Merge tag 'mlx5-updates-2019-08-15' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-08-15

This patchset introduces changes in mlx5 devlink health reporters.
The highlight of these changes is adding a new reporter: RX reporter

mlx5 RX reporter: reports and recovers from timeouts and RX completion
error.

1) Perform TX reporter cleanup. In order to maintain the
code flow as similar as possible between RX and TX reporters, start the
set with cleanup.

2) Prepare for code sharing, generalize and move shared
functionality.

3) Refactor and extend TX reporter diagnostics information
to align the TX reporter diagnostics output with the RX reporter's
diagnostics output.

4) Add helper functions Patch 11: Add RX reporter, initially
supports only the diagnostics call back.

5) Change ICOSQ (Internal Operations Send Queue) open/close flow to
avoid race between interface down and completion error recovery.

6) Introduce recovery flows for RX ring population timeout on ICOSQ,
and for completion errors on ICOSQ and on RQ (Regular receive queues).

7) Include RX reporters in mlx5 documentation.

8) Last two patches of this series, are trivial fixes for previously
submitted patches on this release cycle.
====================

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

18 files changed, 965 insertions, 207 deletions

diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst
index 214325897732..cfda464e52de 100644
--- a/Documentation/networking/device_drivers/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst
@@ -126,7 +126,7 @@ Devlink health reporters
 
 tx reporter
 -----------
-The tx reporter is responsible of two error scenarios:
+The tx reporter is responsible for reporting and recovering of the following two error scenarios:
 
 - TX timeout
     Report on kernel tx timeout detection.
@@ -135,7 +135,7 @@ The tx reporter is responsible of two error scenarios:
     Report on error tx completion.
     Recover by flushing the TX queue and reset it.
 
-TX reporter also support Diagnose callback, on which it provides
+TX reporter also support on demand diagnose callback, on which it provides
 real time information of its send queues status.
 
 User commands examples:
@@ -144,11 +144,40 @@ User commands examples:
 
     $ devlink health diagnose pci/0000:82:00.0 reporter tx
 
+NOTE: This command has valid output only when interface is up, otherwise the command has empty output.
+
 - Show number of tx errors indicated, number of recover flows ended successfully,
   is autorecover enabled and graceful period from last recover::
 
     $ devlink health show pci/0000:82:00.0 reporter tx
 
+rx reporter
+-----------
+The rx reporter is responsible for reporting and recovering of the following two error scenarios:
+
+- RX queues initialization (population) timeout
+    RX queues descriptors population on ring initialization is done in
+    napi context via triggering an irq, in case of a failure to get
+    the minimum amount of descriptors, a timeout would occur and it
+    could be recoverable by polling the EQ (Event Queue).
+- RX completions with errors (reported by HW on interrupt context)
+    Report on rx completion error.
+    Recover (if needed) by flushing the related queue and reset it.
+
+RX reporter also supports on demand diagnose callback, on which it
+provides real time information of its receive queues status.
+
+- Diagnose rx queues status, and corresponding completion queue::
+
+    $ devlink health diagnose pci/0000:82:00.0 reporter rx
+
+NOTE: This command has valid output only when interface is up, otherwise the command has empty output.
+
+- Show number of rx errors indicated, number of recover flows ended successfully,
+  is autorecover enabled and graceful period from last recover::
+
+    $ devlink health show pci/0000:82:00.0 reporter rx
+
 fw reporter
 -----------
 The fw reporter implements diagnose and dump callbacks.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 57d2cc666fe3..a3b9659649a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -23,8 +23,9 @@ 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/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
+		en_selftest.o en/port.o en/monitor_stats.o en/health.o \
+		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \
+		en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
 
 #
 # Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8cf548c7ad9c..7316571a4df5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -300,6 +300,7 @@ struct mlx5e_dcbx_dp {
 
 enum {
 	MLX5E_RQ_STATE_ENABLED,
+	MLX5E_RQ_STATE_RECOVERING,
 	MLX5E_RQ_STATE_AM,
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
 	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
@@ -551,6 +552,8 @@ struct mlx5e_icosq {
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
 	struct mlx5e_channel      *channel;
+
+	struct work_struct         recover_work;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_wqe_frag_info {
@@ -670,6 +673,8 @@ struct mlx5e_rq {
 	struct zero_copy_allocator zca;
 	struct xdp_umem       *umem;
 
+	struct work_struct     recover_work;
+
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
 	__be32                 mkey_be;
@@ -846,6 +851,7 @@ struct mlx5e_priv {
 	struct mlx5e_tls          *tls;
 #endif
 	struct devlink_health_reporter *tx_reporter;
+	struct devlink_health_reporter *rx_reporter;
 	struct mlx5e_xsk           xsk;
 };
 
