Merge tag 'mlx5-updates-2018-01-19' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2018-01-19

From: Or Gerlitz <ogerlitz@mellanox.com>
=======
First six patches of this series further enhances the mlx5 hairpin support.
The first two patches deal with using different hairpin instances
for flows whose packets have different priorities to align with the port
TX QoS model. The next four patches allow us to do HW spreading
of flows over a set of hairpin pairs using RSS. The last two patches
change the driver to also set the size of the HW hairpin queues.
========

Next four patches from Eran Ben Elisha <eranbe@mellanox.com>:
Add more debug data for TX timeout handling, and further enhance and optimize
TX timeout handling upon lost interrupts, which adds a mechanism for explicitly
polling EQ in case of a TX timeout in order to recover from a lost interrupt.
If this is not the case (no pending EQEs), perform a channels full recovery as
usual.

From Kamal Heib <kamalh@mellanox.com>, Two patches to extend the stats group API
to have an update_stats() callback which will be used to fetch the hardware or
software counters data, this will improve the current API and reduce code
duplication.

From Gal Pressman <galp@mellanox.com>, Last patch, Add likely to the common RX checksum
flow.
====================

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

13 files changed, 809 insertions, 300 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 7b988595ac5f..4c9360b25532 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -44,6 +44,7 @@
 #include <linux/mlx5/port.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/transobj.h>
+#include <linux/mlx5/fs.h>
 #include <linux/rhashtable.h>
 #include <net/switchdev.h>
 #include <net/xdp.h>
@@ -560,6 +561,7 @@ struct mlx5e_channel {
 
 	/* data path - accessed per napi poll */
 	struct irq_desc *irq_desc;
+	struct mlx5e_ch_stats      stats;
 
 	/* control */
 	struct mlx5e_priv         *priv;
@@ -696,6 +698,11 @@ enum {
 	MLX5E_ARFS_FT_LEVEL
 };
 
+enum {
+	MLX5E_TC_FT_LEVEL = 0,
+	MLX5E_TC_TTC_FT_LEVEL,
+};
+
 struct mlx5e_ethtool_table {
 	struct mlx5_flow_table *ft;
 	int                    num_rules;
@@ -834,7 +841,7 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
 
-void mlx5e_update_stats(struct mlx5e_priv *priv, bool full);
+void mlx5e_update_stats(struct mlx5e_priv *priv);
 
 int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
@@ -1024,11 +1031,26 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv);
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv);
+struct ttc_params {
+	struct mlx5_flow_table_attr ft_attr;
+	u32 any_tt_tirn;
+	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_ttc_table *inner_ttc;
+};
 
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv);
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv);
+void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
+void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
+void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+			   struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
+			     struct mlx5e_ttc_table *ttc);
+
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+				 struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
+				   struct mlx5e_ttc_table *ttc);
 
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 		     u32 underlay_qpn, u32 *tisn);
@@ -1041,6 +1063,8 @@ int mlx5e_open(struct net_device *netdev);
 void mlx5e_update_stats_work(struct work_struct *work);
 u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
 
+int mlx5e_bits_invert(unsigned long a, int size);
+
 /* ethtool helpers */
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 2d1395015ab5..cc8048f68f11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -207,7 +207,7 @@ void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv,
 		return;
 
 	mutex_lock(&priv->state_lock);
-	mlx5e_update_stats(priv, true);
+	mlx5e_update_stats(priv);
 	mutex_unlock(&priv->state_lock);
 
 	for (i = 0; i < mlx5e_num_stats_grps; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index def513484845..f64dda2bed31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -806,25 +806,25 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 	return err ? ERR_PTR(err) : rule;
 }
 
-static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv)
+static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv,
+					  struct ttc_params *params,
+					  struct mlx5e_ttc_table *ttc)
 {
 	struct mlx5_flow_destination dest = {};
-	struct mlx5e_ttc_table *ttc;
 	struct mlx5_flow_handle **rules;
 	struct mlx5_flow_table *ft;
 	int tt;
 	int err;
 
