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().
  ...

1 files changed, 524 insertions, 0 deletions

diff --git a/drivers/net/mctp/mctp-serial.c b/drivers/net/mctp/mctp-serial.c
new file mode 100644
index 000000000..9f9eaf896
--- /dev/null
+++ b/drivers/net/mctp/mctp-serial.c
@@ -0,0 +1,524 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Management Component Transport Protocol (MCTP) - serial transport
+ * binding. This driver is an implementation of the DMTF specificiation
+ * "DSP0253 - Management Component Transport Protocol (MCTP) Serial Transport
+ * Binding", available at:
+ *
+ *  https://www.dmtf.org/sites/default/files/standards/documents/DSP0253_1.0.0.pdf
+ *
+ * This driver provides DSP0253-type MCTP-over-serial transport using a Linux
+ * tty device, by setting the N_MCTP line discipline on the tty.
+ *
+ * Copyright (c) 2021 Code Construct
+ */
+
+#include <linux/idr.h>
+#include <linux/if_arp.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/tty.h>
+#include <linux/workqueue.h>
+#include <linux/crc-ccitt.h>
+
+#include <linux/mctp.h>
+#include <net/mctp.h>
+#include <net/pkt_sched.h>
+
+#define MCTP_SERIAL_MTU		68 /* base mtu (64) + mctp header */
+#define MCTP_SERIAL_FRAME_MTU	(MCTP_SERIAL_MTU + 6) /* + serial framing */
+
+#define MCTP_SERIAL_VERSION	0x1 /* DSP0253 defines a single version: 1 */
+
+#define BUFSIZE			MCTP_SERIAL_FRAME_MTU
+
+#define BYTE_FRAME		0x7e
+#define BYTE_ESC		0x7d
+
+#define FCS_INIT		0xffff
+
+static DEFINE_IDA(mctp_serial_ida);
+
+enum mctp_serial_state {
+	STATE_IDLE,
+	STATE_START,
+	STATE_HEADER,
+	STATE_DATA,
+	STATE_ESCAPE,
+	STATE_TRAILER,
+	STATE_DONE,
+	STATE_ERR,
+};
+
+struct mctp_serial {
+	struct net_device	*netdev;
+	struct tty_struct	*tty;
+
+	int			idx;
+
+	/* protects our rx & tx state machines; held during both paths */
+	spinlock_t		lock;
+
+	struct work_struct	tx_work;
+	enum mctp_serial_state	txstate, rxstate;
+	u16			txfcs, rxfcs, rxfcs_rcvd;
+	unsigned int		txlen, rxlen;
+	unsigned int		txpos, rxpos;
+	unsigned char		txbuf[BUFSIZE],
+				rxbuf[BUFSIZE];
+};
+
+static bool needs_escape(unsigned char c)
+{
+	return c == BYTE_ESC || c == BYTE_FRAME;
+}
+
+static int next_chunk_len(struct mctp_serial *dev)
+{
+	int i;
+
+	/* either we have no bytes to send ... */
+	if (dev->txpos == dev->txlen)
+		return 0;
+
+	/* ... or the next byte to send is an escaped byte; requiring a
+	 * single-byte chunk...
+	 */
+	if (needs_escape(dev->txbuf[dev->txpos]))
+		return 1;
+
+	/* ... or we have one or more bytes up to the next escape - this chunk
+	 * will be those non-escaped bytes, and does not include the escaped
+	 * byte.
