Commit 5a63f77a authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'bonding-performance-and-reliability' 



Debabrata Banerjee says:

====================
bonding: performance and reliability

Series of fixes to how rlb updates are handled, code cleanup, allowing
higher performance tx hashing in balance-alb mode, and reliability of
link up/down monitoring.

v2: refactor bond_is_nondyn_tlb with inline fn, update log comment to
point out that multicast addresses will not get rlb updates.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 967c2993 1386c36b

Documentation/networking/bonding.txt

+2 −2
Original line number Diff line number Diff line
@@ -828,8 +828,8 @@ use_carrier 
	MII / ETHTOOL ioctl method to determine the link state.



	A value of 1 enables the use of netif_carrier_ok(), a value of

	0 will use the deprecated MII / ETHTOOL ioctls.  The default

	value is 1.

	0 will use the deprecated MII / ETHTOOL ioctls. A value of 2

	will check both.  The default value is 1.



xmit_hash_policy

drivers/net/bonding/bond_alb.c

+31 −19
Original line number Diff line number Diff line
@@ -40,11 +40,6 @@ 
#include <net/bonding.h>

#include <net/bond_alb.h>







static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = {

	0xff, 0xff, 0xff, 0xff, 0xff, 0xff

};

static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {

	0x33, 0x33, 0x00, 0x00, 0x00, 0x01

};
@@ -420,8 +415,7 @@ static void rlb_clear_slave(struct bonding *bond, struct slave *slave) 


			if (assigned_slave) {

				rx_hash_table[index].slave = assigned_slave;

				if (!ether_addr_equal_64bits(rx_hash_table[index].mac_dst,

							     mac_bcast)) {

				if (is_valid_ether_addr(rx_hash_table[index].mac_dst)) {

					bond_info->rx_hashtbl[index].ntt = 1;

					bond_info->rx_ntt = 1;

					/* A slave has been removed from the
@@ -524,7 +518,7 @@ static void rlb_req_update_slave_clients(struct bonding *bond, struct slave *sla 
		client_info = &(bond_info->rx_hashtbl[hash_index]);



		if ((client_info->slave == slave) &&

		    !ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {

		    is_valid_ether_addr(client_info->mac_dst)) {

			client_info->ntt = 1;

			ntt = 1;

		}
@@ -565,7 +559,7 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip) 
		if ((client_info->ip_src == src_ip) &&

		    !ether_addr_equal_64bits(client_info->slave->dev->dev_addr,

					     bond->dev->dev_addr) &&

		    !ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {

		    is_valid_ether_addr(client_info->mac_dst)) {

			client_info->ntt = 1;

			bond_info->rx_ntt = 1;

		}
@@ -593,7 +587,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon 
		if ((client_info->ip_src == arp->ip_src) &&

		    (client_info->ip_dst == arp->ip_dst)) {

			/* the entry is already assigned to this client */

			if (!ether_addr_equal_64bits(arp->mac_dst, mac_bcast)) {

			if (!is_broadcast_ether_addr(arp->mac_dst)) {

				/* update mac address from arp */

				ether_addr_copy(client_info->mac_dst, arp->mac_dst);

			}
@@ -641,7 +635,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon 
		ether_addr_copy(client_info->mac_src, arp->mac_src);

		client_info->slave = assigned_slave;



		if (!ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {

		if (is_valid_ether_addr(client_info->mac_dst)) {

			client_info->ntt = 1;

			bond->alb_info.rx_ntt = 1;

		} else {
@@ -733,10 +727,12 @@ static void rlb_rebalance(struct bonding *bond) 
		assigned_slave = __rlb_next_rx_slave(bond);

		if (assigned_slave && (client_info->slave != assigned_slave)) {

			client_info->slave = assigned_slave;

			if (!is_zero_ether_addr(client_info->mac_dst)) {

				client_info->ntt = 1;

				ntt = 1;

			}

		}

	}



	/* update the team's flag only after the whole iteration */

	if (ntt)
@@ -1412,9 +1408,9 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) 
	case ETH_P_IP: {

		const struct iphdr *iph = ip_hdr(skb);



		if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast) ||

		    (iph->daddr == ip_bcast) ||

		    (iph->protocol == IPPROTO_IGMP)) {

		if (is_broadcast_ether_addr(eth_data->h_dest) ||

		    iph->daddr == ip_bcast ||

		    iph->protocol == IPPROTO_IGMP) {

			do_tx_balance = false;

			break;

		}
@@ -1426,7 +1422,7 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) 
		/* IPv6 doesn't really use broadcast mac address, but leave

		 * that here just in case.

