bond_main.c 129.5 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 * 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.
 *
 */

//#define BONDING_DEBUG 1

#include <linux/kernel.h>
#include <linux/module.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>
44
#include <net/ip.h>
L
Linus Torvalds 已提交
45
#include <linux/ip.h>
46 47
#include <linux/tcp.h>
#include <linux/udp.h>
L
Linus Torvalds 已提交
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
#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>
63
#include <linux/igmp.h>
L
Linus Torvalds 已提交
64 65 66 67 68 69 70 71 72 73 74 75 76
#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>
J
Jay Vosburgh 已提交
77
#include <net/route.h>
78
#include <net/net_namespace.h>
L
Linus Torvalds 已提交
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96
#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;
97
static char *xmit_hash_policy = NULL;
L
Linus Torvalds 已提交
98 99
static int arp_interval = BOND_LINK_ARP_INTERV;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, };
100
static char *arp_validate = NULL;
101
static int fail_over_mac = 0;
102
struct bond_params bonding_defaults;
L
Linus Torvalds 已提交
103 104 105 106 107 108 109 110

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);
111 112
MODULE_PARM_DESC(downdelay, "Delay before considering link down, "
			    "in milliseconds");
L
Linus Torvalds 已提交
113
module_param(use_carrier, int, 0);
114 115
MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
			      "0 for off, 1 for on (default)");
L
Linus Torvalds 已提交
116
module_param(mode, charp, 0);
117 118 119 120
MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
		       "1 for active-backup, 2 for balance-xor, "
		       "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, "
		       "6 for balance-alb");
L
Linus Torvalds 已提交
121 122 123
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
module_param(lacp_rate, charp, 0);
124 125
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
			    "(slow/fast)");
126
module_param(xmit_hash_policy, charp, 0);
127 128
MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)"
				   ", 1 for layer 3+4");
L
Linus Torvalds 已提交
129 130 131 132
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");
133 134
module_param(arp_validate, charp, 0);
MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or all");
135 136
module_param(fail_over_mac, int, 0);
MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC.  0 of off (default), 1 for on.");
L
Linus Torvalds 已提交
137 138 139

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

140
static const char * const version =
L
Linus Torvalds 已提交
141 142
	DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";

143
LIST_HEAD(bond_dev_list);
L
Linus Torvalds 已提交
144 145 146 147 148

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

149
extern struct rw_semaphore bonding_rwsem;
150
static __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ;
L
Linus Torvalds 已提交
151 152
static int arp_ip_count	= 0;
static int bond_mode	= BOND_MODE_ROUNDROBIN;
153
static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2;
L
Linus Torvalds 已提交
154
static int lacp_fast	= 0;
155

L
Linus Torvalds 已提交
156

157
struct bond_parm_tbl bond_lacp_tbl[] = {
L
Linus Torvalds 已提交
158 159 160 161 162
{	"slow",		AD_LACP_SLOW},
{	"fast",		AD_LACP_FAST},
{	NULL,		-1},
};

163
struct bond_parm_tbl bond_mode_tbl[] = {
L
Linus Torvalds 已提交
164 165 166 167 168 169 170 171 172 173
{	"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},
};

174
struct bond_parm_tbl xmit_hashtype_tbl[] = {
175 176 177 178 179
{	"layer2",		BOND_XMIT_POLICY_LAYER2},
{	"layer3+4",		BOND_XMIT_POLICY_LAYER34},
{	NULL,			-1},
};

180 181 182 183 184 185 186 187
struct bond_parm_tbl arp_validate_tbl[] = {
{	"none",			BOND_ARP_VALIDATE_NONE},
{	"active",		BOND_ARP_VALIDATE_ACTIVE},
{	"backup",		BOND_ARP_VALIDATE_BACKUP},
{	"all",			BOND_ARP_VALIDATE_ALL},
{	NULL,			-1},
};

L
Linus Torvalds 已提交
188 189
/*-------------------------- Forward declarations ---------------------------*/

J
Jay Vosburgh 已提交
190
static void bond_send_gratuitous_arp(struct bonding *bond);
191
static void bond_deinit(struct net_device *bond_dev);
L
Linus Torvalds 已提交
192 193 194

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

195
static const char *bond_mode_name(int mode)
L
Linus Torvalds 已提交
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
{
	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;
J
Jay Vosburgh 已提交
240
	vlan->vlan_ip = 0;
L
Linus Torvalds 已提交
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

	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
472
		       ": %s: Error: Failed to add vlan id %d\n",
L
Linus Torvalds 已提交
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496
		       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.
			 */
D
Dan Aloni 已提交
497
			vlan_dev = vlan_group_get_device(bond->vlgrp, vid);
L
Linus Torvalds 已提交
498
			slave_dev->vlan_rx_kill_vid(slave_dev, vid);
D
Dan Aloni 已提交
499
			vlan_group_set_device(bond->vlgrp, vid, vlan_dev);
L
Linus Torvalds 已提交
500 501 502 503 504 505
		}
	}

	res = bond_del_vlan(bond, vid);
	if (res) {
		printk(KERN_ERR DRV_NAME
506
		       ": %s: Error: Failed to remove vlan id %d\n",
L
Linus Torvalds 已提交
507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
		       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.
		 */
D
Dan Aloni 已提交
559
		vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
L
Linus Torvalds 已提交
560
		slave_dev->vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
D
Dan Aloni 已提交
561
		vlan_group_set_device(bond->vlgrp, vlan->vlan_id, vlan_dev);
L
Linus Torvalds 已提交
562 563 564 565 566 567 568 569 570 571 572 573 574 575
	}

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 -------------------------------*/

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
/*
 * Set the carrier state for the master according to the state of its
 * slaves.  If any slaves are up, the master is up.  In 802.3ad mode,
 * do special 802.3ad magic.
 *
 * Returns zero if carrier state does not change, nonzero if it does.
 */
static int bond_set_carrier(struct bonding *bond)
{
	struct slave *slave;
	int i;

	if (bond->slave_cnt == 0)
		goto down;

	if (bond->params.mode == BOND_MODE_8023AD)
		return bond_3ad_set_carrier(bond);

	bond_for_each_slave(bond, slave, i) {
		if (slave->link == BOND_LINK_UP) {
			if (!netif_carrier_ok(bond->dev)) {
				netif_carrier_on(bond->dev);
				return 1;
			}
			return 0;
		}
	}

down:
	if (netif_carrier_ok(bond->dev)) {
		netif_carrier_off(bond->dev);
		return 1;
	}
	return 0;
}

L
Linus Torvalds 已提交
612 613 614 615 616 617 618 619 620 621
/*
 * 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;
	struct ethtool_cmd etool;
622
	int res;
L
Linus Torvalds 已提交
623 624 625 626 627

	/* Fake speed and duplex */
	slave->speed = SPEED_100;
	slave->duplex = DUPLEX_FULL;

628 629
	if (!slave_dev->ethtool_ops || !slave_dev->ethtool_ops->get_settings)
		return -1;
L
Linus Torvalds 已提交
630

631 632
	res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool);
	if (res < 0)
L
Linus Torvalds 已提交
633 634 635 636 637 638
		return -1;

	switch (etool.speed) {
	case SPEED_10:
	case SPEED_100:
	case SPEED_1000:
639
	case SPEED_10000:
L
Linus Torvalds 已提交
640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
		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;

	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);
			}
		}
	}

710 711 712 713
	/*
	 * Some drivers cache ETHTOOL_GLINK for a period of time so we only
	 * attempt to get link status from it if the above MII ioctls fail.
	 */
L
Linus Torvalds 已提交
714 715 716 717 718 719 720 721 722 723 724 725
	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 reporting, report that either there's no dev->do_ioctl,
726
	 * or both SIOCGMIIREG and get_link failed (meaning that we
L
Linus Torvalds 已提交
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
	 * 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);
		}
	}
}

838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859

/*
 * Retrieve the list of registered multicast addresses for the bonding
 * device and retransmit an IGMP JOIN request to the current active
 * slave.
 */
static void bond_resend_igmp_join_requests(struct bonding *bond)
{
	struct in_device *in_dev;
	struct ip_mc_list *im;

	rcu_read_lock();
	in_dev = __in_dev_get_rcu(bond->dev);
	if (in_dev) {
		for (im = in_dev->mc_list; im; im = im->next) {
			ip_mc_rejoin_group(im);
		}
	}

	rcu_read_unlock();
}

L
Linus Torvalds 已提交
860 861 862 863 864 865 866 867 868 869 870 871 872
/*
 * 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;
	}
873
        bond->mc_list = NULL;
L
Linus Torvalds 已提交
874 875 876 877 878
}

/*
 * Copy all the Multicast addresses from src to the bonding device dst
 */
879
static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond,
A
Al Viro 已提交
880
			     gfp_t gfp_flag)
L
Linus Torvalds 已提交
881 882 883 884
{
	struct dev_mc_list *dmi, *new_dmi;

	for (dmi = mc_list; dmi; dmi = dmi->next) {
885
		new_dmi = kmalloc(sizeof(struct dev_mc_list), gfp_flag);
L
Linus Torvalds 已提交
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

		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);
		}
967
		bond_resend_igmp_join_requests(bond);
L
Linus Torvalds 已提交
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
	}
}

/**
 * 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.
 */
1040
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
L
Linus Torvalds 已提交
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
{
	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);
1087 1088 1089 1090
		if (old_active)
			bond_set_slave_inactive_flags(old_active);
		if (new_active)
			bond_set_slave_active_flags(new_active);
L
Linus Torvalds 已提交
1091 1092 1093
	} else {
		bond->curr_active_slave = new_active;
	}
J
Jay Vosburgh 已提交
1094 1095 1096 1097 1098 1099 1100 1101 1102

	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);
		}
1103 1104 1105 1106

		/* when bonding does not set the slave MAC address, the bond MAC
		 * address is the one of the active slave.
		 */
1107
		if (new_active && bond->params.fail_over_mac)
1108 1109
			memcpy(bond->dev->dev_addr,  new_active->dev->dev_addr,
				new_active->dev->addr_len);
1110 1111 1112 1113 1114 1115 1116 1117
		if (bond->curr_active_slave &&
			test_bit(__LINK_STATE_LINKWATCH_PENDING,
					&bond->curr_active_slave->dev->state)) {
			dprintk("delaying gratuitous arp on %s\n",
				bond->curr_active_slave->dev->name);
			bond->send_grat_arp = 1;
		} else
			bond_send_gratuitous_arp(bond);
J
Jay Vosburgh 已提交
1118
	}
L
Linus Torvalds 已提交
1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131
}

/**
 * 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.
 */
1132
void bond_select_active_slave(struct bonding *bond)
L
Linus Torvalds 已提交
1133 1134
{
	struct slave *best_slave;
1135
	int rv;
L
Linus Torvalds 已提交
1136 1137 1138 1139

	best_slave = bond_find_best_slave(bond);
	if (best_slave != bond->curr_active_slave) {
		bond_change_active_slave(bond, best_slave);
1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152
		rv = bond_set_carrier(bond);
		if (!rv)
			return;

		if (netif_carrier_ok(bond->dev)) {
			printk(KERN_INFO DRV_NAME
			       ": %s: first active interface up!\n",
			       bond->dev->name);
		} else {
			printk(KERN_INFO DRV_NAME ": %s: "
			       "now running without any active interface !\n",
			       bond->dev->name);
		}
L
Linus Torvalds 已提交
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
	}
}

/*--------------------------- 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 ----------------------------------*/

1214 1215
static int bond_sethwaddr(struct net_device *bond_dev,
			  struct net_device *slave_dev)
L
Linus Torvalds 已提交
1216 1217 1218 1219 1220 1221 1222 1223
{
	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;
}

1224 1225 1226
#define BOND_VLAN_FEATURES \
	(NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX | \
	 NETIF_F_HW_VLAN_FILTER)
1227 1228

/* 
1229
 * Compute the common dev->feature set available to all slaves.  Some
1230 1231
 * feature bits are managed elsewhere, so preserve those feature bits
 * on the master device.
1232 1233 1234 1235 1236
 */
static int bond_compute_features(struct bonding *bond)
{
	struct slave *slave;
	struct net_device *bond_dev = bond->dev;
1237
	unsigned long features = bond_dev->features;
1238 1239
	unsigned short max_hard_header_len = max((u16)ETH_HLEN,
						bond_dev->hard_header_len);
1240
	int i;
1241

1242 1243 1244 1245
	features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES);
	features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
		    NETIF_F_GSO_MASK | NETIF_F_NO_CSUM;

1246
	bond_for_each_slave(bond, slave, i) {
1247 1248
		features = netdev_compute_features(features,
						   slave->dev->features);
1249 1250 1251
		if (slave->dev->hard_header_len > max_hard_header_len)
			max_hard_header_len = slave->dev->hard_header_len;
	}
1252

1253
	features |= (bond_dev->features & BOND_VLAN_FEATURES);
1254
	bond_dev->features = features;
1255
	bond_dev->hard_header_len = max_hard_header_len;
1256 1257 1258 1259

	return 0;
}

1260 1261 1262 1263

static void bond_setup_by_slave(struct net_device *bond_dev,
				struct net_device *slave_dev)
{
1264 1265
	struct bonding *bond = bond_dev->priv;

1266
	bond_dev->neigh_setup           = slave_dev->neigh_setup;
1267
	bond_dev->header_ops		= slave_dev->header_ops;
1268 1269 1270 1271 1272 1273 1274

	bond_dev->type		    = slave_dev->type;
	bond_dev->hard_header_len   = slave_dev->hard_header_len;
	bond_dev->addr_len	    = slave_dev->addr_len;

	memcpy(bond_dev->broadcast, slave_dev->broadcast,
		slave_dev->addr_len);
1275
	bond->setup_by_slave = 1;
1276 1277
}

L
Linus Torvalds 已提交
1278
/* enslave device <slave> to bond device <master> */
1279
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
L
Linus Torvalds 已提交
1280 1281 1282 1283 1284 1285 1286 1287 1288
{
	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;

