Merge branch 'net-devmem-allow-rx-buf-size-page_size-per-binding'

Bobby Eshleman says: ==================== net: devmem: allow rx-buf-size > PAGE_SIZE per binding Every devmem dmabuf binding hands the page_pool PAGE_SIZE niovs today. On NICs that consume one descriptor per netmem, this caps a single RX descriptor at PAGE_SIZE and burns CPU on buffer churn. In this series, we add a bind-time netlink attribute, NETDEV_A_DMABUF_RX_BUF_SIZE, that lets userspace request a larger niov size (power of two >= PAGE_SIZE). Drivers must opt in via queue_mgmt_ops.QCFG_RX_PAGE_SIZE. Measurements: Setup: kperf devmem RX/TX cuda, 4 flows, 64 MB messages, 60s, dctcp, num-rx-queues=4, dmabuf-rx/tx-size-mb=2048, 10 runs per niov size, mlx5. niov RX dev Gbps RX flow avg Gbps app sys % ----- ---------------- ----------------- ---------------- 4K 300.63 +/- 53.21 75.16 +/- 13.30 54.15 +/- 10.23 16K 321.35 +/- 28.20 80.34 +/- 7.05 41.05 +/- 8.87 32K 347.63 +/- 2.20 86.91 +/- 0.55 44.54 +/- 3.51 64K 332.11 +/- 14.26 83.03 +/- 3.56 35.47 +/- 3.11 RX app sys % drops ~19% from 4K to 64K. kperf support (not yet merged): 8837577f92 ==================== Link: https://patch.msgid.link/20260805-tcpdm-large-niovs-v8-0-3e0225e2808c@meta.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-08-29 20:58:57 -04:00 · 2026-08-07 18:32:41 -07:00
parent 55d20f50a2 8ac4255c1e
commit 001b5d347d
12 changed files with 231 additions and 38 deletions
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -6,6 +6,14 @@ doc: >-
  netdev configuration over generic netlink.

 definitions:
+  -
+    type: const
+    name: page-size
+    # Dummy value, codegen needs a number. The real value comes from
+    # the PAGE_SIZE macro in the header below.
+    value: 0
+    header: asm/page.h
+    scope: kernel
  -
    type: flags
    name: xdp-act
@@ -598,6 +606,16 @@ attribute-sets:
        type: u32
        checks:
          min: 1
+      -
+        name: rx-page-size
+        doc: |
+          Size in bytes of each device page the NIC writes into from the bound
+          dmabuf. Must be a power of two and >= PAGE_SIZE; defaults to
+          PAGE_SIZE.
+        type: u32
+        checks:
+          min: page-size
+          max: u32-max

 operations:
  list:
@@ -812,6 +830,7 @@ operations:
            - ifindex
            - fd
            - queues
+            - rx-page-size
        reply:
          attributes:
            - id
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -219,6 +219,7 @@ enum {
 	NETDEV_A_DMABUF_QUEUES,
 	NETDEV_A_DMABUF_FD,
 	NETDEV_A_DMABUF_ID,
+	NETDEV_A_DMABUF_RX_PAGE_SIZE,

 	__NETDEV_A_DMABUF_MAX,
 	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -46,7 +46,7 @@ static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov)

 	owner = net_devmem_iov_to_chunk_owner(niov);
 	return owner->base_dma_addr +
-	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
+	       ((dma_addr_t)net_iov_idx(niov) << owner->binding->niov_shift);
 }

 static void net_devmem_dmabuf_binding_release(struct percpu_ref *ref)
@@ -93,13 +93,14 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 	ssize_t offset;
 	ssize_t index;

-	dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE,
+	dma_addr = gen_pool_alloc_owner(binding->chunk_pool,
+					1UL << binding->niov_shift,
 					(void **)&owner);
 	if (!dma_addr)
 		return NULL;

 	offset = dma_addr - owner->base_dma_addr;
-	index = offset / PAGE_SIZE;
+	index = offset >> binding->niov_shift;
 	niov = &owner->area.niovs[index];

 	niov->desc.pp_magic = 0;
@@ -113,12 +114,13 @@ void net_devmem_free_dmabuf(struct net_iov *niov)
 {
 	struct net_devmem_dmabuf_binding *binding = net_devmem_iov_binding(niov);
 	unsigned long dma_addr = net_devmem_get_dma_addr(niov);
+	size_t niov_size = 1UL << binding->niov_shift;

 	if (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr,
-				       PAGE_SIZE)))
+				       niov_size)))
 		return;

