Merge branch 'net-mlx5e-add-support-for-devmem-and-io_uring-tcp-zero-copy'

Mark Bloch says:

====================
net/mlx5e: Add support for devmem and io_uring TCP zero-copy

This series adds support for zerocopy rx TCP with devmem and io_uring
for ConnectX7 NICs and above. For performance reasons and simplicity
HW-GRO will also be turned on when header-data split mode is on.

Performance
===========

Test setup:

* CPU: Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz (single NUMA)
* NIC: ConnectX7
* Benchmarking tool: kperf [0]
* Single TCP flow
* Test duration: 60s

With application thread and interrupts pinned to the *same* core:

|------+-----------+----------|
| MTU  | epoll     | io_uring |
|------+-----------+----------|
| 1500 | 61.6 Gbps | 114 Gbps |
| 4096 | 69.3 Gbps | 151 Gbps |
| 9000 | 67.8 Gbps | 187 Gbps |
|------+-----------+----------|

The CPU usage for io_uring is 95%.

Reproduction steps for io_uring:

server --no-daemon -a 2001:db8::1 --no-memcmp --iou --iou_sendzc \
	--iou_zcrx --iou_dev_name eth2 --iou_zcrx_queue_id 2

server --no-daemon -a 2001:db8::2 --no-memcmp --iou --iou_sendzc

client --src 2001:db8::2 --dst 2001:db8::1 \
	--msg-zerocopy -t 60 --cpu-min=2 --cpu-max=2

Patch overview:
================

First, a netmem API for skb_can_coalesce is added to the core to be able
to do skb fragment coalescing on netmems.

The next patches introduce some cleanups in the internal SHAMPO code and
improvements to hw gro capability checks in FW.

A separate page_pool is introduced for headers, to be used only when
the rxq has a memory provider.

Then the driver is converted to use the netmem API and to allow support
for unreadable netmem page pool.

The queue management ops are implemented.

Finally, the tcp-data-split ring parameter is exposed.
References
==========
[0] kperf: git://git.kernel.dk/kperf.git
v1: https://lore.kernel.org/20250116215530.158886-1-saeed@kernel.org
v2: https://lore.kernel.org/1747950086-1246773-1-git-send-email-tariqt@nvidia.com
v3: https://lore.kernel.org/20250609145833.990793-1-mbloch@nvidia.com
v4: https://lore.kernel.org/20250610150950.1094376-1-mbloch@nvidia.com
v5: https://lore.kernel.org/20250612154648.1161201-1-mbloch@nvidia.com
====================

Link: https://patch.msgid.link/20250616141441.1243044-1-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 381 insertions, 167 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5b0d03b3efe8..65a73913b9a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -278,10 +278,6 @@ enum packet_merge {
 struct mlx5e_packet_merge_param {
 	enum packet_merge type;
 	u32 timeout;
-	struct {
-		u8 match_criteria_type;
-		u8 alignment_granularity;
-	} shampo;
 };
 
 struct mlx5e_params {
@@ -557,7 +553,7 @@ struct mlx5e_icosq {
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_frag_page {
-	struct page *page;
+	netmem_ref netmem;
 	u16 frags;
 };
 
@@ -638,7 +634,6 @@ struct mlx5e_shampo_hd {
 	struct mlx5e_frag_page *pages;
 	u32 hd_per_wq;
 	u16 hd_per_wqe;
-	u16 pages_per_wq;
 	unsigned long *bitmap;
 	u16 pi;
 	u16 ci;
@@ -721,7 +716,11 @@ struct mlx5e_rq {
 	struct bpf_prog __rcu *xdp_prog;
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
+
+	/* page pools */
 	struct page_pool      *page_pool;
+	struct page_pool      *hd_page_pool;
+
 	struct mlx5e_xdp_buff mxbuf;
 
 	/* AF_XDP zero-copy */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 58ec5e44aa7a..fc945bce933a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -901,6 +901,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 {
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	u32 lro_timeout;
 	int ndsegs = 1;
 	int err;
 