1289 1290
	if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL &&
		slave_dev->do_ioctl == NULL) {
L
Linus Torvalds 已提交
1291
		printk(KERN_WARNING DRV_NAME
1292 1293
		       ": %s: Warning: no link monitoring support for %s\n",
		       bond_dev->name, slave_dev->name);
L
Linus Torvalds 已提交
1294 1295 1296 1297
	}

	/* bond must be initialized by bond_open() before enslaving */
	if (!(bond_dev->flags & IFF_UP)) {
1298 1299 1300
		printk(KERN_WARNING DRV_NAME
			" %s: master_dev is not up in bond_enslave\n",
			bond_dev->name);
L
Linus Torvalds 已提交
1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314
	}

	/* 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
1315
			       ": %s: Error: cannot enslave VLAN "
L
Linus Torvalds 已提交
1316
			       "challenged slave %s on VLAN enabled "
1317
			       "bond %s\n", bond_dev->name, slave_dev->name,
L
Linus Torvalds 已提交
1318 1319 1320 1321
			       bond_dev->name);
			return -EPERM;
		} else {
			printk(KERN_WARNING DRV_NAME
1322
			       ": %s: Warning: enslaved VLAN challenged "
L
Linus Torvalds 已提交
1323 1324
			       "slave %s. Adding VLANs will be blocked as "
			       "long as %s is part of bond %s\n",
1325
			       bond_dev->name, slave_dev->name, slave_dev->name,
L
Linus Torvalds 已提交
1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
			       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;
		}
	}

1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351
	/*
	 * Old ifenslave binaries are no longer supported.  These can
	 * be identified with moderate accurary by the state of the slave:
	 * the current ifenslave will set the interface down prior to
	 * enslaving it; the old ifenslave will not.
	 */
	if ((slave_dev->flags & IFF_UP)) {
		printk(KERN_ERR DRV_NAME ": %s is up. "
		       "This may be due to an out of date ifenslave.\n",
		       slave_dev->name);
		res = -EPERM;
		goto err_undo_flags;
	}
L
Linus Torvalds 已提交
1352

1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371
	/* set bonding device ether type by slave - bonding netdevices are
	 * created with ether_setup, so when the slave type is not ARPHRD_ETHER
	 * there is a need to override some of the type dependent attribs/funcs.
	 *
	 * bond ether type mutual exclusion - don't allow slaves of dissimilar
	 * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
	 */
	if (bond->slave_cnt == 0) {
		if (slave_dev->type != ARPHRD_ETHER)
			bond_setup_by_slave(bond_dev, slave_dev);
	} else if (bond_dev->type != slave_dev->type) {
		printk(KERN_ERR DRV_NAME ": %s ether type (%d) is different "
			"from other slaves (%d), can not enslave it.\n",
			slave_dev->name,
			slave_dev->type, bond_dev->type);
			res = -EINVAL;
			goto err_undo_flags;
	}

1372
	if (slave_dev->set_mac_address == NULL) {
1373 1374
		if (bond->slave_cnt == 0) {
			printk(KERN_WARNING DRV_NAME
1375 1376 1377 1378 1379 1380
			       ": %s: Warning: The first slave device "
			       "specified does not support setting the MAC "
			       "address. Enabling the fail_over_mac option.",
			       bond_dev->name);
			bond->params.fail_over_mac = 1;
		} else if (!bond->params.fail_over_mac) {
1381
			printk(KERN_ERR DRV_NAME
1382 1383 1384
				": %s: Error: The slave device specified "
				"does not support setting the MAC address, "
				"but fail_over_mac is not enabled.\n"
1385 1386 1387 1388
				, bond_dev->name);
			res = -EOPNOTSUPP;
			goto err_undo_flags;
		}
L
Linus Torvalds 已提交
1389 1390
	}

1391
	new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
L
Linus Torvalds 已提交
1392 1393 1394 1395 1396 1397 1398 1399 1400 1401
	if (!new_slave) {
		res = -ENOMEM;
		goto err_undo_flags;
	}

	/* save slave's original flags before calling
	 * netdev_set_master and dev_open
	 */
	new_slave->original_flags = slave_dev->flags;

1402 1403 1404 1405 1406 1407
	/*
	 * Save slave's original ("permanent") mac address for modes
	 * that need 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);
L
Linus Torvalds 已提交
1408

1409
	if (!bond->params.fail_over_mac) {
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420
		/*
		 * 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;
		}
1421
	}
L
Linus Torvalds 已提交
1422

1423 1424 1425 1426 1427
	res = netdev_set_master(slave_dev, bond_dev);
	if (res) {
		dprintk("Error %d calling netdev_set_master\n", res);
		goto err_close;
	}
1428 1429 1430 1431 1432
	/* 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;
L
Linus Torvalds 已提交
1433 1434 1435
	}

	new_slave->dev = slave_dev;
1436
	slave_dev->priv_flags |= IFF_BONDING;
L
Linus Torvalds 已提交
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 1486

	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;

1487 1488
	bond_compute_features(bond);

1489 1490
	new_slave->last_arp_rx = jiffies;

L
Linus Torvalds 已提交
1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504
	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
1505
			       ": %s: Warning: MII and ETHTOOL support not "
L
Linus Torvalds 已提交
1506 1507 1508 1509
			       "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",
1510
			       bond_dev->name, slave_dev->name);
L
Linus Torvalds 已提交
1511 1512 1513
		} else if (link_reporting == -1) {
			/* unable get link status using mii/ethtool */
			printk(KERN_WARNING DRV_NAME
1514
			       ": %s: Warning: can't get link status from "
L
Linus Torvalds 已提交
1515 1516 1517 1518
			       "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",
1519
			       bond_dev->name, slave_dev->name);
L
Linus Torvalds 已提交
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
		}
	}

	/* 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
1546
		       ": %s: Warning: failed to get speed and duplex from %s, "
L
Linus Torvalds 已提交
1547
		       "assumed to be 100Mb/sec and Full.\n",
1548
		       bond_dev->name, new_slave->dev->name);
L
Linus Torvalds 已提交
1549 1550

		if (bond->params.mode == BOND_MODE_8023AD) {
1551 1552
			printk(KERN_WARNING DRV_NAME
			       ": %s: Warning: Operation of 802.3ad mode requires ETHTOOL "
L
Linus Torvalds 已提交
1553
			       "support in base driver for proper aggregator "
1554
			       "selection.\n", bond_dev->name);
L
Linus Torvalds 已提交
1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566
		}
	}

	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:
1567 1568
		bond_set_slave_inactive_flags(new_slave);
		bond_select_active_slave(bond);
L
Linus Torvalds 已提交
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
		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;
1594
		bond_set_slave_inactive_flags(new_slave);
L
Linus Torvalds 已提交
1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611
		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) */

1612 1613
	bond_set_carrier(bond);

L
Linus Torvalds 已提交
1614 1615
	write_unlock_bh(&bond->lock);

1616 1617 1618 1619
	res = bond_create_slave_symlinks(bond_dev, slave_dev);
	if (res)
		goto err_unset_master;

L
Linus Torvalds 已提交
1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636
	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:
1637
	if (!bond->params.fail_over_mac) {
1638 1639 1640 1641
		memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
		addr.sa_family = slave_dev->type;
		dev_set_mac_address(slave_dev, &addr);
	}
L
Linus Torvalds 已提交
1642 1643 1644 1645 1646 1647

err_free:
	kfree(new_slave);

err_undo_flags:
	bond_dev->features = old_features;
1648
 
L
Linus Torvalds 已提交
1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662
	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.
 */
1663
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
L
Linus Torvalds 已提交
1664 1665 1666 1667 1668
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *oldcurrent;
	struct sockaddr addr;
	int mac_addr_differ;
1669
	DECLARE_MAC_BUF(mac);
L
Linus Torvalds 已提交
1670 1671 1672 1673 1674

	/* 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
1675
		       ": %s: Error: cannot release %s.\n",
L
Linus Torvalds 已提交
1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687
		       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);
1688
		write_unlock_bh(&bond->lock);
L
Linus Torvalds 已提交
1689 1690 1691 1692 1693 1694 1695 1696
		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
1697 1698 1699 1700
		       ": %s: Warning: the permanent HWaddr of %s - "
		       "%s - is still in use by %s. "
		       "Set the HWaddr of %s to a different address "
		       "to avoid conflicts.\n",
1701
		       bond_dev->name,
L
Linus Torvalds 已提交
1702
		       slave_dev->name,
1703
		       print_mac(mac, slave->perm_hwaddr),
L
Linus Torvalds 已提交
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
		       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);

1730 1731
	bond_compute_features(bond);

L
Linus Torvalds 已提交
1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749
	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);
	}

1750 1751 1752 1753 1754 1755 1756 1757 1758 1759
	if (oldcurrent == slave) {
		/*
		 * Note that we hold RTNL over this sequence, so there
		 * is no concern that another slave add/remove event
		 * will interfere.
		 */
		write_unlock_bh(&bond->lock);
		read_lock(&bond->lock);
		write_lock_bh(&bond->curr_slave_lock);

L
Linus Torvalds 已提交
1760 1761
		bond_select_active_slave(bond);

1762 1763 1764 1765 1766
		write_unlock_bh(&bond->curr_slave_lock);
		read_unlock(&bond->lock);
		write_lock_bh(&bond->lock);
	}

L
Linus Torvalds 已提交
1767
	if (bond->slave_cnt == 0) {
1768 1769
		bond_set_carrier(bond);

L
Linus Torvalds 已提交
1770 1771 1772 1773 1774 1775 1776 1777 1778 1779
		/* 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
1780
			       ": %s: Warning: clearing HW address of %s while it "
L
Linus Torvalds 已提交
1781
			       "still has VLANs.\n",
1782
			       bond_dev->name, bond_dev->name);
L
Linus Torvalds 已提交
1783
			printk(KERN_WARNING DRV_NAME
1784 1785 1786
			       ": %s: When re-adding slaves, make sure the bond's "
			       "HW address matches its VLANs'.\n",
			       bond_dev->name);
L
Linus Torvalds 已提交
1787 1788 1789 1790
		}
	} else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
		   !bond_has_challenged_slaves(bond)) {
		printk(KERN_INFO DRV_NAME
1791
		       ": %s: last VLAN challenged slave %s "
L
Linus Torvalds 已提交
1792
		       "left bond %s. VLAN blocking is removed\n",
1793
		       bond_dev->name, slave_dev->name, bond_dev->name);
L
Linus Torvalds 已提交
1794 1795 1796 1797 1798
		bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
	}

	write_unlock_bh(&bond->lock);

1799 1800 1801
	/* must do this from outside any spinlocks */
	bond_destroy_slave_symlinks(bond_dev, slave_dev);

L
Linus Torvalds 已提交
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
	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);

1828
	if (!bond->params.fail_over_mac) {
1829 1830 1831 1832 1833
		/* 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);
	}
L
Linus Torvalds 已提交
1834

1835
	slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
1836 1837
				   IFF_SLAVE_INACTIVE | IFF_BONDING |
				   IFF_SLAVE_NEEDARP);
L
Linus Torvalds 已提交
1838 1839 1840 1841 1842 1843

	kfree(slave);

	return 0;  /* deletion OK */
}

1844 1845 1846 1847 1848 1849 1850 1851
/*
* Destroy a bonding device.
* Must be under rtnl_lock when this function is called.
*/
void bond_destroy(struct bonding *bond)
{
	bond_deinit(bond->dev);
	bond_destroy_sysfs_entry(bond);
1852
	unregister_netdevice(bond->dev);
1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
}

/*
* First release a slave and than destroy the bond if no more slaves iare left.
* Must be under rtnl_lock when this function is called.
*/
int  bond_release_and_destroy(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	int ret;

	ret = bond_release(bond_dev, slave_dev);
	if ((ret == 0) && (bond->slave_cnt == 0)) {
		printk(KERN_INFO DRV_NAME ": %s: destroying bond %s.\n",
		       bond_dev->name, bond_dev->name);
		bond_destroy(bond);
	}
	return ret;
}

L
Linus Torvalds 已提交
1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884
/*
 * 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);

1885 1886
	netif_carrier_off(bond_dev);

L
Linus Torvalds 已提交
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
	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);
		}

1914 1915
		bond_compute_features(bond);

L
Linus Torvalds 已提交
1916 1917 1918 1919 1920 1921
		/* 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);

1922
		bond_destroy_slave_symlinks(bond_dev, slave_dev);
L
Linus Torvalds 已提交
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
		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);

1949
		if (!bond->params.fail_over_mac) {
1950 1951 1952 1953 1954
			/* 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);
		}
L
Linus Torvalds 已提交
1955

1956 1957
		slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
					   IFF_SLAVE_INACTIVE);
L
Linus Torvalds 已提交
1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974

		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
1975
		       ": %s: Warning: clearing HW address of %s while it "
L
Linus Torvalds 已提交
1976
		       "still has VLANs.\n",
1977
		       bond_dev->name, bond_dev->name);
L
Linus Torvalds 已提交
1978
		printk(KERN_WARNING DRV_NAME
1979 1980 1981
		       ": %s: When re-adding slaves, make sure the bond's "
		       "HW address matches its VLANs'.\n",
		       bond_dev->name);
L
Linus Torvalds 已提交
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
	}

	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;
	}

2022
	read_lock(&bond->lock);
L
Linus Torvalds 已提交
2023

2024
	read_lock(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2025
	old_active = bond->curr_active_slave;
2026 2027
	read_unlock(&bond->curr_slave_lock);

L
Linus Torvalds 已提交
2028 2029 2030 2031 2032 2033
	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)) {
2034
		read_unlock(&bond->lock);
L
Linus Torvalds 已提交
2035 2036 2037 2038 2039 2040 2041
		return 0;
	}

	if ((new_active) &&
	    (old_active) &&
	    (new_active->link == BOND_LINK_UP) &&
	    IS_UP(new_active->dev)) {
2042
		write_lock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2043
		bond_change_active_slave(bond, new_active);
2044
		write_unlock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2045 2046 2047 2048
	} else {
		res = -EINVAL;
	}

