diff mbox

[net-next-2.6] bonding: introduce primary_passive option

Message ID 20090901174234.GA3209@psychotron.redhat.com
State Changes Requested, archived
Delegated to: David Miller
Headers show

Commit Message

Jiri Pirko Sept. 1, 2009, 5:42 p.m. UTC
(updated)

In some cases there is not desirable to switch back to primary interface when
it's link recovers and rather stay with currently active one. We need to avoid
packetloss as much as we can in some cases. This is solved by introducing
primary_passive option. Note that enslaved primary slave is set as current
active no matter what.

This patch depends on the following one:
[net-next-2.6] bonding: make ab_arp select active slaves as other modes
http://patchwork.ozlabs.org/patch/32684/

Signed-off-by: Jiri Pirko <jpirko@redhat.com>

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Nicolas de Pesloüan Sept. 3, 2009, 7:56 p.m. UTC | #1
Jiri Pirko wrote:
> (updated)
> 
> In some cases there is not desirable to switch back to primary interface when
> it's link recovers and rather stay with currently active one. We need to avoid
> packetloss as much as we can in some cases. This is solved by introducing
> primary_passive option. Note that enslaved primary slave is set as current
> active no matter what.
> 
> This patch depends on the following one:
> [net-next-2.6] bonding: make ab_arp select active slaves as other modes
> http://patchwork.ozlabs.org/patch/32684/
> 
> Signed-off-by: Jiri Pirko <jpirko@redhat.com>
> 
> diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
> index d5181ce..e70fa8e 100644
> --- a/Documentation/networking/bonding.txt
> +++ b/Documentation/networking/bonding.txt
> @@ -614,6 +614,17 @@ primary
>  
>  	The primary option is only valid for active-backup mode.
>  
> +primary_passive
> +
> +	Specifies the behaviour of the primary slave in case of
> +	it's link recovery has been detected. By default (value 0) the
> +	primary slave is set as active slave immediately after the link
> +	recovery. If the value is 1 or 2 then current active slave doesn't
> +	change as long as it's link status doesn't change. This prevents
> +	the bonding device from flip-flopping. Plus if the value is 1 this
> +	behaviour happens only if the speed and duplex of primary slave is
> +	higher. It the value is 2 then it happens everytime.
> +

May I suggest the following option name and description instead ?

-----

primary_return

	Specifies the behavior of the current active slave when the primary was
	down and comes back up. This option is designed to prevent flip-flopping
	between the primary slave and other slaves. The possible values and
	their respective effects are:

	alway or 0 (default)

		The primary slave becomes the active slave whenever it comes
		back up.

	better or 1

		The primary slave becomes the active slave when it comes back
		up, if the speed and duplex of the primary slave is better
		than the speed and duplex of the current active slave.

	failure_only or 2

		The primary slave becomes the active slave only if the current
		active slave fails and the primary slave is up.

	When no slave are active, if the primary comes back up, it becomes the
	active slave, regardless of the value of primary_return.

-----

Then, to allow those logical names, I suggest you use the bond_parse_parm() 
function and the following constants and struct, to parse module params and 
sysfs configuration.

enum {
         BOND_PRI_RETURN_ALWAYS = 0,
         BOND_PRI_RETURN_BETTER = 1,
         BOND_PRI_RETURN_FAILURE_ONLY = 2,
};

const struct bond_parm_tbl bond_pri_return_tbl[] = {
{       "always",         BOND_PRI_RETURN_ALWAYS},
{       "better",         BOND_PRI_RETURN_BETTER},
{       "failure_only",   BOND_PRI_RETURN_FAILURE_ONLY},
{       NULL,           -1},
};

	Nicolas.