@@ -887,6 +893,26 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
 
+static inline u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
+{
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
+	default:
+		return mlx5_wq_cyc_get_size(&rq->wqe.wq);
+	}
+}
+
+static inline u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
+{
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return rq->mpwqe.wq.cur_sz;
+	default:
+		return rq->wqe.wq.cur_sz;
+	}
+}
+
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
@@ -1005,6 +1031,12 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 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_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
+void mlx5e_activate_rq(struct mlx5e_rq *rq);
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
+void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
+void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq);
 
 int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
 		    struct mlx5e_modify_sq_param *p);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
new file mode 100644
index 000000000000..1d6b58860da6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "health.h"
+#include "lib/eq.h"
+
+int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name)
+{
+	int err;
+
+	err = devlink_fmsg_pair_nest_start(fmsg, name);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg)
+{
+	int err;
+
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_pair_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = cq->channel->priv;
+	u32 out[MLX5_ST_SZ_DW(query_cq_out)] = {};
+	u8 hw_status;
+	void *cqc;
+	int err;
+
+	err = mlx5_core_query_cq(priv->mdev, &cq->mcq, out, sizeof(out));
+	if (err)
+		return err;
+
+	cqc = MLX5_ADDR_OF(query_cq_out, out, cq_context);
+	hw_status = MLX5_GET(cqc, cqc, status);
+
+	err = mlx5e_reporter_named_obj_nest_start(fmsg, "CQ");
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "cqn", cq->mcq.cqn);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "HW status", hw_status);
+	if (err)
+		return err;
+
+	err = mlx5e_reporter_named_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg)
+{
+	u8 cq_log_stride;
+	u32 cq_sz;
+	int err;
+
+	cq_sz = mlx5_cqwq_get_size(&cq->wq);
+	cq_log_stride = mlx5_cqwq_get_log_stride_size(&cq->wq);
+
+	err = mlx5e_reporter_named_obj_nest_start(fmsg, "CQ");
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u64_pair_put(fmsg, "stride size", BIT(cq_log_stride));
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "size", cq_sz);
+	if (err)
+		return err;
+
+	err = mlx5e_reporter_named_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int mlx5e_health_create_reporters(struct mlx5e_priv *priv)
+{
+	int err;
+
+	err = mlx5e_reporter_tx_create(priv);
+	if (err)
+		return err;
+
+	err = mlx5e_reporter_rx_create(priv);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv)
+{
+	mlx5e_reporter_rx_destroy(priv);
+	mlx5e_reporter_tx_destroy(priv);
+}
+
+void mlx5e_health_channels_update(struct mlx5e_priv *priv)
+{
+	if (priv->tx_reporter)
+		devlink_health_reporter_state_update(priv->tx_reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+	if (priv->rx_reporter)
+		devlink_health_reporter_state_update(priv->rx_reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+}
+
+int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn)
+{
+	struct mlx5_core_dev *mdev = channel->mdev;
+	struct net_device *dev = channel->netdev;
+	struct mlx5e_modify_sq_param msp = {};
+	int err;
+
+	msp.curr_state = MLX5_SQC_STATE_ERR;
+	msp.next_state = MLX5_SQC_STATE_RST;
+
+	err = mlx5e_modify_sq(mdev, sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to reset\n", 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, sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sqn);
+		return err;
+	}
+
+	return 0;
+}
+
+int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
+{
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
+	err = mlx5e_safe_reopen_channels(priv);
+
+out:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+
+	return err;
+}
+
+int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel)
+{
+	u32 eqe_count;
+
+	netdev_err(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)
+		return -EIO;
+
+	netdev_err(channel->netdev, "Recovered %d eqes on EQ 0x%x\n",
+		   eqe_count, eq->core.eqn);
+
+	channel->stats->eq_rearm++;
+	return 0;
+}
+
+int mlx5e_health_report(struct mlx5e_priv *priv,
+			struct devlink_health_reporter *reporter, char *err_str,
+			struct mlx5e_err_ctx *err_ctx)
+{
+	if (!reporter) {
+		netdev_err(priv->netdev, err_str);
+		return err_ctx->recover(&err_ctx->ctx);
+	}
+	return devlink_health_report(reporter, err_str, err_ctx);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
new file mode 100644
index 000000000000..d3693fa547ac
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5E_EN_HEALTH_H
+#define __MLX5E_EN_HEALTH_H
+
+#include "en.h"
+
+#define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)
+
+static inline bool cqe_syndrome_needs_recover(u8 syndrome)
+{
+	return syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR ||
+	       syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR ||
+	       syndrome == MLX5_CQE_SYNDROME_LOCAL_PROT_ERR ||
+	       syndrome == MLX5_CQE_SYNDROME_WR_FLUSH_ERR;
+}
+
+int mlx5e_reporter_tx_create(struct mlx5e_priv *priv);
+void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv);
+void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
