diff options
author | Eran Ben Elisha <eranbe@mellanox.com> | 2017-12-19 15:52:29 +0300 |
---|---|---|
committer | Saeed Mahameed <saeedm@mellanox.com> | 2018-01-19 23:41:33 +0300 |
commit | 7ca560b5af70b5f578c9bf32c8fbfbd68d22252f (patch) | |
tree | 1ea15c68151f7fc60fd605c929d55084541dedbc /drivers/net/ethernet/mellanox/mlx5/core/en_main.c | |
parent | 3a32b26a4eccb37435d81bf75e41b2bd4464f8d6 (diff) | |
download | linux-7ca560b5af70b5f578c9bf32c8fbfbd68d22252f.tar.xz |
net/mlx5e: Poll event queue upon TX timeout before performing full channels recovery
Up until this patch, on every TX timeout we would try to do channels
recovery. However, in case of a lost interrupt for an EQ, the channel
associated to it cannot be recovered if reopened as it would never get
another interrupt on sent/received traffic, and eventually ends up with
another TX timeout (Restarting the EQ is not part of channel recovery).
This patch adds a mechanism for explicitly polling EQ in case of a TX
timeout in order to recover from a lost interrupt. If this is not the
case (no pending EQEs), perform a channels full recovery as usual.
Once a lost EQE is recovered, it triggers the NAPI to run and handle all
pending completions. This will free some budget in the bql (via calling
netdev_tx_completed_queue) or by clearing pending TXWQEs and waking up
the queue. One of the above actions will move the queue to be ready for
transmit again.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en_main.c')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 51 |
1 files changed, 36 insertions, 15 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 71b8b171c565..12ea5e319e38 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3757,10 +3757,37 @@ static 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 mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + int irqn_not_used, eqn; + struct mlx5_eq *eq; + u32 eqe_count; + + if (mlx5_vector2eqn(mdev, sq->cq.mcq.vector, &eqn, &irqn_not_used)) + return false; + + eq = mlx5_eqn2eq(mdev, eqn); + if (IS_ERR(eq)) + return false; + + netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + eqn, eq->cons_index, eq->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->eqn); + return true; +} + static void mlx5e_tx_timeout(struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - bool sched_work = false; + bool reopen_channels = false; int i; netdev_err(dev, "TX timeout detected\n"); @@ -3768,29 +3795,23 @@ static void mlx5e_tx_timeout(struct net_device *dev) 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 mlx5e_txqsq *sq = priv->txq2sq[i]; - struct mlx5_core_dev *mdev = priv->mdev; - int irqn_not_used, eqn; - struct mlx5_eq *eq; if (!netif_xmit_stopped(dev_queue)) continue; - sched_work = true; - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); 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 (mlx5_vector2eqn(mdev, sq->cq.mcq.vector, &eqn, - &irqn_not_used)) - continue; - - eq = mlx5_eqn2eq(mdev, eqn); - if (!IS_ERR(eq)) - netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eqn, eq->cons_index, eq->irqn); + /* 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; + } } - if (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state)) + if (reopen_channels && test_bit(MLX5E_STATE_OPENED, &priv->state)) schedule_work(&priv->tx_timeout_work); } |