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, 491 insertions, 0 deletions

diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
new file mode 100644
index 000000000..3e4f17d33
--- /dev/null
+++ b/net/atm/pppoatm.c
@@ -0,0 +1,491 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* net/atm/pppoatm.c - RFC2364 PPP over ATM/AAL5 */
+
+/* Copyright 1999-2000 by Mitchell Blank Jr */
+/* Based on clip.c; 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+/* And on ppp_async.c; Copyright 1999 Paul Mackerras */
+/* And help from Jens Axboe */
+
+/*
+ *
+ * This driver provides the encapsulation and framing for sending
+ * and receiving PPP frames in ATM AAL5 PDUs.
+ */
+
+/*
+ * One shortcoming of this driver is that it does not comply with
+ * section 8 of RFC2364 - we are supposed to detect a change
+ * in encapsulation and immediately abort the connection (in order
+ * to avoid a black-hole being created if our peer loses state
+ * and changes encapsulation unilaterally.  However, since the
+ * ppp_generic layer actually does the decapsulation, we need
+ * a way of notifying it when we _think_ there might be a problem)
+ * There's two cases:
+ *   1.	LLC-encapsulation was missing when it was enabled.  In
+ *	this case, we should tell the upper layer "tear down
+ *	this session if this skb looks ok to you"
+ *   2.	LLC-encapsulation was present when it was disabled.  Then
+ *	we need to tell the upper layer "this packet may be
+ *	ok, but if its in error tear down the session"
+ * These hooks are not yet available in ppp_generic
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/atm.h>
+#include <linux/atmdev.h>
+#include <linux/capability.h>
+#include <linux/ppp_defs.h>
+#include <linux/ppp-ioctl.h>
+#include <linux/ppp_channel.h>
+#include <linux/atmppp.h>
+
+#include "common.h"
+
+enum pppoatm_encaps {
+	e_autodetect = PPPOATM_ENCAPS_AUTODETECT,
+	e_vc = PPPOATM_ENCAPS_VC,
+	e_llc = PPPOATM_ENCAPS_LLC,
+};
+
+struct pppoatm_vcc {
+	struct atm_vcc	*atmvcc;	/* VCC descriptor */
+	void (*old_push)(struct atm_vcc *, struct sk_buff *);
+	void (*old_pop)(struct atm_vcc *, struct sk_buff *);
+	void (*old_release_cb)(struct atm_vcc *);
+	struct module *old_owner;
+					/* keep old push/pop for detaching */
+	enum pppoatm_encaps encaps;
+	atomic_t inflight;
+	unsigned long blocked;
+	int flags;			/* SC_COMP_PROT - compress protocol */
+	struct ppp_channel chan;	/* interface to generic ppp layer */
+	struct tasklet_struct wakeup_tasklet;
+};
+
+/*
+ * We want to allow two packets in the queue. The one that's currently in
+ * flight, and *one* queued up ready for the ATM device to send immediately
+ * from its TX done IRQ. We want to be able to use atomic_inc_not_zero(), so
+ * inflight == -2 represents an empty queue, -1 one packet, and zero means
+ * there are two packets in the queue.
+ */
+#define NONE_INFLIGHT -2
+
+#define BLOCKED 0
+
+/*
+ * Header used for LLC Encapsulated PPP (4 bytes) followed by the LCP protocol
+ * ID (0xC021) used in autodetection
+ */
+static const unsigned char pppllc[6] = { 0xFE, 0xFE, 0x03, 0xCF, 0xC0, 0x21 };
+#define LLC_LEN		(4)
+
+static inline struct pppoatm_vcc *atmvcc_to_pvcc(const struct atm_vcc *atmvcc)
+{
+	return (struct pppoatm_vcc *) (atmvcc->user_back);
+}
+
+static inline struct pppoatm_vcc *chan_to_pvcc(const struct ppp_channel *chan)
+{
+	return (struct pppoatm_vcc *) (chan->private);
+}
+
+/*
+ * We can't do this directly from our _pop handler, since the ppp code
+ * doesn't want to be called in interrupt context, so we do it from
+ * a tasklet
+ */
+static void pppoatm_wakeup_sender(struct tasklet_struct *t)
+{
+	struct pppoatm_vcc *pvcc = from_tasklet(pvcc, t, wakeup_tasklet);
+
+	ppp_output_wakeup(&pvcc->chan);
+}
+
+static void pppoatm_release_cb(struct atm_vcc *atmvcc)
+{
+	struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc);
+
+	/*
+	 * As in pppoatm_pop(), it's safe to clear the BLOCKED bit here because
+	 * the wakeup *can't* race with pppoatm_send(). They both hold the PPP
+	 * channel's ->downl lock. And the potential race with *setting* it,
+	 * which leads to the double-check dance in pppoatm_may_send(), doesn't
+	 * exist here. In the sock_owned_by_user() case in pppoatm_send(), we
+	 * set the BLOCKED bit while the socket is still locked. We know that
+	 * ->release_cb() can't be called until that's done.