-	ttc = &priv->fs.ttc;
 	ft = ttc->ft.t;
 	rules = ttc->rules;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
 		if (tt == MLX5E_TT_ANY)
-			dest.tir_num = priv->direct_tir[0].tirn;
+			dest.tir_num = params->any_tt_tirn;
 		else
-			dest.tir_num = priv->indir_tir[tt].tirn;
+			dest.tir_num = params->indir_tirn[tt];
 		rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest,
 						    ttc_rules[tt].etype,
 						    ttc_rules[tt].proto);
@@ -832,12 +832,12 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv)
 			goto del_rules;
 	}
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	if (!params->inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
 		return 0;
 
 	rules     = ttc->tunnel_rules;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft   = priv->fs.inner_ttc.ft.t;
+	dest.ft   = params->inner_ttc->ft.t;
 	for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) {
 		rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest,
 						    ttc_tunnel_rules[tt].etype,
@@ -977,25 +977,25 @@ mlx5e_generate_inner_ttc_rule(struct mlx5e_priv *priv,
 	return err ? ERR_PTR(err) : rule;
 }
 
-static int mlx5e_generate_inner_ttc_table_rules(struct mlx5e_priv *priv)
+static int mlx5e_generate_inner_ttc_table_rules(struct mlx5e_priv *priv,
+						struct ttc_params *params,
+						struct mlx5e_ttc_table *ttc)
 {
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_handle **rules;
-	struct mlx5e_ttc_table *ttc;
 	struct mlx5_flow_table *ft;
 	int err;
 	int tt;
 
-	ttc =  &priv->fs.inner_ttc;
 	ft = ttc->ft.t;
 	rules = ttc->rules;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
 		if (tt == MLX5E_TT_ANY)
-			dest.tir_num = priv->direct_tir[0].tirn;
+			dest.tir_num = params->any_tt_tirn;
 		else
-			dest.tir_num = priv->inner_indir_tir[tt].tirn;
+			dest.tir_num = params->indir_tirn[tt];
 
 		rules[tt] = mlx5e_generate_inner_ttc_rule(priv, ft, &dest,
 							  ttc_rules[tt].etype,
@@ -1075,21 +1075,42 @@ err:
 	return err;
 }
 
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv)
+void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv,
+				struct ttc_params *ttc_params)
+{
+	ttc_params->any_tt_tirn = priv->direct_tir[0].tirn;
+	ttc_params->inner_ttc = &priv->fs.inner_ttc;
+}
+
+void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params)
+{
+	struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr;
+
+	ft_attr->max_fte = MLX5E_INNER_TTC_TABLE_SIZE;
+	ft_attr->level = MLX5E_INNER_TTC_FT_LEVEL;
+	ft_attr->prio = MLX5E_NIC_PRIO;
+}
+
+void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params)
+
+{
+	struct mlx5_flow_table_attr *ft_attr = &ttc_params->ft_attr;
+
+	ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE;
+	ft_attr->level = MLX5E_TTC_FT_LEVEL;
+	ft_attr->prio = MLX5E_NIC_PRIO;
+}
+
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+				 struct mlx5e_ttc_table *ttc)
 {
-	struct mlx5e_ttc_table *ttc = &priv->fs.inner_ttc;
-	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5e_flow_table *ft = &ttc->ft;
 	int err;
 
 	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
 		return 0;
 
-	ft_attr.max_fte = MLX5E_INNER_TTC_TABLE_SIZE;
-	ft_attr.level   = MLX5E_INNER_TTC_FT_LEVEL;
-	ft_attr.prio    = MLX5E_NIC_PRIO;
-
-	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &params->ft_attr);
 	if (IS_ERR(ft->t)) {
 		err = PTR_ERR(ft->t);
 		ft->t = NULL;
@@ -1100,7 +1121,7 @@ int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv)
 	if (err)
 		goto err;
 
-	err = mlx5e_generate_inner_ttc_table_rules(priv);
+	err = mlx5e_generate_inner_ttc_table_rules(priv, params, ttc);
 	if (err)
 		goto err;
 
@@ -1111,10 +1132,9 @@ err:
 	return err;
 }
 
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv)
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
+				   struct mlx5e_ttc_table *ttc)
 {
-	struct mlx5e_ttc_table *ttc = &priv->fs.inner_ttc;
-
 	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
 		return;
 
@@ -1122,27 +1142,21 @@ void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv)
 	mlx5e_destroy_flow_table(&ttc->ft);
 }
 
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv)
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
+			     struct mlx5e_ttc_table *ttc)
 {
-	struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
-
 	mlx5e_cleanup_ttc_rules(ttc);
 	mlx5e_destroy_flow_table(&ttc->ft);
 }
 
