Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

3 files changed, 770 insertions, 0 deletions

diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
new file mode 100644
index 000000000..92ea4158f
--- /dev/null
+++ b/net/mctp/test/route-test.c
@@ -0,0 +1,684 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <kunit/test.h>
+
+#include "utils.h"
+
+struct mctp_test_route {
+	struct mctp_route	rt;
+	struct sk_buff_head	pkts;
+};
+
+static int mctp_test_route_output(struct mctp_route *rt, struct sk_buff *skb)
+{
+	struct mctp_test_route *test_rt = container_of(rt, struct mctp_test_route, rt);
+
+	skb_queue_tail(&test_rt->pkts, skb);
+
+	return 0;
+}
+
+/* local version of mctp_route_alloc() */
+static struct mctp_test_route *mctp_route_test_alloc(void)
+{
+	struct mctp_test_route *rt;
+
+	rt = kzalloc(sizeof(*rt), GFP_KERNEL);
+	if (!rt)
+		return NULL;
+
+	INIT_LIST_HEAD(&rt->rt.list);
+	refcount_set(&rt->rt.refs, 1);
+	rt->rt.output = mctp_test_route_output;
+
+	skb_queue_head_init(&rt->pkts);
+
+	return rt;
+}
+
+static struct mctp_test_route *mctp_test_create_route(struct net *net,
+						      struct mctp_dev *dev,
+						      mctp_eid_t eid,
+						      unsigned int mtu)
+{
+	struct mctp_test_route *rt;
+
+	rt = mctp_route_test_alloc();
+	if (!rt)
+		return NULL;
+
+	rt->rt.min = eid;
+	rt->rt.max = eid;
+	rt->rt.mtu = mtu;
+	rt->rt.type = RTN_UNSPEC;
+	if (dev)
+		mctp_dev_hold(dev);
+	rt->rt.dev = dev;
+
+	list_add_rcu(&rt->rt.list, &net->mctp.routes);
+
+	return rt;
+}
+
+static void mctp_test_route_destroy(struct kunit *test,
+				    struct mctp_test_route *rt)
+{
+	unsigned int refs;
+
+	rtnl_lock();
+	list_del_rcu(&rt->rt.list);
+	rtnl_unlock();
+
+	skb_queue_purge(&rt->pkts);
+	if (rt->rt.dev)
+		mctp_dev_put(rt->rt.dev);
+
+	refs = refcount_read(&rt->rt.refs);
+	KUNIT_ASSERT_EQ_MSG(test, refs, 1, "route ref imbalance");
+
+	kfree_rcu(&rt->rt, rcu);
+}
+
+static struct sk_buff *mctp_test_create_skb(const struct mctp_hdr *hdr,
+					    unsigned int data_len)
+{
+	size_t hdr_len = sizeof(*hdr);
+	struct sk_buff *skb;
+	unsigned int i;
+	u8 *buf;
+
+	skb = alloc_skb(hdr_len + data_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(skb_put(skb, hdr_len), hdr, hdr_len);
+
+	buf = skb_put(skb, data_len);
+	for (i = 0; i < data_len; i++)
+		buf[i] = i & 0xff;
+
+	return skb;
+}
+
+static struct sk_buff *__mctp_test_create_skb_data(const struct mctp_hdr *hdr,
+						   const void *data,
+						   size_t data_len)
+{
+	size_t hdr_len = sizeof(*hdr);
+	struct sk_buff *skb;
+
+	skb = alloc_skb(hdr_len + data_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(skb_put(skb, hdr_len), hdr, hdr_len);
+	memcpy(skb_put(skb, data_len), data, data_len);
+
+	return skb;
+}
+
+#define mctp_test_create_skb_data(h, d) \
+	__mctp_test_create_skb_data(h, d, sizeof(*d))
+
+struct mctp_frag_test {
+	unsigned int mtu;
+	unsigned int msgsize;
+	unsigned int n_frags;
+};
+
+static void mctp_test_fragment(struct kunit *test)
+{
+	const struct mctp_frag_test *params;
+	int rc, i, n, mtu, msgsize;
+	struct mctp_test_route *rt;
+	struct sk_buff *skb;
+	struct mctp_hdr hdr;
+	u8 seq;
+
+	params = test->param_value;
+	mtu = params->mtu;
+	msgsize = params->msgsize;
+
+	hdr.ver = 1;
+	hdr.src = 8;
+	hdr.dest = 10;
+	hdr.flags_seq_tag = MCTP_HDR_FLAG_TO;
+
+	skb = mctp_test_create_skb(&hdr, msgsize);
+	KUNIT_ASSERT_TRUE(test, skb);
+
+	rt = mctp_test_create_route(&init_net, NULL, 10, mtu);
+	KUNIT_ASSERT_TRUE(test, rt);
+
+	rc = mctp_do_fragment_route(&rt->rt, skb, mtu, MCTP_TAG_OWNER);
