net: Revert devlink health changes.

This reverts the devlink health changes from 9/17/2019,
Jiri wants things to be designed differently and it was
agreed that the easiest way to do this is start from the
beginning again.

Commits reverted:

cb5ccfbe
880ee82f
c7af343b
ff253fed
6f9d5613
fcd852c6
8a66704a
12bd0dce
aba25279
ce019faa
b8c45a03

And the follow-on build fix:

o33a0efa4Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/devlink-health.txt

-The health mechanism is targeted for Real Time Alerting, in order to know when
-something bad had happened to a PCI device
-- Provide alert debug information
-- Self healing
-- If problem needs vendor support, provide a way to gather all needed debugging
-  information.
-
-The main idea is to unify and centralize driver health reports in the
-generic devlink instance and allow the user to set different
-attributes of the health reporting and recovery procedures.
-
-The devlink health reporter:
-Device driver creates a "health reporter" per each error/health type.
-Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error)
-or unknown (driver specific).
-For each registered health reporter a driver can issue error/health reports
-asynchronously. All health reports handling is done by devlink.
-Device driver can provide specific callbacks for each "health reporter", e.g.
- - Recovery procedures
- - Diagnostics and object dump procedures
- - OOB initial parameters
-Different parts of the driver can register different types of health reporters
-with different handlers.
-
-Once an error is reported, devlink health will do the following actions:
-  * A log is being send to the kernel trace events buffer
-  * Health status and statistics are being updated for the reporter instance
-  * Object dump is being taken and saved at the reporter instance (as long as
-    there is no other dump which is already stored)
-  * Auto recovery attempt is being done. Depends on:
-    - Auto-recovery configuration
-    - Grace period vs. time passed since last recover
-
-The user interface:
-User can access/change each reporter's parameters and driver specific callbacks
-via devlink, e.g per error type (per health reporter)
- - Configure reporter's generic parameters (like: disable/enable auto recovery)
- - Invoke recovery procedure
- - Run diagnostics
- - Object dump
-
-The devlink health interface (via netlink):
-DEVLINK_CMD_HEALTH_REPORTER_GET
-  Retrieves status and configuration info per DEV and reporter.
-DEVLINK_CMD_HEALTH_REPORTER_SET
-  Allows reporter-related configuration setting.
-DEVLINK_CMD_HEALTH_REPORTER_RECOVER
-  Triggers a reporter's recovery procedure.
-DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE
-  Retrieves diagnostics data from a reporter on a device.
-DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET
-  Retrieves the last stored dump. Devlink health
-  saves a single dump. If an dump is not already stored by the devlink
-  for this reporter, devlink generates a new dump.
-  dump output is defined by the reporter.
-DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR
-  Clears the last saved dump file for the specified reporter.
-
-
-                                               netlink
-                                      +--------------------------+
-                                      |                          |
-                                      |            +             |
-                                      |            |             |
-                                      +--------------------------+
-                                                   |request for ops
-                                                   |(diagnose,
- mlx5_core                             devlink     |recover,
-                                                   |dump)
-+--------+                            +--------------------------+
-|        |                            |    reporter|             |
-|        |                            |  +---------v----------+  |
-|        |   ops execution            |  |                    |  |
-|     <----------------------------------+                    |  |
-|        |                            |  |                    |  |
-|        |                            |  + ^------------------+  |
-|        |                            |    | request for ops     |
-|        |                            |    | (recover, dump)     |
-|        |                            |    |                     |
-|        |                            |  +-+------------------+  |
-|        |     health report          |  | health handler     |  |
-|        +------------------------------->                    |  |
-|        |                            |  +--------------------+  |
-|        |     health reporter create |                          |
-|        +---------------------------->                          |
-+--------+                            +--------------------------+

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/reporter_tx.o
+		en_selftest.o en/port.o en/monitor_stats.o
 
 #
 # Netdev extra

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

@@ -388,7 +388,10 @@ struct mlx5e_txqsq {
 	struct mlx5e_channel      *channel;
 	int                        txq_ix;
 	u32                        rate_limit;
-	struct work_struct         recover_work;
+	struct mlx5e_txqsq_recover {
+		struct work_struct         recover_work;
+		u64                        last_recover;
+	} recover;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_dma_info {
@@ -679,13 +682,6 @@ 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];
@@ -741,7 +737,6 @@ struct mlx5e_priv {
 #ifdef CONFIG_MLX5_EN_TLS
 	struct mlx5e_tls          *tls;
 #endif
-	struct devlink_health_reporter *tx_reporter;
 };
 
 struct mlx5e_profile {
@@ -871,11 +866,6 @@ 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 OR Linux-OpenIB */
-/* Copyright (c) 2018 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);
-void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
-
-#endif

