*
*/
-//#define BONDING_DEBUG 1
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <net/ipx.h>
#include <net/arp.h>
+#include <net/ipv6.h>
#include <asm/byteorder.h>
#include "bonding.h"
#include "bond_alb.h"
-#define ALB_TIMER_TICKS_PER_SEC 10 /* should be a divisor of HZ */
-#define BOND_TLB_REBALANCE_INTERVAL 10 /* In seconds, periodic re-balancing.
- * Used for division - never set
- * to zero !!!
- */
-#define BOND_ALB_LP_INTERVAL 1 /* In seconds, periodic send of
- * learning packets to the switch
- */
-
-#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \
- * ALB_TIMER_TICKS_PER_SEC)
-
-#define BOND_ALB_LP_TICKS (BOND_ALB_LP_INTERVAL \
- * ALB_TIMER_TICKS_PER_SEC)
-
-#define TLB_HASH_TABLE_SIZE 256 /* The size of the clients hash table.
- * Note that this value MUST NOT be smaller
- * because the key hash table is BYTE wide !
- */
-
-#define TLB_NULL_INDEX 0xffffffff
-#define MAX_LP_BURST 3
-
-/* rlb defs */
-#define RLB_HASH_TABLE_SIZE 256
-#define RLB_NULL_INDEX 0xffffffff
-#define RLB_UPDATE_DELAY 2*ALB_TIMER_TICKS_PER_SEC /* 2 seconds */
-#define RLB_ARP_BURST_SIZE 2
-#define RLB_UPDATE_RETRY 3 /* 3-ticks - must be smaller than the rlb
- * rebalance interval (5 min).
- */
-/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is
- * promiscuous after failover
- */
-#define RLB_PROMISC_TIMEOUT 10*ALB_TIMER_TICKS_PER_SEC
-
-static const u8 mac_bcast[ETH_ALEN] = {0xff,0xff,0xff,0xff,0xff,0xff};
+#ifndef __long_aligned
+#define __long_aligned __attribute__((aligned((sizeof(long)))))
+#endif
+static const u8 mac_bcast[ETH_ALEN] __long_aligned = {
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = {
+ 0x33, 0x33, 0x00, 0x00, 0x00, 0x01
+};
static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC;
#pragma pack(1)
struct learning_pkt {
u8 mac_dst[ETH_ALEN];
u8 mac_src[ETH_ALEN];
- u16 type;
+ __be16 type;
u8 padding[ETH_ZLEN - ETH_HLEN];
};
struct arp_pkt {
- u16 hw_addr_space;
- u16 prot_addr_space;
+ __be16 hw_addr_space;
+ __be16 prot_addr_space;
u8 hw_addr_len;
u8 prot_addr_len;
- u16 op_code;
+ __be16 op_code;
u8 mac_src[ETH_ALEN]; /* sender hardware address */
- u32 ip_src; /* sender IP address */
+ __be32 ip_src; /* sender IP address */
u8 mac_dst[ETH_ALEN]; /* target hardware address */
- u32 ip_dst; /* target IP address */
+ __be32 ip_dst; /* target IP address */
};
#pragma pack()
+static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb)
+{
+ return (struct arp_pkt *)skb_network_header(skb);
+}
+
/* Forward declaration */
static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]);
-static inline u8 _simple_hash(u8 *hash_start, int hash_size)
+static inline u8 _simple_hash(const u8 *hash_start, int hash_size)
{
int i;
u8 hash = 0;
/*********************** tlb specific functions ***************************/
-static inline void _lock_tx_hashtbl(struct bonding *bond)
+static inline void _lock_tx_hashtbl_bh(struct bonding *bond)
{
spin_lock_bh(&(BOND_ALB_INFO(bond).tx_hashtbl_lock));
}
-static inline void _unlock_tx_hashtbl(struct bonding *bond)
+static inline void _unlock_tx_hashtbl_bh(struct bonding *bond)
{
spin_unlock_bh(&(BOND_ALB_INFO(bond).tx_hashtbl_lock));
}
+static inline void _lock_tx_hashtbl(struct bonding *bond)
+{
+ spin_lock(&(BOND_ALB_INFO(bond).tx_hashtbl_lock));
+}
+
+static inline void _unlock_tx_hashtbl(struct bonding *bond)
+{
+ spin_unlock(&(BOND_ALB_INFO(bond).tx_hashtbl_lock));
+}
+
/* Caller must hold tx_hashtbl lock */
static inline void tlb_init_table_entry(struct tlb_client_info *entry, int save_load)
{
SLAVE_TLB_INFO(slave).head = TLB_NULL_INDEX;
}
-/* Caller must hold bond lock for read */
-static void tlb_clear_slave(struct bonding *bond, struct slave *slave, int save_load)
+/* Caller must hold bond lock for read, BH disabled */
+static void __tlb_clear_slave(struct bonding *bond, struct slave *slave,
+ int save_load)
{
struct tlb_client_info *tx_hash_table;
u32 index;
- _lock_tx_hashtbl(bond);
-