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+			   struct mlx5e_ttc_table *ttc)
 {
 	bool match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version);
-	struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
-	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5e_flow_table *ft = &ttc->ft;
 	int err;
 
-	ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE;
-	ft_attr.level = MLX5E_TTC_FT_LEVEL;
-	ft_attr.prio = MLX5E_NIC_PRIO;
-
-	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
+	ft->t = mlx5_create_flow_table(priv->fs.ns, &params->ft_attr);
 	if (IS_ERR(ft->t)) {
 		err = PTR_ERR(ft->t);
 		ft->t = NULL;
@@ -1153,7 +1167,7 @@ int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
 	if (err)
 		goto err;
 
-	err = mlx5e_generate_ttc_table_rules(priv);
+	err = mlx5e_generate_ttc_table_rules(priv, params, ttc);
 	if (err)
 		goto err;
 
@@ -1474,7 +1488,8 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv)
 
 int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 {
-	int err;
+	struct ttc_params ttc_params = {};
+	int tt, err;
 
 	priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
 					       MLX5_FLOW_NAMESPACE_KERNEL);
@@ -1489,14 +1504,23 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 		priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
 	}
 
-	err = mlx5e_create_inner_ttc_table(priv);
+	mlx5e_set_ttc_basic_params(priv, &ttc_params);
+	mlx5e_set_inner_ttc_ft_params(&ttc_params);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		ttc_params.indir_tirn[tt] = priv->inner_indir_tir[tt].tirn;
+
+	err = mlx5e_create_inner_ttc_table(priv, &ttc_params, &priv->fs.inner_ttc);
 	if (err) {
 		netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n",
 			   err);
 		goto err_destroy_arfs_tables;
 	}
 
-	err = mlx5e_create_ttc_table(priv);
+	mlx5e_set_ttc_ft_params(&ttc_params);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		ttc_params.indir_tirn[tt] = priv->indir_tir[tt].tirn;
+
+	err = mlx5e_create_ttc_table(priv, &ttc_params, &priv->fs.ttc);
 	if (err) {
 		netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
 			   err);
@@ -1524,9 +1548,9 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 err_destroy_l2_table:
 	mlx5e_destroy_l2_table(priv);
 err_destroy_ttc_table:
-	mlx5e_destroy_ttc_table(priv);
+	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 err_destroy_inner_ttc_table:
-	mlx5e_destroy_inner_ttc_table(priv);
+	mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc);
 err_destroy_arfs_tables:
 	mlx5e_arfs_destroy_tables(priv);
 
@@ -1537,8 +1561,8 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv)
 {
 	mlx5e_destroy_vlan_table(priv);
 	mlx5e_destroy_l2_table(priv);
-	mlx5e_destroy_ttc_table(priv);
-	mlx5e_destroy_inner_ttc_table(priv);
+	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
+	mlx5e_destroy_inner_ttc_table(priv, &priv->fs.inner_ttc);
 	mlx5e_arfs_destroy_tables(priv);
 	mlx5e_ethtool_cleanup_steering(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 466a4e1244d7..8530c770c873 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -173,182 +173,23 @@ unlock:
 	rtnl_unlock();
 }
 
