Merge: Bonding: add option per-port priority

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/2418

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2092194

Signed-off-by: Hangbin Liu <haliu@redhat.com>

Approved-by: Xin Long <lxin@redhat.com>
Approved-by: Andrea Claudi <aclaudi@redhat.com>

Signed-off-by: Jan Stancek <jstancek@redhat.com>

Author: jstancek

Documentation/networking/bonding.rst

@@ -781,6 +781,17 @@ peer_notif_delay
 	value is 0 which means to match the value of the link monitor
 	interval.
 
+prio
+	Slave priority. A higher number means higher priority.
+	The primary slave has the highest priority. This option also
+	follows the primary_reselect rules.
+
+	This option could only be configured via netlink, and is only valid
+	for active-backup(1), balance-tlb (5) and balance-alb (6) mode.
+	The valid value range is a signed 32 bit integer.
+
+	The default value is 0.
+
 primary
 
 	A string (eth0, eth2, etc) specifying which slave is the

drivers/net/bonding/bond_main.c

@@ -1025,12 +1025,38 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 
 }
 
+/**
+ * bond_choose_primary_or_current - select the primary or high priority slave
+ * @bond: our bonding struct
+ *
+ * - Check if there is a primary link. If the primary link was set and is up,
+ *   go on and do link reselection.
+ *
+ * - If primary link is not set or down, find the highest priority link.
+ *   If the highest priority link is not current slave, set it as primary
+ *   link and do link reselection.
+ */
 static struct slave *bond_choose_primary_or_current(struct bonding *bond)
 {
 	struct slave *prim = rtnl_dereference(bond->primary_slave);
 	struct slave *curr = rtnl_dereference(bond->curr_active_slave);
+	struct slave *slave, *hprio = NULL;
+	struct list_head *iter;
 
 	if (!prim || prim->link != BOND_LINK_UP) {
+		bond_for_each_slave(bond, slave, iter) {
+			if (slave->link == BOND_LINK_UP) {
+				hprio = hprio ?: slave;
+				if (slave->prio > hprio->prio)
+					hprio = slave;
+			}
+		}
+
+		if (hprio && hprio != curr) {
+			prim = hprio;
+			goto link_reselect;
+		}
+
 		if (!curr || curr->link != BOND_LINK_UP)
 			return NULL;
 		return curr;
@@ -1041,6 +1067,7 @@ static struct slave *bond_choose_primary_or_current(struct bonding *bond)
 		return prim;
 	}
 
+link_reselect:
 	if (!curr || curr->link != BOND_LINK_UP)
 		return prim;
 
@@ -2626,8 +2653,11 @@ static void bond_miimon_link_change(struct bonding *bond,
 
 static void bond_miimon_commit(struct bonding *bond)
 {
+	struct slave *slave, *primary, *active;
+	bool do_failover = false;
 	struct list_head *iter;
-	struct slave *slave, *primary;
+
+	ASSERT_RTNL();
 
 	bond_for_each_slave(bond, slave, iter) {
 		switch (slave->link_new_state) {
@@ -2671,8 +2701,9 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			bond_miimon_link_change(bond, slave, BOND_LINK_UP);
 
-			if (!bond->curr_active_slave || slave == primary)
-				goto do_failover;
+			active = rtnl_dereference(bond->curr_active_slave);
+			if (!active || slave == primary || slave->prio > active->prio)
+				do_failover = true;
 
 			continue;
 
@@ -2693,7 +2724,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			bond_miimon_link_change(bond, slave, BOND_LINK_DOWN);
 
 			if (slave == rcu_access_pointer(bond->curr_active_slave))
-				goto do_failover;
+				do_failover = true;
 
 			continue;
 
@@ -2704,8 +2735,9 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			continue;
 		}
+	}
 