+int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
+
+int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg);
+int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg);
+int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name);
+int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg);
+
+int mlx5e_reporter_rx_create(struct mlx5e_priv *priv);
+void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
+void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq);
+void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq);
+void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq);
+
+#define MLX5E_REPORTER_PER_Q_MAX_LEN 256
+
+struct mlx5e_err_ctx {
+	int (*recover)(void *ctx);
+	void *ctx;
+};
+
+int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn);
+int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel);
+int mlx5e_health_recover_channels(struct mlx5e_priv *priv);
+int mlx5e_health_report(struct mlx5e_priv *priv,
+			struct devlink_health_reporter *reporter, char *err_str,
+			struct mlx5e_err_ctx *err_ctx);
+int mlx5e_health_create_reporters(struct mlx5e_priv *priv);
+void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv);
+void mlx5e_health_channels_update(struct mlx5e_priv *priv);
+
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
deleted file mode 100644
index ed7a3881d2c5..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2019 Mellanox Technologies. */
-
-#ifndef __MLX5E_EN_REPORTER_H
-#define __MLX5E_EN_REPORTER_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);
-int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
-
-#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
new file mode 100644
index 000000000000..b860569d4247
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -0,0 +1,404 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "health.h"
+#include "params.h"
+
+static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_rq_out);
+	void *out;
+	void *rqc;
+	int err;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_core_query_rq(dev, rqn, out);
+	if (err)
+		goto out;
+
+	rqc = MLX5_ADDR_OF(query_rq_out, out, rq_context);
+	*state = MLX5_GET(rqc, rqc, state);
+
+out:
+	kvfree(out);
+	return err;
+}
+
+static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq)
+{
+	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+
+	while (time_before(jiffies, exp_time)) {
+		if (icosq->cc == icosq->pc)
+			return 0;
+
+		msleep(20);
+	}
+
+	netdev_err(icosq->channel->netdev,
+		   "Wait for ICOSQ 0x%x flush timeout (cc = 0x%x, pc = 0x%x)\n",
+		   icosq->sqn, icosq->cc, icosq->pc);
+
+	return -ETIMEDOUT;
+}
+
+static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq)
+{
+	WARN_ONCE(icosq->cc != icosq->pc, "ICOSQ 0x%x: cc (0x%x) != pc (0x%x)\n",
+		  icosq->sqn, icosq->cc, icosq->pc);
+	icosq->cc = 0;
+	icosq->pc = 0;
+}
+
+static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
+{
+	struct mlx5_core_dev *mdev;
+	struct mlx5e_icosq *icosq;
+	struct net_device *dev;
+	struct mlx5e_rq *rq;
+	u8 state;
+	int err;
+
+	icosq = ctx;
+	rq = &icosq->channel->rq;
+	mdev = icosq->channel->mdev;
+	dev = icosq->channel->netdev;
+	err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state);
+	if (err) {
+		netdev_err(dev, "Failed to query ICOSQ 0x%x state. err = %d\n",
+			   icosq->sqn, err);
+		goto out;
+	}
+
+	if (state != MLX5_SQC_STATE_ERR)
+		goto out;
+
+	mlx5e_deactivate_rq(rq);
+	err = mlx5e_wait_for_icosq_flush(icosq);
+	if (err)
+		goto out;
+
+	mlx5e_deactivate_icosq(icosq);
+
+	/* At this point, both the rq and the icosq are disabled */
+
+	err = mlx5e_health_sq_to_ready(icosq->channel, icosq->sqn);
+	if (err)
+		goto out;
+
+	mlx5e_reset_icosq_cc_pc(icosq);
+	mlx5e_free_rx_descs(rq);
+	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	mlx5e_activate_icosq(icosq);
+	mlx5e_activate_rq(rq);
+
+	rq->stats->recover++;
+	return 0;
+out:
+	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	return err;
+}
+
+void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq)
+{
+	struct mlx5e_priv *priv = icosq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx = {};
+
+	err_ctx.ctx = icosq;
+	err_ctx.recover = mlx5e_rx_reporter_err_icosq_cqe_recover;
+	sprintf(err_str, "ERR CQE on ICOSQ: 0x%x", icosq->sqn);
+
+	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
+}
+
+static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state)
+{
+	struct net_device *dev = rq->netdev;
+	int err;
+
+	err = mlx5e_modify_rq_state(rq, curr_state, MLX5_RQC_STATE_RST);
+	if (err) {
+		netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn);
+		return err;
+	}
+	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
+	if (err) {
+		netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn);
+		return err;
+	}
+
+	return 0;
+}
+
+static int mlx5e_rx_reporter_err_rq_cqe_recover(void *ctx)
+{
+	struct mlx5_core_dev *mdev;
+	struct net_device *dev;
+	struct mlx5e_rq *rq;
+	u8 state;
+	int err;
+
+	rq = ctx;
+	mdev = rq->mdev;
+	dev = rq->netdev;
+	err = mlx5e_query_rq_state(mdev, rq->rqn, &state);
+	if (err) {
+		netdev_err(dev, "Failed to query RQ 0x%x state. err = %d\n",
+			   rq->rqn, err);
+		goto out;
+	}
+
+	if (state != MLX5_RQC_STATE_ERR)
+		goto out;
+
+	mlx5e_deactivate_rq(rq);
+	mlx5e_free_rx_descs(rq);
+
+	err = mlx5e_rq_to_ready(rq, MLX5_RQC_STATE_ERR);
+	if (err)
+		goto out;
+
+	clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state);
+	mlx5e_activate_rq(rq);
