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>

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);
 

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);

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

 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2019 Mellanox Technologies. */
 
-#include <net/devlink.h>
 #include "reporter.h"
 #include "lib/eq.h"
 
@@ -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);

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)

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);

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

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

@@ -180,15 +180,3 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	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;
-}

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;

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);

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;
 	}

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;
 };
 

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;
 	}
 

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) },

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 */

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 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	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)
 {

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);

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;
 		mss       = 0;
-		ihs       = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+		ihs       = mlx5e_calc_min_inline(mode, skb);
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 		stats->packets++;
 	}

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

@@ -215,11 +215,7 @@ static int mlx5_eq_async_int(struct notifier_block *nb,
 		 */
 		dma_rmb();
 
-		if (likely(eqe->type < MLX5_EVENT_TYPE_MAX))
-			atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe);
-		else
-			mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type);
-
+		atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe);
 		atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe);
 
 		++eq->cons_index;
@@ -945,9 +941,6 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 {
 	struct mlx5_eq_table *eqt = dev->priv.eq_table;
 
-	if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
-		return -EINVAL;
-
 	return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb);
 }
 EXPORT_SYMBOL(mlx5_eq_notifier_register);
@@ -956,9 +949,6 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 {
 	struct mlx5_eq_table *eqt = dev->priv.eq_table;
 
-	if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
-		return -EINVAL;
-
 	return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb);
 }
 EXPORT_SYMBOL(mlx5_eq_notifier_unregister);

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

@@ -58,20 +58,9 @@ struct vport_addr {
 	bool mc_promisc;
 };
 
-enum {
-	UC_ADDR_CHANGE = BIT(0),
-	MC_ADDR_CHANGE = BIT(1),
-	PROMISC_CHANGE = BIT(3),
-};
-
 static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw);
 static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw);
 
-/* Vport context events */
-#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \
-			    MC_ADDR_CHANGE | \
-			    PROMISC_CHANGE)
-
 struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
@@ -108,13 +97,13 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 
 	MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1);
 
-	if (events_mask & UC_ADDR_CHANGE)
+	if (events_mask & MLX5_VPORT_UC_ADDR_CHANGE)
 		MLX5_SET(nic_vport_context, nic_vport_ctx,
 			 event_on_uc_address_change, 1);
-	if (events_mask & MC_ADDR_CHANGE)
+	if (events_mask & MLX5_VPORT_MC_ADDR_CHANGE)
 		MLX5_SET(nic_vport_context, nic_vport_ctx,
 			 event_on_mc_address_change, 1);
-	if (events_mask & PROMISC_CHANGE)
+	if (events_mask & MLX5_VPORT_PROMISC_CHANGE)
 		MLX5_SET(nic_vport_context, nic_vport_ctx,
 			 event_on_promisc_change, 1);
 
@@ -463,6 +452,22 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw)
 	return err;
 }
 
+#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \
+					MLX5_VPORT_MC_ADDR_CHANGE | \
+					MLX5_VPORT_PROMISC_CHANGE)
+
+static int esw_legacy_enable(struct mlx5_eswitch *esw)
+{
+	int ret;
+
+	ret = esw_create_legacy_table(esw);
+	if (ret)
+		return ret;
+
+	mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
+	return 0;
+}
+
 static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
 {
 	esw_cleanup_vepa_rules(esw);
@@ -470,6 +475,19 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
 	esw_destroy_legacy_vepa_table(esw);
 }
 
+static void esw_legacy_disable(struct mlx5_eswitch *esw)
+{
+	struct esw_mc_addr *mc_promisc;
+
+	mlx5_eswitch_disable_pf_vf_vports(esw);
+
+	mc_promisc = &esw->mc_promisc;
+	if (mc_promisc->uplink_rule)
+		mlx5_del_flow_rules(mc_promisc->uplink_rule);
+
+	esw_destroy_legacy_table(esw);
+}
+
 /* E-Switch vport UC/MC lists management */
 typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
 				 struct vport_addr *vaddr);
@@ -901,21 +919,21 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport)
 	esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n",
 		  vport->vport, mac);
 
-	if (vport->enabled_events & UC_ADDR_CHANGE) {
+	if (vport->enabled_events & MLX5_VPORT_UC_ADDR_CHANGE) {
 		esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC);
 		esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC);
 	}
 
-	if (vport->enabled_events & MC_ADDR_CHANGE)
+	if (vport->enabled_events & MLX5_VPORT_MC_ADDR_CHANGE)
 		esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC);
 
-	if (vport->enabled_events & PROMISC_CHANGE) {
+	if (vport->enabled_events & MLX5_VPORT_PROMISC_CHANGE) {
 		esw_update_vport_rx_mode(esw, vport);
 		if (!IS_ERR_OR_NULL(vport->allmulti_rule))
 			esw_update_vport_mc_promisc(esw, vport);
 	}
 
-	if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE))
+	if (vport->enabled_events & (MLX5_VPORT_PROMISC_CHANGE | MLX5_VPORT_MC_ADDR_CHANGE))
 		esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC);
 
 	esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport);
@@ -1393,18 +1411,49 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 	return err;
 }
 