-static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
+void mlx5e_update_stats(struct mlx5e_priv *priv)
 {
-	struct mlx5e_sw_stats temp, *s = &temp;
-	struct mlx5e_rq_stats *rq_stats;
-	struct mlx5e_sq_stats *sq_stats;
-	int i, j;
-
-	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->channels.num; i++) {
-		struct mlx5e_channel *c = priv->channels.c[i];
-
-		rq_stats = &c->rq.stats;
-
-		s->rx_packets	+= rq_stats->packets;
-		s->rx_bytes	+= rq_stats->bytes;
-		s->rx_lro_packets += rq_stats->lro_packets;
-		s->rx_lro_bytes	+= rq_stats->lro_bytes;
-		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
-		s->rx_csum_none	+= rq_stats->csum_none;
-		s->rx_csum_complete += rq_stats->csum_complete;
-		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
-		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
-		s->rx_xdp_drop += rq_stats->xdp_drop;
-		s->rx_xdp_tx += rq_stats->xdp_tx;
-		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
-		s->rx_wqe_err   += rq_stats->wqe_err;
-		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
-		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
-		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
-		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
-		s->rx_page_reuse  += rq_stats->page_reuse;
-		s->rx_cache_reuse += rq_stats->cache_reuse;
-		s->rx_cache_full  += rq_stats->cache_full;
-		s->rx_cache_empty += rq_stats->cache_empty;
-		s->rx_cache_busy  += rq_stats->cache_busy;
-		s->rx_cache_waive += rq_stats->cache_waive;
-
-		for (j = 0; j < priv->channels.params.num_tc; j++) {
-			sq_stats = &c->sq[j].stats;
-
-			s->tx_packets		+= sq_stats->packets;
-			s->tx_bytes		+= sq_stats->bytes;
-			s->tx_tso_packets	+= sq_stats->tso_packets;
-			s->tx_tso_bytes		+= sq_stats->tso_bytes;
-			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
-			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
-			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
-			s->tx_queue_stopped	+= sq_stats->stopped;
-			s->tx_queue_wake	+= sq_stats->wake;
-			s->tx_queue_dropped	+= sq_stats->dropped;
-			s->tx_xmit_more		+= sq_stats->xmit_more;
-			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
-			s->tx_csum_none		+= sq_stats->csum_none;
-			s->tx_csum_partial	+= sq_stats->csum_partial;
-		}
-	}
-
-	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
-				priv->stats.pport.phy_counters,
-				counter_set.phys_layer_cntrs.link_down_events);
-	memcpy(&priv->stats.sw, s, sizeof(*s));
-}
-
-static void mlx5e_update_vport_counters(struct mlx5e_priv *priv)
-{
-	int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
-	u32 *out = (u32 *)priv->stats.vport.query_vport_out;
-	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {0};
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	MLX5_SET(query_vport_counter_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_VPORT_COUNTER);
-	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
-	MLX5_SET(query_vport_counter_in, in, other_vport, 0);
-
-	mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
-}
-
-static void mlx5e_update_pport_counters(struct mlx5e_priv *priv, bool full)
-{
-	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
-	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
-	int prio;
-	void *out;
-
-	MLX5_SET(ppcnt_reg, in, local_port, 1);
-
-	out = pstats->IEEE_802_3_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_IEEE_802_3_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
-
-	if (!full)
-		return;
-
-	out = pstats->RFC_2863_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_RFC_2863_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
-
-	out = pstats->RFC_2819_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_RFC_2819_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
-
-	out = pstats->phy_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
-
-	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group)) {
-		out = pstats->phy_statistical_counters;
-		MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
-		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
-	}
-
-	if (MLX5_CAP_PCAM_FEATURE(mdev, rx_buffer_fullness_counters)) {
-		out = pstats->eth_ext_counters;
-		MLX5_SET(ppcnt_reg, in, grp, MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP);
-		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
-	}
-
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_PER_PRIORITY_COUNTERS_GROUP);
-	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
-		out = pstats->per_prio_counters[prio];
-		MLX5_SET(ppcnt_reg, in, prio_tc, prio);
-		mlx5_core_access_reg(mdev, in, sz, out, sz,
-				     MLX5_REG_PPCNT, 0, 0);
-	}
-}
-
-static void mlx5e_update_q_counter(struct mlx5e_priv *priv)
-{
-	struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
-	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)];
-	int err;
-
-	if (!priv->q_counter)
-		return;
-
-	err = mlx5_core_query_q_counter(priv->mdev, priv->q_counter, 0, out, sizeof(out));
-	if (err)
-		return;
-
-	qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, out, out_of_buffer);
-}
-
-static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv)
-{
-	struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 in[MLX5_ST_SZ_DW(mpcnt_reg)] = {0};
-	int sz = MLX5_ST_SZ_BYTES(mpcnt_reg);
-	void *out;
-
-	if (!MLX5_CAP_MCAM_FEATURE(mdev, pcie_performance_group))
-		return;
-
-	out = pcie_stats->pcie_perf_counters;
-	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
-}
+	int i;
 