2049
	read_unlock(&bond->lock);
L
Linus Torvalds 已提交
2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060

	return res;
}

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;

2061
	read_lock(&bond->lock);
L
Linus Torvalds 已提交
2062
	info->num_slaves = bond->slave_cnt;
2063
	read_unlock(&bond->lock);
L
Linus Torvalds 已提交
2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077

	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;
	}

2078
	read_lock(&bond->lock);
L
Linus Torvalds 已提交
2079 2080 2081 2082 2083 2084 2085 2086

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

2087
	read_unlock(&bond->lock);
L
Linus Torvalds 已提交
2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102

	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 -------------------------------*/

2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114
/*
 * if !have_locks, return nonzero if a failover is necessary.  if
 * have_locks, do whatever failover activities are needed.
 *
 * This is to separate the inspection and failover steps for locking
 * purposes; failover requires rtnl, but acquiring it for every
 * inspection is undesirable, so a wrapper first does inspection, and
 * the acquires the necessary locks and calls again to perform
 * failover if needed.  Since all locks are dropped, a complete
 * restart is needed between calls.
 */
static int __bond_mii_monitor(struct bonding *bond, int have_locks)
L
Linus Torvalds 已提交
2115 2116 2117 2118 2119
{
	struct slave *slave, *oldcurrent;
	int do_failover = 0;
	int i;

2120
	if (bond->slave_cnt == 0)
L
Linus Torvalds 已提交
2121 2122 2123 2124 2125 2126 2127 2128
		goto out;

	/* 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.
	 */

2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139
	if (bond->send_grat_arp) {
		if (bond->curr_active_slave && test_bit(__LINK_STATE_LINKWATCH_PENDING,
				&bond->curr_active_slave->dev->state))
			dprintk("Needs to send gratuitous arp but not yet\n");
		else {
			dprintk("sending delayed gratuitous arp on on %s\n",
				bond->curr_active_slave->dev->name);
			bond_send_gratuitous_arp(bond);
			bond->send_grat_arp = 0;
		}
	}
L
Linus Torvalds 已提交
2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154
	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) {
2155 2156 2157 2158 2159
				if (!oldcurrent) {
					if (!have_locks)
						return 1;
					do_failover = 1;
				}
L
Linus Torvalds 已提交
2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173
				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",
2174
					       bond->dev->name,
L
Linus Torvalds 已提交
2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191
					       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) {
2192 2193 2194
					if (!have_locks)
						return 1;

L
Linus Torvalds 已提交
2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209
					/* 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",
2210
					       bond->dev->name,
L
Linus Torvalds 已提交
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
					       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",
2236
				       bond->dev->name,
L
Linus Torvalds 已提交
2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255
				       (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",
2256
					       bond->dev->name,
L
Linus Torvalds 已提交
2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271
					       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",
2272
				       bond->dev->name,
L
Linus Torvalds 已提交
2273 2274 2275 2276 2277
				       (bond->params.updelay - slave->delay) * bond->params.miimon,
				       slave_dev->name);
			} else {
				/* link stays up */
				if (slave->delay == 0) {
2278 2279 2280
					if (!have_locks)
						return 1;

L
Linus Torvalds 已提交
2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298
					/* 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",
2299
					       bond->dev->name,
L
Linus Torvalds 已提交
2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322
					       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 */
2323 2324
			printk(KERN_ERR DRV_NAME
			       ": %s: Error: %s Illegal value (link=%d)\n",
2325
			       bond->dev->name,
2326 2327
			       slave->dev->name,
			       slave->link);
L
Linus Torvalds 已提交
2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345
			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) {
2346 2347 2348
		ASSERT_RTNL();

		write_lock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2349 2350 2351

		bond_select_active_slave(bond);

2352 2353
		write_unlock_bh(&bond->curr_slave_lock);

2354 2355
	} else
		bond_set_carrier(bond);
L
Linus Torvalds 已提交
2356 2357

out:
2358
	return 0;
L
Linus Torvalds 已提交
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
/*
 * bond_mii_monitor
 *
 * Really a wrapper that splits the mii monitor into two phases: an
 * inspection, then (if inspection indicates something needs to be
 * done) an acquisition of appropriate locks followed by another pass
 * to implement whatever link state changes are indicated.
 */
void bond_mii_monitor(struct work_struct *work)
{
	struct bonding *bond = container_of(work, struct bonding,
					    mii_work.work);
	unsigned long delay;

	read_lock(&bond->lock);
	if (bond->kill_timers) {
		read_unlock(&bond->lock);
		return;
	}
	if (__bond_mii_monitor(bond, 0)) {
		read_unlock(&bond->lock);
		rtnl_lock();
		read_lock(&bond->lock);
		__bond_mii_monitor(bond, 1);
		rtnl_unlock();
	}

	delay = ((bond->params.miimon * HZ) / 1000) ? : 1;
	read_unlock(&bond->lock);
	queue_delayed_work(bond->wq, &bond->mii_work, delay);
}
J
Jay Vosburgh 已提交
2392

2393
static __be32 bond_glean_dev_ip(struct net_device *dev)
J
Jay Vosburgh 已提交
2394 2395 2396
{
	struct in_device *idev;
	struct in_ifaddr *ifa;
A
Al Viro 已提交
2397
	__be32 addr = 0;
J
Jay Vosburgh 已提交
2398 2399 2400 2401 2402

	if (!dev)
		return 0;

	rcu_read_lock();
2403
	idev = __in_dev_get_rcu(dev);
J
Jay Vosburgh 已提交
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
	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;
}

2436
static int bond_has_this_ip(struct bonding *bond, __be32 ip)
2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454
{
	struct vlan_entry *vlan, *vlan_next;

	if (ip == bond->master_ip)
		return 1;

	if (list_empty(&bond->vlan_list))
		return 0;

	list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
				 vlan_list) {
		if (ip == vlan->vlan_ip)
			return 1;
	}

	return 0;
}

J
Jay Vosburgh 已提交
2455 2456 2457 2458 2459
/*
 * 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.
 */
2460
static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
J
Jay Vosburgh 已提交
2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484
{
	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);
}


L
Linus Torvalds 已提交
2485 2486
static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
J
Jay Vosburgh 已提交
2487
	int i, vlan_id, rv;
2488
	__be32 *targets = bond->params.arp_targets;
J
Jay Vosburgh 已提交
2489 2490 2491 2492
	struct vlan_entry *vlan, *vlan_next;
	struct net_device *vlan_dev;
	struct flowi fl;
	struct rtable *rt;
L
Linus Torvalds 已提交
2493

2494 2495 2496
	for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
		if (!targets[i])
			continue;
J
Jay Vosburgh 已提交
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
		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) {
2528
			ip_rt_put(rt);
J
Jay Vosburgh 已提交
2529 2530 2531 2532 2533 2534 2535 2536 2537
			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) {
D
Dan Aloni 已提交
2538
			vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
J
Jay Vosburgh 已提交
2539 2540 2541 2542 2543 2544 2545 2546 2547
			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) {
2548
			ip_rt_put(rt);
J
Jay Vosburgh 已提交
2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559
			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");
		}
2560
		ip_rt_put(rt);
J
Jay Vosburgh 已提交
2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580
	}
}

/*
 * 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,
2581
				bond->master_ip, 0);
J
Jay Vosburgh 已提交
2582 2583 2584
	}

	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
D
Dan Aloni 已提交
2585
		vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
J
Jay Vosburgh 已提交
2586 2587 2588 2589
		if (vlan->vlan_ip) {
			bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
				      vlan->vlan_ip, vlan->vlan_id);
		}
L
Linus Torvalds 已提交
2590 2591 2592
	}
}

2593
static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
2594 2595
{
	int i;
2596
	__be32 *targets = bond->params.arp_targets;
2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617

	targets = bond->params.arp_targets;
	for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) {
		dprintk("bva: sip %u.%u.%u.%u tip %u.%u.%u.%u t[%d] "
			"%u.%u.%u.%u bhti(tip) %d\n",
		       NIPQUAD(sip), NIPQUAD(tip), i, NIPQUAD(targets[i]),
		       bond_has_this_ip(bond, tip));
		if (sip == targets[i]) {
			if (bond_has_this_ip(bond, tip))
				slave->last_arp_rx = jiffies;
			return;
		}
	}
}

static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
	struct arphdr *arp;
	struct slave *slave;
	struct bonding *bond;
	unsigned char *arp_ptr;
2618
	__be32 sip, tip;
2619

2620 2621 2622
	if (dev->nd_net != &init_net)
		goto out;

2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642
	if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER))
		goto out;

	bond = dev->priv;
	read_lock(&bond->lock);

	dprintk("bond_arp_rcv: bond %s skb->dev %s orig_dev %s\n",
		bond->dev->name, skb->dev ? skb->dev->name : "NULL",
		orig_dev ? orig_dev->name : "NULL");

	slave = bond_get_slave_by_dev(bond, orig_dev);
	if (!slave || !slave_do_arp_validate(bond, slave))
		goto out_unlock;

	/* ARP header, plus 2 device addresses, plus 2 IP addresses.  */
	if (!pskb_may_pull(skb, (sizeof(struct arphdr) +
				 (2 * dev->addr_len) +
				 (2 * sizeof(u32)))))
		goto out_unlock;

2643
	arp = arp_hdr(skb);
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
	if (arp->ar_hln != dev->addr_len ||
	    skb->pkt_type == PACKET_OTHERHOST ||
	    skb->pkt_type == PACKET_LOOPBACK ||
	    arp->ar_hrd != htons(ARPHRD_ETHER) ||
	    arp->ar_pro != htons(ETH_P_IP) ||
	    arp->ar_pln != 4)
		goto out_unlock;

	arp_ptr = (unsigned char *)(arp + 1);
	arp_ptr += dev->addr_len;
	memcpy(&sip, arp_ptr, 4);
	arp_ptr += 4 + dev->addr_len;
	memcpy(&tip, arp_ptr, 4);

	dprintk("bond_arp_rcv: %s %s/%d av %d sv %d sip %u.%u.%u.%u"
		" tip %u.%u.%u.%u\n", bond->dev->name, slave->dev->name,
		slave->state, bond->params.arp_validate,
		slave_do_arp_validate(bond, slave), NIPQUAD(sip), NIPQUAD(tip));

	/*
	 * Backup slaves won't see the ARP reply, but do come through
	 * here for each ARP probe (so we swap the sip/tip to validate
	 * the probe).  In a "redundant switch, common router" type of
	 * configuration, the ARP probe will (hopefully) travel from
	 * the active, through one switch, the router, then the other
	 * switch before reaching the backup.
	 */
	if (slave->state == BOND_STATE_ACTIVE)
		bond_validate_arp(bond, slave, sip, tip);
	else
		bond_validate_arp(bond, slave, tip, sip);

out_unlock:
	read_unlock(&bond->lock);
out:
	dev_kfree_skb(skb);
	return NET_RX_SUCCESS;
}

L
Linus Torvalds 已提交
2683 2684 2685 2686 2687 2688 2689
/*
 * 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.
 */
2690
void bond_loadbalance_arp_mon(struct work_struct *work)
L
Linus Torvalds 已提交
2691
{
2692 2693
	struct bonding *bond = container_of(work, struct bonding,
					    arp_work.work);
L
Linus Torvalds 已提交
2694 2695 2696 2697 2698 2699 2700 2701 2702 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
	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, ",
2740
					       bond->dev->name,
L
Linus Torvalds 已提交
2741 2742 2743 2744 2745
					       slave->dev->name);
					do_failover = 1;
				} else {
					printk(KERN_INFO DRV_NAME
					       ": %s: interface %s is now up\n",
2746
					       bond->dev->name,
L
Linus Torvalds 已提交
2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758
					       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)) &&
J
Jay Vosburgh 已提交
2759
			     bond_has_ip(bond))) {
L
Linus Torvalds 已提交
2760 2761 2762 2763 2764 2765 2766 2767 2768 2769

				slave->link  = BOND_LINK_DOWN;
				slave->state = BOND_STATE_BACKUP;

				if (slave->link_failure_count < UINT_MAX) {
					slave->link_failure_count++;
				}

				printk(KERN_INFO DRV_NAME
				       ": %s: interface %s is now down.\n",
2770
				       bond->dev->name,
L
Linus Torvalds 已提交
2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791
				       slave->dev->name);

				if (slave == oldcurrent) {
					do_failover = 1;
				}
			}
		}

		/* note: if switch is in round-robin mode, all links
		 * must tx arp to ensure all links rx an arp - otherwise
		 * links may oscillate or not come up at all; if switch is
		 * in something like xor mode, there is nothing we can
		 * do - all replies will be rx'ed on same link causing slaves
		 * to be unstable during low/no traffic periods
		 */
		if (IS_UP(slave->dev)) {
			bond_arp_send_all(bond, slave);
		}
	}

	if (do_failover) {
2792 2793
		rtnl_lock();
		write_lock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2794 2795 2796

		bond_select_active_slave(bond);

2797 2798 2799
		write_unlock_bh(&bond->curr_slave_lock);
		rtnl_unlock();

L
Linus Torvalds 已提交
2800 2801 2802
	}

re_arm:
2803 2804
	if (bond->params.arp_interval)
		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
L
Linus Torvalds 已提交
2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823
out:
	read_unlock(&bond->lock);
}

