Merge branch 'bonding_neighbours'

bonding: use neighbours instead of own lists

Veaceslav Falico says:

====================
This patchset introduces all the needed infrastructure, on top of current
adjacent lists, to be able to remove bond's slave_list/slave->list. The
overhead in memory/CPU is minimal, and after the patchset bonding can rely
on its slave-related functions, given the proper locking. I've done some
netperf benchmarks on a vm, and the delta was about 0.1gbps for 35gbps as a
whole, so no speed fluctuations.

It also automatically creates lower/upper and master symlinks in dev's
sysfs directory.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_3ad.c

@@ -2117,7 +2117,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	read_lock(&bond->lock);
 
 	//check if there are any slaves
-	if (list_empty(&bond->slave_list))
+	if (!bond_has_slaves(bond))
 		goto re_arm;
 
 	// check if agg_select_timer timer after initialize is timed out
@@ -2417,14 +2417,15 @@ int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info)
 
 int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 {
-	struct slave *slave, *start_at;
 	struct bonding *bond = netdev_priv(dev);
-	int slave_agg_no;
-	int slaves_in_agg;
-	int agg_id;
-	int i;
+	struct slave *slave, *first_ok_slave;
+	struct aggregator *agg;
 	struct ad_info ad_info;
+	struct list_head *iter;
+	int slaves_in_agg;
+	int slave_agg_no;
 	int res = 1;
+	int agg_id;
 
 	read_lock(&bond->lock);
 	if (__bond_3ad_get_active_agg_info(bond, &ad_info)) {
@@ -2437,20 +2438,28 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 	agg_id = ad_info.aggregator_id;
 
 	if (slaves_in_agg == 0) {
-		/*the aggregator is empty*/
 		pr_debug("%s: Error: active aggregator is empty\n", dev->name);
 		goto out;
 	}
 
 	slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg);
+	first_ok_slave = NULL;
 
-	bond_for_each_slave(bond, slave) {
-		struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator;
+	bond_for_each_slave(bond, slave, iter) {
+		agg = SLAVE_AD_INFO(slave).port.aggregator;
+		if (!agg || agg->aggregator_identifier != agg_id)
+			continue;
 
-		if (agg && (agg->aggregator_identifier == agg_id)) {
+		if (slave_agg_no >= 0) {
+			if (!first_ok_slave && SLAVE_IS_OK(slave))
+				first_ok_slave = slave;
 			slave_agg_no--;
-			if (slave_agg_no < 0)
-				break;
+			continue;
+		}
+
+		if (SLAVE_IS_OK(slave)) {
+			res = bond_dev_queue_xmit(bond, skb, slave->dev);
+			goto out;
 		}
 	}
 
@@ -2460,20 +2469,10 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
-	start_at = slave;
-
-	bond_for_each_slave_from(bond, slave, i, start_at) {
-		int slave_agg_id = 0;
-		struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator;
-
-		if (agg)
-			slave_agg_id = agg->aggregator_identifier;
-
-		if (SLAVE_IS_OK(slave) && agg && (slave_agg_id == agg_id)) {
-			res = bond_dev_queue_xmit(bond, skb, slave->dev);
-			break;
-		}
-	}
+	/* we couldn't find any suitable slave after the agg_no, so use the
+	 * first suitable found, if found. */
+	if (first_ok_slave)
+		res = bond_dev_queue_xmit(bond, skb, first_ok_slave->dev);
 
 out:
 	read_unlock(&bond->lock);
@@ -2515,11 +2514,12 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 void bond_3ad_update_lacp_rate(struct bonding *bond)
 {
 	struct port *port = NULL;
+	struct list_head *iter;
 	struct slave *slave;
 	int lacp_fast;
 
 	lacp_fast = bond->params.lacp_fast;
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		port = &(SLAVE_AD_INFO(slave).port);
 		__get_state_machine_lock(port);
 		if (lacp_fast)

drivers/net/bonding/bond_alb.c

@@ -223,13 +223,14 @@ static long long compute_gap(struct slave *slave)
 static struct slave *tlb_get_least_loaded_slave(struct bonding *bond)
 {
 	struct slave *slave, *least_loaded;
+	struct list_head *iter;
 	long long max_gap;
 
 	least_loaded = NULL;
 	max_gap = LLONG_MIN;
 
