From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB

---
 kernel/drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3255 +++++++++++++++++++++++++++++++++-------------------------
 1 files changed, 1,866 insertions(+), 1,389 deletions(-)

diff --git a/kernel/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/kernel/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5979fcf..5673a41 100644
--- a/kernel/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/kernel/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -34,14 +34,18 @@
 #include <net/pkt_cls.h>
 #include <linux/mlx5/fs.h>
 #include <net/vxlan.h>
+#include <net/geneve.h>
 #include <linux/bpf.h>
+#include <linux/if_bridge.h>
 #include <net/page_pool.h>
+#include <net/xdp_sock_drv.h>
 #include "eswitch.h"
 #include "en.h"
+#include "en/txrx.h"
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
-#include "en_accel/ipsec_rxtx.h"
+#include "en_accel/en_accel.h"
 #include "en_accel/tls.h"
 #include "accel/ipsec.h"
 #include "accel/tls.h"
@@ -49,34 +53,17 @@
 #include "lib/clock.h"
 #include "en/port.h"
 #include "en/xdp.h"
-
-struct mlx5e_rq_param {
-	u32			rqc[MLX5_ST_SZ_DW(rqc)];
-	struct mlx5_wq_param	wq;
-	struct mlx5e_rq_frags_info frags_info;
-};
-
-struct mlx5e_sq_param {
-	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
-	struct mlx5_wq_param       wq;
-};
-
-struct mlx5e_cq_param {
-	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
-	struct mlx5_wq_param       wq;
-	u16                        eq_ix;
-	u8                         cq_period_mode;
-};
-
-struct mlx5e_channel_param {
-	struct mlx5e_rq_param      rq;
-	struct mlx5e_sq_param      sq;
-	struct mlx5e_sq_param      xdp_sq;
-	struct mlx5e_sq_param      icosq;
-	struct mlx5e_cq_param      rx_cq;
-	struct mlx5e_cq_param      tx_cq;
-	struct mlx5e_cq_param      icosq_cq;
-};
+#include "lib/eq.h"
+#include "en/monitor_stats.h"
+#include "en/health.h"
+#include "en/params.h"
+#include "en/xsk/pool.h"
+#include "en/xsk/setup.h"
+#include "en/xsk/rx.h"
+#include "en/xsk/tx.h"
+#include "en/hv_vhca_stats.h"
+#include "en/devlink.h"
+#include "lib/mlx5.h"
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
@@ -96,109 +83,9 @@
 	return true;
 }
 
-static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
-{
-	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	u16 linear_rq_headroom = params->xdp_prog ?
-		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
-	u32 frag_sz;
-
-	linear_rq_headroom += NET_IP_ALIGN;
-
-	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
-
-	if (params->xdp_prog && frag_sz < PAGE_SIZE)
-		frag_sz = PAGE_SIZE;
-
-	return frag_sz;
-}
-
-static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
-{
-	u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-
-	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
-}
-
-static bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params)
-{
-	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-
-	return !params->lro_en && frag_sz <= PAGE_SIZE;
-}
-
-#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
-					  MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
-static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
-					 struct mlx5e_params *params)
-{
-	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-	s8 signed_log_num_strides_param;
-	u8 log_num_strides;
-
-	if (!mlx5e_rx_is_linear_skb(mdev, params))
-		return false;
-
-	if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
-		return false;
-
-	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
-		return true;
-
-	log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz);
-	signed_log_num_strides_param =
-		(s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
-
-	return signed_log_num_strides_param >= 0;
-}
-
-static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
-{
-	if (params->log_rq_mtu_frames <
-	    mlx5e_mpwqe_log_pkts_per_wqe(params) + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
-
-	return params->log_rq_mtu_frames - mlx5e_mpwqe_log_pkts_per_wqe(params);
-}
-
-static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
-					  struct mlx5e_params *params)
-{
-	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
-		return order_base_2(mlx5e_rx_get_linear_frag_sz(params));
-
-	return MLX5E_MPWQE_STRIDE_SZ(mdev,
-		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
-}
-
-static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
-					  struct mlx5e_params *params)
-{
-	return MLX5_MPWRQ_LOG_WQE_SZ -
-		mlx5e_mpwqe_get_log_stride_size(mdev, params);
-}
-
-static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
-				 struct mlx5e_params *params)
-{
-	u16 linear_rq_headroom = params->xdp_prog ?
-		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
-	bool is_linear_skb;
-
-	linear_rq_headroom += NET_IP_ALIGN;
-
-	is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
-		mlx5e_rx_is_linear_skb(mdev, params) :
-		mlx5e_rx_mpwqe_is_linear_skb(mdev, params);
-
-	return is_linear_skb ? linear_rq_headroom : 0;
-}
-
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params)
 {
-	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 	params->log_rq_mtu_frames = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
@@ -206,18 +93,31 @@
 	mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
 		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
 		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
-		       BIT(mlx5e_mpwqe_get_log_rq_size(params)) :
+		       BIT(mlx5e_mpwqe_get_log_rq_size(params, NULL)) :
 		       BIT(params->log_rq_mtu_frames),
-		       BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
+		       BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)),
 		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params)
 {
-	return mlx5e_check_fragmented_striding_rq_cap(mdev) &&
-		!MLX5_IPSEC_DEV(mdev) &&
-		!(params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params));
+	if (!mlx5e_check_fragmented_striding_rq_cap(mdev))
+		return false;
+
+	if (MLX5_IPSEC_DEV(mdev))
+		return false;
+
+	if (params->xdp_prog) {
+		/* XSK params are not considered here. If striding RQ is in use,
+		 * and an XSK is being opened, mlx5e_rx_mpwqe_is_linear_skb will
+		 * be called with the known XSK params.
+		 */
+		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
+			return false;
+	}
+
+	return true;
 }
 
 void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
@@ -228,7 +128,7 @@
 		MLX5_WQ_TYPE_CYCLIC;
 }
 
-static void mlx5e_update_carrier(struct mlx5e_priv *priv)
+void mlx5e_update_carrier(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 port_state;
@@ -258,29 +158,9 @@
 	mutex_unlock(&priv->state_lock);
 }
 
-void mlx5e_update_stats(struct mlx5e_priv *priv)
+static void mlx5e_update_stats_work(struct work_struct *work)
 {
-	int i;
-
-	for (i = mlx5e_num_stats_grps - 1; i >= 0; i--)
-		if (mlx5e_stats_grps[i].update_stats)
-			mlx5e_stats_grps[i].update_stats(priv);
-}
-
-static void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
-{
-	int i;
-
-	for (i = mlx5e_num_stats_grps - 1; i >= 0; i--)
-		if (mlx5e_stats_grps[i].update_stats_mask &
-		    MLX5E_NDO_UPDATE_STATS)
-			mlx5e_stats_grps[i].update_stats(priv);
-}
-
-void mlx5e_update_stats_work(struct work_struct *work)
-{
-	struct delayed_work *dwork = to_delayed_work(work);
-	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       update_stats_work);
 
 	mutex_lock(&priv->state_lock);
@@ -288,33 +168,46 @@
 	mutex_unlock(&priv->state_lock);
 }
 
-static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
-			      enum mlx5_dev_event event, unsigned long param)
+void mlx5e_queue_update_stats(struct mlx5e_priv *priv)
 {
-	struct mlx5e_priv *priv = vpriv;
-
-	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
+	if (!priv->profile->update_stats)
 		return;
 
-	switch (event) {
-	case MLX5_DEV_EVENT_PORT_UP:
-	case MLX5_DEV_EVENT_PORT_DOWN:
+	if (unlikely(test_bit(MLX5E_STATE_DESTROYING, &priv->state)))
+		return;
+
+	queue_work(priv->wq, &priv->update_stats_work);
+}
+
+static int async_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+	struct mlx5_eqe   *eqe = data;
+
+	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+		return NOTIFY_DONE;
+
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
 		queue_work(priv->wq, &priv->update_carrier_work);
 		break;
 	default:
-		break;
+		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_OK;
 }
 
 static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 {
-	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
+	priv->events_nb.notifier_call = async_event;
+	mlx5_notifier_register(priv->mdev, &priv->events_nb);
 }
 
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
-	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
+	mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
 }
 
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
@@ -327,33 +220,12 @@
 
 	cseg->qpn_ds    = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
 				      ds_cnt);
-	cseg->fm_ce_se  = MLX5_WQE_CTRL_CQ_UPDATE;
-	cseg->imm       = rq->mkey_be;
+	cseg->umr_mkey  = rq->mkey_be;
 
 	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
 	ucseg->xlt_octowords =
 		cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
-}
-
-static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
-{
-	switch (rq->wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
-	default:
-		return mlx5_wq_cyc_get_size(&rq->wqe.wq);
-	}
-}
-
-static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
-{
-	switch (rq->wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return rq->mpwqe.wq.cur_sz;
-	default:
-		return rq->wqe.wq.cur_sz;
-	}
 }
 
 static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
@@ -374,12 +246,17 @@
 
 static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 				 u64 npages, u8 page_shift,
-				 struct mlx5_core_mkey *umr_mkey)
+				 struct mlx5_core_mkey *umr_mkey,
+				 dma_addr_t filler_addr)
 {
-	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+	struct mlx5_mtt *mtt;
+	int inlen;
 	void *mkc;
 	u32 *in;
 	int err;
+	int i;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
@@ -392,13 +269,25 @@
 	MLX5_SET(mkc, mkc, lw, 1);
 	MLX5_SET(mkc, mkc, lr, 1);
 	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);
-
+	mlx5e_mkey_set_relaxed_ordering(mdev, mkc);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 	MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn);
 	MLX5_SET64(mkc, mkc, len, npages << page_shift);
 	MLX5_SET(mkc, mkc, translations_octword_size,
 		 MLX5_MTT_OCTW(npages));
 	MLX5_SET(mkc, mkc, log_page_size, page_shift);
+	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+		 MLX5_MTT_OCTW(npages));
+
+	/* Initialize the mkey with all MTTs pointing to a default
+	 * page (filler_addr). When the channels are activated, UMR
+	 * WQEs will redirect the RX WQEs to the actual memory from
+	 * the RQ's pool, while the gaps (wqe_overflow) remain mapped
+	 * to the default page.
+	 */
+	mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+	for (i = 0 ; i < npages ; i++)
+		mtt[i].ptag = cpu_to_be64(filler_addr);
 
 	err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
 
@@ -410,12 +299,13 @@
 {
 	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq));
 
-	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey,
+				     rq->wqe_overflow.addr);
 }
 
-static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
+static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix)
 {
-	return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
+	return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT;
 }
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
@@ -452,7 +342,6 @@
 }
 
 static int mlx5e_init_di_list(struct mlx5e_rq *rq,
-			      struct mlx5e_params *params,
 			      int wq_sz, int cpu)
 {
 	int len = wq_sz << rq->wqe.info.log_num_frags;
@@ -472,8 +361,39 @@
 	kvfree(rq->wqe.di);
 }
 
+static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_rq *rq = container_of(recover_work, struct mlx5e_rq, recover_work);
+
+	mlx5e_reporter_rq_cqe_err(rq);
+}
+
+static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+	rq->wqe_overflow.page = alloc_page(GFP_KERNEL);
+	if (!rq->wqe_overflow.page)
+		return -ENOMEM;
+
+	rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0,
+					     PAGE_SIZE, rq->buff.map_dir);
+	if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) {
+		__free_page(rq->wqe_overflow.page);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+	 dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE,
+			rq->buff.map_dir);
+	 __free_page(rq->wqe_overflow.page);
+}
+
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk,
+			  struct xsk_buff_pool *xsk_pool,
 			  struct mlx5e_rq_param *rqp,
 			  struct mlx5e_rq *rq)
 {
@@ -481,6 +401,7 @@
 	struct mlx5_core_dev *mdev = c->mdev;
 	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	u32 rq_xdp_ix;
 	u32 pool_size;
 	int wq_sz;
 	int err;
@@ -497,21 +418,28 @@
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
 	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	rq->stats   = &c->priv->channel_stats[c->ix].rq;
+	rq->xdpsq   = &c->rq_xdpsq;
+	rq->xsk_pool = xsk_pool;
 
-	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
-	if (IS_ERR(rq->xdp_prog)) {
-		err = PTR_ERR(rq->xdp_prog);
-		rq->xdp_prog = NULL;
-		goto err_rq_wq_destroy;
-	}
+	if (rq->xsk_pool)
+		rq->stats = &c->priv->channel_stats[c->ix].xskrq;
+	else
+		rq->stats = &c->priv->channel_stats[c->ix].rq;
+	INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work);
 
-	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix);
+	if (params->xdp_prog)
+		bpf_prog_inc(params->xdp_prog);
+	RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog);
+
+	rq_xdp_ix = rq->ix;
+	if (xsk)
+		rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK;
+	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix);
 	if (err < 0)
-		goto err_rq_wq_destroy;
+		goto err_rq_xdp_prog;
 
-	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params);
+	rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
 	pool_size = 1 << params->log_rq_mtu_frames;
 
 	switch (rq->wq_type) {
@@ -519,114 +447,96 @@
 		err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
 					&rq->wq_ctrl);
 		if (err)
+			goto err_rq_xdp;
+
+		err = mlx5e_alloc_mpwqe_rq_drop_page(rq);
+		if (err)
 			goto err_rq_wq_destroy;
 
 		rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR];
 
 		wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-		pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params);
+		pool_size = MLX5_MPWRQ_PAGES_PER_WQE <<
+			mlx5e_mpwqe_get_log_rq_size(params, xsk);
 
-		rq->post_wqes = mlx5e_post_rx_mpwqes;
-		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
+		rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+		rq->mpwqe.num_strides =
+			BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
 
-		rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe;
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if (MLX5_IPSEC_DEV(mdev)) {
-			err = -EINVAL;
-			netdev_err(c->netdev, "MPWQE RQ with IPSec offload not supported\n");
-			goto err_rq_wq_destroy;
-		}
-#endif
-		if (!rq->handle_rx_cqe) {
-			err = -EINVAL;
-			netdev_err(c->netdev, "RX handler of MPWQE RQ is not set, err %d\n", err);
-			goto err_rq_wq_destroy;
-		}
-
-		rq->mpwqe.skb_from_cqe_mpwrq =
-			mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ?
-			mlx5e_skb_from_cqe_mpwrq_linear :
-			mlx5e_skb_from_cqe_mpwrq_nonlinear;
-		rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params);
-		rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params));
+		rq->buff.frame0_sz = (1 << rq->mpwqe.log_stride_sz);
 
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
-			goto err_rq_wq_destroy;
+			goto err_rq_drop_page;
 		rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
 
 		err = mlx5e_rq_alloc_mpwqe_info(rq, c);
 		if (err)
-			goto err_free;
+			goto err_rq_mkey;
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq,
 					 &rq->wq_ctrl);
 		if (err)
-			goto err_rq_wq_destroy;
+			goto err_rq_xdp;
 
 		rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR];
 
 		wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq);
 
 		rq->wqe.info = rqp->frags_info;
+		rq->buff.frame0_sz = rq->wqe.info.arr[0].frag_stride;
+
 		rq->wqe.frags =
 			kvzalloc_node(array_size(sizeof(*rq->wqe.frags),
 					(wq_sz << rq->wqe.info.log_num_frags)),
 				      GFP_KERNEL, cpu_to_node(c->cpu));
 		if (!rq->wqe.frags) {
 			err = -ENOMEM;
-			goto err_free;
+			goto err_rq_wq_destroy;
 		}
 
-		err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu);
+		err = mlx5e_init_di_list(rq, wq_sz, c->cpu);
 		if (err)
-			goto err_free;
-		rq->post_wqes = mlx5e_post_rx_wqes;
-		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
+			goto err_rq_frags;
 
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if (c->priv->ipsec)
-			rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe;
-		else
-#endif
-			rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe;
-		if (!rq->handle_rx_cqe) {
-			err = -EINVAL;
-			netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err);
-			goto err_free;
-		}
-
-		rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(mdev, params) ?
-			mlx5e_skb_from_cqe_linear :
-			mlx5e_skb_from_cqe_nonlinear;
 		rq->mkey_be = c->mkey_be;
 	}
 