+static bool element_type_supported(struct mlx5_eswitch *esw, int type)
+{
+	struct mlx5_core_dev *dev = esw->dev = esw->dev;
+
+	switch (type) {
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_TASR;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
+	}
+	return false;
+}
+
 /* Vport QoS management */
-static int esw_create_tsar(struct mlx5_eswitch *esw)
+static void esw_create_tsar(struct mlx5_eswitch *esw)
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
 	struct mlx5_core_dev *dev = esw->dev;
+	__be32 *attr;
 	int err;
 
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
-		return 0;
+		return;
+
+	if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
+		return;
 
 	if (esw->qos.enabled)
-		return -EEXIST;
+		return;
+
+	MLX5_SET(scheduling_context, tsar_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	*attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
 
 	err = mlx5_create_scheduling_element_cmd(dev,
 						 SCHEDULING_HIERARCHY_E_SWITCH,
@@ -1412,11 +1461,10 @@ static int esw_create_tsar(struct mlx5_eswitch *esw)
 						 &esw->qos.root_tsar_id);
 	if (err) {
 		esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
-		return err;
+		return;
 	}
 
 	esw->qos.enabled = true;
-	return 0;
 }
 
 static void esw_destroy_tsar(struct mlx5_eswitch *esw)
@@ -1537,6 +1585,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw,
 	return 0;
 }
 
+int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
+			       u32 rate_mbps)
+{
+	u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
+
+	return mlx5_modify_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  ctx,
+						  vport->qos.esw_tsar_ix,
+						  MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW);
+}
+
 static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
 {
 	((u8 *)node_guid)[7] = mac[0];
@@ -1619,7 +1683,7 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport)
 }
 
 static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
-			     int enable_events)
+			     enum mlx5_eswitch_vport_event enabled_events)
 {
 	u16 vport_num = vport->vport;
 
@@ -1641,7 +1705,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 		esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num);
 
 	/* Sync with current vport context */
-	vport->enabled_events = enable_events;
+	vport->enabled_events = enabled_events;
 	vport->enabled = true;
 
 	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
@@ -1770,11 +1834,46 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
-int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
+/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs
+ * whichever are present on the eswitch.
+ */
+void
+mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
+				 enum mlx5_eswitch_vport_event enabled_events)
 {
 	struct mlx5_vport *vport;
+	int i;
+
+	/* Enable PF vport */
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+	esw_enable_vport(esw, vport, enabled_events);
+
+	/* Enable ECPF vports */
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		esw_enable_vport(esw, vport, enabled_events);
+	}
+
+	/* Enable VF vports */
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		esw_enable_vport(esw, vport, enabled_events);
+}
+
+/* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs
+ * whichever are previously enabled on the eswitch.
+ */
+void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	int i;
+
+	mlx5_esw_for_all_vports_reverse(esw, i, vport)
+		esw_disable_vport(esw, vport);
+}
+
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
+{
 	int err;
-	int i, enabled_events;
 
 	if (!ESW_ALLOWED(esw) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
@@ -1788,44 +1887,23 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
 	if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
 		esw_warn(esw->dev, "engress ACL is not supported by FW\n");
 
+	esw_create_tsar(esw);
+
 	esw->mode = mode;
 
 	mlx5_lag_update(esw->dev);
 
 	if (mode == MLX5_ESWITCH_LEGACY) {
-		err = esw_create_legacy_table(esw);
-		if (err)
-			goto abort;
+		err = esw_legacy_enable(esw);
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-		err = esw_offloads_init(esw);
+		err = esw_offloads_enable(esw);
 	}
 
 	if (err)
 		goto abort;
 
-	err = esw_create_tsar(esw);
-	if (err)
-		esw_warn(esw->dev, "Failed to create eswitch TSAR");
-
-	enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS :
-		UC_ADDR_CHANGE;
-
-	/* Enable PF vport */
-	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-	esw_enable_vport(esw, vport, enabled_events);
-
-	/* Enable ECPF vports */
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
-		esw_enable_vport(esw, vport, enabled_events);
-	}
-
-	/* Enable VF vports */
-	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
-		esw_enable_vport(esw, vport, enabled_events);
-
 	mlx5_eswitch_event_handlers_register(esw);
 
 	esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n",
@@ -1847,10 +1925,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
 
 void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 {
-	struct esw_mc_addr *mc_promisc;
-	struct mlx5_vport *vport;
 	int old_mode;
-	int i;
 
 	if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE)
 		return;
@@ -1859,21 +1934,14 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
 		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
-	mc_promisc = &esw->mc_promisc;
 	mlx5_eswitch_event_handlers_unregister(esw);
 
-	mlx5_esw_for_all_vports(esw, i, vport)
-		esw_disable_vport(esw, vport);
-
-	if (mc_promisc && mc_promisc->uplink_rule)
-		mlx5_del_flow_rules(mc_promisc->uplink_rule);
-
-	esw_destroy_tsar(esw);
-
 	if (esw->mode == MLX5_ESWITCH_LEGACY)
-		esw_destroy_legacy_table(esw);
+		esw_legacy_disable(esw);
 	else if (esw->mode == MLX5_ESWITCH_OFFLOADS)
-		esw_offloads_cleanup(esw);
+		esw_offloads_disable(esw);
+
+	esw_destroy_tsar(esw);
 
 	old_mode = esw->mode;
 	esw->mode = MLX5_ESWITCH_NONE;