@@ -926,22 +927,25 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 		MLX5_SET(wq, wq, log_wqe_stride_size,
 			 log_wqe_stride_size - MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
 		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(mdev, params, xsk));
-		if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) {
-			MLX5_SET(wq, wq, shampo_enable, true);
-			MLX5_SET(wq, wq, log_reservation_size,
-				 mlx5e_shampo_get_log_rsrv_size(mdev, params));
-			MLX5_SET(wq, wq,
-				 log_max_num_of_packets_per_reservation,
-				 mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
-			MLX5_SET(wq, wq, log_headers_entry_size,
-				 mlx5e_shampo_get_log_hd_entry_size(mdev, params));
-			MLX5_SET(rqc, rqc, reservation_timeout,
-				 mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT));
-			MLX5_SET(rqc, rqc, shampo_match_criteria_type,
-				 params->packet_merge.shampo.match_criteria_type);
-			MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity,
-				 params->packet_merge.shampo.alignment_granularity);
-		}
+		if (params->packet_merge.type != MLX5E_PACKET_MERGE_SHAMPO)
+			break;
+
+		MLX5_SET(wq, wq, shampo_enable, true);
+		MLX5_SET(wq, wq, log_reservation_size,
+			 mlx5e_shampo_get_log_rsrv_size(mdev, params));
+		MLX5_SET(wq, wq,
+			 log_max_num_of_packets_per_reservation,
+			 mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
+		MLX5_SET(wq, wq, log_headers_entry_size,
+			 mlx5e_shampo_get_log_hd_entry_size(mdev, params));
+		lro_timeout =
+			mlx5e_choose_lro_timeout(mdev,
+						 MLX5E_DEFAULT_SHAMPO_TIMEOUT);
+		MLX5_SET(rqc, rqc, reservation_timeout, lro_timeout);
+		MLX5_SET(rqc, rqc, shampo_match_criteria_type,
+			 MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED);
+		MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity,
+			 MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE);
 		break;
 	}
 	default: /* MLX5_WQ_TYPE_CYCLIC */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index e837c21d3d21..6501252359b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -362,7 +362,8 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 		dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
 		break;
 	case MLX5E_DMA_MAP_PAGE:
-		dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
+		netmem_dma_unmap_page_attrs(pdev, dma->addr, dma->size,
+					    DMA_TO_DEVICE, 0);
 		break;
 	default:
 		WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 8b9ee8bac674..35479cbf98d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
 
 #include <linux/dim.h>
 #include <linux/ethtool_netlink.h>
+#include <net/netdev_queues.h>
 
 #include "en.h"
 #include "en/channels.h"
@@ -365,11 +366,6 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
 	param->rx_pending     = 1 << priv->channels.params.log_rq_mtu_frames;
 	param->tx_pending     = 1 << priv->channels.params.log_sq_size;
-
-	kernel_param->tcp_data_split =
-		(priv->channels.params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) ?
-		ETHTOOL_TCP_DATA_SPLIT_ENABLED :
-		ETHTOOL_TCP_DATA_SPLIT_DISABLED;
 }
 
 static void mlx5e_get_ringparam(struct net_device *dev,
@@ -382,6 +378,27 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 	mlx5e_ethtool_get_ringparam(priv, param, kernel_param);
 }
 
+static bool mlx5e_ethtool_set_tcp_data_split(struct mlx5e_priv *priv,
+					     u8 tcp_data_split,
+					     struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = priv->netdev;
+
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
+	    !(dev->features & NETIF_F_GRO_HW)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "TCP-data-split is not supported when GRO HW is disabled");
+		return false;
+	}
+
+	/* Might need to disable HW-GRO if it was kept on due to hds. */
+	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED &&
+	    dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED)
+		netdev_update_features(priv->netdev);
+
+	return true;
+}
+
 int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 				struct ethtool_ringparam *param,
 				struct netlink_ext_ack *extack)
@@ -440,6 +457,11 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
+	if (!mlx5e_ethtool_set_tcp_data_split(priv,
+					      kernel_param->tcp_data_split,
+					      extack))
+		return -EINVAL;
+
 	return mlx5e_ethtool_set_ringparam(priv, param, extack);
 }
 
@@ -2623,6 +2645,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_USE_CQE,
 	.supported_input_xfrm = RXH_XFRM_SYM_OR_XOR,
+	.supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT,
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
 	.get_link_ext_state  = mlx5e_get_link_ext_state,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ea822c69d137..24559cbcbfc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -41,6 +41,7 @@
 #include <linux/filter.h>
 #include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
 #include <net/page_pool/types.h>
 #include <net/pkt_sched.h>
 #include <net/xdp_sock_drv.h>
@@ -78,7 +79,8 @@
 
 static bool mlx5e_hw_gro_supported(struct mlx5_core_dev *mdev)
 {
-	if (!MLX5_CAP_GEN(mdev, shampo))
+	if (!MLX5_CAP_GEN(mdev, shampo) ||
+	    !MLX5_CAP_SHAMPO(mdev, shampo_header_split_data_merge))
 		return false;
 
 	/* Our HW-GRO implementation relies on "KSM Mkey" for
@@ -331,47 +333,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
-static int mlx5e_rq_shampo_hd_alloc(struct mlx5e_rq *rq, int node)
-{
-	rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo),
-					 GFP_KERNEL, node);
-	if (!rq->mpwqe.shampo)
-		return -ENOMEM;
-	return 0;
-}
-
-static void mlx5e_rq_shampo_hd_free(struct mlx5e_rq *rq)
-{
-	kvfree(rq->mpwqe.shampo);
-}
-
-static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node)
-{
-	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
-
-	shampo->bitmap = bitmap_zalloc_node(shampo->hd_per_wq, GFP_KERNEL,
-					    node);
-	shampo->pages = kvzalloc_node(array_size(shampo->hd_per_wq,
-						 sizeof(*shampo->pages)),
-				     GFP_KERNEL, node);
-	if (!shampo->bitmap || !shampo->pages)
-		goto err_nomem;
-
-	return 0;
-
-err_nomem:
-	bitmap_free(shampo->bitmap);
-	kvfree(shampo->pages);
-
-	return -ENOMEM;
-}
-
-static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq)
-{
-	bitmap_free(rq->mpwqe.shampo->bitmap);
-	kvfree(rq->mpwqe.shampo->pages);
-}
-
 static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
@@ -584,19 +545,18 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 }
 