-	/* Create a page_pool and register it with rxq */
-	pp_params.order     = 0;
-	pp_params.flags     = 0; /* No-internal DMA mapping in page_pool */
-	pp_params.pool_size = pool_size;
-	pp_params.nid       = cpu_to_node(c->cpu);
-	pp_params.dev       = c->pdev;
-	pp_params.dma_dir   = rq->buff.map_dir;
-
-	/* page_pool can be used even when there is no rq->xdp_prog,
-	 * given page_pool does not handle DMA mapping there is no
-	 * required state to clear. And page_pool gracefully handle
-	 * elevated refcnt.
-	 */
-	rq->page_pool = page_pool_create(&pp_params);
-	if (IS_ERR(rq->page_pool)) {
-		err = PTR_ERR(rq->page_pool);
-		rq->page_pool = NULL;
-		goto err_free;
-	}
-	err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
-					 MEM_TYPE_PAGE_POOL, rq->page_pool);
+	err = mlx5e_rq_set_handlers(rq, params, xsk);
 	if (err)
-		goto err_free;
+		goto err_free_by_rq_type;
+
+	if (xsk) {
+		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+						 MEM_TYPE_XSK_BUFF_POOL, NULL);
+		xsk_pool_set_rxq_info(rq->xsk_pool, &rq->xdp_rxq);
+	} else {
+		/* Create a page_pool and register it with rxq */
+		pp_params.order     = 0;
+		pp_params.flags     = 0; /* No-internal DMA mapping in page_pool */
+		pp_params.pool_size = pool_size;
+		pp_params.nid       = cpu_to_node(c->cpu);
+		pp_params.dev       = c->pdev;
+		pp_params.dma_dir   = rq->buff.map_dir;
+
+		/* page_pool can be used even when there is no rq->xdp_prog,
+		 * given page_pool does not handle DMA mapping there is no
+		 * required state to clear. And page_pool gracefully handle
+		 * elevated refcnt.
+		 */
+		rq->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rq->page_pool)) {
+			err = PTR_ERR(rq->page_pool);
+			rq->page_pool = NULL;
+			goto err_free_by_rq_type;
+		}
+		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+						 MEM_TYPE_PAGE_POOL, rq->page_pool);
+	}
+	if (err)
+		goto err_free_by_rq_type;
 
 	for (i = 0; i < wq_sz; i++) {
 		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
@@ -634,7 +544,7 @@
 				mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i);
 			u32 byte_count =
 				rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
-			u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
+			u64 dma_offset = mlx5e_get_mpwqe_offset(i);
 
 			wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom);
 			wqe->data[0].byte_count = cpu_to_be32(byte_count);
@@ -664,11 +574,11 @@
 
 	switch (params->rx_cq_moderation.cq_period_mode) {
 	case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
-		rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE;
+		rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
 		break;
 	case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
 	default:
-		rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	}
 
 	rq->page_cache.head = 0;
@@ -676,43 +586,49 @@
 
 	return 0;
 
-err_free:
+err_free_by_rq_type:
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
+err_rq_mkey:
 		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+err_rq_drop_page:
+		mlx5e_free_mpwqe_rq_drop_page(rq);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
-		kvfree(rq->wqe.frags);
 		mlx5e_free_di_list(rq);
+err_rq_frags:
+		kvfree(rq->wqe.frags);
 	}
-
 err_rq_wq_destroy:
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
-	xdp_rxq_info_unreg(&rq->xdp_rxq);
-	if (rq->page_pool)
-		page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
+err_rq_xdp:
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
+err_rq_xdp_prog:
+	if (params->xdp_prog)
+		bpf_prog_put(params->xdp_prog);
 
 	return err;
 }
 
 static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
+	struct mlx5e_channel *c = rq->channel;
+	struct bpf_prog *old_prog = NULL;
 	int i;
 
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
-
-	xdp_rxq_info_unreg(&rq->xdp_rxq);
-	if (rq->page_pool)
-		page_pool_destroy(rq->page_pool);
+	/* drop_rq has neither channel nor xdp_prog. */
+	if (c)
+		old_prog = rcu_dereference_protected(rq->xdp_prog,
+						     lockdep_is_held(&c->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
+		mlx5e_free_mpwqe_rq_drop_page(rq);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		kvfree(rq->wqe.frags);
@@ -723,8 +639,15 @@
 	     i = (i + 1) & (MLX5E_CACHE_SIZE - 1)) {
 		struct mlx5e_dma_info *dma_info = &rq->page_cache.page_cache[i];
 
-		mlx5e_page_release(rq, dma_info, false);
+		/* With AF_XDP, page_cache is not used, so this loop is not
+		 * entered, and it's safe to call mlx5e_page_release_dynamic
+		 * directly.
+		 */
+		mlx5e_page_release_dynamic(rq, dma_info, false);
 	}
+
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
+	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 
@@ -766,8 +689,7 @@
 	return err;
 }
 
-static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
-				 int next_state)
+int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
 
@@ -781,12 +703,15 @@
 	if (!in)
 		return -ENOMEM;
 
+	if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY)
+		mlx5e_rqwq_reset(rq);
+
 	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
 
 	MLX5_SET(modify_rq_in, in, rq_state, curr_state);
 	MLX5_SET(rqc, rqc, state, next_state);
 
-	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in);
 
 	kvfree(in);
 
@@ -817,7 +742,7 @@
 	MLX5_SET(rqc, rqc, scatter_fcs, enable);
 	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
 
-	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in);
 
 	kvfree(in);
 
@@ -846,7 +771,7 @@
 	MLX5_SET(rqc, rqc, vsd, vsd);
 	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
 
-	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in);
 
 	kvfree(in);
 
@@ -858,7 +783,7 @@
 	mlx5_core_destroy_rq(rq->mdev, rq->rqn);
 }
 
-static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
+int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 {
 	unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time);
 	struct mlx5e_channel *c = rq->channel;
@@ -875,10 +800,34 @@
 	netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
 		    c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes);
 
+	mlx5e_reporter_rx_timeout(rq);
 	return -ETIMEDOUT;
 }
 
-static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq;
+	u16 head;
+	int i;
+
+	if (rq->wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		return;
+
+	wq = &rq->mpwqe.wq;
+	head = wq->head;
+
+	/* Outstanding UMR WQEs (in progress) start at wq->head */
+	for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
+		rq->dealloc_wqe(rq, head);
+		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+	}
+
+	rq->mpwqe.actual_wq_head = wq->head;
+	rq->mpwqe.umr_in_progress = 0;
+	rq->mpwqe.umr_completed = 0;
+}
+
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
 	__be16 wqe_ix_be;
 	u16 wqe_ix;
@@ -886,9 +835,7 @@
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
 
-		/* UMR WQE (if in progress) is always at wq->head */
-		if (rq->mpwqe.umr_in_progress)
-			rq->dealloc_wqe(rq, wq->head);
+		mlx5e_free_rx_in_progress_descs(rq);
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
@@ -912,14 +859,13 @@
 
 }
 
-static int mlx5e_open_rq(struct mlx5e_channel *c,
-			 struct mlx5e_params *params,
-			 struct mlx5e_rq_param *param,
-			 struct mlx5e_rq *rq)
+int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		  struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
+		  struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq)
 {
 	int err;
 
-	err = mlx5e_alloc_rq(c, params, param, rq);
+	err = mlx5e_alloc_rq(c, params, xsk, xsk_pool, param, rq);
 	if (err)
 		return err;
 
@@ -931,6 +877,12 @@
 	if (err)
 		goto err_destroy_rq;
 
+	if (mlx5e_is_tls_on(c->priv) && !mlx5_accel_is_ktls_device(c->mdev))
+		__set_bit(MLX5E_RQ_STATE_FPGA_TLS, &c->rq.state); /* must be FPGA */
+
+	if (MLX5_CAP_ETH(c->mdev, cqe_checksum_full))
+		__set_bit(MLX5E_RQ_STATE_CSUM_FULL, &c->rq.state);
+
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
@@ -940,6 +892,13 @@
 	 */
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
+
+	/* For CQE compression on striding RQ, use stride index provided by
+	 * HW if capability is supported.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ) &&
+	    MLX5_CAP_GEN(c->mdev, mini_cqe_resp_stride_index))
+		__set_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &c->rq.state);
 
 	return 0;
 
@@ -951,29 +910,23 @@
 	return err;
 }
 
-static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
-	struct mlx5e_icosq *sq = &rq->channel->icosq;
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *nopwqe;
-
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
-	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+	mlx5e_trigger_irq(&rq->channel->icosq);
 }
 
-static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
+	synchronize_net(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
 }
 
-static void mlx5e_close_rq(struct mlx5e_rq *rq)
+void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
+	cancel_work_sync(&rq->channel->icosq.recover_work);
+	cancel_work_sync(&rq->recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
 	mlx5e_free_rq(rq);
@@ -981,18 +934,42 @@
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kvfree(sq->db.xdpi);
+	kvfree(sq->db.xdpi_fifo.xi);
+	kvfree(sq->db.wqe_info);
+}
+
+static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa)
+{
+	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
+	int wq_sz        = mlx5_wq_cyc_get_size(&sq->wq);
+	int dsegs_per_wq = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+	xdpi_fifo->xi = kvzalloc_node(sizeof(*xdpi_fifo->xi) * dsegs_per_wq,
+				      GFP_KERNEL, numa);
+	if (!xdpi_fifo->xi)
+		return -ENOMEM;
+
+	xdpi_fifo->pc   = &sq->xdpi_fifo_pc;
+	xdpi_fifo->cc   = &sq->xdpi_fifo_cc;
+	xdpi_fifo->mask = dsegs_per_wq - 1;
+
+	return 0;
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int err;
 
-	sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)),
-				    GFP_KERNEL, numa);
-	if (!sq->db.xdpi) {
-		mlx5e_free_xdpsq_db(sq);
+	sq->db.wqe_info = kvzalloc_node(sizeof(*sq->db.wqe_info) * wq_sz,
+					GFP_KERNEL, numa);
+	if (!sq->db.wqe_info)
 		return -ENOMEM;
+
+	err = mlx5e_alloc_xdpsq_fifo(sq, numa);
+	if (err) {
+		mlx5e_free_xdpsq_db(sq);
+		return err;
 	}
 
 	return 0;
@@ -1000,6 +977,7 @@
 
 static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
+			     struct xsk_buff_pool *xsk_pool,
 			     struct mlx5e_sq_param *param,
 			     struct mlx5e_xdpsq *sq,
 			     bool is_redirect)
@@ -1014,10 +992,14 @@
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
-	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	sq->stats     = is_redirect ?
-		&c->priv->channel_stats[c->ix].xdpsq :
-		&c->priv->channel_stats[c->ix].rq_xdpsq;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
+	sq->xsk_pool  = xsk_pool;
+
+	sq->stats = sq->xsk_pool ?
+		&c->priv->channel_stats[c->ix].xsksq :
+		is_redirect ?
+			&c->priv->channel_stats[c->ix].xdpsq :
+			&c->priv->channel_stats[c->ix].rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1045,25 +1027,44 @@
 
 static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
-	kvfree(sq->db.ico_wqe);
+	kvfree(sq->db.wqe_info);
 }
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
-	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	size_t size;
 
-	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
-						  sizeof(*sq->db.ico_wqe)),
-				       GFP_KERNEL, numa);
-	if (!sq->db.ico_wqe)
+	size = array_size(wq_sz, sizeof(*sq->db.wqe_info));
+	sq->db.wqe_info = kvzalloc_node(size, GFP_KERNEL, numa);
+	if (!sq->db.wqe_info)
 		return -ENOMEM;
 
 	return 0;
 }
 
+static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	mlx5e_reporter_icosq_cqe_err(sq);
+}
+
+static void mlx5e_async_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	/* Not implemented yet. */
+
+	netdev_warn(sq->channel->netdev, "async_icosq recovery is not implemented\n");
+}
+
 static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_icosq *sq)
+			     struct mlx5e_icosq *sq,
+			     work_func_t recover_work_func)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -1083,6 +1084,8 @@
 	if (err)
 		goto err_sq_wq_destroy;
 
+	INIT_WORK(&sq->recover_work, recover_work_func);
+
 	return 0;
 
 err_sq_wq_destroy:
@@ -1100,6 +1103,7 @@
 static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
 	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.skb_fifo);
 	kvfree(sq->db.dma_fifo);
 }
 
@@ -1111,20 +1115,46 @@
 	sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
 						   sizeof(*sq->db.dma_fifo)),
 					GFP_KERNEL, numa);
+	sq->db.skb_fifo = kvzalloc_node(array_size(df_sz,
+						   sizeof(*sq->db.skb_fifo)),
+					GFP_KERNEL, numa);
 	sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
 						   sizeof(*sq->db.wqe_info)),
 					GFP_KERNEL, numa);
-	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
+	if (!sq->db.dma_fifo || !sq->db.skb_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
 		return -ENOMEM;
 	}
 
 	sq->dma_fifo_mask = df_sz - 1;
+	sq->skb_fifo_mask = df_sz - 1;
 
 	return 0;
 }
 
-static void mlx5e_sq_recover(struct work_struct *work);
+static int mlx5e_calc_sq_stop_room(struct mlx5e_txqsq *sq, u8 log_sq_size)
+{
+	int sq_size = 1 << log_sq_size;
+
+	sq->stop_room  = mlx5e_tls_get_stop_room(sq);
+	sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+	if (test_bit(MLX5E_SQ_STATE_MPWQE, &sq->state))
+		/* A MPWQE can take up to the maximum-sized WQE + all the normal
+		 * stop room can be taken if a new packet breaks the active
+		 * MPWQE session and allocates its WQEs right away.
+		 */
+		sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+
+	if (WARN_ON(sq->stop_room >= sq_size)) {
+		netdev_err(sq->channel->netdev, "Stop room %hu is bigger than the SQ size %d\n",
+			   sq->stop_room, sq_size);
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
 static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
 			     struct mlx5e_params *params,
@@ -1142,15 +1172,24 @@
 	sq->clock     = &mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
+	sq->ch_ix     = c->ix;
 	sq->txq_ix    = txq_ix;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
-	INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
+	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))
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
+	if (param->is_mpw)
+		set_bit(MLX5E_SQ_STATE_MPWQE, &sq->state);
+	err = mlx5e_calc_sq_stop_room(sq, params->log_sq_size);
+	if (err)
+		return err;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1234,15 +1273,8 @@
 	return err;
 }
 
-struct mlx5e_modify_sq_param {
-	int curr_state;
-	int next_state;
-	bool rl_update;
-	int rl_index;
-};
-
-static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
-			   struct mlx5e_modify_sq_param *p)
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p)
 {
 	void *in;
 	void *sqc;
@@ -1263,7 +1295,7 @@
 		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, p->rl_index);
 	}
 
-	err = mlx5_core_modify_sq(mdev, sqn, in, inlen);
+	err = mlx5_core_modify_sq(mdev, sqn, in);
 
 	kvfree(in);
 
@@ -1334,32 +1366,20 @@
 	return 0;
 
 err_free_txqsq:
-	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	mlx5e_free_txqsq(sq);
 
 	return err;
 }
 
-static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
-{
-	WARN_ONCE(sq->cc != sq->pc,
-		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
-		  sq->sqn, sq->cc, sq->pc);
-	sq->cc = 0;
-	sq->dma_fifo_cc = 0;
-	sq->pc = 0;
-}
-
-static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 {
 	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
-	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	netdev_tx_reset_queue(sq->txq);
 	netif_tx_start_queue(sq->txq);
 }
 
-static inline void netif_tx_disable_queue(struct netdev_queue *txq)
+void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
 	netif_tx_stop_queue(txq);
@@ -1368,21 +1388,22 @@
 
 static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&c->napi);
+	synchronize_net(); /* Sync with NAPI to prevent netif_tx_wake_queue. */
 
-	netif_tx_disable_queue(sq->txq);
+	mlx5e_tx_disable_queue(sq->txq);
 
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
 		u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 		struct mlx5e_tx_wqe *nop;
 