-void mlx5e_update_stats(struct mlx5e_priv *priv, bool full)
-{
-	if (full) {
-		mlx5e_update_pcie_counters(priv);
-		mlx5e_ipsec_update_stats(priv);
-	}
-	mlx5e_update_pport_counters(priv, full);
-	mlx5e_update_vport_counters(priv);
-	mlx5e_update_q_counter(priv);
-	mlx5e_update_sw_counters(priv);
+	for (i = mlx5e_num_stats_grps - 1; i >= 0; i--)
+		if (mlx5e_stats_grps[i].update_stats)
+			mlx5e_stats_grps[i].update_stats(priv);
 }
 
 static void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
 {
-	mlx5e_update_stats(priv, false);
+	int i;
+
+	for (i = mlx5e_num_stats_grps - 1; i >= 0; i--)
+		if (mlx5e_stats_grps[i].update_stats_mask &
+		    MLX5E_NDO_UPDATE_STATS)
+			mlx5e_stats_grps[i].update_stats(priv);
 }
 
 void mlx5e_update_stats_work(struct work_struct *work)
@@ -2219,7 +2060,7 @@ static int mlx5e_rx_hash_fn(int hfunc)
 	       MLX5_RX_HASH_FN_INVERTED_XOR8;
 }
 
-static int mlx5e_bits_invert(unsigned long a, int size)
+int mlx5e_bits_invert(unsigned long a, int size)
 {
 	int inv = 0;
 	int i;
@@ -3757,26 +3598,62 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
+static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
+					struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int irqn_not_used, eqn;
+	struct mlx5_eq *eq;
+	u32 eqe_count;
+
+	if (mlx5_vector2eqn(mdev, sq->cq.mcq.vector, &eqn, &irqn_not_used))
+		return false;
+
+	eq = mlx5_eqn2eq(mdev, eqn);
+	if (IS_ERR(eq))
+		return false;
+
+	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
+		   eqn, eq->cons_index, eq->irqn);
+
+	eqe_count = mlx5_eq_poll_irq_disabled(eq);
+	if (!eqe_count)
+		return false;
+
+	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
+	sq->channel->stats.eq_rearm++;
+	return true;
+}
+
 static void mlx5e_tx_timeout(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	bool sched_work = false;
+	bool reopen_channels = false;
 	int i;
 
 	netdev_err(dev, "TX timeout detected\n");
 
 	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
+		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
 		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
-		if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
+		if (!netif_xmit_stopped(dev_queue))
 			continue;
-		sched_work = true;
-		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-		netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
-			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
+		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 (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (reopen_channels && test_bit(MLX5E_STATE_OPENED, &priv->state))
 		schedule_work(&priv->tx_timeout_work);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index ff234dfefc27..0d4bb0688faa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -631,7 +631,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (is_last_ethertype_ip(skb, &network_depth)) {
+	if (likely(is_last_ethertype_ip(skb, &network_depth))) {
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
 		if (network_depth > ETH_HLEN)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index b74ddc7984bc..5f0f3493d747 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -71,6 +71,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
 };
 
@@ -99,6 +100,72 @@ static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
 	return idx;
 }
 
+static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_sw_stats temp, *s = &temp;
+	struct mlx5e_rq_stats *rq_stats;
+	struct mlx5e_sq_stats *sq_stats;
+	struct mlx5e_ch_stats *ch_stats;
+	int i, j;
+
+	memset(s, 0, sizeof(*s));
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
+
+		rq_stats = &c->rq.stats;
+		ch_stats = &c->stats;
+
+		s->rx_packets	+= rq_stats->packets;
+		s->rx_bytes	+= rq_stats->bytes;
+		s->rx_lro_packets += rq_stats->lro_packets;
+		s->rx_lro_bytes	+= rq_stats->lro_bytes;
+		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
+		s->rx_csum_none	+= rq_stats->csum_none;
+		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
+		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
+		s->rx_xdp_drop += rq_stats->xdp_drop;
+		s->rx_xdp_tx += rq_stats->xdp_tx;
+		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
+		s->rx_wqe_err   += rq_stats->wqe_err;
+		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
+		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
+		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
+		s->rx_page_reuse  += rq_stats->page_reuse;
+		s->rx_cache_reuse += rq_stats->cache_reuse;
+		s->rx_cache_full  += rq_stats->cache_full;
+		s->rx_cache_empty += rq_stats->cache_empty;
+		s->rx_cache_busy  += rq_stats->cache_busy;
+		s->rx_cache_waive += rq_stats->cache_waive;
+		s->ch_eq_rearm += ch_stats->eq_rearm;
+
+		for (j = 0; j < priv->channels.params.num_tc; j++) {
+			sq_stats = &c->sq[j].stats;
+
+			s->tx_packets		+= sq_stats->packets;
+			s->tx_bytes		+= sq_stats->bytes;
+			s->tx_tso_packets	+= sq_stats->tso_packets;
+			s->tx_tso_bytes		+= sq_stats->tso_bytes;
+			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
+			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
+			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
+			s->tx_queue_stopped	+= sq_stats->stopped;
+			s->tx_queue_wake	+= sq_stats->wake;
+			s->tx_queue_dropped	+= sq_stats->dropped;
+			s->tx_xmit_more		+= sq_stats->xmit_more;
+			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
+			s->tx_csum_none		+= sq_stats->csum_none;
+			s->tx_csum_partial	+= sq_stats->csum_partial;
+		}
+	}
+
+	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
+				priv->stats.pport.phy_counters,
+				counter_set.phys_layer_cntrs.link_down_events);
+	memcpy(&priv->stats.sw, s, sizeof(*s));
+}
+
 static const struct counter_desc q_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_qcounter_stats, rx_out_of_buffer) },
 };
@@ -128,6 +195,22 @@ static int mlx5e_grp_q_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
 	return idx;
 }
 