/* clear slave from tx_hashtbl */
tx_hash_table = BOND_ALB_INFO(bond).tx_hashtbl;
- index = SLAVE_TLB_INFO(slave).head;
- while (index != TLB_NULL_INDEX) {
- u32 next_index = tx_hash_table[index].next;
- tlb_init_table_entry(&tx_hash_table[index], save_load);
- index = next_index;
+ /* skip this if we've already freed the tx hash table */
+ if (tx_hash_table) {
+ index = SLAVE_TLB_INFO(slave).head;
+ while (index != TLB_NULL_INDEX) {
+ u32 next_index = tx_hash_table[index].next;
+ tlb_init_table_entry(&tx_hash_table[index], save_load);
+ index = next_index;
+ }
}
tlb_init_slave(slave);
+}
- _unlock_tx_hashtbl(bond);
+/* Caller must hold bond lock for read */
+static void tlb_clear_slave(struct bonding *bond, struct slave *slave,
+ int save_load)
+{
+ _lock_tx_hashtbl_bh(bond);
+ __tlb_clear_slave(bond, slave, save_load);
+ _unlock_tx_hashtbl_bh(bond);
}
/* Must be called before starting the monitor timer */
struct tlb_client_info *new_hashtbl;
int i;
- spin_lock_init(&(bond_info->tx_hashtbl_lock));
-
- new_hashtbl = kmalloc(size, GFP_KERNEL);
- if (!new_hashtbl) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: Failed to allocate TLB hash table\n",
- bond->dev->name);
+ new_hashtbl = kzalloc(size, GFP_KERNEL);
+ if (!new_hashtbl)
return -1;
- }
- _lock_tx_hashtbl(bond);
- bond_info->tx_hashtbl = new_hashtbl;
+ _lock_tx_hashtbl_bh(bond);
- memset(bond_info->tx_hashtbl, 0, size);
+ bond_info->tx_hashtbl = new_hashtbl;
for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) {
- tlb_init_table_entry(&bond_info->tx_hashtbl[i], 1);
+ tlb_init_table_entry(&bond_info->tx_hashtbl[i], 0);
}
- _unlock_tx_hashtbl(bond);
+ _unlock_tx_hashtbl_bh(bond);
return 0;
}
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
- _lock_tx_hashtbl(bond);
+ _lock_tx_hashtbl_bh(bond);
kfree(bond_info->tx_hashtbl);
bond_info->tx_hashtbl = NULL;
- _unlock_tx_hashtbl(bond);
+ _unlock_tx_hashtbl_bh(bond);
+}
+
+static long long compute_gap(struct slave *slave)
+{
+ return (s64) (slave->speed << 20) - /* Convert to Megabit per sec */
+ (s64) (SLAVE_TLB_INFO(slave).load << 3); /* Bytes to bits */
}
/* Caller must hold bond lock for read */
static struct slave *tlb_get_least_loaded_slave(struct bonding *bond)
{
struct slave *slave, *least_loaded;
- s64 max_gap;
- int i, found = 0;
-
- /* Find the first enabled slave */
- bond_for_each_slave(bond, slave, i) {
- if (SLAVE_IS_OK(slave)) {
- found = 1;
- break;
- }
- }
-
- if (!found) {
- return NULL;
- }
+ long long max_gap;
+ int i;
- least_loaded = slave;
- max_gap = (s64)(slave->speed << 20) - /* Convert to Megabit per sec */
- (s64)(SLAVE_TLB_INFO(slave).load << 3); /* Bytes to bits */
+ least_loaded = NULL;
+ max_gap = LLONG_MIN;
/* Find the slave with the largest gap */
- bond_for_each_slave_from(bond, slave, i, least_loaded) {
+ bond_for_each_slave(bond, slave, i) {
if (SLAVE_IS_OK(slave)) {
- s64 gap = (s64)(slave->speed << 20) -
- (s64)(SLAVE_TLB_INFO(slave).load << 3);
+ long long gap = compute_gap(slave);
+
if (max_gap < gap) {
least_loaded = slave;
max_gap = gap;
return least_loaded;
}
-/* Caller must hold bond lock for read */
-static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index, u32 skb_len)
+static struct slave *__tlb_choose_channel(struct bonding *bond, u32 hash_index,
+ u32 skb_len)
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
struct tlb_client_info *hash_table;
struct slave *assigned_slave;
- _lock_tx_hashtbl(bond);
-
hash_table = bond_info->tx_hashtbl;
assigned_slave = hash_table[hash_index].tx_slave;
if (!assigned_slave) {
hash_table[hash_index].tx_bytes += skb_len;
}
- _unlock_tx_hashtbl(bond);
-
return assigned_slave;
}
+/* Caller must hold bond lock for read */
+static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index,
+ u32 skb_len)
+{
+ struct slave *tx_slave;
+ /*
+ * We don't need to disable softirq here, becase
+ * tlb_choose_channel() is only called by bond_alb_xmit()
+ * which already has softirq disabled.