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

@@ -102,6 +102,13 @@ struct mlx5_vport_info {
 	bool                    trusted;
 };
 
+/* Vport context events */
+enum mlx5_eswitch_vport_event {
+	MLX5_VPORT_UC_ADDR_CHANGE = BIT(0),
+	MLX5_VPORT_MC_ADDR_CHANGE = BIT(1),
+	MLX5_VPORT_PROMISC_CHANGE = BIT(3),
+};
+
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	int                     vport;
@@ -123,7 +130,7 @@ struct mlx5_vport {
 	} qos;
 
 	bool                    enabled;
-	u16                     enabled_events;
+	enum mlx5_eswitch_vport_event enabled_events;
 };
 
 enum offloads_fdb_flags {
@@ -208,8 +215,11 @@ enum {
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
 	struct mlx5_nb          nb;
+	/* legacy data structures */
 	struct mlx5_eswitch_fdb fdb_table;
 	struct hlist_head       mc_table[MLX5_L2_ADDR_HASH_SIZE];
+	struct esw_mc_addr mc_promisc;
+	/* end of legacy */
 	struct workqueue_struct *work_queue;
 	struct mlx5_vport       *vports;
 	u32 flags;
@@ -219,7 +229,6 @@ struct mlx5_eswitch {
 	 * and async SRIOV admin state changes
 	 */
 	struct mutex            state_lock;
-	struct esw_mc_addr	mc_promisc;
 
 	struct {
 		bool            enabled;
@@ -234,8 +243,8 @@ struct mlx5_eswitch {
 	struct mlx5_esw_functions esw_funcs;
 };
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw);
-int esw_offloads_init(struct mlx5_eswitch *esw);
+void esw_offloads_disable(struct mlx5_eswitch *esw);
+int esw_offloads_enable(struct mlx5_eswitch *esw);
 void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
 void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
@@ -252,6 +261,8 @@ void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
 				   struct mlx5_vport *vport);
 void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 					       struct mlx5_vport *vport);
+int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
+			       u32 rate_mbps);
 
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
@@ -514,6 +525,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
 	     (vport) = &(esw)->vports[i],		\
 	     (i) < (esw)->total_vports; (i)++)
 
+#define mlx5_esw_for_all_vports_reverse(esw, i, vport)	\
+	for ((i) = (esw)->total_vports - 1;		\
+	     (vport) = &(esw)->vports[i],		\
+	     (i) >= MLX5_VPORT_PF; (i)--)
+
 #define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)	\
 	for ((i) = MLX5_VPORT_FIRST_VF;			\
 	     (vport) = &(esw)->vports[(i)],		\
@@ -575,6 +591,11 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs);
 int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data);
 
+void
+mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
+				 enum mlx5_eswitch_vport_event enabled_events);
+void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }

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

@@ -594,38 +594,15 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
 	mlx5_del_flow_rules(rule);
 }
 
-static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw)
+static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
 {
 	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
 	u8 fdb_to_vport_reg_c_id;
 	int err;
 
-	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
-						   out, sizeof(out));
-	if (err)
-		return err;
-
-	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
-					 esw_vport_context.fdb_to_vport_reg_c_id);
-
-	fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
-	MLX5_SET(modify_esw_vport_context_in, in,
-		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
-
-	MLX5_SET(modify_esw_vport_context_in, in,
-		 field_select.fdb_to_vport_reg_c_id, 1);
-
-	return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
-						     in, sizeof(in));
-}
-
-static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
-{
-	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
-	u8 fdb_to_vport_reg_c_id;
-	int err;
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
+		return 0;
 
 	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
 						   out, sizeof(out));
@@ -635,7 +612,10 @@ static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
 	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
 					 esw_vport_context.fdb_to_vport_reg_c_id);
 
-	fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;
+	if (enable)
+		fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
+	else
+		fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;
 
 	MLX5_SET(modify_esw_vport_context_in, in,
 		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
@@ -2131,7 +2111,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type
 	return NOTIFY_OK;
 }
 
-int esw_offloads_init(struct mlx5_eswitch *esw)
+int esw_offloads_enable(struct mlx5_eswitch *esw)
 {
 	int err;
 
@@ -2145,11 +2125,11 @@ int esw_offloads_init(struct mlx5_eswitch *esw)
 	if (err)
 		return err;
 
