bond_main.c 137 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
/*
 * originally based on the dummy device.
 *
 * Copyright 1999, Thomas Davis, tadavis@lbl.gov.
 * Licensed under the GPL. Based on dummy.c, and eql.c devices.
 *
 * bonding.c: an Ethernet Bonding driver
 *
 * This is useful to talk to a Cisco EtherChannel compatible equipment:
 *	Cisco 5500
 *	Sun Trunking (Solaris)
 *	Alteon AceDirector Trunks
 *	Linux Bonding
 *	and probably many L2 switches ...
 *
 * How it works:
 *    ifconfig bond0 ipaddress netmask up
 *      will setup a network device, with an ip address.  No mac address
 *	will be assigned at this time.  The hw mac address will come from
 *	the first slave bonded to the channel.  All slaves will then use
 *	this hw mac address.
 *
 *    ifconfig bond0 down
 *         will release all slaves, marking them as down.
 *
 *    ifenslave bond0 eth0
 *	will attach eth0 to bond0 as a slave.  eth0 hw mac address will either
 *	a: be used as initial mac address
 *	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.
Jay Vosburgh's avatar
Jay Vosburgh committed
478
479
480
481
 * 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.
Linus Torvalds's avatar
Linus Torvalds committed
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
 */

//#define BONDING_DEBUG 1

#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/ptrace.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/socket.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/dma.h>
#include <asm/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/if_ether.h>
#include <net/arp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
Jay Vosburgh's avatar
Jay Vosburgh committed
525
#include <net/route.h>
Linus Torvalds's avatar
Linus Torvalds committed
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"

/*---------------------------- Module parameters ----------------------------*/

/* monitor all links that often (in milliseconds). <=0 disables monitoring */
#define BOND_LINK_MON_INTERV	0
#define BOND_LINK_ARP_INTERV	0

static int max_bonds	= BOND_DEFAULT_MAX_BONDS;
static int miimon	= BOND_LINK_MON_INTERV;
static int updelay	= 0;
static int downdelay	= 0;
static int use_carrier	= 1;
static char *mode	= NULL;
static char *primary	= NULL;
static char *lacp_rate	= NULL;
static int arp_interval = BOND_LINK_ARP_INTERV;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, };

module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds");
module_param(downdelay, int, 0);
MODULE_PARM_DESC(downdelay, "Delay before considering link down, in milliseconds");
module_param(use_carrier, int, 0);
MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; 0 for off, 1 for on (default)");
module_param(mode, charp, 0);
MODULE_PARM_DESC(mode, "Mode of operation : 0 for round robin, 1 for active-backup, 2 for xor");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner (slow/fast)");
module_param(arp_interval, int, 0);
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");

/*----------------------------- Global variables ----------------------------*/

static const char *version =
	DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";

static LIST_HEAD(bond_dev_list);

#ifdef CONFIG_PROC_FS
static struct proc_dir_entry *bond_proc_dir = NULL;
#endif

static u32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ;
static int arp_ip_count	= 0;
static int bond_mode	= BOND_MODE_ROUNDROBIN;
static int lacp_fast	= 0;
static int app_abi_ver	= 0;
static int orig_app_abi_ver = -1; /* This is used to save the first ABI version
				   * we receive from the application. Once set,
				   * it won't be changed, and the module will
				   * refuse to enslave/release interfaces if the
				   * command comes from an application using
				   * another ABI version.
				   */

struct bond_parm_tbl {
	char *modename;
	int mode;
};

static struct bond_parm_tbl bond_lacp_tbl[] = {
{	"slow",		AD_LACP_SLOW},
{	"fast",		AD_LACP_FAST},
{	NULL,		-1},
};

static struct bond_parm_tbl bond_mode_tbl[] = {
{	"balance-rr",		BOND_MODE_ROUNDROBIN},
{	"active-backup",	BOND_MODE_ACTIVEBACKUP},
{	"balance-xor",		BOND_MODE_XOR},
{	"broadcast",		BOND_MODE_BROADCAST},
{	"802.3ad",		BOND_MODE_8023AD},
{	"balance-tlb",		BOND_MODE_TLB},
{	"balance-alb",		BOND_MODE_ALB},
{	NULL,			-1},
};

/*-------------------------- Forward declarations ---------------------------*/

static inline void bond_set_mode_ops(struct net_device *bond_dev, int mode);
Jay Vosburgh's avatar
Jay Vosburgh committed
617
static void bond_send_gratuitous_arp(struct bonding *bond);
Linus Torvalds's avatar
Linus Torvalds committed
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665

/*---------------------------- General routines -----------------------------*/

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:
		return "unknown";
	}
}

/*---------------------------------- VLAN -----------------------------------*/

/**
 * bond_add_vlan - add a new vlan id on bond
 * @bond: bond that got the notification
 * @vlan_id: the vlan id to add
 *
 * Returns -ENOMEM if allocation failed.
 */
static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id)
{
	struct vlan_entry *vlan;

	dprintk("bond: %s, vlan id %d\n",
		(bond ? bond->dev->name: "None"), vlan_id);

	vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL);
	if (!vlan) {
		return -ENOMEM;
	}

