[dpdk-stable] [PATCH v1 1/3] net/mlx4: fix unhandled event debug message

[dpdk-stable] [PATCH v1 1/3] net/mlx4: fix unhandled event debug message

[Adrien Mazarguil]

When LSC or RMV events are received by the PMD but are not requested by the
application, a misleading debugging message implying the PMD does not
support them is shown.

Fixes: 6dd7b7056d7f ("net/mlx4: support device removal event")
Cc: Gaetan Rivet <gaetan.rivet@6wind.com>
Cc: stable@dpdk.org

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
---
 drivers/net/mlx4/mlx4_intr.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/mlx4/mlx4_intr.c b/drivers/net/mlx4/mlx4_intr.c
index e3449ee..d7f1098 100644
--- a/drivers/net/mlx4/mlx4_intr.c
+++ b/drivers/net/mlx4/mlx4_intr.c
@@ -160,16 +160,21 @@ mlx4_collect_interrupt_events(struct priv *priv, uint32_t *events)
 	for (;;) {
 		if (ibv_get_async_event(priv->ctx, &event))
 			break;
-		if ((event.event_type == IBV_EVENT_PORT_ACTIVE ||
-		     event.event_type == IBV_EVENT_PORT_ERR) &&
-		    intr_conf->lsc) {
+		switch (event.event_type) {
+		case IBV_EVENT_PORT_ACTIVE:
+		case IBV_EVENT_PORT_ERR:
+			if (!intr_conf->lsc)
+				break;
 			port_change = 1;
 			ret++;
-		} else if (event.event_type == IBV_EVENT_DEVICE_FATAL &&
-			   intr_conf->rmv) {
+			break;
+		case IBV_EVENT_DEVICE_FATAL:
+			if (!intr_conf->rmv)
+				break;
 			*events |= (1 << RTE_ETH_EVENT_INTR_RMV);
 			ret++;
-		} else {
+			break;
+		default:
 			DEBUG("event type %d on port %d not handled",
 			      event.event_type, event.element.port_num);
 		}
-- 
2.1.4

[dpdk-stable] [PATCH v1 2/3] net/mlx4: fix rescheduled link status check

[Adrien Mazarguil]

Link status is sometimes inconsistent during a LSC event. When it occurs,
the PMD refrains from immediately notifying the application; instead, an
alarm is scheduled to check link status later and notify the application
once it has settled.

The problem is that subsequent link status checks are only performed if
additional LSC events occur in the meantime, which is not always the case.

Worse, since support for removal events was added, rescheduled link status
checks may consume them as well without notifying the application. With the
right timing, a link loss occurring just before a device removal event may
hide it from the application.

Fixes: 6dd7b7056d7f ("net/mlx4: support device removal event")
Fixes: 2d449f7c52de ("net/mlx4: fix assertion failure on link update")
Cc: stable@dpdk.org
Cc: Gaetan Rivet <gaetan.rivet@6wind.com>

Reported-by: Matan Azrad <matan@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
---
 drivers/net/mlx4/mlx4_intr.c | 71 +++++++++++++++++++++++++--------------
 1 file changed, 46 insertions(+), 25 deletions(-)

diff --git a/drivers/net/mlx4/mlx4_intr.c b/drivers/net/mlx4/mlx4_intr.c
index d7f1098..e1e6c05 100644
--- a/drivers/net/mlx4/mlx4_intr.c
+++ b/drivers/net/mlx4/mlx4_intr.c
@@ -59,7 +59,7 @@
 #include "mlx4_rxtx.h"
 #include "mlx4_utils.h"
 
-static void mlx4_link_status_alarm(struct priv *priv);
+static int mlx4_link_status_check(struct priv *priv);
 
