdelay;
static int use_carrier = 1;
-static char *mode = NULL;
-static char *primary = NULL;
-static char *lacp_rate = NULL;
-static char *xmit_hash_policy = NULL;
+static char *mode;
+static char *primary;
+static char *primary_reselect;
+static char *lacp_rate;
+static char *ad_select;
+static char *xmit_hash_policy;
static int arp_interval = BOND_LINK_ARP_INTERV;
-static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, };
-struct bond_params bonding_defaults;
+static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
+static char *arp_validate;
+static char *fail_over_mac;
+static struct bond_params bonding_defaults;
module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
+module_param(num_grat_arp, int, 0644);
+MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event");
+module_param(num_unsol_na, int, 0644);
+MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
"6 for balance-alb");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
+module_param(primary_reselect, charp, 0);
+MODULE_PARM_DESC(primary_reselect, "Reselect primary slave "
+ "once it comes up; "
+ "0 for always (default), "
+ "1 for only if speed of primary is "
+ "better, "
+ "2 for only on active slave "
+ "failure");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
"(slow/fast)");
+module_param(ad_select, charp, 0);
+MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)");
module_param(xmit_hash_policy, charp, 0);
MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)"
", 1 for layer 3+4");
MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
module_param_array(arp_ip_target, charp, NULL, 0);
MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");
+module_param(arp_validate, charp, 0);
+MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or 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. none (default), active or follow");
/*----------------------------- Global variables ----------------------------*/
-static const char *version =
+static const char * const version =
DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";
-LIST_HEAD(bond_dev_list);
-
-#ifdef CONFIG_PROC_FS
-static struct proc_dir_entry *bond_proc_dir = NULL;
-#endif
+int bond_net_id __read_mostly;
-static u32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ;
-static int arp_ip_count = 0;
+static __be32 arp_target[BOND_MAX_ARP_TARGETS];
+static int arp_ip_count;
static int bond_mode = BOND_MODE_ROUNDROBIN;
-static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2;
-static int lacp_fast = 0;
+static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
+static int lacp_fast;
-struct bond_parm_tbl bond_lacp_tbl[] = {
+const struct bond_parm_tbl bond_lacp_tbl[] = {
{ "slow", AD_LACP_SLOW},
{ "fast", AD_LACP_FAST},
{ NULL, -1},
};
-struct bond_parm_tbl bond_mode_tbl[] = {
+const struct bond_parm_tbl bond_mode_tbl[] = {
{ "balance-rr", BOND_MODE_ROUNDROBIN},
{ "active-backup", BOND_MODE_ACTIVEBACKUP},
{ "balance-xor", BOND_MODE_XOR},
{ NULL, -1},
};
-struct bond_parm_tbl xmit_hashtype_tbl[] = {
+const struct bond_parm_tbl xmit_hashtype_tbl[] = {
{ "layer2", BOND_XMIT_POLICY_LAYER2},
{ "layer3+4", BOND_XMIT_POLICY_LAYER34},
+{ "layer2+3", BOND_XMIT_POLICY_LAYER23},
+{ NULL, -1},
+};
+
+const struct bond_parm_tbl arp_validate_tbl[] = {
+{ "none", BOND_ARP_VALIDATE_NONE},
+{ "active", BOND_ARP_VALIDATE_ACTIVE},
+{ "backup", BOND_ARP_VALIDATE_BACKUP},
+{ "all", BOND_ARP_VALIDATE_ALL},
+{ NULL, -1},
+};
+
+const struct bond_parm_tbl fail_over_mac_tbl[] = {
+{ "none", BOND_FOM_NONE},
+{ "active", BOND_FOM_ACTIVE},
+{ "follow", BOND_FOM_FOLLOW},
+{ NULL, -1},
+};
+
+const struct bond_parm_tbl pri_reselect_tbl[] = {
+{ "always", BOND_PRI_RESELECT_ALWAYS},
+{ "better", BOND_PRI_RESELECT_BETTER},
+{ "failure", BOND_PRI_RESELECT_FAILURE},
{ NULL, -1},
};
+struct bond_parm_tbl ad_select_tbl[] = {
+{ "stable", BOND_AD_STABLE},
+{ "bandwidth", BOND_AD_BANDWIDTH},
+{ "count", BOND_AD_COUNT},
+{ NULL, -1},
+};
+
/*-------------------------- Forward declarations ---------------------------*/
static void bond_send_gratuitous_arp(struct bonding *bond);
+static int bond_init(struct net_device *bond_dev);
+static void bond_uninit(struct net_device *bond_dev);
/*---------------------------- General routines -----------------------------*/
-const char *bond_mode_name(int mode)
+static const char *bond_mode_name(int mode)
{
- switch (mode) {
- case BOND_MODE_ROUNDROBIN :
- return "load balancing (round-robin)";
- case BOND_MODE_ACTIVEBACKUP :
- return "fault-tolerance (active-backup)";
- case BOND_MODE_XOR :
- return "load balancing (xor)";
- case BOND_MODE_BROADCAST :
- return "fault-tolerance (broadcast)";
- case BOND_MODE_8023AD:
- return "IEEE 802.3ad Dynamic link aggregation";
- case BOND_MODE_TLB:
- return "transmit load balancing";
- case BOND_MODE_ALB:
- return "adaptive load balancing";
- default:
+ static const char *names[] = {
+ [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)",
+ [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)",
+ [BOND_MODE_XOR] = "load balancing (xor)",
+ [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)",
+ [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation",
+ [BOND_MODE_TLB] = "transmit load balancing",
+ [BOND_MODE_ALB] = "adaptive load balancing",
+ };
+
+ if (mode < 0 || mode > BOND_MODE_ALB)
return "unknown";
- }
+
+ return names[mode];
}
/*---------------------------------- VLAN -----------------------------------*/
{
struct vlan_entry *vlan;
- dprintk("bond: %s, vlan id %d\n",
- (bond ? bond->dev->name: "None"), vlan_id);
+ pr_debug("bond: %s, vlan id %d\n",
+ (bond ? bond->dev->name : "None"), vlan_id);
- vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL);
- if (!vlan) {
+ vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL);
+ if (!vlan)
return -ENOMEM;
- }
INIT_LIST_HEAD(&vlan->vlan_list);
vlan->vlan_id = vlan_id;
- vlan->vlan_ip = 0;
write_lock_bh(&bond->lock);
write_unlock_bh(&bond->lock);
- dprintk("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name);
+ pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name);
return 0;
}
*/
static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id)
{
- struct vlan_entry *vlan, *next;
+ struct vlan_entry *vlan;
int res = -ENODEV;
- dprintk("bond: %s, vlan id %d\n", bond->dev->name, vlan_id);
+ pr_debug("bond: %s, vlan id %d\n", bond->dev->name, vlan_id);
write_lock_bh(&bond->lock);
- list_for_each_entry_safe(vlan, next, &bond->vlan_list, vlan_list) {
+ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
if (vlan->vlan_id == vlan_id) {
list_del(&vlan->vlan_list);
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ if (bond_is_lb(bond))
bond_alb_clear_vlan(bond, vlan_id);
- }
- dprintk("removed VLAN ID %d from bond %s\n", vlan_id,
- bond->dev->name);
+ pr_debug("removed VLAN ID %d from bond %s\n",
+ vlan_id, bond->dev->name);
kfree(vlan);
}
}
- dprintk("couldn't find VLAN ID %d in bond %s\n", vlan_id,
- bond->dev->name);
+ pr_debug("couldn't find VLAN ID %d in bond %s\n",
+ vlan_id, bond->dev->name);
out:
write_unlock_bh(&bond->lock);
bond_for_each_slave(bond, slave, i) {
if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) {
- dprintk("found VLAN challenged slave - %s\n",
- slave->dev->name);
+ pr_debug("found VLAN challenged slave - %s\n",
+ slave->dev->name);
return 1;
}
}
- dprintk("no VLAN challenged slaves found\n");
+ pr_debug("no VLAN challenged slaves found\n");
return 0;
}
*
* Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL,
* or @curr->next otherwise (even if it is @curr itself again).
- *
+ *
* Caller must hold bond->lock
*/
struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr)
{
struct vlan_entry *next, *last;
- if (list_empty(&bond->vlan_list)) {
+ if (list_empty(&bond->vlan_list))
return NULL;
- }
if (!curr) {
next = list_entry(bond->vlan_list.next,
/**
* bond_dev_queue_xmit - Prepare skb for xmit.
- *
+ *
* @bond: bond device that got this skb for tx.
* @skb: hw accel VLAN tagged skb to transmit
* @slave_dev: slave that is supposed to xmit this skbuff
- *
+ *
* When the bond gets an skb to transmit that is
* already hardware accelerated VLAN tagged, and it
* needs to relay this skb to a slave that is not
* i.e. strip the hwaccel tag and re-insert it as part
* of the payload.
*/
-int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev)
+int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
+ struct net_device *slave_dev)
{
- unsigned short vlan_id;
+ unsigned short uninitialized_var(vlan_id);
if (!list_empty(&bond->vlan_list) &&
!(slave_dev->features & NETIF_F_HW_VLAN_TX) &&
* b. The operation is protected by the RTNL semaphore in the 8021q code,
* c. Holding a lock with BH disabled while directly calling a base driver
* entry point is generally a BAD idea.
- *
+ *
* The design of synchronization/protection for this operation in the 8021q
* module is good for one or more VLAN devices over a single physical device
* and cannot be extended for a teaming solution like bonding, so there is a
* @bond_dev: bonding net device that got called
* @grp: vlan group being registered
*/
-static void bond_vlan_rx_register(struct net_device *bond_dev, struct vlan_group *grp)
+static void bond_vlan_rx_register(struct net_device *bond_dev,
+ struct vlan_group *grp)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
int i;
bond_for_each_slave(bond, slave, i) {
struct net_device *slave_dev = slave->dev;
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
- slave_dev->vlan_rx_register) {
- slave_dev->vlan_rx_register(slave_dev, grp);
+ slave_ops->ndo_vlan_rx_register) {
+ slave_ops->ndo_vlan_rx_register(slave_dev, grp);
}
}
}
*/
static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
int i, res;
bond_for_each_slave(bond, slave, i) {
struct net_device *slave_dev = slave->dev;
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
- slave_dev->vlan_rx_add_vid) {
- slave_dev->vlan_rx_add_vid(slave_dev, vid);
+ slave_ops->ndo_vlan_rx_add_vid) {
+ slave_ops->ndo_vlan_rx_add_vid(slave_dev, vid);
}
}
res = bond_add_vlan(bond, vid);
if (res) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: Failed to add vlan id %d\n",
+ pr_err("%s: Error: Failed to add vlan id %d\n",
bond_dev->name, vid);
}
}
*/
static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
struct net_device *vlan_dev;
int i, res;
bond_for_each_slave(bond, slave, i) {
struct net_device *slave_dev = slave->dev;
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
- slave_dev->vlan_rx_kill_vid) {
+ slave_ops->ndo_vlan_rx_kill_vid) {
/* Save and then restore vlan_dev in the grp array,
* since the slave's driver might clear it.
*/
- vlan_dev = bond->vlgrp->vlan_devices[vid];
- slave_dev->vlan_rx_kill_vid(slave_dev, vid);
- bond->vlgrp->vlan_devices[vid] = vlan_dev;
+ vlan_dev = vlan_group_get_device(bond->vlgrp, vid);
+ slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vid);
+ vlan_group_set_device(bond->vlgrp, vid, vlan_dev);
}
}
res = bond_del_vlan(bond, vid);
if (res) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: Failed to remove vlan id %d\n",
+ pr_err("%s: Error: Failed to remove vlan id %d\n",
bond_dev->name, vid);
}
}
static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev)
{
struct vlan_entry *vlan;
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
write_lock_bh(&bond->lock);
- if (list_empty(&bond->vlan_list)) {
+ if (list_empty(&bond->vlan_list))
goto out;
- }
if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
- slave_dev->vlan_rx_register) {
- slave_dev->vlan_rx_register(slave_dev, bond->vlgrp);
- }
+ slave_ops->ndo_vlan_rx_register)
+ slave_ops->ndo_vlan_rx_register(slave_dev, bond->vlgrp);
if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
- !(slave_dev->vlan_rx_add_vid)) {
+ !(slave_ops->ndo_vlan_rx_add_vid))
goto out;
- }
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- slave_dev->vlan_rx_add_vid(slave_dev, vlan->vlan_id);
- }
+ list_for_each_entry(vlan, &bond->vlan_list, vlan_list)
+ slave_ops->ndo_vlan_rx_add_vid(slave_dev, vlan->vlan_id);
out:
write_unlock_bh(&bond->lock);
}
-static void bond_del_vlans_from_slave(struct bonding *bond, struct net_device *slave_dev)
+static void bond_del_vlans_from_slave(struct bonding *bond,
+ struct net_device *slave_dev)
{
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct vlan_entry *vlan;
struct net_device *vlan_dev;
write_lock_bh(&bond->lock);
- if (list_empty(&bond->vlan_list)) {
+ if (list_empty(&bond->vlan_list))
goto out;
- }
if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
- !(slave_dev->vlan_rx_kill_vid)) {
+ !(slave_ops->ndo_vlan_rx_kill_vid))
goto unreg;
- }
list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
/* Save and then restore vlan_dev in the grp array,
* since the slave's driver might clear it.
*/
- vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
- slave_dev->vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
- bond->vlgrp->vlan_devices[vlan->vlan_id] = vlan_dev;
+ vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
+ slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
+ vlan_group_set_device(bond->vlgrp, vlan->vlan_id, vlan_dev);
}
unreg:
if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
- slave_dev->vlan_rx_register) {
- slave_dev->vlan_rx_register(slave_dev, NULL);
- }
+ slave_ops->ndo_vlan_rx_register)
+ slave_ops->ndo_vlan_rx_register(slave_dev, NULL);
out:
write_unlock_bh(&bond->lock);
/*------------------------------- Link status -------------------------------*/
/*
+ * Set the carrier state for the master according to the state of its
+ * slaves. If any slaves are up, the master is up. In 802.3ad mode,
+ * do special 802.3ad magic.
+ *
+ * Returns zero if carrier state does not change, nonzero if it does.
+ */
+static int bond_set_carrier(struct bonding *bond)
+{
+ struct slave *slave;
+ int i;
+
+ if (bond->slave_cnt == 0)
+ goto down;
+
+ if (bond->params.mode == BOND_MODE_8023AD)
+ return bond_3ad_set_carrier(bond);
+
+ bond_for_each_slave(bond, slave, i) {
+ if (slave->link == BOND_LINK_UP) {
+ if (!netif_carrier_ok(bond->dev)) {
+ netif_carrier_on(bond->dev);
+ return 1;
+ }
+ return 0;
+ }
+ }
+
+down:
+ if (netif_carrier_ok(bond->dev)) {
+ netif_carrier_off(bond->dev);
+ return 1;
+ }
+ return 0;
+}
+
+/*
* Get link speed and duplex from the slave's base driver
* using ethtool. If for some reason the call fails or the
* values are invalid, fake speed and duplex to 100/Full
static int bond_update_speed_duplex(struct slave *slave)
{
struct net_device *slave_dev = slave->dev;
- static int (* ioctl)(struct net_device *, struct ifreq *, int);
- struct ifreq ifr;
struct ethtool_cmd etool;
+ int res;
/* Fake speed and duplex */
slave->speed = SPEED_100;
slave->duplex = DUPLEX_FULL;
- if (slave_dev->ethtool_ops) {
- u32 res;
-
- if (!slave_dev->ethtool_ops->get_settings) {
- return -1;
- }
-
- res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool);
- if (res < 0) {
- return -1;
- }
-
- goto verify;
- }
+ if (!slave_dev->ethtool_ops || !slave_dev->ethtool_ops->get_settings)
+ return -1;
- ioctl = slave_dev->do_ioctl;
- strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
- etool.cmd = ETHTOOL_GSET;
- ifr.ifr_data = (char*)&etool;
- if (!ioctl || (IOCTL(slave_dev, &ifr, SIOCETHTOOL) < 0)) {
+ res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool);
+ if (res < 0)
return -1;
- }
-verify:
switch (etool.speed) {
case SPEED_10:
case SPEED_100:
case SPEED_1000:
+ case SPEED_10000:
break;
default:
return -1;
* if <dev> supports MII link status reporting, check its link status.
*
* We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(),
- * depening upon the setting of the use_carrier parameter.
+ * depending upon the setting of the use_carrier parameter.
*
* Return either BMSR_LSTATUS, meaning that the link is up (or we
* can't tell and just pretend it is), or 0, meaning that the link is
* It'd be nice if there was a good way to tell if a driver supports
* netif_carrier, but there really isn't.
*/
-static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_dev, int reporting)
+static int bond_check_dev_link(struct bonding *bond,
+ struct net_device *slave_dev, int reporting)
{
- static int (* ioctl)(struct net_device *, struct ifreq *, int);
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
+ int (*ioctl)(struct net_device *, struct ifreq *, int);
struct ifreq ifr;
struct mii_ioctl_data *mii;
- struct ethtool_value etool;
- if (bond->params.use_carrier) {
+ if (!reporting && !netif_running(slave_dev))
+ return 0;
+
+ if (bond->params.use_carrier)
return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
+
+ /* Try to get link status using Ethtool first. */
+ if (slave_dev->ethtool_ops) {
+ if (slave_dev->ethtool_ops->get_link) {
+ u32 link;
+
+ link = slave_dev->ethtool_ops->get_link(slave_dev);
+
+ return link ? BMSR_LSTATUS : 0;
+ }
}
- ioctl = slave_dev->do_ioctl;
+ /* Ethtool can't be used, fallback to MII ioctls. */
+ ioctl = slave_ops->ndo_do_ioctl;
if (ioctl) {
/* TODO: set pointer to correct ioctl on a per team member */
/* bases to make this more efficient. that is, once */
mii = if_mii(&ifr);
if (IOCTL(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
mii->reg_num = MII_BMSR;
- if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0) {
- return (mii->val_out & BMSR_LSTATUS);
- }
- }
- }
-
- /* try SIOCETHTOOL ioctl, some drivers cache ETHTOOL_GLINK */
- /* for a period of time so we attempt to get link status */
- /* from it last if the above MII ioctls fail... */
- if (slave_dev->ethtool_ops) {
- if (slave_dev->ethtool_ops->get_link) {
- u32 link;
-
- link = slave_dev->ethtool_ops->get_link(slave_dev);
-
- return link ? BMSR_LSTATUS : 0;
- }
- }
-
- if (ioctl) {
- strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
- etool.cmd = ETHTOOL_GLINK;
- ifr.ifr_data = (char*)&etool;
- if (IOCTL(slave_dev, &ifr, SIOCETHTOOL) == 0) {
- if (etool.data == 1) {
- return BMSR_LSTATUS;
- } else {
- dprintk("SIOCETHTOOL shows link down\n");
- return 0;
- }
+ if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0)
+ return mii->val_out & BMSR_LSTATUS;
}
}
/*
* If reporting, report that either there's no dev->do_ioctl,
- * or both SIOCGMIIREG and SIOCETHTOOL failed (meaning that we
+ * or both SIOCGMIIREG and get_link failed (meaning that we
* cannot report link status). If not reporting, pretend
* we're ok.
*/
- return (reporting ? -1 : BMSR_LSTATUS);
+ return reporting ? -1 : BMSR_LSTATUS;
}
/*----------------------------- Multicast list ------------------------------*/
/*
* Returns 0 if dmi1 and dmi2 are the same, non-0 otherwise
*/
-static inline int bond_is_dmi_same(struct dev_mc_list *dmi1, struct dev_mc_list *dmi2)
+static inline int bond_is_dmi_same(const struct dev_mc_list *dmi1,
+ const struct dev_mc_list *dmi2)
{
return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 &&
dmi1->dmi_addrlen == dmi2->dmi_addrlen;
/*
* returns dmi entry if found, NULL otherwise
*/
-static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi, struct dev_mc_list *mc_list)
+static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi,
+ struct dev_mc_list *mc_list)
{
struct dev_mc_list *idmi;
for (idmi = mc_list; idmi; idmi = idmi->next) {
- if (bond_is_dmi_same(dmi, idmi)) {
+ if (bond_is_dmi_same(dmi, idmi))
return idmi;
- }
}
return NULL;
/*
* Push the promiscuity flag down to appropriate slaves
*/
-static void bond_set_promiscuity(struct bonding *bond, int inc)
+static int bond_set_promiscuity(struct bonding *bond, int inc)
{
+ int err = 0;
if (USES_PRIMARY(bond->params.mode)) {
/* write lock already acquired */
if (bond->curr_active_slave) {
- dev_set_promiscuity(bond->curr_active_slave->dev, inc);
+ err = dev_set_promiscuity(bond->curr_active_slave->dev,
+ inc);
}
} else {
struct slave *slave;
int i;
bond_for_each_slave(bond, slave, i) {
- dev_set_promiscuity(slave->dev, inc);
+ err = dev_set_promiscuity(slave->dev, inc);
+ if (err)
+ return err;
}
}
+ return err;
}
/*
* Push the allmulti flag down to all slaves
*/
-static void bond_set_allmulti(struct bonding *bond, int inc)
+static int bond_set_allmulti(struct bonding *bond, int inc)
{
+ int err = 0;
if (USES_PRIMARY(bond->params.mode)) {
/* write lock already acquired */
if (bond->curr_active_slave) {
- dev_set_allmulti(bond->curr_active_slave->dev, inc);
+ err = dev_set_allmulti(bond->curr_active_slave->dev,
+ inc);
}
} else {
struct slave *slave;
int i;
bond_for_each_slave(bond, slave, i) {
- dev_set_allmulti(slave->dev, inc);
+ err = dev_set_allmulti(slave->dev, inc);
+ if (err)
+ return err;
}
}
+ return err;
}
/*
{
if (USES_PRIMARY(bond->params.mode)) {
/* write lock already acquired */
- if (bond->curr_active_slave) {
+ if (bond->curr_active_slave)
dev_mc_add(bond->curr_active_slave->dev, addr, alen, 0);
- }
} else {
struct slave *slave;
int i;
- bond_for_each_slave(bond, slave, i) {
+
+ bond_for_each_slave(bond, slave, i)
dev_mc_add(slave->dev, addr, alen, 0);
- }
}
}
{
if (USES_PRIMARY(bond->params.mode)) {
/* write lock already acquired */
- if (bond->curr_active_slave) {
- dev_mc_delete(bond->curr_active_slave->dev, addr, alen, 0);
- }
+ if (bond->curr_active_slave)
+ dev_mc_delete(bond->curr_active_slave->dev, addr,
+ alen, 0);
} else {
struct slave *slave;
int i;
}
}
+
+/*
+ * Retrieve the list of registered multicast addresses for the bonding
+ * device and retransmit an IGMP JOIN request to the current active
+ * slave.