 	/* Find the slave with the largest gap */
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (SLAVE_IS_OK(slave)) {
 			long long gap = compute_gap(slave);
 
@@ -382,30 +383,31 @@ static int rlb_arp_recv(const struct sk_buff *skb, struct bonding *bond,
 static struct slave *rlb_next_rx_slave(struct bonding *bond)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
-	struct slave *rx_slave, *slave, *start_at;
-	int i = 0;
-
-	if (bond_info->next_rx_slave)
-		start_at = bond_info->next_rx_slave;
-	else
-		start_at = bond_first_slave(bond);
-
-	rx_slave = NULL;
+	struct slave *before = NULL, *rx_slave = NULL, *slave;
+	struct list_head *iter;
+	bool found = false;
 
-	bond_for_each_slave_from(bond, slave, i, start_at) {
-		if (SLAVE_IS_OK(slave)) {
-			if (!rx_slave) {
-				rx_slave = slave;
-			} else if (slave->speed > rx_slave->speed) {
+	bond_for_each_slave(bond, slave, iter) {
+		if (!SLAVE_IS_OK(slave))
+			continue;
+		if (!found) {
+			if (!before || before->speed < slave->speed)
+				before = slave;
+		} else {
+			if (!rx_slave || rx_slave->speed < slave->speed)
 				rx_slave = slave;
 		}
+		if (slave == bond_info->rx_slave)
+			found = true;
 	}
-	}
+	/* we didn't find anything after the current or we have something
+	 * better before and up to the current slave
+	 */
+	if (!rx_slave || (before && rx_slave->speed < before->speed))
+		rx_slave = before;
 
-	if (rx_slave) {
-		slave = bond_next_slave(bond, rx_slave);
-		bond_info->next_rx_slave = slave;
-	}
+	if (rx_slave)
+		bond_info->rx_slave = rx_slave;
 
 	return rx_slave;
 }
@@ -1019,7 +1021,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[])
 
 	/* loop through vlans and send one packet for each */
 	rcu_read_lock();
-	netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+	netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
 		if (upper->priv_flags & IFF_802_1Q_VLAN)
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_id(upper));
@@ -1172,10 +1174,11 @@ static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *sla
  */
 static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slave *slave)
 {
-	struct slave *tmp_slave1, *free_mac_slave = NULL;
 	struct slave *has_bond_addr = bond->curr_active_slave;
+	struct slave *tmp_slave1, *free_mac_slave = NULL;
+	struct list_head *iter;
 
-	if (list_empty(&bond->slave_list)) {
+	if (!bond_has_slaves(bond)) {
 		/* this is the first slave */
 		return 0;
 	}
@@ -1196,7 +1199,7 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 	/* The slave's address is equal to the address of the bond.
 	 * Search for a spare address in the bond for this slave.
 	 */
-	bond_for_each_slave(bond, tmp_slave1) {
+	bond_for_each_slave(bond, tmp_slave1, iter) {
 		if (!bond_slave_has_mac(bond, tmp_slave1->perm_hwaddr)) {
 			/* no slave has tmp_slave1's perm addr
 			 * as its curr addr
@@ -1246,15 +1249,16 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
  */
 static int alb_set_mac_address(struct bonding *bond, void *addr)
 {
-	char tmp_addr[ETH_ALEN];
-	struct slave *slave;
+	struct slave *slave, *rollback_slave;
+	struct list_head *iter;
 	struct sockaddr sa;
+	char tmp_addr[ETH_ALEN];
 	int res;
 
 	if (bond->alb_info.rlb_enabled)
 		return 0;
 
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		/* save net_device's current hw address */
 		memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN);
 
@@ -1274,10 +1278,12 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 	sa.sa_family = bond->dev->type;
 
 	/* unwind from head to the slave that failed */
-	bond_for_each_slave_continue_reverse(bond, slave) {
-		memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN);
-		dev_set_mac_address(slave->dev, &sa);
-		memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN);
+	bond_for_each_slave(bond, rollback_slave, iter) {
+		if (rollback_slave == slave)
+			break;
+		memcpy(tmp_addr, rollback_slave->dev->dev_addr, ETH_ALEN);
+		dev_set_mac_address(rollback_slave->dev, &sa);
+		memcpy(rollback_slave->dev->dev_addr, tmp_addr, ETH_ALEN);
 	}
 
 	return res;
@@ -1458,11 +1464,12 @@ 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 list_head *iter;
 	struct slave *slave;
 
 	read_lock(&bond->lock);
 