+ */
+ _lock_tx_hashtbl(bond);
+ tx_slave = __tlb_choose_channel(bond, hash_index, skb_len);
+ _unlock_tx_hashtbl(bond);
+ return tx_slave;
+}
+
/*********************** rlb specific functions ***************************/
-static inline void _lock_rx_hashtbl(struct bonding *bond)
+static inline void _lock_rx_hashtbl_bh(struct bonding *bond)
{
spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
}
-static inline void _unlock_rx_hashtbl(struct bonding *bond)
+static inline void _unlock_rx_hashtbl_bh(struct bonding *bond)
{
spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
}
+static inline void _lock_rx_hashtbl(struct bonding *bond)
+{
+ spin_lock(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
+}
+
+static inline void _unlock_rx_hashtbl(struct bonding *bond)
+{
+ spin_unlock(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
+}
+
/* when an ARP REPLY is received from a client update its info
* in the rx_hashtbl
*/
struct rlb_client_info *client_info;
u32 hash_index;
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
hash_index = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src));
client_info = &(bond_info->rx_hashtbl[hash_index]);
if ((client_info->assigned) &&
(client_info->ip_src == arp->ip_dst) &&
- (client_info->ip_dst == arp->ip_src)) {
+ (client_info->ip_dst == arp->ip_src) &&
+ (compare_ether_addr_64bits(client_info->mac_dst, arp->mac_src))) {
/* update the clients MAC address */
memcpy(client_info->mac_dst, arp->mac_src, ETH_ALEN);
client_info->ntt = 1;
bond_info->rx_ntt = 1;
}
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
}
-static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct packet_type *ptype, struct net_device *orig_dev)
+static int rlb_arp_recv(struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
- struct bonding *bond = bond_dev->priv;
- struct arp_pkt *arp = (struct arp_pkt *)skb->data;
- int res = NET_RX_DROP;
+ struct arp_pkt *arp;
- if (!(bond_dev->flags & IFF_MASTER))
+ if (skb->protocol != cpu_to_be16(ETH_P_ARP))
goto out;
+ arp = (struct arp_pkt *) skb->data;
if (!arp) {
- dprintk("Packet has no ARP data\n");
+ pr_debug("Packet has no ARP data\n");
goto out;
}
+ if (!pskb_may_pull(skb, arp_hdr_len(bond->dev)))
+ goto out;
+
if (skb->len < sizeof(struct arp_pkt)) {
- dprintk("Packet is too small to be an ARP\n");
+ pr_debug("Packet is too small to be an ARP\n");
goto out;
}
if (arp->op_code == htons(ARPOP_REPLY)) {
/* update rx hash table for this ARP */
rlb_update_entry_from_arp(bond, arp);
- dprintk("Server received an ARP Reply from client\n");
+ pr_debug("Server received an ARP Reply from client\n");
}
-
- res = NET_RX_SUCCESS;
-
out:
- dev_kfree_skb(skb);
-
- return res;
+ return RX_HANDLER_ANOTHER;
}
/* Caller must hold bond lock for read */
}
if (!bond->alb_info.primary_is_promisc) {
- bond->alb_info.primary_is_promisc = 1;
- dev_set_promiscuity(bond->curr_active_slave->dev, 1);
+ if (!dev_set_promiscuity(bond->curr_active_slave->dev, 1))
+ bond->alb_info.primary_is_promisc = 1;
+ else
+ bond->alb_info.primary_is_promisc = 0;
}
bond->alb_info.rlb_promisc_timeout_counter = 0;
u32 index, next_index;
/* clear slave from rx_hashtbl */
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
rx_hash_table = bond_info->rx_hashtbl;
index = bond_info->rx_hashtbl_head;
if (assigned_slave) {
rx_hash_table[index].slave = assigned_slave;
- if (memcmp(rx_hash_table[index].mac_dst,
- mac_bcast, ETH_ALEN)) {
+ if (compare_ether_addr_64bits(rx_hash_table[index].mac_dst,
+ mac_bcast)) {
bond_info->rx_hashtbl[index].ntt = 1;
bond_info->rx_ntt = 1;
/* A slave has been removed from the
}
}
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
- write_lock(&bond->curr_slave_lock);
+ write_lock_bh(&bond->curr_slave_lock);
if (slave != bond->curr_active_slave) {
rlb_teach_disabled_mac_on_primary(bond, slave->dev->dev_addr);
}
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
}
static void rlb_update_client(struct rlb_client_info *client_info)
client_info->slave->dev->dev_addr,
client_info->mac_dst);
if (!skb) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: failed to create an ARP packet\n",
+ pr_err("%s: Error: failed to create an ARP packet\n",
client_info->slave->dev->master->name);
continue;
}
if (client_info->tag) {
skb = vlan_put_tag(skb, client_info->vlan_id);
if (!skb) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: failed to insert VLAN tag\n",
+ pr_err("%s: Error: failed to insert VLAN tag\n",
client_info->slave->dev->master->name);
continue;
}
struct rlb_client_info *client_info;
u32 hash_index;
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
hash_index = bond_info->rx_hashtbl_head;
for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) {
}
}
- /* do not update the entries again untill this counter is zero so that
+ /* do not update the entries again until this counter is zero so that
* not to confuse the clients.