+ */
+static void bond_resend_igmp_join_requests(struct bonding *bond)
+{
+ struct in_device *in_dev;
+ struct ip_mc_list *im;
+
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(bond->dev);
+ if (in_dev) {
+ for (im = in_dev->mc_list; im; im = im->next)
+ ip_mc_rejoin_group(im);
+ }
+
+ rcu_read_unlock();
+}
+
/*
* Totally destroys the mc_list in bond
*/
kfree(dmi);
dmi = bond->mc_list;
}
+
+ bond->mc_list = NULL;
}
/*
/*
* flush all members of flush->mc_list from device dev->mc_list
*/
-static void bond_mc_list_flush(struct net_device *bond_dev, struct net_device *slave_dev)
+static void bond_mc_list_flush(struct net_device *bond_dev,
+ struct net_device *slave_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct dev_mc_list *dmi;
- for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) {
+ for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next)
dev_mc_delete(slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
- }
if (bond->params.mode == BOND_MODE_8023AD) {
/* del lacpdu mc addr from mc list */
* old active slaves (if any) according to the multicast mode, and
* promiscuous flags unconditionally.
*/
-static void bond_mc_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active)
+static void bond_mc_swap(struct bonding *bond, struct slave *new_active,
+ struct slave *old_active)
{
struct dev_mc_list *dmi;
- if (!USES_PRIMARY(bond->params.mode)) {
+ if (!USES_PRIMARY(bond->params.mode))
/* nothing to do - mc list is already up-to-date on
* all slaves
*/
return;
- }
if (old_active) {
- if (bond->dev->flags & IFF_PROMISC) {
+ if (bond->dev->flags & IFF_PROMISC)
dev_set_promiscuity(old_active->dev, -1);
- }
- if (bond->dev->flags & IFF_ALLMULTI) {
+ if (bond->dev->flags & IFF_ALLMULTI)
dev_set_allmulti(old_active->dev, -1);
- }
- for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) {
- dev_mc_delete(old_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
- }
+ for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next)
+ dev_mc_delete(old_active->dev, dmi->dmi_addr,
+ dmi->dmi_addrlen, 0);
}
if (new_active) {
- if (bond->dev->flags & IFF_PROMISC) {
+ /* FIXME: Signal errors upstream. */
+ if (bond->dev->flags & IFF_PROMISC)
dev_set_promiscuity(new_active->dev, 1);
- }
- if (bond->dev->flags & IFF_ALLMULTI) {
+ if (bond->dev->flags & IFF_ALLMULTI)
dev_set_allmulti(new_active->dev, 1);
+
+ for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next)
+ dev_mc_add(new_active->dev, dmi->dmi_addr,
+ dmi->dmi_addrlen, 0);
+ bond_resend_igmp_join_requests(bond);
+ }
+}
+
+/*
+ * bond_do_fail_over_mac
+ *
+ * Perform special MAC address swapping for fail_over_mac settings
+ *
+ * Called with RTNL, bond->lock for read, curr_slave_lock for write_bh.
+ */
+static void bond_do_fail_over_mac(struct bonding *bond,
+ struct slave *new_active,
+ struct slave *old_active)
+ __releases(&bond->curr_slave_lock)
+ __releases(&bond->lock)
+ __acquires(&bond->lock)
+ __acquires(&bond->curr_slave_lock)
+{
+ u8 tmp_mac[ETH_ALEN];
+ struct sockaddr saddr;
+ int rv;
+
+ switch (bond->params.fail_over_mac) {
+ case BOND_FOM_ACTIVE:
+ if (new_active)
+ memcpy(bond->dev->dev_addr, new_active->dev->dev_addr,
+ new_active->dev->addr_len);
+ break;
+ case BOND_FOM_FOLLOW:
+ /*
+ * if new_active && old_active, swap them
+ * if just old_active, do nothing (going to no active slave)
+ * if just new_active, set new_active to bond's MAC
+ */
+ if (!new_active)
+ return;
+
+ write_unlock_bh(&bond->curr_slave_lock);
+ read_unlock(&bond->lock);
+
+ if (old_active) {
+ memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
+ memcpy(saddr.sa_data, old_active->dev->dev_addr,
+ ETH_ALEN);
+ saddr.sa_family = new_active->dev->type;
+ } else {
+ memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN);
+ saddr.sa_family = bond->dev->type;
}
- for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) {
- dev_mc_add(new_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
+ rv = dev_set_mac_address(new_active->dev, &saddr);
+ if (rv) {
+ pr_err("%s: Error %d setting MAC of slave %s\n",
+ bond->dev->name, -rv, new_active->dev->name);
+ goto out;
}
+
+ if (!old_active)
+ goto out;
+
+ memcpy(saddr.sa_data, tmp_mac, ETH_ALEN);
+ saddr.sa_family = old_active->dev->type;
+
+ rv = dev_set_mac_address(old_active->dev, &saddr);
+ if (rv)
+ pr_err("%s: Error %d setting MAC of slave %s\n",
+ bond->dev->name, -rv, new_active->dev->name);
+out:
+ read_lock(&bond->lock);
+ write_lock_bh(&bond->curr_slave_lock);
+ break;
+ default:
+ pr_err("%s: bond_do_fail_over_mac impossible: bad policy %d\n",
+ bond->dev->name, bond->params.fail_over_mac);
+ break;
}
+
+}
+
+static bool bond_should_change_active(struct bonding *bond)
+{
+ struct slave *prim = bond->primary_slave;
+ struct slave *curr = bond->curr_active_slave;
+
+ if (!prim || !curr || curr->link != BOND_LINK_UP)
+ return true;
+ if (bond->force_primary) {
+ bond->force_primary = false;
+ return true;
+ }
+ if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER &&
+ (prim->speed < curr->speed ||
+ (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
+ return false;
+ if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE)
+ return false;
+ return true;
}
/**
int mintime = bond->params.updelay;
int i;
- new_active = old_active = bond->curr_active_slave;
+ new_active = bond->curr_active_slave;
if (!new_active) { /* there were no active slaves left */
- if (bond->slave_cnt > 0) { /* found one slave */
+ if (bond->slave_cnt > 0) /* found one slave */
new_active = bond->first_slave;
- } else {
+ else
return NULL; /* still no slave, return NULL */
- }
}
- /* first try the primary link; if arping, a link must tx/rx traffic
- * before it can be considered the curr_active_slave - also, we would skip
- * slaves between the curr_active_slave and primary_slave that may be up
- * and able to arp
- */
if ((bond->primary_slave) &&
- (!bond->params.arp_interval) &&
- (IS_UP(bond->primary_slave->dev))) {
+ bond->primary_slave->link == BOND_LINK_UP &&
+ bond_should_change_active(bond)) {
new_active = bond->primary_slave;
}
old_active = new_active;
bond_for_each_slave_from(bond, new_active, i, old_active) {
- if (IS_UP(new_active->dev)) {
- if (new_active->link == BOND_LINK_UP) {
- return new_active;
- } else if (new_active->link == BOND_LINK_BACK) {
- /* link up, but waiting for stabilization */
- if (new_active->delay < mintime) {
- mintime = new_active->delay;
- bestslave = new_active;
- }
+ if (new_active->link == BOND_LINK_UP) {
+ return new_active;
+ } else if (new_active->link == BOND_LINK_BACK &&
+ IS_UP(new_active->dev)) {
+ /* link up, but waiting for stabilization */
+ if (new_active->delay < mintime) {
+ mintime = new_active->delay;
+ bestslave = new_active;
}
}
}
* because it is apparently the best available slave we have, even though its
* updelay hasn't timed out yet.
*
- * Warning: Caller must hold curr_slave_lock for writing.
+ * If new_active is not NULL, caller must hold bond->lock for read and
+ * curr_slave_lock for write_bh.
*/
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
struct slave *old_active = bond->curr_active_slave;
- if (old_active == new_active) {
+ if (old_active == new_active)
return;
- }
if (new_active) {
+ new_active->jiffies = jiffies;
+
if (new_active->link == BOND_LINK_BACK) {
if (USES_PRIMARY(bond->params.mode)) {
- printk(KERN_INFO DRV_NAME
- ": %s: making interface %s the new "
- "active one %d ms earlier.\n",
- bond->dev->name, new_active->dev->name,
- (bond->params.updelay - new_active->delay) * bond->params.miimon);
+ pr_info("%s: making interface %s the new active one %d ms earlier.\n",
+ bond->dev->name, new_active->dev->name,
+ (bond->params.updelay - new_active->delay) * bond->params.miimon);
}
new_active->delay = 0;
new_active->link = BOND_LINK_UP;
- new_active->jiffies = jiffies;
- if (bond->params.mode == BOND_MODE_8023AD) {
+ if (bond->params.mode == BOND_MODE_8023AD)
bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
- }
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ if (bond_is_lb(bond))
bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
- }
} else {
if (USES_PRIMARY(bond->params.mode)) {
- printk(KERN_INFO DRV_NAME
- ": %s: making interface %s the new "
- "active one.\n",
- bond->dev->name, new_active->dev->name);
+ pr_info("%s: making interface %s the new active one.\n",
+ bond->dev->name, new_active->dev->name);
}
}
}
- if (USES_PRIMARY(bond->params.mode)) {
+ if (USES_PRIMARY(bond->params.mode))
bond_mc_swap(bond, new_active, old_active);
- }
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ if (bond_is_lb(bond)) {
bond_alb_handle_active_change(bond, new_active);
+ if (old_active)
+ bond_set_slave_inactive_flags(old_active);
+ if (new_active)
+ bond_set_slave_active_flags(new_active);
} else {
bond->curr_active_slave = new_active;
}
if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
- if (old_active) {
+ if (old_active)
bond_set_slave_inactive_flags(old_active);
- }
if (new_active) {
bond_set_slave_active_flags(new_active);
+
+ if (bond->params.fail_over_mac)
+ bond_do_fail_over_mac(bond, new_active,
+ old_active);
+
+ bond->send_grat_arp = bond->params.num_grat_arp;
+ bond_send_gratuitous_arp(bond);
+
+ bond->send_unsol_na = bond->params.num_unsol_na;
+ bond_send_unsolicited_na(bond);
+
+ write_unlock_bh(&bond->curr_slave_lock);
+ read_unlock(&bond->lock);
+
+ netdev_bonding_change(bond->dev, NETDEV_BONDING_FAILOVER);
+
+ read_lock(&bond->lock);
+ write_lock_bh(&bond->curr_slave_lock);
}
- bond_send_gratuitous_arp(bond);
}
}
* bond_select_active_slave - select a new active slave, if needed
* @bond: our bonding struct
*
- * This functions shoud be called when one of the following occurs:
+ * This functions should be called when one of the following occurs:
* - The old curr_active_slave has been released or lost its link.
* - The primary_slave has got its link back.
* - A slave has got its link back and there's no old curr_active_slave.
*
- * Warning: Caller must hold curr_slave_lock for writing.
+ * Caller must hold bond->lock for read and curr_slave_lock for write_bh.
*/
void bond_select_active_slave(struct bonding *bond)
{
struct slave *best_slave;
+ int rv;
best_slave = bond_find_best_slave(bond);
if (best_slave != bond->curr_active_slave) {
bond_change_active_slave(bond, best_slave);
+ rv = bond_set_carrier(bond);
+ if (!rv)
+ return;
+
+ if (netif_carrier_ok(bond->dev)) {
+ pr_info("%s: first active interface up!\n",
+ bond->dev->name);
+ } else {
+ pr_info("%s: now running without any active interface !\n",
+ bond->dev->name);
+ }
}
}
*/
static void bond_detach_slave(struct bonding *bond, struct slave *slave)
{
- if (slave->next) {
+ if (slave->next)
slave->next->prev = slave->prev;
- }
- if (slave->prev) {
+ if (slave->prev)
slave->prev->next = slave->next;
- }
if (bond->first_slave == slave) { /* slave is the first slave */
if (bond->slave_cnt > 1) { /* there are more slave */
/*---------------------------------- IOCTL ----------------------------------*/
-int bond_sethwaddr(struct net_device *bond_dev, struct net_device *slave_dev)
+static int bond_sethwaddr(struct net_device *bond_dev,
+ struct net_device *slave_dev)
{
- dprintk("bond_dev=%p\n", bond_dev);
- dprintk("slave_dev=%p\n", slave_dev);
- dprintk("slave_dev->addr_len=%d\n", slave_dev->addr_len);
+ pr_debug("bond_dev=%p\n", bond_dev);
+ pr_debug("slave_dev=%p\n", slave_dev);
+ pr_debug("slave_dev->addr_len=%d\n", slave_dev->addr_len);
memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
return 0;
}
-#define BOND_INTERSECT_FEATURES \
- (NETIF_F_SG|NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM)
+#define BOND_VLAN_FEATURES \
+ (NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX | \
+ NETIF_F_HW_VLAN_FILTER)
-/*
+/*
* Compute the common dev->feature set available to all slaves. Some
- * feature bits are managed elsewhere, so preserve feature bits set on
- * master device that are not part of the examined set.
+ * feature bits are managed elsewhere, so preserve those feature bits
+ * on the master device.
*/
static int bond_compute_features(struct bonding *bond)
{
- unsigned long features = BOND_INTERSECT_FEATURES;
struct slave *slave;
struct net_device *bond_dev = bond->dev;
+ unsigned long features = bond_dev->features;
+ unsigned long vlan_features = 0;
+ unsigned short max_hard_header_len = max((u16)ETH_HLEN,
+ bond_dev->hard_header_len);
int i;
- bond_for_each_slave(bond, slave, i)
- features &= (slave->dev->features & BOND_INTERSECT_FEATURES);
+ features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES);
+ features |= NETIF_F_GSO_MASK | NETIF_F_NO_CSUM;
- if ((features & NETIF_F_SG) &&
- !(features & (NETIF_F_IP_CSUM |
- NETIF_F_NO_CSUM |
- NETIF_F_HW_CSUM)))
- features &= ~NETIF_F_SG;
+ if (!bond->first_slave)
+ goto done;
+
+ features &= ~NETIF_F_ONE_FOR_ALL;
+
+ vlan_features = bond->first_slave->dev->vlan_features;
+ bond_for_each_slave(bond, slave, i) {
+ features = netdev_increment_features(features,
+ slave->dev->features,
+ NETIF_F_ONE_FOR_ALL);
+ vlan_features = netdev_increment_features(vlan_features,
+ slave->dev->vlan_features,
+ NETIF_F_ONE_FOR_ALL);
+ if (slave->dev->hard_header_len > max_hard_header_len)
+ max_hard_header_len = slave->dev->hard_header_len;
+ }
- features |= (bond_dev->features & ~BOND_INTERSECT_FEATURES);
- bond_dev->features = features;
+done:
+ features |= (bond_dev->features & BOND_VLAN_FEATURES);
+ bond_dev->features = netdev_fix_features(features, NULL);
+ bond_dev->vlan_features = netdev_fix_features(vlan_features, NULL);
+ bond_dev->hard_header_len = max_hard_header_len;
return 0;
}
+static void bond_setup_by_slave(struct net_device *bond_dev,
+ struct net_device *slave_dev)
+{
+ struct bonding *bond = netdev_priv(bond_dev);
+
+ bond_dev->header_ops = slave_dev->header_ops;
+
+ bond_dev->type = slave_dev->type;
+ bond_dev->hard_header_len = slave_dev->hard_header_len;
+ bond_dev->addr_len = slave_dev->addr_len;
+
+ memcpy(bond_dev->broadcast, slave_dev->broadcast,
+ slave_dev->addr_len);
+ bond->setup_by_slave = 1;
+}
+
/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct slave *new_slave = NULL;
struct dev_mc_list *dmi;
struct sockaddr addr;
int res = 0;
if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL &&
- slave_dev->do_ioctl == NULL) {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: no link monitoring support for %s\n",
- bond_dev->name, slave_dev->name);
+ slave_ops->ndo_do_ioctl == NULL) {
+ pr_warning("%s: Warning: no link monitoring support for %s\n",
+ bond_dev->name, slave_dev->name);
}
/* bond must be initialized by bond_open() before enslaving */
if (!(bond_dev->flags & IFF_UP)) {
- dprintk("Error, master_dev is not up\n");
- return -EPERM;
+ pr_warning("%s: master_dev is not up in bond_enslave\n",
+ bond_dev->name);
}
/* already enslaved */
if (slave_dev->flags & IFF_SLAVE) {
- dprintk("Error, Device was already enslaved\n");
+ pr_debug("Error, Device was already enslaved\n");
return -EBUSY;
}
/* vlan challenged mutual exclusion */
/* no need to lock since we're protected by rtnl_lock */
if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
- dprintk("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
+ pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
if (!list_empty(&bond->vlan_list)) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: cannot enslave VLAN "
- "challenged slave %s on VLAN enabled "
- "bond %s\n", bond_dev->name, slave_dev->name,
- bond_dev->name);
+ pr_err("%s: Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n",
+ bond_dev->name, slave_dev->name, bond_dev->name);
return -EPERM;
} else {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: enslaved VLAN challenged "
- "slave %s. Adding VLANs will be blocked as "
- "long as %s is part of bond %s\n",
- bond_dev->name, slave_dev->name, slave_dev->name,
- bond_dev->name);
+ pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
+ bond_dev->name, slave_dev->name,
+ slave_dev->name, bond_dev->name);
bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
}
} else {
- dprintk("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
+ pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
if (bond->slave_cnt == 0) {
/* First slave, and it is not VLAN challenged,
* so remove the block of adding VLANs over the bond.
/*
* Old ifenslave binaries are no longer supported. These can
- * be identified with moderate accurary by the state of the slave:
+ * be identified with moderate accuracy by the state of the slave:
* the current ifenslave will set the interface down prior to
* enslaving it; the old ifenslave will not.
*/
if ((slave_dev->flags & IFF_UP)) {
- printk(KERN_ERR DRV_NAME ": %s is up. "
- "This may be due to an out of date ifenslave.\n",
+ pr_err("%s is up. This may be due to an out of date ifenslave.\n",
slave_dev->name);
res = -EPERM;
goto err_undo_flags;
}
- if (slave_dev->set_mac_address == NULL) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: The slave device you specified does "
- "not support setting the MAC address. "
- "Your kernel likely does not support slave "
- "devices.\n", bond_dev->name);
- res = -EOPNOTSUPP;
+ /* set bonding device ether type by slave - bonding netdevices are
+ * created with ether_setup, so when the slave type is not ARPHRD_ETHER
+ * there is a need to override some of the type dependent attribs/funcs.
