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, 499 insertions, 0 deletions

diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
new file mode 100644
index 000000000..96bea1ab1
--- /dev/null
+++ b/drivers/atm/atmtcp.c
@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* drivers/atm/atmtcp.c - ATM over TCP "device" driver */
+
+/* Written 1997-2000 by Werner Almesberger, EPFL LRC/ICA */
+
+
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/atmdev.h>
+#include <linux/atm_tcp.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+
+
+extern int atm_init_aal5(struct atm_vcc *vcc); /* "raw" AAL5 transport */
+
+
+#define PRIV(dev) ((struct atmtcp_dev_data *) ((dev)->dev_data))
+
+
+struct atmtcp_dev_data {
+	struct atm_vcc *vcc;	/* control VCC; NULL if detached */
+	int persist;		/* non-zero if persistent */
+};
+
+
+#define DEV_LABEL    "atmtcp"
+
+#define MAX_VPI_BITS  8	/* simplifies life */
+#define MAX_VCI_BITS 16
+
+
+/*
+ * Hairy code ahead: the control VCC may be closed while we're still
+ * waiting for an answer, so we need to re-validate out_vcc every once
+ * in a while.
+ */
+
+
+static int atmtcp_send_control(struct atm_vcc *vcc,int type,
+    const struct atmtcp_control *msg,int flag)
+{
+	DECLARE_WAITQUEUE(wait,current);
+	struct atm_vcc *out_vcc;
+	struct sk_buff *skb;
+	struct atmtcp_control *new_msg;
+	int old_test;
+	int error = 0;
+
+	out_vcc = PRIV(vcc->dev) ? PRIV(vcc->dev)->vcc : NULL;
+	if (!out_vcc) return -EUNATCH;
+	skb = alloc_skb(sizeof(*msg),GFP_KERNEL);
+	if (!skb) return -ENOMEM;
+	mb();
+	out_vcc = PRIV(vcc->dev) ? PRIV(vcc->dev)->vcc : NULL;
+	if (!out_vcc) {
+		dev_kfree_skb(skb);
+		return -EUNATCH;
+	}
+	atm_force_charge(out_vcc,skb->truesize);
+	new_msg = skb_put(skb, sizeof(*new_msg));
+	*new_msg = *msg;
+	new_msg->hdr.length = ATMTCP_HDR_MAGIC;
+	new_msg->type = type;
+	memset(&new_msg->vcc,0,sizeof(atm_kptr_t));
+	*(struct atm_vcc **) &new_msg->vcc = vcc;
+	old_test = test_bit(flag,&vcc->flags);
+	out_vcc->push(out_vcc,skb);
+	add_wait_queue(sk_sleep(sk_atm(vcc)), &wait);
+	while (test_bit(flag,&vcc->flags) == old_test) {
+		mb();
+		out_vcc = PRIV(vcc->dev) ? PRIV(vcc->dev)->vcc : NULL;
+		if (!out_vcc) {
+			error = -EUNATCH;
+			break;
+		}
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule();
+	}
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(sk_sleep(sk_atm(vcc)), &wait);
+	return error;
+}
+
+
+static int atmtcp_recv_control(const struct atmtcp_control *msg)
+{
+	struct atm_vcc *vcc = *(struct atm_vcc **) &msg->vcc;
+
+	vcc->vpi = msg->addr.sap_addr.vpi;
+	vcc->vci = msg->addr.sap_addr.vci;
+	vcc->qos = msg->qos;
+	sk_atm(vcc)->sk_err = -msg->result;
+	switch (msg->type) {
+	    case ATMTCP_CTRL_OPEN:
+		change_bit(ATM_VF_READY,&vcc->flags);
+		break;
+	    case ATMTCP_CTRL_CLOSE:
+		change_bit(ATM_VF_ADDR,&vcc->flags);
+		break;
+	    default:
+		printk(KERN_ERR "atmtcp_recv_control: unknown type %d\n",
+		    msg->type);
+		return -EINVAL;
+	}
+	wake_up(sk_sleep(sk_atm(vcc)));
+	return 0;
+}
+
+
