aboutsummaryrefslogtreecommitdiff
path: root/net/l2tp/l2tp_core.h
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /net/l2tp/l2tp_core.h
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
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(). ...
Diffstat (limited to 'net/l2tp/l2tp_core.h')
-rw-r--r--net/l2tp/l2tp_core.h346
1 files changed, 346 insertions, 0 deletions
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
new file mode 100644
index 000000000..a88e070b4
--- /dev/null
+++ b/net/l2tp/l2tp_core.h
@@ -0,0 +1,346 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* L2TP internal definitions.
+ *
+ * Copyright (c) 2008,2009 Katalix Systems Ltd
+ */
+#include <linux/refcount.h>
+
+#ifndef _L2TP_CORE_H_
+#define _L2TP_CORE_H_
+
+#include <net/dst.h>
+#include <net/sock.h>
+
+#ifdef CONFIG_XFRM
+#include <net/xfrm.h>
+#endif
+
+/* Random numbers used for internal consistency checks of tunnel and session structures */
+#define L2TP_TUNNEL_MAGIC 0x42114DDA
+#define L2TP_SESSION_MAGIC 0x0C04EB7D
+
+/* Per tunnel session hash table size */
+#define L2TP_HASH_BITS 4
+#define L2TP_HASH_SIZE BIT(L2TP_HASH_BITS)
+
+/* System-wide session hash table size */
+#define L2TP_HASH_BITS_2 8
+#define L2TP_HASH_SIZE_2 BIT(L2TP_HASH_BITS_2)
+
+struct sk_buff;
+
+struct l2tp_stats {
+ atomic_long_t tx_packets;
+ atomic_long_t tx_bytes;
+ atomic_long_t tx_errors;
+ atomic_long_t rx_packets;
+ atomic_long_t rx_bytes;
+ atomic_long_t rx_seq_discards;
+ atomic_long_t rx_oos_packets;
+ atomic_long_t rx_errors;
+ atomic_long_t rx_cookie_discards;
+ atomic_long_t rx_invalid;
+};
+
+struct l2tp_tunnel;
+
+/* L2TP session configuration */
+struct l2tp_session_cfg {
+ enum l2tp_pwtype pw_type;
+ unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */
+ unsigned int send_seq:1; /* send packets with sequence numbers? */
+ unsigned int lns_mode:1; /* behave as LNS?
+ * LAC enables sequence numbers under LNS control.
+ */
+ u16 l2specific_type; /* Layer 2 specific type */
+ u8 cookie[8]; /* optional cookie */
+ int cookie_len; /* 0, 4 or 8 bytes */
+ u8 peer_cookie[8]; /* peer's cookie */
+ int peer_cookie_len; /* 0, 4 or 8 bytes */
+ int reorder_timeout; /* configured reorder timeout (in jiffies) */
+ char *ifname;
+};
+
+/* Represents a session (pseudowire) instance.
+ * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics.
+ * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into
+ * an additional per-net ("global") hashlist.
+ */
+#define L2TP_SESSION_NAME_MAX 32
+struct l2tp_session {
+ int magic; /* should be L2TP_SESSION_MAGIC */
+ long dead;
+
+ struct l2tp_tunnel *tunnel; /* back pointer to tunnel context */
+ u32 session_id;
+ u32 peer_session_id;
+ u8 cookie[8];
+ int cookie_len;
+ u8 peer_cookie[8];
+ int peer_cookie_len;
+ u16 l2specific_type;
+ u16 hdr_len;
+ u32 nr; /* session NR state (receive) */
+ u32 ns; /* session NR state (send) */
+ struct sk_buff_head reorder_q; /* receive reorder queue */
+ u32 nr_max; /* max NR. Depends on tunnel */
+ u32 nr_window_size; /* NR window size */
+ u32 nr_oos; /* NR of last OOS packet */
+ int nr_oos_count; /* for OOS recovery */
+ int nr_oos_count_max;
+ struct hlist_node hlist; /* hash list node */
+ refcount_t ref_count;
+
+ char name[L2TP_SESSION_NAME_MAX]; /* for logging */
+ char ifname[IFNAMSIZ];
+ unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */
+ unsigned int send_seq:1; /* send packets with sequence numbers? */
+ unsigned int lns_mode:1; /* behave as LNS?