+ *
+ * bond ether type mutual exclusion - don't allow slaves of dissimilar
+ * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
+ */
+ if (bond->slave_cnt == 0) {
+ if (bond_dev->type != slave_dev->type) {
+ pr_debug("%s: change device type from %d to %d\n",
+ bond_dev->name,
+ bond_dev->type, slave_dev->type);
+
+ netdev_bonding_change(bond_dev, NETDEV_BONDING_OLDTYPE);
+
+ if (slave_dev->type != ARPHRD_ETHER)
+ bond_setup_by_slave(bond_dev, slave_dev);
+ else
+ ether_setup(bond_dev);
+
+ netdev_bonding_change(bond_dev, NETDEV_BONDING_NEWTYPE);
+ }
+ } else if (bond_dev->type != slave_dev->type) {
+ pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n",
+ slave_dev->name,
+ slave_dev->type, bond_dev->type);
+ res = -EINVAL;
goto err_undo_flags;
}
- new_slave = kmalloc(sizeof(struct slave), GFP_KERNEL);
+ if (slave_ops->ndo_set_mac_address == NULL) {
+ if (bond->slave_cnt == 0) {
+ pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.",
+ bond_dev->name);
+ bond->params.fail_over_mac = BOND_FOM_ACTIVE;
+ } else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
+ pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n",
+ bond_dev->name);
+ res = -EOPNOTSUPP;
+ goto err_undo_flags;
+ }
+ }
+
+ new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
if (!new_slave) {
res = -ENOMEM;
goto err_undo_flags;
}
- memset(new_slave, 0, sizeof(struct slave));
-
/* save slave's original flags before calling
* netdev_set_master and dev_open
*/
*/
memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);
- /*
- * Set slave to master's mac address. The application already
- * set the master's mac address to that of the first slave
- */
- memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
- addr.sa_family = slave_dev->type;
- res = dev_set_mac_address(slave_dev, &addr);
- if (res) {
- dprintk("Error %d calling set_mac_address\n", res);
- goto err_free;
+ if (!bond->params.fail_over_mac) {
+ /*
+ * Set slave to master's mac address. The application already
+ * set the master's mac address to that of the first slave
+ */
+ memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
+ addr.sa_family = slave_dev->type;
+ res = dev_set_mac_address(slave_dev, &addr);
+ if (res) {
+ pr_debug("Error %d calling set_mac_address\n", res);
+ goto err_free;
+ }
}
- /* open the slave since the application closed it */
- res = dev_open(slave_dev);
+ res = netdev_set_master(slave_dev, bond_dev);
if (res) {
- dprintk("Openning slave %s failed\n", slave_dev->name);
+ pr_debug("Error %d calling netdev_set_master\n", res);
goto err_restore_mac;
}
-
- res = netdev_set_master(slave_dev, bond_dev);
+ /* open the slave since the application closed it */
+ res = dev_open(slave_dev);
if (res) {
- dprintk("Error %d calling netdev_set_master\n", res);
- goto err_close;
+ pr_debug("Opening slave %s failed\n", slave_dev->name);
+ goto err_unset_master;
}
new_slave->dev = slave_dev;
+ slave_dev->priv_flags |= IFF_BONDING;
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ if (bond_is_lb(bond)) {
/* bond_alb_init_slave() must be called before all other stages since
* it might fail and we do not want to have to undo everything
*/
res = bond_alb_init_slave(bond, new_slave);
- if (res) {
- goto err_unset_master;
- }
+ if (res)
+ goto err_close;
}
/* If the mode USES_PRIMARY, then the new slave gets the
if (!USES_PRIMARY(bond->params.mode)) {
/* set promiscuity level to new slave */
if (bond_dev->flags & IFF_PROMISC) {
- dev_set_promiscuity(slave_dev, 1);
+ res = dev_set_promiscuity(slave_dev, 1);
+ if (res)
+ goto err_close;
}
/* set allmulti level to new slave */
if (bond_dev->flags & IFF_ALLMULTI) {
- dev_set_allmulti(slave_dev, 1);
+ res = dev_set_allmulti(slave_dev, 1);
+ if (res)
+ goto err_close;
}
+ netif_addr_lock_bh(bond_dev);
/* upload master's mc_list to new slave */
- for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) {
- dev_mc_add (slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
- }
+ for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next)
+ dev_mc_add(slave_dev, dmi->dmi_addr,
+ dmi->dmi_addrlen, 0);
+ netif_addr_unlock_bh(bond_dev);
}
if (bond->params.mode == BOND_MODE_8023AD) {
bond_compute_features(bond);
+ write_unlock_bh(&bond->lock);
+
+ read_lock(&bond->lock);
+
+ new_slave->last_arp_rx = jiffies;
+
if (bond->params.miimon && !bond->params.use_carrier) {
link_reporting = bond_check_dev_link(bond, slave_dev, 1);
* supported); thus, we don't need to change
* the messages for netif_carrier.
*/
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: MII and ETHTOOL support not "
- "available for interface %s, and "
- "arp_interval/arp_ip_target module parameters "
- "not specified, thus bonding will not detect "
- "link failures! see bonding.txt for details.\n",
+ pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n",
bond_dev->name, slave_dev->name);
} else if (link_reporting == -1) {
/* unable get link status using mii/ethtool */
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: can't get link status from "
- "interface %s; the network driver associated "
- "with this interface does not support MII or "
- "ETHTOOL link status reporting, thus miimon "
- "has no effect on this interface.\n",
- bond_dev->name, slave_dev->name);
+ pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n",
+ bond_dev->name, slave_dev->name);
}
}
if (!bond->params.miimon ||
(bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS)) {
if (bond->params.updelay) {
- dprintk("Initial state of slave_dev is "
- "BOND_LINK_BACK\n");
+ pr_debug("Initial state of slave_dev is BOND_LINK_BACK\n");
new_slave->link = BOND_LINK_BACK;
new_slave->delay = bond->params.updelay;
} else {
- dprintk("Initial state of slave_dev is "
- "BOND_LINK_UP\n");
+ pr_debug("Initial state of slave_dev is BOND_LINK_UP\n");
new_slave->link = BOND_LINK_UP;
}
new_slave->jiffies = jiffies;
} else {
- dprintk("Initial state of slave_dev is "
- "BOND_LINK_DOWN\n");
+ pr_debug("Initial state of slave_dev is BOND_LINK_DOWN\n");
new_slave->link = BOND_LINK_DOWN;
}
if (bond_update_speed_duplex(new_slave) &&
(new_slave->link != BOND_LINK_DOWN)) {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: failed to get speed and duplex from %s, "
- "assumed to be 100Mb/sec and Full.\n",
- bond_dev->name, new_slave->dev->name);
+ pr_warning("%s: Warning: failed to get speed and duplex from %s, assumed to be 100Mb/sec and Full.\n",
+ bond_dev->name, new_slave->dev->name);
if (bond->params.mode == BOND_MODE_8023AD) {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: Operation of 802.3ad mode requires ETHTOOL "
- "support in base driver for proper aggregator "
- "selection.\n", bond_dev->name);
+ pr_warning("%s: Warning: Operation of 802.3ad mode requires ETHTOOL support in base driver for proper aggregator selection.\n",
+ bond_dev->name);
}
}
/* if there is a primary slave, remember it */
if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
bond->primary_slave = new_slave;
+ bond->force_primary = true;
}
}
+ write_lock_bh(&bond->curr_slave_lock);
+
switch (bond->params.mode) {
case BOND_MODE_ACTIVEBACKUP:
- /* if we're in active-backup mode, we need one and only one active
- * interface. The backup interfaces will have their NOARP flag set
- * because we need them to be completely deaf and not to respond to
- * any ARP request on the network to avoid fooling a switch. Thus,
- * since we guarantee that curr_active_slave always point to the last
- * usable interface, we just have to verify this interface's flag.
- */
- if (((!bond->curr_active_slave) ||
- (bond->curr_active_slave->dev->flags & IFF_NOARP)) &&
- (new_slave->link != BOND_LINK_DOWN)) {
- dprintk("This is the first active slave\n");
- /* first slave or no active slave yet, and this link
- is OK, so make this interface the active one */
- bond_change_active_slave(bond, new_slave);
- } else {
- dprintk("This is just a backup slave\n");
- bond_set_slave_inactive_flags(new_slave);
- }
+ bond_set_slave_inactive_flags(new_slave);
+ bond_select_active_slave(bond);
break;
case BOND_MODE_8023AD:
/* in 802.3ad mode, the internal mechanism
case BOND_MODE_TLB:
case BOND_MODE_ALB:
new_slave->state = BOND_STATE_ACTIVE;
- if ((!bond->curr_active_slave) &&
- (new_slave->link != BOND_LINK_DOWN)) {
- /* first slave or no active slave yet, and this link
- * is OK, so make this interface the active one
- */
- bond_change_active_slave(bond, new_slave);
- }
+ bond_set_slave_inactive_flags(new_slave);
+ bond_select_active_slave(bond);
break;
default:
- dprintk("This slave is always active in trunk mode\n");
+ pr_debug("This slave is always active in trunk mode\n");
/* always active in trunk mode */
new_slave->state = BOND_STATE_ACTIVE;
* anyway (it holds no special properties of the bond device),
* so we can change it without calling change_active_interface()
*/
- if (!bond->curr_active_slave) {
+ if (!bond->curr_active_slave)
bond->curr_active_slave = new_slave;
- }
+
break;
} /* switch(bond_mode) */
- write_unlock_bh(&bond->lock);
+ write_unlock_bh(&bond->curr_slave_lock);
+
+ bond_set_carrier(bond);
+
+ read_unlock(&bond->lock);
+
+ res = bond_create_slave_symlinks(bond_dev, slave_dev);
+ if (res)
+ goto err_close;
- printk(KERN_INFO DRV_NAME
- ": %s: enslaving %s as a%s interface with a%s link.\n",
- bond_dev->name, slave_dev->name,
- new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup",
- new_slave->link != BOND_LINK_DOWN ? "n up" : " down");
+ pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
+ bond_dev->name, slave_dev->name,
+ new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup",
+ new_slave->link != BOND_LINK_DOWN ? "n up" : " down");
/* enslave is successful */
return 0;
/* Undo stages on error */
-err_unset_master:
- netdev_set_master(slave_dev, NULL);
-
err_close:
dev_close(slave_dev);
+err_unset_master:
+ netdev_set_master(slave_dev, NULL);
+
err_restore_mac:
- memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
+ if (!bond->params.fail_over_mac) {
+ /* XXX TODO - fom follow mode needs to change master's
+ * MAC if this slave's MAC is in use by the bond, or at
+ * least print a warning.
+ */
+ memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
+ addr.sa_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, &addr);
+ }
err_free:
kfree(new_slave);
err_undo_flags:
bond_dev->features = old_features;
-
+
return res;
}
*/
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
struct sockaddr addr;
- int mac_addr_differ;
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
(slave_dev->master != bond_dev)) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: cannot release %s.\n",
+ pr_err("%s: Error: cannot release %s.\n",
bond_dev->name, slave_dev->name);
return -EINVAL;
}
slave = bond_get_slave_by_dev(bond, slave_dev);
if (!slave) {
/* not a slave of this bond */
- printk(KERN_INFO DRV_NAME
- ": %s: %s not enslaved\n",
- bond_dev->name, slave_dev->name);
+ pr_info("%s: %s not enslaved\n",
+ bond_dev->name, slave_dev->name);
+ write_unlock_bh(&bond->lock);
return -EINVAL;
}
- mac_addr_differ = memcmp(bond_dev->dev_addr,
- slave->perm_hwaddr,
- ETH_ALEN);
- if (!mac_addr_differ && (bond->slave_cnt > 1)) {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: the permanent HWaddr of %s "
- "- %02X:%02X:%02X:%02X:%02X:%02X - is "
- "still in use by %s. Set the HWaddr of "
- "%s to a different address to avoid "
- "conflicts.\n",
- bond_dev->name,
- slave_dev->name,
- slave->perm_hwaddr[0],
- slave->perm_hwaddr[1],
- slave->perm_hwaddr[2],
- slave->perm_hwaddr[3],
- slave->perm_hwaddr[4],
- slave->perm_hwaddr[5],
- bond_dev->name,
- slave_dev->name);
+ if (!bond->params.fail_over_mac) {
+ if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) &&
+ bond->slave_cnt > 1)
+ pr_warning("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
+ bond_dev->name, slave_dev->name,
+ slave->perm_hwaddr,
+ bond_dev->name, slave_dev->name);
}
/* Inform AD package of unbinding of slave. */
bond_3ad_unbind_slave(slave);
}
- printk(KERN_INFO DRV_NAME
- ": %s: releasing %s interface %s\n",
- bond_dev->name,
- (slave->state == BOND_STATE_ACTIVE)
- ? "active" : "backup",
- slave_dev->name);
+ pr_info("%s: releasing %s interface %s\n",
+ bond_dev->name,
+ (slave->state == BOND_STATE_ACTIVE) ? "active" : "backup",
+ slave_dev->name);
oldcurrent = bond->curr_active_slave;
bond_compute_features(bond);
- if (bond->primary_slave == slave) {
+ if (bond->primary_slave == slave)
bond->primary_slave = NULL;
- }
- if (oldcurrent == slave) {
+ if (oldcurrent == slave)
bond_change_active_slave(bond, NULL);
- }
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ if (bond_is_lb(bond)) {
/* Must be called only after the slave has been
* detached from the list and the curr_active_slave
* has been cleared (if our_slave == old_current),
* but before a new active slave is selected.
*/
+ write_unlock_bh(&bond->lock);
bond_alb_deinit_slave(bond, slave);
+ write_lock_bh(&bond->lock);
}
if (oldcurrent == slave) {
+ /*
+ * Note that we hold RTNL over this sequence, so there
+ * is no concern that another slave add/remove event
+ * will interfere.
+ */
+ write_unlock_bh(&bond->lock);
+ read_lock(&bond->lock);
+ write_lock_bh(&bond->curr_slave_lock);
+
bond_select_active_slave(bond);
- if (!bond->curr_active_slave) {
- printk(KERN_INFO DRV_NAME
- ": %s: now running without any active "
- "interface !\n",
- bond_dev->name);
- }
+ write_unlock_bh(&bond->curr_slave_lock);
+ read_unlock(&bond->lock);
+ write_lock_bh(&bond->lock);
}
if (bond->slave_cnt == 0) {
+ bond_set_carrier(bond);
+
/* if the last slave was removed, zero the mac address
* of the master so it will be set by the application
* to the mac address of the first slave
if (list_empty(&bond->vlan_list)) {
bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
} else {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: clearing HW address of %s while it "
- "still has VLANs.\n",
- bond_dev->name, bond_dev->name);
- printk(KERN_WARNING DRV_NAME
- ": %s: When re-adding slaves, make sure the bond's "
- "HW address matches its VLANs'.\n",
- bond_dev->name);
+ pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
+ bond_dev->name, bond_dev->name);
+ pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
+ bond_dev->name);
}
} else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
!bond_has_challenged_slaves(bond)) {
- printk(KERN_INFO DRV_NAME
- ": %s: last VLAN challenged slave %s "
- "left bond %s. VLAN blocking is removed\n",
- bond_dev->name, slave_dev->name, bond_dev->name);
+ pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n",
+ bond_dev->name, slave_dev->name, bond_dev->name);
bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
}
write_unlock_bh(&bond->lock);
+ /* must do this from outside any spinlocks */
+ bond_destroy_slave_symlinks(bond_dev, slave_dev);
+
bond_del_vlans_from_slave(bond, slave_dev);
/* If the mode USES_PRIMARY, then we should only remove its
*/
if (!USES_PRIMARY(bond->params.mode)) {
/* unset promiscuity level from slave */
- if (bond_dev->flags & IFF_PROMISC) {
+ if (bond_dev->flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
- }
/* unset allmulti level from slave */
- if (bond_dev->flags & IFF_ALLMULTI) {
+ if (bond_dev->flags & IFF_ALLMULTI)
dev_set_allmulti(slave_dev, -1);
- }
/* flush master's mc_list from slave */
+ netif_addr_lock_bh(bond_dev);
bond_mc_list_flush(bond_dev, slave_dev);
+ netif_addr_unlock_bh(bond_dev);
}
netdev_set_master(slave_dev, NULL);
/* close slave before restoring its mac address */
dev_close(slave_dev);
- /* restore original ("permanent") mac address */
- memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
-
- /* restore the original state of the
- * IFF_NOARP flag that might have been
- * set by bond_set_slave_inactive_flags()
- */
- if ((slave->original_flags & IFF_NOARP) == 0) {
- slave_dev->flags &= ~IFF_NOARP;
+ if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
+ /* restore original ("permanent") mac address */
+ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+ addr.sa_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, &addr);
}
+ slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
+ IFF_SLAVE_INACTIVE | IFF_BONDING |
+ IFF_SLAVE_NEEDARP);
+
kfree(slave);
return 0; /* deletion OK */
}
/*
+* First release a slave and than destroy the bond if no more slaves are left.
+* Must be under rtnl_lock when this function is called.
+*/
+int bond_release_and_destroy(struct net_device *bond_dev,
+ struct net_device *slave_dev)
+{
+ struct bonding *bond = netdev_priv(bond_dev);
+ int ret;
+
+ ret = bond_release(bond_dev, slave_dev);
+ if ((ret == 0) && (bond->slave_cnt == 0)) {
+ pr_info("%s: destroying bond %s.\n",
+ bond_dev->name, bond_dev->name);
+ unregister_netdevice(bond_dev);
+ }
+ return ret;
+}
+
+/*
* This function releases all slaves.
*/
static int bond_release_all(struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
struct net_device *slave_dev;
struct sockaddr addr;
write_lock_bh(&bond->lock);
- if (bond->slave_cnt == 0) {
+ netif_carrier_off(bond_dev);
+
+ if (bond->slave_cnt == 0)
goto out;
- }
bond->current_arp_slave = NULL;
bond->primary_slave = NULL;
/* Inform AD package of unbinding of slave
* before slave is detached from the list.
*/
- if (bond->params.mode == BOND_MODE_8023AD) {
+ if (bond->params.mode == BOND_MODE_8023AD)
bond_3ad_unbind_slave(slave);
- }
slave_dev = slave->dev;
bond_detach_slave(bond, slave);
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ /* now that the slave is detached, unlock and perform
+ * all the undo steps that should not be called from
+ * within a lock.
+ */
+ write_unlock_bh(&bond->lock);
+
+ if (bond_is_lb(bond)) {
/* must be called only after the slave
* has been detached from the list
*/
bond_compute_features(bond);
- /* now that the slave is detached, unlock and perform
- * all the undo steps that should not be called from
- * within a lock.
- */
- write_unlock_bh(&bond->lock);
-
+ bond_destroy_slave_symlinks(bond_dev, slave_dev);
bond_del_vlans_from_slave(bond, slave_dev);
/* If the mode USES_PRIMARY, then we should only remove its
*/
if (!USES_PRIMARY(bond->params.mode)) {
/* unset promiscuity level from slave */
- if (bond_dev->flags & IFF_PROMISC) {
+ if (bond_dev->flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
- }
/* unset allmulti level from slave */
- if (bond_dev->flags & IFF_ALLMULTI) {
+ if (bond_dev->flags & IFF_ALLMULTI)
dev_set_allmulti(slave_dev, -1);
- }
/* flush master's mc_list from slave */
+ netif_addr_lock_bh(bond_dev);
bond_mc_list_flush(bond_dev, slave_dev);
+ netif_addr_unlock_bh(bond_dev);
}
netdev_set_master(slave_dev, NULL);
/* close slave before restoring its mac address */
dev_close(slave_dev);
- /* restore original ("permanent") mac address*/
- memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
-
- /* restore the original state of the IFF_NOARP flag that might have
- * been set by bond_set_slave_inactive_flags()
- */
- if ((slave->original_flags & IFF_NOARP) == 0) {
- slave_dev->flags &= ~IFF_NOARP;
+ if (!bond->params.fail_over_mac) {
+ /* restore original ("permanent") mac address*/
+ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+ addr.sa_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, &addr);
}
+ slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
+ IFF_SLAVE_INACTIVE);
+
kfree(slave);
/* re-acquire the lock before getting the next slave */
*/
memset(bond_dev->dev_addr, 0, bond_dev->addr_len);
- if (list_empty(&bond->vlan_list)) {
+ if (list_empty(&bond->vlan_list))
bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
- } else {
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: clearing HW address of %s while it "
- "still has VLANs.\n",
- bond_dev->name, bond_dev->name);
- printk(KERN_WARNING DRV_NAME
- ": %s: When re-adding slaves, make sure the bond's "
- "HW address matches its VLANs'.\n",
- bond_dev->name);
+ else {
+ pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
+ bond_dev->name, bond_dev->name);
+ pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
+ bond_dev->name);
}
- printk(KERN_INFO DRV_NAME
- ": %s: released all slaves\n",
- bond_dev->name);
+ pr_info("%s: released all slaves\n", bond_dev->name);
out:
write_unlock_bh(&bond->lock);
* - <slave_dev> is already active.
* - The link state of <slave_dev> is not BOND_LINK_UP.
* - <slave_dev> is not running.
- * In these cases, this fuction does nothing.
- * In the other cases, currnt_slave pointer is changed and 0 is returned.
+ * In these cases, this function does nothing.
+ * In the other cases, current_slave pointer is changed and 0 is returned.
*/
static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *old_active = NULL;
struct slave *new_active = NULL;
int res = 0;
- if (!USES_PRIMARY(bond->params.mode)) {
+ if (!USES_PRIMARY(bond->params.mode))
return -EINVAL;
- }
/* Verify that master_dev is indeed the master of slave_dev */
- if (!(slave_dev->flags & IFF_SLAVE) ||
- (slave_dev->master != bond_dev)) {
+ if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev))
return -EINVAL;
- }
- write_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
+ read_lock(&bond->curr_slave_lock);
old_active = bond->curr_active_slave;
+ read_unlock(&bond->curr_slave_lock);
+
new_active = bond_get_slave_by_dev(bond, slave_dev);
/*
* Changing to the current active: do nothing; return success.
*/
if (new_active && (new_active == old_active)) {
- write_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
return 0;
}
(old_active) &&
(new_active->link == BOND_LINK_UP) &&
IS_UP(new_active->dev)) {
+ write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, new_active);
- } else {
+ write_unlock_bh(&bond->curr_slave_lock);
+ } else
res = -EINVAL;
- }
- write_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
return res;
}
static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
info->bond_mode = bond->params.mode;
info->miimon = bond->params.miimon;
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
info->num_slaves = bond->slave_cnt;
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
return 0;
}
static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
- int i, found = 0;
+ int i, res = -ENODEV;
- if (info->slave_id < 0) {
- return -ENODEV;
- }
-
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
bond_for_each_slave(bond, slave, i) {
if (i == (int)info->slave_id) {
- found = 1;
+ res = 0;
+ strcpy(info->slave_name, slave->dev->name);
+ info->link = slave->link;
+ info->state = slave->state;
+ info->link_failure_count = slave->link_failure_count;
break;
}
}
- read_unlock_bh(&bond->lock);
-
- if (found) {
- strcpy(info->slave_name, slave->dev->name);
- info->link = slave->link;
- info->state = slave->state;
- info->link_failure_count = slave->link_failure_count;
- } else {
- return -ENODEV;
- }
+ read_unlock(&bond->lock);
- return 0;
+ return res;
}
/*-------------------------------- Monitoring -------------------------------*/
-/* this function is called regularly to monitor each slave's link. */
-void bond_mii_monitor(struct net_device *bond_dev)
-{
- struct bonding *bond = bond_dev->priv;
- struct slave *slave, *oldcurrent;
- int do_failover = 0;
- int delta_in_ticks;
- int i;
-
- read_lock(&bond->lock);
-
- delta_in_ticks = (bond->params.miimon * HZ) / 1000;
-
- if (bond->kill_timers) {
- goto out;
- }
-
- if (bond->slave_cnt == 0) {
- goto re_arm;
- }
- /* we will try to read the link status of each of our slaves, and
- * set their IFF_RUNNING flag appropriately. For each slave not
- * supporting MII status, we won't do anything so that a user-space
- * program could monitor the link itself if needed.