 static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev,
-				       struct mlx5e_rq *rq)
+				       u16 hd_per_wq, u32 *umr_mkey)
 {
 	u32 max_ksm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size));
 
-	if (max_ksm_size < rq->mpwqe.shampo->hd_per_wq) {
+	if (max_ksm_size < hd_per_wq) {
 		mlx5_core_err(mdev, "max ksm list size 0x%x is smaller than shampo header buffer list size 0x%x\n",
-			      max_ksm_size, rq->mpwqe.shampo->hd_per_wq);
+			      max_ksm_size, hd_per_wq);
 		return -EINVAL;
 	}
-
-	return mlx5e_create_umr_ksm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq,
+	return mlx5e_create_umr_ksm_mkey(mdev, hd_per_wq,
 					 MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE,
-					 &rq->mpwqe.shampo->mkey);
+					 umr_mkey);
 }
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
@@ -758,6 +718,42 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 				  xdp_frag_size);
 }
 
+static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, u16 hd_per_wq,
+					 int node)
+{
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+
+	shampo->hd_per_wq = hd_per_wq;
+
+	shampo->bitmap = bitmap_zalloc_node(hd_per_wq, GFP_KERNEL, node);
+	shampo->pages = kvzalloc_node(array_size(hd_per_wq,
+						 sizeof(*shampo->pages)),
+				      GFP_KERNEL, node);
+	if (!shampo->bitmap || !shampo->pages)
+		goto err_nomem;
+
+	return 0;
+
+err_nomem:
+	kvfree(shampo->pages);
+	bitmap_free(shampo->bitmap);
+
+	return -ENOMEM;
+}
+
+static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq)
+{
+	kvfree(rq->mpwqe.shampo->pages);
+	bitmap_free(rq->mpwqe.shampo->bitmap);
+}
+
+static bool mlx5_rq_needs_separate_hd_pool(struct mlx5e_rq *rq)
+{
+	struct netdev_rx_queue *rxq = __netif_get_rx_queue(rq->netdev, rq->ix);
+
+	return !!rxq->mp_params.mp_ops;
+}
+
 static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params,
 				struct mlx5e_rq_param *rqp,
@@ -765,42 +761,81 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,
 				u32 *pool_size,
 				int node)
 {
+	void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq);
+	u32 hd_pool_size;
+	u16 hd_per_wq;
+	int wq_size;
 	int err;
 
 	if (!test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
 		return 0;
-	err = mlx5e_rq_shampo_hd_alloc(rq, node);
-	if (err)
-		goto out;
-	rq->mpwqe.shampo->hd_per_wq =
-		mlx5e_shampo_hd_per_wq(mdev, params, rqp);
-	err = mlx5e_create_rq_hd_umr_mkey(mdev, rq);
+
+	rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo),
+					 GFP_KERNEL, node);
+	if (!rq->mpwqe.shampo)
+		return -ENOMEM;
+
+	/* split headers data structures */
+	hd_per_wq = mlx5e_shampo_hd_per_wq(mdev, params, rqp);
+	err = mlx5e_rq_shampo_hd_info_alloc(rq, hd_per_wq, node);
 	if (err)
-		goto err_shampo_hd;
-	err = mlx5e_rq_shampo_hd_info_alloc(rq, node);
+		goto err_shampo_hd_info_alloc;
+
+	err = mlx5e_create_rq_hd_umr_mkey(mdev, hd_per_wq,
+					  &rq->mpwqe.shampo->mkey);
 	if (err)
-		goto err_shampo_info;
+		goto err_umr_mkey;
+
+	rq->mpwqe.shampo->key = cpu_to_be32(rq->mpwqe.shampo->mkey);
+	rq->mpwqe.shampo->hd_per_wqe =
+		mlx5e_shampo_hd_per_wqe(mdev, params, rqp);
+	wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz));
+	hd_pool_size = (rq->mpwqe.shampo->hd_per_wqe * wq_size) /
+		MLX5E_SHAMPO_WQ_HEADER_PER_PAGE;
+
+	if (mlx5_rq_needs_separate_hd_pool(rq)) {
+		/* Separate page pool for shampo headers */
+		struct page_pool_params pp_params = { };
+
+		pp_params.order     = 0;
+		pp_params.flags     = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+		pp_params.pool_size = hd_pool_size;
+		pp_params.nid       = node;
+		pp_params.dev       = rq->pdev;
+		pp_params.napi      = rq->cq.napi;
+		pp_params.netdev    = rq->netdev;
+		pp_params.dma_dir   = rq->buff.map_dir;
+		pp_params.max_len   = PAGE_SIZE;
+
+		rq->hd_page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rq->hd_page_pool)) {
+			err = PTR_ERR(rq->hd_page_pool);
+			rq->hd_page_pool = NULL;
+			goto err_hds_page_pool;
+		}
+	} else {
+		/* Common page pool, reserve space for headers. */
+		*pool_size += hd_pool_size;
+		rq->hd_page_pool = NULL;
+	}
+
+	/* gro only data structures */
 	rq->hw_gro_data = kvzalloc_node(sizeof(*rq->hw_gro_data), GFP_KERNEL, node);
 	if (!rq->hw_gro_data) {
 		err = -ENOMEM;
 		goto err_hw_gro_data;
 	}
-	rq->mpwqe.shampo->key =
-		cpu_to_be32(rq->mpwqe.shampo->mkey);
-	rq->mpwqe.shampo->hd_per_wqe =
-		mlx5e_shampo_hd_per_wqe(mdev, params, rqp);
-	rq->mpwqe.shampo->pages_per_wq =
-		rq->mpwqe.shampo->hd_per_wq / MLX5E_SHAMPO_WQ_HEADER_PER_PAGE;
-	*pool_size += rq->mpwqe.shampo->pages_per_wq;
+
 	return 0;
 