*/
bond_info->rlb_update_delay_counter = RLB_UPDATE_DELAY;
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
}
/* The slave was assigned a new mac address - update the clients */
int ntt = 0;
u32 hash_index;
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
hash_index = bond_info->rx_hashtbl_head;
for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) {
client_info = &(bond_info->rx_hashtbl[hash_index]);
if ((client_info->slave == slave) &&
- memcmp(client_info->mac_dst, mac_bcast, ETH_ALEN)) {
+ compare_ether_addr_64bits(client_info->mac_dst, mac_bcast)) {
client_info->ntt = 1;
ntt = 1;
}
bond_info->rlb_update_retry_counter = RLB_UPDATE_RETRY;
}
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
}
/* mark all clients using src_ip to be updated */
-static void rlb_req_update_subnet_clients(struct bonding *bond, u32 src_ip)
+static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip)
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
struct rlb_client_info *client_info;
client_info = &(bond_info->rx_hashtbl[hash_index]);
if (!client_info->slave) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: found a client with no channel in "
- "the client's hash table\n",
+ pr_err("%s: Error: found a client with no channel in the client's hash table\n",
bond->dev->name);
continue;
}
* unicast mac address.
*/
if ((client_info->ip_src == src_ip) &&
- memcmp(client_info->slave->dev->dev_addr,
- bond->dev->dev_addr, ETH_ALEN) &&
- memcmp(client_info->mac_dst, mac_bcast, ETH_ALEN)) {
+ compare_ether_addr_64bits(client_info->slave->dev->dev_addr,
+ bond->dev->dev_addr) &&
+ compare_ether_addr_64bits(client_info->mac_dst, mac_bcast)) {
client_info->ntt = 1;
bond_info->rx_ntt = 1;
}
static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond)
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
- struct arp_pkt *arp = (struct arp_pkt *)skb->nh.raw;
+ struct arp_pkt *arp = arp_pkt(skb);
struct slave *assigned_slave;
struct rlb_client_info *client_info;
u32 hash_index = 0;
_lock_rx_hashtbl(bond);
- hash_index = _simple_hash((u8 *)&arp->ip_dst, sizeof(arp->ip_src));
+ hash_index = _simple_hash((u8 *)&arp->ip_dst, sizeof(arp->ip_dst));
client_info = &(bond_info->rx_hashtbl[hash_index]);
if (client_info->assigned) {
if ((client_info->ip_src == arp->ip_src) &&
(client_info->ip_dst == arp->ip_dst)) {
/* the entry is already assigned to this client */
- if (memcmp(arp->mac_dst, mac_bcast, ETH_ALEN)) {
+ if (compare_ether_addr_64bits(arp->mac_dst, mac_bcast)) {
/* update mac address from arp */
memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN);
}
memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN);
client_info->slave = assigned_slave;
- if (memcmp(client_info->mac_dst, mac_bcast, ETH_ALEN)) {
+ if (compare_ether_addr_64bits(client_info->mac_dst, mac_bcast)) {
client_info->ntt = 1;
bond->alb_info.rx_ntt = 1;
} else {
client_info->ntt = 0;
}
- if (!list_empty(&bond->vlan_list)) {
- unsigned short vlan_id;
- int res = vlan_get_tag(skb, &vlan_id);
- if (!res) {
+ if (bond_vlan_used(bond)) {
+ if (!vlan_get_tag(skb, &client_info->vlan_id))
client_info->tag = 1;
- client_info->vlan_id = vlan_id;
- }
}
if (!client_info->assigned) {
*/
static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
{
- struct arp_pkt *arp = (struct arp_pkt *)skb->nh.raw;
+ struct arp_pkt *arp = arp_pkt(skb);
struct slave *tx_slave = NULL;
- if (arp->op_code == __constant_htons(ARPOP_REPLY)) {
+ if (arp->op_code == htons(ARPOP_REPLY)) {
/* the arp must be sent on the selected
* rx channel
*/
if (tx_slave) {
memcpy(arp->mac_src,tx_slave->dev->dev_addr, ETH_ALEN);
}
- dprintk("Server sent ARP Reply packet\n");
- } else if (arp->op_code == __constant_htons(ARPOP_REQUEST)) {
+ pr_debug("Server sent ARP Reply packet\n");
+ } else if (arp->op_code == htons(ARPOP_REQUEST)) {
/* Create an entry in the rx_hashtbl for this client as a
* place holder.
* When the arp reply is received the entry will be updated
*/
rlb_choose_channel(skb, bond);
- /* The ARP relpy packets must be delayed so that
+ /* The ARP reply packets must be delayed so that
* they can cancel out the influence of the ARP request.
*/
bond->alb_info.rlb_update_delay_counter = RLB_UPDATE_DELAY;
* updated with their assigned mac.