>  updelay
>  
>  	Specifies the time, in milliseconds, to wait before enabling a
> diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
> index 699bfdd..65066c1 100644
> --- a/drivers/net/bonding/bond_main.c
> +++ b/drivers/net/bonding/bond_main.c
> @@ -94,6 +94,7 @@ static int downdelay;
>  static int use_carrier	= 1;
>  static char *mode;
>  static char *primary;
> +static int primary_passive;
>  static char *lacp_rate;
>  static char *ad_select;
>  static char *xmit_hash_policy;
> @@ -126,6 +127,9 @@ MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
>  		       "6 for balance-alb");
>  module_param(primary, charp, 0);
>  MODULE_PARM_DESC(primary, "Primary network device to use");
> +module_param(primary_passive, int, 0);
> +MODULE_PARM_DESC(primary_passive, "Do not set primary slave active once it comes up; "
> +			       "0 for off (default), 1 for on only if speed of primary is not higher, 2 for on");
>  module_param(lacp_rate, charp, 0);
>  MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
>  			    "(slow/fast)");
> @@ -1070,6 +1074,25 @@ out:
>  
>  }
>  
> +static bool bond_should_loose_active(struct bonding *bond)
> +{
> +	struct slave *prim = bond->primary_slave;
> +	struct slave *curr = bond->curr_active_slave;
> +
> +	if (!prim || !curr || curr->link != BOND_LINK_UP)
> +		return true;
> +	if (bond->force_primary) {
> +		bond->force_primary = false;
> +		return true;
> +	}
> +	if (bond->params.primary_passive == 1 &&
> +	    (prim->speed < curr->speed ||
> +	     (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
> +		return false;
> +	if (bond->params.primary_passive == 2)
> +		return false;
> +	return true;
> +}
>  
>  /**
>   * find_best_interface - select the best available slave to be the active one
> @@ -1094,7 +1117,8 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
>  	}
>  
>  	if ((bond->primary_slave) &&
> -	    bond->primary_slave->link == BOND_LINK_UP) {
> +	    bond->primary_slave->link == BOND_LINK_UP &&
> +	    bond_should_loose_active(bond)) {
>  		new_active = bond->primary_slave;
>  	}
>  
> @@ -1675,8 +1699,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
>  
>  	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
>  		/* if there is a primary slave, remember it */
> -		if (strcmp(bond->params.primary, new_slave->dev->name) == 0)
> +		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
>  			bond->primary_slave = new_slave;
> +			bond->force_primary = true;
> +		}
>  	}
>  
>  	write_lock_bh(&bond->curr_slave_lock);
> @@ -4942,6 +4968,18 @@ static int bond_check_params(struct bond_params *params)
>  		primary = NULL;
>  	}
>  
> +	if (primary) {
> +		if ((primary_passive != 0) && (primary_passive != 1) &&
> +		    (primary_passive != 2)) {
> +			pr_warning(DRV_NAME
> +				   ": Warning: primary_passive module parameter "
> +				   "(%d), not of valid value (0/1/2), so it was "
> +				   "set to 0\n",
> +				   primary_passive);
> +			primary_passive = 0;
> +		}
> +	}
> +
>  	if (fail_over_mac) {
>  		fail_over_mac_value = bond_parse_parm(fail_over_mac,
>  						      fail_over_mac_tbl);
> @@ -4973,6 +5011,7 @@ static int bond_check_params(struct bond_params *params)
>  	params->use_carrier = use_carrier;
>  	params->lacp_fast = lacp_fast;
>  	params->primary[0] = 0;
> +	params->primary_passive = primary_passive;
>  	params->fail_over_mac = fail_over_mac_value;
>  
>  	if (primary) {
> diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
> index 6044e12..e813d48 100644
> --- a/drivers/net/bonding/bond_sysfs.c
> +++ b/drivers/net/bonding/bond_sysfs.c
> @@ -1212,6 +1212,59 @@ static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR,
>  		   bonding_show_primary, bonding_store_primary);
>  
>  /*
> + * Show and set the primary_passive flag.
> + */
> +static ssize_t bonding_show_primary_passive(struct device *d,
> +					    struct device_attribute *attr,
> +					    char *buf)
> +{
> +	struct bonding *bond = to_bond(d);
> +
> +	return sprintf(buf, "%d\n", bond->params.primary_passive);
> +}
> +
> +static ssize_t bonding_store_primary_passive(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 (!rtnl_trylock())
> +		return restart_syscall();
> +
> +	if (sscanf(buf, "%d", &new_value) != 1) {
> +		pr_err(DRV_NAME
> +		       ": %s: no primary_passive value specified.\n",
> +		       bond->dev->name);
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +	if (new_value == 0 || new_value == 1 || new_value == 2) {
> +		bond->params.primary_passive = new_value;
> +		pr_info(DRV_NAME ": %s: Setting primary_passive to %d.\n",
> +		       bond->dev->name, new_value);
> +		if (new_value == 0 || new_value == 1) {
> +			bond->force_primary = true;
> +			read_lock(&bond->lock);
> +			write_lock_bh(&bond->curr_slave_lock);
> +			bond_select_active_slave(bond);
> +			write_unlock_bh(&bond->curr_slave_lock);
> +			read_unlock(&bond->lock);
> +		}
> +	} else {
> +		pr_info(DRV_NAME
> +		       ": %s: Ignoring invalid primary_passive value %d.\n",
> +		       bond->dev->name, new_value);
> +	}
> +out:
> +	rtnl_unlock();
> +	return count;
> +}
> +static DEVICE_ATTR(primary_passive, S_IRUGO | S_IWUSR,
> +		   bonding_show_primary_passive, bonding_store_primary_passive);
> +
> +/*
>   * Show and set the use_carrier flag.
>   */
>  static ssize_t bonding_show_carrier(struct device *d,
> @@ -1500,6 +1553,7 @@ static struct attribute *per_bond_attrs[] = {
>  	&dev_attr_num_unsol_na.attr,
>  	&dev_attr_miimon.attr,
>  	&dev_attr_primary.attr,
> +	&dev_attr_primary_passive.attr,
>  	&dev_attr_use_carrier.attr,
>  	&dev_attr_active_slave.attr,
>  	&dev_attr_mii_status.attr,
> diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
> index 6290a50..b6287e0 100644
> --- a/drivers/net/bonding/bonding.h
> +++ b/drivers/net/bonding/bonding.h
> @@ -131,6 +131,7 @@ struct bond_params {
>  	int lacp_fast;
>  	int ad_select;
>  	char primary[IFNAMSIZ];
> +	int primary_passive;
>  	__be32 arp_targets[BOND_MAX_ARP_TARGETS];
>  };
>  
> @@ -190,6 +191,7 @@ struct bonding {
>  	struct   slave *curr_active_slave;
>  	struct   slave *current_arp_slave;
>  	struct   slave *primary_slave;
> +	bool     force_primary;
>  	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
>  	rwlock_t lock;
>  	rwlock_t curr_slave_lock;
> 