-		sq->db.wqe_info[pi].skb = NULL;
+		sq->db.wqe_info[pi] = (struct mlx5e_tx_wqe_info) {
+			.num_wqebbs = 1,
+		};
+
 		nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
@@ -1395,6 +1416,7 @@
 	struct mlx5_rate_limit rl = {0};
 
 	cancel_work_sync(&sq->dim.work);
+	cancel_work_sync(&sq->recover_work);
 	mlx5e_destroy_sq(mdev, sq->sqn);
 	if (sq->rate_limit) {
 		rl.rate = sq->rate_limit;
@@ -1404,123 +1426,28 @@
 	mlx5e_free_txqsq(sq);
 }
 
-static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 {
-	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
+					      recover_work);
 
-	while (time_before(jiffies, exp_time)) {
-		if (sq->cc == sq->pc)
-			return 0;
-
-		msleep(20);
-	}
-
-	netdev_err(sq->channel->netdev,
-		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
-		   sq->sqn, sq->cc, sq->pc);
-
-	return -ETIMEDOUT;
+	mlx5e_reporter_tx_err_cqe(sq);
 }
 
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
-{
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	struct mlx5e_modify_sq_param msp = {0};
-	int err;
-
-	msp.curr_state = curr_state;
-	msp.next_state = MLX5_SQC_STATE_RST;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
-		return err;
-	}
-
-	memset(&msp, 0, sizeof(msp));
-	msp.curr_state = MLX5_SQC_STATE_RST;
-	msp.next_state = MLX5_SQC_STATE_RDY;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
-		return err;
-	}
-
-	return 0;
-}
-
-static void mlx5e_sq_recover(struct work_struct *work)
-{
-	struct mlx5e_txqsq_recover *recover =
-		container_of(work, struct mlx5e_txqsq_recover,
-			     recover_work);
-	struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq,
-					      recover);
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	u8 state;
-	int err;
-
-	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
-	if (err) {
-		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
-			   sq->sqn, err);
-		return;
-	}
-
-	if (state != MLX5_RQC_STATE_ERR) {
-		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
-		return;
-	}
-
-	netif_tx_disable_queue(sq->txq);
-
-	if (mlx5e_wait_for_sq_flush(sq))
-		return;
-
-	/* If the interval between two consecutive recovers per SQ is too
-	 * short, don't recover to avoid infinite loop of ERR_CQE -> recover.
-	 * If we reached this state, there is probably a bug that needs to be
-	 * fixed. let's keep the queue close and let tx timeout cleanup.
-	 */
-	if (jiffies_to_msecs(jiffies - recover->last_recover) <
-	    MLX5E_SQ_RECOVER_MIN_INTERVAL) {
-		netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n",
-			   sq->sqn);
-		return;
-	}
-
-	/* At this point, no new packets will arrive from the stack as TXQ is
-	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
-	 * pending WQEs.  SQ can safely reset the SQ.
-	 */
-	if (mlx5e_sq_to_ready(sq, state))
-		return;
-
-	mlx5e_reset_txqsq_cc_pc(sq);
-	sq->stats->recover++;
-	recover->last_recover = jiffies;
-	mlx5e_activate_txqsq(sq);
-}
-
-static int mlx5e_open_icosq(struct mlx5e_channel *c,
-			    struct mlx5e_params *params,
-			    struct mlx5e_sq_param *param,
-			    struct mlx5e_icosq *sq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param, struct mlx5e_icosq *sq,
+			    work_func_t recover_work_func)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
 
-	err = mlx5e_alloc_icosq(c, param, sq);
+	err = mlx5e_alloc_icosq(c, param, sq, recover_work_func);
 	if (err)
 		return err;
 
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = params->tx_min_inline_mode;
-	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
 		goto err_free_icosq;
@@ -1528,68 +1455,82 @@
 	return 0;
 
 err_free_icosq:
-	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	mlx5e_free_icosq(sq);
 
 	return err;
+}
+
+void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
+{
+	set_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
+}
+
+void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
+{
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
+	synchronize_net(); /* Sync with NAPI. */
 }
 
 static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
-	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	napi_synchronize(&c->napi);
-
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
+	mlx5e_free_icosq_descs(sq);
 	mlx5e_free_icosq(sq);
 }
 
-static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
-			    struct mlx5e_params *params,
-			    struct mlx5e_sq_param *param,
-			    struct mlx5e_xdpsq *sq,
-			    bool is_redirect)
+int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
+		     struct mlx5e_xdpsq *sq, bool is_redirect)
 {
-	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 	struct mlx5e_create_sq_param csp = {};
-	unsigned int inline_hdr_sz = 0;
 	int err;
-	int i;
 
-	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
+	err = mlx5e_alloc_xdpsq(c, params, xsk_pool, param, sq, is_redirect);
 	if (err)
 		return err;
 
 	csp.tis_lst_sz      = 1;
-	csp.tisn            = c->priv->tisn[0]; /* tc = 0 */
+	csp.tisn            = c->priv->tisn[c->lag_port][0]; /* tc = 0 */
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
-	if (is_redirect)
-		set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
 		goto err_free_xdpsq;
 
-	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-		ds_cnt++;
-	}
+	mlx5e_set_xmit_fp(sq, param->is_mpw);
 
-	/* Pre initialize fixed WQE fields */
-	for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-		struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-		struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-		struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-		struct mlx5_wqe_data_seg *dseg;
+	if (!param->is_mpw) {
+		unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
+		unsigned int inline_hdr_sz = 0;
+		int i;
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
+			ds_cnt++;
+		}
 
-		dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
-		dseg->lkey = sq->mkey_be;
+		/* Pre initialize fixed WQE fields */
+		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
+			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+			struct mlx5_wqe_data_seg *dseg;
+
+			sq->db.wqe_info[i] = (struct mlx5e_xdp_wqe_info) {
+				.num_wqebbs = 1,
+				.num_pkts   = 1,
+			};
+
+			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+
+			dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
+			dseg->lkey = sq->mkey_be;
+		}
 	}
 
 	return 0;
@@ -1601,12 +1542,12 @@
 	return err;
 }
 
-static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
+void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	napi_synchronize(&c->napi);
+	synchronize_net(); /* Sync with NAPI. */
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
 	mlx5e_free_xdpsq_descs(sq);
@@ -1618,14 +1559,8 @@
 				 struct mlx5e_cq *cq)
 {
 	struct mlx5_core_cq *mcq = &cq->mcq;
-	int eqn_not_used;
-	unsigned int irqn;
 	int err;
 	u32 i;
-
-	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
-	if (err)
-		return err;
 
 	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
 			       &cq->wq_ctrl);
@@ -1640,7 +1575,6 @@
 	mcq->vector     = param->eq_ix;
 	mcq->comp       = mlx5e_completion_event;
 	mcq->event      = mlx5e_cq_error_event;
-	mcq->irqn       = irqn;
 
 	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
 		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
@@ -1679,17 +1613,17 @@
 
 static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 {
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	struct mlx5_core_dev *mdev = cq->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 
 	void *in;
 	void *cqc;
 	int inlen;
-	unsigned int irqn_not_used;
 	int eqn;
 	int err;
 
-	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
+	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn);
 	if (err)
 		return err;
 
@@ -1713,7 +1647,7 @@
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
 
-	err = mlx5_core_create_cq(mdev, mcq, in, inlen);
+	err = mlx5_core_create_cq(mdev, mcq, in, inlen, out, sizeof(out));
 
 	kvfree(in);
 
@@ -1730,10 +1664,8 @@
 	mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
 }
 
-static int mlx5e_open_cq(struct mlx5e_channel *c,
-			 struct net_dim_cq_moder moder,
-			 struct mlx5e_cq_param *param,
-			 struct mlx5e_cq *cq)
+int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder,
+		  struct mlx5e_cq_param *param, struct mlx5e_cq *cq)
 {
 	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
@@ -1756,15 +1688,10 @@
 	return err;
 }
 
-static void mlx5e_close_cq(struct mlx5e_cq *cq)
+void mlx5e_close_cq(struct mlx5e_cq *cq)
 {
 	mlx5e_destroy_cq(cq);
 	mlx5e_free_cq(cq);
-}
-
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.irq_info[ix + MLX5_EQ_VEC_COMP_BASE].mask);
 }
 
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
@@ -1776,7 +1703,7 @@
 
 	for (tc = 0; tc < c->num_tc; tc++) {
 		err = mlx5e_open_cq(c, params->tx_cq_moderation,
-				    &cparam->tx_cq, &c->sq[tc].cq);
+				    &cparam->txq_sq.cqp, &c->sq[tc].cq);
 		if (err)
 			goto err_close_tx_cqs;
 	}
@@ -1802,14 +1729,13 @@
 			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
 {
-	struct mlx5e_priv *priv = c->priv;
-	int err, tc, max_nch = priv->profile->max_nch(priv->mdev);
+	int err, tc;
 
 	for (tc = 0; tc < params->num_tc; tc++) {
-		int txq_ix = c->ix + tc * max_nch;
+		int txq_ix = c->ix + tc * params->num_channels;
 
-		err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
-				       params, &cparam->sq, &c->sq[tc], tc);
+		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
+				       params, &cparam->txq_sq, &c->sq[tc], tc);
 		if (err)
 			goto err_close_sqs;
 	}
@@ -1912,88 +1838,70 @@
 	return err;
 }
 
-static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
-			      struct mlx5e_params *params,
-			      struct mlx5e_channel_param *cparam,
-			      struct mlx5e_channel **cp)
+static int mlx5e_open_queues(struct mlx5e_channel *c,
+			     struct mlx5e_params *params,
+			     struct mlx5e_channel_param *cparam)
 {
-	struct net_dim_cq_moder icocq_moder = {0, 0};
-	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
-	struct mlx5e_channel *c;
-	unsigned int irq;
+	struct dim_cq_moder icocq_moder = {0, 0};
 	int err;
-	int eqn;
 
-	err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq.cqp, &c->async_icosq.cq);
 	if (err)
 		return err;
 
-	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
-	if (!c)
-		return -ENOMEM;
-
-	c->priv     = priv;
-	c->mdev     = priv->mdev;
-	c->tstamp   = &priv->tstamp;
-	c->ix       = ix;
-	c->cpu      = cpu;
-	c->pdev     = &priv->mdev->pdev->dev;
-	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
-	c->num_tc   = params->num_tc;
-	c->xdp      = !!params->xdp_prog;
-	c->stats    = &priv->channel_stats[ix].ch;
-
-	c->irq_desc = irq_to_desc(irq);
-
-	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
-
-	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
+	err = mlx5e_open_cq(c, icocq_moder, &cparam->async_icosq.cqp, &c->icosq.cq);
 	if (err)
-		goto err_napi_del;
+		goto err_close_async_icosq_cq;
 
 	err = mlx5e_open_tx_cqs(c, params, cparam);
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xdpsq.cq);
+	err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &c->xdpsq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
-	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rq.cqp, &c->rq.cq);
 	if (err)
 		goto err_close_xdp_tx_cqs;
 
-	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
 	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
-				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
+				     &cparam->xdp_sq.cqp, &c->rq_xdpsq.cq) : 0;
 	if (err)
 		goto err_close_rx_cq;
 
 	napi_enable(&c->napi);
 
-	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
+	spin_lock_init(&c->async_icosq_lock);
+
+	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq,
+			       mlx5e_async_icosq_err_cqe_work);
 	if (err)
 		goto err_disable_napi;
+
+	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq,
+			       mlx5e_icosq_err_cqe_work);
+	if (err)
+		goto err_close_async_icosq;
 
 	err = mlx5e_open_sqs(c, params, cparam);
 	if (err)
 		goto err_close_icosq;
 
-	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0;
-	if (err)
-		goto err_close_sqs;
+	if (c->xdp) {
+		err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL,
+				       &c->rq_xdpsq, false);
+		if (err)
+			goto err_close_sqs;
+	}
 
-	err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq);
+	err = mlx5e_open_rq(c, params, &cparam->rq, NULL, NULL, &c->rq);
 	if (err)
 		goto err_close_xdp_sq;
 
-	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true);
+	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true);
 	if (err)
 		goto err_close_rq;
-
-	*cp = c;
 
 	return 0;
 
@@ -2002,7 +1910,7 @@
 
 err_close_xdp_sq:
 	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq);
+		mlx5e_close_xdpsq(&c->rq_xdpsq);
 
 err_close_sqs:
 	mlx5e_close_sqs(c);
@@ -2010,10 +1918,14 @@
 err_close_icosq:
 	mlx5e_close_icosq(&c->icosq);
 
+err_close_async_icosq:
+	mlx5e_close_icosq(&c->async_icosq);
+
 err_disable_napi:
 	napi_disable(&c->napi);
+
 	if (c->xdp)
-		mlx5e_close_cq(&c->rq.xdpsq.cq);
+		mlx5e_close_cq(&c->rq_xdpsq.cq);
 
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
@@ -2027,8 +1939,96 @@
 err_close_icosq_cq:
 	mlx5e_close_cq(&c->icosq.cq);
 
+err_close_async_icosq_cq:
+	mlx5e_close_cq(&c->async_icosq.cq);
+
+	return err;
+}
+
+static void mlx5e_close_queues(struct mlx5e_channel *c)
+{
+	mlx5e_close_xdpsq(&c->xdpsq);
+	mlx5e_close_rq(&c->rq);
+	if (c->xdp)
+		mlx5e_close_xdpsq(&c->rq_xdpsq);
+	mlx5e_close_sqs(c);
+	mlx5e_close_icosq(&c->icosq);
+	mlx5e_close_icosq(&c->async_icosq);
+	napi_disable(&c->napi);
+	if (c->xdp)
+		mlx5e_close_cq(&c->rq_xdpsq.cq);
+	mlx5e_close_cq(&c->rq.cq);
+	mlx5e_close_cq(&c->xdpsq.cq);
+	mlx5e_close_tx_cqs(c);
+	mlx5e_close_cq(&c->icosq.cq);
+	mlx5e_close_cq(&c->async_icosq.cq);
+}
+
+static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix)
+{
+	u16 port_aff_bias = mlx5_core_is_pf(mdev) ? 0 : MLX5_CAP_GEN(mdev, vhca_id);
+
+	return (ix + port_aff_bias) % mlx5e_get_num_lag_ports(mdev);
+}
+
+static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+			      struct mlx5e_params *params,
+			      struct mlx5e_channel_param *cparam,
+			      struct xsk_buff_pool *xsk_pool,
+			      struct mlx5e_channel **cp)
+{
+	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
+	struct net_device *netdev = priv->netdev;
+	struct mlx5e_xsk_param xsk;
+	struct mlx5e_channel *c;
+	unsigned int irq;
+	int err;
+
+	err = mlx5_vector2irqn(priv->mdev, ix, &irq);
+	if (err)
+		return err;
+
+	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	if (!c)
+		return -ENOMEM;
+
+	c->priv     = priv;
+	c->mdev     = priv->mdev;
+	c->tstamp   = &priv->tstamp;
+	c->ix       = ix;
+	c->cpu      = cpu;
+	c->pdev     = mlx5_core_dma_dev(priv->mdev);
+	c->netdev   = priv->netdev;
+	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
+	c->num_tc   = params->num_tc;
+	c->xdp      = !!params->xdp_prog;
+	c->stats    = &priv->channel_stats[ix].ch;
+	c->irq_desc = irq_to_desc(irq);
+	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
+
+	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
+
+	err = mlx5e_open_queues(c, params, cparam);
+	if (unlikely(err))
+		goto err_napi_del;
+
+	if (xsk_pool) {
+		mlx5e_build_xsk_param(xsk_pool, &xsk);
+		err = mlx5e_open_xsk(priv, params, &xsk, xsk_pool, c);
+		if (unlikely(err))
+			goto err_close_queues;
+	}
+
+	*cp = c;
+
+	return 0;
+
+err_close_queues:
+	mlx5e_close_queues(c);
+
 err_napi_del:
 	netif_napi_del(&c->napi);
+
 	kvfree(c);
 
 	return err;
@@ -2040,34 +2040,33 @@
 
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
+	mlx5e_activate_icosq(&c->icosq);
+	mlx5e_activate_icosq(&c->async_icosq);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+
+	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		mlx5e_activate_xsk(c);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 {
 	int tc;
 
