net/mlx5e: Add tx reporter support

Add mlx5e tx reporter to devlink health reporters. This reporter will be
responsible for diagnosing, reporting and recovering of tx errors.
This patch declares the TX reporter operations and creates it using the
devlink health API. Currently, this reporter supports reporting and
recovering from send error CQE only. In addition, it adds diagnose
information for the open SQs.

For a local SQ recover (due to driver error report), in case of SQ recover
failure, the recover operation will be considered as a failure.
For a full tx recover, an attempt to close and open the channels will be
done. If this one passed successfully, it will be considered as a
successful recover.

The SQ recover from error CQE flow is not a new feature in the driver,
this patch re-organize the functions and adapt them for the devlink
health API. For this purpose, move code from en_main.c to a new file
named reporter_tx.c.

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

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

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -22,7 +22,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 #
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o en/monitor_stats.o
+		en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o
 
 #
 # Netdev extra

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -387,10 +387,7 @@ struct mlx5e_txqsq {
 	struct mlx5e_channel      *channel;
 	int                        txq_ix;
 	u32                        rate_limit;
-	struct mlx5e_txqsq_recover {
-		struct work_struct         recover_work;
-		u64                        last_recover;
-	} recover;
+	struct work_struct         recover_work;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_dma_info {
@@ -683,6 +680,13 @@ struct mlx5e_rss_params {
 	u8	hfunc;
 };
 
+struct mlx5e_modify_sq_param {
+	int curr_state;
+	int next_state;
+	int rl_update;
+	int rl_index;
+};
+
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
@@ -738,6 +742,7 @@ struct mlx5e_priv {
 #ifdef CONFIG_MLX5_EN_TLS
 	struct mlx5e_tls          *tls;
 #endif
+	struct devlink_health_reporter *tx_reporter;
 };
 
 struct mlx5e_profile {
@@ -868,6 +873,11 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params);
 
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p);
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq);
+void mlx5e_tx_disable_queue(struct netdev_queue *txq);
+
 static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
 {
 	return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) &&

drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5E_EN_REPORTER_H
+#define __MLX5E_EN_REPORTER_H
+
+#include <linux/mlx5/driver.h>
+#include "en.h"
+
+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);
+
+#endif

drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <net/devlink.h>
+#include "reporter.h"
+#include "lib/eq.h"
+
+#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256
+
+struct mlx5e_tx_err_ctx {
+	int (*recover)(struct mlx5e_txqsq *sq);
+	struct mlx5e_txqsq *sq;
+};
+
+static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
+{
+	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+
+	while (time_before(jiffies, exp_time)) {
+		if (sq->cc == sq->pc)
+			return 0;
+
+		msleep(20);
+	}
+
+	netdev_err(sq->channel->netdev,
+		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
+		   sq->sqn, sq->cc, sq->pc);
+
+	return -ETIMEDOUT;
+}
+
+static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
+{
+	WARN_ONCE(sq->cc != sq->pc,
+		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
+		  sq->sqn, sq->cc, sq->pc);
+	sq->cc = 0;
+	sq->dma_fifo_cc = 0;
+	sq->pc = 0;
+}
+
+static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+	struct net_device *dev = sq->channel->netdev;
+	struct mlx5e_modify_sq_param msp = {0};
+	int err;
+
+	msp.curr_state = curr_state;
+	msp.next_state = MLX5_SQC_STATE_RST;
+
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
+		return err;
+	}
+
+	memset(&msp, 0, sizeof(msp));
+	msp.curr_state = MLX5_SQC_STATE_RST;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
+		return err;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+	struct net_device *dev = sq->channel->netdev;
+	u8 state;
+	int err;
+
+	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+		return 0;
+
+	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
+	if (err) {
+		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
+			   sq->sqn, err);
+		return err;
+	}
+
+	if (state != MLX5_SQC_STATE_ERR) {
+		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
+		return -EINVAL;
+	}
+
+	mlx5e_tx_disable_queue(sq->txq);
+
+	err = mlx5e_wait_for_sq_flush(sq);
+	if (err)
+		return err;
+
+	/* At this point, no new packets will arrive from the stack as TXQ is
+	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
+	 * pending WQEs. SQ can safely reset the SQ.
+	 */
+
+	err = mlx5e_sq_to_ready(sq, state);
+	if (err)
+		return err;
+
+	mlx5e_reset_txqsq_cc_pc(sq);
+	sq->stats->recover++;
+	mlx5e_activate_txqsq(sq);
+
+	return 0;
+}
+
+void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
+{
+	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
+	struct mlx5e_tx_err_ctx err_ctx = {0};
+
+	err_ctx.sq       = sq;
+	err_ctx.recover  = mlx5e_tx_reporter_err_cqe_recover;
+	sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
+
+	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.
+ */
+int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
+{
+	return err_ctx->recover(err_ctx->sq);
+}
+
+static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
+{
+	int err;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+	mlx5e_close_locked(priv->netdev);
+	err = mlx5e_open_locked(priv->netdev);
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+
+	return err;
+}
+
+static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
+				     void *context)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	struct mlx5e_tx_err_ctx *err_ctx = context;
+
+	return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) :
+			 mlx5e_tx_reporter_recover_all(priv);
+}
+
+static int
+mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
+					u32 sqn, u8 state, bool stopped)
+{
+	int err;
+
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "HW state", state);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	int i, err = 0;
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs");
+	if (err)
+		goto unlock;
+
+	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc;
+	     i++) {
+		struct mlx5e_txqsq *sq = priv->txq2sq[i];
+		u8 state;
+
+		err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
+		if (err)
+			break;
+
+		err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
+							      state,
+							      netif_xmit_stopped(sq->txq));
+		if (err)
+			break;
+	}
+	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+	if (err)
+		goto unlock;
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
+		.name = "tx",
+		.recover = mlx5e_tx_reporter_recover,
+		.diagnose = mlx5e_tx_reporter_diagnose,
+};
+
+#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500
+
+int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct devlink *devlink = priv_to_devlink(mdev);
+
+	priv->tx_reporter =
+		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
+					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
+					       true, priv);
+	if (IS_ERR_OR_NULL(priv->tx_reporter))
+		netdev_warn(priv->netdev,
+			    "Failed to create tx reporter, err = %ld\n",
+			    PTR_ERR(priv->tx_reporter));
+	return PTR_ERR_OR_ZERO(priv->tx_reporter);
+}
+
+void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
+{
+	if (IS_ERR_OR_NULL(priv->tx_reporter))
+		return;
+
+	devlink_health_reporter_destroy(priv->tx_reporter);
+}

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -51,6 +51,7 @@
 #include "en/xdp.h"
 #include "lib/eq.h"
 #include "en/monitor_stats.h"
+#include "en/reporter.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -1159,7 +1160,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	return 0;
 }
 
-static void mlx5e_sq_recover(struct work_struct *work);
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
 static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
 			     struct mlx5e_params *params,
@@ -1181,7 +1182,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
-	INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
+	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev))
@@ -1269,15 +1270,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 	return err;
 }
 
-struct mlx5e_modify_sq_param {
-	int curr_state;
-	int next_state;
-	bool rl_update;
-	int rl_index;
-};
-
-static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
-			   struct mlx5e_modify_sq_param *p)
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p)
 {
 	void *in;
 	void *sqc;
@@ -1375,17 +1369,7 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c,
 	return err;
 }
 
-static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
-{
-	WARN_ONCE(sq->cc != sq->pc,
-		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
-		  sq->sqn, sq->cc, sq->pc);
-	sq->cc = 0;
-	sq->dma_fifo_cc = 0;
-	sq->pc = 0;
-}
-
-static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 {
 	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
@@ -1394,7 +1378,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 	netif_tx_start_queue(sq->txq);
 }
 
-static inline void netif_tx_disable_queue(struct netdev_queue *txq)
+void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
 	netif_tx_stop_queue(txq);
@@ -1410,7 +1394,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* prevent netif_tx_wake_queue */
 	napi_synchronize(&c->napi);
 
