Merge tag 'mlx5-updates-2019-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-08-01

Misc updates for mlx5 netdev driver:

1) Ingress rate support for E-Switch vports from Eli.
2) Gavi introduces flow counters bulk allocation and pool,
   To improve the performance of flow counter acquisition.
3) From Tariq, micro improvements for tx path
4) From Shay, small improvement for XDP TX MPWQE inline flow.
5) Aya provides some cleanups for tx devlink health reporters.
6) Saeed, refactor checksum handling into a single function.
7) Tonghao, allows dropping specific tunnel packets.
====================

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

28 files changed, 875 insertions, 347 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 79d93d6c7d7a..30f13f81c965 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -359,6 +359,7 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
+	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -483,8 +484,6 @@ struct mlx5e_xdp_mpwqe {
 	struct mlx5e_tx_wqe *wqe;
 	u8                   ds_count;
 	u8                   pkt_count;
-	u8                   max_ds_count;
-	u8                   complete;
 	u8                   inline_on;
 };
 
@@ -1134,7 +1133,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 			   struct mlx5e_params *params);
 void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 			    u16 num_channels);
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
index e78e92753d73..ed7a3881d2c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
@@ -4,7 +4,6 @@
 #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);
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 f3d98748b211..6e54fefea410 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2019 Mellanox Technologies. */
 
-#include <net/devlink.h>
 #include "reporter.h"
 #include "lib/eq.h"
 
@@ -117,7 +116,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
 				 char *err_str,
 				 struct mlx5e_tx_err_ctx *err_ctx)
 {
-	if (IS_ERR_OR_NULL(tx_reporter)) {
+	if (!tx_reporter) {
 		netdev_err(err_ctx->sq->channel->netdev, err_str);
 		return err_ctx->recover(err_ctx->sq);
 	}
@@ -289,23 +288,27 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
 
 int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
 {
+	struct devlink_health_reporter *reporter;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct devlink *devlink = priv_to_devlink(mdev);
 
-	priv->tx_reporter =
+	reporter =
 		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
 					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
 					       true, priv);
-	if (IS_ERR(priv->tx_reporter))
+	if (IS_ERR(reporter)) {
 		netdev_warn(priv->netdev,
 			    "Failed to create tx reporter, err = %ld\n",
-			    PTR_ERR(priv->tx_reporter));
-	return IS_ERR_OR_NULL(priv->tx_reporter);
+			    PTR_ERR(reporter));
+		return PTR_ERR(reporter);
+	}
+	priv->tx_reporter = reporter;
+	return 0;
 }
 
 void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
 {
-	if (IS_ERR_OR_NULL(priv->tx_reporter))
+	if (!priv->tx_reporter)
 		return;
 
 	devlink_health_reporter_destroy(priv->tx_reporter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index ddfe19adb3d9..87be96747902 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -6,7 +6,7 @@
 
 #include "en.h"
 
-#define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
+#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1)
 #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
 			    MLX5E_SQ_NOPS_ROOM)
 
@@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 	mlx5_write64((__be32 *)ctrl, uar_map);
 }
 
-static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe)
+static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg)
 {
-	return !!wqe->ctrl.tisn;
+	return cseg && !!cseg->tisn;
+}
+
+static inline u8
+mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
+			 struct sk_buff *skb)
+{
+	u8 mode;
+
+	if (mlx5e_transport_inline_tx_wqe(cseg))
+		return MLX5_INLINE_MODE_TCP_UDP;
+
+	mode = sq->min_inline_mode;
+
+	if (skb_vlan_tag_present(skb) &&
+	    test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
+		mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
+
+	return mode;
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index b0b982cf69bb..1ed5c33e022f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -179,33 +179,19 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
-	u8  wqebbs;
-	u16 pi;
-
-	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
-
-	prefetchw(session->wqe->data);
-	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
-	session->pkt_count = 0;
-	session->complete  = 0;
+	u16 pi, contig_wqebbs;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 
-/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
- * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
- * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
- * full-session WQE be cache-aligned.
- */
-#if L1_CACHE_BYTES < 128
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
-#else
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
-#endif
+	if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS))
+		mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
 
-	wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi),
-		       MLX5E_XDP_MPW_MAX_WQEBBS);
+	session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi);
 