/*
 * When using arp monitoring in active-backup mode, this function is
 * called to determine if any backup slaves have went down or a new
 * current slave needs to be found.
 * The backup slaves never generate traffic, they are considered up by merely
 * receiving traffic. If the current slave goes down, each backup slave will
 * be given the opportunity to tx/rx an arp before being taken down - this
 * prevents all slaves from being taken down due to the current slave not
 * sending any traffic for the backups to receive. The arps are not necessarily
 * necessary, any tx and rx traffic will keep the current slave up. While any
 * rx traffic will keep the backup slaves up, the current slave is responsible
 * for generating traffic to keep them up regardless of any other traffic they
 * may have received.
 * see loadbalance_arp_monitor for arp monitoring in load balancing mode
 */
2824
void bond_activebackup_arp_mon(struct work_struct *work)
L
Linus Torvalds 已提交
2825
{
2826 2827
	struct bonding *bond = container_of(work, struct bonding,
					    arp_work.work);
L
Linus Torvalds 已提交
2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850
	struct slave *slave;
	int delta_in_ticks;
	int i;

	read_lock(&bond->lock);

	delta_in_ticks = (bond->params.arp_interval * HZ) / 1000;

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

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

	/* determine if any slave has come up or any backup slave has
	 * gone down
	 * TODO: what about up/down delay in arp mode? it wasn't here before
	 *       so it can wait
	 */
	bond_for_each_slave(bond, slave, i) {
		if (slave->link != BOND_LINK_UP) {
2851 2852
			if ((jiffies - slave_last_rx(bond, slave)) <=
			     delta_in_ticks) {
L
Linus Torvalds 已提交
2853 2854 2855

				slave->link = BOND_LINK_UP;

2856 2857 2858
				rtnl_lock();

				write_lock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874

				if ((!bond->curr_active_slave) &&
				    ((jiffies - slave->dev->trans_start) <= delta_in_ticks)) {
					bond_change_active_slave(bond, slave);
					bond->current_arp_slave = NULL;
				} else if (bond->curr_active_slave != slave) {
					/* this slave has just come up but we
					 * already have a current slave; this
					 * can also happen if bond_enslave adds
					 * a new slave that is up while we are
					 * searching for a new slave
					 */
					bond_set_slave_inactive_flags(slave);
					bond->current_arp_slave = NULL;
				}

2875 2876
				bond_set_carrier(bond);

L
Linus Torvalds 已提交
2877 2878 2879 2880
				if (slave == bond->curr_active_slave) {
					printk(KERN_INFO DRV_NAME
					       ": %s: %s is up and now the "
					       "active interface\n",
2881
					       bond->dev->name,
L
Linus Torvalds 已提交
2882
					       slave->dev->name);
2883
					netif_carrier_on(bond->dev);
L
Linus Torvalds 已提交
2884 2885 2886 2887
				} else {
					printk(KERN_INFO DRV_NAME
					       ": %s: backup interface %s is "
					       "now up\n",
2888
					       bond->dev->name,
L
Linus Torvalds 已提交
2889 2890 2891
					       slave->dev->name);
				}

2892 2893
				write_unlock_bh(&bond->curr_slave_lock);
				rtnl_unlock();
L
Linus Torvalds 已提交
2894 2895 2896 2897 2898 2899
			}
		} else {
			read_lock(&bond->curr_slave_lock);

			if ((slave != bond->curr_active_slave) &&
			    (!bond->current_arp_slave) &&
2900
			    (((jiffies - slave_last_rx(bond, slave)) >= 3*delta_in_ticks) &&
J
Jay Vosburgh 已提交
2901
			     bond_has_ip(bond))) {
L
Linus Torvalds 已提交
2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924
				/* a backup slave has gone down; three times
				 * the delta allows the current slave to be
				 * taken out before the backup slave.
				 * note: a non-null current_arp_slave indicates
				 * the curr_active_slave went down and we are
				 * searching for a new one; under this
				 * condition we only take the curr_active_slave
				 * down - this gives each slave a chance to
				 * tx/rx traffic before being taken out
				 */

				read_unlock(&bond->curr_slave_lock);

				slave->link  = BOND_LINK_DOWN;

				if (slave->link_failure_count < UINT_MAX) {
					slave->link_failure_count++;
				}

				bond_set_slave_inactive_flags(slave);

				printk(KERN_INFO DRV_NAME
				       ": %s: backup interface %s is now down\n",
2925
				       bond->dev->name,
L
Linus Torvalds 已提交
2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946
				       slave->dev->name);
			} else {
				read_unlock(&bond->curr_slave_lock);
			}
		}
	}

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

	if (slave) {
		/* if we have sent traffic in the past 2*arp_intervals but
		 * haven't xmit and rx traffic in that time interval, select
		 * a different slave. slave->jiffies is only updated when
		 * a slave first becomes the curr_active_slave - not necessarily
		 * after every arp; this ensures the slave has a full 2*delta
		 * before being taken out. if a primary is being used, check
		 * if it is up and needs to take over as the curr_active_slave
		 */
		if ((((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) ||
2947
	    (((jiffies - slave_last_rx(bond, slave)) >= (2*delta_in_ticks)) &&
J
Jay Vosburgh 已提交
2948
	     bond_has_ip(bond))) &&
L
Linus Torvalds 已提交
2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959
		    ((jiffies - slave->jiffies) >= 2*delta_in_ticks)) {

			slave->link  = BOND_LINK_DOWN;

			if (slave->link_failure_count < UINT_MAX) {
				slave->link_failure_count++;
			}

			printk(KERN_INFO DRV_NAME
			       ": %s: link status down for active interface "
			       "%s, disabling it\n",
2960
			       bond->dev->name,
L
Linus Torvalds 已提交
2961 2962
			       slave->dev->name);

2963 2964
			rtnl_lock();
			write_lock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2965 2966 2967 2968

			bond_select_active_slave(bond);
			slave = bond->curr_active_slave;

2969 2970 2971
			write_unlock_bh(&bond->curr_slave_lock);

			rtnl_unlock();
L
Linus Torvalds 已提交
2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984

			bond->current_arp_slave = slave;

			if (slave) {
				slave->jiffies = jiffies;
			}
		} else if ((bond->primary_slave) &&
			   (bond->primary_slave != slave) &&
			   (bond->primary_slave->link == BOND_LINK_UP)) {
			/* at this point, slave is the curr_active_slave */
			printk(KERN_INFO DRV_NAME
			       ": %s: changing from interface %s to primary "
			       "interface %s\n",
2985
			       bond->dev->name,
L
Linus Torvalds 已提交
2986 2987 2988 2989
			       slave->dev->name,
			       bond->primary_slave->dev->name);

			/* primary is up so switch to it */
2990 2991
			rtnl_lock();
			write_lock_bh(&bond->curr_slave_lock);
L
Linus Torvalds 已提交
2992
			bond_change_active_slave(bond, bond->primary_slave);
2993 2994 2995
			write_unlock_bh(&bond->curr_slave_lock);

			rtnl_unlock();
L
Linus Torvalds 已提交
2996 2997 2998 2999 3000 3001 3002 3003 3004 3005

			slave = bond->primary_slave;
			slave->jiffies = jiffies;
		} else {
			bond->current_arp_slave = NULL;
		}

		/* the current slave must tx an arp to ensure backup slaves
		 * rx traffic
		 */
J
Jay Vosburgh 已提交
3006
		if (slave && bond_has_ip(bond)) {
L
Linus Torvalds 已提交
3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023
			bond_arp_send_all(bond, slave);
		}
	}

	/* if we don't have a curr_active_slave, search for the next available
	 * backup slave from the current_arp_slave and make it the candidate
	 * for becoming the curr_active_slave
	 */
	if (!slave) {
		if (!bond->current_arp_slave) {
			bond->current_arp_slave = bond->first_slave;
		}

		if (bond->current_arp_slave) {
			bond_set_slave_inactive_flags(bond->current_arp_slave);

			/* search for next candidate */
3024
			bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) {
L
Linus Torvalds 已提交
3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051
				if (IS_UP(slave->dev)) {
					slave->link = BOND_LINK_BACK;
					bond_set_slave_active_flags(slave);
					bond_arp_send_all(bond, slave);
					slave->jiffies = jiffies;
					bond->current_arp_slave = slave;
					break;
				}

				/* if the link state is up at this point, we
				 * mark it down - this can happen if we have
				 * simultaneous link failures and
				 * reselect_active_interface doesn't make this
				 * one the current slave so it is still marked
				 * up when it is actually down
				 */
				if (slave->link == BOND_LINK_UP) {
					slave->link  = BOND_LINK_DOWN;
					if (slave->link_failure_count < UINT_MAX) {
						slave->link_failure_count++;
					}

					bond_set_slave_inactive_flags(slave);

					printk(KERN_INFO DRV_NAME
					       ": %s: backup interface %s is "
					       "now down.\n",
3052
					       bond->dev->name,
L
Linus Torvalds 已提交
3053 3054 3055 3056 3057 3058 3059 3060
					       slave->dev->name);
				}
			}
		}
	}

re_arm:
	if (bond->params.arp_interval) {
3061
		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
L
Linus Torvalds 已提交
3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081
	}
out:
	read_unlock(&bond->lock);
}

/*------------------------------ proc/seq_file-------------------------------*/

#ifdef CONFIG_PROC_FS

#define SEQ_START_TOKEN ((void *)1)

static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bonding *bond = seq->private;
	loff_t off = 0;
	struct slave *slave;
	int i;

	/* make sure the bond won't be taken away */
	read_lock(&dev_base_lock);
3082
	read_lock(&bond->lock);
L
Linus Torvalds 已提交
3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115

	if (*pos == 0) {
		return SEQ_START_TOKEN;
	}

	bond_for_each_slave(bond, slave, i) {
		if (++off == *pos) {
			return slave;
		}
	}

	return NULL;
}

static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bonding *bond = seq->private;
	struct slave *slave = v;

	++*pos;
	if (v == SEQ_START_TOKEN) {
		return bond->first_slave;
	}

	slave = slave->next;

	return (slave == bond->first_slave) ? NULL : slave;
}

static void bond_info_seq_stop(struct seq_file *seq, void *v)
{
	struct bonding *bond = seq->private;

3116
	read_unlock(&bond->lock);
L
Linus Torvalds 已提交
3117 3118 3119 3120 3121 3122 3123
	read_unlock(&dev_base_lock);
}

static void bond_info_show_master(struct seq_file *seq)
{
	struct bonding *bond = seq->private;
	struct slave *curr;
3124 3125
	int i;
	u32 target;
L
Linus Torvalds 已提交
3126 3127 3128 3129 3130

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

3131
	seq_printf(seq, "Bonding Mode: %s",
L
Linus Torvalds 已提交
3132 3133
		   bond_mode_name(bond->params.mode));

3134 3135 3136 3137 3138 3139
	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP &&
	    bond->params.fail_over_mac)
		seq_printf(seq, " (fail_over_mac)");

	seq_printf(seq, "\n");

3140 3141 3142 3143 3144 3145 3146
	if (bond->params.mode == BOND_MODE_XOR ||
		bond->params.mode == BOND_MODE_8023AD) {
		seq_printf(seq, "Transmit Hash Policy: %s (%d)\n",
			xmit_hashtype_tbl[bond->params.xmit_policy].modename,
			bond->params.xmit_policy);
	}

L
Linus Torvalds 已提交
3147 3148
	if (USES_PRIMARY(bond->params.mode)) {
		seq_printf(seq, "Primary Slave: %s\n",
3149 3150
			   (bond->primary_slave) ?
			   bond->primary_slave->dev->name : "None");
L
Linus Torvalds 已提交
3151 3152 3153 3154 3155

		seq_printf(seq, "Currently Active Slave: %s\n",
			   (curr) ? curr->dev->name : "None");
	}

3156 3157
	seq_printf(seq, "MII Status: %s\n", netif_carrier_ok(bond->dev) ?
		   "up" : "down");
L
Linus Torvalds 已提交
3158 3159 3160 3161 3162 3163
	seq_printf(seq, "MII Polling Interval (ms): %d\n", bond->params.miimon);
	seq_printf(seq, "Up Delay (ms): %d\n",
		   bond->params.updelay * bond->params.miimon);
	seq_printf(seq, "Down Delay (ms): %d\n",
		   bond->params.downdelay * bond->params.miimon);

3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184

	/* ARP information */
	if(bond->params.arp_interval > 0) {
		int printed=0;
		seq_printf(seq, "ARP Polling Interval (ms): %d\n",
				bond->params.arp_interval);

		seq_printf(seq, "ARP IP target/s (n.n.n.n form):");

		for(i = 0; (i < BOND_MAX_ARP_TARGETS) ;i++) {
			if (!bond->params.arp_targets[i])
				continue;
			if (printed)
				seq_printf(seq, ",");
			target = ntohl(bond->params.arp_targets[i]);
			seq_printf(seq, " %d.%d.%d.%d", HIPQUAD(target));
			printed = 1;
		}
		seq_printf(seq, "\n");
	}

L
Linus Torvalds 已提交
3185 3186
	if (bond->params.mode == BOND_MODE_8023AD) {
		struct ad_info ad_info;
3187
		DECLARE_MAC_BUF(mac);
L
Linus Torvalds 已提交
3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206

		seq_puts(seq, "\n802.3ad info\n");
		seq_printf(seq, "LACP rate: %s\n",
			   (bond->params.lacp_fast) ? "fast" : "slow");

		if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
			seq_printf(seq, "bond %s has no active aggregator\n",
				   bond->dev->name);
		} else {
			seq_printf(seq, "Active Aggregator Info:\n");

			seq_printf(seq, "\tAggregator ID: %d\n",
				   ad_info.aggregator_id);
			seq_printf(seq, "\tNumber of ports: %d\n",
				   ad_info.ports);
			seq_printf(seq, "\tActor Key: %d\n",
				   ad_info.actor_key);
			seq_printf(seq, "\tPartner Key: %d\n",
				   ad_info.partner_key);
3207 3208
			seq_printf(seq, "\tPartner Mac Address: %s\n",
				   print_mac(mac, ad_info.partner_system));
L
Linus Torvalds 已提交
3209 3210 3211 3212 3213 3214 3215
		}
	}
}

static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave)
{
	struct bonding *bond = seq->private;
3216
	DECLARE_MAC_BUF(mac);
L
Linus Torvalds 已提交
3217 3218 3219 3220

	seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
	seq_printf(seq, "MII Status: %s\n",
		   (slave->link == BOND_LINK_UP) ?  "up" : "down");
3221
	seq_printf(seq, "Link Failure Count: %u\n",
L
Linus Torvalds 已提交
3222 3223
		   slave->link_failure_count);