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

-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2018 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_RQC_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);
-}
-
-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.
- */
-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;
-
-	mutex_lock(&priv->state_lock);
-	mlx5e_close_locked(priv->netdev);
-	err = mlx5e_open_locked(priv->netdev);
-	mutex_unlock(&priv->state_lock);
-
-	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_health_buffer *buffer,
-					u32 sqn, u8 state, u8 stopped)
-{
-	int err, i;
-	int nest = 0;
-	char name[20];
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	sprintf(name, "SQ 0x%x", sqn);
-	err = devlink_health_buffer_put_object_name(buffer, name);
-	if (err)
-		goto buffer_error;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_put_object_name(buffer, "HW state");
-	if (err)
-		goto buffer_error;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_put_value_u8(buffer, state);
-	if (err)
-		goto buffer_error;
-
-	devlink_health_buffer_nest_end(buffer); /* DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE */
-	nest--;
-
-	devlink_health_buffer_nest_end(buffer); /* DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR */
-	nest--;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_put_object_name(buffer, "stopped");
-	if (err)
-		goto buffer_error;
-
-	err = devlink_health_buffer_nest_start(buffer,
-					       DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE);
-	if (err)
-		goto buffer_error;
-	nest++;
-
-	err = devlink_health_buffer_put_value_u8(buffer, stopped);
-	if (err)
-		goto buffer_error;
-
-	for (i = 0; i < nest; i++)
-		devlink_health_buffer_nest_end(buffer);
-
-	return 0;
-
-buffer_error:
-	for (i = 0; i < nest; i++)
-		devlink_health_buffer_nest_cancel(buffer);
-	return err;
-}
-
-static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
-				      struct devlink_health_buffer **buffers_array,
-				      unsigned int buffer_size,
-				      unsigned int num_buffers)
-{
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
-	unsigned int buff = 0;
-	int i = 0, err = 0;
-
-	if (buffer_size < MLX5E_TX_REPORTER_PER_SQ_MAX_LEN)
-		return -ENOMEM;
-
-	mutex_lock(&priv->state_lock);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		mutex_unlock(&priv->state_lock);
-		return 0;
-	}
-
-	while (i < priv->channels.num * priv->channels.params.num_tc) {
-		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(buffers_array[buff],
-							      sq->sqn, state,
-							      netif_xmit_stopped(sq->txq));
-		if (err) {
-			if (++buff == num_buffers)
-				break;
-		} else {
-			i++;
-		}
-	}
-
-	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_size = MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC *
-				 MLX5E_TX_REPORTER_PER_SQ_MAX_LEN,
-		.diagnose = mlx5e_tx_reporter_diagnose,
-		.dump_size = 0,
-		.dump = NULL,
-};
-
-#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);
-	return PTR_ERR_OR_ZERO(priv->tx_reporter);
-}
-
-void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
-{
-	devlink_health_reporter_destroy(priv->tx_reporter);
-}

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

@@ -51,7 +51,6 @@
 #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)];
@@ -1161,7 +1160,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	return 0;
 }
 
-static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
+static void mlx5e_sq_recover(struct work_struct *work);
 static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
 			     struct mlx5e_params *params,
@@ -1183,7 +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_work, mlx5e_tx_err_cqe_work);
+	INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev))
@@ -1271,8 +1270,15 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 	return err;
 }
 
-int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
-		    struct mlx5e_modify_sq_param *p)
+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)
 {
 	void *in;
 	void *sqc;
@@ -1370,7 +1376,17 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c,
 	return err;
 }
 
-void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+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)
 {
 	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
@@ -1379,7 +1395,7 @@ void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 	netif_tx_start_queue(sq->txq);
 }
 
-void mlx5e_tx_disable_queue(struct netdev_queue *txq)
+static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
 	netif_tx_stop_queue(txq);
@@ -1395,7 +1411,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* prevent netif_tx_wake_queue */
 	napi_synchronize(&c->napi);
 
-	mlx5e_tx_disable_queue(sq->txq);
+	netif_tx_disable_queue(sq->txq);
 
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
@@ -1415,7 +1431,6 @@ 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;
@@ -1425,15 +1440,105 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	mlx5e_free_txqsq(sq);
 }
 
-static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
+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)
 {
-	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
-					      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;
 