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Jiri Pirko Sept. 7, 2009, 12:50 p.m. UTC | #2
Thu, Sep 03, 2009 at 09:56:21PM CEST, nicolas.2p.debian@free.fr wrote:
> Jiri Pirko wrote:
>> (updated)
>>
>> In some cases there is not desirable to switch back to primary interface when
>> it's link recovers and rather stay with currently active one. We need to avoid
>> packetloss as much as we can in some cases. This is solved by introducing
>> primary_passive option. Note that enslaved primary slave is set as current
>> active no matter what.
>>
>> This patch depends on the following one:
>> [net-next-2.6] bonding: make ab_arp select active slaves as other modes
>> http://patchwork.ozlabs.org/patch/32684/
>>
>> Signed-off-by: Jiri Pirko <jpirko@redhat.com>
>>
>> diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
>> index d5181ce..e70fa8e 100644
>> --- a/Documentation/networking/bonding.txt
>> +++ b/Documentation/networking/bonding.txt
>> @@ -614,6 +614,17 @@ primary
>>   	The primary option is only valid for active-backup mode.
>>  +primary_passive
>> +
>> +	Specifies the behaviour of the primary slave in case of
>> +	it's link recovery has been detected. By default (value 0) the
>> +	primary slave is set as active slave immediately after the link
>> +	recovery. If the value is 1 or 2 then current active slave doesn't
>> +	change as long as it's link status doesn't change. This prevents
>> +	the bonding device from flip-flopping. Plus if the value is 1 this
>> +	behaviour happens only if the speed and duplex of primary slave is
>> +	higher. It the value is 2 then it happens everytime.
>> +
>
> May I suggest the following option name and description instead ?
>
> -----
>
> primary_return
>
> 	Specifies the behavior of the current active slave when the primary was
> 	down and comes back up. This option is designed to prevent flip-flopping
> 	between the primary slave and other slaves. The possible values and
> 	their respective effects are:
>
> 	alway or 0 (default)
>
> 		The primary slave becomes the active slave whenever it comes
> 		back up.
>
> 	better or 1
>
> 		The primary slave becomes the active slave when it comes back
> 		up, if the speed and duplex of the primary slave is better
> 		than the speed and duplex of the current active slave.
>
> 	failure_only or 2
>
> 		The primary slave becomes the active slave only if the current
> 		active slave fails and the primary slave is up.
>
> 	When no slave are active, if the primary comes back up, it becomes the
> 	active slave, regardless of the value of primary_return.
>
> -----
>
> Then, to allow those logical names, I suggest you use the 
> bond_parse_parm() function and the following constants and struct, to 
> parse module params and sysfs configuration.
>
> enum {
>         BOND_PRI_RETURN_ALWAYS = 0,
>         BOND_PRI_RETURN_BETTER = 1,
>         BOND_PRI_RETURN_FAILURE_ONLY = 2,
> };
>
> const struct bond_parm_tbl bond_pri_return_tbl[] = {
> {       "always",         BOND_PRI_RETURN_ALWAYS},
> {       "better",         BOND_PRI_RETURN_BETTER},
> {       "failure_only",   BOND_PRI_RETURN_FAILURE_ONLY},
> {       NULL,           -1},
> };
>
> 	Nicolas.