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		err = mlx5_eswitch_enable_passing_vport_metadata(esw);
-		if (err)
-			goto err_vport_metadata;
-	}
+	err = esw_set_passing_vport_metadata(esw, true);
+	if (err)
+		goto err_vport_metadata;
+
+	mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE);
 
 	err = esw_offloads_load_all_reps(esw);
 	if (err)
@@ -2163,8 +2143,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw)
 	return 0;
 
 err_reps:
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
-		mlx5_eswitch_disable_passing_vport_metadata(esw);
+	mlx5_eswitch_disable_pf_vf_vports(esw);
+	esw_set_passing_vport_metadata(esw, false);
 err_vport_metadata:
 	esw_offloads_steering_cleanup(esw);
 	return err;
@@ -2189,13 +2169,13 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 	return err;
 }
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw)
+void esw_offloads_disable(struct mlx5_eswitch *esw)
 {
 	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw);
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
-		mlx5_eswitch_disable_passing_vport_metadata(esw);
+	mlx5_eswitch_disable_pf_vf_vports(esw);
+	esw_set_passing_vport_metadata(esw, false);
 	esw_offloads_steering_cleanup(esw);
 	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }

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

@@ -566,7 +566,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id)
+int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev,
+			   enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask,
+			   u32 *id)
 {
 	u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0};
@@ -574,6 +576,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id)
 
 	MLX5_SET(alloc_flow_counter_in, in, opcode,
 		 MLX5_CMD_OP_ALLOC_FLOW_COUNTER);
+	MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (!err)
@@ -581,6 +584,11 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id)
 	return err;
 }
 
+int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id)
+{
+	return mlx5_cmd_fc_bulk_alloc(dev, 0, id);
+}
+
 int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)]   = {0};
@@ -615,67 +623,24 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id,
 	return 0;
 }
 
-struct mlx5_cmd_fc_bulk {
-	u32 id;
-	int num;
-	int outlen;
-	u32 out[0];
-};
-
-struct mlx5_cmd_fc_bulk *
-mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num)
-{
-	struct mlx5_cmd_fc_bulk *b;
-	int outlen =
-		MLX5_ST_SZ_BYTES(query_flow_counter_out) +
-		MLX5_ST_SZ_BYTES(traffic_counter) * num;
-
-	b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL);
-	if (!b)
-		return NULL;
-
-	b->id = id;
-	b->num = num;
-	b->outlen = outlen;
-
-	return b;
-}
-
-void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b)
+int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len)
 {
-	kfree(b);
+	return MLX5_ST_SZ_BYTES(query_flow_counter_out) +
+		MLX5_ST_SZ_BYTES(traffic_counter) * bulk_len;
 }
 
-int
-mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b)
+int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
+			   u32 *out)
 {
+	int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len);
 	u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0};
 
 	MLX5_SET(query_flow_counter_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_FLOW_COUNTER);
 	MLX5_SET(query_flow_counter_in, in, op_mod, 0);
-	MLX5_SET(query_flow_counter_in, in, flow_counter_id, b->id);
-	MLX5_SET(query_flow_counter_in, in, num_of_counters, b->num);
-	return mlx5_cmd_exec(dev, in, sizeof(in), b->out, b->outlen);
-}
-
-void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev,
-			  struct mlx5_cmd_fc_bulk *b, u32 id,
-			  u64 *packets, u64 *bytes)
-{
-	int index = id - b->id;
-	void *stats;
-
-	if (index < 0 || index >= b->num) {
-		mlx5_core_warn(dev, "Flow counter id (0x%x) out of range (0x%x..0x%x). Counter ignored.\n",
-			       id, b->id, b->id + b->num - 1);
-		return;
-	}
-
-	stats = MLX5_ADDR_OF(query_flow_counter_out, b->out,
-			     flow_statistics[index]);
-	*packets = MLX5_GET64(traffic_counter, stats, packets);
-	*bytes = MLX5_GET64(traffic_counter, stats, octets);
+	MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id);
+	MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
 int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,

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

@@ -78,20 +78,16 @@ struct mlx5_flow_cmds {
 };
 
 int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
+int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev,
+			   enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask,
+			   u32 *id);
 int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id);
 int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id,
 		      u64 *packets, u64 *bytes);
 
-struct mlx5_cmd_fc_bulk;
-
-struct mlx5_cmd_fc_bulk *
-mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num);
-void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b);
-int
-mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b);
-void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev,
-			  struct mlx5_cmd_fc_bulk *b, u32 id,
-			  u64 *packets, u64 *bytes);
+int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len);
+int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
+			   u32 *out);
 
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type);
 

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

@@ -40,6 +40,8 @@
 #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
 /* Max number of counters to query in bulk read is 32K */
 #define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
+#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18)
+#define MLX5_FC_POOL_USED_BUFF_RATIO 10
 
 struct mlx5_fc_cache {
 	u64 packets;
@@ -58,12 +60,18 @@ struct mlx5_fc {
 	u64 lastpackets;
 	u64 lastbytes;
 
+	struct mlx5_fc_bulk *bulk;
 	u32 id;
 	bool aging;
 
 	struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
 };
 
+static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev);
+static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool);
+static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool);
+static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc);
+
 /* locking scheme:
  *
  * It is the responsibility of the user to prevent concurrent calls or bad
@@ -75,7 +83,7 @@ struct mlx5_fc {
  * access to counter list:
  * - create (user context)
  *   - mlx5_fc_create() only adds to an addlist to be used by
- *     mlx5_fc_stats_query_work(). addlist is a lockless single linked list
+ *     mlx5_fc_stats_work(). addlist is a lockless single linked list
  *     that doesn't require any additional synchronization when adding single
  *     node.
  *   - spawn thread to do the actual destroy
@@ -136,81 +144,87 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev,
 	spin_unlock(&fc_stats->counters_idr_lock);
 }
 
