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, 690 insertions, 0 deletions

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
new file mode 100644
index 000000000..0fe78826c
--- /dev/null
+++ b/drivers/net/ppp/pptp.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Point-to-Point Tunneling Protocol for Linux
+ *
+ *	Authors: Dmitry Kozlov <xeb@mail.ru>
+ */
+
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/ppp_channel.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp-ioctl.h>
+#include <linux/notifier.h>
+#include <linux/file.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/rcupdate.h>
+#include <linux/spinlock.h>
+
+#include <net/sock.h>
+#include <net/protocol.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/route.h>
+#include <net/gre.h>
+#include <net/pptp.h>
+
+#include <linux/uaccess.h>
+
+#define PPTP_DRIVER_VERSION "0.8.5"
+
+#define MAX_CALLID 65535
+
+static DECLARE_BITMAP(callid_bitmap, MAX_CALLID + 1);
+static struct pppox_sock __rcu **callid_sock;
+
+static DEFINE_SPINLOCK(chan_lock);
+
+static struct proto pptp_sk_proto __read_mostly;
+static const struct ppp_channel_ops pptp_chan_ops;
+static const struct proto_ops pptp_ops;
+
+static struct pppox_sock *lookup_chan(u16 call_id, __be32 s_addr)
+{
+	struct pppox_sock *sock;
+	struct pptp_opt *opt;
+
+	rcu_read_lock();
+	sock = rcu_dereference(callid_sock[call_id]);
+	if (sock) {
+		opt = &sock->proto.pptp;
+		if (opt->dst_addr.sin_addr.s_addr != s_addr)
+			sock = NULL;
+		else
+			sock_hold(sk_pppox(sock));
+	}
+	rcu_read_unlock();
+
+	return sock;
+}
+
+static int lookup_chan_dst(u16 call_id, __be32 d_addr)
+{
+	struct pppox_sock *sock;
+	struct pptp_opt *opt;
+	int i;
+
+	rcu_read_lock();
+	i = 1;
+	for_each_set_bit_from(i, callid_bitmap, MAX_CALLID) {
+		sock = rcu_dereference(callid_sock[i]);
+		if (!sock)
+			continue;
+		opt = &sock->proto.pptp;
+		if (opt->dst_addr.call_id == call_id &&
+			  opt->dst_addr.sin_addr.s_addr == d_addr)
+			break;
+	}
+	rcu_read_unlock();
+
+	return i < MAX_CALLID;
+}
+
+static int add_chan(struct pppox_sock *sock,
+		    struct pptp_addr *sa)
+{
+	static int call_id;
+
+	spin_lock(&chan_lock);
+	if (!sa->call_id)	{
+		call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1);
+		if (call_id == MAX_CALLID) {
+			call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1);
+			if (call_id == MAX_CALLID)
+				goto out_err;
+		}
+		sa->call_id = call_id;
+	} else if (test_bit(sa->call_id, callid_bitmap)) {
+		goto out_err;
+	}
+
+	sock->proto.pptp.src_addr = *sa;
+	set_bit(sa->call_id, callid_bitmap);
+	rcu_assign_pointer(callid_sock[sa->call_id], sock);
+	spin_unlock(&chan_lock);
+
+	return 0;
+
+out_err:
+	spin_unlock(&chan_lock);
+	return -1;
+}
+
+static void del_chan(struct pppox_sock *sock)
+{
+	spin_lock(&chan_lock);
+	clear_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap);
+	RCU_INIT_POINTER(callid_sock[sock->proto.pptp.src_addr.call_id], NULL);
+	spin_unlock(&chan_lock);
+}
+
+static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+	struct sock *sk = (struct sock *) chan->private;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct net *net = sock_net(sk);
+	struct pptp_opt *opt = &po->proto.pptp;
