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: 0x8a,
CQ: 0x35, SQ Cons: 0x2 SQ Prod: 0x2, usecs since last trans: 14912000

$devlink health show
pci/0000:00:09.0:
  name tx
    state healthy #err 1 #recover 0 last_dump_ts N/A
    parameters:
      grace_period 500 auto_recover false

$devlink health diagnose pci/0000:00:09.0 reporter tx -j -p
{
    "SQs": [ {
            "sqn": 138,
            "HW state": 1,
            "stopped": true
        },{
            "sqn": 142,
            "HW state": 1,
            "stopped": false
        } ]
}

$devlink health diagnose pci/0000:00:09.0 reporter tx
SQs:
  sqn: 138 HW state: 1 stopped: true
  sqn: 142 HW state: 1 stopped: false

$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
    parameters:
      grace_period 500 auto_recover false

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 38 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 35568e4820de..0aebfb377cf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -126,6 +126,44 @@ void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
 			      &err_ctx);
 }
 
+static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
+	u32 eqe_count;
+	int ret;
+
+	netdev_err(sq->channel->netdev, "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);
+	ret = eqe_count ? true : false;
+	if (!eqe_count) {
+		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+		return ret;
+	}
+
+	netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
+		   eqe_count, eq->core.eqn);
+	sq->channel->stats->eq_rearm++;
+	return ret;
+}
+
+int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
+{
+	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
+	struct mlx5e_tx_err_ctx err_ctx;
+
+	err_ctx.sq       = sq;
+	err_ctx.recover  = mlx5e_tx_reporter_timeout_recover;
+	sprintf(err_str,
+		"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",
+		sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
+		jiffies_to_usecs(jiffies - sq->txq->trans_start));
+
+	return devlink_health_report(sq->channel->priv->tx_reporter, err_str,
+				     &err_ctx);
+}
+
 /* state lock cannot be grabbed within this function.
  * It can cause a dead lock or a read-after-free.
  */