bonding: alternate agg selection policies for 802.3ad

	This patch implements alternative aggregator selection policies
for 802.3ad.  The existing policy, now termed "stable," selects the active
aggregator by greatest bandwidth, and only reselects a new aggregator
if the active aggregator is entirely disabled (no more ports or all ports
down).

	This patch adds two new policies: bandwidth and count, selecting
the active aggregator by total bandwidth (like the stable policy) or by
the number of ports in the aggregator, respectively.  These two policies
also differ from the stable policy in that they will reselect the active
aggregator when availability-related changes occur in the bond (e.g.,
link state change).

	This permits "gang failover" within 802.3ad, allowing redundant
aggregators along parallel paths to always maintain the "best" aggregator
as the active aggregator (rather than having to wait for the active to
entirely fail).

	This patch also updates the driver version to 3.5.0.
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>

Documentation/networking/bonding.txt

@@ -194,6 +194,48 @@ or, for backwards compatibility, the option value.  E.g.,
 
 	The parameters are as follows:
 
+ad_select
+
+	Specifies the 802.3ad aggregation selection logic to use.  The
+	possible values and their effects are:
+
+	stable or 0
+
+		The active aggregator is chosen by largest aggregate
+		bandwidth.
+
+		Reselection of the active aggregator occurs only when all
+		slaves of the active aggregator are down or the active
+		aggregator has no slaves.
+
+		This is the default value.
+
+	bandwidth or 1
+
+		The active aggregator is chosen by largest aggregate
+		bandwidth.  Reselection occurs if:
+
+		- A slave is added to or removed from the bond
+
+		- Any slave's link state changes
+
+		- Any slave's 802.3ad association state changes
+
+		- The bond's adminstrative state changes to up
+
+	count or 2
+
+		The active aggregator is chosen by the largest number of
+		ports (slaves).  Reselection occurs as described under the
+		"bandwidth" setting, above.
+
+	The bandwidth and count selection policies permit failover of
+	802.3ad aggregations when partial failure of the active aggregator
+	occurs.  This keeps the aggregator with the highest availability
+	(either in bandwidth or in number of ports) active at all times.
+
+	This option was added in bonding version 3.4.0.
+
 arp_interval
 
 	Specifies the ARP link monitoring frequency in milliseconds.

drivers/net/bonding/bond_3ad.h

@@ -42,10 +42,11 @@ typedef struct mac_addr {
 	u8 mac_addr_value[ETH_ALEN];
 } mac_addr_t;
 
-typedef enum {
-	AD_BANDWIDTH = 0,
-	AD_COUNT
-} agg_selection_t;
+enum {
+	BOND_AD_STABLE = 0,
+	BOND_AD_BANDWIDTH = 1,
+	BOND_AD_COUNT = 2,
+};
 
 // rx machine states(43.4.11 in the 802.3ad standard)
 typedef enum {
@@ -277,6 +278,7 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fas
 int  bond_3ad_bind_slave(struct slave *slave);
 void bond_3ad_unbind_slave(struct slave *slave);
 void bond_3ad_state_machine_handler(struct work_struct *);
+void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout);
 void bond_3ad_adapter_speed_changed(struct slave *slave);
 void bond_3ad_adapter_duplex_changed(struct slave *slave);
 void bond_3ad_handle_link_change(struct slave *slave, char link);

drivers/net/bonding/bond_main.c

@@ -97,6 +97,7 @@ static int use_carrier	= 1;
 static char *mode	= NULL;
 static char *primary	= NULL;
 static char *lacp_rate	= NULL;
+static char *ad_select  = NULL;
 static char *xmit_hash_policy = NULL;
 static int arp_interval = BOND_LINK_ARP_INTERV;
 static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, };
@@ -130,6 +131,8 @@ 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(ad_select, charp, 0);
+MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)");
 module_param(xmit_hash_policy, charp, 0);
 MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)"
 				   ", 1 for layer 3+4");
@@ -200,6 +203,13 @@ struct bond_parm_tbl fail_over_mac_tbl[] = {
 {	NULL,			-1},
 };
 
+struct bond_parm_tbl ad_select_tbl[] = {
+{	"stable",	BOND_AD_STABLE},
+{	"bandwidth",	BOND_AD_BANDWIDTH},
+{	"count",	BOND_AD_COUNT},
+{	NULL,		-1},
+};
+
 /*-------------------------- Forward declarations ---------------------------*/
 
 static void bond_send_gratuitous_arp(struct bonding *bond);
@@ -3318,6 +3328,8 @@ static void bond_info_show_master(struct seq_file *seq)
 		seq_puts(seq, "\n802.3ad info\n");
 		seq_printf(seq, "LACP rate: %s\n",
 			   (bond->params.lacp_fast) ? "fast" : "slow");
+		seq_printf(seq, "Aggregator selection policy (ad_select): %s\n",
+			   ad_select_tbl[bond->params.ad_select].modename);
 
 		if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
 			seq_printf(seq, "bond %s has no active aggregator\n",
@@ -3824,6 +3836,7 @@ static int bond_open(struct net_device *bond_dev)
 		queue_delayed_work(bond->wq, &bond->ad_work, 0);
 		/* register to receive LACPDUs */
 		bond_register_lacpdu(bond);
+		bond_3ad_initiate_agg_selection(bond, 1);
 	}
 
 	return 0;
@@ -4763,6 +4776,23 @@ static int bond_check_params(struct bond_params *params)
 		}
 	}
 