-	gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE);
+	gen_pool_free(binding->chunk_pool, dma_addr, niov_size);
 }

 void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
@@ -163,6 +165,9 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 	u32 xa_idx;
 	int err;

+	if (binding->niov_shift != PAGE_SHIFT)
+		mp_params.rx_page_size = 1U << binding->niov_shift;
+
 	err = netif_mp_open_rxq(dev, rxq_idx, &mp_params, extack);
 	if (err)
 		return err;
@@ -184,10 +189,12 @@ struct net_devmem_dmabuf_binding *
 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,
+		       unsigned int dmabuf_fd, unsigned int niov_shift,
+		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack)
 {
 	struct net_devmem_dmabuf_binding *binding;
+	size_t niov_size = 1UL << niov_shift;
 	static u32 id_alloc_next;
 	struct scatterlist *sg;
 	struct dma_buf *dmabuf;
@@ -213,6 +220,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,

 	binding->dev = dev;
 	binding->vdev = vdev;
+	binding->niov_shift = niov_shift;
 	xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC);

 	err = percpu_ref_init(&binding->ref,
@@ -255,11 +263,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		}
 	}

-	/* For simplicity we expect to make PAGE_SIZE allocations, but the
-	 * binding can be much more flexible than that. We may be able to
-	 * allocate MTU sized chunks here. Leave that for future work...
-	 */
-	binding->chunk_pool = gen_pool_create(PAGE_SHIFT,
+	binding->chunk_pool = gen_pool_create(niov_shift,
 					      dev_to_node(&dev->dev));
 	if (!binding->chunk_pool) {
 		err = -ENOMEM;
@@ -273,9 +277,12 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		size_t len = sg_dma_len(sg);
 		struct net_iov *niov;

-		if (!IS_ALIGNED(len, PAGE_SIZE)) {
+		if (!IS_ALIGNED(dma_addr, niov_size) ||
+		    !IS_ALIGNED(len, niov_size)) {
 			err = -EINVAL;
-			NL_SET_ERR_MSG(extack, "dma-buf SG length must be PAGE_SIZE aligned");
+			NL_SET_ERR_MSG_FMT(extack,
+					   "dmabuf sg entry (addr=%pad, len=%zu) not aligned to niov size %zu",
+					   &dma_addr, len, niov_size);
 			goto err_free_chunks;
 		}

@@ -288,7 +295,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,

 		owner->area.base_virtual = virtual;
 		owner->base_dma_addr = dma_addr;
-		owner->area.num_niovs = len / PAGE_SIZE;
+		owner->area.num_niovs = len >> niov_shift;
 		owner->binding = binding;

 		err = gen_pool_add_owner(binding->chunk_pool, dma_addr,
@@ -454,7 +461,7 @@ int mp_dmabuf_devmem_init(struct page_pool *pool)
 	pool->dma_sync = false;
 	pool->dma_sync_for_cpu = false;

-	if (pool->p.order != 0)
+	if (pool->p.order != binding->niov_shift - PAGE_SHIFT)
 		return -E2BIG;

 	net_devmem_dmabuf_binding_get(binding);
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -71,6 +71,8 @@ struct net_devmem_dmabuf_binding {
 	 */
 	struct net_iov **tx_vec;

+	unsigned int niov_shift;
+
 	struct work_struct unbind_w;
 };

@@ -93,7 +95,8 @@ struct net_devmem_dmabuf_binding *
 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,
+		       unsigned int dmabuf_fd, unsigned int niov_shift,
+		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack);
 struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id);
 void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
@@ -122,10 +125,11 @@ static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)

 static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 {
-	struct net_iov_area *owner = net_iov_owner(niov);
+	struct dmabuf_genpool_chunk_owner *co =
+		net_devmem_iov_to_chunk_owner(niov);