-	if (list_empty(&bond->slave_list)) {
+	if (!bond_has_slaves(bond)) {
 		bond_info->tx_rebalance_counter = 0;
 		bond_info->lp_counter = 0;
 		goto re_arm;
@@ -1480,7 +1487,7 @@ void bond_alb_monitor(struct work_struct *work)
 		 */
 		read_lock(&bond->curr_slave_lock);
 
-		bond_for_each_slave(bond, slave)
+		bond_for_each_slave(bond, slave, iter)
 			alb_send_learning_packets(slave, slave->dev->dev_addr);
 
 		read_unlock(&bond->curr_slave_lock);
@@ -1493,7 +1500,7 @@ void bond_alb_monitor(struct work_struct *work)
 
 		read_lock(&bond->curr_slave_lock);
 
-		bond_for_each_slave(bond, slave) {
+		bond_for_each_slave(bond, slave, iter) {
 			tlb_clear_slave(bond, slave, 1);
 			if (slave == bond->curr_active_slave) {
 				SLAVE_TLB_INFO(slave).load =
@@ -1599,13 +1606,13 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave)
  */
 void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave)
 {
-	if (!list_empty(&bond->slave_list))
+	if (bond_has_slaves(bond))
 		alb_change_hw_addr_on_detach(bond, slave);
 
 	tlb_clear_slave(bond, slave, 0);
 
 	if (bond->alb_info.rlb_enabled) {
-		bond->alb_info.next_rx_slave = NULL;
+		bond->alb_info.rx_slave = NULL;
 		rlb_clear_slave(bond, slave);
 	}
 }
@@ -1669,7 +1676,7 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	swap_slave = bond->curr_active_slave;
 	rcu_assign_pointer(bond->curr_active_slave, new_slave);
 
-	if (!new_slave || list_empty(&bond->slave_list))
+	if (!new_slave || !bond_has_slaves(bond))
 		return;
 
 	/* set the new curr_active_slave to the bonds mac address

drivers/net/bonding/bond_alb.h

@@ -154,9 +154,7 @@ struct alb_bond_info {
 	u8			rx_ntt;	/* flag - need to transmit
 					 * to all rx clients
 					 */
-	struct slave		*next_rx_slave;/* next slave to be assigned
-						* to a new rx client for
-						*/
+	struct slave		*rx_slave;/* last slave to xmit from */
 	u8			primary_is_promisc;	   /* boolean */
 	u32			rlb_promisc_timeout_counter;/* counts primary
 							     * promiscuity time

drivers/net/bonding/bond_procfs.c

@@ -10,8 +10,9 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(&bond->lock)
 {
 	struct bonding *bond = seq->private;
-	loff_t off = 0;
+	struct list_head *iter;
 	struct slave *slave;
+	loff_t off = 0;
 
 	/* make sure the bond won't be taken away */
 	rcu_read_lock();
@@ -20,7 +21,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	bond_for_each_slave(bond, slave)
+	bond_for_each_slave(bond, slave, iter)
 		if (++off == *pos)
 			return slave;
 

drivers/net/bonding/bond_sysfs.c

@@ -168,41 +168,6 @@ static const struct class_attribute class_attr_bonding_masters = {
 	.namespace = bonding_namespace,
 };
 
-int bond_create_slave_symlinks(struct net_device *master,
-			       struct net_device *slave)
-{
-	char linkname[IFNAMSIZ+7];
-	int ret = 0;
-
-	/* first, create a link from the slave back to the master */
-	ret = sysfs_create_link(&(slave->dev.kobj), &(master->dev.kobj),
-				"master");
-	if (ret)
-		return ret;
-	/* next, create a link from the master to the slave */
-	sprintf(linkname, "slave_%s", slave->name);
-	ret = sysfs_create_link(&(master->dev.kobj), &(slave->dev.kobj),
-				linkname);
-
-	/* free the master link created earlier in case of error */
-	if (ret)
-		sysfs_remove_link(&(slave->dev.kobj), "master");
-
-	return ret;
-
-}
-
-void bond_destroy_slave_symlinks(struct net_device *master,
-				 struct net_device *slave)
-{
-	char linkname[IFNAMSIZ+7];
-
-	sysfs_remove_link(&(slave->dev.kobj), "master");
-	sprintf(linkname, "slave_%s", slave->name);
-	sysfs_remove_link(&(master->dev.kobj), linkname);
-}
-
-
 /*
  * Show the slaves in the current bond.
  */
@@ -210,11 +175,12 @@ static ssize_t bonding_show_slaves(struct device *d,
 				   struct device_attribute *attr, char *buf)
 {
 	struct bonding *bond = to_bond(d);
+	struct list_head *iter;
 	struct slave *slave;
 	int res = 0;
 