Ok, I like this, but I would stay rather with Jay's suggestion to call this
option primary_passive. Seems more accurate to me.

I'm going to repost soon.

Jirka
>
>>  updelay
>>   	Specifies the time, in milliseconds, to wait before enabling a
>> diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
>> index 699bfdd..65066c1 100644
>> --- a/drivers/net/bonding/bond_main.c
>> +++ b/drivers/net/bonding/bond_main.c
>> @@ -94,6 +94,7 @@ static int downdelay;
>>  static int use_carrier	= 1;
>>  static char *mode;
>>  static char *primary;
>> +static int primary_passive;
>>  static char *lacp_rate;
>>  static char *ad_select;
>>  static char *xmit_hash_policy;
>> @@ -126,6 +127,9 @@ MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
>>  		       "6 for balance-alb");
>>  module_param(primary, charp, 0);
>>  MODULE_PARM_DESC(primary, "Primary network device to use");
>> +module_param(primary_passive, int, 0);
>> +MODULE_PARM_DESC(primary_passive, "Do not set primary slave active once it comes up; "
>> +			       "0 for off (default), 1 for on only if speed of primary is not higher, 2 for on");
>>  module_param(lacp_rate, charp, 0);
>>  MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
>>  			    "(slow/fast)");
>> @@ -1070,6 +1074,25 @@ out:
>>   }
>>  +static bool bond_should_loose_active(struct bonding *bond)
>> +{
>> +	struct slave *prim = bond->primary_slave;
>> +	struct slave *curr = bond->curr_active_slave;
>> +
>> +	if (!prim || !curr || curr->link != BOND_LINK_UP)
>> +		return true;
>> +	if (bond->force_primary) {
>> +		bond->force_primary = false;
>> +		return true;
>> +	}
>> +	if (bond->params.primary_passive == 1 &&
>> +	    (prim->speed < curr->speed ||
>> +	     (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
>> +		return false;
>> +	if (bond->params.primary_passive == 2)
>> +		return false;
>> +	return true;
>> +}
>>   /**
>>   * find_best_interface - select the best available slave to be the active one
>> @@ -1094,7 +1117,8 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
>>  	}
>>   	if ((bond->primary_slave) &&
>> -	    bond->primary_slave->link == BOND_LINK_UP) {
>> +	    bond->primary_slave->link == BOND_LINK_UP &&
>> +	    bond_should_loose_active(bond)) {
>>  		new_active = bond->primary_slave;
>>  	}
>>  @@ -1675,8 +1699,10 @@ int bond_enslave(struct net_device *bond_dev, 
>> struct net_device *slave_dev)
>>   	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
>>  		/* if there is a primary slave, remember it */
>> -		if (strcmp(bond->params.primary, new_slave->dev->name) == 0)
>> +		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
>>  			bond->primary_slave = new_slave;
>> +			bond->force_primary = true;
>> +		}
>>  	}
>>   	write_lock_bh(&bond->curr_slave_lock);
>> @@ -4942,6 +4968,18 @@ static int bond_check_params(struct bond_params *params)
>>  		primary = NULL;
>>  	}
>>  +	if (primary) {
>> +		if ((primary_passive != 0) && (primary_passive != 1) &&
>> +		    (primary_passive != 2)) {
>> +			pr_warning(DRV_NAME
>> +				   ": Warning: primary_passive module parameter "
>> +				   "(%d), not of valid value (0/1/2), so it was "
>> +				   "set to 0\n",
>> +				   primary_passive);
>> +			primary_passive = 0;
>> +		}
>> +	}
>> +
>>  	if (fail_over_mac) {
>>  		fail_over_mac_value = bond_parse_parm(fail_over_mac,
>>  						      fail_over_mac_tbl);