+	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		mlx5e_deactivate_xsk(c);
+
 	mlx5e_deactivate_rq(&c->rq);
+	mlx5e_deactivate_icosq(&c->async_icosq);
+	mlx5e_deactivate_icosq(&c->icosq);
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_deactivate_txqsq(&c->sq[tc]);
 }
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
-	mlx5e_close_xdpsq(&c->xdpsq);
-	mlx5e_close_rq(&c->rq);
-	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq);
-	mlx5e_close_sqs(c);
-	mlx5e_close_icosq(&c->icosq);
-	napi_disable(&c->napi);
-	if (c->xdp)
-		mlx5e_close_cq(&c->rq.xdpsq.cq);
-	mlx5e_close_cq(&c->rq.cq);
-	mlx5e_close_cq(&c->xdpsq.cq);
-	mlx5e_close_tx_cqs(c);
-	mlx5e_close_cq(&c->icosq.cq);
+	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		mlx5e_close_xsk(c);
+	mlx5e_close_queues(c);
 	netif_napi_del(&c->napi);
 
 	kvfree(c);
@@ -2077,6 +2076,7 @@
 
 static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 				      struct mlx5e_params *params,
+				      struct mlx5e_xsk_param *xsk,
 				      struct mlx5e_rq_frags_info *info)
 {
 	u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu);
@@ -2089,10 +2089,10 @@
 		byte_count += MLX5E_METADATA_ETHER_LEN;
 #endif
 
-	if (mlx5e_rx_is_linear_skb(mdev, params)) {
+	if (mlx5e_rx_is_linear_skb(params, xsk)) {
 		int frag_stride;
 
-		frag_stride = mlx5e_rx_get_linear_frag_sz(params);
+		frag_stride = mlx5e_rx_get_linear_frag_sz(params, xsk);
 		frag_stride = roundup_pow_of_two(frag_stride);
 
 		info->arr[0].frag_size = byte_count;
@@ -2143,9 +2143,17 @@
 	return order_base_2(sz);
 }
 
-static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
-				 struct mlx5e_params *params,
-				 struct mlx5e_rq_param *param)
+static u8 mlx5e_get_rq_log_wq_sz(void *rqc)
+{
+	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+
+	return MLX5_GET(wq, wq, log_wq_sz);
+}
+
+void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk,
+			  struct mlx5e_rq_param *param)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqc = param->rqc;
@@ -2155,16 +2163,16 @@
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		MLX5_SET(wq, wq, log_wqe_num_of_strides,
-			 mlx5e_mpwqe_get_log_num_strides(mdev, params) -
+			 mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk) -
 			 MLX5_MPWQE_LOG_NUM_STRIDES_BASE);
 		MLX5_SET(wq, wq, log_wqe_stride_size,
-			 mlx5e_mpwqe_get_log_stride_size(mdev, params) -
+			 mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk) -
 			 MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
-		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
+		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params, xsk));
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
-		mlx5e_build_rq_frags_info(mdev, params, &param->frags_info);
+		mlx5e_build_rq_frags_info(mdev, params, xsk, &param->frags_info);
 		ndsegs = param->frags_info.num_frags;
 	}
 
@@ -2177,7 +2185,8 @@
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
+	mlx5e_build_rx_cq_param(priv, params, xsk, &param->cqp);
 }
 
 static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
@@ -2192,11 +2201,11 @@
 		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
 	MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter);
 
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 }
 
-static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
-					struct mlx5e_sq_param *param)
+void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
+				 struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -2204,7 +2213,7 @@
 	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
 	MLX5_SET(wq, wq, pd,            priv->mdev->mlx5e_res.pdn);
 
-	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(priv->mdev));
 }
 
 static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
@@ -2213,10 +2222,15 @@
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+	bool allow_swp;
 
+	allow_swp = mlx5_geneve_tx_allowed(priv->mdev) ||
+		    !!MLX5_IPSEC_DEV(priv->mdev);
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
-	MLX5_SET(sqc, sqc, allow_swp, !!MLX5_IPSEC_DEV(priv->mdev));
+	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
+	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE);
+	mlx5e_build_tx_cq_param(priv, params, &param->cqp);
 }
 
 static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
@@ -2225,20 +2239,25 @@
 	void *cqc = param->cqc;
 
 	MLX5_SET(cqc, cqc, uar_page, priv->mdev->priv.uar->index);
+	if (MLX5_CAP_GEN(priv->mdev, cqe_128_always) && cache_line_size() >= 128)
+		MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
 }
 
-static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_params *params,
-				    struct mlx5e_cq_param *param)
+void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_xsk_param *xsk,
+			     struct mlx5e_cq_param *param)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	bool hw_stridx = false;
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
-			mlx5e_mpwqe_get_log_num_strides(mdev, params);
+		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) +
+			mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
+		hw_stridx = MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		log_cq_size = params->log_rq_mtu_frames;
@@ -2246,7 +2265,8 @@
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
-		MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM);
+		MLX5_SET(cqc, cqc, mini_cqe_res_format, hw_stridx ?
+			 MLX5_CQE_FORMAT_CSUM_STRIDX : MLX5_CQE_FORMAT_CSUM);
 		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
 	}
 
@@ -2254,9 +2274,9 @@
 	param->cq_period_mode = params->rx_cq_moderation.cq_period_mode;
 }
 
-static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_params *params,
-				    struct mlx5e_cq_param *param)
+void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
@@ -2266,9 +2286,9 @@
 	param->cq_period_mode = params->tx_cq_moderation.cq_period_mode;
 }
 
-static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
-				     u8 log_wq_size,
-				     struct mlx5e_cq_param *param)
+void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
+			      u8 log_wq_size,
+			      struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
@@ -2276,12 +2296,12 @@
 
 	mlx5e_build_common_cq_param(priv, param);
 
-	param->cq_period_mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	param->cq_period_mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
-static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
-				    u8 log_wq_size,
-				    struct mlx5e_sq_param *param)
+void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
+			     u8 log_wq_size,
+			     struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -2290,32 +2310,58 @@
 
 	MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
 	MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
+	mlx5e_build_ico_cq_param(priv, log_wq_size, &param->cqp);
 }
 
-static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_params *params,
-				    struct mlx5e_sq_param *param)
+void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
+	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
+	mlx5e_build_tx_cq_param(priv, params, &param->cqp);
+}
+
+static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params,
+				      struct mlx5e_rq_param *rqp)
+{
+	switch (params->rq_wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE,
+			     order_base_2(MLX5E_UMR_WQEBBS) +
+			     mlx5e_get_rq_log_wq_sz(rqp->rqc));
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	}
+}
+
+static u8 mlx5e_build_async_icosq_log_wq_sz(struct net_device *netdev)
+{
+	if (netdev->hw_features & NETIF_F_HW_TLS_RX)
+		return MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+
+	return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 }
 
 static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
 				      struct mlx5e_params *params,
 				      struct mlx5e_channel_param *cparam)
 {
-	u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	u8 icosq_log_wq_sz, async_icosq_log_wq_sz;
 
-	mlx5e_build_rq_param(priv, params, &cparam->rq);
-	mlx5e_build_sq_param(priv, params, &cparam->sq);
+	mlx5e_build_rq_param(priv, params, NULL, &cparam->rq);
+
+	icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(params, &cparam->rq);
+	async_icosq_log_wq_sz = mlx5e_build_async_icosq_log_wq_sz(priv->netdev);
+
+	mlx5e_build_sq_param(priv, params, &cparam->txq_sq);
 	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
 	mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
-	mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq);
-	mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
-	mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq);
+	mlx5e_build_icosq_param(priv, async_icosq_log_wq_sz, &cparam->async_icosq);
 }
 
 int mlx5e_open_channels(struct mlx5e_priv *priv,
@@ -2334,11 +2380,17 @@
 
 	mlx5e_build_channel_param(priv, &chs->params, cparam);
 	for (i = 0; i < chs->num; i++) {
-		err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]);
+		struct xsk_buff_pool *xsk_pool = NULL;
+
+		if (chs->params.xdp_prog)
+			xsk_pool = mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, i);
+
+		err = mlx5e_open_channel(priv, i, &chs->params, cparam, xsk_pool, &chs->c[i]);
 		if (err)
 			goto err_close_channels;
 	}
 
+	mlx5e_health_channels_update(priv);
 	kvfree(cparam);
 	return 0;
 
@@ -2361,14 +2413,22 @@
 		mlx5e_activate_channel(chs->c[i]);
 }
 
+#define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */
+
 static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
 {
 	int err = 0;
 	int i;
 
-	for (i = 0; i < chs->num; i++)
-		err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq,
-						  err ? 0 : 20000);
+	for (i = 0; i < chs->num; i++) {
+		int timeout = err ? 0 : MLX5E_RQ_WQES_TIMEOUT;
+
+		err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq, timeout);
+
+		/* Don't wait on the XSK RQ, because the newer xdpsock sample
+		 * doesn't provide any Fill Ring entries at the setup stage.
+		 */
+	}
 
 	return err ? -ETIMEDOUT : 0;
 }
@@ -2440,35 +2500,33 @@
 	return err;
 }
 
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
-	struct mlx5e_rqt *rqt;
 	int err;
 	int ix;
 
-	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
-		rqt = &priv->direct_tir[ix].rqt;
-		err = mlx5e_create_rqt(priv, 1 /*size */, rqt);
-		if (err)
+	for (ix = 0; ix < priv->max_nch; ix++) {
+		err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt);
+		if (unlikely(err))
 			goto err_destroy_rqts;
 	}
 
 	return 0;
 
 err_destroy_rqts:
-	mlx5_core_warn(priv->mdev, "create direct rqts failed, %d\n", err);
+	mlx5_core_warn(priv->mdev, "create rqts failed, %d\n", err);
 	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
+		mlx5e_destroy_rqt(priv, &tirs[ix].rqt);
 
 	return err;
 }
 
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv)
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
 	int i;
 
-	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	for (i = 0; i < priv->max_nch; i++)
+		mlx5e_destroy_rqt(priv, &tirs[i].rqt);
 }
 
 static int mlx5e_rx_hash_fn(int hfunc)
@@ -2503,7 +2561,7 @@
 			if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
 				ix = mlx5e_bits_invert(i, ilog2(sz));
 
-			ix = priv->channels.params.indirection_rqt[ix];
+			ix = priv->rss_params.indirection_rqt[ix];
 			rqn = rrp.rss.channels->c[ix]->rq.rqn;
 		} else {
 			rqn = rrp.rqn;
@@ -2561,7 +2619,7 @@
 		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
 	}
 
-	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
+	for (ix = 0; ix < priv->max_nch; ix++) {
 		struct mlx5e_redirect_rqt_param direct_rrp = {
 			.is_rss = false,
 			{
@@ -2586,7 +2644,7 @@
 		{
 			.rss = {
 				.channels  = chs,
-				.hfunc     = chs->params.rss_hfunc,
+				.hfunc     = priv->rss_params.hfunc,
 			}
 		},
 	};
@@ -2606,6 +2664,54 @@
 	mlx5e_redirect_rqts(priv, drop_rrp);
 }
 
+static const struct mlx5e_tirc_config tirc_default_config[MLX5E_NUM_INDIR_TIRS] = {
+	[MLX5E_TT_IPV4_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV6_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV4_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV6_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV4_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				     .l4_prot_type = 0,
+				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV6_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				     .l4_prot_type = 0,
+				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV4_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				      .l4_prot_type = 0,
+				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV6_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				      .l4_prot_type = 0,
+				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV4] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+			    .l4_prot_type = 0,
+			    .rx_hash_fields = MLX5_HASH_IP,
+	},
+	[MLX5E_TT_IPV6] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+			    .l4_prot_type = 0,
+			    .rx_hash_fields = MLX5_HASH_IP,
+	},
+};
+
+struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt)
+{
+	return tirc_default_config[tt];
+}
+
 static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 {
 	if (!params->lro_en)
@@ -2617,120 +2723,72 @@
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
-		 (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
-				    enum mlx5e_traffic_types tt,
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
+				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner)
 {
 	void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) :
 			     MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
-#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP)
-
-#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
-				 MLX5_HASH_FIELD_SEL_L4_DPORT)
-
-#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
-
-	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
-	if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
+	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(rss_params->hfunc));
+	if (rss_params->hfunc == ETH_RSS_HASH_TOP) {
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
 					     rx_hash_toeplitz_key);
 		size_t len = MLX5_FLD_SZ_BYTES(tirc,
 					       rx_hash_toeplitz_key);
 
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-		memcpy(rss_key, params->toeplitz_hash_key, len);
+		memcpy(rss_key, rss_params->toeplitz_hash_key, len);
+	}
+	MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+		 ttconfig->l3_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+		 ttconfig->l4_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+		 ttconfig->rx_hash_fields);
+}
+
+static void mlx5e_update_rx_hash_fields(struct mlx5e_tirc_config *ttconfig,
+					enum mlx5e_traffic_types tt,
+					u32 rx_hash_fields)
+{
+	*ttconfig                = tirc_default_config[tt];
+	ttconfig->rx_hash_fields = rx_hash_fields;
+}
+
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in)
+{
+	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+	struct mlx5e_tirc_config ttconfig;
+	int tt;
+
+	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_update_rx_hash_fields(&ttconfig, tt,
+					    rss->rx_hash_fields[tt]);
+		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, false);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in);
 	}
 
-	switch (tt) {
-	case MLX5E_TT_IPV4_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
+		return;
 
-	case MLX5E_TT_IPV6_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-
-	case MLX5E_TT_IPV6:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-	default:
-		WARN_ONCE(true, "%s: bad traffic type!\n", __func__);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_update_rx_hash_fields(&ttconfig, tt,
+					    rss->rx_hash_fields[tt]);
+		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, true);
+		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in);
 	}
 }
 
@@ -2756,15 +2814,21 @@
 	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in,
-					   inlen);
+		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in);
+		if (err)
+			goto free_in;
+
+		/* Verify inner tirs resources allocated */
+		if (!priv->inner_indir_tir[0].tirn)
+			continue;
+
+		err = mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in);
 		if (err)
 			goto free_in;
 	}
 
-	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
-		err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn,
-					   in, inlen);
+	for (ix = 0; ix < priv->max_nch; ix++) {
+		err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn, in);
 		if (err)
 			goto free_in;
 	}
@@ -2775,20 +2839,7 @@
 	return err;
 }
 
-static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
-					    enum mlx5e_traffic_types tt,
-					    u32 *tirc)
-{
-	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
-
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
-
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1);
-
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
-}
+static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro);
 
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params, u16 mtu)
@@ -2818,7 +2869,7 @@
 	*mtu = MLX5E_HW2SW_MTU(params, hw_mtu);
 }
 
-static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
+int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 {
 	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
@@ -2839,11 +2890,25 @@
 	return 0;
 }
 
-static void mlx5e_netdev_set_tcs(struct net_device *netdev)
+MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_set_dev_port_mtu);
+
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int nch = priv->channels.params.num_channels;
-	int ntc = priv->channels.params.num_tc;
+	struct mlx5e_params *params = &priv->channels.params;
+	struct net_device *netdev   = priv->netdev;
+	struct mlx5_core_dev *mdev  = priv->mdev;
+	u16 max_mtu;
+
+	/* MTU range: 68 - hw-specific max */
+	netdev->min_mtu = ETH_MIN_MTU;
+
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->max_mtu = min_t(unsigned int, MLX5E_HW2SW_MTU(params, max_mtu),
+				ETH_MAX_MTU);
+}
+
+static void mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc)
+{
 	int tc;
 
 	netdev_reset_tc(netdev);
@@ -2860,57 +2925,132 @@
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
-static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv)
+static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 {
-	int max_nch = priv->profile->max_nch(priv->mdev);
-	int i, tc;
+	struct net_device *netdev = priv->netdev;
+	int num_txqs, num_rxqs, nch, ntc;
+	int old_num_txqs, old_ntc;
+	int err;
 