3224
	seq_printf(seq,
3225 3226
		   "Permanent HW addr: %s\n",
		   print_mac(mac, slave->perm_hwaddr));
L
Linus Torvalds 已提交
3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276

	if (bond->params.mode == BOND_MODE_8023AD) {
		const struct aggregator *agg
			= SLAVE_AD_INFO(slave).port.aggregator;

		if (agg) {
			seq_printf(seq, "Aggregator ID: %d\n",
				   agg->aggregator_identifier);
		} else {
			seq_puts(seq, "Aggregator ID: N/A\n");
		}
	}
}

static int bond_info_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "%s\n", version);
		bond_info_show_master(seq);
	} else {
		bond_info_show_slave(seq, v);
	}

	return 0;
}

static struct seq_operations bond_info_seq_ops = {
	.start = bond_info_seq_start,
	.next  = bond_info_seq_next,
	.stop  = bond_info_seq_stop,
	.show  = bond_info_seq_show,
};

static int bond_info_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	struct proc_dir_entry *proc;
	int res;

	res = seq_open(file, &bond_info_seq_ops);
	if (!res) {
		/* recover the pointer buried in proc_dir_entry data */
		seq = file->private_data;
		proc = PDE(inode);
		seq->private = proc->data;
	}

	return res;
}

3277
static const struct file_operations bond_info_fops = {
L
Linus Torvalds 已提交
3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323
	.owner   = THIS_MODULE,
	.open    = bond_info_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};

static int bond_create_proc_entry(struct bonding *bond)
{
	struct net_device *bond_dev = bond->dev;

	if (bond_proc_dir) {
		bond->proc_entry = create_proc_entry(bond_dev->name,
						     S_IRUGO,
						     bond_proc_dir);
		if (bond->proc_entry == NULL) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: Cannot create /proc/net/%s/%s\n",
			       DRV_NAME, bond_dev->name);
		} else {
			bond->proc_entry->data = bond;
			bond->proc_entry->proc_fops = &bond_info_fops;
			bond->proc_entry->owner = THIS_MODULE;
			memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ);
		}
	}

	return 0;
}

static void bond_remove_proc_entry(struct bonding *bond)
{
	if (bond_proc_dir && bond->proc_entry) {
		remove_proc_entry(bond->proc_file_name, bond_proc_dir);
		memset(bond->proc_file_name, 0, IFNAMSIZ);
		bond->proc_entry = NULL;
	}
}

/* Create the bonding directory under /proc/net, if doesn't exist yet.
 * Caller must hold rtnl_lock.
 */
static void bond_create_proc_dir(void)
{
	int len = strlen(DRV_NAME);

3324
	for (bond_proc_dir = init_net.proc_net->subdir; bond_proc_dir;
L
Linus Torvalds 已提交
3325 3326 3327 3328 3329 3330 3331 3332
	     bond_proc_dir = bond_proc_dir->next) {
		if ((bond_proc_dir->namelen == len) &&
		    !memcmp(bond_proc_dir->name, DRV_NAME, len)) {
			break;
		}
	}

	if (!bond_proc_dir) {
3333
		bond_proc_dir = proc_mkdir(DRV_NAME, init_net.proc_net);
L
Linus Torvalds 已提交
3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367
		if (bond_proc_dir) {
			bond_proc_dir->owner = THIS_MODULE;
		} else {
			printk(KERN_WARNING DRV_NAME
				": Warning: cannot create /proc/net/%s\n",
				DRV_NAME);
		}
	}
}

/* Destroy the bonding directory under /proc/net, if empty.
 * Caller must hold rtnl_lock.
 */
static void bond_destroy_proc_dir(void)
{
	struct proc_dir_entry *de;

	if (!bond_proc_dir) {
		return;
	}

	/* verify that the /proc dir is empty */
	for (de = bond_proc_dir->subdir; de; de = de->next) {
		/* ignore . and .. */
		if (*(de->name) != '.') {
			break;
		}
	}

	if (de) {
		if (bond_proc_dir->owner == THIS_MODULE) {
			bond_proc_dir->owner = NULL;
		}
	} else {
3368
		remove_proc_entry(DRV_NAME, init_net.proc_net);
L
Linus Torvalds 已提交
3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384
		bond_proc_dir = NULL;
	}
}
#endif /* CONFIG_PROC_FS */

/*-------------------------- netdev event handling --------------------------*/

/*
 * Change device name
 */
static int bond_event_changename(struct bonding *bond)
{
#ifdef CONFIG_PROC_FS
	bond_remove_proc_entry(bond);
	bond_create_proc_entry(bond);
#endif
3385 3386 3387 3388
	down_write(&(bonding_rwsem));
        bond_destroy_sysfs_entry(bond);
        bond_create_sysfs_entry(bond);
	up_write(&(bonding_rwsem));
L
Linus Torvalds 已提交
3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413
	return NOTIFY_DONE;
}

static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev)
{
	struct bonding *event_bond = bond_dev->priv;

	switch (event) {
	case NETDEV_CHANGENAME:
		return bond_event_changename(event_bond);
	case NETDEV_UNREGISTER:
		/*
		 * TODO: remove a bond from the list?
		 */
		break;
	default:
		break;
	}

	return NOTIFY_DONE;
}

static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev)
{
	struct net_device *bond_dev = slave_dev->master;
3414
	struct bonding *bond = bond_dev->priv;
L
Linus Torvalds 已提交
3415 3416 3417 3418

	switch (event) {
	case NETDEV_UNREGISTER:
		if (bond_dev) {
3419 3420 3421 3422
			if (bond->setup_by_slave)
				bond_release_and_destroy(bond_dev, slave_dev);
			else
				bond_release(bond_dev, slave_dev);
L
Linus Torvalds 已提交
3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455
		}
		break;
	case NETDEV_CHANGE:
		/*
		 * TODO: is this what we get if somebody
		 * sets up a hierarchical bond, then rmmod's
		 * one of the slave bonding devices?
		 */
		break;
	case NETDEV_DOWN:
		/*
		 * ... Or is it this?
		 */
		break;
	case NETDEV_CHANGEMTU:
		/*
		 * TODO: Should slaves be allowed to
		 * independently alter their MTU?  For
		 * an active-backup bond, slaves need
		 * not be the same type of device, so
		 * MTUs may vary.  For other modes,
		 * slaves arguably should have the
		 * same MTUs. To do this, we'd need to
		 * take over the slave's change_mtu
		 * function for the duration of their
		 * servitude.
		 */
		break;
	case NETDEV_CHANGENAME:
		/*
		 * TODO: handle changing the primary's name
		 */
		break;
3456 3457 3458
	case NETDEV_FEAT_CHANGE:
		bond_compute_features(bond);
		break;
L
Linus Torvalds 已提交
3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469
	default:
		break;
	}

	return NOTIFY_DONE;
}

/*
 * bond_netdev_event: handle netdev notifier chain events.
 *
 * This function receives events for the netdev chain.  The caller (an
3470
 * ioctl handler calling blocking_notifier_call_chain) holds the necessary
L
Linus Torvalds 已提交
3471 3472 3473 3474 3475 3476 3477
 * locks for us to safely manipulate the slave devices (RTNL lock,
 * dev_probe_lock).
 */
static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *event_dev = (struct net_device *)ptr;

3478 3479 3480
	if (event_dev->nd_net != &init_net)
		return NOTIFY_DONE;

L
Linus Torvalds 已提交
3481 3482 3483 3484
	dprintk("event_dev: %s, event: %lx\n",
		(event_dev ? event_dev->name : "None"),
		event);

3485 3486 3487
	if (!(event_dev->priv_flags & IFF_BONDING))
		return NOTIFY_DONE;

L
Linus Torvalds 已提交
3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500
	if (event_dev->flags & IFF_MASTER) {
		dprintk("IFF_MASTER\n");
		return bond_master_netdev_event(event, event_dev);
	}

	if (event_dev->flags & IFF_SLAVE) {
		dprintk("IFF_SLAVE\n");
		return bond_slave_netdev_event(event, event_dev);
	}

	return NOTIFY_DONE;
}

J
Jay Vosburgh 已提交
3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534
/*
 * bond_inetaddr_event: handle inetaddr notifier chain events.
 *
 * We keep track of device IPs primarily to use as source addresses in
 * ARP monitor probes (rather than spewing out broadcasts all the time).
 *
 * We track one IP for the main device (if it has one), plus one per VLAN.
 */
static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct in_ifaddr *ifa = ptr;
	struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev;
	struct bonding *bond, *bond_next;
	struct vlan_entry *vlan, *vlan_next;

	list_for_each_entry_safe(bond, bond_next, &bond_dev_list, bond_list) {
		if (bond->dev == event_dev) {
			switch (event) {
			case NETDEV_UP:
				bond->master_ip = ifa->ifa_local;
				return NOTIFY_OK;
			case NETDEV_DOWN:
				bond->master_ip = bond_glean_dev_ip(bond->dev);
				return NOTIFY_OK;
			default:
				return NOTIFY_DONE;
			}
		}

		if (list_empty(&bond->vlan_list))
			continue;

		list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
					 vlan_list) {
D
Dan Aloni 已提交
3535
			vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
J
Jay Vosburgh 已提交
3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553
			if (vlan_dev == event_dev) {
				switch (event) {
				case NETDEV_UP:
					vlan->vlan_ip = ifa->ifa_local;
					return NOTIFY_OK;
				case NETDEV_DOWN:
					vlan->vlan_ip =
						bond_glean_dev_ip(vlan_dev);
					return NOTIFY_OK;
				default:
					return NOTIFY_DONE;
				}
			}
		}
	}
	return NOTIFY_DONE;
}

L
Linus Torvalds 已提交
3554 3555 3556 3557
static struct notifier_block bond_netdev_notifier = {
	.notifier_call = bond_netdev_event,
};

J
Jay Vosburgh 已提交
3558 3559 3560 3561
static struct notifier_block bond_inetaddr_notifier = {
	.notifier_call = bond_inetaddr_event,
};

L
Linus Torvalds 已提交
3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582
/*-------------------------- Packet type handling ---------------------------*/

/* register to receive lacpdus on a bond */
static void bond_register_lacpdu(struct bonding *bond)
{
	struct packet_type *pk_type = &(BOND_AD_INFO(bond).ad_pkt_type);

	/* initialize packet type */
	pk_type->type = PKT_TYPE_LACPDU;
	pk_type->dev = bond->dev;
	pk_type->func = bond_3ad_lacpdu_recv;

	dev_add_pack(pk_type);
}

/* unregister to receive lacpdus on a bond */
static void bond_unregister_lacpdu(struct bonding *bond)
{
	dev_remove_pack(&(BOND_AD_INFO(bond).ad_pkt_type));
}

3583 3584 3585 3586
void bond_register_arp(struct bonding *bond)
{
	struct packet_type *pt = &bond->arp_mon_pt;

J
Jay Vosburgh 已提交
3587 3588 3589
	if (pt->type)
		return;

3590
	pt->type = htons(ETH_P_ARP);
J
Jay Vosburgh 已提交
3591
	pt->dev = bond->dev;
3592 3593 3594 3595 3596 3597
	pt->func = bond_arp_rcv;
	dev_add_pack(pt);
}

void bond_unregister_arp(struct bonding *bond)
{
J
Jay Vosburgh 已提交
3598 3599 3600 3601
	struct packet_type *pt = &bond->arp_mon_pt;

	dev_remove_pack(pt);
	pt->type = 0;
3602 3603
}

3604 3605 3606
/*---------------------------- Hashing Policies -----------------------------*/

/*
3607
 * Hash for the output device based upon layer 3 and layer 4 data. If
3608 3609 3610 3611 3612 3613 3614
 * the packet is a frag or not TCP or UDP, just use layer 3 data.  If it is
 * altogether not IP, mimic bond_xmit_hash_policy_l2()
 */
static int bond_xmit_hash_policy_l34(struct sk_buff *skb,
				    struct net_device *bond_dev, int count)
{
	struct ethhdr *data = (struct ethhdr *)skb->data;
3615
	struct iphdr *iph = ip_hdr(skb);
3616
	__be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
3617 3618 3619 3620 3621 3622
	int layer4_xor = 0;

	if (skb->protocol == __constant_htons(ETH_P_IP)) {
		if (!(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) &&
		    (iph->protocol == IPPROTO_TCP ||
		     iph->protocol == IPPROTO_UDP)) {
3623
			layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1)));
3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643
		}
		return (layer4_xor ^
			((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;

	}

	return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
}

/*
 * Hash for the output device based upon layer 2 data
 */
static int bond_xmit_hash_policy_l2(struct sk_buff *skb,
				   struct net_device *bond_dev, int count)
{
	struct ethhdr *data = (struct ethhdr *)skb->data;

	return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
}

L
Linus Torvalds 已提交
3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661
/*-------------------------- Device entry points ----------------------------*/

static int bond_open(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;

	bond->kill_timers = 0;

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* bond_alb_initialize must be called before the timer
		 * is started.
		 */
		if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB))) {
			/* something went wrong - fail the open operation */
			return -1;
		}