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (res > (PAGE_SIZE - IFNAMSIZ)) {
 			/* not enough space for another interface name */
 			if ((PAGE_SIZE - res) > 10)
@@ -326,7 +292,7 @@ static ssize_t bonding_store_mode(struct device *d,
 		goto out;
 	}
 
-	if (!list_empty(&bond->slave_list)) {
+	if (bond_has_slaves(bond)) {
 		pr_err("unable to update mode of %s because it has slaves.\n",
 			bond->dev->name);
 		ret = -EPERM;
@@ -522,7 +488,7 @@ static ssize_t bonding_store_fail_over_mac(struct device *d,
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	if (!list_empty(&bond->slave_list)) {
+	if (bond_has_slaves(bond)) {
 		pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n",
 		       bond->dev->name);
 		ret = -EPERM;
@@ -656,6 +622,7 @@ static ssize_t bonding_store_arp_targets(struct device *d,
 					 const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
+	struct list_head *iter;
 	struct slave *slave;
 	__be32 newtarget, *targets;
 	unsigned long *targets_rx;
@@ -688,7 +655,7 @@ static ssize_t bonding_store_arp_targets(struct device *d,
 			 &newtarget);
 		/* not to race with bond_arp_rcv */
 		write_lock_bh(&bond->lock);
-		bond_for_each_slave(bond, slave)
+		bond_for_each_slave(bond, slave, iter)
 			slave->target_last_arp_rx[ind] = jiffies;
 		targets[ind] = newtarget;
 		write_unlock_bh(&bond->lock);
@@ -714,7 +681,7 @@ static ssize_t bonding_store_arp_targets(struct device *d,
 			&newtarget);
 
 		write_lock_bh(&bond->lock);
-		bond_for_each_slave(bond, slave) {
+		bond_for_each_slave(bond, slave, iter) {
 			targets_rx = slave->target_last_arp_rx;
 			j = ind;
 			for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
@@ -1111,6 +1078,7 @@ static ssize_t bonding_store_primary(struct device *d,
 				     const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
+	struct list_head *iter;
 	char ifname[IFNAMSIZ];
 	struct slave *slave;
 
@@ -1138,7 +1106,7 @@ static ssize_t bonding_store_primary(struct device *d,
 		goto out;
 	}
 
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) {
 			pr_info("%s: Setting %s as primary slave.\n",
 				bond->dev->name, slave->dev->name);
@@ -1286,6 +1254,7 @@ static ssize_t bonding_store_active_slave(struct device *d,
 {
 	struct slave *slave, *old_active, *new_active;
 	struct bonding *bond = to_bond(d);
+	struct list_head *iter;
 	char ifname[IFNAMSIZ];
 
 	if (!rtnl_trylock())
@@ -1313,7 +1282,7 @@ static ssize_t bonding_store_active_slave(struct device *d,
 		goto out;
 	}
 
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) {
 			old_active = bond->curr_active_slave;
 			new_active = slave;
@@ -1493,6 +1462,7 @@ static ssize_t bonding_show_queue_id(struct device *d,
 				     char *buf)
 {
 	struct bonding *bond = to_bond(d);
+	struct list_head *iter;
 	struct slave *slave;
 	int res = 0;
 
@@ -1500,7 +1470,7 @@ static ssize_t bonding_show_queue_id(struct device *d,
 		return restart_syscall();
 
