diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 95a232fb2127..6bc6472b98f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -181,12 +181,6 @@ do {                                                            \
 #define mlx5e_state_dereference(priv, p) \
 	rcu_dereference_protected((p), lockdep_is_held(&(priv)->state_lock))
 
-enum mlx5e_rq_group {
-	MLX5E_RQ_GROUP_REGULAR,
-	MLX5E_RQ_GROUP_XSK,
-#define MLX5E_NUM_RQ_GROUPS(g) (1 + MLX5E_RQ_GROUP_##g)
-};
-
 static inline u8 mlx5e_get_num_lag_ports(struct mlx5_core_dev *mdev)
 {
 	if (mlx5_lag_is_lacp_owner(mdev))
@@ -660,6 +654,7 @@ struct mlx5e_rq_frags_info {
 	u8 num_frags;
 	u8 log_num_frags;
 	u8 wqe_bulk;
+	u8 wqe_index_mask;
 };
 
 struct mlx5e_dma_info {
@@ -1004,7 +999,6 @@ struct mlx5e_profile {
 	mlx5e_stats_grp_t *stats_grps;
 	const struct mlx5e_rx_handlers *rx_handlers;
 	int	max_tc;
-	u8	rq_groups;
 	u32     features;
 };
 
@@ -1096,7 +1090,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx);
 
-int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
+int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state);
 void mlx5e_activate_rq(struct mlx5e_rq *rq);
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
 void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
index e7c14c0de0a7..48581ea3adcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
@@ -10,28 +10,33 @@ unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs)
 	return chs->num;
 }
 
+static struct mlx5e_channel *mlx5e_channels_get(struct mlx5e_channels *chs, unsigned int ix)
+{
+	WARN_ON_ONCE(ix >= mlx5e_channels_get_num(chs));
+	return chs->c[ix];
+}
+
+bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix)
+{
+	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
+
+	return test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+}
+
 void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
 {
-	struct mlx5e_channel *c;
-
-	WARN_ON(ix >= mlx5e_channels_get_num(chs));
-	c = chs->c[ix];
+	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
 
 	*rqn = c->rq.rqn;
 }
 
-bool mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
+void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
 {
-	struct mlx5e_channel *c;
+	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
 
-	WARN_ON(ix >= mlx5e_channels_get_num(chs));
-	c = chs->c[ix];
-
-	if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
-		return false;
+	WARN_ON_ONCE(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state));
 
 	*rqn = c->xskrq.rqn;
-	return true;
 }
 
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
index ca00cbc827cb..637ca90daaa8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
@@ -9,8 +9,9 @@
 struct mlx5e_channels;
 
 unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs);
+bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix);
 void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
-bool mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
+void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn);
 
 #endif /* __MLX5_EN_CHANNELS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 68bc66cbd8a5..ac4d70bb21e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -586,7 +586,14 @@ static int mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 		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;
+
+		/* N WQEs share the same page, N = PAGE_SIZE / frag_stride. The
+		 * first WQE in the page is responsible for allocation of this
+		 * page, this WQE's index is k*N. If WQEs [k*N+1; k*N+N-1] are
+		 * still not completed, the allocation must stop before k*N.
+		 */
+		info->wqe_index_mask = (PAGE_SIZE / frag_stride) - 1;
+
 		goto out;
 	}
 
@@ -635,11 +642,40 @@ static int mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 		i++;
 	}
 	info->num_frags = i;
-	/* number of different wqes sharing a page */
-	info->wqe_bulk = 1 + (info->num_frags % 2);
+
+	/* The last fragment of WQE with index 2*N may share the page with the
+	 * first fragment of WQE with index 2*N+1 in certain cases. If WQE 2*N+1
+	 * is not completed yet, WQE 2*N must not be allocated, as it's
+	 * responsible for allocating a new page.
+	 */
+	if (frag_size_max == PAGE_SIZE) {
+		/* No WQE can start in the middle of a page. */
+		info->wqe_index_mask = 0;
+	} else {
+		/* PAGE_SIZEs starting from 8192 don't use 2K-sized fragments,
+		 * because there would be more than MLX5E_MAX_RX_FRAGS of them.
+		 */
+		WARN_ON(PAGE_SIZE != 2 * DEFAULT_FRAG_SIZE);
+
+		/* Odd number of fragments allows to pack the last fragment of
+		 * the previous WQE and the first fragment of the next WQE into
+		 * the same page.
+		 * As long as DEFAULT_FRAG_SIZE is 2048, and MLX5E_MAX_RX_FRAGS
+		 * is 4, the last fragment can be bigger than the rest only if
+		 * it's the fourth one, so WQEs consisting of 3 fragments will
+		 * always share a page.
+		 * When a page is shared, WQE bulk size is 2, otherwise just 1.
+		 */
+		info->wqe_index_mask = info->num_frags % 2;
+	}
 
 out:
-	info->wqe_bulk = max_t(u8, info->wqe_bulk, 8);
+	/* Bulking optimization to skip allocation until at least 8 WQEs can be
+	 * allocated in a row. At the same time, never start allocation when
+	 * the page is still used by older WQEs.
+	 */
+	info->wqe_bulk = max_t(u8, info->wqe_index_mask + 1, 8);
+
 	info->log_num_frags = order_base_2(info->num_frags);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index cb862c478376..a3952afdcbe4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -53,38 +53,6 @@ struct mlx5e_create_sq_param {
 	u8                          min_inline_mode;
 };
 
-static inline bool mlx5e_qid_get_ch_if_in_group(struct mlx5e_params *params,
-						u16 qid,
-						enum mlx5e_rq_group group,
-						u16 *ix)
-{
-	int nch = params->num_channels;
-	int ch = qid - nch * group;
-
-	if (ch < 0 || ch >= nch)
-		return false;
-
-	*ix = ch;
-	return true;
-}
-
-static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params,
-					      u16 qid,
-					      u16 *ix,
-					      enum mlx5e_rq_group *group)
-{
-	u16 nch = params->num_channels;
-
-	*ix = qid % nch;
-	*group = qid / nch;
-}
-
-static inline bool mlx5e_qid_validate(const struct mlx5e_profile *profile,
-				      struct mlx5e_params *params, u64 qid)
-{
-	return qid < params->num_channels * profile->rq_groups;
-}
-
 /* Striding RQ dynamic parameters */
 
 u8 mlx5e_mpwrq_page_shift(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 2b946ae1d97f..5f6f95ad6888 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -134,34 +134,13 @@ out:
 	return err;
 }
 