-	for (i = 0; i < max_nch; i++)
-		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			priv->channel_tc2txq[i][tc] = i + tc * max_nch;
+	old_num_txqs = netdev->real_num_tx_queues;
+	old_ntc = netdev->num_tc ? : 1;
+
+	nch = priv->channels.params.num_channels;
+	ntc = priv->channels.params.num_tc;
+	num_txqs = nch * ntc;
+	num_rxqs = nch * priv->profile->rq_groups;
+
+	mlx5e_netdev_set_tcs(netdev, nch, ntc);
+
+	err = netif_set_real_num_tx_queues(netdev, num_txqs);
+	if (err) {
+		netdev_warn(netdev, "netif_set_real_num_tx_queues failed, %d\n", err);
+		goto err_tcs;
+	}
+	err = netif_set_real_num_rx_queues(netdev, num_rxqs);
+	if (err) {
+		netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err);
+		goto err_txqs;
+	}
+
+	return 0;
+
+err_txqs:
+	/* netif_set_real_num_rx_queues could fail only when nch increased. Only
+	 * one of nch and ntc is changed in this function. That means, the call
+	 * to netif_set_real_num_tx_queues below should not fail, because it
+	 * decreases the number of TX queues.
+	 */
+	WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs));
+
+err_tcs:
+	mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc);
+	return err;
 }
 
-static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
+static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
+					   struct mlx5e_params *params)
 {
-	struct mlx5e_channel *c;
-	struct mlx5e_txqsq *sq;
-	int i, tc;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int num_comp_vectors, ix, irq;
 
-	for (i = 0; i < priv->channels.num; i++) {
-		c = priv->channels.c[i];
-		for (tc = 0; tc < c->num_tc; tc++) {
-			sq = &c->sq[tc];
+	num_comp_vectors = mlx5_comp_vectors_count(mdev);
+
+	for (ix = 0; ix < params->num_channels; ix++) {
+		cpumask_clear(priv->scratchpad.cpumask);
+
+		for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
+			int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(mdev, irq));
+
+			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
+		}
+
+		netif_set_xps_queue(priv->netdev, priv->scratchpad.cpumask, ix);
+	}
+}
+
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
+{
+	u16 count = priv->channels.params.num_channels;
+	int err;
+
+	err = mlx5e_update_netdev_queues(priv);
+	if (err)
+		return err;
+
+	mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params);
+
+	if (!netif_is_rxfh_configured(priv->netdev))
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, count);
+
+	return 0;
+}
+
+MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_num_channels_changed);
+
+static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
+{
+	int i, ch;
+
+	ch = priv->channels.num;
+
+	for (i = 0; i < ch; i++) {
+		int tc;
+
+		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+			struct mlx5e_channel *c = priv->channels.c[i];
+			struct mlx5e_txqsq *sq = &c->sq[tc];
+
 			priv->txq2sq[sq->txq_ix] = sq;
+			priv->channel_tc2realtxq[i][tc] = i + tc * ch;
 		}
 	}
 }
 
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 {
-	int num_txqs = priv->channels.num * priv->channels.params.num_tc;
-	struct net_device *netdev = priv->netdev;
-
-	mlx5e_netdev_set_tcs(netdev);
-	netif_set_real_num_tx_queues(netdev, num_txqs);
-	netif_set_real_num_rx_queues(netdev, priv->channels.num);
-
-	mlx5e_build_tx2sq_maps(priv);
+	mlx5e_build_txq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
 	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (mlx5e_is_vport_rep(priv))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
 	mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
+
+	mlx5e_xsk_redirect_rqts_to_channels(priv, &priv->channels);
 }
 
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
+	mlx5e_xsk_redirect_rqts_to_drop(priv, &priv->channels);
+
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (mlx5e_is_vport_rep(priv))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -2922,42 +3062,102 @@
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
-void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
-				struct mlx5e_channels *new_chs,
-				mlx5e_fp_hw_modify hw_modify)
+static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				      struct mlx5e_channels *new_chs,
+				      mlx5e_fp_preactivate preactivate,
+				      void *context)
 {
 	struct net_device *netdev = priv->netdev;
-	int new_num_txqs;
+	struct mlx5e_channels old_chs;
 	int carrier_ok;
-	new_num_txqs = new_chs->num * new_chs->params.num_tc;
+	int err = 0;
 
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
-	if (new_num_txqs < netdev->real_num_tx_queues)
-		netif_set_real_num_tx_queues(netdev, new_num_txqs);
-
 	mlx5e_deactivate_priv_channels(priv);
-	mlx5e_close_channels(&priv->channels);
 
+	old_chs = priv->channels;
 	priv->channels = *new_chs;
 
-	/* New channels are ready to roll, modify HW settings if needed */
-	if (hw_modify)
-		hw_modify(priv);
+	/* New channels are ready to roll, call the preactivate hook if needed
+	 * to modify HW settings or update kernel parameters.
+	 */
+	if (preactivate) {
+		err = preactivate(priv, context);
+		if (err) {
+			priv->channels = old_chs;
+			goto out;
+		}
+	}
 
-	mlx5e_refresh_tirs(priv, false);
+	mlx5e_close_channels(&old_chs);
+	priv->profile->update_rx(priv);
+
+out:
 	mlx5e_activate_priv_channels(priv);
 
 	/* return carrier back if needed */
 	if (carrier_ok)
 		netif_carrier_on(netdev);
+
+	return err;
+}
+
+int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
+			       struct mlx5e_channels *new_chs,
+			       mlx5e_fp_preactivate preactivate,
+			       void *context)
+{
+	int err;
+
+	err = mlx5e_open_channels(priv, new_chs);
+	if (err)
+		return err;
+
+	err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context);
+	if (err)
+		goto err_close;
+
+	return 0;
+
+err_close:
+	mlx5e_close_channels(new_chs);
+
+	return err;
+}
+
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channels new_channels = {};
+
+	new_channels.params = priv->channels.params;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL);
 }
 
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
 	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
 	priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE;
+}
+
+static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
+				     enum mlx5_port_status state)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int vport_admin_state;
+
+	mlx5_set_port_admin_status(mdev, state);
+
+	if (!MLX5_ESWITCH_MANAGER(mdev) ||  mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS)
+		return;
+
+	if (state == MLX5_PORT_UP)
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	else
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
+	mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state);
 }
 
 int mlx5e_open_locked(struct net_device *netdev)
@@ -2971,14 +3171,12 @@
 	if (err)
 		goto err_clear_state_opened_flag;
 
-	mlx5e_refresh_tirs(priv, false);
+	priv->profile->update_rx(priv);
 	mlx5e_activate_priv_channels(priv);
 	if (priv->profile->update_carrier)
 		priv->profile->update_carrier(priv);
 
-	if (priv->profile->update_stats)
-		queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
-
+	mlx5e_queue_update_stats(priv);
 	return 0;
 
 err_clear_state_opened_flag:
@@ -2994,11 +3192,8 @@
 	mutex_lock(&priv->state_lock);
 	err = mlx5e_open_locked(netdev);
 	if (!err)
-		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
+		mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
-
-	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
-		udp_tunnel_get_rx_info(netdev);
 
 	return err;
 }
@@ -3031,7 +3226,7 @@
 		return -ENODEV;
 
 	mutex_lock(&priv->state_lock);
-	mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN);
+	mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN);
 	err = mlx5e_close_locked(netdev);
 	mutex_unlock(&priv->state_lock);
 
@@ -3065,14 +3260,14 @@
 			       struct mlx5e_cq *cq,
 			       struct mlx5e_cq_param *param)
 {
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
-	param->wq.db_numa_node  = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
+	param->wq.db_numa_node  = dev_to_node(mlx5_core_dma_dev(mdev));
 
 	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
 
-static int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
-			      struct mlx5e_rq *drop_rq)
+int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
+		       struct mlx5e_rq *drop_rq)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_cq_param cq_param = {};
@@ -3116,7 +3311,7 @@
 	return err;
 }
 
-static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
+void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
 {
 	mlx5e_destroy_rq(drop_rq);
 	mlx5e_free_rq(drop_rq);
@@ -3124,20 +3319,19 @@
 	mlx5e_free_cq(&drop_rq->cq);
 }
 
-int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
-		     u32 underlay_qpn, u32 *tisn)
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
 {
-	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0};
 	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
 
-	MLX5_SET(tisc, tisc, prio, tc << 1);
-	MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn);
 	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn);
+
+	if (MLX5_GET(tisc, tisc, tls_en))
+		MLX5_SET(tisc, tisc, pd, mdev->mlx5e_res.pdn);
 
 	if (mlx5_lag_is_lacp_owner(mdev))
 		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
 
-	return mlx5_core_create_tis(mdev, in, sizeof(in), tisn);
+	return mlx5_core_create_tis(mdev, in, tisn);
 }
 
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
@@ -3145,59 +3339,97 @@
 	mlx5_core_destroy_tis(mdev, tisn);
 }
 
+void mlx5e_destroy_tises(struct mlx5e_priv *priv)
+{
+	int tc, i;
+
+	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++)
+		for (tc = 0; tc < priv->profile->max_tc; tc++)
+			mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]);
+}
+
+static bool mlx5e_lag_should_assign_affinity(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1;
+}
+
 int mlx5e_create_tises(struct mlx5e_priv *priv)
 {
+	int tc, i;
 	int err;
-	int tc;
 
-	for (tc = 0; tc < priv->profile->max_tc; tc++) {
-		err = mlx5e_create_tis(priv->mdev, tc, 0, &priv->tisn[tc]);
-		if (err)
-			goto err_close_tises;
+	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) {
+		for (tc = 0; tc < priv->profile->max_tc; tc++) {
+			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+			void *tisc;
+
+			tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+			MLX5_SET(tisc, tisc, prio, tc << 1);
+
+			if (mlx5e_lag_should_assign_affinity(priv->mdev))
+				MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1);
+
+			err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[i][tc]);
+			if (err)
+				goto err_close_tises;
+		}
 	}
 
 	return 0;
 
 err_close_tises:
-	for (tc--; tc >= 0; tc--)
-		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
+	for (; i >= 0; i--) {
+		for (tc--; tc >= 0; tc--)
+			mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]);
+		tc = priv->profile->max_tc;
+	}
 
 	return err;
 }
 
-void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
+static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
-	int tc;
+	mlx5e_destroy_tises(priv);
+}
 
-	for (tc = 0; tc < priv->profile->max_tc; tc++)
-		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
+static void mlx5e_build_indir_tir_ctx_common(struct mlx5e_priv *priv,
+					     u32 rqtn, u32 *tirc)
+{
+	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
+	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
+	MLX5_SET(tirc, tirc, indirect_table, rqtn);
+	MLX5_SET(tirc, tirc, tunneled_offload_en,
+		 priv->channels.params.tunneled_offload_en);
+
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 }
 
 static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
 				      enum mlx5e_traffic_types tt,
 				      u32 *tirc)
 {
-	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
-
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
-
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
+	mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc);
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
+				       &tirc_default_config[tt], tirc, false);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
 {
-	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
-
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
-
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, rqtn);
+	mlx5e_build_indir_tir_ctx_common(priv, rqtn, tirc);
 	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
 }
 
-int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
+static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
+					    enum mlx5e_traffic_types tt,
+					    u32 *tirc)
+{
+	mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc);
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
+				       &tirc_default_config[tt], tirc, true);
+}
+
+int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
 {
 	struct mlx5e_tir *tir;
 	void *tirc;
@@ -3217,14 +3449,14 @@
 		tir = &priv->indir_tir[tt];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_indir_tir_ctx(priv, tt, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
+		err = mlx5e_create_tir(priv->mdev, tir, in);
 		if (err) {
 			mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err);
 			goto err_destroy_inner_tirs;
 		}
 	}
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
 		goto out;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) {
@@ -3232,7 +3464,7 @@
 		tir = &priv->inner_indir_tir[i];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_inner_indir_tir_ctx(priv, i, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
+		err = mlx5e_create_tir(priv->mdev, tir, in);
 		if (err) {
 			mlx5_core_warn(priv->mdev, "create inner indirect tirs failed, %d\n", err);
 			goto err_destroy_inner_tirs;
@@ -3256,13 +3488,12 @@
 	return err;
 }
 
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
-	int nch = priv->profile->max_nch(priv->mdev);
 	struct mlx5e_tir *tir;
 	void *tirc;
 	int inlen;
-	int err;
+	int err = 0;
 	u32 *in;
 	int ix;
 
@@ -3271,25 +3502,24 @@
 	if (!in)
 		return -ENOMEM;
 
-	for (ix = 0; ix < nch; ix++) {
+	for (ix = 0; ix < priv->max_nch; ix++) {
 		memset(in, 0, inlen);
-		tir = &priv->direct_tir[ix];
+		tir = &tirs[ix];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
-		if (err)
+		mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc);
+		err = mlx5e_create_tir(priv->mdev, tir, in);
+		if (unlikely(err))
 			goto err_destroy_ch_tirs;
 	}
 
-	kvfree(in);
-
-	return 0;
+	goto out;
 
 err_destroy_ch_tirs:
-	mlx5_core_warn(priv->mdev, "create direct tirs failed, %d\n", err);
+	mlx5_core_warn(priv->mdev, "create tirs failed, %d\n", err);
 	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]);
+		mlx5e_destroy_tir(priv->mdev, &tirs[ix]);
 
+out:
 	kvfree(in);
 
 	return err;
@@ -3302,20 +3532,20 @@
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
 }
 
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
-	int nch = priv->profile->max_nch(priv->mdev);
 	int i;
 
-	for (i = 0; i < nch; i++)
-		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
+	for (i = 0; i < priv->max_nch; i++)
+		mlx5e_destroy_tir(priv->mdev, &tirs[i]);
 }
 
 static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
@@ -3346,10 +3576,9 @@
 	return 0;
 }
 
-static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
+static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 				 struct tc_mqprio_qopt *mqprio)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
 	u8 tc = mqprio->num_tc;
 	int err = 0;
@@ -3365,115 +3594,105 @@
 	new_channels.params.num_tc = tc ? tc : 1;
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		struct mlx5e_params old_params;
+
+		old_params = priv->channels.params;
 		priv->channels.params = new_channels.params;
+		err = mlx5e_num_channels_changed(priv);
+		if (err)
+			priv->channels.params = old_params;
+
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
+	err = mlx5e_safe_switch_channels(priv, &new_channels,
+					 mlx5e_num_channels_changed_ctx, NULL);
 
-	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
-				    new_channels.params.num_tc);
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 out:
+	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
+				    priv->channels.params.num_tc);
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
-#ifdef CONFIG_MLX5_ESWITCH
-static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
-				     struct tc_cls_flower_offload *cls_flower,
-				     int flags)
-{
-	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower, flags);
-	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower, flags);
-	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower, flags);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-				   void *cb_priv)
-{
-	struct mlx5e_priv *priv = cb_priv;
-
-	if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data))
-		return -EOPNOTSUPP;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_setup_tc_block(struct net_device *dev,
-				struct tc_block_offload *f)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
-					     priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
-					priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-#endif
+static LIST_HEAD(mlx5e_block_cb_list);
 
 static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			  void *type_data)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
 	switch (type) {
-#ifdef CONFIG_MLX5_ESWITCH
-	case TC_SETUP_BLOCK:
-		return mlx5e_setup_tc_block(dev, type_data);
-#endif
+	case TC_SETUP_BLOCK: {
+		struct flow_block_offload *f = type_data;
+
+		f->unlocked_driver_cb = true;
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_block_cb_list,
+						  mlx5e_setup_tc_block_cb,
+						  priv, priv, true);
+	}
 	case TC_SETUP_QDISC_MQPRIO:
-		return mlx5e_setup_tc_mqprio(dev, type_data);
+		return mlx5e_setup_tc_mqprio(priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-static void
+void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
+{
+	int i;
+
+	for (i = 0; i < priv->max_nch; i++) {
+		struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
+		struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
+		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
+		int j;
+
+		s->rx_packets   += rq_stats->packets + xskrq_stats->packets;
+		s->rx_bytes     += rq_stats->bytes + xskrq_stats->bytes;
+		s->multicast    += rq_stats->mcast_packets + xskrq_stats->mcast_packets;
+
+		for (j = 0; j < priv->max_opened_tc; j++) {
+			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
+
+			s->tx_packets    += sq_stats->packets;
+			s->tx_bytes      += sq_stats->bytes;
+			s->tx_dropped    += sq_stats->dropped;
+		}
+	}
+}
+
+void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sw_stats *sstats = &priv->stats.sw;
-	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
-	/* update HW stats in background for next time */
-	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+	/* In switchdev mode, monitor counters doesn't monitor
+	 * rx/tx stats of 802_3. The update stats mechanism
+	 * should keep the 802_3 layout counters updated
+	 */
+	if (!mlx5e_monitor_counter_supported(priv) ||
+	    mlx5e_is_uplink_rep(priv)) {
+		/* update HW stats in background for next time */
+		mlx5e_queue_update_stats(priv);
+	}
 
 	if (mlx5e_is_uplink_rep(priv)) {
+		struct mlx5e_vport_stats *vstats = &priv->stats.vport;
+
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
 		stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
 		stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
 		stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
+
+		/* vport multicast also counts packets that are dropped due to steering
+		 * or rx out of buffer
+		 */
+		stats->multicast = VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
 	} else {
-		mlx5e_grp_sw_update_stats(priv);
-		stats->rx_packets = sstats->rx_packets;
-		stats->rx_bytes   = sstats->rx_bytes;
-		stats->tx_packets = sstats->tx_packets;
-		stats->tx_bytes   = sstats->tx_bytes;
-		stats->tx_dropped = sstats->tx_queue_dropped;
+		mlx5e_fold_sw_stats64(priv, stats);
 	}
 
 	stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;
@@ -3489,12 +3708,6 @@
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
-
-	/* vport multicast also counts packets that are dropped due to steering
-	 * or rx out of buffer
-	 */
-	stats->multicast =
-		VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
 }
 
 static void mlx5e_set_rx_mode(struct net_device *dev)
@@ -3536,14 +3749,21 @@
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channels new_channels = {};
-	struct mlx5e_params *old_params;
+	struct mlx5e_params *cur_params;
 	int err = 0;
 	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	old_params = &priv->channels.params;
-	if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
+	if (enable && priv->xsk.refcnt) {
+		netdev_warn(netdev, "LRO is incompatible with AF_XDP (%hu XSKs are active)\n",
+			    priv->xsk.refcnt);
+		err = -EINVAL;
+		goto out;
+	}
+
+	cur_params = &priv->channels.params;
+	if (enable && !MLX5E_GET_PFLAG(cur_params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
 		netdev_warn(netdev, "can't set LRO with legacy RQ\n");
 		err = -EINVAL;
 		goto out;
@@ -3551,26 +3771,28 @@
 