	INIT_LIST_HEAD(&vlan->vlan_list);
	vlan->vlan_id = vlan_id;
Jay Vosburgh's avatar
Jay Vosburgh committed
666
	vlan->vlan_ip = 0;
Linus Torvalds's avatar
Linus Torvalds committed
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485

	write_lock_bh(&bond->lock);

	list_add_tail(&vlan->vlan_list, &bond->vlan_list);

	write_unlock_bh(&bond->lock);

	dprintk("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name);

	return 0;
}

/**
 * bond_del_vlan - delete a vlan id from bond
 * @bond: bond that got the notification
 * @vlan_id: the vlan id to delete
 *
 * returns -ENODEV if @vlan_id was not found in @bond.
 */
static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id)
{
	struct vlan_entry *vlan, *next;
	int res = -ENODEV;

	dprintk("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) {
		if (vlan->vlan_id == vlan_id) {
			list_del(&vlan->vlan_list);

			if ((bond->params.mode == BOND_MODE_TLB) ||
			    (bond->params.mode == BOND_MODE_ALB)) {
				bond_alb_clear_vlan(bond, vlan_id);
			}

			dprintk("removed VLAN ID %d from bond %s\n", vlan_id,
				bond->dev->name);

			kfree(vlan);

			if (list_empty(&bond->vlan_list) &&
			    (bond->slave_cnt == 0)) {
				/* Last VLAN removed and no slaves, so
				 * restore block on adding VLANs. This will
				 * be removed once new slaves that are not
				 * VLAN challenged will be added.
				 */
				bond->dev->features |= NETIF_F_VLAN_CHALLENGED;
			}

			res = 0;
			goto out;
		}
	}

	dprintk("couldn't find VLAN ID %d in bond %s\n", vlan_id,
		bond->dev->name);

out:
	write_unlock_bh(&bond->lock);
	return res;
}

/**
 * bond_has_challenged_slaves
 * @bond: the bond we're working on
 *
 * Searches the slave list. Returns 1 if a vlan challenged slave
 * was found, 0 otherwise.
 *
 * Assumes bond->lock is held.
 */
static int bond_has_challenged_slaves(struct bonding *bond)
{
	struct slave *slave;
	int i;

	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);
			return 1;
		}
	}

	dprintk("no VLAN challenged slaves found\n");
	return 0;
}

/**
 * bond_next_vlan - safely skip to the next item in the vlans list.
 * @bond: the bond we're working on
 * @curr: item we're advancing from
 *
 * 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)) {
		return NULL;
	}

	if (!curr) {
		next = list_entry(bond->vlan_list.next,
				  struct vlan_entry, vlan_list);
	} else {
		last = list_entry(bond->vlan_list.prev,
				  struct vlan_entry, vlan_list);
		if (last == curr) {
			next = list_entry(bond->vlan_list.next,
					  struct vlan_entry, vlan_list);
		} else {
			next = list_entry(curr->vlan_list.next,
					  struct vlan_entry, vlan_list);
		}
	}

	return 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
 * hw accel capable, the skb needs to be "unaccelerated",
 * 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)
{
	unsigned short vlan_id;

	if (!list_empty(&bond->vlan_list) &&
	    !(slave_dev->features & NETIF_F_HW_VLAN_TX) &&
	    vlan_get_tag(skb, &vlan_id) == 0) {
		skb->dev = slave_dev;
		skb = vlan_put_tag(skb, vlan_id);
		if (!skb) {
			/* vlan_put_tag() frees the skb in case of error,
			 * so return success here so the calling functions
			 * won't attempt to free is again.
			 */
			return 0;
		}
	} else {
		skb->dev = slave_dev;
	}

	skb->priority = 1;
	dev_queue_xmit(skb);

	return 0;
}

/*
 * In the following 3 functions, bond_vlan_rx_register(), bond_vlan_rx_add_vid
 * and bond_vlan_rx_kill_vid, We don't protect the slave list iteration with a
 * lock because:
 * a. This operation is performed in IOCTL context,
 * 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
 * potential race condition here where a net device from the vlan group might
 * be referenced (either by a base driver or the 8021q code) while it is being
 * removed from the system. However, it turns out we're not making matters
 * worse, and if it works for regular VLAN usage it will work here too.
*/

/**
 * bond_vlan_rx_register - Propagates registration to slaves
 * @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)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	int i;

	bond->vlgrp = grp;

	bond_for_each_slave(bond, slave, i) {
		struct net_device *slave_dev = slave->dev;

		if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
		    slave_dev->vlan_rx_register) {
			slave_dev->vlan_rx_register(slave_dev, grp);
		}
	}
}

/**
 * bond_vlan_rx_add_vid - Propagates adding an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being added
 */
static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	int i, res;

	bond_for_each_slave(bond, slave, i) {
		struct net_device *slave_dev = slave->dev;

		if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
		    slave_dev->vlan_rx_add_vid) {
			slave_dev->vlan_rx_add_vid(slave_dev, vid);
		}
	}

	res = bond_add_vlan(bond, vid);
	if (res) {
		printk(KERN_ERR DRV_NAME
		       ": %s: Failed to add vlan id %d\n",
		       bond_dev->name, vid);
	}
}

/**
 * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being removed
 */
static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
{
	struct bonding *bond = bond_dev->priv;
	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;

		if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
		    slave_dev->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;
		}
	}

	res = bond_del_vlan(bond, vid);
	if (res) {
		printk(KERN_ERR DRV_NAME
		       ": %s: 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;

	write_lock_bh(&bond->lock);