+	struct pptp_gre_header *hdr;
+	unsigned int header_len = sizeof(*hdr);
+	struct flowi4 fl4;
+	int islcp;
+	int len;
+	unsigned char *data;
+	__u32 seq_recv;
+
+
+	struct rtable *rt;
+	struct net_device *tdev;
+	struct iphdr  *iph;
+	int    max_headroom;
+
+	if (sk_pppox(po)->sk_state & PPPOX_DEAD)
+		goto tx_error;
+
+	rt = ip_route_output_ports(net, &fl4, NULL,
+				   opt->dst_addr.sin_addr.s_addr,
+				   opt->src_addr.sin_addr.s_addr,
+				   0, 0, IPPROTO_GRE,
+				   RT_TOS(0), sk->sk_bound_dev_if);
+	if (IS_ERR(rt))
+		goto tx_error;
+
+	tdev = rt->dst.dev;
+
+	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph) + sizeof(*hdr) + 2;
+
+	if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
+		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
+		if (!new_skb) {
+			ip_rt_put(rt);
+			goto tx_error;
+		}
+		if (skb->sk)
+			skb_set_owner_w(new_skb, skb->sk);
+		consume_skb(skb);
+		skb = new_skb;
+	}
+
+	data = skb->data;
+	islcp = ((data[0] << 8) + data[1]) == PPP_LCP && 1 <= data[2] && data[2] <= 7;
+
+	/* compress protocol field */
+	if ((opt->ppp_flags & SC_COMP_PROT) && data[0] == 0 && !islcp)
+		skb_pull(skb, 1);
+
+	/* Put in the address/control bytes if necessary */
+	if ((opt->ppp_flags & SC_COMP_AC) == 0 || islcp) {
+		data = skb_push(skb, 2);
+		data[0] = PPP_ALLSTATIONS;
+		data[1] = PPP_UI;
+	}
+
+	len = skb->len;
+
+	seq_recv = opt->seq_recv;
+
+	if (opt->ack_sent == seq_recv)
+		header_len -= sizeof(hdr->ack);
+
+	/* Push down and install GRE header */
+	skb_push(skb, header_len);
+	hdr = (struct pptp_gre_header *)(skb->data);
+
+	hdr->gre_hd.flags = GRE_KEY | GRE_VERSION_1 | GRE_SEQ;
+	hdr->gre_hd.protocol = GRE_PROTO_PPP;
+	hdr->call_id = htons(opt->dst_addr.call_id);
+
+	hdr->seq = htonl(++opt->seq_sent);
+	if (opt->ack_sent != seq_recv)	{
+		/* send ack with this message */
+		hdr->gre_hd.flags |= GRE_ACK;
+		hdr->ack  = htonl(seq_recv);
+		opt->ack_sent = seq_recv;
+	}
+	hdr->payload_len = htons(len);
+
+	/*	Push down and install the IP header. */
+
+	skb_reset_transport_header(skb);
+	skb_push(skb, sizeof(*iph));
+	skb_reset_network_header(skb);
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
+
+	iph =	ip_hdr(skb);
+	iph->version =	4;
+	iph->ihl =	sizeof(struct iphdr) >> 2;
+	if (ip_dont_fragment(sk, &rt->dst))
+		iph->frag_off	=	htons(IP_DF);
+	else
+		iph->frag_off	=	0;
+	iph->protocol = IPPROTO_GRE;
+	iph->tos      = 0;
+	iph->daddr    = fl4.daddr;
+	iph->saddr    = fl4.saddr;
+	iph->ttl      = ip4_dst_hoplimit(&rt->dst);
+	iph->tot_len  = htons(skb->len);
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->dst);
+
+	nf_reset_ct(skb);
+
+	skb->ip_summed = CHECKSUM_NONE;
+	ip_select_ident(net, skb, NULL);
+	ip_send_check(iph);
+
+	ip_local_out(net, skb->sk, skb);
+	return 1;
+
+tx_error:
+	kfree_skb(skb);
+	return 1;
+}
+
+static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb)
+{
+	struct pppox_sock *po = pppox_sk(sk);
+	struct pptp_opt *opt = &po->proto.pptp;
+	int headersize, payload_len, seq;
+	__u8 *payload;
+	struct pptp_gre_header *header;
+
+	if (!(sk->sk_state & PPPOX_CONNECTED)) {
+		if (sock_queue_rcv_skb(sk, skb))
+			goto drop;
+		return NET_RX_SUCCESS;
+	}
+
+	header = (struct pptp_gre_header *)(skb->data);