-static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state)
-{
-	struct net_device *dev = rq->netdev;
-	int err;
-
-	err = mlx5e_modify_rq_state(rq, curr_state, MLX5_RQC_STATE_RST);
-	if (err) {
-		netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn);
-		return err;
-	}
-	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
-	if (err) {
-		netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn);
-		return err;
-	}
-
-	return 0;
-}
-
 static int mlx5e_rx_reporter_err_rq_cqe_recover(void *ctx)
 {
 	struct mlx5e_rq *rq = ctx;
 	int err;
 
 	mlx5e_deactivate_rq(rq);
-	mlx5e_free_rx_descs(rq);
-
-	err = mlx5e_rq_to_ready(rq, MLX5_RQC_STATE_ERR);
+	err = mlx5e_flush_rq(rq, MLX5_RQC_STATE_ERR);
 	clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 3436ecfcbc2f..e1095bc36543 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -24,8 +24,6 @@ struct mlx5e_rx_res {
 	struct {
 		struct mlx5e_rqt direct_rqt;
 		struct mlx5e_tir direct_tir;
-		struct mlx5e_rqt xsk_rqt;
-		struct mlx5e_tir xsk_tir;
 	} *channels;
 
 	struct {
@@ -320,48 +318,8 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res)
 		mlx5e_tir_builder_clear(builder);
 	}
 
-	if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
-		goto out;
-
-	for (ix = 0; ix < res->max_nch; ix++) {
-		err = mlx5e_rqt_init_direct(&res->channels[ix].xsk_rqt,
-					    res->mdev, false, res->drop_rqn);
-		if (err) {
-			mlx5_core_warn(res->mdev, "Failed to create an XSK RQT: err = %d, ix = %u\n",
-				       err, ix);
-			goto err_destroy_xsk_rqts;
-		}
-	}
-
-	for (ix = 0; ix < res->max_nch; ix++) {
-		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
-					    mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
-					    inner_ft_support);
-		mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
-		mlx5e_tir_builder_build_direct(builder);
-
-		err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true);
-		if (err) {
-			mlx5_core_warn(res->mdev, "Failed to create an XSK TIR: err = %d, ix = %u\n",
-				       err, ix);
-			goto err_destroy_xsk_tirs;
-		}
-
-		mlx5e_tir_builder_clear(builder);
-	}
-
 	goto out;
 
-err_destroy_xsk_tirs:
-	while (--ix >= 0)
-		mlx5e_tir_destroy(&res->channels[ix].xsk_tir);
-
-	ix = res->max_nch;
-err_destroy_xsk_rqts:
-	while (--ix >= 0)
-		mlx5e_rqt_destroy(&res->channels[ix].xsk_rqt);
-
-	ix = res->max_nch;
 err_destroy_direct_tirs:
 	while (--ix >= 0)
 		mlx5e_tir_destroy(&res->channels[ix].direct_tir);
@@ -420,12 +378,6 @@ static void mlx5e_rx_res_channels_destroy(struct mlx5e_rx_res *res)
 	for (ix = 0; ix < res->max_nch; ix++) {
 		mlx5e_tir_destroy(&res->channels[ix].direct_tir);
 		mlx5e_rqt_destroy(&res->channels[ix].direct_rqt);
-
-		if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
-			continue;
-
-		mlx5e_tir_destroy(&res->channels[ix].xsk_tir);
-		mlx5e_rqt_destroy(&res->channels[ix].xsk_rqt);
 	}
 
 	kvfree(res->channels);
@@ -491,13 +443,6 @@ u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 	return mlx5e_tir_get_tirn(&res->channels[ix].direct_tir);
 }
 
-u32 mlx5e_rx_res_get_tirn_xsk(struct mlx5e_rx_res *res, unsigned int ix)
-{
-	WARN_ON(!(res->features & MLX5E_RX_RES_FEATURE_XSK));
-
-	return mlx5e_tir_get_tirn(&res->channels[ix].xsk_tir);
-}
-
 u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt)
 {
 	struct mlx5e_rss *rss = res->rss[0];
@@ -527,26 +472,14 @@ static void mlx5e_rx_res_channel_activate_direct(struct mlx5e_rx_res *res,
 						 struct mlx5e_channels *chs,
 						 unsigned int ix)
 {
-	u32 rqn;
+	u32 rqn = res->rss_rqns[ix];
 	int err;
 
-	mlx5e_channels_get_regular_rqn(chs, ix, &rqn);
 	err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn);
 	if (err)
 		mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n",
 			       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 			       rqn, ix, err);
-
-	if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
-		return;
-
-	if (!mlx5e_channels_get_xsk_rqn(chs, ix, &rqn))
-		rqn = res->drop_rqn;
-	err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, rqn);
-	if (err)
-		mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to RQ %#x (channel %u): err = %d\n",
-			       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
-			       rqn, ix, err);
 }
 
 static void mlx5e_rx_res_channel_deactivate_direct(struct mlx5e_rx_res *res,
@@ -559,15 +492,6 @@ static void mlx5e_rx_res_channel_deactivate_direct(struct mlx5e_rx_res *res,
 		mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n",
 			       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 			       res->drop_rqn, ix, err);
-
-	if (!(res->features & MLX5E_RX_RES_FEATURE_XSK))
-		return;
-
-	err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn);
-	if (err)
-		mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n",
-			       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
-			       res->drop_rqn, ix, err);
 }
 