	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);
	}

	if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
	    !(slave_dev->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);
	}

out:
	write_unlock_bh(&bond->lock);
}

static void bond_del_vlans_from_slave(struct bonding *bond, struct net_device *slave_dev)
{
	struct vlan_entry *vlan;
	struct net_device *vlan_dev;

	write_lock_bh(&bond->lock);

	if (list_empty(&bond->vlan_list)) {
		goto out;
	}

	if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
	    !(slave_dev->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;
	}

unreg:
	if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
	    slave_dev->vlan_rx_register) {
		slave_dev->vlan_rx_register(slave_dev, NULL);
	}

out:
	write_unlock_bh(&bond->lock);
}

/*------------------------------- Link status -------------------------------*/

/*
 * 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
 * and return error.
 */
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;

	/* 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;
	}

	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)) {
		return -1;
	}

verify:
	switch (etool.speed) {
	case SPEED_10:
	case SPEED_100:
	case SPEED_1000:
		break;
	default:
		return -1;
	}

	switch (etool.duplex) {
	case DUPLEX_FULL:
	case DUPLEX_HALF:
		break;
	default:
		return -1;
	}

	slave->speed = etool.speed;
	slave->duplex = etool.duplex;

	return 0;
}

/*
 * 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.
 *
 * 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
 * down.
 *
 * If reporting is non-zero, instead of faking link up, return -1 if
 * both ETHTOOL and MII ioctls fail (meaning the device does not
 * support them).  If use_carrier is set, return whatever it says.
 * 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 (* ioctl)(struct net_device *, struct ifreq *, int);
	struct ifreq ifr;
	struct mii_ioctl_data *mii;
	struct ethtool_value etool;

	if (bond->params.use_carrier) {
		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
	}

	ioctl = slave_dev->do_ioctl;
	if (ioctl) {
		/* TODO: set pointer to correct ioctl on a per team member */
		/*       bases to make this more efficient. that is, once  */
		/*       we determine the correct ioctl, we will always    */
		/*       call it and not the others for that team          */
		/*       member.                                           */

		/*
		 * We cannot assume that SIOCGMIIPHY will also read a
		 * register; not all network drivers (e.g., e100)
		 * support that.
		 */

		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
		strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
		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 reporting, report that either there's no dev->do_ioctl,
	 * or both SIOCGMIIREG and SIOCETHTOOL failed (meaning that we
	 * cannot report link status).  If not reporting, pretend
	 * we're ok.
	 */
	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)
{
	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)
{
	struct dev_mc_list *idmi;

	for (idmi = mc_list; idmi; idmi = idmi->next) {
		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)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			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);
		}
	}
}

/*
 * Push the allmulti flag down to all slaves
 */
static void bond_set_allmulti(struct bonding *bond, int inc)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			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);
		}
	}
}

/*
 * Add a Multicast address to slaves
 * according to mode
 */
static void bond_mc_add(struct bonding *bond, void *addr, int alen)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		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) {
			dev_mc_add(slave->dev, addr, alen, 0);
		}
	}
}

/*
 * Remove a multicast address from slave
 * according to mode
 */
static void bond_mc_delete(struct bonding *bond, void *addr, int alen)
{
	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);
		}
	} else {
		struct slave *slave;
		int i;
		bond_for_each_slave(bond, slave, i) {
			dev_mc_delete(slave->dev, addr, alen, 0);
		}
	}
}

/*
 * Totally destroys the mc_list in bond
 */
static void bond_mc_list_destroy(struct bonding *bond)
{
	struct dev_mc_list *dmi;

	dmi = bond->mc_list;
	while (dmi) {
		bond->mc_list = dmi->next;
		kfree(dmi);
		dmi = bond->mc_list;
	}
}

/*
 * Copy all the Multicast addresses from src to the bonding device dst
 */
static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond, int gpf_flag)
{
	struct dev_mc_list *dmi, *new_dmi;

	for (dmi = mc_list; dmi; dmi = dmi->next) {
		new_dmi = kmalloc(sizeof(struct dev_mc_list), gpf_flag);

		if (!new_dmi) {
			/* FIXME: Potential memory leak !!! */
			return -ENOMEM;
		}

		new_dmi->next = bond->mc_list;
		bond->mc_list = new_dmi;
		new_dmi->dmi_addrlen = dmi->dmi_addrlen;
		memcpy(new_dmi->dmi_addr, dmi->dmi_addr, dmi->dmi_addrlen);
		new_dmi->dmi_users = dmi->dmi_users;
		new_dmi->dmi_gusers = dmi->dmi_gusers;
	}

	return 0;
}

/*
 * 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)
{
	struct bonding *bond = bond_dev->priv;
	struct dev_mc_list *dmi;

	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 */
		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

		dev_mc_delete(slave_dev, lacpdu_multicast, ETH_ALEN, 0);
	}
}

/*--------------------------- Active slave change ---------------------------*/

/*
 * Update the mc list and multicast-related flags for the new and
 * 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)
{
	struct dev_mc_list *dmi;

	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) {
			dev_set_promiscuity(old_active->dev, -1);
		}

		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);
		}
	}

	if (new_active) {
		if (bond->dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(new_active->dev, 1);
		}

