8 files changed, 239 insertions, 107 deletions

diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile
index 6f9c6fa..0e2737e 100644
--- a/drivers/net/bonding/Makefile
+++ b/drivers/net/bonding/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_BONDING) += bonding.o
 
-bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o
+bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_debugfs.o
 
 ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o
 bonding-objs += $(ipv6-y)
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 881914b..48cf24f 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2474,8 +2474,7 @@ int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct net_device *dev, struct pac
 		goto out;
 
 	read_lock(&bond->lock);
-	slave = bond_get_slave_by_dev((struct bonding *)netdev_priv(dev),
-					orig_dev);
+	slave = bond_get_slave_by_dev(netdev_priv(dev), orig_dev);
 	if (!slave)
 		goto out_unlock;
 
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 26bb118..f4e638c 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -44,42 +44,6 @@
 #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
 
 #ifndef __long_aligned
 #define __long_aligned __attribute__((aligned((sizeof(long)))))
diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h
index 50968f8..118c28a 100644
--- a/drivers/net/bonding/bond_alb.h
+++ b/drivers/net/bonding/bond_alb.h
@@ -31,6 +31,44 @@ struct slave;
 #define BOND_ALB_INFO(bond)   ((bond)->alb_info)
 #define SLAVE_TLB_INFO(slave) ((slave)->tlb_info)
 
+#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)
+
+
 struct tlb_client_info {
 	struct slave *tx_slave;	/* A pointer to slave used for transmiting
 				 * packets to a Client that the Hash function
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
new file mode 100644
index 0000000..3680aa2
--- /dev/null
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -0,0 +1,146 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/netdevice.h>
+
+#include "bonding.h"
+#include "bond_alb.h"
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static struct dentry *bonding_debug_root;
+
+/*
+ *  Show RLB hash table
+ */
+static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
+{
+	struct bonding *bond = m->private;
+	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
+	struct rlb_client_info *client_info;
+	u32 hash_index;
+
+	if (bond->params.mode != BOND_MODE_ALB)
+		return 0;
+
+	seq_printf(m, "SourceIP        DestinationIP   "
+			"Destination MAC   DEV\n");
+
+	spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
+
+	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]);
+		seq_printf(m, "%-15pI4 %-15pI4 %-17pM %s\n",
+			&client_info->ip_src,
+			&client_info->ip_dst,
+			&client_info->mac_dst,
+			client_info->slave->dev->name);
+	}
+
+	spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
+
+	return 0;
+}
+
+static int bond_debug_rlb_hash_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, bond_debug_rlb_hash_show, inode->i_private);
+}
+
+static const struct file_operations bond_debug_rlb_hash_fops = {
+	.owner		= THIS_MODULE,
+	.open		= bond_debug_rlb_hash_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+void bond_debug_register(struct bonding *bond)
+{
+	if (!bonding_debug_root)
+		return;
+
+	bond->debug_dir =
+		debugfs_create_dir(bond->dev->name, bonding_debug_root);
+
+	if (!bond->debug_dir) {
+		pr_warning("%s: Warning: failed to register to debugfs\n",
+			bond->dev->name);
+		return;
+	}
+
+	debugfs_create_file("rlb_hash_table", 0400, bond->debug_dir,
+				bond, &bond_debug_rlb_hash_fops);
+}
+
+void bond_debug_unregister(struct bonding *bond)
+{
+	if (!bonding_debug_root)
+		return;
+
+	debugfs_remove_recursive(bond->debug_dir);
+}
+
+void bond_debug_reregister(struct bonding *bond)
+{
+	struct dentry *d;
+
+	if (!bonding_debug_root)
+		return;
+
+	d = debugfs_rename(bonding_debug_root, bond->debug_dir,
+			   bonding_debug_root, bond->dev->name);
+	if (d) {
+		bond->debug_dir = d;
+	} else {
+		pr_warning("%s: Warning: failed to reregister, "
+				"so just unregister old one\n",
+				bond->dev->name);
+		bond_debug_unregister(bond);
+	}
+}
+
+void bond_create_debugfs(void)
+{
+	bonding_debug_root = debugfs_create_dir("bonding", NULL);
+
+	if (!bonding_debug_root) {
+		pr_warning("Warning: Cannot create bonding directory"
+				" in debugfs\n");
+	}
+}
+
+void bond_destroy_debugfs(void)
+{
+	debugfs_remove_recursive(bonding_debug_root);
+	bonding_debug_root = NULL;
+}
+
+
+#else /* !CONFIG_DEBUG_FS */
+
+void bond_debug_register(struct bonding *bond)
+{
+}
+
+void bond_debug_unregister(struct bonding *bond)
+{
+}
+
+void bond_debug_reregister(struct bonding *bond)
+{
+}
+
+void bond_create_debugfs(void)
+{
+}
+
+void bond_destroy_debugfs(void)
+{
+}
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c
index 121b073..84fbd4e 100644
--- a/drivers/net/bonding/bond_ipv6.c
+++ b/drivers/net/bonding/bond_ipv6.c
@@ -88,7 +88,12 @@ static void bond_na_send(struct net_device *slave_dev,
 	}
 