+	if (ad_select) {
+		params->ad_select = bond_parse_parm(ad_select, ad_select_tbl);
+		if (params->ad_select == -1) {
+			printk(KERN_ERR DRV_NAME
+			       ": Error: Invalid ad_select \"%s\"\n",
+			       ad_select == NULL ? "NULL" : ad_select);
+			return -EINVAL;
+		}
+
+		if (bond_mode != BOND_MODE_8023AD) {
+			printk(KERN_WARNING DRV_NAME
+			       ": ad_select param only affects 802.3ad mode\n");
+		}
+	} else {
+		params->ad_select = BOND_AD_STABLE;
+	}
+
 	if (max_bonds < 0 || max_bonds > INT_MAX) {
 		printk(KERN_WARNING DRV_NAME
 		       ": Warning: max_bonds (%d) not in range %d-%d, so it "

drivers/net/bonding/bond_sysfs.c

@@ -48,6 +48,7 @@ extern struct list_head bond_dev_list;
 extern struct bond_params bonding_defaults;
 extern struct bond_parm_tbl bond_mode_tbl[];
 extern struct bond_parm_tbl bond_lacp_tbl[];
+extern struct bond_parm_tbl ad_select_tbl[];
 extern struct bond_parm_tbl xmit_hashtype_tbl[];
 extern struct bond_parm_tbl arp_validate_tbl[];
 extern struct bond_parm_tbl fail_over_mac_tbl[];
@@ -944,6 +945,53 @@ static ssize_t bonding_store_lacp(struct device *d,
 }
 static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, bonding_show_lacp, bonding_store_lacp);
 
+static ssize_t bonding_show_ad_select(struct device *d,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct bonding *bond = to_bond(d);
+
+	return sprintf(buf, "%s %d\n",
+		ad_select_tbl[bond->params.ad_select].modename,
+		bond->params.ad_select);
+}
+
+
+static ssize_t bonding_store_ad_select(struct device *d,
+				       struct device_attribute *attr,
+				       const char *buf, size_t count)
+{
+	int new_value, ret = count;
+	struct bonding *bond = to_bond(d);
+
+	if (bond->dev->flags & IFF_UP) {
+		printk(KERN_ERR DRV_NAME
+		       ": %s: Unable to update ad_select because interface "
+		       "is up.\n", bond->dev->name);
+		ret = -EPERM;
+		goto out;
+	}
+
+	new_value = bond_parse_parm(buf, ad_select_tbl);
+
+	if (new_value != -1) {
+		bond->params.ad_select = new_value;
+		printk(KERN_INFO DRV_NAME
+		       ": %s: Setting ad_select to %s (%d).\n",
+		       bond->dev->name, ad_select_tbl[new_value].modename,
+		       new_value);
+	} else {
+		printk(KERN_ERR DRV_NAME
+		       ": %s: Ignoring invalid ad_select value %.*s.\n",
+		       bond->dev->name, (int)strlen(buf) - 1, buf);
+		ret = -EINVAL;
+	}
+out:
+	return ret;
+}
+
+static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR, bonding_show_ad_select, bonding_store_ad_select);
+
 /*
  * Show and set the number of grat ARP to send after a failover event.
  */
@@ -1459,6 +1507,7 @@ static struct attribute *per_bond_attrs[] = {
 	&dev_attr_downdelay.attr,
 	&dev_attr_updelay.attr,
 	&dev_attr_lacp_rate.attr,
+	&dev_attr_ad_select.attr,
 	&dev_attr_xmit_hash_policy.attr,
 	&dev_attr_num_grat_arp.attr,
 	&dev_attr_num_unsol_na.attr,

drivers/net/bonding/bonding.h

@@ -23,8 +23,8 @@
 #include "bond_3ad.h"
 #include "bond_alb.h"
 
-#define DRV_VERSION	"3.4.0"
-#define DRV_RELDATE	"October 7, 2008"
+#define DRV_VERSION	"3.5.0"
+#define DRV_RELDATE	"November 4, 2008"
 #define DRV_NAME	"bonding"
 #define DRV_DESCRIPTION	"Ethernet Channel Bonding Driver"
 
@@ -137,6 +137,7 @@ struct bond_params {
 	int updelay;
 	int downdelay;
 	int lacp_fast;
+	int ad_select;
 	char primary[IFNAMSIZ];
 	__be32 arp_targets[BOND_MAX_ARP_TARGETS];
 };