-	return owner->base_virtual +
-	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
+	return net_iov_owner(niov)->base_virtual +
+	       ((unsigned long)net_iov_idx(niov) << co->binding->niov_shift);
 }

 static inline bool
@@ -175,6 +179,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		       struct device *dma_dev,
 		       enum dma_data_direction direction,
 		       unsigned int dmabuf_fd,
+		       unsigned int niov_shift,
 		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack)
 {
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -11,6 +11,7 @@

 #include <uapi/linux/netdev.h>
 #include <net/netdev_netlink.h>
+#include <asm/page.h>

 /* Integer value ranges */
 static const struct netlink_range_validation netdev_a_page_pool_id_range = {
@@ -27,6 +28,11 @@ static const struct netlink_range_validation netdev_a_napi_defer_hard_irqs_range
 	.max	= S32_MAX,
 };

+static const struct netlink_range_validation netdev_a_dmabuf_rx_page_size_range = {
+	.min	= PAGE_SIZE,
+	.max	= U32_MAX,
+};
+
 /* Common nested types */
 const struct nla_policy netdev_lease_nl_policy[NETDEV_A_LEASE_NETNS_ID + 1] = {
 	[NETDEV_A_LEASE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
@@ -106,10 +112,11 @@ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE
 };

 /* NETDEV_CMD_BIND_RX - do */
-static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] = {
+static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_RX_PAGE_SIZE + 1] = {
 	[NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
 	[NETDEV_A_DMABUF_FD] = { .type = NLA_U32, },
 	[NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy),
+	[NETDEV_A_DMABUF_RX_PAGE_SIZE] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_dmabuf_rx_page_size_range),
 };

 /* NETDEV_CMD_NAPI_SET - do */
@@ -219,7 +226,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.cmd		= NETDEV_CMD_BIND_RX,
 		.doit		= netdev_nl_bind_rx_doit,
 		.policy		= netdev_bind_rx_nl_policy,
-		.maxattr	= NETDEV_A_DMABUF_FD,
+		.maxattr	= NETDEV_A_DMABUF_RX_PAGE_SIZE,
 		.flags		= GENL_UNS_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -12,6 +12,7 @@

 #include <uapi/linux/netdev.h>
 #include <net/netdev_netlink.h>
+#include <asm/page.h>

 /* Common nested types */
 extern const struct nla_policy netdev_lease_nl_policy[NETDEV_A_LEASE_NETNS_ID + 1];
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -1013,6 +1013,7 @@ netdev_nl_get_dma_dev(struct net_device *netdev, unsigned long *rxq_bitmap,
 int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net_devmem_dmabuf_binding *binding;
+	unsigned int niov_shift = PAGE_SHIFT;
 	u32 ifindex, dmabuf_fd, rxq_idx;
 	struct netdev_nl_sock *priv;
 	struct net_device *netdev;
@@ -1030,6 +1031,18 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
 	dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);

+	if (info->attrs[NETDEV_A_DMABUF_RX_PAGE_SIZE]) {
+		u32 rx_page_size = nla_get_u32(info->attrs[NETDEV_A_DMABUF_RX_PAGE_SIZE]);
+
+		if (!is_power_of_2(rx_page_size)) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[NETDEV_A_DMABUF_RX_PAGE_SIZE],
+					    "rx-page-size must be a power of 2");
+			return -EINVAL;
+		}
+		niov_shift = ilog2(rx_page_size);
+	}
+
 	priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk);
 	if (IS_ERR(priv))
 		return PTR_ERR(priv);
@@ -1080,7 +1093,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	}

 	binding = net_devmem_bind_dmabuf(netdev, NULL, dma_dev, DMA_FROM_DEVICE,
-					 dmabuf_fd, priv, info->extack);
+					 dmabuf_fd, niov_shift, priv,
+					 info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
 		goto err_rxq_bitmap;
@@ -1221,7 +1235,7 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
 	binding = net_devmem_bind_dmabuf(bind_dev,
 					 bind_dev != netdev ? netdev : NULL,
 					 dma_dev, DMA_TO_DEVICE, dmabuf_fd,
-					 priv, info->extack);
+					 PAGE_SHIFT, priv, info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
 		goto err_unlock_bind_dev;
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -219,6 +219,7 @@ enum {
 	NETDEV_A_DMABUF_QUEUES,
 	NETDEV_A_DMABUF_FD,
 	NETDEV_A_DMABUF_ID,
+	NETDEV_A_DMABUF_RX_PAGE_SIZE,