		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);
		}
	}
}

/**
 * find_best_interface - select the best available slave to be the active one
 * @bond: our bonding struct
 *
 * Warning: Caller must hold curr_slave_lock for writing.
 */
static struct slave *bond_find_best_slave(struct bonding *bond)
{
	struct slave *new_active, *old_active;
	struct slave *bestslave = NULL;
	int mintime = bond->params.updelay;
	int i;

	new_active = old_active = bond->curr_active_slave;

	if (!new_active) { /* there were no active slaves left */
		if (bond->slave_cnt > 0) {  /* found one slave */
			new_active = bond->first_slave;
		} 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))) {
		new_active = bond->primary_slave;
	}

	/* remember where to stop iterating over the slaves */
	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;
				}
			}
		}
	}

	return bestslave;
}

/**
 * change_active_interface - change the active slave into the specified one
 * @bond: our bonding struct
 * @new: the new slave to make the active one
 *
 * Set the new slave to the bond's settings and unset them on the old
 * curr_active_slave.
 * Setting include flags, mc-list, promiscuity, allmulti, etc.
 *
 * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP,
 * 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.
 */
static 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) {
		return;
	}

	if (new_active) {
		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);
			}

			new_active->delay = 0;
			new_active->link = BOND_LINK_UP;
			new_active->jiffies = jiffies;

			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)) {
				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);
			}
		}
	}

	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)) {
		bond_alb_handle_active_change(bond, new_active);
	} else {
		bond->curr_active_slave = new_active;
	}
Jay Vosburgh's avatar
Jay Vosburgh committed
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496

	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
		if (old_active) {
			bond_set_slave_inactive_flags(old_active);
		}

		if (new_active) {
			bond_set_slave_active_flags(new_active);
		}
		bond_send_gratuitous_arp(bond);
	}
Linus Torvalds's avatar
Linus Torvalds committed
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
}

/**
 * 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:
 * - 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.
 */
static void bond_select_active_slave(struct bonding *bond)
{
	struct slave *best_slave;

	best_slave = bond_find_best_slave(bond);
	if (best_slave != bond->curr_active_slave) {
		bond_change_active_slave(bond, best_slave);
	}
}

/*--------------------------- slave list handling ---------------------------*/

/*
 * This function attaches the slave to the end of list.
 *
 * bond->lock held for writing by caller.
 */
static void bond_attach_slave(struct bonding *bond, struct slave *new_slave)
{
	if (bond->first_slave == NULL) { /* attaching the first slave */
		new_slave->next = new_slave;
		new_slave->prev = new_slave;
		bond->first_slave = new_slave;
	} else {
		new_slave->next = bond->first_slave;
		new_slave->prev = bond->first_slave->prev;
		new_slave->next->prev = new_slave;
		new_slave->prev->next = new_slave;
	}

	bond->slave_cnt++;
}

/*
 * This function detaches the slave from the list.
 * WARNING: no check is made to verify if the slave effectively
 * belongs to <bond>.
 * Nothing is freed on return, structures are just unchained.
 * If any slave pointer in bond was pointing to <slave>,
 * it should be changed by the calling function.
 *
 * bond->lock held for writing by caller.
 */
static void bond_detach_slave(struct bonding *bond, struct slave *slave)
{
	if (slave->next) {
		slave->next->prev = 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 */
			bond->first_slave = slave->next;
		} else {
			bond->first_slave = NULL; /* slave was the last one */
		}
	}

	slave->next = NULL;
	slave->prev = NULL;
	bond->slave_cnt--;
}

/*---------------------------------- IOCTL ----------------------------------*/

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);
	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
	return 0;
}

/* enslave device <slave> to bond device <master> */
static int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *new_slave = NULL;
	struct dev_mc_list *dmi;
	struct sockaddr addr;
	int link_reporting;
	int old_features = bond_dev->features;
	int res = 0;

	if (slave_dev->do_ioctl == NULL) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning : no link monitoring support for %s\n",
		       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;
	}

	/* already enslaved */
	if (slave_dev->flags & IFF_SLAVE) {
		dprintk("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);
		if (!list_empty(&bond->vlan_list)) {
			printk(KERN_ERR DRV_NAME
			       ": Error: cannot enslave VLAN "
			       "challenged slave %s on VLAN enabled "
			       "bond %s\n", slave_dev->name,
			       bond_dev->name);
			return -EPERM;
		} else {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: enslaved VLAN challenged "
			       "slave %s. Adding VLANs will be blocked as "
			       "long as %s is part of bond %s\n",
			       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);
		if (bond->slave_cnt == 0) {
			/* First slave, and it is not VLAN challenged,
			 * so remove the block of adding VLANs over the bond.
			 */
			bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
		}
	}

	if (app_abi_ver >= 1) {
		/* The application is using an ABI, which requires the
		 * slave interface to be closed.
		 */
		if ((slave_dev->flags & IFF_UP)) {
			printk(KERN_ERR DRV_NAME
			       ": Error: %s is up\n",
			       slave_dev->name);
			res = -EPERM;
			goto err_undo_flags;
		}

		if (slave_dev->set_mac_address == NULL) {
			printk(KERN_ERR DRV_NAME
			       ": Error: The slave device you specified does "
			       "not support setting the MAC address.\n");
			printk(KERN_ERR
			       "Your kernel likely does not support slave "
			       "devices.\n");