+static void atmtcp_v_dev_close(struct atm_dev *dev)
+{
+	/* Nothing.... Isn't this simple :-)  -- REW */
+}
+
+
+static int atmtcp_v_open(struct atm_vcc *vcc)
+{
+	struct atmtcp_control msg;
+	int error;
+	short vpi = vcc->vpi;
+	int vci = vcc->vci;
+
+	memset(&msg,0,sizeof(msg));
+	msg.addr.sap_family = AF_ATMPVC;
+	msg.hdr.vpi = htons(vpi);
+	msg.addr.sap_addr.vpi = vpi;
+	msg.hdr.vci = htons(vci);
+	msg.addr.sap_addr.vci = vci;
+	if (vpi == ATM_VPI_UNSPEC || vci == ATM_VCI_UNSPEC) return 0;
+	msg.type = ATMTCP_CTRL_OPEN;
+	msg.qos = vcc->qos;
+	set_bit(ATM_VF_ADDR,&vcc->flags);
+	clear_bit(ATM_VF_READY,&vcc->flags); /* just in case ... */
+	error = atmtcp_send_control(vcc,ATMTCP_CTRL_OPEN,&msg,ATM_VF_READY);
+	if (error) return error;
+	return -sk_atm(vcc)->sk_err;
+}
+
+
+static void atmtcp_v_close(struct atm_vcc *vcc)
+{
+	struct atmtcp_control msg;
+
+	memset(&msg,0,sizeof(msg));
+	msg.addr.sap_family = AF_ATMPVC;
+	msg.addr.sap_addr.vpi = vcc->vpi;
+	msg.addr.sap_addr.vci = vcc->vci;
+	clear_bit(ATM_VF_READY,&vcc->flags);
+	(void) atmtcp_send_control(vcc,ATMTCP_CTRL_CLOSE,&msg,ATM_VF_ADDR);
+}
+
+
+static int atmtcp_v_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
+{
+	struct atm_cirange ci;
+	struct atm_vcc *vcc;
+	struct sock *s;
+	int i;
+
+	if (cmd != ATM_SETCIRANGE) return -ENOIOCTLCMD;
+	if (copy_from_user(&ci, arg,sizeof(ci))) return -EFAULT;
+	if (ci.vpi_bits == ATM_CI_MAX) ci.vpi_bits = MAX_VPI_BITS;
+	if (ci.vci_bits == ATM_CI_MAX) ci.vci_bits = MAX_VCI_BITS;
+	if (ci.vpi_bits > MAX_VPI_BITS || ci.vpi_bits < 0 ||
+	    ci.vci_bits > MAX_VCI_BITS || ci.vci_bits < 0) return -EINVAL;
+	read_lock(&vcc_sklist_lock);
+	for(i = 0; i < VCC_HTABLE_SIZE; ++i) {
+		struct hlist_head *head = &vcc_hash[i];
+
+		sk_for_each(s, head) {
+			vcc = atm_sk(s);
+			if (vcc->dev != dev)
+				continue;
+			if ((vcc->vpi >> ci.vpi_bits) ||
+			    (vcc->vci >> ci.vci_bits)) {
+				read_unlock(&vcc_sklist_lock);
+				return -EBUSY;
+			}
+		}
+	}
+	read_unlock(&vcc_sklist_lock);
+	dev->ci_range = ci;
+	return 0;
+}
+
+
+static int atmtcp_v_send(struct atm_vcc *vcc,struct sk_buff *skb)
+{
+	struct atmtcp_dev_data *dev_data;
+	struct atm_vcc *out_vcc=NULL; /* Initializer quietens GCC warning */
+	struct sk_buff *new_skb;
+	struct atmtcp_hdr *hdr;
+	int size;
+
+	if (vcc->qos.txtp.traffic_class == ATM_NONE) {
+		if (vcc->pop) vcc->pop(vcc,skb);
+		else dev_kfree_skb(skb);
+		return -EINVAL;
+	}
+	dev_data = PRIV(vcc->dev);
+	if (dev_data) out_vcc = dev_data->vcc;
+	if (!dev_data || !out_vcc) {
+		if (vcc->pop) vcc->pop(vcc,skb);
+		else dev_kfree_skb(skb);
+		if (dev_data) return 0;
+		atomic_inc(&vcc->stats->tx_err);
+		return -ENOLINK;
+	}
+	size = skb->len+sizeof(struct atmtcp_hdr);
+	new_skb = atm_alloc_charge(out_vcc,size,GFP_ATOMIC);
+	if (!new_skb) {
+		if (vcc->pop) vcc->pop(vcc,skb);
+		else dev_kfree_skb(skb);
+		atomic_inc(&vcc->stats->tx_err);
+		return -ENOBUFS;
+	}
+	hdr = skb_put(new_skb, sizeof(struct atmtcp_hdr));
+	hdr->vpi = htons(vcc->vpi);
+	hdr->vci = htons(vcc->vci);