+	headersize  = sizeof(*header);
+
+	/* test if acknowledgement present */
+	if (GRE_IS_ACK(header->gre_hd.flags)) {
+		__u32 ack;
+
+		if (!pskb_may_pull(skb, headersize))
+			goto drop;
+		header = (struct pptp_gre_header *)(skb->data);
+
+		/* ack in different place if S = 0 */
+		ack = GRE_IS_SEQ(header->gre_hd.flags) ? ntohl(header->ack) :
+							 ntohl(header->seq);
+		if (ack > opt->ack_recv)
+			opt->ack_recv = ack;
+		/* also handle sequence number wrap-around  */
+		if (WRAPPED(ack, opt->ack_recv))
+			opt->ack_recv = ack;
+	} else {
+		headersize -= sizeof(header->ack);
+	}
+	/* test if payload present */
+	if (!GRE_IS_SEQ(header->gre_hd.flags))
+		goto drop;
+
+	payload_len = ntohs(header->payload_len);
+	seq         = ntohl(header->seq);
+
+	/* check for incomplete packet (length smaller than expected) */
+	if (!pskb_may_pull(skb, headersize + payload_len))
+		goto drop;
+
+	payload = skb->data + headersize;
+	/* check for expected sequence number */
+	if (seq < opt->seq_recv + 1 || WRAPPED(opt->seq_recv, seq)) {
+		if ((payload[0] == PPP_ALLSTATIONS) && (payload[1] == PPP_UI) &&
+				(PPP_PROTOCOL(payload) == PPP_LCP) &&
+				((payload[4] == PPP_LCP_ECHOREQ) || (payload[4] == PPP_LCP_ECHOREP)))
+			goto allow_packet;
+	} else {
+		opt->seq_recv = seq;
+allow_packet:
+		skb_pull(skb, headersize);
+
+		if (payload[0] == PPP_ALLSTATIONS && payload[1] == PPP_UI) {
+			/* chop off address/control */
+			if (skb->len < 3)
+				goto drop;
+			skb_pull(skb, 2);
+		}
+
+		skb->ip_summed = CHECKSUM_NONE;
+		skb_set_network_header(skb, skb->head-skb->data);
+		ppp_input(&po->chan, skb);
+
+		return NET_RX_SUCCESS;
+	}
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+static int pptp_rcv(struct sk_buff *skb)
+{
+	struct pppox_sock *po;
+	struct pptp_gre_header *header;
+	struct iphdr *iph;
+
+	if (skb->pkt_type != PACKET_HOST)
+		goto drop;
+
+	if (!pskb_may_pull(skb, 12))
+		goto drop;
+
+	iph = ip_hdr(skb);
+
+	header = (struct pptp_gre_header *)skb->data;
+
+	if (header->gre_hd.protocol != GRE_PROTO_PPP || /* PPTP-GRE protocol for PPTP */
+		GRE_IS_CSUM(header->gre_hd.flags) ||    /* flag CSUM should be clear */
+		GRE_IS_ROUTING(header->gre_hd.flags) || /* flag ROUTING should be clear */
+		!GRE_IS_KEY(header->gre_hd.flags) ||    /* flag KEY should be set */
+		(header->gre_hd.flags & GRE_FLAGS))     /* flag Recursion Ctrl should be clear */
+		/* if invalid, discard this packet */
+		goto drop;
+
+	po = lookup_chan(ntohs(header->call_id), iph->saddr);
+	if (po) {
+		skb_dst_drop(skb);
+		nf_reset_ct(skb);
+		return sk_receive_skb(sk_pppox(po), skb, 0);
+	}
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
+	int sockaddr_len)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;
+	struct pppox_sock *po = pppox_sk(sk);
+	int error = 0;
+
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	if (sk->sk_state & PPPOX_DEAD) {
+		error = -EALREADY;
+		goto out;
+	}
+
+	if (sk->sk_state & PPPOX_BOUND) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	if (add_chan(po, &sp->sa_addr.pptp))
+		error = -EBUSY;
+	else
+		sk->sk_state |= PPPOX_BOUND;
+
+out:
+	release_sock(sk);
+	return error;
+}
+
+static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