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (res > (PAGE_SIZE - IFNAMSIZ - 6)) {
 			/* not enough space for another interface_name:queue_id pair */
 			if ((PAGE_SIZE - res) > 10)
@@ -1529,6 +1499,7 @@ static ssize_t bonding_store_queue_id(struct device *d,
 {
 	struct slave *slave, *update_slave;
 	struct bonding *bond = to_bond(d);
+	struct list_head *iter;
 	u16 qid;
 	int ret = count;
 	char *delim;
@@ -1565,7 +1536,7 @@ static ssize_t bonding_store_queue_id(struct device *d,
 
 	/* Search for thes slave and check for duplicate qids */
 	update_slave = NULL;
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (sdev == slave->dev)
 			/*
 			 * We don't need to check the matching
@@ -1619,6 +1590,7 @@ static ssize_t bonding_store_slaves_active(struct device *d,
 {
 	struct bonding *bond = to_bond(d);
 	int new_value, ret = count;
+	struct list_head *iter;
 	struct slave *slave;
 
 	if (sscanf(buf, "%d", &new_value) != 1) {
@@ -1641,7 +1613,7 @@ static ssize_t bonding_store_slaves_active(struct device *d,
 	}
 
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave) {
+	bond_for_each_slave(bond, slave, iter) {
 		if (!bond_is_active_slave(slave)) {
 			if (new_value)
 				slave->inactive = 0;

drivers/net/bonding/bonding.h

@@ -72,63 +72,40 @@
 	res; })
 
 /* slave list primitives */
-#define bond_to_slave(ptr) list_entry(ptr, struct slave, list)
+#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower)
+
+#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond))
 
 /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */
 #define bond_first_slave(bond) \
-	list_first_entry_or_null(&(bond)->slave_list, struct slave, list)
+	(bond_has_slaves(bond) ? \
+		netdev_adjacent_get_private(bond_slave_list(bond)->next) : \
+		NULL)
 #define bond_last_slave(bond) \
-	(list_empty(&(bond)->slave_list) ? NULL : \
-					   bond_to_slave((bond)->slave_list.prev))
+	(bond_has_slaves(bond) ? \
+		netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \
+		NULL)
 
-#define bond_is_first_slave(bond, pos) ((pos)->list.prev == &(bond)->slave_list)
-#define bond_is_last_slave(bond, pos) ((pos)->list.next == &(bond)->slave_list)
+#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond))
+#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond))
 
 /* Since bond_first/last_slave can return NULL, these can return NULL too */
-#define bond_next_slave(bond, pos) \
-	(bond_is_last_slave(bond, pos) ? bond_first_slave(bond) : \
-					 bond_to_slave((pos)->list.next))
-
-#define bond_prev_slave(bond, pos) \
-	(bond_is_first_slave(bond, pos) ? bond_last_slave(bond) : \
-					  bond_to_slave((pos)->list.prev))
-
-/**
- * bond_for_each_slave_from - iterate the slaves list from a starting point
- * @bond:	the bond holding this list.
- * @pos:	current slave.
- * @cnt:	counter for max number of moves
- * @start:	starting point.
- *
- * Caller must hold bond->lock
- */
-#define bond_for_each_slave_from(bond, pos, cnt, start) \
-	for (cnt = 0, pos = start; pos && cnt < (bond)->slave_cnt; \
-	     cnt++, pos = bond_next_slave(bond, pos))
+#define bond_next_slave(bond, pos) __bond_next_slave(bond, pos)
 
 /**
  * bond_for_each_slave - iterate over all slaves
  * @bond:	the bond holding this list
  * @pos:	current slave
+ * @iter:	list_head * iterator
  *
  * Caller must hold bond->lock
  */
-#define bond_for_each_slave(bond, pos) \
-	list_for_each_entry(pos, &(bond)->slave_list, list)
+#define bond_for_each_slave(bond, pos, iter) \
+	netdev_for_each_lower_private((bond)->dev, pos, iter)
 