+	rq->stats->recover++;
+	return 0;
+out:
+	clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state);
+	return err;
+}
+
+void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq)
+{
+	struct mlx5e_priv *priv = rq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx = {};
+
+	err_ctx.ctx = rq;
+	err_ctx.recover = mlx5e_rx_reporter_err_rq_cqe_recover;
+	sprintf(err_str, "ERR CQE on RQ: 0x%x", rq->rqn);
+
+	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
+}
+
+static int mlx5e_rx_reporter_timeout_recover(void *ctx)
+{
+	struct mlx5e_icosq *icosq;
+	struct mlx5_eq_comp *eq;
+	struct mlx5e_rq *rq;
+	int err;
+
+	rq = ctx;
+	icosq = &rq->channel->icosq;
+	eq = rq->cq.mcq.eq;
+	err = mlx5e_health_channel_eq_recover(eq, rq->channel);
+	if (err)
+		clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
+
+	return err;
+}
+
+void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
+{
+	struct mlx5e_icosq *icosq = &rq->channel->icosq;
+	struct mlx5e_priv *priv = rq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx = {};
+
+	err_ctx.ctx = rq;
+	err_ctx.recover = mlx5e_rx_reporter_timeout_recover;
+	sprintf(err_str, "RX timeout on channel: %d, ICOSQ: 0x%x RQ: 0x%x, CQ: 0x%x\n",
+		icosq->channel->ix, icosq->sqn, rq->rqn, rq->cq.mcq.cqn);
+
+	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
+}
+
+static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
+{
+	return err_ctx->recover(err_ctx->ctx);
+}
+
+static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter,
+				     void *context)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	struct mlx5e_err_ctx *err_ctx = context;
+
+	return err_ctx ? mlx5e_rx_reporter_recover_from_ctx(err_ctx) :
+			 mlx5e_health_recover_channels(priv);
+}
+
+static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq,
+						   struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = rq->channel->priv;
+	struct mlx5e_params *params;
+	struct mlx5e_icosq *icosq;
+	u8 icosq_hw_state;
+	int wqes_sz;
+	u8 hw_state;
+	u16 wq_head;
+	int err;
+
+	params = &priv->channels.params;
+	icosq = &rq->channel->icosq;
+	err = mlx5e_query_rq_state(priv->mdev, rq->rqn, &hw_state);
+	if (err)
+		return err;
+
+	err = mlx5_core_query_sq_state(priv->mdev, icosq->sqn, &icosq_hw_state);
+	if (err)
+		return err;
+
+	wqes_sz = mlx5e_rqwq_get_cur_sz(rq);
+	wq_head = params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
+		  rq->mpwqe.wq.head : mlx5_wq_cyc_get_head(&rq->wqe.wq);
+
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->channel->ix);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "rqn", rq->rqn);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "SW state", rq->state);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "posted WQEs", wqes_sz);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "cc", wq_head);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "ICOSQ HW state", icosq_hw_state);
+	if (err)
+		return err;
+
+	err = mlx5e_reporter_cq_diagnose(&rq->cq, fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	struct mlx5e_params *params = &priv->channels.params;
+	struct mlx5e_rq *generic_rq;
+	u32 rq_stride, rq_sz;
+	int i, err = 0;
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	generic_rq = &priv->channels.c[0]->rq;
+	rq_sz = mlx5e_rqwq_get_size(generic_rq);
+	rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL));
+
+	err = mlx5e_reporter_named_obj_nest_start(fmsg, "Common config");
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_named_obj_nest_start(fmsg, "RQ");
+	if (err)
+		goto unlock;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type);
+	if (err)
+		goto unlock;
+
+	err = devlink_fmsg_u64_pair_put(fmsg, "stride size", rq_stride);
+	if (err)
+		goto unlock;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "size", rq_sz);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_named_obj_nest_end(fmsg);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_cq_common_diagnose(&generic_rq->cq, fmsg);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_named_obj_nest_end(fmsg);
+	if (err)
+		goto unlock;
+
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "RQs");
+	if (err)
+		goto unlock;
+
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+
+		err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
+		if (err)
+			goto unlock;
+	}
+	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_rx_reporter_ops = {
+	.name = "rx",
+	.recover = mlx5e_rx_reporter_recover,
+	.diagnose = mlx5e_rx_reporter_diagnose,
+};
+
+#define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500
+
+int mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
+{
+	struct devlink *devlink = priv_to_devlink(priv->mdev);
+	struct devlink_health_reporter *reporter;
+
+	reporter = devlink_health_reporter_create(devlink,
+						  &mlx5_rx_reporter_ops,
+						  MLX5E_REPORTER_RX_GRACEFUL_PERIOD,
+						  true, priv);
+	if (IS_ERR(reporter)) {
+		netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n",
+			    PTR_ERR(reporter));
+		return PTR_ERR(reporter);
+	}
+	priv->rx_reporter = reporter;
+	return 0;
+}
+
+void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv)
+{
+	if (!priv->rx_reporter)
+		return;
+
+	devlink_health_reporter_destroy(priv->rx_reporter);
+}
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 817c6ea7e349..bfed558637c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -1,15 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2019 Mellanox Technologies. */
 