-	if (!sq->channel->priv->tx_reporter)
+	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;
 
-	mlx5e_tx_reporter_err_cqe(sq);
+	/* 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;
+
+	mlx5e_reset_txqsq_cc_pc(sq);
+	sq->stats->recover++;
+	recover->last_recover = jiffies;
+	mlx5e_activate_txqsq(sq);
 }
 
 static int mlx5e_open_icosq(struct mlx5e_channel *c,
@@ -3102,7 +3207,6 @@ 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]);
 }
@@ -4074,14 +4178,31 @@ 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);
-	int i;
-
-	if (!priv->tx_reporter)
-		return;
+	struct net_device *dev = priv->netdev;
+	bool reopen_channels = false;
+	int i, err;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
@@ -4090,16 +4211,36 @@ 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(priv->netdev, i);
+		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
 		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
 
-		mlx5e_tx_reporter_timeout(sq);
+		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;
+		}
 	}
 
+	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();
@@ -4767,7 +4908,6 @@ 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

@@ -514,7 +514,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
 				queue_work(cq->channel->priv->wq,
-					   &sq->recover_work);
+					   &sq->recover.recover_work);
 			}
 			stats->cqe_err++;
 		}

include/net/devlink.h

@@ -30,7 +30,6 @@ struct devlink {
 	struct list_head param_list;
 	struct list_head region_list;
 	u32 snapshot_id;
-	struct list_head reporter_list;
 	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
@@ -424,36 +423,6 @@ struct devlink_region;
 
 typedef void devlink_snapshot_data_dest_t(const void *data);
 
-struct devlink_health_buffer;
-struct devlink_health_reporter;
-
-/**
- * struct devlink_health_reporter_ops - Reporter operations
- * @name: reporter name
- * dump_size: dump buffer size allocated by the devlink
- * diagnose_size: diagnose buffer size allocated by the devlink
- * recover: callback to recover from reported error
- *          if priv_ctx is NULL, run a full recover
- * dump: callback to dump an object
- *       if priv_ctx is NULL, run a full dump
- * diagnose: callback to diagnose the current status
- */
-
-struct devlink_health_reporter_ops {
-	char *name;
-	unsigned int dump_size;
-	unsigned int diagnose_size;
-	int (*recover)(struct devlink_health_reporter *reporter,
-		       void *priv_ctx);
-	int (*dump)(struct devlink_health_reporter *reporter,
-		    struct devlink_health_buffer **buffers_array,
-		    unsigned int buffer_size, unsigned int num_buffers,
-		    void *priv_ctx);
-	int (*diagnose)(struct devlink_health_reporter *reporter,
-			struct devlink_health_buffer **buffers_array,
-			unsigned int buffer_size, unsigned int num_buffers);
-};
-
 struct devlink_ops {
 	int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
@@ -615,34 +584,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
 				   u8 *data, u32 snapshot_id,
 				   devlink_snapshot_data_dest_t *data_destructor);
 
-int devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer,
-				     int attrtype);
-void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer);
-void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer);
-int devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer,
-					  char *name);
-int devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer,
-				       u8 value);
-int devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer,
-					u32 value);
-int devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer,
-					u64 value);
-int devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer,
-					   char *name);
-int devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer,
-					 void *data, int len);
-struct devlink_health_reporter *
-devlink_health_reporter_create(struct devlink *devlink,
-			       const struct devlink_health_reporter_ops *ops,
-			       u64 graceful_period, bool auto_recover,
-			       void *priv);
-void
-devlink_health_reporter_destroy(struct devlink_health_reporter *reporter);
-
-void *
-devlink_health_reporter_priv(struct devlink_health_reporter *reporter);
-int devlink_health_report(struct devlink_health_reporter *reporter,
-			  const char *msg, void *priv_ctx);
 #else
 
 static inline struct devlink *devlink_alloc(const struct devlink_ops *ops,
@@ -903,91 +844,6 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
 	return 0;
 }
 
-static inline int
-devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer,
-				 int attrtype)
-{
-	return 0;
-}
-
-static inline void
-devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer)
-{
-}
-
-static inline void
-devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer)
-{
-}
-
-static inline int
-devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer,
-				      char *name)
-{
-	return 0;
-}
-
-static inline int
-devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer,
-				   u8 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer,
-				    u32 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer,
-				    u64 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer,
-				       char *name)
-{
-	return 0;
-}
-
-static inline int
-devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer,
-				     void *data, int len)
-{
-	return 0;
-}
-
-static inline struct devlink_health_reporter *
-devlink_health_reporter_create(struct devlink *devlink,
-			       const struct devlink_health_reporter_ops *ops,
-			       u64 graceful_period, bool auto_recover,
-			       void *priv)
-{
-	return NULL;
-}
-
-static inline void
-devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
-{
-}
-
-static inline void *
-devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
-{
-	return NULL;
-}
-
-static inline int
-devlink_health_report(struct devlink_health_reporter *reporter,
-		      const char *msg, void *priv_ctx)
-{
-	return 0;
-}
 #endif
 