 	__NETDEV_A_DMABUF_MAX,
 	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: GPL-2.0

 from os import path
-from devmem_lib import setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds
+from devmem_lib import (setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds,
+                        run_rx_large_niov)
 from lib.py import ksft_run, ksft_exit, ksft_disruptive
 from lib.py import NetDrvEpEnv

@@ -30,11 +31,17 @@ def check_rx_hds(cfg) -> None:
    run_rx_hds(cfg)


+def check_rx_large_niov(cfg) -> None:
+    """Run the devmem RX test with rx-page-size = 16 KiB."""
+    run_rx_large_niov(cfg)
+
+
 def main() -> None:
    """Run the devmem test cases."""
    with NetDrvEpEnv(__file__) as cfg:
        setup_test(cfg, path.abspath(path.dirname(__file__) + "/ncdevmem"))
-        ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds],
+        ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds,
+                  check_rx_large_niov],
                 args=(cfg,))
    ksft_exit()

--- a/tools/testing/selftests/drivers/net/hw/devmem_lib.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem_lib.py
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
+# pylint: disable=invalid-name,too-many-arguments
 """Shared helpers for devmem TCP selftests."""

+import os
 import re

 from lib.py import (bkg, cmd, defer, ethtool, rand_port, wait_port_listen,
@@ -8,19 +10,82 @@ from lib.py import (bkg, cmd, defer, ethtool, rand_port, wait_port_listen,
                    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
+RX_PAGE_SIZE_DEFAULT = 0
+RX_PAGE_SIZE_16K = 16384

-    if not cfg.devmem_supported:
+PROBE_RX_PAGE_SIZES = (RX_PAGE_SIZE_DEFAULT, RX_PAGE_SIZE_16K)
+
+NR_HUGEPAGES_FILE = "/proc/sys/vm/nr_hugepages"
+
+
+def _is_aligned(value, alignment):
+    """Equivalent of the kernel IS_ALIGNED(value, alignment).
+
+    alignment must be a power of two.
+    """
+    return (value & (alignment - 1)) == 0
+
+
+def _restore_nr_hugepages(nr_hugepages):
+    with open(NR_HUGEPAGES_FILE, 'w', encoding='utf-8') as f:
+        f.write(str(nr_hugepages))
+
+
+def _reserve_hugepages(want=64):
+    """Raise nr_hugepages to @want and arrange for it to be restored."""
+    with open(NR_HUGEPAGES_FILE, 'r+', encoding='utf-8') as f:
+        nr_hugepages = int(f.read().strip())
+        if nr_hugepages >= want:
+            return
+        f.seek(0)
+        f.write(str(want))
+    defer(_restore_nr_hugepages, nr_hugepages)
+
+
+def _probe_devmem(cfg, rx_page_size):
+    """Return True if ncdevmem can bind cfg.ifname at @rx_page_size."""
+    probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
+    if rx_page_size != RX_PAGE_SIZE_DEFAULT:
+        probe_command += f" -b {rx_page_size}"
+    return cmd(probe_command, fail=False, shell=True).ret == 0
+
+
+def require_devmem(cfg, rx_page_size=RX_PAGE_SIZE_DEFAULT):
+    """Probe ncdevmem on cfg.ifname and SKIP the test if devmem isn't supported."""
+    if rx_page_size not in PROBE_RX_PAGE_SIZES:
+        raise RuntimeError(
+            f"rx-page-size={rx_page_size} is missing from "
+            f"PROBE_RX_PAGE_SIZES, so it was never probed.")
+
+    if not hasattr(cfg, "devmem_supported"):
+        _reserve_hugepages()
+        # Probe every size upfront: in nk tests a leased queue may land in
+        # ncdevmem's queue range and cause the probe to fail.
+        cfg.devmem_supported = {size: _probe_devmem(cfg, size)
+                                for size in PROBE_RX_PAGE_SIZES}
+
+    if not cfg.devmem_supported[RX_PAGE_SIZE_DEFAULT]:
        raise KsftSkipEx("Test requires devmem support")