-#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;
-};
+#include "health.h"
 
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
 {
@@ -39,41 +31,20 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
 	sq->pc = 0;
 }
 
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 {
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	struct mlx5e_modify_sq_param msp = {0};
+	struct mlx5_core_dev *mdev;
+	struct net_device *dev;
+	struct mlx5e_txqsq *sq;
+	u8 state;
 	int err;
 
-	msp.curr_state = curr_state;
-	msp.next_state = MLX5_SQC_STATE_RST;
+	sq = ctx;
+	mdev = sq->channel->mdev;
+	dev = sq->channel->netdev;
 
-	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) {
@@ -96,7 +67,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
 	 * pending WQEs. SQ can safely reset the SQ.
 	 */
 
-	err = mlx5e_sq_to_ready(sq, state);
+	err = mlx5e_health_sq_to_ready(sq->channel, sq->sqn);
 	if (err)
 		goto out;
 
@@ -111,115 +82,98 @@ out:
 	return err;
 }
 
-static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
-				 char *err_str,
-				 struct mlx5e_tx_err_ctx *err_ctx)
-{
-	if (!tx_reporter) {
-		netdev_err(err_ctx->sq->channel->netdev, err_str);
-		return err_ctx->recover(err_ctx->sq);
-	}
-
-	return devlink_health_report(tx_reporter, err_str, err_ctx);
-}
-
-void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
+void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq)
 {
-	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
-	struct mlx5e_tx_err_ctx err_ctx = {0};
+	struct mlx5e_priv *priv = sq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx = {0};
 
-	err_ctx.sq       = sq;
-	err_ctx.recover  = mlx5e_tx_reporter_err_cqe_recover;
+	err_ctx.ctx = sq;
+	err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover;
 	sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
 
-	mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
-			      &err_ctx);
+	mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
 }
 
-static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
+static int mlx5e_tx_reporter_timeout_recover(void *ctx)
 {
-	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);
+	struct mlx5_eq_comp *eq;
+	struct mlx5e_txqsq *sq;
+	int err;
 
-	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	if (!eqe_count) {
+	sq = ctx;
+	eq = sq->cq.mcq.eq;
+	err = mlx5e_health_channel_eq_recover(eq, sq->channel);
+	if (err)
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-		return -EIO;
-	}
 
-	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;
+	return err;
 }
 
-int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
+int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
 {
-	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
-	struct mlx5e_tx_err_ctx err_ctx;
+	struct mlx5e_priv *priv = sq->channel->priv;
+	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+	struct mlx5e_err_ctx err_ctx;
 
-	err_ctx.sq       = sq;
-	err_ctx.recover  = mlx5e_tx_reporter_timeout_recover;
+	err_ctx.ctx = 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 mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
-				     &err_ctx);
+	return mlx5e_health_report(priv, 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.
  */
-static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
+static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
 {
-	return err_ctx->recover(err_ctx->sq);
-}
-
-static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
-{
-	int err = 0;
-
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto out;
-
-	err = mlx5e_safe_reopen_channels(priv);
-
-out:
-	mutex_unlock(&priv->state_lock);
-	rtnl_unlock();
-
-	return err;
+	return err_ctx->recover(err_ctx->ctx);
 }
 
 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;
+	struct mlx5e_err_ctx *err_ctx = context;
 
 	return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) :
-			 mlx5e_tx_reporter_recover_all(priv);
+			 mlx5e_health_recover_channels(priv);
 }
 
 static int
 mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
-					u32 sqn, u8 state, bool stopped)
+					struct mlx5e_txqsq *sq, int tc)
 {
+	struct mlx5e_priv *priv = sq->channel->priv;
+	bool stopped = netif_xmit_stopped(sq->txq);
+	u8 state;
 	int err;
 
+	err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
+	if (err)
+		return err;
+
 	err = devlink_fmsg_obj_nest_start(fmsg);
 	if (err)
 		return err;
 
-	err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn);
+	err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->ch_ix);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "tc", tc);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn);
 	if (err)
 		return err;
 