			res = -EOPNOTSUPP;
			goto err_undo_flags;
		}
	} else {
		/* The application is not using an ABI, which requires the
		 * slave interface to be open.
		 */
		if (!(slave_dev->flags & IFF_UP)) {
			printk(KERN_ERR DRV_NAME
			       ": Error: %s is not running\n",
			       slave_dev->name);
			res = -EINVAL;
			goto err_undo_flags;
		}

		if ((bond->params.mode == BOND_MODE_8023AD) ||
		    (bond->params.mode == BOND_MODE_TLB)    ||
		    (bond->params.mode == BOND_MODE_ALB)) {
			printk(KERN_ERR DRV_NAME
			       ": Error: to use %s mode, you must upgrade "
			       "ifenslave.\n",
			       bond_mode_name(bond->params.mode));
			res = -EOPNOTSUPP;
			goto err_undo_flags;
		}
	}

	new_slave = kmalloc(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
	 */
	new_slave->original_flags = slave_dev->flags;

	if (app_abi_ver >= 1) {
		/* save slave's original ("permanent") mac address for
		 * modes that needs it, and for restoring it upon release,
		 * and then set it to the master's address
		 */
		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;
		}

		/* open the slave since the application closed it */
		res = dev_open(slave_dev);
		if (res) {
			dprintk("Openning slave %s failed\n", slave_dev->name);
			goto err_restore_mac;
		}
	}

	res = netdev_set_master(slave_dev, bond_dev);
	if (res) {
		dprintk("Error %d calling netdev_set_master\n", res);
		if (app_abi_ver < 1) {
			goto err_free;
		} else {
			goto err_close;
		}
	}

	new_slave->dev = slave_dev;

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* 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 the mode USES_PRIMARY, then the new slave gets the
	 * master's promisc (and mc) settings only if it becomes the
	 * curr_active_slave, and that is taken care of later when calling
	 * bond_change_active()
	 */
	if (!USES_PRIMARY(bond->params.mode)) {
		/* set promiscuity level to new slave */
		if (bond_dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(slave_dev, 1);
		}

		/* set allmulti level to new slave */
		if (bond_dev->flags & IFF_ALLMULTI) {
			dev_set_allmulti(slave_dev, 1);
		}

		/* 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);
		}
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* add lacpdu mc addr to mc list */
		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

		dev_mc_add(slave_dev, lacpdu_multicast, ETH_ALEN, 0);
	}

	bond_add_vlans_on_slave(bond, slave_dev);

	write_lock_bh(&bond->lock);

	bond_attach_slave(bond, new_slave);

	new_slave->delay = 0;
	new_slave->link_failure_count = 0;

	if (bond->params.miimon && !bond->params.use_carrier) {
		link_reporting = bond_check_dev_link(bond, slave_dev, 1);

		if ((link_reporting == -1) && !bond->params.arp_interval) {
			/*
			 * miimon is set but a bonded network driver
			 * does not support ETHTOOL/MII and
			 * arp_interval is not set.  Note: if
			 * use_carrier is enabled, we will never go
			 * here (because netif_carrier is always
			 * supported); thus, we don't need to change
			 * the messages for netif_carrier.
			 */
			printk(KERN_WARNING DRV_NAME
			       ": 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",
			       slave_dev->name);
		} else if (link_reporting == -1) {
			/* unable get link status using mii/ethtool */
			printk(KERN_WARNING DRV_NAME
			       ": 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",
			       slave_dev->name);
		}
	}

	/* check for initial state */
	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");
			new_slave->link  = BOND_LINK_BACK;
			new_slave->delay = bond->params.updelay;
		} else {
			dprintk("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");
		new_slave->link  = BOND_LINK_DOWN;
	}

	if (bond_update_speed_duplex(new_slave) &&
	    (new_slave->link != BOND_LINK_DOWN)) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: failed to get speed and duplex from %s, "
		       "assumed to be 100Mb/sec and Full.\n",
		       new_slave->dev->name);

		if (bond->params.mode == BOND_MODE_8023AD) {
			printk(KERN_WARNING
			       "Operation of 802.3ad mode requires ETHTOOL "
			       "support in base driver for proper aggregator "
			       "selection.\n");
		}
	}

	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
		/* if there is a primary slave, remember it */
		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
			bond->primary_slave = new_slave;
		}
	}

	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);
		}
		break;
	case BOND_MODE_8023AD:
		/* in 802.3ad mode, the internal mechanism
		 * will activate the slaves in the selected
		 * aggregator
		 */
		bond_set_slave_inactive_flags(new_slave);
		/* if this is the first slave */
		if (bond->slave_cnt == 1) {
			SLAVE_AD_INFO(new_slave).id = 1;
			/* Initialize AD with the number of times that the AD timer is called in 1 second
			 * can be called only after the mac address of the bond is set
			 */
			bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL,
					    bond->params.lacp_fast);
		} else {
			SLAVE_AD_INFO(new_slave).id =
				SLAVE_AD_INFO(new_slave->prev).id + 1;
		}

		bond_3ad_bind_slave(new_slave);
		break;
	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);
		}
		break;
	default:
		dprintk("This slave is always active in trunk mode\n");

		/* always active in trunk mode */
		new_slave->state = BOND_STATE_ACTIVE;