>> @@ -4973,6 +5011,7 @@ static int bond_check_params(struct bond_params *params)
>>  	params->use_carrier = use_carrier;
>>  	params->lacp_fast = lacp_fast;
>>  	params->primary[0] = 0;
>> +	params->primary_passive = primary_passive;
>>  	params->fail_over_mac = fail_over_mac_value;
>>   	if (primary) {
>> diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
>> index 6044e12..e813d48 100644
>> --- a/drivers/net/bonding/bond_sysfs.c
>> +++ b/drivers/net/bonding/bond_sysfs.c
>> @@ -1212,6 +1212,59 @@ static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR,
>>  		   bonding_show_primary, bonding_store_primary);
>>   /*
>> + * Show and set the primary_passive flag.
>> + */
>> +static ssize_t bonding_show_primary_passive(struct device *d,
>> +					    struct device_attribute *attr,
>> +					    char *buf)
>> +{
>> +	struct bonding *bond = to_bond(d);
>> +
>> +	return sprintf(buf, "%d\n", bond->params.primary_passive);
>> +}
>> +
>> +static ssize_t bonding_store_primary_passive(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 (!rtnl_trylock())
>> +		return restart_syscall();
>> +
>> +	if (sscanf(buf, "%d", &new_value) != 1) {
>> +		pr_err(DRV_NAME
>> +		       ": %s: no primary_passive value specified.\n",
>> +		       bond->dev->name);
>> +		ret = -EINVAL;
>> +		goto out;
>> +	}
>> +	if (new_value == 0 || new_value == 1 || new_value == 2) {
>> +		bond->params.primary_passive = new_value;
>> +		pr_info(DRV_NAME ": %s: Setting primary_passive to %d.\n",
>> +		       bond->dev->name, new_value);
>> +		if (new_value == 0 || new_value == 1) {
>> +			bond->force_primary = true;
>> +			read_lock(&bond->lock);
>> +			write_lock_bh(&bond->curr_slave_lock);
>> +			bond_select_active_slave(bond);
>> +			write_unlock_bh(&bond->curr_slave_lock);
>> +			read_unlock(&bond->lock);
>> +		}
>> +	} else {
>> +		pr_info(DRV_NAME
>> +		       ": %s: Ignoring invalid primary_passive value %d.\n",
>> +		       bond->dev->name, new_value);
>> +	}
>> +out:
>> +	rtnl_unlock();
>> +	return count;
>> +}
>> +static DEVICE_ATTR(primary_passive, S_IRUGO | S_IWUSR,
>> +		   bonding_show_primary_passive, bonding_store_primary_passive);
>> +
>> +/*
>>   * Show and set the use_carrier flag.
>>   */
>>  static ssize_t bonding_show_carrier(struct device *d,
>> @@ -1500,6 +1553,7 @@ static struct attribute *per_bond_attrs[] = {
>>  	&dev_attr_num_unsol_na.attr,
>>  	&dev_attr_miimon.attr,
>>  	&dev_attr_primary.attr,
>> +	&dev_attr_primary_passive.attr,
>>  	&dev_attr_use_carrier.attr,
>>  	&dev_attr_active_slave.attr,
>>  	&dev_attr_mii_status.attr,
>> diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
>> index 6290a50..b6287e0 100644
>> --- a/drivers/net/bonding/bonding.h
>> +++ b/drivers/net/bonding/bonding.h
>> @@ -131,6 +131,7 @@ struct bond_params {
>>  	int lacp_fast;
>>  	int ad_select;
>>  	char primary[IFNAMSIZ];
>> +	int primary_passive;
>>  	__be32 arp_targets[BOND_MAX_ARP_TARGETS];
>>  };
>>  @@ -190,6 +191,7 @@ struct bonding {
>>  	struct   slave *curr_active_slave;
>>  	struct   slave *current_arp_slave;
>>  	struct   slave *primary_slave;
>> +	bool     force_primary;
>>  	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
>>  	rwlock_t lock;
>>  	rwlock_t curr_slave_lock;
>>
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index d5181ce..e70fa8e 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -614,6 +614,17 @@  primary
 