3662 3663
		INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
		queue_delayed_work(bond->wq, &bond->alb_work, 0);
L
Linus Torvalds 已提交
3664 3665 3666
	}

	if (bond->params.miimon) {  /* link check interval, in milliseconds. */
3667 3668
		INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
		queue_delayed_work(bond->wq, &bond->mii_work, 0);
L
Linus Torvalds 已提交
3669 3670 3671
	}

	if (bond->params.arp_interval) {  /* arp interval, in milliseconds. */
3672 3673 3674 3675 3676 3677 3678 3679
		if (bond->params.mode == BOND_MODE_ACTIVEBACKUP)
			INIT_DELAYED_WORK(&bond->arp_work,
					  bond_activebackup_arp_mon);
		else
			INIT_DELAYED_WORK(&bond->arp_work,
					  bond_loadbalance_arp_mon);

		queue_delayed_work(bond->wq, &bond->arp_work, 0);
3680 3681
		if (bond->params.arp_validate)
			bond_register_arp(bond);
L
Linus Torvalds 已提交
3682 3683 3684
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
3685
		INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
3686
		queue_delayed_work(bond->wq, &bond->ad_work, 0);
L
Linus Torvalds 已提交
3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702
		/* register to receive LACPDUs */
		bond_register_lacpdu(bond);
	}

	return 0;
}

static int bond_close(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* Unregister the receive of LACPDUs */
		bond_unregister_lacpdu(bond);
	}

3703 3704 3705
	if (bond->params.arp_validate)
		bond_unregister_arp(bond);

L
Linus Torvalds 已提交
3706 3707 3708 3709 3710 3711 3712 3713 3714
	write_lock_bh(&bond->lock);


	/* signal timers not to re-arm */
	bond->kill_timers = 1;

	write_unlock_bh(&bond->lock);

	if (bond->params.miimon) {  /* link check interval, in milliseconds. */
3715
		cancel_delayed_work(&bond->mii_work);
L
Linus Torvalds 已提交
3716 3717 3718
	}

	if (bond->params.arp_interval) {  /* arp interval, in milliseconds. */
3719
		cancel_delayed_work(&bond->arp_work);
L
Linus Torvalds 已提交
3720 3721 3722 3723
	}

	switch (bond->params.mode) {
	case BOND_MODE_8023AD:
3724
		cancel_delayed_work(&bond->ad_work);
L
Linus Torvalds 已提交
3725 3726 3727
		break;
	case BOND_MODE_TLB:
	case BOND_MODE_ALB:
3728
		cancel_delayed_work(&bond->alb_work);
L
Linus Torvalds 已提交
3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757
		break;
	default:
		break;
	}


	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* Must be called only after all
		 * slaves have been released
		 */
		bond_alb_deinitialize(bond);
	}

	return 0;
}

static struct net_device_stats *bond_get_stats(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct net_device_stats *stats = &(bond->stats), *sstats;
	struct slave *slave;
	int i;

	memset(stats, 0, sizeof(struct net_device_stats));

	read_lock_bh(&bond->lock);

	bond_for_each_slave(bond, slave, i) {
R
Rusty Russell 已提交
3758
		sstats = slave->dev->get_stats(slave->dev);
3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783
		stats->rx_packets += sstats->rx_packets;
		stats->rx_bytes += sstats->rx_bytes;
		stats->rx_errors += sstats->rx_errors;
		stats->rx_dropped += sstats->rx_dropped;

		stats->tx_packets += sstats->tx_packets;
		stats->tx_bytes += sstats->tx_bytes;
		stats->tx_errors += sstats->tx_errors;
		stats->tx_dropped += sstats->tx_dropped;

		stats->multicast += sstats->multicast;
		stats->collisions += sstats->collisions;

		stats->rx_length_errors += sstats->rx_length_errors;
		stats->rx_over_errors += sstats->rx_over_errors;
		stats->rx_crc_errors += sstats->rx_crc_errors;
		stats->rx_frame_errors += sstats->rx_frame_errors;
		stats->rx_fifo_errors += sstats->rx_fifo_errors;
		stats->rx_missed_errors += sstats->rx_missed_errors;

		stats->tx_aborted_errors += sstats->tx_aborted_errors;
		stats->tx_carrier_errors += sstats->tx_carrier_errors;
		stats->tx_fifo_errors += sstats->tx_fifo_errors;
		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
		stats->tx_window_errors += sstats->tx_window_errors;
L
Linus Torvalds 已提交
3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824
	}

	read_unlock_bh(&bond->lock);

	return stats;
}

static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
{
	struct net_device *slave_dev = NULL;
	struct ifbond k_binfo;
	struct ifbond __user *u_binfo = NULL;
	struct ifslave k_sinfo;
	struct ifslave __user *u_sinfo = NULL;
	struct mii_ioctl_data *mii = NULL;
	int res = 0;

	dprintk("bond_ioctl: master=%s, cmd=%d\n",
		bond_dev->name, cmd);

	switch (cmd) {
	case SIOCGMIIPHY:
		mii = if_mii(ifr);
		if (!mii) {
			return -EINVAL;
		}
		mii->phy_id = 0;
		/* Fall Through */
	case SIOCGMIIREG:
		/*
		 * We do this again just in case we were called by SIOCGMIIREG
		 * instead of SIOCGMIIPHY.
		 */
		mii = if_mii(ifr);
		if (!mii) {
			return -EINVAL;
		}

		if (mii->reg_num == 1) {
			struct bonding *bond = bond_dev->priv;
			mii->val_out = 0;
3825
			read_lock(&bond->lock);
L
Linus Torvalds 已提交
3826
			read_lock(&bond->curr_slave_lock);
3827
			if (netif_carrier_ok(bond->dev)) {
L
Linus Torvalds 已提交
3828 3829 3830
				mii->val_out = BMSR_LSTATUS;
			}
			read_unlock(&bond->curr_slave_lock);
3831
			read_unlock(&bond->lock);
L
Linus Torvalds 已提交
3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875
		}

		return 0;
	case BOND_INFO_QUERY_OLD:
	case SIOCBONDINFOQUERY:
		u_binfo = (struct ifbond __user *)ifr->ifr_data;

		if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) {
			return -EFAULT;
		}

		res = bond_info_query(bond_dev, &k_binfo);
		if (res == 0) {
			if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) {
				return -EFAULT;
			}
		}

		return res;
	case BOND_SLAVE_INFO_QUERY_OLD:
	case SIOCBONDSLAVEINFOQUERY:
		u_sinfo = (struct ifslave __user *)ifr->ifr_data;

		if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) {
			return -EFAULT;
		}

		res = bond_slave_info_query(bond_dev, &k_sinfo);
		if (res == 0) {
			if (copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) {
				return -EFAULT;
			}
		}

		return res;
	default:
		/* Go on */
		break;
	}

	if (!capable(CAP_NET_ADMIN)) {
		return -EPERM;
	}

3876
	down_write(&(bonding_rwsem));
3877
	slave_dev = dev_get_by_name(&init_net, ifr->ifr_slave);
L
Linus Torvalds 已提交
3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908

	dprintk("slave_dev=%p: \n", slave_dev);

	if (!slave_dev) {
		res = -ENODEV;
	} else {
		dprintk("slave_dev->name=%s: \n", slave_dev->name);
		switch (cmd) {
		case BOND_ENSLAVE_OLD:
		case SIOCBONDENSLAVE:
			res = bond_enslave(bond_dev, slave_dev);
			break;
		case BOND_RELEASE_OLD:
		case SIOCBONDRELEASE:
			res = bond_release(bond_dev, slave_dev);
			break;
		case BOND_SETHWADDR_OLD:
		case SIOCBONDSETHWADDR:
			res = bond_sethwaddr(bond_dev, slave_dev);
			break;
		case BOND_CHANGE_ACTIVE_OLD:
		case SIOCBONDCHANGEACTIVE:
			res = bond_ioctl_change_active(bond_dev, slave_dev);
			break;
		default:
			res = -EOPNOTSUPP;
		}

		dev_put(slave_dev);
	}

3909
	up_write(&(bonding_rwsem));
L
Linus Torvalds 已提交
3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993
	return res;
}

static void bond_set_multicast_list(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct dev_mc_list *dmi;

	write_lock_bh(&bond->lock);

	/*
	 * Do promisc before checking multicast_mode
	 */
	if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC)) {
		bond_set_promiscuity(bond, 1);
	}

	if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC)) {
		bond_set_promiscuity(bond, -1);
	}

	/* set allmulti flag to slaves */
	if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI)) {
		bond_set_allmulti(bond, 1);
	}

	if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI)) {
		bond_set_allmulti(bond, -1);
	}

	bond->flags = bond_dev->flags;

	/* looking for addresses to add to slaves' mc list */
	for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) {
		if (!bond_mc_list_find_dmi(dmi, bond->mc_list)) {
			bond_mc_add(bond, dmi->dmi_addr, dmi->dmi_addrlen);
		}
	}

	/* looking for addresses to delete from slaves' list */
	for (dmi = bond->mc_list; dmi; dmi = dmi->next) {
		if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list)) {
			bond_mc_delete(bond, dmi->dmi_addr, dmi->dmi_addrlen);
		}
	}

	/* save master's multicast list */
	bond_mc_list_destroy(bond);
	bond_mc_list_copy(bond_dev->mc_list, bond, GFP_ATOMIC);

	write_unlock_bh(&bond->lock);
}

/*
 * Change the MTU of all of a master's slaves to match the master
 */
static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *stop_at;
	int res = 0;
	int i;

	dprintk("bond=%p, name=%s, new_mtu=%d\n", bond,
		(bond_dev ? bond_dev->name : "None"), new_mtu);

	/* Can't hold bond->lock with bh disabled here since
	 * some base drivers panic. On the other hand we can't
	 * hold bond->lock without bh disabled because we'll
	 * deadlock. The only solution is to rely on the fact
	 * that we're under rtnl_lock here, and the slaves
	 * list won't change. This doesn't solve the problem
	 * of setting the slave's MTU while it is
	 * transmitting, but the assumption is that the base
	 * driver can handle that.
	 *
	 * TODO: figure out a way to safely iterate the slaves
	 * list, but without holding a lock around the actual
	 * call to the base driver.
	 */

	bond_for_each_slave(bond, slave, i) {
		dprintk("s %p s->p %p c_m %p\n", slave,
			slave->prev, slave->dev->change_mtu);
3994

L
Linus Torvalds 已提交
3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047
		res = dev_set_mtu(slave->dev, new_mtu);

		if (res) {
			/* If we failed to set the slave's mtu to the new value
			 * we must abort the operation even in ACTIVE_BACKUP
			 * mode, because if we allow the backup slaves to have
			 * different mtu values than the active slave we'll
			 * need to change their mtu when doing a failover. That
			 * means changing their mtu from timer context, which
			 * is probably not a good idea.
			 */
			dprintk("err %d %s\n", res, slave->dev->name);
			goto unwind;
		}
	}

	bond_dev->mtu = new_mtu;

	return 0;

unwind:
	/* unwind from head to the slave that failed */
	stop_at = slave;
	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) {
		int tmp_res;

		tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu);
		if (tmp_res) {
			dprintk("unwind err %d dev %s\n", tmp_res,
				slave->dev->name);
		}
	}

	return res;
}

/*
 * Change HW address
 *
 * Note that many devices must be down to change the HW address, and
 * downing the master releases all slaves.  We can make bonds full of
 * bonding devices to test this, however.
 */
static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
{
	struct bonding *bond = bond_dev->priv;
	struct sockaddr *sa = addr, tmp_sa;
	struct slave *slave, *stop_at;
	int res = 0;
	int i;

	dprintk("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None"));

4048 4049 4050 4051 4052 4053
	/*
	 * If fail_over_mac is enabled, do nothing and return success.
	 * Returning an error causes ifenslave to fail.
	 */
	if (bond->params.fail_over_mac)
		return 0;
4054

L
Linus Torvalds 已提交
4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122
	if (!is_valid_ether_addr(sa->sa_data)) {
		return -EADDRNOTAVAIL;
	}

	/* Can't hold bond->lock with bh disabled here since
	 * some base drivers panic. On the other hand we can't
	 * hold bond->lock without bh disabled because we'll
	 * deadlock. The only solution is to rely on the fact
	 * that we're under rtnl_lock here, and the slaves
	 * list won't change. This doesn't solve the problem
	 * of setting the slave's hw address while it is
	 * transmitting, but the assumption is that the base
	 * driver can handle that.
	 *
	 * TODO: figure out a way to safely iterate the slaves
	 * list, but without holding a lock around the actual
	 * call to the base driver.
	 */

	bond_for_each_slave(bond, slave, i) {
		dprintk("slave %p %s\n", slave, slave->dev->name);

		if (slave->dev->set_mac_address == NULL) {
			res = -EOPNOTSUPP;
			dprintk("EOPNOTSUPP %s\n", slave->dev->name);
			goto unwind;
		}

		res = dev_set_mac_address(slave->dev, addr);
		if (res) {
			/* TODO: consider downing the slave
			 * and retry ?
			 * User should expect communications
			 * breakage anyway until ARP finish
			 * updating, so...
			 */
			dprintk("err %d %s\n", res, slave->dev->name);
			goto unwind;
		}
	}

	/* success */
	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
	return 0;

unwind:
	memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
	tmp_sa.sa_family = bond_dev->type;

	/* unwind from head to the slave that failed */
	stop_at = slave;
	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) {
		int tmp_res;

		tmp_res = dev_set_mac_address(slave->dev, &tmp_sa);
		if (tmp_res) {
			dprintk("unwind err %d dev %s\n", tmp_res,
				slave->dev->name);
		}
	}

	return res;
}

static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *start_at;
4123
	int i, slave_no, res = 1;
L
Linus Torvalds 已提交
4124 4125 4126 4127 4128 4129 4130

	read_lock(&bond->lock);

	if (!BOND_IS_OK(bond)) {
		goto out;
	}

4131 4132 4133 4134 4135
	/*
	 * Concurrent TX may collide on rr_tx_counter; we accept that
	 * as being rare enough not to justify using an atomic op here
	 */
	slave_no = bond->rr_tx_counter++ % bond->slave_cnt;
L
Linus Torvalds 已提交
4136

4137 4138 4139 4140 4141
	bond_for_each_slave(bond, slave, i) {
		slave_no--;
		if (slave_no < 0) {
			break;
		}
L
Linus Torvalds 已提交
4142 4143
	}