+	 */
+	for (i = 1; i + dev->txpos + 1 < dev->txlen; i++) {
+		if (needs_escape(dev->txbuf[dev->txpos + i + 1]))
+			break;
+	}
+
+	return i;
+}
+
+static int write_chunk(struct mctp_serial *dev, unsigned char *buf, int len)
+{
+	return dev->tty->ops->write(dev->tty, buf, len);
+}
+
+static void mctp_serial_tx_work(struct work_struct *work)
+{
+	struct mctp_serial *dev = container_of(work, struct mctp_serial,
+					       tx_work);
+	unsigned char c, buf[3];
+	unsigned long flags;
+	int len, txlen;
+
+	spin_lock_irqsave(&dev->lock, flags);
+
+	/* txstate represents the next thing to send */
+	switch (dev->txstate) {
+	case STATE_START:
+		dev->txpos = 0;
+		fallthrough;
+	case STATE_HEADER:
+		buf[0] = BYTE_FRAME;
+		buf[1] = MCTP_SERIAL_VERSION;
+		buf[2] = dev->txlen;
+
+		if (!dev->txpos)
+			dev->txfcs = crc_ccitt(FCS_INIT, buf + 1, 2);
+
+		txlen = write_chunk(dev, buf + dev->txpos, 3 - dev->txpos);
+		if (txlen <= 0) {
+			dev->txstate = STATE_ERR;
+		} else {
+			dev->txpos += txlen;
+			if (dev->txpos == 3) {
+				dev->txstate = STATE_DATA;
+				dev->txpos = 0;
+			}
+		}
+		break;
+
+	case STATE_ESCAPE:
+		buf[0] = dev->txbuf[dev->txpos] & ~0x20;
+		txlen = write_chunk(dev, buf, 1);
+		if (txlen <= 0) {
+			dev->txstate = STATE_ERR;
+		} else {
+			dev->txpos += txlen;
+			if (dev->txpos == dev->txlen) {
+				dev->txstate = STATE_TRAILER;
+				dev->txpos = 0;
+			}
+		}
+
+		break;
+
+	case STATE_DATA:
+		len = next_chunk_len(dev);
+		if (len) {
+			c = dev->txbuf[dev->txpos];
+			if (len == 1 && needs_escape(c)) {
+				buf[0] = BYTE_ESC;
+				buf[1] = c & ~0x20;
+				dev->txfcs = crc_ccitt_byte(dev->txfcs, c);
+				txlen = write_chunk(dev, buf, 2);
+				if (txlen == 2)
+					dev->txpos++;
+				else if (txlen == 1)
+					dev->txstate = STATE_ESCAPE;
+				else
+					dev->txstate = STATE_ERR;
+			} else {
+				txlen = write_chunk(dev,
+						    dev->txbuf + dev->txpos,
+						    len);
+				if (txlen <= 0) {
+					dev->txstate = STATE_ERR;
+				} else {
+					dev->txfcs = crc_ccitt(dev->txfcs,
+							       dev->txbuf +
+							       dev->txpos,
+							       txlen);
+					dev->txpos += txlen;
+				}
+			}
+			if (dev->txstate == STATE_DATA &&
+			    dev->txpos == dev->txlen) {
+				dev->txstate = STATE_TRAILER;
+				dev->txpos = 0;
+			}
+			break;
+		}
+		dev->txstate = STATE_TRAILER;
+		dev->txpos = 0;
+		fallthrough;
+
+	case STATE_TRAILER:
+		buf[0] = dev->txfcs >> 8;
+		buf[1] = dev->txfcs & 0xff;
+		buf[2] = BYTE_FRAME;
+		txlen = write_chunk(dev, buf + dev->txpos, 3 - dev->txpos);
+		if (txlen <= 0) {
+			dev->txstate = STATE_ERR;
+		} else {
+			dev->txpos += txlen;
+			if (dev->txpos == 3) {
+				dev->txstate = STATE_DONE;
+				dev->txpos = 0;
+			}
+		}
+		break;
+	default:
+		netdev_err_once(dev->netdev, "invalid tx state %d\n",
+				dev->txstate);
+	}
+
+	if (dev->txstate == STATE_DONE) {
+		dev->netdev->stats.tx_packets++;
+		dev->netdev->stats.tx_bytes += dev->txlen;
+		dev->txlen = 0;
+		dev->txpos = 0;
+		clear_bit(TTY_DO_WRITE_WAKEUP, &dev->tty->flags);
+		dev->txstate = STATE_IDLE;
+		spin_unlock_irqrestore(&dev->lock, flags);
+
+		netif_wake_queue(dev->netdev);
+	} else {