		/* In trunking mode there is little meaning to curr_active_slave
		 * 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) {
			bond->curr_active_slave = new_slave;
		}
		break;
	} /* switch(bond_mode) */

	write_unlock_bh(&bond->lock);

	if (app_abi_ver < 1) {
		/*
		 * !!! This is to support old versions of ifenslave.
		 * We can remove this in 2.5 because our ifenslave takes
		 * care of this for us.
		 * We check to see if the master has a mac address yet.
		 * If not, we'll give it the mac address of our slave device.
		 */
		int ndx = 0;

		for (ndx = 0; ndx < bond_dev->addr_len; ndx++) {
			dprintk("Checking ndx=%d of bond_dev->dev_addr\n",
				ndx);
			if (bond_dev->dev_addr[ndx] != 0) {
				dprintk("Found non-zero byte at ndx=%d\n",
					ndx);
				break;
			}
		}

		if (ndx == bond_dev->addr_len) {
			/*
			 * We got all the way through the address and it was
			 * all 0's.
			 */
			dprintk("%s doesn't have a MAC address yet.  \n",
				bond_dev->name);
			dprintk("Going to give assign it from %s.\n",
				slave_dev->name);
			bond_sethwaddr(bond_dev, slave_dev);
		}
	}

	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");

	/* 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_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);

err_free:
	kfree(new_slave);

err_undo_flags:
	bond_dev->features = old_features;

	return res;
}

/*
 * Try to release the slave device <slave> from the bond device <master>
 * It is legal to access curr_active_slave without a lock because all the function
 * is write-locked.
 *
 * The rules for slave state should be:
 *   for Active/Backup:
 *     Active stays on all backups go down
 *   for Bonded connections:
 *     The first up interface should be left on and all others downed.
 */
static int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	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
		       ": Error: %s: cannot release %s.\n",
		       bond_dev->name, slave_dev->name);
		return -EINVAL;
	}

	write_lock_bh(&bond->lock);

	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);
		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
		       ": 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",
		       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);
	}

	/* Inform AD package of unbinding of slave. */
	if (bond->params.mode == BOND_MODE_8023AD) {
		/* must be called before the slave is
		 * detached from the list
		 */
		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);

	oldcurrent = bond->curr_active_slave;

	bond->current_arp_slave = NULL;

	/* release the slave from its bond */
	bond_detach_slave(bond, slave);

	if (bond->primary_slave == slave) {
		bond->primary_slave = NULL;
	}

	if (oldcurrent == slave) {
		bond_change_active_slave(bond, NULL);
	}

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* 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.
		 */
		bond_alb_deinit_slave(bond, slave);
	}

	if (oldcurrent == slave) {
		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);
		}
	}

	if (bond->slave_cnt == 0) {
		/* 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
		 */
		memset(bond_dev->dev_addr, 0, bond_dev->addr_len);

		if (list_empty(&bond->vlan_list)) {
			bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
		} else {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: clearing HW address of %s while it "
			       "still has VLANs.\n",
			       bond_dev->name);
			printk(KERN_WARNING DRV_NAME
			       ": When re-adding slaves, make sure the bond's "
			       "HW address matches its VLANs'.\n");
		}
	} else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
		   !bond_has_challenged_slaves(bond)) {
		printk(KERN_INFO DRV_NAME
		       ": last VLAN challenged slave %s "
		       "left bond %s. VLAN blocking is removed\n",
		       slave_dev->name, bond_dev->name);
		bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
	}

	write_unlock_bh(&bond->lock);

	bond_del_vlans_from_slave(bond, slave_dev);

	/* If the mode USES_PRIMARY, then we should only remove its
	 * promisc and mc settings if it was the curr_active_slave, but that was
	 * already taken care of above when we detached the slave
	 */
	if (!USES_PRIMARY(bond->params.mode)) {
		/* unset promiscuity level from slave */
		if (bond_dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(slave_dev, -1);
		}

		/* unset allmulti level from slave */
		if (bond_dev->flags & IFF_ALLMULTI) {
			dev_set_allmulti(slave_dev, -1);
		}

		/* flush master's mc_list from slave */
		bond_mc_list_flush(bond_dev, slave_dev);
	}

	netdev_set_master(slave_dev, NULL);

	/* close slave before restoring its mac address */
	dev_close(slave_dev);

	if (app_abi_ver >= 1) {
		/* 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;
	}

	kfree(slave);

	return 0;  /* deletion OK */
}

/*
 * This function releases all slaves.
 */
static int bond_release_all(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	struct net_device *slave_dev;
	struct sockaddr addr;

	write_lock_bh(&bond->lock);

	if (bond->slave_cnt == 0) {
		goto out;
	}

	bond->current_arp_slave = NULL;
	bond->primary_slave = NULL;
	bond_change_active_slave(bond, NULL);

	while ((slave = bond->first_slave) != NULL) {
		/* Inform AD package of unbinding of slave
		 * before slave is detached from the list.
		 */
		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)) {
			/* must be called only after the slave
			 * has been detached from the list
			 */
			bond_alb_deinit_slave(bond, slave);
		}

		/* 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_del_vlans_from_slave(bond, slave_dev);

		/* If the mode USES_PRIMARY, then we should only remove its
		 * promisc and mc settings if it was the curr_active_slave, but that was
		 * already taken care of above when we detached the slave
		 */
		if (!USES_PRIMARY(bond->params.mode)) {
			/* unset promiscuity level from slave */
			if (bond_dev->flags & IFF_PROMISC) {
				dev_set_promiscuity(slave_dev, -1);
			}

