[dpdk-dev] [PATCH] net/bonding: fix slave activation simultaneously

[Matan Azrad]

The bonding PMD decides to activate\deactivate its slaves according to
the slaves link statuses.
Thus, it registers to the LSC events of the slaves ports and
activates\deactivates them from its LSC callbacks called asynchronously
by the host thread when the slave link status is changed.

In addition, the bonding PMD uses the callback for slave activation
when it tries to start it, this operation is probably called by the
master thread.

Consequently, a slave may be activated in the same time by two
different threads and may cause a lot of optional errors, for example,
slave mempool recreation with the same name causes an error.

Synchronize the critical section in the LSC callback using a special
new spinlock.

Fixes: 414b202343ce ("bonding: fix initial link status of slave")
Fixes: a45b288ef21a ("bond: support link status polling")
Cc: stable at dpdk.org

Signed-off-by: Matan Azrad <matan at mellanox.com>
---
 drivers/net/bonding/rte_eth_bond_pmd.c     | 17 +++++++++++++++--
 drivers/net/bonding/rte_eth_bond_private.h |  1 +
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/rte_eth_bond_pmd.c b/drivers/net/bonding/rte_eth_bond_pmd.c
index 2805c71..dffd12f 100644
--- a/drivers/net/bonding/rte_eth_bond_pmd.c
+++ b/drivers/net/bonding/rte_eth_bond_pmd.c
@@ -2654,14 +2654,21 @@ struct bwg_slave {
 	if (!valid_slave)
 		return rc;
 
+	/* Synchronize lsc callback parallel calls either by real link event
+	 * from the slaves PMDs or by the bonding PMD itself.
+	 */
+	rte_spinlock_lock(&internals->lsc_lock);
+
 	/* Search for port in active port list */
 	active_pos = find_slave_by_id(internals->active_slaves,
 			internals->active_slave_count, port_id);
 
 	rte_eth_link_get_nowait(port_id, &link);
 	if (link.link_status) {
-		if (active_pos < internals->active_slave_count)
+		if (active_pos < internals->active_slave_count) {
+			rte_spinlock_unlock(&internals->lsc_lock);
 			return rc;
+		}
 
 		/* if no active slave ports then set this port to be primary port */
 		if (internals->active_slave_count < 1) {
@@ -2680,8 +2687,10 @@ struct bwg_slave {
 				internals->primary_port == port_id)
 			bond_ethdev_primary_set(internals, port_id);
 	} else {
-		if (active_pos == internals->active_slave_count)
+		if (active_pos == internals->active_slave_count) {
+			rte_spinlock_unlock(&internals->lsc_lock);
 			return rc;
+		}
 
 		/* Remove from active slave list */
 		deactivate_slave(bonded_eth_dev, port_id);
@@ -2734,6 +2743,9 @@ struct bwg_slave {
 						NULL);
 		}
 	}
+
+	rte_spinlock_unlock(&internals->lsc_lock);
+
 	return 0;
 }
 
@@ -2942,6 +2954,7 @@ struct bwg_slave {
 	eth_dev->data->dev_flags = RTE_ETH_DEV_INTR_LSC;
 
 	rte_spinlock_init(&internals->lock);
+	rte_spinlock_init(&internals->lsc_lock);
 
 	internals->port_id = eth_dev->data->port_id;
 	internals->mode = BONDING_MODE_INVALID;
diff --git a/drivers/net/bonding/rte_eth_bond_private.h b/drivers/net/bonding/rte_eth_bond_private.h
index 94eca88..9220b61 100644
--- a/drivers/net/bonding/rte_eth_bond_private.h
+++ b/drivers/net/bonding/rte_eth_bond_private.h
@@ -89,6 +89,7 @@ struct bond_dev_private {
 	uint8_t mode;						/**< Link Bonding Mode */
 
 	rte_spinlock_t lock;
+	rte_spinlock_t lsc_lock;
 
 	uint16_t primary_port;			/**< Primary Slave Port */
 	uint16_t current_primary_port;		/**< Primary Slave Port */
-- 
1.9.5