- */
+static int bond_miimon_inspect(struct bonding *bond)
+{
+ struct slave *slave;
+ int i, link_state, commit = 0;
+ bool ignore_updelay;
- read_lock(&bond->curr_slave_lock);
- oldcurrent = bond->curr_active_slave;
- read_unlock(&bond->curr_slave_lock);
+ ignore_updelay = !bond->curr_active_slave ? true : false;
bond_for_each_slave(bond, slave, i) {
- struct net_device *slave_dev = slave->dev;
- int link_state;
- u16 old_speed = slave->speed;
- u8 old_duplex = slave->duplex;
+ slave->new_link = BOND_LINK_NOCHANGE;
- link_state = bond_check_dev_link(bond, slave_dev, 0);
+ link_state = bond_check_dev_link(bond, slave->dev, 0);
switch (slave->link) {
- case BOND_LINK_UP: /* the link was up */
- if (link_state == BMSR_LSTATUS) {
- /* link stays up, nothing more to do */
- break;
- } else { /* link going down */
- slave->link = BOND_LINK_FAIL;
- slave->delay = bond->params.downdelay;
-
- if (slave->link_failure_count < UINT_MAX) {
- slave->link_failure_count++;
- }
+ case BOND_LINK_UP:
+ if (link_state)
+ continue;
- if (bond->params.downdelay) {
- printk(KERN_INFO DRV_NAME
- ": %s: link status down for %s "
- "interface %s, disabling it in "
- "%d ms.\n",
- bond_dev->name,
- IS_UP(slave_dev)
- ? ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
- ? ((slave == oldcurrent)
- ? "active " : "backup ")
- : "")
- : "idle ",
- slave_dev->name,
- bond->params.downdelay * bond->params.miimon);
- }
+ slave->link = BOND_LINK_FAIL;
+ slave->delay = bond->params.downdelay;
+ if (slave->delay) {
+ pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n",
+ bond->dev->name,
+ (bond->params.mode ==
+ BOND_MODE_ACTIVEBACKUP) ?
+ ((slave->state == BOND_STATE_ACTIVE) ?
+ "active " : "backup ") : "",
+ slave->dev->name,
+ bond->params.downdelay * bond->params.miimon);
}
- /* no break ! fall through the BOND_LINK_FAIL test to
- ensure proper action to be taken
- */
- case BOND_LINK_FAIL: /* the link has just gone down */
- if (link_state != BMSR_LSTATUS) {
- /* link stays down */
- if (slave->delay <= 0) {
- /* link down for too long time */
- slave->link = BOND_LINK_DOWN;
-
- /* in active/backup mode, we must
- * completely disable this interface
- */
- if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) ||
- (bond->params.mode == BOND_MODE_8023AD)) {
- bond_set_slave_inactive_flags(slave);
- }
-
- printk(KERN_INFO DRV_NAME
- ": %s: link status definitely "
- "down for interface %s, "
- "disabling it\n",
- bond_dev->name,
- slave_dev->name);
-
- /* notify ad that the link status has changed */
- if (bond->params.mode == BOND_MODE_8023AD) {
- bond_3ad_handle_link_change(slave, BOND_LINK_DOWN);
- }
-
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
- bond_alb_handle_link_change(bond, slave, BOND_LINK_DOWN);
- }
-
- if (slave == oldcurrent) {
- do_failover = 1;
- }
- } else {
- slave->delay--;
- }
- } else {
- /* link up again */
- slave->link = BOND_LINK_UP;
+ /*FALLTHRU*/
+ case BOND_LINK_FAIL:
+ if (link_state) {
+ /*
+ * recovered before downdelay expired
+ */
+ slave->link = BOND_LINK_UP;
slave->jiffies = jiffies;
- printk(KERN_INFO DRV_NAME
- ": %s: link status up again after %d "
- "ms for interface %s.\n",
- bond_dev->name,
- (bond->params.downdelay - slave->delay) * bond->params.miimon,
- slave_dev->name);
- }
- break;
- case BOND_LINK_DOWN: /* the link was down */
- if (link_state != BMSR_LSTATUS) {
- /* the link stays down, nothing more to do */
- break;
- } else { /* link going up */
- slave->link = BOND_LINK_BACK;
- slave->delay = bond->params.updelay;
-
- if (bond->params.updelay) {
- /* if updelay == 0, no need to
- advertise about a 0 ms delay */
- printk(KERN_INFO DRV_NAME
- ": %s: link status up for "
- "interface %s, enabling it "
- "in %d ms.\n",
- bond_dev->name,
- slave_dev->name,
- bond->params.updelay * bond->params.miimon);
- }
+ pr_info("%s: link status up again after %d ms for interface %s.\n",
+ bond->dev->name,
+ (bond->params.downdelay - slave->delay) *
+ bond->params.miimon,
+ slave->dev->name);
+ continue;
}
- /* no break ! fall through the BOND_LINK_BACK state in
- case there's something to do.
- */
- case BOND_LINK_BACK: /* the link has just come back */
- if (link_state != BMSR_LSTATUS) {
- /* link down again */
- slave->link = BOND_LINK_DOWN;
- printk(KERN_INFO DRV_NAME
- ": %s: link status down again after %d "
- "ms for interface %s.\n",
- bond_dev->name,
- (bond->params.updelay - slave->delay) * bond->params.miimon,
- slave_dev->name);
- } else {
- /* link stays up */
- if (slave->delay == 0) {
- /* now the link has been up for long time enough */
- slave->link = BOND_LINK_UP;
- slave->jiffies = jiffies;
-
- if (bond->params.mode == BOND_MODE_8023AD) {
- /* prevent it from being the active one */
- slave->state = BOND_STATE_BACKUP;
- } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
- /* make it immediately active */
- slave->state = BOND_STATE_ACTIVE;
- } else if (slave != bond->primary_slave) {
- /* prevent it from being the active one */
- slave->state = BOND_STATE_BACKUP;
- }
-
- printk(KERN_INFO DRV_NAME
- ": %s: link status definitely "
- "up for interface %s.\n",
- bond_dev->name,
- slave_dev->name);
-
- /* notify ad that the link status has changed */
- if (bond->params.mode == BOND_MODE_8023AD) {
- bond_3ad_handle_link_change(slave, BOND_LINK_UP);
- }
-
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
- bond_alb_handle_link_change(bond, slave, BOND_LINK_UP);
- }
-
- if ((!oldcurrent) ||
- (slave == bond->primary_slave)) {
- do_failover = 1;
- }
- } else {
- slave->delay--;
- }
+ if (slave->delay <= 0) {
+ slave->new_link = BOND_LINK_DOWN;
+ commit++;
+ continue;
}
+
+ slave->delay--;
break;
- default:
- /* Should not happen */
- printk(KERN_ERR DRV_NAME
- ": %s: Error: %s Illegal value (link=%d)\n",
- bond_dev->name,
- slave->dev->name,
- slave->link);
- goto out;
- } /* end of switch (slave->link) */
- bond_update_speed_duplex(slave);
+ case BOND_LINK_DOWN:
+ if (!link_state)
+ continue;
- if (bond->params.mode == BOND_MODE_8023AD) {
- if (old_speed != slave->speed) {
- bond_3ad_adapter_speed_changed(slave);
+ slave->link = BOND_LINK_BACK;
+ slave->delay = bond->params.updelay;
+
+ if (slave->delay) {
+ pr_info("%s: link status up for interface %s, enabling it in %d ms.\n",
+ bond->dev->name, slave->dev->name,
+ ignore_updelay ? 0 :
+ bond->params.updelay *
+ bond->params.miimon);
}
+ /*FALLTHRU*/
+ case BOND_LINK_BACK:
+ if (!link_state) {
+ slave->link = BOND_LINK_DOWN;
+ pr_info("%s: link status down again after %d ms for interface %s.\n",
+ bond->dev->name,
+ (bond->params.updelay - slave->delay) *
+ bond->params.miimon,
+ slave->dev->name);
- if (old_duplex != slave->duplex) {
- bond_3ad_adapter_duplex_changed(slave);
+ continue;
+ }
+
+ if (ignore_updelay)
+ slave->delay = 0;
+
+ if (slave->delay <= 0) {
+ slave->new_link = BOND_LINK_UP;
+ commit++;
+ ignore_updelay = false;
+ continue;
}
+
+ slave->delay--;
+ break;
}
+ }
- } /* end of for */
+ return commit;
+}
- if (do_failover) {
- write_lock(&bond->curr_slave_lock);
+static void bond_miimon_commit(struct bonding *bond)
+{
+ struct slave *slave;
+ int i;
- bond_select_active_slave(bond);
+ bond_for_each_slave(bond, slave, i) {
+ switch (slave->new_link) {
+ case BOND_LINK_NOCHANGE:
+ continue;
- if (oldcurrent && !bond->curr_active_slave) {
- printk(KERN_INFO DRV_NAME
- ": %s: now running without any active "
- "interface !\n",
- bond_dev->name);
+ case BOND_LINK_UP:
+ slave->link = BOND_LINK_UP;
+ slave->jiffies = jiffies;
+
+ if (bond->params.mode == BOND_MODE_8023AD) {
+ /* prevent it from being the active one */
+ slave->state = BOND_STATE_BACKUP;
+ } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+ /* make it immediately active */
+ slave->state = BOND_STATE_ACTIVE;
+ } else if (slave != bond->primary_slave) {
+ /* prevent it from being the active one */
+ slave->state = BOND_STATE_BACKUP;
+ }
+
+ pr_info("%s: link status definitely up for interface %s.\n",
+ bond->dev->name, slave->dev->name);
+
+ /* notify ad that the link status has changed */
+ if (bond->params.mode == BOND_MODE_8023AD)
+ bond_3ad_handle_link_change(slave, BOND_LINK_UP);
+
+ if (bond_is_lb(bond))
+ bond_alb_handle_link_change(bond, slave,
+ BOND_LINK_UP);
+
+ if (!bond->curr_active_slave ||
+ (slave == bond->primary_slave))
+ goto do_failover;
+
+ continue;
+
+ case BOND_LINK_DOWN:
+ if (slave->link_failure_count < UINT_MAX)
+ slave->link_failure_count++;
+
+ slave->link = BOND_LINK_DOWN;
+
+ if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
+ bond->params.mode == BOND_MODE_8023AD)
+ bond_set_slave_inactive_flags(slave);
+
+ pr_info("%s: link status definitely down for interface %s, disabling it\n",
+ bond->dev->name, slave->dev->name);
+
+ if (bond->params.mode == BOND_MODE_8023AD)
+ bond_3ad_handle_link_change(slave,
+ BOND_LINK_DOWN);
+
+ if (bond_is_lb(bond))
+ bond_alb_handle_link_change(bond, slave,
+ BOND_LINK_DOWN);
+
+ if (slave == bond->curr_active_slave)
+ goto do_failover;
+
+ continue;
+
+ default:
+ pr_err("%s: invalid new link %d on slave %s\n",
+ bond->dev->name, slave->new_link,
+ slave->dev->name);
+ slave->new_link = BOND_LINK_NOCHANGE;
+
+ continue;
}
- write_unlock(&bond->curr_slave_lock);
+do_failover:
+ ASSERT_RTNL();
+ write_lock_bh(&bond->curr_slave_lock);
+ bond_select_active_slave(bond);
+ write_unlock_bh(&bond->curr_slave_lock);
+ }
+
+ bond_set_carrier(bond);
+}
+
+/*
+ * bond_mii_monitor
+ *
+ * Really a wrapper that splits the mii monitor into two phases: an
+ * inspection, then (if inspection indicates something needs to be done)
+ * an acquisition of appropriate locks followed by a commit phase to
+ * implement whatever link state changes are indicated.
+ */
+void bond_mii_monitor(struct work_struct *work)
+{
+ struct bonding *bond = container_of(work, struct bonding,
+ mii_work.work);
+
+ read_lock(&bond->lock);
+ if (bond->kill_timers)
+ goto out;
+
+ if (bond->slave_cnt == 0)
+ goto re_arm;
+
+ if (bond->send_grat_arp) {
+ read_lock(&bond->curr_slave_lock);
+ bond_send_gratuitous_arp(bond);
+ read_unlock(&bond->curr_slave_lock);
}
-re_arm:
- if (bond->params.miimon) {
- mod_timer(&bond->mii_timer, jiffies + delta_in_ticks);
+ if (bond->send_unsol_na) {
+ read_lock(&bond->curr_slave_lock);
+ bond_send_unsolicited_na(bond);
+ read_unlock(&bond->curr_slave_lock);
+ }
+
+ if (bond_miimon_inspect(bond)) {
+ read_unlock(&bond->lock);
+ rtnl_lock();
+ read_lock(&bond->lock);
+
+ bond_miimon_commit(bond);
+
+ read_unlock(&bond->lock);
+ rtnl_unlock(); /* might sleep, hold no other locks */
+ read_lock(&bond->lock);
}
+
+re_arm:
+ if (bond->params.miimon)
+ queue_delayed_work(bond->wq, &bond->mii_work,
+ msecs_to_jiffies(bond->params.miimon));
out:
read_unlock(&bond->lock);
}
-
-static u32 bond_glean_dev_ip(struct net_device *dev)
+static __be32 bond_glean_dev_ip(struct net_device *dev)
{
struct in_device *idev;
struct in_ifaddr *ifa;
- u32 addr = 0;
+ __be32 addr = 0;
if (!dev)
return 0;
return addr;
}
-static int bond_has_ip(struct bonding *bond)
+static int bond_has_this_ip(struct bonding *bond, __be32 ip)
{
- struct vlan_entry *vlan, *vlan_next;
+ struct vlan_entry *vlan;
- if (bond->master_ip)
+ if (ip == bond->master_ip)
return 1;
- if (list_empty(&bond->vlan_list))
- return 0;
-
- list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
- vlan_list) {
- if (vlan->vlan_ip)
+ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
+ if (ip == vlan->vlan_ip)
return 1;
}
* switches in VLAN mode (especially if ports are configured as
* "native" to a VLAN) might not pass non-tagged frames.
*/
-static void bond_arp_send(struct net_device *slave_dev, int arp_op, u32 dest_ip, u32 src_ip, unsigned short vlan_id)
+static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
{
struct sk_buff *skb;
- dprintk("arp %d on slave %s: dst %x src %x vid %d\n", arp_op,
- slave_dev->name, dest_ip, src_ip, vlan_id);
-
+ pr_debug("arp %d on slave %s: dst %x src %x vid %d\n", arp_op,
+ slave_dev->name, dest_ip, src_ip, vlan_id);
+
skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
NULL, slave_dev->dev_addr, NULL);
if (!skb) {
- printk(KERN_ERR DRV_NAME ": ARP packet allocation failed\n");
+ pr_err("ARP packet allocation failed\n");
return;
}
if (vlan_id) {
skb = vlan_put_tag(skb, vlan_id);
if (!skb) {
- printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n");
+ pr_err("failed to insert VLAN tag\n");
return;
}
}
static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
int i, vlan_id, rv;
- u32 *targets = bond->params.arp_targets;
- struct vlan_entry *vlan, *vlan_next;
+ __be32 *targets = bond->params.arp_targets;
+ struct vlan_entry *vlan;
struct net_device *vlan_dev;
struct flowi fl;
struct rtable *rt;
for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
if (!targets[i])
- continue;
- dprintk("basa: target %x\n", targets[i]);
+ break;
+ pr_debug("basa: target %x\n", targets[i]);
if (list_empty(&bond->vlan_list)) {
- dprintk("basa: empty vlan: arp_send\n");
+ pr_debug("basa: empty vlan: arp_send\n");
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
bond->master_ip, 0);
continue;
fl.fl4_dst = targets[i];
fl.fl4_tos = RTO_ONLINK;
- rv = ip_route_output_key(&rt, &fl);
+ rv = ip_route_output_key(dev_net(bond->dev), &rt, &fl);
if (rv) {
if (net_ratelimit()) {
- printk(KERN_WARNING DRV_NAME
- ": %s: no route to arp_ip_target %u.%u.%u.%u\n",
- bond->dev->name, NIPQUAD(fl.fl4_dst));
+ pr_warning("%s: no route to arp_ip_target %pI4\n",
+ bond->dev->name, &fl.fl4_dst);
}
continue;
}
*/
if (rt->u.dst.dev == bond->dev) {
ip_rt_put(rt);
- dprintk("basa: rtdev == bond->dev: arp_send\n");
+ pr_debug("basa: rtdev == bond->dev: arp_send\n");
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
bond->master_ip, 0);
continue;
}
vlan_id = 0;
- list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
- vlan_list) {
- vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
+ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
+ vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
if (vlan_dev == rt->u.dst.dev) {
vlan_id = vlan->vlan_id;
- dprintk("basa: vlan match on %s %d\n",
+ pr_debug("basa: vlan match on %s %d\n",
vlan_dev->name, vlan_id);
break;
}
}
if (net_ratelimit()) {
- printk(KERN_WARNING DRV_NAME
- ": %s: no path to arp_ip_target %u.%u.%u.%u via rt.dev %s\n",
- bond->dev->name, NIPQUAD(fl.fl4_dst),
- rt->u.dst.dev ? rt->u.dst.dev->name : "NULL");
+ pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
+ bond->dev->name, &fl.fl4_dst,
+ rt->u.dst.dev ? rt->u.dst.dev->name : "NULL");
}
ip_rt_put(rt);
}
/*
* Kick out a gratuitous ARP for an IP on the bonding master plus one
* for each VLAN above us.
+ *
+ * Caller must hold curr_slave_lock for read or better
*/
static void bond_send_gratuitous_arp(struct bonding *bond)
{
struct vlan_entry *vlan;
struct net_device *vlan_dev;
- dprintk("bond_send_grat_arp: bond %s slave %s\n", bond->dev->name,
- slave ? slave->dev->name : "NULL");
- if (!slave)
+ pr_debug("bond_send_grat_arp: bond %s slave %s\n",
+ bond->dev->name, slave ? slave->dev->name : "NULL");
+
+ if (!slave || !bond->send_grat_arp ||
+ test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
return;
+ bond->send_grat_arp--;
+
if (bond->master_ip) {
bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
- bond->master_ip, 0);
+ bond->master_ip, 0);
}
list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
+ vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
if (vlan->vlan_ip) {
bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
vlan->vlan_ip, vlan->vlan_id);
}
}
+static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
+{
+ int i;
+ __be32 *targets = bond->params.arp_targets;
+
+ for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) {
+ pr_debug("bva: sip %pI4 tip %pI4 t[%d] %pI4 bhti(tip) %d\n",
+ &sip, &tip, i, &targets[i],
+ bond_has_this_ip(bond, tip));
+ if (sip == targets[i]) {
+ if (bond_has_this_ip(bond, tip))
+ slave->last_arp_rx = jiffies;
+ return;
+ }
+ }
+}
+
+static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+{
+ struct arphdr *arp;
+ struct slave *slave;
+ struct bonding *bond;
+ unsigned char *arp_ptr;
+ __be32 sip, tip;
+
+ if (dev->priv_flags & IFF_802_1Q_VLAN) {
+ /*
+ * When using VLANS and bonding, dev and oriv_dev may be
+ * incorrect if the physical interface supports VLAN
+ * acceleration. With this change ARP validation now
+ * works for hosts only reachable on the VLAN interface.
+ */
+ dev = vlan_dev_real_dev(dev);
+ orig_dev = dev_get_by_index_rcu(dev_net(skb->dev),skb->skb_iif);
+ }
+
+ if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER))
+ goto out;
+
+ bond = netdev_priv(dev);
+ read_lock(&bond->lock);
+
+ pr_debug("bond_arp_rcv: bond %s skb->dev %s orig_dev %s\n",
+ bond->dev->name, skb->dev ? skb->dev->name : "NULL",
+ orig_dev ? orig_dev->name : "NULL");
+
+ slave = bond_get_slave_by_dev(bond, orig_dev);
+ if (!slave || !slave_do_arp_validate(bond, slave))
+ goto out_unlock;
+
+ if (!pskb_may_pull(skb, arp_hdr_len(dev)))
+ goto out_unlock;
+
+ arp = arp_hdr(skb);
+ if (arp->ar_hln != dev->addr_len ||
+ skb->pkt_type == PACKET_OTHERHOST ||
+ skb->pkt_type == PACKET_LOOPBACK ||
+ arp->ar_hrd != htons(ARPHRD_ETHER) ||
+ arp->ar_pro != htons(ETH_P_IP) ||
+ arp->ar_pln != 4)
+ goto out_unlock;
+
+ arp_ptr = (unsigned char *)(arp + 1);
+ arp_ptr += dev->addr_len;
+ memcpy(&sip, arp_ptr, 4);
+ arp_ptr += 4 + dev->addr_len;
+ memcpy(&tip, arp_ptr, 4);
+
+ pr_debug("bond_arp_rcv: %s %s/%d av %d sv %d sip %pI4 tip %pI4\n",
+ bond->dev->name, slave->dev->name, slave->state,
+ bond->params.arp_validate, slave_do_arp_validate(bond, slave),
+ &sip, &tip);
+
+ /*
+ * Backup slaves won't see the ARP reply, but do come through
+ * here for each ARP probe (so we swap the sip/tip to validate
+ * the probe). In a "redundant switch, common router" type of
+ * configuration, the ARP probe will (hopefully) travel from
+ * the active, through one switch, the router, then the other
+ * switch before reaching the backup.
+ */
+ if (slave->state == BOND_STATE_ACTIVE)
+ bond_validate_arp(bond, slave, sip, tip);
+ else
+ bond_validate_arp(bond, slave, tip, sip);
+
+out_unlock:
+ read_unlock(&bond->lock);
+out:
+ dev_kfree_skb(skb);
+ return NET_RX_SUCCESS;
+}
+
/*
* this function is called regularly to monitor each slave's link
* ensuring that traffic is being sent and received when arp monitoring
* arp is transmitted to generate traffic. see activebackup_arp_monitor for
* arp monitoring in active backup mode.