 	if (vlan_id) {
-		skb = vlan_put_tag(skb, vlan_id);
+		/* The Ethernet header is not present yet, so it is
+		 * too early to insert a VLAN tag.  Force use of an
+		 * out-of-line tag here and let dev_hard_start_xmit()
+		 * insert it if the slave hardware can't.
+		 */
+		skb = __vlan_hwaccel_put_tag(skb, vlan_id);
 		if (!skb) {
 			pr_err("failed to insert VLAN tag\n");
 			return;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index bdb68a6..b1025b8 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -171,7 +171,7 @@ MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on link
 /*----------------------------- Global variables ----------------------------*/
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-cpumask_var_t netpoll_block_tx;
+atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 #endif
 
 static const char * const version =
@@ -418,36 +418,11 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr)
  * @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 uninitialized_var(vlan_id);
-
-	/* Test vlan_list not vlgrp to catch and handle 802.1p tags */
-	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->dev = slave_dev;
 	skb->priority = 1;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	if (unlikely(bond->dev->priv_flags & IFF_IN_NETPOLL)) {
@@ -873,15 +848,11 @@ static void bond_mc_del(struct bonding *bond, void *addr)
 static void __bond_resend_igmp_join_requests(struct net_device *dev)
 {
 	struct in_device *in_dev;
-	struct ip_mc_list *im;
 
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dev);
-	if (in_dev) {
-		for (im = in_dev->mc_list; im; im = im->next)
-			ip_mc_rejoin_group(im);
-	}
-
+	if (in_dev)
+		ip_mc_rejoin_groups(in_dev);
 	rcu_read_unlock();
 }
 
@@ -1201,11 +1172,13 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 				bond_do_fail_over_mac(bond, new_active,
 						      old_active);
 
-			bond->send_grat_arp = bond->params.num_grat_arp;
-			bond_send_gratuitous_arp(bond);
+			if (netif_running(bond->dev)) {
+				bond->send_grat_arp = bond->params.num_grat_arp;
+				bond_send_gratuitous_arp(bond);
 
-			bond->send_unsol_na = bond->params.num_unsol_na;
-			bond_send_unsolicited_na(bond);
+				bond->send_unsol_na = bond->params.num_unsol_na;
+				bond_send_unsolicited_na(bond);
+			}
 
 			write_unlock_bh(&bond->curr_slave_lock);
 			read_unlock(&bond->lock);
@@ -1219,8 +1192,9 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 
 	/* resend IGMP joins since active slave has changed or
 	 * all were sent on curr_active_slave */
-	if ((USES_PRIMARY(bond->params.mode) && new_active) ||
-	    bond->params.mode == BOND_MODE_ROUNDROBIN) {
+	if (((USES_PRIMARY(bond->params.mode) && new_active) ||
+	     bond->params.mode == BOND_MODE_ROUNDROBIN) &&
+	    netif_running(bond->dev)) {
 		bond->igmp_retrans = bond->params.resend_igmp;
 		queue_delayed_work(bond->wq, &bond->mcast_work, 0);
 	}
@@ -1574,7 +1548,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	/* If this is the first slave, then we need to set the master's hardware
 	 * address to be the same as the slave's. */
-	if (bond->slave_cnt == 0)
+	if (is_zero_ether_addr(bond->dev->dev_addr))
 		memcpy(bond->dev->dev_addr, slave_dev->dev_addr,
 		       slave_dev->addr_len);
 
@@ -3209,7 +3183,7 @@ out:
 #ifdef CONFIG_PROC_FS
 
 static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(&dev_base_lock)
+	__acquires(RCU)
 	__acquires(&bond->lock)
 {
 	struct bonding *bond = seq->private;
@@ -3218,7 +3192,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 	int i;
 
 	/* make sure the bond won't be taken away */
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	read_lock(&bond->lock);
 
 	if (*pos == 0)
@@ -3248,12 +3222,12 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static void bond_info_seq_stop(struct seq_file *seq, void *v)
 	__releases(&bond->lock)
-	__releases(&dev_base_lock)
+	__releases(RCU)
 {
 	struct bonding *bond = seq->private;
 
 	read_unlock(&bond->lock);
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 }
 
 static void bond_info_show_master(struct seq_file *seq)
@@ -3507,6 +3481,8 @@ static int bond_event_changename(struct bonding *bond)
 	bond_remove_proc_entry(bond);
 	bond_create_proc_entry(bond);
 
+	bond_debug_reregister(bond);
+
 	return NOTIFY_DONE;
 }
 
@@ -4789,6 +4765,8 @@ static void bond_uninit(struct net_device *bond_dev)
 
 	bond_remove_proc_entry(bond);
 