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs)
@@ -577,8 +501,12 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann
 
 	nch = mlx5e_channels_get_num(chs);
 
-	for (ix = 0; ix < chs->num; ix++)
-		mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]);
+	for (ix = 0; ix < chs->num; ix++) {
+		if (mlx5e_channels_is_xsk(chs, ix))
+			mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]);
+		else
+			mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]);
+	}
 	res->rss_nch = chs->num;
 
 	mlx5e_rx_res_rss_enable(res);
@@ -621,33 +549,17 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res)
 	}
 }
 
-int mlx5e_rx_res_xsk_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
-			      unsigned int ix)
+void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
+			     unsigned int ix, bool xsk)
 {
-	u32 rqn;
-	int err;
+	if (xsk)
+		mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]);
+	else
+		mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]);
 
-	if (!mlx5e_channels_get_xsk_rqn(chs, ix, &rqn))
-		return -EINVAL;
+	mlx5e_rx_res_rss_enable(res);
 
-	err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, rqn);
-	if (err)
-		mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to XSK RQ %#x (channel %u): err = %d\n",
-			       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
-			       rqn, ix, err);
-	return err;
-}
-
-int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix)
-{
-	int err;
-
-	err = mlx5e_rqt_redirect_direct(&res->channels[ix].xsk_rqt, res->drop_rqn);
-	if (err)
-		mlx5_core_warn(res->mdev, "Failed to redirect XSK RQT %#x to drop RQ %#x (channel %u): err = %d\n",
-			       mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
-			       res->drop_rqn, ix, err);
-	return err;
+	mlx5e_rx_res_channel_activate_direct(res, chs, ix);
 }
 
 int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index b39b20a720e0..5d5f64fab60f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -17,8 +17,7 @@ struct mlx5e_rss_params_hash;
 
 enum mlx5e_rx_res_features {
 	MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0),
-	MLX5E_RX_RES_FEATURE_XSK = BIT(1),
-	MLX5E_RX_RES_FEATURE_PTP = BIT(2),
+	MLX5E_RX_RES_FEATURE_PTP = BIT(1),
 };
 
 /* Setup */
@@ -32,7 +31,6 @@ void mlx5e_rx_res_free(struct mlx5e_rx_res *res);
 
 /* TIRN getters for flow steering */
 u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix);
-u32 mlx5e_rx_res_get_tirn_xsk(struct mlx5e_rx_res *res, unsigned int ix);
 u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
@@ -40,9 +38,8 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
 void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res);
-int mlx5e_rx_res_xsk_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
-			      unsigned int ix);
-int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix);
+void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
+			     unsigned int ix, bool xsk);
 
 /* Configuration API */
 void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index f4f306bb8e6d..4456ad5cedf1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -452,4 +452,11 @@ static inline bool mlx5e_icosq_can_post_wqe(struct mlx5e_icosq *sq, u16 wqe_size
 
 	return mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room);
 }
+
+static inline struct mlx5e_mpw_info *mlx5e_get_mpw_info(struct mlx5e_rq *rq, int i)
+{
+	size_t isz = struct_size(rq->mpwqe.info, alloc_units, rq->mpwqe.pages_per_wqe);
+
+	return (struct mlx5e_mpw_info *)((char *)rq->mpwqe.info + array_size(i, isz));
+}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
index 6058b1e72c6c..9804ef15a4d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
@@ -124,16 +124,10 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 	 * any Fill Ring entries at the setup stage.
 	 */
 
-	err = mlx5e_rx_res_xsk_activate(priv->rx_res, &priv->channels, ix);
-	if (unlikely(err))
-		goto err_deactivate;
+	mlx5e_rx_res_xsk_update(priv->rx_res, &priv->channels, ix, true);
 
 	return 0;
 
-err_deactivate:
-	mlx5e_deactivate_xsk(c);
-	mlx5e_close_xsk(c);
-
 err_remove_pool:
 	mlx5e_xsk_remove_pool(&priv->xsk, ix);
 
@@ -171,7 +165,7 @@ static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
 		goto remove_pool;
 
 	c = priv->channels.c[ix];
-	mlx5e_rx_res_xsk_deactivate(priv->rx_res, ix);
+	mlx5e_rx_res_xsk_update(priv->rx_res, &priv->channels, ix, false);
 	mlx5e_deactivate_xsk(c);
 	mlx5e_close_xsk(c);
 
@@ -209,11 +203,10 @@ int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_params *params = &priv->channels.params;
-	u16 ix;
 
-	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
+	if (unlikely(qid >= params->num_channels))
 		return -EINVAL;
 
-	return pool ? mlx5e_xsk_enable_pool(priv, pool, ix) :
-		      mlx5e_xsk_disable_pool(priv, ix);
+	return pool ? mlx5e_xsk_enable_pool(priv, pool, qid) :
+		      mlx5e_xsk_disable_pool(priv, qid);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 4441d35943d1..aebc1d5a9004 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -8,18 +8,174 @@
 
