1 files changed, 381 insertions, 158 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cee44c21766c..89c96a0f708e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -51,6 +51,7 @@
 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 {
@@ -93,7 +94,7 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 	return true;
 }
 
-static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
+static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
 {
 	if (!params->xdp_prog) {
 		u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
@@ -107,19 +108,27 @@ static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
 
 static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
 {
-	u32 linear_frag_sz = mlx5e_mpwqe_get_linear_frag_sz(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;
+}
+
 static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
 					 struct mlx5e_params *params)
 {
-	u32 frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params);
+	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
 	s8 signed_log_num_strides_param;
 	u8 log_num_strides;
 
-	if (params->lro_en || frag_sz > PAGE_SIZE)
+	if (!mlx5e_rx_is_linear_skb(mdev, params))
 		return false;
 
 	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
@@ -145,7 +154,7 @@ 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_mpwqe_get_linear_frag_sz(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));
@@ -163,16 +172,15 @@ static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 {
 	u16 linear_rq_headroom = params->xdp_prog ?
 		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	bool is_linear_skb;
 
 	linear_rq_headroom += NET_IP_ALIGN;
 
-	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST)
-		return linear_rq_headroom;
-
-	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
-		return linear_rq_headroom;
+	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 0;
+	return is_linear_skb ? linear_rq_headroom : 0;
 }
 
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
@@ -182,14 +190,6 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 	params->log_rq_mtu_frames = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
-	switch (params->rq_wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		/* Extra room needed for build_skb */
-		params->lro_wqe_sz -= mlx5e_get_rq_headroom(mdev, params) +
-			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	}
 
 	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,
@@ -213,7 +213,7 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 	params->rq_wq_type = mlx5e_striding_rq_possible(mdev, params) &&
 		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ) ?
 		MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
-		MLX5_WQ_TYPE_LINKED_LIST;
+		MLX5_WQ_TYPE_CYCLIC;
 }
 
 static void mlx5e_update_carrier(struct mlx5e_priv *priv)
@@ -327,10 +327,30 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
+static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
+{
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
+	default:
+		return mlx5_wq_cyc_get_size(&rq->wqe.wq);
+	}
+}
+
+static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
+{
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return rq->mpwqe.wq.cur_sz;
+	default:
+		return rq->wqe.wq.cur_sz;
+	}
+}
+
 static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 				     struct mlx5e_channel *c)
 {
-	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
+	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
 				      GFP_KERNEL, cpu_to_node(c->cpu));
@@ -378,7 +398,7 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 
 static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq)
 {
-	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->wq));
+	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);
 }
@@ -388,6 +408,61 @@ static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
 	return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
 }
 
+static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
+{
+	struct mlx5e_wqe_frag_info next_frag, *prev;
+	int i;
+
+	next_frag.di = &rq->wqe.di[0];
+	next_frag.offset = 0;
+	prev = NULL;
+
+	for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) {
+		struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+		struct mlx5e_wqe_frag_info *frag =
+			&rq->wqe.frags[i << rq->wqe.info.log_num_frags];
+		int f;
+
+		for (f = 0; f < rq->wqe.info.num_frags; f++, frag++) {
+			if (next_frag.offset + frag_info[f].frag_stride > PAGE_SIZE) {
+				next_frag.di++;
+				next_frag.offset = 0;
+				if (prev)
+					prev->last_in_page = true;
+			}
+			*frag = next_frag;
+
+			/* prepare next */
+			next_frag.offset += frag_info[f].frag_stride;
+			prev = frag;
+		}
+	}
+
+	if (prev)
+		prev->last_in_page = true;
+}
+
+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;
+
+	rq->wqe.di = kvzalloc_node(len * sizeof(*rq->wqe.di),
+				   GFP_KERNEL, cpu_to_node(cpu));
+	if (!rq->wqe.di)
+		return -ENOMEM;
+
+	mlx5e_init_frags_partition(rq);
+
+	return 0;
+}
+
+static void mlx5e_free_di_list(struct mlx5e_rq *rq)
+{
+	kvfree(rq->wqe.di);
+}
+
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_rq_param *rqp,
@@ -397,23 +472,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->mdev;
 	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
-	u32 byte_count, pool_size;
-	int npages;
+	u32 pool_size;
 	int wq_sz;
 	int err;
 	int i;
 