 	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	new_channels.params = *old_params;
+	new_channels.params = *cur_params;
 	new_channels.params.lro_en = enable;
 
-	if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) {
-		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) ==
-		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params))
+	if (cur_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) {
+		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) ==
+		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params, NULL))
 			reset = false;
 	}
 
 	if (!reset) {
-		*old_params = new_channels.params;
+		struct mlx5e_params old_params;
+
+		old_params = *cur_params;
+		*cur_params = new_channels.params;
 		err = mlx5e_modify_tirs_lro(priv);
+		if (err)
+			*cur_params = old_params;
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+	err = mlx5e_safe_switch_channels(priv, &new_channels,
+					 mlx5e_modify_tirs_lro_ctx, NULL);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3588,12 +3810,12 @@
 	return 0;
 }
 
-#ifdef CONFIG_MLX5_ESWITCH
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	if (!enable && mlx5e_tc_num_filters(priv)) {
+	if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -3611,20 +3833,67 @@
 	return mlx5_set_port_fcs(mdev, !enable);
 }
 
+static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable)
+{
+	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {};
+	bool supported, curr_state;
+	int err;
+
+	if (!MLX5_CAP_GEN(mdev, ports_check))
+		return 0;
+
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
+
+	supported = MLX5_GET(pcmr_reg, in, rx_ts_over_crc_cap);
+	curr_state = MLX5_GET(pcmr_reg, in, rx_ts_over_crc);
+
+	if (!supported || enable == curr_state)
+		return 0;
+
+	MLX5_SET(pcmr_reg, in, local_port, 1);
+	MLX5_SET(pcmr_reg, in, rx_ts_over_crc, enable);
+
+	return mlx5_set_ports_check(mdev, in, sizeof(in));
+}
+
 static int set_feature_rx_fcs(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_channels *chs = &priv->channels;
+	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
 	mutex_lock(&priv->state_lock);
 
-	priv->channels.params.scatter_fcs_en = enable;
-	err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable);
-	if (err)
-		priv->channels.params.scatter_fcs_en = !enable;
+	if (enable) {
+		err = mlx5e_set_rx_port_ts(mdev, false);
+		if (err)
+			goto out;
 
+		chs->params.scatter_fcs_en = true;
+		err = mlx5e_modify_channels_scatter_fcs(chs, true);
+		if (err) {
+			chs->params.scatter_fcs_en = false;
+			mlx5e_set_rx_port_ts(mdev, true);
+		}
+	} else {
+		chs->params.scatter_fcs_en = false;
+		err = mlx5e_modify_channels_scatter_fcs(chs, false);
+		if (err) {
+			chs->params.scatter_fcs_en = true;
+			goto out;
+		}
+		err = mlx5e_set_rx_port_ts(mdev, true);
+		if (err) {
+			mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err);
+			err = 0;
+		}
+	}
+
+out:
 	mutex_unlock(&priv->state_lock);
-
 	return err;
 }
 
@@ -3687,8 +3956,7 @@
 	return 0;
 }
 
-static int mlx5e_set_features(struct net_device *netdev,
-			      netdev_features_t features)
+int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	netdev_features_t oper_features = features;
 	int err = 0;
@@ -3699,7 +3967,7 @@
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER,
 				    set_feature_cvlan_filter);
-#ifdef CONFIG_MLX5_ESWITCH
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TC, set_feature_tc_num_filters);
 #endif
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
@@ -3708,6 +3976,7 @@
 #ifdef CONFIG_MLX5_EN_ARFS
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_NTUPLE, set_feature_arfs);
 #endif
+	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TLS_RX, mlx5e_ktls_set_feature_rx);
 
 	if (err) {
 		netdev->features = oper_features;
@@ -3734,9 +4003,17 @@
 			netdev_warn(netdev, "Dropping C-tag vlan stripping offload due to S-tag vlan\n");
 	}
 	if (!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
-		features &= ~NETIF_F_LRO;
-		if (params->lro_en)
+		if (features & NETIF_F_LRO) {
 			netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n");
+			features &= ~NETIF_F_LRO;
+		}
+	}
+
+	if (params->xdp_prog) {
+		if (features & NETIF_F_LRO) {
+			netdev_warn(netdev, "LRO is incompatible with XDP\n");
+			features &= ~NETIF_F_LRO;
+		}
 	}
 
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
@@ -3750,8 +4027,46 @@
 	return features;
 }
 
+static bool mlx5e_xsk_validate_mtu(struct net_device *netdev,
+				   struct mlx5e_channels *chs,
+				   struct mlx5e_params *new_params,
+				   struct mlx5_core_dev *mdev)
+{
+	u16 ix;
+
+	for (ix = 0; ix < chs->params.num_channels; ix++) {
+		struct xsk_buff_pool *xsk_pool =
+			mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, ix);
+		struct mlx5e_xsk_param xsk;
+
+		if (!xsk_pool)
+			continue;
+
+		mlx5e_build_xsk_param(xsk_pool, &xsk);
+
+		if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) {
+			u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk);
+			int max_mtu_frame, max_mtu_page, max_mtu;
+
+			/* Two criteria must be met:
+			 * 1. HW MTU + all headrooms <= XSK frame size.
+			 * 2. Size of SKBs allocated on XDP_PASS <= PAGE_SIZE.
+			 */
+			max_mtu_frame = MLX5E_HW2SW_MTU(new_params, xsk.chunk_size - hr);
+			max_mtu_page = mlx5e_xdp_max_mtu(new_params, &xsk);
+			max_mtu = min(max_mtu_frame, max_mtu_page);
+
+			netdev_err(netdev, "MTU %d is too big for an XSK running on channel %hu. Try MTU <= %d\n",
+				   new_params->sw_mtu, ix, max_mtu);
+			return false;
+		}
+	}
+
+	return true;
+}
+
 int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
-		     change_hw_mtu_cb set_mtu_cb)
+		     mlx5e_fp_preactivate preactivate)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
@@ -3770,34 +4085,53 @@
 	new_channels.params.sw_mtu = new_mtu;
 
 	if (params->xdp_prog &&
-	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+	    !mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
-			   new_mtu, mlx5e_xdp_max_mtu(params));
+			   new_mtu, mlx5e_xdp_max_mtu(params, NULL));
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (priv->xsk.refcnt &&
+	    !mlx5e_xsk_validate_mtu(netdev, &priv->channels,
+				    &new_channels.params, priv->mdev)) {
 		err = -EINVAL;
 		goto out;
 	}
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params);
-		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
-		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
+		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev,
+							      &new_channels.params,
+							      NULL);
+		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params, NULL);
+		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params, NULL);
 
+		/* If XSK is active, XSK RQs are linear. */
+		is_linear |= priv->xsk.refcnt;
+
+		/* Always reset in linear mode - hw_mtu is used in data path. */
 		reset = reset && (is_linear || (ppw_old != ppw_new));
 	}
 
 	if (!reset) {
+		unsigned int old_mtu = params->sw_mtu;
+
 		params->sw_mtu = new_mtu;
-		if (set_mtu_cb)
-			set_mtu_cb(priv);
+		if (preactivate) {
+			err = preactivate(priv, NULL);
+			if (err) {
+				params->sw_mtu = old_mtu;
+				goto out;
+			}
+		}
 		netdev->mtu = params->sw_mtu;
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, preactivate, NULL);
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
@@ -3807,7 +4141,7 @@
 
 static int mlx5e_change_nic_mtu(struct net_device *netdev, int new_mtu)
 {
-	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
+	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu_ctx);
 }
 
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
@@ -3854,7 +4188,8 @@
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
 		/* Disable CQE compression */
-		netdev_warn(priv->netdev, "Disabling cqe compression");
+		if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS))
+			netdev_warn(priv->netdev, "Disabling RX cqe compression\n");
 		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
 		if (err) {
 			netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err);
@@ -3903,7 +4238,7 @@
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
-static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
+int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3940,8 +4275,8 @@
 	return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
 }
 
-static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
-			     int max_tx_rate)
+int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+		      int max_tx_rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3982,8 +4317,8 @@
 					    mlx5_ifla_link2vport(link_state));
 }
 
-static int mlx5e_get_vf_config(struct net_device *dev,
-			       int vf, struct ifla_vf_info *ivi)
+int mlx5e_get_vf_config(struct net_device *dev,
+			int vf, struct ifla_vf_info *ivi)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3996,8 +4331,8 @@
 	return 0;
 }
 
-static int mlx5e_get_vf_stats(struct net_device *dev,
-			      int vf, struct ifla_vf_stats *vf_stats)
+int mlx5e_get_vf_stats(struct net_device *dev,
+		       int vf, struct ifla_vf_stats *vf_stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -4007,83 +4342,19 @@
 }
 #endif
 
-struct mlx5e_vxlan_work {
-	struct work_struct	work;
-	struct mlx5e_priv	*priv;
-	u16			port;
-};
-
-static void mlx5e_vxlan_add_work(struct work_struct *work)
+static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev,
+							   struct sk_buff *skb)
 {
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
-	u16 port = vxlan_work->port;
-
-	mutex_lock(&priv->state_lock);
-	mlx5_vxlan_add_port(priv->mdev->vxlan, port);
-	mutex_unlock(&priv->state_lock);
-
-	kfree(vxlan_work);
-}
-
-static void mlx5e_vxlan_del_work(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv         = vxlan_work->priv;
-	u16 port = vxlan_work->port;
-
-	mutex_lock(&priv->state_lock);
-	mlx5_vxlan_del_port(priv->mdev->vxlan, port);
-	mutex_unlock(&priv->state_lock);
-	kfree(vxlan_work);
-}
-
-static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
-{
-	struct mlx5e_vxlan_work *vxlan_work;
-
-	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
-	if (!vxlan_work)
-		return;
-
-	if (add)
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work);
-	else
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work);
-
-	vxlan_work->priv = priv;
-	vxlan_work->port = port;
-	queue_work(priv->wq, &vxlan_work->work);
-}
-
-static void mlx5e_add_vxlan_port(struct net_device *netdev,
-				 struct udp_tunnel_info *ti)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-
-	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
-		return;
-
-	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
-		return;
-
-	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
-}
-
-static void mlx5e_del_vxlan_port(struct net_device *netdev,
-				 struct udp_tunnel_info *ti)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-
-	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
-		return;
-
-	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
-		return;
-
-	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
+	switch (skb->inner_protocol) {
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+	case htons(ETH_P_TEB):
+		return true;
+	case htons(ETH_P_MPLS_UC):
+	case htons(ETH_P_MPLS_MC):
+		return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre);
+	}
+	return false;
 }
 
 static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
@@ -4108,7 +4379,14 @@
 
 	switch (proto) {
 	case IPPROTO_GRE:
-		return features;
+		if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb))
+			return features;
+		break;
+	case IPPROTO_IPIP:
+	case IPPROTO_IPV6:
+		if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP))
+			return features;
+		break;
 	case IPPROTO_UDP:
 		udph = udp_hdr(skb);
 		port = be16_to_cpu(udph->dest);
@@ -4116,6 +4394,12 @@
 		/* Verify if UDP port is being offloaded by HW */
 		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
 			return features;
+
+#if IS_ENABLED(CONFIG_GENEVE)
+		/* Support Geneve offload for default UDP port */
+		if (port == GENEVE_UDP_PORT && mlx5_geneve_tx_allowed(priv->mdev))
+			return features;
+#endif
 	}
 
 out:
@@ -4123,9 +4407,9 @@
 	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
-static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
-					      struct net_device *netdev,
-					      netdev_features_t features)
+netdev_features_t mlx5e_features_check(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       netdev_features_t features)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -4145,31 +4429,11 @@
 	return features;
 }
 
-static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
-					struct mlx5e_txqsq *sq)
-{
-	struct mlx5_eq *eq = sq->cq.mcq.eq;
-	u32 eqe_count;
-
-	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->eqn, eq->cons_index, eq->irqn);
-
-	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	if (!eqe_count)
-		return false;
-
-	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
-	sq->channel->stats->eq_rearm++;
-	return true;
-}
-
 static void mlx5e_tx_timeout_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       tx_timeout_work);
-	struct net_device *dev = priv->netdev;
-	bool reopen_channels = false;
-	int i, err;
+	int i;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
@@ -4178,42 +4442,24 @@
 		goto unlock;
 
 	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
-		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
+		struct netdev_queue *dev_queue =
+			netdev_get_tx_queue(priv->netdev, i);
 		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
 
-		netdev_err(dev,
-			   "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
-			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
-			   jiffies_to_usecs(jiffies - dev_queue->trans_start));
-
-		/* If we recover a lost interrupt, most likely TX timeout will
-		 * be resolved, skip reopening channels
-		 */
-		if (!mlx5e_tx_timeout_eq_recover(dev, sq)) {
-			clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-			reopen_channels = true;
-		}
+		if (mlx5e_reporter_tx_timeout(sq))
+		/* break if tried to reopened channels */
+			break;
 	}
-
-	if (!reopen_channels)
-		goto unlock;
-
-	mlx5e_close_locked(dev);
-	err = mlx5e_open_locked(dev);
-	if (err)
-		netdev_err(priv->netdev,
-			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
-			   err);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 }
 
-static void mlx5e_tx_timeout(struct net_device *dev)
+static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -4239,14 +4485,27 @@
 	new_channels.params = priv->channels.params;
 	new_channels.params.xdp_prog = prog;
 
-	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+	/* No XSK params: AF_XDP can't be enabled yet at the point of setting
+	 * the XDP program.
+	 */
+	if (!mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
 			    new_channels.params.sw_mtu,
-			    mlx5e_xdp_max_mtu(&new_channels.params));
+			    mlx5e_xdp_max_mtu(&new_channels.params, NULL));
 		return -EINVAL;
 	}
 
 	return 0;
+}
+
+static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog)
+{
+	struct bpf_prog *old_prog;
+
+	old_prog = rcu_replace_pointer(rq->xdp_prog, prog,
+				       lockdep_is_held(&rq->channel->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
 }
 
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
@@ -4269,33 +4528,37 @@
 	/* no need for full reset when exchanging programs */
 	reset = (!priv->channels.params.xdp_prog || !prog);
 