4144
	start_at = slave;
L
Linus Torvalds 已提交
4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162
	bond_for_each_slave_from(bond, slave, i, start_at) {
		if (IS_UP(slave->dev) &&
		    (slave->link == BOND_LINK_UP) &&
		    (slave->state == BOND_STATE_ACTIVE)) {
			res = bond_dev_queue_xmit(bond, skb, slave->dev);
			break;
		}
	}

out:
	if (res) {
		/* no suitable interface, frame not sent */
		dev_kfree_skb(skb);
	}
	read_unlock(&bond->lock);
	return 0;
}

4163

L
Linus Torvalds 已提交
4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179
/*
 * in active-backup mode, we know that bond->curr_active_slave is always valid if
 * the bond has a usable interface.
 */
static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	int res = 1;

	read_lock(&bond->lock);
	read_lock(&bond->curr_slave_lock);

	if (!BOND_IS_OK(bond)) {
		goto out;
	}

4180 4181 4182 4183 4184
	if (!bond->curr_active_slave)
		goto out;

	res = bond_dev_queue_xmit(bond, skb, bond->curr_active_slave->dev);

L
Linus Torvalds 已提交
4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195
out:
	if (res) {
		/* no suitable interface, frame not sent */
		dev_kfree_skb(skb);
	}
	read_unlock(&bond->curr_slave_lock);
	read_unlock(&bond->lock);
	return 0;
}

/*
4196 4197 4198
 * In bond_xmit_xor() , we determine the output device by using a pre-
 * determined xmit_hash_policy(), If the selected device is not enabled,
 * find the next active slave.
L
Linus Torvalds 已提交
4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213
 */
static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *start_at;
	int slave_no;
	int i;
	int res = 1;

	read_lock(&bond->lock);

	if (!BOND_IS_OK(bond)) {
		goto out;
	}

4214
	slave_no = bond->xmit_hash_policy(skb, bond_dev, bond->slave_cnt);
L
Linus Torvalds 已提交
4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275

	bond_for_each_slave(bond, slave, i) {
		slave_no--;
		if (slave_no < 0) {
			break;
		}
	}

	start_at = slave;

	bond_for_each_slave_from(bond, slave, i, start_at) {
		if (IS_UP(slave->dev) &&
		    (slave->link == BOND_LINK_UP) &&
		    (slave->state == BOND_STATE_ACTIVE)) {
			res = bond_dev_queue_xmit(bond, skb, slave->dev);
			break;
		}
	}

out:
	if (res) {
		/* no suitable interface, frame not sent */
		dev_kfree_skb(skb);
	}
	read_unlock(&bond->lock);
	return 0;
}

/*
 * in broadcast mode, we send everything to all usable interfaces.
 */
static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *start_at;
	struct net_device *tx_dev = NULL;
	int i;
	int res = 1;

	read_lock(&bond->lock);

	if (!BOND_IS_OK(bond)) {
		goto out;
	}

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

	if (!start_at) {
		goto out;
	}

	bond_for_each_slave_from(bond, slave, i, start_at) {
		if (IS_UP(slave->dev) &&
		    (slave->link == BOND_LINK_UP) &&
		    (slave->state == BOND_STATE_ACTIVE)) {
			if (tx_dev) {
				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
				if (!skb2) {
					printk(KERN_ERR DRV_NAME
4276 4277 4278
					       ": %s: Error: bond_xmit_broadcast(): "
					       "skb_clone() failed\n",
					       bond_dev->name);
L
Linus Torvalds 已提交
4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310
					continue;
				}

				res = bond_dev_queue_xmit(bond, skb2, tx_dev);
				if (res) {
					dev_kfree_skb(skb2);
					continue;
				}
			}
			tx_dev = slave->dev;
		}
	}

	if (tx_dev) {
		res = bond_dev_queue_xmit(bond, skb, tx_dev);
	}

out:
	if (res) {
		/* no suitable interface, frame not sent */
		dev_kfree_skb(skb);
	}
	/* frame sent to all suitable interfaces */
	read_unlock(&bond->lock);
	return 0;
}

/*------------------------- Device initialization ---------------------------*/

/*
 * set bond mode specific net device operations
 */
4311
void bond_set_mode_ops(struct bonding *bond, int mode)
L
Linus Torvalds 已提交
4312
{
4313 4314
	struct net_device *bond_dev = bond->dev;

L
Linus Torvalds 已提交
4315 4316 4317 4318 4319 4320 4321 4322 4323
	switch (mode) {
	case BOND_MODE_ROUNDROBIN:
		bond_dev->hard_start_xmit = bond_xmit_roundrobin;
		break;
	case BOND_MODE_ACTIVEBACKUP:
		bond_dev->hard_start_xmit = bond_xmit_activebackup;
		break;
	case BOND_MODE_XOR:
		bond_dev->hard_start_xmit = bond_xmit_xor;
4324 4325 4326 4327
		if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
			bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
		else
			bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
L
Linus Torvalds 已提交
4328 4329 4330 4331 4332
		break;
	case BOND_MODE_BROADCAST:
		bond_dev->hard_start_xmit = bond_xmit_broadcast;
		break;
	case BOND_MODE_8023AD:
4333
		bond_set_master_3ad_flags(bond);
L
Linus Torvalds 已提交
4334
		bond_dev->hard_start_xmit = bond_3ad_xmit_xor;
4335 4336 4337 4338
		if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
			bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
		else
			bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
L
Linus Torvalds 已提交
4339 4340
		break;
	case BOND_MODE_ALB:
4341 4342 4343
		bond_set_master_alb_flags(bond);
		/* FALLTHRU */
	case BOND_MODE_TLB:
L
Linus Torvalds 已提交
4344 4345 4346 4347 4348 4349
		bond_dev->hard_start_xmit = bond_alb_xmit;
		bond_dev->set_mac_address = bond_alb_set_mac_address;
		break;
	default:
		/* Should never happen, mode already checked */
		printk(KERN_ERR DRV_NAME
4350 4351
		       ": %s: Error: Unknown bonding mode %d\n",
		       bond_dev->name,
L
Linus Torvalds 已提交
4352 4353 4354 4355 4356
		       mode);
		break;
	}
}

4357 4358 4359 4360 4361 4362 4363 4364
static void bond_ethtool_get_drvinfo(struct net_device *bond_dev,
				    struct ethtool_drvinfo *drvinfo)
{
	strncpy(drvinfo->driver, DRV_NAME, 32);
	strncpy(drvinfo->version, DRV_VERSION, 32);
	snprintf(drvinfo->fw_version, 32, "%d", BOND_ABI_VERSION);
}

4365
static const struct ethtool_ops bond_ethtool_ops = {
4366
	.get_drvinfo		= bond_ethtool_get_drvinfo,
4367 4368
};

L
Linus Torvalds 已提交
4369 4370 4371 4372
/*
 * Does not allocate but creates a /proc entry.
 * Allowed to fail.
 */
4373
static int bond_init(struct net_device *bond_dev, struct bond_params *params)
L
Linus Torvalds 已提交
4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384
{
	struct bonding *bond = bond_dev->priv;

	dprintk("Begin bond_init for %s\n", bond_dev->name);

	/* initialize rwlocks */
	rwlock_init(&bond->lock);
	rwlock_init(&bond->curr_slave_lock);

	bond->params = *params; /* copy params struct */

4385 4386 4387 4388
	bond->wq = create_singlethread_workqueue(bond_dev->name);
	if (!bond->wq)
		return -ENOMEM;

L
Linus Torvalds 已提交
4389 4390 4391 4392 4393 4394
	/* Initialize pointers */
	bond->first_slave = NULL;
	bond->curr_active_slave = NULL;
	bond->current_arp_slave = NULL;
	bond->primary_slave = NULL;
	bond->dev = bond_dev;
4395
	bond->send_grat_arp = 0;
4396
	bond->setup_by_slave = 0;
L
Linus Torvalds 已提交
4397 4398 4399 4400 4401 4402 4403
	INIT_LIST_HEAD(&bond->vlan_list);

	/* Initialize the device entry points */
	bond_dev->open = bond_open;
	bond_dev->stop = bond_close;
	bond_dev->get_stats = bond_get_stats;
	bond_dev->do_ioctl = bond_do_ioctl;
4404
	bond_dev->ethtool_ops = &bond_ethtool_ops;
L
Linus Torvalds 已提交
4405 4406 4407
	bond_dev->set_multicast_list = bond_set_multicast_list;
	bond_dev->change_mtu = bond_change_mtu;
	bond_dev->set_mac_address = bond_set_mac_address;
4408
	bond_dev->validate_addr = NULL;
L
Linus Torvalds 已提交
4409

4410
	bond_set_mode_ops(bond, bond->params.mode);
L
Linus Torvalds 已提交
4411 4412 4413 4414 4415 4416

	bond_dev->destructor = free_netdev;

	/* Initialize the device options */
	bond_dev->tx_queue_len = 0;
	bond_dev->flags |= IFF_MASTER|IFF_MULTICAST;
4417
	bond_dev->priv_flags |= IFF_BONDING;
L
Linus Torvalds 已提交
4418 4419 4420 4421 4422 4423 4424 4425

	/* At first, we block adding VLANs. That's the only way to
	 * prevent problems that occur when adding VLANs over an
	 * empty bond. The block will be removed once non-challenged
	 * slaves are enslaved.
	 */
	bond_dev->features |= NETIF_F_VLAN_CHALLENGED;

H
Herbert Xu 已提交
4426
	/* don't acquire bond device's netif_tx_lock when
L
Linus Torvalds 已提交
4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453
	 * transmitting */
	bond_dev->features |= NETIF_F_LLTX;

	/* By default, we declare the bond to be fully
	 * VLAN hardware accelerated capable. Special
	 * care is taken in the various xmit functions
	 * when there are slaves that are not hw accel
	 * capable
	 */
	bond_dev->vlan_rx_register = bond_vlan_rx_register;
	bond_dev->vlan_rx_add_vid  = bond_vlan_rx_add_vid;
	bond_dev->vlan_rx_kill_vid = bond_vlan_rx_kill_vid;
	bond_dev->features |= (NETIF_F_HW_VLAN_TX |
			       NETIF_F_HW_VLAN_RX |
			       NETIF_F_HW_VLAN_FILTER);

#ifdef CONFIG_PROC_FS
	bond_create_proc_entry(bond);
#endif
	list_add_tail(&bond->bond_list, &bond_dev_list);

	return 0;
}

/* De-initialize device specific data.
 * Caller must hold rtnl_lock.
 */
4454
static void bond_deinit(struct net_device *bond_dev)
L
Linus Torvalds 已提交
4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474
{
	struct bonding *bond = bond_dev->priv;

	list_del(&bond->bond_list);

#ifdef CONFIG_PROC_FS
	bond_remove_proc_entry(bond);
#endif
}

/* Unregister and free all bond devices.
 * Caller must hold rtnl_lock.
 */
static void bond_free_all(void)
{
	struct bonding *bond, *nxt;

	list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) {
		struct net_device *bond_dev = bond->dev;

4475 4476 4477
		bond_mc_list_destroy(bond);
		/* Release the bonded slaves */
		bond_release_all(bond_dev);
4478
		bond_deinit(bond_dev);
4479
		unregister_netdevice(bond_dev);
L
Linus Torvalds 已提交
4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492
	}

#ifdef CONFIG_PROC_FS
	bond_destroy_proc_dir();
#endif
}

/*------------------------- Module initialization ---------------------------*/

/*
 * Convert string input module parms.  Accept either the
 * number of the mode or its string name.
 */
4493
int bond_parse_parm(char *mode_arg, struct bond_parm_tbl *tbl)
L
Linus Torvalds 已提交
4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510
{
	int i;

	for (i = 0; tbl[i].modename; i++) {
		if ((isdigit(*mode_arg) &&
		     tbl[i].mode == simple_strtol(mode_arg, NULL, 0)) ||
		    (strncmp(mode_arg, tbl[i].modename,
			     strlen(tbl[i].modename)) == 0)) {
			return tbl[i].mode;
		}
	}

	return -1;
}

static int bond_check_params(struct bond_params *params)
{
4511 4512
	int arp_validate_value;

L
Linus Torvalds 已提交
4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525
	/*
	 * Convert string parameters.
	 */
	if (mode) {
		bond_mode = bond_parse_parm(mode, bond_mode_tbl);
		if (bond_mode == -1) {
			printk(KERN_ERR DRV_NAME
			       ": Error: Invalid bonding mode \"%s\"\n",
			       mode == NULL ? "NULL" : mode);
			return -EINVAL;
		}
	}

4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544
	if (xmit_hash_policy) {
		if ((bond_mode != BOND_MODE_XOR) &&
		    (bond_mode != BOND_MODE_8023AD)) {
			printk(KERN_INFO DRV_NAME
			       ": xor_mode param is irrelevant in mode %s\n",
			       bond_mode_name(bond_mode));
		} else {
			xmit_hashtype = bond_parse_parm(xmit_hash_policy,
							xmit_hashtype_tbl);
			if (xmit_hashtype == -1) {
				printk(KERN_ERR DRV_NAME
			       	": Error: Invalid xmit_hash_policy \"%s\"\n",
			       	xmit_hash_policy == NULL ? "NULL" :
				       xmit_hash_policy);
				return -EINVAL;
			}
		}
	}