 	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
 
-	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
-				&rq->wq_ctrl);
-	if (err)
-		return err;
-
-	rq->wq.db = &rq->wq.db[MLX5_RCV_DBR];
-
-	wq_sz = mlx5_wq_ll_get_size(&rq->wq);
-
 	rq->wq_type = params->rq_wq_type;
 	rq->pdev    = c->pdev;
 	rq->netdev  = c->netdev;
@@ -423,6 +488,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	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->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
 	if (IS_ERR(rq->xdp_prog)) {
@@ -441,8 +507,17 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
+					&rq->wq_ctrl);
+		if (err)
+			return err;
+
+		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);
+
 		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
@@ -467,8 +542,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		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));
 
-		byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
-
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_wq_destroy;
@@ -476,16 +549,31 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		err = mlx5e_rq_alloc_mpwqe_info(rq, c);
 		if (err)
-			goto err_destroy_umr_mkey;
+			goto err_free;
 		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		rq->wqe.frag_info =
-			kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
-				     GFP_KERNEL, cpu_to_node(c->cpu));
-		if (!rq->wqe.frag_info) {
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq,
+					 &rq->wq_ctrl);
+		if (err)
+			return err;
+
+		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->wqe.frags =
+			kvzalloc_node((wq_sz << rq->wqe.info.log_num_frags) *
+				      sizeof(*rq->wqe.frags),
+				      GFP_KERNEL, cpu_to_node(c->cpu));
+		if (!rq->wqe.frags) {
 			err = -ENOMEM;
-			goto err_rq_wq_destroy;
+			goto err_free;
 		}
+
+		err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu);
+		if (err)
+			goto err_free;
 		rq->post_wqes = mlx5e_post_rx_wqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
@@ -496,32 +584,19 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 #endif
 			rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe;
 		if (!rq->handle_rx_cqe) {
-			kfree(rq->wqe.frag_info);
 			err = -EINVAL;
 			netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err);
-			goto err_rq_wq_destroy;
+			goto err_free;
 		}
 
-		byte_count = params->lro_en  ?
-				params->lro_wqe_sz :
-				MLX5E_SW2HW_MTU(params, params->sw_mtu);
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if (MLX5_IPSEC_DEV(mdev))
-			byte_count += MLX5E_METADATA_ETHER_LEN;
-#endif
-		rq->wqe.page_reuse = !params->xdp_prog && !params->lro_en;
-
-		/* calc the required page order */
-		rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->buff.headroom + byte_count);
-		npages = DIV_ROUND_UP(rq->wqe.frag_sz, PAGE_SIZE);
-		rq->buff.page_order = order_base_2(npages);
-
-		byte_count |= MLX5_HW_START_PADDING;
+		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     = rq->buff.page_order;
+	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);
@@ -535,28 +610,45 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	 */
 	rq->page_pool = page_pool_create(&pp_params);
 	if (IS_ERR(rq->page_pool)) {
-		if (rq->wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-			kfree(rq->wqe.frag_info);
 		err = PTR_ERR(rq->page_pool);
 		rq->page_pool = NULL;
-		goto err_rq_wq_destroy;
+		goto err_free;
 	}
 	err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 					 MEM_TYPE_PAGE_POOL, rq->page_pool);
 	if (err)
-		goto err_rq_wq_destroy;
+		goto err_free;
 
 	for (i = 0; i < wq_sz; i++) {
-		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
-
 		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+			struct mlx5e_rx_wqe_ll *wqe =
+				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);
 
-			wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom);
-		}
+			wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom);
+			wqe->data[0].byte_count = cpu_to_be32(byte_count);
+			wqe->data[0].lkey = rq->mkey_be;
+		} else {
+			struct mlx5e_rx_wqe_cyc *wqe =
+				mlx5_wq_cyc_get_wqe(&rq->wqe.wq, i);
+			int f;
+
+			for (f = 0; f < rq->wqe.info.num_frags; f++) {
+				u32 frag_size = rq->wqe.info.arr[f].frag_size |
+					MLX5_HW_START_PADDING;
 
-		wqe->data.byte_count = cpu_to_be32(byte_count);
-		wqe->data.lkey = rq->mkey_be;
+				wqe->data[f].byte_count = cpu_to_be32(frag_size);
+				wqe->data[f].lkey = rq->mkey_be;
+			}
+			/* check if num_frags is not a pow of two */
+			if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) {
+				wqe->data[f].byte_count = 0;
+				wqe->data[f].lkey = cpu_to_be32(MLX5_INVALID_LKEY);
+				wqe->data[f].addr = 0;
+			}
+		}
 	}
 