*/
rlb_req_update_subnet_clients(bond, arp->ip_src);
- dprintk("Server sent ARP Request packet\n");
+ pr_debug("Server sent ARP Request packet\n");
}
return tx_slave;
int ntt;
u32 hash_index;
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
ntt = 0;
hash_index = bond_info->rx_hashtbl_head;
if (ntt) {
bond_info->rx_ntt = 1;
}
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
}
/* Caller must hold rx_hashtbl lock */
static int rlb_initialize(struct bonding *bond)
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
- struct packet_type *pk_type = &(BOND_ALB_INFO(bond).rlb_pkt_type);
struct rlb_client_info *new_hashtbl;
int size = RLB_HASH_TABLE_SIZE * sizeof(struct rlb_client_info);
int i;
- spin_lock_init(&(bond_info->rx_hashtbl_lock));
-
new_hashtbl = kmalloc(size, GFP_KERNEL);
- if (!new_hashtbl) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: Failed to allocate RLB hash table\n",
- bond->dev->name);
+ if (!new_hashtbl)
return -1;
- }
- _lock_rx_hashtbl(bond);
+
+ _lock_rx_hashtbl_bh(bond);
bond_info->rx_hashtbl = new_hashtbl;
rlb_init_table_entry(bond_info->rx_hashtbl + i);
}
- _unlock_rx_hashtbl(bond);
-
- /*initialize packet type*/
- pk_type->type = __constant_htons(ETH_P_ARP);
- pk_type->dev = bond->dev;
- pk_type->func = rlb_arp_recv;
+ _unlock_rx_hashtbl_bh(bond);
/* register to receive ARPs */
- dev_add_pack(pk_type);
+ bond->recv_probe = rlb_arp_recv;
return 0;
}
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
- dev_remove_pack(&(bond_info->rlb_pkt_type));
-
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
kfree(bond_info->rx_hashtbl);
bond_info->rx_hashtbl = NULL;
bond_info->rx_hashtbl_head = RLB_NULL_INDEX;
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
}
static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id)
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
u32 curr_index;
- _lock_rx_hashtbl(bond);
+ _lock_rx_hashtbl_bh(bond);
curr_index = bond_info->rx_hashtbl_head;
while (curr_index != RLB_NULL_INDEX) {
curr_index = next_index;
}
- _unlock_rx_hashtbl(bond);
+ _unlock_rx_hashtbl_bh(bond);
}
/*********************** tlb/rlb shared functions *********************/
memset(&pkt, 0, size);
memcpy(pkt.mac_dst, mac_addr, ETH_ALEN);
memcpy(pkt.mac_src, mac_addr, ETH_ALEN);
- pkt.type = __constant_htons(ETH_P_LOOP);
+ pkt.type = cpu_to_be16(ETH_P_LOOP);
for (i = 0; i < MAX_LP_BURST; i++) {
struct sk_buff *skb;
data = skb_put(skb, size);
memcpy(data, &pkt, size);
- skb->mac.raw = data;
- skb->nh.raw = data + ETH_HLEN;
+ skb_reset_mac_header(skb);
+ skb->network_header = skb->mac_header + ETH_HLEN;
skb->protocol = pkt.type;
skb->priority = TC_PRIO_CONTROL;
skb->dev = slave->dev;
- if (!list_empty(&bond->vlan_list)) {
+ if (bond_vlan_used(bond)) {
struct vlan_entry *vlan;
vlan = bond_next_vlan(bond,
skb = vlan_put_tag(skb, vlan->vlan_id);
if (!skb) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: failed to insert VLAN tag\n",
+ pr_err("%s: Error: failed to insert VLAN tag\n",
bond->dev->name);
continue;
}
}
}
-/* hw is a boolean parameter that determines whether we should try and
- * set the hw address of the device as well as the hw address of the
- * net_device
- */
-static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[], int hw)
+static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
{
struct net_device *dev = slave->dev;
struct sockaddr s_addr;
- if (!hw) {
+ if (slave->bond->params.mode == BOND_MODE_TLB) {
memcpy(dev->dev_addr, addr, dev->addr_len);
return 0;
}
memcpy(s_addr.sa_data, addr, dev->addr_len);
s_addr.sa_family = dev->type;
if (dev_set_mac_address(dev, &s_addr)) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: dev_set_mac_address of dev %s failed! ALB "
- "mode requires that the base driver support setting "
- "the hw address also when the network device's "
- "interface is open\n",
+ pr_err("%s: Error: dev_set_mac_address of dev %s failed!\n"
+ "ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
dev->master->name, dev->name);
return -EOPNOTSUPP;
}
return 0;
}
-/* Caller must hold bond lock for write or curr_slave_lock for write*/
+/*
+ * Swap MAC addresses between two slaves.
+ *
+ * Called with RTNL held, and no other locks.
+ *
+ */
+
static void alb_swap_mac_addr(struct bonding *bond, struct slave *slave1, struct slave *slave2)
{
- struct slave *disabled_slave = NULL;
u8 tmp_mac_addr[ETH_ALEN];
- int slaves_state_differ;
-
- slaves_state_differ = (SLAVE_IS_OK(slave1) != SLAVE_IS_OK(slave2));
memcpy(tmp_mac_addr, slave1->dev->dev_addr, ETH_ALEN);
- alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr, bond->alb_info.rlb_enabled);
- alb_set_slave_mac_addr(slave2, tmp_mac_addr, bond->alb_info.rlb_enabled);
+ alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr);
+ alb_set_slave_mac_addr(slave2, tmp_mac_addr);
+
+}
+
+/*
+ * Send learning packets after MAC address swap.