-do_failover:
+	if (do_failover) {
 		block_netpoll_tx();
 		bond_select_active_slave(bond);
 		unblock_netpoll_tx();
@@ -3503,6 +3535,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
  */
 static void bond_ab_arp_commit(struct bonding *bond)
 {
+	bool do_failover = false;
 	struct list_head *iter;
 	unsigned long last_tx;
 	struct slave *slave;
@@ -3532,8 +3565,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				slave_info(bond->dev, slave->dev, "link status definitely up\n");
 
 				if (!rtnl_dereference(bond->curr_active_slave) ||
-				    slave == rtnl_dereference(bond->primary_slave))
-					goto do_failover;
+				    slave == rtnl_dereference(bond->primary_slave) ||
+				    slave->prio > rtnl_dereference(bond->curr_active_slave)->prio)
+					do_failover = true;
 
 			}
 
@@ -3552,7 +3586,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 			if (slave == rtnl_dereference(bond->curr_active_slave)) {
 				RCU_INIT_POINTER(bond->current_arp_slave, NULL);
-				goto do_failover;
+				do_failover = true;
 			}
 
 			continue;
@@ -3576,8 +3610,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				  slave->link_new_state);
 			continue;
 		}
+	}
 
-do_failover:
+	if (do_failover) {
 		block_netpoll_tx();
 		bond_select_active_slave(bond);
 		unblock_netpoll_tx();

drivers/net/bonding/bond_netlink.c

@@ -27,6 +27,7 @@ static size_t bond_get_slave_size(const struct net_device *bond_dev,
 		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */
 		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */
+		nla_total_size(sizeof(s32)) +	/* IFLA_BOND_SLAVE_PRIO */
 		0;
 }
 
@@ -53,6 +54,9 @@ static int bond_fill_slave_info(struct sk_buff *skb,
 	if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, slave->queue_id))
 		goto nla_put_failure;
 
+	if (nla_put_s32(skb, IFLA_BOND_SLAVE_PRIO, slave->prio))
+		goto nla_put_failure;
+
 	if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) {
 		const struct aggregator *agg;
 		const struct port *ad_port;
@@ -117,6 +121,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 
 static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = {
 	[IFLA_BOND_SLAVE_QUEUE_ID]	= { .type = NLA_U16 },
+	[IFLA_BOND_SLAVE_PRIO]		= { .type = NLA_S32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -157,6 +162,16 @@ static int bond_slave_changelink(struct net_device *bond_dev,
 			return err;
 	}
 
+	if (data[IFLA_BOND_SLAVE_PRIO]) {
+		int prio = nla_get_s32(data[IFLA_BOND_SLAVE_PRIO]);
+
+		bond_opt_slave_initval(&newval, &slave_dev, prio);
+		err = __bond_opt_set(bond, BOND_OPT_PRIO, &newval,
+				     data[IFLA_BOND_SLAVE_PRIO], extack);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 

drivers/net/bonding/bond_options.c

@@ -40,6 +40,8 @@ static int bond_option_arp_validate_set(struct bonding *bond,
 					const struct bond_opt_value *newval);
 static int bond_option_arp_all_targets_set(struct bonding *bond,
 					   const struct bond_opt_value *newval);
+static int bond_option_prio_set(struct bonding *bond,
+				const struct bond_opt_value *newval);
 static int bond_option_primary_set(struct bonding *bond,
 				   const struct bond_opt_value *newval);
 static int bond_option_primary_reselect_set(struct bonding *bond,
@@ -365,6 +367,16 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.values = bond_intmax_tbl,
 		.set = bond_option_miimon_set
 	},
+	[BOND_OPT_PRIO] = {
+		.id = BOND_OPT_PRIO,
+		.name = "prio",
+		.desc = "Link priority for failover re-selection",
+		.flags = BOND_OPTFLAG_RAWVAL,
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) |
+						BIT(BOND_MODE_TLB) |
+						BIT(BOND_MODE_ALB)),
+		.set = bond_option_prio_set
+	},
 	[BOND_OPT_PRIMARY] = {
 		.id = BOND_OPT_PRIMARY,
 		.name = "primary",
@@ -1306,6 +1318,27 @@ static int bond_option_missed_max_set(struct bonding *bond,
 	return 0;
 }
 