 /* RX data path */
 
-static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data,
-					       u32 cqe_bcnt)
+int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
+	struct mlx5e_mpw_info *wi = mlx5e_get_mpw_info(rq, ix);
+	struct mlx5e_icosq *icosq = rq->icosq;
+	struct mlx5_wq_cyc *wq = &icosq->wq;
+	struct mlx5e_umr_wqe *umr_wqe;
+	int batch, i;
+	u32 offset; /* 17-bit value with MTT. */
+	u16 pi;
+
+	if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool, rq->mpwqe.pages_per_wqe)))
+		goto err;
+
+	BUILD_BUG_ON(sizeof(wi->alloc_units[0]) != sizeof(wi->alloc_units[0].xsk));
+	batch = xsk_buff_alloc_batch(rq->xsk_pool, (struct xdp_buff **)wi->alloc_units,
+				     rq->mpwqe.pages_per_wqe);
+
+	/* If batch < pages_per_wqe, either:
+	 * 1. Some (or all) descriptors were invalid.
+	 * 2. dma_need_sync is true, and it fell back to allocating one frame.
+	 * In either case, try to continue allocating frames one by one, until
+	 * the first error, which will mean there are no more valid descriptors.
+	 */
+	for (; batch < rq->mpwqe.pages_per_wqe; batch++) {
+		wi->alloc_units[batch].xsk = xsk_buff_alloc(rq->xsk_pool);
+		if (unlikely(!wi->alloc_units[batch].xsk))
+			goto err_reuse_batch;
+	}
+
+	pi = mlx5e_icosq_get_next_pi(icosq, rq->mpwqe.umr_wqebbs);
+	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+	memcpy(umr_wqe, &rq->mpwqe.umr_wqe, sizeof(struct mlx5e_umr_wqe));
+
+	if (unlikely(rq->mpwqe.unaligned)) {
+		for (i = 0; i < batch; i++) {
+			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
+
+			umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(addr),
+			};
+		}
+	} else {
+		for (i = 0; i < batch; i++) {
+			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
+
+			umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
+				.ptag = cpu_to_be64(addr | MLX5_EN_WR),
+			};
+		}
+	}
+
+	bitmap_zero(wi->xdp_xmit_bitmap, rq->mpwqe.pages_per_wqe);
+	wi->consumed_strides = 0;
+
+	umr_wqe->ctrl.opmod_idx_opcode =
+		cpu_to_be32((icosq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR);
+
+	offset = ix * rq->mpwqe.mtts_per_wqe;
+	if (likely(!rq->mpwqe.unaligned))
+		offset = MLX5_ALIGNED_MTTS_OCTW(offset);
+	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+
+	icosq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
+		.wqe_type = MLX5E_ICOSQ_WQE_UMR_RX,
+		.num_wqebbs = rq->mpwqe.umr_wqebbs,
+		.umr.rq = rq,
+	};
+
+	icosq->pc += rq->mpwqe.umr_wqebbs;
+
+	icosq->doorbell_cseg = &umr_wqe->ctrl;
+
+	return 0;
+
+err_reuse_batch:
+	while (--batch >= 0)
+		xsk_buff_free(wi->alloc_units[batch].xsk);
+
+err:
+	rq->stats->buff_alloc_err++;
+	return -ENOMEM;
+}
+
+int mlx5e_xsk_alloc_rx_wqes_batched(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
+{
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
+	struct xdp_buff **buffs;
+	u32 contig, alloc;
+	int i;
+
+	/* mlx5e_init_frags_partition creates a 1:1 mapping between
+	 * rq->wqe.frags and rq->wqe.alloc_units, which allows us to
+	 * allocate XDP buffers straight into alloc_units.
+	 */
+	BUILD_BUG_ON(sizeof(rq->wqe.alloc_units[0]) !=
+		     sizeof(rq->wqe.alloc_units[0].xsk));
+	buffs = (struct xdp_buff **)rq->wqe.alloc_units;
+	contig = mlx5_wq_cyc_get_size(wq) - ix;
+	if (wqe_bulk <= contig) {
+		alloc = xsk_buff_alloc_batch(rq->xsk_pool, buffs + ix, wqe_bulk);
+	} else {
+		alloc = xsk_buff_alloc_batch(rq->xsk_pool, buffs + ix, contig);
+		if (likely(alloc == contig))
+			alloc += xsk_buff_alloc_batch(rq->xsk_pool, buffs, wqe_bulk - contig);
+	}
+
+	for (i = 0; i < alloc; i++) {
+		int j = mlx5_wq_cyc_ctr2ix(wq, ix + i);
+		struct mlx5e_wqe_frag_info *frag;
+		struct mlx5e_rx_wqe_cyc *wqe;
+		dma_addr_t addr;
+
+		wqe = mlx5_wq_cyc_get_wqe(wq, j);
+		/* Assumes log_num_frags == 0. */
+		frag = &rq->wqe.frags[j];
+
+		addr = xsk_buff_xdp_get_frame_dma(frag->au->xsk);
+		wqe->data[0].addr = cpu_to_be64(addr + rq->buff.headroom);
+	}
+
+	return alloc;
+}
+
+int mlx5e_xsk_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
+{
+	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
+	int i;
+
+	for (i = 0; i < wqe_bulk; i++) {
+		int j = mlx5_wq_cyc_ctr2ix(wq, ix + i);
+		struct mlx5e_wqe_frag_info *frag;
+		struct mlx5e_rx_wqe_cyc *wqe;
+		dma_addr_t addr;
+
+		wqe = mlx5_wq_cyc_get_wqe(wq, j);
+		/* Assumes log_num_frags == 0. */
+		frag = &rq->wqe.frags[j];
+
+		frag->au->xsk = xsk_buff_alloc(rq->xsk_pool);
+		if (unlikely(!frag->au->xsk))
+			return i;
+
+		addr = xsk_buff_xdp_get_frame_dma(frag->au->xsk);
+		wqe->data[0].addr = cpu_to_be64(addr + rq->buff.headroom);
+	}
+
+	return wqe_bulk;
+}
+
+static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, struct xdp_buff *xdp)
+{
+	u32 totallen = xdp->data_end - xdp->data_meta;
+	u32 metalen = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
 
-	skb = napi_alloc_skb(rq->cq.napi, cqe_bcnt);
+	skb = napi_alloc_skb(rq->cq.napi, totallen);
 	if (unlikely(!skb)) {
 		rq->stats->buff_alloc_err++;
 		return NULL;
 	}
 
-	skb_put_data(skb, data, cqe_bcnt);
+	skb_put_data(skb, xdp->data_meta, totallen);
+
+	if (metalen) {
+		skb_metadata_set(skb, metalen);
+		__skb_pull(skb, metalen);
+	}
 
 	return skb;
 }
@@ -46,8 +202,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 */
 	WARN_ON_ONCE(head_offset);
 
-	xdp->data_end = xdp->data + cqe_bcnt;
-	xdp_set_data_meta_invalid(xdp);
+	xsk_buff_set_size(xdp, cqe_bcnt);
 	xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
 	net_prefetch(xdp->data);
 