-	if (was_opened && reset)
-		mlx5e_close_locked(netdev);
-	if (was_opened && !reset) {
+	if (was_opened && !reset)
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
 		 */
-		prog = bpf_prog_add(prog, priv->channels.num);
-		if (IS_ERR(prog)) {
-			err = PTR_ERR(prog);
+		bpf_prog_add(prog, priv->channels.num);
+
+	if (was_opened && reset) {
+		struct mlx5e_channels new_channels = {};
+
+		new_channels.params = priv->channels.params;
+		new_channels.params.xdp_prog = prog;
+		mlx5e_set_rq_type(priv->mdev, &new_channels.params);
+		old_prog = priv->channels.params.xdp_prog;
+
+		err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL);
+		if (err)
 			goto unlock;
-		}
+	} else {
+		/* exchange programs, extra prog reference we got from caller
+		 * as long as we don't fail from this point onwards.
+		 */
+		old_prog = xchg(&priv->channels.params.xdp_prog, prog);
 	}
 
-	/* exchange programs, extra prog reference we got from caller
-	 * as long as we don't fail from this point onwards.
-	 */
-	old_prog = xchg(&priv->channels.params.xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
-	if (reset) /* change RQ type according to priv->xdp_prog */
+	if (!was_opened && reset) /* change RQ type according to priv->xdp_prog */
 		mlx5e_set_rq_type(priv->mdev, &priv->channels.params);
 
-	if (was_opened && reset)
-		mlx5e_open_locked(netdev);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
+	if (!was_opened || reset)
 		goto unlock;
 
 	/* exchanging programs w/o reset, we update ref counts on behalf
@@ -4304,38 +4567,21 @@
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
 
-		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		napi_synchronize(&c->napi);
-		/* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
-
-		old_prog = xchg(&c->rq.xdp_prog, prog);
-
-		set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		/* napi_schedule in case we have missed anything */
-		napi_schedule(&c->napi);
-
-		if (old_prog)
-			bpf_prog_put(old_prog);
+		mlx5e_rq_replace_xdp_prog(&c->rq, prog);
+		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) {
+			bpf_prog_inc(prog);
+			mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
+		}
 	}
 
 unlock:
 	mutex_unlock(&priv->state_lock);
+
+	/* Need to fix some features. */
+	if (!err)
+		netdev_update_features(netdev);
+
 	return err;
-}
-
-static u32 mlx5e_xdp_query(struct net_device *dev)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	u32 prog_id = 0;
-
-	mutex_lock(&priv->state_lock);
-	xdp_prog = priv->channels.params.xdp_prog;
-	if (xdp_prog)
-		prog_id = xdp_prog->aux->id;
-	mutex_unlock(&priv->state_lock);
-
-	return prog_id;
 }
 
 static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
@@ -4343,13 +4589,68 @@
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mlx5e_xdp_set(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = mlx5e_xdp_query(dev);
-		return 0;
+	case XDP_SETUP_XSK_POOL:
+		return mlx5e_xsk_setup_pool(dev, xdp->xsk.pool,
+					    xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
 }
+
+#ifdef CONFIG_MLX5_ESWITCH
+static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+				struct net_device *dev, u32 filter_mask,
+				int nlflags)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 mode, setting;
+	int err;
+
+	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
+	if (err)
+		return err;
+	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
+				       mode,
+				       0, 0, nlflags, filter_mask, NULL);
+}
+
+static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
+				u16 flags, struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct nlattr *attr, *br_spec;
+	u16 mode = BRIDGE_MODE_UNDEF;
+	u8 setting;
+	int rem;
+
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
+
+	nla_for_each_nested(attr, br_spec, rem) {
+		if (nla_type(attr) != IFLA_BRIDGE_MODE)
+			continue;
+
+		if (nla_len(attr) < sizeof(mode))
+			return -EINVAL;
+
+		mode = nla_get_u16(attr);
+		if (mode > BRIDGE_MODE_VEPA)
+			return -EINVAL;
+
+		break;
+	}
+
+	if (mode == BRIDGE_MODE_UNDEF)
+		return -EINVAL;
+
+	setting = (mode == BRIDGE_MODE_VEPA) ?  1 : 0;
+	return mlx5_eswitch_set_vepa(mdev->priv.eswitch, setting);
+}
+#endif
 
 const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_open                = mlx5e_open,
@@ -4367,16 +4668,20 @@
 	.ndo_change_mtu          = mlx5e_change_nic_mtu,
 	.ndo_do_ioctl            = mlx5e_ioctl,
 	.ndo_set_tx_maxrate      = mlx5e_set_tx_maxrate,
-	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
-	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
+	.ndo_udp_tunnel_add      = udp_tunnel_nic_add_port,
+	.ndo_udp_tunnel_del      = udp_tunnel_nic_del_port,
 	.ndo_features_check      = mlx5e_features_check,
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
 	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
+	.ndo_xsk_wakeup          = mlx5e_xsk_wakeup,
 #ifdef CONFIG_MLX5_EN_ARFS
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
 #ifdef CONFIG_MLX5_ESWITCH
+	.ndo_bridge_setlink      = mlx5e_bridge_setlink,
+	.ndo_bridge_getlink      = mlx5e_bridge_getlink,
+
 	/* SRIOV E-Switch NDOs */
 	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
 	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
@@ -4386,9 +4691,8 @@
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
-	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
-	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
 #endif
+	.ndo_get_devlink_port    = mlx5e_get_devlink_port,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -4441,9 +4745,9 @@
 		link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw;
 }
 
-static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
+static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
 {
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 
 	moder.cq_period_mode = cq_period_mode;
 	moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
@@ -4454,9 +4758,9 @@
 	return moder;
 }
 
-static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
+static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
 {
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 
 	moder.cq_period_mode = cq_period_mode;
 	moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
@@ -4470,11 +4774,11 @@
 static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
 {
 	return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ?
-		NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE :
-		NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+		DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode)
 {
 	if (params->tx_dim_enabled) {
 		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
@@ -4483,13 +4787,9 @@
 	} else {
 		params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode);
 	}
-
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
-			params->tx_cq_moderation.cq_period_mode ==
-				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
 }
 
-void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode)
 {
 	if (params->rx_dim_enabled) {
 		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
@@ -4498,7 +4798,19 @@
 	} else {
 		params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode);
 	}
+}
 
+void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+	mlx5e_reset_tx_moderation(params, cq_period_mode);
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
+			params->tx_cq_moderation.cq_period_mode ==
+				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
+}
+
+void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+	mlx5e_reset_rx_moderation(params, cq_period_mode);
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
 			params->rx_cq_moderation.cq_period_mode ==
 				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
@@ -4516,21 +4828,65 @@
 	return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
 }
 
-void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
-			    struct mlx5e_params *params,
-			    u16 max_channels, u16 mtu)
+void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
+			   struct mlx5e_params *params)
 {
+	/* Prefer Striding RQ, unless any of the following holds:
+	 * - Striding RQ configuration is not possible/supported.
+	 * - Slow PCI heuristic.
+	 * - Legacy RQ would use linear SKB while Striding RQ would use non-linear.
+	 *
+	 * No XSK params: checking the availability of striding RQ in general.
+	 */
+	if (!slow_pci_heuristic(mdev) &&
+	    mlx5e_striding_rq_possible(mdev, params) &&
+	    (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ||
+	     !mlx5e_rx_is_linear_skb(params, NULL)))
+		MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true);
+	mlx5e_set_rq_type(mdev, params);
+	mlx5e_init_rq_type_params(mdev, params);
+}
+
+void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
+			    u16 num_channels)
+{
+	enum mlx5e_traffic_types tt;
+
+	rss_params->hfunc = ETH_RSS_HASH_TOP;
+	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
+			    sizeof(rss_params->toeplitz_hash_key));
+	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, num_channels);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		rss_params->rx_hash_fields[tt] =
+			tirc_default_config[tt].rx_hash_fields;
+}
+
+void mlx5e_build_nic_params(struct mlx5e_priv *priv,
+			    struct mlx5e_xsk *xsk,
+			    struct mlx5e_rss_params *rss_params,
+			    struct mlx5e_params *params,
+			    u16 mtu)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 rx_cq_period_mode;
 
 	params->sw_mtu = mtu;
 	params->hard_mtu = MLX5E_ETH_HARD_MTU;
-	params->num_channels = max_channels;
+	params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2,
+				     priv->max_nch);
 	params->num_tc       = 1;
 
 	/* SQ */
 	params->log_sq_size = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE,
+			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
+
+	/* XDP SQ */
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE,
+			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
 
 	/* set CQE compression */
 	params->rx_cqe_compress_def = false;
@@ -4542,25 +4898,15 @@
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, false);
 
 	/* RQ */
-	/* Prefer Striding RQ, unless any of the following holds:
-	 * - Striding RQ configuration is not possible/supported.
-	 * - Slow PCI heuristic.
-	 * - Legacy RQ would use linear SKB while Striding RQ would use non-linear.
-	 */
-	if (!slow_pci_heuristic(mdev) &&
-	    mlx5e_striding_rq_possible(mdev, params) &&
-	    (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ||
-	     !mlx5e_rx_is_linear_skb(mdev, params)))
-		MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true);
-	mlx5e_set_rq_type(mdev, params);
-	mlx5e_init_rq_type_params(mdev, params);
+	mlx5e_build_rq_params(mdev, params);
 
 	/* HW LRO */
-
-	/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
-	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+	if (MLX5_CAP_ETH(mdev, lro_cap) &&
+	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+		/* No XSK params: checking the availability of striding RQ in general. */
+		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
 			params->lro_en = !slow_pci_heuristic(mdev);
+	}
 	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
@@ -4573,47 +4919,22 @@
 	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 */
-	params->rss_hfunc = ETH_RSS_HASH_XOR;
-	netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
-	mlx5e_build_default_indir_rqt(params->indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, max_channels);
-}
+	mlx5e_build_rss_params(rss_params, params->num_channels);
+	params->tunneled_offload_en =
+		mlx5e_tunnel_inner_ft_supported(mdev);
 
-static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
-					struct net_device *netdev,
-					const struct mlx5e_profile *profile,
-					void *ppriv)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-
-	priv->mdev        = mdev;
-	priv->netdev      = netdev;
-	priv->profile     = profile;
-	priv->ppriv       = ppriv;
-	priv->msglevel    = MLX5E_MSG_LEVEL;
-	priv->max_opened_tc = 1;
-
-	mlx5e_build_nic_params(mdev, &priv->channels.params,
-			       profile->max_nch(mdev), netdev->mtu);
-
-	mutex_init(&priv->state_lock);
-
-	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
-	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
-	INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
-	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
-
-	mlx5e_timestamp_init(priv);
+	/* AF_XDP */
+	params->xsk = xsk;
 }
 
 static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	mlx5_query_nic_vport_mac_address(priv->mdev, 0, netdev->dev_addr);
+	mlx5_query_mac_address(priv->mdev, netdev->dev_addr);
 	if (is_zero_ether_addr(netdev->dev_addr) &&
 	    !MLX5_CAP_GEN(priv->mdev, vport_group_manager)) {
 		eth_hw_addr_random(netdev);
@@ -4621,11 +4942,38 @@
 	}
 }
 
-#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-static const struct switchdev_ops mlx5e_switchdev_ops = {
-	.switchdev_port_attr_get	= mlx5e_attr_get,
-};
-#endif
+static int mlx5e_vxlan_set_port(struct net_device *netdev, unsigned int table,
+				unsigned int entry, struct udp_tunnel_info *ti)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5_vxlan_add_port(priv->mdev->vxlan, ntohs(ti->port));
+}
+
+static int mlx5e_vxlan_unset_port(struct net_device *netdev, unsigned int table,
+				  unsigned int entry, struct udp_tunnel_info *ti)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5_vxlan_del_port(priv->mdev->vxlan, ntohs(ti->port));
+}
+
+void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv)
+{
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
+		return;
+
+	priv->nic_info.set_port = mlx5e_vxlan_set_port;
+	priv->nic_info.unset_port = mlx5e_vxlan_unset_port;
+	priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
+				UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
+	priv->nic_info.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN;
+	/* Don't count the space hard-coded to the IANA port */
+	priv->nic_info.tables[0].n_entries =
+		mlx5_vxlan_max_udp_ports(priv->mdev) - 1;
+
+	priv->netdev->udp_tunnel_nic_info = &priv->nic_info;
+}
 
 static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
@@ -4634,32 +4982,40 @@
 	bool fcs_supported;
 	bool fcs_enabled;
 
-	SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
+	SET_NETDEV_DEV(netdev, mdev->device);
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-	if (MLX5_CAP_GEN(mdev, vport_group_manager) && MLX5_CAP_GEN(mdev, qos))
-		netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
-#endif
+	mlx5e_dcbnl_build_netdev(netdev);
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
 	netdev->ethtool_ops	  = &mlx5e_ethtool_ops;
 
 	netdev->vlan_features    |= NETIF_F_SG;
-	netdev->vlan_features    |= NETIF_F_IP_CSUM;
-	netdev->vlan_features    |= NETIF_F_IPV6_CSUM;
+	netdev->vlan_features    |= NETIF_F_HW_CSUM;
 	netdev->vlan_features    |= NETIF_F_GRO;
 	netdev->vlan_features    |= NETIF_F_TSO;
 	netdev->vlan_features    |= NETIF_F_TSO6;
 	netdev->vlan_features    |= NETIF_F_RXCSUM;
 	netdev->vlan_features    |= NETIF_F_RXHASH;
 
+	netdev->mpls_features    |= NETIF_F_SG;
+	netdev->mpls_features    |= NETIF_F_HW_CSUM;
+	netdev->mpls_features    |= NETIF_F_TSO;
+	netdev->mpls_features    |= NETIF_F_TSO6;
+
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_RX;
 
+	/* Tunneled LRO is not supported in the driver, and the same RQs are
+	 * shared between inner and outer TIRs, so the driver can't disable LRO
+	 * for inner TIRs while having it enabled for outer TIRs. Due to this,
+	 * block LRO altogether if the firmware declares tunneled LRO support.
+	 */
 	if (!!MLX5_CAP_ETH(mdev, lro_cap) &&
+	    !MLX5_CAP_ETH(mdev, tunnel_lro_vxlan) &&
+	    !MLX5_CAP_ETH(mdev, tunnel_lro_gre) &&
 	    mlx5e_check_fragmented_striding_rq_cap(mdev))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
@@ -4669,26 +5025,42 @@
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
-		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
-		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
+	mlx5e_vxlan_set_netdev_info(priv);
+
+	if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) ||
+	    mlx5e_any_tunnel_proto_supported(mdev)) {
+		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
 		netdev->hw_enc_features |= NETIF_F_TSO6;
 		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
 	}
 
-	if (mlx5_vxlan_allowed(mdev->vxlan)) {
-		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL;
-		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL;
+	if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) {
+		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
+					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
+					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL |
+					 NETIF_F_GSO_UDP_TUNNEL_CSUM;
 	}
 
-	if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
+	if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_GRE)) {
 		netdev->hw_features     |= NETIF_F_GSO_GRE |
 					   NETIF_F_GSO_GRE_CSUM;
 		netdev->hw_enc_features |= NETIF_F_GSO_GRE |
 					   NETIF_F_GSO_GRE_CSUM;
 		netdev->gso_partial_features |= NETIF_F_GSO_GRE |
 						NETIF_F_GSO_GRE_CSUM;
+	}
+
+	if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_IPIP)) {
+		netdev->hw_features |= NETIF_F_GSO_IPXIP4 |
+				       NETIF_F_GSO_IPXIP6;
+		netdev->hw_enc_features |= NETIF_F_GSO_IPXIP4 |
+					   NETIF_F_GSO_IPXIP6;
+		netdev->gso_partial_features |= NETIF_F_GSO_IPXIP4 |
+						NETIF_F_GSO_IPXIP6;
 	}
 
 	netdev->hw_features	                 |= NETIF_F_GSO_PARTIAL;
@@ -4723,7 +5095,7 @@
 	    FT_CAP(modify_root) &&
 	    FT_CAP(identified_miss_table_mode) &&
 	    FT_CAP(flow_table_modify)) {
-#ifdef CONFIG_MLX5_ESWITCH
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 		netdev->hw_features      |= NETIF_F_HW_TC;
 #endif
 #ifdef CONFIG_MLX5_EN_ARFS
@@ -4737,52 +5109,66 @@
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
-
-#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_ESWITCH_MANAGER(mdev))
-		netdev->switchdev_ops = &mlx5e_switchdev_ops;
-#endif
-
 	mlx5e_ipsec_build_netdev(priv);
 	mlx5e_tls_build_netdev(priv);
 }
 