-	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+	prefetchw(session->wqe->data);
+	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->pkt_count = 0;
 
 	mlx5e_xdp_update_inline_state(sq);
 
@@ -244,7 +230,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
 {
 	if (unlikely(!sq->mpwqe.wqe)) {
 		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
-						     MLX5_SEND_WQE_MAX_WQEBBS))) {
+						     MLX5E_XDPSQ_STOP_ROOM))) {
 			/* SQ is full, ring doorbell */
 			mlx5e_xmit_xdp_doorbell(sq);
 			sq->stats->full++;
@@ -285,8 +271,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
 
-	if (unlikely(session->complete ||
-		     session->ds_count == session->max_ds_count))
+	if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) ||
+		     session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index b90923932668..36ac1e3816b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -40,6 +40,26 @@
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
+#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM)
+
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
+#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \
+	DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS)
+
+/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
+ * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
+ * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
+ * full-session WQE be cache-aligned.
+ */
+#if L1_CACHE_BYTES < 128
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
+#else
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
+#endif
+
+#define MLX5E_XDP_MPW_MAX_NUM_DS \
+	(MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS)
+
 struct mlx5e_xsk_param;
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
@@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
 		session->inline_on = 1;
 }
 
+static inline bool
+mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
+{
+	return session->inline_on &&
+	       session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
+}
+
+static inline void
+mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq,
+			   u16 pi, u16 nnops)
+{
+	struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
+
+	edge_wi = wi + nnops;
+	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
+	for (; wi < edge_wi; wi++) {
+		wi->num_wqebbs = 1;
+		wi->num_pkts   = 0;
+		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+	}
+
+	sq->stats->nops += nnops;
+}
+
 static inline void
 mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 			 struct mlx5e_xdp_xmit_data *xdptxd,
@@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 
 	session->pkt_count++;
 
-#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
-
 	if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
 		struct mlx5_wqe_inline_seg *inline_dseg =
 			(struct mlx5_wqe_inline_seg *)dseg;
 		u16 ds_len = sizeof(*inline_dseg) + dma_len;
 		u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS);
 
-		if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) {
-			/* Not enough space for inline wqe, send with memory pointer */
-			session->complete = true;
-			goto no_inline;
-		}
-
 		inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
 		memcpy(inline_dseg->data, xdptxd->data, dma_len);
 
@@ -148,21 +184,23 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 		return;
 	}
 
-no_inline:
 	dseg->addr       = cpu_to_be64(xdptxd->dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
 	dseg->lkey       = sq->mkey_be;
 	session->ds_count++;
 }
 
-static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
-					 struct mlx5e_tx_wqe **wqe)
+static inline struct mlx5e_tx_wqe *
+mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_tx_wqe *wqe;
+
+	*pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
+	memset(wqe, 0, sizeof(*wqe));
 
-	*wqe = mlx5_wq_cyc_get_wqe(wq, pi);
-	memset(*wqe, 0, sizeof(**wqe));
+	return wqe;
 }
 
 static inline void
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 1539cf3de5dc..f7890e0ce96c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -180,15 +180,3 @@ out:
 
 	return err;
 }
-
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev)
-{
-	u8 min_inline_mode;
-
-	mlx5_query_min_inline(mdev, &min_inline_mode);
-	if (min_inline_mode == MLX5_INLINE_MODE_NONE &&
-	    !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		min_inline_mode = MLX5_INLINE_MODE_L2;
-
-	return min_inline_mode;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8dd31b5c740c..01f2918063af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv)
 static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv,
 						  struct mlx5e_params *params)
 {
-	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev);
+	mlx5_query_min_inline(priv->mdev, &params->tx_min_inline_mode);
 	if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP &&
 	    params->tx_min_inline_mode == MLX5_INLINE_MODE_L2)
 		params->tx_min_inline_mode = MLX5_INLINE_MODE_IP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b2618dd6dd10..4db595a7eb03 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1131,6 +1131,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
 	sq->stop_room = MLX5E_SQ_STOP_ROOM;
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
+	if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
+		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
@@ -2323,7 +2325,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	if (!IS_ERR_OR_NULL(priv->tx_reporter))
+	if (priv->tx_reporter)
 		devlink_health_reporter_state_update(priv->tx_reporter,
 						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
 