@@ -76,7 +231,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	/* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the
 	 * frame. On SKB allocation failure, NULL is returned.
 	 */
-	return mlx5e_xsk_construct_skb(rq, xdp->data, xdp->data_end - xdp->data);
+	return mlx5e_xsk_construct_skb(rq, xdp);
 }
 
 struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
@@ -93,8 +248,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	 */
 	WARN_ON_ONCE(wi->offset);
 
-	xdp->data_end = xdp->data + cqe_bcnt;
-	xdp_set_data_meta_invalid(xdp);
+	xsk_buff_set_size(xdp, cqe_bcnt);
 	xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
 	net_prefetch(xdp->data);
 
@@ -103,8 +257,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 		return NULL; /* page/packet was consumed by XDP */
 
 	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
-	 * will be handled by mlx5e_put_rx_frag.
+	 * will be handled by mlx5e_free_rx_wqe.
 	 * On SKB allocation failure, NULL is returned.
 	 */
-	return mlx5e_xsk_construct_skb(rq, xdp->data, xdp->data_end - xdp->data);
+	return mlx5e_xsk_construct_skb(rq, xdp);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
index e702cb790476..84a496a8d72f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -9,6 +9,9 @@
 
 /* RX data path */
 
+int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
+int mlx5e_xsk_alloc_rx_wqes_batched(struct mlx5e_rq *rq, u16 ix, int wqe_bulk);
+int mlx5e_xsk_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk);
 struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    struct mlx5e_mpw_info *wi,
 						    u16 cqe_bcnt,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 5129b9bf534f..ff03c43833bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -66,7 +66,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->xsk_pool     = pool;
 	rq->stats        = &c->priv->channel_stats[c->ix]->xskrq;
 	rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev);
-	rq_xdp_ix        = c->ix + params->num_channels * MLX5E_RQ_GROUP_XSK;
+	rq_xdp_ix        = c->ix;
 	err = mlx5e_rq_set_handlers(rq, params, xsk);
 	if (err)
 		return err;
@@ -154,7 +154,7 @@ err_free_cparam:
 void mlx5e_close_xsk(struct mlx5e_channel *c)
 {
 	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-	synchronize_net(); /* Sync with the XSK wakeup and with NAPI. */
+	synchronize_net(); /* Sync with NAPI. */
 
 	mlx5e_close_rq(&c->xskrq);
 	mlx5e_close_cq(&c->xskrq.cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 4902ef74fedf..367a9505ca4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -12,18 +12,14 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_params *params = &priv->channels.params;
 	struct mlx5e_channel *c;
-	u16 ix;
 
 	if (unlikely(!mlx5e_xdp_is_active(priv)))
 		return -ENETDOWN;
 
-	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
+	if (unlikely(qid >= params->num_channels))
 		return -EINVAL;
 
-	c = priv->channels.c[ix];
-
-	if (unlikely(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)))
-		return -EINVAL;
+	c = priv->channels.c[qid];
 
 	if (!napi_if_scheduled_mark_missed(&c->napi)) {
 		/* To avoid WQE overrun, don't post a NOP if async_icosq is not
@@ -36,9 +32,7 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 		if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state))
 			return 0;
 
-		spin_lock_bh(&c->async_icosq_lock);
-		mlx5e_trigger_irq(&c->async_icosq);
-		spin_unlock_bh(&c->async_icosq_lock);
+		mlx5e_trigger_napi_icosq(c);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 2a67798cd446..aac32e505c14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -451,15 +451,7 @@ static int flow_get_tirn(struct mlx5e_priv *priv,
 		eth_rule->rss = rss;
 		mlx5e_rss_refcnt_inc(eth_rule->rss);
 	} else {
-		struct mlx5e_params *params = &priv->channels.params;
-		enum mlx5e_rq_group group;
-		u16 ix;
-
-		mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group);
-
-		*tirn = group == MLX5E_RQ_GROUP_XSK ?
-			mlx5e_rx_res_get_tirn_xsk(priv->rx_res, ix) :
-			mlx5e_rx_res_get_tirn_direct(priv->rx_res, ix);
+		*tirn = mlx5e_rx_res_get_tirn_direct(priv->rx_res, fs->ring_cookie);
 	}
 
 	return 0;
@@ -682,8 +674,7 @@ static int validate_flow(struct mlx5e_priv *priv,
 		return -ENOSPC;
 
 	if (fs->ring_cookie != RX_CLS_FLOW_DISC)
-		if (!mlx5e_qid_validate(priv->profile, &priv->channels.params,
-					fs->ring_cookie))
+		if (fs->ring_cookie >= priv->channels.params.num_channels)
 			return -EINVAL;
 
 	switch (flow_type_mask(fs->flow_type)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2719247b18db..21fe43406d88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -433,6 +433,13 @@ static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
 	struct mlx5e_wqe_frag_info *prev = NULL;
 	int i;
 
+	if (rq->xsk_pool) {
+		/* Assumptions used by XSK batched allocator. */
+		WARN_ON(rq->wqe.info.num_frags != 1);
+		WARN_ON(rq->wqe.info.log_num_frags != 0);
+		WARN_ON(rq->wqe.info.arr[0].frag_stride != PAGE_SIZE);
+	}
+
 	next_frag.au = &rq->wqe.alloc_units[0];
 
 	for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) {
@@ -892,7 +899,7 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
 	return err;
 }
 
-int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
+static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
 
@@ -921,6 +928,32 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
 	return err;
 }
 
+static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state)
+{
+	struct net_device *dev = rq->netdev;
+	int err;
+
+	err = mlx5e_modify_rq_state(rq, curr_state, MLX5_RQC_STATE_RST);
+	if (err) {
+		netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn);
+		return err;
+	}
+	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
+	if (err) {
+		netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn);
+		return err;
+	}
+
+	return 0;
+}
+
+int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state)
+{
+	mlx5e_free_rx_descs(rq);
+
+	return mlx5e_rq_to_ready(rq, curr_state);
+}
+
 static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
@@ -2657,7 +2690,7 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 	struct netdev_tc_txq old_tc_to_txq[TC_MAX_QUEUE], *tc_to_txq;
 	struct net_device *netdev = priv->netdev;
 	int old_num_txqs, old_ntc;
-	int num_rxqs, nch, ntc;
+	int nch, ntc;
 	int err;
 	int i;
 