-static void mlx5e_create_q_counters(struct mlx5e_priv *priv)
+void mlx5e_create_q_counters(struct mlx5e_priv *priv)
 {
+	u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
-	err = mlx5_core_alloc_q_counter(mdev, &priv->q_counter);
-	if (err) {
-		mlx5_core_warn(mdev, "alloc queue counter failed, %d\n", err);
-		priv->q_counter = 0;
-	}
+	MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
+	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
+	if (!err)
+		priv->q_counter =
+			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
 
-	err = mlx5_core_alloc_q_counter(mdev, &priv->drop_rq_q_counter);
-	if (err) {
-		mlx5_core_warn(mdev, "alloc drop RQ counter failed, %d\n", err);
-		priv->drop_rq_q_counter = 0;
-	}
+	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
+	if (!err)
+		priv->drop_rq_q_counter =
+			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
 }
 
-static void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
+void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
 {
-	if (priv->q_counter)
-		mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
+	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
 
-	if (priv->drop_rq_q_counter)
-		mlx5_core_dealloc_q_counter(priv->mdev, priv->drop_rq_q_counter);
+	MLX5_SET(dealloc_q_counter_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
+	if (priv->q_counter) {
+		MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+			 priv->q_counter);
+		mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in);
+	}
+
+	if (priv->drop_rq_q_counter) {
+		MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+			 priv->drop_rq_q_counter);
+		mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in);
+	}
 }
 
-static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
-			   struct net_device *netdev,
-			   const struct mlx5e_profile *profile,
-			   void *ppriv)
+static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
+			  struct net_device *netdev,
+			  const struct mlx5e_profile *profile,
+			  void *ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 	int err;
 
-	mlx5e_build_nic_netdev_priv(mdev, netdev, profile, ppriv);
+	err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
+	if (err)
+		return err;
+
+	mlx5e_build_nic_params(priv, &priv->xsk, rss, &priv->channels.params,
+			       netdev->mtu);
+
+	mlx5e_timestamp_init(priv);
+
 	err = mlx5e_ipsec_init(priv);
 	if (err)
 		mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err);
@@ -4790,13 +5176,21 @@
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
-	mlx5e_build_tc2txq_maps(priv);
+	err = mlx5e_devlink_port_register(priv);
+	if (err)
+		mlx5_core_err(mdev, "mlx5e_devlink_port_register failed, %d\n", err);
+	mlx5e_health_create_reporters(priv);
+
+	return 0;
 }
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
+	mlx5e_health_destroy_reporters(priv);
+	mlx5e_devlink_port_unregister(priv);
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
+	mlx5e_netdev_cleanup(priv->netdev, priv);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
@@ -4804,55 +5198,94 @@
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
+	mlx5e_create_q_counters(priv);
+
+	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
+	if (err) {
+		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+		goto err_destroy_q_counters;
+	}
+
 	err = mlx5e_create_indirect_rqt(priv);
 	if (err)
-		return err;
+		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv);
+	err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_rqts;
 
-	err = mlx5e_create_indirect_tirs(priv);
+	err = mlx5e_create_indirect_tirs(priv, true);
 	if (err)
 		goto err_destroy_direct_rqts;
 
-	err = mlx5e_create_direct_tirs(priv);
+	err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_tirs;
+
+	err = mlx5e_create_direct_rqts(priv, priv->xsk_tir);
+	if (unlikely(err))
+		goto err_destroy_direct_tirs;
+
+	err = mlx5e_create_direct_tirs(priv, priv->xsk_tir);
+	if (unlikely(err))
+		goto err_destroy_xsk_rqts;
 
 	err = mlx5e_create_flow_steering(priv);
 	if (err) {
 		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
-		goto err_destroy_direct_tirs;
+		goto err_destroy_xsk_tirs;
 	}
 
 	err = mlx5e_tc_nic_init(priv);
 	if (err)
 		goto err_destroy_flow_steering;
 
+	err = mlx5e_accel_init_rx(priv);
+	if (err)
+		goto err_tc_nic_cleanup;
+
+#ifdef CONFIG_MLX5_EN_ARFS
+	priv->netdev->rx_cpu_rmap =  mlx5_eq_table_get_rmap(priv->mdev);
+#endif
+
 	return 0;
 
+err_tc_nic_cleanup:
+	mlx5e_tc_nic_cleanup(priv);
 err_destroy_flow_steering:
 	mlx5e_destroy_flow_steering(priv);
+err_destroy_xsk_tirs:
+	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
+err_destroy_xsk_rqts:
+	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
 err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
 	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+err_close_drop_rq:
+	mlx5e_close_drop_rq(&priv->drop_rq);
+err_destroy_q_counters:
+	mlx5e_destroy_q_counters(priv);
 	return err;
 }
 
 static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 {
+	mlx5e_accel_cleanup_rx(priv);
 	mlx5e_tc_nic_cleanup(priv);
 	mlx5e_destroy_flow_steering(priv);
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
+	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 	mlx5e_destroy_indirect_tirs(priv);
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	mlx5e_close_drop_rq(&priv->drop_rq);
+	mlx5e_destroy_q_counters(priv);
 }
 
 static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
@@ -4865,9 +5298,7 @@
 		return err;
 	}
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_initialize(priv);
-#endif
 	return 0;
 }
 
@@ -4875,38 +5306,33 @@
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
 
 	mlx5e_init_l2_addr(priv);
 
 	/* Marking the link as currently not needed by the Driver */
 	if (!netif_running(netdev))
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
+		mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN);
 
-	/* MTU range: 68 - hw-specific max */
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	mlx5e_set_netdev_mtu_boundaries(priv);
 	mlx5e_set_dev_port_mtu(priv);
 
 	mlx5_lag_add(mdev, netdev);
 
 	mlx5e_enable_async_events(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_init(priv);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_register_vport_reps(priv);
-
+	mlx5e_hv_vhca_stats_create(priv);
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_init_app(priv);
-#endif
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	rtnl_lock();
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
+	udp_tunnel_nic_reset_ntf(priv->netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -4915,10 +5341,8 @@
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	if (priv->netdev->reg_state == NETREG_REGISTERED)
 		mlx5e_dcbnl_delete_app(priv);
-#endif
 
 	rtnl_lock();
 	if (netif_running(priv->netdev))
@@ -4928,11 +5352,18 @@
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_unregister_vport_reps(priv);
+	mlx5e_hv_vhca_stats_destroy(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_cleanup(priv);
 
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove(mdev);
+	mlx5_vxlan_reset_to_default(mdev->vxlan);
+}
+
+int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
+{
+	return mlx5e_refresh_tirs(priv, false, false);
 }
 
 static const struct mlx5e_profile mlx5e_nic_profile = {
@@ -4944,59 +5375,102 @@
 	.cleanup_tx	   = mlx5e_cleanup_nic_tx,
 	.enable		   = mlx5e_nic_enable,
 	.disable	   = mlx5e_nic_disable,
-	.update_stats	   = mlx5e_update_ndo_stats,
-	.max_nch	   = mlx5e_get_max_num_channels,
+	.update_rx	   = mlx5e_update_nic_rx,
+	.update_stats	   = mlx5e_stats_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
-	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe,
-	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+	.rx_handlers       = &mlx5e_rx_handlers_nic,
 	.max_tc		   = MLX5E_MAX_NUM_TC,
+	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(XSK),
+	.stats_grps	   = mlx5e_nic_stats_grps,
+	.stats_grps_num	   = mlx5e_nic_stats_grps_num,
 };
 
 /* mlx5e generic netdev management API (move to en_common.c) */
 
+/* mlx5e_netdev_init/cleanup must be called from profile->init/cleanup callbacks */
+int mlx5e_netdev_init(struct net_device *netdev,
+		      struct mlx5e_priv *priv,
+		      struct mlx5_core_dev *mdev,
+		      const struct mlx5e_profile *profile,
+		      void *ppriv)
+{
+	/* priv init */
+	priv->mdev        = mdev;
+	priv->netdev      = netdev;
+	priv->profile     = profile;
+	priv->ppriv       = ppriv;
+	priv->msglevel    = MLX5E_MSG_LEVEL;
+	priv->max_nch     = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
+	priv->max_opened_tc = 1;
+
+	if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	mutex_init(&priv->state_lock);
+	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
+	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
+	INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
+	INIT_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+
+	priv->wq = create_singlethread_workqueue("mlx5e");
+	if (!priv->wq)
+		goto err_free_cpumask;
+
+	/* netdev init */
+	netif_carrier_off(netdev);
+
+	return 0;
+
+err_free_cpumask:
+	free_cpumask_var(priv->scratchpad.cpumask);
+
+	return -ENOMEM;
+}
+
+void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv)
+{
+	destroy_workqueue(priv->wq);
+	free_cpumask_var(priv->scratchpad.cpumask);
+}
+
 struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 				       const struct mlx5e_profile *profile,
+				       int nch,
 				       void *ppriv)
 {
-	int nch = profile->max_nch(mdev);
 	struct net_device *netdev;
-	struct mlx5e_priv *priv;
+	int err;
 
 	netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
 				    nch * profile->max_tc,
-				    nch);
+				    nch * profile->rq_groups);
 	if (!netdev) {
 		mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
 		return NULL;
 	}
 
-#ifdef CONFIG_MLX5_EN_ARFS
-	netdev->rx_cpu_rmap = mdev->rmap;
-#endif
-
-	profile->init(mdev, netdev, profile, ppriv);
-
-	netif_carrier_off(netdev);
-
-	priv = netdev_priv(netdev);
-
-	priv->wq = create_singlethread_workqueue("mlx5e");
-	if (!priv->wq)
-		goto err_cleanup_nic;
+	err = profile->init(mdev, netdev, profile, ppriv);
+	if (err) {
+		mlx5_core_err(mdev, "failed to init mlx5e profile %d\n", err);
+		goto err_free_netdev;
+	}
 
 	return netdev;
 
-err_cleanup_nic:
-	if (profile->cleanup)
-		profile->cleanup(priv);
+err_free_netdev:
 	free_netdev(netdev);
 
 	return NULL;
 }
 
+static void mlx5e_reset_channels(struct net_device *netdev)
+{
+	netdev_reset_tc(netdev);
+}
+
 int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
+	const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED;
 	const struct mlx5e_profile *profile;
 	int max_nch;
 	int err;
@@ -5008,40 +5482,48 @@
 	max_nch = mlx5e_get_max_num_channels(priv->mdev);
 	if (priv->channels.params.num_channels > max_nch) {
 		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+		/* Reducing the number of channels - RXFH has to be reset, and
+		 * mlx5e_num_channels_changed below will build the RQT.
+		 */
+		priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
 		priv->channels.params.num_channels = max_nch;
-		mlx5e_build_default_indir_rqt(priv->channels.params.indirection_rqt,
-					      MLX5E_INDIR_RQT_SIZE, max_nch);
 	}
+	/* 1. Set the real number of queues in the kernel the first time.
+	 * 2. Set our default XPS cpumask.
+	 * 3. Build the RQT.
+	 *
+	 * rtnl_lock is required by netif_set_real_num_*_queues in case the
+	 * netdev has been registered by this point (if this function was called
+	 * in the reload or resume flow).
+	 */
+	if (take_rtnl)
+		rtnl_lock();
+	err = mlx5e_num_channels_changed(priv);
+	if (take_rtnl)
+		rtnl_unlock();
+	if (err)
+		goto out;
 
 	err = profile->init_tx(priv);
 	if (err)
 		goto out;
 
-	mlx5e_create_q_counters(priv);
-
-	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
-	if (err) {
-		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
-		goto err_destroy_q_counters;
-	}
-
 	err = profile->init_rx(priv);
 	if (err)
-		goto err_close_drop_rq;
+		goto err_cleanup_tx;
 
 	if (profile->enable)
 		profile->enable(priv);
 
 	return 0;
 
-err_close_drop_rq:
-	mlx5e_close_drop_rq(&priv->drop_rq);
-
-err_destroy_q_counters:
-	mlx5e_destroy_q_counters(priv);
+err_cleanup_tx:
 	profile->cleanup_tx(priv);
 
 out:
+	mlx5e_reset_channels(priv->netdev);
+	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
+	cancel_work_sync(&priv->update_stats_work);
 	return err;
 }
 
@@ -5056,10 +5538,9 @@
 	flush_workqueue(priv->wq);
 
 	profile->cleanup_rx(priv);
-	mlx5e_close_drop_rq(&priv->drop_rq);
-	mlx5e_destroy_q_counters(priv);
 	profile->cleanup_tx(priv);
-	cancel_delayed_work_sync(&priv->update_stats_work);
+	mlx5e_reset_channels(priv->netdev);
+	cancel_work_sync(&priv->update_stats_work);
 }
 
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv)
@@ -5067,7 +5548,6 @@
 	const struct mlx5e_profile *profile = priv->profile;
 	struct net_device *netdev = priv->netdev;
 
-	destroy_workqueue(priv->wq);
 	if (profile->cleanup)
 		profile->cleanup(priv);
 	free_netdev(netdev);
@@ -5103,6 +5583,11 @@
 	struct mlx5e_priv *priv = vpriv;
 	struct net_device *netdev = priv->netdev;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev)
+		return;
+#endif
+
 	if (!netif_device_present(netdev))
 		return;
 
@@ -5113,30 +5598,30 @@
 static void *mlx5e_add(struct mlx5_core_dev *mdev)
 {
 	struct net_device *netdev;
-	void *rpriv = NULL;
 	void *priv;
 	int err;
+	int nch;
 
 	err = mlx5e_check_required_hca_cap(mdev);
 	if (err)
 		return NULL;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_ESWITCH_MANAGER(mdev)) {
-		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
-		if (!rpriv) {
-			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
-			return NULL;
-		}
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
+	    mlx5_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) {
+		mlx5e_rep_register_vport_reps(mdev);
+		return mdev;
 	}
 #endif
 
-	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, rpriv);
+	nch = mlx5e_get_max_num_channels(mdev);
+	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL);
 	if (!netdev) {
 		mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
-		goto err_free_rpriv;
+		return NULL;
 	}
 
+	dev_net_set(netdev, mlx5_core_net(mdev));
 	priv = netdev_priv(netdev);
 
 	err = mlx5e_attach(mdev, priv);
@@ -5151,39 +5636,33 @@
 		goto err_detach;
 	}
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
+	mlx5e_devlink_port_type_eth_set(priv);
+
 	mlx5e_dcbnl_init_app(priv);
-#endif
 	return priv;
 
 err_detach:
 	mlx5e_detach(mdev, priv);
 err_destroy_netdev:
 	mlx5e_destroy_netdev(priv);
-err_free_rpriv:
-	kfree(rpriv);
 	return NULL;
 }
 
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
-	struct mlx5e_priv *priv = vpriv;
-	void *ppriv = priv->ppriv;
+	struct mlx5e_priv *priv;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-	mlx5e_dcbnl_delete_app(priv);
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) {
+		mlx5e_rep_unregister_vport_reps(mdev);
+		return;
+	}
 #endif
+	priv = vpriv;
+	mlx5e_dcbnl_delete_app(priv);
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
 	mlx5e_destroy_netdev(priv);
-	kfree(ppriv);
-}
-
-static void *mlx5e_get_netdev(void *vpriv)
-{
-	struct mlx5e_priv *priv = vpriv;
-
-	return priv->netdev;
 }
 
 static struct mlx5_interface mlx5e_interface = {
@@ -5191,9 +5670,7 @@
 	.remove    = mlx5e_remove,
 	.attach    = mlx5e_attach,
 	.detach    = mlx5e_detach,
-	.event     = mlx5e_async_event,
 	.protocol  = MLX5_INTERFACE_PROTOCOL_ETH,
-	.get_dev   = mlx5e_get_netdev,
 };
 
 void mlx5e_init(void)

--
Gitblit v1.6.2