+		spin_unlock_irqrestore(&dev->lock, flags);
+	}
+}
+
+static netdev_tx_t mctp_serial_tx(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct mctp_serial *dev = netdev_priv(ndev);
+	unsigned long flags;
+
+	WARN_ON(dev->txstate != STATE_IDLE);
+
+	if (skb->len > MCTP_SERIAL_MTU) {
+		dev->netdev->stats.tx_dropped++;
+		goto out;
+	}
+
+	spin_lock_irqsave(&dev->lock, flags);
+	netif_stop_queue(dev->netdev);
+	skb_copy_bits(skb, 0, dev->txbuf, skb->len);
+	dev->txpos = 0;
+	dev->txlen = skb->len;
+	dev->txstate = STATE_START;
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	set_bit(TTY_DO_WRITE_WAKEUP, &dev->tty->flags);
+	schedule_work(&dev->tx_work);
+
+out:
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static void mctp_serial_tty_write_wakeup(struct tty_struct *tty)
+{
+	struct mctp_serial *dev = tty->disc_data;
+
+	schedule_work(&dev->tx_work);
+}
+
+static void mctp_serial_rx(struct mctp_serial *dev)
+{
+	struct mctp_skb_cb *cb;
+	struct sk_buff *skb;
+
+	if (dev->rxfcs != dev->rxfcs_rcvd) {
+		dev->netdev->stats.rx_dropped++;
+		dev->netdev->stats.rx_crc_errors++;
+		return;
+	}
+
+	skb = netdev_alloc_skb(dev->netdev, dev->rxlen);
+	if (!skb) {
+		dev->netdev->stats.rx_dropped++;
+		return;
+	}
+
+	skb->protocol = htons(ETH_P_MCTP);
+	skb_put_data(skb, dev->rxbuf, dev->rxlen);
+	skb_reset_network_header(skb);
+
+	cb = __mctp_cb(skb);
+	cb->halen = 0;
+
+	netif_rx(skb);
+	dev->netdev->stats.rx_packets++;
+	dev->netdev->stats.rx_bytes += dev->rxlen;
+}
+
+static void mctp_serial_push_header(struct mctp_serial *dev, unsigned char c)
+{
+	switch (dev->rxpos) {
+	case 0:
+		if (c == BYTE_FRAME)
+			dev->rxpos++;
+		else
+			dev->rxstate = STATE_ERR;
+		break;
+	case 1:
+		if (c == MCTP_SERIAL_VERSION) {
+			dev->rxpos++;
+			dev->rxfcs = crc_ccitt_byte(FCS_INIT, c);
+		} else {
+			dev->rxstate = STATE_ERR;
+		}
+		break;
+	case 2:
+		if (c > MCTP_SERIAL_FRAME_MTU) {
+			dev->rxstate = STATE_ERR;
+		} else {
+			dev->rxlen = c;
+			dev->rxpos = 0;
+			dev->rxstate = STATE_DATA;
+			dev->rxfcs = crc_ccitt_byte(dev->rxfcs, c);
+		}
+		break;
+	}
+}
+
+static void mctp_serial_push_trailer(struct mctp_serial *dev, unsigned char c)
+{
+	switch (dev->rxpos) {
+	case 0:
+		dev->rxfcs_rcvd = c << 8;
+		dev->rxpos++;
+		break;
+	case 1:
+		dev->rxfcs_rcvd |= c;
+		dev->rxpos++;
+		break;
+	case 2:
+		if (c != BYTE_FRAME) {
+			dev->rxstate = STATE_ERR;
+		} else {
+			mctp_serial_rx(dev);
+			dev->rxlen = 0;
+			dev->rxpos = 0;
+			dev->rxstate = STATE_IDLE;
+		}
+		break;
+	}
+}
+
+static void mctp_serial_push(struct mctp_serial *dev, unsigned char c)
+{
+	switch (dev->rxstate) {
+	case STATE_IDLE:
+		dev->rxstate = STATE_HEADER;
+		fallthrough;
+	case STATE_HEADER:
+		mctp_serial_push_header(dev, c);
+		break;
+
+	case STATE_ESCAPE:
+		c |= 0x20;
+		fallthrough;
+	case STATE_DATA:
+		if (dev->rxstate != STATE_ESCAPE && c == BYTE_ESC) {
+			dev->rxstate = STATE_ESCAPE;
+		} else {
+			dev->rxfcs = crc_ccitt_byte(dev->rxfcs, c);
+			dev->rxbuf[dev->rxpos] = c;
+			dev->rxpos++;
+			dev->rxstate = STATE_DATA;
+			if (dev->rxpos == dev->rxlen) {
+				dev->rxpos = 0;
+				dev->rxstate = STATE_TRAILER;