+	 */
+	if (test_and_clear_bit(BLOCKED, &pvcc->blocked))
+		tasklet_schedule(&pvcc->wakeup_tasklet);
+	if (pvcc->old_release_cb)
+		pvcc->old_release_cb(atmvcc);
+}
+/*
+ * This gets called every time the ATM card has finished sending our
+ * skb.  The ->old_pop will take care up normal atm flow control,
+ * but we also need to wake up the device if we blocked it
+ */
+static void pppoatm_pop(struct atm_vcc *atmvcc, struct sk_buff *skb)
+{
+	struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc);
+
+	pvcc->old_pop(atmvcc, skb);
+	atomic_dec(&pvcc->inflight);
+
+	/*
+	 * We always used to run the wakeup tasklet unconditionally here, for
+	 * fear of race conditions where we clear the BLOCKED flag just as we
+	 * refuse another packet in pppoatm_send(). This was quite inefficient.
+	 *
+	 * In fact it's OK. The PPP core will only ever call pppoatm_send()
+	 * while holding the channel->downl lock. And ppp_output_wakeup() as
+	 * called by the tasklet will *also* grab that lock. So even if another
+	 * CPU is in pppoatm_send() right now, the tasklet isn't going to race
+	 * with it. The wakeup *will* happen after the other CPU is safely out
+	 * of pppoatm_send() again.
+	 *
+	 * So if the CPU in pppoatm_send() has already set the BLOCKED bit and
+	 * it about to return, that's fine. We trigger a wakeup which will
+	 * happen later. And if the CPU in pppoatm_send() *hasn't* set the
+	 * BLOCKED bit yet, that's fine too because of the double check in
+	 * pppoatm_may_send() which is commented there.
+	 */
+	if (test_and_clear_bit(BLOCKED, &pvcc->blocked))
+		tasklet_schedule(&pvcc->wakeup_tasklet);
+}
+
+/*
+ * Unbind from PPP - currently we only do this when closing the socket,
+ * but we could put this into an ioctl if need be
+ */
+static void pppoatm_unassign_vcc(struct atm_vcc *atmvcc)
+{
+	struct pppoatm_vcc *pvcc;
+	pvcc = atmvcc_to_pvcc(atmvcc);
+	atmvcc->push = pvcc->old_push;
+	atmvcc->pop = pvcc->old_pop;
+	atmvcc->release_cb = pvcc->old_release_cb;
+	tasklet_kill(&pvcc->wakeup_tasklet);
+	ppp_unregister_channel(&pvcc->chan);
+	atmvcc->user_back = NULL;
+	kfree(pvcc);
+}
+
+/* Called when an AAL5 PDU comes in */
+static void pppoatm_push(struct atm_vcc *atmvcc, struct sk_buff *skb)
+{
+	struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc);
+	pr_debug("\n");
+	if (skb == NULL) {			/* VCC was closed */
+		struct module *module;
+
+		pr_debug("removing ATMPPP VCC %p\n", pvcc);
+		module = pvcc->old_owner;
+		pppoatm_unassign_vcc(atmvcc);
+		atmvcc->push(atmvcc, NULL);	/* Pass along bad news */
+		module_put(module);
+		return;
+	}
+	atm_return(atmvcc, skb->truesize);
+	switch (pvcc->encaps) {
+	case e_llc:
+		if (skb->len < LLC_LEN ||
+		    memcmp(skb->data, pppllc, LLC_LEN))
+			goto error;
+		skb_pull(skb, LLC_LEN);
+		break;
+	case e_autodetect:
+		if (pvcc->chan.ppp == NULL) {	/* Not bound yet! */
+			kfree_skb(skb);
+			return;
+		}
+		if (skb->len >= sizeof(pppllc) &&