+	hdr->length = htonl(skb->len);
+	skb_copy_from_linear_data(skb, skb_put(new_skb, skb->len), skb->len);
+	if (vcc->pop) vcc->pop(vcc,skb);
+	else dev_kfree_skb(skb);
+	out_vcc->push(out_vcc,new_skb);
+	atomic_inc(&vcc->stats->tx);
+	atomic_inc(&out_vcc->stats->rx);
+	return 0;
+}
+
+
+static int atmtcp_v_proc(struct atm_dev *dev,loff_t *pos,char *page)
+{
+	struct atmtcp_dev_data *dev_data = PRIV(dev);
+
+	if (*pos) return 0;
+	if (!dev_data->persist) return sprintf(page,"ephemeral\n");
+	return sprintf(page,"persistent, %sconnected\n",
+	    dev_data->vcc ? "" : "dis");
+}
+
+
+static void atmtcp_c_close(struct atm_vcc *vcc)
+{
+	struct atm_dev *atmtcp_dev;
+	struct atmtcp_dev_data *dev_data;
+
+	atmtcp_dev = (struct atm_dev *) vcc->dev_data;
+	dev_data = PRIV(atmtcp_dev);
+	dev_data->vcc = NULL;
+	if (dev_data->persist) return;
+	atmtcp_dev->dev_data = NULL;
+	kfree(dev_data);
+	atm_dev_deregister(atmtcp_dev);
+	vcc->dev_data = NULL;
+	module_put(THIS_MODULE);
+}
+
+
+static struct atm_vcc *find_vcc(struct atm_dev *dev, short vpi, int vci)
+{
+        struct hlist_head *head;
+        struct atm_vcc *vcc;
+        struct sock *s;
+
+        head = &vcc_hash[vci & (VCC_HTABLE_SIZE -1)];
+
+	sk_for_each(s, head) {
+                vcc = atm_sk(s);
+                if (vcc->dev == dev &&
+                    vcc->vci == vci && vcc->vpi == vpi &&
+                    vcc->qos.rxtp.traffic_class != ATM_NONE) {
+                                return vcc;
+                }
+        }
+        return NULL;
+}
+
+
+static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
+{
+	struct atm_dev *dev;
+	struct atmtcp_hdr *hdr;
+	struct atm_vcc *out_vcc;
+	struct sk_buff *new_skb;
+	int result = 0;
+
+	if (!skb->len) return 0;
+	dev = vcc->dev_data;
+	hdr = (struct atmtcp_hdr *) skb->data;
+	if (hdr->length == ATMTCP_HDR_MAGIC) {
+		result = atmtcp_recv_control(
+		    (struct atmtcp_control *) skb->data);
+		goto done;
+	}
+	read_lock(&vcc_sklist_lock);
+	out_vcc = find_vcc(dev, ntohs(hdr->vpi), ntohs(hdr->vci));
+	read_unlock(&vcc_sklist_lock);
+	if (!out_vcc) {
+		result = -EUNATCH;
+		atomic_inc(&vcc->stats->tx_err);
+		goto done;
+	}
+	skb_pull(skb,sizeof(struct atmtcp_hdr));
+	new_skb = atm_alloc_charge(out_vcc,skb->len,GFP_KERNEL);
+	if (!new_skb) {
+		result = -ENOBUFS;
+		goto done;
+	}
+	__net_timestamp(new_skb);
+	skb_copy_from_linear_data(skb, skb_put(new_skb, skb->len), skb->len);
+	out_vcc->push(out_vcc,new_skb);
+	atomic_inc(&vcc->stats->tx);
+	atomic_inc(&out_vcc->stats->rx);
+done:
+	if (vcc->pop) vcc->pop(vcc,skb);
+	else dev_kfree_skb(skb);
+	return result;
+}
+
+
+/*
+ * Device operations for the virtual ATM devices created by ATMTCP.
+ */
+
+
+static const struct atmdev_ops atmtcp_v_dev_ops = {
+	.dev_close	= atmtcp_v_dev_close,
+	.open		= atmtcp_v_open,
+	.close		= atmtcp_v_close,
+	.ioctl		= atmtcp_v_ioctl,
+	.send		= atmtcp_v_send,
+	.proc_read	= atmtcp_v_proc,
+	.owner		= THIS_MODULE
+};
+
+
+/*
+ * Device operations for the ATMTCP control device.