@@ -4777,7 +4779,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 
 	/* TX inline */
-	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev);
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
 	/* RSS */
 	mlx5e_build_rss_params(rss_params, params->num_channels);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 6edf0aeb1e26..bf6f4835457e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1156,6 +1156,23 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 	}
 }
 
+static
+int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv,
+				    struct tc_cls_matchall_offload *ma)
+{
+	switch (ma->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return mlx5e_tc_configure_matchall(priv, ma);
+	case TC_CLSMATCHALL_DESTROY:
+		return mlx5e_tc_delete_matchall(priv, ma);
+	case TC_CLSMATCHALL_STATS:
+		mlx5e_tc_stats_matchall(priv, ma);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 				 void *cb_priv)
 {
@@ -1165,6 +1182,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags);
+	case TC_SETUP_CLSMATCHALL:
+		return mlx5e_rep_setup_tc_cls_matchall(priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 10fafd5fa17b..43eeebe9c8d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -88,6 +88,7 @@ struct mlx5e_rep_priv {
 	struct mlx5_flow_handle *vport_rx_rule;
 	struct list_head       vport_sqs_list;
 	struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
+	struct rtnl_link_stats64 prev_vf_vport_stats;
 	struct devlink_port dl_port;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index ac6e586d403d..60570b442fff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -859,13 +859,24 @@ tail_padding_csum(struct sk_buff *skb, int offset,
 }
 
 static void
-mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
-		       struct mlx5e_rq_stats *stats)
+mlx5e_skb_csum_fixup(struct sk_buff *skb, int network_depth, __be16 proto,
+		     struct mlx5e_rq_stats *stats)
 {
 	struct ipv6hdr *ip6;
 	struct iphdr   *ip4;
 	int pkt_len;
 
+	/* Fixup vlan headers, if any */
+	if (network_depth > ETH_HLEN)
+		/* CQE csum is calculated from the IP header and does
+		 * not cover VLAN headers (if present). This will add
+		 * the checksum manually.
+		 */
+		skb->csum = csum_partial(skb->data + ETH_HLEN,
+					 network_depth - ETH_HLEN,
+					 skb->csum);
+
+	/* Fixup tail padding, if any */
 	switch (proto) {
 	case htons(ETH_P_IP):
 		ip4 = (struct iphdr *)(skb->data + network_depth);
@@ -931,16 +942,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			return; /* CQE csum covers all received bytes */
 
 		/* csum might need some fixups ...*/
-		if (network_depth > ETH_HLEN)
-			/* CQE csum is calculated from the IP header and does
-			 * not cover VLAN headers (if present). This will add
-			 * the checksum manually.
-			 */
-			skb->csum = csum_partial(skb->data + ETH_HLEN,
-						 network_depth - ETH_HLEN,
-						 skb->csum);
-
-		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
+		mlx5e_skb_csum_fixup(skb, network_depth, proto, stats);
 		return;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 539b4d3656da..6eee3c7d4b06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -74,6 +74,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_nops) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
@@ -90,6 +91,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_nops) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
@@ -200,6 +202,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
 		s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe;
 		s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw;
+		s->rx_xdp_tx_nops  += xdpsq_stats->nops;
 		s->rx_xdp_tx_full  += xdpsq_stats->full;
 		s->rx_xdp_tx_err   += xdpsq_stats->err;
 		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
@@ -227,6 +230,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
 		s->tx_xdp_mpwqe   += xdpsq_red_stats->mpwqe;
 		s->tx_xdp_inlnw   += xdpsq_red_stats->inlnw;
+		s->tx_xdp_nops	  += xdpsq_red_stats->nops;
 		s->tx_xdp_full    += xdpsq_red_stats->full;
 		s->tx_xdp_err     += xdpsq_red_stats->err;
 		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
@@ -1331,6 +1335,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
@@ -1340,6 +1345,7 @@ static const struct counter_desc xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 76ac111e14d0..bf645d42c833 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -81,6 +81,7 @@ struct mlx5e_sw_stats {
 	u64 rx_xdp_tx_xmit;
 	u64 rx_xdp_tx_mpwqe;
 	u64 rx_xdp_tx_inlnw;
+	u64 rx_xdp_tx_nops;
 	u64 rx_xdp_tx_full;
 	u64 rx_xdp_tx_err;
 	u64 rx_xdp_tx_cqe;
@@ -97,6 +98,7 @@ struct mlx5e_sw_stats {
 	u64 tx_xdp_xmit;
 	u64 tx_xdp_mpwqe;
 	u64 tx_xdp_inlnw;
+	u64 tx_xdp_nops;
 	u64 tx_xdp_full;
 	u64 tx_xdp_err;
 	u64 tx_xdp_cqes;
@@ -288,6 +290,7 @@ struct mlx5e_xdpsq_stats {
 	u64 xmit;
 	u64 mpwqe;
 	u64 inlnw;
+	u64 nops;
 	u64 full;
 	u64 err;
 	/* dirtied @completion */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f3ed028d5017..c5d75e2ecf54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2485,7 +2485,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 
 	if (flow_flag_test(flow, EGRESS) &&
 	    !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) ||
-	      (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)))
+	      (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
+	      (actions & MLX5_FLOW_CONTEXT_ACTION_DROP)))
 		return false;
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -3638,6 +3639,106 @@ errout:
 	return err;
 }
 