 	INIT_WORK(&rq->dim.work, mlx5e_rx_dim_work);
@@ -575,8 +667,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	return 0;
 
-err_destroy_umr_mkey:
-	mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+err_free:
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		kfree(rq->mpwqe.info);
+		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+		break;
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		kvfree(rq->wqe.frags);
+		mlx5e_free_di_list(rq);
+	}
 
 err_rq_wq_destroy:
 	if (rq->xdp_prog)
@@ -605,8 +705,9 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 		kfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		kfree(rq->wqe.frag_info);
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		kvfree(rq->wqe.frags);
+		mlx5e_free_di_list(rq);
 	}
 
 	for (i = rq->page_cache.head; i != rq->page_cache.tail;
@@ -646,8 +747,8 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq,
 						MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
 
-	mlx5_fill_page_array(&rq->wq_ctrl.buf,
-			     (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+	mlx5_fill_page_frag_array(&rq->wq_ctrl.buf,
+				  (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
 
 	err = mlx5_core_create_rq(mdev, in, inlen, &rq->rqn);
 
@@ -753,52 +854,53 @@ static 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;
 
-	struct mlx5_wq_ll *wq = &rq->wq;
-	u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
+	u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5e_rqwq_get_size(rq));
 
 	do {
-		if (wq->cur_sz >= min_wqes)
+		if (mlx5e_rqwq_get_cur_sz(rq) >= min_wqes)
 			return 0;
 
 		msleep(20);
 	} while (time_before(jiffies, exp_time));
 
 	netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
-		    c->ix, rq->rqn, wq->cur_sz, min_wqes);
+		    c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes);
 
 	return -ETIMEDOUT;
 }
 
 static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
-	struct mlx5_wq_ll *wq = &rq->wq;
-	struct mlx5e_rx_wqe *wqe;
 	__be16 wqe_ix_be;
 	u16 wqe_ix;
 
-	/* UMR WQE (if in progress) is always at wq->head */
-	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
-	    rq->mpwqe.umr_in_progress)
-		mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
-
-	while (!mlx5_wq_ll_is_empty(wq)) {
-		wqe_ix_be = *wq->tail_next;
-		wqe_ix    = be16_to_cpu(wqe_ix_be);
-		wqe       = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
-		rq->dealloc_wqe(rq, wqe_ix);
-		mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
-			       &wqe->next.next_wqe_index);
-	}
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
 
-	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST && rq->wqe.page_reuse) {
-		/* Clean outstanding pages on handled WQEs that decided to do page-reuse,
-		 * but yet to be re-posted.
-		 */
-		int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
+		/* UMR WQE (if in progress) is always at wq->head */
+		if (rq->mpwqe.umr_in_progress)
+			mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
+
+		while (!mlx5_wq_ll_is_empty(wq)) {
+			struct mlx5e_rx_wqe_ll *wqe;
 
-		for (wqe_ix = 0; wqe_ix < wq_sz; wqe_ix++)
+			wqe_ix_be = *wq->tail_next;
+			wqe_ix    = be16_to_cpu(wqe_ix_be);
+			wqe       = mlx5_wq_ll_get_wqe(wq, wqe_ix);
 			rq->dealloc_wqe(rq, wqe_ix);
+			mlx5_wq_ll_pop(wq, wqe_ix_be,
+				       &wqe->next.next_wqe_index);
+		}
+	} else {
+		struct mlx5_wq_cyc *wq = &rq->wqe.wq;
+
+		while (!mlx5_wq_cyc_is_empty(wq)) {
+			wqe_ix = mlx5_wq_cyc_get_tail(wq);
+			rq->dealloc_wqe(rq, wqe_ix);
+			mlx5_wq_cyc_pop(wq);
+		}
 	}
+
 }
 
 static int mlx5e_open_rq(struct mlx5e_channel *c,
@@ -836,13 +938,15 @@ err_free_rq:
 static void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
 	struct mlx5e_icosq *sq = &rq->channel->icosq;
-	u16 pi = sq->pc & sq->wq.sz_m1;
+	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(&sq->wq, sq->sqn, &sq->pc);
-	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
 }
 
 static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
@@ -885,6 +989,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
+	struct mlx5_wq_cyc *wq = &sq->wq;
 	int err;
 
 	sq->pdev      = c->pdev;
@@ -894,10 +999,10 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->min_inline_mode = params->tx_min_inline_mode;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
-	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
 	if (err)
 		return err;
-	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
+	wq->db = &wq->db[MLX5_SND_DBR];
 