*/
-void bond_loadbalance_arp_mon(struct net_device *bond_dev)
+void bond_loadbalance_arp_mon(struct work_struct *work)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = container_of(work, struct bonding,
+ arp_work.work);
struct slave *slave, *oldcurrent;
int do_failover = 0;
int delta_in_ticks;
read_lock(&bond->lock);
- delta_in_ticks = (bond->params.arp_interval * HZ) / 1000;
+ delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
- if (bond->kill_timers) {
+ if (bond->kill_timers)
goto out;
- }
- if (bond->slave_cnt == 0) {
+ if (bond->slave_cnt == 0)
goto re_arm;
- }
read_lock(&bond->curr_slave_lock);
oldcurrent = bond->curr_active_slave;
*/
bond_for_each_slave(bond, slave, i) {
if (slave->link != BOND_LINK_UP) {
- if (((jiffies - slave->dev->trans_start) <= delta_in_ticks) &&
- ((jiffies - slave->dev->last_rx) <= delta_in_ticks)) {
+ if (time_before_eq(jiffies, dev_trans_start(slave->dev) + delta_in_ticks) &&
+ time_before_eq(jiffies, slave->dev->last_rx + delta_in_ticks)) {
slave->link = BOND_LINK_UP;
slave->state = BOND_STATE_ACTIVE;
* is closed.
*/
if (!oldcurrent) {
- printk(KERN_INFO DRV_NAME
- ": %s: link status definitely "
- "up for interface %s, ",
- bond_dev->name,
- slave->dev->name);
+ pr_info("%s: link status definitely up for interface %s, ",
+ bond->dev->name,
+ slave->dev->name);
do_failover = 1;
} else {
- printk(KERN_INFO DRV_NAME
- ": %s: interface %s is now up\n",
- bond_dev->name,
- slave->dev->name);
+ pr_info("%s: interface %s is now up\n",
+ bond->dev->name,
+ slave->dev->name);
}
}
} else {
* when the source ip is 0, so don't take the link down
* if we don't know our ip yet
*/
- if (((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) ||
- (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) &&
- bond_has_ip(bond))) {
+ if (time_after_eq(jiffies, dev_trans_start(slave->dev) + 2*delta_in_ticks) ||
+ (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks))) {
slave->link = BOND_LINK_DOWN;
slave->state = BOND_STATE_BACKUP;
- if (slave->link_failure_count < UINT_MAX) {
+ if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
- }
- printk(KERN_INFO DRV_NAME
- ": %s: interface %s is now down.\n",
- bond_dev->name,
- slave->dev->name);
+ pr_info("%s: interface %s is now down.\n",
+ bond->dev->name,
+ slave->dev->name);
- if (slave == oldcurrent) {
+ if (slave == oldcurrent)
do_failover = 1;
- }
}
}
* do - all replies will be rx'ed on same link causing slaves
* to be unstable during low/no traffic periods
*/
- if (IS_UP(slave->dev)) {
+ if (IS_UP(slave->dev))
bond_arp_send_all(bond, slave);
- }
}
if (do_failover) {
- write_lock(&bond->curr_slave_lock);
+ write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
- if (oldcurrent && !bond->curr_active_slave) {
- printk(KERN_INFO DRV_NAME
- ": %s: now running without any active "
- "interface !\n",
- bond_dev->name);
+ write_unlock_bh(&bond->curr_slave_lock);
+ }
+
+re_arm:
+ if (bond->params.arp_interval)
+ queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
+out:
+ read_unlock(&bond->lock);
+}
+
+/*
+ * Called to inspect slaves for active-backup mode ARP monitor link state
+ * changes. Sets new_link in slaves to specify what action should take
+ * place for the slave. Returns 0 if no changes are found, >0 if changes
+ * to link states must be committed.
+ *
+ * Called with bond->lock held for read.
+ */
+static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
+{
+ struct slave *slave;
+ int i, commit = 0;
+
+ bond_for_each_slave(bond, slave, i) {
+ slave->new_link = BOND_LINK_NOCHANGE;
+
+ if (slave->link != BOND_LINK_UP) {
+ if (time_before_eq(jiffies, slave_last_rx(bond, slave) +
+ delta_in_ticks)) {
+ slave->new_link = BOND_LINK_UP;
+ commit++;
+ }
+
+ continue;
+ }
+
+ /*
+ * Give slaves 2*delta after being enslaved or made
+ * active. This avoids bouncing, as the last receive
+ * times need a full ARP monitor cycle to be updated.
+ */
+ if (!time_after_eq(jiffies, slave->jiffies +
+ 2 * delta_in_ticks))
+ continue;
+
+ /*
+ * Backup slave is down if:
+ * - No current_arp_slave AND
+ * - more than 3*delta since last receive AND
+ * - the bond has an IP address
+ *
+ * Note: a non-null current_arp_slave indicates
+ * the curr_active_slave went down and we are
+ * searching for a new one; under this condition
+ * we only take the curr_active_slave down - this
+ * gives each slave a chance to tx/rx traffic
+ * before being taken out
+ */
+ if (slave->state == BOND_STATE_BACKUP &&
+ !bond->current_arp_slave &&
+ time_after(jiffies, slave_last_rx(bond, slave) +
+ 3 * delta_in_ticks)) {
+ slave->new_link = BOND_LINK_DOWN;
+ commit++;
}
- write_unlock(&bond->curr_slave_lock);
+ /*
+ * Active slave is down if:
+ * - more than 2*delta since transmitting OR
+ * - (more than 2*delta since receive AND
+ * the bond has an IP address)
+ */
+ if ((slave->state == BOND_STATE_ACTIVE) &&
+ (time_after_eq(jiffies, dev_trans_start(slave->dev) +
+ 2 * delta_in_ticks) ||
+ (time_after_eq(jiffies, slave_last_rx(bond, slave)
+ + 2 * delta_in_ticks)))) {
+ slave->new_link = BOND_LINK_DOWN;
+ commit++;
+ }
}
-re_arm:
- if (bond->params.arp_interval) {
- mod_timer(&bond->arp_timer, jiffies + delta_in_ticks);
- }
-out:
- read_unlock(&bond->lock);
+ return commit;
}
/*
- * When using arp monitoring in active-backup mode, this function is
- * called to determine if any backup slaves have went down or a new
- * current slave needs to be found.
- * The backup slaves never generate traffic, they are considered up by merely
- * receiving traffic. If the current slave goes down, each backup slave will
- * be given the opportunity to tx/rx an arp before being taken down - this
- * prevents all slaves from being taken down due to the current slave not
- * sending any traffic for the backups to receive. The arps are not necessarily
- * necessary, any tx and rx traffic will keep the current slave up. While any
- * rx traffic will keep the backup slaves up, the current slave is responsible
- * for generating traffic to keep them up regardless of any other traffic they
- * may have received.
- * see loadbalance_arp_monitor for arp monitoring in load balancing mode
+ * Called to commit link state changes noted by inspection step of
+ * active-backup mode ARP monitor.
+ *
+ * Called with RTNL and bond->lock for read.
*/
-void bond_activebackup_arp_mon(struct net_device *bond_dev)
+static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks)
{
- struct bonding *bond = bond_dev->priv;
struct slave *slave;
- int delta_in_ticks;
int i;
- read_lock(&bond->lock);
-
- delta_in_ticks = (bond->params.arp_interval * HZ) / 1000;
-
- if (bond->kill_timers) {
- goto out;
- }
-
- if (bond->slave_cnt == 0) {
- goto re_arm;
- }
-
- /* determine if any slave has come up or any backup slave has
- * gone down
- * TODO: what about up/down delay in arp mode? it wasn't here before
- * so it can wait
- */
bond_for_each_slave(bond, slave, i) {
- if (slave->link != BOND_LINK_UP) {
- if ((jiffies - slave->dev->last_rx) <= delta_in_ticks) {
+ switch (slave->new_link) {
+ case BOND_LINK_NOCHANGE:
+ continue;
+ case BOND_LINK_UP:
+ if ((!bond->curr_active_slave &&
+ time_before_eq(jiffies,
+ dev_trans_start(slave->dev) +
+ delta_in_ticks)) ||
+ bond->curr_active_slave != slave) {
slave->link = BOND_LINK_UP;
+ bond->current_arp_slave = NULL;
- write_lock(&bond->curr_slave_lock);
-
- if ((!bond->curr_active_slave) &&
- ((jiffies - slave->dev->trans_start) <= delta_in_ticks)) {
- bond_change_active_slave(bond, slave);
- bond->current_arp_slave = NULL;
- } else if (bond->curr_active_slave != slave) {
- /* this slave has just come up but we
- * already have a current slave; this
- * can also happen if bond_enslave adds
- * a new slave that is up while we are
- * searching for a new slave
- */
- bond_set_slave_inactive_flags(slave);
- bond->current_arp_slave = NULL;
- }
+ pr_info("%s: link status definitely up for interface %s.\n",
+ bond->dev->name, slave->dev->name);
- if (slave == bond->curr_active_slave) {
- printk(KERN_INFO DRV_NAME
- ": %s: %s is up and now the "
- "active interface\n",
- bond_dev->name,
- slave->dev->name);
- } else {
- printk(KERN_INFO DRV_NAME
- ": %s: backup interface %s is "
- "now up\n",
- bond_dev->name,
- slave->dev->name);
- }
+ if (!bond->curr_active_slave ||
+ (slave == bond->primary_slave))
+ goto do_failover;
- write_unlock(&bond->curr_slave_lock);
}
- } else {
- read_lock(&bond->curr_slave_lock);
-
- if ((slave != bond->curr_active_slave) &&
- (!bond->current_arp_slave) &&
- (((jiffies - slave->dev->last_rx) >= 3*delta_in_ticks) &&
- bond_has_ip(bond))) {
- /* a backup slave has gone down; three times
- * the delta allows the current slave to be
- * taken out before the backup slave.
- * note: a non-null current_arp_slave indicates
- * the curr_active_slave went down and we are
- * searching for a new one; under this
- * condition we only take the curr_active_slave
- * down - this gives each slave a chance to
- * tx/rx traffic before being taken out
- */
- read_unlock(&bond->curr_slave_lock);
+ continue;
- slave->link = BOND_LINK_DOWN;
+ case BOND_LINK_DOWN:
+ if (slave->link_failure_count < UINT_MAX)
+ slave->link_failure_count++;
- if (slave->link_failure_count < UINT_MAX) {
- slave->link_failure_count++;
- }
+ slave->link = BOND_LINK_DOWN;
+ bond_set_slave_inactive_flags(slave);
- bond_set_slave_inactive_flags(slave);
+ pr_info("%s: link status definitely down for interface %s, disabling it\n",
+ bond->dev->name, slave->dev->name);
- printk(KERN_INFO DRV_NAME
- ": %s: backup interface %s is now down\n",
- bond_dev->name,
- slave->dev->name);
- } else {
- read_unlock(&bond->curr_slave_lock);
+ if (slave == bond->curr_active_slave) {
+ bond->current_arp_slave = NULL;
+ goto do_failover;
}
+
+ continue;
+
+ default:
+ pr_err("%s: impossible: new_link %d on slave %s\n",
+ bond->dev->name, slave->new_link,
+ slave->dev->name);
+ continue;
}
+
+do_failover:
+ ASSERT_RTNL();
+ write_lock_bh(&bond->curr_slave_lock);
+ bond_select_active_slave(bond);
+ write_unlock_bh(&bond->curr_slave_lock);
}
- read_lock(&bond->curr_slave_lock);
- slave = bond->curr_active_slave;
- read_unlock(&bond->curr_slave_lock);
+ bond_set_carrier(bond);
+}
- if (slave) {
- /* if we have sent traffic in the past 2*arp_intervals but
- * haven't xmit and rx traffic in that time interval, select
- * a different slave. slave->jiffies is only updated when
- * a slave first becomes the curr_active_slave - not necessarily
- * after every arp; this ensures the slave has a full 2*delta
- * before being taken out. if a primary is being used, check
- * if it is up and needs to take over as the curr_active_slave
- */
- if ((((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) ||
- (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) &&
- bond_has_ip(bond))) &&
- ((jiffies - slave->jiffies) >= 2*delta_in_ticks)) {
+/*
+ * Send ARP probes for active-backup mode ARP monitor.
+ *
+ * Called with bond->lock held for read.
+ */
+static void bond_ab_arp_probe(struct bonding *bond)
+{
+ struct slave *slave;
+ int i;
- slave->link = BOND_LINK_DOWN;
+ read_lock(&bond->curr_slave_lock);
- if (slave->link_failure_count < UINT_MAX) {
- slave->link_failure_count++;
- }
+ if (bond->current_arp_slave && bond->curr_active_slave)
+ pr_info("PROBE: c_arp %s && cas %s BAD\n",
+ bond->current_arp_slave->dev->name,
+ bond->curr_active_slave->dev->name);
- printk(KERN_INFO DRV_NAME
- ": %s: link status down for active interface "
- "%s, disabling it\n",
- bond_dev->name,
- slave->dev->name);
+ if (bond->curr_active_slave) {
+ bond_arp_send_all(bond, bond->curr_active_slave);
+ read_unlock(&bond->curr_slave_lock);
+ return;
+ }
- write_lock(&bond->curr_slave_lock);
+ read_unlock(&bond->curr_slave_lock);
- bond_select_active_slave(bond);
- slave = bond->curr_active_slave;
+ /* if we don't have a curr_active_slave, search for the next available
+ * backup slave from the current_arp_slave and make it the candidate
+ * for becoming the curr_active_slave
+ */
- write_unlock(&bond->curr_slave_lock);
+ if (!bond->current_arp_slave) {
+ bond->current_arp_slave = bond->first_slave;
+ if (!bond->current_arp_slave)
+ return;
+ }
- bond->current_arp_slave = slave;
+ bond_set_slave_inactive_flags(bond->current_arp_slave);
- if (slave) {
- slave->jiffies = jiffies;
- }
- } else if ((bond->primary_slave) &&
- (bond->primary_slave != slave) &&
- (bond->primary_slave->link == BOND_LINK_UP)) {
- /* at this point, slave is the curr_active_slave */
- printk(KERN_INFO DRV_NAME
- ": %s: changing from interface %s to primary "
- "interface %s\n",
- bond_dev->name,
- slave->dev->name,
- bond->primary_slave->dev->name);
-
- /* primary is up so switch to it */
- write_lock(&bond->curr_slave_lock);
- bond_change_active_slave(bond, bond->primary_slave);
- write_unlock(&bond->curr_slave_lock);
-
- slave = bond->primary_slave;
+ /* search for next candidate */
+ bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) {
+ if (IS_UP(slave->dev)) {
+ slave->link = BOND_LINK_BACK;
+ bond_set_slave_active_flags(slave);
+ bond_arp_send_all(bond, slave);
slave->jiffies = jiffies;
- } else {
- bond->current_arp_slave = NULL;
+ bond->current_arp_slave = slave;
+ break;
}
- /* the current slave must tx an arp to ensure backup slaves
- * rx traffic
+ /* if the link state is up at this point, we
+ * mark it down - this can happen if we have
+ * simultaneous link failures and
+ * reselect_active_interface doesn't make this
+ * one the current slave so it is still marked
+ * up when it is actually down
*/
- if (slave && bond_has_ip(bond)) {
- bond_arp_send_all(bond, slave);
+ if (slave->link == BOND_LINK_UP) {
+ slave->link = BOND_LINK_DOWN;
+ if (slave->link_failure_count < UINT_MAX)
+ slave->link_failure_count++;
+
+ bond_set_slave_inactive_flags(slave);
+
+ pr_info("%s: backup interface %s is now down.\n",
+ bond->dev->name, slave->dev->name);
}
}
+}
- /* if we don't have a curr_active_slave, search for the next available
- * backup slave from the current_arp_slave and make it the candidate
- * for becoming the curr_active_slave
- */
- if (!slave) {
- if (!bond->current_arp_slave) {
- bond->current_arp_slave = bond->first_slave;
- }
+void bond_activebackup_arp_mon(struct work_struct *work)
+{
+ struct bonding *bond = container_of(work, struct bonding,
+ arp_work.work);
+ int delta_in_ticks;
- if (bond->current_arp_slave) {
- bond_set_slave_inactive_flags(bond->current_arp_slave);
-
- /* search for next candidate */
- bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) {
- if (IS_UP(slave->dev)) {
- slave->link = BOND_LINK_BACK;
- bond_set_slave_active_flags(slave);
- bond_arp_send_all(bond, slave);
- slave->jiffies = jiffies;
- bond->current_arp_slave = slave;
- break;
- }
+ read_lock(&bond->lock);
- /* if the link state is up at this point, we
- * mark it down - this can happen if we have
- * simultaneous link failures and
- * reselect_active_interface doesn't make this
- * one the current slave so it is still marked
- * up when it is actually down
- */
- if (slave->link == BOND_LINK_UP) {
- slave->link = BOND_LINK_DOWN;
- if (slave->link_failure_count < UINT_MAX) {
- slave->link_failure_count++;
- }
-
- bond_set_slave_inactive_flags(slave);
-
- printk(KERN_INFO DRV_NAME
- ": %s: backup interface %s is "
- "now down.\n",
- bond_dev->name,
- slave->dev->name);
- }
- }
- }
+ if (bond->kill_timers)
+ goto out;
+
+ delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
+
+ if (bond->slave_cnt == 0)
+ goto re_arm;
+
+ if (bond->send_grat_arp) {
+ read_lock(&bond->curr_slave_lock);
+ bond_send_gratuitous_arp(bond);
+ read_unlock(&bond->curr_slave_lock);
}
-re_arm:
- if (bond->params.arp_interval) {
- mod_timer(&bond->arp_timer, jiffies + delta_in_ticks);
+ if (bond->send_unsol_na) {
+ read_lock(&bond->curr_slave_lock);
+ bond_send_unsolicited_na(bond);
+ read_unlock(&bond->curr_slave_lock);
+ }
+
+ if (bond_ab_arp_inspect(bond, delta_in_ticks)) {
+ read_unlock(&bond->lock);
+ rtnl_lock();
+ read_lock(&bond->lock);
+
+ bond_ab_arp_commit(bond, delta_in_ticks);
+
+ read_unlock(&bond->lock);
+ rtnl_unlock();
+ read_lock(&bond->lock);
}
+
+ bond_ab_arp_probe(bond);
+
+re_arm:
+ if (bond->params.arp_interval)
+ queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
out:
read_unlock(&bond->lock);
}
#ifdef CONFIG_PROC_FS
-#define SEQ_START_TOKEN ((void *)1)
-
static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(&dev_base_lock)
+ __acquires(&bond->lock)
{
struct bonding *bond = seq->private;
loff_t off = 0;
/* make sure the bond won't be taken away */
read_lock(&dev_base_lock);
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
- if (*pos == 0) {
+ if (*pos == 0)
return SEQ_START_TOKEN;
- }
bond_for_each_slave(bond, slave, i) {
- if (++off == *pos) {
+ if (++off == *pos)
return slave;
- }
}
return NULL;
struct slave *slave = v;
++*pos;
- if (v == SEQ_START_TOKEN) {
+ if (v == SEQ_START_TOKEN)
return bond->first_slave;
- }
slave = slave->next;
}
static void bond_info_seq_stop(struct seq_file *seq, void *v)
+ __releases(&bond->lock)
+ __releases(&dev_base_lock)
{
struct bonding *bond = seq->private;
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
read_unlock(&dev_base_lock);
}
struct bonding *bond = seq->private;
struct slave *curr;
int i;
- u32 target;
read_lock(&bond->curr_slave_lock);
curr = bond->curr_active_slave;
read_unlock(&bond->curr_slave_lock);
- seq_printf(seq, "Bonding Mode: %s\n",
+ seq_printf(seq, "Bonding Mode: %s",
bond_mode_name(bond->params.mode));
+ if (bond->params.mode == BOND_MODE_ACTIVEBACKUP &&
+ bond->params.fail_over_mac)
+ seq_printf(seq, " (fail_over_mac %s)",
+ fail_over_mac_tbl[bond->params.fail_over_mac].modename);
+
+ seq_printf(seq, "\n");
+
if (bond->params.mode == BOND_MODE_XOR ||
bond->params.mode == BOND_MODE_8023AD) {
seq_printf(seq, "Transmit Hash Policy: %s (%d)\n",
}
if (USES_PRIMARY(bond->params.mode)) {
- seq_printf(seq, "Primary Slave: %s\n",
+ seq_printf(seq, "Primary Slave: %s",
(bond->primary_slave) ?
bond->primary_slave->dev->name : "None");
+ if (bond->primary_slave)
+ seq_printf(seq, " (primary_reselect %s)",
+ pri_reselect_tbl[bond->params.primary_reselect].modename);
- seq_printf(seq, "Currently Active Slave: %s\n",
+ seq_printf(seq, "\nCurrently Active Slave: %s\n",
(curr) ? curr->dev->name : "None");
}
- seq_printf(seq, "MII Status: %s\n", (curr) ? "up" : "down");
+ seq_printf(seq, "MII Status: %s\n", netif_carrier_ok(bond->dev) ?
