From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eran Ben Elisha Subject: [PATCH RFC net-next 10/19] net/mlx5e: Add TX timeout support for mlx5e TX reporter Date: Mon, 31 Dec 2018 16:32:04 +0200 Message-ID: <1546266733-9512-11-git-send-email-eranbe@mellanox.com> References: <1546266733-9512-1-git-send-email-eranbe@mellanox.com> Cc: Moshe Shemesh , Aya Levin , Eran Ben Elisha , Tal Alon , Ariel Almog To: netdev@vger.kernel.org, "David S. Miller" , Jiri Pirko Return-path: Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52233 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726383AbeLaOc0 (ORCPT ); Mon, 31 Dec 2018 09:32:26 -0500 In-Reply-To: <1546266733-9512-1-git-send-email-eranbe@mellanox.com> Sender: netdev-owner@vger.kernel.org List-ID: 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_objdump_ts N/A objdump_available false attributes: grace_period 500 auto_recover false Signed-off-by: Eran Ben Elisha --- .../ethernet/mellanox/mlx5/core/en/reporter.h | 1 + .../mellanox/mlx5/core/en/reporter_tx.c | 35 +++++++++++++ .../net/ethernet/mellanox/mlx5/core/en_main.c | 51 +++---------------- 3 files changed, 43 insertions(+), 44 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h index 74083e120ab3..2335c5b48820 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -10,5 +10,6 @@ int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv); void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq); +void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq); #endif 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 b88539528f12..5cbb0a611c5b 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 +126,41 @@ 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; + + 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); + if (!eqe_count) { + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); + return 1; + } + + netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n", + eqe_count, eq->core.eqn); + sq->channel->stats->eq_rearm++; + return 0; +} + +void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq) +{ + struct mlx5e_tx_err_ctx err_ctx; + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + + 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)); + 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. */ 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(); -- 2.17.1