-/* The function returns the last counter that was queried so the caller
- * function can continue calling it till all counters are queried.
- */
-static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
-					   struct mlx5_fc *first,
-					   u32 last_id)
+static int get_max_bulk_query_len(struct mlx5_core_dev *dev)
 {
-	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
-	struct mlx5_fc *counter = NULL;
-	struct mlx5_cmd_fc_bulk *b;
-	bool more = false;
-	u32 afirst_id;
-	int num;
-	int err;
+	return min_t(int, MLX5_SW_MAX_COUNTERS_BULK,
+			  (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk)));
+}
 
-	int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK,
-			     (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk)));
+static void update_counter_cache(int index, u32 *bulk_raw_data,
+				 struct mlx5_fc_cache *cache)
+{
+	void *stats = MLX5_ADDR_OF(query_flow_counter_out, bulk_raw_data,
+			     flow_statistics[index]);
+	u64 packets = MLX5_GET64(traffic_counter, stats, packets);
+	u64 bytes = MLX5_GET64(traffic_counter, stats, octets);
 
-	/* first id must be aligned to 4 when using bulk query */
-	afirst_id = first->id & ~0x3;
+	if (cache->packets == packets)
+		return;
 
-	/* number of counters to query inc. the last counter */
-	num = ALIGN(last_id - afirst_id + 1, 4);
-	if (num > max_bulk) {
-		num = max_bulk;
-		last_id = afirst_id + num - 1;
-	}
+	cache->packets = packets;
+	cache->bytes = bytes;
+	cache->lastuse = jiffies;
+}
 
-	b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num);
-	if (!b) {
-		mlx5_core_err(dev, "Error allocating resources for bulk query\n");
-		return NULL;
-	}
+static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev,
+					      struct mlx5_fc *first,
+					      u32 last_id)
+{
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+	bool query_more_counters = (first->id <= last_id);
+	int max_bulk_len = get_max_bulk_query_len(dev);
+	u32 *data = fc_stats->bulk_query_out;
+	struct mlx5_fc *counter = first;
+	u32 bulk_base_id;
+	int bulk_len;
+	int err;
 
-	err = mlx5_cmd_fc_bulk_query(dev, b);
-	if (err) {
-		mlx5_core_err(dev, "Error doing bulk query: %d\n", err);
-		goto out;
-	}
+	while (query_more_counters) {
+		/* first id must be aligned to 4 when using bulk query */
+		bulk_base_id = counter->id & ~0x3;
 
-	counter = first;
-	list_for_each_entry_from(counter, &fc_stats->counters, list) {
-		struct mlx5_fc_cache *c = &counter->cache;
-		u64 packets;
-		u64 bytes;
+		/* number of counters to query inc. the last counter */
+		bulk_len = min_t(int, max_bulk_len,
+				 ALIGN(last_id - bulk_base_id + 1, 4));
 
-		if (counter->id > last_id) {
-			more = true;
-			break;
+		err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len,
+					     data);
+		if (err) {
+			mlx5_core_err(dev, "Error doing bulk query: %d\n", err);
+			return;
 		}
+		query_more_counters = false;
 
-		mlx5_cmd_fc_bulk_get(dev, b,
-				     counter->id, &packets, &bytes);
+		list_for_each_entry_from(counter, &fc_stats->counters, list) {
+			int counter_index = counter->id - bulk_base_id;
+			struct mlx5_fc_cache *cache = &counter->cache;
 
-		if (c->packets == packets)
-			continue;
+			if (counter->id >= bulk_base_id + bulk_len) {
+				query_more_counters = true;
+				break;
+			}
 
-		c->packets = packets;
-		c->bytes = bytes;
-		c->lastuse = jiffies;
+			update_counter_cache(counter_index, data, cache);
+		}
 	}
-
-out:
-	mlx5_cmd_fc_bulk_free(b);
-
-	return more ? counter : NULL;
 }
 
-static void mlx5_free_fc(struct mlx5_core_dev *dev,
-			 struct mlx5_fc *counter)
+static void mlx5_fc_free(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
 {
 	mlx5_cmd_fc_free(dev, counter->id);
 	kfree(counter);
 }
 
+static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
+{
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+
+	if (counter->bulk)
+		mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter);
+	else
+		mlx5_fc_free(dev, counter);
+}
+
 static void mlx5_fc_stats_work(struct work_struct *work)
 {
 	struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev,
@@ -234,7 +248,7 @@ static void mlx5_fc_stats_work(struct work_struct *work)
 	llist_for_each_entry_safe(counter, tmp, dellist, dellist) {
 		mlx5_fc_stats_remove(dev, counter);
 