+ "up" : "down");
seq_printf(seq, "MII Polling Interval (ms): %d\n", bond->params.miimon);
seq_printf(seq, "Up Delay (ms): %d\n",
bond->params.updelay * bond->params.miimon);
/* ARP information */
- if(bond->params.arp_interval > 0) {
- int printed=0;
+ if (bond->params.arp_interval > 0) {
+ int printed = 0;
seq_printf(seq, "ARP Polling Interval (ms): %d\n",
bond->params.arp_interval);
seq_printf(seq, "ARP IP target/s (n.n.n.n form):");
- for(i = 0; (i < BOND_MAX_ARP_TARGETS) ;i++) {
+ for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
if (!bond->params.arp_targets[i])
- continue;
+ break;
if (printed)
seq_printf(seq, ",");
- target = ntohl(bond->params.arp_targets[i]);
- seq_printf(seq, " %d.%d.%d.%d", HIPQUAD(target));
+ seq_printf(seq, " %pI4", &bond->params.arp_targets[i]);
printed = 1;
}
seq_printf(seq, "\n");
seq_puts(seq, "\n802.3ad info\n");
seq_printf(seq, "LACP rate: %s\n",
(bond->params.lacp_fast) ? "fast" : "slow");
+ seq_printf(seq, "Aggregator selection policy (ad_select): %s\n",
+ ad_select_tbl[bond->params.ad_select].modename);
if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
seq_printf(seq, "bond %s has no active aggregator\n",
ad_info.actor_key);
seq_printf(seq, "\tPartner Key: %d\n",
ad_info.partner_key);
- seq_printf(seq, "\tPartner Mac Address: %02x:%02x:%02x:%02x:%02x:%02x\n",
- ad_info.partner_system[0],
- ad_info.partner_system[1],
- ad_info.partner_system[2],
- ad_info.partner_system[3],
- ad_info.partner_system[4],
- ad_info.partner_system[5]);
+ seq_printf(seq, "\tPartner Mac Address: %pM\n",
+ ad_info.partner_system);
}
}
}
-static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave)
+static void bond_info_show_slave(struct seq_file *seq,
+ const struct slave *slave)
{
struct bonding *bond = seq->private;
seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
seq_printf(seq, "MII Status: %s\n",
(slave->link == BOND_LINK_UP) ? "up" : "down");
- seq_printf(seq, "Link Failure Count: %d\n",
+ seq_printf(seq, "Link Failure Count: %u\n",
slave->link_failure_count);
- seq_printf(seq,
- "Permanent HW addr: %02x:%02x:%02x:%02x:%02x:%02x\n",
- slave->perm_hwaddr[0], slave->perm_hwaddr[1],
- slave->perm_hwaddr[2], slave->perm_hwaddr[3],
- slave->perm_hwaddr[4], slave->perm_hwaddr[5]);
+ seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr);
if (bond->params.mode == BOND_MODE_8023AD) {
const struct aggregator *agg
= SLAVE_AD_INFO(slave).port.aggregator;
- if (agg) {
+ if (agg)
seq_printf(seq, "Aggregator ID: %d\n",
agg->aggregator_identifier);
- } else {
+ else
seq_puts(seq, "Aggregator ID: N/A\n");
- }
}
}
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "%s\n", version);
bond_info_show_master(seq);
- } else {
+ } else
bond_info_show_slave(seq, v);
- }
return 0;
}
-static struct seq_operations bond_info_seq_ops = {
+static const struct seq_operations bond_info_seq_ops = {
.start = bond_info_seq_start,
.next = bond_info_seq_next,
.stop = bond_info_seq_stop,
return res;
}
-static struct file_operations bond_info_fops = {
+static const struct file_operations bond_info_fops = {
.owner = THIS_MODULE,
.open = bond_info_open,
.read = seq_read,
.release = seq_release,
};
-static int bond_create_proc_entry(struct bonding *bond)
+static void bond_create_proc_entry(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
-
- if (bond_proc_dir) {
- bond->proc_entry = create_proc_entry(bond_dev->name,
- S_IRUGO,
- bond_proc_dir);
- if (bond->proc_entry == NULL) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: Cannot create /proc/net/%s/%s\n",
- DRV_NAME, bond_dev->name);
- } else {
- bond->proc_entry->data = bond;
- bond->proc_entry->proc_fops = &bond_info_fops;
- bond->proc_entry->owner = THIS_MODULE;
+ struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
+
+ if (bn->proc_dir) {
+ bond->proc_entry = proc_create_data(bond_dev->name,
+ S_IRUGO, bn->proc_dir,
+ &bond_info_fops, bond);
+ if (bond->proc_entry == NULL)
+ pr_warning("Warning: Cannot create /proc/net/%s/%s\n",
+ DRV_NAME, bond_dev->name);
+ else
memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ);
- }
}
-
- return 0;
}
static void bond_remove_proc_entry(struct bonding *bond)
{
- if (bond_proc_dir && bond->proc_entry) {
- remove_proc_entry(bond->proc_file_name, bond_proc_dir);
+ struct net_device *bond_dev = bond->dev;
+ struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
+
+ if (bn->proc_dir && bond->proc_entry) {
+ remove_proc_entry(bond->proc_file_name, bn->proc_dir);
memset(bond->proc_file_name, 0, IFNAMSIZ);
bond->proc_entry = NULL;
}
/* Create the bonding directory under /proc/net, if doesn't exist yet.
* Caller must hold rtnl_lock.
*/
-static void bond_create_proc_dir(void)
+static void __net_init bond_create_proc_dir(struct bond_net *bn)
{
- int len = strlen(DRV_NAME);
-
- for (bond_proc_dir = proc_net->subdir; bond_proc_dir;
- bond_proc_dir = bond_proc_dir->next) {
- if ((bond_proc_dir->namelen == len) &&
- !memcmp(bond_proc_dir->name, DRV_NAME, len)) {
- break;
- }
- }
-
- if (!bond_proc_dir) {
- bond_proc_dir = proc_mkdir(DRV_NAME, proc_net);
- if (bond_proc_dir) {
- bond_proc_dir->owner = THIS_MODULE;
- } else {
- printk(KERN_WARNING DRV_NAME
- ": Warning: cannot create /proc/net/%s\n",
- DRV_NAME);
- }
+ if (!bn->proc_dir) {
+ bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net);
+ if (!bn->proc_dir)
+ pr_warning("Warning: cannot create /proc/net/%s\n",
+ DRV_NAME);
}
}
/* Destroy the bonding directory under /proc/net, if empty.
* Caller must hold rtnl_lock.
*/
-static void bond_destroy_proc_dir(void)
+static void __net_exit bond_destroy_proc_dir(struct bond_net *bn)
{
- struct proc_dir_entry *de;
-
- if (!bond_proc_dir) {
- return;
+ if (bn->proc_dir) {
+ remove_proc_entry(DRV_NAME, bn->net->proc_net);
+ bn->proc_dir = NULL;
}
+}
- /* verify that the /proc dir is empty */
- for (de = bond_proc_dir->subdir; de; de = de->next) {
- /* ignore . and .. */
- if (*(de->name) != '.') {
- break;
- }
- }
+#else /* !CONFIG_PROC_FS */
- if (de) {
- if (bond_proc_dir->owner == THIS_MODULE) {
- bond_proc_dir->owner = NULL;
- }
- } else {
- remove_proc_entry(DRV_NAME, proc_net);
- bond_proc_dir = NULL;
- }
+static void bond_create_proc_entry(struct bonding *bond)
+{
+}
+
+static void bond_remove_proc_entry(struct bonding *bond)
+{
}
+
+static inline void bond_create_proc_dir(struct bond_net *bn)
+{
+}
+
+static inline void bond_destroy_proc_dir(struct bond_net *bn)
+{
+}
+
#endif /* CONFIG_PROC_FS */
+
/*-------------------------- netdev event handling --------------------------*/
/*
*/
static int bond_event_changename(struct bonding *bond)
{
-#ifdef CONFIG_PROC_FS
bond_remove_proc_entry(bond);
bond_create_proc_entry(bond);
-#endif
return NOTIFY_DONE;
}
-static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev)
+static int bond_master_netdev_event(unsigned long event,
+ struct net_device *bond_dev)
{
- struct bonding *event_bond = bond_dev->priv;
+ struct bonding *event_bond = netdev_priv(bond_dev);
switch (event) {
case NETDEV_CHANGENAME:
return bond_event_changename(event_bond);
- case NETDEV_UNREGISTER:
- /*
- * TODO: remove a bond from the list?
- */
- break;
default:
break;
}
return NOTIFY_DONE;
}
-static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev)
+static int bond_slave_netdev_event(unsigned long event,
+ struct net_device *slave_dev)
{
struct net_device *bond_dev = slave_dev->master;
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
switch (event) {
case NETDEV_UNREGISTER:
if (bond_dev) {
- bond_release(bond_dev, slave_dev);
+ if (bond->setup_by_slave)
+ bond_release_and_destroy(bond_dev, slave_dev);
+ else
+ bond_release(bond_dev, slave_dev);
}
break;
case NETDEV_CHANGE:
- /*
- * TODO: is this what we get if somebody
- * sets up a hierarchical bond, then rmmod's
- * one of the slave bonding devices?
- */
+ if (bond->params.mode == BOND_MODE_8023AD || bond_is_lb(bond)) {
+ struct slave *slave;
+
+ slave = bond_get_slave_by_dev(bond, slave_dev);
+ if (slave) {
+ u16 old_speed = slave->speed;
+ u16 old_duplex = slave->duplex;
+
+ bond_update_speed_duplex(slave);
+
+ if (bond_is_lb(bond))
+ break;
+
+ if (old_speed != slave->speed)
+ bond_3ad_adapter_speed_changed(slave);
+ if (old_duplex != slave->duplex)
+ bond_3ad_adapter_duplex_changed(slave);
+ }
+ }
+
break;
case NETDEV_DOWN:
/*
* bond_netdev_event: handle netdev notifier chain events.
*
* This function receives events for the netdev chain. The caller (an
- * ioctl handler calling notifier_call_chain) holds the necessary
+ * ioctl handler calling blocking_notifier_call_chain) holds the necessary
* locks for us to safely manipulate the slave devices (RTNL lock,
* dev_probe_lock).
*/
-static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
+static int bond_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
{
struct net_device *event_dev = (struct net_device *)ptr;
- dprintk("event_dev: %s, event: %lx\n",
- (event_dev ? event_dev->name : "None"),
- event);
+ pr_debug("event_dev: %s, event: %lx\n",
+ event_dev ? event_dev->name : "None",
+ event);
+
+ if (!(event_dev->priv_flags & IFF_BONDING))
+ return NOTIFY_DONE;
if (event_dev->flags & IFF_MASTER) {
- dprintk("IFF_MASTER\n");
+ pr_debug("IFF_MASTER\n");
return bond_master_netdev_event(event, event_dev);
}
if (event_dev->flags & IFF_SLAVE) {
- dprintk("IFF_SLAVE\n");
+ pr_debug("IFF_SLAVE\n");
return bond_slave_netdev_event(event, event_dev);
}
{
struct in_ifaddr *ifa = ptr;
struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev;
- struct bonding *bond, *bond_next;
- struct vlan_entry *vlan, *vlan_next;
+ struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id);
+ struct bonding *bond;
+ struct vlan_entry *vlan;
- list_for_each_entry_safe(bond, bond_next, &bond_dev_list, bond_list) {
+ list_for_each_entry(bond, &bn->dev_list, bond_list) {
if (bond->dev == event_dev) {
switch (event) {
case NETDEV_UP:
}
}
- if (list_empty(&bond->vlan_list))
- continue;
-
- list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
- vlan_list) {
- vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
+ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
+ vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
if (vlan_dev == event_dev) {
switch (event) {
case NETDEV_UP:
dev_remove_pack(&(BOND_AD_INFO(bond).ad_pkt_type));
}
+void bond_register_arp(struct bonding *bond)
+{
+ struct packet_type *pt = &bond->arp_mon_pt;
+
+ if (pt->type)
+ return;
+
+ pt->type = htons(ETH_P_ARP);
+ pt->dev = bond->dev;
+ pt->func = bond_arp_rcv;
+ dev_add_pack(pt);
+}
+
+void bond_unregister_arp(struct bonding *bond)
+{
+ struct packet_type *pt = &bond->arp_mon_pt;
+
+ dev_remove_pack(pt);
+ pt->type = 0;
+}
+
/*---------------------------- Hashing Policies -----------------------------*/
/*
- * Hash for the the output device based upon layer 3 and layer 4 data. If
+ * Hash for the output device based upon layer 2 and layer 3 data. If
+ * the packet is not IP mimic bond_xmit_hash_policy_l2()
+ */
+static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count)
+{
+ struct ethhdr *data = (struct ethhdr *)skb->data;
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^
+ (data->h_dest[5] ^ data->h_source[5])) % count;
+ }
+
+ return (data->h_dest[5] ^ data->h_source[5]) % count;
+}
+
+/*
+ * Hash for the output device based upon layer 3 and layer 4 data. If
* the packet is a frag or not TCP or UDP, just use layer 3 data. If it is
* altogether not IP, mimic bond_xmit_hash_policy_l2()
*/
-static int bond_xmit_hash_policy_l34(struct sk_buff *skb,
- struct net_device *bond_dev, int count)
+static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count)
{
struct ethhdr *data = (struct ethhdr *)skb->data;
- struct iphdr *iph = skb->nh.iph;
- u16 *layer4hdr = (u16 *)((u32 *)iph + iph->ihl);
+ struct iphdr *iph = ip_hdr(skb);
+ __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
int layer4_xor = 0;
- if (skb->protocol == __constant_htons(ETH_P_IP)) {
- if (!(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) &&
+ if (skb->protocol == htons(ETH_P_IP)) {
+ if (!(iph->frag_off & htons(IP_MF|IP_OFFSET)) &&
(iph->protocol == IPPROTO_TCP ||
iph->protocol == IPPROTO_UDP)) {
- layer4_xor = htons((*layer4hdr ^ *(layer4hdr + 1)));
+ layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1)));
}
return (layer4_xor ^
((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;
}
- return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
+ return (data->h_dest[5] ^ data->h_source[5]) % count;
}
/*
* Hash for the output device based upon layer 2 data
*/
-static int bond_xmit_hash_policy_l2(struct sk_buff *skb,
- struct net_device *bond_dev, int count)
+static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count)
{
struct ethhdr *data = (struct ethhdr *)skb->data;
- return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
+ return (data->h_dest[5] ^ data->h_source[5]) % count;
}
/*-------------------------- Device entry points ----------------------------*/
static int bond_open(struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
- struct timer_list *mii_timer = &bond->mii_timer;
- struct timer_list *arp_timer = &bond->arp_timer;
+ struct bonding *bond = netdev_priv(bond_dev);
bond->kill_timers = 0;
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
- struct timer_list *alb_timer = &(BOND_ALB_INFO(bond).alb_timer);
-
+ if (bond_is_lb(bond)) {
/* bond_alb_initialize must be called before the timer
* is started.
*/
return -1;
}
- init_timer(alb_timer);
- alb_timer->expires = jiffies + 1;
- alb_timer->data = (unsigned long)bond;
- alb_timer->function = (void *)&bond_alb_monitor;
- add_timer(alb_timer);
+ INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
+ queue_delayed_work(bond->wq, &bond->alb_work, 0);
}
if (bond->params.miimon) { /* link check interval, in milliseconds. */
- init_timer(mii_timer);
- mii_timer->expires = jiffies + 1;
- mii_timer->data = (unsigned long)bond_dev;
- mii_timer->function = (void *)&bond_mii_monitor;
- add_timer(mii_timer);
+ INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
+ queue_delayed_work(bond->wq, &bond->mii_work, 0);
}
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
- init_timer(arp_timer);
- arp_timer->expires = jiffies + 1;
- arp_timer->data = (unsigned long)bond_dev;
- if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
- arp_timer->function = (void *)&bond_activebackup_arp_mon;
- } else {
- arp_timer->function = (void *)&bond_loadbalance_arp_mon;
- }
- add_timer(arp_timer);
+ if (bond->params.mode == BOND_MODE_ACTIVEBACKUP)
+ INIT_DELAYED_WORK(&bond->arp_work,
+ bond_activebackup_arp_mon);
+ else
+ INIT_DELAYED_WORK(&bond->arp_work,
+ bond_loadbalance_arp_mon);
+
+ queue_delayed_work(bond->wq, &bond->arp_work, 0);
+ if (bond->params.arp_validate)
+ bond_register_arp(bond);
}
if (bond->params.mode == BOND_MODE_8023AD) {
- struct timer_list *ad_timer = &(BOND_AD_INFO(bond).ad_timer);
- init_timer(ad_timer);
- ad_timer->expires = jiffies + 1;
- ad_timer->data = (unsigned long)bond;
- ad_timer->function = (void *)&bond_3ad_state_machine_handler;
- add_timer(ad_timer);
-
+ INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
+ queue_delayed_work(bond->wq, &bond->ad_work, 0);
/* register to receive LACPDUs */
bond_register_lacpdu(bond);
+ bond_3ad_initiate_agg_selection(bond, 1);
}
return 0;
static int bond_close(struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
if (bond->params.mode == BOND_MODE_8023AD) {
/* Unregister the receive of LACPDUs */
bond_unregister_lacpdu(bond);
}
+ if (bond->params.arp_validate)
+ bond_unregister_arp(bond);
+
write_lock_bh(&bond->lock);
- bond_mc_list_destroy(bond);
+ bond->send_grat_arp = 0;
+ bond->send_unsol_na = 0;
/* signal timers not to re-arm */
bond->kill_timers = 1;
write_unlock_bh(&bond->lock);
- /* del_timer_sync must run without holding the bond->lock
- * because a running timer might be trying to hold it too
- */
-
if (bond->params.miimon) { /* link check interval, in milliseconds. */
- del_timer_sync(&bond->mii_timer);
+ cancel_delayed_work(&bond->mii_work);
}
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
- del_timer_sync(&bond->arp_timer);
+ cancel_delayed_work(&bond->arp_work);
}
switch (bond->params.mode) {
case BOND_MODE_8023AD:
- del_timer_sync(&(BOND_AD_INFO(bond).ad_timer));
+ cancel_delayed_work(&bond->ad_work);
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
- del_timer_sync(&(BOND_ALB_INFO(bond).alb_timer));
+ cancel_delayed_work(&bond->alb_work);
break;
default:
break;
}
- /* Release the bonded slaves */
- bond_release_all(bond_dev);
- if ((bond->params.mode == BOND_MODE_TLB) ||
- (bond->params.mode == BOND_MODE_ALB)) {
+ if (bond_is_lb(bond)) {
/* Must be called only after all
* slaves have been released
*/
static struct net_device_stats *bond_get_stats(struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
- struct net_device_stats *stats = &(bond->stats), *sstats;
+ struct bonding *bond = netdev_priv(bond_dev);
+ struct net_device_stats *stats = &bond->stats;
+ struct net_device_stats local_stats;
struct slave *slave;
int i;
- memset(stats, 0, sizeof(struct net_device_stats));
+ memset(&local_stats, 0, sizeof(struct net_device_stats));
read_lock_bh(&bond->lock);
bond_for_each_slave(bond, slave, i) {
- sstats = slave->dev->get_stats(slave->dev);
+ const struct net_device_stats *sstats = dev_get_stats(slave->dev);
- stats->rx_packets += sstats->rx_packets;
- stats->rx_bytes += sstats->rx_bytes;
- stats->rx_errors += sstats->rx_errors;
- stats->rx_dropped += sstats->rx_dropped;
+ local_stats.rx_packets += sstats->rx_packets;
+ local_stats.rx_bytes += sstats->rx_bytes;
+ local_stats.rx_errors += sstats->rx_errors;
+ local_stats.rx_dropped += sstats->rx_dropped;
- stats->tx_packets += sstats->tx_packets;
- stats->tx_bytes += sstats->tx_bytes;
- stats->tx_errors += sstats->tx_errors;
- stats->tx_dropped += sstats->tx_dropped;
+ local_stats.tx_packets += sstats->tx_packets;
+ local_stats.tx_bytes += sstats->tx_bytes;
+ local_stats.tx_errors += sstats->tx_errors;
+ local_stats.tx_dropped += sstats->tx_dropped;
- stats->multicast += sstats->multicast;
- stats->collisions += sstats->collisions;
+ local_stats.multicast += sstats->multicast;
+ local_stats.collisions += sstats->collisions;
- stats->rx_length_errors += sstats->rx_length_errors;
- stats->rx_over_errors += sstats->rx_over_errors;
- stats->rx_crc_errors += sstats->rx_crc_errors;
- stats->rx_frame_errors += sstats->rx_frame_errors;
- stats->rx_fifo_errors += sstats->rx_fifo_errors;
- stats->rx_missed_errors += sstats->rx_missed_errors;
+ local_stats.rx_length_errors += sstats->rx_length_errors;
+ local_stats.rx_over_errors += sstats->rx_over_errors;
+ local_stats.rx_crc_errors += sstats->rx_crc_errors;
+ local_stats.rx_frame_errors += sstats->rx_frame_errors;
+ local_stats.rx_fifo_errors += sstats->rx_fifo_errors;
+ local_stats.rx_missed_errors += sstats->rx_missed_errors;
- stats->tx_aborted_errors += sstats->tx_aborted_errors;
- stats->tx_carrier_errors += sstats->tx_carrier_errors;
- stats->tx_fifo_errors += sstats->tx_fifo_errors;
- stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
- stats->tx_window_errors += sstats->tx_window_errors;
+ local_stats.tx_aborted_errors += sstats->tx_aborted_errors;
+ local_stats.tx_carrier_errors += sstats->tx_carrier_errors;
+ local_stats.tx_fifo_errors += sstats->tx_fifo_errors;
+ local_stats.tx_heartbeat_errors += sstats->tx_heartbeat_errors;
+ local_stats.tx_window_errors += sstats->tx_window_errors;
}
+ memcpy(stats, &local_stats, sizeof(struct net_device_stats));
+
read_unlock_bh(&bond->lock);
return stats;
struct mii_ioctl_data *mii = NULL;
int res = 0;
- dprintk("bond_ioctl: master=%s, cmd=%d\n",
- bond_dev->name, cmd);
+ pr_debug("bond_ioctl: master=%s, cmd=%d\n", bond_dev->name, cmd);
switch (cmd) {
case SIOCGMIIPHY:
mii = if_mii(ifr);
- if (!mii) {
+ if (!mii)
return -EINVAL;
- }
+
mii->phy_id = 0;
/* Fall Through */
case SIOCGMIIREG:
* instead of SIOCGMIIPHY.