+ *
+ * Called with RTNL and no other locks
+ */
+static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1,
+ struct slave *slave2)
+{
+ int slaves_state_differ = (SLAVE_IS_OK(slave1) != SLAVE_IS_OK(slave2));
+ struct slave *disabled_slave = NULL;
+
+ ASSERT_RTNL();
/* fasten the change in the switch */
if (SLAVE_IS_OK(slave1)) {
* a slave that has @slave's permanet address as its current address.
* We'll make sure that that slave no longer uses @slave's permanent address.
*
- * Caller must hold bond lock
+ * Caller must hold RTNL and no other locks
*/
static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *slave)
{
int perm_curr_diff;
int perm_bond_diff;
- perm_curr_diff = memcmp(slave->perm_hwaddr,
- slave->dev->dev_addr,
- ETH_ALEN);
- perm_bond_diff = memcmp(slave->perm_hwaddr,
- bond->dev->dev_addr,
- ETH_ALEN);
+ perm_curr_diff = compare_ether_addr_64bits(slave->perm_hwaddr,
+ slave->dev->dev_addr);
+ perm_bond_diff = compare_ether_addr_64bits(slave->perm_hwaddr,
+ bond->dev->dev_addr);
if (perm_curr_diff && perm_bond_diff) {
struct slave *tmp_slave;
int i, found = 0;
bond_for_each_slave(bond, tmp_slave, i) {
- if (!memcmp(slave->perm_hwaddr,
- tmp_slave->dev->dev_addr,
- ETH_ALEN)) {
+ if (!compare_ether_addr_64bits(slave->perm_hwaddr,
+ tmp_slave->dev->dev_addr)) {
found = 1;
break;
}
}
if (found) {
+ /* locking: needs RTNL and nothing else */
alb_swap_mac_addr(bond, slave, tmp_slave);
+ alb_fasten_mac_swap(bond, slave, tmp_slave);
}
}
}
*
* If the permanent hw address of @slave is @bond's hw address, we need to
* find a different hw address to give @slave, that isn't in use by any other
- * slave in the bond. This address must be, of course, one of the premanent
+ * slave in the bond. This address must be, of course, one of the permanent
* addresses of the other slaves.
*
* We go over the slave list, and for each slave there we compare its
* check uniqueness of slave's mac address against the other
* slaves in the bond.
*/
- if (memcmp(slave->perm_hwaddr, bond->dev->dev_addr, ETH_ALEN)) {
+ if (compare_ether_addr_64bits(slave->perm_hwaddr, bond->dev->dev_addr)) {
bond_for_each_slave(bond, tmp_slave1, i) {
- if (!memcmp(tmp_slave1->dev->dev_addr, slave->dev->dev_addr,
- ETH_ALEN)) {
+ if (!compare_ether_addr_64bits(tmp_slave1->dev->dev_addr,
+ slave->dev->dev_addr)) {
found = 1;
break;
}
/* Try setting slave mac to bond address and fall-through
to code handling that situation below... */
- alb_set_slave_mac_addr(slave, bond->dev->dev_addr,
- bond->alb_info.rlb_enabled);
+ alb_set_slave_mac_addr(slave, bond->dev->dev_addr);
}
/* The slave's address is equal to the address of the bond.
bond_for_each_slave(bond, tmp_slave1, i) {
found = 0;
bond_for_each_slave(bond, tmp_slave2, j) {
- if (!memcmp(tmp_slave1->perm_hwaddr,
- tmp_slave2->dev->dev_addr,
- ETH_ALEN)) {
+ if (!compare_ether_addr_64bits(tmp_slave1->perm_hwaddr,
+ tmp_slave2->dev->dev_addr)) {
found = 1;
break;
}
}
if (!has_bond_addr) {
- if (!memcmp(tmp_slave1->dev->dev_addr,
- bond->dev->dev_addr,
- ETH_ALEN)) {
+ if (!compare_ether_addr_64bits(tmp_slave1->dev->dev_addr,
+ bond->dev->dev_addr)) {
has_bond_addr = tmp_slave1;
}
}
if (free_mac_slave) {
- alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr,
- bond->alb_info.rlb_enabled);
+ alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr);
- printk(KERN_WARNING DRV_NAME
- ": %s: Warning: the hw address of slave %s is in use by "
- "the bond; giving it the hw address of %s\n",
- bond->dev->name, slave->dev->name, free_mac_slave->dev->name);
+ pr_warning("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
+ bond->dev->name, slave->dev->name,
+ free_mac_slave->dev->name);
} else if (has_bond_addr) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: the hw address of slave %s is in use by the "
- "bond; couldn't find a slave with a free hw address to "
- "give it (this should not have happened)\n",
+ pr_err("%s: Error: the hw address of slave %s is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)\n",
bond->dev->name, slave->dev->name);
return -EFAULT;
}
}