+		    !memcmp(skb->data, pppllc, sizeof(pppllc))) {
+			pvcc->encaps = e_llc;
+			skb_pull(skb, LLC_LEN);
+			break;
+		}
+		if (skb->len >= (sizeof(pppllc) - LLC_LEN) &&
+		    !memcmp(skb->data, &pppllc[LLC_LEN],
+		    sizeof(pppllc) - LLC_LEN)) {
+			pvcc->encaps = e_vc;
+			pvcc->chan.mtu += LLC_LEN;
+			break;
+		}
+		pr_debug("Couldn't autodetect yet (skb: %6ph)\n", skb->data);
+		goto error;
+	case e_vc:
+		break;
+	}
+	ppp_input(&pvcc->chan, skb);
+	return;
+
+error:
+	kfree_skb(skb);
+	ppp_input_error(&pvcc->chan, 0);
+}
+
+static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size)
+{
+	/*
+	 * It's not clear that we need to bother with using atm_may_send()
+	 * to check we don't exceed sk->sk_sndbuf. If userspace sets a
+	 * value of sk_sndbuf which is lower than the MTU, we're going to
+	 * block for ever. But the code always did that before we introduced
+	 * the packet count limit, so...
+	 */
+	if (atm_may_send(pvcc->atmvcc, size) &&
+	    atomic_inc_not_zero(&pvcc->inflight))
+		return 1;
+
+	/*
+	 * We use test_and_set_bit() rather than set_bit() here because
+	 * we need to ensure there's a memory barrier after it. The bit
+	 * *must* be set before we do the atomic_inc() on pvcc->inflight.
+	 * There's no smp_mb__after_set_bit(), so it's this or abuse
+	 * smp_mb__after_atomic().
+	 */
+	test_and_set_bit(BLOCKED, &pvcc->blocked);
+
+	/*
+	 * We may have raced with pppoatm_pop(). If it ran for the
+	 * last packet in the queue, *just* before we set the BLOCKED
+	 * bit, then it might never run again and the channel could
+	 * remain permanently blocked. Cope with that race by checking
+	 * *again*. If it did run in that window, we'll have space on
+	 * the queue now and can return success. It's harmless to leave
+	 * the BLOCKED flag set, since it's only used as a trigger to
+	 * run the wakeup tasklet. Another wakeup will never hurt.
+	 * If pppoatm_pop() is running but hasn't got as far as making
+	 * space on the queue yet, then it hasn't checked the BLOCKED
+	 * flag yet either, so we're safe in that case too. It'll issue
+	 * an "immediate" wakeup... where "immediate" actually involves
+	 * taking the PPP channel's ->downl lock, which is held by the
+	 * code path that calls pppoatm_send(), and is thus going to
+	 * wait for us to finish.
+	 */
+	if (atm_may_send(pvcc->atmvcc, size) &&
+	    atomic_inc_not_zero(&pvcc->inflight))
+		return 1;
+
+	return 0;
+}
+/*
+ * Called by the ppp_generic.c to send a packet - returns true if packet
+ * was accepted.  If we return false, then it's our job to call
+ * ppp_output_wakeup(chan) when we're feeling more up to it.
+ * Note that in the ENOMEM case (as opposed to the !atm_may_send case)
+ * we should really drop the packet, but the generic layer doesn't
+ * support this yet.  We just return 'DROP_PACKET' which we actually define
+ * as success, just to be clear what we're really doing.