+	int sockaddr_len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct pptp_opt *opt = &po->proto.pptp;
+	struct rtable *rt;
+	struct flowi4 fl4;
+	int error = 0;
+
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
+	if (sp->sa_protocol != PX_PROTO_PPTP)
+		return -EINVAL;
+
+	if (lookup_chan_dst(sp->sa_addr.pptp.call_id, sp->sa_addr.pptp.sin_addr.s_addr))
+		return -EALREADY;
+
+	lock_sock(sk);
+	/* Check for already bound sockets */
+	if (sk->sk_state & PPPOX_CONNECTED) {
+		error = -EBUSY;
+		goto end;
+	}
+
+	/* Check for already disconnected sockets, on attempts to disconnect */
+	if (sk->sk_state & PPPOX_DEAD) {
+		error = -EALREADY;
+		goto end;
+	}
+
+	if (!opt->src_addr.sin_addr.s_addr || !sp->sa_addr.pptp.sin_addr.s_addr) {
+		error = -EINVAL;
+		goto end;
+	}
+
+	po->chan.private = sk;
+	po->chan.ops = &pptp_chan_ops;
+
+	rt = ip_route_output_ports(sock_net(sk), &fl4, sk,
+				   opt->dst_addr.sin_addr.s_addr,
+				   opt->src_addr.sin_addr.s_addr,
+				   0, 0,
+				   IPPROTO_GRE, RT_CONN_FLAGS(sk),
+				   sk->sk_bound_dev_if);
+	if (IS_ERR(rt)) {
+		error = -EHOSTUNREACH;
+		goto end;
+	}
+	sk_setup_caps(sk, &rt->dst);
+
+	po->chan.mtu = dst_mtu(&rt->dst);
+	if (!po->chan.mtu)
+		po->chan.mtu = PPP_MRU;
+	po->chan.mtu -= PPTP_HEADER_OVERHEAD;
+
+	po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header);
+	error = ppp_register_channel(&po->chan);
+	if (error) {
+		pr_err("PPTP: failed to register PPP channel (%d)\n", error);
+		goto end;
+	}
+
+	opt->dst_addr = sp->sa_addr.pptp;
+	sk->sk_state |= PPPOX_CONNECTED;
+
+ end:
+	release_sock(sk);
+	return error;
+}
+
+static int pptp_getname(struct socket *sock, struct sockaddr *uaddr,
+	int peer)
+{
+	int len = sizeof(struct sockaddr_pppox);
+	struct sockaddr_pppox sp;
+
+	memset(&sp.sa_addr, 0, sizeof(sp.sa_addr));
+
+	sp.sa_family    = AF_PPPOX;
+	sp.sa_protocol  = PX_PROTO_PPTP;
+	sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr;
+
+	memcpy(uaddr, &sp, len);
+
+	return len;
+}
+
+static int pptp_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct pppox_sock *po;
+	int error = 0;
+
+	if (!sk)
+		return 0;
+
+	lock_sock(sk);
+
+	if (sock_flag(sk, SOCK_DEAD)) {
+		release_sock(sk);
+		return -EBADF;
+	}
+
+	po = pppox_sk(sk);
+	del_chan(po);
+	synchronize_rcu();
+
+	pppox_unbind_sock(sk);
+	sk->sk_state = PPPOX_DEAD;
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+
+	release_sock(sk);
+	sock_put(sk);
+
+	return error;
+}
+
+static void pptp_sock_destruct(struct sock *sk)
+{
+	if (!(sk->sk_state & PPPOX_DEAD)) {
+		del_chan(pppox_sk(sk));
+		pppox_unbind_sock(sk);
+	}
+	skb_queue_purge(&sk->sk_receive_queue);
+	dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
+}
+
+static int pptp_create(struct net *net, struct socket *sock, int kern)
+{
+	int error = -ENOMEM;
+	struct sock *sk;
+	struct pppox_sock *po;
+	struct pptp_opt *opt;
+
+	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pptp_sk_proto, kern);
+	if (!sk)
+		goto out;
+
+	sock_init_data(sock, sk);
+
+	sock->state = SS_UNCONNECTED;
+	sock->ops   = &pptp_ops;
+
+	sk->sk_backlog_rcv = pptp_rcv_core;
+	sk->sk_state       = PPPOX_NONE;
+	sk->sk_type        = SOCK_STREAM;
+	sk->sk_family      = PF_PPPOX;