+    if rx_page_size != RX_PAGE_SIZE_DEFAULT:
+        page_size = os.sysconf("SC_PAGE_SIZE")
+        if not _is_aligned(rx_page_size, page_size):
+            raise KsftSkipEx(
+                f"rx-page-size={rx_page_size} is invalid for this platform "
+                f"(must be a multiple of PAGE_SIZE={page_size})")
+
+        if not cfg.devmem_supported[rx_page_size]:
+            raise KsftSkipEx(
+                f"Test requires devmem rx-page-size={rx_page_size} support")
+

 def configure_nic(cfg):
    """Channels, rings, RSS, queue lease for netkit devmem."""
+    if not hasattr(cfg, "devmem_supported"):
+        raise RuntimeError(
+            "require_devmem() must be called before configure_nic(), which "
+            "may lease a queue away and make later probes fail.")
+
    if not hasattr(cfg, 'netns'):
        return

@@ -75,7 +140,8 @@ def set_flow_rule(cfg, port):
    return int(re.search(r'ID (\d+)', output).group(1))


-def ncdevmem_rx(cfg, port, verify=True, fail_on_linear=False, flow_steer=False):
+def ncdevmem_rx(cfg, port, verify=True, fail_on_linear=False, flow_steer=False,
+                rx_page_size=RX_PAGE_SIZE_DEFAULT):
    """Build the ncdevmem RX listener command."""
    if hasattr(cfg, 'netns'):
        flow_rule_id = set_flow_rule(cfg, port)
@@ -95,6 +161,8 @@ def ncdevmem_rx(cfg, port, verify=True, fail_on_linear=False, flow_steer=False):
        extras.append("-v 7")
    if fail_on_linear:
        extras.append("-L")
+    if rx_page_size != RX_PAGE_SIZE_DEFAULT:
+        extras.append(f"-b {rx_page_size}")

    parts = [cfg.bin_local, "-l", f"-f {ifname}", f"-s {addr}",
             f"-p {port}", *extras]
@@ -201,6 +269,33 @@ def run_tx_chunks(cfg):
    ksft_eq(socat.stdout.strip(), "hello\nworld")


+def run_rx_large_niov(cfg):
+    """Run the devmem RX test with a large niov (rx-page-size > PAGE_SIZE).
+
+    Sweep payload sizes that straddle the niov boundary: below, equal to,
+    and above rx_page_size, to exercise sub-niov, exact-niov, and multi-niov
+    RX paths.
+    """
+    require_devmem(cfg, rx_page_size=RX_PAGE_SIZE_16K)
+    _reserve_hugepages()
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+
+    for size in [1024, 4096, 8192, 16384, 32768, 65536]:
+        port = rand_port()
+        socat = socat_send(cfg, port)
+        listen_cmd = ncdevmem_rx(cfg, port,
+                                 flow_steer=not netns,
+                                 rx_page_size=RX_PAGE_SIZE_16K)
+        data_pipe = (f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | "
+                     f"head -c {size} | {socat}")
+        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,
+                f"large-niov failed for payload size {size}")
+
+
 def run_rx_hds(cfg):
    """Run the HDS test by running devmem RX across a segment size sweep."""
    require_devmem(cfg)
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -40,6 +40,7 @@

 #include <linux/uio.h>
 #include <stdarg.h>
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -61,6 +62,7 @@
 #include <sys/time.h>

 #include <linux/memfd.h>
+#include <sys/param.h>
 #include <linux/dma-buf.h>
 #include <linux/errqueue.h>
 #include <linux/udmabuf.h>
@@ -79,6 +81,7 @@
 #define PAGE_SHIFT 12
 #define TEST_PREFIX "ncdevmem"
 #define NUM_PAGES 16000
+#define MB(x) ((x) << 20)