@@ -231,6 +185,18 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
 	if (err)
 		return err;
 
+	err = devlink_fmsg_u32_pair_put(fmsg, "cc", sq->cc);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "pc", sq->pc);
+	if (err)
+		return err;
+
+	err = mlx5e_reporter_cq_diagnose(&sq->cq, fmsg);
+	if (err)
+		return err;
+
 	err = devlink_fmsg_obj_nest_end(fmsg);
 	if (err)
 		return err;
@@ -242,31 +208,61 @@ 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;
+	struct mlx5e_txqsq *generic_sq = priv->txq2sq[0];
+	u32 sq_stride, sq_sz;
+
+	int i, tc, err = 0;
 
 	mutex_lock(&priv->state_lock);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		goto unlock;
 
+	sq_sz = mlx5_wq_cyc_get_size(&generic_sq->wq);
+	sq_stride = MLX5_SEND_WQE_BB;
+
+	err = mlx5e_reporter_named_obj_nest_start(fmsg, "Common Config");
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_named_obj_nest_start(fmsg, "SQ");
+	if (err)
+		goto unlock;
+
+	err = devlink_fmsg_u64_pair_put(fmsg, "stride size", sq_stride);
+	if (err)
+		goto unlock;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "size", sq_sz);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_cq_common_diagnose(&generic_sq->cq, fmsg);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_named_obj_nest_end(fmsg);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_reporter_named_obj_nest_end(fmsg);
+	if (err)
+		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;
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
 
-		err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
-		if (err)
-			goto unlock;
+		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+			struct mlx5e_txqsq *sq = &c->sq[tc];
 
-		err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
-							      state,
-							      netif_xmit_stopped(sq->txq));
-		if (err)
-			goto unlock;
+			err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq, tc);
+			if (err)
+				goto unlock;
+		}
 	}
 	err = devlink_fmsg_arr_pair_nest_end(fmsg);
 	if (err)
@@ -285,12 +281,13 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
 
 #define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500
 
-int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
+int mlx5e_reporter_tx_create(struct mlx5e_priv *priv)
 {
 	struct devlink_health_reporter *reporter;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct devlink *devlink = priv_to_devlink(mdev);
+	struct devlink *devlink;
 
+	devlink = priv_to_devlink(mdev);
 	reporter =
 		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
 					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
@@ -305,7 +302,7 @@ int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
 	return 0;
 }
 
-void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
+void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv)
 {
 	if (!priv->tx_reporter)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 2c4d1f415968..d360750b25b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -150,6 +150,7 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
 {
+	mlx5e_activate_icosq(&c->xskicosq);
 	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
 	/* TX queue is created active. */
 
@@ -162,6 +163,7 @@ void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
 {
 	mlx5e_deactivate_rq(&c->xskrq);
 	/* TX queue is disabled on close. */
+	mlx5e_deactivate_icosq(&c->xskicosq);
 }
 
 static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 35e188cf4ea4..fd2c75b4b519 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -26,6 +26,13 @@ int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid)
 		return -ENXIO;
 
 	if (!napi_if_scheduled_mark_missed(&c->napi)) {
+		/* To avoid WQE overrun, don't post a NOP if XSKICOSQ is not
+		 * active and not polled by NAPI. Return 0, because the upcoming
+		 * activate will trigger the IRQ for us.
+		 */
+		if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &c->xskicosq.state)))
+			return 0;
+
 		spin_lock(&c->xskicosq_lock);
 		mlx5e_trigger_irq(&c->xskicosq);
 		spin_unlock(&c->xskicosq_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0c8e847a9eee..7fdea6479ff6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -56,7 +56,7 @@
 #include "en/xdp.h"
 #include "lib/eq.h"
 #include "en/monitor_stats.h"
-#include "en/reporter.h"
+#include "en/health.h"
 #include "en/params.h"
 #include "en/xsk/umem.h"
 #include "en/xsk/setup.h"
@@ -247,26 +247,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
-static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
-{
-	switch (rq->wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
-	default:
-		return mlx5_wq_cyc_get_size(&rq->wqe.wq);
-	}
-}
-
-static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
-{
-	switch (rq->wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return rq->mpwqe.wq.cur_sz;
-	default:
-		return rq->wqe.wq.cur_sz;
-	}
-}
-
 static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 				     struct mlx5e_channel *c)
 {
@@ -382,6 +362,13 @@ static void mlx5e_free_di_list(struct mlx5e_rq *rq)
 	kvfree(rq->wqe.di);
 }
 
+static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_rq *rq = container_of(recover_work, struct mlx5e_rq, recover_work);
+
+	mlx5e_reporter_rq_cqe_err(rq);
+}
+
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk,
@@ -418,6 +405,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		rq->stats = &c->priv->channel_stats[c->ix].xskrq;
 	else
 		rq->stats = &c->priv->channel_stats[c->ix].rq;
+	INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work);
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
 	if (IS_ERR(rq->xdp_prog)) {
@@ -720,8 +708,7 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq,
 	return err;
 }
 