+	sk->sk_protocol    = PX_PROTO_PPTP;
+	sk->sk_destruct    = pptp_sock_destruct;
+
+	po = pppox_sk(sk);
+	opt = &po->proto.pptp;
+
+	opt->seq_sent = 0; opt->seq_recv = 0xffffffff;
+	opt->ack_recv = 0; opt->ack_sent = 0xffffffff;
+
+	error = 0;
+out:
+	return error;
+}
+
+static int pptp_ppp_ioctl(struct ppp_channel *chan, unsigned int cmd,
+	unsigned long arg)
+{
+	struct sock *sk = (struct sock *) chan->private;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct pptp_opt *opt = &po->proto.pptp;
+	void __user *argp = (void __user *)arg;
+	int __user *p = argp;
+	int err, val;
+
+	err = -EFAULT;
+	switch (cmd) {
+	case PPPIOCGFLAGS:
+		val = opt->ppp_flags;
+		if (put_user(val, p))
+			break;
+		err = 0;
+		break;
+	case PPPIOCSFLAGS:
+		if (get_user(val, p))
+			break;
+		opt->ppp_flags = val & ~SC_RCV_BITS;
+		err = 0;
+		break;
+	default:
+		err = -ENOTTY;
+	}
+
+	return err;
+}
+
+static const struct ppp_channel_ops pptp_chan_ops = {
+	.start_xmit = pptp_xmit,
+	.ioctl      = pptp_ppp_ioctl,
+};
+
+static struct proto pptp_sk_proto __read_mostly = {
+	.name     = "PPTP",
+	.owner    = THIS_MODULE,
+	.obj_size = sizeof(struct pppox_sock),
+};
+
+static const struct proto_ops pptp_ops = {
+	.family     = AF_PPPOX,
+	.owner      = THIS_MODULE,
+	.release    = pptp_release,
+	.bind       = pptp_bind,
+	.connect    = pptp_connect,
+	.socketpair = sock_no_socketpair,
+	.accept     = sock_no_accept,
+	.getname    = pptp_getname,
+	.listen     = sock_no_listen,
+	.shutdown   = sock_no_shutdown,
+	.sendmsg    = sock_no_sendmsg,
+	.recvmsg    = sock_no_recvmsg,
+	.mmap       = sock_no_mmap,
+	.ioctl      = pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = pppox_compat_ioctl,
+#endif
+};
+
+static const struct pppox_proto pppox_pptp_proto = {
+	.create = pptp_create,
+	.owner  = THIS_MODULE,
+};
+
+static const struct gre_protocol gre_pptp_protocol = {
+	.handler = pptp_rcv,
+};
+
+static int __init pptp_init_module(void)
+{
+	int err = 0;
+	pr_info("PPTP driver version " PPTP_DRIVER_VERSION "\n");
+
+	callid_sock = vzalloc(array_size(sizeof(void *), (MAX_CALLID + 1)));
+	if (!callid_sock)
+		return -ENOMEM;
+
+	err = gre_add_protocol(&gre_pptp_protocol, GREPROTO_PPTP);
+	if (err) {
+		pr_err("PPTP: can't add gre protocol\n");
+		goto out_mem_free;
+	}
+
+	err = proto_register(&pptp_sk_proto, 0);
+	if (err) {
+		pr_err("PPTP: can't register sk_proto\n");
+		goto out_gre_del_protocol;
+	}
+
+	err = register_pppox_proto(PX_PROTO_PPTP, &pppox_pptp_proto);
+	if (err) {
+		pr_err("PPTP: can't register pppox_proto\n");
+		goto out_unregister_sk_proto;
+	}
+
+	return 0;
+
+out_unregister_sk_proto:
+	proto_unregister(&pptp_sk_proto);
+out_gre_del_protocol:
+	gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP);
+out_mem_free:
+	vfree(callid_sock);
+
+	return err;
+}
+
+static void __exit pptp_exit_module(void)
+{
+	unregister_pppox_proto(PX_PROTO_PPTP);
+	proto_unregister(&pptp_sk_proto);
+	gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP);
+	vfree(callid_sock);
+}
+
+module_init(pptp_init_module);
+module_exit(pptp_exit_module);
+
+MODULE_DESCRIPTION("Point-to-Point Tunneling Protocol");
+MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_PPTP);