@@ -2668,7 +2701,6 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 
 	nch = priv->channels.params.num_channels;
 	ntc = priv->channels.params.mqprio.num_tc;
-	num_rxqs = nch * priv->profile->rq_groups;
 	tc_to_txq = priv->channels.params.mqprio.tc_to_txq;
 
 	err = mlx5e_netdev_set_tcs(netdev, nch, ntc, tc_to_txq);
@@ -2677,7 +2709,7 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 	err = mlx5e_update_tx_netdev_queues(priv);
 	if (err)
 		goto err_tcs;
-	err = netif_set_real_num_rx_queues(netdev, num_rxqs);
+	err = netif_set_real_num_rx_queues(netdev, nch);
 	if (err) {
 		netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err);
 		goto err_txqs;
@@ -5166,7 +5198,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP;
+	features = MLX5E_RX_RES_FEATURE_PTP;
 	if (priv->channels.params.tunneled_offload_en)
 		features |= MLX5E_RX_RES_FEATURE_INNER_FT;
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features,
@@ -5357,7 +5389,6 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.update_carrier	   = mlx5e_update_carrier,
 	.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,
 	.features          = BIT(MLX5E_PROFILE_FEATURE_PTP_RX) |
@@ -5390,8 +5421,7 @@ mlx5e_calc_max_nch(struct mlx5_core_dev *mdev, struct net_device *netdev,
 	max_nch = mlx5e_profile_max_num_channels(mdev, profile);
 
 	/* netdev rx queues */
-	tmp = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
-	max_nch = min_t(unsigned int, max_nch, tmp);
+	max_nch = min_t(unsigned int, max_nch, netdev->num_rx_queues);
 
 	/* netdev tx queues */
 	tmp = netdev->num_tx_queues;
@@ -5535,11 +5565,7 @@ static unsigned int mlx5e_get_max_num_txqs(struct mlx5_core_dev *mdev,
 static unsigned int mlx5e_get_max_num_rxqs(struct mlx5_core_dev *mdev,
 					   const struct mlx5e_profile *profile)
 {
-	unsigned int nch;
-
-	nch = mlx5e_profile_max_num_channels(mdev, profile);
-
-	return nch * profile->rq_groups;
+	return mlx5e_profile_max_num_channels(mdev, profile);
 }
 
 struct net_device *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 83b2febe8a7b..794cd8dfe9c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1224,7 +1224,6 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= 1,
-	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps		= mlx5e_rep_stats_grps,
 	.stats_grps_num		= mlx5e_rep_stats_grps_num,
 	.max_nch_limit		= mlx5e_rep_max_nch_limit,
@@ -1244,8 +1243,6 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.update_carrier	        = mlx5e_update_carrier,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= MLX5E_MAX_NUM_TC,
-	/* XSK is needed so we can replace profile with NIC netdev */
-	.rq_groups		= MLX5E_NUM_RQ_GROUPS(XSK),
 	.stats_grps		= mlx5e_ul_rep_stats_grps,
 	.stats_grps_num		= mlx5e_ul_rep_stats_grps_num,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 72d74de3ee99..36eda4c958a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -75,13 +75,6 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = {
 	.handle_rx_cqe_mpwqe_shampo = mlx5e_handle_rx_cqe_mpwrq_shampo,
 };
 
-static struct mlx5e_mpw_info *mlx5e_get_mpw_info(struct mlx5e_rq *rq, int i)
-{
-	size_t isz = struct_size(rq->mpwqe.info, alloc_units, rq->mpwqe.pages_per_wqe);
-
-	return (struct mlx5e_mpw_info *)((char *)rq->mpwqe.info + array_size(i, isz));
-}
-
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
 	return config->rx_filter == HWTSTAMP_FILTER_ALL;
@@ -300,16 +293,6 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, union mlx5e_alloc_u
 	return 0;
 }
 
-static inline int mlx5e_page_alloc(struct mlx5e_rq *rq, union mlx5e_alloc_unit *au)
-{
-	if (rq->xsk_pool) {
-		au->xsk = xsk_buff_alloc(rq->xsk_pool);
-		return likely(au->xsk) ? 0 : -ENOMEM;
-	} else {
-		return mlx5e_page_alloc_pool(rq, au);
-	}
-}
-
 void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct page *page)
 {
 	dma_addr_t dma_addr = page_pool_get_dma_addr(page);
@@ -334,20 +317,6 @@ void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, struct page *page, bool rec
 	}
 }
 
-static inline void mlx5e_page_release(struct mlx5e_rq *rq,
-				      union mlx5e_alloc_unit *au,
-				      bool recycle)
-{
-	if (rq->xsk_pool)
-		/* The `recycle` parameter is ignored, and the page is always
-		 * put into the Reuse Ring, because there is no way to return
-		 * the page to the userspace when the interface goes down.
-		 */
-		xsk_buff_free(au->xsk);
-	else
-		mlx5e_page_release_dynamic(rq, au->page, recycle);
-}
-
 static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 				    struct mlx5e_wqe_frag_info *frag)
 {
@@ -359,7 +328,7 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 		 * offset) should just use the new one without replenishing again
 		 * by themselves.
 		 */
-		err = mlx5e_page_alloc(rq, frag->au);
+		err = mlx5e_page_alloc_pool(rq, frag->au);
 
 	return err;
 }
@@ -369,7 +338,7 @@ static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
 				     bool recycle)
 {
 	if (frag->last_in_page)
-		mlx5e_page_release(rq, frag->au, recycle);
+		mlx5e_page_release_dynamic(rq, frag->au->page, recycle);
 }
 
 static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -393,8 +362,7 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
 			goto free_frags;
 
 		headroom = i == 0 ? rq->buff.headroom : 0;
-		addr = rq->xsk_pool ? xsk_buff_xdp_get_frame_dma(frag->au->xsk) :
-				      page_pool_get_dma_addr(frag->au->page);
+		addr = page_pool_get_dma_addr(frag->au->page);
 		wqe->data[i].addr = cpu_to_be64(addr + frag->offset + headroom);
 	}
 
