net/mlx5e: Add TX timeout support for mlx5e TX reporter

With this patch, ndo_tx_timeout callback will be redirected to the TX
reporter in order to detect a TX timeout error and report it to the
devlink health. (The watchdog detects TX timeouts, but the driver verify
the issue still exists before launching any recover method).

In addition, recover from TX timeout in case of lost interrupt was added
to the TX reporter recover method. The TX timeout recover from lost
interrupt is not a new feature in the driver, this patch re-organize the
functionality and move it to the TX reporter recovery flow.

TX timeout example:
(with auto_recover set to false, if set to true, the manual recover and
diagnose sections are irrelevant)

$cat /sys/kernel/debug/tracing/trace
...
devlink_health_report: bus_name=pci dev_name=0000:00:09.0
driver_name=mlx5_core reporter_name=TX: TX timeout on queue: 0, SQ: 0xd8a, CQ:
0x406, SQ Cons: 0x2 SQ Prod: 0x2, usecs since last trans: 13972000

$devlink health diagnose pci/0000:00:09 reporter TX
SQ 0xd8a: HW state: 1, stopped: 1
SQ 0xe44: HW state: 1, stopped: 0
SQ 0xeb4: HW state: 1, stopped: 0
SQ 0xf1f: HW state: 1, stopped: 0
SQ 0xf80: HW state: 1, stopped: 0
SQ 0xfe5: HW state: 1, stopped: 0

$devlink health recover pci/0000:00:09 reporter TX
$devlink health show
pci/0000:00:09.0:
  name TX state healthy #err 1 #recover 1 last_dump_ts N/A dump_available false
    attributes:
        grace_period 500 auto_recover false

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 44 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 4c4507384fed..dee0c8f3d4e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4074,31 +4074,14 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
-static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
-					struct mlx5e_txqsq *sq)
-{
-	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
-	u32 eqe_count;
-
-	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
-
-	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	if (!eqe_count)
-		return false;
-
-	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn);
-	sq->channel->stats->eq_rearm++;
-	return true;
-}
-
 static void mlx5e_tx_timeout_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       tx_timeout_work);
-	struct net_device *dev = priv->netdev;
-	bool reopen_channels = false;
-	int i, err;
+	int i;
+
+	if (!priv->tx_reporter)
+		return;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
@@ -4107,36 +4090,16 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 		goto unlock;
 
 	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
-		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
+		struct netdev_queue *dev_queue =
+			netdev_get_tx_queue(priv->netdev, i);
 		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
 
-		netdev_err(dev,
-			   "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
-			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
-			   jiffies_to_usecs(jiffies - dev_queue->trans_start));
-
-		/* If we recover a lost interrupt, most likely TX timeout will
-		 * be resolved, skip reopening channels
-		 */
-		if (!mlx5e_tx_timeout_eq_recover(dev, sq)) {
-			clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-			reopen_channels = true;
-		}
+		mlx5e_tx_reporter_timeout(sq);
 	}
 
-	if (!reopen_channels)
-		goto unlock;
-
-	mlx5e_close_locked(dev);
-	err = mlx5e_open_locked(dev);
-	if (err)
-		netdev_err(priv->netdev,
-			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
-			   err);
-
 unlock:
 	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();