+static void mlx5e_grp_q_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
+	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)];
+	int err;
+
+	if (!priv->q_counter)
+		return;
+
+	err = mlx5_core_query_q_counter(priv->mdev, priv->q_counter, 0, out, sizeof(out));
+	if (err)
+		return;
+
+	qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, out, out_of_buffer);
+}
+
 #define VPORT_COUNTER_OFF(c) MLX5_BYTE_OFF(query_vport_counter_out, c)
 static const struct counter_desc vport_stats_desc[] = {
 	{ "rx_vport_unicast_packets",
@@ -200,6 +283,19 @@ static int mlx5e_grp_vport_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
+static void mlx5e_grp_vport_update_stats(struct mlx5e_priv *priv)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
+	u32 *out = (u32 *)priv->stats.vport.query_vport_out;
+	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {0};
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	MLX5_SET(query_vport_counter_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_COUNTER);
+	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
+	MLX5_SET(query_vport_counter_in, in, other_vport, 0);
+	mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
+}
+
 #define PPORT_802_3_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.eth_802_3_cntrs_grp_data_layout.c##_high)
@@ -252,6 +348,20 @@ static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
+static void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
+	void *out;
+
+	MLX5_SET(ppcnt_reg, in, local_port, 1);
+	out = pstats->IEEE_802_3_counters;
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_IEEE_802_3_COUNTERS_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+}
+
 #define PPORT_2863_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.eth_2863_cntrs_grp_data_layout.c##_high)
@@ -289,6 +399,20 @@ static int mlx5e_grp_2863_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
+static void mlx5e_grp_2863_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
+	void *out;
+
+	MLX5_SET(ppcnt_reg, in, local_port, 1);
+	out = pstats->RFC_2863_counters;
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_RFC_2863_COUNTERS_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+}
+
 #define PPORT_2819_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.eth_2819_cntrs_grp_data_layout.c##_high)
@@ -336,6 +460,20 @@ static int mlx5e_grp_2819_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
+static void mlx5e_grp_2819_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
+	void *out;
+
+	MLX5_SET(ppcnt_reg, in, local_port, 1);
+	out = pstats->RFC_2819_counters;
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_RFC_2819_COUNTERS_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+}
+
 #define PPORT_PHY_STATISTICAL_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.phys_layer_statistical_cntrs.c##_high)
@@ -376,6 +514,27 @@ static int mlx5e_grp_phy_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
 	return idx;
 }
 
+static void mlx5e_grp_phy_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
+	void *out;
+
+	MLX5_SET(ppcnt_reg, in, local_port, 1);
+	out = pstats->phy_counters;
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
+		return;
+
+	out = pstats->phy_statistical_counters;
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+}
+
 #define PPORT_ETH_EXT_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.eth_extended_cntrs_grp_data_layout.c##_high)
@@ -418,6 +577,23 @@ static int mlx5e_grp_eth_ext_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
+static void mlx5e_grp_eth_ext_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {0};
+	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
+	void *out;
+
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, rx_buffer_fullness_counters))
+		return;
+
+	MLX5_SET(ppcnt_reg, in, local_port, 1);
+	out = pstats->eth_ext_counters;