 #ifndef MSG_SOCK_DEVMEM
 #define MSG_SOCK_DEVMEM 0x2000000
@@ -100,6 +103,7 @@ static unsigned int dmabuf_id;
 static uint32_t tx_dmabuf_id;
 static int waittime_ms = 500;
 static bool fail_on_linear;
+static uint32_t rx_page_size;

 /* System state loaded by current_config_load() */
 #define MAX_FLOWS	8
@@ -142,6 +146,7 @@ static struct memory_buffer *udmabuf_alloc(size_t size)
 {
 	struct udmabuf_create create;
 	struct memory_buffer *ctx;
+	unsigned int memfd_flags;
 	int ret;

 	ctx = malloc(sizeof(*ctx));
@@ -156,9 +161,14 @@ static struct memory_buffer *udmabuf_alloc(size_t size)
 		goto err_free_ctx;
 	}

-	ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
+	memfd_flags = MFD_ALLOW_SEALING;
+	if (rx_page_size > getpagesize())
+		memfd_flags |= MFD_HUGETLB | MFD_HUGE_2MB;
+
+	ctx->memfd = memfd_create("udmabuf-test", memfd_flags);
 	if (ctx->memfd < 0) {
-		pr_err("[skip,no-memfd]");
+		pr_err("[skip,no-memfd%s]",
+		       (memfd_flags & MFD_HUGETLB) ? " (need hugepages)" : "");
 		goto err_close_dev;
 	}

@@ -168,6 +178,11 @@ static struct memory_buffer *udmabuf_alloc(size_t size)
 		goto err_close_memfd;
 	}

+	if (memfd_flags & MFD_HUGETLB) {
+		size = roundup(size, MB(2));
+		ctx->size = size;
+	}
+
 	ret = ftruncate(ctx->memfd, size);
 	if (ret == -1) {
 		pr_err("[FAIL,memfd-truncate]");
@@ -699,6 +714,8 @@ static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
 	netdev_bind_rx_req_set_ifindex(req, ifindex);
 	netdev_bind_rx_req_set_fd(req, dmabuf_fd);
 	__netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
+	if (rx_page_size)
+		netdev_bind_rx_req_set_rx_page_size(req, rx_page_size);

 	rsp = netdev_bind_rx(*ys, req);
 	if (!rsp) {
@@ -1411,7 +1428,7 @@ 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:n")) != -1) {
+	while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:nb:")) != -1) {
 		switch (opt) {
 		case 'L':
 			fail_on_linear = true;
@@ -1446,6 +1463,19 @@ int main(int argc, char *argv[])
 		case 'n':
 			skip_config = 1;
 			break;
+		case 'b': {
+			unsigned long val;
+
+			errno = 0;
+			val = strtoul(optarg, NULL, 0);
+			if ((val == ULONG_MAX && errno == ERANGE) ||
+			    val > UINT32_MAX) {
+				pr_err("invalid rx_page_size: %s", optarg);
+				return 1;
+			}
+			rx_page_size = val;
+			break;
+		}
 		case '?':
 			fprintf(stderr, "unknown option: %c\n", optopt);
 			break;
--- a/tools/testing/selftests/drivers/net/hw/nk_devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/nk_devmem.py
@@ -3,7 +3,8 @@
 """Test devmem TCP with netkit."""

 import os
-from devmem_lib import setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds
+from devmem_lib import (setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds,
+                        run_rx_large_niov)
 from lib.py import ksft_run, ksft_exit, ksft_disruptive
 from lib.py import NetDrvContEnv

@@ -31,6 +32,11 @@ def check_nk_rx_hds(cfg) -> None:
    run_rx_hds(cfg)


+def check_nk_rx_large_niov(cfg) -> None:
+    """Run the devmem RX large-niov test through netkit."""
+    run_rx_large_niov(cfg)
+
+
 def main() -> None:
    """Run the netkit devmem test cases."""
    with NetDrvContEnv(__file__, rxqueues=2, primary_rx_redirect=True) as cfg:
@@ -38,7 +44,7 @@ def main() -> None:
                   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,))
+                  check_nk_rx_hds, check_nk_rx_large_niov], args=(cfg,))
    ksft_exit()