L
Linus Torvalds 已提交
4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563
	if (lacp_rate) {
		if (bond_mode != BOND_MODE_8023AD) {
			printk(KERN_INFO DRV_NAME
			       ": lacp_rate param is irrelevant in mode %s\n",
			       bond_mode_name(bond_mode));
		} else {
			lacp_fast = bond_parse_parm(lacp_rate, bond_lacp_tbl);
			if (lacp_fast == -1) {
				printk(KERN_ERR DRV_NAME
				       ": Error: Invalid lacp rate \"%s\"\n",
				       lacp_rate == NULL ? "NULL" : lacp_rate);
				return -EINVAL;
			}
		}
	}

	if (max_bonds < 1 || max_bonds > INT_MAX) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: max_bonds (%d) not in range %d-%d, so it "
4564
		       "was reset to BOND_DEFAULT_MAX_BONDS (%d)\n",
L
Linus Torvalds 已提交
4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700
		       max_bonds, 1, INT_MAX, BOND_DEFAULT_MAX_BONDS);
		max_bonds = BOND_DEFAULT_MAX_BONDS;
	}

	if (miimon < 0) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: miimon module parameter (%d), "
		       "not in range 0-%d, so it was reset to %d\n",
		       miimon, INT_MAX, BOND_LINK_MON_INTERV);
		miimon = BOND_LINK_MON_INTERV;
	}

	if (updelay < 0) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: updelay module parameter (%d), "
		       "not in range 0-%d, so it was reset to 0\n",
		       updelay, INT_MAX);
		updelay = 0;
	}

	if (downdelay < 0) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: downdelay module parameter (%d), "
		       "not in range 0-%d, so it was reset to 0\n",
		       downdelay, INT_MAX);
		downdelay = 0;
	}

	if ((use_carrier != 0) && (use_carrier != 1)) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: use_carrier module parameter (%d), "
		       "not of valid value (0/1), so it was set to 1\n",
		       use_carrier);
		use_carrier = 1;
	}

	/* reset values for 802.3ad */
	if (bond_mode == BOND_MODE_8023AD) {
		if (!miimon) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: miimon must be specified, "
			       "otherwise bonding will not detect link "
			       "failure, speed and duplex which are "
			       "essential for 802.3ad operation\n");
			printk(KERN_WARNING "Forcing miimon to 100msec\n");
			miimon = 100;
		}
	}

	/* reset values for TLB/ALB */
	if ((bond_mode == BOND_MODE_TLB) ||
	    (bond_mode == BOND_MODE_ALB)) {
		if (!miimon) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: miimon must be specified, "
			       "otherwise bonding will not detect link "
			       "failure and link speed which are essential "
			       "for TLB/ALB load balancing\n");
			printk(KERN_WARNING "Forcing miimon to 100msec\n");
			miimon = 100;
		}
	}

	if (bond_mode == BOND_MODE_ALB) {
		printk(KERN_NOTICE DRV_NAME
		       ": In ALB mode you might experience client "
		       "disconnections upon reconnection of a link if the "
		       "bonding module updelay parameter (%d msec) is "
		       "incompatible with the forwarding delay time of the "
		       "switch\n",
		       updelay);
	}

	if (!miimon) {
		if (updelay || downdelay) {
			/* just warn the user the up/down delay will have
			 * no effect since miimon is zero...
			 */
			printk(KERN_WARNING DRV_NAME
			       ": Warning: miimon module parameter not set "
			       "and updelay (%d) or downdelay (%d) module "
			       "parameter is set; updelay and downdelay have "
			       "no effect unless miimon is set\n",
			       updelay, downdelay);
		}
	} else {
		/* don't allow arp monitoring */
		if (arp_interval) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: miimon (%d) and arp_interval (%d) "
			       "can't be used simultaneously, disabling ARP "
			       "monitoring\n",
			       miimon, arp_interval);
			arp_interval = 0;
		}

		if ((updelay % miimon) != 0) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: updelay (%d) is not a multiple "
			       "of miimon (%d), updelay rounded to %d ms\n",
			       updelay, miimon, (updelay / miimon) * miimon);
		}

		updelay /= miimon;

		if ((downdelay % miimon) != 0) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: downdelay (%d) is not a multiple "
			       "of miimon (%d), downdelay rounded to %d ms\n",
			       downdelay, miimon,
			       (downdelay / miimon) * miimon);
		}

		downdelay /= miimon;
	}

	if (arp_interval < 0) {
		printk(KERN_WARNING DRV_NAME
		       ": Warning: arp_interval module parameter (%d) "
		       ", not in range 0-%d, so it was reset to %d\n",
		       arp_interval, INT_MAX, BOND_LINK_ARP_INTERV);
		arp_interval = BOND_LINK_ARP_INTERV;
	}

	for (arp_ip_count = 0;
	     (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[arp_ip_count];
	     arp_ip_count++) {
		/* not complete check, but should be good enough to
		   catch mistakes */
		if (!isdigit(arp_ip_target[arp_ip_count][0])) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: bad arp_ip_target module parameter "
			       "(%s), ARP monitoring will not be performed\n",
			       arp_ip_target[arp_ip_count]);
			arp_interval = 0;
		} else {
4701
			__be32 ip = in_aton(arp_ip_target[arp_ip_count]);
L
Linus Torvalds 已提交
4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715
			arp_target[arp_ip_count] = ip;
		}
	}

	if (arp_interval && !arp_ip_count) {
		/* don't allow arping if no arp_ip_target given... */
		printk(KERN_WARNING DRV_NAME
		       ": Warning: arp_interval module parameter (%d) "
		       "specified without providing an arp_ip_target "
		       "parameter, arp_interval was reset to 0\n",
		       arp_interval);
		arp_interval = 0;
	}

4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738
	if (arp_validate) {
		if (bond_mode != BOND_MODE_ACTIVEBACKUP) {
			printk(KERN_ERR DRV_NAME
	       ": arp_validate only supported in active-backup mode\n");
			return -EINVAL;
		}
		if (!arp_interval) {
			printk(KERN_ERR DRV_NAME
			       ": arp_validate requires arp_interval\n");
			return -EINVAL;
		}

		arp_validate_value = bond_parse_parm(arp_validate,
						     arp_validate_tbl);
		if (arp_validate_value == -1) {
			printk(KERN_ERR DRV_NAME
			       ": Error: invalid arp_validate \"%s\"\n",
			       arp_validate == NULL ? "NULL" : arp_validate);
			return -EINVAL;
		}
	} else
		arp_validate_value = 0;

L
Linus Torvalds 已提交
4739 4740 4741 4742 4743 4744 4745 4746
	if (miimon) {
		printk(KERN_INFO DRV_NAME
		       ": MII link monitoring set to %d ms\n",
		       miimon);
	} else if (arp_interval) {
		int i;

		printk(KERN_INFO DRV_NAME
4747 4748 4749 4750
		       ": ARP monitoring set to %d ms, validate %s, with %d target(s):",
		       arp_interval,
		       arp_validate_tbl[arp_validate_value].modename,
		       arp_ip_count);
L
Linus Torvalds 已提交
4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778

		for (i = 0; i < arp_ip_count; i++)
			printk (" %s", arp_ip_target[i]);

		printk("\n");

	} else {
		/* miimon and arp_interval not set, we need one so things
		 * work as expected, see bonding.txt for details
		 */
		printk(KERN_WARNING DRV_NAME
		       ": Warning: either miimon or arp_interval and "
		       "arp_ip_target module parameters must be specified, "
		       "otherwise bonding will not detect link failures! see "
		       "bonding.txt for details.\n");
	}

	if (primary && !USES_PRIMARY(bond_mode)) {
		/* currently, using a primary only makes sense
		 * in active backup, TLB or ALB modes
		 */
		printk(KERN_WARNING DRV_NAME
		       ": Warning: %s primary device specified but has no "
		       "effect in %s mode\n",
		       primary, bond_mode_name(bond_mode));
		primary = NULL;
	}

4779 4780 4781 4782 4783
	if (fail_over_mac && (bond_mode != BOND_MODE_ACTIVEBACKUP))
		printk(KERN_WARNING DRV_NAME
		       ": Warning: fail_over_mac only affects "
		       "active-backup mode.\n");

L
Linus Torvalds 已提交
4784 4785
	/* fill params struct with the proper values */
	params->mode = bond_mode;
4786
	params->xmit_policy = xmit_hashtype;
L
Linus Torvalds 已提交
4787 4788
	params->miimon = miimon;
	params->arp_interval = arp_interval;
4789
	params->arp_validate = arp_validate_value;
L
Linus Torvalds 已提交
4790 4791 4792 4793 4794
	params->updelay = updelay;
	params->downdelay = downdelay;
	params->use_carrier = use_carrier;
	params->lacp_fast = lacp_fast;
	params->primary[0] = 0;
4795
	params->fail_over_mac = fail_over_mac;
L
Linus Torvalds 已提交
4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806

	if (primary) {
		strncpy(params->primary, primary, IFNAMSIZ);
		params->primary[IFNAMSIZ - 1] = 0;
	}

	memcpy(params->arp_targets, arp_target, sizeof(arp_target));

	return 0;
}

4807 4808
static struct lock_class_key bonding_netdev_xmit_lock_key;

4809
/* Create a new bond based on the specified name and bonding parameters.
4810
 * If name is NULL, obtain a suitable "bond%d" name for us.
4811 4812 4813 4814 4815 4816 4817 4818 4819
 * Caller must NOT hold rtnl_lock; we need to release it here before we
 * set up our sysfs entries.
 */
int bond_create(char *name, struct bond_params *params, struct bonding **newbond)
{
	struct net_device *bond_dev;
	int res;

	rtnl_lock();
4820 4821
	bond_dev = alloc_netdev(sizeof(struct bonding), name ? name : "",
				ether_setup);
4822 4823 4824 4825 4826 4827 4828 4829
	if (!bond_dev) {
		printk(KERN_ERR DRV_NAME
		       ": %s: eek! can't alloc netdev!\n",
		       name);
		res = -ENOMEM;
		goto out_rtnl;
	}

4830 4831 4832 4833 4834 4835
	if (!name) {
		res = dev_alloc_name(bond_dev, "bond%d");
		if (res < 0)
			goto out_netdev;
	}

4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849
	/* bond_init() must be called after dev_alloc_name() (for the
	 * /proc files), but before register_netdevice(), because we
	 * need to set function pointers.
	 */

	res = bond_init(bond_dev, params);
	if (res < 0) {
		goto out_netdev;
	}

	res = register_netdevice(bond_dev);
	if (res < 0) {
		goto out_bond;
	}
4850 4851 4852

	lockdep_set_class(&bond_dev->_xmit_lock, &bonding_netdev_xmit_lock_key);

4853 4854 4855
	if (newbond)
		*newbond = bond_dev->priv;

4856 4857
	netif_carrier_off(bond_dev);

4858
	rtnl_unlock(); /* allows sysfs registration of net device */
4859
	res = bond_create_sysfs_entry(bond_dev->priv);
4860 4861 4862 4863 4864 4865 4866
	if (res < 0) {
		rtnl_lock();
		goto out_bond;
	}

	return 0;

4867 4868 4869 4870 4871 4872 4873 4874 4875
out_bond:
	bond_deinit(bond_dev);
out_netdev:
	free_netdev(bond_dev);
out_rtnl:
	rtnl_unlock();
	return res;
}

4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896
static void bond_work_cancel_all(struct bonding *bond)
{
	write_lock_bh(&bond->lock);
	bond->kill_timers = 1;
	write_unlock_bh(&bond->lock);

	if (bond->params.miimon && delayed_work_pending(&bond->mii_work))
		cancel_delayed_work(&bond->mii_work);

	if (bond->params.arp_interval && delayed_work_pending(&bond->arp_work))
		cancel_delayed_work(&bond->arp_work);

	if (bond->params.mode == BOND_MODE_ALB &&
	    delayed_work_pending(&bond->alb_work))
		cancel_delayed_work(&bond->alb_work);

	if (bond->params.mode == BOND_MODE_8023AD &&
	    delayed_work_pending(&bond->ad_work))
		cancel_delayed_work(&bond->ad_work);
}

L
Linus Torvalds 已提交
4897 4898 4899 4900
static int __init bonding_init(void)
{
	int i;
	int res;
4901
	struct bonding *bond, *nxt;
L
Linus Torvalds 已提交
4902 4903 4904

	printk(KERN_INFO "%s", version);

4905
	res = bond_check_params(&bonding_defaults);
L
Linus Torvalds 已提交
4906
	if (res) {
4907
		goto out;
L
Linus Torvalds 已提交
4908 4909 4910 4911 4912 4913
	}

#ifdef CONFIG_PROC_FS
	bond_create_proc_dir();
#endif
	for (i = 0; i < max_bonds; i++) {
4914
		res = bond_create(NULL, &bonding_defaults, NULL);
4915 4916
		if (res)
			goto err;
L
Linus Torvalds 已提交
4917 4918
	}

4919 4920 4921 4922
	res = bond_create_sysfs();
	if (res)
		goto err;

L
Linus Torvalds 已提交
4923
	register_netdevice_notifier(&bond_netdev_notifier);
J
Jay Vosburgh 已提交
4924
	register_inetaddr_notifier(&bond_inetaddr_notifier);
L
Linus Torvalds 已提交
4925

4926 4927
	goto out;
err:
4928 4929 4930 4931 4932
	list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) {
		bond_work_cancel_all(bond);
		destroy_workqueue(bond->wq);
	}

4933
	rtnl_lock();
L
Linus Torvalds 已提交
4934
	bond_free_all();
4935
	bond_destroy_sysfs();
L
Linus Torvalds 已提交
4936
	rtnl_unlock();
4937
out:
L
Linus Torvalds 已提交
4938
	return res;
4939

L
Linus Torvalds 已提交
4940 4941 4942 4943 4944
}

static void __exit bonding_exit(void)
{
	unregister_netdevice_notifier(&bond_netdev_notifier);
J
Jay Vosburgh 已提交
4945
	unregister_inetaddr_notifier(&bond_inetaddr_notifier);
L
Linus Torvalds 已提交
4946 4947 4948

	rtnl_lock();
	bond_free_all();
4949
	bond_destroy_sysfs();
L
Linus Torvalds 已提交
4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968
	rtnl_unlock();
}

module_init(bonding_init);
module_exit(bonding_exit);
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION);
MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others");
MODULE_SUPPORTED_DEVICE("most ethernet devices");

/*
 * Local variables:
 *  c-indent-level: 8
 *  c-basic-offset: 8
 *  tab-width: 8
 * End:
 */