@@ -413,6 +381,15 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq,
 {
 	int i;
 
+	if (rq->xsk_pool) {
+		/* The `recycle` parameter is ignored, and the page is always
+		 * put into the Reuse Ring, because there is no way to return
+		 * the page to the userspace when the interface goes down.
+		 */
+		xsk_buff_free(wi->au->xsk);
+		return;
+	}
+
 	for (i = 0; i < rq->wqe.info.num_frags; i++, wi++)
 		mlx5e_put_rx_frag(rq, wi, recycle);
 }
@@ -424,38 +401,22 @@ static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 	mlx5e_free_rx_wqe(rq, wi, false);
 }
 
-static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
+static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
-	int err;
 	int i;
 
-	if (rq->xsk_pool) {
-		int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags;
-
-		/* Check in advance that we have enough frames, instead of
-		 * allocating one-by-one, failing and moving frames to the
-		 * Reuse Ring.
-		 */
-		if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool, pages_desired)))
-			return -ENOMEM;
-	}
-
 	for (i = 0; i < wqe_bulk; i++) {
-		struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i);
+		int j = mlx5_wq_cyc_ctr2ix(wq, ix + i);
+		struct mlx5e_rx_wqe_cyc *wqe;
 
-		err = mlx5e_alloc_rx_wqe(rq, wqe, ix + i);
-		if (unlikely(err))
-			goto free_wqes;
+		wqe = mlx5_wq_cyc_get_wqe(wq, j);
+
+		if (unlikely(mlx5e_alloc_rx_wqe(rq, wqe, j)))
+			break;
 	}
 
-	return 0;
-
-free_wqes:
-	while (--i >= 0)
-		mlx5e_dealloc_rx_wqe(rq, ix + i);
-
-	return err;
+	return i;
 }
 
 static inline void
@@ -497,9 +458,19 @@ mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle
 
 	no_xdp_xmit = bitmap_empty(wi->xdp_xmit_bitmap, rq->mpwqe.pages_per_wqe);
 
-	for (i = 0; i < rq->mpwqe.pages_per_wqe; i++)
-		if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
-			mlx5e_page_release(rq, &alloc_units[i], recycle);
+	if (rq->xsk_pool) {
+		/* The `recycle` parameter is ignored, and the page is always
+		 * put into the Reuse Ring, because there is no way to return
+		 * the page to the userspace when the interface goes down.
+		 */
+		for (i = 0; i < rq->mpwqe.pages_per_wqe; i++)
+			if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
+				xsk_buff_free(alloc_units[i].xsk);
+	} else {
+		for (i = 0; i < rq->mpwqe.pages_per_wqe; i++)
+			if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
+				mlx5e_page_release_dynamic(rq, alloc_units[i].page, recycle);
+	}
 }
 
 static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n)
@@ -586,7 +557,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 		if (!(header_offset & (PAGE_SIZE - 1))) {
 			union mlx5e_alloc_unit au;
 
-			err = mlx5e_page_alloc(rq, &au);
+			err = mlx5e_page_alloc_pool(rq, &au);
 			if (unlikely(err))
 				goto err_unmap;
 			page = dma_info->page = au.page;
@@ -622,12 +593,8 @@ err_unmap:
 	while (--i >= 0) {
 		dma_info = &shampo->info[--index];
 		if (!(i & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1))) {
-			union mlx5e_alloc_unit au = {
-				.page = dma_info->page,
-			};
-
 			dma_info->addr = ALIGN_DOWN(dma_info->addr, PAGE_SIZE);
-			mlx5e_page_release(rq, &au, true);
+			mlx5e_page_release_dynamic(rq, dma_info->page, true);
 		}
 	}
 	rq->stats->buff_alloc_err++;
@@ -685,15 +652,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	int err;
 	int i;
 
-	/* Check in advance that we have enough frames, instead of allocating
-	 * one-by-one, failing and moving frames to the Reuse Ring.
-	 */
-	if (rq->xsk_pool &&
-	    unlikely(!xsk_buff_can_alloc(rq->xsk_pool, rq->mpwqe.pages_per_wqe))) {
-		err = -ENOMEM;
-		goto err;
-	}
-
 	if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) {
 		err = mlx5e_alloc_rx_hd_mpwqe(rq);
 		if (unlikely(err))
@@ -704,33 +662,16 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
 	memcpy(umr_wqe, &rq->mpwqe.umr_wqe, sizeof(struct mlx5e_umr_wqe));
 
-	if (unlikely(rq->mpwqe.unaligned)) {
-		for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, au++) {
-			dma_addr_t addr;
+	for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, au++) {
+		dma_addr_t addr;
 
-			err = mlx5e_page_alloc(rq, au);
-			if (unlikely(err))
-				goto err_unmap;
-			/* Unaligned means XSK. */
-			addr = xsk_buff_xdp_get_frame_dma(au->xsk);
-			umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
-				.key = rq->mkey_be,
-				.va = cpu_to_be64(addr),
-			};
-		}
-	} else {
-		for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, au++) {
-			dma_addr_t addr;
-
-			err = mlx5e_page_alloc(rq, au);
-			if (unlikely(err))
-				goto err_unmap;
-			addr = rq->xsk_pool ? xsk_buff_xdp_get_frame_dma(au->xsk) :
-					      page_pool_get_dma_addr(au->page);
-			umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
-				.ptag = cpu_to_be64(addr | MLX5_EN_WR),
-			};
-		}
+		err = mlx5e_page_alloc_pool(rq, au);
+		if (unlikely(err))
+			goto err_unmap;
+		addr = page_pool_get_dma_addr(au->page);
+		umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
+			.ptag = cpu_to_be64(addr | MLX5_EN_WR),
+		};
 	}
 
 	bitmap_zero(wi->xdp_xmit_bitmap, rq->mpwqe.pages_per_wqe);
@@ -740,9 +681,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
 