+	KUNIT_EXPECT_FALSE(test, rc);
+
+	n = rt->pkts.qlen;
+
+	KUNIT_EXPECT_EQ(test, n, params->n_frags);
+
+	for (i = 0;; i++) {
+		struct mctp_hdr *hdr2;
+		struct sk_buff *skb2;
+		u8 tag_mask, seq2;
+		bool first, last;
+
+		first = i == 0;
+		last = i == (n - 1);
+
+		skb2 = skb_dequeue(&rt->pkts);
+
+		if (!skb2)
+			break;
+
+		hdr2 = mctp_hdr(skb2);
+
+		tag_mask = MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO;
+
+		KUNIT_EXPECT_EQ(test, hdr2->ver, hdr.ver);
+		KUNIT_EXPECT_EQ(test, hdr2->src, hdr.src);
+		KUNIT_EXPECT_EQ(test, hdr2->dest, hdr.dest);
+		KUNIT_EXPECT_EQ(test, hdr2->flags_seq_tag & tag_mask,
+				hdr.flags_seq_tag & tag_mask);
+
+		KUNIT_EXPECT_EQ(test,
+				!!(hdr2->flags_seq_tag & MCTP_HDR_FLAG_SOM), first);
+		KUNIT_EXPECT_EQ(test,
+				!!(hdr2->flags_seq_tag & MCTP_HDR_FLAG_EOM), last);
+
+		seq2 = (hdr2->flags_seq_tag >> MCTP_HDR_SEQ_SHIFT) &
+			MCTP_HDR_SEQ_MASK;
+
+		if (first) {
+			seq = seq2;
+		} else {
+			seq++;
+			KUNIT_EXPECT_EQ(test, seq2, seq & MCTP_HDR_SEQ_MASK);
+		}
+
+		if (!last)
+			KUNIT_EXPECT_EQ(test, skb2->len, mtu);
+		else
+			KUNIT_EXPECT_LE(test, skb2->len, mtu);
+
+		kfree_skb(skb2);
+	}
+
+	mctp_test_route_destroy(test, rt);
+}
+
+static const struct mctp_frag_test mctp_frag_tests[] = {
+	{.mtu = 68, .msgsize = 63, .n_frags = 1},
+	{.mtu = 68, .msgsize = 64, .n_frags = 1},
+	{.mtu = 68, .msgsize = 65, .n_frags = 2},
+	{.mtu = 68, .msgsize = 66, .n_frags = 2},
+	{.mtu = 68, .msgsize = 127, .n_frags = 2},
+	{.mtu = 68, .msgsize = 128, .n_frags = 2},
+	{.mtu = 68, .msgsize = 129, .n_frags = 3},
+	{.mtu = 68, .msgsize = 130, .n_frags = 3},
+};
+
+static void mctp_frag_test_to_desc(const struct mctp_frag_test *t, char *desc)
+{
+	sprintf(desc, "mtu %d len %d -> %d frags",
+		t->msgsize, t->mtu, t->n_frags);
+}
+
+KUNIT_ARRAY_PARAM(mctp_frag, mctp_frag_tests, mctp_frag_test_to_desc);
+
+struct mctp_rx_input_test {
+	struct mctp_hdr hdr;
+	bool input;
+};
+
+static void mctp_test_rx_input(struct kunit *test)
+{
+	const struct mctp_rx_input_test *params;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct sk_buff *skb;
+
+	params = test->param_value;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	skb = mctp_test_create_skb(&params->hdr, 1);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	__mctp_cb(skb);
+
+	mctp_pkttype_receive(skb, dev->ndev, &mctp_packet_type, NULL);
+
+	KUNIT_EXPECT_EQ(test, !!rt->pkts.qlen, params->input);
+
+	mctp_test_route_destroy(test, rt);
+	mctp_test_destroy_dev(dev);
+}
+
+#define RX_HDR(_ver, _src, _dest, _fst) \
+	{ .ver = _ver, .src = _src, .dest = _dest, .flags_seq_tag = _fst }
+
+/* we have a route for EID 8 only */
+static const struct mctp_rx_input_test mctp_rx_input_tests[] = {
+	{ .hdr = RX_HDR(1, 10, 8, 0), .input = true },
+	{ .hdr = RX_HDR(1, 10, 9, 0), .input = false }, /* no input route */
+	{ .hdr = RX_HDR(2, 10, 8, 0), .input = false }, /* invalid version */
+};
+
+static void mctp_rx_input_test_to_desc(const struct mctp_rx_input_test *t,
+				       char *desc)
+{
+	sprintf(desc, "{%x,%x,%x,%x}", t->hdr.ver, t->hdr.src, t->hdr.dest,
+		t->hdr.flags_seq_tag);
+}
+
+KUNIT_ARRAY_PARAM(mctp_rx_input, mctp_rx_input_tests,
+		  mctp_rx_input_test_to_desc);
+
+/* set up a local dev, route on EID 8, and a socket listening on type 0 */
+static void __mctp_route_test_init(struct kunit *test,
+				   struct mctp_test_dev **devp,
+				   struct mctp_test_route **rtp,
+				   struct socket **sockp)
+{
+	struct sockaddr_mctp addr = {0};
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int rc;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	addr.smctp_family = AF_MCTP;