-static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
-				 int next_state)
+int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
 
@@ -829,10 +816,11 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
 		    c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes);
 
+	mlx5e_reporter_rx_timeout(rq);
 	return -ETIMEDOUT;
 }
 
-static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
 	__be16 wqe_ix_be;
 	u16 wqe_ix;
@@ -911,7 +899,7 @@ err_free_rq:
 	return err;
 }
 
-static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	mlx5e_trigger_irq(&rq->channel->icosq);
@@ -926,6 +914,8 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
+	cancel_work_sync(&rq->channel->icosq.recover_work);
+	cancel_work_sync(&rq->recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
 	mlx5e_free_rq(rq);
@@ -1042,6 +1032,14 @@ static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 	return 0;
 }
 
+static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	mlx5e_reporter_icosq_cqe_err(sq);
+}
+
 static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 			     struct mlx5e_sq_param *param,
 			     struct mlx5e_icosq *sq)
@@ -1064,6 +1062,8 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	if (err)
 		goto err_sq_wq_destroy;
 
+	INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work);
+
 	return 0;
 
 err_sq_wq_destroy:
@@ -1379,7 +1379,7 @@ static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
 					      recover_work);
 
-	mlx5e_tx_reporter_err_cqe(sq);
+	mlx5e_reporter_tx_err_cqe(sq);
 }
 
 int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
@@ -1395,7 +1395,6 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = params->tx_min_inline_mode;
-	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
 		goto err_free_icosq;
@@ -1409,12 +1408,22 @@ err_free_icosq:
 	return err;
 }
 
-void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
 {
-	struct mlx5e_channel *c = sq->channel;
+	set_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
+}
 
-	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
+{
+	struct mlx5e_channel *c = icosq->channel;
+
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
 	napi_synchronize(&c->napi);
+}
+
+void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
 	mlx5e_free_icosq(sq);
@@ -1991,6 +2000,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
+	mlx5e_activate_icosq(&c->icosq);
 	mlx5e_activate_rq(&c->rq);
 	netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix);
 
@@ -2006,6 +2016,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 		mlx5e_deactivate_xsk(c);
 
 	mlx5e_deactivate_rq(&c->rq);
+	mlx5e_deactivate_icosq(&c->icosq);
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_deactivate_txqsq(&c->sq[tc]);
 }
@@ -2323,10 +2334,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	if (priv->tx_reporter)
-		devlink_health_reporter_state_update(priv->tx_reporter,
-						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
-
+	mlx5e_health_channels_update(priv);
 	kvfree(cparam);
 	return 0;
 
@@ -3201,7 +3209,6 @@ 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]);
 }
@@ -4271,7 +4278,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
 
-		if (mlx5e_tx_reporter_timeout(sq))
+		if (mlx5e_reporter_tx_timeout(sq))
 			report_failed = true;
 	}
 
@@ -4969,12 +4976,14 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
 	mlx5e_build_tc2txq_maps(priv);
+	mlx5e_health_create_reporters(priv);
 
 	return 0;
 }
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
+	mlx5e_health_destroy_reporters(priv);
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
 	mlx5e_netdev_cleanup(priv->netdev, priv);
@@ -5077,7 +5086,6 @@ 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;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 60570b442fff..2fd2760d0bb7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -48,6 +48,7 @@
 #include "lib/clock.h"
 #include "en/xdp.h"
 #include "en/xsk/rx.h"
+#include "en/health.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
@@ -615,6 +616,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
 			netdev_WARN_ONCE(cq->channel->netdev,
 					 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
+			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+				queue_work(cq->channel->priv->wq, &sq->recover_work);
 			break;
 		}
 		do {
@@ -1067,11 +1070,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
-		rq->stats->wqe_err++;
-		return NULL;
-	}
-
 	rcu_read_lock();
 	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false);
 	rcu_read_unlock();
@@ -1099,11 +1097,6 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	u16 byte_cnt     = cqe_bcnt - headlen;
 	struct sk_buff *skb;
 
-	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
-		rq->stats->wqe_err++;
-		return NULL;
-	}
-
 	/* XDP is not supported in this configuration, as incoming packets
 	 * might spread among multiple pages.
 	 */
@@ -1137,6 +1130,15 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	return skb;
 }
 
+static void trigger_report(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe;
+
+	if (cqe_syndrome_needs_recover(err_cqe->syndrome) &&
+	    !test_and_set_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state))
+		queue_work(rq->channel->priv->wq, &rq->recover_work);
+}
+
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
@@ -1149,6 +1151,12 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
+	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+		trigger_report(rq, cqe);
+		rq->stats->wqe_err++;
+		goto free_wqe;
+	}
+
 	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
@@ -1190,6 +1198,11 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
+	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+		rq->stats->wqe_err++;
+		goto free_wqe;
+	}
+
 	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
@@ -1324,7 +1337,8 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	wi->consumed_strides += cstrides;
 