bond_for_each_slave(bond, slave, i) {
- if (slave->dev->set_mac_address == NULL) {
- res = -EOPNOTSUPP;
- goto unwind;
- }
-
/* save net_device's current hw address */
memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN);
/* restore net_device's hw address */
memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN);
- if (res) {
+ if (res)
goto unwind;
- }
}
return 0;
int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct ethhdr *eth_data;
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
struct slave *tx_slave = NULL;
- static const u32 ip_bcast = 0xffffffff;
+ static const __be32 ip_bcast = htonl(0xffffffff);
int hash_size = 0;
int do_tx_balance = 1;
u32 hash_index = 0;
- u8 *hash_start = NULL;
+ const u8 *hash_start = NULL;
int res = 1;
+ struct ipv6hdr *ip6hdr;
- skb->mac.raw = (unsigned char *)skb->data;
+ skb_reset_mac_header(skb);
eth_data = eth_hdr(skb);
- /* make sure that the curr_active_slave and the slaves list do
- * not change during tx
+ /* make sure that the curr_active_slave do not change during tx
*/
- read_lock(&bond->lock);
read_lock(&bond->curr_slave_lock);
- if (!BOND_IS_OK(bond)) {
- goto out;
- }
-
switch (ntohs(skb->protocol)) {
- case ETH_P_IP:
- if ((memcmp(eth_data->h_dest, mac_bcast, ETH_ALEN) == 0) ||
- (skb->nh.iph->daddr == ip_bcast) ||
- (skb->nh.iph->protocol == IPPROTO_IGMP)) {
+ case ETH_P_IP: {
+ const struct iphdr *iph = ip_hdr(skb);
+
+ if (!compare_ether_addr_64bits(eth_data->h_dest, mac_bcast) ||
+ (iph->daddr == ip_bcast) ||
+ (iph->protocol == IPPROTO_IGMP)) {
do_tx_balance = 0;
break;
}
- hash_start = (char*)&(skb->nh.iph->daddr);
- hash_size = sizeof(skb->nh.iph->daddr);
+ hash_start = (char *)&(iph->daddr);
+ hash_size = sizeof(iph->daddr);
+ }
break;
case ETH_P_IPV6:
- if (memcmp(eth_data->h_dest, mac_bcast, ETH_ALEN) == 0) {
+ /* IPv6 doesn't really use broadcast mac address, but leave
+ * that here just in case.
+ */
+ if (!compare_ether_addr_64bits(eth_data->h_dest, mac_bcast)) {
do_tx_balance = 0;
break;
}
- hash_start = (char*)&(skb->nh.ipv6h->daddr);
- hash_size = sizeof(skb->nh.ipv6h->daddr);
+ /* IPv6 uses all-nodes multicast as an equivalent to
+ * broadcasts in IPv4.
+ */
+ if (!compare_ether_addr_64bits(eth_data->h_dest, mac_v6_allmcast)) {
+ do_tx_balance = 0;
+ break;
+ }
+
+ /* Additianally, DAD probes should not be tx-balanced as that
+ * will lead to false positives for duplicate addresses and
+ * prevent address configuration from working.
+ */
+ ip6hdr = ipv6_hdr(skb);
+ if (ipv6_addr_any(&ip6hdr->saddr)) {
+ do_tx_balance = 0;
+ break;
+ }
+
+ hash_start = (char *)&(ipv6_hdr(skb)->daddr);
+ hash_size = sizeof(ipv6_hdr(skb)->daddr);
break;
case ETH_P_IPX:
- if (ipx_hdr(skb)->ipx_checksum !=
- __constant_htons(IPX_NO_CHECKSUM)) {
+ if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) {
/* something is wrong with this packet */
do_tx_balance = 0;
break;
res = bond_dev_queue_xmit(bond, skb, tx_slave->dev);
} else {
if (tx_slave) {
- tlb_clear_slave(bond, tx_slave, 0);
+ _lock_tx_hashtbl(bond);
+ __tlb_clear_slave(bond, tx_slave, 0);
+ _unlock_tx_hashtbl(bond);
}
}
-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;
+
+ return NETDEV_TX_OK;
}
-void bond_alb_monitor(struct bonding *bond)
+void bond_alb_monitor(struct work_struct *work)
{
+ struct bonding *bond = container_of(work, struct bonding,
+ alb_work.work);
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
struct slave *slave;
int i;
read_lock(&bond->lock);
- if (bond->kill_timers) {
- goto out;
- }
-
if (bond->slave_cnt == 0) {
bond_info->tx_rebalance_counter = 0;
bond_info->lp_counter = 0;
/* handle rlb stuff */
if (bond_info->rlb_enabled) {
- /* the following code changes the promiscuity of the
- * the curr_active_slave. It needs to be locked with a
- * write lock to protect from other code that also
- * sets the promiscuity.
- */
- write_lock_bh(&bond->curr_slave_lock);
-
if (bond_info->primary_is_promisc &&
(++bond_info->rlb_promisc_timeout_counter >= RLB_PROMISC_TIMEOUT)) {
+ /*
+ * dev_set_promiscuity requires rtnl and
+ * nothing else. Avoid race with bond_close.