+			}
+		}
+		break;
+
+	case STATE_TRAILER:
+		mctp_serial_push_trailer(dev, c);
+		break;
+
+	case STATE_ERR:
+		if (c == BYTE_FRAME)
+			dev->rxstate = STATE_IDLE;
+		break;
+
+	default:
+		netdev_err_once(dev->netdev, "invalid rx state %d\n",
+				dev->rxstate);
+	}
+}
+
+static void mctp_serial_tty_receive_buf(struct tty_struct *tty,
+					const unsigned char *c,
+					const char *f, int len)
+{
+	struct mctp_serial *dev = tty->disc_data;
+	int i;
+
+	if (!netif_running(dev->netdev))
+		return;
+
+	/* we don't (currently) use the flag bytes, just data. */
+	for (i = 0; i < len; i++)
+		mctp_serial_push(dev, c[i]);
+}
+
+static void mctp_serial_uninit(struct net_device *ndev)
+{
+	struct mctp_serial *dev = netdev_priv(ndev);
+
+	cancel_work_sync(&dev->tx_work);
+}
+
+static const struct net_device_ops mctp_serial_netdev_ops = {
+	.ndo_start_xmit = mctp_serial_tx,
+	.ndo_uninit = mctp_serial_uninit,
+};
+
+static void mctp_serial_setup(struct net_device *ndev)
+{
+	ndev->type = ARPHRD_MCTP;
+
+	/* we limit at the fixed MTU, which is also the MCTP-standard
+	 * baseline MTU, so is also our minimum
+	 */
+	ndev->mtu = MCTP_SERIAL_MTU;
+	ndev->max_mtu = MCTP_SERIAL_MTU;
+	ndev->min_mtu = MCTP_SERIAL_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_serial_netdev_ops;
+	ndev->needs_free_netdev = true;
+}
+
+static int mctp_serial_open(struct tty_struct *tty)
+{
+	struct mctp_serial *dev;
+	struct net_device *ndev;
+	char name[32];
+	int idx, rc;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (!tty->ops->write)
+		return -EOPNOTSUPP;
+
+	idx = ida_alloc(&mctp_serial_ida, GFP_KERNEL);
+	if (idx < 0)
+		return idx;
+
+	snprintf(name, sizeof(name), "mctpserial%d", idx);
+	ndev = alloc_netdev(sizeof(*dev), name, NET_NAME_ENUM,
+			    mctp_serial_setup);
+	if (!ndev) {
+		rc = -ENOMEM;
+		goto free_ida;
+	}
+
+	dev = netdev_priv(ndev);
+	dev->idx = idx;
+	dev->tty = tty;
+	dev->netdev = ndev;
+	dev->txstate = STATE_IDLE;
+	dev->rxstate = STATE_IDLE;
+	spin_lock_init(&dev->lock);
+	INIT_WORK(&dev->tx_work, mctp_serial_tx_work);
+
+	rc = register_netdev(ndev);
+	if (rc)
+		goto free_netdev;
+
+	tty->receive_room = 64 * 1024;
+	tty->disc_data = dev;
+
+	return 0;
+
+free_netdev:
+	free_netdev(ndev);
+
+free_ida:
+	ida_free(&mctp_serial_ida, idx);
+	return rc;
+}
+
+static void mctp_serial_close(struct tty_struct *tty)
+{
+	struct mctp_serial *dev = tty->disc_data;
+	int idx = dev->idx;
+
+	unregister_netdev(dev->netdev);
+	ida_free(&mctp_serial_ida, idx);
+}
+
+static struct tty_ldisc_ops mctp_ldisc = {
+	.owner		= THIS_MODULE,
+	.num		= N_MCTP,
+	.name		= "mctp",
+	.open		= mctp_serial_open,
+	.close		= mctp_serial_close,
+	.receive_buf	= mctp_serial_tty_receive_buf,
+	.write_wakeup	= mctp_serial_tty_write_wakeup,
+};
+
+static int __init mctp_serial_init(void)
+{
+	return tty_register_ldisc(&mctp_ldisc);
+}
+
+static void __exit mctp_serial_exit(void)
+{
+	tty_unregister_ldisc(&mctp_ldisc);
+}
+
+module_init(mctp_serial_init);
+module_exit(mctp_serial_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jeremy Kerr <jk@codeconstruct.com.au>");
+MODULE_DESCRIPTION("MCTP Serial transport");