[dpdk-dev] [PATCH] net/bonding: fix link status check

[Tomasz Kulasek]

Some devices needs more time to initialize and bring interface up. When
link is down the link properties are not valid, e.g. link_speed is
reported as 0 and this is not a valid speed for slave as well as for whole
bonding.

During NIC (and bonding) initialization there's concurrency between
updating link status and adding slave to the bonding.

This patch:

 - adds delay before configuring bonding (if link is down) to be sure that
   link status of new slave is valid,
 - propagates information about link status from first active slave
   instead of first slave at all, to be sure that link speed is valid.

Fixes: 6abd94d72ab5 ("net/bonding: fix check slaves link properties")
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek at intel.com>
---
 drivers/net/bonding/rte_eth_bond_8023ad_private.h |  1 +
 drivers/net/bonding/rte_eth_bond_api.c            | 50 ++++++++++++++++-------
 2 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/drivers/net/bonding/rte_eth_bond_8023ad_private.h b/drivers/net/bonding/rte_eth_bond_8023ad_private.h
index 433c700..0a72beb 100644
--- a/drivers/net/bonding/rte_eth_bond_8023ad_private.h
+++ b/drivers/net/bonding/rte_eth_bond_8023ad_private.h
@@ -180,6 +180,7 @@ struct mode8023ad_private {
 	rte_eth_bond_8023ad_ext_slowrx_fn slowrx_cb;
 	uint8_t external_sm;
 
+	uint8_t slave_link_valid;
 	struct rte_eth_link slave_link;
 	/***< slave link properties */
 
diff --git a/drivers/net/bonding/rte_eth_bond_api.c b/drivers/net/bonding/rte_eth_bond_api.c
index 980e636..6b65fac 100644
--- a/drivers/net/bonding/rte_eth_bond_api.c
+++ b/drivers/net/bonding/rte_eth_bond_api.c
@@ -33,6 +33,7 @@
 
 #include <string.h>
 
+#include <rte_cycles.h>
 #include <rte_mbuf.h>
 #include <rte_malloc.h>
 #include <rte_ethdev.h>
@@ -239,6 +240,7 @@
 	struct bond_dev_private *internals;
 	struct rte_eth_link link_props;
 	struct rte_eth_dev_info dev_info;
+	int retries = 10;
 
 	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
 	internals = bonded_eth_dev->data->dev_private;
@@ -262,6 +264,20 @@
 		return -1;
 	}
 
+	/* Some devices needs more time to initialize and bring interface up.
+	 * While link status up is preferable we wait some time to be sure that
+	 * link status of slave is valid.
+	 */
+	if (slave_eth_dev->data->dev_link.link_status == ETH_LINK_DOWN) {
+		rte_delay_ms(100);
+		rte_eth_link_get_nowait(slave_port_id, &link_props);
+		while ((link_props.link_status == ETH_LINK_DOWN) && (retries > 0)) {
+			rte_delay_ms(100);
+			rte_eth_link_get_nowait(slave_port_id, &link_props);
+			retries--;
+		}
+	}
+
 	slave_add(internals, slave_eth_dev);
 
 	/* We need to store slaves reta_size to be able to synchronize RETA for all
@@ -270,15 +286,16 @@
 	internals->slaves[internals->slave_count].reta_size = dev_info.reta_size;
 
 	if (internals->slave_count < 1) {
+
+		/* Reset link status information for bonded slaves (it will be taken
+		 * from first active slave) */
+		internals->mode4.slave_link_valid = 0;
+
 		/* if MAC is not user defined then use MAC of first slave add to
 		 * bonded device */
 		if (!internals->user_defined_mac)
 			mac_address_set(bonded_eth_dev, slave_eth_dev->data->mac_addrs);
 
-		/* Inherit eth dev link properties from first slave */
-		link_properties_set(bonded_eth_dev,
-				&(slave_eth_dev->data->dev_link));
-
 		/* Make primary slave */
 		internals->primary_port = slave_port_id;
 		internals->current_primary_port = slave_port_id;
@@ -302,14 +319,6 @@
 		internals->tx_offload_capa &= dev_info.tx_offload_capa;
 		internals->flow_type_rss_offloads &= dev_info.flow_type_rss_offloads;
 
-		if (link_properties_valid(bonded_eth_dev,
-				&slave_eth_dev->data->dev_link) != 0) {
-			RTE_BOND_LOG(ERR, "Invalid link properties for slave %d"
-					" in bonding mode %d", slave_port_id,
-					internals->mode);
-			return -1;
-		}
-
 		/* RETA size is GCD of all slaves RETA sizes, so, if all sizes will be
 		 * the power of 2, the lower one is GCD
 		 */
@@ -355,9 +364,22 @@
 							slave_port_id);
 
 			if (find_slave_by_id(internals->active_slaves,
-					     internals->active_slave_count,
-					     slave_port_id) == internals->active_slave_count)
+						internals->active_slave_count,
+						slave_port_id) == internals->active_slave_count) {
+				if (internals->mode4.slave_link_valid == 0) {
+					internals->mode4.slave_link_valid = 1;
+					/* Inherit dev link properties from first active slave */
+					link_properties_set(bonded_eth_dev,
+							&(slave_eth_dev->data->dev_link));
+				} else if (link_properties_valid(bonded_eth_dev,
+							&slave_eth_dev->data->dev_link) != 0) {
+						RTE_BOND_LOG(ERR, "Invalid link properties for slave %d"
+								" in bonding mode %d", slave_port_id,
+								internals->mode);
+						return -1;
+				}
 				activate_slave(bonded_eth_dev, slave_port_id);
+			}
 		}
 	}
 
-- 
1.9.1