+ */
+ read_unlock(&bond->lock);
+ if (!rtnl_trylock()) {
+ read_lock(&bond->lock);
+ goto re_arm;
+ }
+
bond_info->rlb_promisc_timeout_counter = 0;
/* If the primary was set to promiscuous mode
*/
dev_set_promiscuity(bond->curr_active_slave->dev, -1);
bond_info->primary_is_promisc = 0;
- }
- write_unlock_bh(&bond->curr_slave_lock);
+ rtnl_unlock();
+ read_lock(&bond->lock);
+ }
if (bond_info->rlb_rebalance) {
bond_info->rlb_rebalance = 0;
}
re_arm:
- mod_timer(&(bond_info->alb_timer), jiffies + alb_delta_in_ticks);
-out:
+ queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks);
+
read_unlock(&bond->lock);
}
{
int res;
- res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr,
- bond->alb_info.rlb_enabled);
+ res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr);
if (res) {
return res;
}
/* caller must hold the bond lock for write since the mac addresses
* are compared and may be swapped.
*/
- write_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
res = alb_handle_addr_collision_on_attach(bond, slave);
- write_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
if (res) {
return res;
return 0;
}
-/* Caller must hold bond lock for write */
+/*
+ * Remove slave from tlb and rlb hash tables, and fix up MAC addresses
+ * if necessary.
+ *
+ * Caller must hold RTNL and no other locks
+ */
void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave)
{
if (bond->slave_cnt > 1) {
* Set the bond->curr_active_slave to @new_slave and handle
* mac address swapping and promiscuity changes as needed.
*
- * Caller must hold bond curr_slave_lock for write (or bond lock for write)
+ * If new_slave is NULL, caller must hold curr_slave_lock or
+ * bond->lock for write.
+ *
+ * If new_slave is not NULL, caller must hold RTNL, bond->lock for
+ * read and curr_slave_lock for write. Processing here may sleep, so
+ * no other locks may be held.
*/
void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave)
+ __releases(&bond->curr_slave_lock)
+ __releases(&bond->lock)
+ __acquires(&bond->lock)
+ __acquires(&bond->curr_slave_lock)
{
struct slave *swap_slave;
int i;
struct slave *tmp_slave;
/* find slave that is holding the bond's mac address */
bond_for_each_slave(bond, tmp_slave, i) {
- if (!memcmp(tmp_slave->dev->dev_addr,
- bond->dev->dev_addr, ETH_ALEN)) {
+ if (!compare_ether_addr_64bits(tmp_slave->dev->dev_addr,
+ bond->dev->dev_addr)) {
swap_slave = tmp_slave;
break;
}
}
}
+ /*
+ * Arrange for swap_slave and new_slave to temporarily be
+ * ignored so we can mess with their MAC addresses without
+ * fear of interference from transmit activity.
+ */
+ if (swap_slave) {
+ tlb_clear_slave(bond, swap_slave, 1);
+ }
+ tlb_clear_slave(bond, new_slave, 1);
+
+ write_unlock_bh(&bond->curr_slave_lock);
+ read_unlock(&bond->lock);
+
+ ASSERT_RTNL();
+
/* curr_active_slave must be set before calling alb_swap_mac_addr */
if (swap_slave) {
/* swap mac address */
alb_swap_mac_addr(bond, swap_slave, new_slave);
} else {
/* set the new_slave to the bond mac address */
- alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr,
- bond->alb_info.rlb_enabled);
- /* fasten bond mac on new current slave */
+ alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr);
+ }
+
+ if (swap_slave) {
+ alb_fasten_mac_swap(bond, swap_slave, new_slave);
+ read_lock(&bond->lock);
+ } else {
+ read_lock(&bond->lock);
alb_send_learning_packets(new_slave, bond->dev->dev_addr);
}
+
+ write_lock_bh(&bond->curr_slave_lock);
}
+/*
+ * Called with RTNL
+ */
int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
+ __acquires(&bond->lock)
+ __releases(&bond->lock)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = netdev_priv(bond_dev);
struct sockaddr *sa = addr;
struct slave *slave, *swap_slave;
int res;
swap_slave = NULL;
bond_for_each_slave(bond, slave, i) {
- if (!memcmp(slave->dev->dev_addr, bond_dev->dev_addr, ETH_ALEN)) {
+ if (!compare_ether_addr_64bits(slave->dev->dev_addr,
+ bond_dev->dev_addr)) {
swap_slave = slave;
break;
}
if (swap_slave) {
alb_swap_mac_addr(bond, swap_slave, bond->curr_active_slave);
+ alb_fasten_mac_swap(bond, swap_slave, bond->curr_active_slave);
} else {
- alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr,
- bond->alb_info.rlb_enabled);
+ alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr);
+ read_lock(&bond->lock);
alb_send_learning_packets(bond->curr_active_slave, bond_dev->dev_addr);
if (bond->alb_info.rlb_enabled) {
/* inform clients mac address has changed */
rlb_req_update_slave_clients(bond, bond->curr_active_slave);
}
+ read_unlock(&bond->lock);
}
return 0;