-		mlx5_free_fc(dev, counter);
+		mlx5_fc_release(dev, counter);
 	}
 
 	if (time_before(now, fc_stats->next_query) ||
@@ -244,32 +258,62 @@ static void mlx5_fc_stats_work(struct work_struct *work)
 
 	counter = list_first_entry(&fc_stats->counters, struct mlx5_fc,
 				   list);
-	while (counter)
-		counter = mlx5_fc_stats_query(dev, counter, last->id);
+	if (counter)
+		mlx5_fc_stats_query_counter_range(dev, counter, last->id);
 
 	fc_stats->next_query = now + fc_stats->sampling_interval;
 }
 
-struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
+static struct mlx5_fc *mlx5_fc_single_alloc(struct mlx5_core_dev *dev)
 {
-	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
 	struct mlx5_fc *counter;
 	int err;
 
 	counter = kzalloc(sizeof(*counter), GFP_KERNEL);
 	if (!counter)
 		return ERR_PTR(-ENOMEM);
-	INIT_LIST_HEAD(&counter->list);
 
 	err = mlx5_cmd_fc_alloc(dev, &counter->id);
-	if (err)
-		goto err_out;
+	if (err) {
+		kfree(counter);
+		return ERR_PTR(err);
+	}
+
+	return counter;
+}
+
+static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging)
+{
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+	struct mlx5_fc *counter;
+
+	if (aging && MLX5_CAP_GEN(dev, flow_counter_bulk_alloc) != 0) {
+		counter = mlx5_fc_pool_acquire_counter(&fc_stats->fc_pool);
+		if (!IS_ERR(counter))
+			return counter;
+	}
+
+	return mlx5_fc_single_alloc(dev);
+}
+
+struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
+{
+	struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging);
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+	int err;
+
+	if (IS_ERR(counter))
+		return counter;
+
+	INIT_LIST_HEAD(&counter->list);
+	counter->aging = aging;
 
 	if (aging) {
 		u32 id = counter->id;
 
 		counter->cache.lastuse = jiffies;
-		counter->aging = true;
+		counter->lastbytes = counter->cache.bytes;
+		counter->lastpackets = counter->cache.packets;
 
 		idr_preload(GFP_KERNEL);
 		spin_lock(&fc_stats->counters_idr_lock);
@@ -290,10 +334,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
 	return counter;
 
 err_out_alloc:
-	mlx5_cmd_fc_free(dev, counter->id);
-err_out:
-	kfree(counter);
-
+	mlx5_fc_release(dev, counter);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(mlx5_fc_create);
@@ -317,13 +358,15 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
 		return;
 	}
 
-	mlx5_free_fc(dev, counter);
+	mlx5_fc_release(dev, counter);
 }
 EXPORT_SYMBOL(mlx5_fc_destroy);
 
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+	int max_bulk_len;
+	int max_out_len;
 
 	spin_lock_init(&fc_stats->counters_idr_lock);
 	idr_init(&fc_stats->counters_idr);
@@ -331,14 +374,25 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 	init_llist_head(&fc_stats->addlist);
 	init_llist_head(&fc_stats->dellist);
 
+	max_bulk_len = get_max_bulk_query_len(dev);
+	max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len);
+	fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL);
+	if (!fc_stats->bulk_query_out)
+		return -ENOMEM;
+
 	fc_stats->wq = create_singlethread_workqueue("mlx5_fc");
 	if (!fc_stats->wq)
-		return -ENOMEM;
+		goto err_wq_create;
 
 	fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD;
 	INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work);
 
+	mlx5_fc_pool_init(&fc_stats->fc_pool, dev);
 	return 0;
+
+err_wq_create:
+	kfree(fc_stats->bulk_query_out);
+	return -ENOMEM;
 }
 
 void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
@@ -348,18 +402,21 @@ 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_free_fc(dev, counter);
+		mlx5_fc_release(dev, counter);
 
 	list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list)
-		mlx5_free_fc(dev, counter);
+		mlx5_fc_release(dev, counter);
 }
 