-	offset = ix * rq->mpwqe.mtts_per_wqe;
-	if (!rq->mpwqe.unaligned)
-		offset = MLX5_ALIGNED_MTTS_OCTW(offset);
+	offset = MLX5_ALIGNED_MTTS_OCTW(ix * rq->mpwqe.mtts_per_wqe);
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
@@ -760,7 +699,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 err_unmap:
 	while (--i >= 0) {
 		au--;
-		mlx5e_page_release(rq, au, true);
+		mlx5e_page_release_dynamic(rq, au->page, true);
 	}
 
 err:
@@ -793,12 +732,8 @@ void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close
 		hd_info = &shampo->info[index];
 		hd_info->addr = ALIGN_DOWN(hd_info->addr, PAGE_SIZE);
 		if (hd_info->page != deleted_page) {
-			union mlx5e_alloc_unit au = {
-				.page = hd_info->page,
-			};
-
 			deleted_page = hd_info->page;
-			mlx5e_page_release(rq, &au, false);
+			mlx5e_page_release_dynamic(rq, hd_info->page, false);
 		}
 	}
 
@@ -821,38 +756,51 @@ static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
-	u8 wqe_bulk;
-	int err;
+	int wqe_bulk, count;
+	bool busy = false;
+	u16 head;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return false;
 
-	wqe_bulk = rq->wqe.info.wqe_bulk;
-
-	if (mlx5_wq_cyc_missing(wq) < wqe_bulk)
+	if (mlx5_wq_cyc_missing(wq) < rq->wqe.info.wqe_bulk)
 		return false;
 
 	if (rq->page_pool)
 		page_pool_nid_changed(rq->page_pool, numa_mem_id());
 
-	do {
-		u16 head = mlx5_wq_cyc_get_head(wq);
+	wqe_bulk = mlx5_wq_cyc_missing(wq);
+	head = mlx5_wq_cyc_get_head(wq);
 
-		err = mlx5e_alloc_rx_wqes(rq, head, wqe_bulk);
-		if (unlikely(err)) {
-			rq->stats->buff_alloc_err++;
-			break;
-		}
+	/* Don't allow any newly allocated WQEs to share the same page with old
+	 * WQEs that aren't completed yet. Stop earlier.
+	 */
+	wqe_bulk -= (head + wqe_bulk) & rq->wqe.info.wqe_index_mask;
 
-		mlx5_wq_cyc_push_n(wq, wqe_bulk);
-	} while (mlx5_wq_cyc_missing(wq) >= wqe_bulk);
+	if (!rq->xsk_pool)
+		count = mlx5e_alloc_rx_wqes(rq, head, wqe_bulk);
+	else if (likely(!rq->xsk_pool->dma_need_sync))
+		count = mlx5e_xsk_alloc_rx_wqes_batched(rq, head, wqe_bulk);
+	else
+		/* If dma_need_sync is true, it's more efficient to call
+		 * xsk_buff_alloc in a loop, rather than xsk_buff_alloc_batch,
+		 * because the latter does the same check and returns only one
+		 * frame.
+		 */
+		count = mlx5e_xsk_alloc_rx_wqes(rq, head, wqe_bulk);
+
+	mlx5_wq_cyc_push_n(wq, count);
+	if (unlikely(count != wqe_bulk)) {
+		rq->stats->buff_alloc_err++;
+		busy = true;
+	}
 
 	/* ensure wqes are visible to device before updating doorbell record */
 	dma_wmb();
 
 	mlx5_wq_cyc_update_db_record(wq);
 
-	return !!err;
+	return busy;
 }
 
 void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq)
@@ -1020,7 +968,8 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 	head = rq->mpwqe.actual_wq_head;
 	i = missing;
 	do {
-		alloc_err = mlx5e_alloc_rx_mpwqe(rq, head);
+		alloc_err = rq->xsk_pool ? mlx5e_xsk_alloc_rx_mpwqe(rq, head) :
+					   mlx5e_alloc_rx_mpwqe(rq, head);
 
 		if (unlikely(alloc_err))
 			break;
@@ -2109,12 +2058,8 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
 	u64 addr = shampo->info[header_index].addr;
 
 	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {
-		union mlx5e_alloc_unit au = {
-			.page = shampo->info[header_index].page,
-		};
-
 		shampo->info[header_index].addr = ALIGN_DOWN(addr, PAGE_SIZE);
-		mlx5e_page_release(rq, &au, true);
+		mlx5e_page_release_dynamic(rq, shampo->info[header_index].page, true);
 	}
 	bitmap_clear(shampo->bitmap, header_index, 1);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 35f797cfd21e..4e3a75496dd9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -463,7 +463,6 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.update_carrier    = NULL, /* no HW update in IB link */
 	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
-	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps        = mlx5i_stats_grps,
 	.stats_grps_num    = mlx5i_stats_grps_num,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 0b86e78dbc0e..0227a521d301 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -349,7 +349,6 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.update_stats	   = NULL,
 	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
-	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(REGULAR),
 };
 
 const struct mlx5e_profile *mlx5i_pkey_get_profile(void)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index e5c4dcd1425e..4d629e5ddbc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -123,7 +123,7 @@ static inline void mlx5_wq_cyc_push(struct mlx5_wq_cyc *wq)
 	wq->cur_sz++;
 }
 
-static inline void mlx5_wq_cyc_push_n(struct mlx5_wq_cyc *wq, u8 n)
+static inline void mlx5_wq_cyc_push_n(struct mlx5_wq_cyc *wq, u16 n)
 {
 	wq->wqe_ctr += n;
 	wq->cur_sz += n;