 err_hw_gro_data:
-	mlx5e_rq_shampo_hd_info_free(rq);
-err_shampo_info:
+	page_pool_destroy(rq->hd_page_pool);
+err_hds_page_pool:
 	mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey);
-err_shampo_hd:
-	mlx5e_rq_shampo_hd_free(rq);
-out:
+err_umr_mkey:
+	mlx5e_rq_shampo_hd_info_free(rq);
+err_shampo_hd_info_alloc:
+	kvfree(rq->mpwqe.shampo);
 	return err;
 }
 
@@ -810,9 +845,11 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq)
 		return;
 
 	kvfree(rq->hw_gro_data);
+	if (rq->hd_page_pool != rq->page_pool)
+		page_pool_destroy(rq->hd_page_pool);
 	mlx5e_rq_shampo_hd_info_free(rq);
 	mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey);
-	mlx5e_rq_shampo_hd_free(rq);
+	kvfree(rq->mpwqe.shampo);
 }
 
 static int mlx5e_alloc_rq(struct mlx5e_params *params,
@@ -929,6 +966,11 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		pp_params.netdev    = rq->netdev;
 		pp_params.dma_dir   = rq->buff.map_dir;
 		pp_params.max_len   = PAGE_SIZE;
+		pp_params.queue_idx = rq->ix;
+
+		/* Shampo header data split allow for unreadable netmem */
+		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
+			pp_params.flags |= PP_FLAG_ALLOW_UNREADABLE_NETMEM;
 
 		/* page_pool can be used even when there is no rq->xdp_prog,
 		 * given page_pool does not handle DMA mapping there is no
@@ -941,6 +983,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			rq->page_pool = NULL;
 			goto err_free_by_rq_type;
 		}
+		if (!rq->hd_page_pool)
+			rq->hd_page_pool = rq->page_pool;
 		if (xdp_rxq_info_is_reg(&rq->xdp_rxq))
 			err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 							 MEM_TYPE_PAGE_POOL, rq->page_pool);
@@ -4043,10 +4087,6 @@ static int set_feature_hw_gro(struct net_device *netdev, bool enable)
 
 	if (enable) {
 		new_params.packet_merge.type = MLX5E_PACKET_MERGE_SHAMPO;
-		new_params.packet_merge.shampo.match_criteria_type =
-			MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED;
-		new_params.packet_merge.shampo.alignment_granularity =
-			MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE;
 	} else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) {
 		new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE;
 	} else {
@@ -4373,6 +4413,7 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev
 static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
+	struct netdev_config *cfg = netdev->cfg_pending;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_vlan_table *vlan;
 	struct mlx5e_params *params;
@@ -4439,6 +4480,13 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 		}
 	}
 
+	/* The header-data split ring param requires HW GRO to stay enabled. */
+	if (cfg && cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
+	    !(features & NETIF_F_GRO_HW)) {
+		netdev_warn(netdev, "Keeping HW-GRO enabled, TCP header-data split depends on it\n");
+		features |= NETIF_F_GRO_HW;
+	}
+
 	if (mlx5e_is_uplink_rep(priv)) {
 		features = mlx5e_fix_uplink_rep_features(netdev, features);
 		netdev->netns_immutable = true;
@@ -5454,6 +5502,103 @@ static const struct netdev_stat_ops mlx5e_stat_ops = {
 	.get_base_stats      = mlx5e_get_base_stats,
 };
 
+struct mlx5_qmgmt_data {
+	struct mlx5e_channel *c;
+	struct mlx5e_channel_param cparam;
+};
+
+static int mlx5e_queue_mem_alloc(struct net_device *dev, void *newq,
+				 int queue_index)
+{
+	struct mlx5_qmgmt_data *new = (struct mlx5_qmgmt_data *)newq;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *chs = &priv->channels;
+	struct mlx5e_params params = chs->params;
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		err = -ENODEV;
+		goto unlock;
+	}
+
+	if (queue_index >= chs->num) {
+		err = -ERANGE;
+		goto unlock;
+	}
+
+	if (MLX5E_GET_PFLAG(&chs->params, MLX5E_PFLAG_TX_PORT_TS) ||
+	    chs->params.ptp_rx   ||
+	    chs->params.xdp_prog ||
+	    priv->htb) {
+		netdev_err(priv->netdev,
+			   "Cloning channels with Port/rx PTP, XDP or HTB is not supported\n");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, queue_index);
+	err = mlx5e_build_channel_param(mdev, &params, &new->cparam);
+	if (err)
+		goto unlock;
+
+	err = mlx5e_open_channel(priv, queue_index, &params, NULL, &new->c);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static void mlx5e_queue_mem_free(struct net_device *dev, void *mem)
+{
+	struct mlx5_qmgmt_data *data = (struct mlx5_qmgmt_data *)mem;
+
+	/* not supposed to happen since mlx5e_queue_start never fails
+	 * but this is how this should be implemented just in case
+	 */
+	if (data->c)
+		mlx5e_close_channel(data->c);
+}
+
+static int mlx5e_queue_stop(struct net_device *dev, void *oldq, int queue_index)
+{
+	/* In mlx5 a txq cannot be simply stopped in isolation, only restarted.
+	 * mlx5e_queue_start does not fail, we stop the old queue there.
+	 * TODO: Improve this.
+	 */
+	return 0;
+}
+
+static int mlx5e_queue_start(struct net_device *dev, void *newq,
+			     int queue_index)
+{
+	struct mlx5_qmgmt_data *new = (struct mlx5_qmgmt_data *)newq;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channel *old;
+
+	mutex_lock(&priv->state_lock);
+
+	/* stop and close the old */
+	old = priv->channels.c[queue_index];
+	mlx5e_deactivate_priv_channels(priv);
+	/* close old before activating new, to avoid napi conflict */
+	mlx5e_close_channel(old);
+
+	/* start the new */
+	priv->channels.c[queue_index] = new->c;
+	mlx5e_activate_priv_channels(priv);
+	mutex_unlock(&priv->state_lock);
+	return 0;
+}
+
+static const struct netdev_queue_mgmt_ops mlx5e_queue_mgmt_ops = {
+	.ndo_queue_mem_size	=	sizeof(struct mlx5_qmgmt_data),
+	.ndo_queue_mem_alloc	=	mlx5e_queue_mem_alloc,
+	.ndo_queue_mem_free	=	mlx5e_queue_mem_free,
+	.ndo_queue_start	=	mlx5e_queue_start,
+	.ndo_queue_stop		=	mlx5e_queue_stop,
+};
+
 static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -5464,6 +5609,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	SET_NETDEV_DEV(netdev, mdev->device);
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
+	netdev->queue_mgmt_ops = &mlx5e_queue_mgmt_ops;
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
 	netdev->request_ops_lock = true;
@@ -5506,17 +5652,17 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
+	if (mlx5e_hw_gro_supported(mdev) &&
+	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT,
+						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
+		netdev->vlan_features |= NETIF_F_GRO_HW;
+
 	netdev->hw_features       = netdev->vlan_features;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5e_hw_gro_supported(mdev) &&
-	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT,
-						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
-		netdev->hw_features    |= NETIF_F_GRO_HW;
-
 	if (mlx5e_tunnel_any_tx_proto_supported(mdev)) {
 		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -5595,6 +5741,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
+	netdev->netmem_tx = true;
+
 	netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
 	mlx5e_set_xdp_feature(netdev);
 	mlx5e_set_netdev_dev_addr(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 84b1ab8233b8..2bb32082bfcc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -273,33 +273,32 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 
 #define MLX5E_PAGECNT_BIAS_MAX (PAGE_SIZE / 64)
 
-static int mlx5e_page_alloc_fragmented(struct mlx5e_rq *rq,
+static int mlx5e_page_alloc_fragmented(struct page_pool *pp,
 				       struct mlx5e_frag_page *frag_page)
 {
-	struct page *page;
+	netmem_ref netmem = page_pool_dev_alloc_netmems(pp);
 
-	page = page_pool_dev_alloc_pages(rq->page_pool);
-	if (unlikely(!page))
+	if (unlikely(!netmem))
 		return -ENOMEM;
 
-	page_pool_fragment_page(page, MLX5E_PAGECNT_BIAS_MAX);
+	page_pool_fragment_netmem(netmem, MLX5E_PAGECNT_BIAS_MAX);
 
 	*frag_page = (struct mlx5e_frag_page) {
-		.page	= page,
+		.netmem	= netmem,
 		.frags	= 0,
 	};
 
 	return 0;
 }
 
-static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq,
+static void mlx5e_page_release_fragmented(struct page_pool *pp,
 					  struct mlx5e_frag_page *frag_page)
 {
 	u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags;
-	struct page *page = frag_page->page;
+	netmem_ref netmem = frag_page->netmem;
 
-	if (page_pool_unref_page(page, drain_count) == 0)
-		page_pool_put_unrefed_page(rq->page_pool, page, -1, true);
+	if (page_pool_unref_netmem(netmem, drain_count) == 0)
+		page_pool_put_unrefed_netmem(pp, netmem, -1, true);
 }
 
 static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
@@ -313,7 +312,8 @@ 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_fragmented(rq, frag->frag_page);
+		err = mlx5e_page_alloc_fragmented(rq->page_pool,
+						  frag->frag_page);
 
 	return err;
 }
@@ -332,7 +332,7 @@ static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
 				     struct mlx5e_wqe_frag_info *frag)
 {
 	if (mlx5e_frag_can_release(frag))
-		mlx5e_page_release_fragmented(rq, frag->frag_page);
+		mlx5e_page_release_fragmented(rq->page_pool, frag->frag_page);
 }
 
 static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -358,7 +358,7 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
 		frag->flags &= ~BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
 
 		headroom = i == 0 ? rq->buff.headroom : 0;
-		addr = page_pool_get_dma_addr(frag->frag_page->page);
+		addr = page_pool_get_dma_addr_netmem(frag->frag_page->netmem);
 		wqe->data[i].addr = cpu_to_be64(addr + frag->offset + headroom);
 	}
 
@@ -499,9 +499,10 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf
 			       struct xdp_buff *xdp, struct mlx5e_frag_page *frag_page,
 			       u32 frag_offset, u32 len)
 {
+	netmem_ref netmem = frag_page->netmem;
 	skb_frag_t *frag;
 
-	dma_addr_t addr = page_pool_get_dma_addr(frag_page->page);
+	dma_addr_t addr = page_pool_get_dma_addr_netmem(netmem);
 
 	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, rq->buff.map_dir);
 	if (!xdp_buff_has_frags(xdp)) {
@@ -514,9 +515,9 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf
 	}
 
 	frag = &sinfo->frags[sinfo->nr_frags++];
-	skb_frag_fill_page_desc(frag, frag_page->page, frag_offset, len);
+	skb_frag_fill_netmem_desc(frag, netmem, frag_offset, len);
 
-	if (page_is_pfmemalloc(frag_page->page))
+	if (netmem_is_pfmemalloc(netmem))
 		xdp_buff_set_frag_pfmemalloc(xdp);
 	sinfo->xdp_frags_size += len;
 }
@@ -527,27 +528,29 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
 		   u32 frag_offset, u32 len,
 		   unsigned int truesize)
 {
-	dma_addr_t addr = page_pool_get_dma_addr(frag_page->page);
+	dma_addr_t addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	u8 next_frag = skb_shinfo(skb)->nr_frags;
+	netmem_ref netmem = frag_page->netmem;
 
 	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len,
 				rq->buff.map_dir);
 
-	if (skb_can_coalesce(skb, next_frag, frag_page->page, frag_offset)) {
+	if (skb_can_coalesce_netmem(skb, next_frag, netmem, frag_offset)) {
 		skb_coalesce_rx_frag(skb, next_frag - 1, len, truesize);
-	} else {
-		frag_page->frags++;
-		skb_add_rx_frag(skb, next_frag, frag_page->page,
-				frag_offset, len, truesize);
+		return;
 	}
+
+	frag_page->frags++;
+	skb_add_rx_frag_netmem(skb, next_frag, netmem,
+			       frag_offset, len, truesize);
 }
 
 static inline void
 mlx5e_copy_skb_header(struct mlx5e_rq *rq, struct sk_buff *skb,
-		      struct page *page, dma_addr_t addr,
+		      netmem_ref netmem, dma_addr_t addr,
 		      int offset_from, int dma_offset, u32 headlen)
 {
-	const void *from = page_address(page) + offset_from;
+	const void *from = netmem_address(netmem) + offset_from;
 	/* Aligning len to sizeof(long) optimizes memcpy performance */
 	unsigned int len = ALIGN(headlen, sizeof(long));
 
@@ -584,7 +587,8 @@ mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 				struct mlx5e_frag_page *frag_page;
 
 				frag_page = &wi->alloc_units.frag_pages[i];
-				mlx5e_page_release_fragmented(rq, frag_page);
+				mlx5e_page_release_fragmented(rq->page_pool,
+							      frag_page);
 			}
 		}
 	}
@@ -679,12 +683,11 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
 		u64 addr;
 
-		err = mlx5e_page_alloc_fragmented(rq, frag_page);
+		err = mlx5e_page_alloc_fragmented(rq->hd_page_pool, frag_page);
 		if (unlikely(err))
 			goto err_unmap;
 
-
-		addr = page_pool_get_dma_addr(frag_page->page);
+		addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 
 		for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) {
 			header_offset = mlx5e_shampo_hd_offset(index++);
@@ -715,7 +718,8 @@ err_unmap:
 		if (!header_offset) {
 			struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
 
-			mlx5e_page_release_fragmented(rq, frag_page);
+			mlx5e_page_release_fragmented(rq->hd_page_pool,
+						      frag_page);
 		}
 	}
 
@@ -791,10 +795,11 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, frag_page++) {
 		dma_addr_t addr;
 
-		err = mlx5e_page_alloc_fragmented(rq, frag_page);
+		err = mlx5e_page_alloc_fragmented(rq->page_pool, frag_page);
 		if (unlikely(err))
 			goto err_unmap;
-		addr = page_pool_get_dma_addr(frag_page->page);
+
+		addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 		umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
 			.ptag = cpu_to_be64(addr | MLX5_EN_WR),
 		};
@@ -836,7 +841,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 err_unmap:
 	while (--i >= 0) {
 		frag_page--;
-		mlx5e_page_release_fragmented(rq, frag_page);
+		mlx5e_page_release_fragmented(rq->page_pool, frag_page);
 	}
 
 	bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
@@ -855,7 +860,7 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
 	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {
 		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);
 
-		mlx5e_page_release_fragmented(rq, frag_page);
+		mlx5e_page_release_fragmented(rq->hd_page_pool, frag_page);
 	}
 	clear_bit(header_index, shampo->bitmap);
 }
@@ -1100,6 +1105,8 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 
 	if (rq->page_pool)
 		page_pool_nid_changed(rq->page_pool, numa_mem_id());
+	if (rq->hd_page_pool)
+		page_pool_nid_changed(rq->hd_page_pool, numa_mem_id());
 
 	head = rq->mpwqe.actual_wq_head;
 	i = missing;
@@ -1212,7 +1219,7 @@ static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index)
 	struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);
 	u16 head_offset = mlx5e_shampo_hd_offset(header_index) + rq->buff.headroom;
 
-	return page_address(frag_page->page) + head_offset;
+	return netmem_address(frag_page->netmem) + head_offset;
 }
 
 static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4)
@@ -1673,11 +1680,11 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 	dma_addr_t addr;
 	u32 frag_size;
 
-	va             = page_address(frag_page->page) + wi->offset;
+	va             = netmem_address(frag_page->netmem) + wi->offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 
-	addr = page_pool_get_dma_addr(frag_page->page);
+	addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset,
 				      frag_size, rq->buff.map_dir);
 	net_prefetch(data);
@@ -1727,10 +1734,10 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	frag_page = wi->frag_page;
 
-	va = page_address(frag_page->page) + wi->offset;
+	va = netmem_address(frag_page->netmem) + wi->offset;
 	frag_consumed_bytes = min_t(u32, frag_info->frag_size, cqe_bcnt);
 
-	addr = page_pool_get_dma_addr(frag_page->page);
+	addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset,
 				      rq->buff.frame0_sz, rq->buff.map_dir);
 	net_prefetchw(va); /* xdp_frame data area */
@@ -2003,12 +2010,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 	if (prog) {
 		/* area for bpf_xdp_[store|load]_bytes */
-		net_prefetchw(page_address(frag_page->page) + frag_offset);
-		if (unlikely(mlx5e_page_alloc_fragmented(rq, &wi->linear_page))) {
+		net_prefetchw(netmem_address(frag_page->netmem) + frag_offset);
+		if (unlikely(mlx5e_page_alloc_fragmented(rq->page_pool,
+							 &wi->linear_page))) {
 			rq->stats->buff_alloc_err++;
 			return NULL;
 		}
-		va = page_address(wi->linear_page.page);
+
+		va = netmem_address(wi->linear_page.netmem);
 		net_prefetchw(va); /* xdp_frame data area */
 		linear_hr = XDP_PACKET_HEADROOM;
 		linear_data_len = 0;
@@ -2068,7 +2077,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 				wi->linear_page.frags++;
 			}
-			mlx5e_page_release_fragmented(rq, &wi->linear_page);
+			mlx5e_page_release_fragmented(rq->page_pool,
+						      &wi->linear_page);
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
@@ -2077,13 +2087,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0,
 			mxbuf->xdp.data - mxbuf->xdp.data_meta);
 		if (unlikely(!skb)) {
-			mlx5e_page_release_fragmented(rq, &wi->linear_page);
+			mlx5e_page_release_fragmented(rq->page_pool,
+						      &wi->linear_page);
 			return NULL;
 		}
 
 		skb_mark_for_recycle(skb);
 		wi->linear_page.frags++;
-		mlx5e_page_release_fragmented(rq, &wi->linear_page);
+		mlx5e_page_release_fragmented(rq->page_pool, &wi->linear_page);
 
 		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
@@ -2117,8 +2128,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			while (++pagep < frag_page);
 		}
 		/* copy header */
-		addr = page_pool_get_dma_addr(head_page->page);
-		mlx5e_copy_skb_header(rq, skb, head_page->page, addr,
+		addr = page_pool_get_dma_addr_netmem(head_page->netmem);
+		mlx5e_copy_skb_header(rq, skb, head_page->netmem, addr,
 				      head_offset, head_offset, headlen);
 		/* skb linear part was allocated with headlen and aligned to long */
 		skb->tail += headlen;
@@ -2148,11 +2159,11 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		return NULL;
 	}
 
-	va             = page_address(frag_page->page) + head_offset;
+	va             = netmem_address(frag_page->netmem) + head_offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 
-	addr = page_pool_get_dma_addr(frag_page->page);
+	addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, head_offset,
 				      frag_size, rq->buff.map_dir);
 	net_prefetch(data);
@@ -2191,16 +2202,19 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 			  struct mlx5_cqe64 *cqe, u16 header_index)
 {
 	struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);
-	dma_addr_t page_dma_addr = page_pool_get_dma_addr(frag_page->page);
 	u16 head_offset = mlx5e_shampo_hd_offset(header_index);
-	dma_addr_t dma_addr = page_dma_addr + head_offset;
 	u16 head_size = cqe->shampo.header_size;
 	u16 rx_headroom = rq->buff.headroom;
 	struct sk_buff *skb = NULL;
+	dma_addr_t page_dma_addr;
+	dma_addr_t dma_addr;
 	void *hdr, *data;
 	u32 frag_size;
 
-	hdr		= page_address(frag_page->page) + head_offset;
+	page_dma_addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
+	dma_addr = page_dma_addr + head_offset;
+
+	hdr		= netmem_address(frag_page->netmem) + head_offset;
 	data		= hdr + rx_headroom;
 	frag_size	= MLX5_SKB_FRAG_SZ(rx_headroom + head_size);
 
@@ -2225,7 +2239,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		}
 
 		net_prefetchw(skb->data);
-		mlx5e_copy_skb_header(rq, skb, frag_page->page, dma_addr,
+		mlx5e_copy_skb_header(rq, skb, frag_page->netmem, dma_addr,
 				      head_offset + rx_headroom,
 				      rx_headroom, head_size);
 		/* skb linear part was allocated with headlen and aligned to long */
@@ -2319,11 +2333,23 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	}
 
 	if (!*skb) {
-		if (likely(head_size))
+		if (likely(head_size)) {
 			*skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
-		else
-			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe, cqe_bcnt,
-								  data_offset, page_idx);
+		} else {
+			struct mlx5e_frag_page *frag_page;
+
+			frag_page = &wi->alloc_units.frag_pages[page_idx];
+			/* Drop packets with header in unreadable data area to
+			 * prevent the kernel from touching it.
+			 */
+			if (unlikely(netmem_is_net_iov(frag_page->netmem)))
+				goto free_hd_entry;
+			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe,
+								  cqe_bcnt,
+								  data_offset,
+								  page_idx);
+		}
+
 		if (unlikely(!*skb))
 			goto free_hd_entry;
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5520524c93bf..9508968cb300 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3873,20 +3873,26 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i)
 	__must_check;
 
-static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
-				    const struct page *page, int off)
+static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i,
+					   netmem_ref netmem, int off)
 {
 	if (skb_zcopy(skb))
 		return false;
 	if (i) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
-		return page == skb_frag_page(frag) &&
+		return netmem == skb_frag_netmem(frag) &&
 		       off == skb_frag_off(frag) + skb_frag_size(frag);
 	}
 	return false;
 }
 
+static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
+				    const struct page *page, int off)
+{
+	return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off);
+}
+
 static inline int __skb_linearize(struct sk_buff *skb)
 {
 	return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM;
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 850869b45b45..7a1dafa3f080 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -139,7 +139,7 @@ static inline netmem_ref net_iov_to_netmem(struct net_iov *niov)
 	return (__force netmem_ref)((unsigned long)niov | NET_IOV);
 }
 
-static inline netmem_ref page_to_netmem(struct page *page)
+static inline netmem_ref page_to_netmem(const struct page *page)
 {
 	return (__force netmem_ref)page;
 }
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 93f2c31baf9b..773fc65780b5 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -153,6 +153,13 @@ static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool,
 	return page_pool_alloc_netmem(pool, offset, size, gfp);
 }
 
+static inline netmem_ref page_pool_dev_alloc_netmems(struct page_pool *pool)
+{
+	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+
+	return page_pool_alloc_netmems(pool, gfp);
+}
+
 static inline struct page *page_pool_alloc(struct page_pool *pool,
 					   unsigned int *offset,
 					   unsigned int *size, gfp_t gfp)