+ * LAC enables sequence numbers under LNS control.
+ */
+ int reorder_timeout; /* configured reorder timeout (in jiffies) */
+ int reorder_skip; /* set if skip to next nr */
+ enum l2tp_pwtype pwtype;
+ struct l2tp_stats stats;
+ struct hlist_node global_hlist; /* global hash list node */
+
+ /* Session receive handler for data packets.
+ * Each pseudowire implementation should implement this callback in order to
+ * handle incoming packets. Packets are passed to the pseudowire handler after
+ * reordering, if data sequence numbers are enabled for the session.
+ */
+ void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len);
+
+ /* Session close handler.
+ * Each pseudowire implementation may implement this callback in order to carry
+ * out pseudowire-specific shutdown actions.
+ * The callback is called by core after unhashing the session and purging its
+ * reorder queue.
+ */
+ void (*session_close)(struct l2tp_session *session);
+
+ /* Session show handler.
+ * Pseudowire-specific implementation of debugfs session rendering.
+ * The callback is called by l2tp_debugfs.c after rendering core session
+ * information.
+ */
+ void (*show)(struct seq_file *m, void *priv);
+
+ u8 priv[]; /* private data */
+};
+
+/* L2TP tunnel configuration */
+struct l2tp_tunnel_cfg {
+ enum l2tp_encap_type encap;
+
+ /* Used only for kernel-created sockets */
+ struct in_addr local_ip;
+ struct in_addr peer_ip;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr *local_ip6;
+ struct in6_addr *peer_ip6;
+#endif
+ u16 local_udp_port;
+ u16 peer_udp_port;
+ unsigned int use_udp_checksums:1,
+ udp6_zero_tx_checksums:1,
+ udp6_zero_rx_checksums:1;
+};
+
+/* Represents a tunnel instance.
+ * Tracks runtime state including IO statistics.
+ * Holds the tunnel socket (either passed from userspace or directly created by the kernel).
+ * Maintains a hashlist of sessions belonging to the tunnel instance.
+ * Is linked into a per-net list of tunnels.
+ */
+#define L2TP_TUNNEL_NAME_MAX 20
+struct l2tp_tunnel {
+ int magic; /* Should be L2TP_TUNNEL_MAGIC */
+
+ unsigned long dead;
+
+ struct rcu_head rcu;
+ spinlock_t hlist_lock; /* write-protection for session_hlist */
+ bool acpt_newsess; /* indicates whether this tunnel accepts
+ * new sessions. Protected by hlist_lock.
+ */
+ struct hlist_head session_hlist[L2TP_HASH_SIZE];
+ /* hashed list of sessions, hashed by id */
+ u32 tunnel_id;
+ u32 peer_tunnel_id;
+ int version; /* 2=>L2TPv2, 3=>L2TPv3 */
+
+ char name[L2TP_TUNNEL_NAME_MAX]; /* for logging */
+ enum l2tp_encap_type encap;
+ struct l2tp_stats stats;
+
+ struct list_head list; /* list node on per-namespace list of tunnels */
+ struct net *l2tp_net; /* the net we belong to */
+
+ refcount_t ref_count;
+ void (*old_sk_destruct)(struct sock *sk);
+ struct sock *sock; /* parent socket */
+ int fd; /* parent fd, if tunnel socket was created
+ * by userspace
+ */
+
+ struct work_struct del_work;
+};
+
+/* Pseudowire ops callbacks for use with the l2tp genetlink interface */
+struct l2tp_nl_cmd_ops {
+ /* The pseudowire session create callback is responsible for creating a session
+ * instance for a specific pseudowire type.
+ * It must call l2tp_session_create and l2tp_session_register to register the
+ * session instance, as well as carry out any pseudowire-specific initialisation.
+ * It must return >= 0 on success, or an appropriate negative errno value on failure.
+ */
+ int (*session_create)(struct net *net, struct l2tp_tunnel *tunnel,
+ u32 session_id, u32 peer_session_id,
+ struct l2tp_session_cfg *cfg);
+
+ /* The pseudowire session delete callback is responsible for initiating the deletion
+ * of a session instance.