 /**
  * Clean up Rx interrupts handler.
@@ -149,8 +149,6 @@ static int
 mlx4_collect_interrupt_events(struct priv *priv, uint32_t *events)
 {
 	struct ibv_async_event event;
-	int port_change = 0;
-	struct rte_eth_link *link = &priv->dev->data->dev_link;
 	const struct rte_intr_conf *const intr_conf =
 		&priv->dev->data->dev_conf.intr_conf;
 	int ret = 0;
@@ -163,9 +161,9 @@ mlx4_collect_interrupt_events(struct priv *priv, uint32_t *events)
 		switch (event.event_type) {
 		case IBV_EVENT_PORT_ACTIVE:
 		case IBV_EVENT_PORT_ERR:
-			if (!intr_conf->lsc)
+			if (!intr_conf->lsc || mlx4_link_status_check(priv))
 				break;
-			port_change = 1;
+			*events |= (1 << RTE_ETH_EVENT_INTR_LSC);
 			ret++;
 			break;
 		case IBV_EVENT_DEVICE_FATAL:
@@ -180,47 +178,70 @@ mlx4_collect_interrupt_events(struct priv *priv, uint32_t *events)
 		}
 		ibv_ack_async_event(&event);
 	}
-	if (!port_change)
-		return ret;
-	mlx4_link_update(priv->dev, 0);
-	if (((link->link_speed == 0) && link->link_status) ||
-	    ((link->link_speed != 0) && !link->link_status)) {
-		if (!priv->intr_alarm) {
-			/* Inconsistent status, check again later. */
-			priv->intr_alarm = 1;
-			rte_eal_alarm_set(MLX4_INTR_ALARM_TIMEOUT,
-					  (void (*)(void *))
-					  mlx4_link_status_alarm,
-					  priv);
-		}
-	} else {
-		*events |= (1 << RTE_ETH_EVENT_INTR_LSC);
-	}
 	return ret;
 }
 
 /**
  * Process scheduled link status check.
  *
+ * If LSC interrupts are requested, process related callback.
+ *
  * @param priv
  *   Pointer to private structure.
  */
 static void
 mlx4_link_status_alarm(struct priv *priv)
 {
-	uint32_t events;
-	int ret;
+	const struct rte_intr_conf *const intr_conf =
+		&priv->dev->data->dev_conf.intr_conf;
 
 	assert(priv->intr_alarm == 1);
 	priv->intr_alarm = 0;
-	ret = mlx4_collect_interrupt_events(priv, &events);
-	if (ret > 0 && events & (1 << RTE_ETH_EVENT_INTR_LSC))
+	if (intr_conf->lsc && !mlx4_link_status_check(priv))
 		_rte_eth_dev_callback_process(priv->dev,
 					      RTE_ETH_EVENT_INTR_LSC,
 					      NULL, NULL);
 }
 
 /**
+ * Check link status.
+ *
+ * In case of inconsistency, another check is scheduled.
+ *
+ * @param priv
+ *   Pointer to private structure.
+ *
+ * @return
+ *   0 on success (link status is consistent), negative errno value
+ *   otherwise and rte_errno is set.
+ */
+static int
+mlx4_link_status_check(struct priv *priv)
+{
+	struct rte_eth_link *link = &priv->dev->data->dev_link;
+	int ret = mlx4_link_update(priv->dev, 0);
+
+	if (ret)
+		return ret;
+	if ((!link->link_speed && link->link_status) ||
+	    (link->link_speed && !link->link_status)) {
+		if (!priv->intr_alarm) {
+			/* Inconsistent status, check again later. */
+			ret = rte_eal_alarm_set(MLX4_INTR_ALARM_TIMEOUT,
+						(void (*)(void *))
+						mlx4_link_status_alarm,
+						priv);
+			if (ret)
+				return ret;
+			priv->intr_alarm = 1;
+		}
+		rte_errno = EINPROGRESS;
+		return -rte_errno;
+	}
+	return 0;
+}
+
+/**
  * Handle interrupts from the NIC.
  *
  * @param priv
-- 
2.1.4