-	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+		trigger_report(rq, cqe);
 		rq->stats->wqe_err++;
 		goto mpwrq_cqe_out;
 	}
@@ -1500,6 +1514,11 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
+	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+		rq->stats->wqe_err++;
+		goto wq_free_wqe;
+	}
+
 	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
@@ -1535,26 +1554,27 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
+	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+		rq->stats->wqe_err++;
+		goto wq_free_wqe;
+	}
+
 	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
 			      rq, cqe, wi, cqe_bcnt);
-	if (unlikely(!skb)) {
-		/* a DROP, save the page-reuse checks */
-		mlx5e_free_rx_wqe(rq, wi, true);
-		goto wq_cyc_pop;
-	}
+	if (unlikely(!skb)) /* a DROP, save the page-reuse checks */
+		goto wq_free_wqe;
+
 	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
-	if (unlikely(!skb)) {
-		mlx5e_free_rx_wqe(rq, wi, true);
-		goto wq_cyc_pop;
-	}
+	if (unlikely(!skb))
+		goto wq_free_wqe;
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
+wq_free_wqe:
 	mlx5e_free_rx_wqe(rq, wi, true);
-wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 94a32c76c182..18e4c162256a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -109,6 +109,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
@@ -220,6 +221,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_waive += rq_stats->cache_waive;
 		s->rx_congst_umr  += rq_stats->congst_umr;
 		s->rx_arfs_err    += rq_stats->arfs_err;
+		s->rx_recover     += rq_stats->recover;
 		s->ch_events      += ch_stats->events;
 		s->ch_poll        += ch_stats->poll;
 		s->ch_arm         += ch_stats->arm;
@@ -1298,6 +1300,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
 };
 
 static const struct counter_desc sq_stats_desc[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index bf645d42c833..c281e567711d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -116,6 +116,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_waive;
 	u64 rx_congst_umr;
 	u64 rx_arfs_err;
+	u64 rx_recover;
 	u64 ch_events;
 	u64 ch_poll;
 	u64 ch_arm;
@@ -249,6 +250,7 @@ struct mlx5e_rq_stats {
 	u64 cache_waive;
 	u64 congst_umr;
 	u64 arfs_err;
+	u64 recover;
 };
 
 struct mlx5e_sq_stats {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index c57f7533a6d0..3917834b48ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1481,10 +1481,13 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
 {
 	WARN_ON(!list_empty(&e->flows));
-	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 
-	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
-		mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+	if (e->compl_result > 0) {
+		mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
+
+		if (e->flags & MLX5_ENCAP_ENTRY_VALID)
+			mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+	}
 
 	kfree(e->encap_header);
 	kfree(e);
@@ -2919,7 +2922,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 
 		/* Protect against concurrent neigh update. */
 		mutex_lock(&esw->offloads.encap_tbl_lock);
-		if (e->compl_result) {
+		if (e->compl_result < 0) {
 			err = -EREMOTEIO;
 			goto out_err;
 		}
@@ -2959,6 +2962,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 		e->compl_result = err;
 		goto out_err;
 	}
+	e->compl_result = 1;
 
 attach_flow:
 	flow->encaps[out_index].e = e;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 1804cf3c3814..ab69effb056d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -402,21 +402,20 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
 	struct mlx5_fc *counter;
 	struct mlx5_fc *tmp;
 
-	mlx5_fc_pool_cleanup(&fc_stats->fc_pool);
 	cancel_delayed_work_sync(&dev->priv.fc_stats.work);
 	destroy_workqueue(dev->priv.fc_stats.wq);
 	dev->priv.fc_stats.wq = NULL;
 
-	kfree(fc_stats->bulk_query_out);
-
-	idr_destroy(&fc_stats->counters_idr);
-
 	tmplist = llist_del_all(&fc_stats->addlist);
 	llist_for_each_entry_safe(counter, tmp, tmplist, addlist)
 		mlx5_fc_release(dev, counter);
 
 	list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list)
 		mlx5_fc_release(dev, counter);
+
+	mlx5_fc_pool_cleanup(&fc_stats->fc_pool);
+	idr_destroy(&fc_stats->counters_idr);
+	kfree(fc_stats->bulk_query_out);
 }
 
 int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index 953cc8efba69..dd2315ce4441 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -44,6 +44,11 @@ u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
 	return wq->fbc.sz_m1 + 1;
 }
 
+u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq)
+{
+	return wq->fbc.log_stride;
+}
+
 u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
 {
 	return (u32)wq->fbc.sz_m1 + 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index f1ec58c9e9e3..55791f71a778 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -89,6 +89,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
 		     struct mlx5_wq_ctrl *wq_ctrl);
 u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq);
+u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq);
 
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,