-	netif_tx_disable_queue(sq->txq);
+	mlx5e_tx_disable_queue(sq->txq);
 
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
@@ -1430,6 +1414,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	struct mlx5_rate_limit rl = {0};
 
 	cancel_work_sync(&sq->dim.work);
+	cancel_work_sync(&sq->recover_work);
 	mlx5e_destroy_sq(mdev, sq->sqn);
 	if (sq->rate_limit) {
 		rl.rate = sq->rate_limit;
@@ -1439,105 +1424,12 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	mlx5e_free_txqsq(sq);
 }
 
-static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
-{
-	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
-
-	while (time_before(jiffies, exp_time)) {
-		if (sq->cc == sq->pc)
-			return 0;
-
-		msleep(20);
-	}
-
-	netdev_err(sq->channel->netdev,
-		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
-		   sq->sqn, sq->cc, sq->pc);
-
-	return -ETIMEDOUT;
-}
-
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 {
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	struct mlx5e_modify_sq_param msp = {0};
-	int err;
-
-	msp.curr_state = curr_state;
-	msp.next_state = MLX5_SQC_STATE_RST;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
-		return err;
-	}
-
-	memset(&msp, 0, sizeof(msp));
-	msp.curr_state = MLX5_SQC_STATE_RST;
-	msp.next_state = MLX5_SQC_STATE_RDY;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
-		return err;
-	}
-
-	return 0;
-}
-
-static void mlx5e_sq_recover(struct work_struct *work)
-{
-	struct mlx5e_txqsq_recover *recover =
-		container_of(work, struct mlx5e_txqsq_recover,
-			     recover_work);
-	struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq,
-					      recover);
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	u8 state;
-	int err;
-
-	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
-	if (err) {
-		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
-			   sq->sqn, err);
-		return;
-	}
-
-	if (state != MLX5_RQC_STATE_ERR) {
-		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
-		return;
-	}
-
-	netif_tx_disable_queue(sq->txq);
-
-	if (mlx5e_wait_for_sq_flush(sq))
-		return;
-
-	/* If the interval between two consecutive recovers per SQ is too
-	 * short, don't recover to avoid infinite loop of ERR_CQE -> recover.
-	 * If we reached this state, there is probably a bug that needs to be
-	 * fixed. let's keep the queue close and let tx timeout cleanup.
-	 */
-	if (jiffies_to_msecs(jiffies - recover->last_recover) <
-	    MLX5E_SQ_RECOVER_MIN_INTERVAL) {
-		netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n",
-			   sq->sqn);
-		return;
-	}
-
-	/* At this point, no new packets will arrive from the stack as TXQ is
-	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
-	 * pending WQEs.  SQ can safely reset the SQ.
-	 */
-	if (mlx5e_sq_to_ready(sq, state))
-		return;
+	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
+					      recover_work);
 
-	mlx5e_reset_txqsq_cc_pc(sq);
-	sq->stats->recover++;
-	recover->last_recover = jiffies;
-	mlx5e_activate_txqsq(sq);
+	mlx5e_tx_reporter_err_cqe(sq);
 }
 
 static int mlx5e_open_icosq(struct mlx5e_channel *c,
@@ -3236,6 +3128,7 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	int tc;
 
+	mlx5e_tx_reporter_destroy(priv);
 	for (tc = 0; tc < priv->profile->max_tc; tc++)
 		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 }
@@ -4953,6 +4846,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_initialize(priv);
 #endif
+	mlx5e_tx_reporter_create(priv);
 	return 0;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -513,8 +513,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 					      &sq->state)) {
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
-				queue_work(cq->channel->priv->wq,
-					   &sq->recover.recover_work);
+				if (!IS_ERR_OR_NULL(cq->channel->priv->tx_reporter))
+					queue_work(cq->channel->priv->wq,
+						   &sq->recover_work);
 			}
 			stats->cqe_err++;
 		}