 #endif /* _NET_DEVLINK_H_ */

include/trace/events/devlink.h

@@ -46,65 +46,6 @@ TRACE_EVENT(devlink_hwmsg,
 		  (int) __entry->len, __get_dynamic_array(buf), __entry->len)
 );
 
-TRACE_EVENT(devlink_health_report,
-	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
-		 const char *msg),
-
-	TP_ARGS(devlink, reporter_name, msg),
-
-	TP_STRUCT__entry(
-		__string(bus_name, devlink->dev->bus->name)
-		__string(dev_name, dev_name(devlink->dev))
-		__string(driver_name, devlink->dev->driver->name)
-		__string(reporter_name, msg)
-		__string(msg, msg)
-	),
-
-	TP_fast_assign(
-		__assign_str(bus_name, devlink->dev->bus->name);
-		__assign_str(dev_name, dev_name(devlink->dev));
-		__assign_str(driver_name, devlink->dev->driver->name);
-		__assign_str(reporter_name, reporter_name);
-		__assign_str(msg, msg);
-	),
-
-	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s",
-		  __get_str(bus_name), __get_str(dev_name),
-		  __get_str(driver_name), __get_str(reporter_name),
-		  __get_str(msg))
-);
-
-TRACE_EVENT(devlink_health_recover_aborted,
-	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
-		 bool health_state, u64 time_since_last_recover),
-
-	TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover),
-
-	TP_STRUCT__entry(
-		__string(bus_name, devlink->dev->bus->name)
-		__string(dev_name, dev_name(devlink->dev))
-		__string(driver_name, devlink->dev->driver->name)
-		__string(reporter_name, reporter_name)
-		__field(bool, health_state)
-		__field(u64, time_since_last_recover)
-	),
-
-	TP_fast_assign(
-		__assign_str(bus_name, devlink->dev->bus->name);
-		__assign_str(dev_name, dev_name(devlink->dev));
-		__assign_str(driver_name, devlink->dev->driver->name);
-		__assign_str(reporter_name, reporter_name);
-		__entry->health_state = health_state;
-		__entry->time_since_last_recover = time_since_last_recover;
-	),
-
-	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover = %llu recover aborted",
-		  __get_str(bus_name), __get_str(dev_name),
-		  __get_str(driver_name), __get_str(reporter_name),
-		  __entry->health_state,
-		  __entry->time_since_last_recover)
-);
-
 #endif /* _TRACE_DEVLINK_H */
 
 /* This part must be outside protection */
@@ -123,9 +64,6 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink,
 {
 }
 
-static inline void trace_devlink_health(const char *msg)
-{
-}
 #endif /* _TRACE_DEVLINK_H */
 
 #endif

include/uapi/linux/devlink.h

@@ -89,13 +89,6 @@ enum devlink_command {
 	DEVLINK_CMD_REGION_DEL,
 	DEVLINK_CMD_REGION_READ,
 
-	DEVLINK_CMD_HEALTH_REPORTER_GET,
-	DEVLINK_CMD_HEALTH_REPORTER_SET,
-	DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
-	DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
-	DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
-	DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
-
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -292,24 +285,6 @@ enum devlink_attr {
 	DEVLINK_ATTR_REGION_CHUNK_ADDR,         /* u64 */
 	DEVLINK_ATTR_REGION_CHUNK_LEN,          /* u64 */
 
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT,		/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR,		/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME,		/* string */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE,	/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY,	/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE,	/* u8 */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA,	/* dynamic */
-
-	DEVLINK_ATTR_HEALTH_REPORTER,			/* nested */
-	DEVLINK_ATTR_HEALTH_REPORTER_NAME,		/* string */
-	DEVLINK_ATTR_HEALTH_REPORTER_STATE,		/* u8 */
-	DEVLINK_ATTR_HEALTH_REPORTER_ERR,		/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_RECOVER,		/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL,	/* u8 */
-	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,		/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,	/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,	/* u8 */
-
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,