 	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
@@ -940,23 +1045,22 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
+	struct mlx5_wq_cyc *wq = &sq->wq;
 	int err;
 
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
-	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
 	if (err)
 		return err;
-	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
+	wq->db = &wq->db[MLX5_SND_DBR];
 
 	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
-	sq->edge = (sq->wq.sz_m1 + 1) - MLX5E_ICOSQ_MAX_WQEBBS;
-
 	return 0;
 
 err_sq_wq_destroy:
@@ -1001,10 +1105,12 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
 			     struct mlx5e_params *params,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_txqsq *sq)
+			     struct mlx5e_txqsq *sq,
+			     int tc)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
+	struct mlx5_wq_cyc *wq = &sq->wq;
 	int err;
 
 	sq->pdev      = c->pdev;
@@ -1015,6 +1121,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->txq_ix    = txq_ix;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
 	INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
@@ -1022,10 +1129,10 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
-	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
 	if (err)
 		return err;
-	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
+	wq->db    = &wq->db[MLX5_SND_DBR];
 
 	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
@@ -1034,8 +1141,6 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	INIT_WORK(&sq->dim.work, mlx5e_tx_dim_work);
 	sq->dim.mode = params->tx_cq_moderation.cq_period_mode;
 
-	sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
-
 	return 0;
 
 err_sq_wq_destroy:
@@ -1095,7 +1200,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 					  MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq, dbr_addr,      csp->wq_ctrl->db.dma);
 
-	mlx5_fill_page_array(&csp->wq_ctrl->buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+	mlx5_fill_page_frag_array(&csp->wq_ctrl->buf,
+				  (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
 
 	err = mlx5_core_create_sq(mdev, in, inlen, sqn);
 
@@ -1174,13 +1280,14 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c,
 			    int txq_ix,
 			    struct mlx5e_params *params,
 			    struct mlx5e_sq_param *param,
-			    struct mlx5e_txqsq *sq)
+			    struct mlx5e_txqsq *sq,
+			    int tc)
 {
 	struct mlx5e_create_sq_param csp = {};
 	u32 tx_rate;
 	int err;
 
-	err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq);
+	err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq, tc);
 	if (err)
 		return err;
 
@@ -1238,6 +1345,7 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 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 */
@@ -1246,12 +1354,13 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	netif_tx_disable_queue(sq->txq);
 
 	/* last doorbell out, godspeed .. */
-	if (mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1)) {
+	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[(sq->pc & sq->wq.sz_m1)].skb = NULL;
-		nop = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
-		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nop->ctrl);
+		sq->db.wqe_info[pi].skb = NULL;
+		nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
 }
 
@@ -1366,7 +1475,7 @@ static void mlx5e_sq_recover(struct work_struct *work)
 		return;
 
 	mlx5e_reset_txqsq_cc_pc(sq);
-	sq->stats.recover++;
+	sq->stats->recover++;
 	recover->last_recover = jiffies;
 	mlx5e_activate_txqsq(sq);
 }
@@ -1535,7 +1644,7 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
 
 static void mlx5e_free_cq(struct mlx5e_cq *cq)
 {
-	mlx5_cqwq_destroy(&cq->wq_ctrl);
+	mlx5_wq_destroy(&cq->wq_ctrl);
 }
 
 static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
@@ -1551,7 +1660,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	int err;
 
 	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
-		sizeof(u64) * cq->wq_ctrl.frag_buf.npages;
+		sizeof(u64) * cq->wq_ctrl.buf.npages;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1560,7 +1669,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 
 	memcpy(cqc, param->cqc, sizeof(param->cqc));
 
-	mlx5_fill_page_frag_array(&cq->wq_ctrl.frag_buf,
+	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
 	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
@@ -1568,7 +1677,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
-	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.frag_buf.page_shift -
+	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
 