+	addr.smctp_network = MCTP_NET_ANY;
+	addr.smctp_addr.s_addr = 8;
+	addr.smctp_type = 0;
+	rc = kernel_bind(sock, (struct sockaddr *)&addr, sizeof(addr));
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	*rtp = rt;
+	*devp = dev;
+	*sockp = sock;
+}
+
+static void __mctp_route_test_fini(struct kunit *test,
+				   struct mctp_test_dev *dev,
+				   struct mctp_test_route *rt,
+				   struct socket *sock)
+{
+	sock_release(sock);
+	mctp_test_route_destroy(test, rt);
+	mctp_test_destroy_dev(dev);
+}
+
+struct mctp_route_input_sk_test {
+	struct mctp_hdr hdr;
+	u8 type;
+	bool deliver;
+};
+
+static void mctp_test_route_input_sk(struct kunit *test)
+{
+	const struct mctp_route_input_sk_test *params;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int rc;
+
+	params = test->param_value;
+
+	__mctp_route_test_init(test, &dev, &rt, &sock);
+
+	skb = mctp_test_create_skb_data(&params->hdr, &params->type);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	skb->dev = dev->ndev;
+	__mctp_cb(skb);
+
+	rc = mctp_route_input(&rt->rt, skb);
+
+	if (params->deliver) {
+		KUNIT_EXPECT_EQ(test, rc, 0);
+
+		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+		KUNIT_EXPECT_EQ(test, skb->len, 1);
+
+		skb_free_datagram(sock->sk, skb2);
+
+	} else {
+		KUNIT_EXPECT_NE(test, rc, 0);
+		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+		KUNIT_EXPECT_NULL(test, skb2);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+#define FL_S	(MCTP_HDR_FLAG_SOM)
+#define FL_E	(MCTP_HDR_FLAG_EOM)
+#define FL_TO	(MCTP_HDR_FLAG_TO)
+#define FL_T(t)	((t) & MCTP_HDR_TAG_MASK)
+
+static const struct mctp_route_input_sk_test mctp_route_input_sk_tests[] = {
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 0, .deliver = true },
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 1, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_E | FL_TO), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_TO), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, 0), .type = 0, .deliver = false },
+};
+
+static void mctp_route_input_sk_to_desc(const struct mctp_route_input_sk_test *t,
+					char *desc)
+{
+	sprintf(desc, "{%x,%x,%x,%x} type %d", t->hdr.ver, t->hdr.src,
+		t->hdr.dest, t->hdr.flags_seq_tag, t->type);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk, mctp_route_input_sk_tests,
+		  mctp_route_input_sk_to_desc);
+
+struct mctp_route_input_sk_reasm_test {
+	const char *name;
+	struct mctp_hdr hdrs[4];
+	int n_hdrs;
+	int rx_len;
+};
+
+static void mctp_test_route_input_sk_reasm(struct kunit *test)
+{
+	const struct mctp_route_input_sk_reasm_test *params;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int i, rc;
+	u8 c;
+
+	params = test->param_value;
+
+	__mctp_route_test_init(test, &dev, &rt, &sock);
+
+	for (i = 0; i < params->n_hdrs; i++) {
+		c = i;
+		skb = mctp_test_create_skb_data(&params->hdrs[i], &c);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+		skb->dev = dev->ndev;
+		__mctp_cb(skb);
+
+		rc = mctp_route_input(&rt->rt, skb);
+	}
+
+	skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+
+	if (params->rx_len) {
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+		KUNIT_EXPECT_EQ(test, skb2->len, params->rx_len);
+		skb_free_datagram(sock->sk, skb2);
+
+	} else {
+		KUNIT_EXPECT_NULL(test, skb2);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+#define RX_FRAG(f, s) RX_HDR(1, 10, 8, FL_TO | (f) | ((s) << MCTP_HDR_SEQ_SHIFT))
+
+static const struct mctp_route_input_sk_reasm_test mctp_route_input_sk_reasm_tests[] = {