			/* unset allmulti level from slave */
			if (bond_dev->flags & IFF_ALLMULTI) {
				dev_set_allmulti(slave_dev, -1);
			}

			/* flush master's mc_list from slave */
			bond_mc_list_flush(bond_dev, slave_dev);
		}

		netdev_set_master(slave_dev, NULL);

		/* close slave before restoring its mac address */
		dev_close(slave_dev);

		if (app_abi_ver >= 1) {
			/* 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;
		}

		kfree(slave);

		/* re-acquire the lock before getting the next slave */
		write_lock_bh(&bond->lock);
	}

	/* zero the mac address of the master so it will be
	 * set by the application to the mac address of the
	 * first slave
	 */
	memset(bond_dev->dev_addr, 0, bond_dev->addr_len);

	if (list_empty(&bond->vlan_list)) {
		bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
	} else {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: clearing HW address of %s while it "
		       "still has VLANs.\n",
		       bond_dev->name);
		printk(KERN_WARNING DRV_NAME
		       ": When re-adding slaves, make sure the bond's "
		       "HW address matches its VLANs'.\n");
	}

	printk(KERN_INFO DRV_NAME
	       ": %s: released all slaves\n",
	       bond_dev->name);

out:
	write_unlock_bh(&bond->lock);

	return 0;
}

/*
 * This function changes the active slave to slave <slave_dev>.
 * It returns -EINVAL in the following cases.
 *  - <slave_dev> is not found in the list.
 *  - There is not active slave now.
 *  - <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.
 */
static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *old_active = NULL;
	struct slave *new_active = NULL;
	int res = 0;

	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)) {
		return -EINVAL;
	}

	write_lock_bh(&bond->lock);

	old_active = bond->curr_active_slave;
	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);
		return 0;
	}

	if ((new_active) &&
	    (old_active) &&
	    (new_active->link == BOND_LINK_UP) &&
	    IS_UP(new_active->dev)) {
		bond_change_active_slave(bond, new_active);
	} else {
		res = -EINVAL;
	}

	write_unlock_bh(&bond->lock);

	return res;
}

static int bond_ethtool_ioctl(struct net_device *bond_dev, struct ifreq *ifr)
{
	struct ethtool_drvinfo info;
	void __user *addr = ifr->ifr_data;
	uint32_t cmd;

	if (get_user(cmd, (uint32_t __user *)addr)) {
		return -EFAULT;
	}

	switch (cmd) {
	case ETHTOOL_GDRVINFO:
		if (copy_from_user(&info, addr, sizeof(info))) {
			return -EFAULT;
		}

		if (strcmp(info.driver, "ifenslave") == 0) {
			int new_abi_ver;
			char *endptr;

			new_abi_ver = simple_strtoul(info.fw_version,
						     &endptr, 0);
			if (*endptr) {
				printk(KERN_ERR DRV_NAME
				       ": Error: got invalid ABI "
				       "version from application\n");

				return -EINVAL;
			}

			if (orig_app_abi_ver == -1) {
				orig_app_abi_ver  = new_abi_ver;
			}

			app_abi_ver = new_abi_ver;
		}

		strncpy(info.driver,  DRV_NAME, 32);
		strncpy(info.version, DRV_VERSION, 32);
		snprintf(info.fw_version, 32, "%d", BOND_ABI_VERSION);

		if (copy_to_user(addr, &info, sizeof(info))) {
			return -EFAULT;
		}

		return 0;
	default:
		return -EOPNOTSUPP;
	}
}

static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
	struct bonding *bond = bond_dev->priv;

	info->bond_mode = bond->params.mode;
	info->miimon = bond->params.miimon;

	read_lock_bh(&bond->lock);
	info->num_slaves = bond->slave_cnt;
	read_unlock_bh(&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 slave *slave;
	int i, found = 0;

	if (info->slave_id < 0) {
		return -ENODEV;
	}

	read_lock_bh(&bond->lock);

	bond_for_each_slave(bond, slave, i) {
		if (i == (int)info->slave_id) {
			found = 1;
			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;
	}

	return 0;
}

/*-------------------------------- Monitoring -------------------------------*/

/* this function is called regularly to monitor each slave's link. */
static 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.
	 */

	read_lock(&bond->curr_slave_lock);
	oldcurrent = bond->curr_active_slave;
	read_unlock(&bond->curr_slave_lock);

	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;

		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++;
				}

				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);
				}
			}
			/* 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;
				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);
				}
			}
			/* 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--;
				}
			}
			break;
		default:
			/* Should not happen */
			printk(KERN_ERR "bonding: Error: %s  Illegal value (link=%d)\n",
			       slave->dev->name, slave->link);
			goto out;
		} /* end of switch (slave->link) */

		bond_update_speed_duplex(slave);

		if (bond->params.mode == BOND_MODE_8023AD) {
			if (old_speed != slave->speed) {
				bond_3ad_adapter_speed_changed(slave);
			}

			if (old_duplex != slave->duplex) {
				bond_3ad_adapter_duplex_changed(slave);
			}
		}

	} /* end of for */

	if (do_failover) {
		write_lock(&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(&bond->curr_slave_lock);
	}

re_arm:
	if (bond->params.miimon) {
		mod_timer(&bond->mii_timer, jiffies + delta_in_ticks);
	}
out:
	read_unlock(&bond->lock);
}