@@ -1661,14 +1770,14 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
 {
-	int err;
-	int tc;
+	struct mlx5e_priv *priv = c->priv;
+	int err, tc, max_nch = priv->profile->max_nch(priv->mdev);
 
 	for (tc = 0; tc < params->num_tc; tc++) {
-		int txq_ix = c->ix + tc * params->num_channels;
+		int txq_ix = c->ix + tc * max_nch;
 
 		err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
-				       params, &cparam->sq, &c->sq[tc]);
+				       params, &cparam->sq, &c->sq[tc], tc);
 		if (err)
 			goto err_close_sqs;
 	}
@@ -1798,6 +1907,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	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;
 
 	mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
 	c->irq_desc = irq_to_desc(irq);
@@ -1911,6 +2021,76 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	kfree(c);
 }
 
+#define DEFAULT_FRAG_SIZE (2048)
+
+static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
+				      struct mlx5e_params *params,
+				      struct mlx5e_rq_frags_info *info)
+{
+	u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	int frag_size_max = DEFAULT_FRAG_SIZE;
+	u32 buf_size = 0;
+	int i;
+
+#ifdef CONFIG_MLX5_EN_IPSEC
+	if (MLX5_IPSEC_DEV(mdev))
+		byte_count += MLX5E_METADATA_ETHER_LEN;
+#endif
+
+	if (mlx5e_rx_is_linear_skb(mdev, params)) {
+		int frag_stride;
+
+		frag_stride = mlx5e_rx_get_linear_frag_sz(params);
+		frag_stride = roundup_pow_of_two(frag_stride);
+
+		info->arr[0].frag_size = byte_count;
+		info->arr[0].frag_stride = frag_stride;
+		info->num_frags = 1;
+		info->wqe_bulk = PAGE_SIZE / frag_stride;
+		goto out;
+	}
+
+	if (byte_count > PAGE_SIZE +
+	    (MLX5E_MAX_RX_FRAGS - 1) * frag_size_max)
+		frag_size_max = PAGE_SIZE;
+
+	i = 0;
+	while (buf_size < byte_count) {
+		int frag_size = byte_count - buf_size;
+
+		if (i < MLX5E_MAX_RX_FRAGS - 1)
+			frag_size = min(frag_size, frag_size_max);
+
+		info->arr[i].frag_size = frag_size;
+		info->arr[i].frag_stride = roundup_pow_of_two(frag_size);
+
+		buf_size += frag_size;
+		i++;
+	}
+	info->num_frags = i;
+	/* number of different wqes sharing a page */
+	info->wqe_bulk = 1 + (info->num_frags % 2);
+
+out:
+	info->wqe_bulk = max_t(u8, info->wqe_bulk, 8);
+	info->log_num_frags = order_base_2(info->num_frags);
+}
+
+static inline u8 mlx5e_get_rqwq_log_stride(u8 wq_type, int ndsegs)
+{
+	int sz = sizeof(struct mlx5_wqe_data_seg) * ndsegs;
+
+	switch (wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		sz += sizeof(struct mlx5e_rx_wqe_ll);
+		break;
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		sz += sizeof(struct mlx5e_rx_wqe_cyc);
+	}
+
+	return order_base_2(sz);
+}
+
 static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 				 struct mlx5e_params *params,
 				 struct mlx5e_rq_param *param)
@@ -1918,6 +2098,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	int ndsegs = 1;
 
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
@@ -1927,16 +2108,18 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 		MLX5_SET(wq, wq, log_wqe_stride_size,
 			 mlx5e_mpwqe_get_log_stride_size(mdev, params) -
 			 MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
-		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
 		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
 		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+	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);
+		ndsegs = param->frags_info.num_frags;
 	}
 
+	MLX5_SET(wq, wq, wq_type,          params->rq_wq_type);
 	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
-	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
+	MLX5_SET(wq, wq, log_wq_stride,
+		 mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
 	MLX5_SET(wq, wq, pd,               mdev->mlx5e_res.pdn);
 	MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
@@ -1952,8 +2135,9 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
 
-	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
-	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
+	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
+	MLX5_SET(wq, wq, log_wq_stride,
+		 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);
@@ -2004,7 +2188,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
 			mlx5e_mpwqe_get_log_num_strides(mdev, params);
 		break;
-	default: /* MLX5_WQ_TYPE_LINKED_LIST */
+	default: /* MLX5_WQ_TYPE_CYCLIC */
 		log_cq_size = params->log_rq_mtu_frames;
 	}
 
@@ -2624,15 +2808,21 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
-static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv)
+static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv)
 {
-	struct mlx5e_channel *c;
-	struct mlx5e_txqsq *sq;
+	int max_nch = priv->profile->max_nch(priv->mdev);
 	int i, tc;
 
