bond_main.c

h内核

 *	  made stats a part of bond struct so no need to allocate
 *	  and free it separately; use standard list operations instead
 *	  of pre-allocated array of bonds.
 *	  Version to 2.3.0.
 *
 * 2003/08/07 - Jay Vosburgh <fubar at us dot ibm dot com>,
 *	       Amir Noam <amir.noam at intel dot com> and
 *	       Shmulik Hen <shmulik.hen at intel dot com>
 *	- Propagating master's settings: Distinguish between modes that
 *	  use a primary slave from those that don't, and propagate settings
 *	  accordingly; Consolidate change_active opeartions and add
 *	  reselect_active and find_best opeartions; Decouple promiscuous
 *	  handling from the multicast mode setting; Add support for changing
 *	  HW address and MTU with proper unwind; Consolidate procfs code,
 *	  add CHANGENAME handler; Enhance netdev notification handling.
 *	  Version to 2.4.0.
 *
 * 2003/09/15 - Stephen Hemminger <shemminger at osdl dot org>,
 *	       Amir Noam <amir.noam at intel dot com>
 *	- Convert /proc to seq_file interface.
 *	  Change /proc/net/bondX/info to /proc/net/bonding/bondX.
 *	  Set version to 2.4.1.
 *
 * 2003/11/20 - Amir Noam <amir.noam at intel dot com>
 *	- Fix /proc creation/destruction.
 *
 * 2003/12/01 - Shmulik Hen <shmulik.hen at intel dot com>
 *	- Massive cleanup - Set version to 2.5.0
 *	  Code changes:
 *	  o Consolidate format of prints and debug prints.
 *	  o Remove bonding_t/slave_t typedefs and consolidate all casts.
 *	  o Remove dead code and unnecessary checks.
 *	  o Consolidate starting/stopping timers.
 *	  o Consolidate handling of primary module param throughout the code.
 *	  o Removed multicast module param support - all settings are done
 *	    according to mode.
 *	  o Slave list iteration - bond is no longer part of the list,
 *	    added cyclic list iteration macros.
 *	  o Consolidate error handling in all xmit functions.
 *	  Style changes:
 *	  o Consolidate function naming and declarations.
 *	  o Consolidate function params and local variables names.
 *	  o Consolidate return values.
 *	  o Consolidate curly braces.
 *	  o Consolidate conditionals format.
 *	  o Change struct member names and types.
 *	  o Chomp trailing spaces, remove empty lines, fix indentations.
 *	  o Re-organize code according to context.
 *
 * 2003/12/30 - Amir Noam <amir.noam at intel dot com>
 *	- Fixed: Cannot remove and re-enslave the original active slave.
 *	- Fixed: Releasing the original active slave causes mac address
 *		 duplication.
 *	- Add support for slaves that use ethtool_ops.
 *	  Set version to 2.5.3.
 *
 * 2004/01/05 - Amir Noam <amir.noam at intel dot com>
 *	- Save bonding parameters per bond instead of using the global values.
 *	  Set version to 2.5.4.
 *
 * 2004/01/14 - Shmulik Hen <shmulik.hen at intel dot com>
 *	- Enhance VLAN support:
 *	  * Add support for VLAN hardware acceleration capable slaves.
 *	  * Add capability to tag self generated packets in ALB/TLB modes.
 *	  Set version to 2.6.0.
 * 2004/10/29 - Mitch Williams <mitch.a.williams at intel dot com>
 *      - Fixed bug when unloading module while using 802.3ad.  If
 *        spinlock debugging is turned on, this causes a stack dump.
 *        Solution is to move call to dev_remove_pack outside of the
 *        spinlock.
 *        Set version to 2.6.1.
 *
 */

//#define BONDING_DEBUG 1

#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/interrupt.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/socket.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/dma.h>
#include <asm/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/if_ether.h>
#include <net/arp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"

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

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

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

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

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

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

static LIST_HEAD(bond_dev_list);

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

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

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

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

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

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

static inline void bond_set_mode_ops(struct net_device *bond_dev, int mode);

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

static const char *bond_mode_name(int mode)
{
	switch (mode) {
	case BOND_MODE_ROUNDROBIN :
		return "load balancing (round-robin)";
	case BOND_MODE_ACTIVEBACKUP :
		return "fault-tolerance (active-backup)";
	case BOND_MODE_XOR :
		return "load balancing (xor)";
	case BOND_MODE_BROADCAST :
		return "fault-tolerance (broadcast)";
	case BOND_MODE_8023AD:
		return "IEEE 802.3ad Dynamic link aggregation";
	case BOND_MODE_TLB:
		return "transmit load balancing";
	case BOND_MODE_ALB:
		return "adaptive load balancing";
	default:
		return "unknown";
	}
}

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

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

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

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

	INIT_LIST_HEAD(&vlan->vlan_list);
	vlan->vlan_id = vlan_id;

	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 tarnsmit 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.
 * 
 * Assumption - once a VLAN device is created over the bond device, all
 * packets are going to be hardware accelerated VLAN tagged since the IP
 * binding is done over the VLAN device
 */
int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev)
{
	unsigned short vlan_id;
	int res;

	if (!list_empty(&bond->vlan_list) &&