 	The primary option is only valid for active-backup mode.
 
+primary_passive
+
+	Specifies the behaviour of the primary slave in case of
+	it's link recovery has been detected. By default (value 0) the
+	primary slave is set as active slave immediately after the link
+	recovery. If the value is 1 or 2 then current active slave doesn't
+	change as long as it's link status doesn't change. This prevents
+	the bonding device from flip-flopping. Plus if the value is 1 this
+	behaviour happens only if the speed and duplex of primary slave is
+	higher. It the value is 2 then it happens everytime.
+
 updelay
 
 	Specifies the time, in milliseconds, to wait before enabling a
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 699bfdd..65066c1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -94,6 +94,7 @@  static int downdelay;
 static int use_carrier	= 1;
 static char *mode;
 static char *primary;
+static int primary_passive;
 static char *lacp_rate;
 static char *ad_select;
 static char *xmit_hash_policy;
@@ -126,6 +127,9 @@  MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
 		       "6 for balance-alb");
 module_param(primary, charp, 0);
 MODULE_PARM_DESC(primary, "Primary network device to use");
+module_param(primary_passive, int, 0);
+MODULE_PARM_DESC(primary_passive, "Do not set primary slave active once it comes up; "
+			       "0 for off (default), 1 for on only if speed of primary is not higher, 2 for on");
 module_param(lacp_rate, charp, 0);
 MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
 			    "(slow/fast)");
@@ -1070,6 +1074,25 @@  out:
 
 }
 
+static bool bond_should_loose_active(struct bonding *bond)
+{
+	struct slave *prim = bond->primary_slave;
+	struct slave *curr = bond->curr_active_slave;
+
+	if (!prim || !curr || curr->link != BOND_LINK_UP)
+		return true;
+	if (bond->force_primary) {
+		bond->force_primary = false;
+		return true;
+	}
+	if (bond->params.primary_passive == 1 &&
+	    (prim->speed < curr->speed ||
+	     (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
+		return false;
+	if (bond->params.primary_passive == 2)
+		return false;
+	return true;
+}
 
 /**
  * find_best_interface - select the best available slave to be the active one
@@ -1094,7 +1117,8 @@  static struct slave *bond_find_best_slave(struct bonding *bond)
 	}
 
 	if ((bond->primary_slave) &&
-	    bond->primary_slave->link == BOND_LINK_UP) {
+	    bond->primary_slave->link == BOND_LINK_UP &&
+	    bond_should_loose_active(bond)) {
 		new_active = bond->primary_slave;
 	}
 