-	for (i = 0; i < priv->channels.num; i++)
+	for (i = 0; i < max_nch; i++)
 		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			priv->channel_tc2txq[i][tc] = i + tc * priv->channels.num;
+			priv->channel_tc2txq[i][tc] = i + tc * max_nch;
+}
+
+static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channel *c;
+	struct mlx5e_txqsq *sq;
+	int i, tc;
 
 	for (i = 0; i < priv->channels.num; i++) {
 		c = priv->channels.c[i];
@@ -2652,7 +2842,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	netif_set_real_num_tx_queues(netdev, num_txqs);
 	netif_set_real_num_rx_queues(netdev, priv->channels.num);
 
-	mlx5e_build_channels_tx_maps(priv);
+	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
 	netif_tx_start_all_queues(priv->netdev);
 
@@ -2804,8 +2994,8 @@ static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev,
 
 	param->wq.db_numa_node = param->wq.buf_numa_node;
 
-	err = mlx5_wq_ll_create(mdev, &param->wq, rqc_wq, &rq->wq,
-				&rq->wq_ctrl);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, rqc_wq, &rq->wqe.wq,
+				 &rq->wq_ctrl);
 	if (err)
 		return err;
 
@@ -3129,6 +3319,8 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
 	if (err)
 		goto out;
 
+	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:
 	mutex_unlock(&priv->state_lock);
@@ -3219,6 +3411,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
 		stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
 	} 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;
@@ -3293,12 +3486,18 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 	mutex_lock(&priv->state_lock);
 
 	old_params = &priv->channels.params;
+	if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
+		netdev_warn(netdev, "can't set LRO with legacy RQ\n");
+		err = -EINVAL;
+		goto out;
+	}
+
 	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
 
 	new_channels.params = *old_params;
 	new_channels.params.lro_en = enable;
 
-	if (old_params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+	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))
 			reset = false;
@@ -3462,22 +3661,31 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_params *params;
 
 	mutex_lock(&priv->state_lock);
+	params = &priv->channels.params;
 	if (!bitmap_empty(priv->fs.vlan.active_svlans, VLAN_N_VID)) {
 		/* HW strips the outer C-tag header, this is a problem
 		 * for S-tag traffic.
 		 */
 		features &= ~NETIF_F_HW_VLAN_CTAG_RX;
-		if (!priv->channels.params.vlan_strip_disable)
+		if (!params->vlan_strip_disable)
 			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)
+			netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n");
+	}
+
 	mutex_unlock(&priv->state_lock);
 
 	return features;
 }
 
-static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
+int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
+		     change_hw_mtu_cb set_mtu_cb)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
@@ -3495,7 +3703,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
 
-	if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
 
@@ -3504,7 +3712,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 
 	if (!reset) {
 		params->sw_mtu = new_mtu;
-		mlx5e_set_dev_port_mtu(priv);
+		set_mtu_cb(priv);
 		netdev->mtu = params->sw_mtu;
 		goto out;
 	}
@@ -3513,7 +3721,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
+	mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
@@ -3521,6 +3729,11 @@ out:
 	return err;
 }
 
+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);
+}
+
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 {
 	struct hwtstamp_config config;
@@ -3815,7 +4028,7 @@ static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
 		return false;
 
 	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
-	sq->channel->stats.eq_rearm++;
+	sq->channel->stats->eq_rearm++;
 	return true;
 }
 
@@ -4015,7 +4228,7 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_vlan_rx_kill_vid    = mlx5e_vlan_rx_kill_vid,
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_fix_features        = mlx5e_fix_features,
-	.ndo_change_mtu          = mlx5e_change_mtu,
+	.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,
@@ -4194,9 +4407,16 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
 
 	/* RQ */
-	if (mlx5e_striding_rq_possible(mdev, params))
-		MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ,
-				!slow_pci_heuristic(mdev));
+	/* 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);
 
@@ -4239,6 +4459,7 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	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);
@@ -4303,7 +4524,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_RX;
 
-	if (!!MLX5_CAP_ETH(mdev, lro_cap))
+	if (!!MLX5_CAP_ETH(mdev, lro_cap) &&
+	    mlx5e_check_fragmented_striding_rq_cap(mdev))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
 	netdev->hw_features       = netdev->vlan_features;
@@ -4426,6 +4648,7 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
+	mlx5e_build_tc2txq_maps(priv);
 	mlx5e_vxlan_init(priv);
 }