+ */
+
+
+static const struct atmdev_ops atmtcp_c_dev_ops = {
+	.close		= atmtcp_c_close,
+	.send		= atmtcp_c_send
+};
+
+
+static struct atm_dev atmtcp_control_dev = {
+	.ops		= &atmtcp_c_dev_ops,
+	.type		= "atmtcp",
+	.number		= 999,
+	.lock		= __SPIN_LOCK_UNLOCKED(atmtcp_control_dev.lock)
+};
+
+
+static int atmtcp_create(int itf,int persist,struct atm_dev **result)
+{
+	struct atmtcp_dev_data *dev_data;
+	struct atm_dev *dev;
+
+	dev_data = kmalloc(sizeof(*dev_data),GFP_KERNEL);
+	if (!dev_data)
+		return -ENOMEM;
+
+	dev = atm_dev_register(DEV_LABEL,NULL,&atmtcp_v_dev_ops,itf,NULL);
+	if (!dev) {
+		kfree(dev_data);
+		return itf == -1 ? -ENOMEM : -EBUSY;
+	}
+	dev->ci_range.vpi_bits = MAX_VPI_BITS;
+	dev->ci_range.vci_bits = MAX_VCI_BITS;
+	dev->dev_data = dev_data;
+	PRIV(dev)->vcc = NULL;
+	PRIV(dev)->persist = persist;
+	if (result) *result = dev;
+	return 0;
+}
+
+
+static int atmtcp_attach(struct atm_vcc *vcc,int itf)
+{
+	struct atm_dev *dev;
+
+	dev = NULL;
+	if (itf != -1) dev = atm_dev_lookup(itf);
+	if (dev) {
+		if (dev->ops != &atmtcp_v_dev_ops) {
+			atm_dev_put(dev);
+			return -EMEDIUMTYPE;
+		}
+		if (PRIV(dev)->vcc) {
+			atm_dev_put(dev);
+			return -EBUSY;
+		}
+	}
+	else {
+		int error;
+
+		error = atmtcp_create(itf,0,&dev);
+		if (error) return error;
+	}
+	PRIV(dev)->vcc = vcc;
+	vcc->dev = &atmtcp_control_dev;
+	vcc_insert_socket(sk_atm(vcc));
+	set_bit(ATM_VF_META,&vcc->flags);
+	set_bit(ATM_VF_READY,&vcc->flags);
+	vcc->dev_data = dev;
+	(void) atm_init_aal5(vcc); /* @@@ losing AAL in transit ... */
+	vcc->stats = &atmtcp_control_dev.stats.aal5;
+	return dev->number;
+}
+
+
+static int atmtcp_create_persistent(int itf)
+{
+	return atmtcp_create(itf,1,NULL);
+}
+
+
+static int atmtcp_remove_persistent(int itf)
+{
+	struct atm_dev *dev;
+	struct atmtcp_dev_data *dev_data;
+
+	dev = atm_dev_lookup(itf);
+	if (!dev) return -ENODEV;
+	if (dev->ops != &atmtcp_v_dev_ops) {
+		atm_dev_put(dev);
+		return -EMEDIUMTYPE;
+	}
+	dev_data = PRIV(dev);
+	if (!dev_data->persist) {
+		atm_dev_put(dev);
+		return 0;
+	}
+	dev_data->persist = 0;
+	if (PRIV(dev)->vcc) {
+		atm_dev_put(dev);
+		return 0;
+	}
+	kfree(dev_data);
+	atm_dev_put(dev);
+	atm_dev_deregister(dev);
+	return 0;
+}
+
+static int atmtcp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	int err = 0;
+	struct atm_vcc *vcc = ATM_SD(sock);
+
+	if (cmd != SIOCSIFATMTCP && cmd != ATMTCP_CREATE && cmd != ATMTCP_REMOVE)
+		return -ENOIOCTLCMD;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	switch (cmd) {
+		case SIOCSIFATMTCP:
+			err = atmtcp_attach(vcc, (int) arg);
+			if (err >= 0) {
+				sock->state = SS_CONNECTED;
+				__module_get(THIS_MODULE);
+			}
+			break;
+		case ATMTCP_CREATE:
+			err = atmtcp_create_persistent((int) arg);
+			break;
+		case ATMTCP_REMOVE:
+			err = atmtcp_remove_persistent((int) arg);
+			break;
+	}
+	return err;
+}
+
+static struct atm_ioctl atmtcp_ioctl_ops = {
+	.owner 	= THIS_MODULE,
+	.ioctl	= atmtcp_ioctl,
+};
+
+static __init int atmtcp_init(void)
+{
+	register_atm_ioctl(&atmtcp_ioctl_ops);
+	return 0;
+}
+
+
+static void __exit atmtcp_exit(void)
+{
+	deregister_atm_ioctl(&atmtcp_ioctl_ops);
+}
+
+MODULE_LICENSE("GPL");
+module_init(atmtcp_init);
+module_exit(atmtcp_exit);