 int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
@@ -401,3 +458,243 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
 	fc_stats->sampling_interval = min_t(unsigned long, interval,
 					    fc_stats->sampling_interval);
 }
+
+/* Flow counter bluks */
+
+struct mlx5_fc_bulk {
+	struct list_head pool_list;
+	u32 base_id;
+	int bulk_len;
+	unsigned long *bitmask;
+	struct mlx5_fc fcs[0];
+};
+
+static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk,
+			 u32 id)
+{
+	counter->bulk = bulk;
+	counter->id = id;
+}
+
+static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk)
+{
+	return bitmap_weight(bulk->bitmask, bulk->bulk_len);
+}
+
+static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev)
+{
+	enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask;
+	struct mlx5_fc_bulk *bulk;
+	int err = -ENOMEM;
+	int bulk_len;
+	u32 base_id;
+	int i;
+
+	alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc);
+	bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1;
+
+	bulk = kzalloc(sizeof(*bulk) + bulk_len * sizeof(struct mlx5_fc),
+		       GFP_KERNEL);
+	if (!bulk)
+		goto err_alloc_bulk;
+
+	bulk->bitmask = kcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long),
+				GFP_KERNEL);
+	if (!bulk->bitmask)
+		goto err_alloc_bitmask;
+
+	err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id);
+	if (err)
+		goto err_mlx5_cmd_bulk_alloc;
+
+	bulk->base_id = base_id;
+	bulk->bulk_len = bulk_len;
+	for (i = 0; i < bulk_len; i++) {
+		mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i);
+		set_bit(i, bulk->bitmask);
+	}
+
+	return bulk;
+
+err_mlx5_cmd_bulk_alloc:
+	kfree(bulk->bitmask);
+err_alloc_bitmask:
+	kfree(bulk);
+err_alloc_bulk:
+	return ERR_PTR(err);
+}
+
+static int
+mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk)
+{
+	if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) {
+		mlx5_core_err(dev, "Freeing bulk before all counters were released\n");
+		return -EBUSY;
+	}
+
+	mlx5_cmd_fc_free(dev, bulk->base_id);
+	kfree(bulk->bitmask);
+	kfree(bulk);
+
+	return 0;
+}
+
+static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk)
+{
+	int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len);
+
+	if (free_fc_index >= bulk->bulk_len)
+		return ERR_PTR(-ENOSPC);
+
+	clear_bit(free_fc_index, bulk->bitmask);
+	return &bulk->fcs[free_fc_index];
+}
+
+static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc)
+{
+	int fc_index = fc->id - bulk->base_id;
+
+	if (test_bit(fc_index, bulk->bitmask))
+		return -EINVAL;
+
+	set_bit(fc_index, bulk->bitmask);
+	return 0;
+}
+
+/* Flow counters pool API */
+
+static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev)
+{
+	fc_pool->dev = dev;
+	mutex_init(&fc_pool->pool_lock);
+	INIT_LIST_HEAD(&fc_pool->fully_used);
+	INIT_LIST_HEAD(&fc_pool->partially_used);
+	INIT_LIST_HEAD(&fc_pool->unused);
+	fc_pool->available_fcs = 0;
+	fc_pool->used_fcs = 0;
+	fc_pool->threshold = 0;
+}
+
+static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool)
+{
+	struct mlx5_core_dev *dev = fc_pool->dev;
+	struct mlx5_fc_bulk *bulk;
+	struct mlx5_fc_bulk *tmp;
+
+	list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list)
+		mlx5_fc_bulk_destroy(dev, bulk);
+	list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list)
+		mlx5_fc_bulk_destroy(dev, bulk);
+	list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list)
+		mlx5_fc_bulk_destroy(dev, bulk);
+}
+
+static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool)
+{
+	fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD,
+				   fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO);
+}
+
+static struct mlx5_fc_bulk *
+mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool)
+{
+	struct mlx5_core_dev *dev = fc_pool->dev;
+	struct mlx5_fc_bulk *new_bulk;
+
+	new_bulk = mlx5_fc_bulk_create(dev);
+	if (!IS_ERR(new_bulk))
+		fc_pool->available_fcs += new_bulk->bulk_len;
+	mlx5_fc_pool_update_threshold(fc_pool);
+	return new_bulk;
+}
+
+static void
+mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk)
+{
+	struct mlx5_core_dev *dev = fc_pool->dev;
+
+	fc_pool->available_fcs -= bulk->bulk_len;
+	mlx5_fc_bulk_destroy(dev, bulk);
+	mlx5_fc_pool_update_threshold(fc_pool);
+}
+
+static struct mlx5_fc *
+mlx5_fc_pool_acquire_from_list(struct list_head *src_list,
+			       struct list_head *next_list,
+			       bool move_non_full_bulk)
+{
+	struct mlx5_fc_bulk *bulk;
+	struct mlx5_fc *fc;
+
+	if (list_empty(src_list))
+		return ERR_PTR(-ENODATA);
+
+	bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list);
+	fc = mlx5_fc_bulk_acquire_fc(bulk);
+	if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0)
+		list_move(&bulk->pool_list, next_list);
+	return fc;
+}
+
+static struct mlx5_fc *
+mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool)
+{
+	struct mlx5_fc_bulk *new_bulk;
+	struct mlx5_fc *fc;
+
+	mutex_lock(&fc_pool->pool_lock);
+
+	fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used,
+					    &fc_pool->fully_used, false);
+	if (IS_ERR(fc))
+		fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused,
+						    &fc_pool->partially_used,
+						    true);
+	if (IS_ERR(fc)) {
+		new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool);
+		if (IS_ERR(new_bulk)) {
+			fc = ERR_CAST(new_bulk);
+			goto out;
+		}
+		fc = mlx5_fc_bulk_acquire_fc(new_bulk);
+		list_add(&new_bulk->pool_list, &fc_pool->partially_used);
+	}
+	fc_pool->available_fcs--;
+	fc_pool->used_fcs++;
+
+out:
+	mutex_unlock(&fc_pool->pool_lock);
+	return fc;
+}
+
+static void
+mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc)
+{
+	struct mlx5_core_dev *dev = fc_pool->dev;
+	struct mlx5_fc_bulk *bulk = fc->bulk;
+	int bulk_free_fcs_amount;
+
+	mutex_lock(&fc_pool->pool_lock);
+
+	if (mlx5_fc_bulk_release_fc(bulk, fc)) {
+		mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n");
+		goto unlock;
+	}
+
+	fc_pool->available_fcs++;
+	fc_pool->used_fcs--;
+
+	bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk);
+	if (bulk_free_fcs_amount == 1)
+		list_move_tail(&bulk->pool_list, &fc_pool->partially_used);
+	if (bulk_free_fcs_amount == bulk->bulk_len) {
+		list_del(&bulk->pool_list);
+		if (fc_pool->available_fcs > fc_pool->threshold)
+			mlx5_fc_pool_free_bulk(fc_pool, bulk);
+		else
+			list_add(&bulk->pool_list, &fc_pool->unused);
+	}
+
+unlock:
+	mutex_unlock(&fc_pool->pool_lock);
+}