+static int bond_option_prio_set(struct bonding *bond,
+				const struct bond_opt_value *newval)
+{
+	struct slave *slave;
+
+	slave = bond_slave_get_rtnl(newval->slave_dev);
+	if (!slave) {
+		netdev_dbg(newval->slave_dev, "%s called on NULL slave\n", __func__);
+		return -ENODEV;
+	}
+	slave->prio = newval->value;
+
+	if (rtnl_dereference(bond->primary_slave))
+		slave_warn(bond->dev, slave->dev,
+			   "prio updated, but will not affect failover re-selection as primary slave have been set\n");
+	else
+		bond_select_active_slave(bond);
+
+	return 0;
+}
+
 static int bond_option_primary_set(struct bonding *bond,
 				   const struct bond_opt_value *newval)
 {

include/net/bond_options.h

@@ -67,6 +67,7 @@ enum {
 	BOND_OPT_LACP_ACTIVE,
 	BOND_OPT_MISSED_MAX,
 	BOND_OPT_NS_TARGETS,
+	BOND_OPT_PRIO,
 	BOND_OPT_LAST
 };
 
@@ -83,7 +84,10 @@ struct bond_opt_value {
 	char *string;
 	u64 value;
 	u32 flags;
-	char extra[BOND_OPT_EXTRA_MAXLEN];
+	union {
+		char extra[BOND_OPT_EXTRA_MAXLEN];
+		struct net_device *slave_dev;
+	};
 };
 
 struct bonding;
@@ -133,13 +137,16 @@ static inline void __bond_opt_init(struct bond_opt_value *optval,
 		optval->value = value;
 	else if (string)
 		optval->string = string;
-	else if (extra_len <= BOND_OPT_EXTRA_MAXLEN)
+
+	if (extra && extra_len <= BOND_OPT_EXTRA_MAXLEN)
 		memcpy(optval->extra, extra, extra_len);
 }
 #define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value, NULL, 0)
 #define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX, NULL, 0)
 #define bond_opt_initextra(optval, extra, extra_len) \
 	__bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len)
+#define bond_opt_slave_initval(optval, slave_dev, value) \
+	__bond_opt_init(optval, NULL, value, slave_dev, sizeof(struct net_device *))
 
 void bond_option_arp_ip_targets_clear(struct bonding *bond);
 #if IS_ENABLED(CONFIG_IPV6)

include/net/bonding.h

@@ -179,6 +179,7 @@ struct slave {
 	u32    speed;
 	u16    queue_id;
 	u8     perm_hwaddr[MAX_ADDR_LEN];
+	int    prio;
 	struct ad_slave_info *ad_info;
 	struct tlb_slave_info tlb_info;
 #ifdef CONFIG_NET_POLL_CONTROLLER

include/uapi/linux/if_link.h

@@ -915,6 +915,7 @@ enum {
 	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+	IFLA_BOND_SLAVE_PRIO,
 	__IFLA_BOND_SLAVE_MAX,
 };
 

tools/include/uapi/linux/if_link.h

@@ -891,6 +891,7 @@ enum {
 	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+	IFLA_BOND_SLAVE_PRIO,
 	__IFLA_BOND_SLAVE_MAX,
 };
 

tools/testing/selftests/drivers/net/bonding/Makefile

@@ -7,7 +7,8 @@ TEST_PROGS := \
 	bond-lladdr-target.sh \
 	dev_addr_lists.sh \
 	mode-1-recovery-updelay.sh \
-	mode-2-recovery-updelay.sh
+	mode-2-recovery-updelay.sh \
+	option_prio.sh
 
 TEST_FILES := \
 	lag_lib.sh \