 /* Caller must have rcu_read_lock */
-#define bond_for_each_slave_rcu(bond, pos) \
-	list_for_each_entry_rcu(pos, &(bond)->slave_list, list)
-
-/**
- * bond_for_each_slave_reverse - iterate in reverse from a given position
- * @bond:	the bond holding this list
- * @pos:	slave to continue from
- *
- * Caller must hold bond->lock
- */
-#define bond_for_each_slave_continue_reverse(bond, pos) \
-	list_for_each_entry_continue_reverse(pos, &(bond)->slave_list, list)
+#define bond_for_each_slave_rcu(bond, pos, iter) \
+	netdev_for_each_lower_private_rcu((bond)->dev, pos, iter)
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 extern atomic_t netpoll_block_tx;
@@ -188,7 +165,6 @@ struct bond_parm_tbl {
 
 struct slave {
 	struct net_device *dev; /* first - useful for panic debug */
-	struct list_head list;
 	struct bonding *bond; /* our master */
 	int    delay;
 	unsigned long jiffies;
@@ -228,7 +204,6 @@ struct slave {
  */
 struct bonding {
 	struct   net_device *dev; /* first - useful for panic debug */
-	struct   list_head slave_list;
 	struct   slave *curr_active_slave;
 	struct   slave *current_arp_slave;
 	struct   slave *primary_slave;
@@ -268,6 +243,34 @@ struct bonding {
 #define bond_slave_get_rtnl(dev) \
 	((struct slave *) rtnl_dereference(dev->rx_handler_data))
 
+/**
+ * __bond_next_slave - get the next slave after the one provided
+ * @bond - bonding struct
+ * @slave - the slave provided
+ *
+ * Returns the next slave after the slave provided, first slave if the
+ * slave provided is the last slave and NULL if slave is not found
+ */
+static inline struct slave *__bond_next_slave(struct bonding *bond,
+					      struct slave *slave)
+{
+	struct slave *slave_iter;
+	struct list_head *iter;
+	bool found = false;
+
+	netdev_for_each_lower_private(bond->dev, slave_iter, iter) {
+		if (found)
+			return slave_iter;
+		if (slave_iter == slave)
+			found = true;
+	}
+
+	if (found)
+		return bond_first_slave(bond);
+
+	return NULL;
+}
+
 /**
  * Returns NULL if the net_device does not belong to any of the bond's slaves
  *
@@ -276,13 +279,7 @@ struct bonding {
 static inline struct slave *bond_get_slave_by_dev(struct bonding *bond,
 						  struct net_device *slave_dev)
 {
-	struct slave *slave = NULL;
-
-	bond_for_each_slave(bond, slave)
-		if (slave->dev == slave_dev)
-			return slave;
-
-	return NULL;
+	return netdev_lower_dev_get_private(bond->dev, slave_dev);
 }
 
 static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
@@ -439,8 +436,6 @@ int bond_create(struct net *net, const char *name);
 int bond_create_sysfs(struct bond_net *net);
 void bond_destroy_sysfs(struct bond_net *net);
 void bond_prepare_sysfs_group(struct bonding *bond);
-int bond_create_slave_symlinks(struct net_device *master, struct net_device *slave);
-void bond_destroy_slave_symlinks(struct net_device *master, struct net_device *slave);
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
 void bond_mii_monitor(struct work_struct *);
@@ -492,9 +487,10 @@ static inline void bond_destroy_proc_dir(struct bond_net *bn)
 static inline struct slave *bond_slave_has_mac(struct bonding *bond,
 					       const u8 *mac)
 {
+	struct list_head *iter;
 	struct slave *tmp;
 
-	bond_for_each_slave(bond, tmp)
+	bond_for_each_slave(bond, tmp, iter)
 		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
 			return tmp;
 

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -3983,6 +3983,7 @@ static int cxgb4_inet6addr_handler(struct notifier_block *this,
 	struct net_device *event_dev;
 	int ret = NOTIFY_DONE;
 	struct bonding *bond = netdev_priv(ifa->idev->dev);
+	struct list_head *iter;
 	struct slave *slave;
 	struct pci_dev *first_pdev = NULL;
 
@@ -3995,7 +3996,7 @@ static int cxgb4_inet6addr_handler(struct notifier_block *this,
 		 * in all of them only once.
 		 */
 		read_lock(&bond->lock);
-		bond_for_each_slave(bond, slave) {
+		bond_for_each_slave(bond, slave, iter) {
 			if (!first_pdev) {
 				ret = clip_add(slave->dev, ifa, event);
 				/* If clip_add is success then only initialize

include/linux/netdevice.h

@@ -1143,8 +1143,18 @@ struct net_device {
 	struct list_head	dev_list;
 	struct list_head	napi_list;
 	struct list_head	unreg_list;
-	struct list_head	upper_dev_list; /* List of upper devices */
-	struct list_head	lower_dev_list;
+
+	/* directly linked devices, like slaves for bonding */
+	struct {
+		struct list_head upper;
+		struct list_head lower;
+	} adj_list;
+
+	/* all linked devices, *including* neighbours */
+	struct {
+		struct list_head upper;
+		struct list_head lower;
+	} all_adj_list;
 