+static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch *esw;
+	u16 vport_num;
+	u32 rate_mbps;
+	int err;
+
+	esw = priv->mdev->priv.eswitch;
+	/* rate is given in bytes/sec.
+	 * First convert to bits/sec and then round to the nearest mbit/secs.
+	 * mbit means million bits.
+	 * Moreover, if rate is non zero we choose to configure to a minimum of
+	 * 1 mbit/sec.
+	 */
+	rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0;
+	vport_num = rpriv->rep->vport;
+
+	err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware");
+
+	return err;
+}
+
+static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv,
+					struct flow_action *flow_action,
+					struct netlink_ext_ack *extack)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	const struct flow_action_entry *act;
+	int err;
+	int i;
+
+	if (!flow_action_has_entries(flow_action)) {
+		NL_SET_ERR_MSG_MOD(extack, "matchall called with no action");
+		return -EINVAL;
+	}
+
+	if (!flow_offload_has_one_action(flow_action)) {
+		NL_SET_ERR_MSG_MOD(extack, "matchall policing support only a single action");
+		return -EOPNOTSUPP;
+	}
+
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_POLICE:
+			err = apply_police_params(priv, act->police.rate_bytes_ps, extack);
+			if (err)
+				return err;
+
+			rpriv->prev_vf_vport_stats = priv->stats.vf_vport;
+			break;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
+				struct tc_cls_matchall_offload *ma)
+{
+	struct netlink_ext_ack *extack = ma->common.extack;
+	int prio = TC_H_MAJ(ma->common.prio) >> 16;
+
+	if (prio != 1) {
+		NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported");
+		return -EINVAL;
+	}
+
+	return scan_tc_matchall_fdb_actions(priv, &ma->rule->action, extack);
+}
+
+int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv,
+			     struct tc_cls_matchall_offload *ma)
+{
+	struct netlink_ext_ack *extack = ma->common.extack;
+
+	return apply_police_params(priv, 0, extack);
+}
+
+void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
+			     struct tc_cls_matchall_offload *ma)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct rtnl_link_stats64 cur_stats;
+	u64 dbytes;
+	u64 dpkts;
+
+	cur_stats = priv->stats.vf_vport;
+	dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
+	dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
+	rpriv->prev_vf_vport_stats = cur_stats;
+	flow_stats_update(&ma->stats, dpkts, dbytes, jiffies);
+}
+
 static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,
 					      struct mlx5e_priv *peer_priv)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 1cb66bf76997..20f045e96c92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -63,6 +63,13 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct flow_cls_offload *f, unsigned long flags);
 
+int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
+				struct tc_cls_matchall_offload *f);
+int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv,
+			     struct tc_cls_matchall_offload *f);
+void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
+			     struct tc_cls_matchall_offload *ma);
+
 struct mlx5e_encap_entry;
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 			      struct mlx5e_encap_entry *e);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index acf25cc38fa1..d3a67a9b4eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
-		u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ?
-			MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode;
+		u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb);
 
 		opcode    = MLX5_OPCODE_SEND;
 		mss       = 0;
@@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
+		u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb);
+
 		opcode    = MLX5_OPCODE_SEND;