+ */
+#define DROP_PACKET 1
+static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
+{
+	struct pppoatm_vcc *pvcc = chan_to_pvcc(chan);
+	struct atm_vcc *vcc;
+	int ret;
+
+	ATM_SKB(skb)->vcc = pvcc->atmvcc;
+	pr_debug("(skb=0x%p, vcc=0x%p)\n", skb, pvcc->atmvcc);
+	if (skb->data[0] == '\0' && (pvcc->flags & SC_COMP_PROT))
+		(void) skb_pull(skb, 1);
+
+	vcc = ATM_SKB(skb)->vcc;
+	bh_lock_sock(sk_atm(vcc));
+	if (sock_owned_by_user(sk_atm(vcc))) {
+		/*
+		 * Needs to happen (and be flushed, hence test_and_) before we unlock
+		 * the socket. It needs to be seen by the time our ->release_cb gets
+		 * called.
+		 */
+		test_and_set_bit(BLOCKED, &pvcc->blocked);
+		goto nospace;
+	}
+	if (test_bit(ATM_VF_RELEASED, &vcc->flags) ||
+	    test_bit(ATM_VF_CLOSE, &vcc->flags) ||
+	    !test_bit(ATM_VF_READY, &vcc->flags)) {
+		bh_unlock_sock(sk_atm(vcc));
+		kfree_skb(skb);
+		return DROP_PACKET;
+	}
+
+	switch (pvcc->encaps) {		/* LLC encapsulation needed */
+	case e_llc:
+		if (skb_headroom(skb) < LLC_LEN) {
+			struct sk_buff *n;
+			n = skb_realloc_headroom(skb, LLC_LEN);
+			if (n != NULL &&
+			    !pppoatm_may_send(pvcc, n->truesize)) {
+				kfree_skb(n);
+				goto nospace;
+			}
+			consume_skb(skb);
+			skb = n;
+			if (skb == NULL) {
+				bh_unlock_sock(sk_atm(vcc));
+				return DROP_PACKET;
+			}
+		} else if (!pppoatm_may_send(pvcc, skb->truesize))
+			goto nospace;
+		memcpy(skb_push(skb, LLC_LEN), pppllc, LLC_LEN);
+		break;
+	case e_vc:
+		if (!pppoatm_may_send(pvcc, skb->truesize))
+			goto nospace;
+		break;
+	case e_autodetect:
+		bh_unlock_sock(sk_atm(vcc));
+		pr_debug("Trying to send without setting encaps!\n");
+		kfree_skb(skb);
+		return 1;
+	}
+
+	atm_account_tx(vcc, skb);
+	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
+		 skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
+	ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
+	    ? DROP_PACKET : 1;
+	bh_unlock_sock(sk_atm(vcc));
+	return ret;
+nospace:
+	bh_unlock_sock(sk_atm(vcc));
+	/*
+	 * We don't have space to send this SKB now, but we might have
+	 * already applied SC_COMP_PROT compression, so may need to undo
+	 */
+	if ((pvcc->flags & SC_COMP_PROT) && skb_headroom(skb) > 0 &&
+	    skb->data[-1] == '\0')
+		(void) skb_push(skb, 1);
+	return 0;
+}
+
+/* This handles ioctls sent to the /dev/ppp interface */
+static int pppoatm_devppp_ioctl(struct ppp_channel *chan, unsigned int cmd,
+	unsigned long arg)
+{
+	switch (cmd) {
+	case PPPIOCGFLAGS:
+		return put_user(chan_to_pvcc(chan)->flags, (int __user *) arg)
+		    ? -EFAULT : 0;
+	case PPPIOCSFLAGS:
+		return get_user(chan_to_pvcc(chan)->flags, (int __user *) arg)
+		    ? -EFAULT : 0;
+	}
+	return -ENOTTY;
+}
+
+static const struct ppp_channel_ops pppoatm_ops = {
+	.start_xmit = pppoatm_send,
+	.ioctl = pppoatm_devppp_ioctl,
+};
+
+static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg)