*/
mii = if_mii(ifr);
- if (!mii) {
+ if (!mii)
return -EINVAL;
- }
+
if (mii->reg_num == 1) {
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
mii->val_out = 0;
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
read_lock(&bond->curr_slave_lock);
- if (bond->curr_active_slave) {
+ if (netif_carrier_ok(bond->dev))
mii->val_out = BMSR_LSTATUS;
- }
+
read_unlock(&bond->curr_slave_lock);
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
}
return 0;
case SIOCBONDINFOQUERY:
u_binfo = (struct ifbond __user *)ifr->ifr_data;
- if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) {
+ if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond)))
return -EFAULT;
- }
res = bond_info_query(bond_dev, &k_binfo);
- if (res == 0) {
- if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) {
- return -EFAULT;
- }
- }
+ if (res == 0 &&
+ copy_to_user(u_binfo, &k_binfo, sizeof(ifbond)))
+ return -EFAULT;
return res;
case BOND_SLAVE_INFO_QUERY_OLD:
case SIOCBONDSLAVEINFOQUERY:
u_sinfo = (struct ifslave __user *)ifr->ifr_data;
- if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) {
+ if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave)))
return -EFAULT;
- }
res = bond_slave_info_query(bond_dev, &k_sinfo);
- if (res == 0) {
- if (copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) {
- return -EFAULT;
- }
- }
+ if (res == 0 &&
+ copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave)))
+ return -EFAULT;
return res;
default:
break;
}
- if (!capable(CAP_NET_ADMIN)) {
+ if (!capable(CAP_NET_ADMIN))
return -EPERM;
- }
- slave_dev = dev_get_by_name(ifr->ifr_slave);
+ slave_dev = dev_get_by_name(dev_net(bond_dev), ifr->ifr_slave);
- dprintk("slave_dev=%p: \n", slave_dev);
+ pr_debug("slave_dev=%p:\n", slave_dev);
- if (!slave_dev) {
+ if (!slave_dev)
res = -ENODEV;
- } else {
- dprintk("slave_dev->name=%s: \n", slave_dev->name);
+ else {
+ pr_debug("slave_dev->name=%s:\n", slave_dev->name);
switch (cmd) {
case BOND_ENSLAVE_OLD:
case SIOCBONDENSLAVE:
static void bond_set_multicast_list(struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct dev_mc_list *dmi;
- write_lock_bh(&bond->lock);
-
/*
* Do promisc before checking multicast_mode
*/
- if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC)) {
+ if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC))
+ /*
+ * FIXME: Need to handle the error when one of the multi-slaves
+ * encounters error.
+ */
bond_set_promiscuity(bond, 1);
- }
- if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC)) {
+
+ if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC))
bond_set_promiscuity(bond, -1);
- }
+
/* set allmulti flag to slaves */
- if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI)) {
+ if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI))
+ /*
+ * FIXME: Need to handle the error when one of the multi-slaves
+ * encounters error.
+ */
bond_set_allmulti(bond, 1);
- }
- if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI)) {
+
+ if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI))
bond_set_allmulti(bond, -1);
- }
+
+
+ read_lock(&bond->lock);
bond->flags = bond_dev->flags;
/* looking for addresses to add to slaves' mc list */
for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) {
- if (!bond_mc_list_find_dmi(dmi, bond->mc_list)) {
+ if (!bond_mc_list_find_dmi(dmi, bond->mc_list))
bond_mc_add(bond, dmi->dmi_addr, dmi->dmi_addrlen);
- }
}
/* looking for addresses to delete from slaves' list */
for (dmi = bond->mc_list; dmi; dmi = dmi->next) {
- if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list)) {
+ if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list))
bond_mc_delete(bond, dmi->dmi_addr, dmi->dmi_addrlen);
- }
}
/* save master's multicast list */
bond_mc_list_destroy(bond);
bond_mc_list_copy(bond_dev->mc_list, bond, GFP_ATOMIC);
- write_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
+}
+
+static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms)
+{
+ struct bonding *bond = netdev_priv(dev);
+ struct slave *slave = bond->first_slave;
+
+ if (slave) {
+ const struct net_device_ops *slave_ops
+ = slave->dev->netdev_ops;
+ if (slave_ops->ndo_neigh_setup)
+ return slave_ops->ndo_neigh_setup(slave->dev, parms);
+ }
+ return 0;
}
/*
*/
static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *stop_at;
int res = 0;
int i;
- dprintk("bond=%p, name=%s, new_mtu=%d\n", bond,
- (bond_dev ? bond_dev->name : "None"), new_mtu);
+ pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond,
+ (bond_dev ? bond_dev->name : "None"), new_mtu);
/* Can't hold bond->lock with bh disabled here since
* some base drivers panic. On the other hand we can't
*/
bond_for_each_slave(bond, slave, i) {
- dprintk("s %p s->p %p c_m %p\n", slave,
- slave->prev, slave->dev->change_mtu);
+ pr_debug("s %p s->p %p c_m %p\n",
+ slave,
+ slave->prev,
+ slave->dev->netdev_ops->ndo_change_mtu);
+
res = dev_set_mtu(slave->dev, new_mtu);
if (res) {
* means changing their mtu from timer context, which
* is probably not a good idea.
*/
- dprintk("err %d %s\n", res, slave->dev->name);
+ pr_debug("err %d %s\n", res, slave->dev->name);
goto unwind;
}
}
tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu);
if (tmp_res) {
- dprintk("unwind err %d dev %s\n", tmp_res,
- slave->dev->name);
+ pr_debug("unwind err %d dev %s\n",
+ tmp_res, slave->dev->name);
}
}
*/
static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct sockaddr *sa = addr, tmp_sa;
struct slave *slave, *stop_at;
int res = 0;
int i;
- dprintk("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None"));
+ if (bond->params.mode == BOND_MODE_ALB)
+ return bond_alb_set_mac_address(bond_dev, addr);
- if (!is_valid_ether_addr(sa->sa_data)) {
+
+ pr_debug("bond=%p, name=%s\n",
+ bond, bond_dev ? bond_dev->name : "None");
+
+ /*
+ * If fail_over_mac is set to active, do nothing and return
+ * success. Returning an error causes ifenslave to fail.
+ */
+ if (bond->params.fail_over_mac == BOND_FOM_ACTIVE)
+ return 0;
+
+ if (!is_valid_ether_addr(sa->sa_data))
return -EADDRNOTAVAIL;
- }
/* Can't hold bond->lock with bh disabled here since
* some base drivers panic. On the other hand we can't
*/
bond_for_each_slave(bond, slave, i) {
- dprintk("slave %p %s\n", slave, slave->dev->name);
+ const struct net_device_ops *slave_ops = slave->dev->netdev_ops;
+ pr_debug("slave %p %s\n", slave, slave->dev->name);
- if (slave->dev->set_mac_address == NULL) {
+ if (slave_ops->ndo_set_mac_address == NULL) {
res = -EOPNOTSUPP;
- dprintk("EOPNOTSUPP %s\n", slave->dev->name);
+ pr_debug("EOPNOTSUPP %s\n", slave->dev->name);
goto unwind;
}
* breakage anyway until ARP finish
* updating, so...
*/
- dprintk("err %d %s\n", res, slave->dev->name);
+ pr_debug("err %d %s\n", res, slave->dev->name);
goto unwind;
}
}
tmp_res = dev_set_mac_address(slave->dev, &tmp_sa);
if (tmp_res) {
- dprintk("unwind err %d dev %s\n", tmp_res,
- slave->dev->name);
+ pr_debug("unwind err %d dev %s\n",
+ tmp_res, slave->dev->name);
}
}
static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *start_at;
- int i;
- int res = 1;
+ int i, slave_no, res = 1;
read_lock(&bond->lock);
- if (!BOND_IS_OK(bond)) {
+ if (!BOND_IS_OK(bond))
goto out;
- }
- read_lock(&bond->curr_slave_lock);
- slave = start_at = bond->curr_active_slave;
- read_unlock(&bond->curr_slave_lock);
+ /*
+ * Concurrent TX may collide on rr_tx_counter; we accept that
+ * as being rare enough not to justify using an atomic op here
+ */
+ slave_no = bond->rr_tx_counter++ % bond->slave_cnt;
- if (!slave) {
- goto out;
+ bond_for_each_slave(bond, slave, i) {
+ slave_no--;
+ if (slave_no < 0)
+ break;
}
+ start_at = slave;
bond_for_each_slave_from(bond, slave, i, start_at) {
if (IS_UP(slave->dev) &&
(slave->link == BOND_LINK_UP) &&
(slave->state == BOND_STATE_ACTIVE)) {
res = bond_dev_queue_xmit(bond, skb, slave->dev);
-
- write_lock(&bond->curr_slave_lock);
- bond->curr_active_slave = slave->next;
- write_unlock(&bond->curr_slave_lock);
-
break;
}
}
-
out:
if (res) {
/* no suitable interface, frame not sent */
dev_kfree_skb(skb);
}
read_unlock(&bond->lock);
- return 0;
+ return NETDEV_TX_OK;
}
-static void bond_activebackup_xmit_copy(struct sk_buff *skb,
- struct bonding *bond,
- struct slave *slave)
-{
- struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC);
- struct ethhdr *eth_data;
- u8 *hwaddr;
- int res;
-
- if (!skb2) {
- printk(KERN_ERR DRV_NAME ": Error: "
- "bond_activebackup_xmit_copy(): skb_copy() failed\n");
- return;
- }
-
- skb2->mac.raw = (unsigned char *)skb2->data;
- eth_data = eth_hdr(skb2);
-
- /* Pick an appropriate source MAC address
- * -- use slave's perm MAC addr, unless used by bond
- * -- otherwise, borrow active slave's perm MAC addr
- * since that will not be used
- */
- hwaddr = slave->perm_hwaddr;
- if (!memcmp(eth_data->h_source, hwaddr, ETH_ALEN))
- hwaddr = bond->curr_active_slave->perm_hwaddr;
-
- /* Set source MAC address appropriately */
- memcpy(eth_data->h_source, hwaddr, ETH_ALEN);
-
- res = bond_dev_queue_xmit(bond, skb2, slave->dev);
- if (res)
- dev_kfree_skb(skb2);
-
- return;
-}
/*
* in active-backup mode, we know that bond->curr_active_slave is always valid if
*/
static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
int res = 1;
read_lock(&bond->lock);
read_lock(&bond->curr_slave_lock);
- if (!BOND_IS_OK(bond)) {
+ if (!BOND_IS_OK(bond))
goto out;
- }
if (!bond->curr_active_slave)
goto out;
- /* Xmit IGMP frames on all slaves to ensure rapid fail-over
- for multicast traffic on snooping switches */
- if (skb->protocol == __constant_htons(ETH_P_IP) &&
- skb->nh.iph->protocol == IPPROTO_IGMP) {
- struct slave *slave, *active_slave;
- int i;
-
- active_slave = bond->curr_active_slave;
- bond_for_each_slave_from_to(bond, slave, i, active_slave->next,
- active_slave->prev)
- if (IS_UP(slave->dev) &&
- (slave->link == BOND_LINK_UP))
- bond_activebackup_xmit_copy(skb, bond, slave);
- }
-
res = bond_dev_queue_xmit(bond, skb, bond->curr_active_slave->dev);
out:
- if (res) {
+ if (res)
/* no suitable interface, frame not sent */
dev_kfree_skb(skb);
- }
+
read_unlock(&bond->curr_slave_lock);
read_unlock(&bond->lock);
- return 0;
+ return NETDEV_TX_OK;
}
/*
*/
static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *start_at;
int slave_no;
int i;
read_lock(&bond->lock);
- if (!BOND_IS_OK(bond)) {
+ if (!BOND_IS_OK(bond))
goto out;
- }
- slave_no = bond->xmit_hash_policy(skb, bond_dev, bond->slave_cnt);
+ slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt);
bond_for_each_slave(bond, slave, i) {
slave_no--;
- if (slave_no < 0) {
+ if (slave_no < 0)
break;
- }
}
start_at = slave;
dev_kfree_skb(skb);
}
read_unlock(&bond->lock);
- return 0;
+ return NETDEV_TX_OK;
}
/*
*/
static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *start_at;
struct net_device *tx_dev = NULL;
int i;
read_lock(&bond->lock);
- if (!BOND_IS_OK(bond)) {
+ if (!BOND_IS_OK(bond))
goto out;
- }
read_lock(&bond->curr_slave_lock);
start_at = bond->curr_active_slave;
read_unlock(&bond->curr_slave_lock);
- if (!start_at) {
+ if (!start_at)
goto out;
- }
bond_for_each_slave_from(bond, slave, i, start_at) {
if (IS_UP(slave->dev) &&
if (tx_dev) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: bond_xmit_broadcast(): "
- "skb_clone() failed\n",
+ pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n",
bond_dev->name);
continue;
}
}
}
- if (tx_dev) {
+ if (tx_dev)
res = bond_dev_queue_xmit(bond, skb, tx_dev);
- }
out:
- if (res) {
+ if (res)
/* no suitable interface, frame not sent */
dev_kfree_skb(skb);
- }
+
/* frame sent to all suitable interfaces */
read_unlock(&bond->lock);
- return 0;
+ return NETDEV_TX_OK;
}
/*------------------------- Device initialization ---------------------------*/
+static void bond_set_xmit_hash_policy(struct bonding *bond)
+{
+ switch (bond->params.xmit_policy) {
+ case BOND_XMIT_POLICY_LAYER23:
+ bond->xmit_hash_policy = bond_xmit_hash_policy_l23;
+ break;
+ case BOND_XMIT_POLICY_LAYER34:
+ bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
+ break;
+ case BOND_XMIT_POLICY_LAYER2:
+ default:
+ bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
+ break;
+ }
+}
+
+static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ const struct bonding *bond = netdev_priv(dev);
+
+ switch (bond->params.mode) {
+ case BOND_MODE_ROUNDROBIN:
+ return bond_xmit_roundrobin(skb, dev);
+ case BOND_MODE_ACTIVEBACKUP:
+ return bond_xmit_activebackup(skb, dev);
+ case BOND_MODE_XOR:
+ return bond_xmit_xor(skb, dev);
+ case BOND_MODE_BROADCAST:
+ return bond_xmit_broadcast(skb, dev);
+ case BOND_MODE_8023AD:
+ return bond_3ad_xmit_xor(skb, dev);
+ case BOND_MODE_ALB:
+ case BOND_MODE_TLB:
+ return bond_alb_xmit(skb, dev);
+ default:
+ /* Should never happen, mode already checked */
+ pr_err("%s: Error: Unknown bonding mode %d\n",
+ dev->name, bond->params.mode);
+ WARN_ON_ONCE(1);
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+}
+
+
/*
* set bond mode specific net device operations
*/
switch (mode) {
case BOND_MODE_ROUNDROBIN:
- bond_dev->hard_start_xmit = bond_xmit_roundrobin;
break;
case BOND_MODE_ACTIVEBACKUP:
- bond_dev->hard_start_xmit = bond_xmit_activebackup;
break;
case BOND_MODE_XOR:
- bond_dev->hard_start_xmit = bond_xmit_xor;
- if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
- bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
- else
- bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
+ bond_set_xmit_hash_policy(bond);
break;
case BOND_MODE_BROADCAST:
- bond_dev->hard_start_xmit = bond_xmit_broadcast;
break;
case BOND_MODE_8023AD:
- bond_dev->hard_start_xmit = bond_3ad_xmit_xor;
- if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
- bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
- else
- bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
+ bond_set_master_3ad_flags(bond);
+ bond_set_xmit_hash_policy(bond);
break;
- case BOND_MODE_TLB:
case BOND_MODE_ALB:
- bond_dev->hard_start_xmit = bond_alb_xmit;
- bond_dev->set_mac_address = bond_alb_set_mac_address;
+ bond_set_master_alb_flags(bond);
+ /* FALLTHRU */
+ case BOND_MODE_TLB:
break;
default:
/* Should never happen, mode already checked */
- printk(KERN_ERR DRV_NAME
- ": %s: Error: Unknown bonding mode %d\n",
- bond_dev->name,
- mode);
+ pr_err("%s: Error: Unknown bonding mode %d\n",
+ bond_dev->name, mode);
break;
}
}
snprintf(drvinfo->fw_version, 32, "%d", BOND_ABI_VERSION);
}
-static struct ethtool_ops bond_ethtool_ops = {
+static const struct ethtool_ops bond_ethtool_ops = {
+ .get_drvinfo = bond_ethtool_get_drvinfo,
+ .get_link = ethtool_op_get_link,
.get_tx_csum = ethtool_op_get_tx_csum,
.get_sg = ethtool_op_get_sg,
- .get_drvinfo = bond_ethtool_get_drvinfo,
+ .get_tso = ethtool_op_get_tso,
+ .get_ufo = ethtool_op_get_ufo,
+ .get_flags = ethtool_op_get_flags,
};
-/*
- * Does not allocate but creates a /proc entry.
- * Allowed to fail.
- */
-static int bond_init(struct net_device *bond_dev, struct bond_params *params)
-{
- struct bonding *bond = bond_dev->priv;
+static const struct net_device_ops bond_netdev_ops = {
+ .ndo_init = bond_init,
+ .ndo_uninit = bond_uninit,
+ .ndo_open = bond_open,
+ .ndo_stop = bond_close,
+ .ndo_start_xmit = bond_start_xmit,
+ .ndo_get_stats = bond_get_stats,
+ .ndo_do_ioctl = bond_do_ioctl,
+ .ndo_set_multicast_list = bond_set_multicast_list,
+ .ndo_change_mtu = bond_change_mtu,
+ .ndo_set_mac_address = bond_set_mac_address,
+ .ndo_neigh_setup = bond_neigh_setup,
+ .ndo_vlan_rx_register = bond_vlan_rx_register,
+ .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid,
+};
- dprintk("Begin bond_init for %s\n", bond_dev->name);
+static void bond_setup(struct net_device *bond_dev)
+{
+ struct bonding *bond = netdev_priv(bond_dev);
/* initialize rwlocks */
rwlock_init(&bond->lock);
rwlock_init(&bond->curr_slave_lock);
- bond->params = *params; /* copy params struct */
+ bond->params = bonding_defaults;
/* Initialize pointers */
- bond->first_slave = NULL;
- bond->curr_active_slave = NULL;
- bond->current_arp_slave = NULL;
- bond->primary_slave = NULL;
bond->dev = bond_dev;
INIT_LIST_HEAD(&bond->vlan_list);
/* Initialize the device entry points */
- bond_dev->open = bond_open;
- bond_dev->stop = bond_close;
- bond_dev->get_stats = bond_get_stats;
- bond_dev->do_ioctl = bond_do_ioctl;
+ ether_setup(bond_dev);
+ bond_dev->netdev_ops = &bond_netdev_ops;
bond_dev->ethtool_ops = &bond_ethtool_ops;
- bond_dev->set_multicast_list = bond_set_multicast_list;
- bond_dev->change_mtu = bond_change_mtu;
- bond_dev->set_mac_address = bond_set_mac_address;
-
bond_set_mode_ops(bond, bond->params.mode);
bond_dev->destructor = free_netdev;
/* Initialize the device options */
bond_dev->tx_queue_len = 0;
bond_dev->flags |= IFF_MASTER|IFF_MULTICAST;
+ bond_dev->priv_flags |= IFF_BONDING;
+ bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+
+ if (bond->params.arp_interval)
+ bond_dev->priv_flags |= IFF_MASTER_ARPMON;
/* At first, we block adding VLANs. That's the only way to
* prevent problems that occur when adding VLANs over an
*/
bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
- /* don't acquire bond device's xmit_lock when
+ /* don't acquire bond device's netif_tx_lock when
* transmitting */
bond_dev->features |= NETIF_F_LLTX;
* when there are slaves that are not hw accel
* capable
*/
- bond_dev->vlan_rx_register = bond_vlan_rx_register;
- bond_dev->vlan_rx_add_vid = bond_vlan_rx_add_vid;
- bond_dev->vlan_rx_kill_vid = bond_vlan_rx_kill_vid;
bond_dev->features |= (NETIF_F_HW_VLAN_TX |
NETIF_F_HW_VLAN_RX |
NETIF_F_HW_VLAN_FILTER);
-#ifdef CONFIG_PROC_FS
- bond_create_proc_entry(bond);
-#endif
-
- list_add_tail(&bond->bond_list, &bond_dev_list);
-
- return 0;
}
-/* De-initialize device specific data.
- * Caller must hold rtnl_lock.
- */
-void bond_deinit(struct net_device *bond_dev)
+static void bond_work_cancel_all(struct bonding *bond)
{
- struct bonding *bond = bond_dev->priv;
+ write_lock_bh(&bond->lock);
+ bond->kill_timers = 1;
+ write_unlock_bh(&bond->lock);
- list_del(&bond->bond_list);
+ if (bond->params.miimon && delayed_work_pending(&bond->mii_work))
+ cancel_delayed_work(&bond->mii_work);
-#ifdef CONFIG_PROC_FS
- bond_remove_proc_entry(bond);
-#endif
+ if (bond->params.arp_interval && delayed_work_pending(&bond->arp_work))
+ cancel_delayed_work(&bond->arp_work);
+
+ if (bond->params.mode == BOND_MODE_ALB &&
+ delayed_work_pending(&bond->alb_work))
+ cancel_delayed_work(&bond->alb_work);
+
+ if (bond->params.mode == BOND_MODE_8023AD &&
+ delayed_work_pending(&bond->ad_work))
+ cancel_delayed_work(&bond->ad_work);
}
-/* Unregister and free all bond devices.