 
 	/* currently active device features */
@@ -2813,24 +2823,49 @@ extern int		bpf_jit_enable;
 extern bool netdev_has_upper_dev(struct net_device *dev,
 				 struct net_device *upper_dev);
 extern bool netdev_has_any_upper_dev(struct net_device *dev);
-extern struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+extern struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 							    struct list_head **iter);
 
 /* iterate through upper list, must be called under RCU read lock */
-#define netdev_for_each_upper_dev_rcu(dev, upper, iter) \
-	for (iter = &(dev)->upper_dev_list, \
-	     upper = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
-	     upper; \
-	     upper = netdev_upper_get_next_dev_rcu(dev, &(iter)))
+#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
+	for (iter = &(dev)->all_adj_list.upper, \
+	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
+	     updev; \
+	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
+
+extern void *netdev_lower_get_next_private(struct net_device *dev,
+					   struct list_head **iter);
+extern void *netdev_lower_get_next_private_rcu(struct net_device *dev,
+					       struct list_head **iter);
+
+#define netdev_for_each_lower_private(dev, priv, iter) \
+	for (iter = (dev)->adj_list.lower.next, \
+	     priv = netdev_lower_get_next_private(dev, &(iter)); \
+	     priv; \
+	     priv = netdev_lower_get_next_private(dev, &(iter)))
+
+#define netdev_for_each_lower_private_rcu(dev, priv, iter) \
+	for (iter = &(dev)->adj_list.lower, \
+	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \
+	     priv; \
+	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
 
+extern void *netdev_adjacent_get_private(struct list_head *adj_list);
 extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
 extern int netdev_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev);
 extern int netdev_master_upper_dev_link(struct net_device *dev,
 					struct net_device *upper_dev);
+extern int netdev_master_upper_dev_link_private(struct net_device *dev,
+						struct net_device *upper_dev,
+						void *private);
 extern void netdev_upper_dev_unlink(struct net_device *dev,
 				    struct net_device *upper_dev);
+extern void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
+					      struct net_device *lower_dev);
+extern void *netdev_lower_dev_get_private(struct net_device *dev,
+					  struct net_device *lower_dev);
 extern int skb_checksum_help(struct sk_buff *skb);
 extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 	netdev_features_t features, bool tx_path);

net/8021q/vlan.c

@@ -98,14 +98,14 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 		vlan_gvrp_request_leave(dev);
 
 	vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL);
+
+	netdev_upper_dev_unlink(real_dev, dev);
 	/* Because unregister_netdevice_queue() makes sure at least one rcu
 	 * grace period is respected before device freeing,
 	 * we dont need to call synchronize_net() here.
 	 */
 	unregister_netdevice_queue(dev, head);
 
-	netdev_upper_dev_unlink(real_dev, dev);
-
 	if (grp->nr_vlan_devs == 0) {
 		vlan_mvrp_uninit_applicant(real_dev);
 		vlan_gvrp_uninit_applicant(real_dev);
@@ -169,13 +169,13 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
-	err = netdev_upper_dev_link(real_dev, dev);
-	if (err)
-		goto out_uninit_mvrp;
-
 	err = register_netdevice(dev);
 	if (err < 0)
-		goto out_upper_dev_unlink;
+		goto out_uninit_mvrp;
+
+	err = netdev_upper_dev_link(real_dev, dev);
+	if (err)
+		goto out_unregister_netdev;
 
 	/* Account for reference in struct vlan_dev_priv */
 	dev_hold(real_dev);
@@ -191,8 +191,8 @@ int register_vlan_dev(struct net_device *dev)
 
 	return 0;
 
-out_upper_dev_unlink:
-	netdev_upper_dev_unlink(real_dev, dev);
+out_unregister_netdev:
+	unregister_netdevice(dev);
 out_uninit_mvrp:
 	if (grp->nr_vlan_devs == 0)
 		vlan_mvrp_uninit_applicant(real_dev);