		 */

		if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast)) {

		if (is_broadcast_ether_addr(eth_data->h_dest)) {

			do_tx_balance = false;

			break;

		}
@@ -1482,8 +1478,24 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) 
	}



	if (do_tx_balance) {

		if (bond->params.tlb_dynamic_lb) {

			hash_index = _simple_hash(hash_start, hash_size);

			tx_slave = tlb_choose_channel(bond, hash_index, skb->len);

		} else {

			/*

			 * do_tx_balance means we are free to select the tx_slave

			 * So we do exactly what tlb would do for hash selection

			 */



			struct bond_up_slave *slaves;

			unsigned int count;



			slaves = rcu_dereference(bond->slave_arr);

			count = slaves ? READ_ONCE(slaves->count) : 0;

			if (likely(count))

				tx_slave = slaves->arr[bond_xmit_hash(bond, skb) %

						       count];

		}

	}



	return bond_do_alb_xmit(skb, bond, tx_slave);

drivers/net/bonding/bond_main.c

+23 −14
Original line number Diff line number Diff line
@@ -132,7 +132,7 @@ MODULE_PARM_DESC(downdelay, "Delay before considering link down, " 
			    "in milliseconds");

module_param(use_carrier, int, 0);

MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "

			      "0 for off, 1 for on (default)");

			      "0 for off, 1 for on (default), 2 for carrier then legacy checks");

module_param(mode, charp, 0);

MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, "

		       "1 for active-backup, 2 for balance-xor, "
@@ -159,7 +159,7 @@ module_param(min_links, int, 0); 
MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier");



module_param(xmit_hash_policy, charp, 0);

MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; "

MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; "

				   "0 for layer 2 (default), 1 for layer 3+4, "

				   "2 for layer 2+3, 3 for encap layer 2+3, "

				   "4 for encap layer 3+4");
@@ -434,12 +434,16 @@ static int bond_check_dev_link(struct bonding *bond, 
	int (*ioctl)(struct net_device *, struct ifreq *, int);

	struct ifreq ifr;

	struct mii_ioctl_data *mii;

	bool carrier = true;



	if (!reporting && !netif_running(slave_dev))

		return 0;



	if (bond->params.use_carrier)

		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;

		carrier = netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;



	if (!carrier)

		return carrier;



	/* Try to get link status using Ethtool first. */

	if (slave_dev->ethtool_ops->get_link)
@@ -1735,7 +1739,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, 
		unblock_netpoll_tx();

	}



	if (bond_mode_uses_xmit_hash(bond))

	if (bond_mode_can_use_xmit_hash(bond))

		bond_update_slave_arr(bond, NULL);



	bond->nest_level = dev_get_nest_level(bond_dev);
@@ -1870,7 +1874,7 @@ static int __bond_release_one(struct net_device *bond_dev, 
	if (BOND_MODE(bond) == BOND_MODE_8023AD)

		bond_3ad_unbind_slave(slave);



	if (bond_mode_uses_xmit_hash(bond))

	if (bond_mode_can_use_xmit_hash(bond))

		bond_update_slave_arr(bond, slave);



	netdev_info(bond_dev, "Releasing %s interface %s\n",
@@ -3102,7 +3106,7 @@ static int bond_slave_netdev_event(unsigned long event, 
		 * events. If these (miimon/arpmon) parameters are configured

		 * then array gets refreshed twice and that should be fine!