+	{
+		.name = "single packet",
+		.hdrs = {
+			RX_FRAG(FL_S | FL_E, 0),
+		},
+		.n_hdrs = 1,
+		.rx_len = 1,
+	},
+	{
+		.name = "single packet, offset seq",
+		.hdrs = {
+			RX_FRAG(FL_S | FL_E, 1),
+		},
+		.n_hdrs = 1,
+		.rx_len = 1,
+	},
+	{
+		.name = "start & end packets",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(FL_E, 1),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+	{
+		.name = "start & end packets, offset seq",
+		.hdrs = {
+			RX_FRAG(FL_S, 1),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+	{
+		.name = "start & end packets, out of order",
+		.hdrs = {
+			RX_FRAG(FL_E, 1),
+			RX_FRAG(FL_S, 0),
+		},
+		.n_hdrs = 2,
+		.rx_len = 0,
+	},
+	{
+		.name = "start, middle & end packets",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(0,    1),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 3,
+		.rx_len = 3,
+	},
+	{
+		.name = "missing seq",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 2,
+		.rx_len = 0,
+	},
+	{
+		.name = "seq wrap",
+		.hdrs = {
+			RX_FRAG(FL_S, 3),
+			RX_FRAG(FL_E, 0),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+};
+
+static void mctp_route_input_sk_reasm_to_desc(
+				const struct mctp_route_input_sk_reasm_test *t,
+				char *desc)
+{
+	sprintf(desc, "%s", t->name);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk_reasm, mctp_route_input_sk_reasm_tests,
+		  mctp_route_input_sk_reasm_to_desc);
+
+struct mctp_route_input_sk_keys_test {
+	const char	*name;
+	mctp_eid_t	key_peer_addr;
+	mctp_eid_t	key_local_addr;
+	u8		key_tag;
+	struct mctp_hdr hdr;
+	bool		deliver;
+};
+
+/* test packet rx in the presence of various key configurations */
+static void mctp_test_route_input_sk_keys(struct kunit *test)
+{
+	const struct mctp_route_input_sk_keys_test *params;
+	struct mctp_test_route *rt;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_dev *dev;
+	struct mctp_sk_key *key;
+	struct netns_mctp *mns;
+	struct mctp_sock *msk;
+	struct socket *sock;
+	unsigned long flags;
+	int rc;
+	u8 c;
+
+	params = test->param_value;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	msk = container_of(sock->sk, struct mctp_sock, sk);
+	mns = &sock_net(sock->sk)->mctp;
+
+	/* set the incoming tag according to test params */
+	key = mctp_key_alloc(msk, params->key_local_addr, params->key_peer_addr,
+			     params->key_tag, GFP_KERNEL);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, key);
+
+	spin_lock_irqsave(&mns->keys_lock, flags);
+	mctp_reserve_tag(&init_net, key, msk);
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	/* create packet and route */
+	c = 0;
+	skb = mctp_test_create_skb_data(&params->hdr, &c);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	skb->dev = dev->ndev;
+	__mctp_cb(skb);
+
+	rc = mctp_route_input(&rt->rt, skb);
+
+	/* (potentially) receive message */
+	skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+
+	if (params->deliver)
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+	else
+		KUNIT_EXPECT_PTR_EQ(test, skb2, NULL);
+
+	if (skb2)
+		skb_free_datagram(sock->sk, skb2);
+
+	mctp_key_unref(key);
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+static const struct mctp_route_input_sk_keys_test mctp_route_input_sk_keys_tests[] = {
+	{
+		.name = "direct match",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+	{
+		.name = "flipped src/dest",
+		.key_peer_addr = 8,
+		.key_local_addr = 9,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = false,
+	},
+	{
+		.name = "peer addr mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = false,