@@ -1675,8 +1699,10 @@  int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
 		/* if there is a primary slave, remember it */
-		if (strcmp(bond->params.primary, new_slave->dev->name) == 0)
+		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
 			bond->primary_slave = new_slave;
+			bond->force_primary = true;
+		}
 	}
 
 	write_lock_bh(&bond->curr_slave_lock);
@@ -4942,6 +4968,18 @@  static int bond_check_params(struct bond_params *params)
 		primary = NULL;
 	}
 
+	if (primary) {
+		if ((primary_passive != 0) && (primary_passive != 1) &&
+		    (primary_passive != 2)) {
+			pr_warning(DRV_NAME
+				   ": Warning: primary_passive module parameter "
+				   "(%d), not of valid value (0/1/2), so it was "
+				   "set to 0\n",
+				   primary_passive);
+			primary_passive = 0;
+		}
+	}
+
 	if (fail_over_mac) {
 		fail_over_mac_value = bond_parse_parm(fail_over_mac,
 						      fail_over_mac_tbl);
@@ -4973,6 +5011,7 @@  static int bond_check_params(struct bond_params *params)
 	params->use_carrier = use_carrier;
 	params->lacp_fast = lacp_fast;
 	params->primary[0] = 0;
+	params->primary_passive = primary_passive;
 	params->fail_over_mac = fail_over_mac_value;
 
 	if (primary) {
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 6044e12..e813d48 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1212,6 +1212,59 @@  static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR,
 		   bonding_show_primary, bonding_store_primary);
 
 /*
+ * Show and set the primary_passive flag.
+ */
+static ssize_t bonding_show_primary_passive(struct device *d,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct bonding *bond = to_bond(d);
+
+	return sprintf(buf, "%d\n", bond->params.primary_passive);
+}
+
+static ssize_t bonding_store_primary_passive(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 (!rtnl_trylock())
+		return restart_syscall();
+
+	if (sscanf(buf, "%d", &new_value) != 1) {
+		pr_err(DRV_NAME
+		       ": %s: no primary_passive value specified.\n",
+		       bond->dev->name);
+		ret = -EINVAL;
+		goto out;
+	}
+	if (new_value == 0 || new_value == 1 || new_value == 2) {
+		bond->params.primary_passive = new_value;
+		pr_info(DRV_NAME ": %s: Setting primary_passive to %d.\n",
+		       bond->dev->name, new_value);
+		if (new_value == 0 || new_value == 1) {
+			bond->force_primary = true;
+			read_lock(&bond->lock);
+			write_lock_bh(&bond->curr_slave_lock);
+			bond_select_active_slave(bond);
+			write_unlock_bh(&bond->curr_slave_lock);
+			read_unlock(&bond->lock);
+		}
+	} else {
+		pr_info(DRV_NAME
+		       ": %s: Ignoring invalid primary_passive value %d.\n",
+		       bond->dev->name, new_value);
+	}
+out:
+	rtnl_unlock();
+	return count;
+}
+static DEVICE_ATTR(primary_passive, S_IRUGO | S_IWUSR,
+		   bonding_show_primary_passive, bonding_store_primary_passive);
+
+/*
  * Show and set the use_carrier flag.
  */
 static ssize_t bonding_show_carrier(struct device *d,
@@ -1500,6 +1553,7 @@  static struct attribute *per_bond_attrs[] = {
 	&dev_attr_num_unsol_na.attr,
 	&dev_attr_miimon.attr,
 	&dev_attr_primary.attr,
+	&dev_attr_primary_passive.attr,
 	&dev_attr_use_carrier.attr,
 	&dev_attr_active_slave.attr,
 	&dev_attr_mii_status.attr,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 6290a50..b6287e0 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -131,6 +131,7 @@  struct bond_params {
 	int lacp_fast;
 	int ad_select;
 	char primary[IFNAMSIZ];
+	int primary_passive;
 	__be32 arp_targets[BOND_MAX_ARP_TARGETS];
 };
 
@@ -190,6 +191,7 @@  struct bonding {
 	struct   slave *curr_active_slave;
 	struct   slave *current_arp_slave;
 	struct   slave *primary_slave;
+	bool     force_primary;
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	rwlock_t lock;
 	rwlock_t curr_slave_lock;