+	bond_debug_unregister(bond);
+
 	__hw_addr_flush(&bond->mc_list);
 
 	list_for_each_entry_safe(vlan, tmp, &bond->vlan_list, vlan_list) {
@@ -5191,6 +5169,8 @@ static int bond_init(struct net_device *bond_dev)
 
 	bond_prepare_sysfs_group(bond);
 
+	bond_debug_register(bond);
+
 	__hw_addr_init(&bond->mc_list);
 	return 0;
 }
@@ -5297,13 +5277,6 @@ static int __init bonding_init(void)
 	if (res)
 		goto out;
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	if (!alloc_cpumask_var(&netpoll_block_tx, GFP_KERNEL)) {
-		res = -ENOMEM;
-		goto out;
-	}
-#endif
-
 	res = register_pernet_subsys(&bond_net_ops);
 	if (res)
 		goto out;
@@ -5312,6 +5285,8 @@ static int __init bonding_init(void)
 	if (res)
 		goto err_link;
 
+	bond_create_debugfs();
+
 	for (i = 0; i < max_bonds; i++) {
 		res = bond_create(&init_net, NULL);
 		if (res)
@@ -5322,7 +5297,6 @@ static int __init bonding_init(void)
 	if (res)
 		goto err;
 
-
 	register_netdevice_notifier(&bond_netdev_notifier);
 	register_inetaddr_notifier(&bond_inetaddr_notifier);
 	bond_register_ipv6_notifier();
@@ -5332,9 +5306,6 @@ err:
 	rtnl_link_unregister(&bond_link_ops);
 err_link:
 	unregister_pernet_subsys(&bond_net_ops);
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	free_cpumask_var(netpoll_block_tx);
-#endif
 	goto out;
 
 }
@@ -5346,12 +5317,16 @@ static void __exit bonding_exit(void)
 	bond_unregister_ipv6_notifier();
 
 	bond_destroy_sysfs();
+	bond_destroy_debugfs();
 
 	rtnl_link_unregister(&bond_link_ops);
 	unregister_pernet_subsys(&bond_net_ops);
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	free_cpumask_var(netpoll_block_tx);
+	/*
+	 * Make sure we don't have an imbalance on our netpoll blocking
+	 */
+	WARN_ON(atomic_read(&netpoll_block_tx));
 #endif
 }
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 4eedb12..4da384c 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -119,26 +119,22 @@
 
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-extern cpumask_var_t netpoll_block_tx;
+extern atomic_t netpoll_block_tx;
 
 static inline void block_netpoll_tx(void)
 {
-	preempt_disable();
-	BUG_ON(cpumask_test_and_set_cpu(smp_processor_id(),
-					netpoll_block_tx));
+	atomic_inc(&netpoll_block_tx);
 }
 
 static inline void unblock_netpoll_tx(void)
 {
-	BUG_ON(!cpumask_test_and_clear_cpu(smp_processor_id(),
-					   netpoll_block_tx));
-	preempt_enable();
+	atomic_dec(&netpoll_block_tx);
 }
 
 static inline int is_netpoll_tx_blocked(struct net_device *dev)
 {
 	if (unlikely(dev->priv_flags & IFF_IN_NETPOLL))
-		return cpumask_test_cpu(smp_processor_id(), netpoll_block_tx);
+		return atomic_read(&netpoll_block_tx);
 	return 0;
 }
 #else
@@ -259,6 +255,10 @@ struct bonding {
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	struct   in6_addr master_ipv6;
 #endif
+#ifdef CONFIG_DEBUG_FS
+	/* debugging suport via debugfs */
+	struct	 dentry *debug_dir;
+#endif /* CONFIG_DEBUG_FS */
 };
 
 /**
@@ -273,11 +273,11 @@ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct n
 
 	bond_for_each_slave(bond, slave, i) {
 		if (slave->dev == slave_dev) {
-			break;
+			return slave;
 		}
 	}
 
-	return slave;
+	return 0;
 }
 
 static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
@@ -286,7 +286,7 @@ static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
 		return NULL;
 	}
 
-	return (struct bonding *)netdev_priv(slave->dev->master);
+	return netdev_priv(slave->dev->master);
 }
 
 static inline bool bond_is_lb(const struct bonding *bond)
@@ -380,6 +380,11 @@ void bond_select_active_slave(struct bonding *bond);
 void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
 void bond_register_arp(struct bonding *);
 void bond_unregister_arp(struct bonding *);
+void bond_create_debugfs(void);
+void bond_destroy_debugfs(void);
+void bond_debug_register(struct bonding *bond);
+void bond_debug_unregister(struct bonding *bond);
+void bond_debug_reregister(struct bonding *bond);
 
 struct bond_net {
 	struct net *		net;	/* Associated network namespace */