		 */

		if (bond_mode_uses_xmit_hash(bond))

		if (bond_mode_can_use_xmit_hash(bond))

			bond_update_slave_arr(bond, NULL);

		break;

	case NETDEV_CHANGEMTU:
@@ -3322,7 +3326,7 @@ static int bond_open(struct net_device *bond_dev) 
		 */

		if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB)))

			return -ENOMEM;

		if (bond->params.tlb_dynamic_lb)

		if (bond->params.tlb_dynamic_lb || BOND_MODE(bond) == BOND_MODE_ALB)

			queue_delayed_work(bond->wq, &bond->alb_work, 0);

	}
@@ -3341,7 +3345,7 @@ static int bond_open(struct net_device *bond_dev) 
		bond_3ad_initiate_agg_selection(bond, 1);

	}



	if (bond_mode_uses_xmit_hash(bond))

	if (bond_mode_can_use_xmit_hash(bond))

		bond_update_slave_arr(bond, NULL);



	return 0;
@@ -3894,7 +3898,7 @@ err: 
 * to determine the slave interface -

 * (a) BOND_MODE_8023AD

 * (b) BOND_MODE_XOR

 * (c) BOND_MODE_TLB && tlb_dynamic_lb == 0

 * (c) (BOND_MODE_TLB || BOND_MODE_ALB) && tlb_dynamic_lb == 0

 *

 * The caller is expected to hold RTNL only and NO other lock!

 */
@@ -3947,6 +3951,11 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) 
			continue;

		if (skipslave == slave)

			continue;



		netdev_dbg(bond->dev,

			   "Adding slave dev %s to tx hash array[%d]\n",

			   slave->dev->name, new_arr->count);



		new_arr->arr[new_arr->count++] = slave;

	}
@@ -4324,9 +4333,9 @@ static int bond_check_params(struct bond_params *params) 
	}



	if (xmit_hash_policy) {

		if ((bond_mode != BOND_MODE_XOR) &&

		    (bond_mode != BOND_MODE_8023AD) &&

		    (bond_mode != BOND_MODE_TLB)) {

		if (bond_mode == BOND_MODE_ROUNDROBIN ||

		    bond_mode == BOND_MODE_ACTIVEBACKUP ||

		    bond_mode == BOND_MODE_BROADCAST) {

			pr_info("xmit_hash_policy param is irrelevant in mode %s\n",

				bond_mode_name(bond_mode));

		} else {
@@ -4398,8 +4407,8 @@ static int bond_check_params(struct bond_params *params) 
		downdelay = 0;

	}



	if ((use_carrier != 0) && (use_carrier != 1)) {

		pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n",

	if (use_carrier < 0 || use_carrier > 2) {

		pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0-2), so it was set to 1\n",

			use_carrier);

		use_carrier = 1;

	}

drivers/net/bonding/bond_options.c

+5 −4
Original line number Diff line number Diff line
@@ -166,6 +166,7 @@ static const struct bond_opt_value bond_primary_reselect_tbl[] = { 
static const struct bond_opt_value bond_use_carrier_tbl[] = {

	{ "off",  0,  0},

	{ "on",   1,  BOND_VALFLAG_DEFAULT},

	{ "both", 2,  0},

	{ NULL,  -1,  0}

};
@@ -395,7 +396,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { 
		.id = BOND_OPT_TLB_DYNAMIC_LB,

		.name = "tlb_dynamic_lb",

		.desc = "Enable dynamic flow shuffling",

		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB)),

		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB) | BIT(BOND_MODE_ALB)),

		.values = bond_tlb_dynamic_lb_tbl,

		.flags = BOND_OPTFLAG_IFDOWN,

		.set = bond_option_tlb_dynamic_lb_set,

include/net/bonding.h

+9 −2
Original line number Diff line number Diff line
@@ -285,8 +285,15 @@ static inline bool bond_needs_speed_duplex(const struct bonding *bond) 


static inline bool bond_is_nondyn_tlb(const struct bonding *bond)

{

	return (BOND_MODE(bond) == BOND_MODE_TLB)  &&

	       (bond->params.tlb_dynamic_lb == 0);

	return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0);

}



static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond)

{

	return (BOND_MODE(bond) == BOND_MODE_8023AD ||

		BOND_MODE(bond) == BOND_MODE_XOR ||

		BOND_MODE(bond) == BOND_MODE_TLB ||

		BOND_MODE(bond) == BOND_MODE_ALB);

}



static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond)

CRA Git | Maintained and supported by SUSTech CRA and CCSE