+{
+	struct atm_backend_ppp be;
+	struct pppoatm_vcc *pvcc;
+	int err;
+
+	if (copy_from_user(&be, arg, sizeof be))
+		return -EFAULT;
+	if (be.encaps != PPPOATM_ENCAPS_AUTODETECT &&
+	    be.encaps != PPPOATM_ENCAPS_VC && be.encaps != PPPOATM_ENCAPS_LLC)
+		return -EINVAL;
+	pvcc = kzalloc(sizeof(*pvcc), GFP_KERNEL);
+	if (pvcc == NULL)
+		return -ENOMEM;
+	pvcc->atmvcc = atmvcc;
+
+	/* Maximum is zero, so that we can use atomic_inc_not_zero() */
+	atomic_set(&pvcc->inflight, NONE_INFLIGHT);
+	pvcc->old_push = atmvcc->push;
+	pvcc->old_pop = atmvcc->pop;
+	pvcc->old_owner = atmvcc->owner;
+	pvcc->old_release_cb = atmvcc->release_cb;
+	pvcc->encaps = (enum pppoatm_encaps) be.encaps;
+	pvcc->chan.private = pvcc;
+	pvcc->chan.ops = &pppoatm_ops;
+	pvcc->chan.mtu = atmvcc->qos.txtp.max_sdu - PPP_HDRLEN -
+	    (be.encaps == e_vc ? 0 : LLC_LEN);
+	tasklet_setup(&pvcc->wakeup_tasklet, pppoatm_wakeup_sender);
+	err = ppp_register_channel(&pvcc->chan);
+	if (err != 0) {
+		kfree(pvcc);
+		return err;
+	}
+	atmvcc->user_back = pvcc;
+	atmvcc->push = pppoatm_push;
+	atmvcc->pop = pppoatm_pop;
+	atmvcc->release_cb = pppoatm_release_cb;
+	__module_get(THIS_MODULE);
+	atmvcc->owner = THIS_MODULE;
+
+	/* re-process everything received between connection setup and
+	   backend setup */
+	vcc_process_recv_queue(atmvcc);
+	return 0;
+}
+
+/*
+ * This handles ioctls actually performed on our vcc - we must return
+ * -ENOIOCTLCMD for any unrecognized ioctl
+ */
+static int pppoatm_ioctl(struct socket *sock, unsigned int cmd,
+	unsigned long arg)
+{
+	struct atm_vcc *atmvcc = ATM_SD(sock);
+	void __user *argp = (void __user *)arg;
+
+	if (cmd != ATM_SETBACKEND && atmvcc->push != pppoatm_push)
+		return -ENOIOCTLCMD;
+	switch (cmd) {
+	case ATM_SETBACKEND: {
+		atm_backend_t b;
+		if (get_user(b, (atm_backend_t __user *) argp))
+			return -EFAULT;
+		if (b != ATM_BACKEND_PPP)
+			return -ENOIOCTLCMD;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		if (sock->state != SS_CONNECTED)
+			return -EINVAL;
+		return pppoatm_assign_vcc(atmvcc, argp);
+		}
+	case PPPIOCGCHAN:
+		return put_user(ppp_channel_index(&atmvcc_to_pvcc(atmvcc)->
+		    chan), (int __user *) argp) ? -EFAULT : 0;
+	case PPPIOCGUNIT:
+		return put_user(ppp_unit_number(&atmvcc_to_pvcc(atmvcc)->
+		    chan), (int __user *) argp) ? -EFAULT : 0;
+	}
+	return -ENOIOCTLCMD;
+}
+
+static struct atm_ioctl pppoatm_ioctl_ops = {
+	.owner	= THIS_MODULE,
+	.ioctl	= pppoatm_ioctl,
+};
+
+static int __init pppoatm_init(void)
+{
+	register_atm_ioctl(&pppoatm_ioctl_ops);
+	return 0;
+}
+
+static void __exit pppoatm_exit(void)
+{
+	deregister_atm_ioctl(&pppoatm_ioctl_ops);
+}
+
+module_init(pppoatm_init);
+module_exit(pppoatm_exit);
+
+MODULE_AUTHOR("Mitchell Blank Jr <mitch@sfgoth.com>");
+MODULE_DESCRIPTION("RFC2364 PPP over ATM/AAL5");
+MODULE_LICENSE("GPL");