+ * It must call l2tp_session_delete, as well as carry out any pseudowire-specific
+ * teardown actions.
+ */
+ void (*session_delete)(struct l2tp_session *session);
+};
+
+static inline void *l2tp_session_priv(struct l2tp_session *session)
+{
+ return &session->priv[0];
+}
+
+/* Tunnel and session refcounts */
+void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel);
+void l2tp_session_inc_refcount(struct l2tp_session *session);
+void l2tp_session_dec_refcount(struct l2tp_session *session);
+
+/* Tunnel and session lookup.
+ * These functions take a reference on the instances they return, so
+ * the caller must ensure that the reference is dropped appropriately.
+ */
+struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel,
+ u32 session_id);
+
+struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
+struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
+ const char *ifname);
+
+/* Tunnel and session lifetime management.
+ * Creation of a new instance is a two-step process: create, then register.
+ * Destruction is triggered using the *_delete functions, and completes asynchronously.
+ */
+int l2tp_tunnel_create(int fd, int version, u32 tunnel_id,
+ u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
+ struct l2tp_tunnel **tunnelp);
+int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
+ struct l2tp_tunnel_cfg *cfg);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+
+struct l2tp_session *l2tp_session_create(int priv_size,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, u32 peer_session_id,
+ struct l2tp_session_cfg *cfg);
+int l2tp_session_register(struct l2tp_session *session,
+ struct l2tp_tunnel *tunnel);
+void l2tp_session_delete(struct l2tp_session *session);
+
+/* Receive path helpers. If data sequencing is enabled for the session these
+ * functions handle queuing and reordering prior to passing packets to the
+ * pseudowire code to be passed to userspace.
+ */
+void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
+ unsigned char *ptr, unsigned char *optr, u16 hdrflags,
+ int length);
+int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
+
+/* Transmit path helpers for sending packets over the tunnel socket. */
+void l2tp_session_set_header_len(struct l2tp_session *session, int version);
+int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb);
+
+/* Pseudowire management.
+ * Pseudowires should register with l2tp core on module init, and unregister
+ * on module exit.
+ */
+int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops);
+void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+
+/* IOCTL helper for IP encap modules. */
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+
+/* Extract the tunnel structure from a socket's sk_user_data pointer,
+ * validating the tunnel magic feather.
+ */
+struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk);
+
+static inline int l2tp_get_l2specific_len(struct l2tp_session *session)
+{
+ switch (session->l2specific_type) {
+ case L2TP_L2SPECTYPE_DEFAULT:
+ return 4;
+ case L2TP_L2SPECTYPE_NONE:
+ default:
+ return 0;
+ }
+}
+
+static inline u32 l2tp_tunnel_dst_mtu(const struct l2tp_tunnel *tunnel)
+{
+ struct dst_entry *dst;
+ u32 mtu;
+
+ dst = sk_dst_get(tunnel->sock);
+ if (!dst)
+ return 0;
+
+ mtu = dst_mtu(dst);
+ dst_release(dst);
+
+ return mtu;
+}
+
+#ifdef CONFIG_XFRM
+static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
+{
+ struct sock *sk = tunnel->sock;
+
+ return sk && (rcu_access_pointer(sk->sk_policy[0]) ||
+ rcu_access_pointer(sk->sk_policy[1]));
+}
+#else
+static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
+{
+ return false;
+}
+#endif
+
+static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb,
+ unsigned char **ptr, unsigned char **optr)
+{
+ int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session);
+
+ if (opt_len > 0) {
+ int off = *ptr - *optr;
+
+ if (!pskb_may_pull(skb, off + opt_len))
+ return -1;
+
+ if (skb->data != *optr) {
+ *optr = skb->data;
+ *ptr = skb->data + off;
+ }
+ }
+
+ return 0;
+}
+
+#define MODULE_ALIAS_L2TP_PWTYPE(type) \
+ MODULE_ALIAS("net-l2tp-type-" __stringify(type))
+
+#endif /* _L2TP_CORE_H_ */