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

@@ -1217,8 +1217,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
 	int err = 0;
 
-	if (cleanup)
+	if (cleanup) {
+		mlx5_unregister_device(dev);
 		mlx5_drain_health_wq(dev);
+	}
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
@@ -1369,7 +1371,6 @@ static void remove_one(struct pci_dev *pdev)
 
 	mlx5_crdump_disable(dev);
 	mlx5_devlink_unregister(devlink);
-	mlx5_unregister_device(dev);
 
 	if (mlx5_unload_one(dev, true)) {
 		mlx5_core_err(dev, "mlx5_unload_one failed\n");

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

@@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev,
 			   u8 *min_inline_mode)
 {
 	switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) {
+	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+		if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode))
+			break;
+		/* fall through */
 	case MLX5_CAP_INLINE_MODE_L2:
 		*min_inline_mode = MLX5_INLINE_MODE_L2;
 		break;
-	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
-		mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode);
-		break;
 	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
 		*min_inline_mode = MLX5_INLINE_MODE_NONE;
 		break;

include/linux/mlx5/driver.h

@@ -477,6 +477,17 @@ struct mlx5_core_sriov {
 	u16			max_vfs;
 };
 
+struct mlx5_fc_pool {
+	struct mlx5_core_dev *dev;
+	struct mutex pool_lock; /* protects pool lists */
+	struct list_head fully_used;
+	struct list_head partially_used;
+	struct list_head unused;
+	int available_fcs;
+	int used_fcs;
+	int threshold;
+};
+
 struct mlx5_fc_stats {
 	spinlock_t counters_idr_lock; /* protects counters_idr */
 	struct idr counters_idr;
@@ -488,6 +499,8 @@ struct mlx5_fc_stats {
 	struct delayed_work work;
 	unsigned long next_query;
 	unsigned long sampling_interval; /* jiffies */
+	u32 *bulk_query_out;
+	struct mlx5_fc_pool fc_pool;
 };
 
 struct mlx5_events;

include/linux/mlx5/mlx5_ifc.h

@@ -1040,6 +1040,21 @@ enum {
 	MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1,
 };
 
+#define MLX5_FC_BULK_SIZE_FACTOR 128
+
+enum mlx5_fc_bulk_alloc_bitmask {
+	MLX5_FC_BULK_128   = (1 << 0),
+	MLX5_FC_BULK_256   = (1 << 1),
+	MLX5_FC_BULK_512   = (1 << 2),
+	MLX5_FC_BULK_1024  = (1 << 3),
+	MLX5_FC_BULK_2048  = (1 << 4),
+	MLX5_FC_BULK_4096  = (1 << 5),
+	MLX5_FC_BULK_8192  = (1 << 6),
+	MLX5_FC_BULK_16384 = (1 << 7),
+};
+
+#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
+
 struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_0[0x30];
 	u8         vhca_id[0x10];
@@ -1244,7 +1259,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_2e0[0x7];
 	u8         max_qp_mcg[0x19];
 
-	u8         reserved_at_300[0x18];
+	u8         reserved_at_300[0x10];
+	u8         flow_counter_bulk_alloc[0x8];
 	u8         log_max_mcg[0x8];
 
 	u8         reserved_at_320[0x3];
@@ -2766,7 +2782,7 @@ struct mlx5_ifc_traffic_counter_bits {
 struct mlx5_ifc_tisc_bits {
 	u8         strict_lag_tx_port_affinity[0x1];
 	u8         tls_en[0x1];
-	u8         reserved_at_1[0x2];
+	u8         reserved_at_2[0x2];
 	u8         lag_tx_port_affinity[0x04];
 
 	u8         reserved_at_8[0x4];
@@ -2941,6 +2957,13 @@ enum {
 	SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3,
 };
 
+enum {
+	ELEMENT_TYPE_CAP_MASK_TASR		= 1 << 0,
+	ELEMENT_TYPE_CAP_MASK_VPORT		= 1 << 1,
+	ELEMENT_TYPE_CAP_MASK_VPORT_TC		= 1 << 2,
+	ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC	= 1 << 3,
+};
+
 struct mlx5_ifc_scheduling_context_bits {
 	u8         element_type[0x8];
 	u8         reserved_at_8[0x18];
@@ -7815,7 +7838,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x40];
+	u8         reserved_at_40[0x38];
+	u8         flow_counter_bulk[0x8];
 };
 
 struct mlx5_ifc_add_vxlan_udp_dport_out_bits {