- * Caller must hold rtnl_lock.
- */
-static void bond_free_all(void)
+/*
+* Destroy a bonding device.
+* Must be under rtnl_lock when this function is called.
+*/
+static void bond_uninit(struct net_device *bond_dev)
{
- struct bonding *bond, *nxt;
+ struct bonding *bond = netdev_priv(bond_dev);
- list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) {
- struct net_device *bond_dev = bond->dev;
+ /* Release the bonded slaves */
+ bond_release_all(bond_dev);
- unregister_netdevice(bond_dev);
- bond_deinit(bond_dev);
- }
+ list_del(&bond->bond_list);
-#ifdef CONFIG_PROC_FS
- bond_destroy_proc_dir();
-#endif
+ bond_work_cancel_all(bond);
+
+ bond_remove_proc_entry(bond);
+
+ if (bond->wq)
+ destroy_workqueue(bond->wq);
+
+ netif_addr_lock_bh(bond_dev);
+ bond_mc_list_destroy(bond);
+ netif_addr_unlock_bh(bond_dev);
}
/*------------------------- Module initialization ---------------------------*/
/*
* Convert string input module parms. Accept either the
- * number of the mode or its string name.
+ * number of the mode or its string name. A bit complicated because
+ * some mode names are substrings of other names, and calls from sysfs
+ * may have whitespace in the name (trailing newlines, for example).
*/
-int bond_parse_parm(char *mode_arg, struct bond_parm_tbl *tbl)
+int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl)
{
- int i;
+ int modeint = -1, i, rv;
+ char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, };
+
+ for (p = (char *)buf; *p; p++)
+ if (!(isdigit(*p) || isspace(*p)))
+ break;
+
+ if (*p)
+ rv = sscanf(buf, "%20s", modestr);
+ else
+ rv = sscanf(buf, "%d", &modeint);
+
+ if (!rv)
+ return -1;
for (i = 0; tbl[i].modename; i++) {
- if ((isdigit(*mode_arg) &&
- tbl[i].mode == simple_strtol(mode_arg, NULL, 0)) ||
- (strncmp(mode_arg, tbl[i].modename,
- strlen(tbl[i].modename)) == 0)) {
+ if (modeint == tbl[i].mode)
+ return tbl[i].mode;
+ if (strcmp(modestr, tbl[i].modename) == 0)
return tbl[i].mode;
- }
}
return -1;
static int bond_check_params(struct bond_params *params)
{
+ int arp_validate_value, fail_over_mac_value, primary_reselect_value;
+
/*
* Convert string parameters.
*/
if (mode) {
bond_mode = bond_parse_parm(mode, bond_mode_tbl);
if (bond_mode == -1) {
- printk(KERN_ERR DRV_NAME
- ": Error: Invalid bonding mode \"%s\"\n",
+ pr_err("Error: Invalid bonding mode \"%s\"\n",
mode == NULL ? "NULL" : mode);
return -EINVAL;
}
if (xmit_hash_policy) {
if ((bond_mode != BOND_MODE_XOR) &&
(bond_mode != BOND_MODE_8023AD)) {
- printk(KERN_INFO DRV_NAME
- ": xor_mode param is irrelevant in mode %s\n",
+ pr_info("xmit_hash_policy param is irrelevant in mode %s\n",
bond_mode_name(bond_mode));
} else {
xmit_hashtype = bond_parse_parm(xmit_hash_policy,
xmit_hashtype_tbl);
if (xmit_hashtype == -1) {
- printk(KERN_ERR DRV_NAME
- ": Error: Invalid xmit_hash_policy \"%s\"\n",
- xmit_hash_policy == NULL ? "NULL" :
+ pr_err("Error: Invalid xmit_hash_policy \"%s\"\n",
+ xmit_hash_policy == NULL ? "NULL" :
xmit_hash_policy);
return -EINVAL;
}
if (lacp_rate) {
if (bond_mode != BOND_MODE_8023AD) {
- printk(KERN_INFO DRV_NAME
- ": lacp_rate param is irrelevant in mode %s\n",
- bond_mode_name(bond_mode));
+ pr_info("lacp_rate param is irrelevant in mode %s\n",
+ bond_mode_name(bond_mode));
} else {
lacp_fast = bond_parse_parm(lacp_rate, bond_lacp_tbl);
if (lacp_fast == -1) {
- printk(KERN_ERR DRV_NAME
- ": Error: Invalid lacp rate \"%s\"\n",
+ pr_err("Error: Invalid lacp rate \"%s\"\n",
lacp_rate == NULL ? "NULL" : lacp_rate);
return -EINVAL;
}
}
}
- if (max_bonds < 1 || max_bonds > INT_MAX) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: max_bonds (%d) not in range %d-%d, so it "
- "was reset to BOND_DEFAULT_MAX_BONDS (%d)\n",
- max_bonds, 1, INT_MAX, BOND_DEFAULT_MAX_BONDS);
+ if (ad_select) {
+ params->ad_select = bond_parse_parm(ad_select, ad_select_tbl);
+ if (params->ad_select == -1) {
+ pr_err("Error: Invalid ad_select \"%s\"\n",
+ ad_select == NULL ? "NULL" : ad_select);
+ return -EINVAL;
+ }
+
+ if (bond_mode != BOND_MODE_8023AD) {
+ pr_warning("ad_select param only affects 802.3ad mode\n");
+ }
+ } else {
+ params->ad_select = BOND_AD_STABLE;
+ }
+
+ if (max_bonds < 0) {
+ pr_warning("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n",
+ max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS);
max_bonds = BOND_DEFAULT_MAX_BONDS;
}
if (miimon < 0) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: miimon module parameter (%d), "
- "not in range 0-%d, so it was reset to %d\n",
- miimon, INT_MAX, BOND_LINK_MON_INTERV);
+ pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to %d\n",
+ miimon, INT_MAX, BOND_LINK_MON_INTERV);
miimon = BOND_LINK_MON_INTERV;
}
if (updelay < 0) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: updelay module parameter (%d), "
- "not in range 0-%d, so it was reset to 0\n",
- updelay, INT_MAX);
+ pr_warning("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ updelay, INT_MAX);
updelay = 0;
}
if (downdelay < 0) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: downdelay module parameter (%d), "
- "not in range 0-%d, so it was reset to 0\n",
- downdelay, INT_MAX);
+ pr_warning("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ downdelay, INT_MAX);
downdelay = 0;
}
if ((use_carrier != 0) && (use_carrier != 1)) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: use_carrier module parameter (%d), "
- "not of valid value (0/1), so it was set to 1\n",
- use_carrier);
+ pr_warning("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n",
+ use_carrier);
use_carrier = 1;
}
+ if (num_grat_arp < 0 || num_grat_arp > 255) {
+ pr_warning("Warning: num_grat_arp (%d) not in range 0-255 so it was reset to 1 \n",
+ num_grat_arp);
+ num_grat_arp = 1;
+ }
+
+ if (num_unsol_na < 0 || num_unsol_na > 255) {
+ pr_warning("Warning: num_unsol_na (%d) not in range 0-255 so it was reset to 1 \n",
+ num_unsol_na);
+ num_unsol_na = 1;
+ }
+
/* reset values for 802.3ad */
if (bond_mode == BOND_MODE_8023AD) {
if (!miimon) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: miimon must be specified, "
- "otherwise bonding will not detect link "
- "failure, speed and duplex which are "
- "essential for 802.3ad operation\n");
- printk(KERN_WARNING "Forcing miimon to 100msec\n");
+ pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
+ pr_warning("Forcing miimon to 100msec\n");
miimon = 100;
}
}
if ((bond_mode == BOND_MODE_TLB) ||
(bond_mode == BOND_MODE_ALB)) {
if (!miimon) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: miimon must be specified, "
- "otherwise bonding will not detect link "
- "failure and link speed which are essential "
- "for TLB/ALB load balancing\n");
- printk(KERN_WARNING "Forcing miimon to 100msec\n");
+ pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure and link speed which are essential for TLB/ALB load balancing\n");
+ pr_warning("Forcing miimon to 100msec\n");
miimon = 100;
}
}
if (bond_mode == BOND_MODE_ALB) {
- printk(KERN_NOTICE DRV_NAME
- ": In ALB mode you might experience client "
- "disconnections upon reconnection of a link if the "
- "bonding module updelay parameter (%d msec) is "
- "incompatible with the forwarding delay time of the "
- "switch\n",
- updelay);
+ pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n",
+ updelay);
}
if (!miimon) {
/* just warn the user the up/down delay will have
* no effect since miimon is zero...
*/
- printk(KERN_WARNING DRV_NAME
- ": Warning: miimon module parameter not set "
- "and updelay (%d) or downdelay (%d) module "
- "parameter is set; updelay and downdelay have "
- "no effect unless miimon is set\n",
- updelay, downdelay);
+ pr_warning("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n",
+ updelay, downdelay);
}
} else {
/* don't allow arp monitoring */
if (arp_interval) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: miimon (%d) and arp_interval (%d) "
- "can't be used simultaneously, disabling ARP "
- "monitoring\n",
- miimon, arp_interval);
+ pr_warning("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n",
+ miimon, arp_interval);
arp_interval = 0;
}
if ((updelay % miimon) != 0) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: updelay (%d) is not a multiple "
- "of miimon (%d), updelay rounded to %d ms\n",
- updelay, miimon, (updelay / miimon) * miimon);
+ pr_warning("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
+ updelay, miimon,
+ (updelay / miimon) * miimon);
}
updelay /= miimon;
if ((downdelay % miimon) != 0) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: downdelay (%d) is not a multiple "
- "of miimon (%d), downdelay rounded to %d ms\n",
- downdelay, miimon,
- (downdelay / miimon) * miimon);
+ pr_warning("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n",
+ downdelay, miimon,
+ (downdelay / miimon) * miimon);
}
downdelay /= miimon;
}
if (arp_interval < 0) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: arp_interval module parameter (%d) "
- ", not in range 0-%d, so it was reset to %d\n",
- arp_interval, INT_MAX, BOND_LINK_ARP_INTERV);
+ pr_warning("Warning: arp_interval module parameter (%d) , not in range 0-%d, so it was reset to %d\n",
+ arp_interval, INT_MAX, BOND_LINK_ARP_INTERV);
arp_interval = BOND_LINK_ARP_INTERV;
}
/* not complete check, but should be good enough to
catch mistakes */
if (!isdigit(arp_ip_target[arp_ip_count][0])) {
- printk(KERN_WARNING DRV_NAME
- ": Warning: bad arp_ip_target module parameter "
- "(%s), ARP monitoring will not be performed\n",
- arp_ip_target[arp_ip_count]);
+ pr_warning("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n",
+ arp_ip_target[arp_ip_count]);
arp_interval = 0;
} else {
- u32 ip = in_aton(arp_ip_target[arp_ip_count]);
+ __be32 ip = in_aton(arp_ip_target[arp_ip_count]);
arp_target[arp_ip_count] = ip;
}
}
if (arp_interval && !arp_ip_count) {
/* don't allow arping if no arp_ip_target given... */
- printk(KERN_WARNING DRV_NAME
- ": Warning: arp_interval module parameter (%d) "
- "specified without providing an arp_ip_target "
- "parameter, arp_interval was reset to 0\n",
- arp_interval);
+ pr_warning("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n",
+ arp_interval);
arp_interval = 0;
}
+ if (arp_validate) {
+ if (bond_mode != BOND_MODE_ACTIVEBACKUP) {
+ pr_err("arp_validate only supported in active-backup mode\n");
+ return -EINVAL;
+ }
+ if (!arp_interval) {
+ pr_err("arp_validate requires arp_interval\n");
+ return -EINVAL;
+ }
+
+ arp_validate_value = bond_parse_parm(arp_validate,
+ arp_validate_tbl);
+ if (arp_validate_value == -1) {
+ pr_err("Error: invalid arp_validate \"%s\"\n",
+ arp_validate == NULL ? "NULL" : arp_validate);
+ return -EINVAL;
+ }
+ } else
+ arp_validate_value = 0;
+
if (miimon) {
- printk(KERN_INFO DRV_NAME
- ": MII link monitoring set to %d ms\n",
- miimon);
+ pr_info("MII link monitoring set to %d ms\n", miimon);
} else if (arp_interval) {
int i;
- printk(KERN_INFO DRV_NAME
- ": ARP monitoring set to %d ms with %d target(s):",
- arp_interval, arp_ip_count);
+ pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):",
+ arp_interval,
+ arp_validate_tbl[arp_validate_value].modename,
+ arp_ip_count);
for (i = 0; i < arp_ip_count; i++)
- printk (" %s", arp_ip_target[i]);
+ pr_info(" %s", arp_ip_target[i]);
- printk("\n");
+ pr_info("\n");
- } else {
+ } else if (max_bonds) {
/* miimon and arp_interval not set, we need one so things
* work as expected, see bonding.txt for details
*/
- printk(KERN_WARNING DRV_NAME
- ": Warning: either miimon or arp_interval and "
- "arp_ip_target module parameters must be specified, "
- "otherwise bonding will not detect link failures! see "
- "bonding.txt for details.\n");
+ pr_warning("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n");
}
if (primary && !USES_PRIMARY(bond_mode)) {
/* currently, using a primary only makes sense
* in active backup, TLB or ALB modes
*/
- printk(KERN_WARNING DRV_NAME
- ": Warning: %s primary device specified but has no "
- "effect in %s mode\n",
- primary, bond_mode_name(bond_mode));
+ pr_warning("Warning: %s primary device specified but has no effect in %s mode\n",
+ primary, bond_mode_name(bond_mode));
primary = NULL;
}
+ if (primary && primary_reselect) {
+ primary_reselect_value = bond_parse_parm(primary_reselect,
+ pri_reselect_tbl);
+ if (primary_reselect_value == -1) {
+ pr_err("Error: Invalid primary_reselect \"%s\"\n",
+ primary_reselect ==
+ NULL ? "NULL" : primary_reselect);
+ return -EINVAL;
+ }
+ } else {
+ primary_reselect_value = BOND_PRI_RESELECT_ALWAYS;
+ }
+
+ if (fail_over_mac) {
+ fail_over_mac_value = bond_parse_parm(fail_over_mac,
+ fail_over_mac_tbl);
+ if (fail_over_mac_value == -1) {
+ pr_err("Error: invalid fail_over_mac \"%s\"\n",
+ arp_validate == NULL ? "NULL" : arp_validate);
+ return -EINVAL;
+ }
+
+ if (bond_mode != BOND_MODE_ACTIVEBACKUP)
+ pr_warning("Warning: fail_over_mac only affects active-backup mode.\n");
+ } else {
+ fail_over_mac_value = BOND_FOM_NONE;
+ }
+
/* fill params struct with the proper values */
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->miimon = miimon;
+ params->num_grat_arp = num_grat_arp;
+ params->num_unsol_na = num_unsol_na;
params->arp_interval = arp_interval;
+ params->arp_validate = arp_validate_value;
params->updelay = updelay;
params->downdelay = downdelay;
params->use_carrier = use_carrier;
params->lacp_fast = lacp_fast;
params->primary[0] = 0;
+ params->primary_reselect = primary_reselect_value;
+ params->fail_over_mac = fail_over_mac_value;
if (primary) {
strncpy(params->primary, primary, IFNAMSIZ);
return 0;
}
+static struct lock_class_key bonding_netdev_xmit_lock_key;
+static struct lock_class_key bonding_netdev_addr_lock_key;
+
+static void bond_set_lockdep_class_one(struct net_device *dev,
+ struct netdev_queue *txq,
+ void *_unused)
+{
+ lockdep_set_class(&txq->_xmit_lock,
+ &bonding_netdev_xmit_lock_key);
+}
+
+static void bond_set_lockdep_class(struct net_device *dev)
+{
+ lockdep_set_class(&dev->addr_list_lock,
+ &bonding_netdev_addr_lock_key);
+ netdev_for_each_tx_queue(dev, bond_set_lockdep_class_one, NULL);
+}
+
+/*
+ * Called from registration process
+ */
+static int bond_init(struct net_device *bond_dev)
+{
+ struct bonding *bond = netdev_priv(bond_dev);
+ struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
+
+ pr_debug("Begin bond_init for %s\n", bond_dev->name);
+
+ bond->wq = create_singlethread_workqueue(bond_dev->name);
+ if (!bond->wq)
+ return -ENOMEM;
+
+ bond_set_lockdep_class(bond_dev);
+
+ netif_carrier_off(bond_dev);
+
+ bond_create_proc_entry(bond);
+ list_add_tail(&bond->bond_list, &bn->dev_list);
+
+ bond_prepare_sysfs_group(bond);
+ return 0;
+}
+
+static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ if (tb[IFLA_ADDRESS]) {
+ if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+ return -EINVAL;
+ if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+ return -EADDRNOTAVAIL;
+ }
+ return 0;
+}
+
+static struct rtnl_link_ops bond_link_ops __read_mostly = {
+ .kind = "bond",
+ .priv_size = sizeof(struct bonding),
+ .setup = bond_setup,
+ .validate = bond_validate,
+};
+
/* Create a new bond based on the specified name and bonding parameters.
+ * If name is NULL, obtain a suitable "bond%d" name for us.
* Caller must NOT hold rtnl_lock; we need to release it here before we
* set up our sysfs entries.
*/
-int bond_create(char *name, struct bond_params *params, struct bonding **newbond)
+int bond_create(struct net *net, const char *name)
{
struct net_device *bond_dev;
int res;
rtnl_lock();
- bond_dev = alloc_netdev(sizeof(struct bonding), name, ether_setup);
+
+ bond_dev = alloc_netdev(sizeof(struct bonding), name ? name : "",
+ bond_setup);
if (!bond_dev) {
- printk(KERN_ERR DRV_NAME
- ": %s: eek! can't alloc netdev!\n",
- name);
+ pr_err("%s: eek! can't alloc netdev!\n", name);
res = -ENOMEM;
- goto out_rtnl;
+ goto out;
}
- /* bond_init() must be called after dev_alloc_name() (for the
- * /proc files), but before register_netdevice(), because we
- * need to set function pointers.
- */
+ dev_net_set(bond_dev, net);
+ bond_dev->rtnl_link_ops = &bond_link_ops;
- res = bond_init(bond_dev, params);
- if (res < 0) {
- goto out_netdev;
+ if (!name) {
+ res = dev_alloc_name(bond_dev, "bond%d");
+ if (res < 0)
+ goto out_netdev;
}
- SET_MODULE_OWNER(bond_dev);
-
res = register_netdevice(bond_dev);
- if (res < 0) {
- goto out_bond;
- }
- if (newbond)
- *newbond = bond_dev->priv;
- rtnl_unlock(); /* allows sysfs registration of net device */
- goto done;
-out_bond:
- bond_deinit(bond_dev);
-out_netdev:
- free_netdev(bond_dev);
-out_rtnl:
+out:
rtnl_unlock();
-done:
return res;
+out_netdev:
+ free_netdev(bond_dev);
+ goto out;
+}
+
+static int __net_init bond_net_init(struct net *net)
+{
+ struct bond_net *bn = net_generic(net, bond_net_id);
+
+ bn->net = net;
+ INIT_LIST_HEAD(&bn->dev_list);
+
+ bond_create_proc_dir(bn);
+
+ return 0;
+}
+
+static void __net_exit bond_net_exit(struct net *net)
+{
+ struct bond_net *bn = net_generic(net, bond_net_id);
+
+ bond_destroy_proc_dir(bn);
}
+static struct pernet_operations bond_net_ops = {
+ .init = bond_net_init,
+ .exit = bond_net_exit,
+ .id = &bond_net_id,
+ .size = sizeof(struct bond_net),
+};
+
static int __init bonding_init(void)
{
int i;
int res;
- char new_bond_name[8]; /* Enough room for 999 bonds at init. */
- printk(KERN_INFO "%s", version);
+ pr_info("%s", version);
res = bond_check_params(&bonding_defaults);
- if (res) {
+ if (res)
goto out;
- }
-#ifdef CONFIG_PROC_FS
- bond_create_proc_dir();
-#endif
+ res = register_pernet_subsys(&bond_net_ops);
+ if (res)
+ goto out;
+
+ res = rtnl_link_register(&bond_link_ops);
+ if (res)
+ goto err_link;
+
for (i = 0; i < max_bonds; i++) {
- sprintf(new_bond_name, "bond%d",i);
- res = bond_create(new_bond_name,&bonding_defaults, NULL);
+ res = bond_create(&init_net, NULL);
if (res)
goto err;
}
+ res = bond_create_sysfs();
+ if (res)
+ goto err;
+
register_netdevice_notifier(&bond_netdev_notifier);
register_inetaddr_notifier(&bond_inetaddr_notifier);
-
- goto out;
-err:
- rtnl_lock();
- bond_free_all();
- rtnl_unlock();
+ bond_register_ipv6_notifier();
out:
return res;
+err:
+ rtnl_link_unregister(&bond_link_ops);
+err_link:
+ unregister_pernet_subsys(&bond_net_ops);
+ goto out;
}
{
unregister_netdevice_notifier(&bond_netdev_notifier);
unregister_inetaddr_notifier(&bond_inetaddr_notifier);
+ bond_unregister_ipv6_notifier();
- rtnl_lock();
- bond_free_all();
- rtnl_unlock();
+ bond_destroy_sysfs();
+
+ rtnl_link_unregister(&bond_link_ops);
+ unregister_pernet_subsys(&bond_net_ops);
}
module_init(bonding_init);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION);
MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others");
-MODULE_SUPPORTED_DEVICE("most ethernet devices");
-
-/*
- * Local variables:
- * c-indent-level: 8
- * c-basic-offset: 8
- * tab-width: 8
- * End:
- */
-
+MODULE_ALIAS_RTNL_LINK("bond");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff