diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 1c19bb7705df..7b3392553fd6 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -10,7 +10,7 @@ Type                                Name                        fastpath_tx_acce
 =================================== =========================== =================== =================== ===================================================================================
 unsigned_long:32                    priv_flags                  read_mostly                             __dev_queue_xmit(tx)
 unsigned_long:1                     lltx                        read_mostly                             HARD_TX_LOCK,HARD_TX_TRYLOCK,HARD_TX_UNLOCK(tx)
-unsigned long:1                     netmem_tx:1;                read_mostly
+unsigned_long:2                     netmem_tx:2;                read_mostly
 char                                name[16]
 struct netdev_name_node*            name_node
 struct dev_ifalias*                 ifalias
diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst
index b63aded46337..217869d1108d 100644
--- a/Documentation/networking/netmem.rst
+++ b/Documentation/networking/netmem.rst
@@ -95,4 +95,10 @@ Driver TX Requirements
    netdev@, or reach out to the maintainers and/or almasrymina@google.com for
    help adding the netmem API.
 
-2. Driver should declare support by setting `netdev->netmem_tx = true`
+2. Driver should declare support by setting `netdev->netmem_tx` to the
+   appropriate mode:
+
+   - `NETMEM_TX_DMA`: for physical devices that perform DMA.
+
+   - `NETMEM_TX_NO_DMA`: for virtual or passthrough devices that do
+     not DMA, but still support handling of netmem-backed skbs.
diff --git a/Documentation/translations/zh_CN/networking/netmem.rst b/Documentation/translations/zh_CN/networking/netmem.rst
index fe351a240f02..320f3eacf51b 100644
--- a/Documentation/translations/zh_CN/networking/netmem.rst
+++ b/Documentation/translations/zh_CN/networking/netmem.rst
@@ -89,4 +89,9 @@ dma-mapping API 去处理。
 使用某个还不存在的 netmem API，你可以自行添加并提交到 netdev@，也可以联系维护
 人员或者发送邮件至 almasrymina@google.com 寻求帮助。
 
-2. 驱动程序应通过设置 netdev->netmem_tx = true 来表明自身支持 netmem 功能。
+2. 驱动程序应将 `netdev->netmem_tx` 设置为适当的模式：
+
+   - `NETMEM_TX_DMA`：适用于执行 DMA 的物理设备。
+
+   - `NETMEM_TX_NO_DMA`：适用于不执行 DMA 的虚拟或透传设备，但仍支持
+     处理 netmem 支持的 skb。
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 945a86696f2f..d4f93e62f583 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -17123,7 +17123,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops_unsupp;
 	if (BNXT_SUPPORTS_QUEUE_API(bp))
 		dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
-	dev->netmem_tx = true;
+	dev->netmem_tx = NETMEM_TX_DMA;
 
 	rc = register_netdev(dev);
 	if (rc)
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 00750643e614..e4d78ae52daf 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -2894,7 +2894,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto abort_with_wq;
 
 	if (!gve_is_gqi(priv) && !gve_is_qpl(priv))
-		dev->netmem_tx = true;
+		dev->netmem_tx = NETMEM_TX_DMA;
 
 	err = register_netdev(dev);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a904e468c197..c5d26c6829a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5963,7 +5963,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
-	netdev->netmem_tx = true;
+	netdev->netmem_tx = NETMEM_TX_DMA;
 
 	netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
 	mlx5e_set_xdp_feature(priv);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 4dea2bb58d2f..f99ca551c1ce 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -752,7 +752,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	netdev->netdev_ops = &fbnic_netdev_ops;
 	netdev->stat_ops = &fbnic_stat_ops;
 	netdev->queue_mgmt_ops = &fbnic_queue_mgmt_ops;
-	netdev->netmem_tx = true;
+	netdev->netmem_tx = NETMEM_TX_DMA;
 
 	fbnic_set_ethtool_ops(netdev);
 
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 5e2eecc3165d..0ad6a806d7d5 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -466,6 +466,7 @@ static void netkit_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->priv_flags |= IFF_DISABLE_NETPOLL;
 	dev->lltx = true;
+	dev->netmem_tx = NETMEM_TX_NO_DMA;
 
 	dev->netdev_ops     = &netkit_netdev_ops;
 	dev->ethtool_ops    = &netkit_ethtool_ops;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e7af71491a47..bf3dd9b2c1a7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1794,6 +1794,12 @@ enum netdev_stat_type {
 	NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */
 };
 
+enum netmem_tx_mode {
+	NETMEM_TX_NONE,		/* no netmem TX support */
+	NETMEM_TX_DMA,		/* DMA-capable netmem TX (real HW) */
+	NETMEM_TX_NO_DMA,	/* no DMA, e.g. passthrough for virtual devs */
+};
+
 enum netdev_reg_state {
 	NETREG_UNINITIALIZED = 0,
 	NETREG_REGISTERED,	/* completed register_netdevice */
@@ -1815,7 +1821,7 @@ enum netdev_reg_state {
  *	@lltx:		device supports lockless Tx. Deprecated for real HW
  *			drivers. Mainly used by logical interfaces, such as
  *			bonding and tunnels
- *	@netmem_tx:	device support netmem_tx.
+ *	@netmem_tx:	device netmem TX mode
  *
  *	@name:	This is the first field of the "visible" part of this structure
  *		(i.e. as seen by users in the "Space.c" file).  It is the name
@@ -2138,7 +2144,7 @@ struct net_device {
 	struct_group(priv_flags_fast,
 		unsigned long		priv_flags:32;
 		unsigned long		lltx:1;
-		unsigned long		netmem_tx:1;
+		unsigned long		netmem_tx:2;
 	);
 	const struct net_device_ops *netdev_ops;
 	const struct header_ops *header_ops;
diff --git a/net/core/dev.c b/net/core/dev.c
index 267cf3854395..26ac8eb9b259 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3993,10 +3993,11 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb,
 	struct skb_shared_info *shinfo;
 	struct net_iov *niov;
 
-	if (likely(skb_frags_readable(skb)))
+	if (likely(skb_frags_readable(skb) ||
+		   dev->netmem_tx == NETMEM_TX_NO_DMA))
 		goto out;
 
-	if (!dev->netmem_tx)
+	if (dev->netmem_tx == NETMEM_TX_NONE)
 		goto out_free;
 
 	shinfo = skb_shinfo(skb);
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 468344739db2..893643909f6a 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -181,7 +181,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 }
 
 struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev,
+net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		       struct device *dma_dev,
 		       enum dma_data_direction direction,
 		       unsigned int dmabuf_fd, struct netdev_nl_sock *priv,
@@ -212,6 +212,7 @@ net_devmem_bind_dmabuf(struct net_device *dev,
 	}
 
 	binding->dev = dev;
+	binding->vdev = vdev;
 	xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC);
 
 	err = percpu_ref_init(&binding->ref,
@@ -396,7 +397,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
 	 */
 	dst_dev = dst_dev_rcu(dst);
 	if (unlikely(!dst_dev) ||
-	    unlikely(dst_dev != READ_ONCE(binding->dev))) {
+	    unlikely(dst_dev != READ_ONCE(binding->dev) &&
+		     dst_dev != READ_ONCE(binding->vdev))) {
 		err = -ENODEV;
 		goto out_unlock;
 	}
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 1c5c18581fcb..3852a56036cb 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -19,7 +19,13 @@ struct net_devmem_dmabuf_binding {
 	struct dma_buf *dmabuf;
 	struct dma_buf_attachment *attachment;
 	struct sg_table *sgt;
+	/* Physical NIC that does the actual DMA for this binding. */
 	struct net_device *dev;
+	/* Opaque cookie identifying the virtual device (e.g. netkit) the user
+	 * called bind-tx on. Used only for pointer comparison. Never
+	 * dereferenced.
+	 */
+	void *vdev;
 	struct gen_pool *chunk_pool;
 	/* Protect dev */
 	struct mutex lock;
@@ -84,7 +90,7 @@ struct dmabuf_genpool_chunk_owner {
 
 void __net_devmem_dmabuf_binding_free(struct work_struct *wq);
 struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev,
+net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		       struct device *dma_dev,
 		       enum dma_data_direction direction,
 		       unsigned int dmabuf_fd, struct netdev_nl_sock *priv,
@@ -165,7 +171,7 @@ static inline void net_devmem_put_net_iov(struct net_iov *niov)
 }
 
 static inline struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev,
+net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		       struct device *dma_dev,
 		       enum dma_data_direction direction,
 		       unsigned int dmabuf_fd,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index b8f6076d8007..b4d48f3672a5 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -1077,7 +1077,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_rxq_bitmap;
 	}
 
-	binding = net_devmem_bind_dmabuf(netdev, dma_dev, DMA_FROM_DEVICE,
+	binding = net_devmem_bind_dmabuf(netdev, NULL, dma_dev, DMA_FROM_DEVICE,
 					 dmabuf_fd, priv, info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
@@ -1119,9 +1119,43 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+/* Find the DMA-capable device for a netmem TX binding.
+ *
+ * For NETMEM_TX_DMA devices, return the device itself.
+ * For NETMEM_TX_NO_DMA devices, walk leased RX queues to find the underlying
+ * physical device and return it.
+ */
+static struct net_device *
+netdev_find_netmem_tx_dev(struct net_device *dev)
+{
+	struct netdev_rx_queue *lease_rxq;
+	struct net_device *phys_dev;
+	int i;
+
+	if (dev->netmem_tx == NETMEM_TX_DMA)
+		return dev;
+
+	if (dev->netmem_tx != NETMEM_TX_NO_DMA)
+		return NULL;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		lease_rxq = READ_ONCE(__netif_get_rx_queue(dev, i)->lease);
+		if (!lease_rxq)
+			continue;
+
+		phys_dev = lease_rxq->dev;
+		if (netif_device_present(phys_dev) &&
+		    phys_dev->netmem_tx == NETMEM_TX_DMA)
+			return phys_dev;
+	}
+
+	return NULL;
+}
+
 int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net_devmem_dmabuf_binding *binding;
+	struct net_device *bind_dev;
 	struct netdev_nl_sock *priv;
 	struct net_device *netdev;
 	struct device *dma_dev;
@@ -1164,29 +1198,48 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock_netdev;
 	}
 
-	if (!netdev->netmem_tx) {
+	if (netdev->netmem_tx == NETMEM_TX_NONE) {
 		err = -EOPNOTSUPP;
 		NL_SET_ERR_MSG(info->extack,
 			       "Driver does not support netmem TX");
 		goto err_unlock_netdev;
 	}
 
-	dma_dev = netdev_queue_get_dma_dev(netdev, 0, NETDEV_QUEUE_TYPE_TX);
-	binding = net_devmem_bind_dmabuf(netdev, dma_dev, DMA_TO_DEVICE,
-					 dmabuf_fd, priv, info->extack);
+	bind_dev = netdev_find_netmem_tx_dev(netdev);
+	if (!bind_dev) {
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG(info->extack,
+			       "No DMA-capable device found for netmem TX");
+		goto err_unlock_netdev;
+	}
+
+	if (bind_dev != netdev)
+		netdev_lock(bind_dev);
+
+	dma_dev = netdev_queue_get_dma_dev(bind_dev, 0, NETDEV_QUEUE_TYPE_TX);
+
+	binding = net_devmem_bind_dmabuf(bind_dev,
+					 bind_dev != netdev ? netdev : NULL,
+					 dma_dev, DMA_TO_DEVICE, dmabuf_fd,
+					 priv, info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
-		goto err_unlock_netdev;
+		goto err_unlock_bind_dev;
 	}
 
 	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
 	genlmsg_end(rsp, hdr);
 
+	if (bind_dev != netdev)
+		netdev_unlock(bind_dev);
 	netdev_unlock(netdev);
 	mutex_unlock(&priv->lock);
 
 	return genlmsg_reply(rsp, info);
 
+err_unlock_bind_dev:
+	if (bind_dev != netdev)
+		netdev_unlock(bind_dev);
 err_unlock_netdev:
 	netdev_unlock(netdev);
 err_unlock_sock:
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 82809d5b2478..c7a1206880ea 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -35,6 +35,7 @@ TEST_PROGS = \
 	irq.py \
 	loopback.sh \
 	nic_timestamp.py \
+	nk_devmem.py \
 	nk_netns.py \
 	nk_qlease.py \
 	ntuple.py \
@@ -52,6 +53,7 @@ TEST_PROGS = \
 	#
 
 TEST_FILES := \
+	devmem_lib.py \
 	ethtool_lib.sh \
 	#
 
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
index ee863e90d1e0..031cf9905f65 100755
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -2,91 +2,40 @@
 # SPDX-License-Identifier: GPL-2.0
 
 from os import path
-from lib.py import ksft_run, ksft_exit
-from lib.py import ksft_eq, KsftSkipEx
+from devmem_lib import setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds
+from lib.py import ksft_run, ksft_exit, ksft_disruptive
 from lib.py import NetDrvEpEnv
-from lib.py import bkg, cmd, rand_port, wait_port_listen
-from lib.py import ksft_disruptive
-
-
-def require_devmem(cfg):
-    if not hasattr(cfg, "_devmem_probed"):
-        probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
-        cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
-        cfg._devmem_probed = True
-
-    if not cfg._devmem_supported:
-        raise KsftSkipEx("Test requires devmem support")
 
 
 @ksft_disruptive
 def check_rx(cfg) -> None:
-    require_devmem(cfg)
-
-    port = rand_port()
-    socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}"
-    listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7"
-
-    with bkg(listen_cmd, exit_wait=True) as ncdevmem:
-        wait_port_listen(port)
-        cmd(f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | \
-            head -c 1K | {socat}", host=cfg.remote, shell=True)
-
-    ksft_eq(ncdevmem.ret, 0)
+    """Run the devmem RX test."""
+    run_rx(cfg)
 
 
 @ksft_disruptive
 def check_tx(cfg) -> None:
-    require_devmem(cfg)
-
-    port = rand_port()
-    listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
-
-    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
-        wait_port_listen(port, host=cfg.remote)
-        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port}", shell=True)
-
-    ksft_eq(socat.stdout.strip(), "hello\nworld")
+    """Run the devmem TX test."""
+    run_tx(cfg)
 
 
 @ksft_disruptive
 def check_tx_chunks(cfg) -> None:
-    require_devmem(cfg)
-
-    port = rand_port()
-    listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
-
-    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
-        wait_port_listen(port, host=cfg.remote)
-        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port} -z 3", shell=True)
-
-    ksft_eq(socat.stdout.strip(), "hello\nworld")
+    """Run the devmem TX chunking test."""
+    run_tx_chunks(cfg)
 
 
 def check_rx_hds(cfg) -> None:
-    """Test HDS splitting across payload sizes."""
-    require_devmem(cfg)
-
-    for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]:
-        port = rand_port()
-        listen_cmd = f"{cfg.bin_local} -L -l -f {cfg.ifname} -s {cfg.addr} -p {port}"
-
-        with bkg(listen_cmd, exit_wait=True) as ncdevmem:
-            wait_port_listen(port)
-            cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | " +
-                f"socat -b {size} -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},nodelay",
-                host=cfg.remote, shell=True)
-
-        ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}")
+    """Run the HDS test."""
+    run_rx_hds(cfg)
 
 
 def main() -> None:
+    """Run the devmem test cases."""
     with NetDrvEpEnv(__file__) as cfg:
-        cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem")
-        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
-
+        setup_test(cfg, path.abspath(path.dirname(__file__) + "/ncdevmem"))
         ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds],
-                 args=(cfg, ))
+                 args=(cfg,))
     ksft_exit()
 
 
diff --git a/tools/testing/selftests/drivers/net/hw/devmem_lib.py b/tools/testing/selftests/drivers/net/hw/devmem_lib.py
new file mode 100644
index 000000000000..0921ff03eb81
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/devmem_lib.py
@@ -0,0 +1,222 @@
+# SPDX-License-Identifier: GPL-2.0
+"""Shared helpers for devmem TCP selftests."""
+
+import re
+
+from lib.py import (bkg, cmd, defer, ethtool, rand_port, wait_port_listen,
+                    ksft_eq, KsftSkipEx, NetNSEnter, EthtoolFamily,
+                    NetdevFamily)
+
+
+def require_devmem(cfg):
+    """Probe ncdevmem on cfg.ifname and SKIP the test if devmem isn't supported."""
+    if not hasattr(cfg, "devmem_probed"):
+        probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
+        cfg.devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
+        cfg.devmem_probed = True
+
+    if not cfg.devmem_supported:
+        raise KsftSkipEx("Test requires devmem support")
+
+
+def configure_nic(cfg):
+    """Channels, rings, RSS, queue lease for netkit devmem."""
+    if not hasattr(cfg, 'netns'):
+        return
+
+    cfg.require_ipver('6')
+    ethnl = EthtoolFamily()
+
+    channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    channels = channels['combined-count']
+    if channels < 2:
+        raise KsftSkipEx(
+            'Test requires NETIF with at least 2 combined channels'
+        )
+
+    rings = ethnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    orig_rx_rings = rings['rx']
+    orig_hds_thresh = rings.get('hds-thresh', 0)
+    orig_data_split = rings.get('tcp-data-split', 'unknown')
+
+    ethnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled',
+                     'hds-thresh': 0,
+                     'rx': min(64, orig_rx_rings)})
+    defer(ethnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': orig_data_split,
+                            'hds-thresh': orig_hds_thresh,
+                            'rx': orig_rx_rings})
+
+    cfg.src_queue = channels - 1
+    ethtool(f"-X {cfg.ifname} equal {cfg.src_queue}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    if not hasattr(cfg, 'nk_queue'):
+        with NetNSEnter(str(cfg.netns)):
+            netdevnl = NetdevFamily()
+            lease_result = netdevnl.queue_create({
+                "ifindex": cfg.nk_guest_ifindex,
+                "type": "rx",
+                "lease": {
+                    "ifindex": cfg.ifindex,
+                    "queue": {"id": cfg.src_queue, "type": "rx"},
+                    "netns-id": 0,
+                },
+            })
+            cfg.nk_queue = lease_result['id']
+
+
+def set_flow_rule(cfg, port):
+    """Install a flow rule steering to src_queue and return the flow rule ID."""
+    output = ethtool(
+        f"-N {cfg.ifname} flow-type tcp6 dst-port {port}"
+        f" action {cfg.src_queue}"
+    ).stdout
+    return int(re.search(r'ID (\d+)', output).group(1))
+
+
+def ncdevmem_rx(cfg, port, verify=True, fail_on_linear=False, flow_steer=False):
+    """Build the ncdevmem RX listener command."""
+    if hasattr(cfg, 'netns'):
+        flow_rule_id = set_flow_rule(cfg, port)
+        defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+        ifname = cfg.nk_guest_ifname
+        addr = cfg.nk_guest_ipv6
+        extras = [f"-t {cfg.nk_queue}", "-q 1", "-n"]
+    else:
+        ifname = cfg.ifname
+        addr = cfg.addr
+        extras = []
+        if flow_steer:
+            extras.append(f"-c {cfg.remote_addr}")
+
+    if verify:
+        extras.append("-v 7")
+    if fail_on_linear:
+        extras.append("-L")
+
+    parts = [cfg.bin_local, "-l", f"-f {ifname}", f"-s {addr}",
+             f"-p {port}", *extras]
+    return " ".join(parts)
+
+
+def ncdevmem_tx(cfg, port, chunk_size=0):
+    """Build the ncdevmem TX send command."""
+    if hasattr(cfg, 'netns'):
+        ifname = cfg.nk_guest_ifname
+        addr = cfg.remote_addr_v['6']
+        extras = ["-t 0", "-q 1", "-n"]
+    else:
+        ifname = cfg.ifname
+        addr = cfg.remote_addr
+        extras = []
+
+    if chunk_size:
+        extras.append(f"-z {chunk_size}")
+
+    parts = [cfg.bin_local, f"-f {ifname}", f"-s {addr}",
+             f"-p {port}", *extras]
+    return " ".join(parts)
+
+
+def socat_send(cfg, port, buf_size=0):
+    """Socat command for sending to the devmem listener.
+
+    When buf_size > 0, force one TCP segment per write of exactly that size by
+    setting socat's buffer (-b) and disabling Nagle (TCP_NODELAY).
+    """
+    proto = f"TCP{cfg.addr_ipver}"
+
+    if hasattr(cfg, 'netns'):
+        addr = f"[{cfg.nk_guest_ipv6}]"
+    else:
+        addr = cfg.baddr
+
+    suffix = f",bind={cfg.remote_baddr}:{port}"
+
+    buf = ""
+    if buf_size:
+        buf = f"-b {buf_size}"
+        suffix += ",nodelay"
+
+    return f"socat {buf} -u - {proto}:{addr}:{port}{suffix}"
+
+
+def socat_listen(cfg, port):
+    """Socat listen command for TX tests."""
+    return f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
+
+
+def setup_test(cfg, bin_local):
+    """Stash the local ncdevmem path on cfg and deploy it to the remote."""
+    cfg.bin_local = bin_local
+    cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+
+def run_rx(cfg):
+    """Run the devmem RX test."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    port = rand_port()
+    socat = socat_send(cfg, port)
+    data_pipe = (f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | head -c 1K"
+                 f" | {socat}")
+    netns = getattr(cfg, "netns", None)
+
+    listen_cmd = ncdevmem_rx(cfg, port, flow_steer=not hasattr(cfg, 'netns'))
+    with bkg(listen_cmd, exit_wait=True, ns=netns) as ncdevmem:
+        wait_port_listen(port, proto="tcp", ns=netns)
+        cmd(data_pipe, host=cfg.remote, shell=True)
+    ksft_eq(ncdevmem.ret, 0)
+
+
+def run_tx(cfg):
+    """Run the devmem TX test."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+    port = rand_port()
+    tx_cmd = ncdevmem_tx(cfg, port)
+    listen_cmd = socat_listen(cfg, port)
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+        wait_port_listen(port, host=cfg.remote)
+        cmd(f"bash -c 'echo -e \"hello\\nworld\" | {tx_cmd}'", ns=netns, shell=True)
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+def run_tx_chunks(cfg):
+    """Run the devmem TX chunking test."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+    port = rand_port()
+    tx_cmd = ncdevmem_tx(cfg, port, chunk_size=3)
+    listen_cmd = socat_listen(cfg, port)
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+        wait_port_listen(port, host=cfg.remote)
+        cmd(f"bash -c 'echo -e \"hello\\nworld\" | {tx_cmd}'", ns=netns, shell=True)
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+def run_rx_hds(cfg):
+    """Run the HDS test by running devmem RX across a segment size sweep."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+
+    for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]:
+        port = rand_port()
+
+        listen_cmd = ncdevmem_rx(cfg, port, verify=False,
+                                 fail_on_linear=True)
+        socat = socat_send(cfg, port, buf_size=size)
+
+        with bkg(listen_cmd, exit_wait=True, ns=netns) as ncdevmem:
+            wait_port_listen(port, proto="tcp", ns=netns)
+            cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | "
+                f"{socat}", host=cfg.remote, shell=True)
+        ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}")
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index e098d6534c3c..d96e8a3b5a65 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -93,6 +93,7 @@ static char *port;
 static size_t do_validation;
 static int start_queue = -1;
 static int num_queues = -1;
+static int skip_config;
 static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
@@ -828,7 +829,7 @@ static struct netdev_queue_id *create_queues(void)
 
 static int do_server(struct memory_buffer *mem)
 {
-	struct ethtool_rings_get_rsp *ring_config;
+	struct ethtool_rings_get_rsp *ring_config = NULL;
 	char ctrl_data[sizeof(int) * 20000];
 	size_t non_page_aligned_frags = 0;
 	struct sockaddr_in6 client_addr;
@@ -851,27 +852,29 @@ static int do_server(struct memory_buffer *mem)
 		return -1;
 	}
 
-	ring_config = get_ring_config();
-	if (!ring_config) {
-		pr_err("Failed to get current ring configuration");
-		return -1;
-	}
+	if (!skip_config) {
+		ring_config = get_ring_config();
+		if (!ring_config) {
+			pr_err("Failed to get current ring configuration");
+			return -1;
+		}
 
-	if (configure_headersplit(ring_config, 1)) {
-		pr_err("Failed to enable TCP header split");
-		goto err_free_ring_config;
-	}
+		if (configure_headersplit(ring_config, 1)) {
+			pr_err("Failed to enable TCP header split");
+			goto err_free_ring_config;
+		}
 
-	/* Configure RSS to divert all traffic from our devmem queues */
-	if (configure_rss()) {
-		pr_err("Failed to configure rss");
-		goto err_reset_headersplit;
-	}
+		/* Configure RSS to divert all traffic from our devmem queues */
+		if (configure_rss()) {
+			pr_err("Failed to configure rss");
+			goto err_reset_headersplit;
+		}
 
-	/* Flow steer our devmem flows to start_queue */
-	if (configure_flow_steering(&server_sin)) {
-		pr_err("Failed to configure flow steering");
-		goto err_reset_rss;
+		/* Flow steer our devmem flows to start_queue */
+		if (configure_flow_steering(&server_sin)) {
+			pr_err("Failed to configure flow steering");
+			goto err_reset_rss;
+		}
 	}
 
 	if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) {
@@ -1052,13 +1055,17 @@ static int do_server(struct memory_buffer *mem)
 err_unbind:
 	ynl_sock_destroy(ys);
 err_reset_flow_steering:
-	reset_flow_steering();
+	if (!skip_config)
+		reset_flow_steering();
 err_reset_rss:
-	reset_rss();
+	if (!skip_config)
+		reset_rss();
 err_reset_headersplit:
-	restore_ring_config(ring_config);
+	if (!skip_config)
+		restore_ring_config(ring_config);
 err_free_ring_config:
-	ethtool_rings_get_rsp_free(ring_config);
+	if (!skip_config)
+		ethtool_rings_get_rsp_free(ring_config);
 	return err;
 }
 
@@ -1404,7 +1411,7 @@ int main(int argc, char *argv[])
 	int is_server = 0, opt;
 	int ret, err = 1;
 
-	while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:")) != -1) {
+	while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:n")) != -1) {
 		switch (opt) {
 		case 'L':
 			fail_on_linear = true;
@@ -1436,6 +1443,9 @@ int main(int argc, char *argv[])
 		case 'z':
 			max_chunk = atoi(optarg);
 			break;
+		case 'n':
+			skip_config = 1;
+			break;
 		case '?':
 			fprintf(stderr, "unknown option: %c\n", optopt);
 			break;
diff --git a/tools/testing/selftests/drivers/net/hw/nk_devmem.py b/tools/testing/selftests/drivers/net/hw/nk_devmem.py
new file mode 100755
index 000000000000..300ed2a70ab4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/nk_devmem.py
@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""Test devmem TCP with netkit."""
+
+import os
+from devmem_lib import setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds
+from lib.py import ksft_run, ksft_exit, ksft_disruptive
+from lib.py import NetDrvContEnv
+
+
+@ksft_disruptive
+def check_nk_rx(cfg) -> None:
+    """Run the devmem RX test through netkit."""
+    run_rx(cfg)
+
+
+@ksft_disruptive
+def check_nk_tx(cfg) -> None:
+    """Run the devmem TX test through netkit."""
+    run_tx(cfg)
+
+
+@ksft_disruptive
+def check_nk_tx_chunks(cfg) -> None:
+    """Run the devmem TX chunking test through netkit."""
+    run_tx_chunks(cfg)
+
+
+def check_nk_rx_hds(cfg) -> None:
+    """Run the HDS test through netkit."""
+    run_rx_hds(cfg)
+
+
+def main() -> None:
+    """Run the netkit devmem test cases."""
+    with NetDrvContEnv(__file__, rxqueues=2, primary_rx_redirect=True) as cfg:
+        setup_test(cfg,
+                   os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                "ncdevmem"))
+        ksft_run([check_nk_rx, check_nk_tx, check_nk_tx_chunks,
+                  check_nk_rx_hds], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/nk_primary_rx_redirect.bpf.c b/tools/testing/selftests/drivers/net/hw/nk_primary_rx_redirect.bpf.c
new file mode 100644
index 000000000000..46ff494b23de
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/nk_primary_rx_redirect.bpf.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ipv6.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define ctx_ptr(field)		((void *)(long)(field))
+
+volatile __u32 phys_ifindex;
+
+SEC("tc/ingress")
+int nk_primary_rx_redirect(struct __sk_buff *skb)
+{
+	void *data_end = ctx_ptr(skb->data_end);
+	void *data = ctx_ptr(skb->data);
+	struct ethhdr *eth;
+	struct ipv6hdr *ip6h;
+
+	eth = data;
+	if ((void *)(eth + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
+		return TC_ACT_OK;
+
+	ip6h = data + sizeof(struct ethhdr);
+	if ((void *)(ip6h + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (ip6h->nexthdr == IPPROTO_ICMPV6)
+		return TC_ACT_OK;
+
+	return bpf_redirect_neigh(phys_ifindex, NULL, 0, 0);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/drivers/net/hw/nk_qlease.py b/tools/testing/selftests/drivers/net/hw/nk_qlease.py
index aa83dc321328..139a91ebd229 100755
--- a/tools/testing/selftests/drivers/net/hw/nk_qlease.py
+++ b/tools/testing/selftests/drivers/net/hw/nk_qlease.py
@@ -71,7 +71,7 @@ def test_iou_zcrx(cfg) -> None:
     flow_rule_id = set_flow_rule(cfg)
     defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
 
-    rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg._nk_guest_ifname} -q {cfg.nk_queue}"
+    rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg.nk_guest_ifname} -q {cfg.nk_queue}"
     tx_cmd = f"{cfg.bin_remote} -c -h {cfg.nk_guest_ipv6} -p {cfg.port} -l 12840"
     with bkg(rx_cmd, exit_wait=True):
         wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
@@ -128,7 +128,7 @@ def test_attach_xdp_with_mp(cfg) -> None:
 
     netdevnl = NetdevFamily()
 
-    rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg._nk_guest_ifname} -q {cfg.nk_queue}"
+    rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg.nk_guest_ifname} -q {cfg.nk_queue}"
     with bkg(rx_cmd):
         wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
 
@@ -178,7 +178,7 @@ def test_destroy(cfg) -> None:
     ethtool(f"-X {cfg.ifname} equal {cfg.src_queue}")
     defer(ethtool, f"-X {cfg.ifname} default")
 
-    rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg._nk_guest_ifname} -q {cfg.nk_queue}"
+    rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg.nk_guest_ifname} -q {cfg.nk_queue}"
     rx_proc = cmd(rx_cmd, background=True)
     wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
 
@@ -196,7 +196,7 @@ def test_destroy(cfg) -> None:
     ip(f"link del dev {cfg._nk_host_ifname}")
     kill_timer.join()
     cfg._nk_host_ifname = None
-    cfg._nk_guest_ifname = None
+    cfg.nk_guest_ifname = None
 
     queue_info = netdevnl.queue_get(
         {"ifindex": cfg.ifindex, "id": cfg.src_queue, "type": "rx"}
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 24ce122abd9c..ef317aef3a0a 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -2,6 +2,7 @@
 
 import ipaddress
 import os
+import sys
 import time
 import json
 from pathlib import Path
@@ -336,15 +337,18 @@ class NetDrvContEnv(NetDrvEpEnv):
               +---------------+
     """
 
-    def __init__(self, src_path, rxqueues=1, **kwargs):
+    def __init__(self, src_path, rxqueues=1, primary_rx_redirect=False, **kwargs):
         self.netns = None
         self._nk_host_ifname = None
-        self._nk_guest_ifname = None
+        self.nk_guest_ifname = None
         self._tc_clsact_added = False
         self._tc_attached = False
+        self._primary_rx_redirect_attached = False
+        self._primary_rx_redirect_clsact_added = False
         self._bpf_prog_pref = None
         self._bpf_prog_id = None
         self._init_ns_attached = False
+        self._remote_route_added = False
         self._old_fwd = None
         self._old_accept_ra = None
 
@@ -390,14 +394,24 @@ class NetDrvContEnv(NetDrvEpEnv):
 
         netkit_links.sort(key=lambda x: x['ifindex'])
         self._nk_host_ifname = netkit_links[1]['ifname']
-        self._nk_guest_ifname = netkit_links[0]['ifname']
+        self.nk_guest_ifname = netkit_links[0]['ifname']
         self.nk_host_ifindex = netkit_links[1]['ifindex']
         self.nk_guest_ifindex = netkit_links[0]['ifindex']
 
         self._setup_ns()
         self._attach_bpf()
+        if primary_rx_redirect:
+            self._attach_primary_rx_redirect_bpf()
 
     def __del__(self):
+        if self._primary_rx_redirect_attached:
+            cmd(f"tc filter del dev {self._nk_host_ifname} ingress", fail=False)
+            self._primary_rx_redirect_attached = False
+
+        if self._primary_rx_redirect_clsact_added:
+            cmd(f"tc qdisc del dev {self._nk_host_ifname} clsact", fail=False)
+            self._primary_rx_redirect_clsact_added = False
+
         if self._tc_attached:
             cmd(f"tc filter del dev {self.ifname} ingress pref {self._bpf_prog_pref}")
             self._tc_attached = False
@@ -406,10 +420,15 @@ class NetDrvContEnv(NetDrvEpEnv):
             cmd(f"tc qdisc del dev {self.ifname} clsact")
             self._tc_clsact_added = False
 
+        if self._remote_route_added:
+            cmd(f"ip -6 route del {self.nk_guest_ipv6}/128",
+                host=self.remote, fail=False)
+            self._remote_route_added = False
+
         if self._nk_host_ifname:
             cmd(f"ip link del dev {self._nk_host_ifname}")
             self._nk_host_ifname = None
-            self._nk_guest_ifname = None
+            self.nk_guest_ifname = None
 
         if self._init_ns_attached:
             cmd("ip netns del init", fail=False)
@@ -448,24 +467,30 @@ class NetDrvContEnv(NetDrvEpEnv):
         cmd("ip netns attach init 1")
         self._init_ns_attached = True
         ip("netns set init 0", ns=self.netns)
-        ip(f"link set dev {self._nk_guest_ifname} netns {self.netns.name}")
+        ip(f"link set dev {self.nk_guest_ifname} netns {self.netns.name}")
         ip(f"link set dev {self._nk_host_ifname} up")
         ip(f"-6 addr add fe80::1/64 dev {self._nk_host_ifname} nodad")
         ip(f"-6 route add {self.nk_guest_ipv6}/128 via fe80::2 dev {self._nk_host_ifname}")
 
         ip("link set lo up", ns=self.netns)
-        ip(f"link set dev {self._nk_guest_ifname} up", ns=self.netns)
-        ip(f"-6 addr add fe80::2/64 dev {self._nk_guest_ifname}", ns=self.netns)
-        ip(f"-6 addr add {self.nk_guest_ipv6}/64 dev {self._nk_guest_ifname} nodad", ns=self.netns)
-        ip(f"-6 route add default via fe80::1 dev {self._nk_guest_ifname}", ns=self.netns)
+        ip(f"link set dev {self.nk_guest_ifname} up", ns=self.netns)
+        ip(f"-6 addr add fe80::2/64 dev {self.nk_guest_ifname}", ns=self.netns)
+        ip(f"-6 addr add {self.nk_guest_ipv6}/64 dev {self.nk_guest_ifname} nodad", ns=self.netns)
+        ip(f"-6 route add default via fe80::1 dev {self.nk_guest_ifname}", ns=self.netns)
 
-    def _tc_ensure_clsact(self):
-        qdisc = json.loads(cmd(f"tc -j qdisc show dev {self.ifname}").stdout)
+    def _tc_ensure_clsact(self, ifname=None):
+        """Ensure a clsact qdisc exists on @ifname.
+
+        Returns True if this call added the qdisc, otherwise returns False.
+        """
+        if ifname is None:
+            ifname = self.ifname
+        qdisc = json.loads(cmd(f"tc -j qdisc show dev {ifname}").stdout)
         for q in qdisc:
             if q['kind'] == 'clsact':
-                return
-        cmd(f"tc qdisc add dev {self.ifname} clsact")
-        self._tc_clsact_added = True
+                return False
+        cmd(f"tc qdisc add dev {ifname} clsact")
+        return True
 
     def _get_bpf_prog_ids(self):
         filters = json.loads(cmd(f"tc -j filter show dev {self.ifname} ingress").stdout)
@@ -476,28 +501,28 @@ class NetDrvContEnv(NetDrvEpEnv):
                 return (bpf['pref'], bpf['options']['prog']['id'])
         raise Exception("Failed to get BPF prog ID")
 
+    def _find_bss_map_id(self, prog_id):
+        """Find the .bss map ID for a loaded BPF program."""
+        prog_info = bpftool(f"prog show id {prog_id}", json=True)
+        for map_id in prog_info.get("map_ids", []):
+            map_info = bpftool(f"map show id {map_id}", json=True)
+            if map_info.get("name", "").endswith("bss"):
+                return map_id
+        raise Exception(f"Failed to find .bss map for prog {prog_id}")
+
     def _attach_bpf(self):
         bpf_obj = self.test_dir / "nk_forward.bpf.o"
         if not bpf_obj.exists():
             raise KsftSkipEx("BPF prog not found")
 
-        self._tc_ensure_clsact()
+        if self._tc_ensure_clsact():
+            self._tc_clsact_added = True
         cmd(f"tc filter add dev {self.ifname} ingress bpf obj {bpf_obj}"
             " sec tc/ingress direct-action")
         self._tc_attached = True
 
         (self._bpf_prog_pref, self._bpf_prog_id) = self._get_bpf_prog_ids()
-        prog_info = bpftool(f"prog show id {self._bpf_prog_id}", json=True)
-        map_ids = prog_info.get("map_ids", [])
-
-        bss_map_id = None
-        for map_id in map_ids:
-            map_info = bpftool(f"map show id {map_id}", json=True)
-            if map_info.get("name").endswith("bss"):
-                bss_map_id = map_id
-
-        if bss_map_id is None:
-            raise Exception("Failed to find .bss map")
+        bss_map_id = self._find_bss_map_id(self._bpf_prog_id)
 
         ipv6_addr = ipaddress.IPv6Address(self.ipv6_prefix)
         ipv6_bytes = ipv6_addr.packed
@@ -505,3 +530,36 @@ class NetDrvContEnv(NetDrvEpEnv):
         value = ipv6_bytes + ifindex_bytes
         value_hex = ' '.join(f'{b:02x}' for b in value)
         bpftool(f"map update id {bss_map_id} key hex 00 00 00 00 value hex {value_hex}")
+
+    def _attach_primary_rx_redirect_bpf(self):
+        """Attach BPF redirect program on the primary netkit ingress."""
+        bpf_obj = self.test_dir / "nk_primary_rx_redirect.bpf.o"
+        if not bpf_obj.exists():
+            raise KsftSkipEx("Primary RX redirect BPF prog not found")
+
+        if self._tc_ensure_clsact(self._nk_host_ifname):
+            self._primary_rx_redirect_clsact_added = True
+        cmd(f"tc filter add dev {self._nk_host_ifname} ingress"
+            f" bpf obj {bpf_obj} sec tc/ingress direct-action")
+        self._primary_rx_redirect_attached = True
+
+        ip(f"-6 route add {self.nk_guest_ipv6}/128 via {self.addr_v['6']}",
+           host=self.remote)
+        self._remote_route_added = True
+
+        filters = json.loads(
+            cmd(f"tc -j filter show dev {self._nk_host_ifname} ingress").stdout)
+        redirect_prog_id = None
+        for bpf in filters:
+            if 'options' not in bpf:
+                continue
+            if bpf['options']['bpf_name'].startswith('nk_primary_rx_redirect'):
+                redirect_prog_id = bpf['options']['prog']['id']
+                break
+        if redirect_prog_id is None:
+            raise Exception("Failed to get primary RX redirect BPF prog ID")
+
+        bss_map_id = self._find_bss_map_id(redirect_prog_id)
+        phys_ifindex_bytes = self.ifindex.to_bytes(4, byteorder=sys.byteorder)
+        value_hex = ' '.join(f'{b:02x}' for b in phys_ifindex_bytes)
+        bpftool(f"map update id {bss_map_id} key hex 00 00 00 00 value hex {value_hex}")