+	},
+	{
+		.name = "tag value mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(2)),
+		.deliver = false,
+	},
+	{
+		.name = "TO mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1) | FL_TO),
+		.deliver = false,
+	},
+	{
+		.name = "broadcast response",
+		.key_peer_addr = MCTP_ADDR_ANY,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 11, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+	{
+		.name = "any local match",
+		.key_peer_addr = 12,
+		.key_local_addr = MCTP_ADDR_ANY,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 12, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+};
+
+static void mctp_route_input_sk_keys_to_desc(
+				const struct mctp_route_input_sk_keys_test *t,
+				char *desc)
+{
+	sprintf(desc, "%s", t->name);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk_keys, mctp_route_input_sk_keys_tests,
+		  mctp_route_input_sk_keys_to_desc);
+
+static struct kunit_case mctp_test_cases[] = {
+	KUNIT_CASE_PARAM(mctp_test_fragment, mctp_frag_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_rx_input, mctp_rx_input_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk, mctp_route_input_sk_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk_reasm,
+			 mctp_route_input_sk_reasm_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys,
+			 mctp_route_input_sk_keys_gen_params),
+	{}
+};
+
+static struct kunit_suite mctp_test_suite = {
+	.name = "mctp",
+	.test_cases = mctp_test_cases,
+};
+
+kunit_test_suite(mctp_test_suite);
diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c
new file mode 100644
index 000000000..e03ba66bb
--- /dev/null
+++ b/net/mctp/test/utils.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <linux/mctp.h>
+#include <linux/if_arp.h>
+
+#include <net/mctpdevice.h>
+#include <net/pkt_sched.h>
+
+#include "utils.h"
+
+static netdev_tx_t mctp_test_dev_tx(struct sk_buff *skb,
+				    struct net_device *ndev)
+{
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops mctp_test_netdev_ops = {
+	.ndo_start_xmit = mctp_test_dev_tx,
+};
+
+static void mctp_test_dev_setup(struct net_device *ndev)
+{
+	ndev->type = ARPHRD_MCTP;
+	ndev->mtu = MCTP_DEV_TEST_MTU;
+	ndev->hard_header_len = 0;
+	ndev->addr_len = 0;
+	ndev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
+	ndev->flags = IFF_NOARP;
+	ndev->netdev_ops = &mctp_test_netdev_ops;
+	ndev->needs_free_netdev = true;
+}
+
+struct mctp_test_dev *mctp_test_create_dev(void)
+{
+	struct mctp_test_dev *dev;
+	struct net_device *ndev;
+	int rc;
+
+	ndev = alloc_netdev(sizeof(*dev), "mctptest%d", NET_NAME_ENUM,
+			    mctp_test_dev_setup);
+	if (!ndev)
+		return NULL;
+
+	dev = netdev_priv(ndev);
+	dev->ndev = ndev;
+
+	rc = register_netdev(ndev);
+	if (rc) {
+		free_netdev(ndev);
+		return NULL;
+	}
+
+	rcu_read_lock();
+	dev->mdev = __mctp_dev_get(ndev);
+	rcu_read_unlock();
+
+	return dev;
+}
+
+void mctp_test_destroy_dev(struct mctp_test_dev *dev)
+{
+	mctp_dev_put(dev->mdev);
+	unregister_netdev(dev->ndev);
+}
diff --git a/net/mctp/test/utils.h b/net/mctp/test/utils.h
new file mode 100644
index 000000000..df6aa1c03
--- /dev/null
+++ b/net/mctp/test/utils.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NET_MCTP_TEST_UTILS_H
+#define __NET_MCTP_TEST_UTILS_H
+
+#include <kunit/test.h>
+
+#define MCTP_DEV_TEST_MTU	68
+
+struct mctp_test_dev {
+	struct net_device *ndev;
+	struct mctp_dev *mdev;
+};
+
+struct mctp_test_dev;
+
+struct mctp_test_dev *mctp_test_create_dev(void);
+void mctp_test_destroy_dev(struct mctp_test_dev *dev);
+
+#endif /* __NET_MCTP_TEST_UTILS_H */