Jay Vosburgh's avatar
Jay Vosburgh committed
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776

static u32 bond_glean_dev_ip(struct net_device *dev)
{
	struct in_device *idev;
	struct in_ifaddr *ifa;
	u32 addr = 0;

	if (!dev)
		return 0;

	rcu_read_lock();
	idev = __in_dev_get(dev);
	if (!idev)
		goto out;

	ifa = idev->ifa_list;
	if (!ifa)
		goto out;

	addr = ifa->ifa_local;
out:
	rcu_read_unlock();
	return addr;
}

static int bond_has_ip(struct bonding *bond)
{
	struct vlan_entry *vlan, *vlan_next;

	if (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)
			return 1;
	}

	return 0;
}

/*
 * We go to the (large) trouble of VLAN tagging ARP frames because
 * 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)
{
	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);
	       
	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");
		return;
	}
	if (vlan_id) {
		skb = vlan_put_tag(skb, vlan_id);
		if (!skb) {
			printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n");
			return;
		}
	}
	arp_xmit(skb);
}


Linus Torvalds's avatar
Linus Torvalds committed
2777
2778
static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
Jay Vosburgh's avatar
Jay Vosburgh committed
2779
	int i, vlan_id, rv;
Linus Torvalds's avatar
Linus Torvalds committed
2780
	u32 *targets = bond->params.arp_targets;
Jay Vosburgh's avatar
Jay Vosburgh committed
2781
2782
2783
2784
	struct vlan_entry *vlan, *vlan_next;
	struct net_device *vlan_dev;
	struct flowi fl;
	struct rtable *rt;
Linus Torvalds's avatar
Linus Torvalds committed
2785
2786

	for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) {
Jay Vosburgh's avatar
Jay Vosburgh committed
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
		dprintk("basa: target %x\n", targets[i]);
		if (list_empty(&bond->vlan_list)) {
			dprintk("basa: empty vlan: arp_send\n");
			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
				      bond->master_ip, 0);
			continue;
		}

		/*
		 * If VLANs are configured, we do a route lookup to
		 * determine which VLAN interface would be used, so we
		 * can tag the ARP with the proper VLAN tag.
		 */
		memset(&fl, 0, sizeof(fl));
		fl.fl4_dst = targets[i];
		fl.fl4_tos = RTO_ONLINK;

		rv = ip_route_output_key(&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));
			}
			continue;
		}

		/*
		 * This target is not on a VLAN
		 */
		if (rt->u.dst.dev == bond->dev) {
			dprintk("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];
			if (vlan_dev == rt->u.dst.dev) {
				vlan_id = vlan->vlan_id;
				dprintk("basa: vlan match on %s %d\n",
				       vlan_dev->name, vlan_id);
				break;
			}
		}

		if (vlan_id) {
			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
				      vlan->vlan_ip, vlan_id);
			continue;
		}

		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");
		}
	}
}

/*
 * Kick out a gratuitous ARP for an IP on the bonding master plus one
 * for each VLAN above us.
 */
static void bond_send_gratuitous_arp(struct bonding *bond)
{
	struct slave *slave = bond->curr_active_slave;
	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)
		return;

	if (bond->master_ip) {
		bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
				  bond->master_ip, 0);
	}

	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
		vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
		if (vlan->vlan_ip) {
			bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
				      vlan->vlan_ip, vlan->vlan_id);
		}
Linus Torvalds's avatar
Linus Torvalds committed
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
	}
}

/*
 * this function is called regularly to monitor each slave's link
 * ensuring that traffic is being sent and received when arp monitoring
 * is used in load-balancing mode. if the adapter has been dormant, then an
 * arp is transmitted to generate traffic. see activebackup_arp_monitor for
 * arp monitoring in active backup mode.
 */
static void bond_loadbalance_arp_mon(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.arp_interval * HZ) / 1000;

	if (bond->kill_timers) {
		goto out;
	}

	if (bond->slave_cnt == 0) {
		goto re_arm;
	}

	read_lock(&bond->curr_slave_lock);
	oldcurrent = bond->curr_active_slave;
	read_unlock(&bond->curr_slave_lock);

	/* see if any of the previous devices are up now (i.e. they have
	 * xmt and rcv traffic). the curr_active_slave does not come into
	 * the picture unless it is null. also, slave->jiffies is not needed
	 * here because we send an arp on each slave and give a slave as
	 * long as it needs to get the tx/rx within the delta.
	 * 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->trans_start) <= delta_in_ticks) &&
			    ((jiffies - slave->dev->last_rx) <= delta_in_ticks)) {

				slave->link  = BOND_LINK_UP;
				slave->state = BOND_STATE_ACTIVE;

				/* primary_slave has no meaning in round-robin
				 * mode. the window of a slave being up and
				 * curr_active_slave being null after enslaving
				 * is closed.
				 */
				if (!oldcurrent) {
					printk(KERN_INFO DRV_NAME
					       ": %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);
				}
			}
		} else {
			/* slave->link == BOND_LINK_UP */

			/* not all switches will respond to an arp request
			 * 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)) &&
Jay Vosburgh's avatar
Jay Vosburgh committed
2955
			     bond_has_ip(bond))) {
Linus Torvalds's avatar
Linus Torvalds committed
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020